From d2f810e9fe44c9484d0b889f0908f6e319d08341 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Mon, 13 Jul 2026 15:38:47 +0800 Subject: [PATCH 001/323] feat(docs): build maintainable documentation site --- docs/AGENTS.md | 1 + docs/rfc/INDEX.md | 1 + ...026-07-13-documentation-site-projection.md | 39 + .../user}/zh-CN/develop/basic/config.md | 2 +- .../user}/zh-CN/develop/basic/index.md | 6 +- .../user}/zh-CN/develop/basic/tool.md | 2 +- .../user}/zh-CN/develop/framework/events.md | 2 +- .../user}/zh-CN/develop/framework/index.md | 4 +- .../user}/zh-CN/develop/framework/service.md | 16 +- .../user}/zh-CN/develop/practice/index.md | 4 +- .../zh-CN/develop/practice/llm-adapter.md | 0 docs/user/zh-CN/guide/config.md | 57 + {website => docs/user}/zh-CN/guide/index.md | 6 +- .../user}/zh-CN/guide/quickstart.md | 13 +- {website => docs/user}/zh-CN/index.md | 4 +- eslint.config.mjs | 5 +- knip.json | 10 + package.json | 9 +- pnpm-lock.yaml | 1565 ++++++++++++++++- pnpm-workspace.yaml | 1 + scripts/project-doc-site.spec.ts | 98 ++ scripts/project-doc-site.ts | 215 +++ scripts/run-gates.ts | 1 + scripts/verify-md-wrap.ts | 24 +- tsconfig.json | 4 +- vitest.config.ts | 2 +- website/.gitignore | 5 +- website/.vitepress/config.ts | 142 ++ website/.vitepress/config/index.ts | 17 - website/.vitepress/config/zh-CN.ts | 99 -- website/docs.ts | 213 +++ website/package.json | 15 +- website/zh-CN/api/cordis/context.md | 85 - website/zh-CN/api/cordis/events.md | 120 -- website/zh-CN/api/cordis/fiber.md | 108 -- website/zh-CN/api/cordis/registry.md | 87 - website/zh-CN/api/cordis/service.md | 97 - website/zh-CN/api/harness/agent.md | 85 - website/zh-CN/api/harness/bash.md | 81 - website/zh-CN/api/harness/fs.md | 78 - website/zh-CN/api/harness/llm.md | 124 -- website/zh-CN/api/harness/session.md | 56 - website/zh-CN/api/harness/subagent.md | 85 - website/zh-CN/api/harness/tools.md | 122 -- website/zh-CN/api/index.md | 25 - website/zh-CN/design/composability.md | 72 - website/zh-CN/design/context-model.md | 129 -- website/zh-CN/design/effects-coeffects.md | 69 - website/zh-CN/design/index.md | 39 - website/zh-CN/design/reactive-coeffects.md | 90 - website/zh-CN/design/revertible-effects.md | 128 -- website/zh-CN/guide/config.md | 342 ---- 52 files changed, 2380 insertions(+), 2224 deletions(-) create mode 100644 docs/rfc/implemented/process/2026-07-13-documentation-site-projection.md rename {website => docs/user}/zh-CN/develop/basic/config.md (96%) rename {website => docs/user}/zh-CN/develop/basic/index.md (95%) rename {website => docs/user}/zh-CN/develop/basic/tool.md (98%) rename {website => docs/user}/zh-CN/develop/framework/events.md (97%) rename {website => docs/user}/zh-CN/develop/framework/index.md (95%) rename {website => docs/user}/zh-CN/develop/framework/service.md (83%) rename {website => docs/user}/zh-CN/develop/practice/index.md (95%) rename {website => docs/user}/zh-CN/develop/practice/llm-adapter.md (100%) create mode 100644 docs/user/zh-CN/guide/config.md rename {website => docs/user}/zh-CN/guide/index.md (89%) rename {website => docs/user}/zh-CN/guide/quickstart.md (84%) rename {website => docs/user}/zh-CN/index.md (90%) create mode 100644 scripts/project-doc-site.spec.ts create mode 100644 scripts/project-doc-site.ts create mode 100644 website/.vitepress/config.ts delete mode 100644 website/.vitepress/config/index.ts delete mode 100644 website/.vitepress/config/zh-CN.ts create mode 100644 website/docs.ts delete mode 100644 website/zh-CN/api/cordis/context.md delete mode 100644 website/zh-CN/api/cordis/events.md delete mode 100644 website/zh-CN/api/cordis/fiber.md delete mode 100644 website/zh-CN/api/cordis/registry.md delete mode 100644 website/zh-CN/api/cordis/service.md delete mode 100644 website/zh-CN/api/harness/agent.md delete mode 100644 website/zh-CN/api/harness/bash.md delete mode 100644 website/zh-CN/api/harness/fs.md delete mode 100644 website/zh-CN/api/harness/llm.md delete mode 100644 website/zh-CN/api/harness/session.md delete mode 100644 website/zh-CN/api/harness/subagent.md delete mode 100644 website/zh-CN/api/harness/tools.md delete mode 100644 website/zh-CN/api/index.md delete mode 100644 website/zh-CN/design/composability.md delete mode 100644 website/zh-CN/design/context-model.md delete mode 100644 website/zh-CN/design/effects-coeffects.md delete mode 100644 website/zh-CN/design/index.md delete mode 100644 website/zh-CN/design/reactive-coeffects.md delete mode 100644 website/zh-CN/design/revertible-effects.md delete mode 100644 website/zh-CN/guide/config.md diff --git a/docs/AGENTS.md b/docs/AGENTS.md index 6824c71cc6..53f7d2f5b0 100644 --- a/docs/AGENTS.md +++ b/docs/AGENTS.md @@ -15,6 +15,7 @@ Every fact has exactly one home — the tier whose job it is — and every other | [rfc/](rfc/README.md) | Decision records: the why and the what-was-given-up; `implemented/` RFCs describe shipped reality in present tense | Migration plans, test checklists, and spec-speak ("should…") once the decision has shipped | | [postmortem/](postmortem/README.md) | Incident stories — the only tier where war-story narrative belongs | — | | [cookbook/](cookbook/adding-a-package.md) | Step-by-step how-tos with numbered verify steps | Design rationale (→ the RFC each guide links) | +| [user/](user/zh-CN/index.md) | Product-facing guides published by the documentation website | Generated reference tables, contributor procedures, decision history | | Package README | The per-package contract: config, semantics, limitations, extension points | JSDoc restatement, generated-catalog restatement (event/tool tables), other packages' concerns | | [development.md](development.md) | First-stop contributor onboarding: local setup, daily workflow, and CI shape at summary level; a bilingual pair under the [i18n contract](i18n/README.md) | Runtime/version rationale (→ RFCs), gate-by-gate enumerations that drift from `package.json` scripts | | Generated catalogs: [cordis events](cordis-catalog/events.md), [cordis services](cordis-catalog/services.md), [tool-catalog](tool-catalog.md), [config-catalog](config-catalog.md), [persistence-catalog](persistence-catalog.md), [module-graph.md](module-graph.md) | Exhaustive enumerations regenerated from source, freshness-gated | Hand edits of any kind | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 8dc3b93b47..7a44b009ad 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -160,6 +160,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Raise the Node LTS engine floor to 22.19](implemented/process/2026-07-06-node-engine-floor.md) | 2026-07-06 | | [Parallel GitHub CI gates](implemented/process/2026-07-06-parallel-github-ci-gates.md) | 2026-07-06 | | [Parallel pre-push gates](implemented/process/2026-07-06-parallel-pre-push-gates.md) | 2026-07-06 | +| [Project canonical documentation into the website](implemented/process/2026-07-13-documentation-site-projection.md) | 2026-07-13 | ### Testing diff --git a/docs/rfc/implemented/process/2026-07-13-documentation-site-projection.md b/docs/rfc/implemented/process/2026-07-13-documentation-site-projection.md new file mode 100644 index 0000000000..5bdb0f87c0 --- /dev/null +++ b/docs/rfc/implemented/process/2026-07-13-documentation-site-projection.md @@ -0,0 +1,39 @@ +# RFC: Project canonical documentation into the website + +Status: implemented + +## Problem + +The repository needs a navigable documentation website without turning the website directory into a second documentation source. Copying package guides, architecture pages, or generated catalogs into a site-specific tree allows the two copies to drift, while pointing VitePress directly at the repository root couples public URLs and navigation to the internal file layout. Repository-relative links also need different destinations on the website: published pages stay inside the site, but source files and unpublished contributor documents belong on GitHub. + +## Decision + +Canonical Markdown remains in the repository tier that owns it. Product-facing guides live under `docs/user/`, generated reference remains in the existing generated catalogs, and architectural and cookbook pages remain at their existing `docs/` paths. + +`website/docs.ts` is an explicit publication manifest. Each entry maps one canonical source file to a stable public route, sidebar, section, and order. Adding or removing a published page is therefore a reviewable manifest change rather than an implicit directory crawl. + +`scripts/project-doc-site.ts` projects the manifest into the ignored `website/.generated/` directory before VitePress starts or builds. The generated tree follows public routes so VitePress navigation, locale detection, and local search share the same route vocabulary. Each page receives an `editSource` frontmatter field pointing to its canonical repository file; the edit-link callback reads only that page data, so public URLs remain independent of the source layout. + +The projector parses Markdown links without reserializing the document. A link to another published source becomes a site-relative route; a link to an unpublished repository file becomes a GitHub source link; a repository image becomes a raw GitHub URL. Missing relative targets fail projection. Unit tests pin these transformations, and `docs:check` runs the projector tests plus a production VitePress build as part of `doc-sync` and the parallel documentation gates. + +Mermaid renders the canonical diagrams. The website workspace explicitly declares the five packages that `vitepress-plugin-mermaid` asks Vite to prebundle because pnpm's strict dependency isolation otherwise makes those transitive packages unavailable to the local development server; Knip records this runtime-only use as an intentional dependency exception. + +Site publication is separate from site construction. The repository contains local development and build commands, but no hosting or deployment workflow until a public destination is chosen. + +## Alternatives considered + +**Commit copied Markdown under `website/`.** This makes VitePress setup direct, but every copied guide or API table gains two owners and requires a synchronization convention that cannot identify which copy is authoritative. + +**Make `website/` the canonical home for every published page.** This keeps one copy but moves architecture, generated reference, and contributor-facing material away from their repository ownership tiers merely to satisfy a renderer. + +**Discover every Markdown file automatically.** This minimizes manifest maintenance but publishes internal documents accidentally, exposes source moves as URL changes, and produces navigation from incidental directory order. + +**Use filesystem symlinks.** Symlinks preserve a single source but do not solve public routing or repository-relative links, and their behavior is less predictable across local development, package tooling, and hosted CI environments. + +**Build only in a deployment workflow.** A deployment job can reveal rendering failures after merge. Keeping the production build in `doc-sync` makes the same failure visible locally and in ordinary CI even when no public deployment exists. + +## Consequences + +Documentation facts have one editable home, public routes remain stable across source moves, and the site can include generated references without committing another generated copy. Local development watches canonical inputs and regenerates the disposable projection. + +The publication manifest is a maintained allowlist, and link projection adds a small repository-specific build adapter. A new kind of Markdown link behavior needs a projector test. Mermaid support also increases the client bundle size, but preserves diagrams already used by the canonical documentation. diff --git a/website/zh-CN/develop/basic/config.md b/docs/user/zh-CN/develop/basic/config.md similarity index 96% rename from website/zh-CN/develop/basic/config.md rename to docs/user/zh-CN/develop/basic/config.md index 49bcc4ca77..6c5bf6c651 100644 --- a/website/zh-CN/develop/basic/config.md +++ b/docs/user/zh-CN/develop/basic/config.md @@ -105,4 +105,4 @@ export function apply(ctx: Context, config: Config) { ## 下一步 - [插件与生命周期](../framework/) — 深入了解插件的完整生命周期 -- [服务与依赖](../framework/service) — 让你的插件对外提供服务 +- [服务与依赖](../framework/service.md) — 让你的插件对外提供服务 diff --git a/website/zh-CN/develop/basic/index.md b/docs/user/zh-CN/develop/basic/index.md similarity index 95% rename from website/zh-CN/develop/basic/index.md rename to docs/user/zh-CN/develop/basic/index.md index 71d6962edd..ce68283892 100644 --- a/website/zh-CN/develop/basic/index.md +++ b/docs/user/zh-CN/develop/basic/index.md @@ -115,7 +115,7 @@ export default class MyService extends Service { } ``` -大多数情况下，函数形式足够了。类形式用于需要对外提供服务的插件（见 [服务与依赖](../framework/service)）。 +大多数情况下，函数形式足够了。类形式用于需要对外提供服务的插件（见 [服务与依赖](../framework/service.md)）。 ## 完整示例 @@ -144,5 +144,5 @@ export function apply(ctx: Context) { ## 下一步 -- [开发一个 Tool](./tool) — 详细了解 tool 定义 DSL -- [插件配置](./config) — 让插件接受用户配置 +- [开发一个 Tool](./tool.md) — 详细了解 tool 定义 DSL +- [插件配置](./config.md) — 让插件接受用户配置 diff --git a/website/zh-CN/develop/basic/tool.md b/docs/user/zh-CN/develop/basic/tool.md similarity index 98% rename from website/zh-CN/develop/basic/tool.md rename to docs/user/zh-CN/develop/basic/tool.md index 96d58da78d..47a3af7867 100644 --- a/website/zh-CN/develop/basic/tool.md +++ b/docs/user/zh-CN/develop/basic/tool.md @@ -195,5 +195,5 @@ export function apply(ctx: Context) { ## 下一步 -- [插件配置](./config) — 让你的 tool 可配置 +- [插件配置](./config.md) — 让你的 tool 可配置 - [能力三件套](../practice/) — 了解 seam/impl/consumer 模式 diff --git a/website/zh-CN/develop/framework/events.md b/docs/user/zh-CN/develop/framework/events.md similarity index 97% rename from website/zh-CN/develop/framework/events.md rename to docs/user/zh-CN/develop/framework/events.md index 0546fd68e7..641c63b0f8 100644 --- a/website/zh-CN/develop/framework/events.md +++ b/docs/user/zh-CN/develop/framework/events.md @@ -149,4 +149,4 @@ export function apply(ctx: Context) { ## 下一步 - [能力三件套](../practice/) — 事件在 capability seam 中的角色 -- [LLM 适配器](../practice/llm-adapter) — 实现一个完整的 LLM 后端 +- [LLM 适配器](../practice/llm-adapter.md) — 实现一个完整的 LLM 后端 diff --git a/website/zh-CN/develop/framework/index.md b/docs/user/zh-CN/develop/framework/index.md similarity index 95% rename from website/zh-CN/develop/framework/index.md rename to docs/user/zh-CN/develop/framework/index.md index 8d2f7c2b8a..b0547be61b 100644 --- a/website/zh-CN/develop/framework/index.md +++ b/docs/user/zh-CN/develop/framework/index.md @@ -135,5 +135,5 @@ effect cleaned up ## 下一步 -- [服务与依赖](./service) — 让你的插件对外提供能力 -- [事件系统](./events) — 插件间通信的核心机制 +- [服务与依赖](./service.md) — 让你的插件对外提供能力 +- [事件系统](./events.md) — 插件间通信的核心机制 diff --git a/website/zh-CN/develop/framework/service.md b/docs/user/zh-CN/develop/framework/service.md similarity index 83% rename from website/zh-CN/develop/framework/service.md rename to docs/user/zh-CN/develop/framework/service.md index 08d9a1b2c8..17b9cb4e4e 100644 --- a/website/zh-CN/develop/framework/service.md +++ b/docs/user/zh-CN/develop/framework/service.md @@ -127,21 +127,11 @@ export const inject = { optional: ['metrics'] } `plugin-a` 和 `plugin-b` 各自看到自己组内的 bash 实例，互不影响。 -## Harness 内置服务一览 +## Harness 内置服务 -| 服务名 | 提供者 | 用途 | -|--------|--------|------| -| `tools` | dsh-tools | Tool 注册表 | -| `llm` | dsh-llm | LLM 调用 + 适配器注册 | -| `agents` | dsh-agent | Agent 实例管理 | -| `session` | dsh-session | 会话事件流 | -| `systemPrompt` | dsh-system-prompt | 系统提示词组装 | -| `bash` | dsh-bash-local | Bash 命令执行 | -| `fs` | dsh-fs-local | 文件系统操作 | -| `subagent` | dsh-subagent | 子代理委派 | -| `persistence` | dsh-session-persistence | 会话持久化 | +服务名、公开方法和源码位置由仓库自动生成，见[服务目录](../../../../cordis-catalog/services.md)。开发插件时应以该目录和服务接口的 TypeScript 类型为准，不要复制一份静态清单。 ## 下一步 -- [事件系统](./events) — 插件间松耦合通信 +- [事件系统](./events.md) — 插件间松耦合通信 - [能力三件套](../practice/) — 服务在 seam 模式中的应用 diff --git a/website/zh-CN/develop/practice/index.md b/docs/user/zh-CN/develop/practice/index.md similarity index 95% rename from website/zh-CN/develop/practice/index.md rename to docs/user/zh-CN/develop/practice/index.md index dd0ec1cb60..bffa35f964 100644 --- a/website/zh-CN/develop/practice/index.md +++ b/docs/user/zh-CN/develop/practice/index.md @@ -58,7 +58,7 @@ | 文件系统 | `dsh-fs` | `dsh-fs-local` + `dsh-fs-policy` | `dsh-tool-fs` | | Web | `dsh-web` | `dsh-web-fetch-local` / `dsh-web-search-*` | `dsh-tool-web` | | 子代理 | `dsh-subagent` | `dsh-subagent-spawn` / `dsh-subagent-fork` | `dsh-tool-subagent` | -| 压缩 | `dsh-compact` | `dsh-compact-basic` | (内置于 agent-loop) | +| 压缩 | `dsh-compact` | `dsh-compact-basic` | 由实现插件消费 agent-loop 的扩展事件 | ## 开发你自己的三件套 @@ -153,4 +153,4 @@ export function apply(ctx: Context) { ## 下一步 -- [LLM 适配器](./llm-adapter) — 实现一个 LLM 后端（最常见的 seam 扩展） +- [LLM 适配器](./llm-adapter.md) — 实现一个 LLM 后端（最常见的 seam 扩展） diff --git a/website/zh-CN/develop/practice/llm-adapter.md b/docs/user/zh-CN/develop/practice/llm-adapter.md similarity index 100% rename from website/zh-CN/develop/practice/llm-adapter.md rename to docs/user/zh-CN/develop/practice/llm-adapter.md diff --git a/docs/user/zh-CN/guide/config.md b/docs/user/zh-CN/guide/config.md new file mode 100644 index 0000000000..5e13b69d9f --- /dev/null +++ b/docs/user/zh-CN/guide/config.md @@ -0,0 +1,57 @@ +# 配置文件 + +Harness 使用 `cordis.yml` 描述 Agent 加载哪些插件以及每个插件的参数。配置文件负责组合能力；每个包真正支持的字段和默认值由源码生成的配置目录负责记录，避免两份手写表格逐渐不一致。 + +## 从真实配置开始 + +仓库中的示例就是可以运行的配置，也是新项目最可靠的起点： + +- [echo-agent](../../../../examples/echo-agent/cordis.yml) 使用本地 mock 模型，不需要 API key。 +- [coding-agent](../../../../examples/coding-agent/cordis.yml) 组合 DeepSeek 模型、Bash、文件系统、压缩、子代理和工作流。 +- [acp-agent](../../../../examples/acp-agent/cordis.yml) 通过 ACP 接入编辑器客户端。 + +最小配置由一组插件条目组成： + +```yaml +- id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + models: + - deepseek-v4-flash + +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-agent' + config: + model: deepseek-v4-flash +``` + +## 插件条目 + +`name` 指定 npm 包或相对于 `cordis.yml` 的本地模块，`id` 为插件实例提供稳定标识，`config` 传入插件自己的配置。需要临时跳过某个条目时可设置 `disabled: true`。 + +```yaml +- id: local-tool + name: './src/my-tool.ts' + disabled: false + config: + toolName: my_tool +``` + +插件按文件中的顺序加载。依赖其他服务的插件应该排在提供这些服务的应用或能力插件之后；引用不存在的模型、工具或插件会尽早报错，而不是被静默忽略。 + +## JavaScript 值和环境变量 + +Cordis loader 使用 `!!js` 标签读取运行时表达式。API key 等凭据应放在仓库根目录、已被 Git 忽略的 `.env` 中，不能提交到配置文件。 + +```yaml +config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + cwd: !!js process.cwd() +``` + +标签是 `!!js`，不是 `!js`。 + +## 精确配置参考 + +每个插件当前支持的字段、类型和默认值见自动生成的[插件配置目录](../../../config-catalog.md)。理解插件如何组合可继续阅读[架构说明](../../../architecture.md)和[能力接口](../../../capability-seams.md)；要创建自己的配置，优先复制并修改[示例目录说明](../../../../examples/README.md)中最接近的例子。 diff --git a/website/zh-CN/guide/index.md b/docs/user/zh-CN/guide/index.md similarity index 89% rename from website/zh-CN/guide/index.md rename to docs/user/zh-CN/guide/index.md index 8b7211b308..8c7f7e603a 100644 --- a/website/zh-CN/guide/index.md +++ b/docs/user/zh-CN/guide/index.md @@ -28,7 +28,7 @@ Harness 将一个 AI Agent（智能体） 所需要的所有能力——LLM 调 2. 填写 API key 3. 运行 -不需要写任何代码。详见 [快速开始](./quickstart)。 +不需要写任何代码。详见 [快速开始](./quickstart.md)。 ### 插件开发者 @@ -41,7 +41,7 @@ Harness 将一个 AI Agent（智能体） 所需要的所有能力——LLM 调 ## 技术栈 -- **运行时**: Node.js >= 24 +- **运行时**: Node.js ^22.19 或 >= 24 - **语言**: TypeScript (ESM) - **框架**: Cordis -- **包管理**: pnpm workspaces +- **包管理**: pnpm workspaces（仓库固定使用 pnpm 11） diff --git a/website/zh-CN/guide/quickstart.md b/docs/user/zh-CN/guide/quickstart.md similarity index 84% rename from website/zh-CN/guide/quickstart.md rename to docs/user/zh-CN/guide/quickstart.md index f15ac182cf..7ca4b19332 100644 --- a/website/zh-CN/guide/quickstart.md +++ b/docs/user/zh-CN/guide/quickstart.md @@ -4,13 +4,14 @@ ## 环境准备 -- [Node.js](https://nodejs.org/) >= 24 -- [pnpm](https://pnpm.io/) >= 9 +- [Node.js](https://nodejs.org/) ^22.19 或 >= 24 +- [pnpm](https://pnpm.io/) 11（建议通过 Corepack 使用仓库固定的版本） ```sh # 确认版本 -node -v # v24.x 或更高 -pnpm -v # 9.x 或更高 +node -v # v22.19.x，或 v24.x 及更高版本 +corepack enable +pnpm -v # 11.x ``` ## 第一步：运行 echo-agent @@ -24,8 +25,6 @@ cd deepseek-harness # 安装依赖 pnpm install -# 如果看到 ERR_PNPM_IGNORED_BUILDS，可以忽略——安装已经成功了。 -# 想消除这个提示可以跑一次: pnpm approve-builds # 启动 echo-agent pnpm run demo:echo @@ -94,5 +93,5 @@ echo-agent 和 coding-agent 用的是同一个应用框架(`@deepseek-ai/dsh-std ## 下一步 -- [配置文件](./config) — 了解 `cordis.yml` 的完整语法 +- [配置文件](./config.md) — 了解 `cordis.yml` 的完整语法 - [开发插件](../develop/basic/) — 编写你自己的 tool 或后端 diff --git a/website/zh-CN/index.md b/docs/user/zh-CN/index.md similarity index 90% rename from website/zh-CN/index.md rename to docs/user/zh-CN/index.md index 90b23e483a..cbf700e41e 100644 --- a/website/zh-CN/index.md +++ b/docs/user/zh-CN/index.md @@ -7,10 +7,10 @@ hero: actions: - theme: brand text: 快速开始 - link: /zh-CN/guide/quickstart + link: /guide/quickstart - theme: alt text: 开发插件 - link: /zh-CN/develop/basic/ + link: /develop/basic/ features: - title: 插件化架构 details: 基于 Cordis 效果系统，所有能力通过插件注册，加载即生效、卸载即还原。 diff --git a/eslint.config.mjs b/eslint.config.mjs index c62d3e9739..ab4c78ccb0 100644 --- a/eslint.config.mjs +++ b/eslint.config.mjs @@ -24,6 +24,7 @@ export default tseslint.config( '**/.sessions/**', '.claude/**', // harness-local state (worktrees, skills) — other checkouts, not this one's sources '**/.doc-typecheck-*/**', + 'website/.generated/**', 'vendor/**', // vendored source keeps upstream style and idioms '**/*.js', '**/*.mjs', @@ -33,7 +34,7 @@ export default tseslint.config( // --- our packages: full strictness ------------------------------------- { - files: ['packages/*/*/src/**/*.ts', 'examples/**/*.ts', 'scripts/**/*.ts'], + files: ['packages/*/*/src/**/*.ts', 'examples/**/*.ts', 'scripts/**/*.ts', 'website/**/*.ts'], extends: [ ...tseslint.configs.strictTypeChecked, ], @@ -125,7 +126,7 @@ export default tseslint.config( // --- formatting (everything we own) ------------------------------------- { - files: ['packages/**/*.ts', 'examples/**/*.ts', 'scripts/**/*.ts', 'eslint.config.mjs'], + files: ['packages/**/*.ts', 'examples/**/*.ts', 'scripts/**/*.ts', 'website/**/*.ts', 'eslint.config.mjs'], plugins: { '@stylistic': stylistic }, rules: { '@stylistic/indent': ['error', 2], diff --git a/knip.json b/knip.json index cf43b90e34..88199c02a4 100644 --- a/knip.json +++ b/knip.json @@ -15,6 +15,16 @@ ], "project": ["scripts/**/*.ts", "examples/**/*.ts"] }, + "website": { + "project": ["**/*.ts"], + "ignoreDependencies": [ + "@braintree/sanitize-url", + "cytoscape", + "cytoscape-cose-bilkent", + "dayjs", + "debug" + ] + }, "packages/*/*": { "entry": ["tests/**/*.spec.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] diff --git a/package.json b/package.json index 0fc57b7db5..3a1e49391c 100644 --- a/package.json +++ b/package.json @@ -9,7 +9,8 @@ }, "workspaces": [ "vendor/*", - "packages/*/*" + "packages/*/*", + "website" ], "scripts": { "build": "tsc -b tsconfig.build.json && tsdown", @@ -44,6 +45,10 @@ "verify-type-equiv": "tsx scripts/verify-type-equiv.ts", "verify-translation-pairing": "tsx scripts/verify-translation-pairing.ts", "verify-doc-budgets": "tsx scripts/verify-doc-budgets.ts", + "docs:dev": "pnpm --filter @deepseek-ai/website run dev", + "docs:build": "pnpm --filter @deepseek-ai/website run build", + "docs:preview": "pnpm --filter @deepseek-ai/website run preview", + "docs:check": "pnpm exec vitest run scripts/project-doc-site.spec.ts && pnpm run docs:build", "verify-node-next-types": "tsx scripts/verify-node-next-types.ts", "gen-cordis-catalog": "tsx scripts/gen-cordis-catalog.ts", "gen-rfc-index": "tsx scripts/gen-rfc-index.ts", @@ -62,7 +67,7 @@ "gen-module-graph": "tsx scripts/gen-module-graph.ts", "verify-module-graph": "tsx scripts/gen-module-graph.ts --check", "constraints": "tsx scripts/check-workspace-constraints.ts", - "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets", + "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run docs:check", "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-node-next-types", "demo:echo": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/ui/stdio-agent/src/bin.ts examples/coding-agent/cordis.yml", diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 8bc2ed1495..360ddc7e7e 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -75,31 +75,6 @@ importers: specifier: ^4.1.8 version: 4.1.8(@types/node@22.20.0)(@vitest/coverage-v8@4.1.8)(jsdom@29.1.1)(vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0)) - packages/ui/user-approval: - dependencies: - schemastery: - specifier: ^3.18.0 - version: 3.18.0 - devDependencies: - '@deepseek-ai/dsh-agent': - specifier: workspace:^ - version: link:../../core/agent - '@deepseek-ai/dsh-brand': - specifier: workspace:^ - version: link:../../util/brand - '@deepseek-ai/dsh-llm': - specifier: workspace:^ - version: link:../../llm/llm - '@deepseek-ai/dsh-session': - specifier: workspace:^ - version: link:../../core/session - '@deepseek-ai/dsh-system-prompt': - specifier: workspace:^ - version: link:../../core/system-prompt - cordis: - specifier: ^4.0.0-rc.6 - version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) - packages/bash/bash: devDependencies: '@deepseek-ai/dsh-brand': @@ -164,9 +139,6 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop - '@deepseek-ai/dsh-user-approval': - specifier: workspace:^ - version: link:../../ui/user-approval '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../bash @@ -194,6 +166,9 @@ importers: '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../../ui/user-approval cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -425,9 +400,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../agent - '@deepseek-ai/dsh-user-approval': - specifier: workspace:^ - version: link:../../ui/user-approval '@deepseek-ai/dsh-code-runtime': specifier: workspace:^ version: link:../../code-runtime/code-runtime @@ -440,6 +412,9 @@ importers: '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../system-prompt + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../../ui/user-approval cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -1135,9 +1110,6 @@ importers: '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop - '@deepseek-ai/dsh-user-approval': - specifier: workspace:^ - version: link:../user-approval '@deepseek-ai/dsh-bash': specifier: workspace:^ version: link:../../bash/bash @@ -1186,6 +1158,9 @@ importers: '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../user-approval '@deepseek-ai/dsh-user-interaction': specifier: workspace:^ version: link:../user-interaction @@ -1310,6 +1285,31 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/user-approval: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-brand': + specifier: workspace:^ + version: link:../../util/brand + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-system-prompt': + specifier: workspace:^ + version: link:../../core/system-prompt + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/user-interaction: devDependencies: '@deepseek-ai/dsh-agent': @@ -1654,6 +1654,36 @@ importers: specifier: ^1.8.1 version: 1.8.1 + website: + devDependencies: + '@braintree/sanitize-url': + specifier: 7.1.2 + version: 7.1.2 + cytoscape: + specifier: 3.34.0 + version: 3.34.0 + cytoscape-cose-bilkent: + specifier: 4.1.0 + version: 4.1.0(cytoscape@3.34.0) + dayjs: + specifier: 1.11.21 + version: 1.11.21 + debug: + specifier: 4.4.3 + version: 4.4.3 + mermaid: + specifier: 11.16.0 + version: 11.16.0 + vite: + specifier: ^5.4.14 + version: 5.4.21(@types/node@25.9.3)(lightningcss@1.32.0) + vitepress: + specifier: ^1.6.4 + version: 1.6.4(@algolia/client-search@5.55.2)(@types/node@25.9.3)(lightningcss@1.32.0)(postcss@8.5.15)(search-insights@2.17.3)(typescript@6.0.3) + vitepress-plugin-mermaid: + specifier: ^2.0.17 + version: 2.0.17(mermaid@11.16.0)(vitepress@1.6.4(@algolia/client-search@5.55.2)(@types/node@25.9.3)(lightningcss@1.32.0)(postcss@8.5.15)(search-insights@2.17.3)(typescript@6.0.3)) + packages: '@agentclientprotocol/sdk@0.25.1': @@ -1661,6 +1691,82 @@ packages: peerDependencies: zod: ^3.25.0 || ^4.0.0 + '@algolia/abtesting@1.21.2': + resolution: {integrity: sha512-uXj0rgk30EpsKvOpuS+R+1XFDrnm56hED1Lz56e8uBkZdKCxw99LS2U8eXBqAHYU8kpkbsnV1GC8velBG070Hg==} + engines: {node: '>= 14.0.0'} + + '@algolia/autocomplete-core@1.17.7': + resolution: {integrity: sha512-BjiPOW6ks90UKl7TwMv7oNQMnzU+t/wk9mgIDi6b1tXpUek7MW0lbNOUHpvam9pe3lVCf4xPFT+lK7s+e+fs7Q==} + + '@algolia/autocomplete-plugin-algolia-insights@1.17.7': + resolution: {integrity: sha512-Jca5Ude6yUOuyzjnz57og7Et3aXjbwCSDf/8onLHSQgw1qW3ALl9mrMWaXb5FmPVkV3EtkD2F/+NkT6VHyPu9A==} + peerDependencies: + search-insights: '>= 1 < 3' + + '@algolia/autocomplete-preset-algolia@1.17.7': + resolution: {integrity: sha512-ggOQ950+nwbWROq2MOCIL71RE0DdQZsceqrg32UqnhDz8FlO9rL8ONHNsI2R1MH0tkgVIDKI/D0sMiUchsFdWA==} + peerDependencies: + '@algolia/client-search': '>= 4.9.1 < 6' + algoliasearch: '>= 4.9.1 < 6' + + '@algolia/autocomplete-shared@1.17.7': + resolution: {integrity: sha512-o/1Vurr42U/qskRSuhBH+VKxMvkkUVTLU6WZQr+L5lGZZLYWyhdzWjW0iGXY7EkwRTjBqvN2EsR81yCTGV/kmg==} + peerDependencies: + '@algolia/client-search': '>= 4.9.1 < 6' + algoliasearch: '>= 4.9.1 < 6' + + '@algolia/client-abtesting@5.55.2': + resolution: {integrity: sha512-y7Epol8HcjlBxKXHhyhfFPFhm78B3P6x9cCbCyGTdxjsdVCptXCy5hpkZWxjGpnaLHvWsHS4QRF0TiBOLst2xg==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-analytics@5.55.2': + resolution: {integrity: sha512-8Pxj2VVmpM2d+UZufnlTq7T1QIcYPVugLV5XC50PnHsV5uRM9CSoYkg2Y+CwqwRk2La0xK5QsfZ0obIU+9XftQ==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-common@5.55.2': + resolution: {integrity: sha512-9L4IpIYUqA63a7sw1trnHQGUvwiAjKz67nsgDnal98JGAc7wyposRb0Iag+eiMuyzFFaSHLe2/rGyIo+PafRBA==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-insights@5.55.2': + resolution: {integrity: sha512-ZBm2ytY5EHFcj+kjNsXxMNO/TGlOHe2fBFXGKHJOM1bk1rAy4o2YI+d9oV/w/jrqx44pvJMJlc8X6vKnCuDgUQ==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-personalization@5.55.2': + resolution: {integrity: sha512-3FGVW/jDk7sdYwqa2NKnF/qXWcttc4bvGrwNbvqz3VoWSRv42CNvRk+3Y9QJFIUf1vY50hAuVWUoFKdyc8vaXA==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-query-suggestions@5.55.2': + resolution: {integrity: sha512-JsG8LovDAYul5t8e533tZ3O1uZILxso5zsTtB7ONc5RJ8ACdTxAAC/jaOnsBNYb+x+STP7fzx/Iro55v5DNgoQ==} + engines: {node: '>= 14.0.0'} + + '@algolia/client-search@5.55.2': + resolution: {integrity: sha512-5wDnoIfC75zJ2MSHv5SSzTlRL2z7jQMbqQ5jrzottuq2p3oBObv8pD/JpXWu8pRaimaxNr3/Bs/KZIGVXxJ7hg==} + engines: {node: '>= 14.0.0'} + + '@algolia/ingestion@1.55.2': + resolution: {integrity: sha512-da+SC6ikpza98W7C5ChsKEQDvZc8PQLQ0sxmQ5yMRsHpdD3iPKnclJA6ViB5Nr5T9qOX+IDswC6AyqY4V3rtug==} + engines: {node: '>= 14.0.0'} + + '@algolia/monitoring@1.55.2': + resolution: {integrity: sha512-Y8kEcPqCiIEeaGv83l9RRA09mfYECqAJHNnOyEtZc9UirI6XBMUyFVss/sSeYUiV/Lf30hkbWcl00V1uXsf86Q==} + engines: {node: '>= 14.0.0'} + + '@algolia/recommend@5.55.2': + resolution: {integrity: sha512-5zmobuCQqFZkx+84Nt+suL7vo6jTh2CfAs2ndDSeTS2QHvnzP8YEEGWtWftjyACI0cK/FuH8urWwCHP+d2j8TA==} + engines: {node: '>= 14.0.0'} + + '@algolia/requester-browser-xhr@5.55.2': + resolution: {integrity: sha512-qnGUUuWG66dRMnr33owLsrYIh9fHVxtU4R2rd3SpneAHuoAUcGbDOWNrj05glVU6M8yOqo9gQ22K8zpz0I8Xpg==} + engines: {node: '>= 14.0.0'} + + '@algolia/requester-fetch@5.55.2': + resolution: {integrity: sha512-lKZ5uhafMvR7dWCJEyuaeyZitid1I3ICx+k0vGf5x/ktdIQvc7bndCiOPpmIDqUmN26FE3jTehkAzSqee95G2Q==} + engines: {node: '>= 14.0.0'} + + '@algolia/requester-node-http@5.55.2': + resolution: {integrity: sha512-Zc90xvKWUvxcNicvvTO9Pr/hT2TAnkixOIzJm/KMj5Ptm2pKjk71ngTsdkbRtJQvhZ2Kr9N1YdIjLrNHB5P2xw==} + engines: {node: '>= 14.0.0'} + '@antfu/install-pkg@1.1.0': resolution: {integrity: sha512-MGQsmw10ZyI+EJo45CdSER4zEb+p31LpDAFp2Z3gkSd1yqVZGi0Ebx++YTEMonJy4oChEMLsxZ64j8FH6sSqtQ==} @@ -1839,6 +1945,9 @@ packages: resolution: {integrity: sha512-6zABk/ECA/QYSCQ1NGiVwwbQerUCZ+TQbp64Q3AgmfNvurHH0j8TtXa1qbShXA6qqkpAj4V5W8pP6mLe1mcMqA==} engines: {node: '>=18'} + '@braintree/sanitize-url@6.0.4': + resolution: {integrity: sha512-s3jaWicZd0pkP0jf5ysyHUI/RE7MHos6qlToFcGWXVp+ykHOy77OUMrfbgJ9it2C5bow7OIQwYYaHjk9XlBQ2A==} + '@braintree/sanitize-url@7.1.2': resolution: {integrity: sha512-jigsZK+sMF/cuiB7sERuo9V7N9jx+dhmHHnQyDSVdpZwVutaBu7WvNYqMDLSgFgfB30n452TP3vjDAvFC973mA==} @@ -1901,6 +2010,29 @@ packages: resolution: {integrity: sha512-QxULHAm7cNu72w97JUNCBFODFaXpbDg+dP8b/oWFAZ2MTRppA3U00Y2L1HqaS4J6yBqxwa/Y3nMBaxVKbB/NsA==} engines: {node: '>=20.19.0'} + '@docsearch/css@3.8.2': + resolution: {integrity: sha512-y05ayQFyUmCXze79+56v/4HpycYF3uFqB78pLPrSV5ZKAlDuIAAJNhaRi8tTdRNXh05yxX/TyNnzD6LwSM89vQ==} + + '@docsearch/js@3.8.2': + resolution: {integrity: sha512-Q5wY66qHn0SwA7Taa0aDbHiJvaFJLOJyHmooQ7y8hlwwQLQ/5WwCcoX0g7ii04Qi2DJlHsd0XXzJ8Ypw9+9YmQ==} + + '@docsearch/react@3.8.2': + resolution: {integrity: sha512-xCRrJQlTt8N9GU0DG4ptwHRkfnSnD/YpdeaXe02iKfqs97TkZJv60yE+1eq/tjPcVnTW8dP5qLP7itifFVV5eg==} + peerDependencies: + '@types/react': '>= 16.8.0 < 19.0.0' + react: '>= 16.8.0 < 19.0.0' + react-dom: '>= 16.8.0 < 19.0.0' + search-insights: '>= 1 < 3' + peerDependenciesMeta: + '@types/react': + optional: true + react: + optional: true + react-dom: + optional: true + search-insights: + optional: true + '@earendil-works/pi-ai@0.79.3': resolution: {integrity: sha512-lMSput/haP5uZAGbXhS5rAYd3GB7GYdJkoAUxg3VFummBeqGqGqllaTWrbHFN12kVGyVfWHhdySNXkiqVh65Iw==} engines: {node: '>=22.19.0'} @@ -1924,102 +2056,204 @@ packages: '@emnapi/wasi-threads@1.2.2': resolution: {integrity: sha512-c95qOXkHdydNKhscBTebqEC1CVAZpyqOfVfBzQ1qgzyl3gfeldUjIggDbIZgDKsHLgnsM+igH7TJ/eAasaVuMA==} + '@esbuild/aix-ppc64@0.21.5': + resolution: {integrity: sha512-1SDgH6ZSPTlggy1yI6+Dbkiz8xzpHJEVAlF/AM1tHPLsf5STom9rwtjE4hKAF20FfXXNTFqEYXyJNWh1GiZedQ==} + engines: {node: '>=12'} + cpu: [ppc64] + os: [aix] + '@esbuild/aix-ppc64@0.28.1': resolution: {integrity: sha512-Svl7tq8k/08+p6CXPpRjQ1fKX+1odH/BQbb48fV6fj3CWHhsoIOoY87w1oHXm0qEpkIK3ZfVgp0hed3XBXzXMQ==} engines: {node: '>=18'} cpu: [ppc64] os: [aix] + '@esbuild/android-arm64@0.21.5': + resolution: {integrity: sha512-c0uX9VAUBQ7dTDCjq+wdyGLowMdtR/GoC2U5IYk/7D1H1JYC0qseD7+11iMP2mRLN9RcCMRcjC4YMclCzGwS/A==} + engines: {node: '>=12'} + cpu: [arm64] + os: [android] + '@esbuild/android-arm64@0.28.1': resolution: {integrity: sha512-34EGEbCIAgosYz6goLcopX6Mo7NyGv9tfwEM2/7Ce2VcVRk568iSvniGWcUXIy7wEDR1wzolcxcriFVrWYcwBg==} engines: {node: '>=18'} cpu: [arm64] os: [android] + '@esbuild/android-arm@0.21.5': + resolution: {integrity: sha512-vCPvzSjpPHEi1siZdlvAlsPxXl7WbOVUBBAowWug4rJHb68Ox8KualB+1ocNvT5fjv6wpkX6o/iEpbDrf68zcg==} + engines: {node: '>=12'} + cpu: [arm] + os: [android] + '@esbuild/android-arm@0.28.1': resolution: {integrity: sha512-0k2F129Xdio1TdJfzJ8sy1Q47vUD2NnwdhiAf7drUN1EBTfPf4hsFCtmMgu/6m8JSzsBrlmVjudMBQqOfG8usQ==} engines: {node: '>=18'} cpu: [arm] os: [android] + '@esbuild/android-x64@0.21.5': + resolution: {integrity: sha512-D7aPRUUNHRBwHxzxRvp856rjUHRFW1SdQATKXH2hqA0kAZb1hKmi02OpYRacl0TxIGz/ZmXWlbZgjwWYaCakTA==} + engines: {node: '>=12'} + cpu: [x64] + os: [android] + '@esbuild/android-x64@0.28.1': resolution: {integrity: sha512-dbwY7ltSMDWsRatcRpCnES4F+im88OCUgGZjy52shC7GqHRE/cYlxNbB4Z4UpJswpcc4Qxd2oE/ufM0p61IKng==} engines: {node: '>=18'} cpu: [x64] os: [android] + '@esbuild/darwin-arm64@0.21.5': + resolution: {integrity: sha512-DwqXqZyuk5AiWWf3UfLiRDJ5EDd49zg6O9wclZ7kUMv2WRFr4HKjXp/5t8JZ11QbQfUS6/cRCKGwYhtNAY88kQ==} + engines: {node: '>=12'} + cpu: [arm64] + os: [darwin] + '@esbuild/darwin-arm64@0.28.1': resolution: {integrity: sha512-TZbWkQY7kvTAXbXUT7uVACR5cMHsDiSz9z7ZKAX/RTq/WJEk3QyRr0wZpNhBDX+/0CtdqUIJlOiodQcta6tY3Q==} engines: {node: '>=18'} cpu: [arm64] os: [darwin] + '@esbuild/darwin-x64@0.21.5': + resolution: {integrity: sha512-se/JjF8NlmKVG4kNIuyWMV/22ZaerB+qaSi5MdrXtd6R08kvs2qCN4C09miupktDitvh8jRFflwGFBQcxZRjbw==} + engines: {node: '>=12'} + cpu: [x64] + os: [darwin] + '@esbuild/darwin-x64@0.28.1': resolution: {integrity: sha512-zfdzgK9ACBNZLI/CyHTOx81SyNbM6YXn7rxSgX97VjyiPl9W1i4Ka4fgKECEoFCKGpvBj5qArWIGgQjOwkgskQ==} engines: {node: '>=18'} cpu: [x64] os: [darwin] + '@esbuild/freebsd-arm64@0.21.5': + resolution: {integrity: sha512-5JcRxxRDUJLX8JXp/wcBCy3pENnCgBR9bN6JsY4OmhfUtIHe3ZW0mawA7+RDAcMLrMIZaf03NlQiX9DGyB8h4g==} + engines: {node: '>=12'} + cpu: [arm64] + os: [freebsd] + '@esbuild/freebsd-arm64@0.28.1': resolution: {integrity: sha512-wG2EA8ENdEI0qhkSZMjfqrdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsjtfs3VpnlC7QLzSI5hY/rOAw==} engines: {node: '>=18'} cpu: [arm64] os: [freebsd] + '@esbuild/freebsd-x64@0.21.5': + resolution: {integrity: sha512-J95kNBj1zkbMXtHVH29bBriQygMXqoVQOQYA+ISs0/2l3T9/kj42ow2mpqerRBxDJnmkUDCaQT/dfNXWX/ZZCQ==} + engines: {node: '>=12'} + cpu: [x64] + os: [freebsd] + '@esbuild/freebsd-x64@0.28.1': resolution: {integrity: sha512-i7dZ9vQgnvSCzi/rYCXNgtF/U+eKZNJBzu3eTQbRgHnM7tNSizLOkRFAl3qzVc/Op/u5YkHHa4pf/3DOYHthLQ==} engines: {node: '>=18'} cpu: [x64] os: [freebsd] + '@esbuild/linux-arm64@0.21.5': + resolution: {integrity: sha512-ibKvmyYzKsBeX8d8I7MH/TMfWDXBF3db4qM6sy+7re0YXya+K1cem3on9XgdT2EQGMu4hQyZhan7TeQ8XkGp4Q==} + engines: {node: '>=12'} + cpu: [arm64] + os: [linux] + '@esbuild/linux-arm64@0.28.1': resolution: {integrity: sha512-yHs+0uc8+nvEAfAfxrWQKK5peSNzBc4PegcMO0EJ2hT71uA7vB8Ihg2e77R2P7SG5uYjPbHlLLmve4LLLRCf0g==} engines: {node: '>=18'} cpu: [arm64] os: [linux] + '@esbuild/linux-arm@0.21.5': + resolution: {integrity: sha512-bPb5AHZtbeNGjCKVZ9UGqGwo8EUu4cLq68E95A53KlxAPRmUyYv2D6F0uUI65XisGOL1hBP5mTronbgo+0bFcA==} + engines: {node: '>=12'} + cpu: [arm] + os: [linux] + '@esbuild/linux-arm@0.28.1': resolution: {integrity: sha512-qVXBOHQS+d5Y722GwJzJUtOLlX7km3CraOaGormF1pDtPd2C/l1SHRPgjLunLGe51Sh5YYWKMFDyV4SxgMQYTQ==} engines: {node: '>=18'} cpu: [arm] os: [linux] + '@esbuild/linux-ia32@0.21.5': + resolution: {integrity: sha512-YvjXDqLRqPDl2dvRODYmmhz4rPeVKYvppfGYKSNGdyZkA01046pLWyRKKI3ax8fbJoK5QbxblURkwK/MWY18Tg==} + engines: {node: '>=12'} + cpu: [ia32] + os: [linux] + '@esbuild/linux-ia32@0.28.1': resolution: {integrity: sha512-d1z4ZuP0ajrfz/FhGT4vv278rX8KnPPJx8i5+AtK7TYbx9Le9F1hyzurZpkEyjkGa9dUGhQow4C1NmeGvqxN2w==} engines: {node: '>=18'} cpu: [ia32] os: [linux] + '@esbuild/linux-loong64@0.21.5': + resolution: {integrity: sha512-uHf1BmMG8qEvzdrzAqg2SIG/02+4/DHB6a9Kbya0XDvwDEKCoC8ZRWI5JJvNdUjtciBGFQ5PuBlpEOXQj+JQSg==} + engines: {node: '>=12'} + cpu: [loong64] + os: [linux] + '@esbuild/linux-loong64@0.28.1': resolution: {integrity: sha512-M5sRjUVZrkm1OAPR3dlOYzNmN+loZKGVi1VUQGrwuqLcbR6qeAz+famMhjASeH3YVKvZz+zT1jlh/keC3Rj/lg==} engines: {node: '>=18'} cpu: [loong64] os: [linux] + '@esbuild/linux-mips64el@0.21.5': + resolution: {integrity: sha512-IajOmO+KJK23bj52dFSNCMsz1QP1DqM6cwLUv3W1QwyxkyIWecfafnI555fvSGqEKwjMXVLokcV5ygHW5b3Jbg==} + engines: {node: '>=12'} + cpu: [mips64el] + os: [linux] + '@esbuild/linux-mips64el@0.28.1': resolution: {integrity: sha512-mRObBZeHh2OxcBFPWE/FjylkRgZdYuiTR3vaTozquCGOH14iP9oN4x4Ge81CoIDYQrXmIxpFumJBu5MtZpnQJQ==} engines: {node: '>=18'} cpu: [mips64el] os: [linux] + '@esbuild/linux-ppc64@0.21.5': + resolution: {integrity: sha512-1hHV/Z4OEfMwpLO8rp7CvlhBDnjsC3CttJXIhBi+5Aj5r+MBvy4egg7wCbe//hSsT+RvDAG7s81tAvpL2XAE4w==} + engines: {node: '>=12'} + cpu: [ppc64] + os: [linux] + '@esbuild/linux-ppc64@0.28.1': resolution: {integrity: sha512-slScBsMAb3GFDcdrCgLwZtPYRoH2H/youv10QiZyRjmsP48fznoveWytSgCI/R0ZcUgpc0ZhIUEx6LHts8yrfQ==} engines: {node: '>=18'} cpu: [ppc64] os: [linux] + '@esbuild/linux-riscv64@0.21.5': + resolution: {integrity: sha512-2HdXDMd9GMgTGrPWnJzP2ALSokE/0O5HhTUvWIbD3YdjME8JwvSCnNGBnTThKGEB91OZhzrJ4qIIxk/SBmyDDA==} + engines: {node: '>=12'} + cpu: [riscv64] + os: [linux] + '@esbuild/linux-riscv64@0.28.1': resolution: {integrity: sha512-kw0owk1o0GFETUJyW0jc0G4Yzs0BHZn0JDZ8JRT088vjJYX777BAs1fDGxAC+q831qOs2DTC96mNsG2opdfyyQ==} engines: {node: '>=18'} cpu: [riscv64] os: [linux] + '@esbuild/linux-s390x@0.21.5': + resolution: {integrity: sha512-zus5sxzqBJD3eXxwvjN1yQkRepANgxE9lgOW2qLnmr8ikMTphkjgXu1HR01K4FJg8h1kEEDAqDcZQtbrRnB41A==} + engines: {node: '>=12'} + cpu: [s390x] + os: [linux] + '@esbuild/linux-s390x@0.28.1': resolution: {integrity: sha512-/lAIjX8aYFRByhh6L5rYtPEDRqa9de/4V/juOXcta5frjvzXO4/sqEtyytse0g3zZFuWu5cDN0MkLz2qRDD2Ag==} engines: {node: '>=18'} cpu: [s390x] os: [linux] + '@esbuild/linux-x64@0.21.5': + resolution: {integrity: sha512-1rYdTpyv03iycF1+BhzrzQJCdOuAOtaqHTWJZCWvijKD2N5Xu0TtVC8/+1faWqcP9iBCWOmjmhoH94dH82BxPQ==} + engines: {node: '>=12'} + cpu: [x64] + os: [linux] + '@esbuild/linux-x64@0.28.1': resolution: {integrity: sha512-u/anNYF2mmVOEDwLtnQ1wOr3EZ9sTNGLWrsYGYwHWzGA3Si84IOkHXlbWTD1NB+9/1lcnweYKO54uhxZydNzfA==} engines: {node: '>=18'} @@ -2032,6 +2266,12 @@ packages: cpu: [arm64] os: [netbsd] + '@esbuild/netbsd-x64@0.21.5': + resolution: {integrity: sha512-Woi2MXzXjMULccIwMnLciyZH4nCIMpWQAs049KEeMvOcNADVxo0UBIQPfSmxB3CWKedngg7sWZdLvLczpe0tLg==} + engines: {node: '>=12'} + cpu: [x64] + os: [netbsd] + '@esbuild/netbsd-x64@0.28.1': resolution: {integrity: sha512-aeL6lAnN89Hz43Mlh1G8ARasbuoYvSITDEx0tHh5b7jJnHcssqgjy9Yx430GDpmCa6OyrKoS0aNRjKundRizGg==} engines: {node: '>=18'} @@ -2044,6 +2284,12 @@ packages: cpu: [arm64] os: [openbsd] + '@esbuild/openbsd-x64@0.21.5': + resolution: {integrity: sha512-HLNNw99xsvx12lFBUwoT8EVCsSvRNDVxNpjZ7bPn947b8gJPzeHWyNVhFsaerc0n3TsbOINvRP2byTZ5LKezow==} + engines: {node: '>=12'} + cpu: [x64] + os: [openbsd] + '@esbuild/openbsd-x64@0.28.1': resolution: {integrity: sha512-i/ZLIOafE0Z8cI/XANJAixoJL/uRAoS2xOA3rb0xN+KK0K177cMAsQYkzHtBrtMXAKuAc7HGgcWiZ/sRC1Nxgw==} engines: {node: '>=18'} @@ -2056,24 +2302,48 @@ packages: cpu: [arm64] os: [openharmony] + '@esbuild/sunos-x64@0.21.5': + resolution: {integrity: sha512-6+gjmFpfy0BHU5Tpptkuh8+uw3mnrvgs+dSPQXQOv3ekbordwnzTVEb4qnIvQcYXq6gzkyTnoZ9dZG+D4garKg==} + engines: {node: '>=12'} + cpu: [x64] + os: [sunos] + '@esbuild/sunos-x64@0.28.1': resolution: {integrity: sha512-BEjgtECkL3vY+SaSQ6nzVfiALUeFxpawyp8Jmf5PtYhf1Ug40N1h/hxlhts+f1FvSvarEigdxS3BlSMI2PJLcQ==} engines: {node: '>=18'} cpu: [x64] os: [sunos] + '@esbuild/win32-arm64@0.21.5': + resolution: {integrity: sha512-Z0gOTd75VvXqyq7nsl93zwahcTROgqvuAcYDUr+vOv8uHhNSKROyU961kgtCD1e95IqPKSQKH7tBTslnS3tA8A==} + engines: {node: '>=12'} + cpu: [arm64] + os: [win32] + '@esbuild/win32-arm64@0.28.1': resolution: {integrity: sha512-lCv9eK/H6ZJWbE7bh2nw54CZ9M2nupBxJcTsdk/QQnWkdSjKGuxmmH8/GWrlT1eMmZfn4dGcCjRte397WqfQXA==} engines: {node: '>=18'} cpu: [arm64] os: [win32] + '@esbuild/win32-ia32@0.21.5': + resolution: {integrity: sha512-SWXFF1CL2RVNMaVs+BBClwtfZSvDgtL//G/smwAc5oVK/UPu2Gu9tIaRgFmYFFKrmg3SyAjSrElf0TiJ1v8fYA==} + engines: {node: '>=12'} + cpu: [ia32] + os: [win32] + '@esbuild/win32-ia32@0.28.1': resolution: {integrity: sha512-zvb/mB2bSCoJOpoCBgYKKpX6YM6mJBlBUVUtVj41DlZJVEB6/0CKlRYxP5wWl1C1ILiCoAU5wZZ4q1P3qeS6Eg==} engines: {node: '>=18'} cpu: [ia32] os: [win32] + '@esbuild/win32-x64@0.21.5': + resolution: {integrity: sha512-tQd/1efJuzPC6rCFwEvLtci/xNFcTZknmXs98FYDfGE4wP9ClFV98nyKrzJKVPMhdDnjzLhdUyMX4PsQAPjwIw==} + engines: {node: '>=12'} + cpu: [x64] + os: [win32] + '@esbuild/win32-x64@0.28.1': resolution: {integrity: sha512-bm4Mowrv+GXMlpWX++EcXw/iLyd1o3+bJkC2DkWXYVvgZCqD/bSj9ctZeAMC3cIxgjRVR2Dufaiu4YPxr5gW1A==} engines: {node: '>=18'} @@ -2148,6 +2418,9 @@ packages: resolution: {integrity: sha512-bV0Tgo9K4hfPCek+aMAn81RppFKv2ySDQeMoSZuvTASywNTnVJCArCZE2FWqpvIatKu7VMRLWlR1EazvVhDyhQ==} engines: {node: '>=18.18'} + '@iconify-json/simple-icons@1.2.89': + resolution: {integrity: sha512-hRaCY5s2G5oWAIhc4LCGYn6g6RrwLL4zhoLOT+KUO3joVCxVlZKA+839bv/47Nbe9/ZD4UA6dznZ4XPYcI53wA==} + '@iconify/types@2.0.0': resolution: {integrity: sha512-+wluvCrRhXrhyOmRDJ3q8mux9JkKy5SJ/v8ol2tu4FVjyYvtEzkc/3pK15ET6RKg4b4w4BmTk1+gsCUhf21Ykg==} @@ -2167,6 +2440,9 @@ packages: '@jridgewell/trace-mapping@0.3.31': resolution: {integrity: sha512-zzNR+SdQSDJzc8joaeP8QQoCQr8NuYx2dIIytl1QeBEZHJ9uW6hebsrYgbz8hJwUQao3TWCMtmfV8Nu1twOLAw==} + '@mermaid-js/mermaid-mindmap@9.3.0': + resolution: {integrity: sha512-IhtYSVBBRYviH1Ehu8gk69pMDF8DSRqXBRDMWrEfHoaMruHeaP2DXA3PBnuwsMaCdPQhlUUcy/7DBLAEIXvCAw==} + '@mermaid-js/parser@1.2.0': resolution: {integrity: sha512-oYPyv8A4As1yH5Bx+04iQEQxXuIQDe0GKCNSRgao6z8AM9jixXIfP0vsppRLvGf+nKIOb9/LdpWA4YuJiVvESA==} @@ -2645,6 +2921,168 @@ packages: '@rolldown/pluginutils@1.0.1': resolution: {integrity: sha512-2j9bGt5Jh8hj+vPtgzPtl72j0yRxHAyumoo6TNfAjsLB04UtpSvPbPcDcBMxz7n+9CYB0c1GxQFxYRg2jimqGw==} + '@rollup/rollup-android-arm-eabi@4.62.2': + resolution: {integrity: sha512-6o7ZLZK+BeenkZCFNDXqpbjw9bD6nuWonvS/lwQJp7NoVVxm6p3qE7qQ5jGuBjiFsgvqjD8mZAU5oWxTmbOeOg==} + cpu: [arm] + os: [android] + + '@rollup/rollup-android-arm64@4.62.2': + resolution: {integrity: sha512-BaH7BllCACHoH1LguOU56UItGfUWjujlO65kS9LAodViaN4bwIKd7oeW/ZHJ/4ljr/7MIiENnNy3HJ0zXv8Zkw==} + cpu: [arm64] + os: [android] + + '@rollup/rollup-darwin-arm64@4.62.2': + resolution: {integrity: sha512-v39RCCvj4He82I9sFmk+M1VZ0PLM9sfsLVikjfx2hYBNALhrrOR2D3JjQA6AhlaSOgcR+RzrKY7e1+bT6SUO/A==} + cpu: [arm64] + os: [darwin] + + '@rollup/rollup-darwin-x64@4.62.2': + resolution: {integrity: sha512-yl0y2vq3S3lHeuXhEdss6TWfKW8vkujImO12tn4ZkG/4oghr09LvdYm2RElVjokTQiUvDUGXLGsYeLqUMCKpGA==} + cpu: [x64] + os: [darwin] + + '@rollup/rollup-freebsd-arm64@4.62.2': + resolution: {integrity: sha512-tT4pvt4qXD+vEoezupCWi+a1F0vvDiksiHc+PxRlYTOH1I6/X4id9jPxTP+Fg+545euaFT1jJVs4CEdHZAU1vw==} + cpu: [arm64] + os: [freebsd] + + '@rollup/rollup-freebsd-x64@4.62.2': + resolution: {integrity: sha512-6nU5F2wCW+qvCBhTn1pdIU3bzsIoF7EUwsCDRxilWGprQR6yd508YnH9+OKFCwpfS8pjZqDUmnCAr7exax0XCg==} + cpu: [x64] + os: [freebsd] + + '@rollup/rollup-linux-arm-gnueabihf@4.62.2': + resolution: {integrity: sha512-n1GJHPOvpIfhi3TmrCeh6S6URt9BFCt0KQE3qvexyGCTAKpR4Lg+eWvNZEqu7epxwus/8ElT3hacYEucm49SZg==} + cpu: [arm] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-arm-musleabihf@4.62.2': + resolution: {integrity: sha512-JqgflS8wEB+UXV/vS1RpRbifGBeN4D5lz8D8oOFbFZw4vedvdOgCFAjfBmIMdW3yL10XpQQ0Ambepw6MXrhOnA==} + cpu: [arm] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-arm64-gnu@4.62.2': + resolution: {integrity: sha512-wnFJkogWvN4jm/hQRF2UBaeUmk20j5+DmHvoyWii2b8HJDyvz1MF2OU/6ynXt2KR63rbZLWkFpoytpdc/yBuSA==} + cpu: [arm64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-arm64-musl@4.62.2': + resolution: {integrity: sha512-HVu2bp0zhvJ8xHEV9+UUs7S90VadmBSY3LcIMvozbPo4AuMGDWlz3ymHLHZPX4hR67TKTt8Qp5PJ5RBg/i+RMQ==} + cpu: [arm64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-loong64-gnu@4.62.2': + resolution: {integrity: sha512-mQqqAV8QaoSgr9I2fKDLY2BAVvmKjWoGiu/cSYQonsLvtqwEn1E4QYfnCOcp5zoEqNhsDYin1s6jx/VJmrxlZg==} + cpu: [loong64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-loong64-musl@4.62.2': + resolution: {integrity: sha512-IxKLoxCQ2IWi6bT2akyDUBGsOImDKB+sPp4EsTmwFQ/fMwpCKm8uLSSgP/Kx/QYUgKis6SEZ5/Nlhup0DIA0PQ==} + cpu: [loong64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-ppc64-gnu@4.62.2': + resolution: {integrity: sha512-Mk5ha2RQSgyFfmYYLkBpPnUk8D8FriBxesO1u9O75X0mHgXL1UQcH5Itl2lurWL2tj0RxV9b9tJgipac0hRY9A==} + cpu: [ppc64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-ppc64-musl@4.62.2': + resolution: {integrity: sha512-CjvEnqJL/0/TQ3TXX3OPIJ/kmBellrWd4heXUmHeJlTnmwjKpSJzoehLaL6Xk0ZnMHBu9dZuFADNOrtjF4v+2w==} + cpu: [ppc64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-riscv64-gnu@4.62.2': + resolution: {integrity: sha512-1SiZbzwdkaDURsew/tSOrooKiYy7EQGT6m8ufavAi9NEyQb/6VuIxFXAL1fqa4iZe3g4NbNk4P7J32z2tw5Mgg==} + cpu: [riscv64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-riscv64-musl@4.62.2': + resolution: {integrity: sha512-nQts12zJ3NQRoE6uYljOH89v7szzLDvG2JD/vsX+vGXU8w/At1GowTZ5/7qeFQ8m7L55rpR8Okugnuo5bgjy2Q==} + cpu: [riscv64] + os: [linux] + libc: [musl] + + '@rollup/rollup-linux-s390x-gnu@4.62.2': + resolution: {integrity: sha512-E9/ll019jhPIJgpzfZoIkBGhcz+kKNgVWYRY0zr9srBdPPFVpvOKW8VaJKUbeK+eZXyQF9ltME+Kk6affeaPgg==} + cpu: [s390x] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-x64-gnu@4.62.2': + resolution: {integrity: sha512-5BqxR/pshjey51iliyzTD5Xi3EN0aLmQ2lZ3lvefVV9c82BvrLo2/6OT55iifpWBufs6kdwWbuOKS841DrmK9A==} + cpu: [x64] + os: [linux] + libc: [glibc] + + '@rollup/rollup-linux-x64-musl@4.62.2': + resolution: {integrity: sha512-uNN83XxQrRAh/w0/pmAfibcwyb6YWt4gP+dpnQKPVJshAloQ785ii8CT8ZCIxkGg9opVsvAlGhFitSm6D1Jjpg==} + cpu: [x64] + os: [linux] + libc: [musl] + + '@rollup/rollup-openbsd-x64@4.62.2': + resolution: {integrity: sha512-srjEIxSH3LRnJN6THczDHWQplqEMFiAJrTab0msUryh9kwNpkICf3Ea6q6MN/2cZwRFUNx5w+h6Hpi4QuHS6Zg==} + cpu: [x64] + os: [openbsd] + + '@rollup/rollup-openharmony-arm64@4.62.2': + resolution: {integrity: sha512-8hOJnxgbyObnCm5AlRA3A931xX19xq80RjVTKgJOvEKWqJruP/Uf12IbAOaDjjEXYRewwHLfmF0YRIdK3OwKWA==} + cpu: [arm64] + os: [openharmony] + + '@rollup/rollup-win32-arm64-msvc@4.62.2': + resolution: {integrity: sha512-mmF4AY1i0hG/bLWUctUq59gtmgaSIRa3cu/A3JFRp/sCNEme2bgDEiDS22P9FbnJB8NJNF4jPJiSP5RHQpUTDg==} + cpu: [arm64] + os: [win32] + + '@rollup/rollup-win32-ia32-msvc@4.62.2': + resolution: {integrity: sha512-DZgkknc6jhHrk46V25vbAM0zZkyP0nSDkJB8/dRkLTxv470dOmWDqGoEJl/9A0dFfS7yE3REOwNDxpHwSLSt0Q==} + cpu: [ia32] + os: [win32] + + '@rollup/rollup-win32-x64-gnu@4.62.2': + resolution: {integrity: sha512-T6xr6ucWSFto+VGajA8YH26LdpHRuP4YLHEKAtCWvJDOlnmWcDZVCI2Jmjr+IFHDlt2zRaTAKE4tfjTaWLgJBg==} + cpu: [x64] + os: [win32] + + '@rollup/rollup-win32-x64-msvc@4.62.2': + resolution: {integrity: sha512-BfzEnDJOt9T8M989/lA37EcJgat01wLRnoi5dQf3QzOH7jzpqTAzdDbVfRljVr5r+jzKqpbHeyOfAaXxAd0PAA==} + cpu: [x64] + os: [win32] + + '@shikijs/core@2.5.0': + resolution: {integrity: sha512-uu/8RExTKtavlpH7XqnVYBrfBkUc20ngXiX9NSrBhOVZYv/7XQRKUyhtkeflY5QsxC0GbJThCerruZfsUaSldg==} + + '@shikijs/engine-javascript@2.5.0': + resolution: {integrity: sha512-VjnOpnQf8WuCEZtNUdjjwGUbtAVKuZkVQ/5cHy/tojVVRIRtlWMYVjyWhxOmIq05AlSOv72z7hRNRGVBgQOl0w==} + + '@shikijs/engine-oniguruma@2.5.0': + resolution: {integrity: sha512-pGd1wRATzbo/uatrCIILlAdFVKdxImWJGQ5rFiB5VZi2ve5xj3Ax9jny8QvkaV93btQEwR/rSz5ERFpC5mKNIw==} + + '@shikijs/langs@2.5.0': + resolution: {integrity: sha512-Qfrrt5OsNH5R+5tJ/3uYBBZv3SuGmnRPejV9IlIbFH3HTGLDlkqgHymAlzklVmKBjAaVmkPkyikAV/sQ1wSL+w==} + + '@shikijs/themes@2.5.0': + resolution: {integrity: sha512-wGrk+R8tJnO0VMzmUExHR+QdSaPUl/NKs+a4cQQRWyoc3YFbUzuLEi/KWK1hj+8BfHRKm2jNhhJck1dfstJpiw==} + + '@shikijs/transformers@2.5.0': + resolution: {integrity: sha512-SI494W5X60CaUwgi8u4q4m4s3YAFSxln3tzNjOSYqq54wlVgz0/NbbXEb3mdLbqMBztcmS7bVTaEd2w0qMmfeg==} + + '@shikijs/types@2.5.0': + resolution: {integrity: sha512-ygl5yhxki9ZLNuNpPitBWvcy9fsSKKaRuO4BAlMyagszQidxcpLAr0qiW/q43DtSIDxO6hEbtYLiFZNXO/hdGw==} + + '@shikijs/vscode-textmate@10.0.2': + resolution: {integrity: sha512-83yeghZ2xxin3Nj8z1NMd/NCuca+gsYXswywDy5bHvwlWL8tpTQmzGeUuHd9FC3E/SBEMvzJRwWEOz5gGes9Qg==} + '@smithy/core@3.24.7': resolution: {integrity: sha512-KoUi4M1f3BG6kzN1FnCwL7oyFptTbyBJKjR6yhSib+JHRdUmM1o+VwsFtJ66NZCkCzVfJMWRHJNo0R0jznp0Pg==} engines: {node: '>=18.0.0'} @@ -2811,6 +3249,9 @@ packages: '@types/geojson@7946.0.16': resolution: {integrity: sha512-6C8nqWur3j98U6+lXDfTUWIfgvZU+EumvpHKcYjujKH7woYyLj2sUmff0tRhrqM7BohUw7Pz3ZB1jj2gW9Fvmg==} + '@types/hast@3.0.5': + resolution: {integrity: sha512-rp/ezSWaD1m44dPKICGhiskI13nVr7qTloFwDa/IYkhhf5nzwP+zIQcIJh3WIFSBOy/H1PzB40jPjMDksN4F+g==} + '@types/jsdom@28.0.3': resolution: {integrity: sha512-/HQ2uFoetFTXuye8vzIcHw2z6Fwi7Hi/qcgC+RoS9NCyewiqxhVGqlG+ViGB6lkax481R6dmhf1I7lIGlzJStQ==} @@ -2820,9 +3261,18 @@ packages: '@types/json-schema@7.0.15': resolution: {integrity: sha512-5+fP8P8MFNC+AyZCDxrB2pkZFPGzqQWUzpSeuuVLvm8VMcorNYavBqoFcxK8bQz4Qsbn4oUEEem4wDLfcysGHA==} + '@types/linkify-it@5.0.0': + resolution: {integrity: sha512-sVDA58zAw4eWAffKOaQH5/5j3XeayukzDk+ewSsnv3p4yJEZHCCzMDiZM8e0OUrRvmpGZ85jf4yDHkHsgBNr9Q==} + + '@types/markdown-it@14.1.2': + resolution: {integrity: sha512-promo4eFwuiW+TfGxhi+0x3czqTYJkG8qB17ZUJiVF10Xm7NLVRSLUsfRTU/6h1e24VvRnXCx+hG7li58lkzog==} + '@types/mdast@4.0.4': resolution: {integrity: sha512-kGaNbPh1k7AFzgpud/gMdvIm5xuECykRR+JnWKQno9TAXVa6WIVCGTPvYGekIDL4uwCZQSYbUxNBSb1aUo79oA==} + '@types/mdurl@2.0.0': + resolution: {integrity: sha512-RGdgjQUZba5p6QEFAVx2OGb8rQDL/cPRG7GiedRzMcJ1tYnUANBncjbSB1NRGwbvjcPeikRABz2nshyPk1bhWg==} + '@types/ms@2.1.0': resolution: {integrity: sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA==} @@ -2847,6 +3297,9 @@ packages: '@types/unist@3.0.3': resolution: {integrity: sha512-ko/gIFJRv177XgZsZcBwnqJN5x/Gien8qNOn0D5bQU/zAzVf9Zt3BlcUiLqhV9y4ARk0GbT3tnUiPNgnTXzc/Q==} + '@types/web-bluetooth@0.0.21': + resolution: {integrity: sha512-oIQLCGWtcFZy2JW77j9k8nHzAOpqMHLQejDA48XXMWH6tjCQHz5RCFz1bzsmROyL6PUm+LLnUiI4BCn221inxA==} + '@typescript-eslint/eslint-plugin@8.61.0': resolution: {integrity: sha512-bFNvl9ZczlVb+wR2Akszf3gHfKVj/8WanXaGJ3UstTA7brNKg0cNdk6X1Psu5V7MZ2oQtzZKOEzIUehaoxbDGw==} engines: {node: ^18.18.0 || ^20.9.0 || >=21.1.0} @@ -2906,9 +3359,19 @@ packages: resolution: {integrity: sha512-QVLZu3ZPQEE+HICQyAMZ2yLQhxf0meY/wx6Hx14YcTNj13JB3qHlX3lJ02L3fLGHgERRH71kvYDwiXIguT3AjQ==} engines: {node: ^18.18.0 || ^20.9.0 || >=21.1.0} + '@ungap/structured-clone@1.3.3': + resolution: {integrity: sha512-60YRaenCQcVjYEKOcG824+DRGGIQ3VKErcBoAEDJZz5bKIs2ZG+X/H9Nk+Q6EVkwJk5QNApxbrc5QtBSwtrXAg==} + '@upsetjs/venn.js@2.0.0': resolution: {integrity: sha512-WbBhLrooyePuQ1VZxrJjtLvTc4NVfpOyKx0sKqioq9bX1C1m7Jgykkn8gLrtwumBioXIqam8DLxp88Adbue6Hw==} + '@vitejs/plugin-vue@5.2.4': + resolution: {integrity: sha512-7Yx/SXSOcQq5HiiV3orevHUFn+pmMB4cgbEkDYgnkUWb0WfeQ/wa2yFv6D5ICiCQOVpjA7vYDXrC7AGO8yjDHA==} + engines: {node: ^18.0.0 || >=20.0.0} + peerDependencies: + vite: ^5.0.0 || ^6.0.0 + vue: ^3.2.25 + '@vitest/coverage-v8@4.1.8': resolution: {integrity: sha512-lt3kovsyHwYe00wq4D1ti0Z974fWj4NLp6siqiyEufUpyFwK9Yhi7rBhac9JL5aA0zoMrJqc4vYPZRUnI7l7nw==} peerDependencies: @@ -2947,6 +3410,94 @@ packages: '@vitest/utils@4.1.8': resolution: {integrity: sha512-uOJamYALNhfJ6iolExyQM40yIQwDqYnkKtQ5VCiSe17E33H0aQ/u+1GlRuz4LZBk6Mm3sg90G9hEbmEt37C1Zg==} + '@vue/compiler-core@3.5.39': + resolution: {integrity: sha512-16KBTEXAJCpDr0mwlw+AZyhu8iyC7R3S2vBwsI7QnWJU6X3WKc9VKeNEZpiMdZ569qWhz9574L3vV55qRL0Vtw==} + + '@vue/compiler-dom@3.5.39': + resolution: {integrity: sha512-oQPigALqYbNxTNPvNgSOe+czwVExfbVF02lz8jP0S3AXJiu3jxYDygNUiqSep4ezzW8XgnubqH63My2A7JR/vg==} + + '@vue/compiler-sfc@3.5.39': + resolution: {integrity: sha512-d0ki86iOyN8LoZPBmk5SJWNwHP19CnDDCfuo//+2WJa2g5Ke0Jay983PIBIcSSzldC68I8DrD5GrHV3OSDfodg==} + + '@vue/compiler-ssr@3.5.39': + resolution: {integrity: sha512-Ce7/wvwMHai74bdszfXExdazFigYnlF9zgCmEQUcM1j0fOymlouZ7XilTYNo8oUjhlnjYOZbGrcYKuqjz89Ucw==} + + '@vue/devtools-api@7.7.10': + resolution: {integrity: sha512-KxtEpUOOpFz/qOGRrAwA36QF7DqIA+FXgCYit9mk9wjbaZt0sXOFz81ElOZtKA4HbWHUdwNjZHBFsFFyp5BZiA==} + + '@vue/devtools-kit@7.7.10': + resolution: {integrity: sha512-3WNi2Kq4tbpVbmhml7RiphmAt0279oh3fKNeWMQIrltfX8Q91b4i5PL8DtyNKdwmcsGrV4fg+erwWOmD05CLIw==} + + '@vue/devtools-shared@7.7.10': + resolution: {integrity: sha512-wOPslzB8vTvpxwdaOcR2qAbwmuSP0L+rhpoC6Cf56V3Jip+HWb7PQQXOUPgBNQARpXsbQX/+mvi8kKucmBGRwQ==} + + '@vue/reactivity@3.5.39': + resolution: {integrity: sha512-TpsuBJ9gGlZa5d23XcM2y8EXanz9dZeVDQBXRwzy46ItgvM+rWpzs+UVM0wcRLxGvcav0HE5jz2gNL53xlRAog==} + + '@vue/runtime-core@3.5.39': + resolution: {integrity: sha512-9GLtNyRvPAUMbX+7ono0RC2j0guo2LXVi8LvcmAooImACUKm0oFf0jjwbX8/H0AE/t1nxhAkn8RSl9PMCzzxZw==} + + '@vue/runtime-dom@3.5.39': + resolution: {integrity: sha512-7Y6aAGboKcXAZ3ECuUy7RrS5yy2r47dhTp2SKaJmYxjopImaVFaNa5Ne66NwGovsrxVAl5S5rwc7m22UG7Lmww==} + + '@vue/server-renderer@3.5.39': + resolution: {integrity: sha512-yZSakiAGw85rZfG7UM8akMnIF+FmeiNk47uvHf2nVBBSe+dIKUhZuZq9+XgJhbV3nS5Z4ALH23/MpXofW+mbcw==} + peerDependencies: + vue: 3.5.39 + + '@vue/shared@3.5.39': + resolution: {integrity: sha512-l1rrBtBfTnmxvtsvdQDXltUUy8S1Y+ZaqdfUzmAnJkTd8Z8rv5v/ytW+TKiqEOWyHPoqtPlNFSs0lhRmYVSHVA==} + + '@vueuse/core@12.8.2': + resolution: {integrity: sha512-HbvCmZdzAu3VGi/pWYm5Ut+Kd9mn1ZHnn4L5G8kOQTPs/IwIAmJoBrmYk2ckLArgMXZj0AW3n5CAejLUO+PhdQ==} + + '@vueuse/integrations@12.8.2': + resolution: {integrity: sha512-fbGYivgK5uBTRt7p5F3zy6VrETlV9RtZjBqd1/HxGdjdckBgBM4ugP8LHpjolqTj14TXTxSK1ZfgPbHYyGuH7g==} + peerDependencies: + async-validator: ^4 + axios: ^1 + change-case: ^5 + drauu: ^0.4 + focus-trap: ^7 + fuse.js: ^7 + idb-keyval: ^6 + jwt-decode: ^4 + nprogress: ^0.2 + qrcode: ^1.5 + sortablejs: ^1 + universal-cookie: ^7 + peerDependenciesMeta: + async-validator: + optional: true + axios: + optional: true + change-case: + optional: true + drauu: + optional: true + focus-trap: + optional: true + fuse.js: + optional: true + idb-keyval: + optional: true + jwt-decode: + optional: true + nprogress: + optional: true + qrcode: + optional: true + sortablejs: + optional: true + universal-cookie: + optional: true + + '@vueuse/metadata@12.8.2': + resolution: {integrity: sha512-rAyLGEuoBJ/Il5AmFHiziCPdQzRt88VxR+Y/A/QhJ1EWtWqPBBAxTAFaSkviwEuOEZNtW8pvkPgoCZQ+HxqW1A==} + + '@vueuse/shared@12.8.2': + resolution: {integrity: sha512-dznP38YzxZoNloI0qpEfpkms8knDtaoQ6Y/sfS0L7Yki4zh40LFHEhur0odJC6xTHG5dxWVPiUWBXn+wCG2s5w==} + acorn-jsx@5.3.2: resolution: {integrity: sha512-rq9s+JNhf0IChjtDXxllJ7g41oZk5SlXtp0LHwyA5cejwn7vKmKp4pPri6YEePv2PU65sAsegbXtIinmDFDXgQ==} peerDependencies: @@ -2964,6 +3515,10 @@ packages: ajv@6.15.0: resolution: {integrity: sha512-fgFx7Hfoq60ytK2c7DhnF8jIvzYgOMxfugjLOSMHjLIPgenqa7S7oaagATUq99mV6IYvN2tRmC0wnTYX6iPbMw==} + algoliasearch@5.55.2: + resolution: {integrity: sha512-OyacJsaeuLUvGWOynNqYc6sx88XvyoG39wMT8SYqL3l9wwaorDW/LPRbUPfhzw0bWsUWzNCZTnFYOrWFBKsUaw==} + engines: {node: '>= 14.0.0'} + ansis@4.3.1: resolution: {integrity: sha512-BJ8/l4R5LRE7hW9WdSuGYrLSHi2ynxeFpDFbH0K/CgNeY/tyhk+vO6TYxXC5r5CpUhNVX310xzPsN/H9lCdfOA==} engines: {node: '>=14'} @@ -2998,6 +3553,9 @@ packages: bignumber.js@9.3.1: resolution: {integrity: sha512-Ko0uX15oIUS7wJ3Rb30Fs6SkVbLmPBAKdlm7q9+ak9bbIeFf0MwuBsQV6z7+X768/cHsfg+WlysDWJcmthjsjQ==} + birpc@2.9.0: + resolution: {integrity: sha512-KrayHS5pBi69Xi9JmvoqrIgYGDkD6mcSe/i6YKi3w5kekCLzrX4+nawcXqrj2tIp50Kw/mT/s3p+GVK0A0sKxw==} + birpc@4.0.0: resolution: {integrity: sha512-LShSxJP0KTmd101b6DRyGBj57LZxSDYWKitQNW/mi8GRMvZb078Uf9+pveax1DrVL89vm7mWe+TovdI/UDOuPw==} @@ -3022,6 +3580,12 @@ packages: resolution: {integrity: sha512-NUPRluOfOiTKBKvWPtSD4PhFvWCqOi0BGStNWs57X9js7XGTprSmFoz5F0tWhR4WPjNeR9jXqdC7/UpSJTnlRg==} engines: {node: '>=18'} + character-entities-html4@2.1.0: + resolution: {integrity: sha512-1v7fgQRj6hnSwFpq1Eu0ynr/CDEw0rXo2B61qXrLNdHZmPKgb7fqS1a2JwF0rISo9q77jDI8VMEHoApn8qDoZA==} + + character-entities-legacy@3.0.0: + resolution: {integrity: sha512-RpPp0asT/6ufRm//AJVwpViZbGM/MkjQFxJccQRHmISF/22NBtsHqAWmL+/pmkPWoIUJdWyeVleTl1wydHATVQ==} + character-entities@2.0.2: resolution: {integrity: sha512-shx7oQ0Awen/BRIdkjkvz54PnEEI/EjwXDSIZp86/KKdbafHh1Df/RYGBhn4hbe2+uKC9FnT5UCEdyPz3ai9hQ==} @@ -3029,6 +3593,9 @@ packages: resolution: {integrity: sha512-Qgzu8kfBvo+cA4962jnP1KkS6Dop5NS6g7R5LFYJr4b8Ub94PPQXUksCw9PvXoeXPRRddRNC5C1JQUR2SMGtnA==} engines: {node: '>= 14.16.0'} + comma-separated-tokens@2.0.3: + resolution: {integrity: sha512-Fu4hJdvzeylCfQPp9SGWidpzrMs7tTrlu6Vb8XGaRGck8QSNZJJp538Wrb60Lax4fPwR64ViY468OIUTbRlGZg==} + commander@7.2.0: resolution: {integrity: sha512-QrWXB+ZQSVPmIWIhtEO9H+gwHaMGYiF5ChvoJ+K9ZGHG/sVsa6yiesAD1GC/x46sET00Xlwo1u49RVVVzvcSkw==} engines: {node: '>= 10'} @@ -3040,6 +3607,10 @@ packages: convert-source-map@2.0.0: resolution: {integrity: sha512-Kvp459HrV2FEJ1CAsi1Ku+MY3kasH19TFykTz2xWmMeq6bk2NU3XXvfJ+Q61m0xktWwt+1HSYf3JZsTms3aRJg==} + copy-anything@4.0.5: + resolution: {integrity: sha512-7Vv6asjS4gMOuILabD3l739tsaxFQmC+a7pLZm02zyvs8p977bL3zEgq3yDk5rn9B0PbYgIv++jmHcuUab4RhA==} + engines: {node: '>=18'} + cordis@4.0.0-rc.6: resolution: {integrity: sha512-GzUv7zCKh3FlgM3/Ad2S03UpYO3v4u1GcKa7ig4K2je4lCrgJ/S64ziiZI6XNyKEa1tZwdzj4oBQrhYDLgfEiA==} hasBin: true @@ -3069,6 +3640,9 @@ packages: resolution: {integrity: sha512-X7sjQzceUhu1u7Y/ylrRZFU2FS6LRiFVp6rKLPg23y3x3c3DOKAwuXGDp+PAGjh6CSnCjYeAul8pcT8bAl+lSA==} engines: {node: ^10 || ^12.20.0 || ^14.13.0 || >=15.0.0} + csstype@3.2.3: + resolution: {integrity: sha512-z1HGKcYy2xA8AGQfwrn0PAy+PB7X/GSj3UVJW9qKyn43xWa+gl5nXmU4qqLMRzWVLFC8KusUX8T/0kCiOYpAIQ==} + cytoscape-cose-bilkent@4.1.0: resolution: {integrity: sha512-wgQlVIUJF13Quxiv5e1gstZ08rnZj2XaLHGoFMYXz7SkNfCDOOteKBE6SYRfA9WxxI/iBc3ajfDoc6hb/MRAHQ==} peerDependencies: @@ -3290,10 +3864,17 @@ packages: ecdsa-sig-formatter@1.0.11: resolution: {integrity: sha512-nagl3RYrbNv6kQkeJIpt6NJZy8twLB/2vtz6yN9Z4vRKHN4/QZJIEbqohALSgwKdnksuY3k5Addp5lg8sVoVcQ==} + emoji-regex-xs@1.0.0: + resolution: {integrity: sha512-LRlerrMYoIDrT6jgpeZ2YYl/L8EulRTt5hQcYjy5AInh7HWXKimpqx68aknBFpGL2+/IcogTcaydJEgaTmOpDg==} + empathic@2.0.1: resolution: {integrity: sha512-YGRs8knHhKHVShLkFET/rWAU8kmHbOV5LwN938RHI0pljAJ1Gf6SzXsSmRaEzcXTtOOmVqJ5+WtQPL5uigY50Q==} engines: {node: '>=14'} + entities@7.0.1: + resolution: {integrity: sha512-TWrgLOFUQTH994YUyl1yT4uyavY5nNB5muff+RtWaqNVCAK408b5ZnnbNAUEWLTCpum9w6arT70i1XdQ4UeOPA==} + engines: {node: '>=0.12'} + entities@8.0.0: resolution: {integrity: sha512-zwfzJecQ/Uej6tusMqwAqU/6KL2XaB2VZ2Jg54Je6ahNBGNH6Ek6g3jjNCF0fG9EWQKGZNddNjU5F1ZQn/sBnA==} engines: {node: '>=20.19.0'} @@ -3304,6 +3885,11 @@ packages: es-toolkit@1.49.0: resolution: {integrity: sha512-G5iZ6Pc/FNRY/soKZHC+TxGDD83rHUDXxzaWhGCX44vAv/tMs56WMusnm/KMNK+luUPsgA9U28cGr4RDlSzL2g==} + esbuild@0.21.5: + resolution: {integrity: sha512-mg3OPMV4hXywwpoDxu3Qda5xCKQi+vCTZq8S9J/EpkhB2HzKXq4SNFZE3+NK93JYxc8VMSep+lOUSC/RVKaBqw==} + engines: {node: '>=12'} + hasBin: true + esbuild@0.28.1: resolution: {integrity: sha512-HrJrvZv5ayxBzPfwphOoNzkzOIIlifzk0KJrGK2c8R4+LKpMtpYLQeUdjnwjWv/LZlkH2laZk+4w78pi99D4Vw==} engines: {node: '>=18'} @@ -3363,6 +3949,9 @@ packages: resolution: {integrity: sha512-MMdARuVEQziNTeJD8DgMqmhwR11BRQ/cBP+pLtYdSTnf3MIO8fFeiINEbX36ZdNlfU/7A9f3gUw49B3oQsvwBA==} engines: {node: '>=4.0'} + estree-walker@2.0.2: + resolution: {integrity: sha512-Rfkk/Mp/DL7JVje3u18FxFujQlTNR2q6QfMSMB7AvCBx91NGj/ba3kCfza0f6dVDbw7YlRf/nDrn7pQrCCyQ/w==} + estree-walker@3.0.3: resolution: {integrity: sha512-7RUKfXgSMMkzt6ZuXmqapOurLGPPfgj6l9uRZ7lRGolvk0y2yocc35LdcxKC5PQZdn2DMqioAQ2NoWcrTKmm6g==} @@ -3428,6 +4017,9 @@ packages: flatted@3.4.2: resolution: {integrity: sha512-PjDse7RzhcPkIJwy5t7KPWQSZ9cAbzQXcafsetQoD7sOJRQlGikNbx7yZp2OotDnJyrDcbyRq3Ttb18iYOqkxA==} + focus-trap@7.8.0: + resolution: {integrity: sha512-/yNdlIkpWbM0ptxno3ONTuf+2g318kh2ez3KSeZN5dZ8YC6AAmgeWz+GasYYiBJPFaYcSAPeu4GfhUaChzIJXA==} + formatly@0.3.0: resolution: {integrity: sha512-9XNj/o4wrRFyhSMJOvsuyMwy8aUfBaZ1VrqHVfohyXf0Sw0e+yfKG+xZaY3arGCOMdwFsqObtzVOc1gU9KiT9w==} engines: {node: '>=18.3.0'} @@ -3479,6 +4071,15 @@ packages: resolution: {integrity: sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==} engines: {node: '>=8'} + hast-util-to-html@9.0.5: + resolution: {integrity: sha512-OguPdidb+fbHQSU4Q4ZiLKnzWo8Wwsf5bZfbvu7//a9oTYoqD/fWpe96NuHkoS9h0ccGOTe0C4NGXdtS0iObOw==} + + hast-util-whitespace@3.0.0: + resolution: {integrity: sha512-88JUN06ipLwsnv+dVn+OIYOvAuvBMy/Qoi6O7mQHxdPXpjy+Cd6xRkWwux7DKO+4sYILtLBRIKgsdpS2gQc7qw==} + + hookable@5.5.3: + resolution: {integrity: sha512-Yc+BQe8SvoXH1643Qez1zqLRmbA5rCL+sSmk6TVos0LWVfNIB7PGncdlId77WzLGSIB5KaWgTaNTs2lNVEI6VQ==} + hookable@6.1.1: resolution: {integrity: sha512-U9LYDy1CwhMCnprUfeAZWZGByVbhd54hwepegYTK7Pi5NvqEj63ifz5z+xukznehT7i6NIZRu89Ay1AZmRsLEQ==} @@ -3489,6 +4090,9 @@ packages: html-escaper@2.0.2: resolution: {integrity: sha512-H2iMtd0I4Mt5eYiapRdIDjp+XzelXQ0tFE4JS7YFwFevXXMmOp9myNrUvCg0D6ws8iqkRPBfKHgbwig1SmlLfg==} + html-void-elements@3.0.0: + resolution: {integrity: sha512-bEqo66MRXsUGxWHV5IP0PUiAWwoEjba4VCzg0LjFJBpchPaTfyfCKTG6bc5F8ucKec3q5y6qOdGyYTSBEvhCrg==} + http-proxy-agent@7.0.2: resolution: {integrity: sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==} engines: {node: '>= 14'} @@ -3538,6 +4142,10 @@ packages: is-potential-custom-element-name@1.0.1: resolution: {integrity: sha512-bCYeRA2rVibKZd+s2625gGnGF/t7DSqDs4dP7CrLA1m7jKWz6pps0LpYLJN8Q64HtmPKJ1hrN3nzPNKFEKOUiQ==} + is-what@5.5.0: + resolution: {integrity: sha512-oG7cgbmg5kLYae2N5IVd3jm2s+vldjxJzK1pcu9LfpGuQ93MQSzo0okvRna+7y5ifrD+20FE8FvjusyGaz14fw==} + engines: {node: '>=18'} + isexe@2.0.0: resolution: {integrity: sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==} @@ -3783,6 +4391,9 @@ packages: resolution: {integrity: sha512-hXdUTZYIVOt1Ex//jAQi+wTZZpUpwBj/0QsOzqegb3rGMMeJiSEu5xLHnYfBrRV4RH2+OCSOO95Is/7x1WJ4bw==} engines: {node: '>=10'} + mark.js@8.11.1: + resolution: {integrity: sha512-1I+1qpDt4idfgLQG+BNWmrqku+7/2bi5nLf4YwF8y8zXvmfiTBY3PV3ZibfrjBueCByROpuBjLLFCajqkgYoLQ==} + markdown-table@3.0.4: resolution: {integrity: sha512-wiYz4+JrLyb/DqW2hkFJxP7Vd7JuTDm77fvbM8VfEQdmSMqcImWeeRbHwZjBjIFki/VaMK2BhFi7oUUZeM5bqw==} @@ -3818,6 +4429,9 @@ packages: mdast-util-phrasing@4.1.0: resolution: {integrity: sha512-TqICwyvJJpBwvGAMZjj4J2n0X8QWp21b9l0o7eXyVJ25YNWYbJDVIyD1bZXE6WtV6RmKJVYmQAKWa0zWOABz2w==} + mdast-util-to-hast@13.2.1: + resolution: {integrity: sha512-cctsq2wp5vTsLIcaymblUriiTcZd0CwWtCbLvrOzYCDZoWyMNV8sZ7krj09FSnsiJi3WVsHLM4k6Dq/yaPyCXA==} + mdast-util-to-markdown@2.1.2: resolution: {integrity: sha512-xj68wMTvGXVOKonmog6LwyJKrYXZPvlwabaryTjLh9LuvovB/KAH+kvi8Gjj+7rJjsFi23nkUxRQv1KqSroMqA==} @@ -3918,6 +4532,12 @@ packages: resolution: {integrity: sha512-MULkVLfKGYDFYejP07QOurDLLQpcjk7Fw+7jXS2R2czRQzR56yHRveU5NDJEOviH+hETZKSkIk5c+T23GjFUMg==} engines: {node: 18 || 20 || >=22} + minisearch@7.2.0: + resolution: {integrity: sha512-dqT2XBYUOZOiC5t2HRnwADjhNS2cecp9u+TJRiJ1Qp/f5qjkeT5APcGPjHw+bz89Ms8Jp+cG4AlE+QZ/QnDglg==} + + mitt@3.0.1: + resolution: {integrity: sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw==} + mri@1.2.0: resolution: {integrity: sha512-tzzskb3bG8LvYGFF/mDTpq3jpI6Q9wc3LEmBaghu+DdCssd1FakN7Bc0hVNmEyGq1bq3RgfkCb3cmQLpNPOroA==} engines: {node: '>=4'} @@ -3958,10 +4578,16 @@ packages: resolution: {integrity: sha512-dRB78srN/l6gqWulah9SrxeYnxeddIG30+GOqK/9OlLVyLg3HPnr6SqOWTWOXKRwC2eGYCkZ59NNuSgvSrpgOA==} engines: {node: ^12.20.0 || ^14.13.1 || >=16.0.0} + non-layered-tidy-tree-layout@2.0.2: + resolution: {integrity: sha512-gkXMxRzUH+PB0ax9dUN0yYF0S25BqeAYqhgMaLUFmpXLEk7Fcu8f4emJuOAY0V8kjDICxROIKsTAKsV/v355xw==} + obug@2.1.3: resolution: {integrity: sha512-9miFgM2OFba7hB+pRgvtV84pYTBaoTHohvmIgiRt6dRIzbwEOIaNaP+dIlGs2fNFoB0SeISs0Jz5WFVRid6Xyg==} engines: {node: '>=12.20.0'} + oniguruma-to-es@3.1.1: + resolution: {integrity: sha512-bUH8SDvPkH3ho3dvwJwfonjlQ4R80vjyvrU8YpxuROddv55vAEJrTuCuCVUhhsHbtlD9tGGbaNApGQckXhS8iQ==} + openai@6.26.0: resolution: {integrity: sha512-zd23dbWTjiJ6sSAX6s0HrCZi41JwTA1bQVs0wLQPZ2/5o2gxOJA5wh7yOAUgwYybfhDXyhwlpeQf7Mlgx8EOCA==} hasBin: true @@ -4024,6 +4650,9 @@ packages: pathe@2.0.3: resolution: {integrity: sha512-WUjGcAqP1gQacoQe+OBJsFA7Ld4DyXuUIjZ5cc75cLHvJ7dtNsTugphxIADwspS+AraAUePCKrSVtPLFj/F88w==} + perfect-debounce@1.0.0: + resolution: {integrity: sha512-xCy9V055GLEqoFaHoC1SoLIaLmWctgCUaBaWxDZ7/Zx4CTyX7cJQLJOok/orfjZAh9kEYpjJa4d0KcJmCbctZA==} + picocolors@1.1.1: resolution: {integrity: sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA==} @@ -4041,10 +4670,21 @@ packages: resolution: {integrity: sha512-FfR8sjd4em2T6fb3I2MwAJU7HWVMr9zba+enmQeeWFfCbm+UOC/0X4DS8XtpUTMwWMGbjKYP7xjfNekzyGmB3A==} engines: {node: ^10 || ^12 || >=14} + preact@10.29.7: + resolution: {integrity: sha512-DCHYrK/B10yUD3ZjLfhZ3WIE/9Vf9VFUODcRE2dRomTYDpJk6z6L9wecSfhfE6M9ZTHUdyQkoC46arIDhEV84Q==} + peerDependencies: + preact-render-to-string: '>=5' + peerDependenciesMeta: + preact-render-to-string: + optional: true + prelude-ls@1.2.1: resolution: {integrity: sha512-vkcDPrRZo1QZLbn5RLGPpg/WmIQ65qoWWhcGKf/b5eplkkarX0m9z8ppCat4mlOqUsWpyNuYgO3VRyrYHSzX5g==} engines: {node: '>= 0.8.0'} + property-information@7.2.0: + resolution: {integrity: sha512-IAtzIB6sUiWaJYrX9smp3V46pBGbBeLFRGdh25kg1334VcBlD8HzhPeNIWQH9zhGmo2itIe25EHt9dQP7G5hmg==} + protobufjs@7.6.4: resolution: {integrity: sha512-RJJPTTpvFfHcWLkIa2JFWK4XvtSzS0yEWDmunqHXli1h3JlkbcQZXDZdcWxv+JK3Xsl5/UFDPZ0iGm7DAengYw==} engines: {node: '>=12.0.0'} @@ -4068,6 +4708,15 @@ packages: resolution: {integrity: sha512-GDhwkLfywWL2s6vEjyhri+eXmfH6j1L7JE27WhqLeYzoh/A3DBaYGEj2H/HFZCn/kMfim73FXxEJTw06WtxQwg==} engines: {node: '>= 14.18.0'} + regex-recursion@6.0.2: + resolution: {integrity: sha512-0YCaSCq2VRIebiaUviZNs0cBz1kg5kVS2UKUfNIx8YVs1cN3AV7NTctO5FOKBA+UT2BPJIWZauYHPqJODG50cg==} + + regex-utilities@2.3.0: + resolution: {integrity: sha512-8VhliFJAWRaUiVvREIiW2NXXTmHs4vMNnSzuJVhscgmGav3g9VDxLrQndI3dZZVVdp0ZO/5v0xmX516/7M9cng==} + + regex@6.1.0: + resolution: {integrity: sha512-6VwtthbV4o/7+OaAF9I5L5V3llLEsoPyq9P1JVXkedTP33c7MfCG0/5NOPcSJn0TzXcG9YUrR0gQSWioew3LDg==} + require-from-string@2.0.2: resolution: {integrity: sha512-Xf0nWe6RseziFMu+Ap9biiUbmplq6S9/p+7w7YXP/JBHhrUDDUhwa+vANyubuqfZWTveU//DYVGsDG7RKL/vEw==} engines: {node: '>=0.10.0'} @@ -4079,6 +4728,9 @@ packages: resolution: {integrity: sha512-XQBQ3I8W1Cge0Seh+6gjj03LbmRFWuoszgK9ooCpwYIrhhoO80pfq4cUkU5DkknwfOfFteRwlZ56PYOGYyFWdg==} engines: {node: '>= 4'} + rfdc@1.4.1: + resolution: {integrity: sha512-q1b3N5QkRUWUl7iyylaaj3kOpIT0N2i9MqIEQXP73GVsN9cw3fdx8X63cEmWhJGi2PPCF23Ijp7ktmd39rawIA==} + robust-predicates@3.0.3: resolution: {integrity: sha512-NS3levdsRIUOmiJ8FZWCP7LG3QpJyrs/TE0Zpf1yvZu8cAJJ6QMW92H1c7kWpdIHo8RvmLxN/o2JXTKHp74lUA==} @@ -4111,6 +4763,11 @@ packages: engines: {node: ^20.19.0 || >=22.12.0} hasBin: true + rollup@4.62.2: + resolution: {integrity: sha512-RFnrW4lhXA3s3eqHDZvN654g8OTjzRfqpIRJYczCGB6HzphckVAi/Qh4tbPUbRuDi7s1Llv8g/NspLkttY3gTA==} + engines: {node: '>=18.0.0', npm: '>=8.0.0'} + hasBin: true + roughjs@4.6.6: resolution: {integrity: sha512-ZUz/69+SYpFN/g/lUlo2FXcIjRkSu3nDarreVdGGndHEBJ6cXPdKguS8JGxwj5HA5xIbVKSmLgr5b3AWxtRfvQ==} @@ -4134,6 +4791,9 @@ packages: schemastery@3.18.0: resolution: {integrity: sha512-Jw2uxjoyyqc/yeurmChUEc/jbi8GsrdXV/KmqRUDZXJAXAmrJiPsz8vKa17l/VckyzljHZ9oGaul443CQiXxtA==} + search-insights@2.17.3: + resolution: {integrity: sha512-RQPdCYTa8A68uM2jwxoY842xDhvx3E5LFL1LxvxCNMev4o5mLuokczhzjAgGwUZBAmOKZknArSxLKmXtIi2AxQ==} + semver@7.8.4: resolution: {integrity: sha512-rUCObTnP32Q08R2uuIrt7r9PlEonuTmtuXYcW6s5kjdlj3xbnwe+21yXptAUYcMAABLkYYTtnmzb3w3EDZfueA==} engines: {node: '>=10'} @@ -4147,6 +4807,9 @@ packages: resolution: {integrity: sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==} engines: {node: '>=8'} + shiki@2.5.0: + resolution: {integrity: sha512-mI//trrsaiCIPsja5CNfsyNOqgAZUb6VpJA+340toL42UpzQlXpwRV9nch69X6gaUxrr9kaOOa6e3y3uAkGFxQ==} + siginfo@2.0.0: resolution: {integrity: sha512-ybx0WO1/8bSBLEWXZvEd7gMW3Sn3JFlW3TvX1nREbDLRNQNaeNN8WK0meBwPdAaOI7TtRRRJn/Es1zhrrCHu7g==} @@ -4158,12 +4821,22 @@ packages: resolution: {integrity: sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==} engines: {node: '>=0.10.0'} + space-separated-tokens@2.0.2: + resolution: {integrity: sha512-PEGlAwrG8yXGXRjW32fGbg66JAlOAwbObuqVoJpv/mRgoWDQfgH1wDPvtzWyUSNAXBGSk8h755YDbbcEy3SH2Q==} + + speakingurl@14.0.1: + resolution: {integrity: sha512-1POYv7uv2gXoyGFpBCmpDVSNV74IfsWlDW216UPjbWufNf+bSU6GdbDsxdcxtfwb4xlI3yxzOTKClUosxARYrQ==} + engines: {node: '>=0.10.0'} + stackback@0.0.2: resolution: {integrity: sha512-1XMJE5fQo1jGH6Y/7ebnwPOBEkIEnT4QF32d5R1+VXdXveM0IBMJt8zfaxX1P3QhVwrYe+576+jkANtSS2mBbw==} std-env@4.1.0: resolution: {integrity: sha512-Rq7ybcX2RuC55r9oaPVEW7/xu3tj8u4GeBYHBWCychFtzMIr86A7e3PPEBPT37sHStKX3+TiX/Fr/ACmJLVlLQ==} + stringify-entities@4.0.4: + resolution: {integrity: sha512-IwfBptatlO+QCJUo19AqvrPNqlVMpW9YEL2LIVY+Rpv2qsjCGxaDLNRgeGsQWJhfItebuJhsGSLjaBbNSQ+ieg==} + strip-json-comments@5.0.3: resolution: {integrity: sha512-1tB5mhVo7U+ETBKNf92xT4hrQa3pm0MZ0PQvuDnWgAAGHDsfp4lPSpiS6psrSiet87wyGPh9ft6wmhOMQ0hDiw==} engines: {node: '>=14.16'} @@ -4174,6 +4847,10 @@ packages: stylis@4.4.0: resolution: {integrity: sha512-5Z9ZpRzfuH6l/UAvCPAPUo3665Nk2wLaZU3x+TLHKVzIz33+sbJqbtrYoC3KD4/uVOr2Zp+L0LySezP9OHV9yA==} + superjson@2.2.6: + resolution: {integrity: sha512-H+ue8Zo4vJmV2nRjpx86P35lzwDT3nItnIsocgumgr0hHMQ+ZGq5vrERg9kJBo5AWGmxZDhzDo+WVIJqkB0cGA==} + engines: {node: '>=16'} + supports-color@7.2.0: resolution: {integrity: sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==} engines: {node: '>=8'} @@ -4185,6 +4862,9 @@ packages: symbol-tree@3.2.4: resolution: {integrity: sha512-9QNk5KwDF+Bvz+PyObkmSYjI5ksVUYtjW7AU22r2NKcfLJcXp96hkDWU3+XndOsUb+AQ9QhfzfCT2O+CNWT5Tw==} + tabbable@6.5.0: + resolution: {integrity: sha512-wieBHXygIm7OyQOu5hQlkk62/WyCFYGlWg7L6/ZCUZwx0o398Zkn4pVmMyfYhfMG8kGrj/Krt8eIk6UKC6VzwA==} + tinybench@2.9.0: resolution: {integrity: sha512-0+DUvqWMValLmha6lr4kD8iAMK1HzV0/aKnCtWb9v9641TnP/MFb7Pc2bxoxQjTXAErryXVgUOfv2YqNllqGeg==} @@ -4219,6 +4899,9 @@ packages: resolution: {integrity: sha512-L0Orpi8qGpRG//Nd+H90vFB+3iHnue1zSSGmNOOCh1GLJ7rUKVwV2HvijphGQS2UmhUZewS9VgvxYIdgr+fG1A==} hasBin: true + trim-lines@3.0.1: + resolution: {integrity: sha512-kRj8B+YHZCc9kQYdWfJB2/oUl9rA99qbowYYBtr4ui4mZyAQ2JpvVBd/6U2YloATfqBhBTSMhTpgBHtU0Mf3Rg==} + ts-algebra@2.0.0: resolution: {integrity: sha512-FPAhNPFMrkwz76P7cdjdmiShwMynZYN6SgOujD1urY4oNm80Ou9oMdmbR45LotcKOXoy7wSmHkRFE6Mxbrhefw==} @@ -4324,6 +5007,9 @@ packages: unist-util-is@6.0.1: resolution: {integrity: sha512-LsiILbtBETkDz8I9p1dQ0uyRUWuaQzd/cuEeS1hoRSyW5E5XGmTzlwY1OrNzzakGowI9Dr/I8HVaw4hTtnxy8g==} + unist-util-position@5.0.0: + resolution: {integrity: sha512-fucsC7HjXvkB5R3kTCO7kUjRdrS0BJt3M/FPxmHMBOm8JQi2BsHAHFsy27E0EolP8rp0NzXsJ+jNPyDWvOJZPA==} + unist-util-stringify-position@4.0.0: resolution: {integrity: sha512-0ASV06AAoKCDkS2+xw5RXJywruurpbC4JZSm7nr7MOt1ojAzvyyaO+UxZf18j8FCF6kmzCZKcAgN/yu2gm2XgQ==} @@ -4340,11 +5026,48 @@ packages: resolution: {integrity: sha512-6ZxzVpzDXDa3bJWaHilVayA+BH/1zmxCJoVgvmqJnid/gPoKHxUrS/aC/T6LGQtNHT+XHG9fXPJB4d+IrU30Ew==} hasBin: true + vfile-message@4.0.3: + resolution: {integrity: sha512-QTHzsGd1EhbZs4AsQ20JX1rC3cOlt/IWJruk893DfLRr57lcnOeMaWG4K0JrRta4mIJZKth2Au3mM3u03/JWKw==} + + vfile@6.0.3: + resolution: {integrity: sha512-KzIbH/9tXat2u30jf+smMwFCsno4wHVdNmzFyL+T/L3UGqqk6JKfVqOFOZEpZSHADH1k40ab6NUIXZq422ov3Q==} + vite-tsconfig-paths@6.1.1: resolution: {integrity: sha512-2cihq7zliibCCZ8P9cKJrQBkfgdvcFkOOc3Y02o3GWUDLgqjWsZudaoiuOwO/gzTzy17cS5F7ZPo4bsnS4DGkg==} peerDependencies: vite: '*' + vite@5.4.21: + resolution: {integrity: sha512-o5a9xKjbtuhY6Bi5S3+HvbRERmouabWbyUcpXXUA1u+GNUKoROi9byOJ8M0nHbHYHkYICiMlqxkg1KkYmm25Sw==} + engines: {node: ^18.0.0 || >=20.0.0} + hasBin: true + peerDependencies: + '@types/node': ^18.0.0 || >=20.0.0 + less: '*' + lightningcss: ^1.21.0 + sass: '*' + sass-embedded: '*' + stylus: '*' + sugarss: '*' + terser: ^5.4.0 + peerDependenciesMeta: + '@types/node': + optional: true + less: + optional: true + lightningcss: + optional: true + sass: + optional: true + sass-embedded: + optional: true + stylus: + optional: true + sugarss: + optional: true + terser: + optional: true + vite@8.0.16: resolution: {integrity: sha512-h9bXPmJichP5fLmVQo3PyaGSDE2n3aPuomeAlVRm0JLmt4rY6zmPKd59HYI4LNW8oTK7tlTsuC7l/m7awx9Jcw==} engines: {node: ^20.19.0 || >=22.12.0} @@ -4388,6 +5111,24 @@ packages: yaml: optional: true + vitepress-plugin-mermaid@2.0.17: + resolution: {integrity: sha512-IUzYpwf61GC6k0XzfmAmNrLvMi9TRrVRMsUyCA8KNXhg/mQ1VqWnO0/tBVPiX5UoKF1mDUwqn5QV4qAJl6JnUg==} + peerDependencies: + mermaid: 10 || 11 + vitepress: ^1.0.0 || ^1.0.0-alpha + + vitepress@1.6.4: + resolution: {integrity: sha512-+2ym1/+0VVrbhNyRoFFesVvBvHAVMZMK0rw60E3X/5349M1GuVdKeazuksqopEdvkKwKGs21Q729jX81/bkBJg==} + hasBin: true + peerDependencies: + markdown-it-mathjax3: ^4 + postcss: ^8 + peerDependenciesMeta: + markdown-it-mathjax3: + optional: true + postcss: + optional: true + vitest@4.1.8: resolution: {integrity: sha512-flY6ScbCIt9HThs+C5HS7jvGOB560DJtk/Z15IQROTA6zEy49Nh8T/dofWTQL+n3vswqn87sbJNiuqw1SDp5Ig==} engines: {node: ^20.0.0 || ^22.0.0 || >=24.0.0} @@ -4429,6 +5170,14 @@ packages: jsdom: optional: true + vue@3.5.39: + resolution: {integrity: sha512-xmZCYabFGcirU8r0fTuvl/LICc1OU620rnqepaJDL/a141ZigkG7AyaxQLdqJ02ZRYzWe6YPaDHeQx7MfknQfA==} + peerDependencies: + typescript: '*' + peerDependenciesMeta: + typescript: + optional: true + w3c-xmlserializer@5.0.0: resolution: {integrity: sha512-o8qghlI8NZHU1lLPrpi2+Uq7abh4GGPpYANlalzWxyWteJOCsr/P+oPBA49TOLu5FTZO4d3F9MnWJfiMo4BkmA==} engines: {node: '>=18'} @@ -4516,6 +5265,118 @@ snapshots: dependencies: zod: 4.4.3 + '@algolia/abtesting@1.21.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/autocomplete-core@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3)': + dependencies: + '@algolia/autocomplete-plugin-algolia-insights': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3) + '@algolia/autocomplete-shared': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + transitivePeerDependencies: + - '@algolia/client-search' + - algoliasearch + - search-insights + + '@algolia/autocomplete-plugin-algolia-insights@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3)': + dependencies: + '@algolia/autocomplete-shared': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + search-insights: 2.17.3 + transitivePeerDependencies: + - '@algolia/client-search' + - algoliasearch + + '@algolia/autocomplete-preset-algolia@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)': + dependencies: + '@algolia/autocomplete-shared': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + '@algolia/client-search': 5.55.2 + algoliasearch: 5.55.2 + + '@algolia/autocomplete-shared@1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)': + dependencies: + '@algolia/client-search': 5.55.2 + algoliasearch: 5.55.2 + + '@algolia/client-abtesting@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-analytics@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-common@5.55.2': {} + + '@algolia/client-insights@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-personalization@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-query-suggestions@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/client-search@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/ingestion@1.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/monitoring@1.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/recommend@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + + '@algolia/requester-browser-xhr@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + + '@algolia/requester-fetch@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + + '@algolia/requester-node-http@5.55.2': + dependencies: + '@algolia/client-common': 5.55.2 + '@antfu/install-pkg@1.1.0': dependencies: package-manager-detector: 1.6.0 @@ -4815,6 +5676,9 @@ snapshots: '@bcoe/v8-coverage@1.0.2': {} + '@braintree/sanitize-url@6.0.4': + optional: true + '@braintree/sanitize-url@7.1.2': {} '@bramus/specificity@2.4.2': @@ -4864,6 +5728,31 @@ snapshots: '@csstools/css-tokenizer@4.0.0': {} + '@docsearch/css@3.8.2': {} + + '@docsearch/js@3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3)': + dependencies: + '@docsearch/react': 3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3) + preact: 10.29.7 + transitivePeerDependencies: + - '@algolia/client-search' + - '@types/react' + - preact-render-to-string + - react + - react-dom + - search-insights + + '@docsearch/react@3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3)': + dependencies: + '@algolia/autocomplete-core': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2)(search-insights@2.17.3) + '@algolia/autocomplete-preset-algolia': 1.17.7(@algolia/client-search@5.55.2)(algoliasearch@5.55.2) + '@docsearch/css': 3.8.2 + algoliasearch: 5.55.2 + optionalDependencies: + search-insights: 2.17.3 + transitivePeerDependencies: + - '@algolia/client-search' + '@earendil-works/pi-ai@0.79.3(ws@8.21.0)(zod@4.4.3)': dependencies: '@anthropic-ai/sdk': 0.91.1(zod@4.4.3) @@ -4916,81 +5805,150 @@ snapshots: tslib: 2.8.1 optional: true + '@esbuild/aix-ppc64@0.21.5': + optional: true + '@esbuild/aix-ppc64@0.28.1': optional: true + '@esbuild/android-arm64@0.21.5': + optional: true + '@esbuild/android-arm64@0.28.1': optional: true + '@esbuild/android-arm@0.21.5': + optional: true + '@esbuild/android-arm@0.28.1': optional: true + '@esbuild/android-x64@0.21.5': + optional: true + '@esbuild/android-x64@0.28.1': optional: true + '@esbuild/darwin-arm64@0.21.5': + optional: true + '@esbuild/darwin-arm64@0.28.1': optional: true + '@esbuild/darwin-x64@0.21.5': + optional: true + '@esbuild/darwin-x64@0.28.1': optional: true + '@esbuild/freebsd-arm64@0.21.5': + optional: true + '@esbuild/freebsd-arm64@0.28.1': optional: true + '@esbuild/freebsd-x64@0.21.5': + optional: true + '@esbuild/freebsd-x64@0.28.1': optional: true + '@esbuild/linux-arm64@0.21.5': + optional: true + '@esbuild/linux-arm64@0.28.1': optional: true + '@esbuild/linux-arm@0.21.5': + optional: true + '@esbuild/linux-arm@0.28.1': optional: true + '@esbuild/linux-ia32@0.21.5': + optional: true + '@esbuild/linux-ia32@0.28.1': optional: true + '@esbuild/linux-loong64@0.21.5': + optional: true + '@esbuild/linux-loong64@0.28.1': optional: true + '@esbuild/linux-mips64el@0.21.5': + optional: true + '@esbuild/linux-mips64el@0.28.1': optional: true + '@esbuild/linux-ppc64@0.21.5': + optional: true + '@esbuild/linux-ppc64@0.28.1': optional: true + '@esbuild/linux-riscv64@0.21.5': + optional: true + '@esbuild/linux-riscv64@0.28.1': optional: true + '@esbuild/linux-s390x@0.21.5': + optional: true + '@esbuild/linux-s390x@0.28.1': optional: true + '@esbuild/linux-x64@0.21.5': + optional: true + '@esbuild/linux-x64@0.28.1': optional: true '@esbuild/netbsd-arm64@0.28.1': optional: true + '@esbuild/netbsd-x64@0.21.5': + optional: true + '@esbuild/netbsd-x64@0.28.1': optional: true '@esbuild/openbsd-arm64@0.28.1': optional: true + '@esbuild/openbsd-x64@0.21.5': + optional: true + '@esbuild/openbsd-x64@0.28.1': optional: true '@esbuild/openharmony-arm64@0.28.1': optional: true + '@esbuild/sunos-x64@0.21.5': + optional: true + '@esbuild/sunos-x64@0.28.1': optional: true + '@esbuild/win32-arm64@0.21.5': + optional: true + '@esbuild/win32-arm64@0.28.1': optional: true + '@esbuild/win32-ia32@0.21.5': + optional: true + '@esbuild/win32-ia32@0.28.1': optional: true + '@esbuild/win32-x64@0.21.5': + optional: true + '@esbuild/win32-x64@0.28.1': optional: true @@ -5053,6 +6011,10 @@ snapshots: '@humanwhocodes/retry@0.4.3': {} + '@iconify-json/simple-icons@1.2.89': + dependencies: + '@iconify/types': 2.0.0 + '@iconify/types@2.0.0': {} '@iconify/utils@3.1.3': @@ -5075,6 +6037,17 @@ snapshots: '@jridgewell/resolve-uri': 3.1.2 '@jridgewell/sourcemap-codec': 1.5.5 + '@mermaid-js/mermaid-mindmap@9.3.0': + dependencies: + '@braintree/sanitize-url': 6.0.4 + cytoscape: 3.34.0 + cytoscape-cose-bilkent: 4.1.0(cytoscape@3.34.0) + cytoscape-fcose: 2.2.0(cytoscape@3.34.0) + d3: 7.9.0 + khroma: 2.1.0 + non-layered-tidy-tree-layout: 2.0.2 + optional: true + '@mermaid-js/parser@1.2.0': dependencies: '@chevrotain/types': 11.1.2 @@ -5359,6 +6332,121 @@ snapshots: '@rolldown/pluginutils@1.0.1': {} + '@rollup/rollup-android-arm-eabi@4.62.2': + optional: true + + '@rollup/rollup-android-arm64@4.62.2': + optional: true + + '@rollup/rollup-darwin-arm64@4.62.2': + optional: true + + '@rollup/rollup-darwin-x64@4.62.2': + optional: true + + '@rollup/rollup-freebsd-arm64@4.62.2': + optional: true + + '@rollup/rollup-freebsd-x64@4.62.2': + optional: true + + '@rollup/rollup-linux-arm-gnueabihf@4.62.2': + optional: true + + '@rollup/rollup-linux-arm-musleabihf@4.62.2': + optional: true + + '@rollup/rollup-linux-arm64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-arm64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-loong64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-loong64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-ppc64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-ppc64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-riscv64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-riscv64-musl@4.62.2': + optional: true + + '@rollup/rollup-linux-s390x-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-x64-gnu@4.62.2': + optional: true + + '@rollup/rollup-linux-x64-musl@4.62.2': + optional: true + + '@rollup/rollup-openbsd-x64@4.62.2': + optional: true + + '@rollup/rollup-openharmony-arm64@4.62.2': + optional: true + + '@rollup/rollup-win32-arm64-msvc@4.62.2': + optional: true + + '@rollup/rollup-win32-ia32-msvc@4.62.2': + optional: true + + '@rollup/rollup-win32-x64-gnu@4.62.2': + optional: true + + '@rollup/rollup-win32-x64-msvc@4.62.2': + optional: true + + '@shikijs/core@2.5.0': + dependencies: + '@shikijs/engine-javascript': 2.5.0 + '@shikijs/engine-oniguruma': 2.5.0 + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + '@types/hast': 3.0.5 + hast-util-to-html: 9.0.5 + + '@shikijs/engine-javascript@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + oniguruma-to-es: 3.1.1 + + '@shikijs/engine-oniguruma@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + + '@shikijs/langs@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + + '@shikijs/themes@2.5.0': + dependencies: + '@shikijs/types': 2.5.0 + + '@shikijs/transformers@2.5.0': + dependencies: + '@shikijs/core': 2.5.0 + '@shikijs/types': 2.5.0 + + '@shikijs/types@2.5.0': + dependencies: + '@shikijs/vscode-textmate': 10.0.2 + '@types/hast': 3.0.5 + + '@shikijs/vscode-textmate@10.0.2': {} + '@smithy/core@3.24.7': dependencies: '@aws-crypto/crc32': 5.2.0 @@ -5566,6 +6654,10 @@ snapshots: '@types/geojson@7946.0.16': {} + '@types/hast@3.0.5': + dependencies: + '@types/unist': 3.0.3 + '@types/jsdom@28.0.3': dependencies: '@types/node': 25.9.3 @@ -5577,10 +6669,19 @@ snapshots: '@types/json-schema@7.0.15': {} + '@types/linkify-it@5.0.0': {} + + '@types/markdown-it@14.1.2': + dependencies: + '@types/linkify-it': 5.0.0 + '@types/mdurl': 2.0.0 + '@types/mdast@4.0.4': dependencies: '@types/unist': 3.0.3 + '@types/mdurl@2.0.0': {} + '@types/ms@2.1.0': {} '@types/node@22.20.0': @@ -5602,6 +6703,8 @@ snapshots: '@types/unist@3.0.3': {} + '@types/web-bluetooth@0.0.21': {} + '@typescript-eslint/eslint-plugin@8.61.0(@typescript-eslint/parser@8.61.0(eslint@10.5.0(jiti@2.7.0))(typescript@6.0.3))(eslint@10.5.0(jiti@2.7.0))(typescript@6.0.3)': dependencies: '@eslint-community/regexpp': 4.12.2 @@ -5693,11 +6796,18 @@ snapshots: '@typescript-eslint/types': 8.61.0 eslint-visitor-keys: 5.0.1 + '@ungap/structured-clone@1.3.3': {} + '@upsetjs/venn.js@2.0.0': optionalDependencies: d3-selection: 3.0.0 d3-transition: 3.0.1(d3-selection@3.0.0) + '@vitejs/plugin-vue@5.2.4(vite@5.4.21(@types/node@25.9.3)(lightningcss@1.32.0))(vue@3.5.39(typescript@6.0.3))': + dependencies: + vite: 5.4.21(@types/node@25.9.3)(lightningcss@1.32.0) + vue: 3.5.39(typescript@6.0.3) + '@vitest/coverage-v8@4.1.8(vitest@4.1.8)': dependencies: '@bcoe/v8-coverage': 1.0.2 @@ -5761,6 +6871,105 @@ snapshots: convert-source-map: 2.0.0 tinyrainbow: 3.1.0 + '@vue/compiler-core@3.5.39': + dependencies: + '@babel/parser': 7.29.7 + '@vue/shared': 3.5.39 + entities: 7.0.1 + estree-walker: 2.0.2 + source-map-js: 1.2.1 + + '@vue/compiler-dom@3.5.39': + dependencies: + '@vue/compiler-core': 3.5.39 + '@vue/shared': 3.5.39 + + '@vue/compiler-sfc@3.5.39': + dependencies: + '@babel/parser': 7.29.7 + '@vue/compiler-core': 3.5.39 + '@vue/compiler-dom': 3.5.39 + '@vue/compiler-ssr': 3.5.39 + '@vue/shared': 3.5.39 + estree-walker: 2.0.2 + magic-string: 0.30.21 + postcss: 8.5.15 + source-map-js: 1.2.1 + + '@vue/compiler-ssr@3.5.39': + dependencies: + '@vue/compiler-dom': 3.5.39 + '@vue/shared': 3.5.39 + + '@vue/devtools-api@7.7.10': + dependencies: + '@vue/devtools-kit': 7.7.10 + + '@vue/devtools-kit@7.7.10': + dependencies: + '@vue/devtools-shared': 7.7.10 + birpc: 2.9.0 + hookable: 5.5.3 + mitt: 3.0.1 + perfect-debounce: 1.0.0 + speakingurl: 14.0.1 + superjson: 2.2.6 + + '@vue/devtools-shared@7.7.10': + dependencies: + rfdc: 1.4.1 + + '@vue/reactivity@3.5.39': + dependencies: + '@vue/shared': 3.5.39 + + '@vue/runtime-core@3.5.39': + dependencies: + '@vue/reactivity': 3.5.39 + '@vue/shared': 3.5.39 + + '@vue/runtime-dom@3.5.39': + dependencies: + '@vue/reactivity': 3.5.39 + '@vue/runtime-core': 3.5.39 + '@vue/shared': 3.5.39 + csstype: 3.2.3 + + '@vue/server-renderer@3.5.39(vue@3.5.39(typescript@6.0.3))': + dependencies: + '@vue/compiler-ssr': 3.5.39 + '@vue/shared': 3.5.39 + vue: 3.5.39(typescript@6.0.3) + + '@vue/shared@3.5.39': {} + + '@vueuse/core@12.8.2(typescript@6.0.3)': + dependencies: + '@types/web-bluetooth': 0.0.21 + '@vueuse/metadata': 12.8.2 + '@vueuse/shared': 12.8.2(typescript@6.0.3) + vue: 3.5.39(typescript@6.0.3) + transitivePeerDependencies: + - typescript + + '@vueuse/integrations@12.8.2(focus-trap@7.8.0)(typescript@6.0.3)': + dependencies: + '@vueuse/core': 12.8.2(typescript@6.0.3) + '@vueuse/shared': 12.8.2(typescript@6.0.3) + vue: 3.5.39(typescript@6.0.3) + optionalDependencies: + focus-trap: 7.8.0 + transitivePeerDependencies: + - typescript + + '@vueuse/metadata@12.8.2': {} + + '@vueuse/shared@12.8.2(typescript@6.0.3)': + dependencies: + vue: 3.5.39(typescript@6.0.3) + transitivePeerDependencies: + - typescript + acorn-jsx@5.3.2(acorn@8.17.0): dependencies: acorn: 8.17.0 @@ -5776,6 +6985,23 @@ snapshots: json-schema-traverse: 0.4.1 uri-js: 4.4.1 + algoliasearch@5.55.2: + dependencies: + '@algolia/abtesting': 1.21.2 + '@algolia/client-abtesting': 5.55.2 + '@algolia/client-analytics': 5.55.2 + '@algolia/client-common': 5.55.2 + '@algolia/client-insights': 5.55.2 + '@algolia/client-personalization': 5.55.2 + '@algolia/client-query-suggestions': 5.55.2 + '@algolia/client-search': 5.55.2 + '@algolia/ingestion': 1.55.2 + '@algolia/monitoring': 1.55.2 + '@algolia/recommend': 5.55.2 + '@algolia/requester-browser-xhr': 5.55.2 + '@algolia/requester-fetch': 5.55.2 + '@algolia/requester-node-http': 5.55.2 + ansis@4.3.1: {} anynum@1.0.0: {} @@ -5806,6 +7032,8 @@ snapshots: bignumber.js@9.3.1: {} + birpc@2.9.0: {} + birpc@4.0.0: {} bowser@2.14.1: {} @@ -5822,18 +7050,28 @@ snapshots: chai@6.2.2: {} + character-entities-html4@2.1.0: {} + + character-entities-legacy@3.0.0: {} + character-entities@2.0.2: {} chokidar@4.0.3: dependencies: readdirp: 4.1.2 + comma-separated-tokens@2.0.3: {} + commander@7.2.0: {} commander@8.3.0: {} convert-source-map@2.0.0: {} + copy-anything@4.0.5: + dependencies: + is-what: 5.5.0 + cordis@4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4): dependencies: '@standard-schema/spec': 1.1.0 @@ -5871,6 +7109,8 @@ snapshots: mdn-data: 2.27.1 source-map-js: 1.2.1 + csstype@3.2.3: {} + cytoscape-cose-bilkent@4.1.0(cytoscape@3.34.0): dependencies: cose-base: 1.0.3 @@ -6106,14 +7346,44 @@ snapshots: dependencies: safe-buffer: 5.2.1 + emoji-regex-xs@1.0.0: {} + empathic@2.0.1: {} + entities@7.0.1: {} + entities@8.0.0: {} es-module-lexer@2.1.0: {} es-toolkit@1.49.0: {} + esbuild@0.21.5: + optionalDependencies: + '@esbuild/aix-ppc64': 0.21.5 + '@esbuild/android-arm': 0.21.5 + '@esbuild/android-arm64': 0.21.5 + '@esbuild/android-x64': 0.21.5 + '@esbuild/darwin-arm64': 0.21.5 + '@esbuild/darwin-x64': 0.21.5 + '@esbuild/freebsd-arm64': 0.21.5 + '@esbuild/freebsd-x64': 0.21.5 + '@esbuild/linux-arm': 0.21.5 + '@esbuild/linux-arm64': 0.21.5 + '@esbuild/linux-ia32': 0.21.5 + '@esbuild/linux-loong64': 0.21.5 + '@esbuild/linux-mips64el': 0.21.5 + '@esbuild/linux-ppc64': 0.21.5 + '@esbuild/linux-riscv64': 0.21.5 + '@esbuild/linux-s390x': 0.21.5 + '@esbuild/linux-x64': 0.21.5 + '@esbuild/netbsd-x64': 0.21.5 + '@esbuild/openbsd-x64': 0.21.5 + '@esbuild/sunos-x64': 0.21.5 + '@esbuild/win32-arm64': 0.21.5 + '@esbuild/win32-ia32': 0.21.5 + '@esbuild/win32-x64': 0.21.5 + esbuild@0.28.1: optionalDependencies: '@esbuild/aix-ppc64': 0.28.1 @@ -6219,6 +7489,8 @@ snapshots: estraverse@5.3.0: {} + estree-walker@2.0.2: {} + estree-walker@3.0.3: dependencies: '@types/estree': 1.0.9 @@ -6280,6 +7552,10 @@ snapshots: flatted@3.4.2: {} + focus-trap@7.8.0: + dependencies: + tabbable: 6.5.0 + formatly@0.3.0: dependencies: fd-package-json: 2.0.0 @@ -6338,6 +7614,26 @@ snapshots: has-flag@4.0.0: {} + hast-util-to-html@9.0.5: + dependencies: + '@types/hast': 3.0.5 + '@types/unist': 3.0.3 + ccount: 2.0.1 + comma-separated-tokens: 2.0.3 + hast-util-whitespace: 3.0.0 + html-void-elements: 3.0.0 + mdast-util-to-hast: 13.2.1 + property-information: 7.2.0 + space-separated-tokens: 2.0.2 + stringify-entities: 4.0.4 + zwitch: 2.0.4 + + hast-util-whitespace@3.0.0: + dependencies: + '@types/hast': 3.0.5 + + hookable@5.5.3: {} + hookable@6.1.1: {} html-encoding-sniffer@6.0.0: @@ -6348,6 +7644,8 @@ snapshots: html-escaper@2.0.2: {} + html-void-elements@3.0.0: {} + http-proxy-agent@7.0.2: dependencies: agent-base: 7.1.4 @@ -6388,6 +7686,8 @@ snapshots: is-potential-custom-element-name@1.0.1: {} + is-what@5.5.0: {} + isexe@2.0.0: {} istanbul-lib-coverage@3.2.2: {} @@ -6620,6 +7920,8 @@ snapshots: dependencies: semver: 7.8.4 + mark.js@8.11.1: {} + markdown-table@3.0.4: {} marked@16.4.2: {} @@ -6710,6 +8012,18 @@ snapshots: '@types/mdast': 4.0.4 unist-util-is: 6.0.1 + mdast-util-to-hast@13.2.1: + dependencies: + '@types/hast': 3.0.5 + '@types/mdast': 4.0.4 + '@ungap/structured-clone': 1.3.3 + devlop: 1.1.0 + micromark-util-sanitize-uri: 2.0.1 + trim-lines: 3.0.1 + unist-util-position: 5.0.0 + unist-util-visit: 5.1.0 + vfile: 6.0.3 + mdast-util-to-markdown@2.1.2: dependencies: '@types/mdast': 4.0.4 @@ -6947,6 +8261,10 @@ snapshots: dependencies: brace-expansion: 5.0.6 + minisearch@7.2.0: {} + + mitt@3.0.1: {} + mri@1.2.0: {} ms@2.1.3: {} @@ -6974,8 +8292,17 @@ snapshots: fetch-blob: 3.2.0 formdata-polyfill: 4.0.10 + non-layered-tidy-tree-layout@2.0.2: + optional: true + obug@2.1.3: {} + oniguruma-to-es@3.1.1: + dependencies: + emoji-regex-xs: 1.0.0 + regex: 6.1.0 + regex-recursion: 6.0.2 + openai@6.26.0(ws@8.21.0)(zod@4.4.3): optionalDependencies: ws: 8.21.0 @@ -7068,6 +8395,8 @@ snapshots: pathe@2.0.3: {} + perfect-debounce@1.0.0: {} + picocolors@1.1.1: {} picomatch@4.0.4: {} @@ -7085,8 +8414,12 @@ snapshots: picocolors: 1.1.1 source-map-js: 1.2.1 + preact@10.29.7: {} + prelude-ls@1.2.1: {} + property-information@7.2.0: {} + protobufjs@7.6.4: dependencies: '@protobufjs/aspromise': 1.1.2 @@ -7116,12 +8449,24 @@ snapshots: readdirp@4.1.2: {} + regex-recursion@6.0.2: + dependencies: + regex-utilities: 2.3.0 + + regex-utilities@2.3.0: {} + + regex@6.1.0: + dependencies: + regex-utilities: 2.3.0 + require-from-string@2.0.2: {} resolve-pkg-maps@1.0.0: {} retry@0.13.1: {} + rfdc@1.4.1: {} + robust-predicates@3.0.3: {} rolldown-plugin-dts@0.25.2(oxc-resolver@11.20.0)(rolldown@1.1.1)(typescript@6.0.3): @@ -7182,6 +8527,37 @@ snapshots: '@rolldown/binding-win32-arm64-msvc': 1.1.1 '@rolldown/binding-win32-x64-msvc': 1.1.1 + rollup@4.62.2: + dependencies: + '@types/estree': 1.0.9 + optionalDependencies: + '@rollup/rollup-android-arm-eabi': 4.62.2 + '@rollup/rollup-android-arm64': 4.62.2 + '@rollup/rollup-darwin-arm64': 4.62.2 + '@rollup/rollup-darwin-x64': 4.62.2 + '@rollup/rollup-freebsd-arm64': 4.62.2 + '@rollup/rollup-freebsd-x64': 4.62.2 + '@rollup/rollup-linux-arm-gnueabihf': 4.62.2 + '@rollup/rollup-linux-arm-musleabihf': 4.62.2 + '@rollup/rollup-linux-arm64-gnu': 4.62.2 + '@rollup/rollup-linux-arm64-musl': 4.62.2 + '@rollup/rollup-linux-loong64-gnu': 4.62.2 + '@rollup/rollup-linux-loong64-musl': 4.62.2 + '@rollup/rollup-linux-ppc64-gnu': 4.62.2 + '@rollup/rollup-linux-ppc64-musl': 4.62.2 + '@rollup/rollup-linux-riscv64-gnu': 4.62.2 + '@rollup/rollup-linux-riscv64-musl': 4.62.2 + '@rollup/rollup-linux-s390x-gnu': 4.62.2 + '@rollup/rollup-linux-x64-gnu': 4.62.2 + '@rollup/rollup-linux-x64-musl': 4.62.2 + '@rollup/rollup-openbsd-x64': 4.62.2 + '@rollup/rollup-openharmony-arm64': 4.62.2 + '@rollup/rollup-win32-arm64-msvc': 4.62.2 + '@rollup/rollup-win32-ia32-msvc': 4.62.2 + '@rollup/rollup-win32-x64-gnu': 4.62.2 + '@rollup/rollup-win32-x64-msvc': 4.62.2 + fsevents: 2.3.3 + roughjs@4.6.6: dependencies: hachure-fill: 0.5.2 @@ -7208,6 +8584,8 @@ snapshots: '@standard-schema/spec': 1.1.0 cosmokit: 1.8.1 + search-insights@2.17.3: {} + semver@7.8.4: {} shebang-command@2.0.0: @@ -7216,16 +8594,36 @@ snapshots: shebang-regex@3.0.0: {} + shiki@2.5.0: + dependencies: + '@shikijs/core': 2.5.0 + '@shikijs/engine-javascript': 2.5.0 + '@shikijs/engine-oniguruma': 2.5.0 + '@shikijs/langs': 2.5.0 + '@shikijs/themes': 2.5.0 + '@shikijs/types': 2.5.0 + '@shikijs/vscode-textmate': 10.0.2 + '@types/hast': 3.0.5 + siginfo@2.0.0: {} smol-toml@1.6.1: {} source-map-js@1.2.1: {} + space-separated-tokens@2.0.2: {} + + speakingurl@14.0.1: {} + stackback@0.0.2: {} std-env@4.1.0: {} + stringify-entities@4.0.4: + dependencies: + character-entities-html4: 2.1.0 + character-entities-legacy: 3.0.0 + strip-json-comments@5.0.3: {} strnum@2.4.0: @@ -7234,6 +8632,10 @@ snapshots: stylis@4.4.0: {} + superjson@2.2.6: + dependencies: + copy-anything: 4.0.5 + supports-color@7.2.0: dependencies: has-flag: 4.0.0 @@ -7242,6 +8644,8 @@ snapshots: symbol-tree@3.2.4: {} + tabbable@6.5.0: {} + tinybench@2.9.0: {} tinyexec@1.2.4: {} @@ -7269,6 +8673,8 @@ snapshots: tree-kill@1.2.2: {} + trim-lines@3.0.1: {} + ts-algebra@2.0.0: {} ts-api-utils@2.5.0(typescript@6.0.3): @@ -7352,6 +8758,10 @@ snapshots: dependencies: '@types/unist': 3.0.3 + unist-util-position@5.0.0: + dependencies: + '@types/unist': 3.0.3 + unist-util-stringify-position@4.0.0: dependencies: '@types/unist': 3.0.3 @@ -7373,6 +8783,16 @@ snapshots: uuid@14.0.1: {} + vfile-message@4.0.3: + dependencies: + '@types/unist': 3.0.3 + unist-util-stringify-position: 4.0.0 + + vfile@6.0.3: + dependencies: + '@types/unist': 3.0.3 + vfile-message: 4.0.3 + vite-tsconfig-paths@6.1.1(typescript@6.0.3)(vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0)): dependencies: debug: 4.4.3 @@ -7383,6 +8803,16 @@ snapshots: - supports-color - typescript + vite@5.4.21(@types/node@25.9.3)(lightningcss@1.32.0): + dependencies: + esbuild: 0.21.5 + postcss: 8.5.15 + rollup: 4.62.2 + optionalDependencies: + '@types/node': 25.9.3 + fsevents: 2.3.3 + lightningcss: 1.32.0 + vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0): dependencies: lightningcss: 1.32.0 @@ -7413,6 +8843,63 @@ snapshots: tsx: 4.22.4 yaml: 2.9.0 + vitepress-plugin-mermaid@2.0.17(mermaid@11.16.0)(vitepress@1.6.4(@algolia/client-search@5.55.2)(@types/node@25.9.3)(lightningcss@1.32.0)(postcss@8.5.15)(search-insights@2.17.3)(typescript@6.0.3)): + dependencies: + mermaid: 11.16.0 + vitepress: 1.6.4(@algolia/client-search@5.55.2)(@types/node@25.9.3)(lightningcss@1.32.0)(postcss@8.5.15)(search-insights@2.17.3)(typescript@6.0.3) + optionalDependencies: + '@mermaid-js/mermaid-mindmap': 9.3.0 + + vitepress@1.6.4(@algolia/client-search@5.55.2)(@types/node@25.9.3)(lightningcss@1.32.0)(postcss@8.5.15)(search-insights@2.17.3)(typescript@6.0.3): + dependencies: + '@docsearch/css': 3.8.2 + '@docsearch/js': 3.8.2(@algolia/client-search@5.55.2)(search-insights@2.17.3) + '@iconify-json/simple-icons': 1.2.89 + '@shikijs/core': 2.5.0 + '@shikijs/transformers': 2.5.0 + '@shikijs/types': 2.5.0 + '@types/markdown-it': 14.1.2 + '@vitejs/plugin-vue': 5.2.4(vite@5.4.21(@types/node@25.9.3)(lightningcss@1.32.0))(vue@3.5.39(typescript@6.0.3)) + '@vue/devtools-api': 7.7.10 + '@vue/shared': 3.5.39 + '@vueuse/core': 12.8.2(typescript@6.0.3) + '@vueuse/integrations': 12.8.2(focus-trap@7.8.0)(typescript@6.0.3) + focus-trap: 7.8.0 + mark.js: 8.11.1 + minisearch: 7.2.0 + shiki: 2.5.0 + vite: 5.4.21(@types/node@25.9.3)(lightningcss@1.32.0) + vue: 3.5.39(typescript@6.0.3) + optionalDependencies: + postcss: 8.5.15 + transitivePeerDependencies: + - '@algolia/client-search' + - '@types/node' + - '@types/react' + - async-validator + - axios + - change-case + - drauu + - fuse.js + - idb-keyval + - jwt-decode + - less + - lightningcss + - nprogress + - preact-render-to-string + - qrcode + - react + - react-dom + - sass + - sass-embedded + - search-insights + - sortablejs + - stylus + - sugarss + - terser + - typescript + - universal-cookie + vitest@4.1.8(@types/node@22.20.0)(@vitest/coverage-v8@4.1.8)(jsdom@29.1.1)(vite@8.0.16(@types/node@22.20.0)(esbuild@0.28.1)(jiti@2.7.0)(tsx@4.22.4)(yaml@2.9.0)): dependencies: '@vitest/expect': 4.1.8 @@ -7471,6 +8958,16 @@ snapshots: transitivePeerDependencies: - msw + vue@3.5.39(typescript@6.0.3): + dependencies: + '@vue/compiler-dom': 3.5.39 + '@vue/compiler-sfc': 3.5.39 + '@vue/runtime-dom': 3.5.39 + '@vue/server-renderer': 3.5.39(vue@3.5.39(typescript@6.0.3)) + '@vue/shared': 3.5.39 + optionalDependencies: + typescript: 6.0.3 + w3c-xmlserializer@5.0.0: dependencies: xml-name-validator: 5.0.0 diff --git a/pnpm-workspace.yaml b/pnpm-workspace.yaml index 6407a99f52..3572d7368a 100644 --- a/pnpm-workspace.yaml +++ b/pnpm-workspace.yaml @@ -1,6 +1,7 @@ packages: - vendor/* - packages/*/* + - website peerDependencyRules: allowedVersions: diff --git a/scripts/project-doc-site.spec.ts b/scripts/project-doc-site.spec.ts new file mode 100644 index 0000000000..f44b779d80 --- /dev/null +++ b/scripts/project-doc-site.spec.ts @@ -0,0 +1,98 @@ +/** Tests for the documentation website projection adapter. */ + +import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it } from 'vitest' +import type { DocsPage } from '../website/docs.ts' +import { addProjectionFrontmatter, rewriteMarkdown } from './project-doc-site.ts' + +const roots: string[] = [] + +afterEach(() => { + for (const root of roots.splice(0)) rmSync(root, { recursive: true, force: true }) +}) + +function fixture(): { root: string; pages: DocsPage[] } { + const root = mkdtempSync(join(tmpdir(), 'dsh-doc-site-')) + roots.push(root) + mkdirSync(join(root, 'docs'), { recursive: true }) + mkdirSync(join(root, 'packages'), { recursive: true }) + writeFileSync(join(root, 'docs/a.md'), '# A\n') + writeFileSync(join(root, 'docs/b.md'), '# B\n') + writeFileSync(join(root, 'packages/tool.ts'), 'one\ntwo\n') + writeFileSync(join(root, 'packages/logo.svg'), '\n') + return { + root, + pages: [ + { source: 'docs/a.md', route: 'en/a.md', label: 'A', sidebar: 'en-docs', section: 'Test', order: 1 }, + { source: 'docs/b.md', route: 'en/reference/b.md', label: 'B', sidebar: 'en-docs', section: 'Test', order: 2 }, + ], + } +} + +describe('rewriteMarkdown', () => { + it('maps published pages and pins unpublished source links', () => { + const { root, pages } = fixture() + const source = '[B](b.md#part) [source](../packages/tool.ts:2) [web](https://example.com)\n' + expect(rewriteMarkdown(source, { + sourcePath: 'docs/a.md', + route: 'en/a.md', + pages, + repoRoot: root, + repositoryRef: 'abc123', + })).toBe( + '[B](./reference/b.md#part) ' + + '[source](https://github.com/deepseek-harness/deepseek-harness/blob/abc123/packages/tool.ts#L2) ' + + '[web](https://example.com)\n', + ) + }) + + it('uses raw GitHub content for unpublished images', () => { + const { root, pages } = fixture() + expect(rewriteMarkdown('![logo](../packages/logo.svg)\n', { + sourcePath: 'docs/a.md', + route: 'en/a.md', + pages, + repoRoot: root, + repositoryRef: 'abc123', + })).toBe('![logo](https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/abc123/packages/logo.svg)\n') + }) + + it('does not rewrite Markdown-looking text inside code fences', () => { + const { root, pages } = fixture() + const source = '```md\n[B](b.md)\n```\n' + expect(rewriteMarkdown(source, { + sourcePath: 'docs/a.md', + route: 'en/a.md', + pages, + repoRoot: root, + repositoryRef: 'abc123', + })).toBe(source) + }) + + it('fails loud when a relative target is missing', () => { + const { root, pages } = fixture() + expect(() => rewriteMarkdown('[missing](missing.md)\n', { + sourcePath: 'docs/a.md', + route: 'en/a.md', + pages, + repoRoot: root, + repositoryRef: 'abc123', + })).toThrow('links to missing path "missing.md"') + }) +}) + +describe('addProjectionFrontmatter', () => { + it('adds frontmatter to an ordinary Markdown page', () => { + expect(addProjectionFrontmatter('# Guide\n', 'docs/guide.md')).toBe( + '---\neditSource: "docs/guide.md"\n---\n\n# Guide\n', + ) + }) + + it('extends existing VitePress frontmatter', () => { + expect(addProjectionFrontmatter('---\nlayout: home\n---\n', 'docs/index.md')).toBe( + '---\neditSource: "docs/index.md"\nlayout: home\n---\n', + ) + }) +}) diff --git a/scripts/project-doc-site.ts b/scripts/project-doc-site.ts new file mode 100644 index 0000000000..89e35dfdc8 --- /dev/null +++ b/scripts/project-doc-site.ts @@ -0,0 +1,215 @@ +/** + * Build-time projection from canonical repository Markdown into VitePress. + * + * The generated tree is disposable: sources stay in their owning `docs/` + * tier, while this adapter rewrites cross-source links for the public site. + */ + +import { existsSync, lstatSync, mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs' +import { dirname, extname, posix, relative, resolve, sep } from 'node:path' +import { fromMarkdown } from 'mdast-util-from-markdown' +import { gfmFromMarkdown } from 'mdast-util-gfm' +import { gfm } from 'micromark-extension-gfm' +import type { Nodes } from 'mdast' +import { docsPages, type DocsPage } from '../website/docs.ts' + +const REPOSITORY_URL = 'https://github.com/deepseek-harness/deepseek-harness' +const root = resolve(import.meta.dirname, '..') +const generatedRoot = resolve(root, 'website/.generated') + +interface Replacement { + start: number + end: number + value: string +} + +/** Inputs for rewriting one canonical Markdown page. */ +export interface RewriteMarkdownOptions { + sourcePath: string + route: string + pages: DocsPage[] + repoRoot: string + repositoryRef: string +} + +function repoPath(absPath: string, repoRoot: string): string { + return relative(repoRoot, absPath).split(sep).join('/') +} + +function isExternalOrSiteAbsolute(url: string): boolean { + return url.startsWith('#') + || url.startsWith('//') + || url.startsWith('/') + || /^[a-zA-Z][a-zA-Z0-9+.-]*:/.test(url) +} + +function splitTarget(url: string): { path: string; suffix: string } { + const boundary = url.search(/[?#]/) + if (boundary === -1) return { path: url, suffix: '' } + return { path: url.slice(0, boundary), suffix: url.slice(boundary) } +} + +function decodePath(path: string): string { + try { + return decodeURIComponent(path) + } catch { + throw new Error(`project-doc-site: malformed percent escape in ${JSON.stringify(path)}.`) + } +} + +function routeTarget(fromRoute: string, toRoute: string, suffix: string): string { + const target = posix.relative(posix.dirname(fromRoute), toRoute) + return `${target.startsWith('.') ? target : `./${target}`}${suffix}` +} + +function sourceMap(pages: DocsPage[]): Map { + const map = new Map() + for (const page of pages) { + for (const source of [page.source, ...(page.sourceAliases ?? [])]) { + if (map.has(source)) { + throw new Error(`project-doc-site: duplicate source or alias ${JSON.stringify(source)}.`) + } + map.set(source, page) + } + } + return map +} + +function resolveRepositoryTarget(sourceAbs: string, rawPath: string, repoRoot: string): { absPath: string; line?: number } { + const decoded = decodePath(rawPath) + let absPath = resolve(dirname(sourceAbs), decoded) + if (existsSync(absPath)) return { absPath } + + const lineMatch = decoded.match(/:(\d+)$/) + if (lineMatch !== null) { + const lineText = lineMatch[1] + if (lineText === undefined) throw new Error('project-doc-site: line suffix matched without a line number.') + absPath = resolve(dirname(sourceAbs), decoded.slice(0, -lineMatch[0].length)) + if (existsSync(absPath)) return { absPath, line: Number.parseInt(lineText, 10) } + } + + if (extname(decoded) === '') { + const markdown = resolve(dirname(sourceAbs), `${decoded}.md`) + if (existsSync(markdown)) return { absPath: markdown } + const index = resolve(dirname(sourceAbs), decoded, 'index.md') + if (existsSync(index)) return { absPath: index } + } + + throw new Error(`project-doc-site: ${repoPath(sourceAbs, repoRoot)} links to missing path ${JSON.stringify(rawPath)}.`) +} + +function githubTarget( + absPath: string, + line: number | undefined, + suffix: string, + repositoryRef: string, + repoRoot: string, + image: boolean, +): string { + const path = repoPath(absPath, repoRoot) + if (image) return `https://raw.githubusercontent.com/deepseek-harness/deepseek-harness/${repositoryRef}/${path}${suffix}` + const kind = lstatSync(absPath).isDirectory() ? 'tree' : 'blob' + const lineSuffix = line === undefined ? suffix : `#L${line}` + return `${REPOSITORY_URL}/${kind}/${repositoryRef}/${path}${lineSuffix}` +} + +/** + * Rewrite repository-relative links without reserializing Markdown. + * + * @param source Markdown text from the canonical file. + * @param options Source, route, manifest, and repository context. + * @returns Markdown whose published links resolve inside the site or to GitHub. + */ +export function rewriteMarkdown(source: string, options: RewriteMarkdownOptions): string { + const sourceAbs = resolve(options.repoRoot, options.sourcePath) + const published = sourceMap(options.pages) + const tree = fromMarkdown(source, { extensions: [gfm()], mdastExtensions: [gfmFromMarkdown()] }) + const replacements: Replacement[] = [] + + const rewrite = (node: Nodes & { url: string }): void => { + if (isExternalOrSiteAbsolute(node.url)) return + const { path, suffix } = splitTarget(node.url) + if (path === '') return + const { absPath, line } = resolveRepositoryTarget(sourceAbs, path, options.repoRoot) + const targetPath = repoPath(absPath, options.repoRoot) + const page = published.get(targetPath) + const nextUrl = page === undefined + ? githubTarget(absPath, line, suffix, options.repositoryRef, options.repoRoot, node.type === 'image') + : routeTarget(options.route, page.route, suffix) + + const start = node.position?.start.offset + const end = node.position?.end.offset + if (start === undefined || end === undefined) { + throw new Error(`project-doc-site: link ${JSON.stringify(node.url)} has no source offsets.`) + } + const rawNode = source.slice(start, end) + const urlOffset = rawNode.lastIndexOf(node.url) + if (urlOffset === -1) { + throw new Error(`project-doc-site: cannot locate raw target ${JSON.stringify(node.url)} in ${JSON.stringify(rawNode)}.`) + } + replacements.push({ + start: start + urlOffset, + end: start + urlOffset + node.url.length, + value: nextUrl, + }) + } + + const visit = (node: Nodes): void => { + if ((node.type === 'link' || node.type === 'image' || node.type === 'definition') && 'url' in node) rewrite(node) + if ('children' in node) { + for (const child of node.children) visit(child) + } + } + visit(tree) + + let projected = source + for (const replacement of replacements.sort((a, b) => b.start - a.start)) { + projected = projected.slice(0, replacement.start) + replacement.value + projected.slice(replacement.end) + } + return projected +} + +/** + * Record the canonical edit target in VitePress frontmatter. + * + * @param markdown Projected Markdown content. + * @param sourcePath Repository-relative canonical source path. + * @returns Markdown with an `editSource` frontmatter field. + */ +export function addProjectionFrontmatter(markdown: string, sourcePath: string): string { + const field = `editSource: ${JSON.stringify(sourcePath)}` + if (markdown.startsWith('---\n')) return markdown.replace('---\n', `---\n${field}\n`) + return `---\n${field}\n---\n\n${markdown}` +} + +/** Canonical Markdown files watched by the local VitePress dev server. */ +export function docsSourceFiles(): string[] { + return [...new Set(docsPages.map(page => resolve(root, page.source)))] +} + +/** Rebuild the disposable VitePress source tree from the publication manifest. */ +export function projectDocs(): void { + const routes = new Set() + const repositoryRef = process.env.GITHUB_SHA ?? 'master' + rmSync(generatedRoot, { recursive: true, force: true }) + + for (const page of docsPages) { + if (routes.has(page.route)) throw new Error(`project-doc-site: duplicate route ${JSON.stringify(page.route)}.`) + routes.add(page.route) + const sourceAbs = resolve(root, page.source) + if (!existsSync(sourceAbs) || !lstatSync(sourceAbs).isFile()) { + throw new Error(`project-doc-site: source ${JSON.stringify(page.source)} does not exist or is not a file.`) + } + const output = resolve(generatedRoot, page.route) + mkdirSync(dirname(output), { recursive: true }) + const markdown = readFileSync(sourceAbs, 'utf8') + const projected = rewriteMarkdown(markdown, { + sourcePath: page.source, + route: page.route, + pages: docsPages, + repoRoot: root, + repositoryRef, + }) + writeFileSync(output, addProjectionFrontmatter(projected, page.source)) + } +} diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index ef1e07ea43..c9c9013100 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -272,6 +272,7 @@ function docSyncLeafGates(): Gate[] { pnpmScript('type-equivalence', 'verify-type-equiv', { label: 'type equivalence' }), pnpmScript('translation-pairing', 'verify-translation-pairing', { label: 'translation pairing' }), pnpmScript('doc-budgets', 'verify-doc-budgets', { label: 'doc budgets' }), + pnpmScript('docs-site', 'docs:check', { label: 'documentation site' }), ] } diff --git a/scripts/verify-md-wrap.ts b/scripts/verify-md-wrap.ts index 3143ee5617..65bf35fb03 100644 --- a/scripts/verify-md-wrap.ts +++ b/scripts/verify-md-wrap.ts @@ -10,10 +10,12 @@ * `paragraph` node whose source span covers more than one line. The parser owns * all the structure that legitimately occupies multiple lines — fenced code * (any fence length), tables, list items, blockquotes, HTML blocks, headings, - * thematic breaks, link-reference definitions — so a hard wrap is simply "a - * paragraph node that starts and ends on different lines." This is checker, not - * formatter: it reports and never rewrites, so it introduces zero cosmetic - * churn (no emphasis-marker or table-delimiter normalization). + * thematic breaks, link-reference definitions — while a small preprocessing + * pass masks VitePress YAML frontmatter and custom-container delimiter lines. + * A hard wrap is simply "a paragraph node that starts and ends on different + * lines." This is checker, not formatter: it reports and never rewrites, so it + * introduces zero cosmetic churn (no emphasis-marker or table-delimiter + * normalization). * * A wrapped paragraph inside a list item or blockquote is still a `paragraph` * node, so those are caught too. Scope mirrors doc-typecheck plus the two @@ -57,11 +59,23 @@ interface Violation { text: string } +function maskVitePressStructure(source: string): string { + const lines = source.split('\n') + if (lines[0] === '---') { + const closing = lines.indexOf('---', 1) + if (closing !== -1) { + for (let index = 0; index <= closing; index++) lines[index] = '' + } + } + return lines.map(line => line.trimStart().startsWith(':::') ? '' : line).join('\n') +} + /** Find every hard-wrapped prose paragraph in one Markdown file via its AST. */ function findViolations(absPath: string): Violation[] { const file = relative(root, absPath) const source = readFileSync(absPath, 'utf8') - const tree = fromMarkdown(source, { extensions: [gfm()], mdastExtensions: [gfmFromMarkdown()] }) + const parsedSource = maskVitePressStructure(source) + const tree = fromMarkdown(parsedSource, { extensions: [gfm()], mdastExtensions: [gfmFromMarkdown()] }) const out: Violation[] = [] const visit = (node: Nodes): void => { diff --git a/tsconfig.json b/tsconfig.json index 70780e1c17..800fd39318 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -9,7 +9,9 @@ "examples/*/start.ts", "examples/*/tests/**/*.ts", "packages/*/*/tests/**/*.ts", - "scripts/**/*.ts" + "scripts/**/*.ts", + "website/**/*.ts", + "website/.vitepress/**/*.ts" ], "references": [ { "path": "./vendor/cosmokit" }, diff --git a/vitest.config.ts b/vitest.config.ts index 11d1454b08..459147f4a3 100644 --- a/vitest.config.ts +++ b/vitest.config.ts @@ -19,7 +19,7 @@ export default defineConfig({ // instead applies the one root map to every importer. plugins: [tsconfigPaths({ projects: ['./tsconfig.json'] })], test: { - include: ['packages/*/*/tests/**/*.spec.ts', 'examples/*/tests/**/*.spec.ts'], + include: ['packages/*/*/tests/**/*.spec.ts', 'examples/*/tests/**/*.spec.ts', 'scripts/**/*.spec.ts'], coverage: { provider: 'v8', // Coverage measures OUR runtime source. Types-only files carry no diff --git a/website/.gitignore b/website/.gitignore index 2c1fa99cb4..29099c8fe6 100644 --- a/website/.gitignore +++ b/website/.gitignore @@ -1,3 +1,4 @@ node_modules/ -.vitepress/dist/ -.vitepress/cache/ +.cache/ +.dist/ +.generated/ diff --git a/website/.vitepress/config.ts b/website/.vitepress/config.ts new file mode 100644 index 0000000000..71c276794a --- /dev/null +++ b/website/.vitepress/config.ts @@ -0,0 +1,142 @@ +/** VitePress configuration for the locally projected documentation site. */ + +import type { DefaultTheme, PageData } from 'vitepress' +import type { ViteDevServer } from 'vite' +import { withMermaid } from 'vitepress-plugin-mermaid' +import { docsPages, type DocsPage } from '../docs.ts' +import { docsSourceFiles, projectDocs } from '../../scripts/project-doc-site.ts' + +projectDocs() + +const sectionOrder = [ + '入门', + '基础', + '框架能力', + '实战', + 'Concepts', + 'Generated reference', + 'Data structures', + 'Cookbook', +] + +function sidebar(collection: DocsPage['sidebar']): DefaultTheme.SidebarItem[] { + const pages = docsPages.filter(page => page.sidebar === collection && page.route !== 'index.md') + const sections = new Map() + for (const page of pages) { + const entries = sections.get(page.section) ?? [] + entries.push(page) + sections.set(page.section, entries) + } + return [...sections.entries()] + .sort(([left], [right]) => sectionOrder.indexOf(left) - sectionOrder.indexOf(right)) + .map(([text, entries]) => ({ + text, + items: entries + .sort((left, right) => left.order - right.order) + .map(page => ({ text: page.label, link: `/${page.route.replace(/(?:index)?\.md$/, '')}` })), + })) +} + +function watchCanonicalDocs(server: ViteDevServer): void { + const sources = docsSourceFiles() + server.watcher.add(sources) + server.watcher.on('change', (changed) => { + if (!sources.includes(changed)) return + projectDocs() + }) +} + +function escapeVueInterpolation(html: string): string { + return html.replaceAll('{{', '{{').replaceAll('}}', '}}') +} + +const sharedTheme: Pick = { + search: { provider: 'local' }, + socialLinks: [ + { icon: 'github', link: 'https://github.com/deepseek-harness/deepseek-harness' }, + ], + editLink: { + pattern: ({ frontmatter }: PageData) => { + const data: unknown = frontmatter + const editSource: unknown = typeof data === 'object' && data !== null ? Reflect.get(data, 'editSource') : undefined + if (typeof editSource !== 'string') throw new Error('Projected documentation page has no editSource frontmatter.') + return `https://github.com/deepseek-harness/deepseek-harness/edit/master/${editSource}` + }, + text: '在 GitHub 上编辑此页', + }, +} + +export default withMermaid({ + title: 'DeepSeek Harness', + description: '用于构建 Agent Harness 的插件化 SDK', + cleanUrls: true, + srcDir: '.generated', + cacheDir: '.cache', + outDir: '.dist', + locales: { + root: { + label: '简体中文', + lang: 'zh-CN', + themeConfig: { + nav: [ + { text: '入门', link: '/guide/', activeMatch: '^/guide/' }, + { text: '开发', link: '/develop/basic/', activeMatch: '^/develop/' }, + { text: 'Reference', link: '/en/', activeMatch: '^/en/' }, + ], + sidebar: { + '/guide/': sidebar('zh-guide'), + '/develop/': sidebar('zh-develop'), + }, + outline: { label: '本页目录' }, + docFooter: { prev: '上一篇', next: '下一篇' }, + }, + }, + en: { + label: 'English', + lang: 'en-US', + link: '/en/', + themeConfig: { + nav: [ + { text: 'Concepts', link: '/en/' }, + { text: 'Reference', link: '/en/config-catalog' }, + { text: '中文指南', link: '/guide/' }, + ], + sidebar: { + '/en/': sidebar('en-docs'), + }, + editLink: { + pattern: ({ frontmatter }: PageData) => { + const data: unknown = frontmatter + const editSource: unknown = typeof data === 'object' && data !== null ? Reflect.get(data, 'editSource') : undefined + if (typeof editSource !== 'string') throw new Error('Projected documentation page has no editSource frontmatter.') + return `https://github.com/deepseek-harness/deepseek-harness/edit/master/${editSource}` + }, + text: 'Edit this page on GitHub', + }, + outline: { label: 'On this page' }, + docFooter: { prev: 'Previous', next: 'Next' }, + }, + }, + }, + vite: { + plugins: [ + { + name: 'deepseek-harness-doc-projector', + configureServer: watchCanonicalDocs, + }, + ], + }, + markdown: { + config(md) { + const renderText = md.renderer.rules.text + const renderCode = md.renderer.rules.code_inline + if (renderText === undefined || renderCode === undefined) { + throw new Error('VitePress Markdown renderer is missing its text or inline-code rule.') + } + md.renderer.rules.text = (...args) => escapeVueInterpolation(renderText(...args)) + md.renderer.rules.code_inline = (...args) => escapeVueInterpolation(renderCode(...args)) + }, + }, + mermaid: {}, + themeConfig: sharedTheme, +}) diff --git a/website/.vitepress/config/index.ts b/website/.vitepress/config/index.ts deleted file mode 100644 index b4978ca4aa..0000000000 --- a/website/.vitepress/config/index.ts +++ /dev/null @@ -1,17 +0,0 @@ -import { defineConfig } from 'vitepress' -import { zhCN } from './zh-CN' - -export default defineConfig({ - title: 'DeepSeek Harness', - description: '插件化 Agent 开发框架', - - locales: { - 'zh-CN': zhCN, - }, - - themeConfig: { - socialLinks: [ - { icon: 'github', link: 'https://github.com/deepseek-harness/deepseek-harness' }, - ], - }, -}) diff --git a/website/.vitepress/config/zh-CN.ts b/website/.vitepress/config/zh-CN.ts deleted file mode 100644 index 83767b6cbc..0000000000 --- a/website/.vitepress/config/zh-CN.ts +++ /dev/null @@ -1,99 +0,0 @@ -import type { DefaultTheme, LocaleSpecificConfig } from 'vitepress' - -const guideSidebar: DefaultTheme.SidebarItem[] = [ - { - text: '入门', - items: [ - { text: '介绍', link: '/zh-CN/guide/' }, - { text: '快速开始', link: '/zh-CN/guide/quickstart' }, - { text: '配置文件', link: '/zh-CN/guide/config' }, - ], - }, -] - -const developSidebar: DefaultTheme.SidebarItem[] = [ - { - text: '基础', - items: [ - { text: '第一个插件', link: '/zh-CN/develop/basic/' }, - { text: '开发一个 Tool', link: '/zh-CN/develop/basic/tool' }, - { text: '插件配置', link: '/zh-CN/develop/basic/config' }, - ], - }, - { - text: '框架能力', - items: [ - { text: '插件与生命周期', link: '/zh-CN/develop/framework/' }, - { text: '服务与依赖', link: '/zh-CN/develop/framework/service' }, - { text: '事件系统', link: '/zh-CN/develop/framework/events' }, - ], - }, - { - text: '实战', - items: [ - { text: '能力的三层拆分', link: '/zh-CN/develop/practice/' }, - { text: 'LLM 适配器', link: '/zh-CN/develop/practice/llm-adapter' }, - ], - }, -] - -const apiSidebar: DefaultTheme.SidebarItem[] = [ - { - text: '框架 API', - items: [ - { text: '总览', link: '/zh-CN/api/' }, - { text: 'Context', link: '/zh-CN/api/cordis/context' }, - { text: 'Events', link: '/zh-CN/api/cordis/events' }, - { text: 'Fiber', link: '/zh-CN/api/cordis/fiber' }, - { text: 'Registry', link: '/zh-CN/api/cordis/registry' }, - { text: 'Service', link: '/zh-CN/api/cordis/service' }, - ], - }, - { - text: 'Harness API', - items: [ - { text: 'Tools (dsh-tools)', link: '/zh-CN/api/harness/tools' }, - { text: 'LLM (dsh-llm)', link: '/zh-CN/api/harness/llm' }, - { text: 'Session (dsh-session)', link: '/zh-CN/api/harness/session' }, - { text: 'Agent (dsh-agent)', link: '/zh-CN/api/harness/agent' }, - { text: 'Bash (dsh-bash)', link: '/zh-CN/api/harness/bash' }, - { text: 'Filesystem (dsh-fs)', link: '/zh-CN/api/harness/fs' }, - { text: 'Subagent (dsh-subagent)', link: '/zh-CN/api/harness/subagent' }, - ], - }, -] - -const designSidebar: DefaultTheme.SidebarItem[] = [ - { - text: '系统设计', - items: [ - { text: '概述', link: '/zh-CN/design/' }, - { text: '可组合性与插件系统', link: '/zh-CN/design/composability' }, - { text: '作用与余作用', link: '/zh-CN/design/effects-coeffects' }, - { text: '可逆作用', link: '/zh-CN/design/revertible-effects' }, - { text: '响应式余作用', link: '/zh-CN/design/reactive-coeffects' }, - { text: '上下文模型', link: '/zh-CN/design/context-model' }, - ], - }, -] - -export const zhCN: LocaleSpecificConfig = { - label: '简体中文', - lang: 'zh-CN', - themeConfig: { - nav: [ - { text: '入门', link: '/zh-CN/guide/', activeMatch: '/zh-CN/guide/' }, - { text: '开发', link: '/zh-CN/develop/basic/', activeMatch: '/zh-CN/develop/' }, - { text: 'API', link: '/zh-CN/api/', activeMatch: '/zh-CN/api/' }, - { text: '设计', link: '/zh-CN/design/', activeMatch: '/zh-CN/design/' }, - ], - sidebar: { - '/zh-CN/guide/': guideSidebar, - '/zh-CN/develop/': developSidebar, - '/zh-CN/api/': apiSidebar, - '/zh-CN/design/': designSidebar, - }, - outline: { label: '本页目录' }, - docFooter: { prev: '上一篇', next: '下一篇' }, - }, -} diff --git a/website/docs.ts b/website/docs.ts new file mode 100644 index 0000000000..53e74c2905 --- /dev/null +++ b/website/docs.ts @@ -0,0 +1,213 @@ +/** + * Canonical publication manifest for the documentation website. + * + * Markdown stays in its owning repository tier. This manifest only maps a + * source file to its public route and navigation placement. + */ + +/** A page projected into the VitePress source tree. */ +export interface DocsPage { + /** Repository-relative canonical Markdown source. */ + source: string + /** VitePress route, including the `.md` suffix. */ + route: string + /** Navigation label shown in the sidebar. */ + label: string + /** Sidebar collection that owns the page. */ + sidebar: 'zh-guide' | 'zh-develop' | 'en-docs' + /** Section label within the sidebar. */ + section: string + /** Stable order within the section. */ + order: number + /** Additional repository paths that resolve to this page. */ + sourceAliases?: string[] +} + +const zhGuide: DocsPage[] = [ + { + source: 'docs/user/zh-CN/index.md', + route: 'index.md', + label: 'DeepSeek Harness', + sidebar: 'zh-guide', + section: '入门', + order: 0, + }, + { + source: 'docs/user/zh-CN/guide/index.md', + route: 'guide/index.md', + label: '介绍', + sidebar: 'zh-guide', + section: '入门', + order: 1, + sourceAliases: ['docs/user/zh-CN/guide'], + }, + { + source: 'docs/user/zh-CN/guide/quickstart.md', + route: 'guide/quickstart.md', + label: '快速开始', + sidebar: 'zh-guide', + section: '入门', + order: 2, + }, + { + source: 'docs/user/zh-CN/guide/config.md', + route: 'guide/config.md', + label: '配置文件', + sidebar: 'zh-guide', + section: '入门', + order: 3, + }, +] + +const zhDevelop: DocsPage[] = [ + { + source: 'docs/user/zh-CN/develop/basic/index.md', + route: 'develop/basic/index.md', + label: '第一个插件', + sidebar: 'zh-develop', + section: '基础', + order: 1, + sourceAliases: ['docs/user/zh-CN/develop/basic'], + }, + { + source: 'docs/user/zh-CN/develop/basic/tool.md', + route: 'develop/basic/tool.md', + label: '开发一个 Tool', + sidebar: 'zh-develop', + section: '基础', + order: 2, + }, + { + source: 'docs/user/zh-CN/develop/basic/config.md', + route: 'develop/basic/config.md', + label: '插件配置', + sidebar: 'zh-develop', + section: '基础', + order: 3, + }, + { + source: 'docs/user/zh-CN/develop/framework/index.md', + route: 'develop/framework/index.md', + label: '插件与生命周期', + sidebar: 'zh-develop', + section: '框架能力', + order: 1, + sourceAliases: ['docs/user/zh-CN/develop/framework'], + }, + { + source: 'docs/user/zh-CN/develop/framework/service.md', + route: 'develop/framework/service.md', + label: '服务与依赖', + sidebar: 'zh-develop', + section: '框架能力', + order: 2, + }, + { + source: 'docs/user/zh-CN/develop/framework/events.md', + route: 'develop/framework/events.md', + label: '事件系统', + sidebar: 'zh-develop', + section: '框架能力', + order: 3, + }, + { + source: 'docs/user/zh-CN/develop/practice/index.md', + route: 'develop/practice/index.md', + label: '能力的三层拆分', + sidebar: 'zh-develop', + section: '实战', + order: 1, + sourceAliases: ['docs/user/zh-CN/develop/practice'], + }, + { + source: 'docs/user/zh-CN/develop/practice/llm-adapter.md', + route: 'develop/practice/llm-adapter.md', + label: 'LLM 适配器', + sidebar: 'zh-develop', + section: '实战', + order: 2, + }, +] + +const enOverview: DocsPage[] = ([ + ['docs/architecture.md', 'en/index.md', 'Architecture'], + ['docs/cordis-primer.md', 'en/cordis-primer.md', 'Cordis primer'], + ['docs/capability-seams.md', 'en/capability-seams.md', 'Capability services'], + ['docs/agent-lifecycle.md', 'en/agent-lifecycle.md', 'Agent lifecycle'], + ['docs/tool-execution-pipeline.md', 'en/tool-execution-pipeline.md', 'Tool execution'], +] as const).map(([source, route, label], order) => ({ + source, + route, + label, + sidebar: 'en-docs', + section: 'Concepts', + order, +})) + +const enCatalogs: DocsPage[] = ([ + ['docs/config-catalog.md', 'en/config-catalog.md', 'Plugin configuration'], + ['docs/tool-catalog.md', 'en/tool-catalog.md', 'Tool schemas'], + ['docs/cordis-catalog/services.md', 'en/cordis-catalog/services.md', 'Services'], + ['docs/cordis-catalog/events.md', 'en/cordis-catalog/events.md', 'Events'], + ['docs/persistence-catalog.md', 'en/persistence-catalog.md', 'Persistence events'], +] as const).map(([source, route, label], order) => ({ + source, + route, + label, + sidebar: 'en-docs', + section: 'Generated reference', + order, +})) + +const corePages = [ + ['core.md', 'Core data structures'], + ['session.md', 'Sessions'], + ['tools.md', 'Tools'], + ['llm-streaming.md', 'LLM streaming'], + ['bash.md', 'Bash execution'], + ['filesystem.md', 'Filesystem'], + ['code-runtime.md', 'Code runtime'], + ['compaction.md', 'Compaction'], + ['subagent.md', 'Subagents'], + ['workflow.md', 'Workflows'], + ['skills.md', 'Skills'], + ['approval.md', 'Approvals'], + ['user-interaction.md', 'User interaction'], + ['sandbox.md', 'Sandboxing'], + ['web.md', 'Web access'], + ['persistence.md', 'Session persistence'], +] as const + +const enCore: DocsPage[] = corePages.map(([file, label], order) => ({ + source: `docs/core-data-structures/${file}`, + route: `en/core-data-structures/${file}`, + label, + sidebar: 'en-docs', + section: 'Data structures', + order, + ...(file === 'core.md' ? { sourceAliases: ['docs/core-data-structures'] } : {}), +})) + +const enCookbook: DocsPage[] = ([ + ['adding-a-package.md', 'Adding a package'], + ['adding-a-tool.md', 'Adding a tool'], + ['adding-an-llm-adapter.md', 'Adding an LLM adapter'], + ['extension-cookbook.md', 'Extension patterns'], +] as const).map(([file, label], order) => ({ + source: `docs/cookbook/${file}`, + route: `en/cookbook/${file}`, + label, + sidebar: 'en-docs', + section: 'Cookbook', + order, +})) + +/** Every canonical page published by the documentation website. */ +export const docsPages: DocsPage[] = [ + ...zhGuide, + ...zhDevelop, + ...enOverview, + ...enCatalogs, + ...enCore, + ...enCookbook, +] diff --git a/website/package.json b/website/package.json index 33c32fae4c..a2279418bb 100644 --- a/website/package.json +++ b/website/package.json @@ -4,12 +4,19 @@ "version": "0.0.1", "type": "module", "scripts": { - "dev": "vitepress dev . --port 5173 --open", + "dev": "vitepress dev . --host 127.0.0.1 --port 5173", "build": "vitepress build .", - "preview": "vitepress preview ." + "preview": "vitepress preview . --host 127.0.0.1 --port 4173" }, "devDependencies": { - "vitepress": "^1.6.3", - "vue": "^3.5.13" + "@braintree/sanitize-url": "7.1.2", + "cytoscape": "3.34.0", + "cytoscape-cose-bilkent": "4.1.0", + "dayjs": "1.11.21", + "debug": "4.4.3", + "mermaid": "11.16.0", + "vite": "^5.4.14", + "vitepress": "^1.6.4", + "vitepress-plugin-mermaid": "^2.0.17" } } diff --git a/website/zh-CN/api/cordis/context.md b/website/zh-CN/api/cordis/context.md deleted file mode 100644 index a18f275dad..0000000000 --- a/website/zh-CN/api/cordis/context.md +++ /dev/null @@ -1,85 +0,0 @@ -# Context - -上下文对象是 Cordis 的核心。所有服务、方法、属性都通过 `ctx` 访问。 - -## 服务与混入 - -Context 基于组合式 API 设计，大部分属性和方法挂载在服务上。以下是核心 API： - -- [`ctx.on`](./events#ctx-on) — 注册事件监听器 -- [`ctx.emit`](./events#ctx-emit) — 触发事件 -- [`ctx.bail`](./events#ctx-bail) — 短路事件 -- [`ctx.serial`](./events#ctx-serial) — 顺序异步事件 -- [`ctx.waterfall`](./events#ctx-waterfall) — 管道事件 -- [`ctx.effect`](./fiber#fiber-effect) — 注册可逆效果 -- [`ctx.plugin`](./registry#ctx-plugin) — 加载子插件 -- [`ctx.inject`](./registry#ctx-inject) — 获取依赖的插件 -- [`ctx.get`](#ctx-get) — 获取服务 -- [`ctx.set`](#ctx-set) — 设置服务 -- [`ctx.provide`](#ctx-provide) — 声明服务 - -## 实例属性 - -### ctx.fiber - -- **类型:** [`Fiber`](./fiber) - -当前上下文的作用域对象。 - -## 实例方法 - -### ctx.extend(meta) - -- **meta:** `object` -- **返回值:** `Context` - -构造一个以当前上下文为原型的新上下文实例。 - -### ctx.intercept(name, config) - -- **name:** `string` 服务名称 -- **config:** `object` 配置拦截 -- **返回值:** `Context` - -为指定服务添加一层配置拦截，返回新的上下文实例。 - -### ctx.isolate(name, label?) - -- **name:** `string` 服务名称 -- **label:** `symbol` 隔离域符号（可选） -- **返回值:** `Context` - -创建一个针对指定服务的隔离域，返回新的上下文实例。隔离域中的同名服务互不影响。 - -### ctx.get(name) - -- **name:** `string` 服务名称 -- **返回值:** `Service | undefined` - -获取指定名称的服务实例。 - -### ctx.set(name, value) - -- **name:** `string` 服务名称 -- **value:** `any` 服务值 - -设置指定名称的服务。 - -### ctx.provide(name, value?, options?) - -- **name:** `string` 服务名称 -- **value:** `any` 初始值（可选） -- **options:** `object` -- **返回值:** `void` - -声明一个服务。声明后其他插件可以通过 `inject` 依赖它。 - -## 静态属性 - -### Context.events - -内置事件服务的 symbol key。 - -### Context.current - -当前活跃的 Context 实例（在异步链中通过 AsyncLocalStorage 追踪）。 diff --git a/website/zh-CN/api/cordis/events.md b/website/zh-CN/api/cordis/events.md deleted file mode 100644 index dbc03a87bc..0000000000 --- a/website/zh-CN/api/cordis/events.md +++ /dev/null @@ -1,120 +0,0 @@ -# Events - -`ctx.events` 是内置服务，提供事件系统相关的全部 API。 - -## 实例方法 - -### ctx.on(event, listener, options?) {#ctx-on} - -- **event:** `string` 事件名称 -- **listener:** `Function` 事件监听器 -- **options:** `object` - - **prepend:** `boolean` 是否注册为前置（默认 `false`） - - **global:** `boolean` 是否注册为全局（默认 `false`） -- **返回值:** `() => void` 取消注册函数 - -注册一个事件监听器。返回的函数可用于手动取消注册，但通常不需要——插件卸载时会自动清理。 - -```typescript -ctx.on('agent/turn-end', (data) => { - console.log('turn ended:', data) -}) -``` - -### ctx.emit(thisArg?, event, ...args) {#ctx-emit} - -- **thisArg:** `any` 监听器的 `this` 参数（可选） -- **event:** `string` 事件名称 -- **args:** `any[]` 事件参数 -- **返回值:** `void` - -同步触发所有匹配的监听器（并行，不等待异步完成）。 - -### ctx.parallel(thisArg?, event, ...args) - -- 签名同 `emit` -- **返回值:** `Promise` - -异步触发所有匹配的监听器（并行等待）。 - -### ctx.bail(thisArg?, event, ...args) {#ctx-bail} - -- **返回值:** `any` - -同步依次触发监听器。第一个返回非 `undefined`/`null`/`false` 值的监听器停止链并返回该值。 - -### ctx.serial(thisArg?, event, ...args) {#ctx-serial} - -- **返回值:** `Promise` - -异步依次触发监听器。语义同 `bail` 的异步版本。 - -### ctx.waterfall(thisArg?, event, ...args) {#ctx-waterfall} - -- **返回值:** `Promise` - -管道模式：每个监听器接收前一个的输出。监听器内部必须调用 `next()` 才会传递给下一个。 - -```typescript -// 注册 -ctx.on('llm/pre-request', async (messages, next) => { - messages.push(extraMsg) - return next(messages) // 必须调用 -}) - -// 触发 -const result = await ctx.waterfall('llm/pre-request', initialMessages) -``` - -::: warning -不调用 `next()` 即为否决 (veto)——管道终止。这是设计行为，用于拦截/网关。 -::: - -## Harness 内置事件 - -### agent/pre-step - -- **触发模式:** serial -- **参数:** `{ agentId, turnIndex }` - -Agent 执行一步之前触发。 - -### agent/post-step - -- **触发模式:** emit -- **参数:** `{ agentId, turnIndex, blocks }` - -Agent 执行一步之后触发。 - -### tool/call - -- **触发模式:** emit -- **参数:** `{ name, args, callId }` - -Tool 被模型调用时触发。 - -### tool/result - -- **触发模式:** emit -- **参数:** `{ name, result, callId }` - -Tool 返回结果时触发。 - -### session/event - -- **触发模式:** emit -- **参数:** `SessionEvent` - -会话事件被记录时触发。 - -### compact/start - -- **触发模式:** emit - -上下文压缩开始。 - -### compact/end - -- **触发模式:** emit - -上下文压缩结束。 diff --git a/website/zh-CN/api/cordis/fiber.md b/website/zh-CN/api/cordis/fiber.md deleted file mode 100644 index ffb8f23bb5..0000000000 --- a/website/zh-CN/api/cordis/fiber.md +++ /dev/null @@ -1,108 +0,0 @@ -# Fiber - -Fiber（作用域）是插件实例的运行时容器，管理其生命周期和效果。 - -## 状态机 - -``` -PENDING → LOADING → ACTIVE → UNLOADING → DISPOSED - ↘ FAILED -``` - -| 状态 | 数值 | 含义 | -|------|------|------| -| PENDING | 0 | 依赖未就绪，等待中 | -| LOADING | 1 | 正在执行 `apply` | -| ACTIVE | 2 | 运行中 | -| FAILED | 3 | `apply` 抛出异常 | -| UNLOADING | 4 | 正在撤销效果 | -| DISPOSED | 5 | 已完全卸载 | - -## 实例属性 - -### fiber.uid - -- **类型:** `number` - -Fiber 的唯一标识符。 - -### fiber.status - -- **类型:** `number` - -当前状态（见状态机）。 - -### fiber.config - -- **类型:** `object` - -传递给插件的配置对象。 - -### fiber.error - -- **类型:** `Error | undefined` - -如果状态是 FAILED，包含导致失败的异常。 - -## 实例方法 - -### fiber.effect(callback) {#fiber-effect} - -- **callback:** `() => (() => void) | void` -- **返回值:** `() => void` - -注册一个效果。`callback` 在 Fiber 激活时执行；如果返回函数，该函数在 Fiber dispose 时执行。 - -```typescript -ctx.effect(() => { - const timer = setInterval(tick, 1000) - return () => clearInterval(timer) -}) -``` - -等价地可以通过 `ctx.effect()` 调用（ctx 代理到当前 fiber）。 - -### fiber.dispose() - -- **返回值:** `Promise` - -手动 dispose 该 Fiber。按注册逆序撤销所有效果，递归 dispose 所有子 Fiber。 - -```typescript -const child = ctx.plugin(somePlugin) -// 之后: -await child.dispose() -``` - -### fiber.update(config) - -- **config:** `object` 新配置 -- **返回值:** `void` - -热更新配置。如果新旧配置不同，触发 dispose + 重新 apply。 - -### fiber.restart() - -- **返回值:** `void` - -强制重启：dispose 后重新加载。 - -### fiber.then(resolve, reject?) - -- **返回值:** `Promise` - -使 Fiber 可以被 `await`：等到状态进入 ACTIVE 或 FAILED。 - -```typescript -const fiber = ctx.plugin(myPlugin) -await fiber // 等待插件加载完成 -``` - -## 访问当前 Fiber - -```typescript -export function apply(ctx: Context) { - const fiber = ctx.fiber // 当前插件的 Fiber - console.log(fiber.status) // 1 (LOADING, 因为正在 apply 中) -} -``` diff --git a/website/zh-CN/api/cordis/registry.md b/website/zh-CN/api/cordis/registry.md deleted file mode 100644 index e0f66d8ed7..0000000000 --- a/website/zh-CN/api/cordis/registry.md +++ /dev/null @@ -1,87 +0,0 @@ -# Registry - -插件注册表，管理插件的加载和依赖解析。 - -## 实例方法 - -### ctx.plugin(plugin, config?) {#ctx-plugin} - -- **plugin:** `Plugin` 插件（函数、对象或类） -- **config:** `object` 传递给插件的配置（可选） -- **返回值:** `Fiber` - -加载一个子插件，返回其 Fiber。子 Fiber 的生命周期绑定到父上下文。 - -```typescript -// 函数插件 -ctx.plugin(myPlugin, { key: 'value' }) - -// 类插件 -ctx.plugin(MyService) - -// 返回的 Fiber 可以 await 或 dispose -const fiber = ctx.plugin(myPlugin) -await fiber -``` - -### ctx.inject(names, callback) {#ctx-inject} - -- **names:** `string[]` 服务名列表 -- **callback:** `(ctx: Context) => void` -- **返回值:** `() => void` - -等待指定服务全部就绪后执行 callback。如果服务消失，callback 的效果会自动撤销；服务恢复后重新执行。 - -```typescript -ctx.inject(['tools', 'llm'], (ctx) => { - // tools 和 llm 都就绪了 - ctx.tools.register(/* ... */) -}) -``` - -这是 `export const inject = [...]` 声明的底层 API。大多数情况下直接使用声明式写法即可。 - -## 插件形态 - -`ctx.plugin()` 接受三种插件形态： - -### 函数插件 - -```typescript -function myPlugin(ctx: Context, config?: Config) { - // ... -} -myPlugin.name = 'my-plugin' -myPlugin.inject = ['tools'] -``` - -### 对象插件 - -```typescript -const myPlugin = { - name: 'my-plugin', - inject: ['tools'], - apply(ctx: Context, config?: Config) { - // ... - }, -} -``` - -### 类插件（Service） - -```typescript -class MyService extends Service { - static inject = ['tools'] - constructor(ctx: Context) { - super(ctx, 'myService') - } -} -``` - -## 插件元信息 - -| 属性 | 类型 | 说明 | -|------|------|------| -| `name` | `string` | 插件名称（日志用） | -| `inject` | `string[] \| { required?: string[], optional?: string[] }` | 依赖声明 | -| `Config` | `Schema \| object` | 配置 schema 或默认值 | diff --git a/website/zh-CN/api/cordis/service.md b/website/zh-CN/api/cordis/service.md deleted file mode 100644 index a57a00c461..0000000000 --- a/website/zh-CN/api/cordis/service.md +++ /dev/null @@ -1,97 +0,0 @@ -# Service - -Service 基类，用于创建对外暴露能力的插件。 - -## 基本用法 - -```typescript -import { Service, type Context } from 'cordis' - -declare module 'cordis' { - interface Context { - myService: MyService - } -} - -export default class MyService extends Service { - constructor(ctx: Context) { - super(ctx, 'myService') - } - - // 公开方法 - doSomething() { - // ... - } -} -``` - -加载后，其他插件可通过 `ctx.myService` 访问。 - -## 构造函数 - -### new Service(ctx, name) - -- **ctx:** `Context` 上下文 -- **name:** `string` 服务名（注册到 `ctx[name]`） - -## 实例属性 - -### service.ctx - -- **类型:** `Context` - -该服务绑定的上下文。 - -### service\[Service.tracker\] - -- **类型:** `object` - -服务追踪信息（名称、绑定状态等）。 - -## 生命周期 - -Service 子类可以覆写以下方法： - -### start() - -服务激活时调用。在这里初始化资源。 - -### stop() - -服务停用时调用。在这里释放资源。 - -## 静态属性 - -### Service.inject - -- **类型:** `string[] | { required?: string[], optional?: string[] }` - -声明本服务依赖的其他服务。 - -## 与 inject 的关系 - -当一个 Service 被加载： -1. 框架为该服务名创建声明 (`ctx.provide`) -2. 实例赋值到 `ctx[name]` -3. 依赖该服务的所有 Fiber 从 PENDING 转为 LOADING - -当 Service 被卸载： -1. `ctx[name]` 被置为 `undefined` -2. 依赖它的 Fiber 被 dispose -3. 当新的 provider 出现时，dependant Fiber 重新加载 - -## 示例：Harness 中的 Service - -```typescript -// dsh-tools 的 ToolRegistry 就是一个 Service -export class ToolRegistry extends Service { - constructor(ctx: Context) { - super(ctx, 'tools') - } - - register(tool: ToolDefinition): () => void { - // ...注册逻辑 - return dispose - } -} -``` diff --git a/website/zh-CN/api/harness/agent.md b/website/zh-CN/api/harness/agent.md deleted file mode 100644 index bf46c7e4e1..0000000000 --- a/website/zh-CN/api/harness/agent.md +++ /dev/null @@ -1,85 +0,0 @@ -# Agent (dsh-agent) - -Agent 实例管理和生命周期。 - -**包名:** `@deepseek-ai/dsh-agent` -**服务名:** `ctx.agents` - -## Agent Service - -### ctx.agents.create(options) - -- **options:** `AgentOptions` -- **返回值:** `Agent` - -创建一个新的 Agent 实例。 - -### ctx.agents.get(id) - -- **id:** `AgentId` -- **返回值:** `Agent | undefined` - -获取指定 ID 的 Agent 实例。 - -## AgentOptions - -```typescript -interface AgentOptions { - /** Agent ID（branded） */ - id?: AgentId - /** 使用的模型名 */ - model: string - /** 系统提示词（支持 {{model}} 变量） */ - persona?: string - /** 关联的 session */ - session?: Session -} -``` - -## Agent 实例 - -### agent.id - -- **类型:** `AgentId` - -Agent 的唯一标识符（branded string）。 - -### agent.model - -- **类型:** `string` - -Agent 使用的模型名。 - -### agent.step(input) - -- **input:** `ContentBlock[]` -- **返回值:** `Promise` - -执行一步：将输入发送给模型，获取响应，执行 tool calls。这是 agent-loop 内部使用的核心方法。 - -## Agent Loop - -Agent 的执行循环由 `dsh-agent-loop` 管理。它： - -1. 组装 system prompt + 历史消息 + 当前输入 -2. 调用 LLM（通过 `ctx.llm`） -3. 解析响应中的 tool calls -4. 执行 tools -5. 将 tool results 追加到 session -6. 如果 finish reason 是 `tool-calls`，回到步骤 2 - -### 扩展点 - -- `agent/pre-step` 事件 — 在每一步 LLM 调用前触发 -- `agent/post-step` 事件 — 在每一步完成后触发 -- `llm/pre-request` waterfall — 可修改发送给模型的消息 - -## AgentId - -Opaque branded string： - -```typescript -import { AgentId } from '@deepseek-ai/dsh-agent' - -const id = AgentId('main') -``` diff --git a/website/zh-CN/api/harness/bash.md b/website/zh-CN/api/harness/bash.md deleted file mode 100644 index 8e8d8d3068..0000000000 --- a/website/zh-CN/api/harness/bash.md +++ /dev/null @@ -1,81 +0,0 @@ -# Bash (dsh-bash) - -Bash 命令执行接口。 - -**接口包:** `@deepseek-ai/dsh-bash` -**实现:** `@deepseek-ai/dsh-bash-local` -**消费者:** `@deepseek-ai/dsh-tool-bash`（内置于 agent-core） - -## Bash Service - -### ctx.bash.execute(request) - -- **request:** `BashRequest` -- **返回值:** `Promise` - -执行一个 bash 命令。 - -## BashRequest - -```typescript -interface BashRequest { - /** 要执行的命令 */ - command: string - /** 工作目录 */ - workdir?: string - /** 超时时间 (ms) */ - timeoutMs?: number -} -``` - -## BashResult - -```typescript -interface BashResult { - /** 退出码 */ - exitCode: number - /** stdout 输出 */ - stdout: string - /** stderr 输出 */ - stderr: string - /** 是否超时 */ - timedOut: boolean -} -``` - -## 配置 (dsh-bash-local) - -```typescript -interface Config { - /** 命令超时时间，默认 120000 (2 分钟) */ - timeoutMs: number -} -``` - -在 `cordis.yml` 中： - -```yaml -- name: '@deepseek-ai/dsh-bash-local' - config: - timeoutMs: 60000 -``` - -## 模型可用的 Tools - -`dsh-tool-bash` 向模型暴露以下 tools（由 `agent-core` 捆绑）： - -| Tool | 说明 | -|------|------| -| `bash` | 执行命令（同步，等待完成） | -| `bash_output` | 获取后台命令的输出 | -| `bash_kill` | 终止后台命令 | - -## 设计模式 - -Bash 是 Harness 的"能力三件套"典型案例： - -- `dsh-bash`（接口）：定义 `ctx.bash` 和 `BashRequest`/`BashResult` 类型 -- `dsh-bash-local`（实现）：通过 `child_process.spawn` 在本地执行 -- `dsh-tool-bash`（消费者）：将能力包装为模型可调用的 tool - -换一个沙箱执行器只需替换 `dsh-bash-local`，接口和 tool 不变。 diff --git a/website/zh-CN/api/harness/fs.md b/website/zh-CN/api/harness/fs.md deleted file mode 100644 index 4e336ff962..0000000000 --- a/website/zh-CN/api/harness/fs.md +++ /dev/null @@ -1,78 +0,0 @@ -# Filesystem (dsh-fs) - -文件系统操作接口。 - -**接口包:** `@deepseek-ai/dsh-fs` -**实现:** `@deepseek-ai/dsh-fs-local` + `@deepseek-ai/dsh-fs-policy` -**消费者:** `@deepseek-ai/dsh-tool-fs` - -## FS Service - -### ctx.fs.read(path, options?) - -- **path:** `string` -- **options:** `{ offset?: number; limit?: number }` -- **返回值:** `Promise` - -读取文件内容。 - -### ctx.fs.write(path, content) - -- **path:** `string` -- **content:** `string` -- **返回值:** `Promise` - -写入文件（覆盖）。 - -### ctx.fs.edit(path, edits) - -- **path:** `string` -- **edits:** `Edit[]` -- **返回值:** `Promise` - -对文件执行精确的字符串替换编辑。 - -### ctx.fs.stat(path) - -- **path:** `string` -- **返回值:** `Promise` - -获取文件/目录信息。 - -## 配置 (dsh-fs-local) - -```typescript -interface Config { - /** 工作目录（相对路径的基准） */ - cwd: string -} -``` - -## 策略门 (dsh-fs-policy) - -`dsh-fs-policy` 是一个可选的中间层插件，实现 read-before-write/edit 策略——模型必须先读取文件才能写入或编辑。这防止模型盲目覆盖文件。 - -在 `cordis.yml` 中，它位于 `fs-local` 和 `tool-fs` 之间： - -```yaml -- name: '@deepseek-ai/dsh-fs-local' - config: - cwd: !!js process.cwd() -- name: '@deepseek-ai/dsh-fs-policy' -- name: '@deepseek-ai/dsh-tool-fs' -``` - -## 模型可用的 Tools - -| Tool | 说明 | -|------|------| -| `read` | 读取文件内容（支持 offset/limit） | -| `write` | 写入文件（需要先 read） | -| `edit` | 精确字符串替换（需要先 read） | - -## 三件套结构 - -- `dsh-fs`：接口定义 -- `dsh-fs-local`：本地文件系统实现 -- `dsh-fs-policy`：策略门（read-before-write 检查） -- `dsh-tool-fs`：模型 tool 层 diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md deleted file mode 100644 index 82a4d8e225..0000000000 --- a/website/zh-CN/api/harness/llm.md +++ /dev/null @@ -1,124 +0,0 @@ -# LLM (dsh-llm) - -LLM 服务接口和适配器注册。 - -**包名:** `@deepseek-ai/dsh-llm` -**服务名:** `ctx.llm` - -## LLM Service - -### ctx.llm.registerAdapter(models, adapter) - -- **models:** `string[]` 该适配器支持的模型名列表 -- **adapter:** `LlmAdapter` 适配器实例 -- **返回值:** `() => void` disposer - -注册一个 LLM 适配器。当请求中指定的模型名在 `models` 列表中时，路由到该适配器。 - -```typescript -ctx.llm.registerAdapter(['deepseek-v4-flash', 'deepseek-v4-pro'], adapter) -``` - -## LlmAdapter - -适配器基类。子类必须实现 `stream()` 方法。 - -### stream(options) - -- **options:** `GenerateOptions` -- **返回值:** `AsyncIterable` - -将统一请求格式转换为具体 API 的流式调用。 - -## GenerateOptions - -```typescript -interface GenerateOptions { - model: string - messages: Message[] - tools?: ToolSpec[] - system?: string - maxTokens?: number - temperature?: number -} -``` - -| 字段 | 说明 | -|------|------| -| `model` | 请求的模型名 | -| `messages` | 对话历史 | -| `tools` | 当前可用的 tool 列表（JSON Schema 格式） | -| `system` | 系统提示词 | -| `maxTokens` | 最大输出 token | -| `temperature` | 采样温度 | - -## StreamChunk - -流式响应的增量 chunk 类型： - -```typescript -type StreamChunk = - | { type: 'block-start'; index: number; blockType: 'text' | 'tool-call' } - | { type: 'text-delta'; index: number; text: string } - | { type: 'tool-call-delta'; index: number; id: CallId; name: string; argumentsDelta: string } - | { type: 'block-end'; index: number; block: ContentBlock } - | { type: 'usage'; usage: TokenUsage } - | { type: 'finish'; reason: FinishReason } -``` - -### 协议规则 - -1. 每个内容块以 `block-start` 开始，以 `block-end` 结束 -2. `index` 从 0 递增 -3. `text-delta` 只在 `blockType: 'text'` 的块中 -4. `tool-call-delta` 只在 `blockType: 'tool-call'` 的块中 -5. `usage` 在 `finish` 之前 -6. `finish` 必须是最后一个 chunk - -## CallId - -Tool call 的 opaque branded ID： - -```typescript -import { CallId } from '@deepseek-ai/dsh-llm' - -const id = CallId('call-abc123') -``` - -## TokenUsage - -```typescript -interface TokenUsage { - inputTokens: number - outputTokens: number -} -``` - -## FinishReason - -```typescript -type FinishReason = - | { kind: 'stop' } - | { kind: 'tool-calls' } - | { kind: 'max-tokens' } -``` - -## Message - -对话消息类型： - -```typescript -interface Message { - role: 'user' | 'assistant' - content: ContentBlock[] -} -``` - -## ContentBlock - -```typescript -type ContentBlock = - | { type: 'text'; text: string } - | { type: 'tool-call'; id: CallId; name: string; arguments: string } - | { type: 'tool-result'; callId: CallId; content: ContentBlock[]; isError?: boolean } -``` diff --git a/website/zh-CN/api/harness/session.md b/website/zh-CN/api/harness/session.md deleted file mode 100644 index 5ff5b0d97b..0000000000 --- a/website/zh-CN/api/harness/session.md +++ /dev/null @@ -1,56 +0,0 @@ -# Session (dsh-session) - -会话事件流管理。 - -**包名:** `@deepseek-ai/dsh-session` -**服务名:** `ctx.session` - -## 概述 - -Session 是 Agent 的对话状态容器。所有模型可见的内容都必须经过 session 事件流记录——这是"model-visible = logged"原则的实现。 - -## SessionSurface - -会话的外部接口，用于查询当前状态。 - -### surface.messages - -- **类型:** `Message[]` - -当前会话的完整消息列表（经过 compaction 处理后的视图）。 - -### surface.events - -- **类型:** `SessionEvent[]` - -原始事件流。 - -## SessionEvent - -会话中所有变更以事件形式记录： - -```typescript -type SessionEvent = - | { type: 'user/message'; content: ContentBlock[] } - | { type: 'assistant/message'; content: ContentBlock[] } - | { type: 'tool/call'; name: string; args: unknown; callId: CallId } - | { type: 'tool/result'; callId: CallId; content: ContentBlock[]; isError?: boolean } - | { type: 'compact/start'; range: [number, number] } - | { type: 'compact/end'; summary: string } - | { type: 'todo/write'; items: TodoItem[] } - // ... 更多事件类型 -``` - -## 设计原则 - -### Model-visible = Logged - -任何到达模型请求的内容都必须能从 session log 重建。如果你要引入新的模型可见输入，必须先定义对应的 session event。 - -### 事件是 append-only - -Session 事件流是只追加的。修改历史（如 compaction）通过新事件（compact/start + compact/end）表达，而不是修改旧事件。 - -### 持久化 - -Session 事件流可以通过 `dsh-session-persistence` 持久化到磁盘（JSONL 或 SQLite），实现跨进程恢复。 diff --git a/website/zh-CN/api/harness/subagent.md b/website/zh-CN/api/harness/subagent.md deleted file mode 100644 index 97ad7b5c87..0000000000 --- a/website/zh-CN/api/harness/subagent.md +++ /dev/null @@ -1,85 +0,0 @@ -# Subagent (dsh-subagent) - -子代理委派接口。 - -**接口包:** `@deepseek-ai/dsh-subagent` -**实现:** `@deepseek-ai/dsh-subagent-spawn` / `@deepseek-ai/dsh-subagent-fork` -**消费者:** `@deepseek-ai/dsh-tool-subagent` - -## Subagent Service - -### ctx.subagent.run(request) - -- **request:** `SubagentRequest` -- **返回值:** `Promise` - -委派一个任务给子代理执行。 - -## SubagentRequest - -```typescript -interface SubagentRequest { - /** 使用的 provider 名称 */ - provider: string - /** 委派给子代理的提示 */ - prompt: string - /** 子代理使用的模型（可选，默认继承父） */ - model?: string -} -``` - -## SubagentResult - -```typescript -interface SubagentResult { - /** 子代理的最终回复 */ - response: string -} -``` - -## Provider 模式 - -Subagent 支持多种"后端"（provider），通过配置选择： - -### spawn - -创建一个全新的子代理实例，没有父级的对话历史： - -```yaml -- name: '@deepseek-ai/dsh-subagent-spawn' - config: - providerName: spawn -``` - -### fork - -创建一个携带父级已完成 turn 前缀的子代理，子代理"知道"父级的对话上下文： - -```yaml -- name: '@deepseek-ai/dsh-subagent-fork' - config: - providerName: fork -``` - -## 模型可用的 Tools - -通过 `dsh-tool-subagent` 暴露。可以加载多次，每次绑定不同 provider： - -```yaml -# 暴露为 "subagent" tool，使用 spawn 后端 -- name: '@deepseek-ai/dsh-tool-subagent' - config: - provider: spawn - toolName: subagent - -# 暴露为 "subagent_fork" tool，使用 fork 后端 -- name: '@deepseek-ai/dsh-tool-subagent' - config: - provider: fork - toolName: subagent_fork -``` - -## 使用场景 - -- **spawn** — 独立子任务（如"搜索这个问题"），子代理不需要知道父级上下文 -- **fork** — 需要上下文的子任务（如"基于我们刚才讨论的，去实现这个"），子代理继承父级的对话前缀 diff --git a/website/zh-CN/api/harness/tools.md b/website/zh-CN/api/harness/tools.md deleted file mode 100644 index d2011ad85e..0000000000 --- a/website/zh-CN/api/harness/tools.md +++ /dev/null @@ -1,122 +0,0 @@ -# Tools (dsh-tools) - -Tool 注册表和 `defineTool` DSL。 - -**包名:** `@deepseek-ai/dsh-tools` -**服务名:** `ctx.tools` - -## ToolRegistry - -### ctx.tools.register(tool) - -- **tool:** `ToolDefinition` -- **返回值:** `() => void` disposer - -注册一个 tool。返回的 disposer 可手动撤销注册（通常不需要，插件卸载时自动撤销）。 - -## defineTool\(options) - -类型安全的 tool 定义辅助函数。 - -```typescript -import { defineTool } from '@deepseek-ai/dsh-tools' - -const tool = defineTool({ - name: 'read_file', - description: 'Read a file from disk.', - parameters: { - path: { type: 'string', required: true, description: 'Absolute file path' }, - offset: { type: 'number' }, - limit: { type: 'number', description: 'Max lines to read' }, - }, - async execute(args) { - // args: { path: string; offset?: number; limit?: number } - }, -}) -``` - -### DefineToolOptions\ - -| 字段 | 类型 | 说明 | -|------|------|------| -| `name` | `string` | Tool 名称（全局唯一） | -| `description` | `string` | 发送给模型的描述 | -| `parameters` | `SchemaSpec` | 参数 schema（见下文） | -| `execute` | `(args: InferArgs, exec: ToolExecution) => Promise` | 执行函数 | -| `presentCall?` | `(args: InferArgs) => ToolCallView \| undefined` | UI 展示（纯函数） | -| `presentResult?` | `(args: InferArgs, result: ToolResult) => ToolResultView \| undefined` | 结果 UI 展示（纯函数） | - -## SchemaSpec - -参数 schema DSL。每个属性是一个 `SchemaProp`： - -```typescript -interface SchemaProp { - type: 'string' | 'number' | 'boolean' | 'object' | 'array' - required?: true - description?: string - enum?: string[] - properties?: SchemaSpec // type: 'object' 时 - items?: SchemaProp // type: 'array' 时 -} -``` - -### 类型推导 (InferArgs) - -`InferArgs` 自动从 `SchemaSpec` 推导 TypeScript 类型： - -- `required: true` → 必填字段 -- 无 `required` → 可选字段（`?`） -- `type: 'object'` + `properties` → 递归推导嵌套对象 -- `type: 'array'` + `items` → 推导为数组 - -## ToolDefinition - -运行时 tool 定义（`defineTool` 的返回值）： - -```typescript -interface ToolDefinition { - name: string - description: string - parameters: Record // JSON Schema - execute(args: unknown, exec: ToolExecution): Promise - presentCall?(args: unknown): ToolCallView | undefined - presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined -} -``` - -## ToolExecuteReturn - -```typescript -type ToolExecuteReturn = - | ContentBlock[] // 仅内容 - | { content: ContentBlock[]; meta?: unknown } // 内容 + 元信息 -``` - -## ToolArgsError - -当模型生成的参数不匹配 schema 时抛出： - -```typescript -class ToolArgsError extends HarnessError { - code: 'INVALID_ARGS' - violations: string[] -} -``` - -框架自动捕获并转换为 `isError` 结果返回给模型。 - -## validateArgs(spec, args) - -- **spec:** `SchemaSpec` -- **args:** `unknown` -- **返回值:** `string[]` 违规信息列表（空 = 合法） - -手动校验参数。`defineTool` 内部使用，通常不需要直接调用。 - -## schemaSpecToJsonSchema(spec) - -- **spec:** `SchemaSpec` -- **返回值:** `JsonSchemaObject` - -将 SchemaSpec 转换为标准 JSON Schema。用于发送给模型的 wire format。 diff --git a/website/zh-CN/api/index.md b/website/zh-CN/api/index.md deleted file mode 100644 index 371cd1e622..0000000000 --- a/website/zh-CN/api/index.md +++ /dev/null @@ -1,25 +0,0 @@ -# API 参考 - -本节提供 DeepSeek Harness 的完整 API 参考文档，分为两部分： - -## 框架 API - -Cordis 微内核提供的基础能力，所有插件开发都建立在这些 API 之上： - -- [Context](./cordis/context) — 上下文对象，所有服务和方法的入口 -- [Events](./cordis/events) — 事件系统 API（emit / on / bail / serial / waterfall） -- [Fiber](./cordis/fiber) — 作用域生命周期（状态机、effect、dispose） -- [Registry](./cordis/registry) — 插件注册（plugin / inject） -- [Service](./cordis/service) — 服务基类 - -## Harness API - -DeepSeek Harness SDK 提供的扩展 API，用于构建 Agent 能力： - -- [Tools (dsh-tools)](./harness/tools) — Tool 注册、defineTool DSL、Schema 类型系统 -- [LLM (dsh-llm)](./harness/llm) — LLM 服务、适配器注册、StreamChunk 协议 -- [Session (dsh-session)](./harness/session) — 会话事件流、消息类型 -- [Agent (dsh-agent)](./harness/agent) — Agent 实例管理、生命周期 -- [Bash (dsh-bash)](./harness/bash) — Bash 执行接口 -- [Filesystem (dsh-fs)](./harness/fs) — 文件系统接口 -- [Subagent (dsh-subagent)](./harness/subagent) — 子代理委派接口 diff --git a/website/zh-CN/design/composability.md b/website/zh-CN/design/composability.md deleted file mode 100644 index 8370d8e136..0000000000 --- a/website/zh-CN/design/composability.md +++ /dev/null @@ -1,72 +0,0 @@ -# 可组合性与插件系统 - -## 组合 - -编程的本质就是组合。将小的构建块拼装为更大的系统，再将大系统作为块继续拼装——这是从函数到模块到微服务一脉相承的思想。 - -组合可以分为两种： - -- **静态组合**：编译期确定的组合，例如函数调用、模块导入。 -- **动态组合**：运行时确定的组合，例如热更新、插件加载/卸载。 - -静态组合是逻辑的组合；动态组合为可组合性引入了时间和空间两个新维度。 - -## 三种可组合性 - -| 维度 | 定义 | 对应问题 | -|------|------|----------| -| **逻辑可组合性** (Logical) | 功能能否被任意拆分和组装 | 接口设计是否正交 | -| **时间可组合性** (Temporal) | 能否灵活、安全地控制组合的运行时序 | 能否热加载/卸载而不泄漏 | -| **空间可组合性** (Spatial) | 能否灵活、安全地管理组合的依赖关系 | 依赖缺失时行为是否确定 | - -一门编程语言或应用框架越多地使用组合范式，就称它的可组合性越好。 - -## 传统插件系统的问题 - -插件系统是动态组合的典型形式。浏览器扩展、IDE 插件、操作系统驱动，都是其实例。然而大多数插件系统并不可靠。 - -### 不可逆的插件化 - -以 VSCode 为例： - -- 卸载或更新插件时需要重启整个系统。 -- 无法在运行时追踪和回收副作用，导致内存泄漏和非预期的资源占用。 -- 即便提供了 `deactivate` 钩子，也无法强制开发者正确实现清理逻辑。 - -**根本原因**：未做到时间可组合——系统不知道某个插件产生了哪些副作用、占用了哪些资源。 - -### 不完全的插件化 - -- 无法表达插件间的依赖关系，扩展能力受限。 -- 只有外围功能被下放给插件，核心功能依然通过修改主体代码来实现。 - -**根本原因**：未做到空间可组合——系统缺乏对依赖关系的建模和管理。 - -## Cordis 的解法 - -Cordis 同时解决了上述两个问题： - -1. **可逆作用** (Revertible Effects) 实现时间可组合性——所有注册自动追踪、自动回收。 -2. **响应式余作用** (Reactive Coeffects) 实现空间可组合性——依赖声明驱动加载顺序。 - -两者通过**上下文模型** (Context Model) 统一为单一的编程范式：开发者只需通过 `ctx` 调用框架 API，可逆性和依赖管理由框架保证。 - -## 在 Harness 中的体现 - -DeepSeek Harness 将 Cordis 的可组合性应用到 Agent 开发领域： - -```typescript -// 一个 Harness 插件天然是可逆的 -export const inject = ['tools', 'llm'] // 空间可组合：声明依赖 - -export function apply(ctx: Context) { - // 时间可组合：注册会被自动追踪和回收 - ctx.tools.register(defineTool('my-tool', { - description: '...', - parameters: { /* ... */ }, - async execute(args) { /* ... */ }, - })) -} -``` - -插件卸载时，tool 自动注销、事件监听自动移除——无需手动清理。依赖的服务（如 `llm`）消失时，插件自动挂起；恢复时自动重新加载。 diff --git a/website/zh-CN/design/context-model.md b/website/zh-CN/design/context-model.md deleted file mode 100644 index cc25df88e5..0000000000 --- a/website/zh-CN/design/context-model.md +++ /dev/null @@ -1,129 +0,0 @@ -# 上下文模型 - -上下文 (Context) 是 Cordis 将作用与余作用统一的运行时模型。它提供了一种编程范式，允许开发者无心智负担地编写时间、空间可组合的程序。 - -## 作用上下文 (Effect Context) - -当副作用被记录到全局环境时，$\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)$ 也就变成了一个更大的 $\mathcal{C}$。 - -递归地定义： - -$$ -\begin{matrix} -\mathcal{C}_1=\mathcal{C}_0\times\left(\mathcal{C}_0\to\mathcal{C}_0\right)\\ -\mathcal{C}_2=\mathcal{C}_1\times\left(\mathcal{C}_1\to\mathcal{C}_1\right)\\ -\cdots\\ -\mathcal{C}_{n+1}=\mathcal{C}_n\times\left(\mathcal{C}_n\to\mathcal{C}_n\right)\\ -\end{matrix} -$$ - -每一层 $\mathcal{C}$ 包含上一层的状态，同时记录了上一层的副作用。 - -利用递归类型得到真正的作用上下文： - -$$ -\mathcal{C}=\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right) -$$ - -这就是 Cordis Context 的理论根基：**上下文既是状态容器，又是副作用追踪器。** - -## 上下文的派生 - -当一个插件被加载时，从当前上下文派生出新的上下文实例： - -``` -Root Context -├── Plugin A Context ← 管理 A 的副作用 -│ └── Sub-plugin Context -└── Plugin B Context ← 管理 B 的副作用 -``` - -- 子级上下文管理插件内部的全部副作用 -- 插件整体作为一个副作用被父级上下文收集 -- 父级 dispose 时，子级先被 dispose（保证依赖逆序） - -## 余作用上下文 (Coeffect Context) - -余作用由作用产生： - -- **提供服务**本身是一种作用——它占用了服务命名空间资源 -- 因此服务的提供被记录在作用上下文中 -- 上下文将作用与余作用关联起来，提供了统一的时间、空间可组合性 - -```typescript -// 提供服务 = 一个 effect（占用 ctx.llm 这个 "资源"） -class LlmService extends Service { - // 当此插件卸载时，ctx.llm 被回收（effect 的逆操作） - // 所有依赖 llm 的插件因 coeffect 不满足而挂起 -} -``` - -## 基于上下文的开发范式 - -上下文模型提供了两个关键优势： - -### 无感性 (Transparent) - -框架将领域中的所有方法都封装为 effect 版本。开发者只需调用 `ctx` 上的方法，就能自动获得时间/空间可组合性： - -```typescript -export function apply(ctx: Context) { - // 以下每一行都是 effect——卸载时自动逆序回收 - ctx.on('agent/step-result', validateResult) - ctx.tools.register(myTool) - ctx.llm.registerAdapter(['my-model'], adapter) - - // 开发者无需知道"可逆作用"的存在 - // 只需通过 ctx 调用，框架保证一切安全 -} -``` - -### 渐进性 (Incremental) - -可以逐步将现有框架中的 API 替换为可组合版本，无需一次性重写： - -```typescript -// 第一步：用 ctx.effect 包装遗留 API -ctx.effect(() => { - const legacy = legacySystem.register(handler) - return () => legacySystem.unregister(legacy) -}) - -// 第二步：在未来将遗留 API 原生改造为 effect -// 两种方式可以并存 -``` - -## 在 Harness 中的完整图景 - -DeepSeek Harness 的运行时是一个 Context 树： - -``` -Root Context (Cordis 应用) -├── dsh-session (提供 ctx.sessions) -├── dsh-tools (提供 ctx.tools) -├── dsh-llm (提供 ctx.llm) -│ └── deepseek-adapter (注册模型适配器) -├── dsh-agent-loop (提供 ctx.agentLoop) -├── dsh-bash (提供 ctx.bash) -│ └── bash-local (本地执行器实现) -├── dsh-fs (提供 ctx.fs) -│ └── fs-local (本地 FS 实现) -├── dsh-system-prompt (提供 ctx.systemPrompt) -└── Agent Context (由 agents.create() 派生) - ├── Agent 自己注册的 tools - ├── Agent 的 session - └── Subagent Context (进一步派生) -``` - -每个节点都是一个 Context 实例。插件加载/卸载、服务出现/消失、Agent 创建/销毁——这一切都在 Context 树上以统一的语义发生。 - -## 总结 - -| 概念 | 解决的问题 | Cordis 机制 | -|------|-----------|-------------| -| 作用上下文 | 副作用追踪与回收 | `ctx.effect()` / `fiber.dispose()` | -| 上下文派生 | 副作用的层级隔离 | `ctx.plugin()` 创建子 Context | -| 余作用上下文 | 依赖的动态管理 | `inject` 声明 + 服务生命周期 | -| 统一范式 | 开发者无需关心底层机制 | 只需通过 `ctx` 调用 API | - -这就是为什么 Harness 能在保持「一切皆插件」的同时，不给插件开发者增加心智负担——**上下文模型把复杂性封装在了框架内部**。 diff --git a/website/zh-CN/design/effects-coeffects.md b/website/zh-CN/design/effects-coeffects.md deleted file mode 100644 index 01c181315f..0000000000 --- a/website/zh-CN/design/effects-coeffects.md +++ /dev/null @@ -1,69 +0,0 @@ -# 作用与余作用 - -## 作用 (Effects) - -Effects 是程序中对系统状态或外部环境产生影响的操作：I/O、状态修改、资源占用等。 - -学术界对作用有两种主要建模方式： - -### 单子作用 (Monadic Effects) - -- 通过单子 (monad) 将副作用封装为类型安全的计算链。 -- 提供 `return`（纯值注入）和 `bind`（链式组合）两个基本操作。 -- 以纯函数式的方式处理带有副作用的计算。(Moggi 1991, Wadler 1992) -- 代表语言：Haskell (IO Monad)、Rust (Result/Option) - -### 代数作用 (Algebraic Effects) - -- 允许在函数中"抛出"一个 effect，在调用栈的更高层次"捕获"并处理。 -- 类似异常处理，但更通用——处理后可以恢复执行。 -- 代表语言：Koka、Eff、OCaml 5+ (Kiselyov 2018, Kawahara 2020) - -## 余作用 (Coeffects) - -Coeffects 是程序执行时依赖的上下文信息：环境变量、系统资源、外部服务等。 - -- Coeffects 是 effects 的对偶 (dual) 概念，通常通过余单子 (comonad) 建模。(Petricek 2013, 2014; Brünnler 2014) -- 更前沿的理论将带有资源的上下文建模为 **graded algebra**（有序半环加最大元）： - - 加法 = 并行组合；0 元 = 无资源 - - 乘法 = 串行组合；1 元 = 单位资源 - - 序 = 资源约束；最大元 = 无限资源 - - (Breuvart 2015, Gaboardi 2016, Dal Lago 2022) - -## 现有理论的不足 - -这些理论主要面向**静态分析**和**短时程序**： - -1. **缺乏运行时追踪**：类型系统能标记副作用的存在，但无法在运行时追踪和回收。对长时运行程序（服务端、Agent），这意味着资源泄漏不可避免。 - -2. **缺乏动态性**：面向编译期分析，无法处理运行时的加载/卸载需求。 - -3. **崩溃而非降级**：类型不满足时直接拒绝编译或运行时崩溃，而长时运行程序更希望安全降级——挂起不满足依赖的部分，而非停止整个系统。 - -## Cordis 的突破 - -Cordis 选择了不同的路径——在运行时层面解决可组合性问题： - -| 现有理论 | Cordis 方案 | -|----------|-------------| -| 类型标记副作用 | 运行时追踪并自动回收副作用 | -| 编译期拒绝 | 运行时挂起/恢复 | -| 面向短时程序 | 面向长时运行程序设计 | - -这由两个互补机制实现： - -- **[可逆作用](./revertible-effects)** — 将副作用形式化为可逆的群操作 -- **[响应式余作用](./reactive-coeffects)** — 将依赖建模为具有生命周期的服务 - -## 在 Agent 开发中的意义 - -对 DeepSeek Harness 而言，作用/余作用模型直接支撑了以下能力： - -| 作用 (Effect) | 余作用 (Coeffect) | -|---------------|-------------------| -| 注册一个 tool | 依赖 tool registry 服务 | -| 注册一个 LLM adapter | 依赖 LLM 服务接口 | -| 监听 session 事件 | 依赖 session 服务存在 | -| 启动子进程 | 依赖 bash executor 实现 | - -每一个 effect 都可逆（tool 可注销、adapter 可移除）；每一个 coeffect 都有生命周期（服务消失则依赖者挂起）。这就是 Agent 能被安全热替换的根本原因。 diff --git a/website/zh-CN/design/index.md b/website/zh-CN/design/index.md deleted file mode 100644 index de6ebcf7aa..0000000000 --- a/website/zh-CN/design/index.md +++ /dev/null @@ -1,39 +0,0 @@ -# 系统设计 - -DeepSeek Harness 建立在 Cordis 微内核之上，采用「一切皆插件」的架构。本节阐述这套设计背后的理论基础和设计哲学。 - -## 核心思想 - -Harness 追求三种可组合性的统一： - -| 维度 | 含义 | Cordis 对应机制 | -|------|------|----------------| -| 逻辑可组合性 | 功能能否自由拆分和拼装 | 插件系统、事件系统 | -| 时间可组合性 | 运行时能否安全地加载/卸载功能 | 可逆作用、自动清理 | -| 空间可组合性 | 依赖关系能否被安全地声明和管理 | 服务生命周期、依赖注入 | - -这三种可组合性在上下文模型中统一为单一的编程范式。 - -## 目录 - -- [可组合性与插件系统](./composability) — 组合的本质，以及传统插件系统为什么不可靠 -- [作用与余作用](./effects-coeffects) — Cordis 效果系统的理论模型 -- [可逆作用](./revertible-effects) — 时间可组合性的形式化定义与证明 -- [响应式余作用](./reactive-coeffects) — 空间可组合性的服务语义 -- [上下文模型](./context-model) — Context 如何将作用与余作用统一 - -## 设计如何映射到 Harness - -| 理论概念 | Harness 中的体现 | -|----------|-----------------| -| 可逆作用 | `ctx.tools.register()` 返回 disposer；插件卸载时工具自动注销 | -| 响应式余作用 | `inject: ['llm']` 声明依赖；LLM 适配器不可用时插件自动挂起 | -| 上下文派生 | 子 Agent 拥有独立 Context，继承父级服务但有独立生命周期 | -| Waterfall 事件 | `agent/request` 链式拦截，任一监听器可决定最终请求参数 | -| Capability seam | bash/fs/web 三层拆分：接口 → 实现 → 模型工具 | - -## 进一步阅读 - -- [插件与生命周期](/zh-CN/develop/framework/) — 实践中的 Fiber 状态机 -- [服务与依赖](/zh-CN/develop/framework/service) — 服务声明与注入 -- [能力的三层拆分](/zh-CN/develop/practice/) — Capability seam 模式 diff --git a/website/zh-CN/design/reactive-coeffects.md b/website/zh-CN/design/reactive-coeffects.md deleted file mode 100644 index 45345f934a..0000000000 --- a/website/zh-CN/design/reactive-coeffects.md +++ /dev/null @@ -1,90 +0,0 @@ -# 响应式余作用 - -响应式余作用 (Reactive Coeffects) 是 Cordis 实现**空间可组合性**的核心机制。 - -- 将代码中的资源依赖抽象为服务 (service) 的概念 -- 通过运行时生命周期语义，实现自动、安全、高效的资源管理 - -## 依赖的本质是生命周期 - -传统的依赖注入（如 Angular DI、Spring IoC）解决的是"怎么拿到依赖"的问题，但忽略了一个关键问题：**依赖是有生命周期的**。 - -一个数据库连接池可能重启，一个 API 服务可能下线，一个 LLM adapter 可能被热替换。当依赖消失时，依赖者应当如何表现？ - -- 崩溃？——对长时运行程序不可接受。 -- 继续运行？——可能产生不一致状态。 -- **自动挂起，等待恢复？**——Cordis 的选择。 - -## 服务与生命周期 - -Cordis 将程序中的资源依赖抽象为**服务** (service)： - -- 任何插件都可以声明自己依赖的服务列表 -- 服务存在明确的生命周期（提供、撤销） -- 运行时对依赖不满足的插件**等待**，而非拒绝 -- 服务生命周期结束前，依赖该服务的插件**先一步被回收** - -```typescript -// LLM 适配器插件：提供 llm 服务 -export class LlmService extends Service { - static inject = ['http'] // 自身依赖 http - // 当 http 不可用时，LlmService 自动挂起 - // 挂起导致 ctx.llm 不可用 - // 所有 inject: ['llm'] 的插件级联挂起 -} -``` - -## 与现有理论的对比 - -### 与 Comonad 余作用比较 - -基于 Comonad 的余作用（Petricek 2013）将上下文建模为静态结构，侧重于编译期分析。Cordis 的响应式余作用额外引入了**时序语义**： - -- 服务可在运行时出现/消失 -- 依赖关系随之动态建立/解除 -- 效果的生命周期由依赖关系决定 - -### 与 Grade Algebra 余作用比较 - -基于 Grade Algebra 的余作用（Gaboardi 2016）用有序半环描述资源的组合规则。Cordis 的服务依赖可以建模为**交换半群**： - -- 服务名构成依赖集合 -- 集合并（∪）对应并行依赖 -- 交换律：依赖 A + B ≡ 依赖 B + A（声明顺序无关） -- 结合律：依赖分组方式不影响语义 - -但 Cordis 还增加了代数不具备的运行时行为：当集合中的某个服务不可用时，整个依赖集不满足，触发挂起。 - -## 在 Cordis 中的实现 - -```typescript -// 声明依赖 -export const inject = ['tools', 'llm'] - -export function apply(ctx: Context) { - // 到这里时，ctx.tools 和 ctx.llm 一定可用 - // 如果任一服务消失，此插件自动卸载 - // 服务恢复后，自动重新执行 apply -} -``` - -服务生命周期变化时的行为： - -``` -llm service 可用 → 依赖 llm 的插件 PENDING → ACTIVE -llm service 消失 → 依赖 llm 的插件 ACTIVE → DISPOSED -llm service 恢复 → 依赖 llm 的插件重新 PENDING → ACTIVE -``` - -## 为什么 Agent 需要响应式余作用 - -在 Harness 场景下，响应式余作用直接支撑： - -| 场景 | 行为 | -|------|------| -| LLM adapter 热替换 | 依赖 `llm` 的插件自动挂起/恢复，中间不丢状态 | -| 按需加载 bash 执行器 | bash tool 只在 `bash` 服务就绪后注册 | -| 子 Agent 独立服务空间 | 通过 `ctx.isolate()` 隔离服务实例，互不干扰 | -| 可选能力降级 | `inject: { web: { required: false } }` 允许 web 不可用时继续运行 | - -这意味着 Harness 插件开发者无需编写防御性的 "if service exists" 检查——框架保证：当你的 `apply` 被调用时，声明的依赖一定已就绪。 diff --git a/website/zh-CN/design/revertible-effects.md b/website/zh-CN/design/revertible-effects.md deleted file mode 100644 index 5133400e75..0000000000 --- a/website/zh-CN/design/revertible-effects.md +++ /dev/null @@ -1,128 +0,0 @@ -# 可逆作用 - -可逆作用 (Revertible Effects) 是 Cordis 实现**时间可组合性**的核心机制。 - -- 在单子作用的基础上增加可逆性约束 -- 提供面向长时运行程序的作用系统 -- 确保程序可以在插件粒度上回到任意状态 - -## 副作用的封装 - -现实中的程序需要与各种副作用打交道。假设一个不纯函数： - -$$ -f_\text{impure}: \text{X}\to\text{Y} -$$ - -我们将所有可能的副作用用类型 $\mathcal{C}$ 封装，函数变为： - -$$ -f: \mathcal{C}\times\text{X}\to\mathcal{C}\times\text{Y} -$$ - -对于长时运行程序，忽略函数本身的入参和出参，$f$ 属于函数空间 $\mathfrak{F}=\mathcal{C}\to\mathcal{C}$。 - -## 从幺半群到群 - -任何函数 $f: \mathcal{C}\to\mathcal{C}$ 都是状态空间到自身的变换。在组合 $\circ$ 下构成**幺半群**： - -1. 封闭性：$f\circ g$ 也是 $\mathcal{C}\to\mathcal{C}$ -2. 结合律：$(f\circ g)\circ h=f\circ (g\circ h)$ -3. 单位元：$\text{id}$，使得 $f\circ\text{id}=\text{id}\circ f=f$ - -如果额外要求每个 $f$ 存在逆元 $f^{-1}$（即副作用可回收），$\mathfrak{F}$ 升级为**群**。 - -## 副作用都可逆吗？ - -观察计算机中的副作用模式： - -| 操作 | 占用资源 | 逆操作 | -|------|----------|--------| -| 打开文件 | 文件描述符 | 关闭文件 | -| 创建子进程 | 进程号 | 杀死进程 | -| 监听端口 | 端口 | 取消监听 | -| 添加回调函数 | 事件槽位 | 删除回调 | -| 分配内存 | 内存区块 | 回收内存 | - -**副作用就是对资源的占用。** 计算机的资源天然设计为可重复使用，因此这些副作用一定是可逆的。 - -## 追踪和回收副作用 - -Cordis 通过 $\text{effect}$ 和 $\text{restore}$ 函子追踪和回收逆函数。 - -### effect 函子 - -$$ -\begin{array}{} -\text{effect}&:& -\left(\mathcal{C}\to\mathcal{C}\right)&\to& -\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)&\to& -\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)\\ -\text{effect}&=&f&\mapsto&\left(c, h\right)&\mapsto&\left(f(c), h\circ f^{-1}\right) -\end{array} -$$ - -直觉：执行 $f$ 产生的副作用记入状态 $c$，同时将逆操作 $f^{-1}$ 追加到回收链 $h$ 中。 - -### 同态性证明 - -$\text{effect}$ 是从 $\mathcal{C}\to\mathcal{C}$ 到 $\mathcal{C}\times(\mathcal{C}\to\mathcal{C})\to\mathcal{C}\times(\mathcal{C}\to\mathcal{C})$ 的同态： - -$$ -\begin{aligned} -\text{effect}\ (f\circ g) \left(c, h\right) -&=\left((f\circ g)(c), h\circ (f\circ g)^{-1}\right)\\ -&=\left(f(g(c)), h\circ g^{-1}\circ f^{-1}\right)\\ -&=\left(\text{effect}\ f\right)\left(g(c), h\circ g^{-1}\right)\\ -&=\left(\text{effect}\ f\right)\circ\left(\text{effect}\ g\right) \left(c, h\right) -\end{aligned} -$$ - -这意味着：组合两个操作后再追踪 = 分别追踪后再组合。副作用追踪与执行顺序无关。 - -### restore 函子 - -$$ -\begin{array}{} -\text{restore}&:& -\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)&\to& -\mathcal{C}\times\left(\mathcal{C}\to\mathcal{C}\right)\\ -\text{restore}&=&\left(c, h\right)&\mapsto&\left(h(c),\text{id}\right) -\end{array} -$$ - -直觉：将回收链 $h$ 应用到当前状态，一次性回收所有已追踪的副作用。 - -## 在 Cordis 中的实现 - -理论映射到 API： - -| 数学概念 | Cordis API | 说明 | -|----------|-----------|------| -| $\text{effect}(f)$ | `ctx.effect(() => { ...; return dispose })` | 注册副作用并返回清理函数 | -| $\text{restore}$ | `fiber.dispose()` | 执行 Fiber 的整个回收链 | -| $f^{-1}$ | dispose 返回值 / cleanup 函数 | 逆操作 | - -```typescript -export function apply(ctx: Context) { - // effect: 创建资源，返回其逆操作 - ctx.effect(() => { - const server = startServer(8080) // f: 占用端口 - return () => server.close() // f⁻¹: 释放端口 - }) - - // 框架 API 内部已封装 effect - ctx.on('event', handler) // 内部: effect(addListener, removeListener) - ctx.tools.register(myTool) // 内部: effect(addTool, removeTool) -} -// 当此插件被卸载时，restore 自动按逆序执行所有 f⁻¹ -``` - -## 为什么 Agent 需要可逆作用 - -在 Harness 场景下，可逆作用直接支撑： - -- **热替换 LLM 适配器**：卸载旧适配器（回收注册）、加载新适配器，无需重启 -- **动态 tool 管理**：根据对话上下文动态添加/移除 tool，不泄漏 -- **子 Agent 生命周期**：子 Agent 完成后，其注册的所有临时 tool 和监听器自动清理 -- **优雅关闭**：进程退出时所有插件按依赖逆序 dispose，确保资源完全释放 diff --git a/website/zh-CN/guide/config.md b/website/zh-CN/guide/config.md deleted file mode 100644 index d555a0a478..0000000000 --- a/website/zh-CN/guide/config.md +++ /dev/null @@ -1,342 +0,0 @@ -# 配置文件 - -Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参数运行。 - -## 从例子开始 - -### echo-agent 的配置 - -这是一开始的第一个 Agent 的完整配置： - -```yaml -# 热替换：修改代码后自动重载，不用手动重启 -- id: hmr - name: '@cordisjs/plugin-hmr' - config: - root: ['.'] - -# Mock 模型：从本地 `.ts` 文件加载，注册一个名为 `mock-llm` 的工具 -# 本地模拟 LLM 响应，不联网 -- id: mock-llm - name: './src/mock-llm.ts' - -# Echo 工具：收到文本后转大写返回 -- id: echo-tool - name: './src/echo-tool.ts' - -# Bash 执行器：从 npm 包 `@deepseek-ai/dsh-bash-local`加载，提供 bash 命令执行能力 -- id: bash - name: '@deepseek-ai/dsh-bash-local' - -# 应用主体：把 session 管理、tool 调度、agent loop 等组装成一个可交互的终端 Agent -# 只需告诉它用哪个模型 (`model`)、什么人设 (`persona`) -- id: stdio-agent - name: '@deepseek-ai/dsh-stdio-agent' - config: - model: mock-echo - persona: 'You are echo-agent, a demo agent.' - welcome: 'echo-agent ready. Type a message ("echo " triggers the tool).' - persistenceRoot: './.sessions' -``` - -### coding-agent 的配置 - -真实场景——接入 DeepSeek API，带完整工具链： - -```yaml -# 热替换：同上，开发时自动重载 -- id: hmr - name: '@cordisjs/plugin-hmr' - config: - root: ['.'] - -# LLM 后端：从 npm 包加载，具备接入 DeepSeek API 能力 -# `!!js` 从环境变量读取密钥，不会写进配置文件 -# `models` 声明该适配器能处理哪些模型名 -- id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - config: - apiKey: !!js process.env.DEEPSEEK_API_KEY - baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-pro - - deepseek-v4-flash - -# Bash 执行器：让 Agent 能跑 shell 命令 -# timeoutMs 设置单条命令的超时时间 -- id: bash - name: '@deepseek-ai/dsh-bash-local' - config: - timeoutMs: 60000 - -# 应用主体：和 echo-agent 一样的框架，只是配置不同 -# `model` 指定默认使用哪个模型（要和上面 models 列表里的名字对应） -# `persona` 是系统提示词，{{model}} 会被替换为实际模型名 -# `resumeSessionId` 设了就恢复旧对话，没设就每次新建 -- id: stdio-agent - name: '@deepseek-ai/dsh-stdio-agent' - config: - model: deepseek-v4-flash - resumeSessionId: !!js process.env.RESUME_SESSION_ID - persistenceRoot: './.sessions' - welcome: 'agent REPL ready. Give it a coding task.' - persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. - Verify your work by running the code or tests. Keep answers brief and factual. - -# 自动压缩：对话太长时自动总结旧内容，腾出上下文空间 -# contextWindow 是模型能看到的 token 上限 -# thresholdRatio 超过这个比例就触发压缩 -- id: compact-basic - name: '@deepseek-ai/dsh-compact-basic' - config: - contextWindow: 128000 - thresholdRatio: 0.8 - retainTokens: 20480 - maxTokens: 8192 - -# 子代理：把子任务分配给独立的 Agent 去做 -# subagent 是服务注册，spawn/fork 是两种委派方式： -# spawn — 全新子代理，不知道父级在聊什么 -# fork — 继承父级对话上下文的子代理 -# tool-subagent 把委派能力暴露给模型，toolName 是模型看到的工具名 -- id: subagent - name: '@deepseek-ai/dsh-subagent' - -- id: subagent-spawn - name: '@deepseek-ai/dsh-subagent-spawn' - config: - providerName: spawn - -- id: subagent-fork - name: '@deepseek-ai/dsh-subagent-fork' - config: - providerName: fork - -- id: tool-subagent - name: '@deepseek-ai/dsh-tool-subagent' - config: - provider: spawn - toolName: subagent - -- id: tool-subagent-fork - name: '@deepseek-ai/dsh-tool-subagent' - config: - provider: fork - toolName: subagent_fork - -# 任务追踪：模型可以用 todo_write 记录和更新任务清单 -- id: tool-todo - name: '@deepseek-ai/dsh-tool-todo' - -# 文件系统：让 Agent 能读写编辑文件 -# fs-local 提供本地文件操作能力，cwd 是工作目录 -# fs-policy 是安全策略——必须先读才能写，防止模型盲写 -# tool-fs 把能力暴露给模型（read / write / edit 三个工具） -- id: fs-local - name: '@deepseek-ai/dsh-fs-local' - config: - cwd: !!js process.cwd() - -- id: fs-policy - name: '@deepseek-ai/dsh-fs-policy' - -- id: tool-fs - name: '@deepseek-ai/dsh-tool-fs' -``` - -和 echo-agent 对比：同一个 `dsh-stdio-agent` 应用主体，只是把 mock 换成了真实 API，加上了更多工具插件。 - -## 语法详解 - -### 插件声明字段 - -每个插件条目支持以下字段： - -| 字段 | 类型 | 必填 | 说明 | -|------|------|------|------| -| `name` | string | 是 | 插件来源（npm 包名或相对路径） | -| `id` | string | 否 | 实例标识符，用于日志和调试 | -| `config` | object | 否 | 传递给插件的配置 | -| `disabled` | boolean | 否 | 设为 `true` 临时禁用该插件 | - -### 插件来源 (`name`) - -**npm 包** — 已安装的 `@deepseek-ai/dsh-*` 包或第三方包： - -```yaml -- name: '@deepseek-ai/dsh-llm-deepseek' -``` - -**相对路径** — 本地 TypeScript 文件（相对于 `cordis.yml` 所在目录）： - -```yaml -- name: './src/my-tool.ts' -``` - -### 环境变量 (`!!js`) - -用 `!!js` 标签在配置中引用运行时表达式： - -```yaml -config: - apiKey: !!js process.env.DEEPSEEK_API_KEY - cwd: !!js process.cwd() -``` - -::: warning -是 `!!js`（两个感叹号），不是 `!js`。写错了会静默失败。 -::: - -环境变量从仓库根目录的 `.env` 文件自动加载（已被 gitignore）。 - -### 禁用插件 - -不想删配置但暂时不加载？加一行 `disabled`： - -```yaml -- id: compact-basic - name: '@deepseek-ai/dsh-compact-basic' - disabled: true - config: - contextWindow: 128000 -``` - -## 各插件配置参考 - -### stdio-agent（标准应用主体） - -**包名:** `@deepseek-ai/dsh-stdio-agent` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `model` | string | **必填** | 使用的模型名，需与 LLM 适配器注册的名字一致 | -| `persona` | string | `''` | 系统提示词。支持 `{{model}}` 等模板变量 | -| `toolOrder` | string[] | — | 模型看到的工具顺序。省略则按字母排序 | -| `persistenceRoot` | string | `'./.sessions'` | 会话日志存储目录 | -| `welcome` | string | `'ready.'` | 启动时显示的欢迎信息 | -| `resumeSessionId` | string | — | 恢复指定会话 ID。留空则每次新建 | - -### llm-deepseek（DeepSeek 适配器） - -**包名:** `@deepseek-ai/dsh-llm-deepseek` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `apiKey` | string | `$DEEPSEEK_API_KEY` | API 密钥。省略则从环境变量读取 | -| `baseURL` | string | `$DEEPSEEK_BASE_URL` 或官方地址 | API 端点 | -| `models` | string[] | `['deepseek-v4-flash', 'deepseek-v4-pro']` | 注册的模型名列表 | -| `thinking` | `'enabled'` \| `'disabled'` | `'enabled'` | 是否开启思维链 | -| `reasoningEffort` | `'high'` \| `'max'` | — | 思维链深度（仅 thinking 开启时有效） | - -### bash-local（Bash 执行器） - -**包名:** `@deepseek-ai/dsh-bash-local` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `cwd` | string | `process.cwd()` | 命令执行的工作目录 | -| `timeoutMs` | number | `120000` | 单条命令的超时时间（毫秒） | -| `maxTimeoutMs` | number | `600000` | 单条命令超时的上限（模型不能请求更久） | -| `maxOutputBytes` | number | `64000` | 单次输出的内存上限（超出后溢出到临时文件） | -| `graceMs` | number | `3000` | kill 时从 SIGTERM 到 SIGKILL 的等待时间 | - -### compact-basic（自动压缩） - -**包名:** `@deepseek-ai/dsh-compact-basic` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `contextWindow` | number | **必填** | 模型的上下文窗口大小（token） | -| `thresholdRatio` | number | **必填** | token 占用超过此比例时触发压缩（0-1） | -| `retainTokens` | number | **必填** | 压缩后至少保留多少 token 的近期内容 | -| `maxTokens` | number | **必填** | 总结时的最大输出 token | -| `summarizationModel` | string | `''`（用当前模型） | 专门用于总结的模型名 | -| `compactionRetries` | number | **必填** | 首次压缩后仍超标时的额外重试次数 | -| `auto` | boolean | `true` | 是否自动在每步前检查并触发压缩 | -| `charsPerToken` | number | `4` | 每 token 估算字符数。中文应设 1-2 | - -### fs-local（文件系统） - -**包名:** `@deepseek-ai/dsh-fs-local` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `cwd` | string | `process.cwd()` | 工作目录，相对路径以此为基准 | - -### fs-policy（文件系统策略） - -**包名:** `@deepseek-ai/dsh-fs-policy` - -无配置项。加载即启用"必须先读才能写"的安全策略。 - -### tool-fs（文件系统工具） - -**包名:** `@deepseek-ai/dsh-tool-fs` - -无配置项。加载后向模型暴露 `read`、`write`、`edit` 三个工具。 - -### tool-web（Web 工具） - -**包名:** `@deepseek-ai/dsh-tool-web` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `search` | boolean | `true` | 是否注册 `web_search` 工具 | -| `fetch` | boolean | `true` | 是否注册 `web_fetch` 工具 | -| `searchMaxResults` | number | `8` | 单次搜索返回的最大结果数 | - -### subagent-spawn / subagent-fork（子代理后端） - -**包名:** `@deepseek-ai/dsh-subagent-spawn` / `@deepseek-ai/dsh-subagent-fork` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `providerName` | string | `'spawn'` / `'fork'` | 注册到子代理服务的 provider 名称 | - -### tool-subagent（子代理工具） - -**包名:** `@deepseek-ai/dsh-tool-subagent` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `provider` | string | **必填** | 使用哪个 provider（如 `spawn`、`fork`） | -| `toolName` | string | `'subagent'` | 暴露给模型的工具名。多次加载时必须不同 | -| `agentOptions.model` | string | — | 子代理使用的模型名（省略则继承父代理） | - -### tool-todo（任务清单） - -**包名:** `@deepseek-ai/dsh-tool-todo` - -无配置项。加载后向模型暴露 `todo_write` 工具。 - -### hmr（热替换） - -**包名:** `@cordisjs/plugin-hmr` - -| 字段 | 类型 | 默认值 | 说明 | -|------|------|--------|------| -| `root` | string[] | **必填** | 监听文件变更的目录列表 | - -::: tip -hmr 仅用于开发环境。它需要 `node --expose-internals` 启动参数，`demo:*` 脚本已自动添加。 -::: - ---- - -## 加载顺序 - -`cordis.yml` 的顺序就是加载顺序。推荐： - -1. **hmr** — 热替换（仅开发时需要） -2. **LLM 适配器** — 模型后端 -3. **执行器** — bash、fs 等能力提供者 -4. **应用主体** — `dsh-stdio-agent` 或 `dsh-acp-agent` -5. **附加插件** — compact、subagent、todo 等 - -应用主体内部已经捆绑了核心能力（session、tools、agent-loop），不需要手动加载。 - -## 下一步 - -- [开发插件](../develop/basic/) — 编写自己的插件 -- [API 参考](../api/) — 查看各插件完整接口 From 341b56ebc3b2fcd0d01d519bb0aa9c25847441e3 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Mon, 13 Jul 2026 15:51:35 +0800 Subject: [PATCH 002/323] docs(skill): add documentation site sync workflow --- .agents/skills/dsh-doc-site-sync/SKILL.md | 80 +++++++++++++++++++ .../dsh-doc-site-sync/agents/openai.yaml | 4 + 2 files changed, 84 insertions(+) create mode 100644 .agents/skills/dsh-doc-site-sync/SKILL.md create mode 100644 .agents/skills/dsh-doc-site-sync/agents/openai.yaml diff --git a/.agents/skills/dsh-doc-site-sync/SKILL.md b/.agents/skills/dsh-doc-site-sync/SKILL.md new file mode 100644 index 0000000000..0fdd9b9398 --- /dev/null +++ b/.agents/skills/dsh-doc-site-sync/SKILL.md @@ -0,0 +1,80 @@ +--- +name: dsh-doc-site-sync +description: Use when publishing, updating, moving, or removing DeepSeek Harness documentation website pages; editing website/docs.ts mappings or navigation; diagnosing a page missing from the VitePress site; fixing projected documentation links; or running the docs:dev, docs:check, and doc-sync workflow after website-content changes. +--- + +# Synchronizing the DeepSeek Harness Documentation Site + +Keep repository Markdown as the only editable content source. Treat the website as a tested projection: [website/docs.ts](../../../website/docs.ts) selects public pages, [scripts/project-doc-site.ts](../../../scripts/project-doc-site.ts) rewrites them into the disposable `website/.generated/` tree, and VitePress builds that tree. + +## Read the owning contracts + +- Read [docs/AGENTS.md](../../../docs/AGENTS.md) and use [dsh-doc-standards](../dsh-doc-standards/SKILL.md) when deciding where content belongs or changing product documentation prose. +- Use [dsh-translate-docs](../dsh-translate-docs/SKILL.md) whenever an edited source has a bilingual counterpart. +- Read the current `DocsPage` type and entries in [website/docs.ts](../../../website/docs.ts) before changing the manifest; do not rely on a remembered field set. +- Read [website/.vitepress/config.ts](../../../website/.vitepress/config.ts) before adding a new section, sidebar collection, locale, or top-level navigation item. + +## Classify the change + +- **Edit an already published page:** change only its canonical Markdown source. Do not touch the manifest unless its route or navigation metadata changes. +- **Publish a new page:** create it in its owning `docs/` tier, then add one manifest entry. +- **Rename, move, or remove a page:** update the canonical file, manifest entry, and inbound repository links atomically. Remove stale manifest entries; `docs:check` rejects missing sources. +- **Publish a generated catalog:** map the generated `docs/` file, but change its generator or source metadata rather than editing the catalog by hand. +- **Change site structure:** update the manifest for ordinary pages; update VitePress configuration only when the existing sidebar, section, or locale model cannot express the change. + +Never edit or commit `website/.generated/`, `website/.cache/`, or `website/.dist/`. Never copy a maintained `docs/` page into `website/`. + +## Add or update a manifest entry + +Set every `DocsPage` field deliberately: + +- `source`: repository-relative canonical Markdown path. +- `route`: public VitePress path including the `.md` suffix. +- `label`: sidebar label, not necessarily the document H1. +- `sidebar`: reuse `zh-guide`, `zh-develop`, or `en-docs` unless the information architecture genuinely needs another collection. +- `section`: reuse an existing section when possible. If adding one, also place it in `sectionOrder` in the VitePress config. +- `order`: stable order within the section. +- `sourceAliases`: optional additional repository paths that should resolve to this page when links are projected. It does not create another public route. + +Keep the manifest an explicit public allowlist. Do not publish RFCs, postmortems, testing guides, `AGENTS.md`, or maintainer workflows merely because they exist under `docs/`; add internal material only when the user explicitly changes the publication boundary. + +## Preserve link behavior + +Write normal repository-relative Markdown links in canonical docs. The projector applies these rules: + +- A target present in the manifest becomes a site-relative route. +- An existing target outside the manifest becomes a GitHub source link, including supported line suffixes. +- External URLs, site-absolute URLs, email links, and fragment-only links remain unchanged. +- A missing repository-relative target fails projection instead of silently producing a broken link. + +Do not write website-specific routes into canonical Markdown just to satisfy VitePress. Use `sourceAliases` for directory-style repository links that should resolve to a mapped index page. + +## Preview and validate + +Run local preview while editing: + +```sh +pnpm docs:dev +``` + +The dev server watches mapped source files and reprojects them. Restart it after changing the manifest if the new source is not picked up automatically. + +Run the focused website gate before treating the mapping as valid: + +```sh +pnpm docs:check +``` + +Before committing a documentation-site change, run: + +```sh +pnpm run doc-sync +pnpm run lint +git diff --check +``` + +Use [dsh-pre-push-checks](../dsh-pre-push-checks/SKILL.md) before pushing. Report the canonical files changed, manifest entries added or removed, public routes affected, and the exact checks run. + +## Keep deployment separate + +Synchronizing content into the VitePress build does not publish it to the internet. Do not add GitHub Pages permissions, deployment workflows, custom domains, or public hosting unless the user explicitly requests deployment and confirms the hosting policy. diff --git a/.agents/skills/dsh-doc-site-sync/agents/openai.yaml b/.agents/skills/dsh-doc-site-sync/agents/openai.yaml new file mode 100644 index 0000000000..9f4909f258 --- /dev/null +++ b/.agents/skills/dsh-doc-site-sync/agents/openai.yaml @@ -0,0 +1,4 @@ +interface: + display_name: "DSH Documentation Site Sync" + short_description: "Publish repository docs through the DSH website manifest" + default_prompt: "Use $dsh-doc-site-sync to publish or update a DeepSeek Harness documentation page on the website." From 89f9e4fc2109d7163461f0ea0f6ed771809dd9e1 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Mon, 13 Jul 2026 16:17:36 +0800 Subject: [PATCH 003/323] feat(fs-search): hide grep glob without rg --- docs/config-catalog.md | 2 +- ...6-07-09-bash-backed-grep-glob-discovery.md | 20 ++--- docs/tool-catalog.md | 4 +- examples/coding-agent/cordis.yml | 7 +- .../core/tools/tests/gen-tool-catalog.spec.ts | 13 ++++ packages/fs/README.md | 4 +- packages/fs/tool-fs-search/README.md | 12 +-- packages/fs/tool-fs-search/src/index.ts | 52 +++++++++++-- .../fs/tool-fs-search/tests/tools.spec.ts | 78 ++++++++++++++++--- scripts/gen-tool-catalog.ts | 72 +++++++++++++++-- 10 files changed, 218 insertions(+), 46 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 53db69125c..5ee653103e 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -871,7 +871,7 @@ export interface Config { } ``` -Source: [`packages/fs/tool-fs-search/src/index.ts:59`](../packages/fs/tool-fs-search/src/index.ts) +Source: [`packages/fs/tool-fs-search/src/index.ts:62`](../packages/fs/tool-fs-search/src/index.ts) ## `@deepseek-ai/dsh-tool-skill` diff --git a/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md b/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md index bc8a452c91..4644f3e07a 100644 --- a/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md +++ b/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md @@ -10,13 +10,13 @@ Search output also has two distinct budgets. The tool needs enough raw `rg` outp ## Decision -`glob` and `grep` are model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, backed by the bash seam, not by new `ctx.fs` provider methods. The package registers model-facing filesystem discovery tools, but execution uses `ctx.bash.resolve(request)` followed by `ctx.bash.run(spec)` with fixed `rg` command templates assembled by the tool. The tool layer owns schemas, argument validation, shell quoting, result parsing, result formatting, retention, formatted-result spill handoff, and timeout declaration. The bash executor owns request defaulting/capping, subprocess execution, process-group termination, environment scrubbing, raw output capture, and backend substitution across local, sandboxed, or remote bash implementations. +`glob` and `grep` are conditional model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, backed by the bash seam, not by new `ctx.fs` provider methods. At plugin load, the package checks `command -v rg >/dev/null 2>&1` through `ctx.bash.resolve(request)` followed by `ctx.bash.run(spec)`; if the command exits nonzero, the package logs a warning and registers neither tools nor prompt sections. A probe that cannot start, times out, aborts, is killed, or produces no exit code fails plugin load loudly because that is a broken bash executor rather than an absent optional binary. When registered, execution uses the same `ctx.bash.resolve(request)` followed by `ctx.bash.run(spec)` flow with fixed `rg` command templates assembled by the tool. The tool layer owns schemas, argument validation, shell quoting, result parsing, result formatting, retention, formatted-result spill handoff, and timeout declaration. The bash executor owns request defaulting/capping, subprocess execution, process-group termination, environment scrubbing, raw output capture, and backend substitution across local, sandboxed, or remote bash implementations. The tools do not use `ctx.bash.start()` and do not create model-visible background tasks. They run as ordinary foreground tools from the agent loop's perspective: the tool call returns only after the `rg` command exits, times out, is aborted, or fails. `defineTool({ timeoutMs })` declares the cooperative tool-call budget, `@deepseek-ai/dsh-timeout-policy` enforces it through `exec.signal`, and the tool forwards that signal into the bash request before `resolve()` / `run()`. The bash backend's own timeout remains a second safety cap; whichever aborts first wins. The tools align `path` with Claude Code's search tools while binding resolution to the bash workdir, not to `ctx.fs`. The tool derives the bash request workdir from `exec.agent?.session.header.cwd`, mirroring `dsh-tool-bash` and `dsh-tool-fs`; when no session cwd exists, it omits `request.workdir` so the bash implementation applies its configured cwd or process cwd through `resolve()`. For `grep`, `path` is an optional ripgrep target and may be a file or directory; omitted means the resolved bash workdir. For `glob`, `path` is an optional directory search root; omitted means the resolved bash workdir. Relative `path` values resolve against that workdir. Returned paths are displayed relative to the resolved bash workdir when possible and are intended to be follow-up-readable only in co-located deployments where the bash workdir and filesystem `read` root are the same workspace. v1 documents that deployment requirement but does not perform runtime cross-service validation. Remote or virtual filesystem search is deferred until there is a shared workspace/root contract or a provider-specific search backend. -The package does not inject `fs`. It injects `tools`, `systemPrompt`, and `bash`; it deliberately reads `spillStore` with `ctx.get('spillStore')` instead of static inject because formatted-result spill is optional. Existing `@deepseek-ai/dsh-tool-fs` deployments that only want `read` / `write` / `edit` do not need to load bash. +The package does not inject `fs`. It injects `tools`, `systemPrompt`, and `bash`; it deliberately reads `spillStore` with `ctx.get('spillStore')` instead of static inject because formatted-result spill is optional. Existing `@deepseek-ai/dsh-tool-fs` deployments that only want `read` / `write` / `edit` do not need to load bash. Deployments that load search need `rg` available in the bash executor environment for the tools to enter the model-visible schema. ### Package shape @@ -79,9 +79,9 @@ The `path` field follows the same split as Claude Code: `grep.path` is a file-or Raw `rg` stdout is an internal transport detail. The tool requests `stdoutMaxBytes: rawOutputMaxBytes` through `ctx.bash.resolve()` and parses `stdout.text` only when the executor returns untruncated stdout within that cap. If stdout is larger than `rawOutputMaxBytes`, or the executor still returns `stdout.truncated`, the tool fails with a clear search error telling the model to narrow `pattern`, `path`, or `include`. The tool never exposes raw `rg` output or bash raw spill paths to the model. -Only stdout is a parse source. Stderr is diagnostic text for invalid patterns, missing `rg`, and search failures; if bash truncates stderr, the tool uses the retained stderr tail with a truncation note and does not read `stderr.spillPath`. +Only stdout is a parse source. Stderr is diagnostic text for invalid patterns, runtime `rg` disappearance after registration, and search failures; if bash truncates stderr, the tool uses the retained stderr tail with a truncation note and does not read `stderr.spillPath`. -If `ctx.bash.run()` reports `aborted` because the tool timeout or caller cancellation fired, the tool returns a structured failure rather than pretending there were no matches. If bash reports its own timeout first, the tool likewise fails with a clear timeout message. Nonzero ripgrep exit semantics are tool-owned: exit 0 is success with matches, exit 1 is success with no matches, invalid pattern / missing `rg` / inaccessible search workdir are failures. +If `ctx.bash.run()` reports `aborted` because the tool timeout or caller cancellation fired, the tool returns a structured failure rather than pretending there were no matches. If bash reports its own timeout first, the tool likewise fails with a clear timeout message. Nonzero ripgrep exit semantics are tool-owned: exit 0 is success with matches, exit 1 is success with no matches, invalid pattern / runtime `rg` disappearance / inaccessible search workdir are failures. Search failures use a package-owned `HarnessError` subclass with `SEARCH_*` codes, not `FsErrorCode`, because these tools are not `ctx.fs` provider operations. The v1 vocabulary is `SEARCH_INVALID_PATTERN`, `SEARCH_FAILED`, `SEARCH_RAW_OUTPUT_OVERFLOW`, and `SEARCH_ABORTED`. Model argument validation failures such as missing required fields, blank strings, or unsupported negated/list `include` values remain ordinary tool argument errors. @@ -116,7 +116,7 @@ Line 12: ... (Full grep result stored at: /.../session-abc123/9f8e7d-grep-results.txt. Use read with offset/limit, or grep this path to search within it.) ``` -If the complete logical result fits under the inline cap, no formatted spill artifact is created. If the complete logical result is too large but formatted spill is unavailable, the footer says that the result was capped and the complete result could not be saved. The `truncated` / omitted count is a budget fact, not an incomplete-search fact; timeout, invalid regex, missing `rg`, inaccessible workdirs, raw-output overflow, binary skips, and parse failures stay in tool-domain error or incomplete fields. +If the complete logical result fits under the inline cap, no formatted spill artifact is created. If the complete logical result is too large but formatted spill is unavailable, the footer says that the result was capped and the complete result could not be saved. The `truncated` / omitted count is a budget fact, not an incomplete-search fact; timeout, invalid regex, runtime `rg` disappearance, inaccessible workdirs, raw-output overflow, binary skips, and parse failures stay in tool-domain error or incomplete fields. ## Alternatives considered @@ -138,22 +138,24 @@ If the complete logical result fits under the inline cap, no formatted spill art **Expand the bash seam with a raw-output reader first.** Rejected: a portable `readRawOutput(ref, maxBytes)` API would add reference lifetime, permission, and backend storage semantics. A per-run `stdoutMaxBytes` request is the narrower seam: search either receives complete stdout within `rawOutputMaxBytes` or fails clearly. +**Always register and report missing `rg` only at execution time.** Rejected: a model-visible tool schema is a promise that the deployment can attempt that capability. If the bash executor cannot find ripgrep at load, the safer surface is no `glob` / `grep` tools or prompt guidance. Execution-time missing-`rg` classification remains as a defensive fallback for environments that change after registration. + ## Testing -- Tests prove an aborted `exec.signal` reaches the bash backend (same-reference spec assertion plus the `SEARCH_ABORTED` result), and cover command construction/quoting (malicious patterns, paths with spaces, leading-dash values, quotes, newlines, glob metacharacters — unit assertions plus a real `bash -c` round-trip for every hostile value), `grep.path` as file and directory targets, `glob.path` as a directory search root, invalid pattern handling, no matches, malformed `rg --json` output, matched-line preview truncation, raw-output overflow, timeout/abort, formatted spill success/failure, the package-owned `SEARCH_*` error codes, and the no-background-task invariant. +- Tests cover registration-time `rg` probing (probe success registers both tools and prompt sections, nonzero probe skips both tools and prompt sections with a warning, infrastructure probe failures reject plugin load), prove an aborted `exec.signal` reaches the bash backend (same-reference spec assertion plus the `SEARCH_ABORTED` result), and cover command construction/quoting (malicious patterns, paths with spaces, leading-dash values, quotes, newlines, glob metacharacters — unit assertions plus a real `bash -c` round-trip for every hostile value), `grep.path` as file and directory targets, `glob.path` as a directory search root, invalid pattern handling, no matches, malformed `rg --json` output, matched-line preview truncation, raw-output overflow, timeout/abort, formatted spill success/failure, the package-owned `SEARCH_*` error codes, and the no-background-task invariant. - The first-party tool-owned spill precedent is covered directly: spill backend present, spill backend absent, `saveText()` failure, and missing spill owner. - The package has real Loader-path coverage for the namespace plugin export shape (`name`, `inject`, `Config`, and `apply`, with no default export). -- A real-executor integration suite (`dsh-bash-local` + a real `rg`) verifies the world: hostile patterns stay inert, per-session cwd resolution, VCS-metadata exclusion, modification-time ordering, and real ripgrep stderr classification. It self-skips where `rg` is not on PATH (a CI accommodation mirroring the keyless e2e skip); the fake-executor suite alone carries the per-file 100% coverage gate. +- A real-executor integration suite (`dsh-bash-local` + a real `rg`) verifies the world: hostile patterns stay inert, per-session cwd resolution, VCS-metadata exclusion, modification-time ordering, and real ripgrep stderr classification. It self-skips where `rg` is not on the test process PATH (a CI accommodation mirroring the keyless e2e skip); the fake-executor suite carries registration and execution coverage for missing `rg`, plus the per-file 100% coverage gate. - Snapshot gap note for the transcript-visible spill notice: this landed with the gap note, not a snapshot. The snapshot tier replays the acp-agent tree, and adding the search plugin there changes the assembled system prompt — every golden would need re-recording with a real key, which the implementing environment did not hold. The spill notice's exact transcript text is pinned by unit tests (`formatGlobOutput`/`formatGrepOutput` and the through-the-registry spill tests); wiring the plugin into the acp-agent tree plus a `test:snapshot:record` pass is the follow-up for the next key-holding session. ## Consequences -- `glob` and `grep` are model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, not `ctx.fs` provider methods and not part of the existing `@deepseek-ai/dsh-tool-fs` root plugin. The package injects `tools`, `systemPrompt`, and `bash`; it does not inject `fs`, and `ctx.spillStore` stays optional via `ctx.get('spillStore')`. +- `glob` and `grep` are conditional model-facing tools in `@deepseek-ai/dsh-tool-fs-search`, not `ctx.fs` provider methods and not part of the existing `@deepseek-ai/dsh-tool-fs` root plugin. They register only when the bash executor can find `rg`; the package injects `tools`, `systemPrompt`, and `bash`, does not inject `fs`, and keeps `ctx.spillStore` optional via `ctx.get('spillStore')`. - The schemas are exactly `glob(pattern, path?)` and `grep(pattern, path?, include?)`; search caps and timeout are defaulted, validated Config fields (`globMaxResults`, `grepMaxMatches`, `grepMaxLineBytes`, `rawOutputMaxBytes`, `timeoutMs`). - The tools execute through `ctx.bash.resolve(request)` → `ctx.bash.run(spec)`, forward `exec.signal`, never call `ctx.bash.start()`, and never expose a bash task id. The bash request workdir comes from `exec.agent?.session.header.cwd` when available; the resolved `spec.workdir` drives execution and relative-path display. - The tools request `stdoutMaxBytes: rawOutputMaxBytes` from the bash seam, parse only untruncated stdout within that cap, and treat over-cap or still-truncated raw output as a clear search failure; raw `rg` output is never exposed to the model. - Oversized complete formatted results are saved through `ctx.spillStore.saveText()` when available while inline results stay bounded; spill failure, a missing backend, or a missing owner preserves the inline result and reports the unsaved remainder — never an `isError`. -- The package README, the generated config catalog, and exported JSDoc document the Config fields and `SEARCH_*` codes; the coding-agent example ships the tools (the acp-agent tree waits on the snapshot re-record above); the fs group README records the co-located bash/filesystem deployment requirement. +- The package README, the generated config catalog, and exported JSDoc document the Config fields and `SEARCH_*` codes; the coding-agent example ships the conditional tool plugin (the acp-agent tree waits on the snapshot re-record above); the fs group README records the `rg` availability and co-located bash/filesystem deployment requirements. ## Risks diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 382eb04c4c..5b6e281b1a 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -20,7 +20,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-bash` | `bash`, `bash_kill`, `bash_output` | `ctx.tools`, `ctx.bash` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The bash/bash_output/bash_kill tools are model-facing consumers of the bash executor seam. | | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `live plugin-tree mutations (mount/unmount)` | - | Ships in examples/cordis-agent only (a deliberate opt-in — mounted code gets the real ctx, see docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins the model mounts may register ADDITIONAL model-visible tools at runtime; the request-header ToolsDelta logs those tool-set changes. | | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. | -| `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are bash-backed discovery tools: they run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | +| `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | | `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - | | `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. | | `@deepseek-ai/dsh-tool-todo` | `todo_write` | `ctx.tools`, `owning Agent session` | `tool/call`, `todo/write`, `tool/result` | - | todo_write is session-owned state; UIs render the latest todo/write event as a checklist or ACP plan. | @@ -428,7 +428,7 @@ Search file contents with a ripgrep regular expression. Returns matching lines w Source: [`packages/fs/tool-fs-search/src/index.ts`](../packages/fs/tool-fs-search/src/index.ts) -glob and grep are bash-backed discovery tools: they run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. +glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. ## `@deepseek-ai/dsh-tool-skill` diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index b23d785439..698ae97403 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -133,9 +133,10 @@ - id: tool-fs name: '@deepseek-ai/dsh-tool-fs' -# Bash-backed discovery tools (glob/grep): fixed ripgrep commands through the -# local bash executor above — not ctx.fs. Capped results save the complete -# formatted list through the spill backend below (ctx.spillStore, optional). +# Bash-backed discovery tools (glob/grep): if the local bash executor above +# can find rg, register fixed ripgrep commands — not ctx.fs. Capped results +# save the complete formatted list through the spill backend below +# (ctx.spillStore, optional). - id: tool-fs-search name: '@deepseek-ai/dsh-tool-fs-search' diff --git a/packages/core/tools/tests/gen-tool-catalog.spec.ts b/packages/core/tools/tests/gen-tool-catalog.spec.ts index 43490b99dc..b77cbdfd8d 100644 --- a/packages/core/tools/tests/gen-tool-catalog.spec.ts +++ b/packages/core/tools/tests/gen-tool-catalog.spec.ts @@ -61,6 +61,19 @@ describe('gen-tool-catalog collectToolCatalog', () => { expect(bash?.source).toBe('packages/bash/tool-bash/src/index.ts') }) + it('harvests search tools without depending on the generator process PATH', async () => { + const oldPath = process.env.PATH + try { + process.env.PATH = '' + const catalog = await collectToolCatalog() + const search = catalog.find(entry => entry.pkg === '@deepseek-ai/dsh-tool-fs-search') + expect(search?.schemas.map(s => s.name).sort()).toEqual(['glob', 'grep']) + } finally { + if (oldPath === undefined) delete process.env.PATH + else process.env.PATH = oldPath + } + }) + it('records the shipped `subagent_fork` alias in a note (config-driven tool name)', async () => { // `tool-subagent`'s registered name is the load-time `toolName` config, so // the shipped agents surface this one package as both `subagent` and diff --git a/packages/fs/README.md b/packages/fs/README.md index 039cb39ae9..ba57eede25 100644 --- a/packages/fs/README.md +++ b/packages/fs/README.md @@ -8,9 +8,9 @@ The filesystem stack: a provider seam (text IO + atomic mutation with an optiona | `fs-local/` | Local-filesystem `FileSystem` implementation | (registers `ctx.fs`) | | `fs-policy/` | Policy gate plugin: observed-state + read-before-edit + version-guarded write/edit, via the `fs/*` event gate | (no service — `fs/*` listeners) | | `tool-fs/` | Model-facing `read`/`write`/`edit` tools AND the executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`) | (registers on `ctx.tools`) | -| `tool-fs-search/` | Model-facing `glob`/`grep` discovery tools, backed by fixed ripgrep commands through the bash seam (`ctx.bash`), NOT by `ctx.fs` provider methods | (registers on `ctx.tools`) | +| `tool-fs-search/` | Model-facing `glob`/`grep` discovery tools when `rg` is available on the bash executor `PATH`, backed by fixed ripgrep commands through `ctx.bash`, NOT by `ctx.fs` provider methods | (registers on `ctx.tools`) | -The interface lives at `fs/fs/`. A sandboxed, remote, or project-scoped filesystem backend can replace `fs-local` without touching the seam, the policy gate, or the model-facing tool schemas. The policy (`fs-policy/`) is a plugin that participates only through the `fs/*` event gate, not a service the tool injects — so dropping it gracefully loses the policy and leaves the unconstrained bare provider rather than breaking the tool. A deployment that loads `tool-fs/` is expected to also load it. Discovery (`tool-fs-search/`) deliberately does NOT extend the provider seam: search is a process-backed `rg` workflow on the bash executor, so filesystem backends stay free of a universal search contract; its results are follow-up-readable when the bash workdir and the `read` root are the same workspace (the co-located deployment its README documents). +The interface lives at `fs/fs/`. A sandboxed, remote, or project-scoped filesystem backend can replace `fs-local` without touching the seam, the policy gate, or the model-facing tool schemas. The policy (`fs-policy/`) is a plugin that participates only through the `fs/*` event gate, not a service the tool injects — so dropping it gracefully loses the policy and leaves the unconstrained bare provider rather than breaking the tool. A deployment that loads `tool-fs/` is expected to also load it. Discovery (`tool-fs-search/`) deliberately does NOT extend the provider seam: search is a process-backed `rg` workflow on the bash executor, so filesystem backends stay free of a universal search contract; its tools register only when that executor can find `rg`, and its results are follow-up-readable when the bash workdir and the `read` root are the same workspace (the co-located deployment its README documents). ## No timeouts on file IO diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index 2f9df200de..81e0042e92 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -1,20 +1,20 @@ # @deepseek-ai/dsh-tool-fs-search -The **model-facing filesystem discovery tools** — `glob`, `grep` — backed by the **bash executor seam**, not by `ctx.fs` provider methods. Each call assembles a fixed ripgrep command (every model-controlled value through one package-private shell-quoting helper), runs it via `ctx.bash.resolve(request)` → `ctx.bash.run(spec)` as an ordinary foreground tool call, parses the raw `rg` output, and returns a bounded, workdir-relative result. The package injects `tools`, `systemPrompt`, and `bash` — deliberately **not** `fs`; `ctx.spillStore` is read opportunistically with `ctx.get()` because formatted-result spill is optional. +The **model-facing filesystem discovery tools** — `glob`, `grep` — backed by the **bash executor seam**, not by `ctx.fs` provider methods. At load, the package probes `command -v rg` through `ctx.bash`; if the executor cannot find ripgrep on its `PATH`, it logs a warning and registers no tools or prompt sections. Each call assembles a fixed ripgrep command (every model-controlled value through one package-private shell-quoting helper), runs it via `ctx.bash.resolve(request)` → `ctx.bash.run(spec)` as an ordinary foreground tool call, parses the raw `rg` output, and returns a bounded, workdir-relative result. The package injects `tools`, `systemPrompt`, and `bash` — deliberately **not** `fs`; `ctx.spillStore` is read opportunistically with `ctx.get()` because formatted-result spill is optional. ```ts ignore-check -// Default deployment: a bash executor, then the discovery tools. +// Default deployment: a bash executor whose PATH includes rg, then the discovery tools. await ctx.plugin(LocalBashExecutor, { cwd: process.cwd() }) // @deepseek-ai/dsh-bash-local -await ctx.plugin(ToolFsSearch) // this package — registers glob/grep +await ctx.plugin(ToolFsSearch) // this package — conditionally registers glob/grep // Optional: a spill backend makes capped results fully recoverable. await ctx.plugin(LocalSpillStore) // @deepseek-ai/dsh-spill-local ``` Why bash-backed: local workspace discovery is naturally a process-backed `rg` workflow, and putting search on `ctx.fs` would force every filesystem backend to grow a search API. The bash executor owns request defaulting/capping, subprocess execution, process-group termination, environment scrubbing, raw output capture, and backend substitution (local, sandboxed, remote); this package owns schemas, argument validation, shell quoting, parsing, retention, formatted-result spill, and timeout declaration. The tools never call `ctx.bash.start()` and never expose a bash task id — the call returns only after `rg` exits, times out, is aborted, or fails. -## Deployment requirement: co-located bash + filesystem +## Deployment requirement: rg + co-located bash/filesystem -Returned paths are displayed relative to the resolved bash workdir (the calling agent's session cwd when present, else the executor's configured default) and are follow-up-readable with `read` only when the bash workdir and the filesystem root are the same workspace. v1 documents that requirement and performs no runtime cross-service validation; remote or virtual filesystem search waits for a shared workspace contract or a provider-specific search backend. +The mounted bash executor must be able to resolve `rg` from its `PATH` at plugin load; otherwise `glob` and `grep` are absent from the model-visible tool schema. Returned paths are displayed relative to the resolved bash workdir (the calling agent's session cwd when present, else the executor's configured default) and are follow-up-readable with `read` only when the bash workdir and the filesystem root are the same workspace. v1 documents that co-location requirement and performs no runtime cross-service validation; remote or virtual filesystem search waits for a shared workspace contract or a provider-specific search backend. ## Config @@ -43,4 +43,4 @@ Raw `rg` stdout is an internal transport detail. Each search requests `stdoutMax ## Errors -Search failures carry the package-owned `SearchError` (a `HarnessError` subclass), surfaced as `{ name, code }` on `isError` results: `SEARCH_INVALID_PATTERN` (ripgrep rejected the regex/glob), `SEARCH_FAILED` (missing `rg`, inaccessible target, signal kill, malformed `--json` output), `SEARCH_RAW_OUTPUT_OVERFLOW` (raw output over `rawOutputMaxBytes`, or still truncated after the requested stdout capture budget), and `SEARCH_ABORTED` (tool timeout, caller cancellation, or the bash executor's own timeout). ripgrep exit semantics are tool-owned: exit 0 is success with results, exit 1 is a successful empty search (`No files found` / `No matches found`), and only other exits are failures. Model argument mistakes (blank pattern, a list-valued `include`) stay ordinary tool argument errors. +Search failures carry the package-owned `SearchError` (a `HarnessError` subclass), surfaced as `{ name, code }` on `isError` results: `SEARCH_INVALID_PATTERN` (ripgrep rejected the regex/glob), `SEARCH_FAILED` (runtime `rg` disappearance after registration, inaccessible target, signal kill, malformed `--json` output), `SEARCH_RAW_OUTPUT_OVERFLOW` (raw output over `rawOutputMaxBytes`, or still truncated after the requested stdout capture budget), and `SEARCH_ABORTED` (tool timeout, caller cancellation, or the bash executor's own timeout). ripgrep exit semantics are tool-owned: exit 0 is success with results, exit 1 is a successful empty search (`No files found` / `No matches found`), and only other exits are failures. Model argument mistakes (blank pattern, a list-valued `include`) stay ordinary tool argument errors. diff --git a/packages/fs/tool-fs-search/src/index.ts b/packages/fs/tool-fs-search/src/index.ts index 8c33d5770a..5930890b7a 100644 --- a/packages/fs/tool-fs-search/src/index.ts +++ b/packages/fs/tool-fs-search/src/index.ts @@ -1,6 +1,7 @@ /** * The model-facing filesystem discovery tool suite (`glob`, `grep`) over the - * bash executor seam (`ctx.bash`). This single plugin registers both tools. + * bash executor seam (`ctx.bash`). This single plugin registers both tools + * only when the mounted bash executor can find `rg` on its `PATH`. * * ## Bash-backed, not a `ctx.fs` provider method * @@ -12,9 +13,11 @@ * parsing, retention, formatted-result spill, and timeout declaration; the * bash executor owns request defaulting/capping, subprocess execution, * process-group termination, environment scrubbing, raw output capture, and - * backend substitution. The package injects `tools`, `systemPrompt`, and - * `bash` — deliberately NOT `fs`, and `ctx.spillStore` is read opportunistically - * with `ctx.get()` because formatted-result spill is optional. + * backend substitution. At load, the package probes `command -v rg` through the + * same bash seam; if ripgrep is absent, `glob` / `grep` and their prompt + * sections are not registered. The package injects `tools`, `systemPrompt`, + * and `bash` — deliberately NOT `fs`, and `ctx.spillStore` is read + * opportunistically with `ctx.get()` because formatted-result spill is optional. * * Returned paths are displayed relative to the resolved bash workdir and are * follow-up-readable only in co-located deployments where the bash workdir and @@ -80,6 +83,9 @@ export const Config: z = z.object({ /** The shape after schemastery applied the defaults. */ type ResolvedConfig = Required +/** POSIX-shell builtin probe for the ripgrep binary in the bash executor environment. */ +const RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' + /** Every search cap counts items/bytes/milliseconds — a positive integer, or retention and timeout arithmetic misbehaves silently. */ function assertPositiveInteger(name: string, value: number): void { if (!Number.isInteger(value) || value < 1) { @@ -87,8 +93,38 @@ function assertPositiveInteger(name: string, value: number): void { } } -/** Register the `glob`/`grep` filesystem discovery tool suite. */ -export function apply(ctx: Context, config: Config): void { +/** + * Check whether the mounted bash executor can find `rg`. + * + * Nonzero exit means "not available" and disables this optional tool suite. + * Infrastructure failures stay loud: a deployment with a broken bash executor + * should not silently lose tools in a way that looks like a deliberate skip. + * + * @param ctx - plugin context whose `bash` service is the executor the tools will use. + * @returns true when `command -v rg` exits 0, false when it exits nonzero. + */ +async function ripgrepAvailable(ctx: Context): Promise { + const spec = ctx.bash.resolve({ command: RG_PROBE_COMMAND }) + let result + try { + result = await ctx.bash.run(spec) + } catch (error: unknown) { + throw new Error(`tool-fs-search: ripgrep availability probe could not start: ${String(error)}`, { cause: error }) + } + if (result.aborted || result.timedOut || result.signal !== null || result.exitCode === null) { + throw new Error('tool-fs-search: ripgrep availability probe did not complete') + } + return result.exitCode === 0 +} + +/** + * Register the `glob`/`grep` filesystem discovery tool suite when `rg` exists. + * + * @param ctx - plugin context; registrations are effects scoped to this plugin. + * @param config - resolved plugin configuration from schemastery. + * @returns when ripgrep is unavailable, resolves without registering any tools. + */ +export async function apply(ctx: Context, config: Config): Promise { // schemastery (Config) has already filled every defaulted field. const resolved = config as ResolvedConfig assertPositiveInteger('globMaxResults', resolved.globMaxResults) @@ -96,6 +132,10 @@ export function apply(ctx: Context, config: Config): void { assertPositiveInteger('grepMaxLineBytes', resolved.grepMaxLineBytes) assertPositiveInteger('rawOutputMaxBytes', resolved.rawOutputMaxBytes) assertPositiveInteger('timeoutMs', resolved.timeoutMs) + if (!await ripgrepAvailable(ctx)) { + ctx.logger.warn('tool-fs-search: ripgrep (rg) not found on the bash executor PATH; glob/grep tools not registered') + return + } applyGlobTool(ctx, { maxResults: resolved.globMaxResults, rawOutputMaxBytes: resolved.rawOutputMaxBytes, diff --git a/packages/fs/tool-fs-search/tests/tools.spec.ts b/packages/fs/tool-fs-search/tests/tools.spec.ts index 9131940de5..648eb19585 100644 --- a/packages/fs/tool-fs-search/tests/tools.spec.ts +++ b/packages/fs/tool-fs-search/tests/tools.spec.ts @@ -2,12 +2,12 @@ * Consumer-surface tests for the search tools over a FAKE bash executor and a * FAKE spill backend, exercised through `ctx.tools.execute()` so nothing * bypasses the tool registry. The fake executor makes every seam outcome - * scriptable — truncated stdout with/without a raw spill path, abort/timeout, - * signal kills, ripgrep exit codes — so these tests verify schemas, argument - * validation, shell-safe command construction, workdir derivation, signal - * forwarding, `SEARCH_*` error classification, retention, formatted-result - * spill handoff, and the no-background-task invariant. Real-`rg` behavior is - * pinned separately in integration.spec.ts. + * scriptable — registration-time `rg` probing, truncated stdout with/without a + * raw spill path, abort/timeout, signal kills, ripgrep exit codes — so these + * tests verify schemas, argument validation, shell-safe command construction, + * workdir derivation, signal forwarding, `SEARCH_*` error classification, + * retention, formatted-result spill handoff, and the no-background-task + * invariant. Real-`rg` behavior is pinned separately in integration.spec.ts. */ import { describe, expect, it } from 'vitest' @@ -31,6 +31,8 @@ import { toWorkdirRelative, } from '@deepseek-ai/dsh-tool-fs-search' +const RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' + /** A successful run result over the given stdout; overrides script the failure shapes. */ function runResult(stdout: string, overrides?: Partial): BashRunResult { return { @@ -52,13 +54,18 @@ function runResult(stdout: string, overrides?: Partial): BashRunR * create a background task. */ class FakeBash extends BashExecutor { + probeRequests: BashExecRequest[] = [] + probeSpecs: BashExecSpec[] = [] requests: BashExecRequest[] = [] specs: BashExecSpec[] = [] startCalls = 0 + probeResult: BashRunResult = runResult('') + probeError?: Error handler: (spec: BashExecSpec) => BashRunResult = () => runResult('') override resolve(request: BashExecRequest): BashExecSpec { - this.requests.push(request) + if (request.command === RG_PROBE_COMMAND) this.probeRequests.push(request) + else this.requests.push(request) return { command: request.command, workdir: request.workdir ?? '/work', @@ -69,9 +76,14 @@ class FakeBash extends BashExecutor { sandboxMode: request.sandboxMode, } } - override run(spec: BashExecSpec): Promise { + override async run(spec: BashExecSpec): Promise { + if (spec.command === RG_PROBE_COMMAND) { + this.probeSpecs.push(spec) + if (this.probeError) throw this.probeError + return this.probeResult + } this.specs.push(spec) - return Promise.resolve(this.handler(spec)) + return this.handler(spec) } override start(): BashTask { this.startCalls++ @@ -113,18 +125,36 @@ class FakeSpill extends SpillStore { interface SetupOptions { config?: ToolFsSearch.Config spill?: boolean + probeError?: Error + probeResult?: BashRunResult } async function setup(options: SetupOptions = {}) { const ctx = new Context() + const warnings: string[] = [] + ctx.logger.warn = ((message: unknown) => { warnings.push(String(message)) }) as typeof ctx.logger.warn await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(FakeBash) + const bash = ctx.bash as FakeBash + if (options.probeResult) bash.probeResult = options.probeResult + if (options.probeError) bash.probeError = options.probeError if (options.spill === true) await ctx.plugin(FakeSpill) const fiber = await ctx.plugin(ToolFsSearch, options.config) - const bash = ctx.bash as FakeBash const spill = options.spill === true ? ctx.get('spillStore') as FakeSpill : undefined - return { ctx, bash, spill, fiber } + return { ctx, bash, spill, fiber, warnings } +} + +/** Assert plugin setup rejects without letting Vitest pretty-print a live Context on failure. */ +async function expectSetupRejects(options: SetupOptions, message: RegExp): Promise { + let thrown: string | undefined + try { + const loaded = await setup(options) + await loaded.fiber.dispose() + } catch (error: unknown) { + thrown = error instanceof Error ? error.message : String(error) + } + expect(thrown).toMatch(message) } /** A stand-in agent whose session header carries the given cwd (and a stable id). */ @@ -152,13 +182,37 @@ function matchLine(path: string, lineNumber: number, lineText: string): string { describe('registration', () => { it('registers glob and grep with their prompt sections', async () => { - const { ctx } = await setup() + const { ctx, bash } = await setup() + expect(bash.probeRequests).toHaveLength(1) + expect(bash.probeRequests[0]?.command).toBe(RG_PROBE_COMMAND) + expect(bash.probeRequests[0]).not.toHaveProperty('workdir') expect(ctx.tools.schemas().map(s => s.name).sort()).toEqual(['glob', 'grep']) const prompt = renderPrompt(await ctx.systemPrompt.assemble()) expect(prompt).toContain('Use the glob tool') expect(prompt).toContain('Use the grep tool') }) + it('does not register glob or grep when the bash executor cannot find rg', async () => { + const { ctx, warnings } = await setup({ probeResult: runResult('', { exitCode: 1 }) }) + expect(ctx.tools.schemas()).toHaveLength(0) + const sections = (await ctx.systemPrompt.assemble()).sections.map(s => s.name) + expect(sections).not.toContain('tool:glob') + expect(sections).not.toContain('tool:grep') + expect(warnings).toEqual([ + 'tool-fs-search: ripgrep (rg) not found on the bash executor PATH; glob/grep tools not registered', + ]) + }) + + it('rejects plugin load when the rg availability probe cannot run', async () => { + await expectSetupRejects({ probeError: new Error('spawn bash ENOENT') }, /spawn bash ENOENT/) + }) + + it('rejects plugin load when the rg availability probe is aborted or killed', async () => { + await expectSetupRejects({ + probeResult: runResult('', { aborted: true, exitCode: null, signal: 'SIGTERM' }), + }, /tool-fs-search: ripgrep availability probe did not complete/) + }) + it('stays pending until ctx.bash exists (inject)', async () => { const ctx = new Context() await ctx.plugin(SystemPrompt) diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index e317f2be24..91ac3adfd1 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -39,6 +39,8 @@ import { Context } from 'cordis' import type { ToolSchema } from '@deepseek-ai/dsh-llm' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' +import { BashExecutor } from '@deepseek-ai/dsh-bash' +import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId, BashTaskRead, OwnerToken } from '@deepseek-ai/dsh-bash' import LocalBashExecutor from '@deepseek-ai/dsh-bash-local' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' @@ -63,6 +65,65 @@ import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' const root = resolve(import.meta.dirname, '..') const OUT = 'docs/tool-catalog.md' +const CATALOG_RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' + +/** + * Minimal bash service for harvesting `dsh-tool-fs-search` schemas. The search + * plugin now probes `rg` at registration time, but the generated catalog must + * remain independent of the host PATH and never execute a real search. + */ +class CatalogSearchBashExecutor extends BashExecutor { + override resolve(request: BashExecRequest): BashExecSpec { + return { + command: request.command, + workdir: request.workdir ?? root, + timeoutMs: request.timeoutMs ?? 60_000, + stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000, + signal: request.signal, + owner: request.owner, + sandboxMode: request.sandboxMode, + } + } + + override run(spec: BashExecSpec): Promise { + if (spec.command !== CATALOG_RG_PROBE_COMMAND) { + throw new Error(`gen-tool-catalog: unexpected search bash command during schema harvest: ${spec.command}`) + } + return Promise.resolve({ + exitCode: 0, + signal: null, + timedOut: false, + aborted: false, + timeoutMs: spec.timeoutMs, + stdout: { text: '', truncated: false }, + stderr: { text: '', truncated: false }, + }) + } + + override start(): BashTask { + throw new Error('gen-tool-catalog: search schema harvest must not start bash tasks') + } + + override get(): BashTask | undefined { + return undefined + } + + override ownerOf(): OwnerToken | undefined { + return undefined + } + + override list(): BashTask[] { + return [] + } + + override readOutput(id: BashTaskId): BashTaskRead { + throw new Error(`gen-tool-catalog: unknown bash task ${id}`) + } + + override kill(id: BashTaskId): boolean { + throw new Error(`gen-tool-catalog: unknown bash task ${id}`) + } +} /** * One tool-plugin package to boot. `mount` is a per-entry recipe (async): it @@ -192,14 +253,15 @@ const TOOL_PACKAGES: ToolPackage[] = [ writes: ['tool/call', 'tool/result'], async mount(ctx) { // The tools inject `bash` (search executes fixed `rg` commands through - // the executor seam, not ctx.fs); boot the local executor to satisfy it. - // `ctx.spillStore` is optional (read via ctx.get) and does not affect the - // schemas, so no spill backend is mounted. - await ctx.plugin(LocalBashExecutor) + // the executor seam, not ctx.fs). Use a catalog-only executor so the + // registration-time `rg` probe stays deterministic and the generator + // never depends on the host PATH. `ctx.spillStore` is optional (read via + // ctx.get) and does not affect the schemas, so no spill backend is mounted. + await ctx.plugin(CatalogSearchBashExecutor) await ctx.plugin(ToolFsSearch) }, note: - 'glob and grep are bash-backed discovery tools: they run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.', + 'glob and grep are conditional bash-backed discovery tools: they register only when ctx.bash can find `rg`, then run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments.', }, { pkg: '@deepseek-ai/dsh-tool-skill', From faae2d389b2c2f957fa6e61cc71b1b0e5885ef51 Mon Sep 17 00:00:00 2001 From: Dudu-0223 Date: Mon, 13 Jul 2026 16:43:16 +0800 Subject: [PATCH 004/323] test(fs-search): make loader guard rg-independent --- .../fs/tool-fs-search/tests/load-path.spec.ts | 64 ++++++++++++++++++- 1 file changed, 62 insertions(+), 2 deletions(-) diff --git a/packages/fs/tool-fs-search/tests/load-path.spec.ts b/packages/fs/tool-fs-search/tests/load-path.spec.ts index d3c28619a3..90e4cc16cb 100644 --- a/packages/fs/tool-fs-search/tests/load-path.spec.ts +++ b/packages/fs/tool-fs-search/tests/load-path.spec.ts @@ -18,9 +18,69 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import { BashExecutor } from '@deepseek-ai/dsh-bash' +import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId, BashTaskRead, OwnerToken } from '@deepseek-ai/dsh-bash' import * as toolFsSearch from '@deepseek-ai/dsh-tool-fs-search' +const RG_PROBE_COMMAND = 'command -v rg >/dev/null 2>&1' + +/** + * Deterministic bash service for this Loader guard: the test wants to exercise + * the real unwrap/inject path, not depend on whether the host image has rg. + */ +class ProbeSuccessBashExecutor extends BashExecutor { + override resolve(request: BashExecRequest): BashExecSpec { + return { + command: request.command, + workdir: request.workdir ?? '/work', + timeoutMs: request.timeoutMs ?? 60_000, + stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000, + signal: request.signal, + owner: request.owner, + sandboxMode: request.sandboxMode, + } + } + + override run(spec: BashExecSpec): Promise { + if (spec.command !== RG_PROBE_COMMAND) { + throw new Error(`unexpected command in load-path guard: ${spec.command}`) + } + return Promise.resolve({ + exitCode: 0, + signal: null, + timedOut: false, + aborted: false, + timeoutMs: spec.timeoutMs, + stdout: { text: '', truncated: false }, + stderr: { text: '', truncated: false }, + }) + } + + override start(): BashTask { + throw new Error('load-path guard must not start bash tasks') + } + + override get(): BashTask | undefined { + return undefined + } + + override ownerOf(): OwnerToken | undefined { + return undefined + } + + override list(): BashTask[] { + return [] + } + + override readOutput(id: BashTaskId): BashTaskRead { + throw new Error(`unknown bash task ${id}`) + } + + override kill(id: BashTaskId): boolean { + throw new Error(`unknown bash task ${id}`) + } +} + describe('dsh-tool-fs-search real-load-path guard', () => { it('has no default export and keeps name/inject/Config through unwrapExports', () => { expect('default' in toolFsSearch).toBe(false) @@ -38,7 +98,7 @@ describe('dsh-tool-fs-search real-load-path guard', () => { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(LocalBashExecutor, {}) + await ctx.plugin(ProbeSuccessBashExecutor) const loader = Object.create(Loader.prototype) as Loader const unwrapped = loader.unwrapExports(toolFsSearch) as Parameters[0] From 6be219a0bc7cd2554282fc41a565b5c399271071 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Mon, 13 Jul 2026 17:47:42 +0800 Subject: [PATCH 005/323] fix(docs): address documentation site review --- docs/user/zh-CN/develop/basic/config.md | 17 +- docs/user/zh-CN/develop/basic/index.md | 13 +- docs/user/zh-CN/develop/basic/tool.md | 12 +- docs/user/zh-CN/develop/framework/events.md | 50 ++- docs/user/zh-CN/develop/framework/index.md | 12 +- docs/user/zh-CN/develop/framework/service.md | 17 +- .../zh-CN/develop/practice/llm-adapter.md | 7 +- docs/user/zh-CN/index.md | 2 +- scripts/project-doc-site.spec.ts | 37 ++- scripts/project-doc-site.ts | 18 +- website/.vitepress/config.ts | 61 +++- website/docs.ts | 299 +++++++++++------- 12 files changed, 333 insertions(+), 212 deletions(-) diff --git a/docs/user/zh-CN/develop/basic/config.md b/docs/user/zh-CN/develop/basic/config.md index 6c5bf6c651..23294f7955 100644 --- a/docs/user/zh-CN/develop/basic/config.md +++ b/docs/user/zh-CN/develop/basic/config.md @@ -4,10 +4,11 @@ ## 定义 Config 类型 -在插件中导出一个 `Config` 类型和可选的默认值： +在插件中导出一个 `Config` 类型和同名的 Schemastery schema；默认值直接写在 schema 中： ```typescript import type { Context } from 'cordis' +import Schema from 'schemastery' export const name = 'my-plugin' @@ -17,11 +18,11 @@ export interface Config { verbose?: boolean } -export const Config = { - greeting: 'Hello', - maxRetries: 3, - verbose: false, -} +export const Config: Schema = Schema.object({ + greeting: Schema.string().default('Hello'), + maxRetries: Schema.number().default(3), + verbose: Schema.boolean().default(false), +}) export function apply(ctx: Context, config: Config) { console.log(config.greeting) // 用户配置或默认值 @@ -37,7 +38,7 @@ export function apply(ctx: Context, config: Config) { maxRetries: 5 ``` -未提供的字段使用导出的 `Config` 对象中的默认值。 +插件加载时，Cordis 会通过导出的 schema 校验配置，并填充未提供字段的默认值。不要导出普通对象作为 `Config`，因为它不满足 Cordis 要求的 Standard Schema 接口。 ## Schema 校验 @@ -92,7 +93,7 @@ export interface Config { ```typescript export function apply(ctx: Context, config: Config) { - if (!ctx.llm.hasAdapter(config.model)) { + if (!ctx.llm.models().includes(config.model)) { throw new Error(`Model "${config.model}" is not registered by any LLM adapter`) } } diff --git a/docs/user/zh-CN/develop/basic/index.md b/docs/user/zh-CN/develop/basic/index.md index ce68283892..c1f7ab800b 100644 --- a/docs/user/zh-CN/develop/basic/index.md +++ b/docs/user/zh-CN/develop/basic/index.md @@ -28,10 +28,8 @@ import type { Context } from 'cordis' export const name = 'hello-plugin' export function apply(ctx: Context) { - // 监听 agent-loop 的 ready 事件 - ctx.on('ready', () => { - console.log('[hello-plugin] 插件已加载!') - }) + // apply 被调用时，插件的必选依赖已就绪 + console.log('[hello-plugin] 插件已加载!') } ``` @@ -100,17 +98,14 @@ export default { ### 类形式 ```typescript -import { Service } from 'cordis' +import { Service, type Context } from 'cordis' export default class MyService extends Service { static inject = ['tools'] constructor(ctx: Context) { super(ctx, 'myService') - } - - start() { - // 服务启动逻辑 + // 构造函数内完成同步初始化 } } ``` diff --git a/docs/user/zh-CN/develop/basic/tool.md b/docs/user/zh-CN/develop/basic/tool.md index 47a3af7867..9eb4715385 100644 --- a/docs/user/zh-CN/develop/basic/tool.md +++ b/docs/user/zh-CN/develop/basic/tool.md @@ -133,14 +133,14 @@ defineTool({ // ... presentCall(args) { return { - intent: 'terminal', - title: `bash(${JSON.stringify(args.command).slice(0, 60)})`, + card: 'terminal', + title: args.command, } }, presentResult(args, result) { return { - intent: 'terminal', - body: result.content.map(b => b.type === 'text' ? b.text : '').join(''), + card: 'terminal', + output: result.content.map(b => b.type === 'text' ? b.text : '').join(''), } }, }) @@ -156,9 +156,7 @@ defineTool({ // 这样就够了: ctx.tools.register(defineTool({ /* ... */ })) -// 不需要: -// const dispose = ctx.tools.register(...) -// ctx.on('dispose', dispose) +// 不需要额外保存 disposer 或注册清理逻辑 ``` ## 完整实战示例 diff --git a/docs/user/zh-CN/develop/framework/events.md b/docs/user/zh-CN/develop/framework/events.md index 641c63b0f8..80f49d38dc 100644 --- a/docs/user/zh-CN/develop/framework/events.md +++ b/docs/user/zh-CN/develop/framework/events.md @@ -24,15 +24,15 @@ Cordis 提供多种事件触发模式，适用于不同场景： ### emit — 广播 -所有监听器并行执行，不关心返回值： +所有监听器同步执行，不关心返回值： ```typescript // 触发 -ctx.emit('agent/turn-end', { agentId, turnIndex }) +ctx.emit('my-plugin/ready', { id: 'worker-1' }) // 监听 -ctx.on('agent/turn-end', ({ agentId, turnIndex }) => { - console.log(`Turn ${turnIndex} ended`) +ctx.on('my-plugin/ready', ({ id }) => { + console.log(`${id} is ready`) }) ``` @@ -53,7 +53,7 @@ ctx.on('some-check', (input) => { ### serial — 顺序执行 -所有监听器按注册顺序依次执行（异步安全）： +监听器按注册顺序依次执行，并等待异步结果；第一个返回非空值的监听器会终止后续执行： ```typescript await ctx.serial('setup-phase', context) @@ -61,18 +61,16 @@ await ctx.serial('setup-phase', context) ### waterfall — 管道 -每个监听器接收前一个的输出，形成数据管道。**必须调用 `next()` 传递给下游**，不调用即为否决： +每个监听器可以包装下游返回值，形成处理链。**必须调用 `next()` 传递给下游**，不调用即为否决： ```typescript // 触发 -const finalMessages = await ctx.waterfall('llm/pre-request', messages) +const output = await ctx.waterfall('my-plugin/transform', input, async () => input) // 监听（必须调用 next） -ctx.on('llm/pre-request', async (messages, next) => { - // 可以修改 messages - messages.push(extraMessage) - // 必须调用 next() 传递给下一个监听器 - return next(messages) +ctx.on('my-plugin/transform', async (_input, next) => { + const downstream = await next() + return downstream.trim() }) ``` @@ -89,6 +87,7 @@ declare module 'cordis' { interface Events { 'my-plugin/ready': (payload: { id: string }) => void 'my-plugin/check': (input: string) => boolean | undefined + 'my-plugin/transform': (input: string, next: () => Promise) => Promise } } @@ -96,20 +95,11 @@ declare module 'cordis' { // 都有正确的类型推导 ``` -## 命名约定 +## Cordis 事件与会话记录 -Harness 事件遵循 `namespace/action` 命名： +Harness 的 Cordis 事件遵循 `namespace/action` 命名，例如 `agent/pre-step`、`agent/request`、`agent/step-result`、`tools/result` 和 `session/event`。完整签名与触发模式见[Events 目录](../../../../cordis-catalog/events.md)。 -``` -agent/pre-step — agent 执行一步之前 -agent/post-step — agent 执行一步之后 -tool/call — tool 被调用 -tool/result — tool 返回结果 -llm/pre-request — LLM 请求发送前 -session/event — 会话事件被记录 -compact/start — 压缩开始 -compact/end — 压缩结束 -``` +`turn/*`、`step/*`、`tool/call`、`tool/result` 和 `compact/*` 是持久化的会话事件类型，不是同名 Cordis 事件。需要观察它们时，监听 `session/event` 并检查 `event.type`。 ## 事件也是效果 @@ -118,7 +108,7 @@ compact/end — 压缩结束 ```typescript export function apply(ctx: Context) { // 这个监听器在插件 dispose 时自动清理 - ctx.on('agent/turn-end', handler) + ctx.on('tools/result', handler) } ``` @@ -132,14 +122,10 @@ import type { Context } from 'cordis' export const name = 'tool-logger' export function apply(ctx: Context) { - ctx.on('tool/call', ({ name, args }) => { - console.log(`[tool] ${name}(${JSON.stringify(args)})`) - }) - - ctx.on('tool/result', ({ name, result }) => { + ctx.on('tools/result', (exec, result) => { + console.log(`[tool] ${exec.name}(${JSON.stringify(exec.arguments)})`) const text = result.content - .filter(b => b.type === 'text') - .map(b => b.text) + .map(block => block.type === 'text' ? block.text : '') .join('') console.log(`[tool result] ${text.slice(0, 100)}`) }) diff --git a/docs/user/zh-CN/develop/framework/index.md b/docs/user/zh-CN/develop/framework/index.md index b0547be61b..a3fdd502b5 100644 --- a/docs/user/zh-CN/develop/framework/index.md +++ b/docs/user/zh-CN/develop/framework/index.md @@ -105,14 +105,6 @@ fiber.dispose() export function apply(ctx: Context) { console.log('plugin loading') - ctx.on('ready', () => { - console.log('context ready') - }) - - ctx.on('dispose', () => { - console.log('plugin disposing') - }) - ctx.effect(() => { console.log('effect registered') return () => console.log('effect cleaned up') @@ -124,12 +116,10 @@ export function apply(ctx: Context) { ``` plugin loading effect registered -context ready ``` -卸载时输出（逆序）： +卸载时输出： ``` -plugin disposing effect cleaned up ``` diff --git a/docs/user/zh-CN/develop/framework/service.md b/docs/user/zh-CN/develop/framework/service.md index 17b9cb4e4e..19edf4a975 100644 --- a/docs/user/zh-CN/develop/framework/service.md +++ b/docs/user/zh-CN/develop/framework/service.md @@ -90,8 +90,11 @@ export default class MetricsService extends Service { // 必选：服务不存在时，插件不会加载 export const inject = ['tools'] -// 可选：服务不存在时，插件仍然加载，但 ctx.xxx 可能是 undefined -export const inject = { optional: ['metrics'] } +// 可选：不写入 inject，使用时通过 ctx.get() 查询 +export function apply(ctx: Context) { + const metrics = ctx.get('metrics') + metrics?.record('plugin_loaded', 1) +} ``` ### 服务消失时的行为 @@ -109,7 +112,10 @@ export const inject = { optional: ['metrics'] } ```yaml - id: group-a - name: 'group:' + name: '@cordisjs/plugin-group' + group: true + isolate: + bash: true config: - name: '@deepseek-ai/dsh-bash-local' config: @@ -117,7 +123,10 @@ export const inject = { optional: ['metrics'] } - name: './src/plugin-a.ts' - id: group-b - name: 'group:' + name: '@cordisjs/plugin-group' + group: true + isolate: + bash: true config: - name: '@deepseek-ai/dsh-bash-local' config: diff --git a/docs/user/zh-CN/develop/practice/llm-adapter.md b/docs/user/zh-CN/develop/practice/llm-adapter.md index 20b1fa2c88..0b0ae3cff0 100644 --- a/docs/user/zh-CN/develop/practice/llm-adapter.md +++ b/docs/user/zh-CN/develop/practice/llm-adapter.md @@ -114,6 +114,8 @@ interface GenerateOptions { maxTokens?: number /** 温度 */ temperature?: number + /** 取消或卸载时中止进行中的请求 */ + signal?: AbortSignal } ``` @@ -160,7 +162,10 @@ mock 适配器是学习 StreamChunk 协议的最佳起点——它用纯本地 ```typescript async *stream(options: GenerateOptions): AsyncIterable { - const response = await fetch(this.endpoint, { /* ... */ }) + const response = await fetch(this.endpoint, { + // ...method、headers 和 body + signal: options.signal, + }) if (!response.ok) { throw new Error(`API error: ${response.status}`) } diff --git a/docs/user/zh-CN/index.md b/docs/user/zh-CN/index.md index cbf700e41e..1c495125c6 100644 --- a/docs/user/zh-CN/index.md +++ b/docs/user/zh-CN/index.md @@ -13,7 +13,7 @@ hero: link: /develop/basic/ features: - title: 插件化架构 - details: 基于 Cordis 效果系统，所有能力通过插件注册，加载即生效、卸载即还原。 + details: 基于 Cordis 插件系统，所有能力通过插件注册，加载即生效、卸载即还原。 - title: 配置即组合 details: 一个 cordis.yml 决定整个 Agent 的能力组合——换模型、加工具，只需改一行配置。 - title: 开箱即用 diff --git a/scripts/project-doc-site.spec.ts b/scripts/project-doc-site.spec.ts index f44b779d80..9a6162576d 100644 --- a/scripts/project-doc-site.spec.ts +++ b/scripts/project-doc-site.spec.ts @@ -4,7 +4,7 @@ import { mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' -import type { DocsPage } from '../website/docs.ts' +import { docsPages, type DocsPage } from '../website/docs.ts' import { addProjectionFrontmatter, rewriteMarkdown } from './project-doc-site.ts' const roots: string[] = [] @@ -25,8 +25,10 @@ function fixture(): { root: string; pages: DocsPage[] } { return { root, pages: [ - { source: 'docs/a.md', route: 'en/a.md', label: 'A', sidebar: 'en-docs', section: 'Test', order: 1 }, - { source: 'docs/b.md', route: 'en/reference/b.md', label: 'B', sidebar: 'en-docs', section: 'Test', order: 2 }, + { locale: 'root', contentLocale: 'en-US', source: 'docs/a.md', route: 'a.md', label: 'A', sidebar: 'zh-reference', section: 'Test', order: 1 }, + { locale: 'root', contentLocale: 'en-US', source: 'docs/b.md', route: 'reference-root/b.md', label: 'B', sidebar: 'zh-reference', section: 'Test', order: 2 }, + { locale: 'en', contentLocale: 'en-US', source: 'docs/a.md', route: 'en/a.md', label: 'A', sidebar: 'en-reference', section: 'Test', order: 1 }, + { locale: 'en', contentLocale: 'en-US', source: 'docs/b.md', route: 'en/reference/b.md', label: 'B', sidebar: 'en-reference', section: 'Test', order: 2 }, ], } } @@ -36,6 +38,7 @@ describe('rewriteMarkdown', () => { const { root, pages } = fixture() const source = '[B](b.md#part) [source](../packages/tool.ts:2) [web](https://example.com)\n' expect(rewriteMarkdown(source, { + locale: 'en', sourcePath: 'docs/a.md', route: 'en/a.md', pages, @@ -48,9 +51,22 @@ describe('rewriteMarkdown', () => { ) }) + it('selects the published target in the current site locale', () => { + const { root, pages } = fixture() + expect(rewriteMarkdown('[B](b.md)\n', { + locale: 'root', + sourcePath: 'docs/a.md', + route: 'a.md', + pages, + repoRoot: root, + repositoryRef: 'abc123', + })).toBe('[B](./reference-root/b.md)\n') + }) + it('uses raw GitHub content for unpublished images', () => { const { root, pages } = fixture() expect(rewriteMarkdown('![logo](../packages/logo.svg)\n', { + locale: 'en', sourcePath: 'docs/a.md', route: 'en/a.md', pages, @@ -63,6 +79,7 @@ describe('rewriteMarkdown', () => { const { root, pages } = fixture() const source = '```md\n[B](b.md)\n```\n' expect(rewriteMarkdown(source, { + locale: 'en', sourcePath: 'docs/a.md', route: 'en/a.md', pages, @@ -74,6 +91,7 @@ describe('rewriteMarkdown', () => { it('fails loud when a relative target is missing', () => { const { root, pages } = fixture() expect(() => rewriteMarkdown('[missing](missing.md)\n', { + locale: 'en', sourcePath: 'docs/a.md', route: 'en/a.md', pages, @@ -83,6 +101,19 @@ describe('rewriteMarkdown', () => { }) }) +describe('docsPages locale routes', () => { + it('publishes the same canonical source at every corresponding locale route', () => { + const byRoute = new Map(docsPages.map(page => [page.route, page])) + for (const page of docsPages.filter(page => page.locale === 'root')) { + const counterpart = byRoute.get(`en/${page.route}`) + expect(counterpart, page.route).toBeDefined() + expect(counterpart?.locale).toBe('en') + expect(counterpart?.source).toBe(page.source) + expect(counterpart?.contentLocale).toBe(page.contentLocale) + } + }) +}) + describe('addProjectionFrontmatter', () => { it('adds frontmatter to an ordinary Markdown page', () => { expect(addProjectionFrontmatter('# Guide\n', 'docs/guide.md')).toBe( diff --git a/scripts/project-doc-site.ts b/scripts/project-doc-site.ts index 89e35dfdc8..7ef35a6d28 100644 --- a/scripts/project-doc-site.ts +++ b/scripts/project-doc-site.ts @@ -11,7 +11,7 @@ import { fromMarkdown } from 'mdast-util-from-markdown' import { gfmFromMarkdown } from 'mdast-util-gfm' import { gfm } from 'micromark-extension-gfm' import type { Nodes } from 'mdast' -import { docsPages, type DocsPage } from '../website/docs.ts' +import { docsPages, type DocsLocale, type DocsPage } from '../website/docs.ts' const REPOSITORY_URL = 'https://github.com/deepseek-harness/deepseek-harness' const root = resolve(import.meta.dirname, '..') @@ -25,6 +25,7 @@ interface Replacement { /** Inputs for rewriting one canonical Markdown page. */ export interface RewriteMarkdownOptions { + locale: DocsLocale sourcePath: string route: string pages: DocsPage[] @@ -62,14 +63,16 @@ function routeTarget(fromRoute: string, toRoute: string, suffix: string): string return `${target.startsWith('.') ? target : `./${target}`}${suffix}` } -function sourceMap(pages: DocsPage[]): Map { - const map = new Map() +function sourceMap(pages: DocsPage[]): Map> { + const map = new Map>() for (const page of pages) { for (const source of [page.source, ...(page.sourceAliases ?? [])]) { - if (map.has(source)) { - throw new Error(`project-doc-site: duplicate source or alias ${JSON.stringify(source)}.`) + const localized = map.get(source) ?? new Map() + if (localized.has(page.locale)) { + throw new Error(`project-doc-site: duplicate source or alias ${JSON.stringify(source)} for locale ${JSON.stringify(page.locale)}.`) } - map.set(source, page) + localized.set(page.locale, page) + map.set(source, localized) } } return map @@ -132,7 +135,7 @@ export function rewriteMarkdown(source: string, options: RewriteMarkdownOptions) if (path === '') return const { absPath, line } = resolveRepositoryTarget(sourceAbs, path, options.repoRoot) const targetPath = repoPath(absPath, options.repoRoot) - const page = published.get(targetPath) + const page = published.get(targetPath)?.get(options.locale) const nextUrl = page === undefined ? githubTarget(absPath, line, suffix, options.repositoryRef, options.repoRoot, node.type === 'image') : routeTarget(options.route, page.route, suffix) @@ -205,6 +208,7 @@ export function projectDocs(): void { const markdown = readFileSync(sourceAbs, 'utf8') const projected = rewriteMarkdown(markdown, { sourcePath: page.source, + locale: page.locale, route: page.route, pages: docsPages, repoRoot: root, diff --git a/website/.vitepress/config.ts b/website/.vitepress/config.ts index 71c276794a..b553d6b2da 100644 --- a/website/.vitepress/config.ts +++ b/website/.vitepress/config.ts @@ -13,6 +13,14 @@ const sectionOrder = [ '基础', '框架能力', '实战', + '概念', + '生成参考', + '数据结构', + '开发手册', + 'Guide', + 'Basics', + 'Framework', + 'Practice', 'Concepts', 'Generated reference', 'Data structures', @@ -20,7 +28,7 @@ const sectionOrder = [ ] function sidebar(collection: DocsPage['sidebar']): DefaultTheme.SidebarItem[] { - const pages = docsPages.filter(page => page.sidebar === collection && page.route !== 'index.md') + const pages = docsPages.filter(page => page.sidebar === collection) const sections = new Map() for (const page of pages) { const entries = sections.get(page.section) ?? [] @@ -51,7 +59,36 @@ function escapeVueInterpolation(html: string): string { } const sharedTheme: Pick = { - search: { provider: 'local' }, + search: { + provider: 'local', + options: { + locales: { + root: { + translations: { + button: { + buttonText: '搜索文档', + buttonAriaLabel: '搜索文档', + }, + modal: { + displayDetails: '显示详细列表', + resetButtonTitle: '清除搜索', + backButtonTitle: '关闭搜索', + noResultsText: '未找到相关结果', + footer: { + selectText: '选择', + selectKeyAriaLabel: '回车键', + navigateText: '切换', + navigateUpKeyAriaLabel: '上方向键', + navigateDownKeyAriaLabel: '下方向键', + closeText: '关闭', + closeKeyAriaLabel: 'Esc 键', + }, + }, + }, + }, + }, + }, + }, socialLinks: [ { icon: 'github', link: 'https://github.com/deepseek-harness/deepseek-harness' }, ], @@ -81,14 +118,22 @@ export default withMermaid({ nav: [ { text: '入门', link: '/guide/', activeMatch: '^/guide/' }, { text: '开发', link: '/develop/basic/', activeMatch: '^/develop/' }, - { text: 'Reference', link: '/en/', activeMatch: '^/en/' }, + { text: '参考', link: '/reference/', activeMatch: '^/reference/' }, ], sidebar: { '/guide/': sidebar('zh-guide'), '/develop/': sidebar('zh-develop'), + '/reference/': sidebar('zh-reference'), }, outline: { label: '本页目录' }, docFooter: { prev: '上一篇', next: '下一篇' }, + darkModeSwitchLabel: '外观', + lightModeSwitchTitle: '切换到浅色主题', + darkModeSwitchTitle: '切换到深色主题', + sidebarMenuLabel: '菜单', + returnToTopLabel: '返回顶部', + langMenuLabel: '切换语言', + skipToContentLabel: '跳至内容', }, }, en: { @@ -97,12 +142,14 @@ export default withMermaid({ link: '/en/', themeConfig: { nav: [ - { text: 'Concepts', link: '/en/' }, - { text: 'Reference', link: '/en/config-catalog' }, - { text: '中文指南', link: '/guide/' }, + { text: 'Guide', link: '/en/guide/', activeMatch: '^/en/guide/' }, + { text: 'Develop', link: '/en/develop/basic/', activeMatch: '^/en/develop/' }, + { text: 'Reference', link: '/en/reference/', activeMatch: '^/en/reference/' }, ], sidebar: { - '/en/': sidebar('en-docs'), + '/en/guide/': sidebar('en-guide'), + '/en/develop/': sidebar('en-develop'), + '/en/reference/': sidebar('en-reference'), }, editLink: { pattern: ({ frontmatter }: PageData) => { diff --git a/website/docs.ts b/website/docs.ts index 53e74c2905..16d53e5b8a 100644 --- a/website/docs.ts +++ b/website/docs.ts @@ -1,20 +1,38 @@ /** * Canonical publication manifest for the documentation website. * - * Markdown stays in its owning repository tier. This manifest only maps a - * source file to its public route and navigation placement. + * Markdown stays in its owning repository tier. This manifest maps each + * canonical source into matching route trees for both site locales; when a + * translation is absent, both routes intentionally project the available + * source instead of copying Markdown. */ +/** Locale key used by the VitePress site. */ +export type DocsLocale = 'root' | 'en' + +/** Sidebar collection rendered for one locale and top-level module. */ +type DocsSidebar = + | 'zh-guide' + | 'zh-develop' + | 'zh-reference' + | 'en-guide' + | 'en-develop' + | 'en-reference' + /** A page projected into the VitePress source tree. */ export interface DocsPage { + /** VitePress locale whose route tree owns this projection. */ + locale: DocsLocale + /** Language of the canonical source currently projected at this route. */ + contentLocale: 'zh-CN' | 'en-US' /** Repository-relative canonical Markdown source. */ source: string /** VitePress route, including the `.md` suffix. */ route: string /** Navigation label shown in the sidebar. */ label: string - /** Sidebar collection that owns the page. */ - sidebar: 'zh-guide' | 'zh-develop' | 'en-docs' + /** Sidebar collection that owns the page, or null for a locale home page. */ + sidebar: DocsSidebar | null /** Section label within the sidebar. */ section: string /** Stable order within the section. */ @@ -23,191 +41,228 @@ export interface DocsPage { sourceAliases?: string[] } -const zhGuide: DocsPage[] = [ +interface MirroredPage { + source: string + route: string + contentLocale: DocsPage['contentLocale'] + label: Record + sidebar: Record + section: Record + order: number + sourceAliases?: string[] +} + +function mirroredPages(pages: MirroredPage[]): DocsPage[] { + return pages.flatMap(page => (['root', 'en'] as const).map(locale => ({ + locale, + contentLocale: page.contentLocale, + source: page.source, + route: locale === 'root' ? page.route : `en/${page.route}`, + label: page.label[locale], + sidebar: page.sidebar[locale], + section: page.section[locale], + order: page.order, + ...(page.sourceAliases === undefined ? {} : { sourceAliases: page.sourceAliases }), + }))) +} + +const homeAndGuide = mirroredPages([ { source: 'docs/user/zh-CN/index.md', route: 'index.md', - label: 'DeepSeek Harness', - sidebar: 'zh-guide', - section: '入门', + contentLocale: 'zh-CN', + label: { root: 'DeepSeek Harness', en: 'DeepSeek Harness' }, + sidebar: { root: null, en: null }, + section: { root: '首页', en: 'Home' }, order: 0, }, { source: 'docs/user/zh-CN/guide/index.md', route: 'guide/index.md', - label: '介绍', - sidebar: 'zh-guide', - section: '入门', + contentLocale: 'zh-CN', + label: { root: '介绍', en: 'Introduction' }, + sidebar: { root: 'zh-guide', en: 'en-guide' }, + section: { root: '入门', en: 'Guide' }, order: 1, sourceAliases: ['docs/user/zh-CN/guide'], }, { source: 'docs/user/zh-CN/guide/quickstart.md', route: 'guide/quickstart.md', - label: '快速开始', - sidebar: 'zh-guide', - section: '入门', + contentLocale: 'zh-CN', + label: { root: '快速开始', en: 'Quick start' }, + sidebar: { root: 'zh-guide', en: 'en-guide' }, + section: { root: '入门', en: 'Guide' }, order: 2, }, { source: 'docs/user/zh-CN/guide/config.md', route: 'guide/config.md', - label: '配置文件', - sidebar: 'zh-guide', - section: '入门', + contentLocale: 'zh-CN', + label: { root: '配置文件', en: 'Configuration' }, + sidebar: { root: 'zh-guide', en: 'en-guide' }, + section: { root: '入门', en: 'Guide' }, order: 3, }, -] +]) -const zhDevelop: DocsPage[] = [ +const develop = mirroredPages([ { source: 'docs/user/zh-CN/develop/basic/index.md', route: 'develop/basic/index.md', - label: '第一个插件', - sidebar: 'zh-develop', - section: '基础', + contentLocale: 'zh-CN', + label: { root: '第一个插件', en: 'First plugin' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '基础', en: 'Basics' }, order: 1, sourceAliases: ['docs/user/zh-CN/develop/basic'], }, { source: 'docs/user/zh-CN/develop/basic/tool.md', route: 'develop/basic/tool.md', - label: '开发一个 Tool', - sidebar: 'zh-develop', - section: '基础', + contentLocale: 'zh-CN', + label: { root: '开发一个 Tool', en: 'Build a tool' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '基础', en: 'Basics' }, order: 2, }, { source: 'docs/user/zh-CN/develop/basic/config.md', route: 'develop/basic/config.md', - label: '插件配置', - sidebar: 'zh-develop', - section: '基础', + contentLocale: 'zh-CN', + label: { root: '插件配置', en: 'Plugin configuration' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '基础', en: 'Basics' }, order: 3, }, { source: 'docs/user/zh-CN/develop/framework/index.md', route: 'develop/framework/index.md', - label: '插件与生命周期', - sidebar: 'zh-develop', - section: '框架能力', + contentLocale: 'zh-CN', + label: { root: '插件与生命周期', en: 'Plugin lifecycle' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '框架能力', en: 'Framework' }, order: 1, sourceAliases: ['docs/user/zh-CN/develop/framework'], }, { source: 'docs/user/zh-CN/develop/framework/service.md', route: 'develop/framework/service.md', - label: '服务与依赖', - sidebar: 'zh-develop', - section: '框架能力', + contentLocale: 'zh-CN', + label: { root: '服务与依赖', en: 'Services and dependencies' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '框架能力', en: 'Framework' }, order: 2, }, { source: 'docs/user/zh-CN/develop/framework/events.md', route: 'develop/framework/events.md', - label: '事件系统', - sidebar: 'zh-develop', - section: '框架能力', + contentLocale: 'zh-CN', + label: { root: '事件系统', en: 'Event system' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '框架能力', en: 'Framework' }, order: 3, }, { source: 'docs/user/zh-CN/develop/practice/index.md', route: 'develop/practice/index.md', - label: '能力的三层拆分', - sidebar: 'zh-develop', - section: '实战', + contentLocale: 'zh-CN', + label: { root: '能力的三层拆分', en: 'Capability layering' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '实战', en: 'Practice' }, order: 1, sourceAliases: ['docs/user/zh-CN/develop/practice'], }, { source: 'docs/user/zh-CN/develop/practice/llm-adapter.md', route: 'develop/practice/llm-adapter.md', - label: 'LLM 适配器', - sidebar: 'zh-develop', - section: '实战', + contentLocale: 'zh-CN', + label: { root: 'LLM 适配器', en: 'LLM adapter' }, + sidebar: { root: 'zh-develop', en: 'en-develop' }, + section: { root: '实战', en: 'Practice' }, order: 2, }, -] +]) -const enOverview: DocsPage[] = ([ - ['docs/architecture.md', 'en/index.md', 'Architecture'], - ['docs/cordis-primer.md', 'en/cordis-primer.md', 'Cordis primer'], - ['docs/capability-seams.md', 'en/capability-seams.md', 'Capability services'], - ['docs/agent-lifecycle.md', 'en/agent-lifecycle.md', 'Agent lifecycle'], - ['docs/tool-execution-pipeline.md', 'en/tool-execution-pipeline.md', 'Tool execution'], -] as const).map(([source, route, label], order) => ({ - source, - route, - label, - sidebar: 'en-docs', - section: 'Concepts', - order, -})) - -const enCatalogs: DocsPage[] = ([ - ['docs/config-catalog.md', 'en/config-catalog.md', 'Plugin configuration'], - ['docs/tool-catalog.md', 'en/tool-catalog.md', 'Tool schemas'], - ['docs/cordis-catalog/services.md', 'en/cordis-catalog/services.md', 'Services'], - ['docs/cordis-catalog/events.md', 'en/cordis-catalog/events.md', 'Events'], - ['docs/persistence-catalog.md', 'en/persistence-catalog.md', 'Persistence events'], -] as const).map(([source, route, label], order) => ({ - source, - route, - label, - sidebar: 'en-docs', - section: 'Generated reference', - order, -})) - -const corePages = [ - ['core.md', 'Core data structures'], - ['session.md', 'Sessions'], - ['tools.md', 'Tools'], - ['llm-streaming.md', 'LLM streaming'], - ['bash.md', 'Bash execution'], - ['filesystem.md', 'Filesystem'], - ['code-runtime.md', 'Code runtime'], - ['compaction.md', 'Compaction'], - ['subagent.md', 'Subagents'], - ['workflow.md', 'Workflows'], - ['skills.md', 'Skills'], - ['approval.md', 'Approvals'], - ['user-interaction.md', 'User interaction'], - ['sandbox.md', 'Sandboxing'], - ['web.md', 'Web access'], - ['persistence.md', 'Session persistence'], -] as const - -const enCore: DocsPage[] = corePages.map(([file, label], order) => ({ - source: `docs/core-data-structures/${file}`, - route: `en/core-data-structures/${file}`, - label, - sidebar: 'en-docs', - section: 'Data structures', - order, - ...(file === 'core.md' ? { sourceAliases: ['docs/core-data-structures'] } : {}), -})) - -const enCookbook: DocsPage[] = ([ - ['adding-a-package.md', 'Adding a package'], - ['adding-a-tool.md', 'Adding a tool'], - ['adding-an-llm-adapter.md', 'Adding an LLM adapter'], - ['extension-cookbook.md', 'Extension patterns'], -] as const).map(([file, label], order) => ({ - source: `docs/cookbook/${file}`, - route: `en/cookbook/${file}`, - label, - sidebar: 'en-docs', - section: 'Cookbook', - order, -})) +const reference = mirroredPages([ + ...([ + ['docs/architecture.md', 'reference/index.md', '架构', 'Architecture'], + ['docs/cordis-primer.md', 'reference/cordis-primer.md', 'Cordis 入门', 'Cordis primer'], + ['docs/capability-seams.md', 'reference/capability-seams.md', '能力服务', 'Capability services'], + ['docs/agent-lifecycle.md', 'reference/agent-lifecycle.md', 'Agent 生命周期', 'Agent lifecycle'], + ['docs/tool-execution-pipeline.md', 'reference/tool-execution-pipeline.md', 'Tool 执行', 'Tool execution'], + ] as const).map(([source, route, rootLabel, enLabel], order): MirroredPage => ({ + source, + route, + contentLocale: 'en-US', + label: { root: rootLabel, en: enLabel }, + sidebar: { root: 'zh-reference', en: 'en-reference' }, + section: { root: '概念', en: 'Concepts' }, + order, + })), + ...([ + ['docs/config-catalog.md', 'reference/config-catalog.md', '插件配置', 'Plugin configuration'], + ['docs/tool-catalog.md', 'reference/tool-catalog.md', 'Tool Schema', 'Tool schemas'], + ['docs/cordis-catalog/services.md', 'reference/cordis-catalog/services.md', '服务', 'Services'], + ['docs/cordis-catalog/events.md', 'reference/cordis-catalog/events.md', '事件', 'Events'], + ['docs/persistence-catalog.md', 'reference/persistence-catalog.md', '持久化事件', 'Persistence events'], + ] as const).map(([source, route, rootLabel, enLabel], order): MirroredPage => ({ + source, + route, + contentLocale: 'en-US', + label: { root: rootLabel, en: enLabel }, + sidebar: { root: 'zh-reference', en: 'en-reference' }, + section: { root: '生成参考', en: 'Generated reference' }, + order, + })), + ...([ + ['core.md', '核心数据结构', 'Core data structures'], + ['scope.md', '作用域', 'Scopes'], + ['session.md', '会话', 'Sessions'], + ['system-prompt.md', '系统提示词', 'System prompts'], + ['tools.md', '工具', 'Tools'], + ['llm-streaming.md', 'LLM 流式响应', 'LLM streaming'], + ['bash.md', 'Bash 执行', 'Bash execution'], + ['filesystem.md', '文件系统', 'Filesystem'], + ['code-runtime.md', '代码运行时', 'Code runtime'], + ['compaction.md', '上下文压缩', 'Compaction'], + ['subagent.md', '子代理', 'Subagents'], + ['workflow.md', '工作流', 'Workflows'], + ['skills.md', '技能', 'Skills'], + ['approval.md', '审批', 'Approvals'], + ['user-interaction.md', '用户交互', 'User interaction'], + ['sandbox.md', '沙箱', 'Sandboxing'], + ['web.md', 'Web 访问', 'Web access'], + ['persistence.md', '会话持久化', 'Session persistence'], + ] as const).map(([file, rootLabel, enLabel], order): MirroredPage => ({ + source: `docs/core-data-structures/${file}`, + route: `reference/core-data-structures/${file}`, + contentLocale: 'en-US', + label: { root: rootLabel, en: enLabel }, + sidebar: { root: 'zh-reference', en: 'en-reference' }, + section: { root: '数据结构', en: 'Data structures' }, + order, + ...(file === 'core.md' ? { sourceAliases: ['docs/core-data-structures'] } : {}), + })), + ...([ + ['adding-a-package.md', '新增 Package', 'Adding a package'], + ['adding-a-tool.md', '新增 Tool', 'Adding a tool'], + ['adding-an-llm-adapter.md', '新增 LLM Adapter', 'Adding an LLM adapter'], + ['extension-cookbook.md', '扩展模式', 'Extension patterns'], + ] as const).map(([file, rootLabel, enLabel], order): MirroredPage => ({ + source: `docs/cookbook/${file}`, + route: `reference/cookbook/${file}`, + contentLocale: 'en-US', + label: { root: rootLabel, en: enLabel }, + sidebar: { root: 'zh-reference', en: 'en-reference' }, + section: { root: '开发手册', en: 'Cookbook' }, + order, + })), +]) /** Every canonical page published by the documentation website. */ export const docsPages: DocsPage[] = [ - ...zhGuide, - ...zhDevelop, - ...enOverview, - ...enCatalogs, - ...enCore, - ...enCookbook, + ...homeAndGuide, + ...develop, + ...reference, ] From e481288a3a5fdf05f4bcc491dc120820975710d3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:04:11 +0800 Subject: [PATCH 006/323] refactor: derive snapshot session fixtures from disk --- .../2026-07-08-shared-acp-snapshot-package.md | 2 +- .../2026-06-20-discover-package-inventory.md | 5 +- examples/acp-agent/tests/acp.snapshot.ts | 10 +-- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/suite.ts | 68 +++++++++++-------- .../support/acp-snapshot/tests/suite.spec.ts | 44 +++++++++--- 6 files changed, 85 insertions(+), 46 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index c622a7f1be..eca3661b33 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -16,7 +16,7 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. -**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`childFixturePaths`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. +**`src/suite.ts`** — the `Scenario` type and `defineAcpSnapshotSuite(options)`, registering the per-scenario compares, record/refresh fixture write-back, the header pin with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL a `scrubSystemPrompts` fixed point, non-pinning fixtures also `scrubRequestHeaders` fixed points). A scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are its ordered primary/child inventory, so the scenario table declares policy without duplicating a child count. The pinned-header contract ([pinned-header RFC](2026-07-06-pin-request-header-content-in-one-scenario.md)) is per-suite: each header class flags exactly one `pinsHeader` scenario, whose `system-prompt.golden.md` and JSONL tool list split the composed header into reviewable artifacts; the uniformity guard compares both against every live header in that class. A pinning scenario declares any legitimate changed-header count, and its Markdown artifact records every full changed prompt. The pure helpers (`sessionFixtureNames`, `fixtureContext`, `normalizedHeaders`, `normalizedSystemPrompts`, `formatSystemPromptSnapshot`, `headerChangeCount`) are exported from the module for direct unit coverage. ## Alternatives considered diff --git a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md b/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md index 3587393efe..a091203da9 100644 --- a/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md +++ b/docs/rfc/proposed/process/2026-06-20-discover-package-inventory.md @@ -4,7 +4,7 @@ Status: proposed ## Problem -Package and gate inventories are repeated by hand. The [package cookbook](../../../cookbook/adding-a-package.md) tells authors to update several files. The [package README](../../../../packages/README.md) carries a hand-written dependency graph. [CI](../../../../.github/workflows/ci.yml) and [development docs](../../../development.md) can drift from the actual `doc-sync` subcommands when new gates are added. `tsconfig.build.json` and the root `tsconfig.json` each hand-list every package as explicit project `references` — two identical sets that grow in lockstep, so a single generator can emit both — and `tsconfig.base.json`'s paths map hand-lists the per-group glob fan-out. `knip.json` restates a per-package `entry` stanza for each package that gains an `*.e2e.ts` suite — byte-identical overrides that exist only because the shared `packages/*/*` stanza omits the e2e glob (an entry glob matching no files is inert, so the default stanza could carry it for every package). The ACP snapshot suite's scenario table (`examples/acp-agent/tests/acp.snapshot.ts`) hand-maintains a `childSessions` count per scenario that duplicates the number of `session..jsonl` fixture siblings on disk. These lists are small today, but every new package or scenario class creates another manual synchronization point. +Package and gate inventories are repeated by hand. The [package cookbook](../../../cookbook/adding-a-package.md) tells authors to update several files. The [package README](../../../../packages/README.md) carries a hand-written dependency graph. [CI](../../../../.github/workflows/ci.yml) and [development docs](../../../development.md) can drift from the actual `doc-sync` subcommands when new gates are added. `tsconfig.build.json` and the root `tsconfig.json` each hand-list every package as explicit project `references` — two identical sets that grow in lockstep, so a single generator can emit both — and `tsconfig.base.json`'s paths map hand-lists the per-group glob fan-out. `knip.json` restates a per-package `entry` stanza for each package that gains an `*.e2e.ts` suite — byte-identical overrides that exist only because the shared `packages/*/*` stanza omits the e2e glob (an entry glob matching no files is inert, so the default stanza could carry it for every package). These lists are small today, but every new package creates another manual synchronization point. The [package hierarchy](../../implemented/architecture/2026-06-20-package-hierarchy.md) already removed several of these by hand: `scripts/publint-all.ts` now derives its list from the `packages//` layout, and the two `tsconfig` `paths` maps collapsed to one `@deepseek-ai/dsh-*` wildcard. What remains is the inventory that cannot be globbed away — chiefly `tsconfig.build.json`'s project `references`, which TypeScript requires as an explicit array (no wildcard form). @@ -16,7 +16,7 @@ Make the remaining package/gate inventories discoverable. A single canonical sou The hierarchy does not need to encode every fact about a package, but it should encode the broad maintenance policy: core/product packages, integrations, capability seams, and support/test/example packages should not all require a hand-maintained exception list before scripts can tell them apart. -Two of the cataloged items need no generator at all: folding the e2e entry glob into knip's default stanza deletes the per-package restatements outright, and `childSessions` can be discovered from each scenario's fixture directory, leaving the scenario table to declare only policy (`recorded`, `hasModelTurn`, `comparesLog`) — and even those track fixture-derivable facts today (`comparesLog` ⟺ the committed log has entries beyond its header line; `recorded` ⟺ `hasModelTurn` with no `replay.override.json` sibling), so each new scenario class keeps adding knobs the fixture directory already answers. +One cataloged item needs no generator at all: folding the e2e entry glob into knip's default stanza deletes the per-package restatements outright. ## Acceptance criteria @@ -25,7 +25,6 @@ Two of the cataloged items need no generator at all: folding the e2e entry glob - Docs describe the source of truth rather than repeating generated inventories. - CI invokes the aggregate commands and lets those commands own their sub-gate lists. - `knip.json` carries a per-package override only where it encodes real information (an extra entry file, an ignored dependency), never a restatement of the default stanza. -- Snapshot scenarios declare policy, not facts discoverable from their fixture directories. ## Risks diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index eaa4e0381a..b1a43b83db 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -67,14 +67,14 @@ const SCENARIOS: Scenario[] = [ // tiers (gentle at 3, detailed at 5) as context/message in transcript and log. { name: 'repeat-tool-guard', hasModelTurn: true, recorded: false }, { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true }, - { name: 'subagent-spawn', hasModelTurn: true, recorded: true, childSessions: 1 }, - { name: 'subagent-multi', hasModelTurn: true, recorded: true, childSessions: 2 }, - { name: 'subagent-fork', hasModelTurn: true, recorded: true, childSessions: 1 }, - { name: 'subagent-mixed', hasModelTurn: true, recorded: true, childSessions: 2 }, + { name: 'subagent-spawn', hasModelTurn: true, recorded: true }, + { name: 'subagent-multi', hasModelTurn: true, recorded: true }, + { name: 'subagent-fork', hasModelTurn: true, recorded: true }, + { name: 'subagent-mixed', hasModelTurn: true, recorded: true }, // The workflow tool: the model writes a one-child orchestration script; the // child runs as a spawn subagent under the worker-thread engine (its session is the // child fixture), and the tool result carries the script's return value. - { name: 'workflow-run', hasModelTurn: true, recorded: true, childSessions: 1 }, + { name: 'workflow-run', hasModelTurn: true, recorded: true }, // Hook matrix — one scenario per hook point × its headline Decision outcome, // across BOTH bridges (Claude `hooks.json`, Codex `codex-hooks.json`, seeded in // workspace/). The block scenarios need no model call: a UserPromptSubmit hook diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 13dd1ab247..ac9c0ceee3 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -6,7 +6,7 @@ Three layers, importable separately: - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). -- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Must be called at vitest collection time. +- **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. A consuming `*.snapshot.ts` is the scenario table plus one factory call: diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 523092bf09..6311a15031 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -80,14 +80,6 @@ export interface Scenario { * false (replay derives from the fixture's `assistant/chunk` events). */ overridden?: boolean - /** - * How many SUBAGENT child sessions this scenario records beyond the top-level - * one (0 for a single-session scenario). Each child rides in a sibling fixture - * `session..jsonl` (1-based); replay forwards them to `dsh-llm-replay` so - * each child session replays from its own script, and record mode writes the - * harvested child logs back to those files. Defaults to 0. - */ - childSessions?: number /** * Whether THIS scenario pins its header class's model-facing request-header * content. Its actual composed prompt is maintained as a readable @@ -150,14 +142,40 @@ export interface SnapshotSuiteOptions { } /** - * The sibling child-fixture paths for a scenario (`session.1.jsonl` …). + * Validate and order a scenario directory's session-fixture filenames. * - * @param dir The scenario's snapshots directory (`/`). - * @param childSessions How many subagent child sessions the scenario records. - * @returns One path per child, 1-based, in fixture order. + * The primary fixture is always `session.jsonl`; child sessions are discovered + * from contiguous `session.1.jsonl` … filenames. The directory is the source of + * truth, so scenario tables do not duplicate a child count that can drift from + * the files. A session-like JSONL with any other suffix fails loud. + * + * @param names File names in one scenario directory. + * @returns The primary and child fixture names in replay/harvest order. */ -export function childFixturePaths(dir: string, childSessions: number): string[] { - return Array.from({ length: childSessions }, (_, i) => join(dir, `session.${i + 1}.jsonl`)) +export function sessionFixtureNames(names: readonly string[]): string[] { + if (!names.includes('session.jsonl')) throw new Error('missing session.jsonl') + const children: { name: string; index: number }[] = [] + for (const name of names) { + if (name === 'session.jsonl') continue + if (!name.startsWith('session.') || !name.endsWith('.jsonl')) continue + const match = /^session\.([1-9]\d*)\.jsonl$/.exec(name) + if (match === null) throw new Error(`invalid child session fixture name: ${name}`) + children.push({ name, index: Number(match[1]) }) + } + children.sort((a, b) => a.index - b.index) + for (const [offset, child] of children.entries()) { + const expected = offset + 1 + if (child.index !== expected) { + throw new Error(`child session fixtures must be contiguous: expected session.${expected}.jsonl, found ${child.name}`) + } + } + return ['session.jsonl', ...children.map(child => child.name)] +} + +/** Read one scenario directory's validated session-fixture inventory. */ +async function sessionFixtures(dir: string): Promise { + const entries = await readdir(dir, { withFileTypes: true }) + return sessionFixtureNames(entries.filter(entry => entry.isFile()).map(entry => entry.name)) } /** @@ -392,7 +410,9 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript const overrideFile = join(dir, 'replay.override.json') const workspaceDir = join(dir, 'workspace') - const childSessions = scenario.childSessions ?? 0 + const fixtureFiles = await sessionFixtures(dir) + const childFixtureFiles = fixtureFiles.slice(1) + const childSessions = childFixtureFiles.length const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn const result = await runScenario(input, { agent, @@ -401,7 +421,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { ...existsSync(overrideFile) ? { overrideFile } : {}, // In REPLAY, forward the recorded child fixtures so each subagent session // replays from its own script. In RECORD they are harvested, not read. - ...!RECORDING && childSessions > 0 ? { childFiles: childFixturePaths(dir, childSessions) } : {}, + ...!RECORDING && childSessions > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, ...existsSync(workspaceDir) ? { workspaceDir } : {}, // A scenario booting an overlay tree passes its own live config; the // bin's replay swap derives the sibling `*cordis.snapshot.yml` from it. @@ -432,7 +452,6 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const scrub = scenario.pinsHeader === true ? scrubSystemPrompts : scrubRequestHeaders - const fixtureFiles = ['session.jsonl', ...Array.from({ length: childSessions }, (_, i) => `session.${i + 1}.jsonl`)] const existingFixtures = REFRESHING ? await Promise.all(fixtureFiles.map(file => readFile(join(dir, file), 'utf8'))) : [] @@ -543,7 +562,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { expect(onDisk).toEqual(registered) }) - it('every registered scenario has its required fixture files', () => { + it('every registered scenario has its required fixture files', async () => { // Every scenario has an input script and an stdout golden. EVERY scenario // also needs `session.jsonl`: the suite boots `llm-replay` with that path // as the replay source for ALL scenarios (the factory passes @@ -556,7 +575,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // `overridden` flag: required when set, forbidden when not — the harness // forwards the file purely on existence, so an unregistered stray sidecar // would silently replace the derived script. - for (const { name, overridden, childSessions, pinsHeader } of scenarios) { + for (const { name, overridden, pinsHeader } of scenarios) { const dir = join(snapshotsDir, name) expect(existsSync(join(dir, 'input.json')), `${name}/input.json`).toBe(true) expect(existsSync(join(dir, 'stdout.golden.jsonl')), `${name}/stdout.golden.jsonl`).toBe(true) @@ -565,11 +584,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { .toBe(overridden === true) expect(existsSync(join(dir, SYSTEM_PROMPT_SNAPSHOT)), `${name}/${SYSTEM_PROMPT_SNAPSHOT} presence must match \`pinsHeader\``) .toBe(pinsHeader === true) - // A nested-agent scenario ships one child fixture per recorded subagent - // session (`session.1.jsonl` …), the replay source for that child session. - for (const childFixture of childFixturePaths(dir, childSessions ?? 0)) { - expect(existsSync(childFixture), childFixture).toBe(true) - } + await expect(sessionFixtures(dir), `${name}: session fixture inventory`).resolves.toBeDefined() } }) @@ -615,10 +630,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // all header bulk. Fixed-point checks make both storage rules fail loud. for (const scenario of scenarios) { const dir = join(snapshotsDir, scenario.name) - const files = [ - 'session.jsonl', - ...Array.from({ length: scenario.childSessions ?? 0 }, (_, i) => `session.${i + 1}.jsonl`), - ] + const files = await sessionFixtures(dir) for (const file of files) { const fixture = await readFile(join(dir, file), 'utf8') expect(scrubSystemPrompts(fixture), `${scenario.name}/${file} carries an unscrubbed system prompt`) diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index 4ca9c8573d..f27f36c564 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -6,13 +6,13 @@ import { fileURLToPath } from 'node:url' import { afterAll, describe, expect, it } from 'vitest' import { defineAcpSnapshotSuite, type HarvestedLog, type Scenario } from '../src/index.ts' import { - childFixturePaths, fixtureContext, formatSystemPromptSnapshot, headerChangeCount, normalizedHeaders, normalizedSystemPrompts, refreshFixtureReplacements, + sessionFixtureNames, stabilizeRefreshLog, } from '../src/suite.ts' @@ -51,7 +51,7 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta. // example's code-mode scenarios). const REPLAY_SCENARIOS: Scenario[] = [ { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'main' }, - { name: 'plain-turn', hasModelTurn: true, recorded: true, childSessions: 1, headerClass: 'main', configPath: AGENT.configPath }, + { name: 'plain-turn', hasModelTurn: true, recorded: true, headerClass: 'main', configPath: AGENT.configPath }, { name: 'no-model', hasModelTurn: false, recorded: false, headerClass: 'main' }, { name: 'blocked-log', hasModelTurn: false, comparesLog: true, recorded: false, headerClass: 'main' }, { name: 'authored-error', hasModelTurn: true, recorded: false, overridden: true, headerClass: 'main' }, @@ -59,7 +59,7 @@ const REPLAY_SCENARIOS: Scenario[] = [ const RECORD_SCENARIOS: Scenario[] = [ { name: 'rec-pin', hasModelTurn: true, recorded: true, pinsHeader: true }, - { name: 'rec-child', hasModelTurn: true, recorded: true, childSessions: 1 }, + { name: 'rec-child', hasModelTurn: true, recorded: true }, // recorded:false in record mode → registered but skipped (never re-recorded). { name: 'rec-skip', hasModelTurn: true, recorded: false, overridden: true }, ] @@ -180,13 +180,41 @@ describe('defineAcpSnapshotSuite: registration contract', () => { }) }) -describe('childFixturePaths', () => { - it('yields one sibling path per child, 1-based', () => { - expect(childFixturePaths('/snap/s', 2)).toEqual(['/snap/s/session.1.jsonl', '/snap/s/session.2.jsonl']) +describe('sessionFixtureNames', () => { + it('orders the primary and contiguous child fixtures while ignoring other files', () => { + expect(sessionFixtureNames([ + 'stdout.golden.jsonl', + 'session.2.jsonl', + 'session.jsonl', + 'session.1.jsonl', + 'input.json', + ])).toEqual(['session.jsonl', 'session.1.jsonl', 'session.2.jsonl']) }) - it('yields nothing for a single-session scenario', () => { - expect(childFixturePaths('/snap/s', 0)).toEqual([]) + it('accepts a primary-only scenario', () => { + expect(sessionFixtureNames(['session.jsonl'])).toEqual(['session.jsonl']) + }) + + it('rejects a directory without the primary fixture', () => { + expect(() => sessionFixtureNames(['session.1.jsonl'])).toThrow('missing session.jsonl') + }) + + it('rejects gapped child fixtures', () => { + expect(() => sessionFixtureNames(['session.jsonl', 'session.2.jsonl'])) + .toThrow('expected session.1.jsonl, found session.2.jsonl') + }) + + it.each(['session.0.jsonl', 'session.child.jsonl', 'session.01.jsonl'])( + 'rejects invalid child fixture name %s', + (name) => { + expect(() => sessionFixtureNames(['session.jsonl', name])) + .toThrow(`invalid child session fixture name: ${name}`) + }, + ) + + it('rejects duplicate child indexes', () => { + expect(() => sessionFixtureNames(['session.jsonl', 'session.1.jsonl', 'session.1.jsonl'])) + .toThrow('expected session.2.jsonl, found session.1.jsonl') }) }) From 0e7d539bbc5b75ad224b312a11cc1e15e1ba527a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:18:00 +0800 Subject: [PATCH 007/323] refactor: share the ACP test launcher --- .../2026-07-08-shared-acp-snapshot-package.md | 10 +- examples/acp-agent/tests/acp.e2e.ts | 182 +++--------------- examples/acp-agent/tests/hooks.e2e.ts | 68 ++----- .../sandbox-acp-agent/tests/escalation.e2e.ts | 79 +++----- packages/support/README.md | 4 +- packages/support/acp-snapshot/README.md | 5 +- packages/support/acp-snapshot/package.json | 2 +- packages/support/acp-snapshot/src/harness.ts | 130 ++----------- packages/support/acp-snapshot/src/index.ts | 24 ++- packages/support/acp-snapshot/src/launcher.ts | 152 +++++++++++++++ .../acp-snapshot/tests/harness.spec.ts | 33 ++++ 11 files changed, 292 insertions(+), 397 deletions(-) create mode 100644 packages/support/acp-snapshot/src/launcher.ts diff --git a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md index eca3661b33..59734535b8 100644 --- a/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md +++ b/docs/rfc/implemented/testing/2026-07-08-shared-acp-snapshot-package.md @@ -6,13 +6,15 @@ Status: implemented The ACP snapshot tier ([snapshot RFC](2026-06-19-acp-snapshot-tests.md)) was built from three modules living inside one example's test directory: `snapshot-harness.ts` (boot the real bin subprocess, drive it over ACP JSON-RPC, harvest the persisted logs), `snapshot-normalize.ts` (the pure golden normalizers), and the ~150-line scenario body plus fixture guards in `acp.snapshot.ts` (record/replay modes, the stdout-golden and log compares, the pinned-header uniformity guard, the orphan/required-file/single-pin meta-tests). -A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was already triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness (`TODO(acp-test-harness)`). Location also decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all. +A second ACP example wanting snapshot coverage — the sandbox/approval composition is the immediate consumer — could only copy those modules, forking exactly the logic that must not drift: record write-back, header scrubbing, child-session harvest ordering. The spawn/client glue was also triplicated across `acp.e2e.ts`, `hooks.e2e.ts`, and the harness. Location decided test rigor: the per-file 100% coverage gate measures `packages/*/*/src` only, so none of this machinery was measured — the same gap that had moved `dsh-llm-replay` out of `examples/` into [packages/support](../../../../packages/support/README.md). And the harness's ACP client hardcoded `requestPermission → cancelled`, so an approval round-trip — the headline behavior of the sandbox composition — could not be expressed at the snapshot tier at all. ## Decision The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/support/acp-snapshot/README.md) (`@deepseek-ai/dsh-acp-snapshot`); an example's `*.snapshot.ts` is its scenario table, its agent paths, and one factory call, over its own `snapshots/` fixtures and `cordis.snapshot.yml` overlay ([single-source replay config](2026-07-04-single-source-acp-replay-config.md)). Reading `DSH_SNAPSHOT` stays at that edge — the library takes a resolved `mode`. -**`src/harness.ts`** — `runScenario` and the input-script/result types, parameterized by an `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath`; absolute paths the consuming suite resolves from its own `import.meta.url`). The client's `session/request_permission` handler consumes an optional `InputScript.permissionAnswers` FIFO queue, each entry selecting by option **kind** (ids are agent-issued randoms a committed script cannot know; kinds are the ACP-stable vocabulary, mapped to the offered `optionId` at answer time); an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run — the agent itself is answered `cancelled`, so the scenario bug fails the harness rather than being absorbed as an agent-side denial. This is what lets an approval suite drive allow/reject round-trips deterministically from `input.json`. +**`src/launcher.ts`** — `launchAcpTestAgent` owns the common unbuilt-process boundary: absolute tsx loader resolution, `TSX_TSCONFIG_PATH`, isolated harness homes, stdio wiring, a raw-byte stdout tee, stderr and update capture, fail-closed permission fallback, update waiters, and graceful or signalled shutdown. Snapshot scenarios and ordinary e2e suites supply the same `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath`); a test that plays a user supplies only its permission handler. The ACP and hook e2e suites plus the sandbox/approval e2e suite use this launcher instead of rebuilding the SDK client boundary. + +**`src/harness.ts`** — `runScenario` and the input-script/result types layer deterministic steps, temp workspaces, snapshot environment, and persisted-log harvest over the launcher. Its `session/request_permission` handler consumes an optional `InputScript.permissionAnswers` FIFO queue, each entry selecting by option **kind** (ids are agent-issued randoms a committed script cannot know; kinds are the ACP-stable vocabulary, mapped to the offered `optionId` at answer time); an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run — the agent itself is answered `cancelled`, so the scenario bug fails the harness rather than being absorbed as an agent-side denial. This is what lets an approval suite drive allow/reject round-trips deterministically from `input.json`. **`src/normalize.ts`** — the pure normalizers, hook-free by policy: when a future event carries a new volatile field (an approval duration, say), the shared normalizer learns it in the same change, keeping one home for what "normalized" means rather than per-suite scrub extensions. @@ -29,8 +31,8 @@ The machinery lives in [`packages/support/acp-snapshot`](../../../../packages/su ## Testing -Extraction parity was proven mechanically: after the move, `pnpm run test:snapshot` matched the base commit's result with zero byte changes under `examples/acp-agent/tests/snapshots/`. The package's `src/` holds per-file 100% statements/branches/functions/lines under the gating unit run, driven through the REAL spawn path by a scripted fake ACP bin (`tests/fixtures/fake-acp-agent.ts`, behavior scripted per scenario via a `behavior.json` beside the fixture): `harness.spec.ts` covers every step op, both expect-error arms, the permission queue (selection, fallback, impossible-click), env forwarding, workspace seeding, and the harvest ordering/noise/fallback branches; `suite.spec.ts` runs the factory for real at collection time — a replay suite over committed synthetic fixtures and a record suite over a temp copy (write-back never touches the committed tree; `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` re-bootstraps it) — plus direct cases for the pure helpers. Two structurally unreachable guards carry reasoned `v8 ignore` comments. The fake bin substitutes the `session/new` cwd, not `process.cwd()`, into scripted logs, matching what the real bin's header carries (darwin realpaths `/var/folders/…` to `/private/var/folders/…`). +Extraction parity was proven mechanically: after the move, `pnpm run test:snapshot` matched the base commit's result with zero byte changes under `examples/acp-agent/tests/snapshots/`. The package's `src/` holds per-file 100% statements/branches/functions/lines under the gating unit run, driven through the real launcher by a scripted fake ACP bin (`tests/fixtures/fake-acp-agent.ts`, behavior scripted per scenario via a `behavior.json` beside the fixture): `harness.spec.ts` directly covers launcher defaults, captures, update waiting, shutdown, and environment/config variants, then covers every scenario step op, both expect-error arms, the permission queue (selection, fallback, impossible-click), workspace seeding, and the harvest ordering/noise/fallback branches; `suite.spec.ts` runs the factory for real at collection time — a replay suite over committed synthetic fixtures and a record suite over a temp copy (write-back never touches the committed tree; `ACP_SNAPSHOT_SPEC_BOOTSTRAP=1` re-bootstraps it) — plus direct cases for the pure helpers. The fake bin substitutes the `session/new` cwd, not `process.cwd()`, into scripted logs, matching what the real bin's header carries (darwin realpaths `/var/folders/…` to `/private/var/folders/…`). ## Consequences -A new example gets the whole snapshot tier from a scenario table plus fixtures — the sandbox branch merges master down and adds its own suite (own pin scenario, own overlay, fixtures via `test:snapshot:record`, approvals via `permissionAnswers`). The costs: `suite.ts` imports vitest, so the package is importable only inside a vitest run — a shape no other package has, stated in its README; each suite pins its own ~8 KB header fixture (a genuinely distinct composition deserves its own pin; an identical one would be caught by that suite's uniformity guard); and the e2e launcher duplication remains (`TODO(acp-test-harness)`) — the harness is the extraction target when that migration lands. +A new example gets the whole snapshot tier from a scenario table plus fixtures, while an ordinary ACP e2e gets the same tested process/client boundary from one launcher call. The costs: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run — a shape no other package has, stated in its README; and each suite pins its own ~8 KB header fixture (a genuinely distinct composition deserves its own pin; an identical one would be caught by that suite's uniformity guard). diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index 8ff012c2c3..4b6c675208 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -1,20 +1,14 @@ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' import { mkdtemp, rm, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { - ClientSideConnection, - ndJsonStream, - PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, - type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, -} from '@agentclientprotocol/sdk' + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * End-to-end: boot examples/acp-agent as a real subprocess speaking ACP over @@ -26,127 +20,18 @@ import { * WITHOUT a key, since it only needs the server to boot and answer initialize. */ -// The dsh-acp-agent bin (the demo:acp entry) and this example's cordis.yml. The -// bin resolves its config-path arg from CWD; the subprocess runs from a temp -// workdir, so pass the example config's ABSOLUTE path. -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -// Resolve tsx's loader to an ABSOLUTE path: the subprocess runs with cwd set to -// a temp workdir (this test launches there and uses it as the session cwd; the -// bridge no longer requires cwd === the launch dir, but a temp dir keeps the -// test hermetic), where a bare `--import tsx` would not resolve from -// node_modules. import.meta.resolve gives the worktree's tsx regardless of cwd. -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -// Absolute path to the repo-root tsconfig. Dev/test/demo run UNBUILT: the -// `@deepseek-ai/dsh-*` workspace imports resolve through the `paths` map in the -// root tsconfig (tsx reads it), NOT through built `lib/` output. But tsx finds -// that tsconfig by searching UP from the child's cwd — and the child's cwd is a -// temp workdir OUTSIDE the repo, so the search misses and the dsh-* imports fail -// (the child dies before writing a byte). Point tsx at the repo tsconfig -// explicitly via TSX_TSCONFIG_PATH so resolution is cwd-independent. (Without -// this the suite only passed by accident when a stale built `lib/` happened to -// exist — exactly the contamination that masked the inject bug this suite now -// guards.) The repo root is four levels up from this file (examples/acp-agent/tests). -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) - -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] - stderr: string[] +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } -// TODO(acp-test-harness): this subprocess/client boot glue is duplicated with -// hooks.e2e.ts and partly with dsh-acp-snapshot's harness. Migrate both e2e -// files onto that launcher before the TSX/env/permission-stub details drift. -function spawnAcpAgent(cwd: string, env: NodeJS.ProcessEnv = process.env): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { - cwd, - env: { - ...env, - TSX_TSCONFIG_PATH: repoTsconfig, - DSH_HOME: join(cwd, '.dsh'), - DSH_AGENTS_HOME: join(cwd, '.agents'), - }, - stdio: ['pipe', 'pipe', 'pipe'], - }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(_params: RequestPermissionRequest): Promise { - // This example composes no ask-producing policy (no hooks), so the - // bridge never prompts here; answer cancelled (fail closed) if it ever - // does — an unexpected prompt must not grant anything. - return Promise.resolve({ outcome: { outcome: 'cancelled' } }) - }, - }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, stderr } -} - -let spawned: Spawned | undefined +let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined -function hasStdoutLine(out: string[]): boolean { - return out.join('').split('\n').some(line => line.trim().length > 0) -} - -async function waitForStdoutLine(child: ChildProcessWithoutNullStreams, out: string[], stderr: string[], timeoutMs: number): Promise { - await new Promise((resolve, reject) => { - const cleanup = () => { - clearTimeout(timeout) - child.stdout.off('data', onData) - child.off('exit', onExit) - child.off('error', onError) - } - const pass = () => { - cleanup() - resolve() - } - const fail = (reason: string) => { - cleanup() - reject(new Error(`${reason}; stderr: ${stderr.join('')}`)) - } - const onData = () => { - if (hasStdoutLine(out)) pass() - } - const onExit = (code: number | null, signal: NodeJS.Signals | null) => { - fail(`ACP child exited before emitting a stdout frame (code ${code ?? 'null'}, signal ${signal ?? 'null'})`) - } - const onError = (error: Error) => { - fail(`ACP child failed before emitting a stdout frame: ${error.message}`) - } - const timeout = setTimeout(() => { - fail(`ACP child did not emit a stdout frame within ${timeoutMs}ms`) - }, timeoutMs) - - child.stdout.on('data', onData) - child.on('exit', onExit) - child.on('error', onError) - onData() - }) -} - afterEach(async () => { - if (spawned) { - spawned.child.kill('SIGKILL') - spawned = undefined - } + await spawned?.close('SIGKILL') + spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined }) @@ -154,39 +39,18 @@ afterEach(async () => { describe('acp-agent over real stdio (no key required)', () => { it('emits only framed JSON-RPC on stdout', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - // Collect raw stdout bytes directly (bypass the SDK framing) to inspect. + // Inspect the launcher's raw-byte tee in addition to driving its SDK client. // A dummy key lets the deepseek adapter APPLY (it only checks the key is // present at boot, not valid — the key is used only on a real model call, // which this purity test never triggers). So this runs WITHOUT real creds. - const child = spawn(process.execPath, ['--import', tsxLoader, binScript, configPath], { + spawned = launchAcpTestAgent({ + agent: AGENT, cwd: workdir, - env: { - ...process.env, - DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', - TSX_TSCONFIG_PATH: repoTsconfig, - DSH_HOME: join(workdir, '.dsh'), - DSH_AGENTS_HOME: join(workdir, '.agents'), - }, - stdio: ['pipe', 'pipe', 'pipe'], + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, }) - const out: string[] = [] - const stderr: string[] = [] - child.stdout.setEncoding('utf8') - child.stderr.setEncoding('utf8') - child.stdout.on('data', (c: string) => out.push(c)) - child.stderr.on('data', (c: string) => stderr.push(c)) + await spawned.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - // Send a single initialize request as a newline-delimited JSON-RPC frame. - const req = JSON.stringify({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} } }) - child.stdin.write(req + '\n') - - try { - await waitForStdoutLine(child, out, stderr, 15_000) - } finally { - child.kill('SIGKILL') - } - - const lines = out.join('').split('\n').filter(l => l.trim().length > 0) + const lines = spawned.rawStdout().split('\n').filter(line => line.trim().length > 0) expect(lines.length).toBeGreaterThan(0) for (const line of lines) { // Every stdout line MUST parse as JSON (a JSON-RPC frame). A non-JSON @@ -210,7 +74,11 @@ describe('acp-agent over real stdio (no key required)', () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) // A dummy key lets the deepseek adapter boot (it only checks presence, not // validity, at apply time); no model call is made, so the key is never used. - spawned = spawnAcpAgent(workdir, { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }) + spawned = launchAcpTestAgent({ + agent: AGENT, + cwd: workdir, + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + }) const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -223,7 +91,7 @@ describe('acp-agent over real stdio (no key required)', () => { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over ACP', () => { it('runs a real turn and the agent writes the requested file (verified on disk)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -264,7 +132,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: real prompt over it('with the terminal_output capability, a real bash call renders as a terminal card (content + _meta + exit)', async () => { workdir = await mkdtemp(join(tmpdir(), 'acp-e2e-')) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned // Advertise the Zed `_meta.terminal_output` capability so the bridge emits diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index bdb800186a..a553addc96 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -1,20 +1,14 @@ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' import { mkdtemp, rm, writeFile, access } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { - ClientSideConnection, - ndJsonStream, - PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, - type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, -} from '@agentclientprotocol/sdk' + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * With-key e2e: the Claude Code hook bridge running against the REAL acp-agent @@ -34,54 +28,18 @@ import { * only a real model deciding to call bash exercises the PreToolUse seam live. */ -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) - -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] - stderr: string[] +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), } -function spawnAcpAgent(cwd: string): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { cwd, env: { ...process.env, TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'] }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(_params: RequestPermissionRequest): Promise { - return Promise.resolve({ outcome: { outcome: 'cancelled' } }) - }, - }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, stderr } -} - -let spawned: Spawned | undefined +let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - if (spawned) { - spawned.child.kill('SIGKILL') - spawned = undefined - } + await spawned?.close('SIGKILL') + spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined }) @@ -96,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook hooks: { PreToolUse: [{ hooks: [{ type: 'command', command: 'echo "bash blocked by policy" >&2; exit 2' }] }] }, })) - spawned = spawnAcpAgent(workdir) + spawned = launchAcpTestAgent({ agent: AGENT, cwd: workdir }) const { client, updates } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) diff --git a/examples/sandbox-acp-agent/tests/escalation.e2e.ts b/examples/sandbox-acp-agent/tests/escalation.e2e.ts index 93915717a1..a7e8787e36 100644 --- a/examples/sandbox-acp-agent/tests/escalation.e2e.ts +++ b/examples/sandbox-acp-agent/tests/escalation.e2e.ts @@ -1,20 +1,18 @@ -import { spawn, spawnSync, type ChildProcessWithoutNullStreams } from 'node:child_process' -import { Readable, Writable } from 'node:stream' +import { spawnSync } from 'node:child_process' import { mkdtemp, readFile, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it } from 'vitest' import { - ClientSideConnection, - ndJsonStream, PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, type RequestPermissionRequest, - type RequestPermissionResponse, - type SessionNotification, } from '@agentclientprotocol/sdk' +import { + launchAcpTestAgent, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from '@deepseek-ai/dsh-acp-snapshot' /** * examples/sandbox-acp-agent end to end. @@ -35,12 +33,11 @@ import { * escalation target the model picks can land the write. */ -const binScript = fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) -// The subprocess runs from a temp cwd OUTSIDE the repo; point tsx at the repo -// tsconfig so the unbuilt `paths` map resolves (see examples/AGENTS.md). -const repoTsconfig = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const AGENT: AgentUnderTest = { + binScript: fileURLToPath(new URL('../../../packages/ui/acp-agent/src/bin.ts', import.meta.url)), + configPath: fileURLToPath(new URL('../cordis.yml', import.meta.url)), + tsconfigPath: fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)), +} // A usable confining runner, probed the same way the executor suites do: // bwrap on Linux, Seatbelt's sandbox-exec on macOS. Without one the strict @@ -56,44 +53,19 @@ const hasSeatbelt = process.platform === 'darwin' && spawnSync('sandbox-exec', [ }).status === 0 const hasRunner = hasBwrap || hasSeatbelt -interface Spawned { - child: ChildProcessWithoutNullStreams - client: ClientSideConnection - updates: SessionNotification['update'][] +interface Spawned extends LaunchedAcpTestAgent { permissionRequests: RequestPermissionRequest[] - stderr: string[] } /** Boot the example as an ACP subprocess; the scripted client answers every permission prompt with `answer`. */ -function spawnSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { - const child = spawn( - process.execPath, - ['--import', tsxLoader, binScript, configPath], - { - cwd, - // A dummy key lets the deepseek adapter boot keyless (presence-checked at - // apply, used only on a real model call); the with-key tests carry the - // real key, so the fallback is inert there. - env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig }, - stdio: ['pipe', 'pipe', 'pipe'], - }, - ) - const stderr: string[] = [] - child.stderr.setEncoding('utf8') - child.stderr.on('data', (chunk: string) => stderr.push(chunk)) - - const updates: SessionNotification['update'][] = [] +function launchSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawned { const permissionRequests: RequestPermissionRequest[] = [] - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(child.stdout) as ReadableStream, - ) - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - return Promise.resolve() - }, - requestPermission(params: RequestPermissionRequest): Promise { + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd, + // A dummy key lets the adapter boot keylessly; live tests carry the real key. + env: { DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot' }, + requestPermission(params) { permissionRequests.push(params) const option = params.options.find(o => o.optionId === answer) // The scripted human: pick the requested option when the prompt offers @@ -102,15 +74,14 @@ function spawnSandboxAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once') return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } }) }, }) - const client = new ClientSideConnection(makeClient, stream) - return { child, client, updates, permissionRequests, stderr } + return Object.assign(launched, { permissionRequests }) } let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - if (spawned !== undefined && spawned.child.exitCode === null) spawned.child.kill('SIGKILL') + await spawned?.close('SIGKILL') spawned = undefined if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) workdir = undefined @@ -119,7 +90,7 @@ afterEach(async () => { describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => { it('boots the tree — sandbox executor + approval service + bridge — and opens a session', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-smoke-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client } = spawned // A dummy key boots the adapter; no prompt is ever sent, so no model call // and no sandbox runner probe happen. This drives the fiber tree the same @@ -132,7 +103,7 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () it('advertises both session config options and honors a switch end to end (no key, no model)', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) // This tree composes bash-sandbox (mode: read-only) + approval → both @@ -164,7 +135,7 @@ describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent e2e: the live approval loop', () => { it('denial → model escalation → editor prompt → allow-once → the retried write lands on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = spawnSandboxAcpAgent(workdir, 'allow-once') + spawned = launchSandboxAcpAgent(workdir, 'allow-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) @@ -193,7 +164,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || !hasRunner)('sandbox-acp-agent it('a rejected escalation stays denied: no write lands, the turn still ends', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-e2e-')) - spawned = spawnSandboxAcpAgent(workdir, 'reject-once') + spawned = launchSandboxAcpAgent(workdir, 'reject-once') const { client, permissionRequests } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) diff --git a/packages/support/README.md b/packages/support/README.md index c8883a89ff..9a05ad3c9a 100644 --- a/packages/support/README.md +++ b/packages/support/README.md @@ -4,9 +4,9 @@ Packages that exist to serve development, testing, and the examples rather than | Package | Role | ctx key | |---|---|---| -| `acp-snapshot/` | ACP snapshot suite kit: subprocess scenario harness + golden normalizers + the `defineAcpSnapshotSuite` factory | (library — imported by example `*.snapshot.ts` suites) | +| `acp-snapshot/` | ACP test kit: shared subprocess/client launcher + snapshot harness, normalizers, and suite factory | (library — imported by ACP e2e and `*.snapshot.ts` suites) | | `invariants/` | Dev-mode event-contract assertions | (listens on `session/*`, `agent/*`) | | `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) | | `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) | -`invariants` runs only in dev mode (contract checks, not runtime behavior). `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the snapshot tier's harness/normalizer/suite machinery so every example's suite is a scenario table over one shared, gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. +`invariants` runs only in dev mode (contract checks, not runtime behavior). `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the ACP subprocess/client boundary plus the snapshot harness, normalizers, and suite machinery, so e2e tests share one launcher and every snapshot suite is a scenario table over one gate-covered implementation. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index ac9c0ceee3..4a43d0eef9 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -2,8 +2,9 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tier (`pnpm run test:snapshot`, [testing policy](../../../docs/testing.md)). An example gets a full snapshot suite from a scenario table plus a fixtures directory; every compare/guard mechanic lives here, under the per-file coverage gate, instead of being copied per example. -Three layers, importable separately: +Four layers, importable separately: +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. @@ -39,4 +40,4 @@ A scenario booting a differently-composed tree sets its own `configPath` (an ove The example also ships a `cordis.snapshot.yml` replay overlay next to its `cordis.yml` (the bin swaps them under `DSH_SNAPSHOT=replay` — [single-source replay config RFC](../../../docs/rfc/implemented/testing/2026-07-04-single-source-acp-replay-config.md)); replay fixtures are served by [`dsh-llm-replay`](../llm-replay/README.md), which this package points at via the `DSH_SNAPSHOT_*` env vars it sets on the child. `pnpm run test:snapshot:record` calls the live LLM and rewrites the recorded scenarios' model fixtures; `pnpm run test:snapshot:refresh` stays keyless, runs the replay overlay, and rewrites stdout, comparable session-log goldens, and each pin's Markdown prompt snapshot from the committed model scripts. Fixture roles, record/replay/refresh semantics, and scenario-table fields are documented on `Scenario` and in the [snapshot RFC](../../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md). -Constraints: `suite.ts` imports vitest, so the package is importable only inside a vitest run (the harness and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the harness speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript). +Constraints: `suite.ts` imports vitest, so the package entry is importable only inside a vitest run (the launcher, harness, and normalizers have no such dependency but ship from the same entry). ACP-specific by design — the launcher speaks the SDK's `ClientSideConnection`. Permission round-trips are scriptable: `InputScript.permissionAnswers` is a FIFO queue of option-kind selections (`allow_once`, `reject_once`, …) the client maps to the agent-issued `optionId` at answer time; an absent or exhausted queue answers `cancelled`, and a kind the request never offered rejects the run (the agent is answered `cancelled`, so a tolerant agent cannot absorb the scenario bug). Session config options are scriptable too: the `setConfigOption` step switches a knob over `session/set_config_option`, and `setConfigOptionExpectError` asserts the bridge rejects an unknown id or out-of-vocabulary value (the error frame stays in the transcript). diff --git a/packages/support/acp-snapshot/package.json b/packages/support/acp-snapshot/package.json index 363bc86e25..b14be09c5b 100644 --- a/packages/support/acp-snapshot/package.json +++ b/packages/support/acp-snapshot/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-acp-snapshot", - "description": "ACP snapshot suite kit: real-subprocess scenario harness, golden normalizers, and the suite factory behind the keyless snapshot tier", + "description": "ACP test kit: shared subprocess launcher, snapshot scenario harness, golden normalizers, and suite factory", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 491d3ea884..93bb556ba6 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -16,54 +16,20 @@ * @module @deepseek-ai/dsh-acp-snapshot/harness */ -import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' import { cp, mkdtemp, readFile, readdir, rm } from 'node:fs/promises' import { existsSync } from 'node:fs' import { tmpdir } from 'node:os' import { join, delimiter } from 'node:path' -import { fileURLToPath } from 'node:url' -import { Readable, Writable } from 'node:stream' import { ClientSideConnection, - ndJsonStream, PROTOCOL_VERSION, - type Agent as AcpAgent, - type Client, type RequestPermissionRequest, type RequestPermissionResponse, type SessionNotification, } from '@agentclientprotocol/sdk' +import { launchAcpTestAgent, type AgentUnderTest, type LaunchedAcpTestAgent } from './launcher.ts' -// Resolve tsx's ESM loader to an ABSOLUTE path once: the child runs with its -// cwd in a temp dir OUTSIDE the repo, where a bare `--import tsx` would not -// resolve from node_modules. import.meta.resolve gives this package's tsx -// regardless of the child cwd. -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) - -/** - * The agent composition a scenario runs against: which bin to boot and which - * leaf config it loads. All paths are ABSOLUTE — the subprocess cwd is a temp - * dir outside the repo, so relative resolution would miss; a suite resolves - * them from its own `import.meta.url`. - */ -export interface AgentUnderTest { - /** The agent bin entry (e.g. `packages/ui/acp-agent/src/bin.ts`), run unbuilt via tsx. */ - binScript: string - /** - * The example's live `cordis.yml`. Under `DSH_SNAPSHOT=replay` the bin swaps - * it for the sibling `cordis.snapshot.yml` (the keyless replay overlay), so - * one path serves both modes. - */ - configPath: string - /** - * The repo-root tsconfig whose `paths` map resolves the unbuilt workspace - * imports. Passed to the child as `TSX_TSCONFIG_PATH`: tsx finds a tsconfig - * by searching UP from the child's cwd — a temp dir outside the repo — so - * without the explicit pin the dsh-* imports fail before the bin writes a - * byte. - */ - tsconfigPath: string -} +export type { AgentUnderTest } from './launcher.ts' /** * One step of a scenario's deterministic input script (`input.json`). The @@ -194,11 +160,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Everything past the temp-dir creation runs under a try/finally that always // removes both dirs — so a failure in workspace seeding, spawn, or any step // never leaks them (the "e2e tests own their resources" rule). - let child: ChildProcessWithoutNullStreams | undefined + let launched: LaunchedAcpTestAgent | undefined let sessionId: string | undefined let sessionLogs: HarvestedLog[] = [] - const rawBuffers: Buffer[] = [] - const stderrChunks: string[] = [] try { // Seed the workspace if the scenario ships one (a file the agent reads/edits). // Copied into the temp cwd so the agent's bash tools see it; the goldens @@ -207,51 +171,15 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise await cp(opts.workspaceDir, cwd, { recursive: true }) } const env: NodeJS.ProcessEnv = { - ...process.env, - TSX_TSCONFIG_PATH: opts.agent.tsconfigPath, DSH_SNAPSHOT: opts.mode, DSH_SNAPSHOT_FILE: opts.fixtureFile, DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot, - DSH_HOME: join(cwd, '.dsh'), - DSH_AGENTS_HOME: join(cwd, '.agents'), ...opts.overrideFile !== undefined ? { DSH_SNAPSHOT_OVERRIDE: opts.overrideFile } : {}, ...opts.childFiles !== undefined && opts.childFiles.length > 0 ? { DSH_SNAPSHOT_CHILD_FILES: opts.childFiles.join(delimiter) } : {}, } - child = spawn( - process.execPath, - ['--import', tsxLoader, opts.agent.binScript, opts.configPath ?? opts.agent.configPath], - { cwd, env, stdio: ['pipe', 'pipe', 'pipe'] }, - ) - - child.stderr.setEncoding('utf8') - child.stderr.on('data', (c: string) => stderrChunks.push(c)) - - // Tee raw stdout: accumulate the bytes for the golden + purity check, and ALSO - // feed the same bytes to the SDK client through a passthrough. Buffer the raw - // bytes (not per-chunk utf8 strings) and decode once at the end, so a - // multibyte sequence split across two 'data' events can't corrupt the golden. - const passthrough = new Readable({ read() {} }) - child.stdout.on('data', (buf: Buffer) => { - rawBuffers.push(buf) - passthrough.push(buf) - }) - child.stdout.on('end', () => passthrough.push(null)) - - const stream = ndJsonStream( - Writable.toWeb(child.stdin) as WritableStream, - Readable.toWeb(passthrough) as ReadableStream, - ) - // Watcher so a step can block until the client OBSERVES a particular - // session/update — used by promptAndCancel to pin frame order (send cancel - // only after the streamed agent_message_chunk has arrived, so those frames - // deterministically precede the cancelled prompt response). - const updateWaiters: { match: (u: SessionNotification['update']) => boolean; resolve: () => void }[] = [] - const waitForUpdate = (match: (u: SessionNotification['update']) => boolean): Promise => - new Promise(resolve => updateWaiters.push({ match, resolve })) - // Permission answers are consumed FIFO across the whole run; exhaustion // falls back to `cancelled` so approval-free scenarios keep the plain stub. const permissionQueue = [...input.permissionAnswers ?? []] @@ -263,22 +191,11 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // callback answers `cancelled` (a well-defined path for the agent), // captures the error here, and the step loop fails the run on it. let scriptError: Error | undefined - const makeClient = (_agent: AcpAgent): Client => ({ - sessionUpdate(params: SessionNotification): Promise { - for (let i = updateWaiters.length - 1; i >= 0; i--) { - const waiter = updateWaiters[i] - // The index is always in-bounds (i only decreases; splice removes at - // i, so lower entries stay valid); the guard satisfies - // noUncheckedIndexedAccess. - /* v8 ignore next 1 -- unreachable in-bounds guard, see above */ - if (waiter === undefined) continue - if (waiter.match(params.update)) { - updateWaiters.splice(i, 1) - waiter.resolve() - } - } - return Promise.resolve() - }, + launched = launchAcpTestAgent({ + agent: opts.agent, + cwd, + ...opts.configPath !== undefined ? { configPath: opts.configPath } : {}, + env, requestPermission(params: RequestPermissionRequest): Promise { const answer = permissionQueue.shift() if (answer === undefined) return Promise.resolve({ outcome: { outcome: 'cancelled' } }) @@ -296,10 +213,11 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise return Promise.resolve({ outcome: { outcome: 'selected', optionId: option.optionId } }) }, }) - const client = new ClientSideConnection(makeClient, stream) + const active = launched + const { client } = active for (const step of input.steps) { - await runStep(client, step, cwd, waitForUpdate, () => sessionId, (id) => { sessionId = id }) + await runStep(client, step, cwd, match => active.waitForUpdate(match), () => sessionId, (id) => { sessionId = id }) // A permission exchange happens while a step's request is in flight, so // by the time the step settles any script bug it exposed is captured — // fail the run HERE, as a harness error, rather than hoping the agent's @@ -308,26 +226,22 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise } // Done driving: close stdin so the server disposes gracefully (flushing // persistence) and exits. Then await exit so the harvested log is complete. - child.stdin.end() - await waitForExit(child) + await active.close() // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) } finally { // Failure-safe teardown: kill a still-running child and drop the temp dirs // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a - // process or dir. `child` is undefined only if spawn itself threw. - if (child !== undefined && child.exitCode === null && child.signalCode === null) { - child.kill('SIGKILL') - await waitForExit(child) - } + // process or dir. `launched` is undefined only if launch itself threw. + await launched?.close('SIGKILL') await rm(cwd, { recursive: true, force: true }) await rm(sessionsRoot, { recursive: true, force: true }) } return { - rawStdout: Buffer.concat(rawBuffers).toString('utf8'), - stderr: stderrChunks.join(''), + rawStdout: launched.rawStdout(), + stderr: launched.stderr(), cwd, ...sessionId !== undefined ? { sessionId } : {}, sessionLogs, @@ -339,7 +253,7 @@ async function runStep( client: ClientSideConnection, step: InputStep, cwd: string, - waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise, + waitForUpdate: (match: (u: SessionNotification['update']) => boolean) => Promise, getSessionId: () => string | undefined, setSessionId: (id: string) => void, ): Promise { @@ -433,16 +347,6 @@ async function runStep( } } -/** Resolve once the child process exits (any code/signal). */ -function waitForExit(child: ChildProcessWithoutNullStreams): Promise { - // Race guard: both call sites run within one synchronous frame of - // stdin.end()/kill(), so the exit event cannot have been delivered yet; - // kept for any future caller that awaits in between. - /* v8 ignore next 1 -- unreachable race guard, see above */ - if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve() - return new Promise(resolve => child.once('exit', () => { resolve() })) -} - /** * Harvest EVERY persisted `.jsonl` session log under a sessions root, parse each * header line, and return them ordered primary-first: the top-level session (no diff --git a/packages/support/acp-snapshot/src/index.ts b/packages/support/acp-snapshot/src/index.ts index 74bee95385..402bd3aa3d 100644 --- a/packages/support/acp-snapshot/src/index.ts +++ b/packages/support/acp-snapshot/src/index.ts @@ -1,13 +1,14 @@ /** * ACP snapshot suite kit — the shared machinery behind the keyless snapshot - * tier (`pnpm run test:snapshot`). Three layers, composable per example: - * the subprocess scenario harness ({@link runScenario}), the pure golden - * normalizers ({@link normalizeStdout} / {@link normalizeSessionLog} / - * {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite factory - * ({@link defineAcpSnapshotSuite}) that registers a scenario table as a full - * describe/it tree. An example's `*.snapshot.ts` supplies only its - * {@link AgentUnderTest} paths, its snapshots directory, and its - * {@link Scenario} table. + * tier (`pnpm run test:snapshot`). Four layers, composable per example: the + * shared subprocess/client launcher ({@link launchAcpTestAgent}), the scripted + * scenario harness ({@link runScenario}), the pure golden normalizers + * ({@link normalizeStdout} / {@link normalizeSessionLog} / + * {@link scrubRequestHeaders} / {@link scrubSystemPrompts}), and the suite + * factory ({@link defineAcpSnapshotSuite}) that registers a scenario table as a + * full describe/it tree. Ordinary ACP e2e tests can use the launcher directly; + * an example's `*.snapshot.ts` supplies only its {@link AgentUnderTest} paths, + * snapshots directory, and {@link Scenario} table. * * NOTE: ./suite.ts imports vitest, so this package is importable only inside a * vitest run — a support-tier constraint stated in the README. @@ -17,7 +18,6 @@ export { runScenario, - type AgentUnderTest, type HarvestedLog, type InputScript, type InputStep, @@ -25,6 +25,12 @@ export { type RunOptions, type RunResult, } from './harness.ts' +export { + launchAcpTestAgent, + type AcpTestLaunchOptions, + type AgentUnderTest, + type LaunchedAcpTestAgent, +} from './launcher.ts' export { normalizeSessionLog, normalizeStdout, diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts new file mode 100644 index 0000000000..635a02ca35 --- /dev/null +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -0,0 +1,152 @@ +/** + * Shared launcher for ACP tests that drive an unbuilt agent subprocess over + * JSON-RPC stdio. It owns the tsx loader, workspace-resolution environment, + * stdout tee, SDK client, update collection, permission fallback, and process + * shutdown so e2e and snapshot suites do not each reconstruct that boundary. + * + * @module @deepseek-ai/dsh-acp-snapshot/launcher + */ + +import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { Readable, Writable } from 'node:stream' +import { + ClientSideConnection, + ndJsonStream, + type Agent as AcpAgent, + type Client, + type RequestPermissionRequest, + type RequestPermissionResponse, + type SessionNotification, +} from '@agentclientprotocol/sdk' + +// The child runs from a temp directory outside the repo, where a bare +// `--import tsx` cannot resolve. Resolve this package's loader once instead. +const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) + +/** The unbuilt agent entry, leaf config, and workspace tsconfig an ACP test boots. */ +export interface AgentUnderTest { + /** The agent bin entry (for example `packages/ui/acp-agent/src/bin.ts`). */ + binScript: string + /** The leaf `cordis.yml` loaded by the bin. */ + configPath: string + /** The repo tsconfig whose paths resolve unbuilt workspace imports. */ + tsconfigPath: string +} + +/** Options for one ACP test subprocess. */ +export interface AcpTestLaunchOptions { + /** The agent composition to boot. */ + agent: AgentUnderTest + /** Process cwd and default session-home root. */ + cwd: string + /** Alternate leaf config for this launch. */ + configPath?: string + /** Extra environment values layered over the parent environment. */ + env?: NodeJS.ProcessEnv + /** Permission handler; omitted requests fail closed as `cancelled`. */ + requestPermission?: (params: RequestPermissionRequest) => Promise +} + +/** A running ACP test process and its captured client-side surfaces. */ +export interface LaunchedAcpTestAgent { + /** The child process, exposed for process-level assertions. */ + child: ChildProcessWithoutNullStreams + /** The SDK connection backed by the child's stdio. */ + client: ClientSideConnection + /** Session updates in receive order. */ + updates: SessionNotification['update'][] + /** Decode all stdout bytes captured so far. */ + rawStdout(): string + /** Decode all stderr chunks captured so far. */ + stderr(): string + /** Resolve when a future session update matches the predicate. */ + waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise + /** Gracefully close stdin, or send a signal, and wait for process exit. */ + close(signal?: NodeJS.Signals): Promise +} + +/** + * Boot an ACP agent subprocess and connect an SDK client to its stdio. + * + * @param options Agent paths, cwd, environment, and optional permission handler. + * @returns The running process, connected client, captures, and shutdown handle. + */ +export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTestAgent { + const { agent, cwd } = options + const child = spawn( + process.execPath, + ['--import', tsxLoader, agent.binScript, options.configPath ?? agent.configPath], + { + cwd, + env: { + ...process.env, + ...options.env, + TSX_TSCONFIG_PATH: agent.tsconfigPath, + DSH_HOME: join(cwd, '.dsh'), + DSH_AGENTS_HOME: join(cwd, '.agents'), + }, + stdio: ['pipe', 'pipe', 'pipe'], + }, + ) + + const stderrChunks: string[] = [] + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => stderrChunks.push(chunk)) + + const rawBuffers: Buffer[] = [] + const passthrough = new Readable({ read() {} }) + child.stdout.on('data', (buffer: Buffer) => { + rawBuffers.push(buffer) + passthrough.push(buffer) + }) + child.stdout.on('end', () => passthrough.push(null)) + + const updates: SessionNotification['update'][] = [] + const updateWaiters: { + match: (update: SessionNotification['update']) => boolean + resolve: (update: SessionNotification['update']) => void + }[] = [] + const stream = ndJsonStream( + Writable.toWeb(child.stdin) as WritableStream, + Readable.toWeb(passthrough) as ReadableStream, + ) + const makeClient = (_agent: AcpAgent): Client => ({ + sessionUpdate(params: SessionNotification): Promise { + updates.push(params.update) + for (let index = updateWaiters.length - 1; index >= 0; index--) { + const waiter = updateWaiters[index] + /* v8 ignore next 1 -- index is bounded by the array length */ + if (waiter === undefined) continue + if (!waiter.match(params.update)) continue + updateWaiters.splice(index, 1) + waiter.resolve(params.update) + } + return Promise.resolve() + }, + requestPermission: options.requestPermission + ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), + }) + const client = new ClientSideConnection(makeClient, stream) + + return { + child, + client, + updates, + rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), + stderr: () => stderrChunks.join(''), + waitForUpdate: match => new Promise(resolve => updateWaiters.push({ match, resolve })), + async close(signal?: NodeJS.Signals): Promise { + if (child.exitCode !== null || child.signalCode !== null) return + if (signal === undefined) child.stdin.end() + else child.kill(signal) + await waitForExit(child) + }, + } +} + +/** Resolve once a running child exits. */ +function waitForExit(child: ChildProcessWithoutNullStreams): Promise { + return new Promise(resolve => child.once('exit', () => { resolve() })) +} diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index b0817a8d04..ec1ed5cf6f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -3,7 +3,9 @@ import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' import { afterAll, describe, expect, it } from 'vitest' +import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { runScenario, type AgentUnderTest, type InputStep } from '../src/harness.ts' +import { launchAcpTestAgent } from '../src/launcher.ts' /** * Unit tests for the subprocess harness, driven through the REAL spawn path @@ -38,6 +40,37 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ permissionProbe: true, echoEnv: true, stderrNote: 'launcher stderr' }) + const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-launcher-sessions-')) + tempDirs.push(sessionsRoot) + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + configPath: AGENT.configPath, + env: { + DSH_SNAPSHOT: 'replay', + DSH_SNAPSHOT_FILE: fixtureFile, + DSH_SNAPSHOT_SESSIONS_ROOT: sessionsRoot, + }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) + const nextChunk = launched.waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk') + await launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) + expect((await nextChunk).sessionUpdate).toBe('agent_message_chunk') + expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) + expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') + expect(launched.stderr()).toContain('launcher stderr') + await launched.close() + await launched.close('SIGKILL') + + // The minimal shape needs no environment or config override. + const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + await minimal.close() + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From b579a13db759c38c41541a021bbbac188f4bf8a8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 00:28:20 +0800 Subject: [PATCH 008/323] test: trim PostToolUse snapshot retries --- .../2026-07-04-hook-snapshot-matrix.md | 4 +- examples/acp-agent/tests/acp.snapshot.ts | 3 - .../hook-cc-posttool-block/input.json | 2 +- .../hook-cc-posttool-block/session.jsonl | 694 +----------------- .../stdout.golden.jsonl | 434 +---------- .../hook-codex-posttool-block/input.json | 2 +- .../hook-codex-posttool-block/session.jsonl | 2 +- 7 files changed, 16 insertions(+), 1125 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 47db2cd793..1b3e70eb13 100644 --- a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -29,6 +29,8 @@ Thirteen scenarios under `examples/acp-agent/tests/snapshots/`, naming `hook- Date: Tue, 14 Jul 2026 00:46:46 +0800 Subject: [PATCH 009/323] fix: let snapshot recording create fixture inventory --- packages/support/acp-snapshot/src/suite.ts | 38 ++++++++++++++----- .../support/acp-snapshot/tests/suite.spec.ts | 17 ++++++++- 2 files changed, 44 insertions(+), 11 deletions(-) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 6311a15031..4d87093c8a 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -31,7 +31,7 @@ * @module @deepseek-ai/dsh-acp-snapshot/suite */ -import { readFile, readdir, writeFile } from 'node:fs/promises' +import { readFile, readdir, rm, writeFile } from 'node:fs/promises' import { existsSync } from 'node:fs' import { join } from 'node:path' import { describe, expect, it } from 'vitest' @@ -410,9 +410,12 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const input = JSON.parse(await readFile(join(dir, 'input.json'), 'utf8')) as InputScript const overrideFile = join(dir, 'replay.override.json') const workspaceDir = join(dir, 'workspace') - const fixtureFiles = await sessionFixtures(dir) + // Replay/refresh need the committed inventory up front because those + // files drive the model scripts. Record mode creates that inventory + // from the harvested live logs, so it must also work for a brand-new + // scenario with no session.jsonl yet. + let fixtureFiles = RECORDING ? [] : await sessionFixtures(dir) const childFixtureFiles = fixtureFiles.slice(1) - const childSessions = childFixtureFiles.length const comparesLog = scenario.comparesLog ?? scenario.hasModelTurn const result = await runScenario(input, { agent, @@ -421,7 +424,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { ...existsSync(overrideFile) ? { overrideFile } : {}, // In REPLAY, forward the recorded child fixtures so each subagent session // replays from its own script. In RECORD they are harvested, not read. - ...!RECORDING && childSessions > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, + ...!RECORDING && childFixtureFiles.length > 0 ? { childFiles: childFixtureFiles.map(file => join(dir, file)) } : {}, ...existsSync(workspaceDir) ? { workspaceDir } : {}, // A scenario booting an overlay tree passes its own live config; the // bin's replay swap derives the sibling `*cordis.snapshot.yml` from it. @@ -460,18 +463,35 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { || (REFRESHING && comparesLog) if (writesSessionFixtures) { expect(result.sessionLogs.length, `${mode} produced no session log to harvest`).toBeGreaterThan(0) - expect(result.sessionLogs.length, `expected ${childSessions + 1} session logs (parent + children)`) - .toBe(childSessions + 1) + if (REFRESHING) { + expect(result.sessionLogs.length, `expected ${fixtureFiles.length} session logs (parent + children)`) + .toBe(fixtureFiles.length) + } + const outputFixtureFiles = [ + 'session.jsonl', + ...Array.from({ length: result.sessionLogs.length - 1 }, (_, i) => `session.${i + 1}.jsonl`), + ] const primary = (result.sessionLogs[0] as HarvestedLog).content - await writeFile(join(dir, 'session.jsonl'), scrub( + await writeFile(join(dir, outputFixtureFiles[0] as string), scrub( REFRESHING ? stabilizeRefreshLog(primary, existingFixtures[0] as string, replacements) : primary, )) for (let i = 1; i < result.sessionLogs.length; i++) { const child = (result.sessionLogs[i] as HarvestedLog).content - await writeFile(join(dir, `session.${i}.jsonl`), scrub( + await writeFile(join(dir, outputFixtureFiles[i] as string), scrub( REFRESHING ? stabilizeRefreshLog(child, existingFixtures[i] as string, replacements) : child, )) } + if (RECORDING) { + const outputNames = new Set(outputFixtureFiles) + const entries = await readdir(dir, { withFileTypes: true }) + await Promise.all(entries + .filter(entry => entry.isFile() + && entry.name.startsWith('session.') + && entry.name.endsWith('.jsonl') + && !outputNames.has(entry.name)) + .map(entry => rm(join(dir, entry.name)))) + fixtureFiles = outputFixtureFiles + } if (scenario.pinsHeader === true) { const primary = result.sessionLogs[0] as HarvestedLog const prompts = normalizedSystemPrompts(primary.content, ctx) @@ -498,7 +518,7 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { // prompt becomes the fixture's `{{system}}`; non-pinning scenarios // additionally tokenize tools/prefix. The dedicated header guard below // compares those omitted values against their class's pin artifacts. - expect(result.sessionLogs.length, 'this scenario must persist a session log').toBe(childSessions + 1) + expect(result.sessionLogs.length, 'this scenario must persist one log per session fixture').toBe(fixtureFiles.length) for (let i = 0; i < fixtureFiles.length; i++) { const harvested = scrub((result.sessionLogs[i] as HarvestedLog).content) const fixture = scrub(await readFile(join(dir, fixtureFiles[i] as string), 'utf8')) diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index f27f36c564..7aa218526c 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -1,4 +1,4 @@ -import { cpSync, mkdtempSync, readFileSync, writeFileSync } from 'node:fs' +import { cpSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs' import { rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' @@ -69,7 +69,13 @@ const RECORD_SCENARIOS: Scenario[] = [ // committed record fixtures/goldens in place. const BOOTSTRAP = process.env.ACP_SNAPSHOT_SPEC_BOOTSTRAP === '1' const recordDir = BOOTSTRAP ? RECORD_SRC : mkdtempSync(join(tmpdir(), 'acp-snap-record-suite-')) -if (!BOOTSTRAP) cpSync(RECORD_SRC, recordDir, { recursive: true }) +if (!BOOTSTRAP) { + cpSync(RECORD_SRC, recordDir, { recursive: true }) + // Record mode owns its output inventory: a new scenario has no primary yet, + // while a changed child count can leave old numbered fixtures behind. + rmSync(join(recordDir, 'rec-pin', 'session.jsonl')) + writeFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'stale child\n') +} const refreshDir = mkdtempSync(join(tmpdir(), 'acp-snap-refresh-suite-')) cpSync(REPLAY_DIR, refreshDir, { recursive: true }) staleRefreshFixtures(refreshDir) @@ -141,6 +147,13 @@ describe('defineAcpSnapshotSuite: refresh write-back', () => { }) }) +describe('defineAcpSnapshotSuite: record inventory write-back', () => { + it('creates a missing primary fixture and prunes stale child fixtures', () => { + expect(readFileSync(join(recordDir, 'rec-pin', 'session.jsonl'), 'utf8')).toContain('"type":"session"') + expect(() => readFileSync(join(recordDir, 'rec-child', 'session.2.jsonl'), 'utf8')).toThrow() + }) +}) + describe('defineAcpSnapshotSuite: registration contract', () => { it("throws when a scenario's header class has no pinning scenario", () => { expect(() => { From f95a411b0ac7d5f347c602308df1123dc1aecd5f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:09:07 +0800 Subject: [PATCH 010/323] fix: record self-limiting hook snapshot --- .../2026-07-04-hook-snapshot-matrix.md | 2 +- .../hook-cc-posttool-block/input.json | 2 +- .../hook-cc-posttool-block/session.jsonl | 253 ++++++++++++------ .../stdout.golden.jsonl | 83 +++++- .../workspace/hooks.json | 2 +- .../workspace/posttool-once.sh | 7 + 6 files changed, 259 insertions(+), 90 deletions(-) create mode 100644 examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh diff --git a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md index 1b3e70eb13..0327662d3d 100644 --- a/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md +++ b/docs/rfc/implemented/testing/2026-07-04-hook-snapshot-matrix.md @@ -29,7 +29,7 @@ Thirteen scenarios under `examples/acp-agent/tests/snapshots/`, naming `hook-&2; exit 2" } + { "type": "command", "command": "sh posttool-once.sh" } ] } ] diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh new file mode 100644 index 0000000000..2acc98bb58 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/workspace/posttool-once.sh @@ -0,0 +1,7 @@ +#!/bin/sh +if test -e .posttool-blocked; then + exit 0 +fi +: > .posttool-blocked +printf '%s\n' 'tool output rejected by policy: retry once' >&2 +exit 2 From d7de8a8d138b70d79e7066195ac11a512cbf4249 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:24:20 +0800 Subject: [PATCH 011/323] refactor: narrow compaction surface --- docs/cordis-catalog/services.md | 4 +- docs/core-data-structures/compaction.md | 14 +- .../2026-06-18-compaction-capability-seam.md | 4 +- packages/compact/compact-basic/README.md | 2 +- packages/compact/compact-basic/src/index.ts | 24 ++- .../compact-basic/tests/compact-basic.spec.ts | 147 +++++++----------- packages/compact/compact/README.md | 2 +- packages/compact/compact/src/index.ts | 11 +- packages/compact/compact/src/types.ts | 8 - .../compact/compact/tests/compact.spec.ts | 23 ++- .../cordis/tool-cordis/src/api-catalog.ts | 4 +- 11 files changed, 95 insertions(+), 148 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index ecb68913df..bfb31749d5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -113,12 +113,12 @@ Implementations MUST honor: ```ts cordis-catalog abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise -abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise +abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` Types: [Message](../core-data-structures/core.md) -Source: [`packages/compact/compact/src/index.ts:65`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:66`](../../packages/compact/compact/src/index.ts) ## `ctx.fs` — `FileSystem` (abstract seam) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 2f402be57d..de350df9f3 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -1,6 +1,6 @@ # Compaction -The compaction seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary (see the [compaction capability-seam RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). +The compaction seam — a [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md) split like bash: interface ([dsh-compact](../../packages/compact/compact), `ctx.compact`), implementation (a backend such as [dsh-compact-basic](../../packages/compact/compact-basic)), and consumer (a `/compact` tool, deferred). Compaction is **one optional capability**, not part of the agent-loop spine — so its vocabulary lives here, not in [core.md](core.md). A tokenizer- or template-based backend is a sibling package implementing the same interface. Unlike bash, the interface necessarily depends on `dsh-session` and `dsh-llm`: its verbs act on an agent-owned `Session`, and its durable summary event uses the `ContentBlock` vocabulary (see the [compaction capability-seam RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). Source: [`packages/compact/compact/src/types.ts`](../../packages/compact/compact/src/types.ts) @@ -20,18 +20,10 @@ These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` b ## `CompactionResult` -What a successful compaction returns to its caller: the seqs of the three appended `compact/*` events, the summary blocks, and the shadowed range/seqs plus the estimated token count. +What a successful compaction returns to its caller: the shadowed range and seqs plus the estimated token count. The durable `compact/summary` event owns the raw summary and bookkeeping-event identity. ```ts type-equiv interface CompactionResult { - /** The seq of the appended `compact/start` event. */ - startSeq: number - /** The seq of the appended `compact/summary` event. */ - summarySeq: number - /** The seq of the appended `compact/end` event. */ - endSeq: number - /** The summary content blocks produced by the backend. */ - summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A @@ -50,6 +42,6 @@ interface CompactionResult { ## The service -`CompactService` (`ctx.compact`, abstract — defined in [`packages/compact/compact/src/index.ts`](../../packages/compact/compact/src/index.ts)) declares two abstract methods: `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` checks token pressure and compacts an older range if the history is too large (returning `null` when nothing needs it), and `compactRegion(session, start, end, agent, signal?)` forcibly summarizes surface nodes `[start, end]` into a single replacement node. `compactIfNeeded`'s parameters are all required — the loop's `agent/pre-step` checkpoint supplies the agent, the assembled `fullSystemPrompt`, the instance's composed `sessionPrefix` (request-only messages the derived history omits, so the pressure estimate must count them), and the turn `signal`. A backend summarizing via `ctx.llm.stream()` must forward `signal` into the call's `GenerateOptions.signal`, so an abort or dispose tears down the in-flight summarization. The entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation. +`CompactService` (`ctx.compact`, abstract — defined in [`packages/compact/compact/src/index.ts`](../../packages/compact/compact/src/index.ts)) declares two abstract methods: `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` checks token pressure and compacts an older range if the history is too large (returning `null` when nothing needs it), and `compactRegion(start, end, agent, signal?)` forcibly summarizes surface nodes `[start, end]` from `agent.session` into a single replacement node. `compactIfNeeded`'s parameters are all required — the loop's `agent/pre-step` checkpoint supplies the agent, the assembled `fullSystemPrompt`, the instance's composed `sessionPrefix` (request-only messages the derived history omits, so the pressure estimate must count them), and the turn `signal`. A backend summarizing via `ctx.llm.stream()` must forward `signal` into the call's `GenerateOptions.signal`, so an abort or dispose tears down the in-flight summarization. The entire strategy — token estimation, retention policy, event sequencing, summarization — is a HOW decision owned by the implementation. Auto-compaction runs on the serial `agent/pre-step` loop seam (fired once per step, after `turn/start` and BEFORE the step opens and its request history is derived), not the `agent/request` waterfall: compaction mutates the session surface in place — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives the request from the already-compacted surface. Retention is turn-agnostic — the only structural guard is tool-pairing balance (a compacted region's edges are balanced cuts on the surface, so it never splits a step's tool-calls from their results), so a single runaway turn that alone exceeds the window compacts its own early closed steps rather than being retained verbatim. The backend that ships this (`dsh-compact-basic`) documents the retention walk, summary shrink validation, bounded re-compaction, and the crash/recoverable failure taxonomy. diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index e0835dcaa6..b99bdfc3b3 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -22,7 +22,7 @@ Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capabil ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation -The capability-seams RFC states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs are defined *over* a `Session` (`compactRegion(session, start, end)`) and its output *is* the content vocabulary (`CompactionResult.summary: ContentBlock[]`). There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). +The capability-seams RFC states the interface package "depends only on cordis" (true of `dsh-bash`, whose vocabulary is self-contained). Compaction **cannot** honor that: its verbs act on an agent-owned `Session` (`compactRegion(start, end, agent)`) and the durable `compact/summary` event carries `ContentBlock[]`. There is no way to express the contract without naming `Session`/`SessionEvent` (from `dsh-session`) and `ContentBlock` (from `dsh-llm`). This is not a coupling smell — it is the contract's domain. The "only cordis" guidance was always shorthand for "the interface depends only on what the contract genuinely names, and never on an implementation." `dsh-session` and `dsh-llm` are themselves interface/vocabulary packages, not implementations; `dsh-compact` still imports no backend. The seam's real invariant — *consumers and implementations evolve independently behind an abstract service* — holds intact. @@ -30,7 +30,7 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface, with only `estimateContentTokens()` and `summarize()` abstract. That recouples the contract to one strategy: a backend that wants a different retention policy or a different event-sequencing would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend, where it belongs, and keeps the interface a pure statement of *what*. The backend remains internally factored — `estimateContentTokens()` and `summarize()` are `protected` hooks a sub-backend can override without reimplementing the walk — but that factoring is the backend's private concern, not the contract's. -`compactIfNeeded(agent, turn, step, fullSystemPrompt, signal)` takes **required** parameters (not the original all-optional shape). The auto-compaction seam (below) always supplies the agent, lifecycle context, assembled system prompt (counted toward the estimate), and the turn's abort signal, so optionality would only invite a hidden default at the seam. The session being compacted comes from the agent context. `compactRegion(session, start, end, agent, turn, step, signal?)` keeps an optional signal (a manual caller may omit it). Passing lifecycle context rather than a concrete model keeps router agents honest: the backend's summarization request can run through `agent/request`, where model-routing plugins already choose the actual model. +`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required inputs from the auto-compaction seam: the agent, assembled system prompt, composed request prefix, and turn abort signal. `compactRegion(start, end, agent, signal?)` uses `agent.session` as its single session identity and keeps an optional signal for manual callers. The backend's summarization request is a direct `ctx.llm.stream()` call; the configured summarization model falls back to the agent's model, and adapters can still route through the LLM seam. ### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index a06e74b818..c956b1e9de 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -17,7 +17,7 @@ The abstract contract states only WHAT compaction does; this backend owns every - **Auto-compaction** — an `agent/pre-step` listener delegates to `compactIfNeeded()` before every step (not just a turn's first — a tool-heavy turn grows the surface mid-turn, so a runaway turn still compacts, and per-step firing is the only moment to rescue it before overflow). `agent/pre-step` is a serial (awaited, in-order) surface-mutation checkpoint that fires after `turn/start` and BEFORE the step opens (`step/start`) and its request history is derived, so compaction mutates the surface — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives once from the result: no double-derive, and the listener cannot see (or need to rewrite) an already-assembled `messages` array. The listener owns no threshold logic of its own (the single token-pressure check lives in `compactIfNeeded()`); because Cordis `serial` bails early on non-void return values, the listener returns `void` and does not use the dispatcher's bail channel as a veto surface. - **Failure handling** — the `compact/start … compact/end` bracket is a log-recorded lock: it makes a crash mid-summarization a detectable orphan (a `compact/start` with no `compact/end`), records provenance, and prevents a concurrent compaction. Two failure paths: a **crash** (the loop dies mid-summarization) leaves a dangling `compact/start` that is inert — `compact/*` events are log-only, the surface replacement never landed, so the full history derives fine and generic turn-repair closes the turn; a **recoverable** failure (summarization throws but the loop survives) appends `compact/end` with its `error` field set, leaving the surface untouched so the call proceeds with full history. Core session repair stays compaction-agnostic by design — it never learns about `compact/*`. -`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. +The protected `estimateContentTokens()` and `summarize()` methods are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the private retention/pressure accounting and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. ## Config (`BasicCompactConfig`) diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 0b0300472c..27e81cd3d9 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -41,12 +41,11 @@ import type { BasicCompactConfig, ResolvedConfig } from './types.ts' import { resolveConfig } from './types.ts' export type { BasicCompactConfig, ResolvedConfig } from './types.ts' -export { resolveConfig } from './types.ts' /** Per-block structural overhead for JSON framing / type tag. */ const BLOCK_OVERHEAD = 4 -/** Role-field framing overhead added per message in {@link BasicCompactService.estimateTokens}. */ +/** Role-field framing overhead added per message in the request estimator. */ const ROLE_OVERHEAD = 4 /** Tags wrapping the structured summary inside the landed checkpoint node. */ @@ -222,7 +221,7 @@ export class BasicCompactService extends CompactService { * their JSON-stringified length. * @returns the estimated token count. */ - estimateContentTokens(blocks: readonly ContentBlock[]): number { + protected estimateContentTokens(blocks: readonly ContentBlock[]): number { const { charsPerToken } = this.config let tokens = 0 for (const block of blocks) { @@ -257,7 +256,8 @@ export class BasicCompactService extends CompactService { * @returns the estimated token count of the event's content, or 0 for a * non-message event. */ - estimateEventTokens(event: SessionEvent): number { + private estimateEventTokens(event: SessionEvent): number { + /* v8 ignore next -- callers traverse surface nodes, whose event types are the five cases below */ switch (event.type) { case 'user/message': case 'assistant/message': @@ -278,7 +278,7 @@ export class BasicCompactService extends CompactService { * @param systemPrompt - counted at chars / `charsPerToken` when provided. * @returns the estimated token footprint of the whole request. */ - estimateTokens(messages: readonly Message[], systemPrompt?: string): number { + private estimateTokens(messages: readonly Message[], systemPrompt?: string): number { let total = 0 for (const msg of messages) { total += this.estimateContentTokens(msg.content) @@ -318,7 +318,7 @@ export class BasicCompactService extends CompactService { * @returns the text-only summary blocks plus the call envelope used * (`model`, and `maxTokens` when the summarizer has a cap). */ - async summarize( + protected async summarize( text: string, agent: Agent, signal?: AbortSignal, ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { const assembler = new BlockAssembler() @@ -417,7 +417,7 @@ export class BasicCompactService extends CompactService { break } - result = await this.compactRegion(session, range.start, range.end, agent, signal) + result = await this.compactRegion(range.start, range.end, agent, signal) } const totalTokens = this.estimatePressure(session, fullSystemPrompt, sessionPrefix) @@ -439,17 +439,17 @@ export class BasicCompactService extends CompactService { * @param sessionPrefix - the instance's composed session prefix (counts toward pressure). * @returns the estimated token total the next request will carry. */ - estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number { + private estimatePressure(session: Session, fullSystemPrompt: string, sessionPrefix: readonly Message[]): number { return this.estimateTokens([...sessionPrefix, ...session.deriveMessages()], fullSystemPrompt) } override async compactRegion( - session: Session, start: number, end: number, agent: Agent, signal?: AbortSignal, ): Promise { + const session = agent.session // Resolve the range by surface POSITION, not numeric seq interval. A prior // replace lands a fresh high-seq summary node AT the shadowed range's // position, so the surface order (head→tail) no longer tracks seq order — @@ -556,13 +556,9 @@ export class BasicCompactService extends CompactService { // compact/start and here leaves a detectable orphaned lock (a compact/start // with no matching compact/end) rather than a compact/end that falsely // claims compaction finished before the surface replacement landed. - const endEvent = session.append('compact/end', { turn: openTurn }) + session.append('compact/end', { turn: openTurn }) return { - startSeq: startEvent.seq, - summarySeq: summaryEvent.seq, - endSeq: endEvent.seq, - summary, shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 1a30cc9fc9..46bcb9911c 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -5,7 +5,7 @@ import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter, LlmService } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' -import type { SessionEvent, SurfaceEvent } from '@deepseek-ai/dsh-session' +import type { SurfaceEvent } from '@deepseek-ai/dsh-session' import * as Invariants from '@deepseek-ai/dsh-invariants' import type { Agent } from '@deepseek-ai/dsh-agent' @@ -68,6 +68,20 @@ class TestCompactService extends BasicCompactService { } } +/** Expose the backend's protected extension hooks for their focused contract tests. */ +class InspectableCompactService extends BasicCompactService { + estimateContent(blocks: readonly ContentBlock[]): number { + return this.estimateContentTokens(blocks) + } + + summarizeForTest( + text: string, + agent: Agent, + ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + return this.summarize(text, agent) + } +} + function isFramedCheckpoint(blocks: readonly ContentBlock[]): boolean { const first = blocks[0] const last = blocks[blocks.length - 1] @@ -333,51 +347,6 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai }) }) -describe('BasicCompactService.estimateEventTokens', () => { - it('returns 0 for non-message events (boundary, chunk, step/end, tool/call)', () => { - const svc = createTestService() - expect(svc.estimateEventTokens({ type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'assistant/chunk', seq: 2, time: 3, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'step/end', seq: 3, time: 4, data: { turn: 1, step: 1 } })).toBe(0) - expect(svc.estimateEventTokens({ type: 'tool/call', seq: 4, time: 5, data: { turn: 1, step: 1, callId: CallId('c1'), name: 'read', arguments: '{}' } })).toBe(0) - }) - - it('returns estimate for message-producing events', () => { - const svc = createTestService() - const userEvent: SessionEvent = { type: 'user/message', seq: 0, time: 1, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } } } - expect(svc.estimateEventTokens(userEvent)).toBe(10) - - const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }] } } - expect(svc.estimateEventTokens(asstEvent)).toBe(20) - - const toolEvent: SessionEvent = { type: 'tool/result', seq: 2, time: 3, data: { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'output' }], isError: false } } - expect(svc.estimateEventTokens(toolEvent)).toBe(10) - }) -}) - -describe('BasicCompactService.estimateTokens', () => { - it('sums token estimates across messages', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hello' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'hi' }, { type: 'text', text: 'there' }] }, - ] - // 1 block * 10 + 4 (role) + 2 blocks * 10 + 4 (role) = 10 + 4 + 20 + 4 = 38 - expect(svc.estimateTokens(messages)).toBe(38) - }) - - it('includes system prompt in the estimate', () => { - const svc = createTestService() - const messages: Message[] = [ - { role: 'user', content: [{ type: 'text', text: 'hi' }] }, - ] - const systemPrompt = 'You are a helpful assistant.' - // 1 block * 10 + 4 (role) + ceil(28/4) = 10 + 4 + 7 = 21 - expect(svc.estimateTokens(messages, systemPrompt)).toBe(21) - }) -}) - describe('BasicCompactService.compactRegion', () => { it('shadows surface nodes and inserts a summary via user/message', async () => { const svc = createTestService() @@ -393,7 +362,7 @@ describe('BasicCompactService.compactRegion', () => { expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) expect(result.shadowedRange.start).toBe(firstSeq) expect(result.shadowedRange.end).toBe(secondSeq) - expect(result.summary).toEqual(svc.mockSummary) + expect(result.shadowedTokenCount).toBe(20) const events = session.events const startEvent = events.findLast(e => e.type === 'compact/start') @@ -405,6 +374,7 @@ describe('BasicCompactService.compactRegion', () => { // The provenance record carries the summarize call's envelope, so "which // model wrote this summary" is answerable from the log alone. expect(summaryEvent?.type === 'compact/summary' && summaryEvent.data.model).toBe('test-model') + expect(summaryEvent?.type === 'compact/summary' && summaryEvent.data.summary).toEqual(svc.mockSummary) // compact/* events are log-only — no surfaceOp (type system enforces this). const startRaw = startEvent as unknown as { surfaceOp?: unknown } @@ -509,10 +479,9 @@ describe('BasicCompactService.compactRegion', () => { const session = multiTurnSession(3, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'm') // Provenance (compact/summary) carries the RAW, unframed summary. - expect(result.summary).toEqual([{ type: 'text', text: 'STRUCTURED SUMMARY' }]) const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! expect(summaryEvent.data).toMatchObject({ summary: [{ type: 'text', text: 'STRUCTURED SUMMARY' }] }) @@ -590,7 +559,6 @@ describe('BasicCompactService.compactIfNeeded', () => { expect(result).not.toBeNull() expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(1) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(70) }) it('walks tail→head and retains nodes within token budget', async () => { @@ -716,7 +684,6 @@ describe('BasicCompactService.compactIfNeeded', () => { expect(result).not.toBeNull() expect(svc.summarizeCalls).toHaveLength(2) expect(session.events.filter(e => e.type === 'compact/summary')).toHaveLength(2) - expect(svc.estimateTokens(session.deriveMessages(), '')).toBeLessThan(50) }) it('throws after the configured re-compaction attempts still leave the surface above threshold', async () => { @@ -801,53 +768,51 @@ describe('BasicCompactService blocking (compaction in progress)', () => { describe('BasicCompactService token estimation (char/4 heuristic)', () => { it('estimates text blocks with char/4 + overhead', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'this is a somewhat longer text block' = 36 → ceil(36/4)+4 = 13; 'short' = 5 → 2+4 = 6 const blocks: ContentBlock[] = [ { type: 'text', text: 'this is a somewhat longer text block' }, { type: 'text', text: 'short' }, ] - expect(svc.estimateContentTokens(blocks)).toBe(19) + expect(svc.estimateContent(blocks)).toBe(19) }) it('estimates reasoning blocks same as text', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'thinking about this...' = 22 → ceil(22/4)+4 = 10 - expect(svc.estimateContentTokens([{ type: 'reasoning', text: 'thinking about this...' }])).toBe(10) + expect(svc.estimateContent([{ type: 'reasoning', text: 'thinking about this...' }])).toBe(10) }) it('estimates tool-call blocks from name + arguments', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // 'bash' = 4 → 1; '{"command":"ls"}' = 16 → 4; + 4 overhead = 9 - expect(svc.estimateContentTokens([ + expect(svc.estimateContent([ { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{"command":"ls"}' }, ])).toBe(9) }) it('estimates tool-result blocks recursively', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // inner text 5 → 2+4 = 6; outer 6 + 4 overhead = 10 - expect(svc.estimateContentTokens([ + expect(svc.estimateContent([ { type: 'tool-result', toolCallId: CallId('c1'), content: [{ type: 'text', text: 'hello' }], isError: false }, ])).toBe(10) }) it('returns 0 for empty content blocks', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) - expect(svc.estimateContentTokens([])).toBe(0) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) + expect(svc.estimateContent([])).toBe(0) }) it('honors a configured charsPerToken (fractional densities included)', () => { // 'this is a somewhat longer text block' = 36 chars. const blocks: ContentBlock[] = [{ type: 'text', text: 'this is a somewhat longer text block' }] // charsPerToken 2: ceil(36/2)+4 = 22 — a CJK-density config doubles the estimate. - const dense = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 2 })) - expect(dense.estimateContentTokens(blocks)).toBe(22) + const dense = new InspectableCompactService(new Context(), cfg({ auto: false, charsPerToken: 2 })) + expect(dense.estimateContent(blocks)).toBe(22) // Fractional density is legal: ceil(36/1.5)+4 = 28. - const fractional = new BasicCompactService(new Context(), cfg({ auto: false, charsPerToken: 1.5 })) - expect(fractional.estimateContentTokens(blocks)).toBe(28) - // The system-prompt term scales with the same knob: 36-char prompt at density 2 → ceil(36/2) = 18. - expect(dense.estimateTokens([], 'this is a somewhat longer text block')).toBe(18) + const fractional = new InspectableCompactService(new Context(), cfg({ auto: false, charsPerToken: 1.5 })) + expect(fractional.estimateContent(blocks)).toBe(28) }) }) @@ -1013,17 +978,17 @@ function compactRegion( model: string, signal?: AbortSignal, ) { - return svc.compactRegion(session, start, end, stubAgent(session, model), signal) + return svc.compactRegion(start, end, stubAgent(session, model), signal) } -function summarize(svc: BasicCompactService, text: string, model: string) { - return svc.summarize(text, stubAgent(new Session(SessionId('summary')), model)) +function summarize(svc: InspectableCompactService, text: string, model: string) { + return svc.summarizeForTest(text, stubAgent(new Session(SessionId('summary')), model)) } describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('summarizes via the registered adapter and returns its content', async () => { const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ auto: false, maxTokens: 512 })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false, maxTokens: 512 })) const { summary, model, maxTokens } = await summarize(svc, 'User: hi\n\nAssistant: hello', 'test-model') expect(summary).toEqual([{ type: 'text', text: 'SUMMARY TEXT' }]) @@ -1041,7 +1006,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('uses maxTokens as the summarization provider cap', async () => { const { ctx, adapter } = await ctxWithModel('SUMMARY TEXT') - const svc = new BasicCompactService(ctx, cfg({ + const svc = new InspectableCompactService(ctx, cfg({ auto: false, maxTokens: 50, })) @@ -1059,7 +1024,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { // synthesized user/message summary as an orphaned call. { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }, ]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) const { summary } = await summarize(svc, 'User: hi', 'test-model') @@ -1068,26 +1033,26 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('throws when no text block remains after filtering', async () => { const { ctx } = await ctxWithBlocks([{ type: 'reasoning', text: 'private only' }]) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'User: hi', 'test-model')).rejects.toThrow(/no text summary content/) }) it('throws when no model is provided', async () => { const { ctx } = await ctxWithModel('x') - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', '')).rejects.toThrow(/no model available/) }) it('rethrows when the stream ends with a finish-error chunk', async () => { const ctx = await ctxWithFinish({ kind: 'error', message: 'provider 401', code: 'UNAUTHORIZED' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'provider 401', code: 'UNAUTHORIZED' }) }) it('rethrows a finish-error chunk without a code (code stays undefined)', async () => { const ctx = await ctxWithFinish({ kind: 'error', message: 'opaque failure' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) const error = await summarize(svc, 'text', 'test-model').then(() => null, (e: unknown) => e as Error & { code?: string }) expect(error?.message).toBe('opaque failure') expect(error?.code).toBeUndefined() @@ -1095,13 +1060,13 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('rethrows when the stream ends with a finish-aborted chunk', async () => { const ctx = await ctxWithFinish({ kind: 'aborted' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ message: 'summarization stream aborted', code: 'ABORTED' }) }) it('fails closed on a max-tokens finish (an incomplete checkpoint must not commit)', async () => { const ctx = await ctxWithFinish({ kind: 'max-tokens' }) - const svc = new BasicCompactService(ctx, cfg({ auto: false })) + const svc = new InspectableCompactService(ctx, cfg({ auto: false })) await expect(summarize(svc, 'text', 'test-model')).rejects.toMatchObject({ code: 'MAX_TOKENS' }) }) @@ -1129,8 +1094,9 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! + expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // The raw summary is wrapped in the checkpoint framing on the surface. expect(session.deriveMessages()[0]!.content).toContainEqual({ type: 'text', text: 'CONDENSED' }) }) @@ -1392,10 +1358,10 @@ describe('BasicCompactService edge cases', () => { }) it('estimates unknown block types via JSON length (default branch)', () => { - const svc = new BasicCompactService(new Context(), cfg({ auto: false })) + const svc = new InspectableCompactService(new Context(), cfg({ auto: false })) // A block whose type is none of the known kinds — exercises the default arm. const unknown = { type: 'custom-widget', payload: 'some data' } as unknown as ContentBlock - expect(svc.estimateContentTokens([unknown])).toBeGreaterThan(0) + expect(svc.estimateContent([unknown])).toBeGreaterThan(0) }) it('auto-compaction reports bounded retry exhaustion after committing a smaller summary', async () => { @@ -1604,14 +1570,15 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a // First compaction: shadow the two oldest surface nodes. const nodes0 = session.surface.nodes - const first = await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') + await compactRegion(svc, session, nodes0[0]!, nodes0[1]!, 'm') + const firstSummarySeq = session.events.findLast(e => e.type === 'compact/summary')!.seq // The summary node now sits at the head with a seq HIGHER than the // retained older nodes that follow it — the non-monotonic surface. (The // head is the user/message replace node, appended after the compact/summary - // provenance event, so its seq is at least first.summarySeq.) + // provenance event. const nodes1 = session.surface.nodes - expect(nodes1[0]!).toBeGreaterThanOrEqual(first.summarySeq) + expect(nodes1[0]!).toBeGreaterThan(firstSummarySeq) expect(nodes1[0]!).toBeGreaterThan(nodes1[1]!) // Second compaction: shadow [summary(head) … turn-2's step end]. The start @@ -1623,13 +1590,14 @@ describe('BasicCompactService positional range (surface seqs are not monotonic a const endSeq = nodes1[2]! expect(startSeq).toBeGreaterThan(endSeq) const second = await compactRegion(svc, session, startSeq, endSeq, 'm') + const secondSummarySeq = session.events.findLast(e => e.type === 'compact/summary')!.seq // Exactly the three nodes at surface positions [0..2] are shadowed, in // surface order — the positional slice, regardless of their seq values. expect(second.shadowedSeqs).toEqual([nodes1[0]!, nodes1[1]!, nodes1[2]!]) // The surface still derives cleanly: a new head replace node + the rest. const finalNodes = session.surface.nodes - expect(finalNodes[0]!).toBeGreaterThanOrEqual(second.summarySeq) + expect(finalNodes[0]!).toBeGreaterThan(secondSummarySeq) expect(session.deriveMessages().length).toBe(finalNodes.length) }) @@ -1679,8 +1647,9 @@ describe('BasicCompactService llm inject (real plugin-load path)', () => { const svc = ctx.compact as BasicCompactService const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') - expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) + await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! + expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // Tear the fiber down so this test owns no leaked registration; the // dedicated cleanup assertion lives in the "HMR safety" suite. diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index e98f00899f..fafcad76b8 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -19,7 +19,7 @@ Both methods are **abstract** — the backend owns the entire strategy (token es | Member | Semantics | |---|---| | `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | -| `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | +| `compactRegion(start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) from `agent.session` into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 7d1138314c..1eb73c60db 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -14,7 +14,8 @@ * implementation (deferred) / consumer (a `/compact` tool, deferred) — modeled * on the bash trio. Unlike `dsh-bash`, this interface necessarily * depends on `dsh-session` and `dsh-llm`: the contract's verbs are defined over - * a `Session` and its output is the `ContentBlock` vocabulary. That deviation + * an agent-owned `Session` and the durable summary event uses the + * `ContentBlock` vocabulary. That deviation * from the "interface depends only on cordis" guidance is intentional and * recorded in the [compaction capability-seam RFC](../../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). * @@ -132,10 +133,10 @@ export abstract class CompactService extends Service { * open (unclosed) tail step is invalid — its tool-calls have no results yet. * `dsh-session` exports `isToolPairingBalanced` for this check. * - * @param session - the session whose surface is mutated. * @param start - inclusive seq of the first surface node to compact. * @param end - inclusive seq of the last surface node to compact. - * @param agent - agent context used by router-aware summarizers. + * @param agent - agent context whose session is mutated and whose routing + * options are used by summarizers. * @param signal - optional cancellation signal. A backend that summarizes via * `ctx.llm.stream()` MUST forward this into the call's `GenerateOptions.signal` * so an abort/dispose tears down the in-flight summarization rather than @@ -146,10 +147,10 @@ export abstract class CompactService extends Service { * prior replace can leave the surface non-monotonic in seq order), or if * either boundary is not a balanced tool-pairing cut (would split a step's * tool-call/result pair). - * @returns what the compaction did (the replaced range and its summary node). + * @returns the replaced range and its token accounting. The durable + * `compact/summary` event owns the summary and bookkeeping-event identity. */ abstract compactRegion( - session: Session, start: number, end: number, agent: CompactAgentContext, diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index ba9834910f..78e94173a3 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -49,14 +49,6 @@ declare module '@deepseek-ai/dsh-session' { /** Result of a successful compaction operation. */ export interface CompactionResult { - /** The seq of the appended `compact/start` event. */ - startSeq: number - /** The seq of the appended `compact/summary` event. */ - summarySeq: number - /** The seq of the appended `compact/end` event. */ - endSeq: number - /** The summary content blocks produced by the backend. */ - summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index c4daa8cc5a..e34c8420d9 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -27,28 +27,24 @@ class StubCompactService extends CompactService { } override async compactRegion( - session: Session, start: number, end: number, - _agent: CompactAgentContext, + agent: CompactAgentContext, signal?: AbortSignal, ): Promise { this.lastSignal = signal + const session = agent.session // Minimal stub honoring the lock + log-only event contract. - const startEvent = session.append('compact/start', { turn: 0 }) - const summaryEvent = session.append('compact/summary', { + session.append('compact/start', { turn: 0 }) + session.append('compact/summary', { summary: [{ type: 'text', text: 'stub' }], shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, model: 'stub', }) - const endEvent = session.append('compact/end', { turn: 0 }) + session.append('compact/end', { turn: 0 }) return { - startSeq: startEvent.seq, - summarySeq: summaryEvent.seq, - endSeq: endEvent.seq, - summary: [{ type: 'text', text: 'stub' }], shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, @@ -88,7 +84,7 @@ describe('CompactService seam', () => { const svc = new StubCompactService(ctx) const session = new Session(SessionId('s')) - const result = await svc.compactRegion(session, 0, 0, stubAgent(session, 'm')) + const result = await svc.compactRegion(0, 0, stubAgent(session, 'm')) const startEvent = session.events.find(e => e.type === 'compact/start') expect(startEvent).toBeDefined() @@ -96,8 +92,9 @@ describe('CompactService seam', () => { // verify the runtime value is absent. const raw = startEvent as unknown as { surfaceOp?: unknown } expect(raw.surfaceOp).toBeUndefined() - expect(result.summarySeq).toBeGreaterThan(result.startSeq) - expect(result.endSeq).toBeGreaterThan(result.summarySeq) + expect(result.shadowedRange).toEqual({ start: 0, end: 0 }) + expect(session.events.filter(e => e.type.startsWith('compact/')).map(e => e.type)) + .toEqual(['compact/start', 'compact/summary', 'compact/end']) }) it('threads the cancellation signal through to the backend', async () => { @@ -106,7 +103,7 @@ describe('CompactService seam', () => { const session = new Session(SessionId('s')) const controller = new AbortController() - await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), controller.signal) + await svc.compactRegion(0, 0, stubAgent(session, 'm'), controller.signal) expect(svc.lastSignal).toBe(controller.signal) await svc.compactIfNeeded(stubAgent(session), '', [], controller.signal) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index b4420e80c7..3d6ade301f 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -109,7 +109,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ summary: 'Abstract compaction service.', methods: [ 'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise', - 'abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', + 'abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', ], }, { @@ -624,7 +624,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CompactionResult', - declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', + declaration: 'export interface CompactionResult {\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, { name: 'ConfinedArgv', From 7a33ee94be9f4338369f388c5efe3deb4965b50d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:29:16 +0800 Subject: [PATCH 012/323] refactor: remove agent entry mirror --- packages/core/agent/src/index.ts | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 7864f5938c..edb7f59a37 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -202,9 +202,6 @@ interface FactorySlot { */ export class AgentRegistry extends Service { private store = new Map() - // TODO(agent-entry-mirror): derive exact-object checks from store.get(agent.id) - // plus entry.agent identity; this WeakMap mirrors the authoritative id map. - private entries = new WeakMap() private factory: FactorySlot | undefined constructor(ctx: Context) { @@ -334,7 +331,7 @@ export class AgentRegistry extends Service { const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume // operations may both prepare, but only one exact entry can publish. - if (this.entries.has(agent) || this.store.has(id)) throw new Error(`agent "${id}" is already registered`) + if (this.store.has(id)) throw new Error(`agent "${id}" is already registered`) const entry: AgentEntry = { id, agent, @@ -344,7 +341,6 @@ export class AgentRegistry extends Service { detachRequested: false, } this.store.set(id, entry) - this.entries.set(agent, entry) let entered = true const detach = (): void => { if (!entered) return @@ -371,7 +367,6 @@ export class AgentRegistry extends Service { /* v8 ignore next -- enter() rejects replacement while this single-shot detach capability is live. */ if (this.store.get(entry.id) !== entry) return this.store.delete(entry.id) - this.entries.delete(entry.agent) // An insertion rolled back before announce was never externally created, // so emitting disposed would invent an impossible lifecycle edge. Marking // happens before the created emit: if a later created listener throws, @@ -403,8 +398,8 @@ export class AgentRegistry extends Service { * creation listener). */ announce(agent: Agent): void { - const entry = this.entries.get(agent) - if (entry === undefined || this.store.get(entry.id) !== entry) { + const entry = this.store.get(agent.id) + if (entry === undefined || entry.agent !== agent) { throw new Error(`agent "${agent.id}" is not live in this registry`) } if (entry.announced || entry.announcing) { From 709cc7200eb2b3ac64090c67833a25a367a1b3df Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 01:59:21 +0800 Subject: [PATCH 013/323] refactor: unify agent and session identity --- docs/config-catalog.md | 18 +- docs/cookbook/extension-cookbook.md | 4 +- docs/cordis-catalog/events.md | 34 +-- docs/cordis-catalog/services.md | 12 +- docs/core-data-structures/approval.md | 2 +- docs/core-data-structures/bash.md | 2 +- docs/core-data-structures/core.md | 8 +- docs/core-data-structures/subagent.md | 2 +- docs/event-producer-consumer.md | 34 +-- .../2026-06-11-content-block-vocabulary.md | 2 +- .../2026-06-14-session-persistence.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 10 +- .../2026-06-30-event-domain-semantics.md | 2 +- .../2026-07-08-agent-scope-contexts.md | 3 +- .../feature/2026-07-08-repeat-tool-guard.md | 5 +- ...-20-remove-agent-boundary-mirror-events.md | 8 +- ...claude-code-and-codex-subagent-backends.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 6 +- examples/coding-agent/tests/code-mode.e2e.ts | 7 +- .../coding-agent/tests/coding-task.e2e.ts | 4 +- examples/coding-agent/tests/compaction.e2e.ts | 4 +- examples/coding-agent/tests/full-loop.e2e.ts | 4 +- examples/coding-agent/tests/resume.e2e.ts | 3 - examples/coding-agent/tests/todo-write.e2e.ts | 4 +- .../cordis-agent/tests/cordis-tools.e2e.ts | 8 +- .../bash/tool-bash/tests/integration.spec.ts | 11 +- packages/bash/tool-bash/tests/tools.spec.ts | 2 +- .../tests/compact-loop-repro.spec.ts | 7 +- .../cordis/tool-cordis/src/api-catalog.ts | 16 +- .../tool-cordis/tests/integration.spec.ts | 7 +- packages/core/agent-core/README.md | 2 +- .../core/agent-core/tests/agent-core.spec.ts | 12 +- packages/core/agent-loop/README.md | 10 +- packages/core/agent-loop/src/agent.ts | 8 +- packages/core/agent-loop/src/index.ts | 29 ++- packages/core/agent-loop/tests/agent.spec.ts | 53 +++-- packages/core/agent-loop/tests/cancel.spec.ts | 35 ++-- .../tests/config-session-id.spec.ts | 29 +-- .../agent-loop/tests/coverage-edges.spec.ts | 21 +- .../agent-loop/tests/interception.spec.ts | 62 +++--- packages/core/agent-loop/tests/loop.spec.ts | 85 ++++---- .../core/agent-loop/tests/properties.spec.ts | 11 +- .../agent-loop/tests/request-cache.e2e.ts | 7 +- .../tests/request-reconstruction.spec.ts | 22 +- packages/core/agent-loop/tests/resume.spec.ts | 85 ++++---- .../agent-loop/tests/review-fixes.spec.ts | 83 ++++---- .../agent-loop/tests/scope-lifecycle.spec.ts | 193 ++++++++---------- .../core/agent-loop/tests/tool-order.spec.ts | 9 +- .../core/agent-loop/tests/turn-stop.spec.ts | 19 +- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 28 ++- packages/core/agent/src/types.ts | 20 +- packages/core/agent/tests/agent.spec.ts | 29 +-- packages/core/session/src/index.ts | 7 +- packages/core/tools/tests/code-mode.spec.ts | 3 +- packages/core/tools/tests/scoped.spec.ts | 14 +- packages/fs/tool-fs/tests/fs-tools.e2e.ts | 4 +- packages/guard/repeat-tool-guard/README.md | 4 +- packages/guard/repeat-tool-guard/src/index.ts | 19 +- .../tests/repeat-tool-guard.spec.ts | 39 ++-- .../hooks/hooks-claude/tests/bridge.spec.ts | 31 +-- .../hooks/hooks-claude/tests/coverage.spec.ts | 73 +++---- .../hooks/hooks-codex/tests/bridge.spec.ts | 17 +- .../hooks/hooks-codex/tests/coverage.spec.ts | 73 +++---- packages/subagent/subagent-acp/src/run.ts | 4 +- .../tests/multi-subagent.spec.ts | 7 +- .../subagent-fork/tests/subagent-fork.spec.ts | 7 +- .../subagent/subagent-inprocess/src/index.ts | 7 +- .../tests/structured.spec.ts | 9 +- .../tests/subagent-inprocess.spec.ts | 7 +- .../subagent-spawn/tests/spawn.e2e.ts | 4 +- .../tests/subagent-spawn.spec.ts | 13 +- packages/subagent/subagent/src/index.ts | 7 +- packages/subagent/subagent/src/types.ts | 5 +- .../subagent/subagent/tests/service.spec.ts | 12 +- .../tool-subagent/tests/tool-subagent.spec.ts | 24 ++- packages/support/subagent-mock/src/index.ts | 4 +- .../subagent-mock/tests/subagent-mock.spec.ts | 6 +- .../todo/tool-todo/tests/integration.spec.ts | 9 +- .../todo/tool-todo/tests/tool-todo.spec.ts | 5 +- packages/ui/acp/src/index.ts | 3 - packages/ui/acp/tests/approval.spec.ts | 6 +- packages/ui/acp/tests/bridge.spec.ts | 24 +-- packages/ui/acp/tests/dispose.spec.ts | 43 ++-- packages/ui/acp/tests/edges.spec.ts | 3 +- packages/ui/acp/tests/load.spec.ts | 9 +- packages/ui/acp/tests/multi-session.spec.ts | 6 +- packages/ui/acp/tests/turns.spec.ts | 6 +- packages/ui/jsonrpc/src/server.ts | 2 - packages/ui/jsonrpc/tests/server.spec.ts | 27 +-- packages/ui/stdio-agent/README.md | 8 +- packages/ui/stdio-agent/src/index.ts | 23 +-- packages/ui/stdio-agent/src/stdio-chat.ts | 40 ++-- .../ui/stdio-agent/tests/readline.spec.ts | 2 +- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 16 +- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 60 +++--- packages/util/brand/README.md | 4 +- packages/util/brand/src/index.ts | 8 +- .../tool-workflow/tests/tool-workflow.spec.ts | 6 +- .../workflow-workerthread/src/runtime.ts | 4 +- .../tests/integration.spec.ts | 9 +- .../tests/source-worker.compat.spec.ts | 4 +- .../tests/workflow-workerthread.e2e.ts | 8 +- .../tests/workflow-workerthread.spec.ts | 20 +- packages/workflow/workflow/src/types.ts | 5 +- 105 files changed, 899 insertions(+), 948 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..94d613bc4e 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` @@ -117,8 +117,8 @@ Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -127,9 +127,9 @@ export interface Config { } ``` -Depends on: [`AgentId`](../packages/core/agent/src/index.ts) · [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) +Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:325`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -611,7 +611,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l ```ts config-catalog /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -620,7 +620,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -635,7 +635,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -645,7 +645,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index e2677e463a..1db5e85828 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -36,7 +36,7 @@ A UI plugin renders from the `session/event` feed (the assistant token stream as ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -50,7 +50,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 5a3398f9a8..a5e018079a 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:304`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:593`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:426`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:444`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:348`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:473`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:525`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:369`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:540`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:558`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -317,7 +317,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:90`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:91`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -327,7 +327,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` -Source: [`packages/subagent/subagent/src/index.ts:66`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:67`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -337,7 +337,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:72`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:73`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -347,7 +347,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:82`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index bfb31749d5..4d162a55f5 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -14,12 +14,12 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary Concrete ReactLoopAgent factory and driver service. ```ts cordis-catalog -create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:338`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` @@ -32,13 +32,13 @@ async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void enter(agent: Agent): () => void announce(agent: Agent): void -get(id: AgentId): Agent | undefined +get(id: SessionId): Agent | undefined list(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:203`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` @@ -218,7 +218,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:592`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:597`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` @@ -244,7 +244,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:123`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:124`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/approval.md b/docs/core-data-structures/approval.md index c5fa1fe13b..e8820ccfeb 100644 --- a/docs/core-data-structures/approval.md +++ b/docs/core-data-structures/approval.md @@ -6,7 +6,7 @@ Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approv ## Identity and outcome -Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call, session, or agent ids. +Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call or agent/session ids. ```ts type-equiv type ApprovalRequestId = Branded<'ApprovalRequestId'> diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index 51f7cb0696..df6c5ab16b 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -110,7 +110,7 @@ The `owner` token is the isolation key: the executor stores it but never interpr `stdin` and `env` are set by in-process plugins (the hooks bridges, native plugins) to feed a hook command its JSON payload on stdin and its `CLAUDE_PROJECT_DIR`/`CLAUDE_PLUGIN_ROOT` env. The model-facing `dsh-tool-bash` tool does not expose them as parameters — its request is built from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only — because a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), so duplicating them as tool params would be redundant. This is NOT a security boundary: the credential scrub in `dsh-bash-local` is what stops the harness's ambient secrets reaching a spawned command, and it works regardless of these fields (a model cannot read a value the scrub removed, and tool-call args are static JSON, never shell-evaluated). A guard test asserts the tool doesn't forward model `env`/`stdin` — to catch a future `...args` spread, not to defend a trust wall. `env` is merged AFTER the scrub so an explicit caller entry (a value it already holds) wins even on a credential-shaped name. See [the bash-stdin-env RFC](../rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). -Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`/`AgentId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. +Both ids the seam handles are [branded](core.md) (zero-cost `string` brands, the same machinery as `SessionId`): `BashTaskId` (a tracked background task, generated `bash-N` by the local executor) and `OwnerToken` (the opaque isolation key). `OwnerToken` is deliberately a DISTINCT brand from `SessionId`, not an alias: the bash seam is a capability seam that must not know what an owner token *means*, so it never imports `dsh-session`'s vocabulary — the `dsh-tool-bash` consumer is the single boundary that casts the owning agent's `SessionId` into an `OwnerToken`. Branding both stops a raw `string` (or a `BashTaskId` where an `OwnerToken` is expected, or vice versa) from slipping through the type checker on the model-facing `task_id` path. ## Foreground runs: `BashRunResult` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 168d727c8d..c6b74ed3c0 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -73,7 +73,7 @@ Two large discriminated unions are the ones consumers `switch` over most: **`Str ## Branded IDs -IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (an `AgentId` can't be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. +IDs that cross package boundaries are **branded** — structurally strings, but non-interchangeable at the type level (a `SessionId` cannot be passed where a `CallId` is expected). Construction goes through a per-type factory; comparison, logging, and JSON behave as ordinary strings. The `Branded` primitive lives in its own type-only package, [dsh-brand](../../packages/util/brand) (no runtime code, no harness-package dependency), so any package can brand the ids it owns without depending on an unrelated capability package (e.g. dsh-bash brands `BashTaskId`/`OwnerToken` via dsh-brand alone, never pulling in dsh-llm). @@ -83,7 +83,7 @@ Source: [`packages/util/brand/src/index.ts`](../../packages/util/brand/src/index type Branded = string & { readonly [BRAND]: B } ``` -The three core IDs: `CallId` (correlates a tool call with its result; dsh-llm), `SessionId` (dsh-session), `AgentId` (dsh-agent). Each is `Branded<'CallId'>` etc. plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). +The two core IDs are `CallId` (correlates a tool call with its result; dsh-llm) and `SessionId` (the shared live agent and durable session identity; dsh-session). Each is a `Branded<'…'>` plus a same-named factory function. Capability seams brand their own ids too — see `BashTaskId`/`OwnerToken` in [bash.md](bash.md). ## Content blocks and messages @@ -254,7 +254,7 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types ```ts type-equiv interface Agent { - readonly id: AgentId + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus @@ -353,7 +353,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. +`AgentStatus` is `'idle' | 'running' | 'disposed'`. `Agent.id` and `Agent.session.id` are the same branded `SessionId`. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. ## Interception decisions diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 5454f326b3..883c33020a 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -68,7 +68,7 @@ The handle the consumer holds after a provider has established a ready child. Th ```ts type-equiv interface SubagentRun { - readonly id: AgentId + readonly id: SessionId readonly result: Promise dispose(): Promise sendMessage?(content: ContentBlock[]): void diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index a7e2c8bb37..80389608cc 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:576`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | @@ -31,10 +31,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:100`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `skill/provider-added` | `emit` | [`packages/skill/skill/src/index.ts:131`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | | `skill/provider-removed` | `emit` | [`packages/skill/skill/src/index.ts:137`](../packages/skill/skill/src/index.ts) | [`skill`](../packages/skill/skill) (`emit`) | - | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:90`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:73`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md index 42efb34774..fb272c5df9 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md +++ b/docs/rfc/implemented/architecture/2026-06-11-content-block-vocabulary.md @@ -21,4 +21,4 @@ In-session context injection (`context/message`, `steering/message`) renders as - Reasoning has a home without provider contortions. Multimodal content deliberately has NO core block type: the core set is limited to blocks every shipping path honors, and a multimodal feature adds its block type through the merge-extensible map in the same coordinated change that maps it in the adapters, surfaces it in the UI bridges, and prices it in compaction — see [the drop-image RFC](../simplification/2026-07-04-drop-image-content-block.md). Block cache hints likewise have no core field: DeepSeek prompt caching is automatic, so no shipping adapter can transmit a hint; a caching feature adds a `cache` field together with the adapter that honors it — see [the producer-less-variants RFC](../simplification/2026-07-04-prune-producerless-vocabulary-variants.md). Assistant-prefix continuation (prefill) likewise has no request field: DeepSeek's chat-prefix completion is a Beta feature on a base URL neither shipping adapter targets, so a prefill feature adds `GenerateOptions.prefill` together with the adapter that honors it — see [the inert-request-knobs RFC](../simplification/2026-07-04-drop-inert-request-knobs.md). - Every adapter pays a translation cost; the first real adapters have since validated the streaming protocol, and new adapters should continue proving their provider-specific mapping in adapter-local tests. -- IDs that cross package boundaries are branded (`CallId`, `SessionId`, `AgentId`) — nominal typing at zero runtime cost. +- IDs that cross package boundaries are branded (`CallId`, the shared agent/session `SessionId`) — nominal typing at zero runtime cost. diff --git a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md index 03d8a30b37..824e59a172 100644 --- a/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md +++ b/docs/rfc/implemented/architecture/2026-06-14-session-persistence.md @@ -23,7 +23,7 @@ Key choices recorded here because they are durable, contested, and surprising: - **Append-only; a crashed turn is closed, never truncated.** Committed events — those at or below a flushed `turn/end` — are never rewritten. The loop only flushes at `turn/end`, so a crash can leave a durable log whose final turn never closed: real, fully-written events sit after the last `turn/end`. **A single turn can be huge in a long-horizon task** (many steps, large tool output spanning a long autonomous run), so discarding the interrupted turn would silently destroy a large amount of real work — truncating a turn is wrong. Instead, on reload `load` PRESERVES those events and CLOSES the orphaned turn by durably appending the minimal synthetic boundary events: an error `tool/result` for every `tool-call` the crash left unanswered, then a `step/end` if a step was still open, then a `turn/end` carrying the merge-extensible `{ kind: 'interrupted' }` reason (a marker that records the turn was cut short by a crash, not completed by the model — no loop ever emits it). The synthetic tool results matter for resume correctness: the loop logs the `assistant/message` (carrying the `tool-call` blocks) BEFORE running the tools, so a crash mid-tool leaves calls without results; `deriveMessages()` would then replay a dangling assistant tool-call, which every provider rejects as an invalid transcript on the next request. Answering each orphaned call with an error result keeps the rehydrated history valid. `load` returns the balanced log, so a resumed session is immediately usable. The ONLY thing discarded is a never-fully-written **torn tail fragment** — a final record whose bytes (JSONL) or row were never completely flushed; that fragment is not a valid event and is dropped before the synthetic closers are written. A parse error or `seq` gap in the COMMITTED region (at or before the last real `turn/end`) is genuine corruption and makes the session unloadable. - **File backend canonical, DB backend a proven drop-in.** `SessionEvent` maps 1:1 onto a row `(session_id, seq, type, time, data)` — `append` is INSERT (in a transaction asserting the contiguous-seq contract), `load` is SELECT … ORDER BY seq. `dsh-session-persistence-sqlite` is exactly this: a `SessionPersistence` subclass with no interface change (opencode runs this exact shape on SQLite/WAL), and it passes the same `runPersistenceContract` suite as the JSONL backend — so the contract holds both backends to identical semantics (lazy materialization, interrupted-turn close on load, contiguous-seq), expressed once over file bytes and once over rows. - **Metadata is out-of-log.** Format version, cwd, and lineage are storage concerns, not replayable conversation state, so they live in a `SessionHeader` owned by `dsh-session` and attached to a `Session` via a new readonly `session.header` — never in `SessionEventMap`, never reaching `deriveMessages()`. The alternative (a merge-extensible `session/meta` event as log line 0) was rejected: an in-log event would ride along with a seeded/forked session for free, but metadata is not replayable state, so the explicit out-of-log header seam is the cleaner cost. (The header was originally split into an immutable `SessionHeader` plus a mutable `SessionSummary` whose union was `SessionMeta`; the mutable summary was later removed as dead state — see [Drop the mutable session summary](../simplification/2026-06-19-drop-mutable-session-summary.md).) -- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and starts a fresh agent on the resumed id (NOT `${agentId}-session`). The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. +- **`ctx.agents.create()` and `ctx.agents.resume()` are async factories; resume additionally crosses the persistence boundary.** `ctx.agents.resume({ resumeSessionId })` awaits `ctx.sessionPersistence.load`, recreates the live session with the loaded events (so `lastTurnNumber`/`deriveMessages` continue), and registers the fresh agent under the exact resumed id. The agent-loop does NOT hard-inject `sessionPersistence` (that would pend non-persistent demos forever); `resume` rejects with a clear error when it is absent. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 8171a05d30..5fe8224644 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -4,23 +4,23 @@ Status: implemented ## Problem -The harness already brands three identifiers — `CallId` (`packages/llm/llm/src/brand.ts`), `SessionId` (`packages/core/session/src/types.ts`), and `AgentId` (`packages/core/agent/src/types.ts`) — using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. +The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared agent/session `SessionId` (`packages/core/session/src/types.ts`) using the `Branded = string & { readonly [BRAND]: B }` machinery (owned by the type-only `@deepseek-ai/dsh-brand` package at `packages/util/brand/` — see its [README](../../../../packages/util/brand/README.md)) and a zero-cost cast factory per type. `dsh-brand` also states the governing policy: *"Branding is for ids that cross package boundaries and could plausibly be confused; not every string needs a brand."* That policy is right; the problem is that it is only half-applied. Two gaps let a structurally-identical-but-semantically-wrong string slip through the type checker today. **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". -**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId`/`SessionId`/`AgentId` decay back to bare `string` at exactly the places confusion is most likely: the registry/store `Map` key types and most public method params. Representative sites: `SessionStore.store = new Map()` and `create`/`prepare(id?: string)`/`get(id: string)` (`packages/core/session/src/index.ts`); `AgentRegistry.store = new Map()` and `register`/`get(id: string)` (`packages/core/agent/src/index.ts`); `ToolPresenter.pending = new Map()` keyed by call id and `call(callId: string)`/`result(callId: string)` (`packages/ui/acp/src/index.ts`); the ACP session-id surface beyond the store map — `SessionRecord.sessionId: string`, `bySession = new WeakMap()`, `loadingIds = new Set()`, `requireSession(sessionId: string)`, and the exported `streamSessionEventUpdate(sessionId: string, …)` (`packages/ui/acp/src/index.ts`); and the persistence coordinator's `Map` keyed by session id (`packages/session-persistence/session-persistence/src/coordinator.ts`). A brand that is dropped at the `Map` key buys nothing on lookups — the value of the existing brands is partly unrealized. +**Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. ## Decision A type-only change. Brands are zero-cost casts; nothing about runtime behavior, serialization, comparison, or the wire format changes. The work is in three parts, all honoring the existing "not every string" policy. -- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId`/`AgentId` already do. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). +- **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). - **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) -- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `get(id: SessionId)`, `Map`, `Map`, the ACP `SessionRecord.sessionId: SessionId` surface, the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on the struct fields. +- **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. Illustrative shape (the factory pattern is identical to the three existing brands): @@ -58,7 +58,7 @@ Kept deliberately narrow per the "not every string needs a brand" policy. Each o ## Verification -The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`AgentId`/`BashTaskId`) is keyed by bare `string` — `Map` keys, `WeakMap` value slots, `Set` membership (the ACP `bySession`/`loadingIds`), public method params, and exported signatures (`streamSessionEventUpdate`) all take the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. +The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` and threaded end-to-end (executor seam, the `dsh-bash-local` generation site, the `dsh-tool-bash` model-facing surface) with no `dsh-bash` dependency on `dsh-session`; no collection keyed by an in-scope branded id (`CallId`/`SessionId`/`BashTaskId`) is keyed by bare `string`; public method params and exported signatures keep the brand; and brands are constructed via the cast factory at each boundary where a raw string enters (provider call id, ACP session id, model-supplied `task_id`), never as scattered `as` casts. ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md index f0ab95ca80..f785851237 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md +++ b/docs/rfc/implemented/architecture/2026-06-30-event-domain-semantics.md @@ -24,7 +24,7 @@ This is the foundational change in a stack that adds a Hooks subsystem; it estab **The boundary rule:** a durable, replayable fact is a `SessionEvent`; a live interception or a transient/live-object signal is an `agent`/`tools` Cordis event. A turn or step boundary is a durable fact, so it lives in the session log and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` emit. -**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) was migrated to render boundaries from `session/event`, recovering the short agent label from an `agent/created`→id map. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). +**Applying the rule to the boundary twins:** all four boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are **REMOVED**. No production consumer needs the live `Agent` at a boundary: the ACP bridge settles from `session/event` `turn/end` plus `agent/status`, and the only turn-mirror consumer (`dsh-ui-stdio`, a disposable test REPL) renders boundaries from `session/event` while retaining its live target object for the fixed `main` label. The step mirrors were removed first (they had no consumer at all); the turn mirrors followed once ui-stdio was migrated — see [the remove-boundary-mirror-events RFC](../simplification/2026-06-20-remove-agent-boundary-mirror-events.md), which owns that decision. Removing the emits also simplifies the loop's `closeStep`/`closeTurn` (one append each, no paired emit). ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md index dcff4d3220..15477e023a 100644 --- a/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md +++ b/docs/rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md @@ -60,8 +60,7 @@ The ordinary contributor pattern is to register the complete local world during ```js const handle = await ctx.agents.create({ - agentId: AgentId('reviewer'), - sessionId: SessionId('reviewer-session'), + sessionId: SessionId('reviewer'), agentOptions: { model: 'model-name' }, setup(agentCtx) { agentCtx.systemPrompt.section({ diff --git a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md index 9d0446dcad..6961883318 100644 --- a/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md +++ b/docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md @@ -12,11 +12,10 @@ The harness already has every seam the pi extension uses, and better ones: [the The guard is a loop-hygiene plugin, not a model-facing tool: it never appears in the tool list, never vetoes or rewrites a call, and adds exactly one behavior — it watches each agent's stream of tool calls, counts runs of consecutive calls to the same tool with identical canonicalized arguments, and at configured run lengths injects an escalating advisory reminder telling the model to stop repeating itself, re-read the last result, and either change approach or conclude. The purpose is to break unproductive loops within a few wasted steps instead of letting them run to the turn's natural end — while leaving the decision (retry differently, gather more evidence, or finish) entirely with the model, so a legitimately repeated call is delayed by nothing and blocked by nothing. -The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers three listeners and holds all state in plugin-local maps keyed by `AgentId` — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish. +The plugin is `@deepseek-ai/dsh-repeat-tool-guard` at `packages/guard/repeat-tool-guard/`, opening the `guard/` group for loop-hygiene plugins (single-package groups have precedent: [the todo-write RFC](2026-06-29-todo-write-tool.md) shipped `todo/tool-todo`). It registers two listeners and holds state in a `WeakMap` keyed by the live `Agent` object — the tool registry is a context-level singleton whose waterfalls interleave every agent's calls (subagents run on the same context), so per-agent keying is correctness, not polish; weak object keys also make a disposal-only cleanup listener unnecessary. - **`tools/post-execute` (waterfall)** — the one detection point. The listener receives `(exec, result)` together, so counting and reminder delivery need no cross-event pending map (the pi extension needs one only because its `tool_call`/`tool_result` hooks are separate events). It always delegates via `next()` and, when a threshold is hit, folds a reminder onto the downstream decision's `additionalContext` — the observe-and-enrich posture [the hooks bridges](2026-06-30-hook-bridges.md) already use, honoring the waterfall contract. Counting happens here rather than in `tools/pre-execute` because post-execute also runs for denied calls (`ToolRegistry.execute` routes a deny through the same pipeline), and a model hammering a denied call is exactly the loop worth breaking. - **`agent/prompt-submit` (waterfall)** — pure reset hook: delegate via `next()`, clear the submitting agent's chain. A user interjection changes the context; repetition across it is not a loop. -- **`agent/status` (emit)** — on `disposed`, drop the agent's state, bounding the maps over harness lifetime. ### Detection semantics @@ -25,7 +24,7 @@ The chain key is `(tool name, canonical arguments)`; a call identical to the pre Two deliberate rules, both documented in [the package README](../../../../packages/guard/repeat-tool-guard/README.md) because they are behavior a reader would otherwise guess at: - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful — bookkeeping tools interleaved into a loop must not launder it — and it is the pi extension's (undocumented) semantics, kept on purpose and written down. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no `AgentId` to key on. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller (tests, non-loop consumers) has no model to remind and no live agent object to key on. ### Reminder delivery diff --git a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md index dbef22f3a3..f4b49281ea 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md +++ b/docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md @@ -21,9 +21,9 @@ This duplication is not free. Every lifecycle change had to update the session e Make `session/event` the single live boundary/transcript stream. Consumers that render turns, tool calls, tool results, assistant messages, and durable boundaries subscribe to `session/event` and derive their UI from the same event vocabulary persistence uses. -The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle (or its short id) at a boundary keeps a small map from session id to agent id built from `agent/created`/`agent/disposed`; `dsh-ui-stdio` does exactly this to label its `[ turn N]` header, since the `turn/start` session event carries only the turn number. The canonical record remains the event-sourced session log. +The four durable-boundary mirrors — `agent/turn-start`, `agent/turn-end`, `agent/step-start`, `agent/step-end` — are removed from the agent event taxonomy. A UI that wants the agent handle at a boundary retains the live target object from `agent/created`/`agent/disposed` and compares its session directly; `dsh-ui-stdio` uses this to label the app-owned agent's `[main turn N]` header while other sessions render their durable id. The canonical record remains the event-sourced session log. -The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it was migrated to `session/event` + the id map, and the turn mirrors were removed too. +The step mirrors (which had no consumer at all) were removed first, in [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md); that RFC KEPT the turn mirrors on the stated justification that the stdio UI needed the `Agent` handle at the turn boundary. This RFC finishes the job: `dsh-ui-stdio` is a disposable test REPL whose rendering can change freely, so "ui-stdio needs it" is not a reason to keep a mirror — it reads `session/event` and retains only its live target object. ## Scope: what is and isn't removed @@ -38,8 +38,8 @@ RETAINED — NOT durable-boundary mirrors, so out of scope for this decision: ## Alternatives considered - **Bundling `agent/steering` into the removal** — the original proposal's shape; narrowed out as scope creep: it mirrors the durable `steering/message` control record, not a boundary, and was removed by [its own later decision](2026-07-04-remove-agent-steering-mirror.md) (as was `agent/stream-chunk`, by [the stream-chunk-mirror RFC](2026-07-02-remove-stream-chunk-mirror.md)). -- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` + the id map instead. +- **Keeping the turn mirrors for the stdio UI** — [the event-domain-semantics RFC](../architecture/2026-06-30-event-domain-semantics.md)'s original stance; rejected here because `dsh-ui-stdio` is a disposable test REPL, not a load-bearing consumer, and it renders boundaries from `session/event` plus its live target object instead. ## Consequences -A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It must either subscribe to `session/event` or maintain a session-to-agent association. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. +A plugin can no longer observe turn/step boundaries from a convenient `Agent`-first event. It subscribes to `session/event` and, if it needs the live object, resolves the shared id through `ctx.agents` or retains the object it already owns. That is an acceptable trade: boundary consumers should not depend on a second event feed that can drift from the durable log. diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 3de3c7d9be..911d28cf1f 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -14,7 +14,7 @@ Two sibling provider packages, structural variants of the ACP backend, plus one - `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package. - `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`SENSITIVE_ENV_PATTERN`/`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. -Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = AgentId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. +Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. ## Verified interface facts (pinned versions) diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md index 1a69f9ebe6..6e3eea1515 100644 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,13 +16,13 @@ Session itself repeats the same fact as `Session.id` and `Session.header.id`. Co Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. -The config-driven path must first settle its currently hidden resume-or-create policy. Today it uses a stable agent label and fresh UUID-suffixed session id to avoid colliding with a durable log on the next run. Under unification it must deliberately resume the fixed id, mint a fresh combined id, or expose an explicit policy; implementation must not pick silently. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. ## Alternatives considered -**Keep separate routing and log identities.** The config-driven loop uses a stable configured agent id with a fresh UUID session on each fresh process start. That is a real use of the distinction: a stable routing/display label plus a new durable conversation. Unification can proceed only after choosing whether this path resumes a fixed identity, mints a combined per-run identity, or exposes the policy explicitly. If the stable label is a required product contract, reject this proposal rather than hiding it in another map. +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. ## Acceptance criteria @@ -35,4 +35,4 @@ The config-driven path must first settle its currently hidden resume-or-create p ## Risks -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. The config restart decision is blocking, not mechanical. If separate routing identity is a real requirement, reject this RFC and retain the current caller-supplied pair plus final-entry arbitration. +This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 512688d88d..22446f0dc3 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -4,11 +4,12 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -72,7 +73,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-')) ctx = await codeModeHarness(workdir) - const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/coding-agent/tests/coding-task.e2e.ts index ce716bdb2c..e1ae9804ac 100644 --- a/examples/coding-agent/tests/coding-task.e2e.ts +++ b/examples/coding-agent/tests/coding-task.e2e.ts @@ -4,8 +4,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The swebench-style smoke test: a real model fixes a real bug in a temp @@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test expect(before.status).not.toBe(0) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-task'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index 854cf49d2a..a0e71aacc4 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The compaction smoke test: a real model runs a multi-step bash task with a @@ -64,7 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa }, persistenceRoot: join(workdir, '.sessions'), }) - const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-compaction'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/full-loop.e2e.ts b/examples/coding-agent/tests/full-loop.e2e.ts index 8718139ced..9a01713222 100644 --- a/examples/coding-agent/tests/full-loop.e2e.ts +++ b/examples/coding-agent/tests/full-loop.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The first place a REAL model meets the REAL bash tool: the cheap canary @@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas it('runs a bash command on request and reports its output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-')) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-loop'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) await waitForIdle(ctx, agent) diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 70382b4beb..48e135ad92 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -4,7 +4,6 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' @@ -40,7 +39,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // log on disk survives. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const first = (await ctx.agents.create({ - agentId: AgentId('resume-1'), sessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent @@ -54,7 +52,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses // run 1's exchange as conversation history. ctx = await codingHarness(process.cwd(), { persona: SYSTEM_PROMPT, persistenceRoot: root }) const resumed = (await ctx.agents.resume({ - agentId: AgentId('resume-2'), resumeSessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/coding-agent/tests/todo-write.e2e.ts index 698fbd9e9e..7f3c3c1e4a 100644 --- a/examples/coding-agent/tests/todo-write.e2e.ts +++ b/examples/coding-agent/tests/todo-write.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * A REAL model drives the REAL todo_write tool: verify the WORLD (the session @@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a it('appends a todo/write event with the model-produced task list', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-')) ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Use the todo_write tool to record a plan of exactly two steps: first ' diff --git a/examples/cordis-agent/tests/cordis-tools.e2e.ts b/examples/cordis-agent/tests/cordis-tools.e2e.ts index 388fcb0058..ffe9a290eb 100644 --- a/examples/cordis-agent/tests/cordis-tools.e2e.ts +++ b/examples/cordis-agent/tests/cordis-tools.e2e.ts @@ -1,8 +1,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import type { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId } from '@deepseek-ai/dsh-agent' import { cordisHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the self-referential cordis tools: a REAL model drives @@ -38,7 +38,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => { ctx = await cordisHarness() const log = vi.spyOn(console, 'log').mockImplementation(() => {}) - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -66,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('builds itself a reverse_text tool and actually calls it', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index a22e86bd99..3ab3ae6628 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' @@ -74,7 +75,7 @@ describe('bash tool through the agent loop', () => { textResponse('The command printed integration-ok.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-fg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-fg'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) @@ -106,7 +107,7 @@ describe('bash tool through the agent loop', () => { textResponse('It failed with code 9.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-exit'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-exit'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) @@ -128,7 +129,7 @@ describe('bash tool through the agent loop', () => { let taskId = '' const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-bg'), { model: 'mock' }) // Capture the generated id so the deterministic fixture is checked against // the real executor instead of silently assuming it. diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 12b4a53958..c68c445f0a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -57,7 +57,7 @@ async function setup() { const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id) — a config agent has `agentId !== sessionId`. The + // token (session.header.id), which is also the agent's durable id. The // owner token IS the session id, so the notice path must find the agent by // `session.header.id`, NOT the registry key. Using distinct values here makes // the test fail if a regression matched on the wrong field (a same-value fake diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index bb77e44a9c..52a2ecd134 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -3,11 +3,12 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' @@ -119,7 +120,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { - const agent = ctx.agentLoop.create(AgentId('repro'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('repro'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 3d6ade301f..5721bd97d9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -56,7 +56,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'agentLoop', summary: 'Concrete ReactLoopAgent factory and driver service.', methods: [ - 'create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', + 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', ], @@ -71,7 +71,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'register(agent: Agent): () => void', 'enter(agent: Agent): () => void', 'announce(agent: Agent): void', - 'get(id: AgentId): Agent | undefined', + 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', ], }, @@ -488,7 +488,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ export const TYPE_API: readonly TypeApiEntry[] = [ { name: 'Agent', - declaration: 'export interface Agent {\n readonly id: AgentId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', + declaration: 'export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: SendOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', }, { name: 'AgentFactory', @@ -498,10 +498,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AgentHandle', declaration: 'export interface AgentHandle {\n agent: Agent;\n dispose(): Promise;\n}', }, - { - name: 'AgentId', - declaration: 'export type AgentId = Branded<\'AgentId\'>;', - }, { name: 'AgentOptions', declaration: 'export interface AgentOptions {\n model?: string;\n}', @@ -644,7 +640,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CreateAgentOptions', - declaration: 'export interface CreateAgentOptions {\n readonly agentId: AgentId;\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface CreateAgentOptions {\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'CreateSessionOptions', @@ -756,7 +752,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'ResumeAgentOptions', - declaration: 'export interface ResumeAgentOptions {\n readonly agentId: AgentId;\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface ResumeAgentOptions {\n readonly resumeSessionId: SessionId;\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'SandboxEnforcement', @@ -868,7 +864,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SubagentRun', - declaration: 'export interface SubagentRun {\n readonly id: AgentId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', + declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', }, { name: 'SubagentStartRequest', diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..0d4c6c5c18 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -51,7 +52,7 @@ describe('cordis tools through the agent loop', () => { textResponse('Done.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-cordis'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-cordis'), { model: 'mock' }) agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) await waitForIdle(ctx, agent) diff --git a/packages/core/agent-core/README.md b/packages/core/agent-core/README.md index 33cd0faddd..accbf66a7c 100644 --- a/packages/core/agent-core/README.md +++ b/packages/core/agent-core/README.md @@ -43,7 +43,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-core' // so validation and defaulting can never drift from the owners. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates one under the `main` config label; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; and `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer. Forwarding is exactly why the owners can live in the shared spine even though the apps disagree on what to configure. ## Why a code bundle, not a shared YAML include diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index 855bb28d49..058191c88f 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -6,8 +6,10 @@ import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as agentCore from '../src/index.ts' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' async function composePrefix(ctx: Context, cwd: string): Promise { const agent = { session: { header: { cwd } } } as unknown as Agent @@ -102,16 +104,18 @@ describe('dsh-agent-core bundle', () => { it('defaults the agents list to empty (no pre-created agents)', async () => { const ctx = await mount() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.get(SessionId('main'))).toBeUndefined() await ctx.fiber.dispose() }) it('forwards a pre-created agent to the loop and the persona to system-prompt', async () => { const ctx = await mount({ - agents: [{ id: AgentId('main'), model: 'mock' }], + agents: [{ id: 'main', model: 'mock' }], persona: 'You are main.', }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) const assembly = await ctx.get('systemPrompt')!.assemble() expect(assembly.sections.find(s => s.name === 'deployment:persona')?.text).toBe('You are main.') await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 6832800d2e..f40577bb95 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -12,14 +12,14 @@ Creation and resume are one rollback-covered transaction: construct a private se The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createAgent(ownerCtx, options)` and `resume(ownerCtx, options)` receive caller ownership explicitly, while the factory keeps its own dependency context for `sessions`/`llm`/`tools`/`systemPrompt`; this lets a caller inject only `agents` without shrinking the new agent's service surface. Caller unload, handle disposal, or provider unload converge on one memoized quiescence boundary. Provider shutdown waits both resource teardown and the public create/resume wrapper that observed deactivation, so no continuation can publish after dependencies disappear. -IDs are caller-chosen and assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same agent or session id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; IDs become reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. +Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: string, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create, used directly by programs and by `cordis.yml`-configured agents. It creates a fresh per-run session id `${id}-session-` with optional metadata; the uuid avoids colliding with a prior durable log. Each call is a new session (a deliberate demo simplification — a real resume-or-create policy is a TODO). Disposed with the calling fiber. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): -- `ctx.agents.create({ agentId, sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create on a caller-supplied `sessionId`, NOT `${id}-session`. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. -- `ctx.agents.resume({ agentId, resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. The live session id is the resumed id; turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. +- `ctx.agents.create({ sessionId, meta?, seed?, agentOptions?, setup?, signal? }): Promise` — programmatic create under the caller-supplied shared id. It awaits the unpublished setup transaction before returning; `meta` carries cwd/lineage/seed-boundary metadata and `seed` reconstructs a forked child prefix after the session boundary validates and snapshots the durable values. `signal` applies only until this promise settles. The resolved [`AgentHandle`](../agent/README.md) owns exact teardown. +- `ctx.agents.resume({ resumeSessionId, agentOptions?, setup?, signal? }): Promise` — load a persisted session via `ctx.sessionPersistence` ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), register the agent under that same id, reconstruct its history, then await setup against a fresh unpublished agent scope before rollback-covered publication. Turn numbering and derived history continue from the loaded log. Requires a session-persistence backend (NOT hard-injected — non-persistent demos still work; `resume` rejects with a clear error when persistence is absent). `signal` is creation-only. Returns an `AgentHandle`. The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loop fiber (it discards the handle). For a programmatic agent, the handle holder is the only consumer-facing teardown capability; AgentLoop provider unload is the independent structural teardown edge, not another handle exposed to application code. @@ -32,7 +32,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ```ts interface Config { agents: Array<{ - id: string // required + id: string // required stable label; prefixes fresh combined ids model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index ff66f942be..d54baab597 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -8,11 +8,11 @@ import type { Context } from 'cordis' import { agentEvents } from '@deepseek-ai/dsh-agent' -import type { AgentId, AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' +import type { AgentOptions, AgentStatus, SendOptions } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { deepFreeze } from '@deepseek-ai/dsh-llm' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' -import { snapshotJsonValue, type Session } from '@deepseek-ai/dsh-session' +import { snapshotJsonValue, type Session, type SessionId } from '@deepseek-ai/dsh-session' import { Inbox, type InboxMessage } from './inbox.ts' import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts' @@ -59,7 +59,7 @@ export interface PreparedReactLoopAgent { * @returns the agent and closures bound only to that exact instance. */ export function prepareReactLoopAgent( - ctx: Context, id: AgentId, options: AgentOptions, session: Session, + ctx: Context, id: SessionId, options: AgentOptions, session: Session, ): PreparedReactLoopAgent { if (claimedDriverSessions.has(session)) { throw new Error(`session "${session.id}" already has a concrete agent driver`) @@ -163,7 +163,7 @@ export class ReactLoopAgent implements Agent { constructor( private loopCtx: Context, - public readonly id: AgentId, + public readonly id: SessionId, public readonly options: AgentOptions, public readonly session: Session, ) { diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 4ad4779176..33276c01f8 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -14,7 +14,6 @@ import { agentEvents } from '@deepseek-ai/dsh-agent' import type { AgentFactory, AgentHandle, - AgentId, AgentOptions, CreateAgentOptions, ResumeAgentOptions, @@ -68,7 +67,7 @@ class FactoryOwnership { } /** Build the public cancellation error while preserving a caller-supplied cause. */ -function signalAbortError(id: AgentId, signal: AbortSignal): Error { +function signalAbortError(id: SessionId, signal: AbortSignal): Error { if (signal.reason instanceof Error) return signal.reason return new Error(`agent "${id}" creation aborted`, { cause: signal.reason }) } @@ -108,7 +107,7 @@ class AgentCreationTransaction { private readonly loopCtx: Context, private readonly ownerCtx: Context, private readonly ownership: FactoryOwnership, - readonly id: AgentId, + readonly id: SessionId, signal?: AbortSignal, ) { ownerCtx.fiber.assertActive() @@ -325,8 +324,8 @@ declare module 'cordis' { export interface Config { /** Agents created or resumed at plugin startup. */ agents: (AgentOptions & { - /** Registry identity for the live agent. */ - id: AgentId + /** Stable config label used in logs and as the fresh combined-id prefix. */ + id: string /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -363,13 +362,13 @@ export class AgentLoop extends Service implements AgentFactory { for (const { id, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(id, options, cwd === undefined ? {} : { cwd }) + const sessionId = SessionId(`${id}-session-${randomUUID()}`) + this.create(sessionId, options, cwd === undefined ? {} : { cwd }) continue } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { - agentId: id, resumeSessionId, agentOptions: options, }).catch((error: unknown) => { @@ -382,19 +381,19 @@ export class AgentLoop extends Service implements AgentFactory { } /** - * Create an agent on a fresh per-run session, owned by the accessing fiber. - * Constructor-driven config calls use the loop fiber itself. - * @param id - agent registry id. + * Create an agent and session under one caller-supplied identity, owned by + * the accessing fiber. Constructor-driven config calls mint a fresh combined + * id before entering this boundary. + * @param id - shared agent/session identity. * @param options - concrete loop options. * @param meta - optional fresh-session workspace metadata. * @returns the published running agent. */ - create(id: AgentId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - const session = loopCtx.sessions.prepare(sessionId, { meta }) + const session = loopCtx.sessions.prepare(id, { meta }) const agent = transaction.prepare(options, session) transaction.publish('startup') return agent @@ -417,7 +416,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.sessionId, options.signal, ) try { @@ -461,7 +460,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime.ctx, ownerCtx, this.ownership, - options.agentId, + options.resumeSessionId, options.signal, ) try { diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7f65bbc5f3..56d6489fbe 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -1,6 +1,5 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -53,10 +52,10 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) - const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('first-driver'), { model: 'mock' }, session) expect(() => prepared.agent.ctx).toThrow('context is not bound') - expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session)) + expect(() => prepareReactLoopAgent(ctx, SessionId('second-driver'), { model: 'mock' }, session)) .toThrow('already has a concrete agent driver') await prepared.dispose() @@ -66,11 +65,11 @@ describe('ReactLoopAgent', () => { it('borrows caller options and binds its scoped context exactly once', async () => { const ctx = await harness(new MockAdapter([textResponse('unused')])) const options = { model: 'mock' } - const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options) + const agent = ctx.agentLoop.create(SessionId('owned-bindings'), options) expect(agent.options).toBe(options) expect(agent.id).toBe('owned-bindings') - expect(agent.session.id).toMatch(/^owned-bindings-session-/) + expect(agent.session.id).toBe(agent.id) expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/) await ctx.fiber.dispose() @@ -81,7 +80,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -96,7 +95,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -111,7 +110,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -124,7 +123,7 @@ describe('ReactLoopAgent', () => { it('inject() decides enclosure from the LOG (open turn), not agent status', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Simulate an OPEN turn in the log while the agent is idle (status is not a // reliable open-turn signal). inject must append into that open turn, NOT @@ -150,7 +149,7 @@ describe('ReactLoopAgent', () => { // A persistence-like listener whose flush rejects. ctx.on('session/flush', () => { throw new Error('disk gone') }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // inject() is synchronous and fires a fire-and-forget flush; a rejecting // flush must be contained (logged), never thrown into the caller. @@ -163,7 +162,7 @@ describe('ReactLoopAgent', () => { it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) @@ -183,7 +182,7 @@ describe('ReactLoopAgent', () => { it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) // Session contains a throwing post-commit turn/end observer. The accepted @@ -206,7 +205,7 @@ describe('ReactLoopAgent', () => { // A non-Error rejection exercises the String() normalization branch. ctx.on('session/flush', () => { throw 'disk gone' }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: { turn: number; step: number; message: string }[] = [] ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message })) @@ -225,7 +224,7 @@ describe('ReactLoopAgent', () => { it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A non-serializable source makes the turn/start append throw BEFORE the // event is pushed (Session.append validates before push), so NO turn opens. @@ -240,7 +239,7 @@ describe('ReactLoopAgent', () => { it('steer() when idle falls through to send() and starts a turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // steer while idle delegates to send agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -258,7 +257,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared // Start the loop to get the disposer; the agent waits for messages @@ -280,7 +279,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) - const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('pre-start-dispose'), { model: 'mock' }, session) await prepared.dispose() expect(prepared.agent.status).toBe('disposed') @@ -294,7 +293,7 @@ describe('ReactLoopAgent', () => { it('setting the same status does not emit agent/status again', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const statuses: string[] = [] ctx.on('agent/status', (subject, status) => { @@ -313,7 +312,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() resolves immediately when the agent is not running', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Fresh agent is idle — whenIdle() takes the not-running fast path and // resolves without subscribing. await must not hang. @@ -324,7 +323,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() waits for queued work that has not flipped status yet', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'queued') let settled = false @@ -342,8 +341,8 @@ describe('ReactLoopAgent', () => { it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => { const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) // Drive `agent` into `running`, then await whenIdle() — it subscribes to // agent/status and resolves on the first transition out of running. @@ -379,7 +378,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter(['hang']) ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, SessionId('bare'), { model: 'mock' }, session) const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() @@ -404,7 +403,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -425,7 +424,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -446,7 +445,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'running') throw new Error('bad running listener') }) @@ -464,7 +463,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'idle') throw new Error('bad idle listener') }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 56376b69a7..82b1f6c58c 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -16,7 +16,8 @@ import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ describe('Agent.cancel()', () => { it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The loop is parked at the idle wait with nothing queued. A cancel here must // NOT arm the marker — otherwise the next legitimate prompt would be dropped. @@ -74,7 +75,7 @@ describe('Agent.cancel()', () => { it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // send() queues synchronously (status still idle, loop microtask not yet // resumed). Cancel in that pre-step window: the queued turn must not run. @@ -93,7 +94,7 @@ describe('Agent.cancel()', () => { it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => { const adapter = new MockAdapter([textResponse('x')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Queue work, then register a whenIdle() waiter while in the pre-step window // (status idle, hasQueued true) — it does NOT take the fast path. Then cancel. @@ -114,7 +115,7 @@ describe('Agent.cancel()', () => { it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -131,7 +132,7 @@ describe('Agent.cancel()', () => { it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -147,7 +148,7 @@ describe('Agent.cancel()', () => { it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // First turn hangs; cancel it mid-step. send(agent, 'first') @@ -169,7 +170,7 @@ describe('Agent.cancel()', () => { it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Prefix composition runs before the pre-step seam on the instance's first // step; a cancel landing inside it must drop the about-to-start step @@ -203,7 +204,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-prefix'), sessionId: SessionId('dispose-prefix-session'), agentOptions: { model: 'mock' }, }) @@ -232,7 +232,7 @@ describe('Agent.cancel()', () => { it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // The first composition is interrupted mid-waterfall and — like an // abort-aware listener bailing on a firing signal — contributes nothing. @@ -266,7 +266,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A turn/start listener fires right after turn/start is appended, BEFORE any // AbortController is installed for the step. Cancelling there must still drop @@ -295,7 +295,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous step/start session-event listener drops the step (post-step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A step/start session-event listener fires AFTER step/start is appended // (and after the pre-step seam), so cancelling there lands in the SECOND @@ -334,7 +334,6 @@ describe('Agent.cancel()', () => { ctx.llm.registerAdapter(['mock'], adapter) const handle = await ctx.agents.create({ - agentId: AgentId('a-dispose-step-start'), sessionId: SessionId('dispose-step-start-session'), agentOptions: { model: 'mock' }, }) @@ -366,7 +365,7 @@ describe('Agent.cancel()', () => { // `aborted` and run NO second step. const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 const reasons: TurnEndReason[] = [] @@ -398,7 +397,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // setStatus('running') emits agent/status SYNCHRONOUSLY, so a running // listener can cancel in the gap between the loop's pre-step check and @@ -428,7 +427,7 @@ describe('Agent.cancel()', () => { // so whenIdle() resolves on the replacement turn's running→idle, not before. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let replaced = false const dispose = ctx.on('agent/status', (subject, status) => { @@ -458,7 +457,7 @@ describe('Agent.cancel()', () => { // settle (the quiescence contract), not resolve before B's first event. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'A') // queues A (status still idle, loop microtask pending) const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path) @@ -478,7 +477,7 @@ describe('Agent.cancel()', () => { it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 07d6cd9e9b..134ea68c32 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -7,7 +7,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -32,7 +33,7 @@ describe('config-driven session id', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], + agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('deferred') }], }) const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)') @@ -53,11 +54,13 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx1.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) - const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent + const a1 = ctx1.agents.list()[0] as ReactLoopAgent + expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) + expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -70,10 +73,11 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) - const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent + const a2 = ctx2.agents.list()[0] as ReactLoopAgent + expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) a2.send([{ type: 'text', text: 'q2' }], { source: { kind: 'user' } }) @@ -96,7 +100,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -110,7 +114,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -118,11 +122,12 @@ describe('config-driven session id', () => { let resumed: ReactLoopAgent | undefined for (let i = 0; i < 50 && !resumed; i++) { await new Promise(r => setTimeout(r, 5)) - resumed = ctx2.agents.get(AgentId('main')) as ReactLoopAgent | undefined + resumed = ctx2.agents.get(SessionId('sticky-1')) as ReactLoopAgent | undefined } expect(resumed).toBeDefined() // The live session id IS the resumed id (NOT a fresh ${id}-session-), // and the prior turn's user message is in the derived history. + expect(resumed!.id).toBe(SessionId('sticky-1')) expect(resumed!.session.id).toBe('sticky-1') const derived = resumed!.session.deriveMessages() expect(JSON.stringify(derived)).toContain('remember me') @@ -138,16 +143,16 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + await ctx.plugin(AgentLoop, { agents: [{ id: 'main', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('x')])) // The deferred resume fails (no such session on disk). It must be contained: - // a warning is logged, no 'main' agent is registered, and the app stays up. + // a warning is logged, no agent is registered, and the app stays up. await new Promise(r => setTimeout(r, 200)) - expect(ctx.agents.get(AgentId('main'))).toBeUndefined() + expect(ctx.agents.list()).toEqual([]) expect(warn).toHaveBeenCalledWith(expect.stringContaining('config-driven resume of "does-not-exist" failed')) warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 23e5670f85..4e82e398f1 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' -import SessionStore, { TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -40,7 +41,7 @@ describe('inbox acceptance', () => { it('rejects non-serializable content or source synchronously before notification or enqueue', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let queued = 0 ctx.on('agent/queued', () => { queued += 1 }) @@ -80,7 +81,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -113,7 +114,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: 'ran with empty args' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -126,7 +127,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('internal/dispatch', (_mode, name, args) => { @@ -152,7 +153,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => { const adapter = new MockAdapter([textResponse('irrelevant')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => { @@ -180,7 +181,7 @@ describe('coded error data emission', () => { it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => { @@ -214,7 +215,7 @@ describe('disposed vs aborted branching', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -242,7 +243,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2) textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'boom', description: 'always fails', diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 1ec48e553f..8c95be0d82 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -1,15 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { - AgentId, - type ContinuationDecision, - type PromptDecision, - type SessionStartSource, -} from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -57,7 +53,7 @@ describe('agent/prompt-submit', () => { it('allow (default via next) records the user/message unchanged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => { @@ -76,7 +72,7 @@ describe('agent/prompt-submit', () => { it('allow with content REWRITES the prompt before it is recorded', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] })) @@ -94,7 +90,7 @@ describe('agent/prompt-submit', () => { it('allow with additionalContext injects a separate context/message into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -127,7 +123,7 @@ describe('agent/prompt-submit', () => { // elsewhere; this asserts they see each other's effects on the same turn). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -157,7 +153,7 @@ describe('agent/prompt-submit', () => { it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'block', reason: 'blocked by policy' })) @@ -194,7 +190,7 @@ describe('agent/prompt-submit', () => { // vetoed prompt and its reason would vanish from the log entirely. const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise => { const text = content.map(b => (b.type === 'text' ? b.text : '')).join('') @@ -230,7 +226,7 @@ describe('agent/prompt-submit', () => { it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => { const adapter = new MockAdapter([textResponse('after')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false ctx.on('agent/prompt-submit', async () => { @@ -263,7 +259,7 @@ describe('agent/session-start', () => { const sources: SessionStartSource[] = [] ctx.on('agent/session-start', (_agent, source) => void sources.push(source)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires synchronously at create, before any turn expect(sources).toEqual(['startup']) expect(events(agent).some(e => e.type === 'turn/start')).toBe(false) @@ -282,7 +278,7 @@ describe('agent/session-start', () => { agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } }) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -300,8 +296,8 @@ describe('agent/session-start', () => { ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') }) // create must not throw — the listener error is contained/logged - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - expect(agent.id).toBe(AgentId('a1')) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + expect(agent.id).toBe(SessionId('a1')) // and the agent still runs send(agent, 'go') @@ -314,8 +310,8 @@ describe('agent/session-prefix', () => { it('dispatches to global and matching agent-scope listeners only', async () => { const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')]) const ctx = await harness(adapter) - const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { model: 'mock' }) - const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { model: 'mock' }) + const agentA = ctx.agentLoop.create(SessionId('prefix-a'), { model: 'mock' }) + const agentB = ctx.agentLoop.create(SessionId('prefix-b'), { model: 'mock' }) const seen: string[] = [] ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => { seen.push(`global:${agent.id}`) @@ -352,7 +348,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'catalog' }] } let composed = 0 @@ -385,7 +381,7 @@ describe('agent/session-prefix', () => { it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] } const order: string[] = [] @@ -412,7 +408,7 @@ describe('agent/session-prefix', () => { it('the canonical prepend pattern composes contributions in registration order', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Both listeners use the canonical `[mine, ...await next()]` prepend: the // waterfall unwinds innermost-first (the second listener's array is built @@ -434,7 +430,7 @@ describe('agent/session-prefix', () => { it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A listener that delegates without contributing — the canonical no-op. ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next()) @@ -450,7 +446,7 @@ describe('agent/session-prefix', () => { it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let mutationError: unknown ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise => { @@ -479,7 +475,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] } ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise => [...await next(), held]) @@ -500,7 +496,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { it('a continue decision with a reason records next-step steering in the same turn', async () => { const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let forced = false ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise => { @@ -533,7 +529,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async (): Promise => ({ action: 'stop' })) @@ -563,7 +559,7 @@ describe('tools/post-execute additionalContext buffering across a multi-call ste name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Each call attaches additionalContext naming itself. ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -599,7 +595,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t name: 'danger', description: 'danger', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' } @@ -663,7 +659,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'please echo hi') await waitForIdle(ctx, agent) @@ -686,7 +682,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) await ctx.plugin(NativeGuard) - const agent = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -705,7 +701,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se await fiber.dispose() // After disposal, a destructive prompt is NOT blocked (the listener is gone). - const agent = ctx.agentLoop.create(AgentId('a3'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a3'), { model: 'mock' }) send(agent, 'run rm -rf /') await waitForIdle(ctx, agent) // the prompt ran (not rejected) — proving the prompt-submit listener was disposed diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 71be5b339e..c4e49e0fa5 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -44,7 +45,7 @@ describe('agent loop', () => { it('runs a simple turn: queued message → model → idle, with ordered events', async () => { const adapter = new MockAdapter([textResponse('hello there')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // All boundaries — turn and step — are durable session events on the // session/event feed (no agent/* mirror). Record them in fire order to @@ -92,7 +93,7 @@ describe('agent loop', () => { return [{ type: 'text', text: `echo: ${args.text}` }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -131,7 +132,7 @@ describe('agent loop', () => { return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -155,7 +156,7 @@ describe('agent loop', () => { return [] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -169,7 +170,6 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter, 'Working in {{cwd}}.') const handle = await ctx.agents.create({ - agentId: AgentId('a-cwd'), sessionId: SessionId('s-cwd'), meta: { cwd: '/work/space' }, agentOptions: { model: 'mock' }, @@ -192,7 +192,7 @@ describe('agent loop', () => { const ctx = await harness(adapter, 'In {{cwd}}.') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -233,7 +233,7 @@ describe('agent loop', () => { ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } }) - const agent = ctx.agentLoop.create(AgentId('a-late-model'), {}) + const agent = ctx.agentLoop.create(SessionId('a-late-model'), {}) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -259,7 +259,7 @@ describe('agent loop', () => { parameters: {}, execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }), })) - const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-meta-agent'), { model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -288,7 +288,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} })) - const agent = ctx.agentLoop.create(AgentId('a-no-system'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-no-system'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -300,7 +300,7 @@ describe('agent loop', () => { it('records raw chunks for replay as assistant/chunk session events', async () => { const adapter = new MockAdapter([textResponse('abc')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -324,7 +324,7 @@ describe('agent loop', () => { ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'slow', description: '', @@ -356,7 +356,7 @@ describe('agent loop', () => { it('steering while idle behaves like send (starts a turn)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.steer([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) @@ -366,7 +366,7 @@ describe('agent loop', () => { it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } }) // The idle inject records a self-contained turn (turn/start → context/message @@ -393,7 +393,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // A tool that injects mid-execution: at this point the agent is running, so // inject must append the context/message into the ALREADY-open turn rather // than wrap it in its own one-shot turn. @@ -427,7 +427,7 @@ describe('agent loop', () => { textResponse('step 3'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -453,7 +453,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const) @@ -469,7 +469,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.llm.registerAdapter(['other-model'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { // The seed is frozen — config is not a mutable per-call knob; a switch @@ -502,7 +502,7 @@ describe('agent loop', () => { name: 'echo', description: 'echo', parameters: {}, async execute() { return [{ type: 'text', text: 'echoed' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { @@ -527,7 +527,7 @@ describe('agent loop', () => { // the derived request for that step (derive happens after step/start). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/pre-step', (subject) => { @@ -563,7 +563,7 @@ describe('agent loop', () => { // The loop survives and a follow-up prompt still runs. const adapter = new MockAdapter([textResponse('second turn ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let throwOnce = true ctx.on('agent/pre-step', () => { @@ -597,7 +597,7 @@ describe('agent loop', () => { it('cancel() mid-stream ends the turn with reason aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -617,7 +617,7 @@ describe('agent loop', () => { // turn stops by default and ends max-tokens, not completed. const adapter = new MockAdapter([maxTokensResponse('truncat')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -642,7 +642,7 @@ describe('agent loop', () => { textResponse('second half'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -673,7 +673,7 @@ describe('agent loop', () => { // stop. The per-turn reason must be independent — turn 2 ends completed. const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -706,7 +706,7 @@ describe('agent loop', () => { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -748,7 +748,7 @@ describe('agent loop', () => { parameters: { text: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -767,7 +767,7 @@ describe('agent loop', () => { // on the normal step path suppresses a pure trace-only empty assistant/message. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -797,7 +797,7 @@ describe('agent loop', () => { expect(message.content).toEqual([{ type: 'text', text: 'partial text' }]) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -824,7 +824,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threw = false // Post-commit session observers cannot control the loop. The tool call still // drives the second model request, and the turn completes normally. @@ -843,7 +843,7 @@ describe('agent loop', () => { it('chains queued messages into consecutive turns', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) @@ -868,7 +868,7 @@ describe('agent loop', () => { it('awaits session/flush at turn end (persistence checkpoint)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let flushed = 0 let flushedBeforeIdle = false @@ -888,7 +888,7 @@ describe('agent loop', () => { it('errors from the model surface as agent/error and end the turn', async () => { const adapter = new MockAdapter([]) // script exhausted → throws const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] const reasons: TurnEndReason[] = [] @@ -913,10 +913,10 @@ describe('agent loop', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) - expect(ctx.agents.get(AgentId('scoped'))).toBe(agent) + expect(ctx.agents.get(SessionId('scoped'))).toBe(agent) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -925,7 +925,7 @@ describe('agent loop', () => { await agent.done expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() expect(() => { send(agent, 'too late') }).toThrow('disposed') }) @@ -938,13 +938,14 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock' }], + agents: [{ id: 'config-agent', model: 'mock' }], }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent).toBeDefined() - expect(agent.id).toBe('config-agent') + expect(agent.id).toBe(agent.session.id) + expect(agent.id).toMatch(/^config-agent-session-/) expect(agent.options.model).toBe('mock') // the agent is alive: send triggers a turn @@ -961,10 +962,10 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }], + agents: [{ id: 'config-agent', model: 'mock', cwd: '/work/project' }], }) - const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent + const agent = ctx.agents.list()[0]! as ReactLoopAgent expect(agent.session.header.cwd).toBe('/work/project') }) @@ -982,7 +983,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'run') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 1e603a1cc4..b3653d6540 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -14,10 +14,11 @@ import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' @@ -95,7 +96,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) const { seen: trace } = recordStatus(ctx, agent) const idle = nextIdle(ctx, agent) // Send all in one synchronous tick: they queue before the loop wakes. @@ -120,7 +121,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) agent.send([{ type: 'text', text }]) @@ -145,7 +146,7 @@ describe('agent loop scheduling properties', () => { async (steps) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) // Capture an idle waiter before EACH send; the last one is guaranteed // to resolve because the final send always triggers (or joins) a turn // that ends idle. Awaiting an already-resolved waiter is a no-op, so a diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 5ccaa7e797..7eddb6be39 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -71,7 +72,7 @@ function waitForIdle(context: Context, agent: Agent): Promise { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => { it('every request after the first hits the provider prefix cache', async () => { ctx = await loopHarness() - const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('cache-e2e'), { model: 'deepseek-v4-flash' }) // Turn 1: forces a tool call → at least two steps (two model requests). agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 7054b683cb..202a8f6795 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -15,7 +15,8 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -74,7 +75,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -95,7 +96,7 @@ describe('request stability across the loop', () => { it('a later turn append-extends the previous turn (one conversation, one log)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -109,7 +110,7 @@ describe('request stability across the loop', () => { it('a compaction replace rewrites the resend, and the log explains it', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('request stability across the loop', () => { it('a real system-prompt change is a full changed-header snapshot; a stable prompt logs nothing', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('request stability across the loop', () => { it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let injected = false ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { @@ -194,7 +195,7 @@ describe('request stability across the loop', () => { it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -215,7 +216,7 @@ describe('request stability across the loop', () => { it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('gen1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('gen1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -224,7 +225,6 @@ describe('request stability across the loop', () => { const adapter2 = new MockAdapter([textResponse('two')]) const ctx2 = await harness(adapter2) const handle = await ctx2.agents.create({ - agentId: AgentId('gen2'), sessionId: SessionId('gen2-session'), seed: [...agent.session.events], agentOptions: { model: 'mock' }, @@ -244,7 +244,7 @@ describe('request stability across the loop', () => { it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { const config = await next() @@ -278,7 +278,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 93605008ec..f5809575ab 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -8,7 +8,8 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -83,11 +84,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => throwUnknown(failure)) await expect(ctx.agents.resume({ - agentId: AgentId('unknown-resume-failure'), resumeSessionId: sessionId, })).rejects.toBe(failure) - expect(ctx.agents.get(AgentId('unknown-resume-failure'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-resume-failure'))).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() await ctx.fiber.dispose() }) @@ -95,27 +95,26 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('createAgent uses the caller-supplied sessionId (not ${id}-session)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('custom-session'), meta: { cwd: '/w' } }) expect(agent.session.id).toBe('custom-session') expect(agent.session.header.cwd).toBe('/w') await ctx.fiber.dispose() }) - it('createAgent rejects a duplicate agent id BEFORE creating the session (no orphan)', async () => { + it('createAgent rejects a duplicate identity without orphaning a session', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - await ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-a') }) - // A second create with the SAME agent id but a fresh session id must reject - // up front — and must NOT leave an orphaned 'sess-b' session behind. - await expect(ctx.agents.create({ agentId: AgentId('dup'), sessionId: SessionId('sess-b') })).rejects.toThrow(/already registered/) - expect(ctx.sessions.get(SessionId('sess-b'))).toBeUndefined() + const sessionId = SessionId('sess-a') + await ctx.agents.create({ sessionId }) + await expect(ctx.agents.create({ sessionId })).rejects.toThrow(/already exists/) + expect(ctx.sessions.list()).toHaveLength(1) await ctx.fiber.dispose() }) it('createAgent works without meta (no cwd)', async () => { const adapter = new MockAdapter([textResponse('hi')]) const { ctx } = await persistentHarness(adapter) - const { agent } = await ctx.agents.create({ agentId: AgentId('a-nometa'), sessionId: SessionId('nometa-session') }) + const { agent } = await ctx.agents.create({ sessionId: SessionId('nometa-session') }) expect(agent.session.id).toBe('nometa-session') expect(agent.session.header.cwd).toBeUndefined() await ctx.fiber.dispose() @@ -125,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: create a no-cwd session and run a turn. const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -141,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent expect(a2.session.header.cwd).toBeUndefined() await ctx2.fiber.dispose() }) @@ -152,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const sources1: string[] = [] ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) - const a1 = (await ctx1.agents.create({ agentId: AgentId('s'), sessionId: SessionId('start-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent as ReactLoopAgent expect(sources1).toEqual(['startup']) a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) @@ -171,7 +170,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx2.llm.registerAdapter(['mock'], adapter2) const sources2: string[] = [] ctx2.on('agent/session-start', (_agent, source) => void sources2.push(source)) - await ctx2.agents.resume({ agentId: AgentId('s'), resumeSessionId: SessionId('start-sess') }) + await ctx2.agents.resume({ resumeSessionId: SessionId('start-sess') }) expect(sources2).toEqual(['resume']) await ctx2.fiber.dispose() }) @@ -186,7 +185,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('resumed-atomic'))?.session).toBe(session) + expect(ctx.agents.get(sessionId)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', (agent) => { @@ -199,11 +198,10 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) const resuming = ctx.agents.resume({ - agentId: AgentId('resumed-atomic'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic')) + expect(agentCtx.agent?.id).toBe(sessionId) expect(agentCtx.agent?.session.events).toHaveLength(2) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) @@ -215,7 +213,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { }) await setupStarted.promise - expect(ctx.agents.get(AgentId('resumed-atomic'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() expect(order).toEqual(['setup:start']) @@ -236,17 +234,15 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('successful resume disposal retires its caller-owned transaction effects', async () => { const sessionId = SessionId('resume-retired-effects-s') - const agentId = AgentId('resume-retired-effects') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const handle = await ctx.agents.resume({ - agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) const transactionLabels = [ - `agentLoop.owner(${agentId})`, - `agentLoop.lifecycle(${agentId})`, + `agentLoop.owner(${sessionId})`, + `agentLoop.lifecycle(${sessionId})`, ] expect(ctx.fiber.getEffects().map(effect => effect.label)).toEqual(expect.arrayContaining(transactionLabels)) @@ -255,7 +251,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('resume setup rejection publishes nothing, unwinds, and releases both identities', async () => { + it('resume setup rejection publishes nothing, unwinds, and releases the identity', async () => { const sessionId = SessionId('resume-setup-reject') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) @@ -265,7 +261,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -275,10 +270,9 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { })).rejects.toThrow('resume setup failed') expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-reject'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() const retry = await ctx.agents.resume({ - agentId: AgentId('resume-reject'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, }) @@ -299,7 +293,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { resuming = inner.agents.resume({ - agentId: AgentId('resume-owner-race'), resumeSessionId: sessionId, agentOptions: { model: 'mock' }, setup: async () => { @@ -313,7 +306,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await owner.dispose() await expect(resuming).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('resume-owner-race'))).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() gate.resolve(undefined) @@ -322,9 +315,8 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('owner unload aborts a never-settling persistence load, releases identities, and blocks late publication', async () => { + it('owner unload aborts a never-settling persistence load, releases the identity, and blocks late publication', async () => { const sessionId = SessionId('resume-load-owner-unload') - const agentId = AgentId('resume-load-race') const root = await persistSession(sessionId) const ctx = await mountPersistentHarness(root, new MockAdapter([textResponse('next')])) const snapshot = await ctx.sessionPersistence.load(sessionId) @@ -348,19 +340,19 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { - resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + resuming = inner.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/owner disposed during setup/) await promptly(owner.dispose()) expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - // owner.dispose() awaited transaction settlement, so the same identities - // can be reused before awaiting the public rejection. - const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) + // owner.dispose() awaited transaction settlement, so the identity can be + // reused before awaiting the public rejection. + const retry = await promptly(ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) await rejection expect(loads).toBe(2) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -370,7 +362,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() await Promise.resolve() - expect(ctx.agents.get(agentId)).toBe(retry.agent) + expect(ctx.agents.get(sessionId)).toBe(retry.agent) expect(ctx.sessions.get(sessionId)).toBe(retry.agent.session) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -380,7 +372,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { it('AgentLoop unload aborts persistence load and awaits wrapper settlement', async () => { const sessionId = SessionId('resume-load-factory-unload') - const agentId = AgentId('resume-load-factory-race') const root = await persistSession(sessionId) const ctx = new Context() await ctx.plugin(LlmService) @@ -404,14 +395,14 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => void published.push('session/created')) ctx.on('agent/created', () => void published.push('agent/created')) - const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + const resuming = ctx.agents.resume({ resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/) await promptly(loopFiber.dispose()) await rejection expect(published).toEqual([]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() lateLoad.resolve(structuredClone(snapshot)) await Promise.resolve() @@ -452,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) @@ -466,7 +457,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // disk, since a crash before the next turn would otherwise lose it. const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -491,7 +482,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // drop it on reload (the bug this guards). const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('m'), sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -509,7 +500,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent const flat = JSON.stringify(a2.session.deriveMessages()) expect(flat).toContain('background task 42 finished') await ctx2.fiber.dispose() @@ -519,7 +510,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: run one full turn, persisting it. const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ agentId: AgentId('main'), sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] @@ -539,7 +530,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ agentId: AgentId('main'), resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent // The resumed session carries the prior history… expect(a2.session.id).toBe('sess-resume') expect(a2.session.events.length).toBe(events1.length) @@ -567,7 +558,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) - await expect(ctx.agents.resume({ agentId: AgentId('m'), resumeSessionId: SessionId('nope') })) + await expect(ctx.agents.resume({ resumeSessionId: SessionId('nope') })) .rejects.toThrow(/session persistence is not configured/) await ctx.fiber.dispose() }) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 5898a82ee2..942199e9eb 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -4,7 +4,8 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationDecision } from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -53,7 +54,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( return [{ type: 'text', text: 'ran' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Plugin rewrites the message: replaces the text AND adds a tool call. let rewritten = false @@ -104,7 +105,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { ]) const ctx = await harness(adapter) const executed: string[] = [] - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -148,7 +149,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('continued because of steering'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => { @@ -188,7 +189,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('after goal reminder'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let steeredOnce = false ctx.on('session/event', (subject, event) => { @@ -218,7 +219,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) const turns: number[] = [] let steeredOnce = false @@ -244,7 +245,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steering queued during an aborted step is re-delivered, not silently consumed', async () => { const adapter = new MockAdapter(['hang', textResponse('recovered')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -267,7 +268,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let threwOnce = false ctx.on('agent/turn-continuation', async (): Promise => { @@ -295,7 +296,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a rejecting session/flush listener is reported but does not kill the agent', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) let rejectedOnce = false ctx.on('session/flush', async () => { @@ -325,7 +326,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const statuses: string[] = [] @@ -348,7 +349,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.on('agent/status', (_agent, status) => { @@ -361,7 +362,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { await agent.done // must not hang expect(agent.status).toBe('disposed') - expect(ctx.agents.get(AgentId('scoped'))).toBeUndefined() // unregistered despite the throw + expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw }) }) @@ -380,7 +381,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { const adapter = new MockAdapter([textResponse('never')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -395,7 +396,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('the agent/request waterfall can supply the model for a model-less agent', async () => { const adapter = new MockAdapter([textResponse('routed')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides + const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model — router plugin decides ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { return { ...config, model: 'mock' } @@ -410,7 +411,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('agent/queued carries the resolved source; steering/message records its source', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.tools.register(defineTool({ name: 'noop', description: '', @@ -438,7 +439,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('send() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-send'), { model: 'mock' }) const content = [{ type: 'text' as const, text: 'accepted-send' }] const source = { kind: 'plugin' as const, plugin: 'accepted-source' } let notifiedContent: ContentBlock[] | undefined @@ -474,7 +475,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('running steer() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-steer'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-steer'), { model: 'mock' }) const entered = Promise.withResolvers() const release = Promise.withResolvers() ctx.tools.register(defineTool({ @@ -528,7 +529,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -544,7 +545,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () ctx2.llm.registerAdapter(['mock'], second) const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) - const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded) + const prepared = prepareReactLoopAgent(ctx2, SessionId('forked-agent'), { model: 'mock' }, seeded) const forked = prepared.agent prepared.markPublished() ctx2.effect(() => prepared.startDriver()) @@ -591,7 +592,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -616,7 +617,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([abortedStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-aborted'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -634,7 +635,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-finish-error-nocode'), { model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -650,7 +651,7 @@ describe('step boundary publication order', () => { it('the step/start event is in session.events when its session/event listener fires', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-step-order'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-step-order'), { model: 'mock' }) // Session.append pushes the event BEFORE notifying session/event listeners, // so a step/start listener always finds the matching event already in the @@ -711,7 +712,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/start observer cannot change a successful turn', async () => { const adapter = new MockAdapter([textResponse('request completed')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart'), { model: 'mock' }) // Session owns post-commit containment. The loop sees a successful append, // runs the request, and balances the ordinary step and turn boundaries. @@ -740,7 +741,7 @@ describe('turn and step boundary recovery', () => { it('a pre-commit step/start validation failure does not invent a step boundary', async () => { const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepstart-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -771,7 +772,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }] const adapter = new MockAdapter([errorStream]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -805,7 +806,7 @@ describe('turn and step boundary recovery', () => { it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => { const adapter = new MockAdapter([textResponse('completed before close validation')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-veto'), { model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -839,7 +840,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-errorlistener'), { model: 'mock' }) let threw = false ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } }) @@ -872,7 +873,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -901,7 +902,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { model: 'mock' }) }, { inject: ['agentLoop'] })) let threw = false @@ -935,7 +936,7 @@ describe('turn and step boundary recovery', () => { it('a throwing turn/start observer cannot starve the loop or later turns', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-preturn'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-preturn'), { model: 'mock' }) let threw = false ctx.on('session/event', (_session, event) => { @@ -966,7 +967,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/end observer cannot rewrite the turn outcome', async () => { const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stepend-throw'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1008,7 +1009,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-stependthrow'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1038,7 +1039,7 @@ describe('turn and step boundary recovery', () => { // boundary stays authoritative and the loop continues normally. const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-turnendappend'), { model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1085,7 +1086,7 @@ describe('tool result call identity', () => { return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] }) }, { prepend: true }) - const agent = ctx.agentLoop.create(AgentId('a-callid'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a-callid'), { model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -1120,7 +1121,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({ role: 'assistant' as const, @@ -1171,7 +1172,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1227,7 +1228,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1282,7 +1283,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1334,7 +1335,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1384,7 +1385,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' }) + agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 2c478ad1f0..c68d96e525 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -4,7 +4,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' + import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' @@ -57,33 +58,31 @@ function disposeCurrentLifecycle(ownerCtx: Context): void { } describe('agent scope lifecycle', () => { - it('rejects an already-aborted creation signal before publishing either identity', async () => { + it('rejects an already-aborted creation signal before publishing either object', async () => { const ctx = await harness() const reason = new Error('cancelled before creation') const controller = new AbortController() controller.abort(reason) await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted'), sessionId: SessionId('pre-aborted-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('pre-aborted'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-s'))).toBeUndefined() const valueController = new AbortController() valueController.abort('plain cancellation reason') await expect(ctx.agents.create({ - agentId: AgentId('pre-aborted-value'), sessionId: SessionId('pre-aborted-value-s'), signal: valueController.signal, })).rejects.toMatchObject({ - message: 'agent "pre-aborted-value" creation aborted', + message: 'agent "pre-aborted-value-s" creation aborted', cause: 'plain cancellation reason', }) - expect(ctx.agents.get(AgentId('pre-aborted-value'))).toBeUndefined() + expect(ctx.agents.get(SessionId('pre-aborted-value-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('pre-aborted-value-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -100,12 +99,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('prepare-abort'), sessionId: SessionId('prepare-abort-s'), signal: controller.signal, })).rejects.toBe(reason) - expect(ctx.agents.get(AgentId('prepare-abort'))).toBeUndefined() + expect(ctx.agents.get(SessionId('prepare-abort-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('prepare-abort-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -124,7 +122,7 @@ describe('agent scope lifecycle', () => { thrown = createFailure let createCaught: unknown try { - ctx.agentLoop.create(AgentId('unknown-create')) + ctx.agentLoop.create(SessionId('unknown-create')) } catch (error: unknown) { createCaught = error } @@ -133,28 +131,27 @@ describe('agent scope lifecycle', () => { const ownedFailure = { source: 'createAgent' } thrown = ownedFailure await expect(ctx.agents.create({ - agentId: AgentId('unknown-owned-create'), sessionId: SessionId('unknown-owned-create-s'), })).rejects.toBe(ownedFailure) - expect(ctx.agents.get(AgentId('unknown-create'))).toBeUndefined() - expect(ctx.agents.get(AgentId('unknown-owned-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-create'))).toBeUndefined() + expect(ctx.agents.get(SessionId('unknown-owned-create-s'))).toBeUndefined() await ctx.fiber.dispose() }) it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) expect(scopeOf(agent.ctx)).toBe(agent) expect(agent.ctx.agent).toBe(agent) // The root accessor default: a plain context answers undefined, not a throw. expect(ctx.agent).toBeUndefined() - await ctx.agents.get(AgentId('a1'))?.whenIdle() + await ctx.agents.get(SessionId('a1'))?.whenIdle() }) it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) const { agent } = handle agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) agent.ctx.tools.register({ @@ -179,8 +176,8 @@ describe('agent scope lifecycle', () => { it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => { const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')])) - const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) - const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' }) + const a = ctx.agentLoop.create(SessionId('a'), { model: 'mock' }) + const b = ctx.agentLoop.create(SessionId('b'), { model: 'mock' }) const heard: string[] = [] a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`)) @@ -210,7 +207,6 @@ describe('agent scope lifecycle', () => { }) const handle = await ctx.agents.create({ - agentId: AgentId('child'), sessionId: SessionId('child-s'), agentOptions: { model: 'mock' }, setup: async (agentCtx) => { @@ -224,14 +220,14 @@ describe('agent scope lifecycle', () => { await handle.dispose() }) - it('keeps both identities unpublished until async setup completes, then announces in order', async () => { + it('keeps both objects unpublished until async setup completes, then announces in order', async () => { const ctx = await harness() const gate = Promise.withResolvers() const setupStarted = Promise.withResolvers() const order: string[] = [] ctx.on('session/created', (session) => { expect(ctx.sessions.get(session.id)).toBe(session) - expect(ctx.agents.get(AgentId('atomic'))?.session).toBe(session) + expect(ctx.agents.get(session.id)?.session).toBe(session) order.push('session/created') }) ctx.on('agent/created', () => void order.push('agent/created')) @@ -239,11 +235,10 @@ describe('agent scope lifecycle', () => { const acceptedOptions = { model: 'mock' } const creating = ctx.agents.create({ - agentId: AgentId('atomic'), - sessionId: SessionId('atomic-s'), + sessionId: SessionId('atomic'), agentOptions: acceptedOptions, setup: async (agentCtx) => { - expect(agentCtx.agent?.id).toBe(AgentId('atomic')) + expect(agentCtx.agent?.id).toBe(SessionId('atomic')) agentCtx.on('session/created', () => void order.push('setup-listener:session/created')) agentCtx.on('agent/created', () => void order.push('setup-listener:agent/created')) order.push('setup:start') @@ -253,7 +248,7 @@ describe('agent scope lifecycle', () => { }, }) await setupStarted.promise - expect(ctx.agents.get(AgentId('atomic'))).toBeUndefined() + expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) @@ -281,16 +276,14 @@ describe('agent scope lifecycle', () => { if (started === 2) bothStarted.resolve(undefined) await gate.promise } - const agentId = AgentId('concurrent-final-enter') + const sessionId = SessionId('concurrent-final-enter') const first = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-a'), + sessionId, agentOptions: { model: 'mock' }, setup, }) const second = ctx.agents.create({ - agentId, - sessionId: SessionId('concurrent-final-enter-b'), + sessionId, agentOptions: { model: 'mock' }, setup, }) @@ -304,7 +297,7 @@ describe('agent scope lifecycle', () => { const rejected = outcomes.filter((outcome): outcome is PromiseRejectedResult => outcome.status === 'rejected') expect(fulfilled).toHaveLength(1) expect(rejected).toHaveLength(1) - expect(String(rejected[0]!.reason)).toMatch(/already registered/) + expect(String(rejected[0]!.reason)).toMatch(/already exists/) expect(ctx.agents.list()).toEqual([fulfilled[0]!.value.agent]) expect(ctx.sessions.list()).toEqual([fulfilled[0]!.value.agent.session]) @@ -318,7 +311,6 @@ describe('agent scope lifecycle', () => { const pendingController = new AbortController() const setupStarted = Promise.withResolvers() const pending = ctx.agents.create({ - agentId: AgentId('signal-pending'), sessionId: SessionId('signal-pending-s'), agentOptions: { model: 'mock' }, signal: pendingController.signal, @@ -330,12 +322,11 @@ describe('agent scope lifecycle', () => { await setupStarted.promise pendingController.abort(new Error('cancel pending creation')) await expect(pending).rejects.toThrow('cancel pending creation') - expect(ctx.agents.get(AgentId('signal-pending'))).toBeUndefined() + expect(ctx.agents.get(SessionId('signal-pending-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('signal-pending-s'))).toBeUndefined() const liveController = new AbortController() const live = await ctx.agents.create({ - agentId: AgentId('signal-live'), sessionId: SessionId('signal-live-s'), agentOptions: { model: 'mock' }, signal: liveController.signal, @@ -358,7 +349,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('owner-race'), sessionId: SessionId('owner-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -372,7 +362,7 @@ describe('agent scope lifecycle', () => { await owner.dispose() await expect(creating).rejects.toThrow(/owner disposed during setup/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('owner-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s'))).toBeUndefined() // Let the losing callback settle; Promise.race already observes it. gate.resolve(undefined) @@ -386,7 +376,6 @@ describe('agent scope lifecycle', () => { let creating2!: ReturnType const owner2 = await ctx.plugin(Object.assign((inner: Context) => { creating2 = inner.agents.create({ - agentId: AgentId('owner-race-2'), sessionId: SessionId('owner-race-s-2'), agentOptions: { model: 'mock' }, setup: async () => { @@ -400,7 +389,7 @@ describe('agent scope lifecycle', () => { const unload2 = owner2.dispose() await expect(creating2).rejects.toThrow(/owner disposed during setup/) await unload2 - expect(ctx.agents.get(AgentId('owner-race-2'))).toBeUndefined() + expect(ctx.agents.get(SessionId('owner-race-s-2'))).toBeUndefined() expect(ctx.sessions.get(SessionId('owner-race-s-2'))).toBeUndefined() }) @@ -413,7 +402,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) const creating = ctx.agents.create({ - agentId: AgentId('factory-setup-race'), sessionId: SessionId('factory-setup-race-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -426,7 +414,7 @@ describe('agent scope lifecycle', () => { await loopFiber.dispose() await expect(creating).rejects.toThrow(/agent loop is not active/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('factory-setup-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-setup-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-setup-race-s'))).toBeUndefined() gate.resolve(undefined) @@ -444,7 +432,6 @@ describe('agent scope lifecycle', () => { }) const creating = ctx.agents.create({ - agentId: AgentId('factory-scope-race'), sessionId: SessionId('factory-scope-race-s'), agentOptions: { model: 'mock' }, setup: () => { setupCalls += 1 }, @@ -452,7 +439,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/agent loop is not active/) await loopFiber.dispose() expect(setupCalls).toBe(0) - expect(ctx.agents.get(AgentId('factory-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-race-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -479,7 +466,6 @@ describe('agent scope lifecycle', () => { const owner = ctx.plugin(Object.assign((inner: Context) => { ownerFiber = inner.fiber creating = inner.agents.create({ - agentId: AgentId('caller-scope-race'), sessionId: SessionId('caller-scope-race-s'), agentOptions: { model: 'mock' }, }) @@ -495,7 +481,7 @@ describe('agent scope lifecycle', () => { await ownerDisposal await owner expect(scopeFiber?.uid).toBeNull() - expect(ctx.agents.get(AgentId('caller-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('caller-scope-race-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('caller-scope-race-s'))).toBeUndefined() await owner.dispose() await ctx.fiber.dispose() @@ -511,17 +497,17 @@ describe('agent scope lifecycle', () => { void loopFiber.dispose() }) - expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-scope-race'), { model: 'mock' })) .toThrow(/agent loop is not active/) await loopFiber.dispose() - expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-scope-race'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) await ctx.fiber.dispose() }) it('synchronous create leaves no lifecycle state when session preparation fails', async () => { const ctx = await harness() - const id = AgentId('config-prepare-failure') + const id = SessionId('config-prepare-failure') expect(() => ctx.agentLoop.create(id, { model: 'mock' }, { cwd: 'relative' })) .toThrow(/absolute path/) @@ -542,12 +528,11 @@ describe('agent scope lifecycle', () => { }) await expect(ctx.agents.create({ - agentId: AgentId('factory-scope-throw'), sessionId: SessionId('factory-scope-throw-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('scope preparation failed') await loopFiber.dispose() - expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined() + expect(ctx.agents.get(SessionId('factory-scope-throw-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('factory-scope-throw-s'))).toBeUndefined() await ctx.fiber.dispose() @@ -556,23 +541,21 @@ describe('agent scope lifecycle', () => { it('AgentLoop unload is a structural co-owner of every live programmatic agent', async () => { const { ctx, loopFiber } = await harnessWithLoop() const loop = ctx.agentLoop - const agentId = AgentId('factory-live') + const sessionId = SessionId('factory-live') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('factory-live-s'), + sessionId, agentOptions: { model: 'mock' }, }) await loopFiber.dispose() expect(handle.agent.status).toBe('disposed') - expect(ctx.agents.get(agentId)).toBeUndefined() - expect(ctx.sessions.get(SessionId('factory-live-s'))).toBeUndefined() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.agents.get(sessionId)).toBeUndefined() + expect(ctx.sessions.get(sessionId)).toBeUndefined() + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) // The consumer handle shares the provider's completed quiescence boundary. await handle.dispose() await expect(loop.createAgent(ctx, { - agentId: AgentId('factory-inactive'), sessionId: SessionId('factory-inactive-s'), })).rejects.toThrow('agent loop is not active') await ctx.fiber.dispose() @@ -583,7 +566,6 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { creating = inner.agents.create({ - agentId: AgentId('dependency-origin'), sessionId: SessionId('dependency-origin-s'), agentOptions: { model: 'mock' }, setup: (agentCtx) => { @@ -623,7 +605,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('session/created', (session) => { if (session.id !== SessionId('session-created-barrier-s')) return - const agent = ctx.agents.get(AgentId('session-created-barrier'))! + const agent = ctx.agents.get(SessionId('session-created-barrier-s'))! expect(ctx.sessions.get(session.id)).toBe(session) expect(agent.session).toBe(session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) @@ -638,7 +620,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-created-barrier'), sessionId: SessionId('session-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -652,7 +633,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('session-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -666,19 +647,19 @@ describe('agent scope lifecycle', () => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-created') }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return lifecycle.push('agent-created:dispose') disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/created', (agent) => { - if (agent.id !== AgentId('agent-created-barrier')) return + if (agent.id !== SessionId('agent-created-barrier-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { lifecycle.push('scope-disposed') }) lifecycle.push('agent-created:observer') }) ctx.on('agent/disposed', (agent) => { - if (agent.id === AgentId('agent-created-barrier')) lifecycle.push('agent-disposed') + if (agent.id === SessionId('agent-created-barrier-s')) lifecycle.push('agent-disposed') }) ctx.on('session/disposed', (session) => { if (session.id === SessionId('agent-created-barrier-s')) lifecycle.push('session-disposed') @@ -687,7 +668,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('agent-created-barrier'), sessionId: SessionId('agent-created-barrier-s'), agentOptions: { model: 'mock' }, }) @@ -703,7 +683,7 @@ describe('agent scope lifecycle', () => { 'session-disposed', 'scope-disposed', ]) - expect(ctx.agents.get(AgentId('agent-created-barrier'))).toBeUndefined() + expect(ctx.agents.get(SessionId('agent-created-barrier-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('agent-created-barrier-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -715,13 +695,12 @@ describe('agent scope lifecycle', () => { let creating!: ReturnType ctx.on('agent/session-start', agent => void starts.push(agent.id)) ctx.on('agent/created', (agent) => { - if (agent.id === AgentId('listener-dispose')) void ownerCtx.fiber.dispose() + if (agent.id === SessionId('listener-dispose-s')) void ownerCtx.fiber.dispose() }) const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('listener-dispose'), sessionId: SessionId('listener-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -730,7 +709,7 @@ describe('agent scope lifecycle', () => { await expect(creating).rejects.toThrow(/owner disposed during setup/) await owner.dispose() expect(starts).toEqual([]) - expect(ctx.agents.get(AgentId('listener-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('listener-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('listener-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -744,15 +723,15 @@ describe('agent scope lifecycle', () => { let scopeDisposed = false let observerSawLive = false ctx.on('agent/status', (agent, status) => { - if (agent.id === AgentId('session-start-dispose')) statuses.push(status) + if (agent.id === SessionId('session-start-dispose-s')) statuses.push(status) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return announced = agent as ReactLoopAgent disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/session-start', (agent) => { - if (agent.id !== AgentId('session-start-dispose')) return + if (agent.id !== SessionId('session-start-dispose-s')) return expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.sessions.get(agent.session.id)).toBe(agent.session) agent.ctx.effect(() => () => { scopeDisposed = true }) @@ -762,7 +741,6 @@ describe('agent scope lifecycle', () => { const owner = await ctx.plugin(Object.assign((inner: Context) => { ownerCtx = inner creating = inner.agents.create({ - agentId: AgentId('session-start-dispose'), sessionId: SessionId('session-start-dispose-s'), agentOptions: { model: 'mock' }, }) @@ -775,7 +753,7 @@ describe('agent scope lifecycle', () => { expect(observerSawLive).toBe(true) expect(scopeDisposed).toBe(true) expect(announced.session.events).toEqual([]) - expect(ctx.agents.get(AgentId('session-start-dispose'))).toBeUndefined() + expect(ctx.agents.get(SessionId('session-start-dispose-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('session-start-dispose-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -787,7 +765,6 @@ describe('agent scope lifecycle', () => { ctx.on('agent/created', () => void published.push('agent/created')) ctx.on('agent/session-start', () => void published.push('agent/session-start')) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, setup: async () => { @@ -798,13 +775,13 @@ describe('agent scope lifecycle', () => { // Nothing leaked: no agent, no session, and the ids are reusable. expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) await retry.dispose() }) - it('rejects an exotic durable seed before publishing either identity', async () => { + it('rejects an exotic durable seed before publishing either object', async () => { const ctx = await harness() const published: string[] = [] ctx.on('session/created', () => { published.push('session') }) @@ -817,17 +794,15 @@ describe('agent scope lifecycle', () => { }] as unknown as SessionEvent[] await expect(ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, seed, })).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/) expect(published).toEqual([]) - expect(ctx.agents.get(AgentId('exotic-seed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('exotic-seed-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('exotic-seed-session'))).toBeUndefined() const retry = await ctx.agents.create({ - agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), agentOptions: { model: 'mock' }, }) @@ -843,13 +818,13 @@ describe('agent scope lifecycle', () => { if (boom) { boom = false; throw new Error('boom created') } }) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, + sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, })).rejects.toThrow('boom created') - expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('bad-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge // The rollback also disposed the scope fiber: re-creating works cleanly. - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) expect(scopeOf(retry.agent.ctx)).toBe(retry.agent) await retry.dispose() }) @@ -866,18 +841,17 @@ describe('agent scope lifecycle', () => { ctx.on('agent/disposed', (agent) => { lifecycle.push(`agent-disposed:${agent.id}`) }) await expect(ctx.agents.create({ - agentId: AgentId('partial-agent'), sessionId: SessionId('partial-session'), agentOptions: { model: 'mock' }, })).rejects.toThrow('agent observer failed') expect(lifecycle).toEqual([ 'session-created:partial-session', - 'agent-created:partial-agent', - 'agent-disposed:partial-agent', + 'agent-created:partial-session', + 'agent-disposed:partial-session', 'session-disposed:partial-session', ]) - expect(ctx.agents.get(AgentId('partial-agent'))).toBeUndefined() + expect(ctx.agents.get(SessionId('partial-session'))).toBeUndefined() expect(ctx.sessions.get(SessionId('partial-session'))).toBeUndefined() }) @@ -892,23 +866,23 @@ describe('agent scope lifecycle', () => { } }) - expect(() => ctx.agentLoop.create(AgentId('config-bad'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(SessionId('config-bad'), { model: 'mock' })) .toThrow('config publish failed') - expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined() + expect(ctx.agents.get(SessionId('config-bad'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) }) it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) await handle.dispose() expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/) }) it('agentEvents fuses carrier and subject for custom drivers', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) + const other = ctx.agentLoop.create(SessionId('a2'), { model: 'mock' }) const heard: string[] = [] agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`)) @@ -921,7 +895,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const { agent } = handle @@ -930,7 +904,7 @@ describe('agent scope lifecycle', () => { if (event.type === 'turn/end') order.push('turn-end') }) ctx.on('agent/disposed', () => { - order.push(`disposed(listed=${ctx.agents.get(AgentId('o1')) !== undefined})`) + order.push(`disposed(listed=${ctx.agents.get(SessionId('o1-s')) !== undefined})`) order.push(`session-still-stored=${ctx.sessions.get(SessionId('o1-s')) !== undefined}`) }) @@ -955,7 +929,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) }, { inject: ['agents'] })) const teardownDone: string[] = [] @@ -967,23 +941,22 @@ describe('agent scope lifecycle', () => { // actually finished (the raw wrapper returns undefined on a repeat call). await handle.dispose() expect(teardownDone).toContain('unregistered') - expect(ctx.agents.get(AgentId('h1'))).toBeUndefined() + expect(ctx.agents.get(SessionId('h1-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('h1-s'))).toBeUndefined() await unload }) it('successful handle disposal retires its caller ownership effect', async () => { const ctx = await harness() - const agentId = AgentId('retired-owner-effect') + const sessionId = SessionId('retired-owner-effect') const handle = await ctx.agents.create({ - agentId, - sessionId: SessionId('retired-owner-effect-s'), + sessionId, agentOptions: { model: 'mock' }, }) - expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`) + expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${sessionId})`) await handle.dispose() - expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${agentId})`)).toEqual([]) + expect(ctx.fiber.getEffects().filter(effect => effect.label === `agentLoop.owner(${sessionId})`)).toEqual([]) await ctx.fiber.dispose() }) @@ -994,7 +967,6 @@ describe('agent scope lifecycle', () => { let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { handle = await inner.agents.create({ - agentId: AgentId('manual-first'), sessionId: SessionId('manual-first-s'), agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1014,7 +986,7 @@ describe('agent scope lifecycle', () => { expect(ownerSettled).toBe(false) gate.resolve(undefined) await Promise.all([disposing, unloading]) - expect(ctx.agents.get(AgentId('manual-first'))).toBeUndefined() + expect(ctx.agents.get(SessionId('manual-first-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('manual-first-s'))).toBeUndefined() await ctx.fiber.dispose() }) @@ -1024,13 +996,11 @@ describe('agent scope lifecycle', () => { const gate = Promise.withResolvers() const cleanupStarted = Promise.withResolvers() const sessionDisposed = Promise.withResolvers() - const agentId = AgentId('quiescent-reuse') - const sessionId = SessionId('quiescent-reuse-s') + const sessionId = SessionId('quiescent-reuse') ctx.on('session/disposed', (session) => { if (session.id === sessionId) sessionDisposed.resolve(undefined) }) const first = await ctx.agents.create({ - agentId, sessionId, agentOptions: { model: 'mock' }, setup(agentCtx) { @@ -1043,10 +1013,10 @@ describe('agent scope lifecycle', () => { const disposing = first.dispose() await Promise.all([sessionDisposed.promise, cleanupStarted.promise]) - expect(ctx.agents.get(agentId)).toBeUndefined() + expect(ctx.agents.get(sessionId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { model: 'mock' } }) - expect(ctx.agents.get(agentId)).toBe(replacement.agent) + const replacement = await ctx.agents.create({ sessionId, agentOptions: { model: 'mock' } }) + expect(ctx.agents.get(sessionId)).toBe(replacement.agent) expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session) gate.resolve(undefined) @@ -1058,7 +1028,6 @@ describe('agent scope lifecycle', () => { it('handle.dispose() awaits an idle-injection flush before unregistering or detaching', async () => { const ctx = await harness() const handle = await ctx.agents.create({ - agentId: AgentId('idle-flush'), sessionId: SessionId('idle-flush-s'), agentOptions: { model: 'mock' }, }) @@ -1077,12 +1046,12 @@ describe('agent scope lifecycle', () => { const disposal = handle.dispose().then(() => { disposed = true }) await new Promise(resolve => setTimeout(resolve, 0)) expect(disposed).toBe(false) - expect(ctx.agents.get(AgentId('idle-flush'))).toBe(handle.agent) + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBe(handle.agent) expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBe(handle.agent.session) gate.resolve(undefined) await disposal - expect(ctx.agents.get(AgentId('idle-flush'))).toBeUndefined() + expect(ctx.agents.get(SessionId('idle-flush-s'))).toBeUndefined() expect(ctx.sessions.get(SessionId('idle-flush-s'))).toBeUndefined() }) }) diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index d9b0a87e1d..1085f01a4c 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -10,11 +10,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { foldRequestHeader } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -57,7 +58,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter, toolOrder) for (const name of registrationOrder) registerNamed(ctx, name) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } @@ -103,7 +104,7 @@ describe('loop-level canonical tool order', () => { registerNamed(ctx, 'alpha') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c275fee88c..c7823a2aa5 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type TurnEndReason } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type ContinuationStop } from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -45,7 +46,7 @@ describe('agent/turn-stop', () => { textResponse('must not be requested'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let steered = false @@ -72,7 +73,7 @@ describe('agent/turn-stop', () => { textResponse('must not become a late-steering turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-steering'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let injected = false @@ -98,7 +99,7 @@ describe('agent/turn-stop', () => { textResponse('queued follow-up answer'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('terminal-flush-send'), { model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let queued = false @@ -124,8 +125,8 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const stopped = ctx.agentLoop.create(AgentId('stopped'), { model: 'mock' }) - const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { model: 'mock' }) + const stopped = ctx.agentLoop.create(SessionId('stopped'), { model: 'mock' }) + const ordinary = ctx.agentLoop.create(SessionId('ordinary'), { model: 'mock' }) stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(stopped) @@ -145,7 +146,7 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('owned-listener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('owned-listener'), { model: 'mock' }) const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(agent, 'first turn') @@ -162,7 +163,7 @@ describe('agent/turn-stop', () => { textResponse('healthy later turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('bad-policy'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('bad-policy'), { model: 'mock' }) const reasons: TurnEndReason[] = [] const errors: string[] = [] ctx.on('session/event', (session, event) => { diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 9ee324b0c3..4eddb050d5 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -12,7 +12,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. -- `ctx.agents.get(id: AgentId): Agent | undefined` +- `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index edb7f59a37..1306e8004d 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -9,7 +9,7 @@ import { Context, getTraceable, Service, symbols } from 'cordis' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' -import type { Agent, AgentId, AgentOptions } from './types.ts' +import type { Agent, AgentOptions } from './types.ts' export * from './types.ts' export { agentEvents, assembleContextFor } from './dispatch.ts' @@ -33,15 +33,13 @@ declare module 'cordis' { /** * Options for programmatically creating an agent through the registry factory - * ({@link AgentRegistry.create}). The caller supplies the live `sessionId` - * (e.g. an ACP-generated id) and optional session metadata (the validated - * `cwd`, fork lineage); the factory creates the session, the agent, and wires - * them together. + * ({@link AgentRegistry.create}). The caller supplies the single live + * `sessionId` shared by the agent registry and session log (e.g. an + * ACP-generated id), plus optional session metadata (the validated `cwd`, fork + * lineage); the factory creates the session and agent under that identity. */ export interface CreateAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The live session's id (NOT derived from agentId). */ + /** The live agent/session identity. */ readonly sessionId: SessionId /** * Session creation metadata: validated absolute `cwd`, `parentSession` @@ -93,9 +91,7 @@ export interface CreateAgentOptions { * ({@link AgentRegistry.resume}). */ export interface ResumeAgentOptions { - /** The agent's id (the registry handle). */ - readonly agentId: AgentId - /** The persisted session id to load and resume on. */ + /** The persisted session id to load and use as the live agent/session identity. */ readonly resumeSessionId: SessionId /** Per-agent options (model, …). */ readonly agentOptions?: AgentOptions @@ -180,7 +176,7 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug /** All mutable lifecycle state for one exact registry entry. */ interface AgentEntry { - readonly id: AgentId + readonly id: SessionId readonly agent: Agent readonly carrier: Scoped announced: boolean @@ -201,7 +197,7 @@ interface FactorySlot { * {@link setFactory}. */ export class AgentRegistry extends Service { - private store = new Map() + private store = new Map() private factory: FactorySlot | undefined constructor(ctx: Context) { @@ -257,7 +253,7 @@ export class AgentRegistry extends Service { * agent): this constructs the agent and its session. Rejects if no factory is * registered or creation/setup fails. The resolved {@link AgentHandle} lets * the owner tear down exactly this agent. - * @param options - agent id, session id/seed/metadata, and agent options. + * @param options - shared identity, session seed/metadata, and agent options. * @returns the handle after setup, rollback-covered publication, and loop start complete. */ async create(options: CreateAgentOptions): Promise { @@ -428,10 +424,10 @@ export class AgentRegistry extends Service { /** * Look up a live agent. - * @param id - the agent id to look up. + * @param id - the shared agent/session id to look up. * @returns the agent, or undefined when no live agent has that id. */ - get(id: AgentId): Agent | undefined { + get(id: SessionId): Agent | undefined { return this.store.get(id)?.agent } diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index a990f0d67d..b0fb78ad66 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -32,7 +32,7 @@ * event. A turn/step boundary is a durable fact: it lives in the session log * and is read off the `session/event` feed — it is NOT mirrored as an `agent/*` * emit. A consumer that needs the `Agent` handle (or its short id) at a boundary - * keeps a session-id→agent map from `agent/created`/`agent/disposed`. + * looks up the agent directly by the event's session id. * See `docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md` * and `docs/rfc/implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md`. * @@ -45,25 +45,12 @@ * @module @deepseek-ai/dsh-agent/types */ -import type { Branded } from '@deepseek-ai/dsh-brand' import type { Context } from 'cordis' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { ContentBlock, LlmCallConfig, Message, MessageSource } from '@deepseek-ai/dsh-llm' +import type { Session, SessionId } from '@deepseek-ai/dsh-session' import type {} from '@deepseek-ai/dsh-system-prompt' -/** Identifies one live agent in the registry. */ -export type AgentId = Branded<'AgentId'> - -/** - * Brand a string as an {@link AgentId}. - * @param id - the raw agent id string. - * @returns the same string, branded (a compile-time cast — no runtime cost). - */ -export function AgentId(id: string): AgentId { - return id as AgentId -} -import type { Session } from '@deepseek-ai/dsh-session' - declare module '@deepseek-ai/dsh-system-prompt' { interface AssembleContext { /** @@ -186,7 +173,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' * package should depend on the implementation. */ export interface Agent { - readonly id: AgentId + /** The single identity shared with {@link session}. */ + readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5d541d56a8..cba833b212 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -2,11 +2,12 @@ import { describe, expect, expectTypeOf, it } from 'vitest' import { Context, Service, symbols } from 'cordis' import type { Events } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId, agentEvents } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent' + import type { Agent, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent' function stubAgent(rawId: string): Agent { - const id = AgentId(rawId) + const id = SessionId(rawId) return { id, options: {}, @@ -57,7 +58,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) expect(() => ctx.agents.register(stubAgent('vetoed'))).toThrow('creation veto') - expect(ctx.agents.get(AgentId('vetoed'))).toBeUndefined() + expect(ctx.agents.get(SessionId('vetoed'))).toBeUndefined() expect(lifecycle).toEqual(['created:vetoed', 'disposed:vetoed']) }) @@ -158,11 +159,11 @@ describe('AgentRegistry factory seam', () => { const factory: AgentFactory = { async createAgent(ownerCtx, options) { calls.create.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } }, async resume(ownerCtx, options) { calls.resume.push({ ownerCtx, options }) - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } }, } return { factory, calls } @@ -171,15 +172,15 @@ describe('AgentRegistry factory seam', () => { it('requires a factory and delegates through the calling context', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) - await expect(ctx.agents.create({ agentId: AgentId('a'), sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('s') })).rejects.toThrow(/no agent factory/) const { factory, calls } = stubFactory() ctx.agents.setFactory(factory) let callerFiber: Context['fiber'] | undefined await ctx.plugin(Object.assign(async (inner: Context) => { callerFiber = inner.fiber - await inner.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await inner.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await inner.agents.create({ sessionId: SessionId('create-s') }) + await inner.agents.resume({ resumeSessionId: SessionId('resume-s') }) }, { inject: ['agents'] })) expect(calls.create[0]?.ownerCtx.fiber).toBe(callerFiber) expect(calls.resume[0]?.ownerCtx.fiber).toBe(callerFiber) @@ -192,9 +193,9 @@ describe('AgentRegistry factory seam', () => { inner.agents.setFactory(stubFactory().factory) expect(() => inner.agents.setFactory(stubFactory().factory)).toThrow(/already registered/) }, { inject: ['agents'] })) - await expect(ctx.agents.create({ agentId: AgentId('before'), sessionId: SessionId('before-s') })).resolves.toBeDefined() + await expect(ctx.agents.create({ sessionId: SessionId('before-s') })).resolves.toBeDefined() await owner.dispose() - await expect(ctx.agents.create({ agentId: AgentId('after'), sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) + await expect(ctx.agents.create({ sessionId: SessionId('after-s') })).rejects.toThrow(/no agent factory/) }) it('canonicalizes an already traced Service before tracing it for the caller', async () => { @@ -214,18 +215,18 @@ describe('AgentRegistry factory seam', () => { } async createAgent(_ownerCtx: Context, options: CreateAgentOptions) { this.calls().push('create') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.sessionId), dispose: () => Promise.resolve() } } async resume(_ownerCtx: Context, options: ResumeAgentOptions) { this.calls().push('resume') - return { agent: stubAgent(options.agentId), dispose: () => Promise.resolve() } + return { agent: stubAgent(options.resumeSessionId), dispose: () => Promise.resolve() } } } await ctx.plugin(TracedFactory) const traced = (ctx as Context & { tracedFactory: TracedFactory }).tracedFactory ctx.agents.setFactory(traced) - await ctx.agents.create({ agentId: AgentId('create'), sessionId: SessionId('create-s') }) - await ctx.agents.resume({ agentId: AgentId('resume'), resumeSessionId: SessionId('resume-s') }) + await ctx.agents.create({ sessionId: SessionId('create-s') }) + await ctx.agents.resume({ resumeSessionId: SessionId('resume-s') }) const raw = (traced as unknown as { [symbols.original]?: TracedFactory })[symbols.original] expect(states.get(raw!)).toEqual(['create', 'resume']) }) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index 06669ca85c..cb6e1304c3 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -288,7 +288,12 @@ export class Session { */ readonly header: SessionHeader - constructor(public readonly id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { + /** The session identity, derived from its durable header's single copy. */ + get id(): SessionId { + return this.header.id + } + + constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader) { if (seed) { // Validate the seed to the SAME invariants `append` enforces, so a // replay/fork (`ctx.sessions.create(id, { seed })`) cannot construct a diff --git a/packages/core/tools/tests/code-mode.spec.ts b/packages/core/tools/tests/code-mode.spec.ts index f9d84aadbf..2339657ec8 100644 --- a/packages/core/tools/tests/code-mode.spec.ts +++ b/packages/core/tools/tests/code-mode.spec.ts @@ -8,7 +8,6 @@ import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime' import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime' import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools' import type { Config, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEventMap } from '@deepseek-ai/dsh-session' @@ -59,7 +58,7 @@ async function setup(options: SetupOptions = {}) { /** Mint one production-shaped agent scope that can register scoped tool policy. */ async function mintAgentScope(ctx: Context, name = 'scoped'): Promise<{ scope: Scope; agent: Agent }> { - const agent = { id: AgentId(name) } as Agent + const agent = { id: SessionId(name) } as Agent let scope!: Scope await ctx.plugin(Object.assign((inner: Context) => { scope = createScope(inner, agent) }, { inject: ['tools', 'systemPrompt'] })) diff --git a/packages/core/tools/tests/scoped.spec.ts b/packages/core/tools/tests/scoped.spec.ts index 6599112c2a..8b8e1cfead 100644 --- a/packages/core/tools/tests/scoped.spec.ts +++ b/packages/core/tools/tests/scoped.spec.ts @@ -6,9 +6,11 @@ import type { Scope } from '@deepseek-ai/dsh-scope' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { PreToolDecision, ToolDefinition, ToolExecution, ToolExecutionInput, ToolExecutionToken } from '@deepseek-ai/dsh-tools' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' + import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Mount the registry (with its systemPrompt dependency) on a fresh context. */ async function mount(): Promise { @@ -20,7 +22,7 @@ async function mount(): Promise { /** Mint a scope whose key doubles as a minimal Agent-like object. */ async function mintAgentScope(ctx: Context, name: string): Promise<{ scope: Scope; key: Agent }> { - const key = { id: name as AgentId } as Agent + const key = { id: name as SessionId } as Agent let scope!: Scope // The scoped context resolves services through the MINTING plugin's // dependency chain — the minter must inject what scope holders will reach @@ -62,7 +64,7 @@ describe('scoped tool registration', () => { it('files a scoped tool in its layer: visible/executable for that scope only', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('shared')) scope.ctx.tools.register(tool('mine')) @@ -195,7 +197,7 @@ describe('scoped execution dispatch', () => { it('an agent.ctx pre-execute listener gates only its own agent (and never subject-less calls)', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent ctx.tools.register(tool('t')) const seen: (string | undefined)[] = [] @@ -213,7 +215,7 @@ describe('scoped execution dispatch', () => { it('applies scoped guards after pre-execute and unwinds duplicate registrations independently', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'a') - const other = { id: 'other' as AgentId } as Agent + const other = { id: 'other' as SessionId } as Agent let bodyCalls = 0 ctx.tools.register({ ...tool('t'), @@ -428,7 +430,7 @@ describe('scoped execution dispatch', () => { it('uses one input snapshot for the normalized error shell', async () => { const ctx = await mount() const { scope, key } = await mintAgentScope(ctx, 'accepted') - const driftAgent = { id: 'drift' as AgentId } as Agent + const driftAgent = { id: 'drift' as SessionId } as Agent ctx.tools.register(tool('parent')) ctx.tools.register(tool('t')) let parent!: ToolExecutionToken diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index a270e7c6d8..dca48d65ab 100644 --- a/packages/fs/tool-fs/tests/fs-tools.e2e.ts +++ b/packages/fs/tool-fs/tests/fs-tools.e2e.ts @@ -3,7 +3,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { fsHarness, waitForIdle } from './harness.ts' @@ -35,7 +34,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => ctx = await fsHarness(workdir, SYSTEM) // agentLoop.create prepares a session with no cwd, so the provider default // (config.cwd = workdir) is the workspace. - const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(SessionId('fs-e2e'), { model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Create a file named note.txt containing exactly the line: status: draft. ' @@ -65,7 +64,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => try { ctx = await fsHarness(configDir, SYSTEM) const handle = await ctx.agents.create({ - agentId: AgentId('fs-e2e-cwd'), sessionId: SessionId(`fs-e2e-cwd-${Date.now()}`), meta: { cwd: sessionDir }, agentOptions: { model: 'deepseek-v4-flash' }, diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index dc385bc033..e46f113301 100644 --- a/packages/guard/repeat-tool-guard/README.md +++ b/packages/guard/repeat-tool-guard/README.md @@ -24,8 +24,8 @@ The chain key is `(tool name, canonical arguments)` — canonicalization is a de - **Untracked calls are transparent to the chain.** A call excluded by `include`/`exclude` neither increments nor resets the counter, so `grep X → todo_write → grep X` still counts as two consecutive `grep X` when `todo_write` is excluded. This is what makes exclusion useful: bookkeeping tools interleaved into a loop must not launder it. - **Denied calls count.** Detection sits on `tools/post-execute`, which also runs for calls a `tools/pre-execute` listener denied — a model hammering a denied call is exactly the loop worth breaking. -- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no `AgentId` to key on. -- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so chains are keyed by `AgentId`; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain; agent disposal drops its state. +- **Calls without an agent are ignored.** A direct `ctx.tools.execute()` caller has no model to remind and no live agent object to key on. +- **Per-agent keying.** The tool registry is context-level and subagents interleave through the same waterfall, so a `WeakMap` keys each chain by the live agent object; one agent's repetition never trips another's reminder. A user prompt (`agent/prompt-submit`) resets the submitting agent's chain, and object lifetime bounds the weak entry without a disposal listener. - **In-memory only.** A session resumed from persistence starts with a fresh chain — the guard is a heuristic nudge, not a logged invariant, later reminders are the accepted cost. ## Reminder delivery diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index 6a5662d693..d51df1d829 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -22,7 +22,7 @@ * exclude: [todo_write] # tool-name patterns transparent to the chain * ``` * - * Chain state is keyed per {@link AgentId} — the tool registry is a + * Chain state is keyed by the live agent object — the tool registry is a * context-level singleton whose waterfalls interleave every agent's calls, so * a shared counter would let one agent's repetition trip another's reminder. * State is in-memory only: a session resumed from persistence starts with a @@ -37,7 +37,7 @@ import type { Context } from 'cordis' import z from 'schemastery' -import type { AgentId, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' +import type { Agent, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { MessageSource } from '@deepseek-ai/dsh-llm' import type { PostToolDecision, ToolExecution } from '@deepseek-ai/dsh-tools' @@ -202,9 +202,7 @@ export function apply(ctx: Context, config: Config): void { throw new Error(`repeat-tool-guard: invalid argumentsPreviewChars ${argumentsPreviewChars} — must be an integer >= 1`) } - // TODO(agent-keyed-repeat-chain): key a WeakMap by the Agent itself; that - // removes the disposal-only status listener and cannot collide on id reuse. - const chains = new Map() + const chains = new WeakMap() /** Whether a tool participates in the chain (untracked calls are transparent: they neither count nor reset). */ function tracked(toolName: string): boolean { @@ -227,9 +225,9 @@ export function apply(ctx: Context, config: Config): void { if (!tracked(exec.name)) return undefined const canonical = canonicalize(exec.arguments) const key = JSON.stringify([exec.name, canonical]) - const chain = chains.get(exec.agent.id) + const chain = chains.get(exec.agent) const count = chain !== undefined && chain.key === key ? chain.count + 1 : 1 - chains.set(exec.agent.id, { key, count }) + chains.set(exec.agent, { key, count }) if (!thresholdSet.has(count)) return undefined const text = count === thresholds[0] ? GENTLE_REMINDER @@ -259,12 +257,7 @@ export function apply(ctx: Context, config: Config): void { // loop. Pure reset hook: always delegates (attaching nothing, vetoing // nothing). ctx.on('agent/prompt-submit', (agent, _content, _source, next): Promise => { - chains.delete(agent.id) + chains.delete(agent) return next() }) - - // Drop state when an agent goes away, bounding the map over harness lifetime. - ctx.on('agent/status', (agent, status) => { - if (status === 'disposed') chains.delete(agent.id) - }) } diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..9538166fc4 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId } from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' @@ -57,7 +58,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -78,7 +79,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -100,7 +101,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -142,7 +143,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -163,7 +164,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -179,7 +180,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -195,7 +196,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -215,8 +216,8 @@ describe('chain semantics', () => { toolCallResponse('b3', 'probe', { q: 1 }), textResponse('done'), ])) - const agentA = ctx.agentLoop.create(AgentId('a'), { model: 'mock-a' }) - const agentB = ctx.agentLoop.create(AgentId('b'), { model: 'mock-b' }) + const agentA = ctx.agentLoop.create(SessionId('a'), { model: 'mock-a' }) + const agentB = ctx.agentLoop.create(SessionId('b'), { model: 'mock-b' }) agentA.send([{ type: 'text', text: 'go' }]) agentB.send([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) @@ -235,7 +236,7 @@ describe('chain semantics', () => { textResponse('turn two done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) agent.send([{ type: 'text', text: 'again' }]) @@ -256,14 +257,14 @@ describe('chain semantics', () => { // (the loop.spec pattern): a child plugin fiber owns `first`. let first!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - first = inner.agentLoop.create(AgentId('reused'), { model: 'mock' }) + first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() await first.done - const second = ctx.agentLoop.create(AgentId('reused'), { model: 'mock' }) + const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) @@ -279,7 +280,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -295,7 +296,7 @@ describe('chain semantics', () => { toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2 textResponse('done'), ])) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -317,7 +318,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -348,7 +349,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2cbc995ce3..2f0a2666c9 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context, type Fiber } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -95,7 +96,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) @@ -118,7 +119,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -143,7 +144,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) @@ -166,7 +167,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) @@ -188,7 +189,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -209,7 +210,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -233,7 +234,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -257,7 +258,7 @@ describe('hooks-claude bridge — SessionStart', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // session-start fires async (detached .then → agent.inject); wait for the // injected context/message to actually land before sending, rather than a // fixed sleep that flakes under load. @@ -294,8 +295,8 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => // Drive the observe-only lifecycle events directly (no real child needed — the // bridge just listens). No child agent is registered, so SubagentStart's // child lookup yields undefined and it simply runs the hook. - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) - ctx.emit('subagent/end', { provider: 'inproc', id: AgentId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) + ctx.emit('subagent/end', { provider: 'inproc', id: SessionId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) // Both hooks run async (detached .then); poll for their marker files rather // than a fixed sleep that flakes under load. @@ -330,7 +331,7 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.emit('subagent/start', { provider: 'inproc', id: AgentId('child-1') }) + ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await hooks.dispose() @@ -359,7 +360,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. @@ -385,7 +386,7 @@ describe('hooks-claude bridge — load resilience', () => { const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 7feb46df05..16c48aa149 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' @@ -72,7 +73,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) ctx.logger.warn = warn as never ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran @@ -88,7 +89,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war ctx.logger.warn = warn as never let sawArgs: unknown ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. @@ -104,7 +105,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ran')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The prompt proceeded unchanged; no context/message injected. @@ -134,7 +135,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -159,7 +160,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -175,7 +176,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -192,7 +193,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. @@ -208,9 +209,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: AgentId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-x') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) expect(injected).toContain('child guidance') }) @@ -224,9 +225,9 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: AgentId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: AgentId('child-y') }) + ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) @@ -240,7 +241,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -254,7 +255,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -270,7 +271,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: AgentId('child-z'), stopReason: 'completed' }) + ctx.emit('subagent/end', { provider: 'p', id: SessionId('child-z'), stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) }) @@ -283,7 +284,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') @@ -298,7 +299,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. @@ -313,7 +314,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -342,7 +343,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () // the protocol lib's reference default, not a config knob). HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) @@ -357,7 +358,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -372,7 +373,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -393,7 +394,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -410,7 +411,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -430,7 +431,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran @@ -448,7 +449,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) // NB: no projectDir // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' @@ -466,7 +467,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(path, adapter) // A later listener that blocks every prompt (registered AFTER the bridge). - const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') + const { SessionId: AId } = await import('@deepseek-ai/dsh-session') ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) @@ -492,7 +493,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) @@ -514,7 +515,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -533,7 +534,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -557,7 +558,7 @@ describe('hooks-claude coverage — executor reject + no-open-turn', () => { const bash = ctx.bash bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -573,7 +574,7 @@ describe('hooks-claude coverage — detached-listener catch handlers', () => { const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Make inject throw, forcing the SessionStart .catch path. const original = agent.inject.bind(agent) let threw = false @@ -613,7 +614,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) @@ -649,7 +650,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') - const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) + const childHandle = await ctx.agents.create({ sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) @@ -670,7 +671,7 @@ describe('hooks-claude coverage — systemMessage is warned, not surfaced', () = const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) @@ -691,7 +692,7 @@ describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait) const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // Send immediately — do NOT wait for the session-start inject. agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index e0677306b0..4aa678c36e 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -5,10 +5,11 @@ import { join } from 'node:path' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -82,7 +83,7 @@ describe('hooks-codex bridge', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) @@ -107,7 +108,7 @@ describe('hooks-codex bridge', () => { // Step 1 has no tool calls → would stop; the Stop hook forces step 2. const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +125,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // Ran normally; the unknown event was dropped at parse. @@ -135,7 +136,7 @@ describe('hooks-codex bridge', () => { const dir = configDir() // no hooks.json written const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -161,7 +162,7 @@ describe('hooks-codex bridge', () => { const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -190,7 +191,7 @@ describe('hooks-codex bridge', () => { ctx.llm.registerAdapter(['mock'], new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) // fires agent/session-start + ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) // fires agent/session-start await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await fiber.dispose() diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 774b308fa1..75b04d4c57 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -4,10 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' @@ -52,7 +53,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) const te = events(agent).findLast(e => e.type === 'turn/end') @@ -64,7 +65,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -78,7 +79,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(events(agent).some(e => e.type === 'user/message')).toBe(false) @@ -96,7 +97,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') @@ -111,7 +112,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) @@ -125,7 +126,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) @@ -138,7 +139,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -151,7 +152,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -164,7 +165,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) }) @@ -176,7 +177,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -187,7 +188,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) @@ -200,7 +201,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) @@ -223,7 +224,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') @@ -246,7 +247,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) @@ -259,7 +260,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -273,7 +274,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the clean no-output hook has finished agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message')).toBe(false) @@ -285,7 +286,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.inject = (() => { throw new Error('inject boom') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) @@ -298,7 +299,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -311,7 +312,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) @@ -327,7 +328,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded @@ -340,7 +341,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) @@ -352,7 +353,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -369,7 +370,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } expect(payload.tool_input.command).toBe('') @@ -405,7 +406,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) @@ -419,7 +420,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') @@ -432,7 +433,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') }) @@ -448,7 +449,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => existsSync(marker)) // the exit-2 hook has finished expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) @@ -462,7 +463,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') @@ -473,7 +474,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -487,7 +488,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -502,7 +503,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } expect(payload.tool_name).toBe('shell') @@ -518,7 +519,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(false) // the matcher fired → the hook denied the tool expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) @@ -530,7 +531,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('a1'), { model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') @@ -553,7 +554,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { ctx.llm.registerAdapter(['mock'], adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(existsSync(marker)).toBe(true) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 5222906a2d..1e82ef85b0 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -37,8 +37,8 @@ import { type SessionNotification, type StopReason, } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentResult, SubagentRun, SubagentStartRequest, SubagentStopReason } from '@deepseek-ai/dsh-subagent' import { buildChildEnv, disposeChildProcess, spawnFailure } from '@deepseek-ai/dsh-subagent-subprocess' @@ -190,7 +190,7 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = AgentId(randomUUID()) + const id = SessionId(randomUUID()) if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') diff --git a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts index 8060a77fd4..d1b9065c60 100644 --- a/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts +++ b/packages/subagent/subagent-fork/tests/multi-subagent.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(Spawn, { providerName: 'spawn' }) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index e089cebe5f..360098e369 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -2,10 +2,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' @@ -43,7 +44,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(fork, { providerName: 'fork' }) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index f6de7200cf..965d9c8e78 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -9,7 +9,7 @@ import { randomUUID } from 'node:crypto' import type { Context } from 'cordis' -import { AgentId, type Agent, type AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertSubagentMaxDepth } from '@deepseek-ai/dsh-subagent' @@ -104,7 +104,7 @@ export async function startInProcessRun( throw new SubagentDepthError(childDepth, request.maxDepth) } - const childId = AgentId(randomUUID()) + const childId = SessionId(randomUUID()) const seedLength = options.seed?.length ?? 0 const parentHeader = parent.session.header const parentModel = parent.options.model @@ -127,8 +127,7 @@ export async function startInProcessRun( const flags = { cancelled: false } const handle = await parent.ctx.agents.create({ - agentId: childId, - sessionId: SessionId(randomUUID()), + sessionId: childId, meta: { ...parentHeader.cwd !== undefined ? { cwd: parentHeader.cwd } : {}, parentSession: parentHeader.id, diff --git a/packages/subagent/subagent-inprocess/tests/structured.spec.ts b/packages/subagent/subagent-inprocess/tests/structured.spec.ts index 3e23123622..93da5b1d51 100644 --- a/packages/subagent/subagent-inprocess/tests/structured.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/structured.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, type ContentBlock, type GenerateOptions } from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import type { ContinuationDecision } from '@deepseek-ai/dsh-agent' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -68,7 +69,7 @@ async function setup(script: Script, options: SetupOptions = {}) { start: (request: SubagentStartRequest) => startInProcessRun(request, {}), }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter, disposeProvider } } @@ -333,7 +334,7 @@ describe('in-process structured output', () => { await expect(ctx.subagents.start('spawn', structuredRequest(parent, { outputSchema: { type: 'object', oneOf: [] } as unknown as StructuredOutputSchema, }))).rejects.toThrow(/unsupported output schema/) - expect(ctx.agents.get(AgentId('parent'))).toBeDefined() + expect(ctx.agents.get(SessionId('parent'))).toBeDefined() }) it('a schema carrying non-JSON values fails as OutputSchemaError at the validation boundary', async () => { diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..aa0f946c89 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -24,7 +25,7 @@ async function setup(script: Script) { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts index daa032199e..b156f951ed 100644 --- a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts +++ b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts @@ -3,8 +3,8 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import { spawnHarness, waitForIdle } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * With-key smoke for the in-process spawn backend: a REAL parent agent delegates @@ -29,7 +29,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', ( it('a parent delegates to a child that writes a file on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-subagent-spawn-e2e-')) ctx = await spawnHarness(workdir) - const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { model: 'deepseek-v4-flash' }) + const parent = ctx.agentLoop.create(SessionId('e2e-parent'), { model: 'deepseek-v4-flash' }) parent.send([{ type: 'text', text: 'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text ' diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 9e4e489882..06aa40ca9f 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -5,7 +5,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -36,7 +37,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -237,7 +238,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('x')]) // A parent WITH a cwd (config agents have none, so create one explicitly). const parentHandle = await ctx.agents.create({ - agentId: AgentId('cwd-parent'), sessionId: SessionId('cwd-parent-session'), meta: { cwd: '/tmp/parent-workspace' }, agentOptions: { model: 'mock' }, @@ -254,7 +254,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([textResponse('explicit model child')]) // A parent with NO model (its own turns would need one supplied per-request). const parentHandle = await ctx.agents.create({ - agentId: AgentId('modelless-parent'), sessionId: SessionId('modelless-parent-session'), agentOptions: {}, }) @@ -318,7 +317,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const controller = new AbortController() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'q' }], @@ -349,7 +348,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) const parentEffects = parent.ctx.fiber.getEffects().length const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) @@ -442,7 +441,6 @@ describe('dsh-subagent-spawn', () => { const { ctx } = await setup([]) // A handle-owned parent we can dispose (config agents dispose with the loop fiber). const parentHandle = await ctx.agents.create({ - agentId: AgentId('doomed-parent'), sessionId: SessionId('doomed-s'), agentOptions: { model: 'mock' }, }) @@ -465,7 +463,6 @@ describe('dsh-subagent-spawn', () => { it('parent disposal during the child setup transaction prevents every publication notification', async () => { const { ctx } = await setup([]) const parentHandle = await ctx.agents.create({ - agentId: AgentId('setup-race-parent'), sessionId: SessionId('setup-race-parent-session'), agentOptions: { model: 'mock' }, }) diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 4635de9697..e885c16469 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -18,7 +18,8 @@ import type { Scoped } from '@deepseek-ai/dsh-scope' import { assertSupportedOutputSchema } from '@deepseek-ai/dsh-tools' import { HarnessError } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -96,7 +97,7 @@ export interface SubagentRunInfo { /** The provider that established the run. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId } /** Observe-only outcome detail for a settled subagent run. */ @@ -104,7 +105,7 @@ export interface SubagentRunEndInfo { /** The provider that ran it. */ readonly provider: string /** The child agent's id. */ - readonly id: AgentId + readonly id: SessionId /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] /** The child's final assistant output, absent on infrastructure rejection. */ diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 3bdc78569a..8d360b1182 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -6,8 +6,9 @@ * @module @deepseek-ai/dsh-subagent/types */ -import type { Agent, AgentId, AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { SessionId } from '@deepseek-ai/dsh-session' import type { StructuredOutputSchema, ToolRestriction } from '@deepseek-ai/dsh-tools' /** @@ -147,7 +148,7 @@ export interface SubagentResult { */ export interface SubagentRun { /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ - readonly id: AgentId + readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport diff --git a/packages/subagent/subagent/tests/service.spec.ts b/packages/subagent/subagent/tests/service.spec.ts index 3d10b425ed..ad7dbaafff 100644 --- a/packages/subagent/subagent/tests/service.spec.ts +++ b/packages/subagent/subagent/tests/service.spec.ts @@ -1,6 +1,7 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import { HarnessError } from '@deepseek-ai/dsh-llm' import { carrierKeyOf } from '@deepseek-ai/dsh-scope' import SubagentService, { @@ -12,9 +13,10 @@ import SubagentService, { type SubagentRun, type SubagentStartRequest, } from '@deepseek-ai/dsh-subagent' +import { SessionId } from '@deepseek-ai/dsh-session' function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } const ALL_CAPS: SubagentCapabilities = { outputSchema: true, depthLimit: true, toolFilter: true, persona: true } @@ -45,7 +47,7 @@ class StubProvider implements SubagentProvider { async start(request: SubagentStartRequest): Promise { this.startCount += 1 return { - id: AgentId(`child:${this.name}:${request.parent.id}`), + id: SessionId(`child:${this.name}:${request.parent.id}`), result: Promise.resolve(this.outcome), async dispose() {}, } @@ -141,7 +143,7 @@ describe('SubagentService', () => { const starting = subagents.start('deferred', baseRequest({ parent })) await Promise.resolve() expect(events).toEqual([]) - ready.resolve({ id: AgentId('child'), result: result.promise, async dispose() {} }) + ready.resolve({ id: SessionId('child'), result: result.promise, async dispose() {} }) const run = await starting expect(events).toEqual(['start']) result.resolve({ output: [{ type: 'text', text: 'answer' }], stopReason: 'completed' }) @@ -190,7 +192,7 @@ describe('SubagentService', () => { capabilities: NO_CAPS, inheritsParentContext: false, async start() { - return { id: AgentId('infra-child'), result: failure.promise, async dispose() {} } + return { id: SessionId('infra-child'), result: failure.promise, async dispose() {} } }, }) const failedRun = await subagents.start('infra', baseRequest()) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 5830513cf4..79df080657 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -4,10 +4,12 @@ import Loader from '@cordisjs/plugin-loader' import { CallId } from '@deepseek-ai/dsh-llm' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService from '@deepseek-ai/dsh-subagent' import * as mock from '@deepseek-ai/dsh-subagent-mock' import * as tool from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real @@ -20,7 +22,7 @@ import * as tool from '../src/index.ts' /** A minimal parent Agent — the tool reads `agent.id` for `parent`. */ function fakeAgent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } async function setup(toolConfig: tool.Config, mockConfig: Partial = {}) { @@ -114,7 +116,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('weird-child'), + id: SessionId('weird-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }), dispose: async () => {}, }), @@ -141,7 +143,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture-child'), + id: SessionId('capture-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -170,7 +172,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('bare-child'), + id: SessionId('bare-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -297,7 +299,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => void disposed(), }), @@ -319,7 +321,7 @@ describe('dsh-tool-subagent', () => { capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('spy-child'), + id: SessionId('spy-child'), result: Promise.resolve({ output: [], stopReason: 'error' as const }), dispose: async () => void disposed(), }), @@ -350,7 +352,7 @@ describe('dsh-tool-subagent', () => { resolveResult({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('spy-child'), + id: SessionId('spy-child'), result, dispose: async () => {}, } @@ -442,7 +444,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture2-child'), + id: SessionId('capture2-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -499,7 +501,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture3-child'), + id: SessionId('capture3-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -528,7 +530,7 @@ describe('dsh-tool-subagent', () => { start: async (request) => { seen = request return { - id: AgentId('capture4-child'), + id: SessionId('capture4-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index abc1a6c5e9..bf7bcbe2fb 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -13,8 +13,8 @@ import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import type { SubagentCapabilities, SubagentProvider, @@ -65,7 +65,7 @@ class MockSubagentProvider implements SubagentProvider { // A deterministic child id derived from the parent — no clock/random (both // banned in deterministic paths here, and unnecessary for a scripted run). - const id = AgentId(`mock-subagent:${this.name}:${request.parent.id}`) + const id = SessionId(`mock-subagent:${this.name}:${request.parent.id}`) const resultFor = (): SubagentResult => ({ output, diff --git a/packages/support/subagent-mock/tests/subagent-mock.spec.ts b/packages/support/subagent-mock/tests/subagent-mock.spec.ts index 7fd93c62bc..b5e7180782 100644 --- a/packages/support/subagent-mock/tests/subagent-mock.spec.ts +++ b/packages/support/subagent-mock/tests/subagent-mock.spec.ts @@ -1,13 +1,15 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import * as mock from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent — the mock provider only reads `parent.id`. */ function fakeParent(id = 'parent-1'): Agent { - return { id: AgentId(id) } as unknown as Agent + return { id: SessionId(id) } as unknown as Agent } function baseRequest(over: Partial = {}): SubagentStartRequest { diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..8376a70425 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -1,11 +1,12 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -64,7 +65,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Plan recorded.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) @@ -92,7 +93,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Done planning.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(SessionId('it-todo-2'), { model: 'mock' }) agent.send([{ type: 'text', text: 'plan then update' }]) await waitForIdle(ctx, agent) diff --git a/packages/todo/tool-todo/tests/tool-todo.spec.ts b/packages/todo/tool-todo/tests/tool-todo.spec.ts index 86e8814633..b426b6760c 100644 --- a/packages/todo/tool-todo/tests/tool-todo.spec.ts +++ b/packages/todo/tool-todo/tests/tool-todo.spec.ts @@ -6,7 +6,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { TodoItem } from '@deepseek-ai/dsh-session' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import * as tool from '../src/index.ts' /** @@ -20,7 +21,7 @@ import * as tool from '../src/index.ts' /** A parent Agent backed by a real Session — the tool reads `agent.session`. */ function agentWithSession(id = 'parent-1'): Agent & { session: Session } { const session = new Session(SessionId(id)) - return { id: AgentId(id), session } as unknown as Agent & { session: Session } + return { id: SessionId(id), session } as unknown as Agent & { session: Session } } async function setup(): Promise { diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index a3fdc38f97..e795c7e177 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -72,7 +72,6 @@ import { import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { assertNever, CallId } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-bash' import { APPROVAL_POLICIES, effectiveApprovalPolicy, setApprovalPolicy } from '@deepseek-ai/dsh-user-approval' @@ -686,7 +685,6 @@ export function apply(ctx: Context, config: AcpConfig): void { validateMcpServers(params) const sessionId = SessionId(randomUUID()) const handle = await agents.create({ - agentId: AgentId(sessionId), sessionId, meta: { cwd: params.cwd }, agentOptions: agentOptions(config), @@ -757,7 +755,6 @@ export function apply(ctx: Context, config: AcpConfig): void { } } const handle = await agents.resume({ - agentId: AgentId(sessionId), resumeSessionId: sessionId, agentOptions: agentOptions(config), }) diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index ed035aaf80..36846ac728 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -4,9 +4,11 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { CallId } from '@deepseek-ai/dsh-llm' -import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent } from '@deepseek-ai/dsh-agent' + import ApprovalService, { type ApprovalRequest } from '@deepseek-ai/dsh-user-approval' import { makeBridgeHarness, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * The bridge's `approval/request` answerer: an ask for an agent the bridge @@ -31,7 +33,7 @@ describe('acp bridge — approval answerer', () => { ): Promise<{ agent: Agent; request: ApprovalRequest }> { await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = h.ctx.agents.get(AgentId(sessionId)) + const agent = h.ctx.agents.get(SessionId(sessionId)) if (agent === undefined) throw new Error('newSession created no agent') // In production an ask always fires mid-turn (tool execution); open one so // request()'s turn-enclosure precondition holds for the direct drive below. diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index be05a09644..7e780348ba 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** * End-to-end bridge specs over an in-memory transport: a real @@ -98,7 +98,7 @@ describe('acp bridge', () => { required: [], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') const toolResultBlock = toolResult?.type === 'tool/result' ? toolResult.data.content[0] : undefined const toolResultText = toolResultBlock?.type === 'text' ? toolResultBlock.text : undefined expect(toolResultText).toBe('{"answers":[{"id":"language","selected":["Python"]}]}') @@ -127,7 +127,7 @@ describe('acp bridge', () => { required: ['custom'], }, }) - const toolResult = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'tool/result') + const toolResult = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'tool/result') expect(JSON.stringify(toolResult)).toContain('apollo') }) @@ -136,7 +136,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const result = await harness.ctx.userInteraction.ask({ agent, @@ -167,7 +167,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: 'TypeScript', custom: 'Use Zig' } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -184,7 +184,7 @@ describe('acp bridge', () => { harness.onElicitation = () => ({ action: 'accept', content: { choice: ['Tests', 'Docs'] } }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ agent, @@ -201,7 +201,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) @@ -225,7 +225,7 @@ describe('acp bridge', () => { harness = await makeBridgeHarness({ storageDir, withAskUser: true }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! const alreadyAborted = new AbortController() alreadyAborted.abort() @@ -265,8 +265,8 @@ describe('acp bridge', () => { expect(b.sessionId).toBeTruthy() expect(a.sessionId).not.toBe(b.sessionId) // Both agents are live and independently registered. - expect(harness.ctx.agents.get(AgentId(a.sessionId))).toBeDefined() - expect(harness.ctx.agents.get(AgentId(b.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(a.sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(b.sessionId))).toBeDefined() }) it('rejects a non-absolute cwd but accepts any absolute cwd (per-session workspace)', async () => { @@ -281,7 +281,7 @@ describe('acp bridge', () => { const res = await harness.client.newSession({ cwd: '/tmp', mcpServers: [] }) expect(res.sessionId).toBeTruthy() // The session header records that cwd, so its bash tools run there. - expect(harness.ctx.agents.get(AgentId(res.sessionId))!.session.header.cwd).toBe('/tmp') + expect(harness.ctx.agents.get(SessionId(res.sessionId))!.session.header.cwd).toBe('/tmp') }) it('rejects non-empty additionalDirectories', async () => { @@ -321,7 +321,7 @@ describe('acp bridge', () => { ], }) expect(result.stopReason).toBe('end_turn') - const user = harness.ctx.agents.get(AgentId(sessionId))!.session.events.find(event => event.type === 'user/message') + const user = harness.ctx.agents.get(SessionId(sessionId))!.session.events.find(event => event.type === 'user/message') expect(JSON.stringify(user)).toContain('resource_link') }) diff --git a/packages/ui/acp/tests/dispose.spec.ts b/packages/ui/acp/tests/dispose.spec.ts index f02a7b0649..b5d98c0881 100644 --- a/packages/ui/acp/tests/dispose.spec.ts +++ b/packages/ui/acp/tests/dispose.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse } from './harness.ts' describe('acp bridge — disposal & HMR safety', () => { @@ -17,7 +16,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. const promptDone = harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) @@ -62,10 +61,10 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeDefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeDefined() await harness.acpFiber.dispose() // tear down ONLY the bridge - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -92,7 +91,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // Start a prompt that hangs in the model stream. The prompt RPC will never // return (its transport is severed), so do not await it. void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) @@ -115,7 +114,7 @@ describe('acp bridge — disposal & HMR safety', () => { // and its session removed from the store, not merely idled (the old // behavior). The services live on the root ctx, so they survive this. await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId(sessionId))).toBeUndefined() await harness.dispose() }) @@ -128,7 +127,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -145,7 +144,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const session = harness.ctx.agents.get(AgentId(sessionId))!.session + const session = harness.ctx.agents.get(SessionId(sessionId))!.session await harness.ctx.fiber.dispose() const before = harness.updates.length @@ -169,12 +168,12 @@ describe('acp bridge — disposal & HMR safety', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) - const liveEvents = harness.ctx.agents.get(AgentId(sessionId))!.session.events.length + const liveEvents = harness.ctx.agents.get(SessionId(sessionId))!.session.events.length expect(liveEvents).toBeGreaterThan(0) // Tear down JUST the bridge (the AgentHandle dispose runs to quiescence). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // Re-load the session from disk: every live event (incl. the closing // turn/end) was flushed before the session was detached. @@ -201,7 +200,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! void harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => {}) await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') @@ -211,7 +210,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose JUST the bridge: a fiber unload that must STILL honor the ordered // teardown (the composite effect runs its disposer chain as a unit). await harness.acpFiber.dispose() - expect(harness.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId(sessionId))).toBeUndefined() // The loop's own `turn/end {disposed}` is on disk (re-load: the world, not // self-report) — NOT a crash-recovery `interrupted` substitute. @@ -230,21 +229,21 @@ describe('acp bridge — disposal & HMR safety', () => { // queryable, with its session still in the store. const harness = await makeBridgeHarness({ storageDir, script: [] }) const handleA = await harness.ctx.agents.create({ - agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, }) const handleB = await harness.ctx.agents.create({ - agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, + sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, }) - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBe(handleA.agent) - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBe(handleA.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) await handleA.dispose() // A is gone — unregistered AND its session removed from the store. - expect(harness.ctx.agents.get(AgentId('sib-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('sib-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('sib-a'))).toBeUndefined() expect(handleA.agent.status).toBe('disposed') // B is wholly unaffected. - expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) + expect(harness.ctx.agents.get(SessionId('sib-b'))).toBe(handleB.agent) expect(harness.ctx.sessions.get(SessionId('sib-b'))).toBeDefined() expect(handleB.agent.status).not.toBe('disposed') await harness.dispose() @@ -262,7 +261,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] }) harness.ctx.on('agent/disposed', () => { throw new Error('boom disposed listener') }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, }) handle.agent.send([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() @@ -270,7 +269,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Dispose: the throwing listener must NOT break the chain before detach. await handle.dispose() - expect(harness.ctx.agents.get(AgentId('guard-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('guard-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('guard-a'))).toBeUndefined() // detach still ran await harness.dispose() }) @@ -283,7 +282,7 @@ describe('acp bridge — disposal & HMR safety', () => { // observe the same quiescence boundary. const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, + sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, }) // Drive a turn that hangs in the model stream, so the loop is mid-turn when // disposed — its exit runs a final session/flush we can gate to hold the @@ -313,7 +312,7 @@ describe('acp bridge — disposal & HMR safety', () => { // Release the flush; both resolve together and the session is gone. releaseFlush() await Promise.all([first, second]) - expect(harness.ctx.agents.get(AgentId('conc-a'))).toBeUndefined() + expect(harness.ctx.agents.get(SessionId('conc-a'))).toBeUndefined() expect(harness.ctx.sessions.get(SessionId('conc-a'))).toBeUndefined() await harness.dispose() }) diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts index e86fb9fc94..329016a69e 100644 --- a/packages/ui/acp/tests/edges.spec.ts +++ b/packages/ui/acp/tests/edges.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { makeBridgeHarness, textResponse, type BridgeHarness } from './harness.ts' @@ -27,7 +26,7 @@ describe('acp bridge — demux & config edges', () => { await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const before = harness.updates.length - const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) + const { agent: foreign } = await harness.ctx.agents.create({ sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) foreign.send([{ type: 'text', text: 'hi' }]) await foreign.whenIdle() await new Promise(r => setTimeout(r, 10)) diff --git a/packages/ui/acp/tests/load.spec.ts b/packages/ui/acp/tests/load.spec.ts index 2fbc95b3d9..efc9399c75 100644 --- a/packages/ui/acp/tests/load.spec.ts +++ b/packages/ui/acp/tests/load.spec.ts @@ -4,7 +4,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { SESSION_FORMAT_VERSION, SessionId } from '@deepseek-ai/dsh-session' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, toolCallResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' /** Concatenate the text of all agent_message_chunk updates. */ @@ -194,7 +193,7 @@ describe('acp bridge — session/load replay', () => { release() // resume() finishes AFTER teardown expect(await loadResult).toBe('rejected') // No live agent was installed for the closed connection. - expect(loader.ctx.agents.get(AgentId(sessionId))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId(sessionId))).toBeUndefined() }) it('rejects load when the requested cwd does not match the persisted session cwd', async () => { @@ -215,11 +214,11 @@ describe('acp bridge — session/load replay', () => { await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) await expect(loader.client.loadSession({ sessionId: 'elsewhere', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/cwd mismatch/) - expect(loader.ctx.agents.get(AgentId('elsewhere'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('elsewhere'))).toBeUndefined() const res = await loader.client.loadSession({ sessionId: 'elsewhere', cwd: `${otherCwd}/.`, mcpServers: [] }) expect(res).toBeDefined() - expect(loader.ctx.agents.get(AgentId('elsewhere'))!.session.header.cwd).toBe(otherCwd) + expect(loader.ctx.agents.get(SessionId('elsewhere'))!.session.header.cwd).toBe(otherCwd) }) it('rejects load for a non-absolute cwd (still required to be absolute)', async () => { @@ -254,7 +253,7 @@ describe('acp bridge — session/load replay', () => { // Rejected BEFORE resume (metadata-only check) — no agent was registered, so // the id is not wedged: a later attempt hits the same clean rejection, not a // duplicate-registration error. - expect(loader.ctx.agents.get(AgentId('legacy'))).toBeUndefined() + expect(loader.ctx.agents.get(SessionId('legacy'))).toBeUndefined() await expect(loader.client.loadSession({ sessionId: 'legacy', cwd: process.cwd(), mcpServers: [] })) .rejects.toThrow(/no absolute persisted cwd/) }) diff --git a/packages/ui/acp/tests/multi-session.spec.ts b/packages/ui/acp/tests/multi-session.spec.ts index ca11934046..0881fe4199 100644 --- a/packages/ui/acp/tests/multi-session.spec.ts +++ b/packages/ui/acp/tests/multi-session.spec.ts @@ -3,8 +3,8 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' -import { AgentId } from '@deepseek-ai/dsh-agent' import { makeBridgeHarness, textResponse, type BridgeHarness, type CapturedUpdate } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Text of the agent_message_chunk updates scoped to one session id. */ function messageTextFor(updates: { sessionId?: string; update: CapturedUpdate }[], sessionId: string): string { @@ -102,8 +102,8 @@ describe('acp bridge — RFC 011 multi-session isolation', () => { await harness.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const a = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId const b = (await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] })).sessionId - const agentA = harness.ctx.agents.get(AgentId(a))! - const agentB = harness.ctx.agents.get(AgentId(b))! + const agentA = harness.ctx.agents.get(SessionId(a))! + const agentB = harness.ctx.agents.get(SessionId(b))! // Wait deterministically for BOTH agents to enter `running` (not a fixed // sleep — agent startup latency is unbounded on a loaded worker). diff --git a/packages/ui/acp/tests/turns.spec.ts b/packages/ui/acp/tests/turns.spec.ts index f559ca36d9..000b80336d 100644 --- a/packages/ui/acp/tests/turns.spec.ts +++ b/packages/ui/acp/tests/turns.spec.ts @@ -3,7 +3,6 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { errorResponse, @@ -13,6 +12,7 @@ import { toolCallResponse, type BridgeHarness, } from './harness.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** Boilerplate: initialize + create one session, returning its id. */ async function newSession(h: BridgeHarness, clientCapabilities: Record = {}): Promise { @@ -279,7 +279,7 @@ describe('acp bridge — turn outcomes', () => { // OWN turn with the real model answer. harness = await makeBridgeHarness({ storageDir, script: [textResponse('real answer')] }) const sessionId = await newSession(harness) - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! // On the queued prompt, synchronously inject a one-shot context turn (idle // inject writes turn/start{injection} → context/message → turn/end). Fire // once so it lands between install and the prompt turn. @@ -335,7 +335,7 @@ describe('acp bridge — turn outcomes', () => { await harness.client.cancel({ sessionId }) const res = await promptDone expect(res.stopReason).toBe('cancelled') - const agent = harness.ctx.agents.get(AgentId(sessionId))! + const agent = harness.ctx.agents.get(SessionId(sessionId))! await agent.whenIdle() // At most ONE turn ran (the cancelled one) — the cancel cleared the queue, so // no second turn was batched or leaked. (A best-effort abort that left queued diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 86af6645f3..4dbfeb0fa2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -16,7 +16,6 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -255,7 +254,6 @@ export class HarnessSdkServer { private async createSession(sessionId: string): Promise { const handle = await this.ctx.agents.create({ - agentId: AgentId(sessionId), sessionId: SessionId(sessionId), meta: { cwd: this.cwd }, agentOptions: { model: this.model }, diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 1cde550f2e..9260a59aae 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -5,7 +5,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId, type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' +import { type Agent, type AgentHandle } from '@deepseek-ai/dsh-agent' + import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -135,7 +136,6 @@ describe('HarnessSdkServer', () => { expect(llmServer.requests).toHaveLength(2) const orphanHandle = await ctx.agents.create({ - agentId: AgentId('orphan-agent'), sessionId: SessionId('orphan-session'), meta: { cwd: storageDir }, agentOptions: { model: 'dsagent-model' }, @@ -170,8 +170,8 @@ describe('HarnessSdkServer', () => { } as unknown as Agent const mainHandle = { agent: mainAgent, dispose: vi.fn(() => Promise.resolve()) } const otherHandle = { agent: otherAgent, dispose: vi.fn(() => Promise.resolve()) } - const create = vi.fn(async (options: { agentId: AgentId }) => - String(options.agentId) === 'main' ? mainHandle : otherHandle) + const create = vi.fn(async (options: { sessionId: SessionId }) => + String(options.sessionId) === 'main' ? mainHandle : otherHandle) const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, @@ -263,20 +263,18 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, transport) const parentHandle = await ctx.agents.create({ - agentId: AgentId('parent-agent'), sessionId: SessionId('main'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) const handle = await ctx.agents.create({ - agentId: AgentId('child-agent'), sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', - id: AgentId('child-agent'), + id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) @@ -285,7 +283,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'spawn', - agentId: 'child-agent', + agentId: 'child-session', parentSessionId: 'main', childSessionId: 'child-session', status: 'ok', @@ -311,19 +309,16 @@ describe('HarnessSdkServer', () => { let failedHandle: AgentHandle | undefined try { parentHandle = await ctx.agents.create({ - agentId: AgentId('fallback-parent-agent'), sessionId: SessionId('fallback-parent'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) handle = await ctx.agents.create({ - agentId: AgentId('fallback-child-agent'), sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) failedHandle = await ctx.agents.create({ - agentId: AgentId('failed-child-agent'), sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -333,18 +328,18 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('fallback-child-agent'), + id: SessionId('fallback-child-session'), stopReason: 'max-tokens', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('failed-child-agent'), + id: SessionId('failed-child-session'), stopReason: 'error', }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', - id: AgentId('missing-child-agent'), + id: SessionId('missing-child-agent'), stopReason: 'error', }) @@ -352,7 +347,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'fallback-child-agent', + agentId: 'fallback-child-session', parentSessionId: 'fallback-parent', childSessionId: 'fallback-child-session', status: 'error', @@ -364,7 +359,7 @@ describe('HarnessSdkServer', () => { method: 'subagent.finished', params: { provider: 'fork', - agentId: 'failed-child-agent', + agentId: 'failed-child-session', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..82da64cd81 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -11,11 +11,11 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | Plugin | Why it is here | |---|---| | `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) | -| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's `model` with `process.cwd()` as the fresh session cwd and carrying its `persona` | +| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating one agent under the `main` config label from this app's `model`, with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | -| `stdio-chat` (in-package module) | the readline UI, bound to the `main` agent | +| `stdio-chat` (in-package module) | the readline UI, holding the app-owned agent object directly and rendering it as `main` | `@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, NOT baked in here: it is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader`, and the in-process test tier cannot even import it (so a package whose `apply` statically pulled it in could never carry the per-file coverage gate). Unlike the console logger, a stray `hmr` is not a stdout-purity footgun, so leaving it at the leaf costs no safety. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. @@ -25,14 +25,14 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| -| `model` | (required) | the pre-created `main` agent's model | +| `model` | (required) | the pre-created agent's model | | `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd`, so project-scoped features such as skill discovery and default bash workdir follow the directory where `dsh-stdio-agent` was started. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 127851eaf5..f01c48a615 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -3,11 +3,11 @@ * @deepseek-ai/dsh-agent-core}) plus the coupled front-door cluster a terminal * chat needs — a console logger, the readline UI (the in-package `stdio-chat` * module), JSONL session - * persistence, and a pre-created `main` agent the UI drives. + * persistence, and one pre-created agent the UI drives under its `main` label. * * The cluster is BAKED IN, not left to the leaf: a stdio app always logs to the - * console (stdout is just the terminal) and always pre-creates the `main` agent - * the readline UI sends to. The leaf supplies the swappable backends (the LLM + * console (stdout is just the terminal) and always pre-creates one agent the + * readline UI labels `main`. The leaf supplies the swappable backends (the LLM * adapter, the bash executor), optional product tools, the optional `hmr` * dev-reload plugin, and this app's {@link Config} (model, prompt, persistence * root, welcome banner). @@ -41,7 +41,6 @@ import type { Context } from 'cordis' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' import * as agentCore from '@deepseek-ai/dsh-agent-core' @@ -54,7 +53,7 @@ export const name = 'stdio-agent' /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `model`/`resumeSessionId` configure the pre-created agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -63,7 +62,7 @@ export const name = 'stdio-agent' * `welcome` is the UI banner. */ export interface Config { - /** Model name for the `main` agent (must have a registered adapter). */ + /** Model name for the pre-created agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ persona?: string @@ -78,7 +77,7 @@ export interface Config { /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-core. */ skills?: agentCore.SkillConfig /** - * If set, the `main` agent RESUMES this persisted session id instead of + * If set, the pre-created agent RESUMES this persisted session id instead of * starting fresh. Sourced from an env var in the leaf `cordis.yml` * (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`). */ @@ -103,9 +102,9 @@ export const Config: z = z.object({ /** * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating the `main` agent from this - * app's `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI bound to `main`. The `hmr` dev-reload plugin is + * (infra), then the agent-core bundle pre-creating one agent from this app's + * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL + * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { @@ -115,7 +114,7 @@ export function apply(ctx: Context, config: Config): void { ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, ...config.tools !== undefined ? { tools: config.tools } : {}, agents: [{ - id: AgentId('main'), + id: 'main', model: config.model, cwd: process.cwd(), ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, @@ -125,5 +124,5 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' }) + ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 8e3c1f467b..cb9ce0bc10 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -19,7 +19,7 @@ import { createInterface } from 'node:readline' import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' import { UserInteractionError, type AskUserQuestionAnswer, @@ -36,15 +36,10 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - // TODO(fixed-stdio-agent): this app-internal plugin is mounted only for the - // precreated `main` agent; remove configurability and its config-only test. - /** Id of the agent stdin drives (`send`/`steer`) and whose status gates the EOF exit; rendering is global. Defaults to `'main'`. */ - agent?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - agent: z.string().default('main'), }) /** @@ -98,23 +93,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Loader validation, so it must be self-contained rather than trusting the // cast — `config.welcome as string` would otherwise be `undefined` on `{}`. const welcome = config.welcome ?? 'ready.' - const agentId = AgentId(config.agent ?? 'main') const { input, output, exit } = runtime - // Render label lookup: the `turn/start` session event carries only the turn - // number, so to print the short agent id (`[main turn 1]`) we map the - // session's id to its agent's id. The session id is not reliably the agent id - // (a session can be created with an explicit/client-supplied id), so build the - // map from `agent/created` rather than parsing the id string. Seed from the - // registry's current agents first: an agent registered before this plugin - // installed (e.g. the pre-created `main` agent, or any agent surviving an HMR - // reload of just this fiber) already fired its `agent/created`, so the live - // listener alone would miss it and its turns would fall back to the raw - // session id. - const labelBySession = new Map() - for (const agent of ctx.agents.list()) labelBySession.set(agent.session.header.id, agent.id) - ctx.on('agent/created', (agent) => { labelBySession.set(agent.session.header.id, agent.id) }) - ctx.on('agent/disposed', (agent) => { labelBySession.delete(agent.session.header.id) }) + // This app owns exactly one pre-created agent. Hold the live object directly: + // its per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) + ctx.on('agent/disposed', (agent) => { + if (target === agent) target = undefined + }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -136,7 +124,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt output.write(chunk.text) } } else if (event.type === 'turn/start') { - const label = labelBySession.get(session.header.id) ?? session.header.id + const label = target?.session === session ? 'main' : session.id output.write(`\n[${label} turn ${event.data.turn}] `) } else if (event.type === 'turn/end') { if (inReasoning) output.write('\x1B[0m') @@ -187,7 +175,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // Work submitted: wait until a turn has run and the agent is idle. if (submittedWork) { if (!sawRunning) return - const agent = ctx.agents.get(agentId) + const agent = target if (agent && agent.status !== 'idle') return // a turn is still running } // Let any final output flush, then exit. The handle is tracked so the @@ -201,7 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const disposeStatusListener = ctx.on('agent/status', (subject, status) => { - if (subject.id !== agentId) return + if (subject !== target) return if (status === 'running') sawRunning = true if (status === 'idle') maybeExit() }) @@ -354,9 +342,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return - const agent = ctx.agents.get(agentId) + const agent = target if (!agent) { - ctx.logger.error('ui-stdio: agent "%s" is not running', agentId) + ctx.logger.error('ui-stdio: main agent is not running') return } submittedWork = true diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index a958c435c1..6116aa356f 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,7 +16,7 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its label map from the registry at install; this suite only + // The UI seeds its target object from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. agents: { list: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 0668d25fb0..5c5c0d2667 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -4,7 +4,8 @@ import { join } from 'node:path' import { tmpdir } from 'node:os' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' + import type { Message } from '@deepseek-ai/dsh-llm' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as stdioAgent from '../src/index.ts' @@ -82,9 +83,12 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('sessionPersistence')).toBeDefined() expect(ctx.get('userInteraction')).toBeDefined() expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() - // The pre-created `main` agent the UI drives. - const agent = ctx.get('agents')?.get(AgentId('main')) + // The sole pre-created agent the UI drives. `main` is its stable config + // label; each fresh process mints a durable combined agent/session id. + const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() + expect(agent?.id).toBe(agent?.session.id) + expect(agent?.id).toMatch(/^main-session-/) expect(agent?.session.header.cwd).toBe(process.cwd()) await ctx.fiber.dispose() }) @@ -99,7 +103,7 @@ describe('dsh-stdio-agent app', () => { stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + expect(ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) @@ -116,7 +120,7 @@ describe('dsh-stdio-agent app', () => { it('forwards resumeSessionId onto the pre-created agent when set', async () => { // A resume id defers agent creation until persistence loads; with no backing - // session the resume is contained + logged, so no `main` agent registers — + // session the resume is contained + logged, so no agent registers — // the branch that maps resumeSessionId through is what this covers. const ctx = await mount({ model: 'mock', @@ -125,7 +129,7 @@ describe('dsh-stdio-agent app', () => { resumeSessionId: 'no-such-session', skills: await isolatedSkillsConfig(), }) - expect(ctx.get('agents')?.get(AgentId('main'))).toBeUndefined() + expect(ctx.get('agents')?.list()).toEqual([]) await ctx.fiber.dispose() }) diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 93683d0768..69ca5f8837 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -57,17 +57,16 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { status, sent, steered, - // A minimal session stub: the UI reads only `session.header.id` (to map the - // session back to its agent id for the turn-boundary label). - session: { header: { id: `${id}-session` } }, + // A minimal session stub with the agent's shared durable identity. + session: { id, header: { id } }, send: (content: ContentBlock[]) => void sent.push(content), steer: (content: ContentBlock[]) => void steered.push(content), } as never } /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ -function makeSession(agentId: string): Session { - return { header: { id: `${agentId}-session` } } as Session +function makeSession(id: string): Session { + return { id, header: { id } } as Session } /** An `assistant/chunk` session event carrying one raw stream chunk. */ @@ -75,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', agent: 'main' } +const CONFIG: Config = { welcome: 'hi there' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -99,12 +98,11 @@ describe('createStdioChat rendering', () => { expect(out.text()).toBe('hi there\n> ') }) - it('falls back to default welcome/agent when called with empty config', async () => { + it('falls back to the default welcome when called with empty config', async () => { // createStdioChat is exported and may be driven directly (bypassing the - // Loader's schemastery validation), so it must default welcome/agent itself. + // Loader's schemastery validation), so it must default the welcome itself. const { out } = await setup({}) expect(out.text()).toBe('ready.\n> ') - // And it drives the default agent id 'main'. }) it('detects readline terminal mode from both stream TTY flags', async () => { @@ -156,9 +154,9 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created populates the session-id → agent-id label map. + // agent/created supplies the app-owned target object. ctx.emit('agent/created', agent) - const session = makeSession('main') + const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, } as SessionEvent) @@ -169,21 +167,20 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\n> ') }) - it('falls back to the session id as the label when no agent is mapped', async () => { + it('uses the session id as the label for a non-target session', async () => { const { ctx, out } = await setup() - // No agent/created emitted, so the label map is empty — the header id shows. + // No target exists, so the event's durable identity is the label. ctx.emit('session/event', makeSession('orphan'), { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[orphan-session turn 1] ') + expect(out.text()).toContain('[orphan turn 1] ') }) - it('seeds labels for agents already registered before the UI installs', async () => { + it('uses an agent already registered before the UI installs as its target', async () => { // The pre-created `main` agent (and any agent surviving an HMR reload of just // this fiber) fired its `agent/created` before the UI's listener existed, so // the live listener alone would miss it. Seeding from `ctx.agents.list()` at - // install time is what keeps its turn header showing `[main turn N]` instead - // of the raw session id. + // install time preserves the terminal's fixed `[main turn N]` label. const ctx = new Context() await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) @@ -193,7 +190,7 @@ describe('createStdioChat rendering', () => { await ctx.plugin(Object.assign((inner: Context) => { createStdioChat(inner, CONFIG, runtime) }, { inject: ['agents', 'userInteraction'] })) - ctx.emit('session/event', makeSession('main'), { + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 5, trigger: { kind: 'message' } }, } as SessionEvent) expect(out.text()).toContain('[main turn 5] ') @@ -209,17 +206,28 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('\x1B[2mmid\x1B[0m') }) - it('drops the label mapping on agent/disposed', async () => { + it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') ctx.emit('agent/created', agent) ctx.emit('agent/disposed', agent) - // After disposal the map no longer resolves the agent id — fall back to the - // session header id. - ctx.emit('session/event', makeSession('main'), { + // After disposal the event belongs to a non-target session, so its durable + // identity is rendered directly. + ctx.emit('session/event', agent.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, } as SessionEvent) - expect(out.text()).toContain('[main-session turn 1] ') + expect(out.text()).toContain('[main turn 1] ') + }) + + it('keeps the target when a different agent is disposed', async () => { + const { ctx, out } = await setup() + const target = makeAgent('target') + ctx.emit('agent/created', target) + ctx.emit('agent/disposed', makeAgent('other')) + ctx.emit('session/event', target.session, { + type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, + } as SessionEvent) + expect(out.text()).toContain('[main turn 1] ') }) it('renders tool/call and tool/result session events', async () => { @@ -666,11 +674,11 @@ describe('createStdioChat input', () => { const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: agent "%s" is not running', 'main') + expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the agent named in config, not a hardcoded id', async () => { - const { ctx, input } = await setup({ welcome: 'w', agent: 'worker' }) + it('drives the app-owned agent without a duplicate id config', async () => { + const { ctx, input } = await setup({ welcome: 'w' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') diff --git a/packages/util/brand/README.md b/packages/util/brand/README.md index 8f7943def7..be25edd55e 100644 --- a/packages/util/brand/README.md +++ b/packages/util/brand/README.md @@ -4,7 +4,7 @@ The `Branded` nominal-typing primitive — a tiny, **type-only** package (no ## What `Branded` is -A brand makes structurally-identical strings non-interchangeable at the type level: an `AgentId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. +A brand makes structurally-identical strings non-interchangeable at the type level: a `SessionId` cannot be passed where a `CallId` is expected, even though both are plain `string`s at runtime. ```ts import type { Branded } from '@deepseek-ai/dsh-brand' @@ -21,6 +21,6 @@ Construction goes through the per-id factory in the OWNING package (a plain cast ## Policy: brand ids that cross package boundaries -A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), `SessionId` in `dsh-session`, `AgentId` in `dsh-agent`, `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** +A package brands the ids it OWNS — `CallId` in `dsh-llm` (tool-call correlation), the shared agent/session `SessionId` in `dsh-session`, and `BashTaskId`/`OwnerToken` in `dsh-bash`. Branding is for ids that cross package boundaries and could plausibly be confused; **not every string needs a brand.** This package owns ONLY the primitive — no concrete id, no runtime code beyond the (erased) type. Keeping the primitive dependency-free is the point: a capability package can brand its ids without depending on an unrelated package. `dsh-bash`, for example, brands `BashTaskId`/`OwnerToken` by depending on `dsh-brand` alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. diff --git a/packages/util/brand/src/index.ts b/packages/util/brand/src/index.ts index 051ced94b7..d8c28846b3 100644 --- a/packages/util/brand/src/index.ts +++ b/packages/util/brand/src/index.ts @@ -4,15 +4,15 @@ * cross-boundary id. * * A brand makes structurally-identical strings non-interchangeable at the type - * level: an `AgentId` cannot be passed where a `CallId` is expected, even + * level: a `SessionId` cannot be passed where a `CallId` is expected, even * though both are plain strings at runtime. Construction goes through a per-id * factory in the OWNING package (a plain cast inside — zero runtime cost); * comparison, logging, and serialization all behave as ordinary strings. * * Policy: a package brands the ids it owns — `CallId` in dsh-llm (tool-call - * correlation), `SessionId` in dsh-session, `AgentId` in dsh-agent, - * `BashTaskId`/`OwnerToken` in dsh-bash. Branding is for ids that cross package - * boundaries and could plausibly be confused; not every string needs a brand. + * correlation), and `SessionId` in dsh-session; `BashTaskId`/`OwnerToken` live + * in dsh-bash. Branding is for ids that cross package boundaries and could + * plausibly be confused; not every string needs a brand. * This package owns ONLY the primitive — no concrete id, no runtime code beyond * the (erased) type — so the brand vocabulary stays dependency-free and a * package can brand its ids without depending on an unrelated capability diff --git a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts index 0585889617..ac7112a0f0 100644 --- a/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts +++ b/packages/workflow/tool-workflow/tests/tool-workflow.spec.ts @@ -4,7 +4,6 @@ import Loader from '@cordisjs/plugin-loader' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import { WorkflowRunId, WorkflowService } from '@deepseek-ai/dsh-workflow' import type { WorkflowResult, WorkflowRun, WorkflowStartRequest } from '@deepseek-ai/dsh-workflow' @@ -12,6 +11,7 @@ import { CallId } from '@deepseek-ai/dsh-llm' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread' import * as toolWorkflow from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A controllable engine standing in behind ctx.workflows (the tool's only seam). */ class StubEngine extends WorkflowService { @@ -51,7 +51,7 @@ async function setup(config?: { toolName?: string; maxResultChars?: number }) { await ctx.plugin(StubEngine) await ctx.plugin(toolWorkflow, config ?? {}) const engine = ctx.workflows as StubEngine - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent return { ctx, engine, parent } } @@ -237,7 +237,7 @@ describe('dsh-tool-workflow', () => { await ctx.plugin(SubagentService) await ctx.plugin(WorkerWorkflowEngine, { disposeGraceMs: 30 }) await ctx.plugin(toolWorkflow, {}) - const parent = { id: AgentId('caller'), options: {} } as unknown as Agent + const parent = { id: SessionId('caller'), options: {} } as unknown as Agent const controller = new AbortController() const pending = execute(ctx, { script: 'await new Promise(() => {})\nreturn 1', diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 94282cb173..7dbdccbb43 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -38,8 +38,8 @@ */ import * as vm from 'node:vm' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import { assertSupportedOutputSchema, OutputSchemaError } from '@deepseek-ai/dsh-tools' import type { StructuredOutputSchema } from '@deepseek-ai/dsh-tools' import { isFatalWorkflowError, WorkflowError } from '@deepseek-ai/dsh-workflow' @@ -319,7 +319,7 @@ export class WorkflowExecution { await run.dispose() throw this.cancelledError() } - const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: AgentId(run.id) } + const info: WorkflowAgentInfo = { seq, label, ...phase !== undefined ? { phase } : {}, childId: SessionId(run.id) } this.observer.agentStart(info) try { let result diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..2e13ddcb8b 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -1,10 +1,11 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -37,7 +38,7 @@ async function setup(script: Script) { await ctx.plugin(spawn, { providerName: 'spawn' }) await ctx.plugin(WorkerWorkflowEngine, {}) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { model: 'mock' }) return { ctx, parent, adapter } } @@ -73,7 +74,7 @@ return { prose, verdict: judged.verdict, confidence: judged.confidence }`, // Both children were disposed to quiescence — no live child agents remain. expect(childIds.length).toBe(2) for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } }) diff --git a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts index 7f34396d52..673a43ee0a 100644 --- a/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/source-worker.compat.spec.ts @@ -6,10 +6,10 @@ import { expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import WorkerWorkflowEngine from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' // A fresh thread compiles the source runtime. Leave contention headroom on // shared CI runners without weakening any engine-level timeout assertion. @@ -19,7 +19,7 @@ it('runs the default config through the source worker', async () => { const ctx = new Context() const subagents = await ctx.plugin(SubagentService) const engine = await ctx.plugin(WorkerWorkflowEngine, {}) - const parent = { id: AgentId('workflow-compat-parent'), options: {} } as unknown as Agent + const parent = { id: SessionId('workflow-compat-parent'), options: {} } as unknown as Agent try { const run = ctx.workflows.start({ script: 'return 6 * 7', diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 1d6f61432a..169d80cda7 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -62,7 +63,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key it('runs a two-phase script in a worker thread over real children, one through the structured runtime', async () => { ctx = await harness() const parentHandle = await ctx.agents.create({ - agentId: AgentId('wf-worker-e2e-parent'), sessionId: 'wf-worker-e2e-session' as never, agentOptions: { model: 'deepseek-v4-flash' }, }) @@ -95,7 +95,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key expect(childIds.length).toBe(2) // The children were disposed to quiescence after collection. for (const childId of childIds) { - expect(ctx.agents.get(AgentId(childId))).toBeUndefined() + expect(ctx.agents.get(SessionId(childId))).toBeUndefined() } await parentHandle.dispose() }, 240_000) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 4ad00ee02f..09fb606d69 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -3,17 +3,17 @@ import { fileURLToPath } from 'node:url' import type { Worker } from 'node:worker_threads' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' -import { AgentId } from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentCapabilities, SubagentProvider, SubagentResult, SubagentRun, SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import type { WorkflowMeta, WorkflowResult, WorkflowResultInfo, WorkflowRunInfo } from '@deepseek-ai/dsh-workflow' import * as workerEngineModule from '../src/index.ts' import WorkerWorkflowEngine, { HostToWorkerType, WorkerToHostType, type Config } from '../src/index.ts' +import { SessionId } from '@deepseek-ai/dsh-session' /** A minimal parent stand-in: the engine only threads it through to the provider. */ function fakeParent(): Agent { - return { id: AgentId('workflow-parent'), options: {} } as unknown as Agent + return { id: SessionId('workflow-parent'), options: {} } as unknown as Agent } // Worker-thread startup is CPU-bound (a fresh thread compiles the runtime on @@ -117,7 +117,7 @@ class StubProvider implements SubagentProvider { } if (request.signal.aborted) throw new Error('child start aborted before publication') return { - id: AgentId(`stub-child-${index}`), + id: SessionId(`stub-child-${index}`), result: terminal.promise, dispose: () => { controlled.disposeCalls += 1 @@ -366,7 +366,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('reject-child'), + id: SessionId('reject-child'), result: Promise.reject(new Error('backend exploded')), dispose: () => Promise.resolve(), }), @@ -400,7 +400,7 @@ describe('dsh-workflow-workerthread', () => { stopReason: 'completed', } as unknown as SubagentResult const start = vi.spyOn(ctx.subagents, 'start').mockResolvedValue({ - id: AgentId('raw-invalid-child'), + id: SessionId('raw-invalid-child'), result: Promise.resolve(invalid), dispose: () => Promise.resolve(), }) @@ -423,7 +423,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('bad-dispose-child'), + id: SessionId('bad-dispose-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, dispose: () => { throw new Error('dispose exploded') }, @@ -444,7 +444,7 @@ describe('dsh-workflow-workerthread', () => { capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: false }, inheritsParentContext: false, start: async () => ({ - id: AgentId('trap-child'), + id: SessionId('trap-child'), result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, // The rejection VALUE's own coercion throws: a warn built with bare @@ -771,7 +771,7 @@ describe('dsh-workflow-workerthread', () => { settle({ output: [], stopReason: 'aborted' }) }, { once: true }) return { - id: AgentId('signal-only-child'), + id: SessionId('signal-only-child'), result, dispose: () => Promise.resolve(), } @@ -1092,7 +1092,7 @@ describe('dsh-workflow-workerthread', () => { expect(request.signal.reason).toBe('workflow worker gone') ready.resolve({ - id: AgentId('late-ready-child'), + id: SessionId('late-ready-child'), result: Promise.resolve({ output: [], stopReason: 'aborted' }), dispose: () => { disposeCalls += 1 @@ -1128,7 +1128,7 @@ describe('dsh-workflow-workerthread', () => { handle.cancel('reentered from worker-death signal cleanup') }, { once: true }) return { - id: AgentId('doomed-child'), + id: SessionId('doomed-child'), result: new Promise(() => { /* never settles; the reap is the teardown */ }), dispose: () => Promise.reject(new Error('dispose exploded during reap')), } diff --git a/packages/workflow/workflow/src/types.ts b/packages/workflow/workflow/src/types.ts index 981a2da172..35ea4fb053 100644 --- a/packages/workflow/workflow/src/types.ts +++ b/packages/workflow/workflow/src/types.ts @@ -7,7 +7,8 @@ */ import type { Branded } from '@deepseek-ai/dsh-brand' -import type { Agent, AgentId } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import type { SessionId } from '@deepseek-ai/dsh-session' /** Identifies one workflow run. */ export type WorkflowRunId = Branded<'WorkflowRunId'> @@ -145,7 +146,7 @@ export interface WorkflowAgentInfo { /** The phase this agent belongs to (the `phase` option, else the current `phase()` title). */ phase?: string /** The child agent's id on the subagent seam. */ - childId: AgentId + childId: SessionId } /** How one `agent()` call settled: clean result, child failure (script sees `null`), or run cancellation. */ From 61136b22bbfabae49227843f924cc4832a07fe51 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:09:09 +0800 Subject: [PATCH 014/323] refactor: remove UI identity translations --- docs/config-catalog.md | 4 +- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 ++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 -------------- packages/ui/acp/README.md | 4 +- packages/ui/acp/src/index.ts | 52 ++++++++----------- packages/ui/acp/tests/approval.spec.ts | 9 ++-- packages/ui/acp/tests/bridge.spec.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 ++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 20 ++++--- 12 files changed, 100 insertions(+), 110 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..4ae020f0be 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -11,7 +11,7 @@ A `Requires:` line lists the service keys the plugin `inject`s: its `cordis.yml` ## `@deepseek-ai/dsh-acp` -Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` +Requires: `agents` · `sessionPersistence` · `tools` · `userInteraction` ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:246`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..79d7332553 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; subagent creation mints one combined id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. ACP verifies exact `Agent` ownership from the forward session map; JSON-RPC caches only disposable-child parent lineage. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index f4947e5d25..31a865c068 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -`inject: ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. +`inject: ['agents', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` (forward) with a `WeakMap` reverse map so agent-scoped approval events demultiplex in O(1). Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership: the `approval/request` answerer resolves the owning session through the reverse map and prompts only there. +The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` keyed by the shared agent/session id. Agent-scoped events derive that id from `agent.session.id` and verify the record owns the exact agent object, so a foreign same-id object cannot claim the bridge's session. Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership and prompt only the matching session. ## Session config options diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index e795c7e177..369c8ae166 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -18,12 +18,11 @@ * turn about to start) + settle the in-flight prompt * * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by id in `sessions` (forward) with an - * `agent→sessionId` reverse map for O(1) demux of `agent/*` events; every - * `session/event` and `agent/*` event is routed strictly to its owning session - * record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts ride the same ownership - * map: the bridge answers `approval/request` for its own agents over + * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; + * every `session/event` and `agent/*` event is routed strictly to its owning + * session record, so two sessions streaming at once never interleave their + * `session/update` notifications. Permission prompts use the same identity: the + * bridge answers `approval/request` for its own agents over * `session/request_permission` (see the approval answerer below) — whether a * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. * @@ -106,9 +105,7 @@ export const name = 'acp' // because `initialize` advertises `loadSession: true`. `tools` lets a tool own // how its calls render (`presentCall`/`presentResult`); the bridge looks up the // definition by name and falls back to a generic presentation when absent. -// TODO(acp-session-inject): drop `sessions`; this bridge never reads -// ctx.sessions, and agent/session ownership is already behind ctx.agents. -export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction'] +export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction'] /** * Build an ACP "invalid params" error whose human detail rides in the message. @@ -268,7 +265,6 @@ export const Config: Schema = Schema.object({ * map keyed by id (RFC 011 multi-session). */ interface SessionRecord { - sessionId: SessionId agent: Agent /** * The owned-agent disposer (from the {@link AgentHandle} the factory returned). @@ -353,15 +349,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // this warn sink so a throwing tool presenter is logged, not propagated. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) - // TODO(derive-acp-session-id): derive an event's id from agent.session and - // verify sessions.get(id)?.agent === agent; then remove this reverse map and - // SessionRecord.sessionId, whose sole read duplicates the same identity. - // Live sessions keyed by id (RFC 011 multi-session), plus an agent→sessionId - // reverse map so `agent/*` events (which carry only the Agent) demux in O(1). - // The forward record and weak reverse entry are installed together; removing - // the record releases its strong Agent reference, so the WeakMap entry expires. + // Live sessions keyed by their shared agent/session id (RFC 011 multi-session). const sessions = new Map() - const bySession = new WeakMap() // Session ids whose `session/load` is mid-`resume()` (the slot is reserved // before the async resume so a pipelined load/new for the SAME id can't create // two agents). Distinct ids load concurrently; a given id loads once at a time. @@ -382,20 +371,26 @@ export function apply(ctx: Context, config: AcpConfig): void { // `notify` never observes it unset — no undefined guard needed. let conn: AgentSideConnection + /** Return the bridge-owned record for an agent, rejecting same-id impostors. */ + const ownedRecord = (agent: Agent): SessionRecord | undefined => { + const rec = sessions.get(agent.session.id) + return rec?.agent === agent ? rec : undefined + } + userInteraction.registerProvider({ async ask(request: AskUserQuestionRequest): Promise { if (request.agent === undefined) { throw new UserInteractionError('ACP user questions must come from an agent-owned request', 'NO_AGENT') } - const sessionId = bySession.get(request.agent) - if (sessionId === undefined) { + const rec = ownedRecord(request.agent) + if (rec === undefined) { throw new UserInteractionError('ACP user question has no matching session', 'NO_SESSION') } const answers: AskUserQuestionAnswerItem[] = [] for (const question of request.questions) { const options = question.options ?? [] const response = await withAbort(conn.unstable_createElicitation( - elicitationForQuestion(sessionId, question, options), + elicitationForQuestion(rec.agent.session.id, question, options), ), request.signal).catch((error: unknown) => { if (error instanceof UserInteractionError) throw error throw new UserInteractionError('ACP elicitation request failed', 'ASK_FAILED', { cause: error }) @@ -496,7 +491,7 @@ export function apply(ctx: Context, config: AcpConfig): void { const rec = sessions.get(session.header.id) if (rec === undefined) return try { - streamSessionEventUpdate(rec.sessionId, event, notify, rec.presenter, { + streamSessionEventUpdate(rec.agent.session.id, event, notify, rec.presenter, { enabled: rec.terminalEnabled, cwd: session.header.cwd, }, { includeUserMessages: false }) @@ -527,12 +522,12 @@ export function apply(ctx: Context, config: AcpConfig): void { // allow_always is a grant-storage design the approval RFC defers, so the // prompt never offers a durable grant the harness could not honor. ctx.on('approval/request', (req, next) => { - const sessionId = bySession.get(req.agent) + const rec = ownedRecord(req.agent) // The protocol requires `toolCall` (the prompt renders attached to it), so // a request without a callId has nothing to attach to — delegate. - if (sessionId === undefined || req.callId === undefined) return next() + if (rec === undefined || req.callId === undefined) return next() return conn.requestPermission({ - sessionId, + sessionId: rec.agent.session.id, toolCall: { toolCallId: req.callId }, options: [ { optionId: 'allow-once', name: 'Allow once', kind: 'allow_once' }, @@ -639,8 +634,7 @@ export function apply(ctx: Context, config: AcpConfig): void { // turn) leaves the switch pending — it runs no step, so nothing executes // or assembles under a stale value. ctx.on('agent/prompt-submit', (agent, _content, _source, next) => { - const sessionId = bySession.get(agent) - const rec = sessionId === undefined ? undefined : sessions.get(sessionId) + const rec = ownedRecord(agent) if (rec !== undefined) flushPendingSwitches(rec) return next() }) @@ -699,9 +693,7 @@ export function apply(ctx: Context, config: AcpConfig): void { await handle.dispose() throw internalError('connection closed during session/new') } - bySession.set(handle.agent, sessionId) sessions.set(sessionId, { - sessionId, agent: handle.agent, dispose: () => handle.dispose(), presenter: makePresenter(handle.agent), @@ -773,13 +765,11 @@ export function apply(ctx: Context, config: AcpConfig): void { throw invalidParams('connection closed during session/load') } const agent = handle.agent - bySession.set(agent, sessionId) // Snapshot the terminal capability ONCE for this session (used by both // the replay below and the post-load live stream) so a later // `initialize` can't desync the call/result of a tool card. const terminalEnabled = terminalOutputCap const record: SessionRecord = { - sessionId, agent, dispose: () => handle.dispose(), presenter: makePresenter(agent), diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index 36846ac728..65679cd905 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -90,9 +90,12 @@ describe('acp bridge — approval answerer', () => { await harness.ctx.plugin(ApprovalService) harness.onPermission = () => ({ outcome: { outcome: 'selected', optionId: 'allow-once' } }) - // Not created through the bridge: no bySession entry, so the answerer must - // call next() — nobody else answers, so the seam fails closed. - const foreign = { session: { events: [{ type: 'turn/start' }], append: () => ({}) } } as unknown as Agent + const { agent } = await ownedAgentRequest(harness) + // Even an impostor that claims the bridge-owned session id must delegate: + // ownership requires the exact Agent object stored in the session record. + const foreign = { + session: { id: agent.session.id, events: [{ type: 'turn/start' }], append: () => ({}) }, + } as unknown as Agent await expect(harness.ctx.approval.request({ agent: foreign, toolName: 'echo', callId: CallId('c') })) .resolves.toBe('unavailable') expect(harness.permissionRequests).toHaveLength(0) diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index 7e780348ba..e7170c380f 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -205,7 +205,8 @@ describe('acp bridge', () => { await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) - await expect(harness.ctx.userInteraction.ask({ agent: { id: 'other' } as typeof agent, questions: [{ id: 'x', question: 'No session?' }] })) + const impostor = { session: { id: agent.session.id } } as typeof agent + await expect(harness.ctx.userInteraction.ask({ agent: impostor, questions: [{ id: 'x', question: 'No session?' }] })) .rejects.toMatchObject({ code: 'NO_SESSION' }) harness.onElicitation = () => ({ action: 'cancel' }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 007bd1a5f1..933023a2d9 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 4dbfeb0fa2..cfa083c394 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,11 +58,6 @@ interface SessionRecord { activePrompt: boolean } -interface SubagentRecord { - childSessionId: string - parentSessionId: string | undefined -} - /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -76,7 +71,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentSessions = new Map() + private readonly subagentParents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,29 +95,22 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache agent → session lineage on creation: by the time `subagent/end` - // fires the child agent may already be disposed and gone from the registry. + // Cache parent lineage on creation: by the time `subagent/end` fires the + // child agent may already be disposed and gone from the registry. The child + // session id needs no cache because it is the shared agent/session id. this.disposers.push(ctx.on('agent/created', (agent) => { - this.subagentSessions.set(String(agent.id), { - childSessionId: String(agent.session.id), - parentSessionId: agent.session.header.parentSession === undefined - ? undefined - : String(agent.session.header.parentSession), - }) + const parentSessionId = agent.session.header.parentSession + if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const rec = this.subagentSessions.get(String(info.id)) const agent = this.ctx.agents.get(info.id) - const childSessionId = rec?.childSessionId ?? (agent === undefined ? undefined : String(agent.session.id)) - const parentSessionId = rec?.parentSessionId ?? ( - agent?.session.header.parentSession === undefined ? undefined : String(agent.session.header.parentSession) - ) - if (childSessionId === undefined) return + const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + this.subagentParents.delete(info.id) this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId }), - childSessionId, + ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, ...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }), @@ -195,7 +183,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentSessions.clear() + this.subagentParents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 9260a59aae..433119e046 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,6 +272,9 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + // The backend may dispose the child before publishing its run outcome; + // only the cached parent lineage should be needed at this point. + await handle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), @@ -292,7 +295,6 @@ describe('HarnessSdkServer', () => { }, }) - await handle.dispose() await parentHandle.dispose() await server.shutdown() } finally { @@ -301,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live agent lineage for uncached subagent end events', async () => { + it('falls back to live lineage and treats the shared id as the child session id', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -365,10 +367,16 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications.some(n => - n.method === 'subagent.finished' - && n.params?.agentId === 'missing-child-agent', - )).toBe(false) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'fork', + agentId: 'missing-child-agent', + childSessionId: 'missing-child-agent', + status: 'error', + stopReason: 'error', + }, + }) await server.shutdown() } finally { From 17c99efcc14c76bbc548f64ec536d95a2dbb25c5 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:22:20 +0800 Subject: [PATCH 015/323] fix: complete unified subagent identity --- docs/module-graph.md | 12 ++++-- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 +++++++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 ------------------- packages/subagent/subagent-acp/package.json | 2 + packages/subagent/subagent-acp/src/run.ts | 16 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 2 +- .../subagent-acp/tests/subagent-acp.spec.ts | 3 +- packages/subagent/subagent/package.json | 2 + packages/support/subagent-mock/package.json | 2 + packages/workflow/workflow/package.json | 1 + pnpm-lock.yaml | 9 +++++ 13 files changed, 77 insertions(+), 54 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/module-graph.md b/docs/module-graph.md index e4d0b3367d..8ac71b11cc 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -179,6 +179,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -215,6 +216,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -265,6 +267,7 @@ flowchart TD pkg_agent_core --> pkg_tools pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -285,6 +288,7 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm @@ -362,14 +366,14 @@ flowchart TD | [`invariants`](../packages/support/invariants) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session) | | [`user-approval`](../packages/ui/user-approval) | `ui` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | -| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | +| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -380,11 +384,11 @@ flowchart TD | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`agent-core`](../packages/core/agent-core) | `core` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tools`](../packages/core/tools) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..be1052830a --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/subagent/subagent-acp/package.json b/packages/subagent/subagent-acp/package.json index e73d861a79..4c34ebe3fc 100644 --- a/packages/subagent/subagent-acp/package.json +++ b/packages/subagent/subagent-acp/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "@deepseek-ai/dsh-subagent-subprocess": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -35,6 +36,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-subagent-subprocess": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1e82ef85b0..1cc220204f 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,7 +23,6 @@ */ import { spawn } from 'node:child_process' -import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,8 +189,6 @@ function toError(value: unknown): Error { * @returns the ready run handle for the child subprocess. */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { - const id = SessionId(randomUUID()) - if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP @@ -260,7 +257,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: string | undefined + let sessionId: SessionId | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -309,7 +306,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + sessionId = SessionId(session.sessionId) if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -321,6 +318,11 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } + // The startup race can fulfill only after newSession assigned the id; this + // guard keeps that cross-closure invariant explicit for TypeScript. + /* v8 ignore next */ + if (sessionId === undefined) throw new Error('ACP child published without a session id') + const runId = sessionId const result: Promise = (async (): Promise => { try { @@ -332,7 +334,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: sessionId as string, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -366,7 +368,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id, + id: runId, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index fb200f3505..5145941526 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -99,7 +99,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } - return { sessionId: randomUUID() } + return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { // No auth methods advertised; nothing to do. diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index eed3cfe1ed..115d5c3e97 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -122,8 +122,9 @@ describe('buildChildEnv', () => { describe('dsh-subagent-acp', () => { it('drives a child process to completion and returns its streamed output', async () => { - const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn' }) + const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) + expect(run.id).toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index eb0dbf8da0..cf1ebf9485 100644 --- a/packages/subagent/subagent/package.json +++ b/packages/subagent/subagent/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -32,6 +33,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" } diff --git a/packages/support/subagent-mock/package.json b/packages/support/subagent-mock/package.json index 8980cc35d2..528691daef 100644 --- a/packages/support/subagent-mock/package.json +++ b/packages/support/subagent-mock/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -33,6 +34,7 @@ "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@cordisjs/plugin-loader": "^1.0.0-rc.4", "cordis": "^4.0.0-rc.6" diff --git a/packages/workflow/workflow/package.json b/packages/workflow/workflow/package.json index a6c004d6d0..4d79d672a1 100644 --- a/packages/workflow/workflow/package.json +++ b/packages/workflow/workflow/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d02b4a9ca6..6214564eae 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -827,6 +827,9 @@ importers: '@deepseek-ai/dsh-scope': specifier: workspace:^ version: link:../../core/scope + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -852,6 +855,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../subagent @@ -1085,6 +1091,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent From 9ebb40b84b404b3568a53cd6fab1b966e2c82c74 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:28:04 +0800 Subject: [PATCH 016/323] fix: keep SDK subagent notifications local --- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 8 +++++++- packages/ui/jsonrpc/tests/server.spec.ts | 16 +++++----------- 4 files changed, 14 insertions(+), 14 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 10521447e0..bb77717e3b 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only disposable-child parent lineage. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only local disposable-child parent lineage while leaving remote runs outside its local-session notification pair. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 933023a2d9..2324227ff7 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index cfa083c394..3c803a6c8c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -104,8 +104,14 @@ export class HarnessSdkServer { })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + const cachedParentSessionId = this.subagentParents.get(info.id) this.subagentParents.delete(info.id) + // This protocol reports LOCAL child sessions, paired with the + // session/created-driven subagent.started notification above. A remote + // provider may use a real remote SessionId for its run, but that session + // does not exist in this harness and therefore has no paired start event. + if (cachedParentSessionId === undefined && agent === undefined) return + const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 433119e046..e7f591b88f 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -303,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live lineage and treats the shared id as the child session id', async () => { + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -367,16 +367,10 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications).toContainEqual({ - method: 'subagent.finished', - params: { - provider: 'fork', - agentId: 'missing-child-agent', - childSessionId: 'missing-child-agent', - status: 'error', - stopReason: 'error', - }, - }) + expect(transport.notifications.some(n => + n.method === 'subagent.finished' + && n.params?.agentId === 'missing-child-agent', + )).toBe(false) await server.shutdown() } finally { From 225796c90dc5a6ea9b4afa2a9f4081f9d48606ae Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:32:35 +0800 Subject: [PATCH 017/323] refactor: hide the concrete agent loop --- docs/architecture.md | 2 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 26 ++++----- docs/cordis-catalog/services.md | 8 ++- docs/core-data-structures/core.md | 2 +- docs/event-producer-consumer.md | 26 ++++----- .../2026-06-21-subagent-capability-seam.md | 2 +- examples/coding-agent/tests/code-mode.e2e.ts | 6 +- examples/coding-agent/tests/harness.ts | 6 +- examples/coding-agent/tests/resume.e2e.ts | 5 +- examples/cordis-agent/tests/harness.ts | 6 +- .../bash/tool-bash/tests/integration.spec.ts | 8 +-- .../tests/compact-loop-repro.spec.ts | 6 +- .../cordis/tool-cordis/src/api-catalog.ts | 4 +- .../tool-cordis/tests/integration.spec.ts | 6 +- packages/core/README.md | 2 +- packages/core/agent-loop/README.md | 10 ++-- packages/core/agent-loop/src/index.ts | 7 +-- packages/core/agent-loop/tests/agent.spec.ts | 42 +++++++------- packages/core/agent-loop/tests/cancel.spec.ts | 22 +++++--- .../tests/config-session-id.spec.ts | 16 +++--- .../agent-loop/tests/coverage-edges.spec.ts | 16 ++++-- .../agent-loop/tests/interception.spec.ts | 10 ++-- packages/core/agent-loop/tests/loop.spec.ts | 22 +++++--- .../core/agent-loop/tests/properties.spec.ts | 12 ++-- .../tests/request-reconstruction.spec.ts | 10 ++-- packages/core/agent-loop/tests/resume.spec.ts | 24 ++++---- .../agent-loop/tests/review-fixes.spec.ts | 56 ++++++++++--------- .../agent-loop/tests/scope-lifecycle.spec.ts | 8 +-- .../core/agent-loop/tests/tool-order.spec.ts | 6 +- .../core/agent-loop/tests/turn-stop.spec.ts | 6 +- packages/core/agent/src/types.ts | 5 +- .../tests/repeat-tool-guard.spec.ts | 12 ++-- .../hooks/hooks-claude/tests/bridge.spec.ts | 8 +-- .../hooks/hooks-claude/tests/coverage.spec.ts | 14 ++--- .../hooks/hooks-codex/tests/bridge.spec.ts | 8 +-- .../hooks/hooks-codex/tests/coverage.spec.ts | 10 ++-- .../todo/tool-todo/tests/integration.spec.ts | 6 +- packages/ui/acp/README.md | 2 +- packages/ui/acp/src/index.ts | 2 +- 40 files changed, 234 insertions(+), 217 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..272191c9c6 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -17,7 +17,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | | `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | -| `ctx.agentLoop` | `dsh-agent-loop` | shipped `ReactLoopAgent` driver | +| `ctx.agentLoop` | `dsh-agent-loop` | shipped concrete `Agent` driver | ### Capability Services diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4ae020f0be..20d90d1e8b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -129,7 +129,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:323`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a5e018079a..32d697f1eb 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:304`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:303`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:319`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:318`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:593`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:592`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:426`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:425`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:444`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:443`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:348`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:347`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:473`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:472`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:525`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:524`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:369`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:368`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:332`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:540`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:539`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:558`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:557`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:575`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 4d162a55f5..89a8dc4edb 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -11,15 +11,17 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary ## `ctx.agentLoop` — `AgentLoop` -Concrete ReactLoopAgent factory and driver service. +Concrete agent factory and driver service. ```ts cordis-catalog -create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent +create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent-loop/src/index.ts:336`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index c6b74ed3c0..897b04240b 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -248,7 +248,7 @@ The fourteen event variants (`turn/start`, `turn/end`, `step/start`, `step/end`, ## The agent handle -`Agent` is the surface every plugin (UI, hooks, orchestrators) programs against. The concrete implementation is `ReactLoopAgent` in dsh-agent-loop; nothing outside the loop depends on the implementation. +`Agent` is the surface every plugin (UI, hooks, orchestrators) programs against. The concrete implementation is package-internal to dsh-agent-loop; nothing outside the loop depends on it. Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..ba0d9722b2 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:576`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:303`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:318`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:592`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:425`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:443`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:347`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:472`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:524`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:368`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:332`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:539`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:557`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:575`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md index 652eac5522..3c42e83691 100644 --- a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md @@ -10,7 +10,7 @@ The harness has a long-deferred seam for **subagents** — an agent delegating w The distinctive requirement — the one that shapes the whole design — is that **multiple subagent implementations must coexist at runtime**. A parent may want a cheap in-process child for a scoped subtask AND an isolated out-of-process child (over ACP) in the same session. The transports we foresee: -- **in-process** — a child `ReactLoopAgent` on the same `Context` (the cheapest, and nearly free given the existing agent factory); +- **in-process** — a child concrete `Agent` on the same `Context` (the cheapest, and nearly free given the existing agent factory); - **ACP** — act as an ACP *client* driving another agent process (which can be another instance of ourselves); - later: **A2A**, the **Codex app-server**, and the **Claude Code Agent SDK** — each the same out-of-process "start a child, prompt it, stream updates, cancel" shape as the ACP backend. diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 22446f0dc3..176b2898d6 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -8,9 +8,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -58,7 +58,7 @@ async function codeModeHarness(cwd: string): Promise { return harness } -function waitForIdle(harness: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(harness: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = harness.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..6535e30ac3 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -4,8 +4,8 @@ import SessionStore from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' @@ -70,7 +70,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio return ctx } -export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +export function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 48e135ad92..486e32608c 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -3,7 +3,6 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import type { Context } from 'cordis' -import type { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { SessionId } from '@deepseek-ai/dsh-session' import { codingHarness, finalText, SYSTEM_PROMPT, waitForIdle } from './harness.ts' @@ -41,7 +40,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const first = (await ctx.agents.create({ sessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, - })).agent as ReactLoopAgent + })).agent first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }]) await waitForIdle(ctx, first) await ctx.fiber.dispose() @@ -54,7 +53,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const resumed = (await ctx.agents.resume({ resumeSessionId: SESSION_ID, agentOptions: { model: 'deepseek-v4-flash' }, - })).agent as ReactLoopAgent + })).agent expect(resumed.session.id).toBe(SESSION_ID) // The prior user turn is in the rehydrated log before the model is asked. expect(JSON.stringify(resumed.session.deriveMessages())).toContain(SECRET) diff --git a/examples/cordis-agent/tests/harness.ts b/examples/cordis-agent/tests/harness.ts index 78e5b0bb93..c9ccd59767 100644 --- a/examples/cordis-agent/tests/harness.ts +++ b/examples/cordis-agent/tests/harness.ts @@ -3,8 +3,8 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis' @@ -34,7 +34,7 @@ export async function cordisHarness(): Promise { return ctx } -export function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +export function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index 3ab3ae6628..b8275fedba 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -5,9 +5,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { BashTaskId } from '@deepseek-ai/dsh-bash' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -43,7 +43,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index 52a2ecd134..c9d9e34b26 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -7,9 +7,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import { isToolPairingBalanced } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { SurfaceEvent } from '@deepseek-ai/dsh-session' @@ -105,7 +105,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr return { ctx, compact } } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..23a8c8e1d0 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -54,9 +54,9 @@ export interface TypeApiEntry { export const SERVICE_API: readonly ServiceApiEntry[] = [ { key: 'agentLoop', - summary: 'Concrete ReactLoopAgent factory and driver service.', + summary: 'Concrete agent factory and driver service.', methods: [ - 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent', + 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent', 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', ], diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 0d4c6c5c18..25adece9bc 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -4,9 +4,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as ToolCordis from '../src/index.ts' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' import { REVERSE_TOOL_CODE } from './helpers.ts' @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/core/README.md b/packages/core/README.md index b132b04d49..d822627136 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -9,7 +9,7 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | -| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` | +| `agent-loop/` | The concrete `Agent` plugin and loop driver | `ctx.agentLoop` | | `agent-core/` | Bundle plugin: the default executor-less/UI-less spine as code | (loads the spine) | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f40577bb95..f5b25c0e25 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -1,6 +1,6 @@ # dsh-agent-loop -THE concrete agent plugin: `ReactLoopAgent` and the loop driver. Implements the `Agent` interface and drives the session/turn/step lifecycle. +THE concrete agent plugin and loop driver. Its package-internal implementation satisfies the `Agent` interface and drives the session/turn/step lifecycle. This is the only package in the harness that contains concrete loop logic. Everything else is an abstract service or a plugin against extension seams — new behavior goes into plugins, not here. @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): Agent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -42,11 +42,9 @@ interface Config { Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. -### Exported concrete class +### Internal concrete driver -- `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy. - -`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. +The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. The concrete `send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33276c01f8..c9c97fb206 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -12,6 +12,7 @@ import { createScope } from '@deepseek-ai/dsh-scope' import type { Scope } from '@deepseek-ai/dsh-scope' import { agentEvents } from '@deepseek-ai/dsh-agent' import type { + Agent, AgentFactory, AgentHandle, AgentOptions, @@ -32,8 +33,6 @@ import { } from './agent.ts' import type { PreparedReactLoopAgent } from './agent.ts' -export { ReactLoopAgent } from './agent.ts' - /** Fiber states that cannot own or serve a new lifecycle. */ const INACTIVE_STATES: ReadonlySet = new Set([ FiberState.UNLOADING, @@ -333,7 +332,7 @@ export interface Config { })[] } -/** Concrete ReactLoopAgent factory and driver service. */ +/** Concrete agent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -389,7 +388,7 @@ export class AgentLoop extends Service implements AgentFactory { * @param meta - optional fresh-session workspace metadata. * @returns the published running agent. */ - create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): ReactLoopAgent { + create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent { const loopCtx = this.runtime.ctx const transaction = new AgentCreationTransaction(loopCtx, this.ctx, this.ownership, id) try { diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 56d6489fbe..7969d18200 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -4,11 +4,15 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { bindReactLoopAgentContext, prepareReactLoopAgent } from '../src/agent.ts' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' +import { bindReactLoopAgentContext, prepareReactLoopAgent, type ReactLoopAgent } from '../src/agent.ts' import { MockAdapter, textResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -21,7 +25,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -32,7 +36,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopAgent['status']): Promise { +function waitForStatus(ctx: Context, agent: Agent, expected: Agent['status']): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === expected) { @@ -43,11 +47,11 @@ function waitForStatus(ctx: Context, agent: ReactLoopAgent, expected: ReactLoopA }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -describe('ReactLoopAgent', () => { +describe('Agent', () => { it('rejects access before context binding and a second driver for one session', async () => { const ctx = new Context() await ctx.plugin(SessionStore) @@ -70,7 +74,7 @@ describe('ReactLoopAgent', () => { expect(agent.options).toBe(options) expect(agent.id).toBe('owned-bindings') expect(agent.session.id).toBe(agent.id) - expect(() => { bindReactLoopAgentContext(agent, new Context()) }).toThrow(/context is already bound/) + expect(() => { bindReactLoopAgentContext(agent as ReactLoopAgent, new Context()) }).toThrow(/context is already bound/) await ctx.fiber.dispose() }) @@ -78,14 +82,14 @@ describe('ReactLoopAgent', () => { it('send() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.send([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -93,14 +97,14 @@ describe('ReactLoopAgent', () => { it('steer() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.steer([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -108,14 +112,14 @@ describe('ReactLoopAgent', () => { it('inject() throws after disposal', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(() => { agent.inject([{ type: 'text', text: 'too late' }]) }).toThrow('disposed') }) @@ -251,7 +255,7 @@ describe('ReactLoopAgent', () => { }) it('disposer is idempotent (double-stop)', async () => { - // Create a bare ReactLoopAgent and start it through the package-internal + // Create a bare Agent and start it through the package-internal // test seam. Then call its disposer twice — the second call hits the // early-return branch. const ctx = new Context() @@ -367,7 +371,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() subscribed while running resolves via done when the agent is then disposed', async () => { // Covers the waiter's disposed arm: whenIdle() queues an internal waiter // while running (not the fast path), then the disposer settles it and chains - // `done` (loop exit), not an eager resolve. A bare ReactLoopAgent + direct + // `done` (loop exit), not an eager resolve. A bare Agent + direct // internal driver disposer keeps the emit synchronous. const ctx = new Context() await ctx.plugin(LlmService) @@ -401,7 +405,7 @@ describe('ReactLoopAgent', () => { // it. Regression for the round-3 whenIdle finding. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -422,7 +426,7 @@ describe('ReactLoopAgent', () => { // only after `done` — i.e. the loop has actually exited. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -430,7 +434,7 @@ describe('ReactLoopAgent', () => { await new Promise(r => setTimeout(r, 30)) let doneResolved = false - void agent.done.then(() => { doneResolved = true }) + void driverDone(agent).then(() => { doneResolved = true }) await fiber.dispose() // sets status disposed, aborts, drains the loop expect(agent.status).toBe('disposed') diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 82b1f6c58c..d88d58a340 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -16,11 +16,15 @@ import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -33,12 +37,12 @@ async function harness(adapter: MockAdapter) { return ctx } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } /** Resolve on the agent's next idle transition (event-based, not status poll). */ -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -47,7 +51,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { } /** All user-message texts recorded in the log (to assert what actually ran). */ -function userTexts(agent: ReactLoopAgent): string[] { +function userTexts(agent: Agent): string[] { return agent.session.events .filter(e => e.type === 'user/message') .flatMap(e => e.type === 'user/message' ? e.data.content : []) @@ -207,7 +211,7 @@ describe('Agent.cancel()', () => { sessionId: SessionId('dispose-prefix-session'), agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent let disposalDone: Promise | undefined let streamed = false @@ -220,7 +224,7 @@ describe('Agent.cancel()', () => { send(agent, 'go') await new Promise(resolve => setTimeout(resolve, 0)) await disposalDone - await agent.done + await driverDone(agent) // No step opened, no model call ran, and the turn closed disposed. expect(streamed).toBe(false) @@ -337,7 +341,7 @@ describe('Agent.cancel()', () => { sessionId: SessionId('dispose-step-start-session'), agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent let disposalDone: Promise | undefined let streamed = false @@ -348,7 +352,7 @@ describe('Agent.cancel()', () => { send(agent, 'go') await disposalDone - await agent.done + await driverDone(agent) expect(streamed).toBe(false) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 134ea68c32..428581bb58 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -7,16 +7,16 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' const dirs: string[] = [] afterEach(async () => { for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) }) -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -57,7 +57,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) - const a1 = ctx1.agents.list()[0] as ReactLoopAgent + const a1 = ctx1.agents.list()[0] as Agent expect(a1.id).toBe(a1.session.id) expect(a1.session.id).toMatch(idPattern) expect(ctx1.agents.get(SessionId('cfg'))).toBeUndefined() @@ -76,7 +76,7 @@ describe('config-driven session id', () => { await ctx2.plugin(AgentLoop, { agents: [{ id: 'cfg', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) - const a2 = ctx2.agents.list()[0] as ReactLoopAgent + const a2 = ctx2.agents.list()[0] as Agent expect(a2.id).toBe(a2.session.id) expect(a2.session.id).toMatch(idPattern) expect(a2.session.id).not.toBe(a1.session.id) @@ -100,7 +100,7 @@ describe('config-driven session id', () => { await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sticky-1') })).agent a1.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -119,10 +119,10 @@ describe('config-driven session id', () => { ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) // The deferred resume runs on a microtask after the backend is available. - let resumed: ReactLoopAgent | undefined + let resumed: Agent | undefined for (let i = 0; i < 50 && !resumed; i++) { await new Promise(r => setTimeout(r, 5)) - resumed = ctx2.agents.get(SessionId('sticky-1')) as ReactLoopAgent | undefined + resumed = ctx2.agents.get(SessionId('sticky-1')) } expect(resumed).toBeDefined() // The live session id IS the resumed id (NOT a fresh ${id}-session-), diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 4e82e398f1..708cff504b 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -5,11 +5,15 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter) { const ctx = new Context() await ctx.plugin(LlmService) @@ -22,7 +26,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -33,7 +37,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -213,7 +217,7 @@ describe('disposed vs aborted branching', () => { it('handles dispose during model streaming producing reason "disposed"', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -224,7 +228,7 @@ describe('disposed vs aborted branching', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() // dispose during hang - await agent.done + await driverDone(agent) // The review-fixes test for 'HIGH: disposed status' already covers // this assertion path. The reason is 'disposed' because isDisposed() is diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 8c95be0d82..bbae57d7f9 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -4,9 +4,9 @@ import LlmService, { CallId, type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' /** @@ -30,7 +30,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -41,11 +41,11 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index c4e49e0fa5..49a7c6a328 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -4,11 +4,15 @@ import LlmService, { CallId, StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + async function harness(adapter: MockAdapter, persona = '') { const ctx = new Context() await ctx.plugin(LlmService) @@ -26,7 +30,7 @@ async function harness(adapter: MockAdapter, persona = '') { * invoke this right after send(), when the loop hasn't woken yet (status is * still 'idle' synchronously), so polling the current status would lie. */ -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -37,7 +41,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -175,7 +179,7 @@ describe('agent loop', () => { agentOptions: { model: 'mock' }, }) - const agent = handle.agent as ReactLoopAgent + const agent = handle.agent send(agent, 'hi') await waitForIdle(ctx, agent) @@ -911,7 +915,7 @@ describe('agent loop', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -922,7 +926,7 @@ describe('agent loop', () => { expect(agent.status).toBe('running') await fiber.dispose() - await agent.done + await driverDone(agent) expect(agent.status).toBe('disposed') expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() @@ -942,7 +946,7 @@ describe('agent loop', () => { }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agents.list()[0]! as ReactLoopAgent + const agent = ctx.agents.list()[0]! expect(agent).toBeDefined() expect(agent.id).toBe(agent.session.id) expect(agent.id).toMatch(/^config-agent-session-/) @@ -965,7 +969,7 @@ describe('agent loop', () => { agents: [{ id: 'config-agent', model: 'mock', cwd: '/work/project' }], }) - const agent = ctx.agents.list()[0]! as ReactLoopAgent + const agent = ctx.agents.list()[0]! expect(agent.session.header.cwd).toBe('/work/project') }) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index b3653d6540..a4539587d5 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -17,9 +17,9 @@ import { LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' /** A never-exhausting adapter: every model call returns the same short reply. */ @@ -48,7 +48,7 @@ async function harness() { } /** Resolve on the agent's next transition to idle (event-based, not polled). */ -function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function nextIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -61,7 +61,7 @@ function nextIdle(ctx: Context, agent: ReactLoopAgent): Promise { /** Record every status transition for the legal-machine assertion. Returns * the seen list plus a disposer for the listener (per the registry convention). */ -function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; dispose: () => void } { +function recordStatus(ctx: Context, agent: Agent): { seen: string[]; dispose: () => void } { const seen: string[] = [] const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent) seen.push(status) @@ -69,13 +69,13 @@ function recordStatus(ctx: Context, agent: ReactLoopAgent): { seen: string[]; di return { seen, dispose } } -function userMessageTexts(agent: ReactLoopAgent): string[] { +function userMessageTexts(agent: Agent): string[] { return agent.session.events .filter(e => e.type === 'user/message') .map(e => (e.data as { content: { type: string; text?: string }[] }).content.map(b => b.text ?? '').join('')) } -function turnNumbers(agent: ReactLoopAgent): number[] { +function turnNumbers(agent: Agent): number[] { return agent.session.events .filter(e => e.type === 'turn/start') .map(e => (e.data as { turn: number }).turn) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 202a8f6795..03b9a058ea 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -15,9 +15,9 @@ import type { GenerateOptions } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter, persona = 'stable base') { @@ -32,7 +32,7 @@ async function harness(adapter: MockAdapter, persona = 'stable base') { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -43,7 +43,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -229,7 +229,7 @@ describe('request stability across the loop', () => { seed: [...agent.session.events], agentOptions: { model: 'mock' }, }) - const agent2 = handle.agent as ReactLoopAgent + const agent2 = handle.agent send(agent2, 'second') await waitForIdle(ctx2, agent2) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index f5809575ab..630331c39c 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -8,10 +8,10 @@ import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' const dirs: string[] = [] @@ -51,7 +51,7 @@ async function persistSession(sessionId: SessionId): Promise { return root } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -124,7 +124,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: create a no-cwd session and run a turn. const adapter1 = new MockAdapter([textResponse('a')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('nocwd-sess') })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) await ctx1.fiber.dispose() @@ -140,7 +140,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('nocwd-sess') })).agent expect(a2.session.header.cwd).toBeUndefined() await ctx2.fiber.dispose() }) @@ -151,7 +151,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const sources1: string[] = [] ctx1.on('agent/session-start', (_agent, source) => void sources1.push(source)) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('start-sess') })).agent expect(sources1).toEqual(['startup']) a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) @@ -443,7 +443,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('forked-sess') })).agent expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) @@ -457,7 +457,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // disk, since a crash before the next turn would otherwise lose it. const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -482,7 +482,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // drop it on reload (the bug this guards). const adapter1 = new MockAdapter([textResponse('answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('inject-sess'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'q' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) a1.inject([{ type: 'text', text: 'background task 42 finished' }], { source: { kind: 'plugin', plugin: 'tool-bash' } }) @@ -500,7 +500,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('inject-sess') })).agent const flat = JSON.stringify(a2.session.deriveMessages()) expect(flat).toContain('background task 42 finished') await ctx2.fiber.dispose() @@ -510,7 +510,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // Lifecycle 1: run one full turn, persisting it. const adapter1 = new MockAdapter([textResponse('first answer')]) const { ctx: ctx1, root } = await persistentHarness(adapter1) - const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent as ReactLoopAgent + const a1 = (await ctx1.agents.create({ sessionId: SessionId('sess-resume'), meta: { cwd: '/w' } })).agent a1.send([{ type: 'text', text: 'first question' }], { source: { kind: 'user' } }) await waitForIdle(ctx1, a1) const events1 = [...a1.session.events] @@ -530,7 +530,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) - const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent as ReactLoopAgent + const a2 = (await ctx2.agents.resume({ resumeSessionId: SessionId('sess-resume') })).agent // The resumed session carries the prior history… expect(a2.session.id).toBe('sess-resume') expect(a2.session.events.length).toBe(events1.length) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 942199e9eb..2664e38c04 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -4,13 +4,17 @@ import LlmService, { CallId, ContentBlock, MessageSource, StreamChunk } from '@d import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationDecision } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationDecision } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' +function driverDone(agent: Agent): Promise { + return (agent as Agent & { done: Promise }).done +} + /** Regression tests for agent-loop boundary, identity, and lifecycle contracts. */ async function harness(adapter: MockAdapter) { @@ -25,7 +29,7 @@ async function harness(adapter: MockAdapter) { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -36,7 +40,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function send(agent: ReactLoopAgent, text: string) { +function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } @@ -324,7 +328,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -337,7 +341,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done + await driverDone(agent) expect(statuses).toEqual(['running', 'disposed']) expect(reasons).toEqual([{ kind: 'disposed' }]) @@ -347,7 +351,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('scoped'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -359,7 +363,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() - await agent.done // must not hang + await driverDone(agent) // must not hang expect(agent.status).toBe('disposed') expect(ctx.agents.get(SessionId('scoped'))).toBeUndefined() // unregistered despite the throw @@ -697,7 +701,7 @@ describe('turn and step boundary recovery', () => { } /** Count turn/step boundary events for balance assertions. */ - function boundaryCounts(agent: ReactLoopAgent) { + function boundaryCounts(agent: Agent) { const e = [...agent.session.events] return { turnStart: e.filter(x => x.type === 'turn/start').length, @@ -871,7 +875,7 @@ describe('turn and step boundary recovery', () => { // balanced with reason disposed (no error event for a disposal). const adapter = new MockAdapter(['hang']) const ctx = await balancedHarness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -882,7 +886,7 @@ describe('turn and step boundary recovery', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) await fiber.dispose() // dispose during the hanging step - await agent.done + await driverDone(agent) const e = [...agent.session.events] const turnStarts = e.filter(x => x.type === 'turn/start').length @@ -900,7 +904,7 @@ describe('turn and step boundary recovery', () => { // and must preserve reason=disposed rather than rewrite it as a plugin error. const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-prestep-dispose-throw'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -919,7 +923,7 @@ describe('turn and step boundary recovery', () => { ctx.on('agent/error', (_a, _t, _s, error) => void errorEmits.push(error)) send(agent, 'go') - await agent.done + await driverDone(agent) const e = [...agent.session.events] // Balanced: one turn/start, one turn/end carrying disposed (NOT error). @@ -1148,7 +1152,7 @@ describe('disposal and cancellation during pre-step assembly', () => { // calls stop() synchronously, setting status=disposed), then release the // block. The loop must check isDisposed() after assembly and end the turn // `disposed` — no LLM call. Don't await fiber.dispose() before releasing - // the blocker: the dispose chain awaits agent.done, which hangs until the + // the blocker: the dispose chain awaits driverDone(agent), which hangs until the // loop unblocks. const adapter = new MockAdapter(['hang']) let releaseAssemble!: () => void @@ -1170,7 +1174,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1183,15 +1187,15 @@ describe('disposal and cancellation during pre-step assembly', () => { await new Promise(r => setTimeout(r, 50)) // Start disposal — stop() sets status=disposed synchronously, then the - // disposer's await agent.done hangs because the loop is blocked in the + // disposer's await driverDone(agent) hangs because the loop is blocked in the // waterfall. Do NOT await yet; release the blocker first. const disposalDone = fiber.dispose() // Now release the blocked waterfall — the loop unblocks, checks - // isDisposed(), and exits, which resolves agent.done and disposalDone. + // isDisposed(), and exits, which resolves driverDone(agent) and disposalDone. releaseAssemble() await disposalDone - await agent.done + await driverDone(agent) unlisten() const e = [...agent.session.events] @@ -1226,7 +1230,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-cancel-assemble'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1241,7 +1245,7 @@ describe('disposal and cancellation during pre-step assembly', () => { releaseAssemble() await waitForIdle(ctx, agent) await fiber.dispose() - await agent.done + await driverDone(agent) unlisten() const e = [...agent.session.events] @@ -1281,7 +1285,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await blocker }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1296,7 +1300,7 @@ describe('disposal and cancellation during pre-step assembly', () => { const disposalDone = fiber.dispose() releasePreStep() await disposalDone - await agent.done + await driverDone(agent) // After the pre-step seam finishes, the post-seam cancel/dispose check // catches disposal. The step was never opened, no LLM call was made. @@ -1333,7 +1337,7 @@ describe('disposal and cancellation during pre-step assembly', () => { await blocker }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-cancel-prestep'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1348,7 +1352,7 @@ describe('disposal and cancellation during pre-step assembly', () => { releasePreStep() await waitForIdle(ctx, agent) await fiber.dispose() - await agent.done + await driverDone(agent) const e = [...agent.session.events] expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1) @@ -1383,7 +1387,7 @@ describe('disposal and cancellation during pre-step assembly', () => { return next() }) - let agent!: ReactLoopAgent + let agent!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { agent = inner.agentLoop.create(SessionId('a-dispose-no-leak'), { model: 'mock' }) }, { inject: ['agentLoop'] })) @@ -1394,7 +1398,7 @@ describe('disposal and cancellation during pre-step assembly', () => { const disposalDone = fiber.dispose() releaseAssemble() await disposalDone - await agent.done + await driverDone(agent) const e = [...agent.session.events] expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1) diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index c68d96e525..57dae254c8 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -8,7 +8,7 @@ import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -28,7 +28,7 @@ async function harness(adapter: MockAdapter = new MockAdapter([textResponse('ok' return (await harnessWithLoop(adapter)).ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { @@ -718,7 +718,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let ownerCtx!: Context let creating!: ReturnType - let announced!: ReactLoopAgent + let announced!: Agent const statuses: string[] = [] let scopeDisposed = false let observerSawLive = false @@ -727,7 +727,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('agent/session-start', (agent) => { if (agent.id !== SessionId('session-start-dispose-s')) return - announced = agent as ReactLoopAgent + announced = agent disposeCurrentLifecycle(ownerCtx) }) ctx.on('agent/session-start', (agent) => { diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 1085f01a4c..3b7df63965 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -14,9 +14,9 @@ import SessionStore, { SessionId, foldRequestHeader } from '@deepseek-ai/dsh-ses import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['toolOrder']) { @@ -31,7 +31,7 @@ async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['too return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c7823a2aa5..90bc0f9558 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -4,9 +4,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry, { type ContinuationStop } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent, type ContinuationStop } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -23,7 +23,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function send(agent: ReactLoopAgent, text = 'go'): Promise { +function send(agent: Agent, text = 'go'): Promise { agent.send([{ type: 'text', text }]) return agent.whenIdle() } diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index b0fb78ad66..edd38e31b6 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -168,9 +168,8 @@ export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' /** * The agent handle — the surface every plugin (UI, hooks, orchestrators) - * programs against. The concrete implementation lives in - * `@deepseek-ai/dsh-agent-loop` (class `ReactLoopAgent`); nothing outside the loop - * package should depend on the implementation. + * programs against. The concrete implementation is package-internal to + * `@deepseek-ai/dsh-agent-loop`; nothing outside that package depends on it. */ export interface Agent { /** The single identity shared with {@link session}. */ diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 9538166fc4..4f7015d8c4 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -4,9 +4,9 @@ import LlmService, { CallId } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as RepeatToolGuard from '@deepseek-ai/dsh-repeat-tool-guard' import type { Config } from '@deepseek-ai/dsh-repeat-tool-guard' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -34,12 +34,12 @@ async function harness(config: Config = {}): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } /** Every `context/message` in the agent's log, flattened to joined text + source for terse assertions. */ -function reminders(agent: ReactLoopAgent): { text: string; source: unknown }[] { +function reminders(agent: Agent): { text: string; source: unknown }[] { return [...agent.session.events] .filter((e): e is SessionEvent<'context/message'> => e.type === 'context/message') .map(e => ({ @@ -255,14 +255,14 @@ describe('chain semantics', () => { ])) // Loop agents are torn down by disposing the scope that created them // (the loop.spec pattern): a child plugin fiber owns `first`. - let first!: ReactLoopAgent + let first!: Agent const fiber = await ctx.plugin(Object.assign((inner: Context) => { first = inner.agentLoop.create(SessionId('reused'), { model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() - await first.done + await first.whenIdle() const second = ctx.agentLoop.create(SessionId('reused'), { model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2f0a2666c9..2c26d64f5a 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -8,9 +8,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -58,7 +58,7 @@ async function harnessWithFiber(configDir: string, adapter: MockAdapter): Promis return { ctx, hooks } } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } @@ -66,7 +66,7 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } -function events(agent: ReactLoopAgent): SessionEvent[] { +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 16c48aa149..7997e0fd87 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -7,9 +7,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -42,10 +42,10 @@ async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOp ctx.llm.registerAdapter(['mock'], adapter) return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll until `predicate` holds or the deadline passes — robust to detached * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { @@ -451,8 +451,8 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) - expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' + await waitForIdle(ctx, handle.agent) + expect(events(handle.agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes(`dir=${workspace}`)))).toBe(true) await handle.dispose() }) @@ -616,7 +616,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) + await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) // the marker landed in the SESSION dir const { readFileSync } = await import('node:fs') diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index 4aa678c36e..84e877af97 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -8,9 +8,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -54,14 +54,14 @@ async function harness(dir: string, adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { dispose(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll `predicate` until true or the deadline passes (detached hook effects can't be awaited directly). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 75b04d4c57..018f109a83 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -7,9 +7,9 @@ import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as HooksCodex from '@deepseek-ai/dsh-hooks-codex' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -33,10 +33,10 @@ async function harness(configPath: string, adapter: MockAdapter, opts: { stderrS ctx.llm.registerAdapter(['mock'], adapter) return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const d = ctx.on('agent/status', (s, st) => { if (s === agent && st === 'idle') { d(); resolve() } }) }) } -function events(agent: ReactLoopAgent): SessionEvent[] { return [...agent.session.events] } +function events(agent: Agent): SessionEvent[] { return [...agent.session.events] } /** Poll until `predicate` holds or the deadline passes — robust to detached * emit-listener hooks firing on a `.then` (a fixed sleep flakes under load). */ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): Promise { @@ -556,7 +556,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const { SessionId } = await import('@deepseek-ai/dsh-session') const handle = await ctx.agents.create({ sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) - await waitForIdle(ctx, handle.agent as ReactLoopAgent) + await waitForIdle(ctx, handle.agent) expect(existsSync(marker)).toBe(true) expect(readFileSync(marker, 'utf8').trim().endsWith(sessionDir.split('/').pop()!)).toBe(true) await handle.dispose() diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 8376a70425..ba2df4f6ea 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -5,9 +5,9 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -30,7 +30,7 @@ async function harness(adapter: MockAdapter): Promise { return ctx } -function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { +function waitForIdle(ctx: Context, agent: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { if (subject === agent && status === 'idle') { diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 31a865c068..9f4e8b7c0b 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-acp -The **Agent Client Protocol (ACP)** bridge: exposes DeepSeek Harness SDK agents as an ACP server over JSON-RPC stdio, so editors (Zed and other ACP clients) can drive them — streaming render, tool-call display, and resumable sessions. Zed is the current target client: baseline ACP behavior should remain reasonable for other clients, but bridge capabilities and compatibility decisions are evaluated against Zed first. **N concurrent sessions per connection** (see [ACP multi-session](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md)): each maps to its own `ReactLoopAgent`, and every event is demuxed strictly by session id so two sessions streaming at once never interleave. +The **Agent Client Protocol (ACP)** bridge: exposes DeepSeek Harness SDK agents as an ACP server over JSON-RPC stdio, so editors (Zed and other ACP clients) can drive them — streaming render, tool-call display, and resumable sessions. Zed is the current target client: baseline ACP behavior should remain reasonable for other clients, but bridge capabilities and compatibility decisions are evaluated against Zed first. **N concurrent sessions per connection** (see [ACP multi-session](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md)): each maps to its own concrete `Agent`, and every event is demuxed strictly by session id so two sessions streaming at once never interleave. It is a **client-driver / UI plugin**, the structured analogue of the readline `stdio-chat` plugin — NOT a loop change and NOT a [capability seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`. diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 369c8ae166..7c97ad715c 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -18,7 +18,7 @@ * turn about to start) + settle the in-flight prompt * * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; + * its own concrete `Agent`. Sessions are keyed by their shared agent/session id; * every `session/event` and `agent/*` event is routed strictly to its owning * session record, so two sessions streaming at once never interleave their * `session/update` notifications. Permission prompts use the same identity: the From f85b831bd2cd0d37ca814473abc17ccfb2a6c287 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:41:23 +0800 Subject: [PATCH 018/323] refactor: hide subagent implementation helpers --- ...claude-code-and-codex-subagent-backends.md | 2 +- .../subagent-acp/tests/subagent-acp.spec.ts | 3 +- .../subagent/subagent-inprocess/README.md | 2 +- .../subagent/subagent-inprocess/src/index.ts | 4 +- .../tests/subagent-inprocess.spec.ts | 24 ++---- .../tests/subagent-spawn.spec.ts | 8 +- .../subagent/subagent-subprocess/README.md | 8 +- .../subagent/subagent-subprocess/src/index.ts | 6 +- .../tests/subagent-subprocess.spec.ts | 84 +++++++------------ 9 files changed, 54 insertions(+), 87 deletions(-) diff --git a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md index 911d28cf1f..c05ae8d67f 100644 --- a/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md +++ b/docs/rfc/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md @@ -12,7 +12,7 @@ Two sibling provider packages, structural variants of the ACP backend, plus one - `@deepseek-ai/dsh-subagent-claude-code` — drives a Claude Code child through `@anthropic-ai/claude-agent-sdk`'s `query()` (the SDK runs in the parent process and spawns its bundled `claude` CLI as the subprocess). Provider name `claude-code`: the child is the Claude Code *product*, not an Anthropic model adapter — "claude" stays reserved for a future `dsh-llm` adapter. - `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package. -- `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`SENSITIVE_ENV_PATTERN`/`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. +- `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change. Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk. diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index 115d5c3e97..cc4d8307f8 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -6,7 +6,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import SubagentService from '@deepseek-ai/dsh-subagent' -import { buildChildEnv, SENSITIVE_ENV_PATTERN } from '@deepseek-ai/dsh-subagent-subprocess' +import { buildChildEnv } from '@deepseek-ai/dsh-subagent-subprocess' import type { Agent } from '@deepseek-ai/dsh-agent' import * as acp from '../src/index.ts' import { acpStopReason, acpContentText, DEFAULT_DISPOSE_EOF_GRACE_MS, DEFAULT_DISPOSE_GRACE_MS, startAcpRun, toAcpPrompt, type AcpRunSpec } from '../src/run.ts' @@ -112,7 +112,6 @@ describe('buildChildEnv', () => { // The explicitly-supplied key survives (an opt-in for the child's creds). expect(env.DEEPSEEK_API_KEY).toBe('explicit') // A normal ambient var is forwarded. - expect(SENSITIVE_ENV_PATTERN.test('PATH')).toBe(false) expect(env.PATH).toBe(process.env.PATH) } finally { delete process.env.DSH_ACP_TEST_SECRET_TOKEN diff --git a/packages/subagent/subagent-inprocess/README.md b/packages/subagent/subagent-inprocess/README.md index 48fd0a201d..83c2ba3500 100644 --- a/packages/subagent/subagent-inprocess/README.md +++ b/packages/subagent/subagent-inprocess/README.md @@ -26,7 +26,7 @@ After fulfillment, the caller owns the run. Provider-plugin unload does not revo `InProcessRunOptions` is `{ seed?: SessionEvent[] }`. Spawn omits it. Fork supplies a balanced completed-turn prefix and records its length so the result reader never mistakes a seeded parent message for child output. -`depthOf(agent)` reads `AgentOptions.subagentDepth`, treating absence as top-level depth zero and rejecting malformed stored values. `SubagentDepthError` reports an attempted child depth above `maxDepth`; an unrepresentable depth above the safe-integer domain is a `RangeError`. +Depth enforcement is internal to `startInProcessRun`: it reads `AgentOptions.subagentDepth`, treats absence as top-level depth zero, rejects malformed stored values, and reports an attempted child depth above `maxDepth`. An unrepresentable depth above the safe-integer domain is a `RangeError`. ## Structured output diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 965d9c8e78..9676c74b5b 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -36,7 +36,7 @@ declare module '@deepseek-ai/dsh-agent' { * @param agent - the agent whose options carry the depth. * @returns its non-negative safe-integer depth. */ -export function depthOf(agent: Agent): number { +function depthOf(agent: Agent): number { const depth = agent.options.subagentDepth if (depth === undefined) return 0 if (!Number.isSafeInteger(depth) || depth < 0 || Object.is(depth, -0)) { @@ -46,7 +46,7 @@ export function depthOf(agent: Agent): number { } /** Thrown when starting a child would exceed the requested depth cap. */ -export class SubagentDepthError extends Error { +class SubagentDepthError extends Error { constructor(public readonly attemptedDepth: number, public readonly maxDepth: number) { super(`subagent depth ${attemptedDepth} exceeds maxDepth ${maxDepth}`) this.name = 'SubagentDepthError' diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index aa0f946c89..c594e27fa8 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -10,7 +10,7 @@ import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService from '@deepseek-ai/dsh-subagent' import { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' -import { depthOf, SubagentDepthError, startInProcessRun } from '../src/index.ts' +import { startInProcessRun } from '../src/index.ts' type Script = ConstructorParameters[0] @@ -37,19 +37,6 @@ function text(blocks: readonly { type: string; text?: string }[]): string { return blocks.filter(block => block.type === 'text').map(block => block.text).join('') } -describe('depthOf', () => { - it('reads zero for a top-level agent and an explicit child depth', async () => { - const { parent } = await setup([]) - expect(depthOf(parent)).toBe(0) - expect(depthOf({ options: { subagentDepth: 3 } } as unknown as Agent)).toBe(3) - }) - - it.each([Number.NaN, 1.5, -1, -0, Number.MAX_SAFE_INTEGER + 1])('rejects malformed depth %s', (value) => { - expect(() => depthOf({ options: { subagentDepth: value } } as unknown as Agent)) - .toThrow('non-negative safe integer') - }) -}) - describe('startInProcessRun', () => { it('returns only after publication, drives a fresh child, and disposes it', async () => { const { ctx, parent } = await setup([textResponse('driver answer')]) @@ -58,7 +45,7 @@ describe('startInProcessRun', () => { const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('driver answer') - expect(depthOf(ctx.agents.get(run.id)!)).toBe(1) + expect(ctx.agents.get(run.id)!.options.subagentDepth).toBe(1) await run.dispose() await run.dispose() expect(ctx.agents.get(run.id)).toBeUndefined() @@ -83,7 +70,12 @@ describe('startInProcessRun', () => { await expect(startInProcessRun({ ...request(parent), maxDepth: -1 }, {})) .rejects.toThrow('non-negative safe integer') await expect(startInProcessRun({ ...request(parent), maxDepth: 0 }, {})) - .rejects.toBeInstanceOf(SubagentDepthError) + .rejects.toMatchObject({ name: 'SubagentDepthError' }) + for (const value of [Number.NaN, 1.5, -1, -0, Number.MAX_SAFE_INTEGER + 1]) { + const malformed = { options: { subagentDepth: value } } as unknown as Agent + await expect(startInProcessRun(request(malformed), {})) + .rejects.toThrow('agent subagentDepth must be a non-negative safe integer') + } const maxParent = { options: { subagentDepth: Number.MAX_SAFE_INTEGER } } as unknown as Agent await expect(startInProcessRun(request(maxParent), {})).rejects.toBeInstanceOf(RangeError) }) diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 06aa40ca9f..9b9e2a8fd2 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -13,7 +13,7 @@ import * as Invariants from '@deepseek-ai/dsh-invariants' import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' import * as spawn from '../src/index.ts' -import { depthOf, STRUCTURED_OUTPUT_TOOL, SubagentDepthError } from '@deepseek-ai/dsh-subagent-inprocess' +import { STRUCTURED_OUTPUT_TOOL } from '@deepseek-ai/dsh-subagent-inprocess' type Script = ConstructorParameters[0] @@ -118,11 +118,11 @@ describe('dsh-subagent-spawn', () => { it('stamps child depth = parent depth + 1 (via the merged AgentOptions field)', async () => { const { ctx, parent } = await setup([textResponse('x')]) - expect(depthOf(parent)).toBe(0) + expect(parent.options.subagentDepth).toBeUndefined() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent }) await run.result const child = ctx.agents.get(run.id)! - expect(depthOf(child)).toBe(1) + expect(child.options.subagentDepth).toBe(1) await run.dispose() }) @@ -130,7 +130,7 @@ describe('dsh-subagent-spawn', () => { const { ctx, parent } = await setup([]) // parent is depth 0, child would be depth 1 — cap at 0 forbids any child. await expect(start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent, maxDepth: 0 })) - .rejects.toThrow(SubagentDepthError) + .rejects.toThrow('subagent depth 1 exceeds maxDepth 0') }) it('maps a child that hit its token ceiling to stopReason "max-tokens"', async () => { diff --git a/packages/subagent/subagent-subprocess/README.md b/packages/subagent/subagent-subprocess/README.md index ccc68bf31b..c8b8a06437 100644 --- a/packages/subagent/subagent-subprocess/README.md +++ b/packages/subagent/subagent-subprocess/README.md @@ -6,7 +6,7 @@ Every tunable is a **parameter**: the dispose ladder takes its grace periods per ## What it exports -### `SENSITIVE_ENV_PATTERN` / `buildChildEnv(extra)` +### `buildChildEnv(extra)` The credential env scrub (same pattern as the [bash executor](../../bash/bash-local/README.md)): the child env is the ambient env minus credential-shaped vars (`/KEY|SECRET|TOKEN/i`), with `extra` layered on top AFTER the scrub. `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive, so the child CLI runs normally; the parent's own secrets never leak implicitly, while an explicitly supplied credential (the child's OWN key in a backend's `env` config) still reaches the child. @@ -14,10 +14,6 @@ The credential env scrub (same pattern as the [bash executor](../../bash/bash-lo Spawn-failure capture: a promise that resolves (never rejects) with the child's first `error` event. A spawn failure such as `ENOENT` is an event, not a thrown exception — without a listener Node crashes the parent process — so call this in the same tick as `spawn()` and race it in the run's result path; a bad command then settles as an ordinary child-level failure. For a child that spawns cleanly the promise never settles. -### `waitForExit(child)` / `exitsWithin(child, ms)` - -Exit waits over a `ChildProcess`: resolve once the child exits by any code or signal (immediately if it is already gone), or race that against a timer (`true` = exited in time). The race cleans up after itself on both outcomes — the pending timer is `unref()`ed and cleared on exit, the exit listener removed on timeout — so repeated calls (the dispose ladder's tiers, a poll loop) never accumulate listeners on the child. - ### `disposeChildProcess(child, graces)` The three-tier dispose ladder. Resolves only once the child has ACTUALLY exited — quiescence reached, not merely requested (see [defensive patterns](../../../docs/defensive-patterns.md)): @@ -28,6 +24,8 @@ The three-tier dispose ladder. Resolves only once the child has ACTUALLY exited The two graces (`DisposeLadderGraces`) come from the consuming plugin's `disposeEofGraceMs`/`disposeGraceMs` Config fields; the EOF window is deliberately a separate — usually wider — grace than the signal tier, since a cooperative child's EOF teardown may itself await a signal-trapping grandchild plus a final flush. +The exit waits are internal to this ladder. They clean up their timer and listener on either outcome, so escalation never accumulates listeners on the child. + ### `createIsolatedConfigDir(prefix, pinnedPath?)` A per-run isolated config directory for an external CLI child (the target of `CLAUDE_CONFIG_DIR` / `CODEX_HOME`-style redirection), so child behavior is a function of deployment config alone — never of whatever `~/.claude` / `~/.codex`-style state exists on the host. Returns an `IsolatedConfigDir` handle: `path` goes into the child env, `remove()` runs on dispose. diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index 35d7383456..2ee2745985 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -32,7 +32,7 @@ import { join } from 'node:path' * the scrub, so an intended `DEEPSEEK_API_KEY` survives while an incidental * `AWS_SECRET_ACCESS_KEY` does not. */ -export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i +const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i /** * The ambient env minus credential-shaped vars, plus the caller's explicit @@ -72,7 +72,7 @@ export function spawnFailure(child: ChildProcess): Promise { * already gone. * @param child - the child process to await. */ -export function waitForExit(child: ChildProcess): Promise { +function waitForExit(child: ChildProcess): Promise { if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve() return new Promise(resolve => child.once('exit', () => { resolve() })) } @@ -87,7 +87,7 @@ export function waitForExit(child: ChildProcess): Promise { * @returns `true` if the child exits within `ms` (immediately if it is * already gone), `false` on timeout. */ -export function exitsWithin(child: ChildProcess, ms: number): Promise { +function exitsWithin(child: ChildProcess, ms: number): Promise { if (child.exitCode !== null || child.signalCode !== null) return Promise.resolve(true) return new Promise((resolve) => { const onExit = (): void => { diff --git a/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts b/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts index 2766ed0a41..8e19a8a4a1 100644 --- a/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts +++ b/packages/subagent/subagent-subprocess/tests/subagent-subprocess.spec.ts @@ -9,10 +9,7 @@ import { buildChildEnv, createIsolatedConfigDir, disposeChildProcess, - exitsWithin, - SENSITIVE_ENV_PATTERN, spawnFailure, - waitForExit, } from '../src/index.ts' // `rm` is wrapped (real-passthrough by default) so ONE test can inject a @@ -47,6 +44,8 @@ interface FakeChildScript { diesOn?: LethalTrigger /** Delay (ms) between the lethal trigger and the exit event. */ delayMs?: number + /** Complete the scripted exit inside the triggering call. */ + synchronousExit?: boolean /** `false` models a child spawned without a stdin pipe. */ stdin?: boolean } @@ -80,11 +79,13 @@ class FakeChild extends EventEmitter { // SIGKILL is uncatchable — it always fells the child; any other trigger // only when the scenario scripts it as the lethal one. if (trigger !== 'SIGKILL' && this.script.diesOn !== trigger) return - setTimeout(() => { + const exit = (): void => { if (trigger === 'eof') this.exitCode = 0 else this.signalCode = trigger this.emit('exit', this.exitCode, this.signalCode) - }, this.script.delayMs ?? 0) + } + if (this.script.synchronousExit === true) exit() + else setTimeout(exit, this.script.delayMs ?? 0) } } @@ -93,7 +94,7 @@ function asChild(fake: FakeChild): ChildProcess { return fake as unknown as ChildProcess } -describe('buildChildEnv / SENSITIVE_ENV_PATTERN', () => { +describe('buildChildEnv', () => { it('drops credential-shaped ambient vars (KEY/SECRET/TOKEN, case-insensitive)', () => { process.env.DSH_PROC_TEST_API_KEY = 'leak' process.env.dsh_proc_test_secret = 'leak' @@ -111,7 +112,6 @@ describe('buildChildEnv / SENSITIVE_ENV_PATTERN', () => { }) it('forwards normal ambient vars', () => { - expect(SENSITIVE_ENV_PATTERN.test('PATH')).toBe(false) expect(buildChildEnv({}).PATH).toBe(process.env.PATH) }) @@ -149,7 +149,7 @@ describe('spawnFailure', () => { const fake = new FakeChild({ diesOn: 'SIGTERM' }) const failure = spawnFailure(asChild(fake)) fake.kill('SIGTERM') - await waitForExit(asChild(fake)) + await new Promise(resolve => fake.once('exit', () => { resolve() })) // A clean lifecycle emits `exit`, never `error` — the capture stays // pending forever, so a race against it is decided by the other arms. const settled = await Promise.race([ @@ -160,51 +160,6 @@ describe('spawnFailure', () => { }) }) -describe('waitForExit / exitsWithin', () => { - it('resolves immediately for a child that already exited by code', async () => { - const fake = new FakeChild() - fake.exitCode = 0 - await expect(waitForExit(asChild(fake))).resolves.toBeUndefined() - }) - - it('resolves immediately for a child that already died by signal', async () => { - const fake = new FakeChild() - fake.signalCode = 'SIGTERM' - await expect(waitForExit(asChild(fake))).resolves.toBeUndefined() - }) - - it('resolves on the exit event of a live child', async () => { - const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) - const exited = waitForExit(asChild(fake)) - fake.kill('SIGTERM') - await expect(exited).resolves.toBeUndefined() - expect(fake.signalCode).toBe('SIGTERM') - }) - - it('exitsWithin resolves true immediately for an already-exited child (no listener attached)', async () => { - const fake = new FakeChild() - fake.exitCode = 0 - await expect(exitsWithin(asChild(fake), 1000)).resolves.toBe(true) - expect(fake.listenerCount('exit')).toBe(0) - }) - - it('exitsWithin resolves true when the child exits inside the window', async () => { - const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) - fake.kill('SIGTERM') - await expect(exitsWithin(asChild(fake), 1000)).resolves.toBe(true) - // The once-listener fired and the grace timer was cleared — nothing lingers. - expect(fake.listenerCount('exit')).toBe(0) - }) - - it('exitsWithin resolves false on timeout for a child that never exits', async () => { - const fake = new FakeChild() // nothing short of SIGKILL fells it; no signal sent - await expect(exitsWithin(asChild(fake), 20)).resolves.toBe(false) - // The timeout arm removed its exit listener: repeated waits (a poll loop, - // the ladder's tiers) never accumulate listeners on the same child. - expect(fake.listenerCount('exit')).toBe(0) - }) -}) - describe('disposeChildProcess', () => { it('returns immediately for an already-exited child (no EOF, no signals)', async () => { const fake = new FakeChild() @@ -230,12 +185,28 @@ describe('disposeChildProcess', () => { expect(fake.exitCode).toBe(0) }) + it('recognizes a child that exits synchronously on stdin EOF', async () => { + const fake = new FakeChild({ diesOn: 'eof', synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 1000, disposeGraceMs: 1000 }) + expect(fake.exitCode).toBe(0) + expect(fake.listenerCount('exit')).toBe(0) + }) + it('tier 2: a child that ignores EOF but honors SIGTERM dies on the middle rung', async () => { const fake = new FakeChild({ diesOn: 'SIGTERM', delayMs: 5 }) await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) expect(fake.stdinEnded).toBe(true) expect(fake.kills).toEqual(['SIGTERM']) expect(fake.signalCode).toBe('SIGTERM') + expect(fake.listenerCount('exit')).toBe(0) + }) + + it('recognizes a child that exits synchronously on SIGTERM', async () => { + const fake = new FakeChild({ diesOn: 'SIGTERM', synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) + expect(fake.kills).toEqual(['SIGTERM']) + expect(fake.signalCode).toBe('SIGTERM') + expect(fake.listenerCount('exit')).toBe(0) }) it('tier 3: a SIGTERM-trapping child is SIGKILLed, and dispose resolves only after the exit', async () => { @@ -247,6 +218,13 @@ describe('disposeChildProcess', () => { expect(fake.signalCode).toBe('SIGKILL') }) + it('recognizes a child already gone when the final exit wait begins', async () => { + const fake = new FakeChild({ synchronousExit: true }) + await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 20 }) + expect(fake.kills).toEqual(['SIGTERM', 'SIGKILL']) + expect(fake.signalCode).toBe('SIGKILL') + }) + it('walks the ladder for a child spawned without a stdin pipe', async () => { const fake = new FakeChild({ stdin: false, diesOn: 'SIGTERM', delayMs: 5 }) await disposeChildProcess(asChild(fake), { disposeEofGraceMs: 20, disposeGraceMs: 1000 }) From 65521b589f3ffa1a912bb3d8db05a6e2ce204a85 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:45:34 +0800 Subject: [PATCH 019/323] refactor: hide remaining subagent helpers --- ...t-variables-and-tool-guidance-ownership.md | 2 +- ...7-05-subagent-provider-lifecycle-events.md | 2 +- .../2026-06-22-fork-snapshot-scenarios.md | 2 +- packages/subagent/subagent-fork/README.md | 2 +- packages/subagent/subagent-fork/src/index.ts | 2 +- .../subagent-fork/tests/subagent-fork.spec.ts | 42 ++++++++----------- packages/subagent/tool-subagent/src/index.ts | 4 +- 7 files changed, 25 insertions(+), 31 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 0961830c1a..aae4564513 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -38,7 +38,7 @@ Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship ### The subagent conversation-history descriptor -`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag (`providerWording`): the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag: the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md b/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md index 46e7ea4e71..4a96ef7419 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md +++ b/docs/rfc/implemented/architecture/2026-07-05-subagent-provider-lifecycle-events.md @@ -4,7 +4,7 @@ Status: implemented ## Problem -[The prompt-variables RFC](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description (`providerWording`), so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. +[The prompt-variables RFC](2026-07-05-prompt-variables-and-tool-guidance-ownership.md) makes `dsh-tool-subagent` DERIVE its model-facing wording from its provider: `SubagentProvider.inheritsParentContext` (spawn/ACP `false`, fork `true`) drives both the tool description and the `prompt` parameter description, so the fork tool stops lying about context inheritance. That fix created a cross-fiber data dependency: a tool's description is fixed at TOOL REGISTRATION (deliberately — the description is where tool-choice guidance lives), but the provider arrives on its own plugin fiber, on no particular schedule. The first implementation resolved the provider at the tool plugin's `apply` time and threw when it was absent — an implicit load-order requirement ("list the backend before the tool in cordis.yml"). Review reproduced the failure that requirement hides: the cordis Loader starts sibling entries CONCURRENTLY (`Promise.all` over the group) and `Entry.init()` does not await activation, so a backend whose activation is delayed leaves the tool's fiber permanently failed even when "listed first". The ordering the requirement leaned on is not a contract the Loader offers — "async state is not synchronous state" ([defensive patterns](../../../defensive-patterns.md)). diff --git a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md b/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md index b2c39047b9..34bebd1194 100644 --- a/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md +++ b/docs/rfc/implemented/testing/2026-06-22-fork-snapshot-scenarios.md @@ -17,7 +17,7 @@ Record two scenarios against the real API, both replayed keyless in the default ### Why a completed turn-1 is required -The fork backend seeds the child with the parent's **balanced completed-turn prefix** ([`completedTurnPrefix`](../../../../packages/subagent/subagent-fork)). A parent that forks on its very first turn has no completed turn to inherit, so the seed is empty (≡ a fresh spawn, `seedLength` 0) — which would NOT exercise the slice. Both scenarios therefore use a two-prompt input: the first prompt completes a turn (establishing a codeword the child is later asked to recall), the second delegates the fork. The recalled codeword in the child's transcript is incidental to the model's behavior; the load-bearing artifact is the child fixture's recorded `seedLength`, which the replay slice consumes. +The fork backend seeds the child with the parent's **balanced completed-turn prefix**. A parent that forks on its very first turn has no completed turn to inherit, so the seed is empty (≡ a fresh spawn, `seedLength` 0) — which would NOT exercise the slice. Both scenarios therefore use a two-prompt input: the first prompt completes a turn (establishing a codeword the child is later asked to recall), the second delegates the fork. The recalled codeword in the child's transcript is incidental to the model's behavior; the load-bearing artifact is the child fixture's recorded `seedLength`, which the replay slice consumes. ## Consequences diff --git a/packages/subagent/subagent-fork/README.md b/packages/subagent/subagent-fork/README.md index bf90ecdf52..0909dc0bf1 100644 --- a/packages/subagent/subagent-fork/README.md +++ b/packages/subagent/subagent-fork/README.md @@ -6,7 +6,7 @@ The fork provider creates an in-process child seeded with the parent's completed The parent's current tool-calling turn is still open when a subagent starts: its log contains the assistant tool call but not the matching tool result or `turn/end`. Copying that raw log would give the child an invalid, unbalanced session. -Fork therefore uses `completedTurnPrefix(parent.session.events)`: the contiguous prefix ending at the last `turn/end`. The child sees all completed parent turns and none of the in-flight turn. If the parent has not completed a turn yet, the seed is empty and the child behaves like a fresh spawn. +Fork therefore computes the contiguous prefix ending at the last `turn/end`. The child sees all completed parent turns and none of the in-flight turn. If the parent has not completed a turn yet, the seed is empty and the child behaves like a fresh spawn. The seed transfers conversation history only. The child still receives a fresh flat registration scope; it does not inherit the parent's tool restrictions or authority. diff --git a/packages/subagent/subagent-fork/src/index.ts b/packages/subagent/subagent-fork/src/index.ts index ebf64e7b70..22be47cc56 100644 --- a/packages/subagent/subagent-fork/src/index.ts +++ b/packages/subagent/subagent-fork/src/index.ts @@ -54,7 +54,7 @@ export const Config: z = z.object({ * @param parent - the agent whose session log to slice. * @returns the seed events, contiguous from seq 0; empty when no turn has completed. */ -export function completedTurnPrefix(parent: Agent): SessionEvent[] { +function completedTurnPrefix(parent: Agent): SessionEvent[] { const events = parent.session.events const lastEnd = events.findLast(e => e.type === 'turn/end') if (lastEnd === undefined) return [] diff --git a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts index 360098e369..bfb0bedac7 100644 --- a/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts +++ b/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts @@ -14,7 +14,6 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent import type { StreamChunk } from '@deepseek-ai/dsh-llm' import * as fork from '../src/index.ts' import { STRUCTURED_OUTPUT_TOOL } from '@deepseek-ai/dsh-subagent-inprocess' -import { completedTurnPrefix } from '../src/index.ts' type Script = ConstructorParameters[0] @@ -52,28 +51,6 @@ function text(blocks: { type: string; text?: string }[]): string { return blocks.filter(b => b.type === 'text').map(b => b.text).join('') } -describe('completedTurnPrefix', () => { - it('returns an empty prefix for a parent that has never completed a turn', async () => { - const { parent } = await setup([]) - expect(completedTurnPrefix(parent)).toEqual([]) - }) - - it('returns the balanced prefix up to and including the last turn/end', async () => { - const { parent } = await setup([textResponse('first'), textResponse('second')]) - parent.send([{ type: 'text', text: 'q1' }]) - await parent.whenIdle() - parent.send([{ type: 'text', text: 'q2' }]) - await parent.whenIdle() - - const prefix = completedTurnPrefix(parent) - // Ends exactly at the last turn/end; seq is contiguous from 0. - expect(prefix.at(-1)?.type).toBe('turn/end') - expect(prefix.map(e => e.seq)).toEqual(prefix.map((_, i) => i)) - // Both completed turns are present. - expect(prefix.filter(e => e.type === 'turn/end')).toHaveLength(2) - }) -}) - describe('dsh-subagent-fork', () => { it('emits subagent/start only after the seeded child is published', async () => { const { ctx, parent } = await setup([textResponse('child answer')]) @@ -96,7 +73,6 @@ describe('dsh-subagent-fork', () => { // The parent has never completed a turn → empty prefix → the provider omits // the seed → the child runs fresh. Exercises the `seed.length > 0` false arm. const { ctx, parent } = await setup([textResponse('fresh child')]) - expect(completedTurnPrefix(parent)).toEqual([]) const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'child q' }], parent }) const result = await run.result expect(result.stopReason).toBe('completed') @@ -104,6 +80,24 @@ describe('dsh-subagent-fork', () => { const child = ctx.agents.get(run.id)! // Only the child's own turn — no seeded parent turns. expect(child.session.events.filter(e => e.type === 'turn/end')).toHaveLength(1) + expect(child.session.header.seedLength).toBeUndefined() + await run.dispose() + }) + + it('seeds every completed parent turn through the last turn/end', async () => { + const { ctx, parent } = await setup([textResponse('first'), textResponse('second'), textResponse('child')]) + parent.send([{ type: 'text', text: 'q1' }]) + await parent.whenIdle() + parent.send([{ type: 'text', text: 'q2' }]) + await parent.whenIdle() + const parentPrefixLen = parent.session.events.length + + const run = await start(ctx, 'fork', { prompt: [{ type: 'text', text: 'child q' }], parent }) + await run.result + const child = ctx.agents.get(run.id)! + expect(child.session.header.seedLength).toBe(parentPrefixLen) + expect(child.session.events.slice(0, parentPrefixLen).at(-1)?.type).toBe('turn/end') + expect(child.session.events.slice(0, parentPrefixLen).filter(e => e.type === 'turn/end')).toHaveLength(2) await run.dispose() }) diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index d07e6726dd..426753dbb9 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -161,13 +161,13 @@ function stopReasonError(result: SubagentResult): string | undefined { * A fresh child needs a standalone prompt; a forked child already sees the * conversation's completed turns — telling the model to restate everything * (or, worse, that the child "does not see this conversation") would be false - * for a fork. Exported for tests. + * for a fork. * @param inheritsConversation - whether the child's conversation is seeded * with the parent's completed turns; this says nothing about tool, service, * scope, or authority inheritance. * @returns the tool `description` and the `prompt` parameter description. */ -export function providerWording(inheritsConversation: boolean): { description: string; promptDescription: string } { +function providerWording(inheritsConversation: boolean): { description: string; promptDescription: string } { if (inheritsConversation) { return { description: From 5c82310f47a57f5031e3301042a53a0768a53b30 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 03:58:34 +0800 Subject: [PATCH 020/323] refactor: prune unused llm contract fields --- docs/cordis-catalog/services.md | 2 +- .../testing/2026-06-19-acp-snapshot-tests.md | 2 +- ...0-remove-redundant-snapshot-log-goldens.md | 2 +- .../error-finish/replay.override.json | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 8 ++-- .../llm/llm-deepseek/tests/adapter.spec.ts | 7 +-- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/assembler.ts | 8 ++-- packages/llm/llm/src/index.ts | 6 +-- packages/llm/llm/tests/assembler.spec.ts | 43 ++++++------------- packages/llm/llm/tests/service.spec.ts | 5 ++- packages/support/llm-replay/src/index.ts | 4 +- .../llm-replay/tests/llm-replay.spec.ts | 10 ++--- 13 files changed, 37 insertions(+), 64 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 0aea3f1589..95df09d45e 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -159,7 +159,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:86`](../../packages/llm/llm/src/index.ts) ## `ctx.sandbox` — `SandboxProvider` (abstract seam) diff --git a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md b/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md index b424a253bd..4bfa3660bf 100644 --- a/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md +++ b/docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md @@ -30,7 +30,7 @@ The replay seam is the provider-agnostic `llm/stream` waterfall ([packages/llm/l ``` { kind: 'chunks', chunks: StreamChunk[] } -| { kind: 'throw', chunks: StreamChunk[], message: string, code: string, status?: number } +| { kind: 'throw', chunks: StreamChunk[], message: string, code: string } | { kind: 'hang' } ``` diff --git a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md b/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md index 2a6f8b7ae3..a7c56af2bd 100644 --- a/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md +++ b/docs/rfc/implemented/testing/2026-06-20-remove-redundant-snapshot-log-goldens.md @@ -6,7 +6,7 @@ Status: implemented Model-driving ACP snapshot scenarios ship both `session.jsonl` and `session.golden.jsonl`. For normal recorded scenarios, `session.jsonl` is the replay fixture harvested from a real run, and the replay test normalizes the newly persisted log and compares it to `session.golden.jsonl`. In the current fixtures, the normalized recorded log and normalized golden are identical for the ordinary recorded scenarios. -Authored override scenarios (`error-finish`, `cancel`) currently use `replay.override.json` to drive model behavior and keep `session.jsonl` as a minimal dummy fixture, while `session.golden.jsonl` holds the expected persisted log. The override file is a JSON array of `ReplayEntry` objects: `{ "kind": "chunks", "chunks": StreamChunk[] }`, `{ "kind": "throw", "chunks": StreamChunk[], "message": string, "code": string, "status"?: number }`, or `{ "kind": "hang" }`. That split is also unnecessary: when an override sidecar exists, `llm-replay` replaces the derived script and does not need `session.jsonl` for model chunks, so `session.jsonl` can still be the expected session-log artifact for the scenario. +Authored override scenarios (`error-finish`, `cancel`) currently use `replay.override.json` to drive model behavior and keep `session.jsonl` as a minimal dummy fixture, while `session.golden.jsonl` holds the expected persisted log. The override file is a JSON array of `ReplayEntry` objects: `{ "kind": "chunks", "chunks": StreamChunk[] }`, `{ "kind": "throw", "chunks": StreamChunk[], "message": string, "code": string }`, or `{ "kind": "hang" }`. That split is also unnecessary: when an override sidecar exists, `llm-replay` replaces the derived script and does not need `session.jsonl` for model chunks, so `session.jsonl` can still be the expected session-log artifact for the scenario. ## Decision diff --git a/examples/acp-agent/tests/snapshots/error-finish/replay.override.json b/examples/acp-agent/tests/snapshots/error-finish/replay.override.json index eea32f25ca..cfa0d84227 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/replay.override.json +++ b/examples/acp-agent/tests/snapshots/error-finish/replay.override.json @@ -1,3 +1,3 @@ [ - { "kind": "throw", "chunks": [], "message": "simulated provider error (HTTP 401)", "code": "AUTH", "status": 401 } + { "kind": "throw", "chunks": [], "message": "simulated provider error (HTTP 401)", "code": "AUTH" } ] diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index e0627c5695..c90404720b 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -79,9 +79,9 @@ export class DeepSeekAdapter extends LlmAdapter { const parsed = await response.json() as WireError if (parsed.error?.message) message = parsed.error.message } catch { - // Paranoid by design: `code` and the HTTP status are ALREADY captured - // above (and passed to LlmError below), so the only thing this `try` - // can add is a richer provider-supplied message. A malformed, empty, + // Paranoid by design: the stable `code` and status-line message are + // already captured above, so the only thing this `try` can add is a + // richer provider-supplied message. A malformed, empty, // or non-JSON error body is a normal thing for gateways/proxies to // return on a 5xx/429 — swallowing the parse failure keeps the usable // status-line message instead of letting a JSON.parse throw mask the @@ -89,7 +89,7 @@ export class DeepSeekAdapter extends LlmAdapter { // is the sole statement, and any non-parse failure (e.g. body already // consumed) is equally non-actionable here. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, code) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..1f1aef3f05 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior, behavior]) + const server = await mockServer([behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,11 +166,6 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) - // The numeric HTTP status is carried on the error for explicit handling. - await expect( - assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - .catch((error: unknown) => (error as LlmError).status), - ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 42694ba5ea..7c847447b8 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter must identify the application on every provider HTTP reque - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. ### Real adapters diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index 1b8ba6e60c..fb34afe0b9 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -38,12 +38,10 @@ export class BlockAssembler { private _finish: FinishReason | undefined /** - * Feed one chunk. Returns the completed block when the chunk closes one - * (an explicit `block-end`), otherwise undefined. + * Feed one chunk into the assembly state. * @param chunk - the next raw chunk, in stream order. - * @returns the authoritative block from the first `block-end` at its index; undefined for every other chunk. */ - push(chunk: StreamChunk): ContentBlock | undefined { + push(chunk: StreamChunk): void { switch (chunk.type) { case 'block-start': { if (!this.partials.has(chunk.index)) { @@ -79,7 +77,7 @@ export class BlockAssembler { // re-close could rewrite a block already flushed downstream. if (partial.block) return partial.block = chunk.block - return chunk.block + return } case 'usage': { this._usage = chunk.usage diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 667e9bca78..e32894efdd 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,12 +42,10 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; - * `status` carries the HTTP status when the error originated from a non-2xx - * provider response (absent for protocol/usage errors that have no HTTP status). + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. */ export class LlmError extends HarnessError { - constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { + constructor(message: string, code: string, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/assembler.spec.ts b/packages/llm/llm/tests/assembler.spec.ts index d9a4fe33f3..0674c55fb8 100644 --- a/packages/llm/llm/tests/assembler.spec.ts +++ b/packages/llm/llm/tests/assembler.spec.ts @@ -29,12 +29,12 @@ describe('BlockAssembler', () => { expect(assembler.message().role).toBe('assistant') }) - it('returns the completed block from push() on block-end', () => { + it('records the completed block from block-end', () => { const assembler = new BlockAssembler() - expect(assembler.push({ type: 'block-start', index: 0, blockType: 'text' })).toBeUndefined() - expect(assembler.push({ type: 'text-delta', index: 0, text: 'hi' })).toBeUndefined() - const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) - expect(block).toEqual({ type: 'text', text: 'hi' }) + assembler.push({ type: 'block-start', index: 0, blockType: 'text' }) + assembler.push({ type: 'text-delta', index: 0, text: 'hi' }) + assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) + expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }]) }) it('tolerates deltas without explicit block-start/end', () => { @@ -57,8 +57,8 @@ describe('BlockAssembler', () => { // push a delta first to guarantee the partial exists assembler.push({ type: 'text-delta', index: 0, text: 'hi' }) // block-end's ensure() must find the existing partial (the second branch path) - const block = assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) - expect(block).toEqual({ type: 'text', text: 'hi' }) + assembler.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }) + expect(assembler.blocks()).toEqual([{ type: 'text', text: 'hi' }]) }) it('throws from assemble() when a partial has an unhandled blockType', () => { @@ -130,7 +130,7 @@ describe('assertNever', () => { it('BlockAssembler.push rejects chunks outside the closed StreamChunk union', () => { const assembler = new BlockAssembler() - expect(() => assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk)) + expect(() => { assembler.push({ type: 'rogue-chunk' } as unknown as StreamChunk) }) .toThrow('unreachable variant in BlockAssembler.push') }) }) @@ -140,32 +140,13 @@ describe('BlockAssembler regressions (property-test findings)', () => { // Found by fast-check (the property-testing RFC): two block-ends at the same index made the // streamed prefix (first block) disagree with final blocks() (second // block). The first close must win — same straggler rule as post-close - // deltas — so the prefix returned incrementally by push() and the final - // blocks() stay identical. + // deltas — so later chunks cannot rewrite the completed block. const chunks: StreamChunk[] = [ { type: 'block-end', index: 0, block: { type: 'reasoning', text: 'first' } }, { type: 'block-end', index: 0, block: { type: 'text', text: 'second' } }, ] - const streaming = new BlockAssembler() - const closed = [] - for (const chunk of chunks) { - const block = streaming.push(chunk) - if (block) closed.push(block) - } - - const oneShot = new BlockAssembler() - for (const chunk of chunks) oneShot.push(chunk) - - expect(closed).toEqual([{ type: 'reasoning', text: 'first' }]) - expect(oneShot.blocks()).toEqual([{ type: 'reasoning', text: 'first' }]) - expect(closed).toEqual(oneShot.blocks()) - }) - - it('push returns undefined for a duplicate block-end (it closed nothing)', () => { - const a = new BlockAssembler() - expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'x' } })) - .toEqual({ type: 'text', text: 'x' }) - expect(a.push({ type: 'block-end', index: 0, block: { type: 'text', text: 'y' } })) - .toBeUndefined() + const assembler = new BlockAssembler() + for (const chunk of chunks) assembler.push(chunk) + expect(assembler.blocks()).toEqual([{ type: 'reasoning', text: 'first' }]) }) }) diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..125a810261 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,11 +79,12 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const err = new LlmError('boom', 'AUTH', 401) + const cause = new Error('root cause') + const err = new LlmError('boom', 'AUTH', { cause }) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.status).toBe(401) + expect(err.cause).toBe(cause) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 94bd0cdd7e..b919c21176 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -74,7 +74,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -324,7 +324,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code, entry.status) + throw new LlmError(entry.message, entry.code) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 3b4e8c5fee..f7e85a74bf 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From 91075e010ab641a3cc236881d0713f68b27e8191 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 04:03:44 +0800 Subject: [PATCH 021/323] refactor: hide llm adapter helpers --- docs/config-catalog.md | 4 ++-- packages/llm/llm-deepseek/README.md | 2 ++ packages/llm/llm-deepseek/src/index.ts | 5 +---- packages/llm/llm-deepseek/tests/adapter.spec.ts | 16 +++++++++++++++- .../llm/llm-deepseek/tests/serialize.spec.ts | 2 +- packages/llm/llm-deepseek/tests/sse.spec.ts | 2 +- .../llm/llm-deepseek/tests/translate.spec.ts | 3 ++- packages/llm/llm-pi-ai/README.md | 2 ++ packages/llm/llm-pi-ai/src/index.ts | 3 +-- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 9 ++++++++- packages/llm/llm-pi-ai/tests/convert.spec.ts | 2 +- 11 files changed, 36 insertions(+), 14 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..9db148cbae 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -389,7 +389,7 @@ export interface Config { } ``` -Source: [`packages/llm/llm-deepseek/src/index.ts:43`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:40`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` @@ -420,7 +420,7 @@ export interface Config { export type PiAiReasoning = 'off' | 'high' | 'xhigh' ``` -Source: [`packages/llm/llm-pi-ai/src/index.ts:37`](../packages/llm/llm-pi-ai/src/index.ts) +Source: [`packages/llm/llm-pi-ai/src/index.ts:36`](../packages/llm/llm-pi-ai/src/index.ts) ## `@deepseek-ai/dsh-llm-replay` diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 15fad9f881..4d9ff8fcae 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -4,6 +4,8 @@ DeepSeek chat-completions adapter for the harness LLM seam: hand-rolled `fetch` A second, independent implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai` (library-backed). Same Config shape — pick one per context (registering both for the same model names throws by design). +The package root exposes the Cordis plugin contract and `DeepSeekAdapter`; wire serialization, SSE parsing, and chunk translation helpers are not part of that root contract. + ## Config ```yaml diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index 3a3d7bb4a1..3b8013de5c 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -23,12 +23,9 @@ import z from 'schemastery' import type {} from '@deepseek-ai/dsh-llm' import { DeepSeekAdapter } from './adapter.ts' -export { DeepSeekAdapter, httpErrorCode } from './adapter.ts' +export { DeepSeekAdapter } from './adapter.ts' export type { DeepSeekAdapterOptions } from './adapter.ts' -export { serializeMessages, serializeRequest } from './serialize.ts' export type { RequestDefaults } from './serialize.ts' -export { DONE, parseSse } from './sse.ts' -export { mapFinishReason, mapUsage, translate } from './translate.ts' export type * from './types.ts' export const name = 'llm-deepseek' diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 1f1aef3f05..ca9c6b7097 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' -import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek' +import { DeepSeekAdapter } from '@deepseek-ai/dsh-llm-deepseek' +import { httpErrorCode } from '../src/adapter.ts' import { assemble } from './assemble.ts' /** One scripted behavior for the next request the mock server receives. */ @@ -234,6 +235,19 @@ describe('DeepSeekAdapter against a mock server', () => { }) describe('plugin registration and config', () => { + it('keeps wire helpers off the package root', () => { + for (const helper of [ + 'httpErrorCode', + 'serializeMessages', + 'serializeRequest', + 'DONE', + 'parseSse', + 'mapFinishReason', + 'mapUsage', + 'translate', + ]) expect(LlmDeepSeek).not.toHaveProperty(helper) + }) + it('registers the configured models and unregisters on dispose (HMR safety)', async () => { const server = await mockServer([]) const ctx = new Context() diff --git a/packages/llm/llm-deepseek/tests/serialize.spec.ts b/packages/llm/llm-deepseek/tests/serialize.spec.ts index 3e533f8e7c..a1d7d8b4a7 100644 --- a/packages/llm/llm-deepseek/tests/serialize.spec.ts +++ b/packages/llm/llm-deepseek/tests/serialize.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-llm' -import { serializeMessages, serializeRequest } from '@deepseek-ai/dsh-llm-deepseek' +import { serializeMessages, serializeRequest } from '../src/serialize.ts' function request(overrides: Partial = {}): GenerateOptions { return { model: 'deepseek-v4-flash', messages: [], ...overrides } diff --git a/packages/llm/llm-deepseek/tests/sse.spec.ts b/packages/llm/llm-deepseek/tests/sse.spec.ts index 2fc297bbec..b18862e4f3 100644 --- a/packages/llm/llm-deepseek/tests/sse.spec.ts +++ b/packages/llm/llm-deepseek/tests/sse.spec.ts @@ -1,6 +1,6 @@ import { describe, expect, it } from 'vitest' import { LlmError } from '@deepseek-ai/dsh-llm' -import { DONE, parseSse } from '@deepseek-ai/dsh-llm-deepseek' +import { DONE, parseSse } from '../src/sse.ts' /** Build a byte stream from string fragments (fragments = network reads). */ async function* bytes(...fragments: (string | Uint8Array)[]): AsyncGenerator { diff --git a/packages/llm/llm-deepseek/tests/translate.spec.ts b/packages/llm/llm-deepseek/tests/translate.spec.ts index d6968faed5..e62cebc4af 100644 --- a/packages/llm/llm-deepseek/tests/translate.spec.ts +++ b/packages/llm/llm-deepseek/tests/translate.spec.ts @@ -1,7 +1,8 @@ import { describe, expect, it } from 'vitest' import { BlockAssembler, LlmError } from '@deepseek-ai/dsh-llm' import type { StreamChunk } from '@deepseek-ai/dsh-llm' -import { DONE, mapFinishReason, mapUsage, translate } from '@deepseek-ai/dsh-llm-deepseek' +import { DONE } from '../src/sse.ts' +import { mapFinishReason, mapUsage, translate } from '../src/translate.ts' async function* feed(...payloads: (string | object)[]): AsyncGenerator { for (const payload of payloads) { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index f74ccd2246..adb22c585c 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -2,6 +2,8 @@ DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai) (the LLM library behind the pi agent). +The package root exposes the Cordis plugin contract and `PiAiAdapter`; model construction and event-conversion helpers are not part of that root contract. + ## Why a second adapter exists `@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose: diff --git a/packages/llm/llm-pi-ai/src/index.ts b/packages/llm/llm-pi-ai/src/index.ts index 43468ba507..fd81b77b56 100644 --- a/packages/llm/llm-pi-ai/src/index.ts +++ b/packages/llm/llm-pi-ai/src/index.ts @@ -22,9 +22,8 @@ import type {} from '@deepseek-ai/dsh-llm' import { PiAiAdapter } from './adapter.ts' import type { PiAiReasoning } from './adapter.ts' -export { buildModel, PiAiAdapter } from './adapter.ts' +export { PiAiAdapter } from './adapter.ts' export type { PiAiAdapterOptions, PiAiReasoning } from './adapter.ts' -export { mapStopReason, mapUsage, toPiContext, toStreamChunks } from './convert.ts' export const name = 'llm-pi-ai' export const inject = ['llm'] diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index cefaa9f745..cc4f129b72 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -4,7 +4,8 @@ import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import LlmService, { CallId, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import { buildModel, PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { buildModel } from '../src/adapter.ts' import { assemble } from './assemble.ts' /** Scripted SSE responses, one per request (OpenAI chat-completions shape). */ @@ -245,6 +246,12 @@ describe('PiAiAdapter against a mock server', () => { }) describe('option spreads and env fallbacks', () => { + it('keeps adapter conversion helpers off the package root', () => { + for (const helper of ['buildModel', 'mapStopReason', 'mapUsage', 'toPiContext', 'toStreamChunks']) { + expect(LlmPiAi).not.toHaveProperty(helper) + } + }) + it('forwards temperature, maxTokens, and signal', async () => { const server = await mockServer([{ events: textEvents }]) const ctx = await harness(server.url) diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 078d2a4d3b..3dc4709603 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -2,7 +2,7 @@ import { describe, expect, it } from 'vitest' import { CallId } from '@deepseek-ai/dsh-llm' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai' -import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' +import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '../src/convert.ts' function usage(input = 0, output = 0, cacheRead = 0, cacheWrite = 0): Usage { return { From f1373cd7abc479ae89a219e6a3fad6023f66aa64 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:15:17 +0800 Subject: [PATCH 022/323] refactor: drop unused tool schema defaults --- docs/core-data-structures/tools.md | 2 -- packages/core/tools/README.md | 2 +- packages/core/tools/src/schema.ts | 10 ------- packages/core/tools/tests/tools.spec.ts | 37 ++----------------------- 4 files changed, 3 insertions(+), 48 deletions(-) diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 36c59aea17..1d59542404 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -57,8 +57,6 @@ interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] - /** Default value. */ - default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index d57aeba10b..5f06154ec4 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -77,7 +77,7 @@ ctx.tools.register(defineTool({ The helper converts the author-facing `SchemaSpec` (with `required: true` as a per-property boolean) to standard JSON Schema for the wire format and uses the same typed spec for execute/presentation validation. Raw JSON-Schema tool definitions (from MCP servers) are still accepted by the registry directly. -A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, `default` is not applied, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. +A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, and `schemaSpecToJsonSchema` in the public API for details. diff --git a/packages/core/tools/src/schema.ts b/packages/core/tools/src/schema.ts index d3a2d32e18..ad7c28760e 100644 --- a/packages/core/tools/src/schema.ts +++ b/packages/core/tools/src/schema.ts @@ -39,15 +39,6 @@ export interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] - /** - * Default value, emitted into the JSON Schema only (validation never applies - * it — see the validator note below). - * - * XXX(unused-default): no tool definition in the repo sets `default`; it rides - * into the wire schema for a model that no tool surfaces it to. Drop the field - * and its converter line unless a real tool needs a model-visible default. - */ - default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ @@ -123,7 +114,6 @@ function propToJsonSchema(prop: SchemaProp): { schema: Record; const result: Record = { type: prop.type } if (prop.description) result.description = prop.description if (prop.enum) result.enum = prop.enum - if (prop.default !== undefined) result.default = prop.default const required = prop.required === true diff --git a/packages/core/tools/tests/tools.spec.ts b/packages/core/tools/tests/tools.spec.ts index a2dff84287..2bca8e05fc 100644 --- a/packages/core/tools/tests/tools.spec.ts +++ b/packages/core/tools/tests/tools.spec.ts @@ -904,17 +904,6 @@ describe('schema DSL edge cases', () => { }) }) - it('emits default value in JSON Schema property', () => { - const spec = { - limit: { type: 'number', default: 25 }, - } satisfies SchemaSpec - const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['limit']).toMatchObject({ - type: 'number', - default: 25, - }) - }) - it('handles array items without nested properties (plain type array)', () => { const spec = { tags: { type: 'array', items: { type: 'string' } }, @@ -926,28 +915,12 @@ describe('schema DSL edge cases', () => { }) }) - it('handles enum and default together in one property', () => { - const spec = { - level: { type: 'string', enum: ['low', 'high'], default: 'low' }, - } satisfies SchemaSpec - const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['level']).toMatchObject({ - type: 'string', - enum: ['low', 'high'], - default: 'low', - }) - }) - - it('omits description, enum, default keys when not specified', () => { + it('emits only the type when optional fields are omitted', () => { const spec = { bare: { type: 'string' }, } satisfies SchemaSpec const jsonSchema = schemaSpecToJsonSchema(spec) - const prop = jsonSchema.properties['bare'] as Record - expect(prop).toEqual({ type: 'string' }) - expect('description' in prop).toBe(false) - expect('enum' in prop).toBe(false) - expect('default' in prop).toBe(false) + expect(jsonSchema.properties['bare']).toEqual({ type: 'string' }) }) it('handles array with no items (items omitted)', () => { @@ -1137,12 +1110,6 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => { expect(validateArgs(spec, { path: '/tmp', extra: 1 })).toEqual([]) }) - it('does not apply defaults (validation only)', () => { - const spec = { limit: { type: 'number', default: 25 } } satisfies SchemaSpec - // absent optional is valid, and validation does not synthesize the default - expect(validateArgs(spec, {})).toEqual([]) - }) - it('type-checks primitives', () => { const spec = { s: { type: 'string' }, From 863116daaf406d3fc6485be819bcba0fc3d275f1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:23:17 +0800 Subject: [PATCH 023/323] fix: retain dynamic tool schema defaults --- docs/core-data-structures/tools.md | 2 + .../cordis/tool-cordis/tests/mount.spec.ts | 6 ++- packages/core/tools/README.md | 2 +- packages/core/tools/src/schema.ts | 6 +++ packages/core/tools/tests/tools.spec.ts | 37 ++++++++++++++++++- 5 files changed, 49 insertions(+), 4 deletions(-) diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index 1d59542404..36c59aea17 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -57,6 +57,8 @@ interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] + /** Default value. */ + default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ diff --git a/packages/cordis/tool-cordis/tests/mount.spec.ts b/packages/cordis/tool-cordis/tests/mount.spec.ts index fc29eeb2a0..bf2e57c13e 100644 --- a/packages/cordis/tool-cordis/tests/mount.spec.ts +++ b/packages/cordis/tool-cordis/tests/mount.spec.ts @@ -185,9 +185,13 @@ describe('cordis_mount', () => { // The registered schema is canonical JSON Schema derived from the DSL: // the required array survived, integer became number, extra is optional. const schema = ctx.tools.schemas().find(s => s.name === 'json_schema_tool')! - const parameters = schema.parameters as { properties: Record; required?: string[] } + const parameters = schema.parameters as { + properties: Record + required?: string[] + } expect(parameters.required).toEqual(['text']) expect(parameters.properties.count!.type).toBe('number') + expect(parameters.properties.count!.default).toBe(1) expect(parameters.properties.mode!.enum).toEqual(['fast', 'slow']) // Arg validation enforces the normalized spec: text required, extra not. expect((await call(ctx, 'json_schema_tool', { count: 2 })).isError).toBe(true) diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 5f06154ec4..d57aeba10b 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -77,7 +77,7 @@ ctx.tools.register(defineTool({ The helper converts the author-facing `SchemaSpec` (with `required: true` as a per-property boolean) to standard JSON Schema for the wire format and uses the same typed spec for execute/presentation validation. Raw JSON-Schema tool definitions (from MCP servers) are still accepted by the registry directly. -A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. +A `defineTool` tool also **validates the model-generated arguments against its `SchemaSpec` before `execute` runs** (`validateArgs`). The model's JSON is untrusted — `InferArgs` is a compile-time claim, not a runtime guarantee — so on a mismatch (missing required key, wrong primitive, bad enum member, nested violation) the tool throws a `ToolArgsError` (`code: 'INVALID_ARGS'`); the registry turns it into an `isError` result whose text lists the violations, which the model sees and self-corrects from. Validation mirrors the JSON Schema conversion exactly: extra keys are allowed, `default` is not applied, and an `object`/`array` prop without `properties`/`items` only type-checks. Raw-registered tools (MCP) are **not** validated by the harness — they validate their own input. See `defineTool`, `validateArgs`, `ToolArgsError`, `SchemaSpec`, `InferArgs`, and `schemaSpecToJsonSchema` in the public API for details. diff --git a/packages/core/tools/src/schema.ts b/packages/core/tools/src/schema.ts index ad7c28760e..e912252b18 100644 --- a/packages/core/tools/src/schema.ts +++ b/packages/core/tools/src/schema.ts @@ -39,6 +39,11 @@ export interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] + /** + * Model-visible JSON Schema default annotation. Validation does not apply it; + * dynamic tool mounts may supply it even though first-party definitions do not. + */ + default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec /** Items schema for type: 'array'. */ @@ -114,6 +119,7 @@ function propToJsonSchema(prop: SchemaProp): { schema: Record; const result: Record = { type: prop.type } if (prop.description) result.description = prop.description if (prop.enum) result.enum = prop.enum + if (prop.default !== undefined) result.default = prop.default const required = prop.required === true diff --git a/packages/core/tools/tests/tools.spec.ts b/packages/core/tools/tests/tools.spec.ts index 2bca8e05fc..a2dff84287 100644 --- a/packages/core/tools/tests/tools.spec.ts +++ b/packages/core/tools/tests/tools.spec.ts @@ -904,6 +904,17 @@ describe('schema DSL edge cases', () => { }) }) + it('emits default value in JSON Schema property', () => { + const spec = { + limit: { type: 'number', default: 25 }, + } satisfies SchemaSpec + const jsonSchema = schemaSpecToJsonSchema(spec) + expect(jsonSchema.properties['limit']).toMatchObject({ + type: 'number', + default: 25, + }) + }) + it('handles array items without nested properties (plain type array)', () => { const spec = { tags: { type: 'array', items: { type: 'string' } }, @@ -915,12 +926,28 @@ describe('schema DSL edge cases', () => { }) }) - it('emits only the type when optional fields are omitted', () => { + it('handles enum and default together in one property', () => { + const spec = { + level: { type: 'string', enum: ['low', 'high'], default: 'low' }, + } satisfies SchemaSpec + const jsonSchema = schemaSpecToJsonSchema(spec) + expect(jsonSchema.properties['level']).toMatchObject({ + type: 'string', + enum: ['low', 'high'], + default: 'low', + }) + }) + + it('omits description, enum, default keys when not specified', () => { const spec = { bare: { type: 'string' }, } satisfies SchemaSpec const jsonSchema = schemaSpecToJsonSchema(spec) - expect(jsonSchema.properties['bare']).toEqual({ type: 'string' }) + const prop = jsonSchema.properties['bare'] as Record + expect(prop).toEqual({ type: 'string' }) + expect('description' in prop).toBe(false) + expect('enum' in prop).toBe(false) + expect('default' in prop).toBe(false) }) it('handles array with no items (items omitted)', () => { @@ -1110,6 +1137,12 @@ describe('validateArgs (the runtime-validation RFC, part 1)', () => { expect(validateArgs(spec, { path: '/tmp', extra: 1 })).toEqual([]) }) + it('does not apply defaults (validation only)', () => { + const spec = { limit: { type: 'number', default: 25 } } satisfies SchemaSpec + // absent optional is valid, and validation does not synthesize the default + expect(validateArgs(spec, {})).toEqual([]) + }) + it('type-checks primitives', () => { const spec = { s: { type: 'string' }, From 9028c9b63b6c3ed1737c168ae5e1548bab064668 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:35:34 +0800 Subject: [PATCH 024/323] fix: contain ACP update predicate failures --- packages/support/acp-snapshot/src/launcher.ts | 13 +++++++++++-- packages/support/acp-snapshot/tests/harness.spec.ts | 4 ++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 635a02ca35..975b1bb852 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -107,6 +107,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const updateWaiters: { match: (update: SessionNotification['update']) => boolean resolve: (update: SessionNotification['update']) => void + reject: (reason: unknown) => void }[] = [] const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, @@ -119,7 +120,15 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const waiter = updateWaiters[index] /* v8 ignore next 1 -- index is bounded by the array length */ if (waiter === undefined) continue - if (!waiter.match(params.update)) continue + let matches: boolean + try { + matches = waiter.match(params.update) + } catch (error: unknown) { + updateWaiters.splice(index, 1) + waiter.reject(error) + continue + } + if (!matches) continue updateWaiters.splice(index, 1) waiter.resolve(params.update) } @@ -136,7 +145,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), - waitForUpdate: match => new Promise(resolve => updateWaiters.push({ match, resolve })), + waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { if (child.exitCode !== null || child.signalCode !== null) return if (signal === undefined) child.stdin.end() diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index ec1ed5cf6f..db715db90c 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -57,7 +57,11 @@ describe('runScenario', () => { await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) const nextChunk = launched.waitForUpdate(update => update.sessionUpdate === 'agent_message_chunk') + const predicateFailure = new Error('predicate failed') + const failedPredicate = launched.waitForUpdate(() => { throw predicateFailure }) + .catch((error: unknown): unknown => error) await launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }) + expect(await failedPredicate).toBe(predicateFailure) expect((await nextChunk).sessionUpdate).toBe('agent_message_chunk') expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') From 7d711c44a8a6202680f2801ba16b391858715163 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:41:01 +0800 Subject: [PATCH 025/323] fix: keep remote subagent ids parent-scoped --- .../2026-06-20-unify-agent-and-session-id.md | 4 ++-- .../core/agent-loop/tests/scope-lifecycle.spec.ts | 2 +- packages/subagent/subagent-acp/README.md | 2 ++ packages/subagent/subagent-acp/src/run.ts | 15 ++++++++++----- .../subagent-acp/tests/subagent-acp.spec.ts | 10 ++++++++-- packages/subagent/subagent/src/types.ts | 2 +- 6 files changed, 24 insertions(+), 11 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index be1052830a..032eae4f7d 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -14,7 +14,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C ## Decision -An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process and ACP subagent creation use the child session id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index c68d96e525..e29e73c393 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -249,7 +249,7 @@ describe('agent scope lifecycle', () => { }) await setupStarted.promise expect(ctx.agents.get(SessionId('atomic'))).toBeUndefined() - expect(ctx.sessions.get(SessionId('atomic-s'))).toBeUndefined() + expect(ctx.sessions.get(SessionId('atomic'))).toBeUndefined() expect(order).toEqual(['setup:start']) gate.resolve(undefined) const handle = await creating diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index c949685fcc..03b1a856ed 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -6,6 +6,8 @@ The ACP provider runs each subagent in a fresh subprocess and drives it as an Ag `start(request)` performs `spawn` → ACP `initialize` → `newSession` before it fulfills. Fulfillment therefore means a remote session is ready and ownership has transferred to the caller. A spawn, initialization, new-session, or pre-publication cancellation failure rejects only after the subprocess has been reaped. +The returned run id is minted in the parent namespace. The child server's session id remains private to ACP wire calls because ACP guarantees it only within that fresh child process; using it as the parent lifecycle id could collide with another remote run or a local agent. + After publication, the provider sends the prompt and collects streamed `agent_message_chunk` text into `SubagentResult.output`. A prompt/transport failure resolves with `stopReason: 'error'`, or `aborted` when the required request signal or disposal requested cancellation. `dispose()` is idempotent. It removes the signal listener, requests ACP cancellation when possible, closes stdin, waits `disposeEofGraceMs`, escalates to SIGTERM, waits `disposeGraceMs`, and finally uses SIGKILL if necessary. Every run uses a fresh process; process pooling is not implemented. diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 1cc220204f..7d0c11cbe1 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -23,6 +23,7 @@ */ import { spawn } from 'node:child_process' +import { randomUUID } from 'node:crypto' import { Readable, Writable } from 'node:stream' import { ClientSideConnection, @@ -190,6 +191,10 @@ function toError(value: unknown): Error { */ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpec): Promise { if (request.signal.aborted) throw new Error('subagent request was aborted before the ACP child started') + // ACP session ids are unique only within the child server. The lifecycle id + // is minted in the parent namespace so fresh processes cannot collide with + // each other or with a local agent that happens to use the same session id. + const id = SessionId(randomUUID()) // Spawn the child ACP agent. stdin = ACP request channel, stdout = ACP // response channel, stderr = INHERIT so the child's diagnostics surface on the @@ -257,7 +262,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe ), ) - let sessionId: SessionId | undefined + let sessionId: string | undefined // Resolves when a cancel is requested, so `result` can settle `aborted` even // if the child never cooperates with `session/cancel` (it ignores the notify, // or the prompt wedges). The result path races this against the ACP drive: the @@ -306,7 +311,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = SessionId(session.sessionId) + sessionId = session.sessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -322,7 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // guard keeps that cross-closure invariant explicit for TypeScript. /* v8 ignore next */ if (sessionId === undefined) throw new Error('ACP child published without a session id') - const runId = sessionId + const remoteSessionId = sessionId const result: Promise = (async (): Promise => { try { @@ -334,7 +339,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe // succeeds, transport/process failure rejects the in-flight prompt RPC. const prompt = async (): Promise => { // The startup phase cannot fulfill without assigning the session id. - const promptResult = await conn.prompt({ sessionId: runId, prompt: toAcpPrompt(request.prompt) }) + const promptResult = await conn.prompt({ sessionId: remoteSessionId, prompt: toAcpPrompt(request.prompt) }) return { output: collectOutput(), stopReason: acpStopReason(promptResult.stopReason) } } return await Promise.race([ @@ -368,7 +373,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { - id: runId, + id, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index 115d5c3e97..e5fe05384e 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -121,16 +121,22 @@ describe('buildChildEnv', () => { }) describe('dsh-subagent-acp', () => { - it('drives a child process to completion and returns its streamed output', async () => { + it('drives child processes with parent-unique run ids and returns streamed output', async () => { const ctx = await setup({ MOCK_TEXT: 'hello from acp child', MOCK_STOP: 'end_turn', MOCK_SESSION_ID: 'acp-child-session' }) const run = await ctx.subagents.start('acp', request('do X')) - expect(run.id).toBe('acp-child-session') + expect(run.id).not.toBe('acp-child-session') const result = await run.result expect(result.stopReason).toBe('completed') expect(text(result.output)).toBe('hello from acp child') const disposal = run.dispose() expect(run.dispose()).toBe(disposal) await disposal + + const nextRun = await ctx.subagents.start('acp', request('do X again')) + expect(nextRun.id).not.toBe(run.id) + expect(nextRun.id).not.toBe('acp-child-session') + await nextRun.result + await nextRun.dispose() }) it('maps a max_tokens stop reason', async () => { diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 8d360b1182..827c2db7a7 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,7 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** The child agent's id (local in-process runs are already published in `ctx.agents`; remote transports need not publish locally). */ + /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run From a415d8fdb1b3de4425495b6c87707b58f5c3f65f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 05:43:10 +0800 Subject: [PATCH 026/323] docs: remove stale streamed-prefix rationale --- .../implemented/testing/2026-06-11-property-based-testing.md | 2 +- packages/llm/llm/src/assembler.ts | 5 ++--- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md b/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md index 67404ab49a..db7a9c8a79 100644 --- a/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md +++ b/docs/rfc/implemented/testing/2026-06-11-property-based-testing.md @@ -20,7 +20,7 @@ Adopt `fast-check` (a root devDependency) with one `tests/properties.spec.ts` pe ## Consequences - Generator quality is the value lever — the generators bias toward small index pools and short strings so collisions and interleavings are common. -- **It already paid off:** the BlockAssembler stream found a real bug — a duplicate `block-end` at the same index overwrote an already-flushed block, so the streamed prefix disagreed with final `blocks()`. Fixed (first close wins, matching the existing straggler rule) with a dedicated regression test. +- **It already paid off:** the BlockAssembler stream found a real bug — a duplicate `block-end` at the same index rewrote a completed block. Fixed (first close wins, matching the existing straggler rule) with a dedicated regression test. - A property flake from a timeout is a finding, not something to retry away. The loop properties are deterministic by construction (settle on `agent/status`), so a hang is a real defect. - Property tests supplement, not replace, the example tests that pin specific branches for the 100%-coverage gate. diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index fb34afe0b9..1dd023d177 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -72,9 +72,8 @@ export class BlockAssembler { case 'block-end': { const partial = this.ensure(chunk.index, chunk.block.type) // First close wins: a second block-end for an already-closed index is - // a straggler (same rule as post-close deltas). Ignoring it keeps the - // streamed prefix and the final blocks() in agreement — otherwise a - // re-close could rewrite a block already flushed downstream. + // a straggler (same rule as post-close deltas). Ignoring it prevents a + // later chunk from rewriting a completed block. if (partial.block) return partial.block = chunk.block return From 60ce23d77c52b6f4c183c320d2a1b54c4aedea7f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:07:37 +0800 Subject: [PATCH 027/323] fix: surface ACP launcher spawn failures --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 1 + packages/support/acp-snapshot/src/launcher.ts | 22 ++++++++++++++++++- .../acp-snapshot/tests/harness.spec.ts | 13 ++++++++++- 4 files changed, 35 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 4a43d0eef9..0058e9116f 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 93bb556ba6..d04b0bc2b5 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -214,6 +214,7 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise }, }) const active = launched + await active.spawned const { client } = active for (const step of input.steps) { diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 975b1bb852..3508b02ec5 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -53,6 +53,8 @@ export interface AcpTestLaunchOptions { export interface LaunchedAcpTestAgent { /** The child process, exposed for process-level assertions. */ child: ChildProcessWithoutNullStreams + /** Resolve when the OS spawns the child; reject with its asynchronous spawn failure. */ + spawned: Promise /** The SDK connection backed by the child's stdio. */ client: ClientSideConnection /** Session updates in receive order. */ @@ -90,6 +92,18 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe stdio: ['pipe', 'pipe', 'pipe'], }, ) + // A spawn-level failure is an asynchronous `error` event. Observe it in the + // same tick as spawn so a missing cwd or OS rejection cannot crash the test + // runner, then make startup and shutdown surface the original error. + const childFailure = new Promise(resolve => child.once('error', resolve)) + const spawned = Promise.race([ + new Promise(resolve => child.once('spawn', resolve)), + childFailure.then((error): never => { throw error }), + ]) + // `spawned` is public and close() also awaits it, but a caller may ignore both. + // Keep that misuse from turning the already-observed child error into an + // unhandled promise rejection. + void spawned.catch(() => undefined) const stderrChunks: string[] = [] child.stderr.setEncoding('utf8') @@ -141,16 +155,22 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe return { child, + spawned, client, updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { + await spawned if (child.exitCode !== null || child.signalCode !== null) return if (signal === undefined) child.stdin.end() else child.kill(signal) - await waitForExit(child) + const failure = await Promise.race([ + waitForExit(child).then((): undefined => undefined), + childFailure, + ]) + if (failure !== undefined) throw failure }, } } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index db715db90c..69c02a407f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -40,6 +40,13 @@ async function scenario(behavior: object): Promise<{ dir: string; fixtureFile: s const boot: InputStep[] = [{ op: 'initialize' }, { op: 'newSession' }] describe('runScenario', () => { + it('surfaces an asynchronous child spawn failure through startup and close', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: join(dir, 'missing') }) + await expect(launched.spawned).rejects.toMatchObject({ code: 'ENOENT' }) + await expect(launched.close()).rejects.toMatchObject({ code: 'ENOENT' }) + }) + it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { const { dir, fixtureFile } = await scenario({ permissionProbe: true, echoEnv: true, stderrNote: 'launcher stderr' }) const sessionsRoot = await mkdtemp(join(tmpdir(), 'acp-launcher-sessions-')) @@ -72,7 +79,11 @@ describe('runScenario', () => { // The minimal shape needs no environment or config override. const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) - await minimal.close() + const childFailure = new Error('child process failed') + const exited = new Promise(resolve => minimal.child.once('exit', () => { resolve() })) + minimal.child.emit('error', childFailure) + await expect(minimal.close('SIGKILL')).rejects.toBe(childFailure) + await exited }) it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { From e9d1e1cdda70eedb49a12f9adce2afb18caa4c00 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:19:24 +0800 Subject: [PATCH 028/323] docs: update ACP ownership routing --- .../rfc/implemented/feature/2026-06-14-acp-multi-session.md | 4 ++-- .../rfc/implemented/feature/2026-06-25-ask-user-question.md | 2 +- docs/rfc/implemented/feature/2026-07-06-approval-seam.md | 6 +++--- packages/ui/acp/README.md | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md index 77fa2b4669..64961bee89 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md +++ b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md @@ -8,11 +8,11 @@ An ACP editor can keep several conversations alive over one agent subprocess. A ## Decision -The ACP bridge stores live sessions in `Map` and keeps a `WeakMap` reverse index for agent-scoped callbacks. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. +The ACP bridge stores live sessions in `Map`. Agent-scoped callbacks use `ownedRecord`: look up `agent.session.id` in that forward map and accept the record only when it owns the exact agent object, so a foreign same-id object cannot claim the session. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. Every `session/event` and `agent/status` callback resolves the owning record before sending or settling anything. Each session permits one in-flight prompt independently. The prompt records a log watermark, captures its own `turn/start`, and settles only on the matching `turn/end`; a late end from a cancelled prior turn cannot resolve a newer prompt. `session/cancel` addresses one record and calls only that agent's queue-aware cancel path. -Permission ownership uses the same reverse index. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. +Permission ownership uses the same exact-agent check against the forward map. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. Background bash tasks carry an opaque owner token equal to the owning session id. `bash_output` and `bash_kill` compare the caller's token with the executor's task ownership before reading or killing; a predictable task id alone grants no access. Ownership is stored with the executor task, so a tool plugin reload does not erase it. diff --git a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md index 9320189de1..42e5d9a7ab 100644 --- a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md +++ b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md @@ -22,7 +22,7 @@ Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is alway `dsh-stdio-agent`'s in-package readline module renders each question, shows each option's `description` on the next line, supports comma/space-separated numeric choices for `multi_select`, accepts free-form custom answers, and rejects pending questions on abort, provider disposal, or stdin EOF. A batched request is asked in order and resolved as one answer object. The stdio provider serializes simultaneous requests with an internal queue so only one prompt owns stdin at a time. -`dsh-acp` provides the same seam for ACP sessions. It routes an ask request from the calling `Agent` through the bridge's `agent→sessionId` reverse map and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. +`dsh-acp` provides the same seam for ACP sessions. It resolves the calling `Agent` through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. The ACP mapping deliberately uses elicitation, not `session/request_permission`. `request_permission` is still reserved for the separate permission gate: it is a yes/no-or-policy authorization protocol around tool execution. `ask_user_question` is a general information-gathering tool with optional free-form answers, so ACP form elicitation is the closer protocol fit. The bridge's session routing is shared with the future permission gate, but the user intent is different. diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 5d82226a96..c5d61b0edb 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -65,9 +65,9 @@ The seam also owns the session-scoped approval policy — the approval knob of t #### The ACP answerer -The bridge registers the first real answerer: it resolves the owning session through its existing `WeakMap` reverse map, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. +The bridge registers the first real answerer: it resolves the owning session through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. -The answerer routes through the bridge's reverse-map ownership seam described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). +The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). #### Audit, and what the model sees @@ -137,5 +137,5 @@ In-repo precedents this design copies or contrasts with: - The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses. - `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges RFC](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer. - [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services. -- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the `WeakMap` ownership seam the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. +- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the exact-agent ownership check against the forward session map that the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. - The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 31a865c068..4b9a278707 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -75,7 +75,7 @@ A `session/prompt` resolves or rejects exactly once from the canonical `session/ ## Permission prompts -The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning session through the reverse map and issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. +The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning `SessionRecord` through `ownedRecord`, which looks up `agent.session.id` in the forward session map and requires the record to own that exact agent object. It then issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. ## Disposal & disconnect From 140d32681ef2fc4b35dbae710044c7b7c4e693b7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:33:22 +0800 Subject: [PATCH 029/323] fix: make ACP test teardown failure-safe --- examples/acp-agent/tests/acp.e2e.ts | 14 ++++-- examples/acp-agent/tests/hooks.e2e.ts | 14 ++++-- .../sandbox-acp-agent/tests/escalation.e2e.ts | 14 ++++-- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/harness.ts | 44 ++++++++++++------- packages/support/acp-snapshot/src/launcher.ts | 25 +++++++++-- .../acp-snapshot/tests/harness.spec.ts | 8 ++-- 7 files changed, 86 insertions(+), 35 deletions(-) diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index 4b6c675208..871006dfb4 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -30,10 +30,16 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe('acp-agent over real stdio (no key required)', () => { diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index a553addc96..8dc169f437 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -38,10 +38,16 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook blocks bash (real model)', () => { diff --git a/examples/sandbox-acp-agent/tests/escalation.e2e.ts b/examples/sandbox-acp-agent/tests/escalation.e2e.ts index a7e8787e36..0ddaa6426e 100644 --- a/examples/sandbox-acp-agent/tests/escalation.e2e.ts +++ b/examples/sandbox-acp-agent/tests/escalation.e2e.ts @@ -81,10 +81,16 @@ let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - await spawned?.close('SIGKILL') - spawned = undefined - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - workdir = undefined + try { + await spawned?.close('SIGKILL') + } finally { + spawned = undefined + try { + if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) + } finally { + workdir = undefined + } + } }) describe('sandbox-acp-agent keyless smoke (real cordis.yml via the Loader)', () => { diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 0058e9116f..26192f1cac 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit before resolving or propagating a child error, so callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index d04b0bc2b5..3db1355b0f 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -163,7 +163,7 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise let launched: LaunchedAcpTestAgent | undefined let sessionId: string | undefined let sessionLogs: HarvestedLog[] = [] - try { + const outcome = await (async (): Promise => { // Seed the workspace if the scenario ships one (a file the agent reads/edits). // Copied into the temp cwd so the agent's bash tools see it; the goldens // normalize the cwd, so the seeded paths stay stable across runs. @@ -231,22 +231,36 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise // Harvest EVERY persisted log (parent + any subagent children) while the // temp dirs still exist, ordered primary-first. sessionLogs = await harvestSessionLogs(sessionsRoot) - } finally { - // Failure-safe teardown: kill a still-running child and drop the temp dirs - // even if seeding/spawn/a step/harvest threw, so a flaky run never leaks a - // process or dir. `launched` is undefined only if launch itself threw. - await launched?.close('SIGKILL') - await rm(cwd, { recursive: true, force: true }) - await rm(sessionsRoot, { recursive: true, force: true }) - } + return { + rawStdout: launched.rawStdout(), + stderr: launched.stderr(), + cwd, + ...sessionId !== undefined ? { sessionId } : {}, + sessionLogs, + } + })().then( + value => ({ status: 'fulfilled', value } as const), + (error: unknown) => ({ status: 'rejected', error } as const), + ) - return { - rawStdout: launched.rawStdout(), - stderr: launched.stderr(), - cwd, - ...sessionId !== undefined ? { sessionId } : {}, - sessionLogs, + // Failure-safe teardown: wait for a still-running child, then attempt BOTH + // directory removals even when an earlier cleanup rejects. The main outcome + // wins over teardown noise so a step/harvest failure is never replaced; on a + // successful run, the first cleanup failure remains visible to the caller. + const cleanupResults: PromiseSettledResult[] = [] + const cleanup = async (action: () => Promise): Promise => { + cleanupResults.push(...await Promise.allSettled([action()])) } + /* v8 ignore next 1 -- launch itself can only throw on a defensive synchronous spawn API failure */ + await cleanup(() => launched?.close('SIGKILL') ?? Promise.resolve()) + await cleanup(() => rm(cwd, { recursive: true, force: true })) + await cleanup(() => rm(sessionsRoot, { recursive: true, force: true })) + + if (outcome.status === 'rejected') throw outcome.error + const cleanupFailure = cleanupResults.find((result): result is PromiseRejectedResult => result.status === 'rejected') + /* v8 ignore next 1 -- defensive OS cleanup failure after an otherwise successful real subprocess run */ + if (cleanupFailure !== undefined) throw cleanupFailure.reason + return outcome.value } /** Drive one input step over the client connection. */ diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 3508b02ec5..7f2ec9b0a7 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -95,7 +95,10 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // A spawn-level failure is an asynchronous `error` event. Observe it in the // same tick as spawn so a missing cwd or OS rejection cannot crash the test // runner, then make startup and shutdown surface the original error. - const childFailure = new Promise(resolve => child.once('error', resolve)) + // Keep observing after the first error: a fallback kill attempted during + // shutdown may itself report another process error, which must not become an + // unhandled EventEmitter error after the promise has already settled. + const childFailure = new Promise(resolve => child.on('error', resolve)) const spawned = Promise.race([ new Promise(resolve => child.once('spawn', resolve)), childFailure.then((error): never => { throw error }), @@ -163,14 +166,23 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), async close(signal?: NodeJS.Signals): Promise { await spawned - if (child.exitCode !== null || child.signalCode !== null) return + if (!isRunning(child)) return + const exited = waitForExit(child) if (signal === undefined) child.stdin.end() else child.kill(signal) const failure = await Promise.race([ - waitForExit(child).then((): undefined => undefined), + exited.then((): undefined => undefined), childFailure, ]) - if (failure !== undefined) throw failure + if (failure === undefined) return + + // An `error` after spawn is not an exit edge: in particular, a failed + // signal can leave the subprocess live. Force termination, await the + // already-observed exit edge, and only then propagate the child error so + // callers may safely remove cwd/session resources after close rejects. + child.kill('SIGKILL') + await exited + throw failure }, } } @@ -179,3 +191,8 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe function waitForExit(child: ChildProcessWithoutNullStreams): Promise { return new Promise(resolve => child.once('exit', () => { resolve() })) } + +/** Whether the child still lacks either OS termination marker. */ +function isRunning(child: ChildProcessWithoutNullStreams): boolean { + return child.exitCode === null && child.signalCode === null +} diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 69c02a407f..3c1bb0d44a 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -80,10 +80,12 @@ describe('runScenario', () => { const minimal = launchAcpTestAgent({ agent: AGENT, cwd: dir }) await minimal.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const childFailure = new Error('child process failed') - const exited = new Promise(resolve => minimal.child.once('exit', () => { resolve() })) + let exited = false + minimal.child.once('exit', () => { exited = true }) minimal.child.emit('error', childFailure) - await expect(minimal.close('SIGKILL')).rejects.toBe(childFailure) - await exited + await expect(minimal.close('SIGTERM')).rejects.toBe(childFailure) + // close rejects only after the fallback SIGKILL has produced an exit edge. + expect(exited).toBe(true) }) it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { From 58e61ae20ba28101be0bed01505b03ec20cd6a7e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:37:58 +0800 Subject: [PATCH 030/323] fix: retain stdio target across agent replacement --- packages/ui/stdio-agent/src/stdio-chat.ts | 19 +++++++++++------ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 21 +++++++++++++++++++ 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index cb9ce0bc10..bfb58e3a57 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,13 +95,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns exactly one pre-created agent. Hold the live object directly: - // its per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one root agent. Hold the live object directly: its per-run id + // is intentionally fresh, while `main` remains only the terminal's fixed + // display label. HMR may publish the replacement before old teardown emits + // disposed, so a target disposal reselects the surviving root from the live + // registry instead of leaving the terminal detached. Fork children carry + // parentSession lineage and must never become the terminal target. + const rootAgent = (): Agent | undefined => + ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) + let target: Agent | undefined = rootAgent() + ctx.on('agent/created', (agent) => { + if (target === undefined && agent.session.header.parentSession === undefined) target = agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined + if (target === agent) target = rootAgent() }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 69ca5f8837..2b1df53921 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -230,6 +230,27 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) + it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { + const { ctx, input } = await setup() + const oldRoot = makeAgent('old-root') + const child = makeAgent('child') + ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id + const replacement = makeAgent('replacement') + const disposeOld = ctx.agents.register(oldRoot) + ctx.agents.register(child) + ctx.agents.register(replacement) + + // The replacement's created edge arrived while oldRoot was still targeted. + // Once oldRoot is removed, registry order is child then replacement; the + // UI must skip the surviving child and route input to the replacement root. + disposeOld() + input.feed('after hmr') + await new Promise(resolve => setImmediate(resolve)) + + expect(child.sent).toEqual([]) + expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session From 3bd2052d7251b9500e8afca02aaee64ca8b2ad40 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:52:46 +0800 Subject: [PATCH 031/323] fix: allow lineage-bearing stdio targets --- packages/ui/stdio-agent/src/stdio-chat.ts | 24 +++++++++---------- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 17 ++++++++++++- 2 files changed, 27 insertions(+), 14 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index bfb58e3a57..2a4d620494 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,20 +95,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one root agent. Hold the live object directly: its per-run id - // is intentionally fresh, while `main` remains only the terminal's fixed - // display label. HMR may publish the replacement before old teardown emits - // disposed, so a target disposal reselects the surviving root from the live - // registry instead of leaving the terminal detached. Fork children carry - // parentSession lineage and must never become the terminal target. - const rootAgent = (): Agent | undefined => - ctx.agents.list().find(agent => agent.session.header.parentSession === undefined) - let target: Agent | undefined = rootAgent() - ctx.on('agent/created', (agent) => { - if (target === undefined && agent.session.header.parentSession === undefined) target = agent - }) + // This app owns one configured agent. Hold the live object directly: its + // per-run id is intentionally fresh, while `main` remains only the + // terminal's fixed display label. At install the configured agent is the + // earliest registry entry (it creates any subagents later). During HMR the + // replacement is published after the old tree, so when old teardown finally + // emits disposed, the newest survivor is the replacement. Persisted + // parentSession lineage is deliberately irrelevant: a resumed child session + // can itself be this process's configured top-level agent. + let target: Agent | undefined = ctx.agents.list()[0] + ctx.on('agent/created', (agent) => { target ??= agent }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = rootAgent() + if (target === agent) target = ctx.agents.list().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2b1df53921..2654a05680 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -185,6 +185,9 @@ describe('createStdioChat rendering', () => { await ctx.plugin(AgentRegistry) await ctx.plugin(UserInteractionService) const agent = makeAgent('main') + // Durable lineage does not imply runtime child ownership: the stdio app + // may explicitly resume a persisted fork as its one configured agent. + ;(agent.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(agent) // registered BEFORE the UI plugin below const { runtime, out } = makeRuntime() await ctx.plugin(Object.assign((inner: Context) => { @@ -196,6 +199,18 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) + it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + const { ctx, input } = await setup() + const resumed = makeAgent('resumed') + ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' + ctx.emit('agent/created', resumed) + + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + + expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) + }) + it('resets dim styling at turn/end if a turn ends mid-reasoning', async () => { const { ctx, out } = await setup() const session = makeSession('main') @@ -242,7 +257,7 @@ describe('createStdioChat rendering', () => { // The replacement's created edge arrived while oldRoot was still targeted. // Once oldRoot is removed, registry order is child then replacement; the - // UI must skip the surviving child and route input to the replacement root. + // most recently published survivor is the HMR replacement. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) From e2a5a160d3763ee7faaa9b4235ae7284144f05ee Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:00:10 +0800 Subject: [PATCH 032/323] fix: settle ACP update waiters on shutdown --- packages/support/acp-snapshot/src/launcher.ts | 43 ++++++++++++++----- .../acp-snapshot/tests/harness.spec.ts | 3 ++ 2 files changed, 36 insertions(+), 10 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 7f2ec9b0a7..253e67fd5a 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -114,18 +114,26 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const rawBuffers: Buffer[] = [] const passthrough = new Readable({ read() {} }) - child.stdout.on('data', (buffer: Buffer) => { - rawBuffers.push(buffer) - passthrough.push(buffer) - }) - child.stdout.on('end', () => passthrough.push(null)) - const updates: SessionNotification['update'][] = [] const updateWaiters: { match: (update: SessionNotification['update']) => boolean resolve: (update: SessionNotification['update']) => void reject: (reason: unknown) => void }[] = [] + let updateStreamFailure: Error | undefined + const closeUpdateStream = (): void => { + if (updateStreamFailure !== undefined) return + updateStreamFailure = new Error('ACP test agent update stream closed before a matching session update arrived') + for (const waiter of updateWaiters.splice(0)) waiter.reject(updateStreamFailure) + } + child.stdout.on('data', (buffer: Buffer) => { + rawBuffers.push(buffer) + passthrough.push(buffer) + }) + child.stdout.on('end', () => { + passthrough.push(null) + closeUpdateStream() + }) const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, Readable.toWeb(passthrough) as ReadableStream, @@ -163,10 +171,21 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe updates, rawStdout: () => Buffer.concat(rawBuffers).toString('utf8'), stderr: () => stderrChunks.join(''), - waitForUpdate: match => new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })), + waitForUpdate(match): Promise { + if (updateStreamFailure !== undefined) return Promise.reject(updateStreamFailure) + return new Promise((resolve, reject) => updateWaiters.push({ match, resolve, reject })) + }, async close(signal?: NodeJS.Signals): Promise { - await spawned - if (!isRunning(child)) return + try { + await spawned + } catch (error: unknown) { + closeUpdateStream() + throw error + } + if (!isRunning(child)) { + closeUpdateStream() + return + } const exited = waitForExit(child) if (signal === undefined) child.stdin.end() else child.kill(signal) @@ -174,7 +193,10 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe exited.then((): undefined => undefined), childFailure, ]) - if (failure === undefined) return + if (failure === undefined) { + closeUpdateStream() + return + } // An `error` after spawn is not an exit edge: in particular, a failed // signal can leave the subprocess live. Force termination, await the @@ -182,6 +204,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // callers may safely remove cwd/session resources after close rejects. child.kill('SIGKILL') await exited + closeUpdateStream() throw failure }, } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 3c1bb0d44a..192d36dc6c 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -73,7 +73,10 @@ describe('runScenario', () => { expect(launched.updates.some(update => update.sessionUpdate === 'agent_message_chunk')).toBe(true) expect(launched.rawStdout()).toContain('permission:{\\"outcome\\":\\"cancelled\\"}') expect(launched.stderr()).toContain('launcher stderr') + const unmatched = expect(launched.waitForUpdate(() => false)).rejects.toThrow(/update stream closed/) await launched.close() + await unmatched + await expect(launched.waitForUpdate(() => true)).rejects.toThrow(/update stream closed/) await launched.close('SIGKILL') // The minimal shape needs no environment or config override. From c2979322c8b938b1c2e91920740688788867e6d7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:13:42 +0800 Subject: [PATCH 033/323] fix: keep stdio targeting on runtime roots --- docs/cordis-catalog/services.md | 5 ++-- packages/core/agent-loop/src/index.ts | 2 +- .../agent-loop/tests/scope-lifecycle.spec.ts | 18 +++++++++++++ packages/core/agent/README.md | 3 ++- packages/core/agent/src/index.ts | 22 ++++++++++++++-- packages/core/agent/tests/agent.spec.ts | 24 +++++++++++++++--- packages/ui/stdio-agent/src/stdio-chat.ts | 20 +++++++-------- .../ui/stdio-agent/tests/readline.spec.ts | 4 +-- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 25 ++++++++++++------- 9 files changed, 92 insertions(+), 31 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 4d162a55f5..1366fcf6f6 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -30,15 +30,16 @@ setFactory(factory: AgentFactory): () => void async create(options: CreateAgentOptions): Promise async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void -enter(agent: Agent): () => void +enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined list(): Agent[] +roots(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:199`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33276c01f8..dbe503ff6a 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -229,7 +229,7 @@ class AgentCreationTransaction { this.publishing = true try { this.detachSession = agent.ctx.sessions.enter(session) - this.detachAgent = this.loopCtx.agents.enter(agent) + this.detachAgent = this.loopCtx.agents.enter(agent, this.ownerAgent) agent.ctx.sessions.announce(session) this.assertActive() diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index e29e73c393..610e077a67 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -149,6 +149,24 @@ describe('agent scope lifecycle', () => { await ctx.agents.get(SessionId('a1'))?.whenIdle() }) + it('records agents created through an agent context as non-root runtime children', async () => { + const ctx = await harness() + const root = await ctx.agents.create({ + sessionId: SessionId('runtime-root'), + agentOptions: { model: 'mock' }, + }) + const child = await root.agent.ctx.agents.create({ + sessionId: SessionId('runtime-child'), + agentOptions: { model: 'mock' }, + }) + + expect(ctx.agents.list()).toEqual([root.agent, child.agent]) + expect(ctx.agents.roots()).toEqual([root.agent]) + + await child.dispose() + await root.dispose() + }) + it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() const handle = await ctx.agents.create({ sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 4eddb050d5..643c15002b 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,9 +11,10 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent): () => void` performs the authoritative ID collision check and inserts without announcing; `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` +- `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 1306e8004d..b25d1e3cac 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -178,6 +178,8 @@ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plug interface AgentEntry { readonly id: SessionId readonly agent: Agent + /** Runtime creator-agent ownership; independent of durable session lineage. */ + readonly owner: Agent | undefined readonly carrier: Scoped announced: boolean announcing: boolean @@ -303,7 +305,7 @@ export class AgentRegistry extends Service { */ register(agent: Agent): () => void { const dispose = this.ctx.effect(function* (this: AgentRegistry) { - yield this.enter(agent) + yield this.enter(agent, this.ctx.agent) this.announce(agent) }.bind(this), 'agents.register()') // eslint-disable-next-line @typescript-eslint/no-misused-promises -- synchronous cleanup; direct return preserves disposer identity @@ -317,12 +319,15 @@ export class AgentRegistry extends Service { * returned detach closure into its pre-installed composite teardown before * calling {@link announce}. Ordinary callers use {@link register}. * @param agent - the prepared, unpublished agent. + * @param owner - live agent whose scoped context created this agent, or + * undefined for a top-level runtime root. This is runtime ownership, not + * the resumed session's durable parent lineage. * @returns an idempotent closure that removes this exact entry and emits * `agent/disposed` with listener failures contained. When called from a * synchronous `agent/created` listener, removal and disposal wait until * that creation dispatch unwinds. */ - enter(agent: Agent): () => void { + enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume @@ -331,6 +336,7 @@ export class AgentRegistry extends Service { const entry: AgentEntry = { id, agent, + owner, carrier, announced: false, announcing: false, @@ -438,6 +444,18 @@ export class AgentRegistry extends Service { list(): Agent[] { return [...this.store.values()].map(entry => entry.agent) } + + /** + * All live top-level agents in registration order. A top-level agent was + * created without an owning agent context; durable session lineage does not + * affect this runtime relation, so a resumed fork may still be a root. + * @returns a fresh array; mutating it does not affect the registry. + */ + roots(): Agent[] { + return [...this.store.values()] + .filter(entry => entry.owner === undefined) + .map(entry => entry.agent) + } } export default AgentRegistry diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index cba833b212..5563d01cad 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -42,6 +42,7 @@ describe('AgentRegistry', () => { const dispose = ctx.agents.register(agent) expect(ctx.agents.get(agent.id)).toBe(agent) expect(ctx.agents.list()).toEqual([agent]) + expect(ctx.agents.roots()).toEqual([agent]) expect(() => ctx.agents.register(stubAgent('a1'))).toThrow(/already registered/) dispose() @@ -49,6 +50,23 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('tracks runtime creator ownership separately from registry order', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const root = stubAgent('root') + const child = stubAgent('child') + const detachRoot = ctx.agents.enter(root, undefined) + ctx.agents.announce(root) + const detachChild = ctx.agents.enter(child, root) + ctx.agents.announce(child) + + expect(ctx.agents.list()).toEqual([root, child]) + expect(ctx.agents.roots()).toEqual([root]) + + detachChild() + detachRoot() + }) + it('rolls an entry back and pairs a partially delivered creation when a listener throws', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -94,7 +112,7 @@ describe('AgentRegistry', () => { ctx.on('agent/disposed', agent => void lifecycle.push(`disposed:${agent.id}`)) const first = stubAgent('split') - const detachFirst = ctx.agents.enter(first) + const detachFirst = ctx.agents.enter(first, undefined) expect(lifecycle).toEqual([]) ctx.agents.announce(first) expect(() => { ctx.agents.announce(first) }).toThrow(/already announced/) @@ -102,7 +120,7 @@ describe('AgentRegistry', () => { detachFirst() const replacement = stubAgent('split') - const detachReplacement = ctx.agents.enter(replacement) + const detachReplacement = ctx.agents.enter(replacement, undefined) detachFirst() expect(ctx.agents.get(replacement.id)).toBe(replacement) expect(() => { ctx.agents.announce(first) }).toThrow(/not live/) @@ -122,7 +140,7 @@ describe('AgentRegistry', () => { }) ctx.on('agent/created', () => void order.push(`second:${ctx.agents.get(agent.id) === agent}`)) ctx.on('agent/disposed', () => void order.push('disposed')) - const detach = ctx.agents.enter(agent) + const detach = ctx.agents.enter(agent, undefined) ctx.agents.announce(agent) expect(order).toEqual(['first:true', 'after-detach:true', 'second:true', 'disposed']) expect(ctx.agents.get(agent.id)).toBeUndefined() diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 2a4d620494..a295274786 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -95,18 +95,16 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured agent. Hold the live object directly: its - // per-run id is intentionally fresh, while `main` remains only the - // terminal's fixed display label. At install the configured agent is the - // earliest registry entry (it creates any subagents later). During HMR the - // replacement is published after the old tree, so when old teardown finally - // emits disposed, the newest survivor is the replacement. Persisted - // parentSession lineage is deliberately irrelevant: a resumed child session - // can itself be this process's configured top-level agent. - let target: Agent | undefined = ctx.agents.list()[0] - ctx.on('agent/created', (agent) => { target ??= agent }) + // This app owns one configured top-level agent. Hold the live object + // directly: its per-run id is intentionally fresh, while `main` remains only + // the terminal's fixed display label. Runtime creator ownership distinguishes + // that root from its subagents even if a child is registered after an HMR + // replacement. Persisted parentSession lineage is deliberately irrelevant: + // a resumed child session can itself be this process's configured root. + let target: Agent | undefined = ctx.agents.roots()[0] + ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.list().at(-1) + if (target === agent) target = ctx.agents.roots().at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/readline.spec.ts b/packages/ui/stdio-agent/tests/readline.spec.ts index 6116aa356f..fa82db4d96 100644 --- a/packages/ui/stdio-agent/tests/readline.spec.ts +++ b/packages/ui/stdio-agent/tests/readline.spec.ts @@ -16,9 +16,9 @@ function fakeContext(): Context { return { on: vi.fn(() => vi.fn()), effect: vi.fn((callback: () => () => void) => callback()), - // The UI seeds its target object from the registry at install; this suite only + // The UI seeds its root target from the registry at install; this suite only // exercises readline terminal-mode selection, so an empty roster suffices. - agents: { list: vi.fn(() => []) }, + agents: { roots: vi.fn(() => []) }, userInteraction: { registerProvider: vi.fn(() => vi.fn()) }, } as unknown as Context } diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2654a05680..2600fdb24f 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -154,8 +154,7 @@ describe('createStdioChat rendering', () => { it('renders turn/start and turn/end markers from the session feed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - // agent/created supplies the app-owned target object. - ctx.emit('agent/created', agent) + ctx.agents.register(agent) const session = agent.session ctx.emit('session/event', session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 3, trigger: { kind: 'message' } }, @@ -203,7 +202,7 @@ describe('createStdioChat rendering', () => { const { ctx, input } = await setup() const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' - ctx.emit('agent/created', resumed) + ctx.agents.register(resumed) input.feed('continue') await new Promise(resolve => setImmediate(resolve)) @@ -224,8 +223,8 @@ describe('createStdioChat rendering', () => { it('drops the target object on agent/disposed', async () => { const { ctx, out } = await setup() const agent = makeAgent('main') - ctx.emit('agent/created', agent) - ctx.emit('agent/disposed', agent) + const dispose = ctx.agents.register(agent) + dispose() // After disposal the event belongs to a non-target session, so its durable // identity is rendered directly. ctx.emit('session/event', agent.session, { @@ -237,7 +236,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() const target = makeAgent('target') - ctx.emit('agent/created', target) + ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { type: 'turn/start', seq: 1, time: 0, data: { turn: 1, trigger: { kind: 'message' } }, @@ -251,19 +250,27 @@ describe('createStdioChat rendering', () => { const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id const replacement = makeAgent('replacement') + const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) - ctx.agents.register(child) + const disposeChild = ctx.agents.enter(child, oldRoot) + ctx.agents.announce(child) ctx.agents.register(replacement) + const disposeLateChild = ctx.agents.enter(lateChild, replacement) + ctx.agents.announce(lateChild) // The replacement's created edge arrived while oldRoot was still targeted. - // Once oldRoot is removed, registry order is child then replacement; the - // most recently published survivor is the HMR replacement. + // A replacement-owned child then arrived even later. Once oldRoot is + // removed, runtime ownership still identifies replacement as the only + // surviving root instead of selecting either newer child by insertion order. disposeOld() input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) expect(child.sent).toEqual([]) + expect(lateChild.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) + disposeLateChild() + disposeChild() }) it('renders tool/call and tool/result session events', async () => { From 0b492e6e62be53abb8560d16f806a4078f56c651 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:22:22 +0800 Subject: [PATCH 034/323] fix: drain ACP test launcher streams --- packages/support/acp-snapshot/README.md | 2 +- packages/support/acp-snapshot/src/launcher.ts | 17 +++++++++++++-- .../tests/fixtures/fake-acp-agent.ts | 21 +++++++++++++++++++ .../acp-snapshot/tests/harness.spec.ts | 21 +++++++++++++++++++ 4 files changed, 58 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 26192f1cac..b95615abea 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -4,7 +4,7 @@ The ACP snapshot suite kit: the shared machinery behind the keyless snapshot tie Four layers, importable separately: -- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit before resolving or propagating a child error, so callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. +- **`launchAcpTestAgent` (launcher)** — boots an unbuilt ACP agent from a temp cwd, pins tsx to the repo tsconfig, connects the SDK client over a raw-byte stdout tee, collects session updates and stderr, surfaces asynchronous spawn failures through its startup lifecycle, fails closed on unhandled permission requests, and owns graceful or signalled shutdown. Shutdown waits for process exit, inherited stdio closure, and ACP parser exhaustion before resolving or propagating a child error, so captures are complete and callers can remove owned paths after either outcome. Snapshot and ordinary e2e suites share this process boundary; a test supplies only agent paths, cwd, environment overrides, and any permission policy. - **`runScenario` (harness)** — boots the real agent bin as a subprocess via tsx (unbuilt, Loader path), drives it over ACP JSON-RPC stdio from a deterministic `input.json` script, tees raw stdout for the golden + purity check, and harvests every persisted session JSONL (parent + subagent children, primary-first) after a graceful stdin-EOF shutdown. Parameterized by `AgentUnderTest` (`binScript`, `configPath`, `tsconfigPath` — absolute paths; the subprocess cwd is a temp dir outside the repo). - **Normalizers** — pure functions turning the two captured surfaces into stable text: `normalizeStdout` (JSON-RPC ids → first-seen sequence; UUIDs/cwd → tokens; doubles as the stdout-purity check), `normalizeSessionLog` (times zeroed, `seq` kept), `scrubSystemPrompts` (prompt text → `{{system}}` in every JSONL), and `scrubRequestHeaders` (the remaining header bulk → `{{tools}}`/`{{messagePrefix}}` outside each pin, structure kept — [pinned-header RFC](../../../docs/rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). - **`defineAcpSnapshotSuite` (factory)** — registers the whole describe/it tree for a scenario table: per-scenario golden + re-persisted-log compares, record/refresh fixture write-back, the per-header-class pin (`system-prompt.golden.md` plus the JSONL's full tool schemas) with its live uniformity guard, and the fixture guard block (no orphan scenario dirs, required files present, exactly one pin per class, every JSONL prompt-scrubbed, non-pinning fixtures fully header-scrubbed). Each scenario directory's `session.jsonl` plus contiguous `session..jsonl` siblings are the ordered primary/child inventory; the scenario table does not duplicate their count. Must be called at vitest collection time. diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 253e67fd5a..815753ae5f 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, and wait for process exit. */ + /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, and ACP parser drain. */ close(signal?: NodeJS.Signals): Promise } @@ -132,7 +132,6 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe }) child.stdout.on('end', () => { passthrough.push(null) - closeUpdateStream() }) const stream = ndJsonStream( Writable.toWeb(child.stdin) as WritableStream, @@ -163,6 +162,17 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), }) const client = new ClientSideConnection(makeClient, stream) + // `exit` only reports the parent process's status. Descendants may retain + // inherited stdout/stderr handles and buffered ACP frames may still be + // crossing the SDK parser. Node's `close` follows stdio closure; the SDK's + // `closed` follows parser exhaustion. Capture both eagerly so a caller that + // invokes close after process exit still joins the complete drain boundary. + const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) + const drained = Promise.all([stdioClosed, client.closed]).then(() => undefined) + // A caller may await a pending update without calling close(). Make natural + // stream exhaustion terminal for those waiters too, but only after the + // parser has dispatched every buffered frame. + void client.closed.then(closeUpdateStream) return { child, @@ -183,6 +193,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe throw error } if (!isRunning(child)) { + await drained closeUpdateStream() return } @@ -194,6 +205,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe childFailure, ]) if (failure === undefined) { + await drained closeUpdateStream() return } @@ -204,6 +216,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // callers may safely remove cwd/session resources after close rejects. child.kill('SIGKILL') await exited + await drained closeUpdateStream() throw failure }, diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index 861c9d2b04..9b0760213c 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -18,6 +18,7 @@ import { mkdirSync, readFileSync, rmSync, writeFileSync } from 'node:fs' import { readdirSync } from 'node:fs' +import { spawn } from 'node:child_process' import { dirname, join } from 'node:path' import { randomUUID } from 'node:crypto' import { createInterface } from 'node:readline' @@ -50,6 +51,8 @@ interface Behavior { echoWorkspace?: boolean /** Write a line to stderr on boot (spec-side stderr-capture assertions). */ stderrNote?: string + /** Let a short-lived descendant retain stdio and emit one final ACP update plus stderr line after this parent exits. */ + lateInheritedOutput?: boolean /** Session logs to persist on stdin EOF. */ logs?: ScriptedLog[] /** Leave a stray FILE directly under the sessions root (harvest must skip it). */ @@ -256,6 +259,24 @@ function flushLogsAndExit(): void { writeFileSync(join(sessionsRoot, 'bucket-noise', 'notes.txt'), 'not a session log\n') } if (behavior.deleteSessionsRoot === true) rmSync(sessionsRoot, { recursive: true, force: true }) + if (behavior.lateInheritedOutput === true) { + const frame = JSON.stringify({ + jsonrpc: '2.0', + method: 'session/update', + params: { + sessionId, + update: { + sessionUpdate: 'agent_message_chunk', + content: { type: 'text', text: 'late inherited stdout' }, + }, + }, + }) + const code = [ + `setTimeout(() => process.stdout.write(${JSON.stringify(`${frame}\n`)}), 50)`, + `setTimeout(() => process.stderr.write(${JSON.stringify('late inherited stderr\n')}), 75)`, + ].join(';') + spawn(process.execPath, ['-e', code], { stdio: ['ignore', 1, 2] }).unref() + } process.exit(0) } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 192d36dc6c..051db6a0ba 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -91,6 +91,27 @@ describe('runScenario', () => { expect(exited).toBe(true) }) + it('waits for inherited stdio and buffered ACP parsing after the parent exits', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ lateInheritedOutput: true }) + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + env: { DSH_SNAPSHOT_FILE: fixtureFile }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + await launched.client.newSession({ cwd: dir, mcpServers: [] }) + const lateUpdate = launched.waitForUpdate(update => + update.sessionUpdate === 'agent_message_chunk' + && update.content.type === 'text' + && update.content.text === 'late inherited stdout') + + await launched.close() + + await expect(lateUpdate).resolves.toMatchObject({ sessionUpdate: 'agent_message_chunk' }) + expect(launched.rawStdout()).toContain('late inherited stdout') + expect(launched.stderr()).toContain('late inherited stderr') + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From 99b5f04c9bb5ff2ac78d9cc30ce22d65a181c097 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:26:46 +0800 Subject: [PATCH 035/323] fix: use unified identity for bash ownership --- docs/core-data-structures/bash.md | 2 +- ...-18-agent-lifecycle-and-ownership-seams.md | 4 +- .../architecture/2026-06-20-branded-ids.md | 4 +- packages/bash/bash/src/types.ts | 2 +- packages/bash/tool-bash/README.md | 4 +- packages/bash/tool-bash/src/index.ts | 22 ++++----- packages/bash/tool-bash/tests/tools.spec.ts | 46 +++++++++---------- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- 8 files changed, 40 insertions(+), 47 deletions(-) diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index df6c5ab16b..0cc82e5165 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -37,7 +37,7 @@ interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md index d64329262e..d75ec379fc 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md +++ b/docs/rfc/implemented/architecture/2026-06-18-agent-lifecycle-and-ownership-seams.md @@ -22,7 +22,7 @@ A new `cancel()` verb on the `Agent` interface — the single public stop primit ### 3. Bash owner token in the seam -Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.session.header.id` as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.session.header.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +Background-task ownership moved from a `tool-bash` plugin-local `Map` into the executor. `BashExecRequest` gains an optional `owner?: string`; the resolved `BashExecSpec` carries it as required-but-nullable `owner: string | undefined` (a forgotten owner is a visible `undefined`, never a silently-absent property). The executor stores the token on its task and exposes it via a new `BashExecutor.ownerOf(id): string | undefined` seam (NOT on the public `BashTask` — one read path, no redundant API). `tool-bash` deletes its `Map` entirely: it stamps `exec.agent?.id` (the shared registry/session id) as the owner at `start`, and `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token with `!== undefined` semantics (an empty-string token is still a real owner). The completion notice finds the live agent by scanning `ctx.get('agents')?.list()` for `agent.id === ownerToken` (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, where the `ctx.agents` proxy would throw). Because ownership now lives on the task in the executor (disposed with the `dsh-bash` fiber), it SURVIVES a `tool-bash` HMR reload — closing the old `XXX(tool-bash-owner-hmr)` gap. (The `onTaskDone` listener is still effect-scoped to `tool-bash`'s `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## Verification @@ -35,7 +35,7 @@ These invariants hold and are pinned by tests: ## Session owner tokens are unique among live agents -The bash owner-token comparison relies on `session.header.id` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. +The bash owner-token comparison relies on the shared `Agent.id`/`SessionId` being unique among live agents. Concurrent same-ID operations may both prepare privately, but publication enters the session and agent in order; `SessionStore.enter()` rejects a duplicate live session id, and every losing transaction rolls its private state back. A programmatic caller therefore cannot publish two live agents with one session token. The access *policy* (token comparison) stays in `tool-bash` (the consumer); the bash seam stores only an opaque `owner` string and never interprets it — the correct interface/implementation/consumer split. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 4fe7f58168..fd5c5bf953 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's shared `Agent.id`/`SessionId` (`callerToken = (exec) => exec.agent?.id` in `packages/bash/tool-bash/src/index.ts`) wearing a different seam-local name. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the shared id alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -18,7 +18,7 @@ A type-only change. Brands are zero-cost casts; nothing about runtime behavior, - **Brand the bash task id.** Add `BashTaskId = Branded<'BashTaskId'>` plus its same-named factory in `packages/bash/bash/src/types.ts` (the package that *owns* the id), importing `Branded` from `@deepseek-ai/dsh-brand` exactly as `SessionId` does. The brand primitive lives in the dependency-free `dsh-brand` utility package precisely so `dsh-bash` can brand its ids by depending on it alone — it never pulls in `dsh-llm` (or `dsh-session`) just to reach `Branded`. Thread it through `BashTask.id`, the `BashExecutor` seam methods (`get`/`ownerOf`/`readOutput`/`kill`), the generation site in `dsh-bash-local` (brand the counter output once, at creation), and the `dsh-tool-bash` validate/access surface (`validateTaskId` returns a `BashTaskId`; `task_id` is branded at the tool boundary where the model's string arrives). -- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's `session.header.id` (a `SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) +- **Mint a distinct `OwnerToken` brand.** Add `OwnerToken = Branded<'OwnerToken'>` in `packages/bash/bash/src/types.ts`; type `BashExecRequest.owner` / `BashExecSpec.owner` / `BashExecutor.ownerOf` as `OwnerToken | undefined`. The `dsh-tool-bash` consumer casts the agent's shared `id` (`SessionId`) into an `OwnerToken` at the boundary — the one place the two vocabularies meet. The bash seam never imports `dsh-session`. (Rationale in the next section.) - **Stop the brand erosion.** Propagate the existing brands to the `Map` key types and public method params listed under Gap 2 — `Map`, `Map`, `get(id: SessionId)`, `Map`, ACP's `SessionId` surface, and the coordinator's `Map`. This is the larger mechanical share of the diff and the part that makes the *existing* brands actually load-bearing on lookups, not just on struct fields. diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 39dbc162c6..c4c48645e1 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -117,7 +117,7 @@ export interface BashExecRequest { env?: Record | undefined /** * Opaque OWNER token for a background task — the consumer's isolation key - * (the tool layer passes the owning agent's `session.header.id`). The + * (the tool layer passes the owning agent's shared `id`). The * executor stores it on the task and exposes it via {@link BashExecutor.ownerOf}; * the executor itself NEVER interprets it (no access policy lives in the * seam — that is the consumer's job). Absent for foreground runs and for an diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index 800de0132c..c4ea498e07 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -34,7 +34,7 @@ Result text: stdout, then a `[stderr]` section, then status markers — `[sandbo ### Task ownership (cross-session isolation) -The owning agent's session token (`session.header.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token (`session.header.id`) with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) +The owning agent's shared registry/session id (`agent.id`) is stamped onto the task at spawn — passed to the executor via `resolve({ …, owner })` and stored ON THE TASK inside the executor (the `dsh-bash` `ownerOf(id)` seam), **not** in a plugin-local map. `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's shared id with `!== undefined` semantics and reject a task owned by a *different* session with `task belongs to another session` (a task started with no agent — a non-loop caller — has no owner token and is open to anyone; a call with no `exec.agent` cannot access an owned task). Task ids are global and predictable, so under multi-session ACP this token check is the fence that stops one session's agent from reading or killing another session's background task. Because ownership lives on the task in the executor (disposed with the `dsh-bash` fiber), it **survives an independent `tool-bash` HMR reload** — closing the old plugin-local-map gap where a reload orphaned pre-reload tasks. (The `onTaskDone` listener is still effect-scoped to this plugin's `apply`, so a completion landing during the reload gap still drops its one notice — the pre-existing reload-gap drop — but the ownership fence itself is HMR-proof.) ## UI presentation @@ -42,7 +42,7 @@ These tools own how their calls render in a UI (an editor's tool-call card) via ## Background completion notices -When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The owning agent is found by its session token: the listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for an agent whose `session.header.id` matches (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. +When a background task finishes, a short notice is injected into the owning agent's session (`agent.inject()`, source `{kind: 'plugin', plugin: 'tool-bash'}`). The listener reads `ctx.bash.ownerOf(task.id)` and scans `ctx.get('agents')?.list()` for that shared agent/session id (read via `ctx.get` — `onTaskDone` runs on the bash fiber, a foreign fiber, so the `ctx.agents` proxy would throw). If no live agent carries that token — e.g. the owning session disconnected and its agent was disposed while the task ran on — the notice is dropped cleanly. Injection is **durable context for the next model request, not a wake-up** — an idle agent stays idle until something sends a message. That's why the tool descriptions tell the model to poll with `bash_output`. ## The tool builds its request from named args only diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 31e6512ae0..fe07b80989 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -12,7 +12,7 @@ * `bash_output`. * * Task ownership: a background task's OWNER is an opaque token — the owning - * agent's `session.header.id` — passed to the executor at spawn + * agent's shared `id` — passed to the executor at spawn * (`resolve({ …, owner })`) and stored ON THE TASK inside the executor * (`@deepseek-ai/dsh-bash`'s `ownerOf(id)` seam), NOT in a plugin-local map. * `bash_output`/`bash_kill` compare `ctx.bash.ownerOf(id)` to the caller's token @@ -414,16 +414,12 @@ export function apply(ctx: Context): void { }) /** - * The caller's owner TOKEN — the owning agent's `session.header.id`, or - * `undefined` for a non-agent caller. Read `session.header.id` (NOT - * `session.id`): every other subsystem keys off the header id (the ACP bridge, - * both persistence backends), and the sibling `resolveWorkdir` already reads - * `session.header.cwd`, so using `session.id` here would be the asymmetry smell - * the conventions flag. The two are equal in production, but the header is the - * canonical identity. + * The caller's owner TOKEN — the owning agent's shared registry/session id, + * or `undefined` for a non-agent caller. Agent and Session deliberately have + * one live identity; workdir remains separate session metadata. */ const callerToken = (exec: { agent?: Agent }): OwnerToken | undefined => - exec.agent ? OwnerToken(exec.agent.session.header.id) : undefined + exec.agent ? OwnerToken(exec.agent.id) : undefined /** * Authorize a `bash_output`/`bash_kill` call against the task's stored owner @@ -443,18 +439,16 @@ export function apply(ctx: Context): void { } // Background completion → inject a notice into the owning agent's session. - // Find the live agent by its session id token via the agent registry, read + // Find the live agent by its shared registry/session token, read // opportunistically with `ctx.get('agents')` (NOT `ctx.agents`/static inject): // this listener runs from `task.done.then` on the bash fiber — a foreign // fiber — where the `ctx.agents` property proxy would throw through the // traceable shadow; `ctx.get(name)` is the topology-independent lookup. No - // registry mounted (`undefined`) → drop the notice. Match on - // `agent.session.header.id`, NOT the registry key: a config agent's id differs - // from its session id, and the owner token IS the session id. + // registry mounted (`undefined`) → drop the notice. ctx.bash.onTaskDone((task) => { const ownerToken = ctx.bash.ownerOf(task.id) if (ownerToken === undefined) return - const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.session.header.id) === ownerToken) + const agent = ctx.get('agents')?.list().find(a => OwnerToken(a.id) === ownerToken) if (!agent) return try { agent.inject( diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index c68c445f0a..639dd8631a 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -47,22 +47,16 @@ async function setup() { } /** - * Build a fake {@link Agent} whose session token is `sessionId`, REGISTER it in - * `ctx.agents` (the completion-notice path finds the owning agent by scanning - * the registry for a matching `session.header.id`), and return it. The returned + * Build a fake {@link Agent} with the shared registry/session `sessionId`, + * REGISTER it in `ctx.agents`, and return it. The returned * agent is also passed to `execute` as `exec.agent` so it owns the spawned task. * The registration disposer is tracked so {@link unregisterFakeAgents} can drop * it (simulating the owning session disconnecting before a task completes). */ const fakeAgentDisposers = new Map Promise | void)[]>() function registerFakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void): Agent { - // The registry KEY (agent.id) is deliberately DIFFERENT from the session - // token (session.header.id), which is also the agent's durable id. The - // owner token IS the session id, so the notice path must find the agent by - // `session.header.id`, NOT the registry key. Using distinct values here makes - // the test fail if a regression matched on the wrong field (a same-value fake - // would pass either way — the "hits the line but not the scenario" trap). - const agent = { id: `agent-${sessionId}`, inject, session: { header: { version: 0, id: sessionId, createdAt: 0 } } } as unknown as Agent + const id = SessionId(sessionId) + const agent = { id, inject, session: new Session(id) } as unknown as Agent const dispose = ctx.agents.register(agent) const list = fakeAgentDisposers.get(ctx) ?? [] list.push(dispose) @@ -418,9 +412,9 @@ describe('background tools', () => { it('injects a completion notice into the owning agent (found via the registry by session token)', async () => { const ctx = await setup() const inject = vi.fn() - // The notice path looks the agent up in ctx.agents by its session token, so + // The notice path looks the agent up in ctx.agents by its shared id, so // the agent must be REGISTERED (not merely passed to execute). Mount a - // registry and register a fake whose session.header.id IS the owner token. + // registry and register a fake whose agent/session id IS the owner token. const agent = registerFakeAgent(ctx, 'bg', inject) const started = await ctx.tools.execute({ @@ -517,13 +511,14 @@ describe('background task ownership (cross-session isolation)', () => { function callAs(ctx: Context, agent: import('@deepseek-ai/dsh-agent').Agent | undefined, name: string, args: unknown) { return ctx.tools.execute({ callId: CallId(`own-${++callCounter}`), name, arguments: args, ...agent ? { agent } : {} }) } - // Ownership is by TOKEN (session.header.id), NOT agent object identity — so - // each agent needs a DISTINCT session id, else every fake yields the same + // Ownership is by the shared agent/session TOKEN, NOT agent object identity — + // so each agent needs a DISTINCT id, else every fake yields the same // token and the isolation tests pass for the wrong reason (all tasks owned by - // the same token). The impl reads `session.header.id`, so the fakes MUST carry - // it. - const fakeAgent = (sessionId: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: sessionId, createdAt: 0 } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + // the same token). + const fakeAgent = (sessionId: string) => { + const id = SessionId(sessionId) + return { id, inject: () => undefined, session: new Session(id) } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('rejects bash_output/bash_kill for a task owned by a DIFFERENT session token', async () => { const ctx = await setup() @@ -548,7 +543,7 @@ describe('background task ownership (cross-session isolation)', () => { }) it('a DIFFERENT Agent object with the SAME session token may access the task (ownership is by token, not object identity)', async () => { - // Ownership fences by session.header.id, NOT Agent object identity. Two + // Ownership fences by the shared id, NOT Agent object identity. Two // distinct Agent objects sharing one session token (e.g. an agent re-created // on the same session) are the SAME owner. const ctx = await setup() @@ -638,8 +633,10 @@ describe('session-cwd routing (per-session workdir)', () => { return ctx.tools.execute({ callId: CallId(`cwd-${++callCounter}`), name: 'bash', arguments: args, ...agent ? { agent } : {} }) } // An agent whose session header carries a cwd (what session/new records). - const agentInCwd = (cwd: string) => - ({ inject: () => undefined, session: { header: { version: 0, id: 'c', createdAt: 0, cwd } } }) as unknown as import('@deepseek-ai/dsh-agent').Agent + const agentInCwd = (cwd: string) => { + const id = SessionId('c') + return { id, inject: () => undefined, session: { header: { version: 0, id, createdAt: 0, cwd } } } as unknown as import('@deepseek-ai/dsh-agent').Agent + } it('defaults bash to the agent\'s session cwd (not the server launch dir)', async () => { const ctx = await setup() @@ -1188,10 +1185,11 @@ describe('sandbox escalation (sandbox_permissions / justification)', () => { * enforces the enclosure. */ function escalationAgent(events: Array<{ type: string; data: Record }>): Agent { + const id = SessionId('sess-esc') return { - id: 'agent-esc', + id, session: { - header: { version: 0, id: 'sess-esc', createdAt: 0 }, + header: { version: 0, id, createdAt: 0 }, events: [{ type: 'turn/start' }], append: (type: string, data: Record) => { events.push({ type, data }) }, }, @@ -1406,7 +1404,7 @@ describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) const injected: string[] = [] const agent = { - id, + id: SessionId(id), session, inject: (content: { type: string; text: string }[]) => { injected.push(content[0]?.text ?? '') }, } as unknown as Agent diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { From 03f91a547183919422aeb1d699af58d678a8984d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:29:40 +0800 Subject: [PATCH 036/323] fix: retain local subagent completion identity --- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 +++++++++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 23 ++++++++++++- 4 files changed, 45 insertions(+), 17 deletions(-) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 2324227ff7..735cfead0a 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 3c803a6c8c..bf21f7fc2d 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,6 +58,11 @@ interface SessionRecord { activePrompt: boolean } +/** Runtime-local agent identity plus optional durable fork lineage. */ +interface LocalAgentRecord { + parentSessionId?: SessionId +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -71,7 +76,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentParents = new Map() + private readonly localAgents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -95,23 +100,24 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache parent lineage on creation: by the time `subagent/end` fires the - // child agent may already be disposed and gone from the registry. The child - // session id needs no cache because it is the shared agent/session id. + // Cache runtime-local identity and optional lineage on creation: by the + // time `subagent/end` fires the child agent may already be disposed and + // gone from the registry. Parent lineage is not required by the provider + // contract, so an empty record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession - if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) + this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const cachedParentSessionId = this.subagentParents.get(info.id) - this.subagentParents.delete(info.id) - // This protocol reports LOCAL child sessions, paired with the - // session/created-driven subagent.started notification above. A remote - // provider may use a real remote SessionId for its run, but that session - // does not exist in this harness and therefore has no paired start event. - if (cachedParentSessionId === undefined && agent === undefined) return - const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession + const cachedLocalAgent = this.localAgents.get(info.id) + this.localAgents.delete(info.id) + // This protocol reports LOCAL child sessions. A lineage-bearing child + // has the session/created-driven start notification above; a parentless + // local provider still gets its terminal notification. A remote provider + // has neither a cached creation nor a live local agent and is ignored. + if (cachedLocalAgent === undefined && agent === undefined) return + const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), @@ -189,7 +195,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentParents.clear() + this.localAgents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index e7f591b88f..163aee4c0c 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,15 +272,26 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + const parentlessHandle = await ctx.agents.create({ + sessionId: SessionId('parentless-child-session'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) // The backend may dispose the child before publishing its run outcome; - // only the cached parent lineage should be needed at this point. + // cached locality must survive with or without optional parent lineage. await handle.dispose() + await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'spawn', + id: SessionId('parentless-child-session'), + stopReason: 'error', + }) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -294,6 +305,16 @@ describe('HarnessSdkServer', () => { lastAssistantMessage: [{ type: 'text', text: 'child done' }], }, }) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'spawn', + agentId: 'parentless-child-session', + childSessionId: 'parentless-child-session', + status: 'error', + stopReason: 'error', + }, + }) await parentHandle.dispose() await server.shutdown() From f02005c832b450d65d372c935c612c7d83eec54d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:39:28 +0800 Subject: [PATCH 037/323] fix: enforce unified agent startup invariants --- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 3 +++ packages/core/agent/tests/agent.spec.ts | 12 ++++++++- .../hooks/hooks-claude/tests/coverage.spec.ts | 8 +++--- packages/subagent/subagent-acp/src/run.ts | 11 ++++---- .../subagent-acp/tests/mock-acp-server.ts | 3 +++ .../subagent-acp/tests/subagent-acp.spec.ts | 26 +++++++++++++++++++ 7 files changed, 55 insertions(+), 10 deletions(-) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 643c15002b..a45603f191 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -11,7 +11,7 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. -- Advanced ordered lifecycle: `enter(agent, owner): () => void` performs the authoritative ID collision check and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. +- Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index b25d1e3cac..abafa38e45 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -329,6 +329,9 @@ export class AgentRegistry extends Service { */ enter(agent: Agent, owner: Agent | undefined): () => void { const id = agent.id + if (id !== agent.session.id) { + throw new Error(`agent id "${id}" does not match session id "${agent.session.id}"`) + } const carrier = scopeTarget(agent, agent) // This is the authoritative collision boundary. Concurrent create/resume // operations may both prepare, but only one exact entry can publish. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5563d01cad..d2866cacb3 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -11,7 +11,7 @@ function stubAgent(rawId: string): Agent { return { id, options: {}, - session: new Session(SessionId(`${id}-session`)), + session: new Session(id), status: 'idle', ctx: new Context(), send() {}, @@ -50,6 +50,16 @@ describe('AgentRegistry', () => { expect(lifecycle).toEqual(['created:a1', 'disposed:a1']) }) + it('rejects an agent whose registry and session identities differ', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const agent = { ...stubAgent('agent-id'), session: new Session(SessionId('session-id')) } + + expect(() => ctx.agents.enter(agent, undefined)) + .toThrow('agent id "agent-id" does not match session id "session-id"') + expect(ctx.agents.list()).toEqual([]) + }) + it('tracks runtime creator ownership separately from registry order', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 16c48aa149..0b41fd0d10 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -4,7 +4,7 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionStore, { Session, SessionId, type SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' @@ -209,7 +209,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const ctx = await harness(path, new MockAdapter([])) // Register a fake child agent under the id the event carries. const injected: string[] = [] - const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { header: { id: 'child-x' } } } as unknown as Parameters[0] + const childId = SessionId('child-x') + const child = { id: childId, inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) await waitFor(() => injected.includes('child guidance')) @@ -225,7 +226,8 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { SubagentStart: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) const warn = vi.fn(); ctx.logger.warn = warn as never - const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { header: { id: 'child-y' } } } as unknown as Parameters[0] + const childId = SessionId('child-y') + const child = { id: childId, inject: () => { throw new Error('inject boom') }, session: new Session(childId) } as unknown as Parameters[0] ctx.agents.register(child) ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 7d0c11cbe1..8ef49f0f7d 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -311,7 +311,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe clientCapabilities: {}, }) const session = await conn.newSession({ cwd: spec.cwd, mcpServers: [] }) - sessionId = session.sessionId + const returnedSessionId: unknown = Reflect.get(session, 'sessionId') + if (typeof returnedSessionId !== 'string') throw new Error('ACP child published without a session id') + sessionId = returnedSessionId if (flags.cancelled) throw new Error('subagent cancelled before the ACP session started') })(), spawnFailed.then((err): never => { throw err }), @@ -323,10 +325,9 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe if (flags.cancelled) throw new Error('subagent request was aborted before the ACP child started') throw toError(error) } - // The startup race can fulfill only after newSession assigned the id; this - // guard keeps that cross-closure invariant explicit for TypeScript. - /* v8 ignore next */ - if (sessionId === undefined) throw new Error('ACP child published without a session id') + // The startup transaction validates the returned id before it can fulfill. + // This assertion carries that cross-closure invariant into TypeScript. + if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId const result: Promise = (async (): Promise => { diff --git a/packages/subagent/subagent-acp/tests/mock-acp-server.ts b/packages/subagent/subagent-acp/tests/mock-acp-server.ts index 5145941526..f56404834b 100644 --- a/packages/subagent/subagent-acp/tests/mock-acp-server.ts +++ b/packages/subagent/subagent-acp/tests/mock-acp-server.ts @@ -19,6 +19,8 @@ * handler is in flight (it has streamed its chunk). A test * polls for this file to cancel on a CONDITION rather than * an arbitrary timeout (subprocess cold-start is variable). + * - `MOCK_MISSING_SESSION_ID` — if `1`, return a malformed empty `session/new` + * response to exercise startup rollback. * - `MOCK_FLUSH_ON_EOF` — if set, on stdin EOF the agent takes an async beat * (MOCK_FLUSH_DELAY_MS, default 150) simulating the real * acp-agent's EOF-driven quiesce+flush, then touches this @@ -99,6 +101,7 @@ function makeAgent(conn: AgentSideConnection): Agent { writeFileSync(NEWSESSION_GATE.ready, 'at-newSession') while (!existsSync(NEWSESSION_GATE.go)) await new Promise(r => setTimeout(r, 10)) } + if (process.env.MOCK_MISSING_SESSION_ID === '1') return {} as NewSessionResponse return { sessionId: process.env.MOCK_SESSION_ID ?? randomUUID() } }, authenticate(_params: AuthenticateRequest): Promise { diff --git a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts index e5fe05384e..daa037ca20 100644 --- a/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts +++ b/packages/subagent/subagent-acp/tests/subagent-acp.spec.ts @@ -195,6 +195,32 @@ describe('dsh-subagent-acp', () => { } }) + it('reaps a child whose session/new response omits the session id', async () => { + const tmp = mkdtempSync(join(tmpdir(), 'acp-malformed-session-')) + const flushed = join(tmp, 'flushed') + try { + await expect(startAcpRun(request(), { + command: process.execPath, + args: ['--import', tsxLoader, mockServer], + cwd: process.cwd(), + permission: 'reject', + env: { + MOCK_MISSING_SESSION_ID: '1', + MOCK_FLUSH_ON_EOF: flushed, + MOCK_FLUSH_DELAY_MS: '20', + TSX_TSCONFIG_PATH: repoTsconfig, + }, + disposeEofGraceMs: 1000, + disposeGraceMs: 100, + })).rejects.toThrow('ACP child published without a session id') + // Startup rejects only after its private child reaches quiescence. The + // marker proves rollback closed stdin and allowed the child's EOF flush. + expect(existsSync(flushed)).toBe(true) + } finally { + rmSync(tmp, { recursive: true, force: true }) + } + }) + it('dispose escalates SIGTERM → SIGKILL for a child that traps SIGTERM (bounded quiescence)', async () => { // The child traps SIGTERM and keeps its event loop alive, so a graceful // term alone would hang dispose forever. With a short grace, dispose must From a9c4fe2c4ba9f92a85117d60ad01ce1ee5930c69 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:43:01 +0800 Subject: [PATCH 038/323] test: exclude validated ACP assertion --- packages/subagent/subagent-acp/src/run.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index 8ef49f0f7d..e135beb210 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -327,6 +327,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe } // The startup transaction validates the returned id before it can fulfill. // This assertion carries that cross-closure invariant into TypeScript. + /* v8 ignore next */ if (sessionId === undefined) throw new Error('unreachable: ACP startup fulfilled without a session id') const remoteSessionId = sessionId From 47812b45db85a9824530e800b12de1c82fdd6972 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:57:45 +0800 Subject: [PATCH 039/323] test: re-record Codex hook snapshot --- .../hook-codex-posttool-block/session.jsonl | 340 ++++++------------ .../stdout.golden.jsonl | 153 ++------ 2 files changed, 142 insertions(+), 351 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl index ae105f6679..94bbbc5a08 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl @@ -1,222 +1,118 @@ -{"type":"session","version":0,"id":"7a5183c0-ec3a-46a8-a382-475eaa0c205b","createdAt":1783352220743,"cwd":"/tmp/acp-snap-cwd-vGnYqn"} -{"type":"turn/start","seq":0,"time":1783352220747,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352220748,"data":{"content":[{"type":"text","text":"Call the bash tool exactly once to run: echo HELLO. Whatever tool result comes back, quote it verbatim and stop without calling another tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352220749,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352220750,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352221651,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352221685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352221685,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} -{"type":"assistant/chunk","seq":11,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":12,"time":1783352221686,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} -{"type":"assistant/chunk","seq":13,"time":1783352221709,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":14,"time":1783352221710,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"echo"}}} -{"type":"assistant/chunk","seq":15,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" HE"}}} -{"type":"assistant/chunk","seq":16,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LL"}}} -{"type":"assistant/chunk","seq":17,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"O"}}} -{"type":"assistant/chunk","seq":18,"time":1783352221711,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":19,"time":1783352221738,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} -{"type":"assistant/chunk","seq":20,"time":1783352221738,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":21,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} -{"type":"assistant/chunk","seq":22,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":23,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":24,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":25,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":26,"time":1783352221768,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":27,"time":1783352221794,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":28,"time":1783352221795,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":29,"time":1783352221795,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":30,"time":1783352221884,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":31,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":32,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":33,"time":1783352221885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":34,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"command"}}} -{"type":"assistant/chunk","seq":35,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":36,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":37,"time":1783352221915,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":38,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"echo"}}} -{"type":"assistant/chunk","seq":39,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" HE"}}} -{"type":"assistant/chunk","seq":40,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"LL"}}} -{"type":"assistant/chunk","seq":41,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"O"}}} -{"type":"assistant/chunk","seq":42,"time":1783352221945,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":43,"time":1783352222000,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":44,"time":1783352222000,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":45,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":46,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":47,"time":1783352222001,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":48,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":49,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"Print"}}} -{"type":"assistant/chunk","seq":50,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" HE"}}} -{"type":"assistant/chunk","seq":51,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"LL"}}} -{"type":"assistant/chunk","seq":52,"time":1783352222031,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"O"}}} -{"type":"assistant/chunk","seq":53,"time":1783352222058,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" to"}}} -{"type":"assistant/chunk","seq":54,"time":1783352222059,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":" stdout"}}} -{"type":"assistant/chunk","seq":55,"time":1783352222059,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":56,"time":1783352222088,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":57,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."}}}} -{"type":"assistant/chunk","seq":58,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}}}} -{"type":"assistant/chunk","seq":59,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}}}} -{"type":"assistant/chunk","seq":60,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":61,"time":1783352222124,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}],"usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} -{"type":"tool/call","seq":62,"time":1783352222124,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}} -{"type":"hook/invoked","seq":63,"time":1783352222138,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} -{"type":"hook/result","seq":64,"time":1783352222148,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":9.571565000000192}} -{"type":"tool/result","seq":65,"time":1783352222148,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","content":[{"type":"text","text":"tool output rejected by codex policy: summarize instead"}],"isError":true},"sourceEventSeqs":[62],"surfaceOp":"append"} -{"type":"step/end","seq":66,"time":1783352222149,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":67,"time":1783352222149,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":68,"time":1783352223151,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":69,"time":1783352223151,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":70,"time":1783352223301,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":71,"time":1783352223315,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} -{"type":"assistant/chunk","seq":72,"time":1783352223316,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":73,"time":1783352223316,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} -{"type":"assistant/chunk","seq":74,"time":1783352223343,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":75,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} -{"type":"assistant/chunk","seq":76,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} -{"type":"assistant/chunk","seq":77,"time":1783352223344,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":78,"time":1783352223372,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":79,"time":1783352223406,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":80,"time":1783352223407,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instruction"}}} -{"type":"assistant/chunk","seq":81,"time":1783352223407,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":82,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":83,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"sum"}}} -{"type":"assistant/chunk","seq":84,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"mar"}}} -{"type":"assistant/chunk","seq":85,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ize"}}} -{"type":"assistant/chunk","seq":86,"time":1783352223430,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instead"}}} -{"type":"assistant/chunk","seq":87,"time":1783352223458,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":88,"time":1783352223487,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" This"}}} -{"type":"assistant/chunk","seq":89,"time":1783352223487,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" means"}}} -{"type":"assistant/chunk","seq":90,"time":1783352223488,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":91,"time":1783352223519,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" cannot"}}} -{"type":"assistant/chunk","seq":92,"time":1783352223520,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" show"}}} -{"type":"assistant/chunk","seq":93,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":94,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" raw"}}} -{"type":"assistant/chunk","seq":95,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":96,"time":1783352223548,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":97,"time":1783352223576,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":98,"time":1783352223576,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":99,"time":1783352223605,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":100,"time":1783352223640,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":101,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" requested"}}} -{"type":"assistant/chunk","seq":102,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":103,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} -{"type":"assistant/chunk","seq":104,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":105,"time":1783352223641,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" try"}}} -{"type":"assistant/chunk","seq":106,"time":1783352223663,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":107,"time":1783352223664,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" comply"}}} -{"type":"assistant/chunk","seq":108,"time":1783352223691,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" but"}}} -{"type":"assistant/chunk","seq":109,"time":1783352223692,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":110,"time":1783352223721,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} -{"type":"assistant/chunk","seq":111,"time":1783352223721,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" happened"}}} -{"type":"assistant/chunk","seq":112,"time":1783352223749,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":".\n\n"}}} -{"type":"assistant/chunk","seq":113,"time":1783352223749,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"Actually"}}} -{"type":"assistant/chunk","seq":114,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":115,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":116,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":117,"time":1783352223750,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":118,"time":1783352223778,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":119,"time":1783352223779,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":120,"time":1783352223779,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":121,"time":1783352223813,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":122,"time":1783352223813,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":123,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":124,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":125,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":126,"time":1783352223837,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":127,"time":1783352223865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} -{"type":"assistant/chunk","seq":128,"time":1783352223866,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":129,"time":1783352223866,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} -{"type":"assistant/chunk","seq":130,"time":1783352223896,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":131,"time":1783352223897,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" got"}}} -{"type":"assistant/chunk","seq":132,"time":1783352223923,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" back"}}} -{"type":"assistant/chunk","seq":133,"time":1783352223923,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":134,"time":1783352223952,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":135,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":136,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"tool"}}} -{"type":"assistant/chunk","seq":137,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} -{"type":"assistant/chunk","seq":138,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} -{"type":"assistant/chunk","seq":139,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} -{"type":"assistant/chunk","seq":140,"time":1783352223953,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} -{"type":"assistant/chunk","seq":141,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} -{"type":"assistant/chunk","seq":142,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} -{"type":"assistant/chunk","seq":143,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":144,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" summarize"}}} -{"type":"assistant/chunk","seq":145,"time":1783352223981,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" instead"}}} -{"type":"assistant/chunk","seq":146,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"\n\n"}}} -{"type":"assistant/chunk","seq":147,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"So"}}} -{"type":"assistant/chunk","seq":148,"time":1783352224017,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":149,"time":1783352224018,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":150,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" report"}}} -{"type":"assistant/chunk","seq":151,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":152,"time":1783352224039,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":153,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":154,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":155,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":156,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"The"}}} -{"type":"assistant/chunk","seq":157,"time":1783352224068,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} -{"type":"assistant/chunk","seq":158,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} -{"type":"assistant/chunk","seq":159,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" I"}}} -{"type":"assistant/chunk","seq":160,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" got"}}} -{"type":"assistant/chunk","seq":161,"time":1783352224105,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" back"}}} -{"type":"assistant/chunk","seq":162,"time":1783352224129,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":163,"time":1783352224159,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":164,"time":1783352224159,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":">"}}} -{"type":"assistant/chunk","seq":165,"time":1783352224186,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" `"}}} -{"type":"assistant/chunk","seq":166,"time":1783352224186,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} -{"type":"assistant/chunk","seq":167,"time":1783352224187,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} -{"type":"assistant/chunk","seq":168,"time":1783352224215,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} -{"type":"assistant/chunk","seq":169,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" by"}}} -{"type":"assistant/chunk","seq":170,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} -{"type":"assistant/chunk","seq":171,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} -{"type":"assistant/chunk","seq":172,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} -{"type":"assistant/chunk","seq":173,"time":1783352224216,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} -{"type":"assistant/chunk","seq":174,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} -{"type":"assistant/chunk","seq":175,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} -{"type":"assistant/chunk","seq":176,"time":1783352224244,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"`\n\n"}}} -{"type":"assistant/chunk","seq":177,"time":1783352224245,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"This"}}} -{"type":"assistant/chunk","seq":178,"time":1783352224245,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" is"}}} -{"type":"assistant/chunk","seq":179,"time":1783352224297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":180,"time":1783352224297,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" verb"}}} -{"type":"assistant/chunk","seq":181,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"atim"}}} -{"type":"assistant/chunk","seq":182,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" result"}}} -{"type":"assistant/chunk","seq":183,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" from"}}} -{"type":"assistant/chunk","seq":184,"time":1783352224305,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":185,"time":1783352224331,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" tool"}}} -{"type":"assistant/chunk","seq":186,"time":1783352224360,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" —"}}} -{"type":"assistant/chunk","seq":187,"time":1783352224361,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" it"}}} -{"type":"assistant/chunk","seq":188,"time":1783352224361,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" was"}}} -{"type":"assistant/chunk","seq":189,"time":1783352224392,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" not"}}} -{"type":"assistant/chunk","seq":190,"time":1783352224418,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":191,"time":1783352224446,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" expected"}}} -{"type":"assistant/chunk","seq":192,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" `"}}} -{"type":"assistant/chunk","seq":193,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\""}}} -{"type":"assistant/chunk","seq":194,"time":1783352224476,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"HE"}}} -{"type":"assistant/chunk","seq":195,"time":1783352224505,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"LL"}}} -{"type":"assistant/chunk","seq":196,"time":1783352224505,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"O"}}} -{"type":"assistant/chunk","seq":197,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\""}}} -{"type":"assistant/chunk","seq":198,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"`"}}} -{"type":"assistant/chunk","seq":199,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} -{"type":"assistant/chunk","seq":200,"time":1783352224506,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" because"}}} -{"type":"assistant/chunk","seq":201,"time":1783352224533,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" the"}}} -{"type":"assistant/chunk","seq":202,"time":1783352224534,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} -{"type":"assistant/chunk","seq":203,"time":1783352224534,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} -{"type":"assistant/chunk","seq":204,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} -{"type":"assistant/chunk","seq":205,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" blocked"}}} -{"type":"assistant/chunk","seq":206,"time":1783352224563,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" it"}}} -{"type":"assistant/chunk","seq":207,"time":1783352224592,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" and"}}} -{"type":"assistant/chunk","seq":208,"time":1783352224621,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instructed"}}} -{"type":"assistant/chunk","seq":209,"time":1783352224621,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" me"}}} -{"type":"assistant/chunk","seq":210,"time":1783352224653,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" to"}}} -{"type":"assistant/chunk","seq":211,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} -{"type":"assistant/chunk","seq":212,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} -{"type":"assistant/chunk","seq":213,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"."}}} -{"type":"assistant/chunk","seq":214,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."}}}} -{"type":"assistant/chunk","seq":215,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}}}} -{"type":"assistant/chunk","seq":216,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}}}} -{"type":"assistant/chunk","seq":217,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":218,"time":1783352224655,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."},{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}],"usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}},"sourceEventSeqs":[68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217],"surfaceOp":"append"} -{"type":"step/end","seq":219,"time":1783352224655,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":220,"time":1783352224655,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"01aa6a36-e9c2-42ba-934b-30bec80a1658","createdAt":1783986962232,"cwd":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-x67BsP"} +{"type":"turn/start","seq":0,"time":1783986962235,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783986962235,"data":{"content":[{"type":"text","text":"Call the bash tool exactly once to run: echo HELLO. Whatever tool result comes back, quote it verbatim and stop without calling another tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783986962240,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783986962240,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783986962953,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783986962953,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" call"}}} +{"type":"assistant/chunk","seq":11,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":12,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} +{"type":"assistant/chunk","seq":13,"time":1783986963134,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":14,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} +{"type":"assistant/chunk","seq":15,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1783986963135,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" `"}}} +{"type":"assistant/chunk","seq":17,"time":1783986963160,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"echo"}}} +{"type":"assistant/chunk","seq":18,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" HE"}}} +{"type":"assistant/chunk","seq":19,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"LL"}}} +{"type":"assistant/chunk","seq":20,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"O"}}} +{"type":"assistant/chunk","seq":21,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"`,"}}} +{"type":"assistant/chunk","seq":22,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":23,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" quote"}}} +{"type":"assistant/chunk","seq":24,"time":1783986963213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":25,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" result"}}} +{"type":"assistant/chunk","seq":26,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} +{"type":"assistant/chunk","seq":27,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} +{"type":"assistant/chunk","seq":28,"time":1783986963221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":29,"time":1783986963252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":30,"time":1783986963252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":31,"time":1783986963314,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":32,"time":1783986963315,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":33,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":34,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":35,"time":1783986963345,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":36,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":37,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":38,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":39,"time":1783986963369,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"echo"}}} +{"type":"assistant/chunk","seq":40,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" HE"}}} +{"type":"assistant/chunk","seq":41,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"LL"}}} +{"type":"assistant/chunk","seq":42,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"O"}}} +{"type":"assistant/chunk","seq":43,"time":1783986963397,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":44,"time":1783986963428,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":45,"time":1783986963429,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":46,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":47,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":48,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":49,"time":1783986963457,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":50,"time":1783986963489,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"E"}}} +{"type":"assistant/chunk","seq":51,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"cho"}}} +{"type":"assistant/chunk","seq":52,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" HE"}}} +{"type":"assistant/chunk","seq":53,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"LL"}}} +{"type":"assistant/chunk","seq":54,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"O"}}} +{"type":"assistant/chunk","seq":55,"time":1783986963514,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":56,"time":1783986963544,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":" stdout"}}} +{"type":"assistant/chunk","seq":57,"time":1783986963544,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":58,"time":1783986963658,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":59,"time":1783986963659,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to call the bash tool once with `echo HELLO`, then quote the result verbatim and stop."}}}} +{"type":"assistant/chunk","seq":60,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}}}} +{"type":"assistant/chunk","seq":61,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3256,"outputTokens":94,"cacheReadTokens":0,"reasoningTokens":26}}}} +{"type":"assistant/chunk","seq":62,"time":1783986963660,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":63,"time":1783986963663,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to call the bash tool once with `echo HELLO`, then quote the result verbatim and stop."},{"type":"tool-call","id":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}],"usage":{"inputTokens":3256,"outputTokens":94,"cacheReadTokens":0,"reasoningTokens":26}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62],"surfaceOp":"append"} +{"type":"tool/call","seq":64,"time":1783986963664,"data":{"turn":1,"step":1,"callId":"call_00_1rmSWHhVchVg7PDTmegT0421","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}} +{"type":"hook/invoked","seq":65,"time":1783986963673,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} +{"type":"hook/result","seq":66,"time":1783986963677,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":4.42941699999983}} +{"type":"tool/result","seq":67,"time":1783986963678,"data":{"turn":1,"step":1,"callId":"call_00_1rmSWHhVchVg7PDTmegT0421","content":[{"type":"text","text":"tool output rejected by codex policy: summarize instead"}],"isError":true},"sourceEventSeqs":[64],"surfaceOp":"append"} +{"type":"step/end","seq":68,"time":1783986963678,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":69,"time":1783986963679,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":70,"time":1783986964555,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":71,"time":1783986964555,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":72,"time":1783986964809,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":73,"time":1783986964835,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} +{"type":"assistant/chunk","seq":74,"time":1783986964835,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} +{"type":"assistant/chunk","seq":75,"time":1783986964836,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" rejected"}}} +{"type":"assistant/chunk","seq":76,"time":1783986964864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" by"}}} +{"type":"assistant/chunk","seq":77,"time":1783986964865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" code"}}} +{"type":"assistant/chunk","seq":78,"time":1783986964865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"x"}}} +{"type":"assistant/chunk","seq":79,"time":1783986964893,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" policy"}}} +{"type":"assistant/chunk","seq":80,"time":1783986964899,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":81,"time":1783986964900,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":82,"time":1783986964924,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":83,"time":1783986964924,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" quote"}}} +{"type":"assistant/chunk","seq":84,"time":1783986964955,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} +{"type":"assistant/chunk","seq":85,"time":1783986964985,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":86,"time":1783986965013,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" got"}}} +{"type":"assistant/chunk","seq":87,"time":1783986965014,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" back"}}} +{"type":"assistant/chunk","seq":88,"time":1783986965045,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":89,"time":1783986965132,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":90,"time":1783986965132,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```\n"}}} +{"type":"assistant/chunk","seq":91,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"<"}}} +{"type":"assistant/chunk","seq":92,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} +{"type":"assistant/chunk","seq":93,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_result"}}} +{"type":"assistant/chunk","seq":94,"time":1783986965133,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":">"}}} +{"type":"assistant/chunk","seq":95,"time":1783986965233,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"tool"}}} +{"type":"assistant/chunk","seq":96,"time":1783986965234,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" output"}}} +{"type":"assistant/chunk","seq":97,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" rejected"}}} +{"type":"assistant/chunk","seq":98,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" by"}}} +{"type":"assistant/chunk","seq":99,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" code"}}} +{"type":"assistant/chunk","seq":100,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"x"}}} +{"type":"assistant/chunk","seq":101,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" policy"}}} +{"type":"assistant/chunk","seq":102,"time":1783986965235,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":":"}}} +{"type":"assistant/chunk","seq":103,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" summarize"}}} +{"type":"assistant/chunk","seq":104,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":" instead"}}} +{"type":"assistant/chunk","seq":105,"time":1783986965236,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"\n"}}} +{"type":"assistant/chunk","seq":109,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"```"}}} +{"type":"assistant/chunk","seq":110,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The tool output was rejected by codex policy. Let me quote what I got back."}}}} +{"type":"assistant/chunk","seq":111,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"```\ntool output rejected by codex policy: summarize instead\n```"}}}} +{"type":"assistant/chunk","seq":112,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":44,"outputTokens":39,"cacheReadTokens":3328,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":113,"time":1783986965237,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":114,"time":1783986965238,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The tool output was rejected by codex policy. Let me quote what I got back."},{"type":"text","text":"```\ntool output rejected by codex policy: summarize instead\n```"}],"usage":{"inputTokens":44,"outputTokens":39,"cacheReadTokens":3328,"reasoningTokens":18}},"sourceEventSeqs":[70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113],"surfaceOp":"append"} +{"type":"step/end","seq":115,"time":1783986965238,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":116,"time":1783986965238,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index fddecc08c6..1c99b178a3 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -5,124 +5,52 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" call"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" command"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" once"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" `"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"echo"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" HE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"LL"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"O"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"`,"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" quote"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_wNJIQDMLdssZp45zIXvz2684","title":"echo HELLO","kind":"execute","status":"in_progress","rawInput":"echo HELLO","content":[{"type":"content","content":{"type":"text","text":"Print HELLO to stdout"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_wNJIQDMLdssZp45zIXvz2684","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\ntool output rejected by codex policy: summarize instead\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_1rmSWHhVchVg7PDTmegT0421","title":"echo HELLO","kind":"execute","status":"in_progress","rawInput":"echo HELLO","content":[{"type":"content","content":{"type":"text","text":"Echo HELLO to stdout"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_1rmSWHhVchVg7PDTmegT0421","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\ntool output rejected by codex policy: summarize instead\n```"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" by"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" code"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"x"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instruction"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sum"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"mar"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" This"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" means"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cannot"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" show"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" raw"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" requested"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" try"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" comply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" but"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" quote"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" what"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" happened"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Actually"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" got"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" back"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" rejected"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" by"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" code"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"x"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" summarize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"So"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" report"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" got"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" back"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":":\n\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"```\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"<"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"tool"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"_result"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":">"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" `"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" output"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" rejected"}}}} @@ -133,42 +61,9 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":":"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" summarize"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"`\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"This"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" is"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" result"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" from"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" —"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" was"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" not"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" expected"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" `"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"HE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"LL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"O"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"`"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" output"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" because"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" code"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"x"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" policy"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" blocked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instructed"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" summarize"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":" instead"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"```"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} From 8ada835396a021a7dce8f72d6b025dcd3a264c15 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:03:33 +0800 Subject: [PATCH 040/323] docs: remove links to private subagent helpers --- packages/subagent/subagent-subprocess/src/index.ts | 12 +++++------- packages/subagent/tool-subagent/src/index.ts | 10 +++++----- 2 files changed, 10 insertions(+), 12 deletions(-) diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index 2ee2745985..bd792e7f23 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -2,11 +2,10 @@ * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn * an external agent as a child process and must keep the parent deployment's * credentials out of it, tear it down to quiescence, and isolate it from the - * host user's on-disk CLI state. The pieces: the credential env scrub - * ({@link SENSITIVE_ENV_PATTERN} / {@link buildChildEnv}), the spawn-failure - * capture ({@link spawnFailure}), the child-exit waits ({@link waitForExit} / - * {@link exitsWithin}), the stdin-EOF → SIGTERM → SIGKILL dispose ladder - * ({@link disposeChildProcess}), and the per-run isolated config dir + * host user's on-disk CLI state. The pieces: credential-shaped env scrubbing + * ({@link buildChildEnv}), spawn-failure capture ({@link spawnFailure}), + * bounded child-exit waits inside the stdin-EOF → SIGTERM → SIGKILL dispose + * ladder ({@link disposeChildProcess}), and the per-run isolated config dir * ({@link createIsolatedConfigDir}). * * This package owns no provider and registers nothing; it is a pure library @@ -37,8 +36,7 @@ const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i /** * The ambient env minus credential-shaped vars, plus the caller's explicit * env. `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive the scrub, so - * a child CLI runs normally; only {@link SENSITIVE_ENV_PATTERN}-shaped names - * are dropped. + * a child CLI runs normally; only credential-shaped names are dropped. * @param extra - explicit vars layered on top AFTER the scrub, so a * credential-shaped name supplied deliberately still reaches the child. * @returns the environment to spawn the child with. diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index 426753dbb9..ff54bc109a 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -12,11 +12,11 @@ * sees only `{ description, prompt }`. * * The tool DESCRIPTION is derived from the bound provider's conversation-history - * descriptor ({@link providerWording}): a fresh-conversation provider (spawn, - * ACP) gets the standalone-prompt wording, while a seeded-conversation provider - * (fork) tells the model the child already sees the conversation's completed - * turns. This descriptor says nothing about Cordis scope, services, tools, or - * authority. The tool MIRRORS the + * descriptor ({@link SubagentProvider.inheritsParentContext}): a + * fresh-conversation provider (spawn, ACP) gets the standalone-prompt wording, + * while a seeded-conversation provider (fork) tells the model the child already + * sees the conversation's completed turns. This descriptor says nothing about + * Cordis scope, services, tools, or authority. The tool MIRRORS the * provider's lifecycle via `subagent/provider-added`/`-removed` — it registers * when the provider is (or becomes) available and unregisters when the * provider goes away — so no load-order requirement exists and an HMR reload From cb80277e60c17ac5238dc7ee740ae315ee3521ff Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:11:13 +0800 Subject: [PATCH 041/323] fix: retain JSON-RPC subagent locality per run --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 45 +++++++++++---- packages/ui/jsonrpc/tests/server.spec.ts | 73 ++++++++++++++++++++---- 4 files changed, 98 insertions(+), 26 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..04aff464a9 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -8,7 +8,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | @@ -34,7 +34,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:73`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 735cfead0a..95d7d7c7d7 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index bf21f7fc2d..12bf82de3c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -17,7 +17,7 @@ import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' -import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -65,10 +65,11 @@ interface LocalAgentRecord { /** * The SDK server over a booted harness context. Constructing it subscribes to - * the context's `session/event`, `session/created`, `agent/created`, and - * `subagent/end` events and forwards them to the host as notifications; the - * subscriptions live until {@link shutdown}. One instance serves one transport - * peer for the process lifetime — there is no re-`initialize`. + * session, agent, and subagent lifecycle events, forwarding durable session + * events and SDK-facing completion notifications while retaining local-run + * identity across child disposal. The subscriptions live until + * {@link shutdown}. One instance serves one transport peer for the process + * lifetime — there is no re-`initialize`. */ export class HarnessSdkServer { private cwd = process.cwd() @@ -77,6 +78,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() + private readonly localRuns = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,18 +102,38 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage on creation: by the - // time `subagent/end` fires the child agent may already be disposed and - // gone from the registry. Parent lineage is not required by the provider - // contract, so an empty record remains a load-bearing locality marker. + // Cache runtime-local identity and optional lineage for each agent lifetime. + // Parent lineage is not required by the provider contract, so an empty + // record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + this.disposers.push(ctx.on('agent/disposed', (agent) => { + this.localAgents.delete(agent.id) + })) + // Snapshot locality per run. A provider may settle one run, continue the + // same live child in another run, and dispose that child before the later + // result settles. Consuming an agent-lifetime marker at the first end would + // lose the later notification; this queue pairs each start with one end. + this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) - this.localAgents.delete(info.id) + const localAgent = cachedLocalAgent ?? (agent === undefined + ? undefined + : agent.session.header.parentSession === undefined + ? {} + : { parentSessionId: agent.session.header.parentSession }) + if (localAgent === undefined) return + const runs = this.localRuns.get(info.id) ?? [] + runs.push(localAgent) + this.localRuns.set(info.id, runs) + })) + this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + const agent = this.ctx.agents.get(info.id) + const runs = this.localRuns.get(info.id) + const cachedLocalAgent = runs?.shift() + if (runs?.length === 0) this.localRuns.delete(info.id) // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider @@ -196,6 +218,7 @@ export class HarnessSdkServer { const records = [...this.sessions.values()] this.sessions.clear() this.localAgents.clear() + this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 163aee4c0c..d56f3000f6 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -11,7 +11,7 @@ import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' -import SubagentService, { type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import SubagentService, { type SubagentResult, type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import { HarnessSdkServer, type JsonRpcTransportPeer } from '../src/index.ts' class FakeTransport implements JsonRpcTransportPeer { @@ -67,7 +67,13 @@ async function makeHarness(storageDir: string) { } /** Drive the owning service so test lifecycle events carry the real parent scope. */ -async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndInfo): Promise { +async function settleSubagent( + ctx: Context, + parent: Agent, + info: SubagentRunEndInfo, + beforeSettle?: () => Promise, +): Promise { + const result = Promise.withResolvers() const disposeProvider = ctx.subagents.registerProvider({ name: info.provider, capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, @@ -75,9 +81,7 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI async start() { return { id: info.id, - result: info.lastAssistantMessage === undefined - ? Promise.reject(new Error('synthetic infrastructure failure')) - : Promise.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }), + result: result.promise, dispose: () => Promise.resolve(), } }, @@ -88,6 +92,12 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI prompt: [], signal: new AbortController().signal, }) + await beforeSettle?.() + if (info.lastAssistantMessage === undefined) { + result.reject(new Error('synthetic infrastructure failure')) + } else { + result.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }) + } await run.result.then(() => undefined, () => undefined) await run.dispose() } finally { @@ -277,21 +287,17 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - // The backend may dispose the child before publishing its run outcome; - // cached locality must survive with or without optional parent lineage. - await handle.dispose() - await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], - }) + }, () => handle.dispose()) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('parentless-child-session'), stopReason: 'error', - }) + }, () => parentlessHandle.dispose()) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -324,6 +330,49 @@ describe('HarnessSdkServer', () => { } }) + it('retains locality across continuation runs on one live child', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const childHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-child'), + meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'first' }], + }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'second' }], + }, () => childHandle.dispose()) + + expect(transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'continuation-child', + )).toHaveLength(2) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -585,6 +634,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(4) + expect(on).toHaveBeenCalledTimes(6) }) }) From d898d1faf0739e4e4f2edd5b6f7a156f54ed2d25 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:25:52 +0800 Subject: [PATCH 042/323] fix: avoid FIFO subagent lineage attribution --- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 49 ++++++--- packages/ui/jsonrpc/tests/server.spec.ts | 123 ++++++++++++++++++++++- 3 files changed, 158 insertions(+), 16 deletions(-) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 95d7d7c7d7..5ff7eb7f8e 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 12bf82de3c..ce0ac9c75a 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -63,6 +63,13 @@ interface LocalAgentRecord { parentSessionId?: SessionId } +/** Pending local runs that share one provider/id correlation key. */ +interface PendingLocalRuns { + count: number + parentSessionId?: SessionId + parentAmbiguous: boolean +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session, agent, and subagent lifecycle events, forwarding durable session @@ -78,7 +85,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() - private readonly localRuns = new Map() + private readonly localRuns = new Map>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -112,10 +119,12 @@ export class HarnessSdkServer { this.disposers.push(ctx.on('agent/disposed', (agent) => { this.localAgents.delete(agent.id) })) - // Snapshot locality per run. A provider may settle one run, continue the - // same live child in another run, and dispose that child before the later - // result settles. Consuming an agent-lifetime marker at the first end would - // lose the later notification; this queue pairs each start with one end. + // Snapshot locality per provider/id run key. A provider may settle one run, + // continue the same live child in another run, and dispose that child before + // the later result settles. Counts preserve every completion without + // assuming settlement order. If id reuse produces disagreeing lineage, the + // optional parent is omitted until that pending group drains rather than + // attributed to the wrong completion. this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) @@ -125,21 +134,35 @@ export class HarnessSdkServer { ? {} : { parentSessionId: agent.session.header.parentSession }) if (localAgent === undefined) return - const runs = this.localRuns.get(info.id) ?? [] - runs.push(localAgent) - this.localRuns.set(info.id, runs) + const providerRuns = this.localRuns.get(info.provider) ?? new Map() + const pending = providerRuns.get(info.id) + if (pending === undefined) { + providerRuns.set(info.id, localAgent.parentSessionId === undefined + ? { count: 1, parentAmbiguous: false } + : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) + } else { + pending.count += 1 + if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true + } + this.localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const runs = this.localRuns.get(info.id) - const cachedLocalAgent = runs?.shift() - if (runs?.length === 0) this.localRuns.delete(info.id) + const providerRuns = this.localRuns.get(info.provider) + const pending = providerRuns?.get(info.id) + if (pending !== undefined) { + pending.count -= 1 + if (pending.count === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider // has neither a cached creation nor a live local agent and is ignored. - if (cachedLocalAgent === undefined && agent === undefined) return - const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession + if (pending === undefined && agent === undefined) return + const parentSessionId = pending === undefined + ? agent?.session.header.parentSession + : pending.parentAmbiguous ? undefined : pending.parentSessionId this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index d56f3000f6..48b8c4b1be 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -373,6 +373,100 @@ describe('HarnessSdkServer', () => { } }) + it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const oldParent = await ctx.agents.create({ + sessionId: SessionId('old-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const oldChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const first = Promise.withResolvers() + const sameLifetime = Promise.withResolvers() + const replacement = Promise.withResolvers() + const results = [first.promise, sameLifetime.promise, replacement.promise] + let starts = 0 + const disposeProvider = ctx.subagents.registerProvider({ + name: 'reused', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + const result = results[starts] + starts += 1 + if (result === undefined) throw new Error('unexpected fourth reused-id run') + return Promise.resolve({ id: SessionId('reused-child'), result, dispose: () => Promise.resolve() }) + }, + }) + + const firstRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + const sameLifetimeRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + sameLifetime.resolve({ output: [{ type: 'text', text: 'same lifetime' }], stopReason: 'completed' }) + await sameLifetimeRun.result + await oldChild.dispose() + const newParent = await ctx.agents.create({ + sessionId: SessionId('new-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const newChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const secondRun = await ctx.subagents.start('reused', { + parent: newParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + + replacement.resolve({ output: [{ type: 'text', text: 'new lifetime' }], stopReason: 'completed' }) + await secondRun.result + first.resolve({ output: [{ type: 'text', text: 'old lifetime' }], stopReason: 'completed' }) + await firstRun.result + await Promise.resolve() + + const finished = transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'reused-child', + ) + expect(finished.map(notification => notification.params?.lastAssistantMessage)).toEqual([ + [{ type: 'text', text: 'same lifetime' }], + [{ type: 'text', text: 'new lifetime' }], + [{ type: 'text', text: 'old lifetime' }], + ]) + expect(finished[0]?.params?.parentSessionId).toBe('old-parent') + expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + + await firstRun.dispose() + await sameLifetimeRun.dispose() + await secondRun.dispose() + disposeProvider() + await newChild.dispose() + await oldParent.dispose() + await newParent.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -395,13 +489,38 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) + const missedStartResult = Promise.withResolvers() + const disposeMissedStartProvider = ctx.subagents.registerProvider({ + name: 'fork', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: true, + start: () => Promise.resolve({ + id: SessionId('fallback-child-session'), + result: missedStartResult.promise, + dispose: () => Promise.resolve(), + }), + }) + // Start before the server subscribes, so the terminal fallback must use + // the still-live registry entry rather than a cached start record. + const missedStartRun = await ctx.subagents.start('fork', { + parent: parentHandle.agent, + prompt: [], + signal: new AbortController().signal, + }) const transport = new FakeTransport() const server = new HarnessSdkServer(ctx, transport) + missedStartResult.resolve({ output: [], stopReason: 'max-tokens' }) + await missedStartRun.result + await Promise.resolve() + await missedStartRun.dispose() + disposeMissedStartProvider() + // The server also missed this agent's creation, but observes the start; + // recover its lineage from the still-live registry entry. await settleSubagent(ctx, parentHandle.agent, { - provider: 'fork', + provider: 'fork-live-fallback', id: SessionId('fallback-child-session'), - stopReason: 'max-tokens', + stopReason: 'completed', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { From 45e3997efcecf48c57e171a7d77401b1c914ea32 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:41:31 +0800 Subject: [PATCH 043/323] fix: correlate subagent completion by parent scope --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 101 ++++++++--------------- packages/ui/jsonrpc/tests/server.spec.ts | 13 ++- 4 files changed, 47 insertions(+), 73 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 04aff464a9..bc1c0d38d0 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,8 +7,8 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:444`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 5ff7eb7f8e..ffbd7a1288 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index ce0ac9c75a..352563f7f2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -15,8 +15,10 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { AgentHandle } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentHandle } from '@deepseek-ai/dsh-agent' +import { carrierKeyOf, type Scoped } from '@deepseek-ai/dsh-scope' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' +import type SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -58,21 +60,14 @@ interface SessionRecord { activePrompt: boolean } -/** Runtime-local agent identity plus optional durable fork lineage. */ -interface LocalAgentRecord { - parentSessionId?: SessionId -} - -/** Pending local runs that share one provider/id correlation key. */ -interface PendingLocalRuns { - count: number - parentSessionId?: SessionId - parentAmbiguous: boolean +/** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ +function subagentParentOf(carrier: Scoped): Agent { + return carrierKeyOf(carrier) as Agent } /** * The SDK server over a booted harness context. Constructing it subscribes to - * session, agent, and subagent lifecycle events, forwarding durable session + * session and subagent lifecycle events, forwarding durable session * events and SDK-facing completion notifications while retaining local-run * identity across child disposal. The subscriptions live until * {@link shutdown}. One instance serves one transport peer for the process @@ -84,8 +79,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly localAgents = new Map() - private readonly localRuns = new Map>() + private readonly localRuns = new Map>>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -109,64 +103,40 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage for each agent lifetime. - // Parent lineage is not required by the provider contract, so an empty - // record remains a load-bearing locality marker. - this.disposers.push(ctx.on('agent/created', (agent) => { - const parentSessionId = agent.session.header.parentSession - this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) + // In-process providers publish the child before start. Count those starts by + // the exact delegating-parent carrier so later completions remain local after + // child disposal and reused ids need no settlement-order assumption. + const localRuns = this.localRuns + this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { + if (ctx.agents.get(info.id) === undefined) return + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) ?? new Map>() + const parentRuns = providerRuns.get(info.id) ?? new Map() + parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) + providerRuns.set(info.id, parentRuns) + localRuns.set(info.provider, providerRuns) })) - this.disposers.push(ctx.on('agent/disposed', (agent) => { - this.localAgents.delete(agent.id) - })) - // Snapshot locality per provider/id run key. A provider may settle one run, - // continue the same live child in another run, and dispose that child before - // the later result settles. Counts preserve every completion without - // assuming settlement order. If id reuse produces disagreeing lineage, the - // optional parent is omitted until that pending group drains rather than - // attributed to the wrong completion. - this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { - const agent = this.ctx.agents.get(info.id) - const cachedLocalAgent = this.localAgents.get(info.id) - const localAgent = cachedLocalAgent ?? (agent === undefined - ? undefined - : agent.session.header.parentSession === undefined - ? {} - : { parentSessionId: agent.session.header.parentSession }) - if (localAgent === undefined) return - const providerRuns = this.localRuns.get(info.provider) ?? new Map() - const pending = providerRuns.get(info.id) - if (pending === undefined) { - providerRuns.set(info.id, localAgent.parentSessionId === undefined - ? { count: 1, parentAmbiguous: false } - : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) - } else { - pending.count += 1 - if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true - } - this.localRuns.set(info.provider, providerRuns) - })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const agent = this.ctx.agents.get(info.id) - const providerRuns = this.localRuns.get(info.provider) - const pending = providerRuns?.get(info.id) - if (pending !== undefined) { - pending.count -= 1 - if (pending.count === 0) providerRuns?.delete(info.id) - if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { + const agent = ctx.agents.get(info.id) + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) + const parentRuns = providerRuns?.get(info.id) + const pendingCount = parentRuns?.get(parent) + if (pendingCount !== undefined) { + if (pendingCount === 1) parentRuns?.delete(parent) + else parentRuns?.set(parent, pendingCount - 1) + if (parentRuns?.size === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider - // has neither a cached creation nor a live local agent and is ignored. - if (pending === undefined && agent === undefined) return - const parentSessionId = pending === undefined - ? agent?.session.header.parentSession - : pending.parentAmbiguous ? undefined : pending.parentSessionId - this.transport.notify('subagent.finished', { + // has neither a pending local start nor a live local agent and is ignored. + if (pendingCount === undefined && agent === undefined) return + transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + parentSessionId: String(parent.session.id), childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, @@ -240,7 +210,6 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.localAgents.clear() this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 48b8c4b1be..427a190c36 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -316,6 +316,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'spawn', agentId: 'parentless-child-session', + parentSessionId: 'main', childSessionId: 'parentless-child-session', status: 'error', stopReason: 'error', @@ -373,7 +374,7 @@ describe('HarnessSdkServer', () => { } }) - it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + it('correlates reused local ids by parent scope when runs settle out of order', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) const ctx = await makeHarness(storageDir) try { @@ -450,8 +451,11 @@ describe('HarnessSdkServer', () => { [{ type: 'text', text: 'new lifetime' }], [{ type: 'text', text: 'old lifetime' }], ]) - expect(finished[0]?.params?.parentSessionId).toBe('old-parent') - expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + expect(finished.map(notification => notification.params?.parentSessionId)).toEqual([ + 'old-parent', + 'new-parent', + 'old-parent', + ]) await firstRun.dispose() await sameLifetimeRun.dispose() @@ -551,6 +555,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'fork', agentId: 'failed-child-session', + parentSessionId: 'fallback-parent', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', @@ -753,6 +758,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(6) + expect(on).toHaveBeenCalledTimes(4) }) }) From d33a819d15964fac1212f7b716f50106c8bb0ed1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:55:38 +0800 Subject: [PATCH 044/323] fix: share scope carrier across built JSON-RPC --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 + .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ++++++++++++++++++ pnpm-lock.yaml | 3 + scripts/run-gates.ts | 1 + 6 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 4dfbedb97b..1494d3fcf8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index 23cca651fe..a1a841296a 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index be19ab7217..bf4fe39118 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -38,6 +39,7 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts new file mode 100644 index 0000000000..159600e49c --- /dev/null +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -0,0 +1,121 @@ +/** + * Built-artifact guard for the scope carrier shared by `dsh-subagent` and + * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must + * externalize `dsh-scope`; source-mode tests cannot expose an accidentally + * inlined second registry. This test runs the real `lib/index.js` bundles in a + * plain Node subprocess, disposes the child before settlement, and requires the + * SDK completion notification to retain the delegating parent. + */ + +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) +const execFileAsync = promisify(execFile) + +const builtRuntimeProbe = String.raw` +import { mkdtemp, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import { join, resolve } from "node:path"; +import { pathToFileURL } from "node:url"; + +const load = (path) => import(pathToFileURL(resolve(path)).href); +const [ + { Context }, + agentCore, + { default: SubagentService }, + { default: SessionPersistenceJsonl }, + { HarnessSdkServer }, + { SessionId }, +] = await Promise.all([ + load("vendor/cordis/lib/index.js"), + load("packages/core/agent-core/lib/index.js"), + load("packages/subagent/subagent/lib/index.js"), + load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), + load("packages/ui/jsonrpc/lib/index.js"), + load("packages/core/session/lib/index.js"), +]); + +const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); +const ctx = new Context(); +try { + await ctx.plugin(agentCore); + await ctx.plugin(SubagentService); + await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); + await new Promise((ready) => setTimeout(ready, 50)); + + const notifications = []; + const server = new HarnessSdkServer(ctx, { + request() { return Promise.reject(new Error("unexpected host request")); }, + notify(method, params) { notifications.push({ method, params }); }, + }); + const parent = await ctx.agents.create({ + sessionId: SessionId("built-parent"), + meta: { cwd: storageRoot }, + agentOptions: { model: "test" }, + }); + const child = await ctx.agents.create({ + sessionId: SessionId("built-child"), + meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, + agentOptions: { model: "test" }, + }); + const result = Promise.withResolvers(); + const unregister = ctx.subagents.registerProvider({ + name: "built-local", + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + return Promise.resolve({ + id: child.agent.id, + result: result.promise, + dispose() { return Promise.resolve(); }, + }); + }, + }); + const run = await ctx.subagents.start("built-local", { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }); + await child.dispose(); + result.resolve({ output: [], stopReason: "completed" }); + await run.result; + await Promise.resolve(); + + console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); + await run.dispose(); + unregister(); + await parent.dispose(); + await server.shutdown(); +} finally { + await ctx.fiber.dispose(); + await rm(storageRoot, { recursive: true, force: true }); +} +` + +describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { + it('preserves parent-scoped completion after child disposal', async () => { + const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { + cwd: repoRoot, + timeout: 15_000, + }) + + expect(stderr).not.toContain('listener threw') + expect(JSON.parse(stdout) as unknown).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'built-local', + agentId: 'built-child', + parentSessionId: 'built-parent', + childSessionId: 'built-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [], + }, + }]) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..dec8c3024f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,6 +1288,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 131501abb0..e1c41149ca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,6 +332,7 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', + 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From 39c6c1120abdcc0414325bbdd1624917b0cb8624 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:56:21 +0800 Subject: [PATCH 045/323] Revert "fix: share scope carrier across built JSON-RPC" This reverts commit 835fd3ca4f46e0c6464098e3d0864dc56f31398d. --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 - .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ------------------ pnpm-lock.yaml | 3 - scripts/run-gates.ts | 1 - 6 files changed, 2 insertions(+), 129 deletions(-) delete mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 1494d3fcf8..4dfbedb97b 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index a1a841296a..23cca651fe 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index bf4fe39118..be19ab7217 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,7 +28,6 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", - "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -39,7 +38,6 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", - "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts deleted file mode 100644 index 159600e49c..0000000000 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ /dev/null @@ -1,121 +0,0 @@ -/** - * Built-artifact guard for the scope carrier shared by `dsh-subagent` and - * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must - * externalize `dsh-scope`; source-mode tests cannot expose an accidentally - * inlined second registry. This test runs the real `lib/index.js` bundles in a - * plain Node subprocess, disposes the child before settlement, and requires the - * SDK completion notification to retain the delegating parent. - */ - -import { execFile } from 'node:child_process' -import { existsSync } from 'node:fs' -import { fileURLToPath } from 'node:url' -import { promisify } from 'node:util' -import { describe, expect, it } from 'vitest' - -const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) -const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) -const execFileAsync = promisify(execFile) - -const builtRuntimeProbe = String.raw` -import { mkdtemp, rm } from "node:fs/promises"; -import { tmpdir } from "node:os"; -import { join, resolve } from "node:path"; -import { pathToFileURL } from "node:url"; - -const load = (path) => import(pathToFileURL(resolve(path)).href); -const [ - { Context }, - agentCore, - { default: SubagentService }, - { default: SessionPersistenceJsonl }, - { HarnessSdkServer }, - { SessionId }, -] = await Promise.all([ - load("vendor/cordis/lib/index.js"), - load("packages/core/agent-core/lib/index.js"), - load("packages/subagent/subagent/lib/index.js"), - load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), - load("packages/ui/jsonrpc/lib/index.js"), - load("packages/core/session/lib/index.js"), -]); - -const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); -const ctx = new Context(); -try { - await ctx.plugin(agentCore); - await ctx.plugin(SubagentService); - await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); - await new Promise((ready) => setTimeout(ready, 50)); - - const notifications = []; - const server = new HarnessSdkServer(ctx, { - request() { return Promise.reject(new Error("unexpected host request")); }, - notify(method, params) { notifications.push({ method, params }); }, - }); - const parent = await ctx.agents.create({ - sessionId: SessionId("built-parent"), - meta: { cwd: storageRoot }, - agentOptions: { model: "test" }, - }); - const child = await ctx.agents.create({ - sessionId: SessionId("built-child"), - meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, - agentOptions: { model: "test" }, - }); - const result = Promise.withResolvers(); - const unregister = ctx.subagents.registerProvider({ - name: "built-local", - capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, - inheritsParentContext: false, - start() { - return Promise.resolve({ - id: child.agent.id, - result: result.promise, - dispose() { return Promise.resolve(); }, - }); - }, - }); - const run = await ctx.subagents.start("built-local", { - parent: parent.agent, - prompt: [], - signal: new AbortController().signal, - }); - await child.dispose(); - result.resolve({ output: [], stopReason: "completed" }); - await run.result; - await Promise.resolve(); - - console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); - await run.dispose(); - unregister(); - await parent.dispose(); - await server.shutdown(); -} finally { - await ctx.fiber.dispose(); - await rm(storageRoot, { recursive: true, force: true }); -} -` - -describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { - it('preserves parent-scoped completion after child disposal', async () => { - const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { - cwd: repoRoot, - timeout: 15_000, - }) - - expect(stderr).not.toContain('listener threw') - expect(JSON.parse(stdout) as unknown).toEqual([{ - method: 'subagent.finished', - params: { - provider: 'built-local', - agentId: 'built-child', - parentSessionId: 'built-parent', - childSessionId: 'built-child', - status: 'ok', - stopReason: 'completed', - lastAssistantMessage: [], - }, - }]) - }) -}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index dec8c3024f..6214564eae 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,9 +1288,6 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek - '@deepseek-ai/dsh-scope': - specifier: workspace:^ - version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index e1c41149ca..131501abb0 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,7 +332,6 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', - 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From c6cb9f4210d9303c197ac985fca7a4dc3b11cb88 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:55:38 +0800 Subject: [PATCH 046/323] fix: share scope carrier across built JSON-RPC --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 + .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ++++++++++++++++++ pnpm-lock.yaml | 3 + scripts/run-gates.ts | 1 + 6 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 4dfbedb97b..1494d3fcf8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index 23cca651fe..a1a841296a 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index be19ab7217..bf4fe39118 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -38,6 +39,7 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts new file mode 100644 index 0000000000..159600e49c --- /dev/null +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -0,0 +1,121 @@ +/** + * Built-artifact guard for the scope carrier shared by `dsh-subagent` and + * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must + * externalize `dsh-scope`; source-mode tests cannot expose an accidentally + * inlined second registry. This test runs the real `lib/index.js` bundles in a + * plain Node subprocess, disposes the child before settlement, and requires the + * SDK completion notification to retain the delegating parent. + */ + +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) +const execFileAsync = promisify(execFile) + +const builtRuntimeProbe = String.raw` +import { mkdtemp, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import { join, resolve } from "node:path"; +import { pathToFileURL } from "node:url"; + +const load = (path) => import(pathToFileURL(resolve(path)).href); +const [ + { Context }, + agentCore, + { default: SubagentService }, + { default: SessionPersistenceJsonl }, + { HarnessSdkServer }, + { SessionId }, +] = await Promise.all([ + load("vendor/cordis/lib/index.js"), + load("packages/core/agent-core/lib/index.js"), + load("packages/subagent/subagent/lib/index.js"), + load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), + load("packages/ui/jsonrpc/lib/index.js"), + load("packages/core/session/lib/index.js"), +]); + +const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); +const ctx = new Context(); +try { + await ctx.plugin(agentCore); + await ctx.plugin(SubagentService); + await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); + await new Promise((ready) => setTimeout(ready, 50)); + + const notifications = []; + const server = new HarnessSdkServer(ctx, { + request() { return Promise.reject(new Error("unexpected host request")); }, + notify(method, params) { notifications.push({ method, params }); }, + }); + const parent = await ctx.agents.create({ + sessionId: SessionId("built-parent"), + meta: { cwd: storageRoot }, + agentOptions: { model: "test" }, + }); + const child = await ctx.agents.create({ + sessionId: SessionId("built-child"), + meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, + agentOptions: { model: "test" }, + }); + const result = Promise.withResolvers(); + const unregister = ctx.subagents.registerProvider({ + name: "built-local", + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + return Promise.resolve({ + id: child.agent.id, + result: result.promise, + dispose() { return Promise.resolve(); }, + }); + }, + }); + const run = await ctx.subagents.start("built-local", { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }); + await child.dispose(); + result.resolve({ output: [], stopReason: "completed" }); + await run.result; + await Promise.resolve(); + + console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); + await run.dispose(); + unregister(); + await parent.dispose(); + await server.shutdown(); +} finally { + await ctx.fiber.dispose(); + await rm(storageRoot, { recursive: true, force: true }); +} +` + +describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { + it('preserves parent-scoped completion after child disposal', async () => { + const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { + cwd: repoRoot, + timeout: 15_000, + }) + + expect(stderr).not.toContain('listener threw') + expect(JSON.parse(stdout) as unknown).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'built-local', + agentId: 'built-child', + parentSessionId: 'built-parent', + childSessionId: 'built-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [], + }, + }]) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..dec8c3024f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,6 +1288,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 131501abb0..e1c41149ca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,6 +332,7 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', + 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From 151d6387e03b9f41b553e7f079588f76d7317516 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:57:46 +0800 Subject: [PATCH 047/323] docs: refresh module dependency graph --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..864f39359f 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -293,6 +293,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_workflow_workerthread --> pkg_agent @@ -389,7 +390,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | From 82c0d1fb7cc291196bc3fd5733dfec867d84dac7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:59:33 +0800 Subject: [PATCH 048/323] test: register JSON-RPC artifact smoke --- knip.json | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/knip.json b/knip.json index 825980f205..fe2366e3fa 100644 --- a/knip.json +++ b/knip.json @@ -77,13 +77,17 @@ "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, - "packages/ui/stdio-agent": { + "packages/ui/jsonrpc": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/ui/jsonrpc-agent": { "project": ["src/**/*.ts"] }, + "packages/ui/stdio-agent": { + "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"] + }, "packages/subagent/subagent-spawn": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] From e784e4dce5f5178b5e22a3d3376599144d8bea1b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:12:32 +0800 Subject: [PATCH 049/323] fix: await ACP client callbacks during shutdown --- packages/support/acp-snapshot/src/launcher.ts | 59 ++++++++++++------- .../acp-snapshot/tests/harness.spec.ts | 36 +++++++++++ 2 files changed, 75 insertions(+), 20 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 815753ae5f..30702a5888 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, and ACP parser drain. */ + /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, ACP parsing, and client callbacks. */ close(signal?: NodeJS.Signals): Promise } @@ -137,29 +137,41 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe Writable.toWeb(child.stdin) as WritableStream, Readable.toWeb(passthrough) as ReadableStream, ) + const inFlightClientCallbacks = new Set>() + const trackClientCallback = (callback: () => T | PromiseLike): Promise => { + const pending = Promise.resolve().then(callback) + inFlightClientCallbacks.add(pending) + void pending.then( + () => { inFlightClientCallbacks.delete(pending) }, + () => { inFlightClientCallbacks.delete(pending) }, + ) + return pending + } + const requestPermission = options.requestPermission + ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' as const } })) const makeClient = (_agent: AcpAgent): Client => ({ sessionUpdate(params: SessionNotification): Promise { - updates.push(params.update) - for (let index = updateWaiters.length - 1; index >= 0; index--) { - const waiter = updateWaiters[index] - /* v8 ignore next 1 -- index is bounded by the array length */ - if (waiter === undefined) continue - let matches: boolean - try { - matches = waiter.match(params.update) - } catch (error: unknown) { + return trackClientCallback(() => { + updates.push(params.update) + for (let index = updateWaiters.length - 1; index >= 0; index--) { + const waiter = updateWaiters[index] + /* v8 ignore next 1 -- index is bounded by the array length */ + if (waiter === undefined) continue + let matches: boolean + try { + matches = waiter.match(params.update) + } catch (error: unknown) { + updateWaiters.splice(index, 1) + waiter.reject(error) + continue + } + if (!matches) continue updateWaiters.splice(index, 1) - waiter.reject(error) - continue + waiter.resolve(params.update) } - if (!matches) continue - updateWaiters.splice(index, 1) - waiter.resolve(params.update) - } - return Promise.resolve() + }) }, - requestPermission: options.requestPermission - ?? (() => Promise.resolve({ outcome: { outcome: 'cancelled' } })), + requestPermission: params => trackClientCallback(() => requestPermission(params)), }) const client = new ClientSideConnection(makeClient, stream) // `exit` only reports the parent process's status. Descendants may retain @@ -168,7 +180,14 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.all([stdioClosed, client.closed]).then(() => undefined) + const drained = Promise.all([stdioClosed, client.closed]).then(async () => { + // The ACP SDK's readable loop dispatches client callbacks without awaiting + // them. Once `closed` settles no new callbacks can start, but callbacks + // already in flight still belong to this launch's teardown boundary. + while (inFlightClientCallbacks.size > 0) { + await Promise.allSettled([...inFlightClientCallbacks]) + } + }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the // parser has dispatched every buffered frame. diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 051db6a0ba..902f48d2cf 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -1,4 +1,5 @@ import { mkdtemp, rm, writeFile } from 'node:fs/promises' +import { once } from 'node:events' import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -112,6 +113,41 @@ describe('runScenario', () => { expect(launched.stderr()).toContain('late inherited stderr') }) + it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => { + const { dir, fixtureFile } = await scenario({ permissionProbe: true }) + let releasePermission: (() => void) | undefined + const permissionReleased = new Promise((resolve) => { releasePermission = resolve }) + let markPermissionStarted: (() => void) | undefined + const permissionStarted = new Promise((resolve) => { markPermissionStarted = resolve }) + let permissionFinished = false + const launched = launchAcpTestAgent({ + agent: AGENT, + cwd: dir, + env: { DSH_SNAPSHOT_FILE: fixtureFile }, + async requestPermission() { + markPermissionStarted?.() + await permissionReleased + permissionFinished = true + return { outcome: { outcome: 'cancelled' } } + }, + }) + await launched.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await launched.client.newSession({ cwd: dir, mcpServers: [] }) + void launched.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }).catch(() => undefined) + await permissionStarted + + const childClosed = once(launched.child, 'close') + let closeSettled = false + const closing = launched.close('SIGKILL').then(() => { closeSettled = true }) + await childClosed + await launched.client.closed + expect(closeSettled).toBe(false) + + releasePermission?.() + await closing + expect(permissionFinished).toBe(true) + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From d4c96deac3802164c430335309f936f3e5ab4f1d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:19:02 +0800 Subject: [PATCH 050/323] refactor: share ACP callback cleanup --- packages/support/acp-snapshot/src/launcher.ts | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 30702a5888..f1271986c0 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -141,10 +141,8 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe const trackClientCallback = (callback: () => T | PromiseLike): Promise => { const pending = Promise.resolve().then(callback) inFlightClientCallbacks.add(pending) - void pending.then( - () => { inFlightClientCallbacks.delete(pending) }, - () => { inFlightClientCallbacks.delete(pending) }, - ) + const untrack = (): void => { inFlightClientCallbacks.delete(pending) } + void pending.then(untrack, untrack) return pending } const requestPermission = options.requestPermission From 2dea4afac0d49976700139a766d40734e3204f4e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:23:02 +0800 Subject: [PATCH 051/323] fix: bind stdio to its configured agent --- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 5 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 30 +++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 35 ++++++++++++++----- 4 files changed, 53 insertions(+), 19 deletions(-) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 82da64cd81..d7d30ee49d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id. Resumed sessions register under the exact `resumeSessionId` and keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index f01c48a615..2eca0cceb3 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -124,5 +124,8 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.' }) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index a295274786..76347c91e4 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,10 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string + /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ + resumeSessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), + resumeSessionId: z.string(), }) /** @@ -95,16 +98,25 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // This app owns one configured top-level agent. Hold the live object - // directly: its per-run id is intentionally fresh, while `main` remains only - // the terminal's fixed display label. Runtime creator ownership distinguishes - // that root from its subagents even if a child is registered after an HMR - // replacement. Persisted parentSession lineage is deliberately irrelevant: - // a resumed child session can itself be this process's configured root. - let target: Agent | undefined = ctx.agents.roots()[0] - ctx.on('agent/created', () => { target ??= ctx.agents.roots()[0] }) + // Bind only to this app's configured top-level agent. Fresh runs own the + // `main-session-*` namespace; resumed runs own the exact persisted id. The + // registry's runtime-root relation excludes subagents without confusing it + // with durable parentSession lineage. Keeping the matching candidates also + // covers HMR's publish-new-before-dispose-old ordering without ever falling + // through to an unrelated root owned by another app or test fixture. + const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + ? agent.id.startsWith('main-session-') + : agent.id === config.resumeSessionId + const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) + let target: Agent | undefined = [...configuredRoots].at(-1) + ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return + configuredRoots.add(agent) + target ??= agent + }) ctx.on('agent/disposed', (agent) => { - if (target === agent) target = ctx.agents.roots().at(-1) + configuredRoots.delete(agent) + if (target === agent) target = [...configuredRoots].at(-1) }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2600fdb24f..668068a72d 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there' } +const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,9 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup() + const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) @@ -207,6 +209,7 @@ describe('createStdioChat rendering', () => { input.feed('continue') await new Promise(resolve => setImmediate(resolve)) + expect(unrelated.sent).toEqual([]) expect(resumed.sent).toEqual([[{ type: 'text', text: 'continue' }]]) }) @@ -235,7 +238,7 @@ describe('createStdioChat rendering', () => { it('keeps the target when a different agent is disposed', async () => { const { ctx, out } = await setup() - const target = makeAgent('target') + const target = makeAgent('main') ctx.agents.register(target) ctx.emit('agent/disposed', makeAgent('other')) ctx.emit('session/event', target.session, { @@ -245,11 +248,11 @@ describe('createStdioChat rendering', () => { }) it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup() - const oldRoot = makeAgent('old-root') + const { ctx, input } = await setup({ welcome: 'hi there' }) + const oldRoot = makeAgent('main-session-old') const child = makeAgent('child') ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('replacement') + const replacement = makeAgent('main-session-replacement') const lateChild = makeAgent('late-child') const disposeOld = ctx.agents.register(oldRoot) const disposeChild = ctx.agents.enter(child, oldRoot) @@ -273,6 +276,22 @@ describe('createStdioChat rendering', () => { disposeChild() }) + it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { + const { ctx, input } = await setup() + const unrelated = makeAgent('unrelated') + ctx.agents.register(unrelated) + const configured = makeAgent('main') + const disposeConfigured = ctx.agents.register(configured) + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + + disposeConfigured() + input.feed('must not leak') + await new Promise(resolve => setImmediate(resolve)) + + expect(unrelated.sent).toEqual([]) + expect(error).toHaveBeenCalledWith('ui-stdio: main agent is not running') + }) + it('renders tool/call and tool/result session events', async () => { const { ctx, out } = await setup() const session = {} as Session @@ -720,8 +739,8 @@ describe('createStdioChat input', () => { expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') }) - it('drives the app-owned agent without a duplicate id config', async () => { - const { ctx, input } = await setup({ welcome: 'w' }) + it('drives the exact app-configured resumed session', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') From 1bb9995128f75474eeec9933e2bab6fc69a8b60e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:28:41 +0800 Subject: [PATCH 052/323] docs: state subagent carrier invariant --- packages/ui/jsonrpc/src/server.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 352563f7f2..fe605a8536 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -62,6 +62,7 @@ interface SessionRecord { /** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ function subagentParentOf(carrier: Scoped): Agent { + // SubagentService emits this lifecycle pair only through scopeTarget(this, parent). return carrierKeyOf(carrier) as Agent } From ba8a5c89ed4390b4b1679b736f2c44d79bdbaab9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:29:02 +0800 Subject: [PATCH 053/323] docs: name the public agent injection seam --- packages/bash/tool-bash/src/index.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index fe07b80989..cda683c5b4 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -457,7 +457,7 @@ export function apply(ctx: Context): void { ) } catch (error: unknown) { // The ONE expected failure: the agent was disposed between task - // completion and this injection (ReactLoopAgent.inject throws + // completion and this injection (Agent.inject throws // `agent "" is disposed`). That race is benign — drop the notice. // Anything else is a real bug and must surface, not be swallowed. if (error instanceof Error && error.message.includes('is disposed')) return From ccd810f84d74ce452d858b553eb0cbdb282d715c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:36:22 +0800 Subject: [PATCH 054/323] fix: normalize empty stdio resume identity --- packages/ui/stdio-agent/src/stdio-chat.ts | 5 +++-- packages/ui/stdio-agent/tests/stdio-chat.spec.ts | 9 +++++++++ 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 76347c91e4..17a11168db 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -104,9 +104,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt // with durable parentSession lineage. Keeping the matching candidates also // covers HMR's publish-new-before-dispose-old ordering without ever falling // through to an unrelated root owned by another app or test fixture. - const matchesConfiguredIdentity = (agent: Agent): boolean => config.resumeSessionId === undefined + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined ? agent.id.startsWith('main-session-') - : agent.id === config.resumeSessionId + : agent.id === resumeSessionId const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) let target: Agent | undefined = [...configuredRoots].at(-1) ctx.on('agent/created', (agent) => { diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 668068a72d..2ebc51e14e 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -747,6 +747,15 @@ describe('createStdioChat input', () => { await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) }) + + it('treats an empty resume session id as a fresh configured identity', async () => { + const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) + const agent = makeAgent('main-session-fresh') + ctx.agents.register(agent) + input.feed('hi') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toHaveLength(1) + }) }) describe('createStdioChat EOF exit', () => { From 6b59b6050e379de30bb8f53bbc38172f8ffe896a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:43:12 +0800 Subject: [PATCH 055/323] fix: preserve ACP scenario cleanup failures --- packages/support/acp-snapshot/src/harness.ts | 20 +++++++--- .../acp-snapshot/tests/harness.spec.ts | 38 ++++++++++++++++++- 2 files changed, 51 insertions(+), 7 deletions(-) diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index 3db1355b0f..22b22deacd 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -244,9 +244,9 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise ) // Failure-safe teardown: wait for a still-running child, then attempt BOTH - // directory removals even when an earlier cleanup rejects. The main outcome - // wins over teardown noise so a step/harvest failure is never replaced; on a - // successful run, the first cleanup failure remains visible to the caller. + // directory removals even when an earlier cleanup rejects. Report every + // teardown failure alongside a scenario failure so neither orthogonal + // outcome hides the other. const cleanupResults: PromiseSettledResult[] = [] const cleanup = async (action: () => Promise): Promise => { cleanupResults.push(...await Promise.allSettled([action()])) @@ -256,10 +256,18 @@ export async function runScenario(input: InputScript, opts: RunOptions): Promise await cleanup(() => rm(cwd, { recursive: true, force: true })) await cleanup(() => rm(sessionsRoot, { recursive: true, force: true })) + const cleanupFailures = cleanupResults + .filter((result): result is PromiseRejectedResult => result.status === 'rejected') + .map(result => result.reason as unknown) + if (cleanupFailures.length > 0) { + throw new AggregateError( + outcome.status === 'rejected' ? [outcome.error, ...cleanupFailures] : cleanupFailures, + outcome.status === 'rejected' + ? 'snapshot scenario and cleanup failed' + : 'snapshot cleanup failed', + ) + } if (outcome.status === 'rejected') throw outcome.error - const cleanupFailure = cleanupResults.find((result): result is PromiseRejectedResult => result.status === 'rejected') - /* v8 ignore next 1 -- defensive OS cleanup failure after an otherwise successful real subprocess run */ - if (cleanupFailure !== undefined) throw cleanupFailure.reason return outcome.value } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 902f48d2cf..de764cfd8a 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -3,11 +3,29 @@ import { once } from 'node:events' import { tmpdir } from 'node:os' import { delimiter, join } from 'node:path' import { fileURLToPath } from 'node:url' -import { afterAll, describe, expect, it } from 'vitest' +import { afterAll, describe, expect, it, vi } from 'vitest' import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk' import { runScenario, type AgentUnderTest, type InputStep } from '../src/harness.ts' import { launchAcpTestAgent } from '../src/launcher.ts' +const fsControl = vi.hoisted(() => ({ cleanupFailure: undefined as Error | undefined })) + +vi.mock('node:fs/promises', async (importOriginal) => { + const actual = await importOriginal() + return { + ...actual, + async rm(...args: Parameters): Promise { + if (String(args[0]).includes('acp-snap-cwd-') && fsControl.cleanupFailure !== undefined) { + const failure = fsControl.cleanupFailure + fsControl.cleanupFailure = undefined + await actual.rm(...args) + throw failure + } + await actual.rm(...args) + }, + } +}) + /** * Unit tests for the subprocess harness, driven through the REAL spawn path * (tsx loader, temp cwd, env plumbing) against the scripted fake ACP bin in @@ -238,6 +256,24 @@ describe('runScenario', () => { )).rejects.toThrow(/expected the prompt to fail/) }) + it('reports scenario and cleanup failures together', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({ prompt: 'respond' }) + const cleanupFailure = new Error('cleanup failed') + fsControl.cleanupFailure = cleanupFailure + + const failure = await runScenario( + { steps: [...boot, { op: 'promptExpectError', text: 'fine' }] }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ).catch((error: unknown): unknown => error) + + expect(failure).toBeInstanceOf(AggregateError) + const failures = (failure as AggregateError).errors as unknown[] + expect(failures).toHaveLength(2) + expect(failures[0]).toBeInstanceOf(Error) + expect((failures[0] as Error).message).toMatch(/expected the prompt to fail/) + expect(failures[1]).toBe(cleanupFailure) + }) + it('newSessionExpectError swallows the rejection, with and without extra dirs', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ rejectExtraDirs: true }) const result = await runScenario( From 2333ab19e3b03bc84cf050b16e897b830b2dfdf2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:46:05 +0800 Subject: [PATCH 056/323] fix: verify JSON-RPC child ownership --- docs/cordis-catalog/services.md | 1 + packages/core/agent/README.md | 1 + packages/core/agent/src/index.ts | 12 ++++++ packages/core/agent/tests/agent.spec.ts | 4 ++ packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 11 +++-- packages/ui/jsonrpc/tests/server.spec.ts | 51 ++++++++++++++++++++---- 7 files changed, 68 insertions(+), 14 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6a40f88a23 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -33,6 +33,7 @@ register(agent: Agent): () => void enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined +isOwnedBy(id: SessionId, owner: Agent): boolean list(): Agent[] roots(): Agent[] ``` diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index a45603f191..941f46baf0 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -13,6 +13,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` +- `ctx.agents.isOwnedBy(id: SessionId, owner: Agent): boolean` — whether the exact live entry was created through that parent agent's scoped context; runtime ownership is independent of durable session lineage. - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index abafa38e45..8a9ed68ab6 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -440,6 +440,18 @@ export class AgentRegistry extends Service { return this.store.get(id)?.agent } + /** + * Test whether a live agent was created through one exact parent agent's + * scoped context. Runtime ownership is independent of durable session + * lineage and remains unambiguous when unrelated providers reuse an id. + * @param id - the candidate child agent's shared agent/session id. + * @param owner - the expected runtime creator agent. + * @returns true only while the exact child entry is live under that owner. + */ + isOwnedBy(id: SessionId, owner: Agent): boolean { + return this.store.get(id)?.owner === owner + } + /** * All live agents, in registration order. * @returns a fresh array; mutating it does not affect the registry. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index d2866cacb3..5d79d1a91f 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -72,8 +72,12 @@ describe('AgentRegistry', () => { expect(ctx.agents.list()).toEqual([root, child]) expect(ctx.agents.roots()).toEqual([root]) + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(true) + expect(ctx.agents.isOwnedBy(root.id, root)).toBe(false) + expect(ctx.agents.isOwnedBy(SessionId('missing'), root)).toBe(false) detachChild() + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(false) detachRoot() }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index ffbd7a1288..df612ac263 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index fe605a8536..d78f24b5ab 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -109,8 +109,8 @@ export class HarnessSdkServer { // child disposal and reused ids need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { - if (ctx.agents.get(info.id) === undefined) return const parent = subagentParentOf(this) + if (!ctx.agents.isOwnedBy(info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -118,7 +118,6 @@ export class HarnessSdkServer { localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { - const agent = ctx.agents.get(info.id) const parent = subagentParentOf(this) const providerRuns = localRuns.get(info.provider) const parentRuns = providerRuns?.get(info.id) @@ -130,10 +129,10 @@ export class HarnessSdkServer { if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child - // has the session/created-driven start notification above; a parentless - // local provider still gets its terminal notification. A remote provider - // has neither a pending local start nor a live local agent and is ignored. - if (pendingCount === undefined && agent === undefined) return + // has the session/created-driven start notification above. A remote run + // has neither a cached owned start nor a live child owned by this exact + // parent; an unrelated local agent with the same id never makes it local. + if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 427a190c36..c97bd1a6e1 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,12 +277,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await ctx.agents.create({ + const handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) - const parentlessHandle = await ctx.agents.create({ + const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -331,6 +331,43 @@ describe('HarnessSdkServer', () => { } }) + it('ignores a remote run id that collides with an unrelated local agent', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-remote-collision-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('collision-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const unrelatedHandle = await ctx.agents.create({ + sessionId: SessionId('remote-run-id'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'remote', + id: SessionId('remote-run-id'), + stopReason: 'completed', + lastAssistantMessage: [], + }, () => unrelatedHandle.dispose()) + + expect(transport.notifications.some(notification => + notification.method === 'subagent.finished' + && notification.params?.agentId === 'remote-run-id', + )).toBe(false) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('retains locality across continuation runs on one live child', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) const ctx = await makeHarness(storageDir) @@ -342,7 +379,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const childHandle = await ctx.agents.create({ + const childHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('continuation-child'), meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, agentOptions: { model: 'deepseek' }, @@ -385,7 +422,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const oldChild = await ctx.agents.create({ + const oldChild = await oldParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, agentOptions: { model: 'deepseek' }, @@ -425,7 +462,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const newChild = await ctx.agents.create({ + const newChild = await newParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, agentOptions: { model: 'deepseek' }, @@ -483,12 +520,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - handle = await ctx.agents.create({ + handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) - failedHandle = await ctx.agents.create({ + failedHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, From 6b782b018927139ea07e5907488b0b948d90c813 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:54:34 +0800 Subject: [PATCH 057/323] fix: bind stdio to its exact fresh identity --- docs/config-catalog.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/core/agent-loop/README.md | 5 ++- packages/core/agent-loop/src/index.ts | 11 +++-- .../tests/config-session-id.spec.ts | 30 +++++++++++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/index.ts | 7 ++- packages/ui/stdio-agent/src/stdio-chat.ts | 32 +++++--------- .../ui/stdio-agent/tests/stdio-agent.spec.ts | 13 ++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 44 +++++-------------- 10 files changed, 88 insertions(+), 62 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..66791edb0a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,6 +119,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -645,7 +647,7 @@ export interface Config { Depends on: [`agentCore`](../packages/core/agent-core/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/ui/stdio-agent/src/index.ts:64`](../packages/ui/stdio-agent/src/index.ts) +Source: [`packages/ui/stdio-agent/src/index.ts:65`](../packages/ui/stdio-agent/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 032eae4f7d..404ba83636 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -16,7 +16,7 @@ Session itself repeated the same fact as `Session.id` and `Session.header.id`. C An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f40577bb95..246c9cdc27 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and mints `${label}-session-` before calling this boundary; `resumeSessionId` instead loads and registers the exact persisted id. This keeps fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,6 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids + sessionId?: string // optional exact identity for a fresh session model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -40,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index dbe503ff6a..0041b984d1 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,6 +326,8 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string + /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string /** Persisted session to resume instead of creating a fresh session. */ @@ -341,6 +343,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), + sessionId: z.string(), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), @@ -360,12 +363,14 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('model', context => context.agent?.options.model) ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) - for (const { id, cwd, resumeSessionId, ...options } of config.agents) { + for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { if (resumeSessionId === undefined || resumeSessionId === '') { - const sessionId = SessionId(`${id}-session-${randomUUID()}`) - this.create(sessionId, options, cwd === undefined ? {} : { cwd }) + this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) continue } + if (sessionId !== undefined) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 134ea68c32..543335e5fd 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -24,7 +24,37 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { }) } +async function makeCoreContext(): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + return ctx +} + describe('config-driven session id', () => { + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { + const exact = await makeCoreContext() + await exact.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact'), model: 'mock' }], + }) + expect(exact.agents.get(SessionId('stdio-exact'))?.session.id).toBe('stdio-exact') + await exact.fiber.dispose() + + const conflicting = await makeCoreContext() + await expect(conflicting.plugin(AgentLoop, { + agents: [{ + id: 'main', + sessionId: SessionId('fresh'), + resumeSessionId: SessionId('persisted'), + model: 'mock', + }], + })).rejects.toThrow('sessionId and resumeSessionId are mutually exclusive') + await conflicting.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index d7d30ee49d..b509e46781 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The UI's `main` text is a display label, not a second routing id; the UI binds to that fresh-id namespace, or to the exact `resumeSessionId` for a resumed run, and never selects unrelated registry roots. Resumed sessions keep the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 2eca0cceb3..03f3d49555 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -39,6 +39,7 @@ */ import type { Context } from 'cordis' +import { randomUUID } from 'node:crypto' import ConsoleExporter from '@cordisjs/plugin-logger-console' import z from 'schemastery' import { SessionId } from '@deepseek-ai/dsh-session' @@ -108,6 +109,8 @@ export const Config: z = z.object({ * a leaf concern (see the module doc), so it is not mounted here. */ export function apply(ctx: Context, config: Config): void { + const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId + const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, @@ -117,7 +120,7 @@ export function apply(ctx: Context, config: Config): void { id: 'main', model: config.model, cwd: process.cwd(), - ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, + ...resumeSessionId === undefined ? { sessionId } : { resumeSessionId: sessionId }, }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) @@ -126,6 +129,6 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(toolAskUser) ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', - ...config.resumeSessionId !== undefined ? { resumeSessionId: config.resumeSessionId } : {}, + sessionId, }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17a11168db..93c8f9b4f1 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -36,13 +36,13 @@ export const inject = ['agents', 'userInteraction'] export interface Config { /** Banner printed once on start, before the first `> ` prompt. */ welcome?: string - /** Exact persisted session id the app configured for resume; absent selects the app's fresh `main-session-*` identity. */ - resumeSessionId?: string + /** Exact shared agent/session identity this app instance created or resumed. */ + sessionId?: string } export const Config: z = z.object({ welcome: z.string().default('ready.'), - resumeSessionId: z.string(), + sessionId: z.string(), }) /** @@ -98,26 +98,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const welcome = config.welcome ?? 'ready.' const { input, output, exit } = runtime - // Bind only to this app's configured top-level agent. Fresh runs own the - // `main-session-*` namespace; resumed runs own the exact persisted id. The - // registry's runtime-root relation excludes subagents without confusing it - // with durable parentSession lineage. Keeping the matching candidates also - // covers HMR's publish-new-before-dispose-old ordering without ever falling - // through to an unrelated root owned by another app or test fixture. - const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId - const matchesConfiguredIdentity = (agent: Agent): boolean => resumeSessionId === undefined - ? agent.id.startsWith('main-session-') - : agent.id === resumeSessionId - const configuredRoots = new Set(ctx.agents.roots().filter(matchesConfiguredIdentity)) - let target: Agent | undefined = [...configuredRoots].at(-1) + // Bind only to the exact identity this app passed to its config-created + // agent. Session ids are opaque: neither a prefix nor registry order can + // identify ownership. The root check rejects a child that somehow preempts + // the configured id; later recreation under the same id supports loop HMR. + const matchesConfiguredIdentity = (agent: Agent): boolean => + agent.id === config.sessionId && ctx.agents.roots().includes(agent) + let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) ctx.on('agent/created', (agent) => { - if (!matchesConfiguredIdentity(agent) || !ctx.agents.roots().includes(agent)) return - configuredRoots.add(agent) - target ??= agent + if (matchesConfiguredIdentity(agent)) target = agent }) ctx.on('agent/disposed', (agent) => { - configuredRoots.delete(agent) - if (target === agent) target = [...configuredRoots].at(-1) + if (target === agent) target = undefined }) // Transcript rendering off the durable `session/event` feed — the assistant diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 5c5c0d2667..9a7bf10bad 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -93,6 +93,19 @@ describe('dsh-stdio-agent app', () => { await ctx.fiber.dispose() }) + it('normalizes an empty resume id to a fresh exact app identity', async () => { + const ctx = await mount({ + model: 'mock', + resumeSessionId: '', + persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', + skills: await isolatedSkillsConfig(), + }) + const agent = ctx.get('agents')?.list()[0] + expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) + expect(agent?.id).toBe(agent?.session.id) + await ctx.fiber.dispose() + }) + it('defaults persistenceRoot and welcome when omitted', async () => { // Direct apply (NOT via ctx.plugin, which validates+defaults the config // first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 2ebc51e14e..f1ca914525 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -74,7 +74,7 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { return { type: 'assistant/chunk', seq: 0, time: 0, data: { turn: 1, step: 0, chunk } } } -const CONFIG: Config = { welcome: 'hi there', resumeSessionId: 'main' } +const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() @@ -199,7 +199,7 @@ describe('createStdioChat rendering', () => { }) it('accepts a lineage-bearing configured agent created after the UI installs', async () => { - const { ctx, input } = await setup({ welcome: 'hi there', resumeSessionId: 'resumed' }) + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const resumed = makeAgent('resumed') @@ -247,33 +247,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 1] ') }) - it('retargets a surviving root when HMR publishes it before disposing the old root', async () => { - const { ctx, input } = await setup({ welcome: 'hi there' }) - const oldRoot = makeAgent('main-session-old') - const child = makeAgent('child') - ;(child.session.header as { parentSession?: string }).parentSession = oldRoot.id - const replacement = makeAgent('main-session-replacement') - const lateChild = makeAgent('late-child') + it('retargets only the exact identity after loop HMR recreation', async () => { + const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'main-session-fixed' }) + const oldRoot = makeAgent('main-session-fixed') + const prefixCollision = makeAgent('main-session-unrelated') const disposeOld = ctx.agents.register(oldRoot) - const disposeChild = ctx.agents.enter(child, oldRoot) - ctx.agents.announce(child) - ctx.agents.register(replacement) - const disposeLateChild = ctx.agents.enter(lateChild, replacement) - ctx.agents.announce(lateChild) - - // The replacement's created edge arrived while oldRoot was still targeted. - // A replacement-owned child then arrived even later. Once oldRoot is - // removed, runtime ownership still identifies replacement as the only - // surviving root instead of selecting either newer child by insertion order. + ctx.agents.register(prefixCollision) disposeOld() + const replacement = makeAgent('main-session-fixed') + ctx.agents.register(replacement) + input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) - expect(child.sent).toEqual([]) - expect(lateChild.sent).toEqual([]) + expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) - disposeLateChild() - disposeChild() }) it('does not retarget stdin to an unrelated root after the configured agent is disposed', async () => { @@ -740,7 +728,7 @@ describe('createStdioChat input', () => { }) it('drives the exact app-configured resumed session', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: 'worker' }) + const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') ctx.agents.register(agent) input.feed('hi') @@ -748,14 +736,6 @@ describe('createStdioChat input', () => { expect(agent.sent).toHaveLength(1) }) - it('treats an empty resume session id as a fresh configured identity', async () => { - const { ctx, input } = await setup({ welcome: 'w', resumeSessionId: '' }) - const agent = makeAgent('main-session-fresh') - ctx.agents.register(agent) - input.feed('hi') - await new Promise(r => setImmediate(r)) - expect(agent.sent).toHaveLength(1) - }) }) describe('createStdioChat EOF exit', () => { From a8c0e8a03c35b1303d7780b8215e482809c32d6f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:55:15 +0800 Subject: [PATCH 058/323] test: cover successful ACP cleanup failure --- .../support/acp-snapshot/tests/harness.spec.ts | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index de764cfd8a..23b4192a4d 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -274,6 +274,21 @@ describe('runScenario', () => { expect(failures[1]).toBe(cleanupFailure) }) + it('reports cleanup failure after an otherwise successful scenario', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({}) + const cleanupFailure = new Error('cleanup failed') + fsControl.cleanupFailure = cleanupFailure + + const failure = await runScenario( + { steps: boot }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ).catch((error: unknown): unknown => error) + + expect(failure).toBeInstanceOf(AggregateError) + expect((failure as AggregateError).message).toBe('snapshot cleanup failed') + expect((failure as AggregateError).errors as unknown[]).toEqual([cleanupFailure]) + }) + it('newSessionExpectError swallows the rejection, with and without extra dirs', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ rejectExtraDirs: true }) const result = await runScenario( From 2dca8e2151ef3745f88507fe2aac17cabd630eac Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:58:35 +0800 Subject: [PATCH 059/323] docs: refresh agent loop catalog location --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6b456ef942 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:337`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From 00462f80a6ff59604e44b71446bb9b2427a212c8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:01:36 +0800 Subject: [PATCH 060/323] docs: expose agent ownership in Cordis catalog --- packages/cordis/tool-cordis/src/api-catalog.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..ede7935f8e 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -72,6 +72,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', + 'isOwnedBy(id: SessionId, owner: Agent): boolean', 'list(): Agent[]', 'roots(): Agent[]', ], From db3e97fc17a0f96fda7a2ecee94af86e7fad2102 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:05:19 +0800 Subject: [PATCH 061/323] test: create built probe child in parent scope --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index 159600e49c..bc6642263e 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -58,7 +58,7 @@ try { meta: { cwd: storageRoot }, agentOptions: { model: "test" }, }); - const child = await ctx.agents.create({ + const child = await parent.agent.ctx.agents.create({ sessionId: SessionId("built-child"), meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, agentOptions: { model: "test" }, From 3e2ba3f5574b43dc5af5d03e146769be241f96a3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:13:05 +0800 Subject: [PATCH 062/323] fix: stop ACP teardown when fallback kill fails --- packages/support/acp-snapshot/src/launcher.ts | 27 ++++++++- .../acp-snapshot/tests/harness.spec.ts | 59 +++++++++++++++++++ 2 files changed, 83 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index f1271986c0..8d25a6f56c 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -65,7 +65,7 @@ export interface LaunchedAcpTestAgent { stderr(): string /** Resolve when a future session update matches the predicate. */ waitForUpdate(match: (update: SessionNotification['update']) => boolean): Promise - /** Gracefully close stdin, or send a signal, then wait for process exit, inherited stdio closure, ACP parsing, and client callbacks. */ + /** Close the process and drain its streams and callbacks; rejects promptly if fallback termination is refused. */ close(signal?: NodeJS.Signals): Promise } @@ -231,8 +231,29 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // signal can leave the subprocess live. Force termination, await the // already-observed exit edge, and only then propagate the child error so // callers may safely remove cwd/session resources after close rejects. - child.kill('SIGKILL') - await exited + const fallbackError = Promise.withResolvers() + const observeFallbackError = (error: Error): void => { fallbackError.resolve(error) } + child.once('error', observeFallbackError) + if (!child.kill('SIGKILL')) { + child.off('error', observeFallbackError) + closeUpdateStream() + throw new AggregateError( + [failure, new Error('Fallback SIGKILL was not accepted by the child process')], + 'ACP test agent failed and fallback termination was refused', + ) + } + const fallbackFailure = await Promise.race([ + exited.then((): undefined => undefined), + fallbackError.promise, + ]) + child.off('error', observeFallbackError) + if (fallbackFailure !== undefined) { + closeUpdateStream() + throw new AggregateError( + [failure, fallbackFailure], + 'ACP test agent failed and fallback termination was refused', + ) + } await drained closeUpdateStream() throw failure diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 23b4192a4d..ff7c304121 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -131,6 +131,65 @@ describe('runScenario', () => { expect(launched.stderr()).toContain('late inherited stderr') }) + it('rejects promptly when fallback termination is refused', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await launched.spawned + + const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' }) + const originalKill = launched.child.kill.bind(launched.child) + const kill = vi.spyOn(launched.child, 'kill').mockReturnValue(false) + const closed = new Promise(resolve => launched.child.once('close', () => { resolve() })) + try { + launched.child.emit('error', childFailure) + const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error) + expect(rejection).toBeInstanceOf(AggregateError) + expect(rejection).toMatchObject({ + message: 'ACP test agent failed and fallback termination was refused', + errors: [ + childFailure, + expect.objectContaining({ message: 'Fallback SIGKILL was not accepted by the child process' }), + ], + }) + expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM') + expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL') + } finally { + kill.mockRestore() + originalKill('SIGKILL') + await closed + } + }) + + it('rejects promptly when fallback termination emits an error', async () => { + const { dir } = await scenario({}) + const launched = launchAcpTestAgent({ agent: AGENT, cwd: dir }) + await launched.spawned + + const childFailure = Object.assign(new Error('signal refused'), { code: 'EPERM' }) + const fallbackFailure = Object.assign(new Error('fallback signal refused'), { code: 'EPERM' }) + const originalKill = launched.child.kill.bind(launched.child) + const kill = vi.spyOn(launched.child, 'kill').mockImplementation((signal) => { + if (signal === 'SIGKILL') queueMicrotask(() => launched.child.emit('error', fallbackFailure)) + return signal === 'SIGKILL' + }) + const closed = new Promise(resolve => launched.child.once('close', () => { resolve() })) + try { + launched.child.emit('error', childFailure) + const rejection = await launched.close('SIGTERM').catch((error: unknown): unknown => error) + expect(rejection).toBeInstanceOf(AggregateError) + expect(rejection).toMatchObject({ + message: 'ACP test agent failed and fallback termination was refused', + errors: [childFailure, fallbackFailure], + }) + expect(kill).toHaveBeenNthCalledWith(1, 'SIGTERM') + expect(kill).toHaveBeenNthCalledWith(2, 'SIGKILL') + } finally { + kill.mockRestore() + originalKill('SIGKILL') + await closed + } + }) + it('waits for in-flight client callbacks after the ACP stream closes', { timeout: 20_000 }, async () => { const { dir, fixtureFile } = await scenario({ permissionProbe: true }) let releasePermission: (() => void) | undefined From 816b6e4c68e26c38c4ac0aab1cad3ee14714a510 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:25:49 +0800 Subject: [PATCH 063/323] fix: restore exact config sessions on loop reload --- docs/config-catalog.md | 2 +- .../2026-06-20-unify-agent-and-session-id.md | 10 ++--- .../2026-07-02-remove-stream-chunk-mirror.md | 2 +- packages/core/agent-loop/README.md | 6 +-- packages/core/agent-loop/src/index.ts | 29 ++++++++++++++- .../tests/config-session-id.spec.ts | 37 +++++++++++++++++++ packages/ui/stdio-agent/README.md | 2 +- 7 files changed, 75 insertions(+), 13 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 66791edb0a..024d3b766b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -119,7 +119,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 404ba83636..20ba40c196 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -4,19 +4,19 @@ Status: implemented ## Problem -The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. +A live agent/session pair needs one identity for registry routing, event sourcing, and persistence. Giving the factory independent `agentId` and `sessionId` inputs would permit pairings no production path can use, while forcing every consumer to choose or translate between two names for the same lifecycle. -ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. +ACP uses the same value for both identities. Stdio and hooks also operate on the session event stream and need the corresponding live agent directly; no production path reattaches one live agent object to several sessions or drives one session through several agent ids. -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) uses one `AgentCreationTransaction` for create and resume, and agent/session entries share the same final-entry collision rule. A second identity would not represent separate liveness, rollback, or quiescence; it would only add API and translation state around the same transaction. -Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. +Session identity likewise has one home in `Session.header.id`; `Session.id` is a derived accessor rather than independent state that needs duplicate validation. ## Decision An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; in-process subagent creation uses the child session id; and `Session.id` derives from `header.id`. A remote ACP run has no local agent/session pair: it keeps one parent-minted lifecycle id while the child server's wire-local session id remains private to ACP calls. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between local ids are gone. -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start normally mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; a coupled app may pre-mint and pass the exact fresh `sessionId`, while `resumeSessionId` supplies the exact combined identity to load and register. The two exact-id inputs are mutually exclusive. Stdio uses this narrow escape hatch so its config-created agent and UI share one opaque identity instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. An ordinary fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide. A coupled app may pre-mint and pass an exact `sessionId`: first use creates it, while an AgentLoop remount with an already-present persistence service resumes materialized history under that same identity. `resumeSessionId` instead requires an existing persisted identity. The two exact-id inputs are mutually exclusive. Stdio uses the resume-or-create form so its config-created agent and UI share one opaque identity across loop reloads instead of guessing from a prefix. Logs may use the stable label while all live and durable lookups use the one `SessionId`. `agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. diff --git a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md index a272dfe0b2..6ca85b3d16 100644 --- a/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md +++ b/docs/rfc/implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md @@ -42,4 +42,4 @@ Not touched: ## Consequences -A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event` and filters `assistant/chunk` (the `Agent` handle, if needed, is recovered from a session-id→agent map built from `agent/created`/`agent/disposed`, exactly as boundary consumers already do). No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. +A plugin can no longer observe token deltas from an `Agent`-first event. It subscribes to `session/event`, filters `assistant/chunk`, and looks up the corresponding live handle directly with `ctx.agents.get(session.id)` when needed. No production consumer needed the live `Agent` at chunk time; this is the same acceptable trade the boundary-mirror removal made. diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 246c9cdc27..2db1a6c079 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -14,7 +14,7 @@ The caller fiber and the AgentLoop provider are co-owners. `AgentFactory.createA Each agent and its session share one caller-chosen `SessionId`, assumed globally unique; accidental UUID collisions are outside the supported model. Two concurrent operations with the same id may both prepare, but the final `enter()` calls arbitrate publication and every loser rolls its private resources back. Each detach is bound to the exact entered object, so a stale disposer cannot remove a later same-id replacement. A detach requested during a synchronous creation notification waits for that dispatch to unwind, preserving created/disposed pairing. Teardown runs stop and drain (including outstanding idle-injection flushes) → detach agent → detach session → unwind scope; the id becomes reusable at detach even if private scope cleanup is still finishing. Ordinary non-vetoing `agent/*` notifications go through `agentEvents(ctx, agent)`, per-step assembly goes through `assembleContextFor(agent)`, and turn-end durability checkpoints go through `ctx.sessions.flush(session)`. -- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary; an app may instead supply an exact fresh `sessionId` when another coupled component must bind to it. `resumeSessionId` loads and registers the exact persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. +- `ctx.agentLoop.create(id: SessionId, options?: AgentOptions, meta?: { cwd?: string }): ReactLoopAgent` — synchronous no-setup create under the exact shared agent/session id, disposed with the calling fiber. Declarative config treats `agents[].id` as a stable label and normally mints `${label}-session-` before calling this boundary. An app may instead supply a stable exact `sessionId`: first use creates it, while a remount with persistence already present resumes its materialized history. `resumeSessionId` requires and loads an existing persisted id and is mutually exclusive with `sessionId`. This keeps default fresh restarts collision-free without retaining a second live routing identity. `AgentLoop` also implements the `AgentFactory` seam and registers itself via `ctx.agents.setFactory(this)`, so plugins create/resume agents through `ctx.agents` (the interface): @@ -33,7 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required stable label; prefixes fresh combined ids - sessionId?: string // optional exact identity for a fresh session + sessionId?: string // optional exact resume-or-create identity model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` and optional `sessionId` apply only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 0041b984d1..33e8c3c443 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -326,7 +326,7 @@ export interface Config { agents: (AgentOptions & { /** Stable config label used in logs and as the fresh combined-id prefix. */ id: string - /** Optional exact identity for a fresh session; absent lets the loop mint one from the label. */ + /** Optional stable identity; remounts resume its materialized history, while first use creates it fresh. */ sessionId?: SessionId /** Optional workspace for a fresh session. */ cwd?: string @@ -364,8 +364,17 @@ export class AgentLoop extends Service implements AgentFactory { ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) for (const { id, sessionId, cwd, resumeSessionId, ...options } of config.agents) { + const meta = cwd === undefined ? {} : { cwd } if (resumeSessionId === undefined || resumeSessionId === '') { - this.create(sessionId ?? SessionId(`${id}-session-${randomUUID()}`), options, cwd === undefined ? {} : { cwd }) + const configuredId = sessionId ?? SessionId(`${id}-session-${randomUUID()}`) + const persistence = sessionId === undefined ? undefined : ctx.get('sessionPersistence') + if (persistence === undefined) { + this.create(configuredId, options, meta) + } else { + void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + }) + } continue } if (sessionId !== undefined) { @@ -385,6 +394,22 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Restore a materialized exact config identity on remount, or create it on first use. */ + private async restoreOrCreateConfigured( + ownerCtx: Context, + persistence: SessionPersistence, + sessionId: SessionId, + agentOptions: AgentOptions, + meta: Pick, + ): Promise { + const exists = (await persistence.list()).some(header => header.id === sessionId) + if (exists) { + await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) + return + } + this.create(sessionId, agentOptions, meta) + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 543335e5fd..9382804527 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -55,6 +55,43 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first'), textResponse('second')])) + const config = { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-reload'), model: 'mock' }] } + + const firstLoop = await ctx.plugin(AgentLoop, config) + let first: ReactLoopAgent | undefined + for (let i = 0; i < 50 && first === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + first = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(first).toBeDefined() + first!.send([{ type: 'text', text: 'remember me' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, first!) + await firstLoop.dispose() + + const secondLoop = await ctx.plugin(AgentLoop, config) + let second: ReactLoopAgent | undefined + for (let i = 0; i < 50 && second === undefined; i++) { + await new Promise(resolve => setTimeout(resolve, 5)) + second = ctx.agents.get(SessionId('stdio-exact-reload')) as ReactLoopAgent | undefined + } + expect(second).toBeDefined() + expect(JSON.stringify(second!.session.deriveMessages())).toContain('remember me') + second!.send([{ type: 'text', text: 'continue' }], { source: { kind: 'user' } }) + await waitForIdle(ctx, second!) + await ctx.sessions.flush(second!.session) + const loaded = await ctx.sessionPersistence.load(SessionId('stdio-exact-reload')) + expect(loaded.events.filter(event => event.type === 'turn/start')).toHaveLength(2) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index b509e46781..15b1c78f09 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; the UI's `main` text is only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin From 656ae95263cfd9f832bdeefbf9da6a91b8ce72bb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:28:04 +0800 Subject: [PATCH 064/323] test: await exact stdio startup condition --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 9a7bf10bad..a14848a549 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -114,9 +114,8 @@ describe('dsh-stdio-agent app', () => { const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) - await new Promise(resolve => setTimeout(resolve, 80)) - expect(ctx.get('sessionPersistence')).toBeDefined() - expect(ctx.get('agents')?.list()).toHaveLength(1) + await expect.poll(() => ctx.get('sessionPersistence')).toBeDefined() + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) await ctx.fiber.dispose() }) From cf21e252fa8fd7e66c4b0c6a5acface4821d4712 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:32:02 +0800 Subject: [PATCH 065/323] fix: recognize provider-owned local subagents --- packages/subagent/subagent/README.md | 2 ++ packages/subagent/subagent/src/types.ts | 6 +++++- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 22 ++++++++++++++++------ packages/ui/jsonrpc/tests/server.spec.ts | 5 ++++- 5 files changed, 28 insertions(+), 9 deletions(-) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 413bbbdafc..016d363d78 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -50,6 +50,8 @@ Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a `SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for the child resources to quiesce. +A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, and records `request.parent.session.id` in the child's `parentSession` header. The child may be owned by the parent scope or by a provider/root scope; durable lineage is the transport-neutral local-child relation. Remote providers instead mint a parent-scoped lifecycle id without publishing a local child. + The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. In-process start observers can resolve the published child through `ctx.agents.get(info.id)`; remote providers need not publish a local agent. Run events are scoped to the delegating parent. Every listener is independently contained: a synchronous throw or rejected returned promise is logged without starving peer listeners or changing the run. diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 827c2db7a7..37e0b28323 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,11 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ + /** + * Parent-scoped run id. A local run publishes a child session whose + * `parentSession` records `request.parent`; a remote provider mints an id + * unique in the parent namespace. + */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index df612ac263..4ef9e86ffc 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server recognizes a live child through either exact delegating-parent runtime ownership or matching durable `parentSession` lineage, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index d78f24b5ab..723f2eb4eb 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -66,6 +66,15 @@ function subagentParentOf(carrier: Scoped): Agent { return carrierKeyOf(carrier) as Agent } +/** Whether the live id names a local child related to this exact delegating parent. */ +function isLocalChild(ctx: Context, id: SessionId, parent: Agent): boolean { + const child = ctx.agents.get(id) + return child !== undefined && ( + ctx.agents.isOwnedBy(id, parent) + || child.session.header.parentSession === parent.session.id + ) +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session and subagent lifecycle events, forwarding durable session @@ -104,13 +113,14 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // In-process providers publish the child before start. Count those starts by - // the exact delegating-parent carrier so later completions remain local after - // child disposal and reused ids need no settlement-order assumption. + // In-process providers publish the child before start. Count starts related + // by exact runtime ownership or durable parent lineage so provider-owned + // roots remain local, completions survive child disposal, and reused ids + // need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { const parent = subagentParentOf(this) - if (!ctx.agents.isOwnedBy(info.id, parent)) return + if (!isLocalChild(ctx, info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -130,9 +140,9 @@ export class HarnessSdkServer { } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above. A remote run - // has neither a cached owned start nor a live child owned by this exact + // has neither a cached local start nor a live child related to this // parent; an unrelated local agent with the same id never makes it local. - if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return + if (pendingCount === undefined && !isLocalChild(ctx, info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index c97bd1a6e1..3861a6729d 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,11 +277,14 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await parentHandle.agent.ctx.agents.create({ + // A custom in-process provider may own its child at the provider/root + // scope while preserving durable parent lineage. + const handle = await ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + expect(ctx.agents.roots()).toContain(handle.agent) const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, From 949ee03377719aea96a26fd96ba0bc284cf740ec Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:38:53 +0800 Subject: [PATCH 066/323] test: cover exact session restore failure --- .../tests/config-session-id.spec.ts | 21 +++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 9382804527..dcde82efe2 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,27 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains an exact-id persistence lookup failure', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const failure = new Error('persistence index failed') + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-failure'), model: 'mock' }], + }) + + await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( + 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', + )) + expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From 46b8bce03acebd579cdcb4daf91c02e51eddf78e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:47:47 +0800 Subject: [PATCH 067/323] fix: join exact session startup on teardown --- docs/config-catalog.md | 2 +- docs/cordis-catalog/services.md | 2 +- packages/core/agent-loop/src/index.ts | 19 +++++++++++--- .../tests/config-session-id.spec.ts | 25 +++++++++++++++++++ 4 files changed, 42 insertions(+), 6 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 024d3b766b..d22bcca6f7 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:324`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 6b456ef942..e79422b94f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 33e8c3c443..d2d8648595 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -45,6 +45,7 @@ const INACTIVE_STATES: ReadonlySet = new Set([ class FactoryOwnership { private accepting = true private transactions = new Set() + private startupTasks = new Set>() constructor(private readonly fiber: Context['fiber']) {} @@ -57,12 +58,20 @@ class FactoryOwnership { return () => { this.transactions.delete(transaction) } } + /** Join config startup work that begins before an agent transaction exists. */ + trackStartup(task: Promise): void { + this.startupTasks.add(task) + const forget = () => { this.startupTasks.delete(task) } + void task.then(forget, forget) + } + async dispose(): Promise { this.accepting = false const reason = new Error('agent loop is not active') - await Promise.all( - [...this.transactions].map(transaction => transaction.disposeForFactory(reason)), - ) + await Promise.all([ + ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), + ...this.startupTasks, + ]) } } @@ -371,9 +380,10 @@ export class AgentLoop extends Service implements AgentFactory { if (persistence === undefined) { this.create(configuredId, options, meta) } else { - void this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { + const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) }) + this.ownership.trackStartup(startup) } continue } @@ -403,6 +413,7 @@ export class AgentLoop extends Service implements AgentFactory { meta: Pick, ): Promise { const exists = (await persistence.list()).some(header => header.id === sessionId) + if (!this.ownership.isActive()) return if (exists) { await this.resumeWith(ownerCtx, persistence, { resumeSessionId: sessionId, agentOptions }) return diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index dcde82efe2..c1a04fadd0 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -113,6 +113,31 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) + + listing.resolve([]) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }) + it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() await ctx.plugin(LlmService) From 288023dac182c407c296571f3730ff3a89a0696a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:51:36 +0800 Subject: [PATCH 068/323] docs: define local subagent lineage --- docs/core-data-structures/subagent.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 883c33020a..7b57789a7c 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -76,6 +76,8 @@ interface SubagentRun { } ``` +A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope; `parentSession` is the durable transport-neutral lineage. A remote provider instead returns a parent-scoped lifecycle id and does not publish a local child. + ## The provider seam: `SubagentProvider` One transport for running a child agent. Implementations register under a unique name via `SubagentService.registerProvider`; multiple coexist in one context. The service validates every requested start-time capability before calling `start`, so an implementation may assume e.g. `request.maxDepth` is honorable when present. `inheritsParentContext` is a DESCRIPTIVE fact beside the capabilities (nothing validates against it): whether a child sees the parent conversation (`fork`: true, `spawn`/`acp`: false) — the model-facing consumer derives truthful tool wording from it. It describes conversation history only, not tool registrations, injected services, or authority inheritance. From e8f1bd41f5bd96c529c59ed524cfdeef7d3d1ce3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:02:18 +0800 Subject: [PATCH 069/323] fix: buffer stdio until exact session starts --- docs/event-producer-consumer.md | 2 +- packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/src/stdio-chat.ts | 65 ++++++++++++----- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 72 +++++++++++++++---- 4 files changed, 108 insertions(+), 33 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..1439873f69 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -15,7 +15,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:348`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:473`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:525`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:369`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:540`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:558`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 15b1c78f09..bbf175d92d 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 93c8f9b4f1..17d396c042 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -3,9 +3,10 @@ * `steer()`, and renders the durable transcript to stdout. A UI is "just a * plugin" — it consumes the `session/event` feed (the assistant token stream, * turn/step boundaries, tool activity, todos) plus a few `agent/*` control - * events (`agent/status`, `agent/created`/`agent/disposed`) and the `agents` - * service. Dimmed chain-of-thought rendering plus robust piped-stdin EOF→idle - * exit handling, configured via {@link Config}. + * events (`agent/status`, `agent/created`/`agent/disposed`, + * `agent/session-start`) and the `agents` service. Dimmed chain-of-thought + * rendering plus robust piped-stdin EOF→idle exit handling, configured via + * {@link Config}. * * An internal module of the stdio app, not a package of its own: the app's * front-door cluster always includes this UI, and nothing else composes it. @@ -105,12 +106,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const matchesConfiguredIdentity = (agent: Agent): boolean => agent.id === config.sessionId && ctx.agents.roots().includes(agent) let target: Agent | undefined = ctx.agents.roots().find(agent => agent.id === config.sessionId) - ctx.on('agent/created', (agent) => { - if (matchesConfiguredIdentity(agent)) target = agent - }) - ctx.on('agent/disposed', (agent) => { - if (target === agent) target = undefined - }) // Transcript rendering off the durable `session/event` feed — the assistant // token stream, turn/step boundaries, tool activity, and todos all come from @@ -158,7 +153,6 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt }) ctx.effect(() => { - const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) // Piped-input exit, once stdin reaches EOF: // - If no line ever submitted work (empty stdin, blank-only lines), exit // immediately — no turn will ever start, so there is nothing to wait @@ -176,6 +170,36 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt let exitTimer: ReturnType | undefined let activeQuestion: PendingQuestion | undefined const questionQueue: PendingQuestion[] = [] + const queuedInput: string[] = [] + let targetReady = target !== undefined + let hadReadyTarget = targetReady + + const submit = (agent: Agent, text: string): void => { + submittedWork = true + if (agent.status === 'running') { + agent.steer([{ type: 'text', text }]) + } else { + agent.send([{ type: 'text', text }]) + } + } + + const disposeCreatedListener = ctx.on('agent/created', (agent) => { + if (!matchesConfiguredIdentity(agent)) return + target = agent + targetReady = false + }) + const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { + if (agent !== target) return + targetReady = true + hadReadyTarget = true + for (const text of queuedInput.splice(0)) submit(agent, text) + }) + const disposeDisposedListener = ctx.on('agent/disposed', (agent) => { + if (target !== agent) return + target = undefined + targetReady = false + }) + const reader = createInterface({ input, output, terminal: isTTYPair(input, output) }) const maybeExit = (): void => { if (disposed || !stdinClosed) return @@ -351,16 +375,20 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return const agent = target - if (!agent) { + if (agent === undefined || !targetReady) { + // Initial exact-id restoration is asynchronous. Preserve input until + // session-start, the first supported point for queueing agent work. + // After a previously ready target disappears, a line in the HMR gap + // still fails loud unless its exact replacement is already publishing. + if (!hadReadyTarget || agent !== undefined) { + submittedWork = true + queuedInput.push(text) + return + } ctx.logger.error('ui-stdio: main agent is not running') return } - submittedWork = true - if (agent.status === 'running') { - agent.steer([{ type: 'text', text }]) - } else { - agent.send([{ type: 'text', text }]) - } + submit(agent, text) }) reader.on('close', () => { // Fires for BOTH stdin EOF and plugin disposal (reader.close() below); @@ -376,6 +404,9 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposePendingQuestions() disposeUserInteractionProvider() disposeStatusListener() + disposeCreatedListener() + disposeSessionStartListener() + disposeDisposedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index f1ca914525..943c48ef08 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -64,6 +64,13 @@ function makeAgent(id: string, status: AgentStatus = 'idle'): Agent & { } as never } +/** Register a fake configured agent and cross the supported startup-work boundary. */ +function registerReady(ctx: Context, agent: Agent, source: 'startup' | 'resume' = 'startup'): () => void { + const dispose = ctx.agents.register(agent) + ctx.emit('agent/session-start', agent, source) + return dispose +} + /** A session stub whose `header.id` matches an agent's, for `session/event` emits. */ function makeSession(id: string): Session { return { id, header: { id } } as Session @@ -198,15 +205,21 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[main turn 5] ') }) - it('accepts a lineage-bearing configured agent created after the UI installs', async () => { + it('buffers input for a lineage-bearing configured agent until its session starts', async () => { const { ctx, input } = await setup({ welcome: 'hi there', sessionId: 'resumed' }) + input.feed('continue') + await new Promise(resolve => setImmediate(resolve)) + const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) + ctx.emit('agent/session-start', unrelated, 'startup') const resumed = makeAgent('resumed') ;(resumed.session.header as { parentSession?: string }).parentSession = 'persisted-parent' ctx.agents.register(resumed) + await new Promise(resolve => setImmediate(resolve)) + expect(resumed.sent).toEqual([]) - input.feed('continue') + ctx.emit('agent/session-start', resumed, 'resume') await new Promise(resolve => setImmediate(resolve)) expect(unrelated.sent).toEqual([]) @@ -256,9 +269,11 @@ describe('createStdioChat rendering', () => { disposeOld() const replacement = makeAgent('main-session-fixed') ctx.agents.register(replacement) - input.feed('after hmr') await new Promise(resolve => setImmediate(resolve)) + expect(replacement.sent).toEqual([]) + ctx.emit('agent/session-start', replacement, 'resume') + await new Promise(resolve => setImmediate(resolve)) expect(prefixCollision.sent).toEqual([]) expect(replacement.sent).toEqual([[{ type: 'text', text: 'after hmr' }]]) @@ -269,7 +284,7 @@ describe('createStdioChat rendering', () => { const unrelated = makeAgent('unrelated') ctx.agents.register(unrelated) const configured = makeAgent('main') - const disposeConfigured = ctx.agents.register(configured) + const disposeConfigured = registerReady(ctx, configured) const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) disposeConfigured() @@ -693,7 +708,7 @@ describe('createStdioChat input', () => { it('sends a typed line to an idle agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('do a thing') await new Promise(r => setImmediate(r)) expect(agent.sent).toEqual([[{ type: 'text', text: 'do a thing' }]]) @@ -703,7 +718,7 @@ describe('createStdioChat input', () => { it('steers a typed line into a running agent', async () => { const { ctx, input } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('steer me') await new Promise(r => setImmediate(r)) expect(agent.steered).toEqual([[{ type: 'text', text: 'steer me' }]]) @@ -719,18 +734,26 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([]) }) - it('logs and drops a line when the target agent is not running', async () => { + it('buffers a line until the initial target session starts', async () => { const { ctx, input } = await setup() const spy = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) input.feed('nobody home') await new Promise(r => setImmediate(r)) - expect(spy).toHaveBeenCalledWith('ui-stdio: main agent is not running') + expect(spy).not.toHaveBeenCalled() + + const agent = makeAgent('main') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') - ctx.agents.register(agent) + registerReady(ctx, agent, 'resume') input.feed('hi') await new Promise(r => setImmediate(r)) expect(agent.sent).toHaveLength(1) @@ -749,7 +772,7 @@ describe('createStdioChat EOF exit', () => { it('waits for the agent to settle idle after running before exiting', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -764,10 +787,31 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('keeps piped EOF pending until buffered startup input runs', async () => { + const { ctx, input, exit } = await setup() + input.feed('work') + input.finish() + await flushExit() + expect(exit).not.toHaveBeenCalled() + + const agent = makeAgent('main', 'idle') + ctx.agents.register(agent) + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([]) + ctx.emit('agent/session-start', agent, 'startup') + await new Promise(r => setImmediate(r)) + expect(agent.sent).toEqual([[{ type: 'text', text: 'work' }]]) + ctx.emit('agent/status', agent, 'running') + ;(agent as { status: AgentStatus }).status = 'idle' + ctx.emit('agent/status', agent, 'idle') + await flushExit() + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') // sawRunning = true @@ -785,7 +829,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit on an idle transition for a different agent', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) input.finish() @@ -799,7 +843,7 @@ describe('createStdioChat EOF exit', () => { it('does not exit while a turn is still running at EOF', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) ctx.emit('agent/status', agent, 'running') @@ -848,7 +892,7 @@ describe('createStdioChat disposal (HMR safety)', () => { it('removes the agent/status listener on dispose', async () => { const { ctx, fiber, input, exit } = await setup() const agent = makeAgent('main', 'idle') - ctx.agents.register(agent) + registerReady(ctx, agent) input.feed('work') await new Promise(r => setImmediate(r)) await fiber.dispose() From c1fb97c63a3ac7c3a6d4066ccc7615d292c0dfa7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:23:38 +0800 Subject: [PATCH 070/323] fix: surface config startup failures --- docs/architecture.md | 7 ++- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 12 +++++ docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 1 + docs/module-graph.md | 3 +- .../cordis/tool-cordis/src/api-catalog.ts | 6 +++ packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 30 +++++++++++- .../tests/config-session-id.spec.ts | 10 ++++ packages/ui/stdio-agent/README.md | 2 +- packages/ui/stdio-agent/package.json | 2 + packages/ui/stdio-agent/src/index.ts | 23 ++++----- packages/ui/stdio-agent/src/stdio-chat.ts | 20 ++++++++ .../ui/stdio-agent/tests/stdio-chat.spec.ts | 47 ++++++++++++++++++- pnpm-lock.yaml | 3 ++ 16 files changed, 151 insertions(+), 21 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..06a3a86fb4 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -51,14 +51,17 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. +Default loop processing remains exposed through plugin-visible services and events. A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +Declarative startup chooses one agent/session identity. No id mints `-session-`; exact `sessionId` resumes when stored and otherwise creates; `resumeSessionId` requires stored history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, letting front doors reject buffered work. + ### Turn Flow ```text -prepare private session + agent.ctx -> await unpublished setup +choose declarative identity and fresh/resume path + -> prepare private session + agent.ctx -> await unpublished setup -> enter session + agent -> session/created -> agent/created -> enable driving -> agent/session-start(source) -> start driver forever: diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d22bcca6f7..839e7967e6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:333`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a5e018079a..3c56882494 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -175,6 +175,18 @@ Types: [Agent](../core-data-structures/core.md) Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/types.ts) +## `agent-loop/*` + +### `agent-loop/config-start-failed` — emit + +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. + +```ts cordis-catalog +'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void +``` + +Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) + ## `approval/*` ### `approval/request` — waterfall diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e79422b94f..63375a46bf 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 1439873f69..0ab96fca31 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,6 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..cc4cd86c47 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -316,6 +316,7 @@ flowchart TD pkg_acp_agent --> pkg_user_interaction pkg_stdio_agent --> pkg_agent pkg_stdio_agent --> pkg_agent_core + pkg_stdio_agent --> pkg_agent_loop pkg_stdio_agent --> pkg_app_boot pkg_stdio_agent --> pkg_llm pkg_stdio_agent --> pkg_session @@ -394,4 +395,4 @@ flowchart TD | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-agent`](../packages/ui/acp-agent) | `ui` | [`acp`](../packages/ui/acp), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-agent`](../packages/ui/stdio-agent) | `ui` | [`agent`](../packages/core/agent), [`agent-core`](../packages/core/agent-core), [`agent-loop`](../packages/core/agent-loop), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..a9d1d5acaa 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -237,6 +237,12 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ /** Every harness event, sorted by name. */ export const EVENT_API: readonly EventApiEntry[] = [ + { + name: 'agent-loop/config-start-failed', + mode: 'emit', + signature: '\'agent-loop/config-start-failed\'(sessionId: SessionId, error: unknown): void', + summary: 'A declarative agent entry failed before it could publish a live agent.', + }, { name: 'agent/created', mode: 'emit', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2db1a6c079..2593da7c47 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index d2d8648595..62c5d94b06 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -327,6 +327,17 @@ declare module 'cordis' { interface Context { agentLoop: AgentLoop } + interface Events { + /** + * A declarative agent entry failed before it could publish a live agent. + * Consumers that buffer work for the configured identity use this + * transient signal to reject that work instead of waiting forever. + * @param sessionId - exact shared agent/session identity that failed startup. + * @param error - persistence, setup, or publication failure. + * @mode emit + */ + 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void + } } /** Plugin configuration for declarative startup agents. */ @@ -381,7 +392,7 @@ export class AgentLoop extends Service implements AgentFactory { this.create(configuredId, options, meta) } else { const startup = this.restoreOrCreateConfigured(ctx, persistence, configuredId, options, meta).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven restore of "${configuredId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'restore', configuredId, error) }) this.ownership.trackStartup(startup) } @@ -396,7 +407,7 @@ export class AgentLoop extends Service implements AgentFactory { resumeSessionId, agentOptions: options, }).catch((error: unknown) => { - ctx.logger.warn(`agent "${id}": config-driven resume of "${resumeSessionId}" failed: ${String(error)}`) + this.reportConfiguredStartupFailure(id, 'resume', resumeSessionId, error) }) }) return fiber.dispose @@ -404,6 +415,21 @@ export class AgentLoop extends Service implements AgentFactory { } } + /** Report a contained declarative-start failure to identity-bound consumers. */ + private reportConfiguredStartupFailure( + configId: string, + action: 'restore' | 'resume', + sessionId: SessionId, + error: unknown, + ): void { + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + try { + this.ctx.emit('agent-loop/config-start-failed', sessionId, error) + } catch (listenerError) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } + } + /** Restore a materialized exact config identity on remount, or create it on first use. */ private async restoreOrCreateConfigured( ownerCtx: Context, diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index c1a04fadd0..ad9ec6b792 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -98,6 +98,12 @@ describe('config-driven session id', () => { const ctx = await makeCoreContext() await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') + const listenerFailure = new Error('failure observer failed') + const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + failures.push({ sessionId, error }) + }) + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -108,6 +114,10 @@ describe('config-driven session id', () => { await expect.poll(() => warn).toHaveBeenCalledWith(expect.stringContaining( 'config-driven restore of "stdio-exact-failure" failed: Error: persistence index failed', )) + expect(failures).toEqual([{ sessionId: SessionId('stdio-exact-failure'), error: failure }]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: Error: failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index bbf175d92d..a91bef85a0 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -32,7 +32,7 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `welcome` | `ready.` | the stdin-chat banner | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | -Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. +Fresh stdio sessions use the process launch directory as `session.header.cwd` and mint one combined `main-session-` agent/session id, so durable restarts cannot collide. The app passes that exact opaque id to both its config-created agent and UI; an AgentLoop-only reload resumes materialized history under that id, while the UI's `main` text remains only a display label and never selects another registry root by prefix or insertion order. Readline buffers nonblank startup input for that identity until `agent/session-start`, so piped stdin cannot outrun asynchronous exact-id restoration or let EOF discard the queued prompt; `agent-loop/config-start-failed` instead drains and reports buffered input so a missing or corrupt persisted session cannot hang EOF. A resumed run binds both components to the exact `resumeSessionId` and keeps the cwd stored in the persisted session header. ## The bin diff --git a/packages/ui/stdio-agent/package.json b/packages/ui/stdio-agent/package.json index fcd432a9fd..60a9529d47 100644 --- a/packages/ui/stdio-agent/package.json +++ b/packages/ui/stdio-agent/package.json @@ -35,6 +35,7 @@ "@deepseek-ai/dsh-app-boot": "^0.0.1", "@cordisjs/plugin-logger-console": "^1.0.0", "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-agent-core": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -51,6 +52,7 @@ "@deepseek-ai/dsh-app-boot": "workspace:^", "@cordisjs/plugin-logger-console": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 03f3d49555..1278ded88a 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -102,16 +102,23 @@ export const Config: z = z.object({ }) /** - * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-core bundle pre-creating one agent from this app's - * `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI rendering that object as `main`. The `hmr` dev-reload plugin is - * a leaf concern (see the module doc), so it is not mounted here. + * Compose the spine with the stdio front door. Console logging, persistence, + * and user interaction mount first; the readline UI then waits on the agent + * registry and subscribes to config-start failures before agent-core can start + * the configured identity. The ask-user tool waits on the completed spine. + * The `hmr` dev-reload plugin is a leaf concern (see the module doc), so it is + * not mounted here. */ export function apply(ctx: Context, config: Config): void { const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(UserInteractionService) + ctx.plugin(uiStdio, { + welcome: config.welcome ?? 'ready.', + sessionId, + }) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, @@ -124,11 +131,5 @@ export function apply(ctx: Context, config: Config): void { }], ...config.skills !== undefined ? { skills: config.skills } : {}, }) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) - ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { - welcome: config.welcome ?? 'ready.', - sessionId, - }) } diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 17d396c042..39d59dfdc0 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -21,6 +21,7 @@ import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' import type { Agent } from '@deepseek-ai/dsh-agent' +import type {} from '@deepseek-ai/dsh-agent-loop' import { UserInteractionError, type AskUserQuestionAnswer, @@ -173,6 +174,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const queuedInput: string[] = [] let targetReady = target !== undefined let hadReadyTarget = targetReady + let failedStartup: { error: unknown } | undefined const submit = (agent: Agent, text: string): void => { submittedWork = true @@ -187,6 +189,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt if (!matchesConfiguredIdentity(agent)) return target = agent targetReady = false + failedStartup = undefined }) const disposeSessionStartListener = ctx.on('agent/session-start', (agent) => { if (agent !== target) return @@ -220,6 +223,18 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt exitTimer = setTimeout(() => { exit(0) }, 200) } + const disposeStartupFailedListener = ctx.on('agent-loop/config-start-failed', (sessionId, error) => { + if (sessionId !== config.sessionId || targetReady) return + failedStartup = { error } + const dropped = queuedInput.length + queuedInput.length = 0 + submittedWork = sawRunning + if (dropped > 0) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + } + maybeExit() + }) + const disposeStatusListener = ctx.on('agent/status', (subject, status) => { if (subject !== target) return if (status === 'running') sawRunning = true @@ -374,6 +389,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt } const text = line.trim() if (!text) return + if (failedStartup !== undefined) { + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + return + } const agent = target if (agent === undefined || !targetReady) { // Initial exact-id restoration is asynchronous. Preserve input until @@ -407,6 +426,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt disposeCreatedListener() disposeSessionStartListener() disposeDisposedListener() + disposeStartupFailedListener() reader.close() } }, 'ui-stdio') diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 943c48ef08..11e64ac19c 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -4,7 +4,7 @@ import { Context } from 'cordis' import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' -import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId, type Session, type SessionEvent } from '@deepseek-ai/dsh-session' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' import { createStdioChat, type Config, type StdioRuntime } from '../src/stdio-chat.ts' @@ -750,6 +750,32 @@ describe('createStdioChat input', () => { expect(agent.sent).toEqual([[{ type: 'text', text: 'nobody home' }]]) }) + it('drops later input after the configured startup fails', async () => { + const { ctx, input } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + const failure = new Error('persisted session is corrupt') + ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) + + input.feed('cannot run') + await new Promise(r => setImmediate(r)) + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + ) + }) + + it('ignores a stale config-start failure after the exact target is ready', async () => { + const { ctx, input } = await setup() + const agent = makeAgent('main') + registerReady(ctx, agent) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('stale')) + + input.feed('still live') + await new Promise(r => setImmediate(r)) + + expect(agent.sent).toEqual([[{ type: 'text', text: 'still live' }]]) + }) + it('drives the exact app-configured resumed session', async () => { const { ctx, input } = await setup({ welcome: 'w', sessionId: 'worker' }) const agent = makeAgent('worker') @@ -808,6 +834,25 @@ describe('createStdioChat EOF exit', () => { expect(exit).toHaveBeenCalledWith(0) }) + it('drains buffered piped input and exits when configured startup fails', async () => { + const { ctx, input, exit } = await setup() + const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) + input.feed('work') + input.finish() + await new Promise(r => setImmediate(r)) + ctx.emit('agent-loop/config-start-failed', SessionId('other'), new Error('unrelated')) + await flushExit() + expect(exit).not.toHaveBeenCalled() + + ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + await flushExit() + + expect(error).toHaveBeenCalledWith( + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + ) + expect(exit).toHaveBeenCalledWith(0) + }) + it('schedules the exit only once when idle fires repeatedly', async () => { const { ctx, input, exit } = await setup() const agent = makeAgent('main', 'running') diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..7a8fe5a6ea 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1328,6 +1328,9 @@ importers: '@deepseek-ai/dsh-agent-core': specifier: workspace:^ version: link:../../core/agent-core + '@deepseek-ai/dsh-agent-loop': + specifier: workspace:^ + version: link:../../core/agent-loop '@deepseek-ai/dsh-app-boot': specifier: workspace:^ version: link:../app-boot From 7d6ef0a47260a096a7594e54c797fde9e1ba8ca0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 11:33:36 +0800 Subject: [PATCH 071/323] fix: contain config failure observers --- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 14 ++++++++++---- .../agent-loop/tests/config-session-id.spec.ts | 7 ++++++- scripts/gen-doc-graphs.ts | 3 +++ 4 files changed, 20 insertions(+), 6 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 0ab96fca31..de89a69f18 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 62c5d94b06..5a7484a378 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -423,10 +423,16 @@ export class AgentLoop extends Service implements AgentFactory { error: unknown, ): void { this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) - try { - this.ctx.emit('agent-loop/config-start-failed', sessionId, error) - } catch (listenerError) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] + for (const callback of this.ctx.events.dispatch('emit', args)) { + try { + const returned: unknown = callback(...args) + void Promise.resolve(returned).catch((listenerError: unknown) => { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + }) + } catch (listenerError: unknown) { + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index ad9ec6b792..a7292b2284 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -99,11 +99,13 @@ describe('config-driven session id', () => { await ctx.plugin(SessionPersistenceJsonl, { root }) const failure = new Error('persistence index failed') const listenerFailure = new Error('failure observer failed') + const asyncListenerFailure = new Error('async failure observer failed') const failures: { sessionId: SessionId; error: unknown }[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) + ctx.on('agent-loop/config-start-failed', () => Promise.reject(asyncListenerFailure) as never) ctx.on('agent-loop/config-start-failed', (sessionId, error) => { failures.push({ sessionId, error }) }) - ctx.on('agent-loop/config-start-failed', () => { throw listenerFailure }) vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(failure) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) @@ -118,6 +120,9 @@ describe('config-driven session id', () => { expect(warn).toHaveBeenCalledWith( 'agent "main": config-start-failed listener threw: Error: failure observer failed', ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: Error: async failure observer failed', + ) expect(ctx.agents.get(SessionId('stdio-exact-failure'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5144e388a2..fa7daed85e 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -245,6 +245,9 @@ const DYNAMIC_EVENT_DISPATCHERS: Array<{ event: string; pkg: string; method: str // Registry disposal reuses the stable carrier captured before entry commit // and contains each listener directly rather than rebuilding via agentEvents. { event: 'agent/disposed', pkg: 'agent', method: 'events.dispatch' }, + // Config startup failures have no live Agent carrier; AgentLoop resolves the + // callbacks directly to contain each synchronous throw and async rejection. + { event: 'agent-loop/config-start-failed', pkg: 'agent-loop', method: 'events.dispatch' }, { event: 'session/created', pkg: 'session', method: 'events.dispatch' }, // Session event callbacks are likewise resolved before the log push, then // invoked individually after commit so observer failures are contained. From a25c0f084f035f94a11292b17ec9a31e93349c2e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:25:30 +0800 Subject: [PATCH 072/323] fix: totalize configured startup failures --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/src/index.ts | 15 ++++++-- .../tests/config-session-id.spec.ts | 36 +++++++++++++++++++ 6 files changed, 52 insertions(+), 7 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index d7a973fd81..484ba1c632 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:344`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 088e60450d..e44df3c3b2 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:339`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 8c00bd45ef..699c73fe2c 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:359`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 825f54b077..78a30bd4e1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:339`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 5a7484a378..3c09ef2e7f 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -41,6 +41,15 @@ const INACTIVE_STATES: ReadonlySet = new Set([ FiberState.FAILED, ]) +/** Render an arbitrary thrown value without letting coercion escape containment. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true @@ -422,16 +431,16 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { - this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${String(error)}`) + this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { try { const returned: unknown = callback(...args) void Promise.resolve(returned).catch((listenerError: unknown) => { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener rejected: ${renderThrown(listenerError)}`) }) } catch (listenerError: unknown) { - this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${String(listenerError)}`) + this.ctx.logger.warn(`agent "${configId}": config-start-failed listener threw: ${renderThrown(listenerError)}`) } } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index a7292b2284..b35dc71739 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -128,6 +128,42 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('contains startup and observer failures whose string coercion throws', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-unrenderable-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const unrenderable = { + [Symbol.toPrimitive](): never { + throw new Error('coercion escaped') + }, + } + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', () => { throw unrenderable }) + // Deliberately violate the normal Error-only rejection rule to exercise the unknown boundary. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + ctx.on('agent-loop/config-start-failed', () => Promise.reject(unrenderable) as never) + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + vi.spyOn(ctx.sessionPersistence, 'list').mockRejectedValue(unrenderable) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + + await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-unrenderable'), model: 'mock' }], + }) + + await expect.poll(() => failures).toEqual([unrenderable]) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-driven restore of "stdio-exact-unrenderable" failed: ', + ) + expect(warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener threw: ', + ) + await expect.poll(() => warn).toHaveBeenCalledWith( + 'agent "main": config-start-failed listener rejected: ', + ) + await ctx.fiber.dispose() + }) + it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) dirs.push(root) From 287041e39e93b368646f0fe8298b65feab692acc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:35:25 +0800 Subject: [PATCH 073/323] fix: preserve malformed snapshot fixtures --- packages/support/acp-snapshot/src/suite.ts | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 4d87093c8a..906521c42d 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -486,8 +486,10 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { const entries = await readdir(dir, { withFileTypes: true }) await Promise.all(entries .filter(entry => entry.isFile() - && entry.name.startsWith('session.') - && entry.name.endsWith('.jsonl') + // Only valid numbered children are record-owned stale output. + // Malformed session-like names stay for the inventory guard to + // reject instead of being silently deleted during mutation. + && /^session\.[1-9]\d*\.jsonl$/.test(entry.name) && !outputNames.has(entry.name)) .map(entry => rm(join(dir, entry.name)))) fixtureFiles = outputFixtureFiles From 2027c70a17661fe2b8b5aab1685cd443ac2c3b56 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:38:32 +0800 Subject: [PATCH 074/323] fix: drain failed ACP launches --- packages/support/acp-snapshot/src/launcher.ts | 4 +++- packages/support/acp-snapshot/tests/harness.spec.ts | 9 +++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 3f9a21d596..30ca0b42b8 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -178,13 +178,14 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.all([stdioClosed, client.closed]).then(async () => { + const drained = Promise.allSettled([stdioClosed, client.closed]).then(async ([, clientResult]) => { // The ACP SDK's readable loop dispatches client callbacks without awaiting // them. Once `closed` settles no new callbacks can start, but callbacks // already in flight still belong to this launch's teardown boundary. while (inFlightClientCallbacks.size > 0) { await Promise.allSettled([...inFlightClientCallbacks]) } + if (clientResult.status === 'rejected') throw clientResult.reason }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the @@ -206,6 +207,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe try { await spawned } catch (error: unknown) { + await drained.catch(() => undefined) closeUpdateStream() throw error } diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index ff7c304121..6adb0d4268 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -62,8 +62,17 @@ describe('runScenario', () => { it('surfaces an asynchronous child spawn failure through startup and close', async () => { const { dir } = await scenario({}) const launched = launchAcpTestAgent({ agent: AGENT, cwd: join(dir, 'missing') }) + let stdioClosed = false + let clientClosed = false + launched.child.once('close', () => { stdioClosed = true }) + void launched.client.closed.then( + () => { clientClosed = true }, + () => { clientClosed = true }, + ) await expect(launched.spawned).rejects.toMatchObject({ code: 'ENOENT' }) await expect(launched.close()).rejects.toMatchObject({ code: 'ENOENT' }) + expect(stdioClosed).toBe(true) + expect(clientClosed).toBe(true) }) it('centralizes ACP boot, captures, updates, fail-closed permissions, and shutdown', { timeout: 20_000 }, async () => { From 9f9f83c11f0ba190da488156efb015e3f7d921f4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:40:22 +0800 Subject: [PATCH 075/323] docs: align compaction output contract --- packages/compact/compact/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index fafcad76b8..adad9cfdfa 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -10,7 +10,7 @@ This package is the interface tier of the compaction capability, split so each c | `@deepseek-ai/dsh-compact-basic` (deferred) | a backend: chars-per-token estimation (`charsPerToken`, default 4) + token-budget retention + `llm.stream()` summarization | | `@deepseek-ai/dsh-tool-compact` (deferred) | the model-facing `/compact` tool over `ctx.compact` | -Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). +Unlike the bash seam, this interface depends on `@deepseek-ai/dsh-session` and `@deepseek-ai/dsh-llm` — the contract's verbs are defined over a `Session`, and its durable `compact/summary` event uses the `ContentBlock` vocabulary, so they cannot be expressed without naming those packages. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). ## Service API (`ctx.compact`) From b47e4c5276604dd1e5a400f5f60d2c16e195df10 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 12:45:12 +0800 Subject: [PATCH 076/323] fix: suppress teardown startup failures --- docs/architecture.md | 2 +- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 4 ++-- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 4 +++- packages/core/agent-loop/tests/config-session-id.spec.ts | 5 ++++- 8 files changed, 14 insertions(+), 9 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 41ab5c716b..0eb7f1fe55 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -56,7 +56,7 @@ Default loop processing remains exposed through plugin-visible services and even A **session** is an append-only event log. A **turn** drains queued input until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. -Startup resolves one identity. No id mints `-session-`; `sessionId` resumes stored or creates; `resumeSessionId` requires history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject buffered work. +Startup resolves identity. No id mints `-session-`; `sessionId` resumes or creates; `resumeSessionId` requires history. Active failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject work; teardown stays silent. ### Turn Flow diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 484ba1c632..173806572a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index e44df3c3b2..df3aec8b12 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -179,13 +179,13 @@ Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/t ### `agent-loop/config-start-failed` — emit -A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. +A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt. ```ts cordis-catalog 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 965a640966..74496739e2 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 78a30bd4e1..cc155ebb16 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2593da7c47..e27e8b625a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3c09ef2e7f..06c108d324 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -340,7 +340,8 @@ declare module 'cordis' { /** * A declarative agent entry failed before it could publish a live agent. * Consumers that buffer work for the configured identity use this - * transient signal to reject that work instead of waiting forever. + * transient signal to reject that work instead of waiting forever. Normal + * factory teardown suppresses failures from the cancelled startup attempt. * @param sessionId - exact shared agent/session identity that failed startup. * @param error - persistence, setup, or publication failure. * @mode emit @@ -431,6 +432,7 @@ export class AgentLoop extends Service implements AgentFactory { sessionId: SessionId, error: unknown, ): void { + if (!this.ownership.isActive()) return this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`) const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error] for (const callback of this.ctx.events.dispatch('emit', args)) { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index b35dc71739..53782fe03c 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -172,6 +172,8 @@ describe('config-driven session id', () => { const listing = Promise.withResolvers>>() vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) const loop = await ctx.plugin(AgentLoop, { agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], @@ -181,9 +183,10 @@ describe('config-driven session id', () => { await Promise.resolve() expect(disposed).toBe(false) - listing.resolve([]) + listing.reject(new Error('startup cancelled by teardown')) await disposal expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) expect(warn).not.toHaveBeenCalled() warn.mockRestore() await ctx.fiber.dispose() From 1f2c85c854985384febdf6829cc3d9eb2181b3ed Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 13:47:44 +0800 Subject: [PATCH 077/323] test: await fresh stdio agent publication --- packages/ui/stdio-agent/tests/stdio-agent.spec.ts | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index a14848a549..4d555f5965 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -85,6 +85,7 @@ describe('dsh-stdio-agent app', () => { expect(ctx.get('tools')?.get('ask_user_question')).toBeDefined() // The sole pre-created agent the UI drives. `main` is its stable config // label; each fresh process mints a durable combined agent/session id. + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent).toBeDefined() expect(agent?.id).toBe(agent?.session.id) @@ -100,6 +101,7 @@ describe('dsh-stdio-agent app', () => { persistenceRoot: '/tmp/dsh-stdio-agent-spec-empty-resume', skills: await isolatedSkillsConfig(), }) + await expect.poll(() => ctx.get('agents')?.list()).toHaveLength(1) const agent = ctx.get('agents')?.list()[0] expect(agent?.id).toMatch(/^main-session-[0-9a-f-]{36}$/) expect(agent?.id).toBe(agent?.session.id) From 628006889e07846af0816a127683b3e5aa5f2b5c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 13:51:21 +0800 Subject: [PATCH 078/323] docs: keep agent-loop map concise --- docs/architecture.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/architecture.md b/docs/architecture.md index 0e83cba072..89bb27604b 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -17,7 +17,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | | `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | -| `ctx.agentLoop` | `dsh-agent-loop` | shipped concrete `Agent` driver | +| `ctx.agentLoop` | `dsh-agent-loop` | concrete `Agent` driver | ### Capability Services From bb40259083f10cb2071c024f05810c74021e4035 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:11:33 +0800 Subject: [PATCH 079/323] test: preserve ACP cleanup failures --- examples/acp-agent/tests/acp.e2e.ts | 18 ++++------ examples/acp-agent/tests/cleanup.e2e.ts | 38 ++++++++++++++++++++++ examples/acp-agent/tests/cleanup.ts | 23 +++++++++++++ examples/acp-agent/tests/escalation.e2e.ts | 18 ++++------ examples/acp-agent/tests/hooks.e2e.ts | 18 ++++------ 5 files changed, 82 insertions(+), 33 deletions(-) create mode 100644 examples/acp-agent/tests/cleanup.e2e.ts create mode 100644 examples/acp-agent/tests/cleanup.ts diff --git a/examples/acp-agent/tests/acp.e2e.ts b/examples/acp-agent/tests/acp.e2e.ts index a1ddbeccc6..a0bfc9d943 100644 --- a/examples/acp-agent/tests/acp.e2e.ts +++ b/examples/acp-agent/tests/acp.e2e.ts @@ -1,4 +1,4 @@ -import { mkdtemp, rm, readFile } from 'node:fs/promises' +import { mkdtemp, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -9,6 +9,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * End-to-end: boot examples/acp-agent as a real subprocess speaking ACP over @@ -31,16 +32,11 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe('acp-agent over real stdio (no key required)', () => { diff --git a/examples/acp-agent/tests/cleanup.e2e.ts b/examples/acp-agent/tests/cleanup.e2e.ts new file mode 100644 index 0000000000..1f6e6493e0 --- /dev/null +++ b/examples/acp-agent/tests/cleanup.e2e.ts @@ -0,0 +1,38 @@ +/** Regression coverage for ACP example teardown. */ + +import { access, mkdtemp, rm } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it, vi } from 'vitest' +import { cleanupAcpExampleTest } from './cleanup.ts' + +let fallbackWorkdir: string | undefined + +afterEach(async () => { + if (fallbackWorkdir !== undefined) await rm(fallbackWorkdir, { recursive: true, force: true }) + fallbackWorkdir = undefined +}) + +describe('cleanupAcpExampleTest', () => { + it('removes the workspace after process shutdown fails', async () => { + fallbackWorkdir = await mkdtemp(join(tmpdir(), 'acp-cleanup-')) + const closeFailure = new Error('close failed') + const spawned = { close: vi.fn().mockRejectedValue(closeFailure) } + + await expect(cleanupAcpExampleTest(spawned, fallbackWorkdir)) + .rejects.toMatchObject({ errors: [closeFailure] }) + await expect(access(fallbackWorkdir)).rejects.toThrow() + fallbackWorkdir = undefined + }) + + it('reports process and workspace failures together', async () => { + const closeFailure = new Error('close failed') + const spawned = { close: vi.fn().mockRejectedValue(closeFailure) } + + const failure = await cleanupAcpExampleTest(spawned, '\0').catch((error: unknown) => error) + + expect(failure).toBeInstanceOf(AggregateError) + expect((failure as AggregateError).errors).toHaveLength(2) + expect((failure as AggregateError).errors[0]).toBe(closeFailure) + }) +}) diff --git a/examples/acp-agent/tests/cleanup.ts b/examples/acp-agent/tests/cleanup.ts new file mode 100644 index 0000000000..28a896334a --- /dev/null +++ b/examples/acp-agent/tests/cleanup.ts @@ -0,0 +1,23 @@ +/** Shared teardown for ACP example tests. */ + +import { rm } from 'node:fs/promises' +import type { LaunchedAcpTestAgent } from '@deepseek-ai/dsh-acp-snapshot' + +/** + * Close the test agent, then remove its workspace, attempting both operations + * and reporting every failure instead of allowing the later one to mask the + * earlier one. + */ +export async function cleanupAcpExampleTest( + spawned: Pick | undefined, + workdir: string | undefined, +): Promise { + const results: PromiseSettledResult[] = [] + if (spawned !== undefined) results.push(...await Promise.allSettled([spawned.close('SIGKILL')])) + if (workdir !== undefined) results.push(...await Promise.allSettled([rm(workdir, { recursive: true, force: true })])) + + const failures = results + .filter((result): result is PromiseRejectedResult => result.status === 'rejected') + .map(result => result.reason as unknown) + if (failures.length > 0) throw new AggregateError(failures, 'ACP example cleanup failed') +} diff --git a/examples/acp-agent/tests/escalation.e2e.ts b/examples/acp-agent/tests/escalation.e2e.ts index da8d3408c2..3b84dd721c 100644 --- a/examples/acp-agent/tests/escalation.e2e.ts +++ b/examples/acp-agent/tests/escalation.e2e.ts @@ -1,5 +1,5 @@ import { spawnSync } from 'node:child_process' -import { mkdtemp, readFile, rm } from 'node:fs/promises' +import { mkdtemp, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -13,6 +13,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * The default ACP composition (`cordis.yml`) end to end. @@ -81,16 +82,11 @@ let spawned: Spawned | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe('default sandbox composition keyless smoke (real cordis.yml via the Loader)', () => { diff --git a/examples/acp-agent/tests/hooks.e2e.ts b/examples/acp-agent/tests/hooks.e2e.ts index df231184c3..dbe98ab358 100644 --- a/examples/acp-agent/tests/hooks.e2e.ts +++ b/examples/acp-agent/tests/hooks.e2e.ts @@ -1,4 +1,4 @@ -import { mkdtemp, rm, writeFile, access } from 'node:fs/promises' +import { mkdtemp, writeFile, access } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' @@ -9,6 +9,7 @@ import { type AgentUnderTest, type LaunchedAcpTestAgent, } from '@deepseek-ai/dsh-acp-snapshot' +import { cleanupAcpExampleTest } from './cleanup.ts' /** * With-key e2e: the Claude Code hook bridge running against the REAL acp-agent @@ -38,16 +39,11 @@ let spawned: LaunchedAcpTestAgent | undefined let workdir: string | undefined afterEach(async () => { - try { - await spawned?.close('SIGKILL') - } finally { - spawned = undefined - try { - if (workdir !== undefined) await rm(workdir, { recursive: true, force: true }) - } finally { - workdir = undefined - } - } + const ownedSpawned = spawned + const ownedWorkdir = workdir + spawned = undefined + workdir = undefined + await cleanupAcpExampleTest(ownedSpawned, ownedWorkdir) }) describe.skipIf(!process.env.DEEPSEEK_API_KEY)('acp-agent e2e: a PreToolUse hook blocks bash (real model)', () => { From b58cf7ec2fdb3ba7d88ec097766dd47f2a188a2a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 14:24:21 +0800 Subject: [PATCH 080/323] fix: coordinate overlapping configured reloads --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 2 +- docs/event-producer-consumer.md | 2 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 35 +++++++++++++++ .../tests/config-session-id.spec.ts | 44 +++++++++++++++++++ packages/ui/stdio-agent/src/stdio-chat.ts | 13 +++++- .../ui/stdio-agent/tests/stdio-chat.spec.ts | 12 +++-- 9 files changed, 103 insertions(+), 11 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 173806572a..9bebe62380 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -131,7 +131,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:361`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index df3aec8b12..f913b95c36 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -185,7 +185,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:356`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d3e8b74edf..e4e68fe17f 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:376`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index cc155ebb16..2b62ec93eb 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:356`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index e27e8b625a..881d60027a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -41,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. An overlapping remount waits for an already-disposed same-id agent to finish detaching both registries before it inspects persistence, so asynchronous teardown cannot strand the configured identity. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 06c108d324..3274e36587 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -53,6 +53,7 @@ function renderThrown(value: unknown): string { /** Factory-level ownership of every preparing or live transaction. */ class FactoryOwnership { private accepting = true + private readonly inactive = Promise.withResolvers() private transactions = new Set() private startupTasks = new Set>() @@ -74,8 +75,14 @@ class FactoryOwnership { void task.then(forget, forget) } + /** Resolve `task`, or stop waiting when factory teardown begins. */ + async waitWhileActive(task: Promise): Promise { + await Promise.race([task, this.inactive.promise]) + } + async dispose(): Promise { this.accepting = false + this.inactive.resolve() const reason = new Error('agent loop is not active') await Promise.all([ ...[...this.transactions].map(transaction => transaction.disposeForFactory(reason)), @@ -455,6 +462,8 @@ export class AgentLoop extends Service implements AgentFactory { agentOptions: AgentOptions, meta: Pick, ): Promise { + await this.waitForDrainingConfiguredIdentity(ownerCtx, sessionId) + if (!this.ownership.isActive()) return const exists = (await persistence.list()).some(header => header.id === sessionId) if (!this.ownership.isActive()) return if (exists) { @@ -464,6 +473,32 @@ export class AgentLoop extends Service implements AgentFactory { this.create(sessionId, agentOptions, meta) } + /** Wait for an already-disposed same-id lifecycle to finish registry teardown. */ + private async waitForDrainingConfiguredIdentity(ownerCtx: Context, sessionId: SessionId): Promise { + const current = ownerCtx.agents.get(sessionId) + if (current?.status !== 'disposed') return + + const released = Promise.withResolvers() + const checkReleased = (): void => { + if (ownerCtx.agents.get(sessionId) === undefined && ownerCtx.sessions.get(sessionId) === undefined) { + released.resolve() + } + } + const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { + if (agent.id === sessionId) checkReleased() + }) + const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { + if (session.id === sessionId) checkReleased() + }) + try { + checkReleased() + await this.ownership.waitWhileActive(released.promise) + } finally { + disposeAgentListener() + disposeSessionListener() + } + } + /** * Create an agent and session under one caller-supplied identity, owned by * the accessing fiber. Constructor-driven config calls mint a fresh combined diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 53782fe03c..fda5681c29 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -92,6 +92,50 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('waits for a draining exact-id lifecycle during an overlapping reload', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-overlap-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-overlap') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + let flushStarted = false + ctx.on('session/flush', (session) => { + if (session !== first.session) return + flushStarted = true + return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before replacement' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + expect(flushStarted).toBe(true) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_id, error) => { failures.push(error) }) + const secondLoop = await ctx.plugin(AgentLoop, config) + await new Promise(resolve => setTimeout(resolve, 0)) + expect(ctx.agents.get(sessionId)).toBe(first) + expect(failures).toEqual([]) + + flushGate.resolve(undefined) + await firstDisposal + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const second = ctx.agents.get(sessionId) as ReactLoopAgent + expect(second).not.toBe(first) + expect(JSON.stringify(second.session.deriveMessages())).toContain('persist before replacement') + expect(failures).toEqual([]) + + await secondLoop.dispose() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) diff --git a/packages/ui/stdio-agent/src/stdio-chat.ts b/packages/ui/stdio-agent/src/stdio-chat.ts index 39d59dfdc0..4505f19b98 100644 --- a/packages/ui/stdio-agent/src/stdio-chat.ts +++ b/packages/ui/stdio-agent/src/stdio-chat.ts @@ -67,6 +67,15 @@ function isTTYPair(input: Readable, output: Writable): boolean { return Boolean((input as { isTTY?: boolean }).isTTY && (output as { isTTY?: boolean }).isTTY) } +/** Render an arbitrary failure without allowing hostile coercion to escape the UI boundary. */ +function renderThrown(value: unknown): string { + try { + return String(value) + } catch { + return '' + } +} + interface PendingQuestion { request: AskUserQuestionRequest questionIndex: number @@ -230,7 +239,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt queuedInput.length = 0 submittedWork = sawRunning if (dropped > 0) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${String(error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (${dropped} line(s)): ${renderThrown(error)}`) } maybeExit() }) @@ -390,7 +399,7 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt const text = line.trim() if (!text) return if (failedStartup !== undefined) { - ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${String(failedStartup.error)}`) + ctx.logger.error(`ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ${renderThrown(failedStartup.error)}`) return } const agent = target diff --git a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts index 11e64ac19c..c303577c48 100644 --- a/packages/ui/stdio-agent/tests/stdio-chat.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-chat.spec.ts @@ -83,6 +83,10 @@ function chunkEvent(chunk: StreamChunk): SessionEvent { const CONFIG: Config = { welcome: 'hi there', sessionId: 'main' } +function unrenderableFailure(): unknown { + return { [Symbol.toPrimitive](): never { throw new Error('coercion escaped') } } +} + async function setup(config: Config = CONFIG, runtimeOver: Partial = {}) { const ctx = new Context() await ctx.plugin(AgentRegistry) @@ -753,14 +757,14 @@ describe('createStdioChat input', () => { it('drops later input after the configured startup fails', async () => { const { ctx, input } = await setup() const error = vi.spyOn(ctx.logger, 'error').mockImplementation(() => {}) - const failure = new Error('persisted session is corrupt') + const failure = unrenderableFailure() ctx.emit('agent-loop/config-start-failed', SessionId('main'), failure) input.feed('cannot run') await new Promise(r => setImmediate(r)) expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: persisted session is corrupt', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) }) @@ -844,11 +848,11 @@ describe('createStdioChat EOF exit', () => { await flushExit() expect(exit).not.toHaveBeenCalled() - ctx.emit('agent-loop/config-start-failed', SessionId('main'), new Error('missing persisted session')) + ctx.emit('agent-loop/config-start-failed', SessionId('main'), unrenderableFailure()) await flushExit() expect(error).toHaveBeenCalledWith( - 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): Error: missing persisted session', + 'ui-stdio: main agent failed to start; dropped queued stdin (1 line(s)): ', ) expect(exit).toHaveBeenCalledWith(0) }) From 7e9bf9b951913b1c5d70b5e94e22ccd8f60bed76 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 15:03:01 +0800 Subject: [PATCH 081/323] refactor: remove impossible ACP drain branch --- packages/support/acp-snapshot/src/launcher.ts | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index 30ca0b42b8..c0dc21dc06 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -178,14 +178,13 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe // `closed` follows parser exhaustion. Capture both eagerly so a caller that // invokes close after process exit still joins the complete drain boundary. const stdioClosed = new Promise(resolve => child.once('close', () => { resolve() })) - const drained = Promise.allSettled([stdioClosed, client.closed]).then(async ([, clientResult]) => { + const drained = Promise.all([stdioClosed, client.closed]).then(async () => { // The ACP SDK's readable loop dispatches client callbacks without awaiting // them. Once `closed` settles no new callbacks can start, but callbacks // already in flight still belong to this launch's teardown boundary. while (inFlightClientCallbacks.size > 0) { await Promise.allSettled([...inFlightClientCallbacks]) } - if (clientResult.status === 'rejected') throw clientResult.reason }) // A caller may await a pending update without calling close(). Make natural // stream exhaustion terminal for those waiters too, but only after the @@ -207,7 +206,7 @@ export function launchAcpTestAgent(options: AcpTestLaunchOptions): LaunchedAcpTe try { await spawned } catch (error: unknown) { - await drained.catch(() => undefined) + await drained closeUpdateStream() throw error } From d83aa8d11aa217fdbee379dce37aa5146228dd21 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 15:31:00 +0800 Subject: [PATCH 082/323] test: cover exact-id reload cancellation --- packages/core/agent-loop/src/index.ts | 8 +- .../tests/config-session-id.spec.ts | 85 +++++++++++++------ 2 files changed, 62 insertions(+), 31 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 3274e36587..ff0c692928 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -484,12 +484,8 @@ export class AgentLoop extends Service implements AgentFactory { released.resolve() } } - const disposeAgentListener = ownerCtx.on('agent/disposed', (agent) => { - if (agent.id === sessionId) checkReleased() - }) - const disposeSessionListener = ownerCtx.on('session/disposed', (session) => { - if (session.id === sessionId) checkReleased() - }) + const disposeAgentListener = ownerCtx.on('agent/disposed', checkReleased) + const disposeSessionListener = ownerCtx.on('session/disposed', checkReleased) try { checkReleased() await this.ownership.waitWhileActive(released.promise) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index fda5681c29..ceaf6597cb 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -136,6 +136,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) + it('cancels an exact-id reload while the prior lifecycle is still draining', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-cancel-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const sessionId = SessionId('stdio-exact-cancel') + const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } + const firstLoop = await ctx.plugin(AgentLoop, config) + await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() + const first = ctx.agents.get(sessionId) as ReactLoopAgent + + const flushGate = Promise.withResolvers() + ctx.on('session/flush', (session) => { + if (session === first.session) return flushGate.promise + }) + first.inject([{ type: 'text', text: 'persist before cancellation' }], { + source: { kind: 'plugin', plugin: 'test' }, + }) + + const firstDisposal = firstLoop.dispose() + await expect.poll(() => first.status).toBe('disposed') + const secondLoop = await ctx.plugin(AgentLoop, config) + await secondLoop.dispose() + expect(ctx.agents.get(sessionId)).toBe(first) + + flushGate.resolve(undefined) + await firstDisposal + expect(ctx.agents.get(sessionId)).toBeUndefined() + await ctx.fiber.dispose() + }) + it('contains an exact-id persistence lookup failure', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-failure-')) dirs.push(root) @@ -208,33 +239,37 @@ describe('config-driven session id', () => { await ctx.fiber.dispose() }) - it('joins an exact-id persistence lookup before AgentLoop disposal completes', async () => { - const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) - dirs.push(root) - const ctx = await makeCoreContext() - await ctx.plugin(SessionPersistenceJsonl, { root }) - const listing = Promise.withResolvers>>() - vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) - const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const failures: unknown[] = [] - ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) + it.each(['resolve', 'reject'] as const)( + 'joins an exact-id persistence lookup that will %s before AgentLoop disposal completes', + async (outcome) => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-dispose-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + const listing = Promise.withResolvers>>() + vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise) + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) + const failures: unknown[] = [] + ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) }) - const loop = await ctx.plugin(AgentLoop, { - agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], - }) - let disposed = false - const disposal = loop.dispose().then(() => { disposed = true }) - await Promise.resolve() - expect(disposed).toBe(false) + const loop = await ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }], + }) + let disposed = false + const disposal = loop.dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) - listing.reject(new Error('startup cancelled by teardown')) - await disposal - expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() - expect(failures).toEqual([]) - expect(warn).not.toHaveBeenCalled() - warn.mockRestore() - await ctx.fiber.dispose() - }) + if (outcome === 'resolve') listing.resolve([]) + else listing.reject(new Error('startup cancelled by teardown')) + await disposal + expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined() + expect(failures).toEqual([]) + expect(warn).not.toHaveBeenCalled() + warn.mockRestore() + await ctx.fiber.dispose() + }, + ) it('identity-nests the deferred resume fiber under its labeled owner effect', async () => { const ctx = new Context() From 4a5463cfc49b8f505b5f47aa7634909c08602a08 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 16:53:38 +0800 Subject: [PATCH 083/323] test: use the public agent type --- packages/core/agent-loop/tests/config-session-id.spec.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index f001fa3154..2c8a5c31bd 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -145,7 +145,7 @@ describe('config-driven session id', () => { const config = { agents: [{ id: 'main', sessionId, model: 'mock' }] } const firstLoop = await ctx.plugin(AgentLoop, config) await expect.poll(() => ctx.agents.get(sessionId)).toBeDefined() - const first = ctx.agents.get(sessionId) as ReactLoopAgent + const first = ctx.agents.get(sessionId) as Agent const flushGate = Promise.withResolvers() ctx.on('session/flush', (session) => { From 64a3933270a0f4636b36b485197597c66945599b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 19:03:07 +0800 Subject: [PATCH 084/323] docs: refresh config catalog after parent merge --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 14cc973995..6f74792213 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -899,7 +899,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) -Source: [`packages/subagent/tool-subagent/src/index.ts:24`](../packages/subagent/tool-subagent/src/index.ts) +Source: [`packages/subagent/tool-subagent/src/index.ts:47`](../packages/subagent/tool-subagent/src/index.ts) ## `@deepseek-ai/dsh-tool-web` From 5409452cc705804386fe029908f14b31840efe96 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 19:30:29 +0800 Subject: [PATCH 085/323] test: refresh snapshots after master merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/stdout.golden.jsonl | 2 +- .../snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/cancel/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/config-options/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/error-finish/stdout.golden.jsonl | 2 +- .../tests/snapshots/escalation-approved/session.jsonl | 4 ++-- .../tests/snapshots/escalation-approved/stdout.golden.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/session.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/stdout.golden.jsonl | 4 ++-- .../acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-policy-reject/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-read-window/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-terminal-card/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-write-overwrite/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/handshake/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-block/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-context/stdout.golden.jsonl | 2 +- .../tests/snapshots/hook-cc-pretool-ask/session.jsonl | 4 ++-- .../tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-pretool-deny/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-stop-continue/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-posttool-block/stdout.golden.jsonl | 2 +- .../hook-codex-posttool-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-pretool-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-stop-continue/stdout.golden.jsonl | 2 +- .../tests/snapshots/multi-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/permission-switching/session.jsonl | 2 +- .../snapshots/permission-switching/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/repeat-tool-guard/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- .../tests/snapshots/skill-load/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-fork/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-mixed/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-multi/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-spawn/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- .../acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl | 2 +- .../tests/snapshots/tool-call-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/workflow-run/stdout.golden.jsonl | 2 +- .../tests/snapshots/workspace-edit/stdout.golden.jsonl | 2 +- 55 files changed, 64 insertions(+), 64 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 991806d74b..cdc09c92c0 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index a6a3371913..79d9b94ad9 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index c6213cd558..7155b1c2a6 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl index bc4da17bb0..80a9cc9339 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 5ad12cddff..6e8f157ace 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index a68bb37f9f..66cdecedfb 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl index 577f10445b..c9d2c87c27 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl index 60235cac75..1f8c0ca024 100644 --- a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl index bfa379815e..5fe0944ac7 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl index aa033fb673..7c85717676 100644 --- a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown permission value \"plan\""}} {"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl index d5d4f1c400..99e00460c6 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 8aac1627bc..74fbed6ee3 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -131,8 +131,8 @@ {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"daa6d214-9e99-4cb6-b4f7-7f6086379133","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"daa6d214-9e99-4cb6-b4f7-7f6086379133","outcome":"allowed-once"}} {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl index f438444dc4..5c63764aae 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index 7c0a743413..bf86999cd9 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -155,8 +155,8 @@ {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"9e6c7946-af56-4535-9cce-993e0165c2f9","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"71281495-1503-47de-bbdf-11d5de1e5f06","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"71281495-1503-47de-bbdf-11d5de1e5f06","outcome":"rejected"}} {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl index b926355bd7..07e48d9e22 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl index acc193ad1e..919c0f169e 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl index 5aa75c026c..c27544a176 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl index 05832400c8..8b75c30e8c 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl index 19abb7f418..30aa0d2460 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl index 0e7dcca6f8..e045c7b228 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl index 4801d9410d..f554fa3123 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl index d5b3ca5d15..d04def6af2 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl index e4c4984fc5..312569a491 100644 --- a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl @@ -1,2 +1,2 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl index 0a93b649da..36f050a694 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl index e9243d8a05..bbc16779ba 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index b975c54aac..faed620b4c 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,8 +55,8 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","outcome":"rejected"}} {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl index 3905e82ca7..db38650167 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl index 92906adb59..f0c5e005d9 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl index 6304582220..5d88350cad 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl index c4ad3ba541..ac203d50cc 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl index 5c4a564d26..01297aa39d 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index cbaec45f9f..57b297ccfc 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl index 4bf92f3197..faa1255a32 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl index 5459da1a17..11b47d6e58 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl index 6304582220..5d88350cad 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl index 8cae81a5c9..116a8ebbbd 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl index 66d8c816be..d231f60e0a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl index 1d9d45954a..b45d9e947c 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 0d8e018ae5..a30f9e4a46 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl index 651897e850..9c3c78be5c 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -44,7 +44,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl index a0901b6297..876f6c490a 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_1","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 9a26fa2efe..1c85ee81ba 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl index 10198918d6..b5f25f2c07 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl index 44fc4402fc..e390bda86a 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl index 08ad14dc9c..db5f28fa79 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl index 93b38e33cb..4c0c7d2601 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl index 26d45699cc..ce114fccf0 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 0643740e4f..c66f5676cc 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl index 1059a9cc6c..8de447de6d 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl index f060b6b92f..a947ed4997 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl index 041ea02703..9d06e9d6ac 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl index 9c0bbd37be..56b8f3537a 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl index 23f13ff3c2..513a02a6af 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} From 2dc62497ceb19edfd55a8afb9c2198dd60d6a3bc Mon Sep 17 00:00:00 2001 From: kingwl Date: Tue, 14 Jul 2026 20:05:57 +0800 Subject: [PATCH 086/323] =?UTF-8?q?feat(sandbox):=20cross-family=20file=20?= =?UTF-8?q?sandbox=20=E2=80=94=20one=20policy=20home,=20sandboxed=20fs=20p?= =?UTF-8?q?rovider,=20fs=20escalation=20parity?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extend SandboxMode enforcement from bash to the filesystem tools, the sandbox RFC's deferred cross-family phase. - dsh-sandbox-policy (new, ctx.sandboxPolicy): the single home for the deployment default mode + workspaceRoot and the per-session override event, renamed bash/sandbox-mode -> sandbox/mode and moved here with its fold/setter. Decouples the bash seam from dsh-session. - dsh-fs-sandbox (new): SandboxedFileSystem extends LocalFileSystem and fences write/edit by the per-call mode (read-only denies, workspace-write contains to the workspace + temp roots via the shared writableRoots, danger passes through); reads pass through. Structured FS_SANDBOX_DENIED; in-lock parent re-canonicalization. A policy fence in trusted code, not a kernel boundary. - dsh-sandbox: the shared escalation kit (writableRoots, the strictly-wider ladder, denial/hint markers, approveEscalation) both tool families use; approveEscalation takes a structural approver so dsh-sandbox gains no approval/agent dependency, and both tools stay duplication-free. - tool-fs: write/edit advertise sandbox_permissions/justification under a confining ctx.fs, map FS_SANDBOX_DENIED to the shared [sandbox: ...] marker, and resolve the same one-approved-wider retry. - examples/acp-agent: composes sandbox-policy + fs-sandbox, drops the gating that disabled the fs stack under confined modes. RFC docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md; the old sandbox RFC's In-process/deferred/FAQ sections updated to shipped fact. --- docs/architecture.md | 1 + docs/capability-seams.md | 11 +- docs/config-catalog.md | 74 ++++-- docs/cordis-catalog/events.md | 6 +- docs/cordis-catalog/services.md | 20 +- docs/core-data-structures/filesystem.md | 3 +- docs/event-producer-consumer.md | 6 +- docs/module-graph.md | 49 ++-- docs/persistence-catalog.md | 28 +-- docs/rfc/INDEX.md | 1 + .../implemented/feature/2026-07-06-sandbox.md | 13 +- .../2026-07-14-cross-family-fs-sandbox.md | 92 +++++++ examples/acp-agent/composition.md | 9 +- examples/acp-agent/cordis.yml | 33 +-- .../advanced-toolchain/session.1.jsonl | 2 +- .../advanced-toolchain/session.2.jsonl | 2 +- .../advanced-toolchain/session.jsonl | 2 +- .../system-prompt.golden.md | 41 ++++ .../snapshots/both-mode-turn/session.jsonl | 2 +- .../both-mode-turn/system-prompt.golden.md | 41 ++++ .../code-mode-turn/system-prompt.golden.md | 41 ++++ .../escalation-approved/session.jsonl | 6 +- .../escalation-rejected/session.jsonl | 6 +- .../tests/snapshots/fs-edit/session.jsonl | 4 +- .../snapshots/fs-edit/stdout.golden.jsonl | 8 +- .../snapshots/fs-policy-reject/session.jsonl | 6 +- .../fs-policy-reject/stdout.golden.jsonl | 12 +- .../snapshots/fs-read-window/session.jsonl | 2 +- .../fs-read-window/stdout.golden.jsonl | 4 +- .../tests/snapshots/fs-read/session.jsonl | 2 +- .../snapshots/fs-read/stdout.golden.jsonl | 4 +- .../fs-write-overwrite/session.jsonl | 4 +- .../fs-write-overwrite/stdout.golden.jsonl | 8 +- .../tests/snapshots/fs-write/session.jsonl | 2 +- .../snapshots/fs-write/stdout.golden.jsonl | 4 +- .../hook-cc-pretool-ask/session.jsonl | 4 +- .../permission-switching/session.jsonl | 8 +- .../system-prompt.golden.md | 8 +- .../tests/snapshots/skill-load/session.jsonl | 2 +- .../skill-load/system-prompt.golden.md | 6 + .../tests/snapshots/text-turn/session.jsonl | 2 +- .../text-turn/system-prompt.golden.md | 6 + .../snapshots/workspace-edit/session.jsonl | 2 +- .../workspace-edit/stdout.golden.jsonl | 4 +- packages/bash/bash-sandbox/package.json | 5 +- packages/bash/bash-sandbox/src/index.ts | 51 ++-- packages/bash/bash-sandbox/tests/bwrap.e2e.ts | 4 +- .../bash/bash-sandbox/tests/landlock.e2e.ts | 4 +- .../bash/bash-sandbox/tests/sandbox.spec.ts | 27 ++- .../bash/bash-sandbox/tests/seatbelt.e2e.ts | 4 +- packages/bash/bash-sandbox/tsconfig.json | 6 +- packages/bash/bash/package.json | 2 - packages/bash/bash/src/index.ts | 1 - packages/bash/bash/src/types.ts | 2 +- packages/bash/bash/tsconfig.json | 3 - packages/bash/tool-bash/package.json | 3 +- packages/bash/tool-bash/src/index.ts | 124 +++------- packages/bash/tool-bash/tests/tools.spec.ts | 15 +- packages/bash/tool-bash/tsconfig.json | 6 +- .../cordis/tool-cordis/src/api-catalog.ts | 9 +- packages/fs/README.md | 5 +- packages/fs/fs-sandbox/README.md | 19 ++ packages/fs/fs-sandbox/package.json | 38 +++ packages/fs/fs-sandbox/src/index.ts | 155 ++++++++++++ .../fs/fs-sandbox/tests/fs-sandbox.spec.ts | 224 ++++++++++++++++++ packages/fs/fs-sandbox/tsconfig.json | 30 +++ packages/fs/fs/package.json | 2 + packages/fs/fs/src/index.ts | 39 ++- packages/fs/fs/src/types.ts | 1 + packages/fs/fs/tsconfig.json | 3 +- packages/fs/tool-fs/package.json | 6 + packages/fs/tool-fs/src/edit.ts | 43 +++- packages/fs/tool-fs/src/index.ts | 12 +- packages/fs/tool-fs/src/sandbox.ts | 132 +++++++++++ packages/fs/tool-fs/src/write.ts | 32 ++- packages/fs/tool-fs/tests/tools.spec.ts | 162 +++++++++++++ packages/fs/tool-fs/tsconfig.json | 5 +- packages/sandbox/README.md | 7 +- packages/sandbox/sandbox-policy/README.md | 23 ++ packages/sandbox/sandbox-policy/package.json | 37 +++ packages/sandbox/sandbox-policy/src/index.ts | 84 +++++++ .../sandbox-policy}/src/session-mode.ts | 47 ++-- .../sandbox-policy/tests/policy.spec.ts | 67 ++++++ packages/sandbox/sandbox-policy/tsconfig.json | 27 +++ packages/sandbox/sandbox/src/escalation.ts | 189 +++++++++++++++ packages/sandbox/sandbox/src/index.ts | 11 + packages/sandbox/sandbox/src/roots.ts | 51 ++++ .../sandbox/sandbox/tests/escalation.spec.ts | 111 +++++++++ packages/sandbox/sandbox/tests/roots.spec.ts | 39 +++ packages/ui/acp/tests/config-options.spec.ts | 10 +- packages/ui/permission/package.json | 2 + packages/ui/permission/src/index.ts | 11 +- .../ui/permission/tests/permission.spec.ts | 10 +- packages/ui/permission/tsconfig.json | 3 + pnpm-lock.yaml | 109 ++++++--- python/sdk-runtime/package.json | 1 + scripts/doc-budgets.manifest.json | 2 +- scripts/gen-doc-graphs.ts | 13 +- tsconfig.build.json | 2 + tsconfig.json | 2 + 100 files changed, 2238 insertions(+), 385 deletions(-) create mode 100644 docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md create mode 100644 packages/fs/fs-sandbox/README.md create mode 100644 packages/fs/fs-sandbox/package.json create mode 100644 packages/fs/fs-sandbox/src/index.ts create mode 100644 packages/fs/fs-sandbox/tests/fs-sandbox.spec.ts create mode 100644 packages/fs/fs-sandbox/tsconfig.json create mode 100644 packages/fs/tool-fs/src/sandbox.ts create mode 100644 packages/sandbox/sandbox-policy/README.md create mode 100644 packages/sandbox/sandbox-policy/package.json create mode 100644 packages/sandbox/sandbox-policy/src/index.ts rename packages/{bash/bash => sandbox/sandbox-policy}/src/session-mode.ts (52%) create mode 100644 packages/sandbox/sandbox-policy/tests/policy.spec.ts create mode 100644 packages/sandbox/sandbox-policy/tsconfig.json create mode 100644 packages/sandbox/sandbox/src/escalation.ts create mode 100644 packages/sandbox/sandbox/src/roots.ts create mode 100644 packages/sandbox/sandbox/tests/escalation.spec.ts create mode 100644 packages/sandbox/sandbox/tests/roots.spec.ts diff --git a/docs/architecture.md b/docs/architecture.md index 8dc7f6f4b1..7483caf040 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -26,6 +26,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.llm` | [`llm/`](../packages/llm/README.md) | adapter registry and streaming model calls | | `ctx.bash` | [`bash/`](../packages/bash/README.md) | foreground/background command execution | | `ctx.sandbox` | [`sandbox/`](../packages/sandbox/README.md) | same-world process confinement (argv wrapping, per-call policy) | +| `ctx.sandboxPolicy` | [`sandbox/`](../packages/sandbox/README.md) | shared sandbox policy: mode, workspace root, per-session override | | `ctx.codeRuntime` | [`code-runtime/`](../packages/code-runtime/README.md) | model-written program execution | | `ctx.fs` | [`fs/`](../packages/fs/README.md) | filesystem provider primitives and policy events | | `ctx.skills` | [`skill/`](../packages/skill/README.md) | skill provider registry and progressive disclosure | diff --git a/docs/capability-seams.md b/docs/capability-seams.md index fb4746dc68..c683b59283 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -56,6 +56,8 @@ flowchart LR pkg_sandbox["sandbox"] svc_sandbox["ctx.sandbox
Process-sandbox seam"] pkg_sandbox_local["sandbox-local"] + svc_sandboxPolicy["ctx.sandboxPolicy
Sandbox policy home"] + pkg_fs_sandbox["fs-sandbox"] pkg_approval["approval"] svc_approval["ctx.approval
Approval seam"] pkg_permission["permission"] @@ -99,12 +101,14 @@ flowchart LR pkg_compact_basic --> svc_compact pkg_fs --> svc_fs pkg_fs_local --> svc_fs + pkg_fs_sandbox --> svc_fs pkg_llm --> svc_llm pkg_llm_deepseek --> svc_llm pkg_llm_pi_ai --> svc_llm pkg_llm_replay --> svc_llm pkg_permission --> svc_permission pkg_sandbox --> svc_sandbox + pkg_sandbox --> svc_sandboxPolicy pkg_sandbox_local --> svc_sandbox pkg_session --> svc_sessions pkg_session_persistence --> svc_sessionPersistence @@ -147,6 +151,10 @@ flowchart LR svc_llm --> pkg_compact_basic svc_permission --> pkg_acp svc_sandbox --> pkg_bash_sandbox + svc_sandboxPolicy --> pkg_bash_sandbox + svc_sandboxPolicy --> pkg_fs_sandbox + svc_sandboxPolicy --> pkg_tool_bash + svc_sandboxPolicy --> pkg_tool_fs svc_sessionPersistence --> pkg_acp svc_sessionPersistence --> pkg_agent_loop svc_sessionPersistence --> pkg_session_query @@ -194,10 +202,11 @@ flowchart LR | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-core`](../packages/core/agent-core) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. | | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. | | `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. | +| `ctx.sandboxPolicy` | `core` | [`sandbox`](../packages/sandbox/sandbox) | - | [`bash-sandbox`](../packages/bash/bash-sandbox), [`fs-sandbox`](../packages/fs/fs-sandbox), [`tool-bash`](../packages/bash/tool-bash), [`tool-fs`](../packages/fs/tool-fs) | - | The one home for the deployment default mode + workspace root and the per-session `sandbox/mode` override; both enforcing families read it so bash and fs cannot confine to different roots. | | `ctx.approval` | `seam` | `approval` | [`acp`](../packages/ui/acp) | [`tools`](../packages/core/tools), [`tool-bash`](../packages/bash/tool-bash) | - | One-shot permission decisions dispatched over the `approval/request` waterfall; answerers are listeners (the ACP bridge for its own agents), absence fails closed to `unavailable`. | | `ctx.permission` | `core` | [`permission`](../packages/ui/permission) | - | [`acp`](../packages/ui/acp) | - | User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events. | | `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). | -| `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate. | +| `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local), [`fs-sandbox`](../packages/fs/fs-sandbox) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-sandbox fences mutations by the shared sandbox mode; fs-policy contributes observed-state checks through the fs/* event gate. | | `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred. | | `ctx.subagents` | `seam` | [`subagent`](../packages/subagent/subagent) | [`subagent-spawn`](../packages/subagent/subagent-spawn), [`subagent-fork`](../packages/subagent/subagent-fork), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-mock`](../packages/support/subagent-mock) | [`tool-subagent`](../packages/subagent/tool-subagent) | - | Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name. | | `ctx.web` | `seam` | [`web`](../packages/web/web) | [`web-search-exa`](../packages/web/web-search-exa), [`web-search-perplexity`](../packages/web/web-search-perplexity), [`web-search-deepseek`](../packages/web/web-search-deepseek), [`web-fetch-local`](../packages/web/web-fetch-local) | [`tool-web`](../packages/web/tool-web) | - | Search and fetch providers register into one ctx.web seam; tool-web owns the stable model-facing names. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4492d413d8..c5e9346af6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -153,28 +153,21 @@ Source: [`packages/bash/bash-local/src/index.ts:29`](../packages/bash/bash-local ## `@deepseek-ai/dsh-bash-sandbox` -Requires: `sandbox` +Requires: `sandbox` · `sandboxPolicy` ```ts config-catalog /** - * Plugin config: the local executor's knobs plus the sandbox policy. All - * optional — `static Config` supplies the defaults (`mode: 'read-only'` is the - * fail-safe default; an example that wants a workspace-writable agent opts in - * explicitly). The runner choice is NOT configured here: which platform - * backend confines the command is the `ctx.sandbox` provider's config. + * Plugin config: the local executor's knobs, verbatim. The sandbox policy — + * the default mode and the `workspace-write` boundary root — is NOT here: it + * lives on `ctx.sandboxPolicy` (`@deepseek-ai/dsh-sandbox-policy`), the one + * home both enforcing families read, so bash and fs can never confine to + * different roots. The runner choice is likewise the `ctx.sandbox` provider's + * config, not this executor's. */ -export interface Config extends LocalConfig { - /** File-sandbox mode commands run under (default: `read-only`). */ - mode?: SandboxMode - /** - * Root directory `workspace-write` mode may write under (default: the - * executor's default working directory — `cwd`, else `process.cwd()`). - */ - workspaceRoot?: string -} +export type Config = LocalConfig ``` -Depends on: [`LocalConfig`](#deepseek-aidsh-bash-local) · [`SandboxMode`](core-data-structures/sandbox.md) +Depends on: [`LocalConfig`](#deepseek-aidsh-bash-local) Source: [`packages/bash/bash-sandbox/src/index.ts:60`](../packages/bash/bash-sandbox/src/index.ts) @@ -267,6 +260,24 @@ export interface Config { Source: [`packages/fs/fs-local/src/index.ts:58`](../packages/fs/fs-local/src/index.ts) +## `@deepseek-ai/dsh-fs-sandbox` + +Requires: `sandboxPolicy` + +```ts config-catalog +/** + * Plugin config: the local backend's knobs, verbatim (only `cwd`, the resolve + * base for relative paths). The sandbox default (mode + `workspace-write` + * boundary root) is NOT here — it lives on `ctx.sandboxPolicy`, the one home + * both enforcing families share. + */ +export type Config = LocalConfig +``` + +Depends on: [`LocalConfig`](#deepseek-aidsh-fs-local) + +Source: [`packages/fs/fs-sandbox/src/index.ts:49`](../packages/fs/fs-sandbox/src/index.ts) + ## `@deepseek-ai/dsh-hooks-claude` Requires: `bash` @@ -464,7 +475,7 @@ export interface Config { * runs under while the preset is active — plus its presentation. */ export interface PresetSpec { - /** The `bash/sandbox-mode` value the preset writes through. */ + /** The `sandbox/mode` value the preset writes through. */ sandbox: SandboxMode /** The `approval/policy` value the preset writes through. */ approval: ApprovalPolicy @@ -477,7 +488,7 @@ export interface PresetSpec { Depends on: [`ApprovalPolicy`](core-data-structures/approval.md) · [`SandboxMode`](core-data-structures/sandbox.md) -Source: [`packages/ui/permission/src/index.ts:97`](../packages/ui/permission/src/index.ts) +Source: [`packages/ui/permission/src/index.ts:100`](../packages/ui/permission/src/index.ts) ## `@deepseek-ai/dsh-repeat-tool-guard` @@ -558,6 +569,31 @@ export interface Config { Source: [`packages/sandbox/sandbox-local/src/index.ts:36`](../packages/sandbox/sandbox-local/src/index.ts) +## `@deepseek-ai/dsh-sandbox-policy` + +```ts config-catalog +/** + * Plugin config: the deployment's sandbox default. All optional — `Config` + * supplies the defaults (`mode: 'read-only'` is the fail-safe default; a + * deployment that wants a workspace-writable agent opts in explicitly). The + * runner choice is NOT here (it is the `ctx.sandbox` provider's config), nor + * is any per-family knob: this is the one shared policy home. + */ +export interface Config { + /** File-sandbox mode a session starts from (default: `read-only`). */ + mode?: SandboxMode + /** + * Absolute root directory `workspace-write` may write under (default: + * `process.cwd()`). Both enforcing families fence against this SAME root. + */ + workspaceRoot?: string +} +``` + +Depends on: [`SandboxMode`](core-data-structures/sandbox.md) + +Source: [`packages/sandbox/sandbox-policy/src/index.ts:44`](../packages/sandbox/sandbox-policy/src/index.ts) + ## `@deepseek-ai/dsh-session-persistence-jsonl` Requires: `sessions` @@ -900,7 +936,7 @@ export interface Config { } ``` -Source: [`packages/fs/tool-fs/src/index.ts:48`](../packages/fs/tool-fs/src/index.ts) +Source: [`packages/fs/tool-fs/src/index.ts:52`](../packages/fs/tool-fs/src/index.ts) ## `@deepseek-ai/dsh-tool-skill` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index acbd39b8fa..2600fe9cfc 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -201,7 +201,7 @@ Single-slot decision: produce the optional version guard for the next FileSystem Types: [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) -Source: [`packages/fs/fs/src/index.ts:123`](../../packages/fs/fs/src/index.ts) +Source: [`packages/fs/fs/src/index.ts:124`](../../packages/fs/fs/src/index.ts) ### `fs/observed` — emit @@ -213,7 +213,7 @@ Record that an actor observed a target at a version, after a successful read/wri Types: [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) -Source: [`packages/fs/fs/src/index.ts:138`](../../packages/fs/fs/src/index.ts) +Source: [`packages/fs/fs/src/index.ts:139`](../../packages/fs/fs/src/index.ts) ### `fs/write-intent` — waterfall @@ -225,7 +225,7 @@ Single-slot decision: produce the write intent for the next FileSystem.writeText Types: [FsTarget](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md) -Source: [`packages/fs/fs/src/index.ts:109`](../../packages/fs/fs/src/index.ts) +Source: [`packages/fs/fs/src/index.ts:110`](../../packages/fs/fs/src/index.ts) ## `llm/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index c399cf83d4..3d0087a129 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -79,7 +79,7 @@ onTaskDone(listener: BashTaskListener): () => void Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md) · [BashTask](../core-data-structures/bash.md) · [BashTaskRead](../core-data-structures/bash.md) -Source: [`packages/bash/bash/src/index.ts:62`](../../packages/bash/bash/src/index.ts) +Source: [`packages/bash/bash/src/index.ts:61`](../../packages/bash/bash/src/index.ts) ## `ctx.codeRuntime` — `CodeRuntime` (abstract seam) @@ -139,13 +139,13 @@ abstract stat(target: FsTarget, signal?: AbortSignal): Promise abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> abstract listDir(target: FsTarget, signal?: AbortSignal): Promise -abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise -abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise +abstract writeText( target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal, sandboxMode?: SandboxMode, ): Promise +abstract editText( target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal, sandboxMode?: SandboxMode, ): Promise ``` -Types: [FsEditOutcome](../core-data-structures/filesystem.md) · [FsEditRequest](../core-data-structures/filesystem.md) · [FsInfo](../core-data-structures/filesystem.md) · [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md) · [FsWriteOutcome](../core-data-structures/filesystem.md) +Types: [FsEditOutcome](../core-data-structures/filesystem.md) · [FsEditRequest](../core-data-structures/filesystem.md) · [FsInfo](../core-data-structures/filesystem.md) · [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md) · [FsWriteOutcome](../core-data-structures/filesystem.md) · [SandboxMode](../core-data-structures/sandbox.md) -Source: [`packages/fs/fs/src/index.ts:172`](../../packages/fs/fs/src/index.ts) +Source: [`packages/fs/fs/src/index.ts:173`](../../packages/fs/fs/src/index.ts) ## `ctx.llm` — `LlmService` @@ -174,7 +174,7 @@ set(session: Session, name: string): void Types: [SessionEvent](../core-data-structures/core.md) -Source: [`packages/ui/permission/src/index.ts:115`](../../packages/ui/permission/src/index.ts) +Source: [`packages/ui/permission/src/index.ts:118`](../../packages/ui/permission/src/index.ts) ## `ctx.sandbox` — `SandboxProvider` (abstract seam) @@ -192,7 +192,13 @@ abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv Types: [ConfinedArgv](../core-data-structures/sandbox.md) · [SandboxPolicy](../core-data-structures/sandbox.md) -Source: [`packages/sandbox/sandbox/src/index.ts:180`](../../packages/sandbox/sandbox/src/index.ts) +Source: [`packages/sandbox/sandbox/src/index.ts:191`](../../packages/sandbox/sandbox/src/index.ts) + +## `ctx.sandboxPolicy` — `SandboxPolicyService` + +The sandbox-policy service (`ctx.sandboxPolicy`). Owns the deployment default mode and workspace root; enforcing implementations read defaultMode and workspaceRoot, and the tool layers fold each session's `sandbox/mode` override with effectiveSandboxMode on top. + +Source: [`packages/sandbox/sandbox-policy/src/index.ts:60`](../../packages/sandbox/sandbox-policy/src/index.ts) ## `ctx.sessionPersistence` — `SessionPersistence` (abstract seam) diff --git a/docs/core-data-structures/filesystem.md b/docs/core-data-structures/filesystem.md index bbc55be966..80e3fa8e95 100644 --- a/docs/core-data-structures/filesystem.md +++ b/docs/core-data-structures/filesystem.md @@ -132,6 +132,7 @@ type FsErrorCode = | 'FS_NOT_TEXT' | 'FS_NOT_REGULAR_FILE' | 'FS_PERMISSION_DENIED' + | 'FS_SANDBOX_DENIED' | 'FS_IO_ERROR' | 'FS_STALE_VERSION' | 'FS_NOT_OBSERVED' @@ -140,7 +141,7 @@ type FsErrorCode = | 'FS_ABORTED' ``` -`FS_NOT_DIRECTORY`, `FS_PERMISSION_DENIED`, and `FS_IO_ERROR` are used by directory listing to distinguish an existing non-directory target, a denied listing, and an unexpected backend I/O failure. `FS_NOT_OBSERVED` means the policy plugin has no prior-observation record for this owner (or a `createIfAbsent` hit an existing file). `FS_STALE_VERSION` means the backend version no longer matches the observed one (or an edit hit a missing target). Freshness authorization has no partial/full distinction, so there is no `FS_PARTIAL_OBSERVATION`. +`FS_NOT_DIRECTORY`, `FS_PERMISSION_DENIED`, and `FS_IO_ERROR` are used by directory listing to distinguish an existing non-directory target, a denied listing, and an unexpected backend I/O failure. `FS_SANDBOX_DENIED` is a POLICY refusal from a sandbox-enforcing backend (`dsh-fs-sandbox`) — the mode fence denied a write/edit — distinct from `FS_PERMISSION_DENIED` (the host kernel refusing). `FS_NOT_OBSERVED` means the policy plugin has no prior-observation record for this owner (or a `createIfAbsent` hit an existing file). `FS_STALE_VERSION` means the backend version no longer matches the observed one (or an edit hit a missing target). Freshness authorization has no partial/full distinction, so there is no `FS_PARTIAL_OBSERVATION`. ## The service and the plugin diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 5b0a82673e..c084facc40 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -21,9 +21,9 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | -| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | -| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | -| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | +| `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:124`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | +| `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:139`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | +| `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:110`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:64`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 7d6bf65c21..eed8b99f41 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -35,6 +35,7 @@ flowchart TD pkg_fs["fs"] pkg_fs_local["fs-local"] pkg_fs_policy["fs-policy"] + pkg_fs_sandbox["fs-sandbox"] pkg_tool_fs["tool-fs"] end subgraph group_skill["packages/skill"] @@ -113,6 +114,7 @@ flowchart TD subgraph group_sandbox["packages/sandbox"] pkg_sandbox["sandbox"] pkg_sandbox_local["sandbox-local"] + pkg_sandbox_policy["sandbox-policy"] end subgraph group_workflow["packages/workflow"] pkg_tool_workflow["tool-workflow"] @@ -128,8 +130,6 @@ flowchart TD pkg_session --> pkg_scope pkg_system_prompt --> pkg_llm pkg_system_prompt --> pkg_scope - pkg_fs --> pkg_brand - pkg_fs --> pkg_llm pkg_web --> pkg_llm pkg_sandbox --> pkg_llm pkg_agent --> pkg_brand @@ -139,11 +139,9 @@ flowchart TD pkg_agent --> pkg_system_prompt pkg_bash --> pkg_brand pkg_bash --> pkg_sandbox - pkg_bash --> pkg_session - pkg_fs_local --> pkg_fs - pkg_fs_policy --> pkg_fs - pkg_skill_local --> pkg_fs - pkg_skill_local --> pkg_skill + pkg_fs --> pkg_brand + pkg_fs --> pkg_llm + pkg_fs --> pkg_sandbox pkg_compact --> pkg_llm pkg_compact --> pkg_session pkg_web_fetch_local --> pkg_timeout @@ -156,8 +154,14 @@ flowchart TD pkg_llm_replay --> pkg_session pkg_sandbox_local --> pkg_llm pkg_sandbox_local --> pkg_sandbox + pkg_sandbox_policy --> pkg_sandbox + pkg_sandbox_policy --> pkg_session pkg_bash_local --> pkg_bash pkg_bash_local --> pkg_timeout + pkg_fs_local --> pkg_fs + pkg_fs_policy --> pkg_fs + pkg_skill_local --> pkg_fs + pkg_skill_local --> pkg_skill pkg_compact_basic --> pkg_agent pkg_compact_basic --> pkg_compact pkg_compact_basic --> pkg_llm @@ -196,8 +200,14 @@ flowchart TD pkg_bash_sandbox --> pkg_bash pkg_bash_sandbox --> pkg_bash_local pkg_bash_sandbox --> pkg_sandbox + pkg_bash_sandbox --> pkg_sandbox_policy + pkg_fs_sandbox --> pkg_fs + pkg_fs_sandbox --> pkg_fs_local + pkg_fs_sandbox --> pkg_sandbox + pkg_fs_sandbox --> pkg_sandbox_policy pkg_permission --> pkg_bash pkg_permission --> pkg_sandbox + pkg_permission --> pkg_sandbox_policy pkg_permission --> pkg_session pkg_permission --> pkg_user_approval pkg_agent_loop --> pkg_agent @@ -209,16 +219,19 @@ flowchart TD pkg_agent_loop --> pkg_tools pkg_tool_bash --> pkg_agent pkg_tool_bash --> pkg_bash - pkg_tool_bash --> pkg_llm pkg_tool_bash --> pkg_sandbox + pkg_tool_bash --> pkg_sandbox_policy pkg_tool_bash --> pkg_system_prompt pkg_tool_bash --> pkg_tools pkg_tool_bash --> pkg_user_approval pkg_tool_fs --> pkg_fs pkg_tool_fs --> pkg_llm + pkg_tool_fs --> pkg_sandbox + pkg_tool_fs --> pkg_sandbox_policy pkg_tool_fs --> pkg_session pkg_tool_fs --> pkg_system_prompt pkg_tool_fs --> pkg_tools + pkg_tool_fs --> pkg_user_approval pkg_tool_skill --> pkg_agent pkg_tool_skill --> pkg_llm pkg_tool_skill --> pkg_skill @@ -350,14 +363,11 @@ flowchart TD | [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`llm`](../packages/llm/llm) | | [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope) | | [`system-prompt`](../packages/core/system-prompt) | `core` | [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope) | -| [`fs`](../packages/fs/fs) | `fs` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`web`](../packages/web/web) | `web` | [`llm`](../packages/llm/llm) | | [`sandbox`](../packages/sandbox/sandbox) | `sandbox` | [`llm`](../packages/llm/llm) | | [`agent`](../packages/core/agent) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt) | -| [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) | -| [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) | -| [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) | -| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) | +| [`bash`](../packages/bash/bash) | `bash` | [`brand`](../packages/util/brand), [`sandbox`](../packages/sandbox/sandbox) | +| [`fs`](../packages/fs/fs) | `fs` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | | [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) | | [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) | @@ -366,7 +376,11 @@ flowchart TD | [`session-persistence`](../packages/session-persistence/session-persistence) | `session-persistence` | [`session`](../packages/core/session) | | [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | +| [`sandbox-policy`](../packages/sandbox/sandbox-policy) | `sandbox` | [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) | | [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) | +| [`fs-local`](../packages/fs/fs-local) | `fs` | [`fs`](../packages/fs/fs) | +| [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) | +| [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) | | [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) | | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | @@ -377,11 +391,12 @@ flowchart TD | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | -| [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | -| [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | +| [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | +| [`fs-sandbox`](../packages/fs/fs-sandbox) | `fs` | [`fs`](../packages/fs/fs), [`fs-local`](../packages/fs/fs-local), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | +| [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | -| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | -| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | +| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | +| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | | [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index afa07bb89d..53ffa04792 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -71,18 +71,6 @@ Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-st Source: [`packages/core/session/src/types.ts:329`](../packages/core/session/src/types.ts) -### `bash/*` - -#### `bash/sandbox-mode` — log-only - -The session's sandbox mode was switched — log-only (like `approval/*`; NOT a surface event, carries no `surfaceOp`): durable and replayable, never in the model transcript. The LAST such event is the session's override (effectiveSandboxMode); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user; see the tool layer's narrator). - -```ts persistence-catalog -'bash/sandbox-mode': { mode: SandboxMode } -``` - -Source: [`packages/bash/bash/src/session-mode.ts:31`](../packages/bash/bash/src/session-mode.ts) - ### `compact/*` #### `compact/end` — log-only @@ -157,13 +145,13 @@ Source: [`packages/hooks/hook-protocol/src/types.ts:45`](../packages/hooks/hook- #### `permission/preset` — log-only -The session's permission preset was switched — log-only (the `bash/sandbox-mode` precedent): durable and replayable, never in the model transcript. The LAST such event is the session's preset (effectivePermissionPreset); the knob events the switch wrote through follow it in the same turn, and they — not this record of the user's choice — are what execution reads. +The session's permission preset was switched — log-only (the `sandbox/mode` precedent): durable and replayable, never in the model transcript. The LAST such event is the session's preset (effectivePermissionPreset); the knob events the switch wrote through follow it in the same turn, and they — not this record of the user's choice — are what execution reads. ```ts persistence-catalog 'permission/preset': { preset: string } ``` -Source: [`packages/ui/permission/src/index.ts:42`](../packages/ui/permission/src/index.ts) +Source: [`packages/ui/permission/src/index.ts:45`](../packages/ui/permission/src/index.ts) ### `prompt/*` @@ -201,6 +189,18 @@ Amendment to the folded EpochHeader: at least one of a SystemDelta, a ToolsDelta Source: [`packages/core/session/src/types.ts:391`](../packages/core/session/src/types.ts) +### `sandbox/*` + +#### `sandbox/mode` — log-only + +The session's sandbox mode was switched — log-only (like `approval/*`; NOT a surface event, carries no `surfaceOp`): durable and replayable, never in the model transcript. The LAST such event is the session's override (effectiveSandboxMode); who asked for it is derivable from position (an event after the log's last `request/header*` was a runtime switch by the user; see the tool layer's narrator). + +```ts persistence-catalog +'sandbox/mode': { mode: SandboxMode } +``` + +Source: [`packages/sandbox/sandbox-policy/src/session-mode.ts:34`](../packages/sandbox/sandbox-policy/src/session-mode.ts) + ### `steering/*` #### `steering/message` — surface diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 54e59f7aa1..5bd4d46676 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -78,6 +78,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 | | [Exact session query service](implemented/feature/2026-07-10-session-query-service.md) | 2026-07-10 | | [Configure subagent persona, tool visibility, and depth](implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md) | 2026-07-12 | +| [Cross-family file sandbox — one policy home, a sandboxed fs provider, and fs escalation parity](implemented/feature/2026-07-14-cross-family-fs-sandbox.md) | 2026-07-14 | ### Simplification diff --git a/docs/rfc/implemented/feature/2026-07-06-sandbox.md b/docs/rfc/implemented/feature/2026-07-06-sandbox.md index fa10a783a2..4f86ad35a4 100644 --- a/docs/rfc/implemented/feature/2026-07-06-sandbox.md +++ b/docs/rfc/implemented/feature/2026-07-06-sandbox.md @@ -115,7 +115,7 @@ The default is composition config (`cordis.yml`) — operator-owned, process-wid ```ts interface SessionEventMap { - 'bash/sandbox-mode': { mode: 'read-only' | 'workspace-write' | 'danger-full-access' } + 'sandbox/mode': { mode: 'read-only' | 'workspace-write' | 'danger-full-access' } 'approval/policy': { policy: 'ask' | 'never' } } ``` @@ -130,9 +130,7 @@ Each owner exports the same three-piece kit: the event declaration, a pure fold #### In-process tools -fs/web/todo execute in-process, so their sandbox semantics are policy at their seams: the fs intent gates deciding by the shared mode vocabulary (§ Deferred phases, cross-family) make `read-only` a real boundary instead of a bash-only approximation — until then the contract says so honestly. No generic per-tool sandbox runtime: a host-mediated tool leaves the process only by returning declarative effects the host validates, which is a rewrite, not a wrapper. - -FIXME: Revisit this tool-local boundary. The follow-up design needs to determine whether sandboxing becomes a global harness capability that applies uniformly to every tool, instead of expressing in-process enforcement independently at each tool seam. +fs/web/todo execute in-process, so their sandbox semantics are policy at their seams. The fs seam now enforces the shared mode vocabulary through a sandboxed provider (`dsh-fs-sandbox` fences write/edit by mode; see [the cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)), so `read-only`/`workspace-write` are real boundaries for the filesystem tools, not a bash-only approximation. web/todo remain unfenced (web's only effect is network, outside the file-effect mode vocabulary). No generic per-tool sandbox runtime: a host-mediated tool leaves the process only by returning declarative effects the host validates, which is a rewrite, not a wrapper — the follow-up settled on one shared policy home (`ctx.sandboxPolicy`) with per-seam enforcement, not a uniform wrapper. ### Testing @@ -145,8 +143,7 @@ FIXME: Revisit this tool-local boundary. The follow-up design needs to determine Each phase gets its full design when picked up, validated against the code at that time, and lands with unit, real-API e2e, and snapshot coverage at the tiers it touches. -- **Per-session workspace root** — the executor's write boundary stays config-fixed for its lifetime while each ACP session has its own cwd; a per-session root rides the same per-call policy carrier once designed. -- **Cross-family boundary** — the fs intent gates decide by the shared mode, making `read-only`/`workspace-write` real boundaries beyond bash. +- **Per-session workspace root** — the executor's write boundary stays config-fixed for its lifetime while each ACP session has its own cwd; a per-session root rides the same per-call policy carrier once designed. Centralizing the root on `ctx.sandboxPolicy` (the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)) is the groundwork. - **Second consumer** — `subagent-acp` optionally confines child agents (per-call policy; unconfined default — a child agent must write its own persistence). - **More environments** — an environment-coherent capability group example (e.g. bash+fs against one container). - **Windows chain** — `PLATFORM_CHAINS.win32` is reserved and empty (fail-closed); filling it means a confinement runner from the AppContainer/restricted-token family, shipped from its own repository on the `node-addon-landlock-run` template, plus its profile dialect and denial/runner-failure signatures. @@ -190,7 +187,7 @@ What shipped pins — the tiers in Testing hold each: Costs and accepted limits: - **The one-wrapper illusion is given up knowingly.** A `tools/pre-execute` wrapper plus prompt conventions does not solve sandbox approval — the correct design costs structured denials, native runner probes, per-call policy carriage, and consistent cross-family enforcement, and this design pays it. -- **`read-only` is not yet a cross-family boundary.** Until the fs intent gates decide by the shared mode, the claim holds for bash only; the contract says so honestly (§ In-process tools). +- **`read-only` became a cross-family boundary through a follow-up.** This RFC shipped bash-only enforcement; the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md) extends the same mode vocabulary to the filesystem tools through a sandboxed `ctx.fs` provider and relocates the mode/root config and the `sandbox/mode` override to `ctx.sandboxPolicy` (§ In-process tools). - **Windows has no backend.** Its chain slot is reserved empty — fail-closed, never a fallthrough; filling it is a deferred phase. - **The Seatbelt rung leans on Apple's deprecated-but-shipped `sandbox-exec` CLI.** As darwin's sole candidate it is selected without probing, so a future removal surfaces at execution as the runner-failure classification — re-thrown `SANDBOX_UNAVAILABLE`, the command never runs; fail closed, never open. - **Landlock confinement is only as complete as the running kernel's ABI.** Reported as `enforcement: 'partial'` rather than refused — the deliberate trade that keeps the fallback available on older-kernel hosts. @@ -212,7 +209,7 @@ Behavioral and usage questions only — every "why not X?" design question lives - **What happens on a platform with no backend — Windows today?** `confine()` throws the fail-closed `SANDBOX_UNAVAILABLE` and the command never spawns; `win32` is a reserved EMPTY chain, pinned by test to fail closed identically until a Windows runner fills it (§ Deferred phases). - **`bwrap` is installed on my host but unusable (disabled unprivileged userns, an LSM denying `mount`) — what happens?** The chain probe is functional — it builds and enforces a real profile rather than checking `--version` — so a present-but-unusable `bwrap` fails its probe, selection falls to the registry-installed Landlock launcher, and the verdict is cached for the provider's lifetime. - **Does the sandbox restrict network or process visibility?** No — `SandboxMode` claims FILE effects only; the bwrap profile deliberately does not unshare pid, and no backend claims network. Whether network restriction becomes its own knob is left open in § The seam. -- **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively. fs/web/todo execute in-process, where an `execve` wrapper is mechanically meaningless; their `read-only` semantics arrive with the cross-family deferred phase, and until then the contract says bash-only honestly. +- **Which tools actually run confined?** OS subprocesses through `ctx.bash` — the bash tools, and hook commands transitively — plus the filesystem tools (`read`/`write`/`edit`) through the sandboxed `ctx.fs` provider (the [cross-family fs sandbox RFC](2026-07-14-cross-family-fs-sandbox.md)): bash confines via the OS runner, fs via an in-process path fence, both keying off the same `ctx.sandboxPolicy` mode. web/todo stay in-process and unfenced (web's only effect is network, outside the file-effect mode vocabulary). - **Does a granted escalation persist, or cover background tasks?** Neither: the grant is consumed by the very call that asked (foreground or background), that one call reports the mode it actually ran under, and every neighbor keeps its own. How escalation should be DEFINED for a background denial that only surfaces later via `bash_output` is left open in § Escalation. - **When does an editor's mode switch take effect?** Mid-turn: appended immediately, honored by the very next call's stamp. Idle: held on the bridge's session record, anchored at the next turn's `agent/prompt-submit`, with N flips coalescing to at most one event (none if net-zero); a crash before anchoring reverts it and `session/load` reports the truth. The model is not told — its next command simply behaves under the new mode. - **What survives a restart — and what if the operator changed the config default while the process was down?** Overrides replay from the session log (`effective = fold ?? config`), so a resumed session keeps its modes with zero catch-up machinery; a default that drifted offline changes behavior the same way a switch does (the approval policy, being stated, is additionally narrated with operator/config attribution). diff --git a/docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md b/docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md new file mode 100644 index 0000000000..cfac649368 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md @@ -0,0 +1,92 @@ +# RFC: Cross-family file sandbox — one policy home, a sandboxed fs provider, and fs escalation parity + +Status: implemented + +## Problem + +`SandboxMode` claims file effects, but originally only `ctx.bash` enforced it. The fs tools (`write`/`edit`) mutate the host filesystem in-process through `ctx.fs`, where an OS argv wrapper is mechanically meaningless — [the sandbox RFC](2026-07-06-sandbox.md) § In-process tools records this and left cross-family enforcement as a deferred phase with an open question: whether in-process enforcement stays per-seam or becomes a uniform harness capability. This RFC is that phase, and answers it: one shared policy home, per-seam enforcement at each family's correct altitude. + +The gap was not read-only-shaped. A confined coding agent's product mode is `workspace-write`: bash may already write under the workspace root while everything outside is denied, so an fs enforcement that could only deny-all would be strictly worse than disabling the fs tools — the model would attempt an in-workspace `write`, be denied, and learn to detour through `bash` heredocs. Cross-family enforcement therefore speaks the full mode ladder, including the path-containment judgment `workspace-write` requires (canonical targets; `..`/symlink/absolute-path escapes) and the same escalation lever bash carries. + +A second enforcing family also exposed an ownership problem in the original layout. The deployment default (`mode` + `workspaceRoot`) was configured on `dsh-bash-sandbox`, and the per-session override event was `bash/sandbox-mode`, folded and written by `dsh-bash`'s session-mode kit. With fs enforcing the same policy, either fs reads bash's config and events (a capability family depending on a sibling's plugin config) or each family carries its own copy — and two copies of `workspaceRoot` drift into exactly the split world the sandbox RFC warns about: bash confined to one root while fs fences another. + +## Decision + +Three coordinated pieces, all composed from the leaf `cordis.yml`, none touching `agent-loop`. + +### `ctx.sandboxPolicy` — one home for mode and workspace root + +`packages/sandbox/sandbox-policy/` (`@deepseek-ai/dsh-sandbox-policy`) registers `ctx.sandboxPolicy`, the single owner of the deployment's sandbox policy: + +- `Config`: `mode` (the closed `SandboxMode` union, default `read-only`) and `workspaceRoot` (default the process cwd, resolved absolute). Misconfiguration fails loud at load. +- The per-session override event `sandbox/mode`, with its pure fold (`effectiveSandboxMode(events)`), its write path (`setSandboxMode(session, mode)`), and `SANDBOX_MODES`. The event is policy state — consumed by two families — so it lives here, not in either capability's seam. Its shape and log-only semantics match the `approval/*` precedent. +- `defaultMode` / `workspaceRoot` accessors the enforcing implementations read for their resolve fallback and boundary. + +`dsh-bash-sandbox` carries no sandbox config of its own — it injects `sandboxPolicy` and reads the default from it; its `resolve()` precedence is unchanged (escalation grant > per-call stamp > default). `dsh-tool-bash` and `dsh-tool-fs` fold the session's `sandbox/mode` with `effectiveSandboxMode` to stamp each call; `dsh-permission` presets and the ACP bridge write through the relocated setter. The seam that owns bash execution no longer depends on `dsh-session` at all — the session dependency moved to the policy package with the fold. + +### `dsh-fs-sandbox` — enforcement inside the provider + +`packages/fs/fs-sandbox/` (`@deepseek-ai/dsh-fs-sandbox`) mirrors the `bash-local`/`bash-sandbox` split: `SandboxedFileSystem extends LocalFileSystem`, registered as `ctx.fs`, injecting `sandboxPolicy`. Reads (`resolve`/`stat`/`readText`/`streamText`/`listDir`) pass through untouched — every mode permits reading. The two mutations enforce by mode before delegating to the inherited atomic write: + +- `read-only` denies `writeText`/`editText` outright. +- `workspace-write` fences the canonicalized target against the writable-root set — `writableRoots(policy)` in `dsh-sandbox`: the workspace root plus the platform temp areas (`/tmp`, `os.tmpdir()`), each realpathed — the SAME set the Seatbelt profile grants, so the fs fence is the fourth dialect of one mode meaning alongside the bwrap/Landlock/Seatbelt profiles, and "the write tool cannot write `/tmp` but bash can" asymmetries cannot arise. Containment is prefix-inclusion on real paths; the target is re-canonicalized (`resolve` realpaths the deepest existing ancestor) immediately before delegating, so an ancestor symlink swapped since the tool resolved it is caught. +- `danger-full-access` delegates unfenced. + +A denial is the structured `FS_SANDBOX_DENIED` carrying the effective mode — distinct from `FS_PERMISSION_DENIED` (a host EACCES is the world refusing; this is policy refusing). No text inference: an in-process fence knows exactly what it denied. The per-call carrier is a trailing optional `sandboxMode` on `writeText`/`editText` (the filesystem twin of `BashExecRequest.sandboxMode`); the seam stays session-free (the caller stamps, exactly as `resolve` takes a cwd), and the bare local backend carries-and-ignores it. `FileSystem.sandboxMode` is the capability fact (`undefined` on the base and `fs-local`, the default on `SandboxedFileSystem`), so the tool layer advertises escalation from composition truth. + +The threat model is stated in the package README: a policy fence in trusted code over model-controlled paths, not a kernel boundary — the operations are the seam's own, only the target path is untrusted, so canonicalize-then-contain is the complete answer to this surface (the `code-runtime` "containment, not a security boundary" precedent). Kernel-grade isolation of untrusted CODE stays `ctx.bash`'s job. The residual resolve-to-syscall race is narrowed by the in-place re-canonicalization and eliminated only by platform primitives (`openat2` `RESOLVE_BENEATH`) not worth their portability cost here. + +### Tool parity — one denial marker, one escalation flow + +`dsh-tool-fs` stamps the effective mode onto each mutation and maps `FS_SANDBOX_DENIED` to the marker the model already knows from bash: `[sandbox: file access denied under mode]`. When `ctx.fs.sandboxMode` reports a confining mode at registration, `write` and `edit` advertise the same `sandbox_permissions` + `justification` fields, teach the same same-turn retry, and resolve the same `ctx.approval` request before executing — the four outcomes and their verbatim fail-closed texts carried over from [the sandbox RFC](2026-07-06-sandbox.md) § Escalation (strict widening checked at execution against the call's effective mode; a grant consumed by the one call that asked; no new session events). + +The shared pieces live in `dsh-sandbox`, which owns the mode types: `WIDER_MODES`, the escalation-target enum, the argument-pairing validation, the denial/hint marker builders, and `approveEscalation` — the ordered fail-closed choreography. `approveEscalation` takes a minimal STRUCTURAL ask-function (`EscalationChannel`), not the approval service type, so `dsh-sandbox` gains no dependency on the approval or agent packages: each tool closes over its own `ctx.approval.request(...)`, agent, call id, and tool name and hands the closure down. `dsh-tool-bash` and `dsh-tool-fs` both use these; the cross-file duplication gate holds the single-sourcing honest. + +The [`examples/acp-agent`](../../../../examples/acp-agent/cordis.yml) composition loads `dsh-sandbox-policy` and `dsh-fs-sandbox`, moves the `mode`/`workspaceRoot` config to the policy entry, and drops the old gating that disabled the fs stack under confined modes; `fs-policy` (read-before-edit) composes orthogonally on top. The system prompt still states no sandbox mode — the marker teaches the boundary at the moment it matters, per the sandbox RFC's live evidence. + +### The enforcement point: provider, not intent gate + +The sandbox RFC's original cross-family sketch put fs enforcement on the `fs/write-intent`/`fs/edit-intent` events. This RFC enforces in the provider instead, on two mechanical facts: the intent slots are single-decision first-wins (occupied by `dsh-fs-policy`, whose contract names a second decider a misconfiguration), and the intent events are dispatched only by `dsh-tool-fs` — a direct `ctx.fs` caller (a cordis-mounted plugin, a custom tool) bypasses them, where provider-level enforcement covers every caller by construction. The sandbox RFC's deferred-phase wording is updated to match in the same change. + +### Out of scope + +- **Network policy for `ctx.web`** — `SandboxMode` claims file effects only; a web-only network knob while bash `curl` runs free would be a false boundary. Revisit when a bash backend enforces network (bwrap `--unshare-net`, Landlock ABI v4+). +- **The `subagent-acp` consumer** and **per-session workspace root** — unchanged deferred phases of the sandbox RFC; centralizing the root in `ctx.sandboxPolicy` is groundwork for the latter, not its design. +- **A uniform per-tool sandbox runtime** — remains rejected for the reasons in the sandbox RFC. + +## Alternatives considered + +- **Enforce on the `fs/*` intent events (the sandbox RFC's original sketch)** — rejected on the two mechanical facts in § The enforcement point: single-slot first-wins already occupied, and a bypass for direct `ctx.fs` callers. Provider-level enforcement covers every caller and mirrors bash's swap-the-implementation shape. +- **Enforce in `tools/pre-execute`** — rejected: the listener sees the model's raw path string before `resolve()`, so it would re-implement cwd defaulting and symlink canonicalization and still race the real resolve. Disqualifying for `workspace-write`, a judgment over canonical paths. +- **Inline checks in `dsh-tool-fs`** — rejected: covers only the tool path (same bypass as the intent events) and duplicates resolve knowledge one layer above where the canonical target already exists. +- **A `mode` flag on `dsh-fs-local` instead of a sibling backend** — rejected: the capability fact must be composition truth the way `dsh-bash-local` vs `dsh-bash-sandbox` is; a config flag makes the tool's advertisement conditional on configuration, and the bash family already establishes the sibling-package shape. +- **Kernel-enforced fs mutations via a confined helper subprocess** — rejected: a process per write; `editText`'s read-match-write critical section would have to move wholesale into the child to stay atomic; and the threat surface (trusted operations, untrusted path argument) does not need a kernel — the fence in trusted code is the complete answer, while untrusted-code isolation stays on `ctx.bash`. +- **Per-family policy config with a load-time consistency check** — rejected: two homes for one fact, patched by a check that must enumerate every future enforcing family; the policy service makes drift inexpressible instead of detected. +- **Keep the override event in `dsh-bash` as `bash/sandbox-mode`** — rejected: the event is policy state consumed by two families; leaving it bash-named forces `dsh-fs-sandbox` to depend on bash vocabulary. Pre-release, the rename is a same-change move with snapshot re-records, no shims. +- **Escalation choreography imported from the approval/agent packages into `dsh-sandbox`** — rejected: it would invert the layering (a base vocabulary package depending on UI/agent packages). The structural ask-function keeps the logic single-sourced in `dsh-sandbox` while the dependencies stay in the tool layer that already holds them. +- **A consolidated mutation-options object on the fs seam** (the shape first sketched for the per-call carrier) — rejected on friction: it churns every `writeText`/`editText` caller and splits `signal` across an options bag for mutations while reads keep it positional. A trailing optional `sandboxMode` matches bash's carry-and-ignore pattern and keeps `signal` symmetric across the seam. +- **Extra writable-root grants on `SandboxPolicy` now** — deferred unchanged: `writableRoots()` derives from the mode meaning today; ad-hoc grants are an escalation-scope question the sandbox RFC left open. + +## Consequences + +What shipped — the tiers in § Testing hold each: + +- Under `read-only`, `write`/`edit` return the `[sandbox: file access denied under read-only mode]` marker and the disk is untouched; `read`/`listDir` behave identically to `dsh-fs-local`. +- Under `workspace-write`, mutations land under the workspace root and the temp areas and are denied outside; the containment matrix — `..` traversal, absolute paths outside, a pre-existing symlinked directory inside pointing out, and a new file created under such a symlink — denies every escape on real disks. +- A denied fs mutation retried once with `sandbox_permissions` + `justification` prompts through the composed approval chain; a grant runs exactly that call under the wider mode and the write lands; rejected/cancelled/unavailable each produce their verbatim fail-closed text and mutate nothing. +- One `permission` preset switch governs both families: after a session switches modes, the next bash call and the next fs mutation both honor the new mode from the same `sandbox/mode` fold. +- A direct `ctx.fs.writeText` with no per-call stamp is confined at the deployment default. +- The escalation fields on `write`/`edit` exist exactly when the mounted `ctx.fs` confines, absent under `dsh-fs-local`. +- `agent-loop` is untouched — everything rides `ctx.sandboxPolicy`, the `ctx.fs` seam, `SessionEventMap` merging, and the tool-execution pipeline. + +Costs and accepted limits: + +- **The fs fence is a policy boundary, not a kernel one.** Its threat surface is model-chosen paths, not adversarial host processes; the residual resolve-to-syscall TOCTOU is narrowed, not eliminated, and the README says so. Kernel boundaries remain bash's. +- **`dsh-bash-sandbox` gains a hard dependency on `ctx.sandboxPolicy`.** Every sandboxed composition adds one `cordis.yml` entry or fails loud at load — the intended pre-release foundation move; the examples update in the same change. +- **Fence-vs-runner parity is derived, not asserted.** The fs fence and the Seatbelt profile both take their writable set from `writableRoots`, and a parity unit test pins the sets; a runner profile changing its writable set without that function would drift. +- **The marker and escalation teaching now serve two families.** A wording change is a coordinated edit behind one builder in `dsh-sandbox`; the duplication gate and pinned snapshots hold it single-sourced, at the cost that fs and bash cannot deliberately diverge in phrasing without splitting the builder. + +## Testing + +- Unit: `dsh-sandbox` pins the escalation ladder, the marker builders, the argument-pairing validation, and `approveEscalation`'s ordered fail-closed sequence (non-widening, no-approval, no-agent, each outcome), plus `writableRoots`/`canonicalPath`. `dsh-sandbox-policy` pins the default accessors, the fold/setter, the load-time mode rejection, and HMR safety. `dsh-fs-sandbox` pins the per-mode fence and the containment matrix (inside, temp area, absolute-outside, `..`, symlinked-out directory, new file under one, path-equals-root, root-ending-in-separator) on a real filesystem, plus the per-call override and HMR safety. `dsh-tool-fs` pins advertisement gating, the mode stamp, the fold, denial-marker mapping, and the full escalation matrix (grant, reject, no-service, no-agent, pairing, non-confining guard). `dsh-tool-bash`, `dsh-bash-sandbox`, and `dsh-permission` migrate to the relocated policy/kit. +- Snapshot: the acp-agent example composes `dsh-sandbox-policy` + `dsh-fs-sandbox`; the pinned header carries the fs escalation fields and the `sandbox/mode` event name, re-recorded once. diff --git a/examples/acp-agent/composition.md b/examples/acp-agent/composition.md index d5c3096666..f7ec986a9d 100644 --- a/examples/acp-agent/composition.md +++ b/examples/acp-agent/composition.md @@ -12,6 +12,8 @@ flowchart LR cfg --> plugin_acp_llm_deepseek plugin_acp_sandbox["sandbox
@deepseek-ai/dsh-sandbox-local"] cfg --> plugin_acp_sandbox + plugin_acp_sandbox_policy["sandbox-policy
@deepseek-ai/dsh-sandbox-policy"] + cfg --> plugin_acp_sandbox_policy plugin_acp_bash["bash
@deepseek-ai/dsh-bash-sandbox"] cfg --> plugin_acp_bash plugin_acp_approval["approval
@deepseek-ai/dsh-user-approval"] @@ -45,8 +47,8 @@ flowchart LR cfg --> plugin_acp_tool_todo plugin_acp_repeat_tool_guard["repeat-tool-guard
@deepseek-ai/dsh-repeat-tool-guard"] cfg --> plugin_acp_repeat_tool_guard - plugin_acp_fs_local["fs-local
@deepseek-ai/dsh-fs-local"] - cfg --> plugin_acp_fs_local + plugin_acp_fs_sandbox["fs-sandbox
@deepseek-ai/dsh-fs-sandbox"] + cfg --> plugin_acp_fs_sandbox plugin_acp_fs_policy["fs-policy
@deepseek-ai/dsh-fs-policy"] cfg --> plugin_acp_fs_policy plugin_acp_tool_fs["tool-fs
@deepseek-ai/dsh-tool-fs"] @@ -61,6 +63,7 @@ flowchart LR | --- | --- | | `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` | | `sandbox` | `@deepseek-ai/dsh-sandbox-local` | +| `sandbox-policy` | `@deepseek-ai/dsh-sandbox-policy` | | `bash` | `@deepseek-ai/dsh-bash-sandbox` | | `approval` | `@deepseek-ai/dsh-user-approval` | | `permission` | `@deepseek-ai/dsh-permission` | @@ -74,7 +77,7 @@ flowchart LR | `tool-workflow` | `@deepseek-ai/dsh-tool-workflow` | | `tool-todo` | `@deepseek-ai/dsh-tool-todo` | | `repeat-tool-guard` | `@deepseek-ai/dsh-repeat-tool-guard` | -| `fs-local` | `@deepseek-ai/dsh-fs-local` | +| `fs-sandbox` | `@deepseek-ai/dsh-fs-sandbox` | | `fs-policy` | `@deepseek-ai/dsh-fs-policy` | | `tool-fs` | `@deepseek-ai/dsh-tool-fs` | | `hooks-claude` | `@deepseek-ai/dsh-hooks-claude` | diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index 42c8bb46f0..e752dcc710 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -23,19 +23,25 @@ - deepseek-v4-flash - deepseek-v4-pro -# The default composition confines bash to the workspace and asks before a -# wider retry. Snapshot runs select danger-full-access so the established -# scenarios remain runner-independent; DSH_PERMISSION_MODE provides the same -# explicit deployment/test override outside the snapshot harness. +# The default composition confines bash AND the filesystem tools to the +# workspace and asks before a wider retry. Snapshot runs select +# danger-full-access so the established scenarios remain runner-independent; +# DSH_PERMISSION_MODE provides the same explicit deployment/test override +# outside the snapshot harness. The sandbox mode + workspace root live on +# ctx.sandboxPolicy — the one home both enforcing families (bash, fs) read. - id: sandbox name: '@deepseek-ai/dsh-sandbox-local' +- id: sandbox-policy + name: '@deepseek-ai/dsh-sandbox-policy' + config: + mode: !!js "process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')" + workspaceRoot: !!js process.cwd() + - id: bash name: '@deepseek-ai/dsh-bash-sandbox' config: timeoutMs: 60000 - mode: !!js "process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')" - workspaceRoot: !!js process.cwd() - id: approval name: '@deepseek-ai/dsh-user-approval' @@ -119,22 +125,21 @@ - id: repeat-tool-guard name: '@deepseek-ai/dsh-repeat-tool-guard' -# Filesystem tools do not ride the bash sandbox, so the confined default omits -# them. Snapshot tests and explicit danger-full-access launches keep the -# established filesystem scenarios by enabling the whole stack together. -- id: fs-local - name: '@deepseek-ai/dsh-fs-local' - disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'" +# The filesystem stack rides the SAME sandbox policy as bash: dsh-fs-sandbox +# replaces dsh-fs-local behind ctx.fs and fences write/edit by the effective +# mode (read-only denies, workspace-write contains to the workspace + temp +# roots, danger-full-access passes through), so read/write/edit are available +# under every mode. fs-policy (read-before-edit) composes orthogonally on top. +- id: fs-sandbox + name: '@deepseek-ai/dsh-fs-sandbox' config: cwd: !!js process.cwd() - id: fs-policy name: '@deepseek-ai/dsh-fs-policy' - disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'" - id: tool-fs name: '@deepseek-ai/dsh-tool-fs' - disabled: !!js "(process.env.DSH_PERMISSION_MODE ?? (process.env.DSH_SNAPSHOT === undefined ? 'workspace-write' : 'danger-full-access')) !== 'danger-full-access'" # The Claude Code hook bridge. `configPath` is PROCESS-LEVEL: it is read ONCE at # load and the relative `./hooks.json` resolves against the ACP server's launch diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index cdc09c92c0..735f6fe05f 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 79d9b94ad9..dab6ace37c 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index 7155b1c2a6..6beb7cb53e 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 6e8f157ace..94cba74575 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -5,6 +5,12 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. + +Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. + +Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. + Check the [exit code: N] marker on every bash result; investigate failures before moving on. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -67,6 +73,30 @@ declare const tools: { /** The dynamic mount id returned by cordis_mount (e.g. "dyn-1"). */ id: string; }): Promise; + /** Edit an existing UTF-8 text file by replacing literal text. */ + edit(args: { + /** Path to edit, resolved by the filesystem backend. */ + file_path: string; + /** Literal text to replace. Must match exactly. */ + old_string: string; + /** Literal replacement text. Use an empty string to delete the match. */ + new_string: string; + /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ + replace_all?: boolean; + /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ + justification?: string; + }): Promise; + /** Read a UTF-8 text file and return line-numbered content. */ + read(args: { + /** Path to read, resolved by the filesystem backend. */ + file_path: string; + /** 1-based first line to return. Defaults to 1. */ + offset?: number; + /** Maximum number of lines to return. Defaults to 2000. */ + limit?: number; + }): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -121,5 +151,16 @@ declare const tools: { /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ args?: Record; }): Promise; + /** Create or fully replace a UTF-8 text file. */ + write(args: { + /** Path to write, resolved by the filesystem backend. */ + file_path: string; + /** Full UTF-8 text content to write. */ + content: string; + /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ + justification?: string; + }): Promise; } ``` diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index 66cdecedfb..60297e92d6 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 98b4f97fee..5f71fbdd76 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -5,6 +5,12 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. + +Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. + +Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. + Check the [exit code: N] marker on every bash result; investigate failures before moving on. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -52,6 +58,30 @@ declare const tools: { /** Task id returned by the bash tool. */ task_id: string; }): Promise; + /** Edit an existing UTF-8 text file by replacing literal text. */ + edit(args: { + /** Path to edit, resolved by the filesystem backend. */ + file_path: string; + /** Literal text to replace. Must match exactly. */ + old_string: string; + /** Literal replacement text. Use an empty string to delete the match. */ + new_string: string; + /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ + replace_all?: boolean; + /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ + justification?: string; + }): Promise; + /** Read a UTF-8 text file and return line-numbered content. */ + read(args: { + /** Path to read, resolved by the filesystem backend. */ + file_path: string; + /** 1-based first line to return. Defaults to 1. */ + offset?: number; + /** Maximum number of lines to return. Defaults to 2000. */ + limit?: number; + }): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -106,5 +136,16 @@ declare const tools: { /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ args?: Record; }): Promise; + /** Create or fully replace a UTF-8 text file. */ + write(args: { + /** Path to write, resolved by the filesystem backend. */ + file_path: string; + /** Full UTF-8 text content to write. */ + content: string; + /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ + justification?: string; + }): Promise; } ``` diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 98b4f97fee..5f71fbdd76 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -5,6 +5,12 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. + +Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. + +Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. + Check the [exit code: N] marker on every bash result; investigate failures before moving on. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). @@ -52,6 +58,30 @@ declare const tools: { /** Task id returned by the bash tool. */ task_id: string; }): Promise; + /** Edit an existing UTF-8 text file by replacing literal text. */ + edit(args: { + /** Path to edit, resolved by the filesystem backend. */ + file_path: string; + /** Literal text to replace. Must match exactly. */ + old_string: string; + /** Literal replacement text. Use an empty string to delete the match. */ + new_string: string; + /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */ + replace_all?: boolean; + /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ + justification?: string; + }): Promise; + /** Read a UTF-8 text file and return line-numbered content. */ + read(args: { + /** Path to read, resolved by the filesystem backend. */ + file_path: string; + /** 1-based first line to return. Defaults to 1. */ + offset?: number; + /** Maximum number of lines to return. Defaults to 2000. */ + limit?: number; + }): Promise; /** Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill. */ skill(args: { /** The exact skill name from the available skills list. */ @@ -106,5 +136,16 @@ declare const tools: { /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {"files": [...]}). */ args?: Record; }): Promise; + /** Create or fully replace a UTF-8 text file. */ + write(args: { + /** Path to write, resolved by the filesystem backend. */ + file_path: string; + /** Full UTF-8 text content to write. */ + content: string; + /** The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval. */ + sandbox_permissions?: "workspace-write" | "danger-full-access"; + /** Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access. */ + justification?: string; + }): Promise; } ``` diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 7dff360513..743ce40663 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -1,7 +1,7 @@ {"type":"session","version":0,"id":"f3cbd087-fb45-4b32-b0f2-3082d65bfcb4","createdAt":1783860675270,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-cbBLh2"} {"type":"turn/start","seq":0,"time":1783860675271,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"permission/preset","seq":1,"time":1783962245380,"data":{"preset":"workspace-write"}} -{"type":"bash/sandbox-mode","seq":2,"time":1783962245380,"data":{"mode":"workspace-write"}} +{"type":"sandbox/mode","seq":2,"time":1784023679499,"data":{"mode":"workspace-write"}} {"type":"approval/policy","seq":3,"time":1783962245380,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962245380,"data":{"content":[{"type":"text","text":"The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962245382,"data":{"turn":1,"step":1}} @@ -131,8 +131,8 @@ {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"d409f075-74f1-4637-9e13-6e80d7b6f6ff","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"d409f075-74f1-4637-9e13-6e80d7b6f6ff","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"0dfc6fba-ccdf-4233-8b48-87003f0b75b7","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"0dfc6fba-ccdf-4233-8b48-87003f0b75b7","outcome":"allowed-once"}} {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index 55cad3689d..56380e66c3 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -1,7 +1,7 @@ {"type":"session","version":0,"id":"d692fe7f-7079-4ee4-8b06-f44fd026d4ea","createdAt":1783860679475,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-Hn29Od"} {"type":"turn/start","seq":0,"time":1783860679476,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"permission/preset","seq":1,"time":1783962246267,"data":{"preset":"workspace-write"}} -{"type":"bash/sandbox-mode","seq":2,"time":1783962246267,"data":{"mode":"workspace-write"}} +{"type":"sandbox/mode","seq":2,"time":1784023680100,"data":{"mode":"workspace-write"}} {"type":"approval/policy","seq":3,"time":1783962246267,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962246267,"data":{"content":[{"type":"text","text":"The sandbox already denied writing /tmp/dsh-escalated.txt earlier (it is outside this workspace). Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt, with sandbox_permissions set to danger-full-access and the justification 'the user asked to write a file outside the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962246269,"data":{"turn":1,"step":1}} @@ -155,8 +155,8 @@ {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"e592115c-e915-4010-9bf5-cc5e7bb6f8bc","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"e592115c-e915-4010-9bf5-cc5e7bb6f8bc","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"5b59a78f-4b4c-400b-b7f7-d8f689f75854","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"5b59a78f-4b4c-400b-b7f7-d8f689f75854","outcome":"rejected"}} {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl index 723282d1a8..90f009946d 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl @@ -69,7 +69,7 @@ {"type":"assistant/chunk","seq":67,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":68,"time":1783352086059,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read config.txt in the current directory\n2. Use the edit tool to replace DEBUG with RELEASE\n3. Reply with exactly \"DONE\"\n\nLet me start by reading the file."},{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}],"usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67],"surfaceOp":"append"} {"type":"tool/call","seq":69,"time":1783352086059,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}} -{"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[69],"surfaceOp":"append"} +{"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"/tmp/acp-snap-cwd-0BxHdV/config.txt\nfile\n\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n"}],"isError":false},"sourceEventSeqs":[69],"surfaceOp":"append"} {"type":"step/end","seq":71,"time":1783352086065,"data":{"turn":1,"step":1}} {"type":"step/start","seq":72,"time":1783352086066,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":73,"time":1783352086901,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -129,7 +129,7 @@ {"type":"assistant/chunk","seq":127,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":128,"time":1783352087469,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Now I need to replace \"DEBUG\" with \"RELEASE\" using the edit tool."},{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}],"usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"} {"type":"tool/call","seq":129,"time":1783352087469,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}} -{"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[129],"surfaceOp":"append"} +{"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"The file /tmp/acp-snap-cwd-0BxHdV/config.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}]}},"sourceEventSeqs":[129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352087477,"data":{"turn":1,"step":2}} {"type":"step/start","seq":132,"time":1783352087477,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":133,"time":1783352088286,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl index 5bc88537ce..c7eda2cfd0 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl @@ -46,8 +46,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"config.txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","title":"Read config.txt","kind":"read","status":"in_progress","locations":[{"path":"config.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_S6krdIDHoSCGWv7WnXX97617","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/config.txt\nfile\n\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Now"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} @@ -66,8 +66,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" edit"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"config.txt","old_string":"DEBUG","new_string":"RELEASE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","title":"Edit config.txt","kind":"edit","status":"in_progress","locations":[{"path":"config.txt"}],"content":[{"type":"diff","path":"config.txt","oldText":"DEBUG","newText":"RELEASE"}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_vOytneZ0XpsLslEEJAxR6398","status":"completed","content":[{"type":"diff","path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}],"title":"Edit config.txt"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Done"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl index 8a500475c0..802120fd9c 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl @@ -77,7 +77,7 @@ {"type":"assistant/chunk","seq":75,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":76,"time":1783611703972,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"} {"type":"tool/call","seq":77,"time":1783611703972,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} -{"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[77],"surfaceOp":"append"} +{"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: edit requires reading \"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\" first"}],"isError":true,"error":{"name":"FsError","code":"FS_NOT_OBSERVED"}},"sourceEventSeqs":[77],"surfaceOp":"append"} {"type":"step/end","seq":79,"time":1783611703978,"data":{"turn":1,"step":1}} {"type":"step/start","seq":80,"time":1783611703978,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":81,"time":1783611704825,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -144,7 +144,7 @@ {"type":"assistant/chunk","seq":142,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":143,"time":1783611705573,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The edit tool requires reading the file first. The user said \"Do not read the file first\" but the tool's own constraints require reading. I need to follow the tool requirements. Let me read the file first."},{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}],"usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}},"sourceEventSeqs":[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} {"type":"tool/call","seq":144,"time":1783611705573,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}} -{"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[144],"surfaceOp":"append"} +{"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\nfile\n\n1: color: blue\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783611705579,"data":{"turn":1,"step":2}} {"type":"step/start","seq":147,"time":1783611705579,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":148,"time":1783611706200,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -225,7 +225,7 @@ {"type":"assistant/chunk","seq":223,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":224,"time":1783611707097,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file contains \"color: blue\". I need to replace \"blue\" with \"green\". The edit tool said it requires reading first — now I've read it, so the edit should work."},{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223],"surfaceOp":"append"} {"type":"tool/call","seq":225,"time":1783611707097,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} -{"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"Error: unknown tool \"edit\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[225],"surfaceOp":"append"} +{"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"The file /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"settings.txt","oldText":"color: blue","newText":"color: green"}]}},"sourceEventSeqs":[225],"surfaceOp":"append"} {"type":"step/end","seq":227,"time":1783611707114,"data":{"turn":1,"step":3}} {"type":"step/start","seq":228,"time":1783611707114,"data":{"turn":1,"step":4}} {"type":"assistant/chunk","seq":229,"time":1783611707747,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl index 864cc3de9f..fd465755bf 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl @@ -36,8 +36,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt","old_string":"blue","new_string":"green"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","title":"Edit settings.txt","kind":"edit","status":"in_progress","locations":[{"path":"settings.txt"}],"content":[{"type":"diff","path":"settings.txt","oldText":"blue","newText":"green"}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: edit requires reading \"{{cwd}}/settings.txt\" first"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" edit"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} @@ -82,8 +82,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","title":"Read settings.txt","kind":"read","status":"in_progress","locations":[{"path":"settings.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_tfr0gdIclW92oIEgi7NF0891","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/settings.txt\nfile\n\n1: color: blue\n\n(End of file - total 1 lines)\n"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}} @@ -124,8 +124,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" work"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","title":"edit","kind":"other","status":"in_progress","rawInput":{"file_path":"settings.txt","old_string":"blue","new_string":"green"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"edit\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","title":"Edit settings.txt","kind":"edit","status":"in_progress","locations":[{"path":"settings.txt"}],"content":[{"type":"diff","path":"settings.txt","oldText":"blue","newText":"green"}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GVknJu2tksKkP4lALCwh0926","status":"completed","content":[{"type":"diff","path":"settings.txt","oldText":"color: blue","newText":"color: green"}],"title":"Edit settings.txt"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" replacement"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl index f22aba96b2..becc503c65 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl @@ -91,7 +91,7 @@ {"type":"assistant/chunk","seq":89,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":90,"time":1783352101348,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the read tool with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE.\n\nLet me first check the current directory, then read the file."},{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}],"usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"surfaceOp":"append"} {"type":"tool/call","seq":91,"time":1783352101348,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}} -{"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[91],"surfaceOp":"append"} +{"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"/tmp/acp-snap-cwd-N9HCkt/big.txt\nfile\n\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n"}],"isError":false},"sourceEventSeqs":[91],"surfaceOp":"append"} {"type":"step/end","seq":93,"time":1783352101353,"data":{"turn":1,"step":1}} {"type":"step/start","seq":94,"time":1783352101354,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":95,"time":1783352102021,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl index c283736334..67c1a6ba08 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl @@ -56,8 +56,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"big.txt","offset":5,"limit":4}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","title":"Read big.txt (5 - 8)","kind":"read","status":"in_progress","locations":[{"path":"big.txt","line":5}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/big.txt\nfile\n\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" read"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl index d91d10d39a..3af4b2ac61 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl @@ -53,7 +53,7 @@ {"type":"assistant/chunk","seq":51,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":52,"time":1783352073708,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file greeting.txt using the read tool (not bash), then reply with exactly the single word \"DONE\"."},{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352073709,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} -{"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[53],"surfaceOp":"append"} +{"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"/tmp/acp-snap-cwd-PEETkS/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":55,"time":1783352073718,"data":{"turn":1,"step":1}} {"type":"step/start","seq":56,"time":1783352073719,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":57,"time":1783352074666,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl index 4f2973bcc5..269d184534 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl @@ -29,8 +29,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"greeting.txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","title":"Read greeting.txt","kind":"read","status":"in_progress","locations":[{"path":"greeting.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_hHPZCcivsIkXAGS9jTGy8417","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl index 0233abbe39..47627ae7a5 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl @@ -65,7 +65,7 @@ {"type":"assistant/chunk","seq":63,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":64,"time":1783352093617,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read data.txt using the read tool\n2. Replace its entire contents with exactly \"replaced\" using the write tool\n3. Reply with exactly \"DONE\""},{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}],"usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"} {"type":"tool/call","seq":65,"time":1783352093617,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}} -{"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[65],"surfaceOp":"append"} +{"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\n1: original contents\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"} {"type":"step/end","seq":67,"time":1783352093624,"data":{"turn":1,"step":1}} {"type":"step/start","seq":68,"time":1783352093625,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":69,"time":1783352094455,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} @@ -114,7 +114,7 @@ {"type":"assistant/chunk","seq":112,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":113,"time":1783352094988,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"original contents\". Now I'll replace it with \"replaced\"."},{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}],"usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"tool/call","seq":114,"time":1783352094988,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}} -{"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"Error: unknown tool \"write\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[114],"surfaceOp":"append"} +{"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\nUpdated file\n"}],"isError":false,"meta":{"diffs":[{"path":"data.txt","oldText":"original contents","newText":"replaced"}]}},"sourceEventSeqs":[114],"surfaceOp":"append"} {"type":"step/end","seq":116,"time":1783352094995,"data":{"turn":1,"step":2}} {"type":"step/start","seq":117,"time":1783352094995,"data":{"turn":1,"step":3}} {"type":"assistant/chunk","seq":118,"time":1783352096090,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl index 03c77cae98..1b85301ee4 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl @@ -42,8 +42,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"data.txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","title":"Read data.txt","kind":"read","status":"in_progress","locations":[{"path":"data.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_n4eRJuGoxNR07svgNtk82243","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/data.txt\nfile\n\n1: original contents\n\n(End of file - total 1 lines)\n"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}} @@ -61,8 +61,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"re"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"placed"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","title":"write","kind":"other","status":"in_progress","rawInput":{"file_path":"data.txt","content":"replaced"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"write\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","title":"Write data.txt","kind":"edit","status":"in_progress","locations":[{"path":"data.txt"}],"content":[{"type":"diff","path":"data.txt","oldText":null,"newText":"replaced"}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_N23EvXjDo4c8enyWpIUq4043","status":"completed","content":[{"type":"diff","path":"data.txt","oldText":"original contents","newText":"replaced"}],"title":"Write data.txt"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" has"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl index 6170af99a5..7e4b2dda01 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl @@ -62,7 +62,7 @@ {"type":"assistant/chunk","seq":60,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":61,"time":1783352079888,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file named notes.txt with the content \"hello world\" using the write tool, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}],"usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"tool/call","seq":62,"time":1783352079888,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}} -{"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"Error: unknown tool \"write\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[62],"surfaceOp":"append"} +{"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"/tmp/acp-snap-cwd-sNvn5N/notes.txt\nfile\n\nCreated file\n"}],"isError":false},"sourceEventSeqs":[62],"surfaceOp":"append"} {"type":"step/end","seq":64,"time":1783352079898,"data":{"turn":1,"step":1}} {"type":"step/start","seq":65,"time":1783352079899,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":66,"time":1783352080825,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl index 1e68a6b90a..9d1b9744e4 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl @@ -30,8 +30,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","title":"write","kind":"other","status":"in_progress","rawInput":{"file_path":"notes.txt","content":"hello world"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"write\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","title":"Write notes.txt","kind":"edit","status":"in_progress","locations":[{"path":"notes.txt"}],"content":[{"type":"diff","path":"notes.txt","oldText":null,"newText":"hello world"}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_APMUCJJm9lrTSlVbg6dB0185","status":"completed","content":[{"type":"diff","path":"notes.txt","oldText":null,"newText":"hello world"}],"title":"Write notes.txt"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" has"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index 3933a939ba..43b3369b77 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,8 +55,8 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"cdd11a3a-c721-4d08-8255-732218775c33","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"cdd11a3a-c721-4d08-8255-732218775c33","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"f8f9d54e-a313-4719-9950-713e317b29b7","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"f8f9d54e-a313-4719-9950-713e317b29b7","outcome":"rejected"}} {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index e1438965b7..8f6d461cff 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -1,11 +1,11 @@ {"type":"session","version":0,"id":"df041acb-2f14-4d5f-b6e2-2fb6b9eb6427","createdAt":1783860666204,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-4oJKT4"} {"type":"turn/start","seq":0,"time":1783860666206,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"permission/preset","seq":1,"time":1783962244578,"data":{"preset":"workspace-write"}} -{"type":"bash/sandbox-mode","seq":2,"time":1783962244578,"data":{"mode":"workspace-write"}} +{"type":"sandbox/mode","seq":2,"time":1784023678825,"data":{"mode":"workspace-write"}} {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -102,12 +102,12 @@ {"type":"turn/end","seq":100,"time":1783962244601,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":101,"time":1783962244623,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"permission/preset","seq":102,"time":1783962244624,"data":{"preset":"danger-full-access"}} -{"type":"bash/sandbox-mode","seq":103,"time":1783962244624,"data":{"mode":"danger-full-access"}} +{"type":"sandbox/mode","seq":103,"time":1784023678940,"data":{"mode":"danger-full-access"}} {"type":"approval/policy","seq":104,"time":1783962244624,"data":{"policy":"never"}} {"type":"user/message","seq":105,"time":1783962244624,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"context/message","seq":106,"time":1783962244624,"data":{"content":[{"type":"text","text":"The approval policy changed from \"ask\" to \"never\" (changed by the user)."}],"source":{"kind":"plugin","plugin":"user-approval"}},"surfaceOp":"append"} {"type":"step/start","seq":107,"time":1783962244624,"data":{"turn":2,"step":1}} -{"type":"request/header-delta","seq":108,"time":1783962244624,"data":{"system":{"keepStart":9,"keepEnd":2,"insert":["{{system}}","{{system}}"]}}} +{"type":"request/header-delta","seq":108,"time":1783962244624,"data":{"system":{"keepStart":15,"keepEnd":2,"insert":["{{system}}","{{system}}"]}}} {"type":"assistant/chunk","seq":109,"time":1783860671025,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":110,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":111,"time":1783860671026,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md index 3da863d3b8..f20a32d382 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/permission-switching/system-prompt.golden.md @@ -5,13 +5,19 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. + +Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. + +Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. + Check the [exit code: N] marker on every bash result; investigate failures before moving on. Use the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls. - + Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 1c85ee81ba..fb29d33cd0 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","content"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md index d0ce1272d0..6bb634b339 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/skill-load/system-prompt.golden.md @@ -5,6 +5,12 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. + +Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. + +Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. + Check the [exit code: N] marker on every bash result; investigate failures before moving on. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index c66f5676cc..9ad8d8506c 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md index d0ce1272d0..6bb634b339 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/text-turn/system-prompt.golden.md @@ -5,6 +5,12 @@ You are a coding assistant powered by the deepseek-v4-flash model. Your working Verify your work by running the code or tests. Keep answers brief and factual. +Use the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files. + +Use the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes. + +Use the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session. + Check the [exit code: N] marker on every bash result; investigate failures before moving on. Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl index 04e3c3b59e..9a908f24a3 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl @@ -79,7 +79,7 @@ {"type":"assistant/chunk","seq":77,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":78,"time":1783352265491,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read the file greeting.txt\n2. Append the word WORLD as a second line\n3. Read the file back with cat to confirm\n4. Reply with DONE\n\nLet me start by reading the file to see its contents."},{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"} {"type":"tool/call","seq":79,"time":1783352265491,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} -{"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"Error: unknown tool \"read\""}],"isError":true,"error":{"name":"ToolNotFoundError","code":"UNKNOWN_TOOL"}},"sourceEventSeqs":[79],"surfaceOp":"append"} +{"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"/tmp/acp-snap-cwd-rxbEpP/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[79],"surfaceOp":"append"} {"type":"step/end","seq":81,"time":1783352265504,"data":{"turn":1,"step":1}} {"type":"step/start","seq":82,"time":1783352265505,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":83,"time":1783352266385,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl index d3fd50b416..8f139d7949 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl @@ -55,8 +55,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" its"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contents"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","title":"read","kind":"other","status":"in_progress","rawInput":{"file_path":"greeting.txt"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","status":"failed","content":[{"type":"content","content":{"type":"text","text":"Error: unknown tool \"read\""}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","title":"Read greeting.txt","kind":"read","status":"in_progress","locations":[{"path":"greeting.txt","line":1}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_OjRFB4zvxu6UALDjytZD0978","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" contains"}}}} diff --git a/packages/bash/bash-sandbox/package.json b/packages/bash/bash-sandbox/package.json index 0077511946..73b2b88ac7 100644 --- a/packages/bash/bash-sandbox/package.json +++ b/packages/bash/bash-sandbox/package.json @@ -25,16 +25,15 @@ "@deepseek-ai/dsh-bash": "^0.0.1", "@deepseek-ai/dsh-bash-local": "^0.0.1", "@deepseek-ai/dsh-sandbox": "^0.0.1", + "@deepseek-ai/dsh-sandbox-policy": "^0.0.1", "cordis": "^4.0.0-rc.6" }, - "dependencies": { - "schemastery": "^3.18.0" - }, "devDependencies": { "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", "@deepseek-ai/dsh-sandbox-local": "workspace:^", + "@deepseek-ai/dsh-sandbox-policy": "workspace:^", "node-addon-landlock-run": "0.0.0-test.0", "cordis": "^4.0.0-rc.6" } diff --git a/packages/bash/bash-sandbox/src/index.ts b/packages/bash/bash-sandbox/src/index.ts index 090d06b2fe..ad49a60a84 100644 --- a/packages/bash/bash-sandbox/src/index.ts +++ b/packages/bash/bash-sandbox/src/index.ts @@ -41,31 +41,23 @@ * @module @deepseek-ai/dsh-bash-sandbox */ -import { resolve } from 'node:path' import { Context } from 'cordis' -import z from 'schemastery' import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId } from '@deepseek-ai/dsh-bash' import { SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox' import type { ConfinedSandboxMode, SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox' +import type {} from '@deepseek-ai/dsh-sandbox-policy' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import type { Config as LocalConfig } from '@deepseek-ai/dsh-bash-local' /** - * Plugin config: the local executor's knobs plus the sandbox policy. All - * optional — `static Config` supplies the defaults (`mode: 'read-only'` is the - * fail-safe default; an example that wants a workspace-writable agent opts in - * explicitly). The runner choice is NOT configured here: which platform - * backend confines the command is the `ctx.sandbox` provider's config. + * Plugin config: the local executor's knobs, verbatim. The sandbox policy — + * the default mode and the `workspace-write` boundary root — is NOT here: it + * lives on `ctx.sandboxPolicy` (`@deepseek-ai/dsh-sandbox-policy`), the one + * home both enforcing families read, so bash and fs can never confine to + * different roots. The runner choice is likewise the `ctx.sandbox` provider's + * config, not this executor's. */ -export interface Config extends LocalConfig { - /** File-sandbox mode commands run under (default: `read-only`). */ - mode?: SandboxMode - /** - * Root directory `workspace-write` mode may write under (default: the - * executor's default working directory — `cwd`, else `process.cwd()`). - */ - workspaceRoot?: string -} +export type Config = LocalConfig /** * Quote one string as a single-quoted POSIX shell word (embedded single @@ -141,24 +133,18 @@ function matchesSignature(exitCode: number | null, stderr: string, signatures: r * INSTEAD OF `dsh-bash-local`, together with a `ctx.sandbox` provider, is * the whole swap — the tool layer is untouched). Its configured mode is the * fallback exposed by {@link sandboxMode}; `dsh-tool-bash` folds a session's - * durable `bash/sandbox-mode` override and stamps the effective mode onto each + * durable `sandbox/mode` override and stamps the effective mode onto each * request, while an approved escalation may stamp a strictly wider mode for * one call. The tool's per-agent prompt section states that same effective * mode, and each run's `result.sandbox` reports what actually executed plus * enforcement completeness. */ export class SandboxBashExecutor extends LocalBashExecutor { - static inject = ['sandbox'] + static inject = ['sandbox', 'sandboxPolicy'] - // The sandbox-specific fields intersect the local executor's Config as an - // inline schema call: the config catalog walks `static Config` statically. - static override Config: z = z.intersect([ - LocalBashExecutor.Config, - z.object({ - mode: z.union(['read-only', 'workspace-write', 'danger-full-access'] as const).default('read-only'), - workspaceRoot: z.string(), - }), - ]) + // No own Config: the sandbox default (mode + workspaceRoot) moved to + // ctx.sandboxPolicy, so this executor inherits LocalBashExecutor's Config + // verbatim (the config catalog walks the inherited static). private readonly mode: SandboxMode private readonly workspaceRoot: string @@ -182,12 +168,11 @@ export class SandboxBashExecutor extends LocalBashExecutor { constructor(ctx: Context, config: Config) { super(ctx, config) - // schemastery (static Config) already filled the defaulted fields — the - // cast records that runtime fact (mirrors LocalBashExecutor's config - // cast). `workspaceRoot` and `cwd` have NO schema default, so their - // fallback chain is real branching. - this.mode = config.mode as SandboxMode - this.workspaceRoot = resolve(config.workspaceRoot ?? config.cwd ?? process.cwd()) + // The sandbox default (mode + workspaceRoot) is the one shared policy home + // both enforcing families read; injecting sandboxPolicy guarantees it is + // constructed first. workspaceRoot arrives already resolved absolute. + this.mode = ctx.sandboxPolicy.defaultMode + this.workspaceRoot = ctx.sandboxPolicy.workspaceRoot } /** The configured default mode — the capability fact the tool layer reads. */ diff --git a/packages/bash/bash-sandbox/tests/bwrap.e2e.ts b/packages/bash/bash-sandbox/tests/bwrap.e2e.ts index 6a748bc389..ced6dcea5a 100644 --- a/packages/bash/bash-sandbox/tests/bwrap.e2e.ts +++ b/packages/bash/bash-sandbox/tests/bwrap.e2e.ts @@ -6,6 +6,7 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import { bwrapProfileArgs, LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local' +import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy' import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox' /** @@ -46,7 +47,8 @@ async function tempDir(base: string): Promise { async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-write'): Promise { ctx = new Context() await ctx.plugin(LocalSandboxProvider, {}) - await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 }) + await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace }) + await ctx.plugin(SandboxBashExecutor, { cwd: workspace, timeoutMs: 30_000 }) return ctx.bash as SandboxBashExecutor } diff --git a/packages/bash/bash-sandbox/tests/landlock.e2e.ts b/packages/bash/bash-sandbox/tests/landlock.e2e.ts index 8263dad6fe..b8c86d95b2 100644 --- a/packages/bash/bash-sandbox/tests/landlock.e2e.ts +++ b/packages/bash/bash-sandbox/tests/landlock.e2e.ts @@ -7,6 +7,7 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import { launcherPath } from 'node-addon-landlock-run' import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local' +import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy' import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox' /** @@ -45,7 +46,8 @@ async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-w ctx = new Context() await ctx.plugin(LocalSandboxProvider, {}) ;(ctx.sandbox as LocalSandboxProvider).internals = { probeBwrap: () => false } - await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 }) + await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace }) + await ctx.plugin(SandboxBashExecutor, { cwd: workspace, timeoutMs: 30_000 }) return ctx.bash as SandboxBashExecutor } diff --git a/packages/bash/bash-sandbox/tests/sandbox.spec.ts b/packages/bash/bash-sandbox/tests/sandbox.spec.ts index 4f92ba38f0..58788edcf7 100644 --- a/packages/bash/bash-sandbox/tests/sandbox.spec.ts +++ b/packages/bash/bash-sandbox/tests/sandbox.spec.ts @@ -15,7 +15,8 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import type { BashRunResult, CollectedOutput } from '@deepseek-ai/dsh-bash' import { SANDBOX_UNAVAILABLE, SandboxProvider, SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox' -import type { ConfinedArgv, SandboxPolicy } from '@deepseek-ai/dsh-sandbox' +import type { ConfinedArgv, SandboxMode, SandboxPolicy } from '@deepseek-ai/dsh-sandbox' +import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy' import { classifyDenial, classifyRunnerFailure, SandboxBashExecutor, shellQuote } from '@deepseek-ai/dsh-bash-sandbox' import type { Config } from '@deepseek-ai/dsh-bash-sandbox' @@ -39,9 +40,15 @@ const passthrough = (argv: readonly string[]): ConfinedArgv => /** * Boot a context with a recording fake `ctx.sandbox` (behavior injectable - * per test) and the executor under test on top of it. + * per test), the shared `ctx.sandboxPolicy` (mode + workspaceRoot), and the + * executor under test on top of them. `mode`/`workspaceRoot` route to the + * policy service; the rest (cwd, graceMs, timeoutMs) to the executor. */ -async function setup(config: Config = {}, behavior: (argv: readonly string[], policy: SandboxPolicy) => ConfinedArgv = passthrough) { +async function setup( + config: { mode?: SandboxMode; workspaceRoot?: string } & Config = {}, + behavior: (argv: readonly string[], policy: SandboxPolicy) => ConfinedArgv = passthrough, +) { + const { mode, workspaceRoot, ...execConfig } = config const calls: ConfineCall[] = [] class FakeSandboxProvider extends SandboxProvider { confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv { @@ -51,7 +58,11 @@ async function setup(config: Config = {}, behavior: (argv: readonly string[], po } const ctx = new Context() await ctx.plugin(FakeSandboxProvider) - await ctx.plugin(SandboxBashExecutor, { graceMs: 200, ...config }) + await ctx.plugin(SandboxPolicyService, { + ...mode !== undefined ? { mode } : {}, + ...workspaceRoot !== undefined ? { workspaceRoot } : {}, + }) + await ctx.plugin(SandboxBashExecutor, { graceMs: 200, ...execConfig }) const bash = ctx.bash as SandboxBashExecutor bash.internals = { spillDir } return { ctx, bash, calls } @@ -86,14 +97,14 @@ describe('the provider hand-off', () => { expect(result.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' }) }) - it('workspace-write rides the policy, workspaceRoot falling back to cwd when not configured', async () => { - const { bash, calls } = await setup({ mode: 'workspace-write', cwd: tmpdir() }) + it('workspace-write rides the policy, workspaceRoot falling back to process.cwd() when not configured', async () => { + const { bash, calls } = await setup({ mode: 'workspace-write' }) const result = await bash.run(bash.resolve({ command: 'true' })) expect(result.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' }) - expect(calls[0]?.policy).toEqual({ mode: 'workspace-write', workspaceRoot: resolve(tmpdir()) }) + expect(calls[0]?.policy).toEqual({ mode: 'workspace-write', workspaceRoot: resolve(process.cwd()) }) }) - it('an explicit workspaceRoot wins over cwd', async () => { + it('an explicit workspaceRoot on the policy wins', async () => { const { calls, bash } = await setup({ mode: 'workspace-write', workspaceRoot: '/ws', cwd: tmpdir() }) await bash.run(bash.resolve({ command: 'true' })) expect(calls[0]?.policy.workspaceRoot).toBe(resolve('/ws')) diff --git a/packages/bash/bash-sandbox/tests/seatbelt.e2e.ts b/packages/bash/bash-sandbox/tests/seatbelt.e2e.ts index 8ae25a8d39..9c01442042 100644 --- a/packages/bash/bash-sandbox/tests/seatbelt.e2e.ts +++ b/packages/bash/bash-sandbox/tests/seatbelt.e2e.ts @@ -6,6 +6,7 @@ import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import { LocalSandboxProvider, seatbeltProfileArgs } from '@deepseek-ai/dsh-sandbox-local' +import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy' import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox' /** @@ -43,7 +44,8 @@ async function sandboxedBash(workspace: string, mode: 'read-only' | 'workspace-w ctx = new Context() await ctx.plugin(LocalSandboxProvider, {}) ;(ctx.sandbox as LocalSandboxProvider).internals = { probeBwrap: () => false, probeLandlock: () => 'unusable' } - await ctx.plugin(SandboxBashExecutor, { mode, cwd: workspace, workspaceRoot: workspace, timeoutMs: 30_000 }) + await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace }) + await ctx.plugin(SandboxBashExecutor, { cwd: workspace, timeoutMs: 30_000 }) return ctx.bash as SandboxBashExecutor } diff --git a/packages/bash/bash-sandbox/tsconfig.json b/packages/bash/bash-sandbox/tsconfig.json index 6dad98d54f..531ae140ea 100644 --- a/packages/bash/bash-sandbox/tsconfig.json +++ b/packages/bash/bash-sandbox/tsconfig.json @@ -14,9 +14,6 @@ { "path": "../../../vendor/cordis" }, - { - "path": "../../../vendor/schemastery" - }, { "path": "../../util/brand" }, @@ -26,6 +23,9 @@ { "path": "../../sandbox/sandbox" }, + { + "path": "../../sandbox/sandbox-policy" + }, { "path": "../../bash/bash" }, diff --git a/packages/bash/bash/package.json b/packages/bash/bash/package.json index bfa71d73e3..eb92cfdac5 100644 --- a/packages/bash/bash/package.json +++ b/packages/bash/bash/package.json @@ -24,13 +24,11 @@ "peerDependencies": { "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-sandbox": "^0.0.1", - "@deepseek-ai/dsh-session": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", - "@deepseek-ai/dsh-session": "workspace:^", "cordis": "^4.0.0-rc.6" } } diff --git a/packages/bash/bash/src/index.ts b/packages/bash/bash/src/index.ts index 63c5757175..31135941c2 100644 --- a/packages/bash/bash/src/index.ts +++ b/packages/bash/bash/src/index.ts @@ -19,7 +19,6 @@ import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskId, BashTaskListener, BashTaskRead, OwnerToken } from './types.ts' export { BashTaskId, OwnerToken } from './types.ts' -export { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from './session-mode.ts' export type { BashExecRequest, BashExecSpec, diff --git a/packages/bash/bash/src/types.ts b/packages/bash/bash/src/types.ts index 39dbc162c6..e36c9b32e7 100644 --- a/packages/bash/bash/src/types.ts +++ b/packages/bash/bash/src/types.ts @@ -130,7 +130,7 @@ export interface BashExecRequest { * consumer sets it only from an explicit policy source — an * `'allowed-once'` grant a human just issued through `ctx.approval` (the * escalation flow in the sandbox RFC § Escalation, which outranks), or the - * session's standing override folded from its own `bash/sandbox-mode` + * session's standing override folded from its own `sandbox/mode` * events (the sandbox RFC § Per-session mode switching — the user's recorded per-session * choice). A sandboxing executor confines THIS call under the given mode; * a non-sandboxing executor carries the field and confines nothing (the diff --git a/packages/bash/bash/tsconfig.json b/packages/bash/bash/tsconfig.json index 13d297a292..bbc2fec3cd 100644 --- a/packages/bash/bash/tsconfig.json +++ b/packages/bash/bash/tsconfig.json @@ -19,9 +19,6 @@ }, { "path": "../../sandbox/sandbox" - }, - { - "path": "../../core/session" } ] } diff --git a/packages/bash/tool-bash/package.json b/packages/bash/tool-bash/package.json index eec5d79ccb..3f71e14b87 100644 --- a/packages/bash/tool-bash/package.json +++ b/packages/bash/tool-bash/package.json @@ -25,8 +25,8 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-user-approval": "^0.0.1", "@deepseek-ai/dsh-bash": "^0.0.1", - "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-sandbox": "^0.0.1", + "@deepseek-ai/dsh-sandbox-policy": "^0.0.1", "@deepseek-ai/dsh-system-prompt": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -41,6 +41,7 @@ "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", "@deepseek-ai/dsh-sandbox-local": "workspace:^", + "@deepseek-ai/dsh-sandbox-policy": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 31e6512ae0..694ff8f7e4 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -44,7 +44,7 @@ * that the composition cannot honor. * * Per-session mode switching (the sandbox RFC § Per-session mode switching): a session may carry a - * standing sandbox-mode override — the `bash/sandbox-mode` event fold from + * standing sandbox-mode override — the `sandbox/mode` event fold from * `@deepseek-ai/dsh-bash` — which this plugin makes real at EXECUTION: each * call is stamped `escalation grant > session override > executor default`. * The prompt deliberately does NOT state the mode and no switch is narrated: @@ -60,14 +60,21 @@ import { isAbsolute, resolve as resolvePath } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, TerminalCallView, ToolExecution, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools' import type { Agent } from '@deepseek-ai/dsh-agent' -import { assertNever } from '@deepseek-ai/dsh-llm' import type {} from '@deepseek-ai/dsh-system-prompt' // Side-effect type import: declaration-merges `ctx.approval`, consumed // opportunistically by the escalation gate (`ctx.get('approval')` — the seam // stays optional at runtime, same pattern as dsh-tools' ask routing). import type {} from '@deepseek-ai/dsh-user-approval' import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' -import { BashTaskId, OwnerToken, effectiveSandboxMode } from '@deepseek-ai/dsh-bash' +import { + ESCALATION_TARGETS, + approveEscalation, + escalationHintMarker, + sandboxDenialMarker, + validateEscalationArgs, +} from '@deepseek-ai/dsh-sandbox' +import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy' +import { BashTaskId, OwnerToken } from '@deepseek-ai/dsh-bash' import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash' export const name = 'tool-bash' @@ -93,15 +100,9 @@ function validateBashArgs(args: BashToolArgs): void { if (args.timeoutMs !== undefined && (!Number.isFinite(args.timeoutMs) || args.timeoutMs <= 0)) { throw new Error(`invalid timeoutMs: expected a positive number, got ${JSON.stringify(args.timeoutMs)}`) } - if (args.sandbox_permissions !== undefined && args.justification === undefined) { - throw new Error('invalid escalation: sandbox_permissions requires a justification') - } - if (args.justification !== undefined && args.sandbox_permissions === undefined) { - throw new Error('invalid escalation: justification is only valid together with sandbox_permissions') - } - if (args.justification !== undefined && args.justification.trim().length === 0) { - throw new Error('invalid justification: expected a non-empty sentence') - } + // The escalation pairing (sandbox_permissions ⇔ justification, non-empty) is + // the shared rule both enforcing families validate identically. + validateEscalationArgs(args.sandbox_permissions, args.justification) } /** @@ -132,27 +133,6 @@ interface BashToolArgs { justification?: string } -/** - * The strictly-wider table: what a call whose effective mode is the key may - * escalate TO. Checked at EXECUTION, never baked into the schema — the - * schema's enum is {@link ESCALATION_TARGETS}, because schemas are - * registry-global while the effective mode is per-call truth. - */ -const WIDER_MODES: Record = { - 'read-only': ['workspace-write', 'danger-full-access'], - 'workspace-write': ['danger-full-access'], -} - -/** - * The closed escalation-target vocabulary — every mode a call could ever - * escalate TO (`read-only` is the floor; nothing escalates to it). Advertised - * whenever the mounted executor confines: cutting the enum down to the modes - * wider than the executor's DEFAULT would strand a session whose effective - * mode sits below it (a `danger-full-access` default would advertise nothing - * while a narrower-switched session stays confined with no lever). - */ -const ESCALATION_TARGETS: readonly SandboxMode[] = ['workspace-write', 'danger-full-access'] - /** * The bash tool's static description. The base text is byte-stable regardless * of composition (it is part of the pinned snapshot header); the escalation @@ -222,13 +202,13 @@ export function renderResult( // stays the LAST line (exitStatus() anchors its parse there). Denial is a // reported fact like timeout: the model decides how to react. if (result.sandbox?.denied) { - markers.push(`[sandbox: file access denied under ${result.sandbox.mode} mode]`) + markers.push(sandboxDenialMarker(result.sandbox.mode)) // The same-turn nudge lives at the decision point: only when this // composition advertises the fields (a lever is never hinted that the // schema does not offer), and inside the sandbox marker family so the // exit-code marker stays the last line. if (escalationModes.length > 0) { - markers.push('[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]') + markers.push(escalationHintMarker('command')) } } // Timeout is reported independently of how the process actually ended: a @@ -482,7 +462,7 @@ export function apply(ctx: Context): void { /** * The session's standing mode override for an ordinary (non-escalating) - * call: the `bash/sandbox-mode` fold of the calling agent's log, stamped + * call: the `sandbox/mode` fold of the calling agent's log, stamped * onto the request so EXECUTION follows the same effective mode the prompt * section states. Weakest precedence — an escalation grant (freshly * approved for exactly this call) outranks it, and without either the @@ -495,58 +475,30 @@ export function apply(ctx: Context): void { /** * Resolve a sandbox-escalation request through `ctx.approval` BEFORE - * anything executes. Returns the granted mode to stamp onto the bash - * request; throws the distinct fail-closed text for every other path (no - * service composed, an agent-less execution, a rejection, a cancellation, - * an unanswerable ask) — the registry turns the throw into this call's - * isError result, and nothing has run. The seam is consumed - * opportunistically (`ctx.get`, the dsh-tools ask-routing pattern), so a - * deployment without it degrades per call, never at registration. + * anything executes, delegating the shared fail-closed sequence (strict + * widening, channel resolution, outcome mapping) to + * {@link approveEscalation}. This tool contributes only the composition + * guard (the fields are unadvertised without a sandboxing executor, yet + * schema validation checks advertised keys only, so an unadvertised + * `sandbox_permissions` still reaches execute) and the channel closure over + * `ctx.approval` — consumed opportunistically (`ctx.get`, the dsh-tools + * ask-routing pattern) so a deployment without it degrades per call. */ - const approveEscalation = async (mode: string, justification: string, exec: ToolExecution): Promise => { - // Schema validation only checks ADVERTISED keys, so an unadvertised - // `sandbox_permissions` (no sandboxing executor) still reaches execute — reject it here so a - // human is never prompted to "escalate" a sandbox that is not there. When - // the fields ARE advertised, the registry's SchemaSpec enum has already - // pinned `mode` to this ladder for every caller. + const approveBashEscalation = (mode: string, justification: string, exec: ToolExecution): Promise => { if (escalationModes.length === 0) { throw new Error('sandbox_permissions is not available in this composition (no sandboxing executor to escalate)') } - // Strict widening is an EXECUTION check against the call's effective - // mode — session override ?? executor default, the same fold ordinary - // calls are stamped with — deliberately not a schema constraint (the - // enum is the closed target vocabulary; the effective mode is per-call - // truth). A non-widening request fails closed here and never prompts a - // human. const effectiveMode = (sessionOverride(exec) ?? defaultMode) as SandboxMode - if (!(WIDER_MODES[effectiveMode] ?? []).includes(mode as SandboxMode)) { - throw new Error(`sandbox escalation to "${mode}" is not strictly wider than this call's current "${effectiveMode}" mode`) - } - const approval = ctx.get('approval') - if (approval === undefined) { - throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval service is composed`) - } - if (exec.agent === undefined) { - throw new Error(`sandbox escalation to "${mode}" requires approval, but the call has no agent to route it through`) - } - const outcome = await approval.request({ - agent: exec.agent, - toolName: 'bash', - callId: exec.callId, - // Self-contained for the audit trail: approval/asked stores this - // reason, and the target mode is part of the grant's identity. - reason: `escalate sandbox to ${mode}: ${justification}`, - ...exec.signal ? { signal: exec.signal } : {}, - }) - switch (outcome) { - // The SchemaSpec enum already pinned `mode` to the closed target - // vocabulary; the per-call check above proved it is strictly wider. - case 'allowed-once': return mode as SandboxMode - case 'rejected': throw new Error(`the user rejected escalating this command to "${mode}"`) - case 'cancelled': throw new Error(`approval for escalating to "${mode}" was cancelled`) - case 'unavailable': throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval channel is available`) - default: return assertNever(outcome, 'ApprovalOutcome') - } + return approveEscalation( + { requestedMode: mode, justification, effectiveMode, subject: 'command' }, + { + approver: ctx.get('approval'), + agent: exec.agent, + callId: exec.callId, + toolName: 'bash', + ...exec.signal ? { signal: exec.signal } : {}, + }, + ) } ctx.tools.register(defineTool({ @@ -589,7 +541,7 @@ export function apply(ctx: Context): void { // An ordinary call carries the session's standing override instead — // grant > session override > executor default (see sessionOverride). const sandboxMode = args.sandbox_permissions !== undefined && args.justification !== undefined - ? await approveEscalation(args.sandbox_permissions, args.justification, exec) + ? await approveBashEscalation(args.sandbox_permissions, args.justification, exec) : sessionOverride(exec) // Default the workdir to the calling agent's session cwd so each ACP // session runs in its own workspace (see resolveWorkdir); an explicit @@ -649,9 +601,9 @@ export function apply(ctx: Context): void { // hint). Background denials are only classifiable once the task // settles (the classifier needs the whole stderr), so the marker // rides every read that sees the settled task. - text += `\n[sandbox: file access denied under ${read.task.sandbox.mode} mode]` + text += `\n${sandboxDenialMarker(read.task.sandbox.mode)}` if (escalationModes.length > 0) { - text += '\n[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]' + text += `\n${escalationHintMarker('command')}` } } return Promise.resolve([{ type: 'text', text }]) diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 12b4a53958..867ae359da 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -4,7 +4,7 @@ import { join } from 'node:path' import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' -import { BashExecutor, BashTaskId, setSandboxMode } from '@deepseek-ai/dsh-bash' +import { BashExecutor, BashTaskId } from '@deepseek-ai/dsh-bash' import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskRead, OwnerToken } from '@deepseek-ai/dsh-bash' import { Session, SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -15,6 +15,7 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox' import { SandboxProvider } from '@deepseek-ai/dsh-sandbox' import type { ConfinedArgv } from '@deepseek-ai/dsh-sandbox' +import { SandboxPolicyService, setSandboxMode } from '@deepseek-ai/dsh-sandbox-policy' import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local' import ApprovalService from '@deepseek-ai/dsh-user-approval' import type { ApprovalOutcome } from '@deepseek-ai/dsh-user-approval' @@ -1040,6 +1041,7 @@ describe('sandbox rendering', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG) + await ctx.plugin(SandboxPolicyService, {}) await ctx.plugin(SandboxBashExecutor, { graceMs: 200 }) const bash = ctx.bash as SandboxBashExecutor bash.internals = { spillDir } @@ -1106,6 +1108,7 @@ describe('sandbox rendering', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(FakeProvider) + await ctx.plugin(SandboxPolicyService, {}) await ctx.plugin(SandboxBashExecutor, { graceMs: 200 }) const bash = ctx.bash as SandboxBashExecutor bash.internals = { spillDir } @@ -1126,6 +1129,7 @@ describe('sandbox rendering', () => { runnerCommand: ['bash', '-c', `printf '${signature}\\n' >&2; exit 125`, 'custom-runner'], runnerFailureSignatures: [signature], }) + await ctx.plugin(SandboxPolicyService, {}) await ctx.plugin(SandboxBashExecutor, { graceMs: 200 }) const bash = ctx.bash as SandboxBashExecutor bash.internals = { spillDir } @@ -1144,6 +1148,7 @@ describe('sandbox rendering', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG) + await ctx.plugin(SandboxPolicyService, {}) await ctx.plugin(SandboxBashExecutor, { graceMs: 200 }) const bash = ctx.bash as SandboxBashExecutor bash.internals = { spillDir } @@ -1167,7 +1172,8 @@ describe('sandbox escalation (sandbox_permissions / justification)', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG) - await ctx.plugin(SandboxBashExecutor, { graceMs: 200, ...mode !== undefined ? { mode } : {} }) + await ctx.plugin(SandboxPolicyService, mode !== undefined ? { mode } : {}) + await ctx.plugin(SandboxBashExecutor, { graceMs: 200 }) const bash = ctx.bash as SandboxBashExecutor bash.internals = { spillDir } if (opts.approval === true) await ctx.plugin(ApprovalService, opts.policy !== undefined ? { policy: opts.policy } : {}) @@ -1381,7 +1387,7 @@ describe('sandbox escalation (sandbox_permissions / justification)', () => { }) }) -describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => { +describe('per-session sandbox mode (the sandbox/mode fold)', () => { /** Compose the real sandbox stack (passthrough runner) at a given default mode. */ async function setupModal(mode: 'read-only' | 'workspace-write' | 'danger-full-access' = 'read-only', opts: { approval?: boolean } = {}) { const ctx = new Context() @@ -1389,7 +1395,8 @@ describe('per-session sandbox mode (the bash/sandbox-mode fold)', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(LocalSandboxProvider, PASSTHROUGH_RUNNER_CONFIG) - await ctx.plugin(SandboxBashExecutor, { graceMs: 200, mode }) + await ctx.plugin(SandboxPolicyService, { mode }) + await ctx.plugin(SandboxBashExecutor, { graceMs: 200 }) ;(ctx.bash as SandboxBashExecutor).internals = { spillDir } if (opts.approval === true) await ctx.plugin(ApprovalService) await ctx.plugin(ToolBash) diff --git a/packages/bash/tool-bash/tsconfig.json b/packages/bash/tool-bash/tsconfig.json index c4d738c7dd..b9091bd067 100644 --- a/packages/bash/tool-bash/tsconfig.json +++ b/packages/bash/tool-bash/tsconfig.json @@ -14,9 +14,6 @@ { "path": "../../../vendor/cordis" }, - { - "path": "../../llm/llm" - }, { "path": "../../core/tools" }, @@ -34,6 +31,9 @@ }, { "path": "../../sandbox/sandbox" + }, + { + "path": "../../sandbox/sandbox-policy" } ] } diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 392e3592ad..0f9583855b 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -121,8 +121,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'abstract readText(target: FsTarget, signal?: AbortSignal): Promise', 'abstract streamText(target: FsTarget, signal?: AbortSignal): Promise>', 'abstract listDir(target: FsTarget, signal?: AbortSignal): Promise', - 'abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise', - 'abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise', + 'abstract writeText( target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal, sandboxMode?: SandboxMode, ): Promise', + 'abstract editText( target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal, sandboxMode?: SandboxMode, ): Promise', ], }, { @@ -151,6 +151,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv', ], }, + { + key: 'sandboxPolicy', + summary: 'The sandbox-policy service (`ctx.sandboxPolicy`).', + methods: [], + }, { key: 'sessionPersistence', summary: 'Abstract durable session-persistence service.', diff --git a/packages/fs/README.md b/packages/fs/README.md index ec3bb62afb..8993bd292f 100644 --- a/packages/fs/README.md +++ b/packages/fs/README.md @@ -6,10 +6,11 @@ The filesystem stack: a provider seam (text IO + atomic mutation with an optiona |---|---|---| | `fs/` | Provider seam: text IO + atomic mutation primitives (optional version guard); owns the `fs/*` policy events | `ctx.fs` | | `fs-local/` | Local-filesystem `FileSystem` implementation | (registers `ctx.fs`) | +| `fs-sandbox/` | Sandbox-enforcing `FileSystem`: extends `fs-local` and fences write/edit by the per-call sandbox mode (read-only denies, workspace-write contains to the workspace + temp roots), reads pass through | (registers `ctx.fs`) | | `fs-policy/` | Policy gate plugin: observed-state + read-before-edit + version-guarded write/edit, via the `fs/*` event gate | (no service — `fs/*` listeners) | -| `tool-fs/` | Model-facing `read`/`write`/`edit` tools AND the executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`) | (registers on `ctx.tools`) | +| `tool-fs/` | Model-facing `read`/`write`/`edit` tools AND the executor (reads via `ctx.fs`, owns read windowing, dispatches `fs/*`); advertises the sandbox escalation fields when the mounted `ctx.fs` confines | (registers on `ctx.tools`) | -The interface lives at `fs/fs/`. A sandboxed, remote, or project-scoped filesystem backend can replace `fs-local` without touching the seam, the policy gate, or the model-facing tool schemas. The policy (`fs-policy/`) is a plugin that participates only through the `fs/*` event gate, not a service the tool injects — so dropping it gracefully loses the policy and leaves the unconstrained bare provider rather than breaking the tool. A deployment that loads `tool-fs/` is expected to also load it. +The interface lives at `fs/fs/`. A sandboxed, remote, or project-scoped filesystem backend can replace `fs-local` without touching the seam, the policy gate, or the model-facing tool schemas — `fs-sandbox` is the first such replacement (an in-process path fence over the shared sandbox mode; see [the cross-family fs sandbox RFC](../../docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md)). The policy (`fs-policy/`) is a plugin that participates only through the `fs/*` event gate, not a service the tool injects — so dropping it gracefully loses the policy and leaves the unconstrained bare provider rather than breaking the tool. A deployment that loads `tool-fs/` is expected to also load it. The mode fence and the read-before-edit gate are orthogonal and compose. ## No timeouts on file IO diff --git a/packages/fs/fs-sandbox/README.md b/packages/fs/fs-sandbox/README.md new file mode 100644 index 0000000000..649dfb1e41 --- /dev/null +++ b/packages/fs/fs-sandbox/README.md @@ -0,0 +1,19 @@ +# dsh-fs-sandbox — the sandbox-enforcing filesystem backend + +`SandboxedFileSystem` extends [`LocalFileSystem`](../fs-local/README.md) and registers as `ctx.fs`. It inherits every text-storage mechanic verbatim (resolve, stat, read/stream, list, the atomic write, the read-match-write edit critical section) and adds only a per-call MODE fence on `writeText`/`editText`. Reads always pass through — every mode permits reading. + +Loading it INSTEAD OF `dsh-fs-local`, together with a [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/README.md), is the whole swap; the model-facing tools (`dsh-tool-fs`) are untouched. Injects `sandboxPolicy` for the default mode and the `workspace-write` boundary root — the SAME policy home bash reads, so the two families never confine to different roots. + +## The fence + +The per-call mode is the tool-stamped effective mode (session override or escalation grant), falling back to the deployment default: + +- `read-only` — denies every mutation with the structured `FS_SANDBOX_DENIED`. +- `workspace-write` — allows a mutation only when the target canonicalizes under a writable root: the workspace root plus the platform temp areas (`/tmp`, `os.tmpdir()`), the SAME set the Seatbelt profile grants, derived from the one [`writableRoots`](../../sandbox/README.md) function so the fs fence and the bash runner cannot drift. The target is re-canonicalized immediately before delegating, so an ancestor symlink swapped since the tool resolved it is caught. +- `danger-full-access` — delegates unfenced. + +## Threat model: a policy fence, not a kernel boundary + +The fence is a check in TRUSTED code over a MODEL-CONTROLLED path — the operations are the seam's own (open, rename), only the target path is untrusted, so canonicalize-then-contain is the complete answer to this surface. This mirrors the `code-runtime` stance: containment, not a security boundary. Kernel-grade isolation of untrusted CODE stays `ctx.bash`'s job ([`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md)). The residual TOCTOU (an ancestor symlink swapped between the containment re-check and the syscall) is narrowed by re-canonicalizing immediately before the write and is accepted for this threat model; a kernel-tight boundary needs `openat2`-class primitives not worth their portability cost here. + +A denial is a structured `FsError` (`FS_SANDBOX_DENIED`, carrying the effective mode) — no stderr text inference (unlike bash's kernel denials), because an in-process fence knows exactly what it refused. The model-facing `[sandbox: file access denied under mode]` marker and the one-approved-wider retry live in the tool layer (`dsh-tool-fs`), exactly as bash's do. See [the cross-family fs sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md). diff --git a/packages/fs/fs-sandbox/package.json b/packages/fs/fs-sandbox/package.json new file mode 100644 index 0000000000..3e562984ae --- /dev/null +++ b/packages/fs/fs-sandbox/package.json @@ -0,0 +1,38 @@ +{ + "name": "@deepseek-ai/dsh-fs-sandbox", + "description": "Sandbox-enforcing implementation of the DeepSeek Harness filesystem seam: fences write/edit by the per-call sandbox mode (read-only denies mutation, workspace-write contains it to the workspace + temp roots) while reads pass through", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-fs": "^0.0.1", + "@deepseek-ai/dsh-fs-local": "^0.0.1", + "@deepseek-ai/dsh-sandbox": "^0.0.1", + "@deepseek-ai/dsh-sandbox-policy": "^0.0.1", + "cordis": "^4.0.0-rc.6" + }, + "devDependencies": { + "@deepseek-ai/dsh-fs": "workspace:^", + "@deepseek-ai/dsh-fs-local": "workspace:^", + "@deepseek-ai/dsh-sandbox": "workspace:^", + "@deepseek-ai/dsh-sandbox-policy": "workspace:^", + "cordis": "^4.0.0-rc.6" + } +} diff --git a/packages/fs/fs-sandbox/src/index.ts b/packages/fs/fs-sandbox/src/index.ts new file mode 100644 index 0000000000..d12858e6f0 --- /dev/null +++ b/packages/fs/fs-sandbox/src/index.ts @@ -0,0 +1,155 @@ +/** + * `SandboxedFileSystem`: the sandbox-enforcing implementation of the + * `@deepseek-ai/dsh-fs` provider seam. It extends `LocalFileSystem` so all + * text-storage mechanics — resolve, stat, read/stream, list, the atomic + * write and the read-match-write edit critical section — are the local + * implementation's, verbatim; this package adds only the per-call MODE fence + * on the two mutations. Reads pass through untouched: every mode permits + * reading. + * + * The fence is a policy check in TRUSTED code over a MODEL-CONTROLLED path, + * NOT a kernel boundary — the operations are the seam's own (open, rename), + * and only the target path is untrusted, so canonicalize-then-contain is the + * complete answer to this surface. Kernel-grade isolation of untrusted CODE + * stays `ctx.bash`'s job (`@deepseek-ai/dsh-bash-sandbox`). This mirrors the + * `code-runtime` stance: containment, not a security boundary. The residual + * TOCTOU (an ancestor symlink swapped between the containment re-check and the + * syscall) is narrowed by re-canonicalizing immediately before delegating and + * is accepted for this threat model. + * + * Per-call mode: `read-only` denies every mutation; `workspace-write` allows a + * mutation only when the target canonicalizes under the workspace root or a + * platform temp area (the SAME writable-root set the Seatbelt profile grants, + * derived from the one `writableRoots` function so bash and fs cannot drift); + * `danger-full-access` delegates unfenced. A denial throws the structured + * `FS_SANDBOX_DENIED` — no text inference is needed (unlike bash's kernel + * stderr), because an in-process fence knows exactly what it refused. The + * escalation retry lives in the tool layer (`@deepseek-ai/dsh-tool-fs`), + * exactly as bash's does. + * + * @module @deepseek-ai/dsh-fs-sandbox + */ + +import { sep } from 'node:path' +import { Context } from 'cordis' +import { LocalFileSystem } from '@deepseek-ai/dsh-fs-local' +import type { Config as LocalConfig } from '@deepseek-ai/dsh-fs-local' +import { FsError } from '@deepseek-ai/dsh-fs' +import type { FsEditOutcome, FsEditRequest, FsTarget, FsVersion, FsWriteIntent, FsWriteOutcome } from '@deepseek-ai/dsh-fs' +import { writableRoots } from '@deepseek-ai/dsh-sandbox' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' +import type {} from '@deepseek-ai/dsh-sandbox-policy' + +/** + * Plugin config: the local backend's knobs, verbatim (only `cwd`, the resolve + * base for relative paths). The sandbox default (mode + `workspace-write` + * boundary root) is NOT here — it lives on `ctx.sandboxPolicy`, the one home + * both enforcing families share. + */ +export type Config = LocalConfig + +/** Whether `path` is `root` itself or lies beneath it (both already canonical). */ +function isUnder(path: string, root: string): boolean { + if (path === root) return true + const prefix = root.endsWith(sep) ? root : root + sep + return path.startsWith(prefix) +} + +/** + * Sandbox-enforcing filesystem backend. Registers as `ctx.fs` (loading it + * INSTEAD OF `dsh-fs-local`, together with a `ctx.sandboxPolicy`, is the whole + * swap — the model-facing tools are untouched). Its configured default mode is + * the fallback exposed by {@link sandboxMode}; `dsh-tool-fs` folds a session's + * `sandbox/mode` override and stamps the effective mode onto each mutation, + * while an approved escalation may stamp a strictly wider mode for one call. + */ +export class SandboxedFileSystem extends LocalFileSystem { + static inject = ['sandboxPolicy'] + + private readonly defaultMode: SandboxMode + /** + * The canonical roots a `workspace-write` mutation may land under, computed + * once (the workspace root and platform temp areas are fixed for the + * provider's lifetime): the same set {@link writableRoots} gives every + * enforcement dialect, so the fs fence and the bash runner agree. + */ + private readonly writableRoots: string[] + + constructor(ctx: Context, config: Config) { + super(ctx, config) + this.defaultMode = ctx.sandboxPolicy.defaultMode + this.writableRoots = writableRoots({ mode: 'workspace-write', workspaceRoot: ctx.sandboxPolicy.workspaceRoot }) + } + + /** The deployment default mode — the capability fact the tool layer reads to advertise escalation. */ + override get sandboxMode(): SandboxMode { + return this.defaultMode + } + + /** + * Fence the write by the per-call mode, then delegate to the inherited + * atomic write. See {@link assertWritable}. + * @param target - the resolved target to write. + * @param content - the full new file content. + * @param expected - the write intent guarding the write; omit for unconditional. + * @param signal - aborts before the atomic rename takes effect. + * @param sandboxMode - the per-call mode; omit to use the deployment default. + * @returns the write outcome from the inherited backend. + */ + override async writeText( + target: FsTarget, + content: string, + expected?: FsWriteIntent, + signal?: AbortSignal, + sandboxMode?: SandboxMode, + ): Promise { + await this.assertWritable(target, sandboxMode) + return super.writeText(target, content, expected, signal) + } + + /** + * Fence the edit by the per-call mode, then delegate to the inherited + * atomic edit. See {@link assertWritable}. + * @param target - the resolved target to edit. + * @param edit - the literal search/replace request. + * @param expected - the version guard; omit for an unconditional edit. + * @param signal - aborts before the atomic rename takes effect. + * @param sandboxMode - the per-call mode; omit to use the deployment default. + * @returns the edit outcome from the inherited backend. + */ + override async editText( + target: FsTarget, + edit: FsEditRequest, + expected?: { version: FsVersion }, + signal?: AbortSignal, + sandboxMode?: SandboxMode, + ): Promise { + await this.assertWritable(target, sandboxMode) + return super.editText(target, edit, expected, signal) + } + + /** + * Enforce the per-call mode against `target` before delegating the mutation. + * `read-only` denies; `workspace-write` re-canonicalizes the target NOW + * (`resolve` realpaths the deepest existing ancestor, reflecting a + * concurrently swapped symlink) and requires containment under a writable + * root; `danger-full-access` allows. Throws the structured + * `FS_SANDBOX_DENIED` on refusal — the tool layer maps it to the model-facing + * `[sandbox: …]` marker and the escalation hint. + */ + private async assertWritable(target: FsTarget, sandboxMode?: SandboxMode): Promise { + const mode = sandboxMode ?? this.defaultMode + if (mode === 'danger-full-access') return + if (mode === 'read-only') { + throw new FsError(`cannot write "${target.displayPath}": file access denied under read-only mode`, 'FS_SANDBOX_DENIED') + } + // workspace-write: containment on the FRESH canonical path (catches a + // symlink ancestor swapped since the tool resolved this target). + const fresh = await this.resolve(target.displayPath) + if (!this.writableRoots.some(root => isUnder(fresh.targetKey, root))) { + throw new FsError(`cannot write "${target.displayPath}": file access denied under workspace-write mode`, 'FS_SANDBOX_DENIED') + } + } +} + +export default SandboxedFileSystem diff --git a/packages/fs/fs-sandbox/tests/fs-sandbox.spec.ts b/packages/fs/fs-sandbox/tests/fs-sandbox.spec.ts new file mode 100644 index 0000000000..095cedd695 --- /dev/null +++ b/packages/fs/fs-sandbox/tests/fs-sandbox.spec.ts @@ -0,0 +1,224 @@ +/** + * Tests for the sandbox-enforcing filesystem backend: the per-call mode fence + * on write/edit (read-only denies, workspace-write contains, danger-full-access + * passes through), reads always passing through, the capability fact, and the + * containment matrix — `..` traversal, absolute paths outside, and symlink + * escapes (a symlinked directory inside the workspace pointing out, and a new + * file created under one). The fence is exercised on a real filesystem: a + * denied write leaves no file on disk. + */ + +import { afterEach, beforeEach, describe, expect, it } from 'vitest' +import { mkdir, mkdtemp, readFile, rm, symlink, writeFile } from 'node:fs/promises' +import { existsSync } from 'node:fs' +import { homedir, tmpdir } from 'node:os' +import { join } from 'node:path' +import { Context } from 'cordis' +import { FsError } from '@deepseek-ai/dsh-fs' +import type { FsTarget } from '@deepseek-ai/dsh-fs' +import SandboxPolicyService from '@deepseek-ai/dsh-sandbox-policy' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' +import { SandboxedFileSystem } from '@deepseek-ai/dsh-fs-sandbox' + +let base: string +let workspace: string +let outside: string +let ctx: Context +let fs: SandboxedFileSystem +let fiber: Awaited> + +async function boot(mode: SandboxMode): Promise { + ctx = new Context() + await ctx.plugin(SandboxPolicyService, { mode, workspaceRoot: workspace }) + fiber = await ctx.plugin(SandboxedFileSystem, { cwd: workspace }) + fs = ctx.fs as SandboxedFileSystem +} + +beforeEach(async () => { + // Base under HOME, deliberately NOT tmpdir: `workspace-write` grants /tmp and + // os.tmpdir() (parity with the bash runner), so an "outside" dir under tmpdir + // would be legitimately writable. Sibling dirs under HOME are outside every + // grant, so containment failures are real denials. (The bwrap e2e roots its + // workspaces under HOME for the same reason.) + base = await mkdtemp(join(homedir(), '.dsh-fssbx-')) + workspace = join(base, 'ws') + outside = join(base, 'out') + await mkdir(workspace) + await mkdir(outside) +}) +afterEach(async () => { + await fiber?.dispose() + await rm(base, { recursive: true, force: true }) +}) + +/** Resolve a path through the backend and return its target. */ +function target(path: string): Promise { + return fs.resolve(path) +} + +describe('the capability fact', () => { + it('reports the deployment default mode (what the tool layer advertises against)', async () => { + await boot('workspace-write') + expect(fs.sandboxMode).toBe('workspace-write') + }) +}) + +describe('read-only', () => { + beforeEach(() => boot('read-only')) + + it('denies write, leaving no file on disk', async () => { + const path = join(workspace, 'denied.txt') + await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + expect(existsSync(path)).toBe(false) + }) + + it('denies edit of an existing file (the content is unchanged)', async () => { + const path = join(workspace, 'file.txt') + await writeFile(path, 'original') + await expect(fs.editText(await target(path), { oldString: 'original', newString: 'changed', replaceAll: false })) + .rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + expect(await readFile(path, 'utf8')).toBe('original') + }) + + it('allows reads (every mode permits reading)', async () => { + const path = join(workspace, 'readable.txt') + await writeFile(path, 'hello') + expect(await fs.readText(await target(path))).toBe('hello') + }) +}) + +describe('workspace-write containment', () => { + beforeEach(() => boot('workspace-write')) + + it('a write under the workspace lands', async () => { + const path = join(workspace, 'nested', 'ok.txt') + const outcome = await fs.writeText(await target(path), 'inside') + expect(outcome.operation).toBe('create') + expect(await readFile(path, 'utf8')).toBe('inside') + }) + + it('a write to the platform temp area lands (parity with the bash runner grant)', async () => { + const path = join(await mkdtemp(join(tmpdir(), 'dsh-fssbx-tmp-')), 'temp.txt') + await fs.writeText(await target(path), 'temp') + expect(await readFile(path, 'utf8')).toBe('temp') + }) + + it('an absolute path outside the workspace is denied, no file created', async () => { + const path = join(outside, 'escape.txt') + await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + expect(existsSync(path)).toBe(false) + }) + + it('a `..` traversal out of the workspace is denied', async () => { + const path = join(workspace, '..', 'sibling-escape.txt') + await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + expect(existsSync(join(workspace, '..', 'sibling-escape.txt'))).toBe(false) + }) + + it('a symlinked directory inside the workspace pointing OUT is denied (canonicalized before containment)', async () => { + // workspace/link -> outside ; writing workspace/link/f.txt would land in outside/f.txt. + await symlink(outside, join(workspace, 'link')) + const path = join(workspace, 'link', 'f.txt') + await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + expect(existsSync(join(outside, 'f.txt'))).toBe(false) + }) + + it('a NEW file created under a symlinked-out directory is denied (deepest-ancestor realpath)', async () => { + await symlink(outside, join(workspace, 'link')) + const path = join(workspace, 'link', 'newdir', 'deep.txt') + await expect(fs.writeText(await target(path), 'x')).rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + expect(existsSync(join(outside, 'newdir'))).toBe(false) + }) + + it('an edit outside the workspace is denied; the original is untouched', async () => { + const path = join(outside, 'file.txt') + await writeFile(path, 'original') + await expect(fs.editText(await target(path), { oldString: 'original', newString: 'x', replaceAll: false })) + .rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + expect(await readFile(path, 'utf8')).toBe('original') + }) + + it('an edit inside the workspace lands', async () => { + const path = join(workspace, 'edit.txt') + await writeFile(path, 'original') + const outcome = await fs.editText(await target(path), { oldString: 'original', newString: 'changed', replaceAll: false }) + expect(outcome.after).toBe('changed') + expect(await readFile(path, 'utf8')).toBe('changed') + }) + + it('the workspace root itself passes the fence (path equal to a writable root), failing only on file type', async () => { + // isUnder's path-equals-root branch: the fence allows the root, and the + // write then fails because the root is a directory, not a regular file. + await expect(fs.writeText(await target(workspace), 'x')).rejects.toMatchObject({ code: 'FS_NOT_REGULAR_FILE' }) + }) +}) + +describe('workspace-write with the filesystem root as the workspace (a root ending in the path separator)', () => { + it('grants writes anywhere: containment against `/` allows any absolute path', async () => { + // A degenerate but valid config — workspaceRoot '/'. It exercises isUnder's + // separator-suffixed-root branch: `/` already ends in the separator, so the + // prefix stays `/` and every absolute path is contained. + const rootCtx = new Context() + await rootCtx.plugin(SandboxPolicyService, { mode: 'workspace-write', workspaceRoot: '/' }) + const rootFiber = await rootCtx.plugin(SandboxedFileSystem, { cwd: workspace }) + const rootFs = rootCtx.fs as SandboxedFileSystem + try { + const path = join(base, 'anywhere.txt') // under HOME, outside /tmp — allowed only via the `/` root + await rootFs.writeText(await rootFs.resolve(path), 'anywhere') + expect(await readFile(path, 'utf8')).toBe('anywhere') + } finally { + await rootFiber.dispose() + } + }) +}) + +describe('danger-full-access', () => { + beforeEach(() => boot('danger-full-access')) + + it('writes anywhere, unfenced', async () => { + const path = join(outside, 'free.txt') + await fs.writeText(await target(path), 'free') + expect(await readFile(path, 'utf8')).toBe('free') + }) +}) + +describe('the per-call mode override (escalation)', () => { + it('a workspace-write stamp on a read-only default lets a contained write land for that call only', async () => { + await boot('read-only') + const path = join(workspace, 'escalated.txt') + // Default read-only would deny; the per-call workspace-write stamp allows it (contained). + await fs.writeText(await target(path), 'granted', undefined, undefined, 'workspace-write') + expect(await readFile(path, 'utf8')).toBe('granted') + // A neighboring plain call still runs under the read-only default. + await expect(fs.writeText(await target(join(workspace, 'plain.txt')), 'x')) + .rejects.toMatchObject({ code: 'FS_SANDBOX_DENIED' }) + }) + + it('a danger-full-access stamp bypasses the fence for that call', async () => { + await boot('read-only') + const path = join(outside, 'granted-full.txt') + await fs.writeText(await target(path), 'full', undefined, undefined, 'danger-full-access') + expect(await readFile(path, 'utf8')).toBe('full') + }) +}) + +describe('registration and HMR safety', () => { + it('registers as ctx.fs and unregisters cleanly from a child fiber', async () => { + await boot('workspace-write') + expect(ctx.fs).toBeInstanceOf(SandboxedFileSystem) + await fiber.dispose() + expect(ctx.get('fs')).toBeUndefined() + // Re-mount below the disposed one to prove no lingering registration. + fiber = await ctx.plugin(SandboxedFileSystem, { cwd: workspace }) + expect(ctx.fs).toBeInstanceOf(SandboxedFileSystem) + }) +}) + +describe('FsError identity', () => { + it('the denial is a structured FsError distinct from a host permission error', async () => { + await boot('read-only') + const error = await fs.writeText(await target(join(workspace, 'x.txt')), 'x').catch((e: unknown) => e) + expect(error).toBeInstanceOf(FsError) + expect((error as FsError).code).toBe('FS_SANDBOX_DENIED') + }) +}) diff --git a/packages/fs/fs-sandbox/tsconfig.json b/packages/fs/fs-sandbox/tsconfig.json new file mode 100644 index 0000000000..c9e2f629d5 --- /dev/null +++ b/packages/fs/fs-sandbox/tsconfig.json @@ -0,0 +1,30 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../fs" + }, + { + "path": "../fs-local" + }, + { + "path": "../../sandbox/sandbox" + }, + { + "path": "../../sandbox/sandbox-policy" + } + ] +} diff --git a/packages/fs/fs/package.json b/packages/fs/fs/package.json index 813cb04e16..8b02766278 100644 --- a/packages/fs/fs/package.json +++ b/packages/fs/fs/package.json @@ -24,11 +24,13 @@ "peerDependencies": { "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-sandbox": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-sandbox": "workspace:^", "cordis": "^4.0.0-rc.6" } } diff --git a/packages/fs/fs/src/index.ts b/packages/fs/fs/src/index.ts index 1e0ab03b85..35a3ffe9ec 100644 --- a/packages/fs/fs/src/index.ts +++ b/packages/fs/fs/src/index.ts @@ -58,6 +58,7 @@ */ import { Context, Service } from 'cordis' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' import type { FsDirEntry, FsEditOutcome, @@ -174,6 +175,22 @@ export abstract class FileSystem extends Service { super(ctx, 'fs') } + /** + * The sandbox mode this backend enforces on mutations BY DEFAULT, or + * `undefined` when it does not confine at all — the capability fact the tool + * layer reads to advertise the escalation fields honestly (mirrors + * `BashExecutor.sandboxMode`). The base class and the bare local backend + * report `undefined`; a sandboxing backend (`@deepseek-ai/dsh-fs-sandbox`) + * overrides it with the deployment default. A session override may make the + * effective mode narrower or wider, so strict escalation widening is checked + * per call rather than encoded in this default-relative fact. + * @returns the configured default mode of a sandboxing backend; `undefined` + * for a backend that never confines. + */ + get sandboxMode(): SandboxMode | undefined { + return undefined + } + /** * Resolve a model/plugin-supplied path into a stable {@link FsTarget}. May * perform I/O (a remote/sandboxed backend may need a round-trip to map a path @@ -238,9 +255,18 @@ export abstract class FileSystem extends Service { * @param content - the full new file content. * @param expected - the write intent guarding the write; omit for unconditional. * @param signal - aborts before the atomic rename takes effect. + * @param sandboxMode - the per-call sandbox mode this write runs under; a + * sandboxing backend fences the write by it, the bare backend ignores it. + * Omit to leave the backend its own default. * @returns the outcome, including the version the write produced. */ - abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise + abstract writeText( + target: FsTarget, + content: string, + expected?: FsWriteIntent, + signal?: AbortSignal, + sandboxMode?: SandboxMode, + ): Promise /** * Apply a literal edit to an existing UTF-8 text file. When `expected` is @@ -252,9 +278,18 @@ export abstract class FileSystem extends Service { * @param edit - the literal search/replace request. * @param expected - the version guard; omit for an unconditional edit. * @param signal - aborts before the atomic rename takes effect. + * @param sandboxMode - the per-call sandbox mode this edit runs under; a + * sandboxing backend fences the edit by it, the bare backend ignores it. + * Omit to leave the backend its own default. * @returns the outcome, including the version the edit produced. */ - abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise + abstract editText( + target: FsTarget, + edit: FsEditRequest, + expected?: { version: FsVersion }, + signal?: AbortSignal, + sandboxMode?: SandboxMode, + ): Promise } export default FileSystem diff --git a/packages/fs/fs/src/types.ts b/packages/fs/fs/src/types.ts index f6f5b8005f..bfad9df358 100644 --- a/packages/fs/fs/src/types.ts +++ b/packages/fs/fs/src/types.ts @@ -173,6 +173,7 @@ export type FsErrorCode = | 'FS_NOT_TEXT' | 'FS_NOT_REGULAR_FILE' | 'FS_PERMISSION_DENIED' + | 'FS_SANDBOX_DENIED' | 'FS_IO_ERROR' | 'FS_STALE_VERSION' | 'FS_NOT_OBSERVED' diff --git a/packages/fs/fs/tsconfig.json b/packages/fs/fs/tsconfig.json index a352aea65a..eb981277c7 100644 --- a/packages/fs/fs/tsconfig.json +++ b/packages/fs/fs/tsconfig.json @@ -9,6 +9,7 @@ { "path": "../../../vendor/cosmokit" }, { "path": "../../../vendor/cordis" }, { "path": "../../util/brand" }, - { "path": "../../llm/llm" } + { "path": "../../llm/llm" }, + { "path": "../../sandbox/sandbox" } ] } diff --git a/packages/fs/tool-fs/package.json b/packages/fs/tool-fs/package.json index 7e7b78aa38..e6c074c35e 100644 --- a/packages/fs/tool-fs/package.json +++ b/packages/fs/tool-fs/package.json @@ -28,9 +28,12 @@ "peerDependencies": { "@deepseek-ai/dsh-fs": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-sandbox": "^0.0.1", + "@deepseek-ai/dsh-sandbox-policy": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-system-prompt": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", + "@deepseek-ai/dsh-user-approval": "^0.0.1", "cordis": "^4.0.0-rc.6" }, "devDependencies": { @@ -41,9 +44,12 @@ "@deepseek-ai/dsh-fs-local": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-sandbox": "workspace:^", + "@deepseek-ai/dsh-sandbox-policy": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", + "@deepseek-ai/dsh-user-approval": "workspace:^", "cordis": "^4.0.0-rc.6" } } diff --git a/packages/fs/tool-fs/src/edit.ts b/packages/fs/tool-fs/src/edit.ts index 220c850d69..20434f1b67 100644 --- a/packages/fs/tool-fs/src/edit.ts +++ b/packages/fs/tool-fs/src/edit.ts @@ -20,6 +20,7 @@ import type {} from '@deepseek-ai/dsh-fs' import type {} from '@deepseek-ai/dsh-system-prompt' import { computeHunkDiffs, diffsFromMeta, type FsDiffMeta } from './diff.ts' import { sessionCwd } from './session-cwd.ts' +import type { FsSandboxSurface } from './sandbox.ts' /** Validated `edit` arguments after defaulting. */ interface EditInput { @@ -29,6 +30,20 @@ interface EditInput { replaceAll: boolean } +/** + * The `edit` tool's validated argument shape: the base parameters plus the two + * escalation fields, advertised only under a confining `ctx.fs` (absent from + * the schema otherwise, so the validator rejects them before `execute`). + */ +interface EditToolArgs { + file_path: string + old_string: string + new_string: string + replace_all?: boolean + sandbox_permissions?: string + justification?: string +} + /** * Validate value constraints the schema DSL can't express: a non-blank * `file_path`, a non-empty `old_string`, and `old_string !== new_string` @@ -63,8 +78,9 @@ export function formatEditOutput(displayPath: string, replaceAll: boolean): stri /** * Register the `edit` tool and its system-prompt guidance. * @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service. + * @param sandbox - the shared sandbox-escalation surface (advertisement, mode stamping, denial mapping). */ -export function applyEditTool(ctx: Context): void { +export function applyEditTool(ctx: Context, sandbox: FsSandboxSurface): void { ctx.systemPrompt.section({ name: 'tool:edit', order: 102, @@ -79,21 +95,32 @@ export function applyEditTool(ctx: Context): void { old_string: { type: 'string', required: true, description: 'Literal text to replace. Must match exactly.' }, new_string: { type: 'string', required: true, description: 'Literal replacement text. Use an empty string to delete the match.' }, replace_all: { type: 'boolean', description: 'Replace all matches. Defaults to false; when false, old_string must appear exactly once.' }, + ...sandbox.escalationModes.length > 0 ? sandbox.schemaFields() : {}, }, - async execute(args, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> { + async execute(args: EditToolArgs, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> { const input = parseEditArgs(args) + // Resolve the per-call sandbox mode (escalation grant > session override + // > backend default) BEFORE anything executes. + const sandboxMode = await sandbox.stampMode('edit', args, exec) const cwd = sessionCwd(exec) const target = await ctx.fs.resolve(input.filePath, cwd !== undefined ? { cwd } : undefined) // Single-slot decision: the policy plugin returns { version: vObserved } or // throws FS_NOT_OBSERVED; the bare default is undefined (unconditional edit). // No stat — the bare default never manufactures a version basis. const intent = await ctx.waterfall('fs/edit-intent', target, exec, () => undefined) - const outcome = await ctx.fs.editText( - target, - { oldString: input.oldString, newString: input.newString, replaceAll: input.replaceAll }, - intent, - exec.signal, - ) + let outcome + try { + outcome = await ctx.fs.editText( + target, + { oldString: input.oldString, newString: input.newString, replaceAll: input.replaceAll }, + intent, + exec.signal, + sandboxMode, + ) + } catch (error: unknown) { + // A sandbox denial becomes the shared [sandbox: …] marker; any other error passes through. + throw sandbox.mapError(error, sandboxMode) + } // Record the observed version (a no-op when no policy plugin listens). ctx.emit('fs/observed', target, outcome.version, exec) // The result-time applied-hunk diff (before→after with context lines). An diff --git a/packages/fs/tool-fs/src/index.ts b/packages/fs/tool-fs/src/index.ts index f5d0d9ef91..9644b941cb 100644 --- a/packages/fs/tool-fs/src/index.ts +++ b/packages/fs/tool-fs/src/index.ts @@ -24,10 +24,12 @@ import type { Context } from 'cordis' import z from 'schemastery' +import type {} from '@deepseek-ai/dsh-user-approval' import { applyReadTool, READ_LIMIT, STREAM_MIN_SIZE } from './read.ts' import { applyWriteTool } from './write.ts' import { applyEditTool } from './edit.ts' import { READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from './read-render.ts' +import { FsSandboxSurface } from './sandbox.ts' export { READ_LIMIT, STREAM_MIN_SIZE, applyReadTool, parseReadArgs } from './read.ts' export type { ReadToolCaps } from './read.ts' @@ -37,6 +39,8 @@ export { READ_MAX_BYTES, READ_MAX_LINE_LENGTH, buildWindow, formatReadOutput } f export type { FileReadOutcome, FileTextLine, ReadWindow, WindowResult } from './read-render.ts' export { DIFF_CONTEXT, computeHunkDiffs, diffsFromMeta } from './diff.ts' export type { FsDiffMeta } from './diff.ts' +export { FsSandboxSurface } from './sandbox.ts' +export type { EscalationSchemaFields, FsEscalationArgs } from './sandbox.ts' /** Cordis plugin name used by loader diagnostics. */ export const name = 'tool-fs' @@ -87,6 +91,10 @@ export function apply(ctx: Context, config: Config): void { maxBytes: resolved.readMaxBytes, streamMinSize: resolved.readStreamMinSize, }) - applyWriteTool(ctx) - applyEditTool(ctx) + // One escalation surface shared by both mutating tools: advertisement gating, + // per-call mode stamping, and denial-marker mapping, all keyed off whether + // the mounted ctx.fs confines (ctx.fs.sandboxMode). + const sandbox = new FsSandboxSurface(ctx) + applyWriteTool(ctx, sandbox) + applyEditTool(ctx, sandbox) } diff --git a/packages/fs/tool-fs/src/sandbox.ts b/packages/fs/tool-fs/src/sandbox.ts new file mode 100644 index 0000000000..2149ee07a6 --- /dev/null +++ b/packages/fs/tool-fs/src/sandbox.ts @@ -0,0 +1,132 @@ +/** + * The sandbox-escalation surface shared by the `write` and `edit` tools: the + * per-call mode stamp, the advertised escalation fields, and the denial-marker + * mapping — all delegating the vocabulary and the fail-closed approval + * sequence to `@deepseek-ai/dsh-sandbox` (the same pieces `@deepseek-ai/dsh-tool-bash` + * uses), so bash and fs escalate identically. Built ONCE per plugin from + * `ctx.fs.sandboxMode` (the capability fact — is a confining backend mounted?) + * and shared by both mutating tools. + * + * @module @deepseek-ai/dsh-tool-fs/sandbox + */ + +import type { Context } from 'cordis' +import type { ToolExecution } from '@deepseek-ai/dsh-tools' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' +import { ESCALATION_TARGETS, approveEscalation, escalationHintMarker, sandboxDenialMarker, validateEscalationArgs } from '@deepseek-ai/dsh-sandbox' +import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy' +import { FsError } from '@deepseek-ai/dsh-fs' + +/** The two escalation arguments a mutating tool may carry (advertised only under a confining backend). */ +export interface FsEscalationArgs { + sandbox_permissions?: string + justification?: string +} + +/** The schema fields for the escalation arguments, spread into a tool's `parameters` when a confining backend is mounted. */ +export interface EscalationSchemaFields { + sandbox_permissions: { type: 'string'; enum: string[]; description: string } + justification: { type: 'string'; description: string } +} + +/** + * The filesystem escalation surface: advertisement gating, per-call mode + * stamping (folding the session's `sandbox/mode` override), the one-approved + * wider retry, and denial-marker mapping. A pure product of `ctx` at plugin + * apply time. + */ +export class FsSandboxSurface { + /** The escalation targets this composition advertises (`[]` when no confining backend is mounted). */ + readonly escalationModes: readonly SandboxMode[] + /** The backend's default mode, or `undefined` when `ctx.fs` does not confine. */ + private readonly defaultMode: SandboxMode | undefined + + constructor(private readonly ctx: Context) { + this.defaultMode = ctx.fs.sandboxMode + this.escalationModes = this.defaultMode === undefined ? [] : ESCALATION_TARGETS + } + + /** + * The escalation schema fields for a mutating tool's `parameters`. Call it + * only under a confining backend (guard on {@link escalationModes}); the + * enum pins the closed target vocabulary, the strict-wider check happens per + * call at execution. + * @returns the two escalation parameter specs. + */ + schemaFields(): EscalationSchemaFields { + return { + sandbox_permissions: { + type: 'string', + enum: [...this.escalationModes], + description: 'The wider sandbox mode this file operation needs. Only valid as a one-shot retry ' + + 'of an operation the sandbox just denied; requires justification and user approval.', + }, + justification: { + type: 'string', + description: 'Required with sandbox_permissions: one sentence for the user explaining ' + + 'why this exact file operation needs the wider access.', + }, + } + } + + /** + * The session's standing mode override for an ordinary (non-escalating) + * call — the `sandbox/mode` fold of the calling agent's log. Undefined for a + * non-confining backend and for agent-less callers. + */ + private sessionOverride(exec: ToolExecution): SandboxMode | undefined { + if (this.defaultMode === undefined || exec.agent === undefined) return undefined + return effectiveSandboxMode(exec.agent.session.events) + } + + /** + * The mode to STAMP onto this mutation: an approved escalation grant (a + * strictly wider retry resolved through `ctx.approval` before anything + * executes), else the session's standing override, else `undefined` (the + * backend applies its own default). Validates the escalation argument + * pairing first. + * @param toolName - the mutating tool's name, for the approval audit trail. + * @param args - the call's escalation arguments. + * @param exec - the tool-execution context (agent, callId, signal). + * @returns the mode to pass to the mutation, or undefined for the backend default. + */ + async stampMode(toolName: string, args: FsEscalationArgs, exec: ToolExecution): Promise { + validateEscalationArgs(args.sandbox_permissions, args.justification) + if (args.sandbox_permissions === undefined || args.justification === undefined) { + return this.sessionOverride(exec) + } + if (this.escalationModes.length === 0) { + throw new Error('sandbox_permissions is not available in this composition (no sandboxing filesystem to escalate)') + } + const effectiveMode = (this.sessionOverride(exec) ?? this.defaultMode) as SandboxMode + return approveEscalation( + { requestedMode: args.sandbox_permissions, justification: args.justification, effectiveMode, subject: 'operation' }, + { + approver: this.ctx.get('approval'), + agent: exec.agent, + callId: exec.callId, + toolName, + ...exec.signal ? { signal: exec.signal } : {}, + }, + ) + } + + /** + * Map a thrown provider error for the model: a `FS_SANDBOX_DENIED` becomes an + * error whose text is the shared `[sandbox: …]` denial marker plus the + * same-turn escalation hint, so a policy denial reads identically to bash's; + * any other error passes through unchanged. A `FS_SANDBOX_DENIED` only arises + * under a confining backend, which always advertises the escalation fields, + * so the hint always applies here. + * @param error - the error thrown by the mutation. + * @param stampedMode - the mode stamped onto the call (names the mode in the marker). + * @returns the error to throw — the marker error for a sandbox denial, else the original. + */ + mapError(error: unknown, stampedMode: SandboxMode | undefined): unknown { + if (!(error instanceof FsError) || error.code !== 'FS_SANDBOX_DENIED') return error + // A FS_SANDBOX_DENIED only arises under a confining backend, so defaultMode + // (hence the resolved mode) is defined here. + const mode = (stampedMode ?? this.defaultMode) as SandboxMode + return new Error(`${sandboxDenialMarker(mode)}\n${escalationHintMarker('operation')}`) + } +} diff --git a/packages/fs/tool-fs/src/write.ts b/packages/fs/tool-fs/src/write.ts index fd4eec45f3..ffa9e50b37 100644 --- a/packages/fs/tool-fs/src/write.ts +++ b/packages/fs/tool-fs/src/write.ts @@ -20,6 +20,7 @@ import type {} from '@deepseek-ai/dsh-fs' import type {} from '@deepseek-ai/dsh-system-prompt' import { computeHunkDiffs, diffsFromMeta, type FsDiffMeta } from './diff.ts' import { sessionCwd } from './session-cwd.ts' +import type { FsSandboxSurface } from './sandbox.ts' /** * Validate value constraints the schema DSL can't express: only a non-blank @@ -47,11 +48,24 @@ ${verb} file ` } +/** + * The `write` tool's validated argument shape: the base parameters plus the + * two escalation fields, advertised only under a confining `ctx.fs` (absent + * from the schema otherwise, so the validator rejects them before `execute`). + */ +interface WriteToolArgs { + file_path: string + content: string + sandbox_permissions?: string + justification?: string +} + /** * Register the `write` tool and its system-prompt guidance. * @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service. + * @param sandbox - the shared sandbox-escalation surface (advertisement, mode stamping, denial mapping). */ -export function applyWriteTool(ctx: Context): void { +export function applyWriteTool(ctx: Context, sandbox: FsSandboxSurface): void { ctx.systemPrompt.section({ name: 'tool:write', order: 101, @@ -64,15 +78,27 @@ export function applyWriteTool(ctx: Context): void { parameters: { file_path: { type: 'string', required: true, description: 'Path to write, resolved by the filesystem backend.' }, content: { type: 'string', required: true, description: 'Full UTF-8 text content to write.' }, + ...sandbox.escalationModes.length > 0 ? sandbox.schemaFields() : {}, }, - async execute(args, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> { + async execute(args: WriteToolArgs, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> { const input = parseWriteArgs(args) + // Resolve the per-call sandbox mode (escalation grant > session override + // > backend default) BEFORE anything executes; an escalating call + // resolves approval here and throws its distinct text on any non-grant. + const sandboxMode = await sandbox.stampMode('write', args, exec) const cwd = sessionCwd(exec) const target = await ctx.fs.resolve(input.filePath, cwd !== undefined ? { cwd } : undefined) // Single-slot decision: the policy plugin produces createIfAbsent/ // replaceIfVersion; the bare default is undefined (unconditional). No stat. const intent = await ctx.waterfall('fs/write-intent', target, exec, () => undefined) - const outcome = await ctx.fs.writeText(target, input.content, intent, exec.signal) + let outcome: FsWriteOutcome + try { + outcome = await ctx.fs.writeText(target, input.content, intent, exec.signal, sandboxMode) + } catch (error: unknown) { + // A sandbox denial becomes the shared [sandbox: …] marker (the model + // recognizes it from bash); any other error passes through. + throw sandbox.mapError(error, sandboxMode) + } // Record the observed version (a no-op when no policy plugin listens). ctx.emit('fs/observed', target, outcome.version, exec) // Attach a contextual hunk as `meta` ONLY for an overwrite (a before-version diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index c17bd875ba..05238c6593 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -27,6 +27,8 @@ import * as FsPolicy from '@deepseek-ai/dsh-fs-policy' import * as ToolFs from '@deepseek-ai/dsh-tool-fs' import { formatReadOutput, STREAM_MIN_SIZE } from '@deepseek-ai/dsh-tool-fs' import type { FileReadOutcome } from '@deepseek-ai/dsh-tool-fs' +import ApprovalService from '@deepseek-ai/dsh-user-approval' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' /** An in-memory fake provider; a test can arm a rejection on any primitive. */ class FakeFs extends FileSystem { @@ -570,3 +572,163 @@ describe('read caps are plugin config', () => { expect('default' in ToolFs).toBe(false) }) }) + +describe('sandbox escalation surface (write/edit)', () => { + /** A confining fake `ctx.fs`: reports a default mode, records the per-call mode stamped, and can arm a sandbox denial. */ + class SandboxingFakeFs extends FakeFs { + stamped: (SandboxMode | undefined)[] = [] + override get sandboxMode(): SandboxMode { + return 'workspace-write' + } + override async writeText( + target: FsTarget, + content: string, + expected?: FsWriteIntent, + _signal?: AbortSignal, + sandboxMode?: SandboxMode, + ): Promise { + this.stamped.push(sandboxMode) + return super.writeText(target, content, expected) + } + override async editText( + target: FsTarget, + edit: FsEditRequest, + expected?: { version: FsVersion }, + _signal?: AbortSignal, + sandboxMode?: SandboxMode, + ): Promise { + this.stamped.push(sandboxMode) + return super.editText(target, edit, expected) + } + } + + async function setupConfining(opts: { approval?: boolean } = {}) { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(SandboxingFakeFs) + await ctx.plugin(FsPolicy) + if (opts.approval === true) await ctx.plugin(ApprovalService) + await ctx.plugin(ToolFs) + return { ctx, fs: ctx.fs as SandboxingFakeFs } + } + + /** A fake agent whose session records appends (the approval audit surface), mid-turn, carrying the given events for the fold. */ + function escalationAgent(events: Array<{ type: string; data?: Record }> = []): object { + return { + id: 'agent-fs-esc', + session: { + header: { version: 0, id: 'sess-fs-esc', createdAt: 0 }, + events: [{ type: 'turn/start' }, ...events], + append: (type: string, data: Record) => { events.push({ type, data }) }, + }, + } + } + + function fsSchema(ctx: Context, name: 'write' | 'edit') { + const schema = ctx.tools.schemas().find(s => s.name === name) + if (!schema) throw new Error(`${name} tool not registered`) + return schema as unknown as { parameters: { properties: Record } } + } + + it('advertises no escalation fields under a non-confining backend', async () => { + const { ctx } = await setup() + expect(ctx.fs.sandboxMode).toBeUndefined() + for (const name of ['write', 'edit'] as const) { + const props = fsSchema(ctx, name).parameters.properties + expect(props['sandbox_permissions']).toBeUndefined() + expect(props['justification']).toBeUndefined() + } + }) + + it('advertises the closed target vocabulary on write and edit under a confining backend', async () => { + const { ctx } = await setupConfining() + for (const name of ['write', 'edit'] as const) { + const props = fsSchema(ctx, name).parameters.properties + expect(props['sandbox_permissions']?.enum).toEqual(['workspace-write', 'danger-full-access']) + expect(props['justification']).toBeDefined() + } + }) + + it('a plain write stamps nothing (backend default) and no session override folds without one', async () => { + const { ctx, fs } = await setupConfining() + await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent()) + expect(fs.stamped).toEqual([undefined]) + }) + + it('a standing session override folds onto the stamp', async () => { + const { ctx, fs } = await setupConfining() + await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent([{ type: 'sandbox/mode', data: { mode: 'read-only' } }])) + expect(fs.stamped).toEqual(['read-only']) + }) + + it('a denied write maps to the shared marker plus the escalation hint (isError)', async () => { + const { ctx, fs } = await setupConfining() + fs.rejectWith = new FsError('denied', 'FS_SANDBOX_DENIED') + const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent()) + expect(result.isError).toBe(true) + expect(text(result)).toContain('[sandbox: file access denied under workspace-write mode]') + expect(text(result)).toContain('retry this exact operation once with sandbox_permissions') + }) + + it('a non-FS_SANDBOX_DENIED provider error passes through unchanged', async () => { + const { ctx, fs } = await setupConfining() + fs.rejectWith = new FsError('boom', 'FS_IO_ERROR') + const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x' }, escalationAgent()) + expect(result.isError).toBe(true) + expect(text(result)).toContain('boom') + expect(text(result)).not.toContain('[sandbox:') + }) + + it('an approved escalation stamps the granted mode onto that write', async () => { + const { ctx, fs } = await setupConfining({ approval: true }) + ctx.on('approval/request', () => Promise.resolve('allowed-once' as const)) + // Pass a signal so the escalation ask forwards it to the approval request + // (the request rides the tool-execution abort signal). + await ctx.tools.execute({ + callId: CallId('call-fs-esc-grant'), + name: 'write', + arguments: { file_path: 'a.txt', content: 'x', sandbox_permissions: 'danger-full-access', justification: 'the test needs it' }, + agent: escalationAgent() as never, + signal: new AbortController().signal, + }) + expect(fs.stamped).toEqual(['danger-full-access']) + }) + + it('a rejected escalation fails closed with its own text and never mutates', async () => { + const { ctx, fs } = await setupConfining({ approval: true }) + ctx.on('approval/request', () => Promise.resolve('rejected' as const)) + const result = await call(ctx, 'edit', { file_path: 'a.txt', old_string: 'x', new_string: 'y', sandbox_permissions: 'danger-full-access', justification: 'the test needs it' }, escalationAgent()) + expect(result.isError).toBe(true) + expect(text(result)).toContain('the user rejected escalating this operation to "danger-full-access"') + expect(fs.stamped).toEqual([]) + }) + + it('escalation without an approval service fails closed', async () => { + const { ctx } = await setupConfining() + const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'danger-full-access', justification: 'why' }, escalationAgent()) + expect(result.isError).toBe(true) + expect(text(result)).toContain('no approval service is composed') + }) + + it('escalation with an approval service but no agent fails closed', async () => { + const { ctx } = await setupConfining({ approval: true }) + const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'danger-full-access', justification: 'why' }) + expect(result.isError).toBe(true) + expect(text(result)).toContain('no agent to route it through') + }) + + it('rejects the escalation argument pairing (one field without the other)', async () => { + const { ctx } = await setupConfining() + const missing = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'workspace-write' }, escalationAgent()) + expect(missing.isError).toBe(true) + expect(text(missing)).toContain('sandbox_permissions requires a justification') + }) + + it('sandbox_permissions under a non-confining backend fails closed (unadvertised field still reaches execute)', async () => { + const { ctx } = await setup() + const result = await call(ctx, 'write', { file_path: 'a.txt', content: 'x', sandbox_permissions: 'workspace-write', justification: 'why' }, escalationAgent()) + expect(result.isError).toBe(true) + expect(text(result)).toContain('not available in this composition') + }) +}) diff --git a/packages/fs/tool-fs/tsconfig.json b/packages/fs/tool-fs/tsconfig.json index f0133b1d2b..d2adddae03 100644 --- a/packages/fs/tool-fs/tsconfig.json +++ b/packages/fs/tool-fs/tsconfig.json @@ -13,6 +13,9 @@ { "path": "../../core/tools" }, { "path": "../../core/system-prompt" }, { "path": "../fs" }, - { "path": "../fs-policy" } + { "path": "../fs-policy" }, + { "path": "../../sandbox/sandbox" }, + { "path": "../../sandbox/sandbox-policy" }, + { "path": "../../ui/user-approval" } ] } diff --git a/packages/sandbox/README.md b/packages/sandbox/README.md index cb2c7b5747..902b215280 100644 --- a/packages/sandbox/README.md +++ b/packages/sandbox/README.md @@ -1,12 +1,13 @@ # sandbox/ — process-sandbox capability family -The confinement half of the [capability-seam split](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md): an abstract provider interface and platform backends. Consumers hand `ctx.sandbox` the exact argv they are about to spawn and spawn the returned (wrapped) argv instead; policy (`SandboxPolicy`: mode + workspace root) rides each call, so different consumers confine under different policies at the same instant. All **product** packages. +The confinement half of the [capability-seam split](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md): an abstract provider interface, platform backends, and the shared policy home. Consumers hand `ctx.sandbox` the exact argv they are about to spawn and spawn the returned (wrapped) argv instead; policy (`SandboxPolicy`: mode + workspace root) rides each call, so different consumers confine under different policies at the same instant. All **product** packages. | Package | Role | ctx key | |---|---|---| -| `sandbox/` | Abstract process-sandbox seam (the `SandboxProvider` contract + the mode/enforcement/policy vocabulary) | `ctx.sandbox` | +| `sandbox/` | Abstract process-sandbox seam (the `SandboxProvider` contract + the mode/enforcement/policy vocabulary) plus the shared ESCALATION kit (`approveEscalation`, the strictly-wider ladder, the denial/hint markers) and the `writableRoots` derivation every enforcement dialect shares | `ctx.sandbox` | | `sandbox-local/` | Local backends by platform chain: Linux `bwrap` else the `landlock-run` launcher (the npm-distributed [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run) family, built and released from its own repository), darwin `sandbox-exec`/Seatbelt — multi-candidate chains functionally probed, sole candidates selected directly, verdict cached, fail-closed | (registers `ctx.sandbox`) | +| `sandbox-policy/` | The policy home: the deployment default (mode + `workspace-write` boundary root) and the per-session `sandbox/mode` override (event + fold + write path). Both enforcing families read it, so bash and fs can never confine to different roots | `ctx.sandboxPolicy` | The seam confines SAME-WORLD subprocesses only (shared filesystem and kernel). Containers, microVMs, and remote executors are NOT backends here — they replace whole capability implementations (`ctx.bash`, `ctx.fs`) as environment-coherent groups; the boundary is recorded in [the sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). -Consumers today: [`bash/bash-sandbox`](../bash/bash-sandbox/) (wraps `['bash', '-c', command]`; see [the acp-agent example's default composition](../../examples/acp-agent/) for the composed leaf). In-process tools (fs/web) cannot be confined by an OS wrapper — their sandbox semantics are policy at their own seams (the sandbox RFC's cross-family phase). +Consumers today: [`bash/bash-sandbox`](../bash/bash-sandbox/) (wraps `['bash', '-c', command]` through `ctx.sandbox`) and [`fs/fs-sandbox`](../fs/fs-sandbox/) (an in-process path fence, not an argv wrapper — reads `ctx.sandboxPolicy` and enforces the shared mode on write/edit). The cross-family boundary is the sandbox RFC's [cross-family fs sandbox](../../docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md) phase; the shared vocabulary lets both families teach the model one denial marker and one escalation flow. diff --git a/packages/sandbox/sandbox-policy/README.md b/packages/sandbox/sandbox-policy/README.md new file mode 100644 index 0000000000..0fdfb4b5a9 --- /dev/null +++ b/packages/sandbox/sandbox-policy/README.md @@ -0,0 +1,23 @@ +# dsh-sandbox-policy — the sandbox policy home (`ctx.sandboxPolicy`) + +The single owner of the deployment's sandbox policy: the file-effect [`SandboxMode`](../sandbox/README.md) a session starts from, the `workspace-write` boundary root, and the per-session `sandbox/mode` override every enforcing capability family reads. + +## Why a shared home + +Two families enforce the same mode vocabulary: the sandboxed bash executor (`@deepseek-ai/dsh-bash-sandbox`) and the sandboxed filesystem provider (`@deepseek-ai/dsh-fs-sandbox`). If each held its own `mode` + `workspaceRoot` config, the two could drift into a split world — bash confined to one root while fs fences another, exactly what [the sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md) warns against. Both inject `ctx.sandboxPolicy` and read the SAME default instead. The [cross-family fs sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md) records the decision. + +## Config + +- `mode` — the deployment default `SandboxMode` (`read-only` / `workspace-write` / `danger-full-access`), validated at load. Default `read-only` (fail-safe). +- `workspaceRoot` — the absolute directory `workspace-write` may write under. Default `process.cwd()`, resolved absolute either way. + +## Surface + +- `ctx.sandboxPolicy.defaultMode` / `ctx.sandboxPolicy.workspaceRoot` — the deployment default the enforcing implementations read for their resolve fallback and boundary. +- `effectiveSandboxMode(events)` — the pure fold of a session's `sandbox/mode` events (the last switch wins, or `undefined`). The tool layers apply it to stamp each call, so neither the executor nor the provider depends on session events. +- `setSandboxMode(session, mode)` — THE write path for a per-session override: appends exactly one `sandbox/mode` event. The switch IS its event; nothing mutates the mode out of band. +- `SANDBOX_MODES` — every mode, for option advertisement and runtime validation. + +## The per-session store + +A runtime switch (an ACP `session/set_config_option`, a test scenario) is one log-only `sandbox/mode` event on the session it applies to. `effective = fold(events) ?? the deployment default`, so an override survives restart by replay, two sessions never see each other's state, and there is no external config store. The event is log-only (the `approval/*` precedent): the model learns the mode from the enforcing tools' denial markers, never from the event. Execution honors the fold in each tool layer, weakest-precedence beneath an escalation grant. diff --git a/packages/sandbox/sandbox-policy/package.json b/packages/sandbox/sandbox-policy/package.json new file mode 100644 index 0000000000..4f8568acb9 --- /dev/null +++ b/packages/sandbox/sandbox-policy/package.json @@ -0,0 +1,37 @@ +{ + "name": "@deepseek-ai/dsh-sandbox-policy", + "description": "Sandbox policy home (ctx.sandboxPolicy) for the DeepSeek Harness: the deployment default mode + workspace root and the per-session sandbox/mode override, shared by every enforcing capability family", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-sandbox": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "cordis": "^4.0.0-rc.6" + }, + "dependencies": { + "schemastery": "^3.18.0" + }, + "devDependencies": { + "@deepseek-ai/dsh-sandbox": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "cordis": "^4.0.0-rc.6" + } +} diff --git a/packages/sandbox/sandbox-policy/src/index.ts b/packages/sandbox/sandbox-policy/src/index.ts new file mode 100644 index 0000000000..cd7a1545a8 --- /dev/null +++ b/packages/sandbox/sandbox-policy/src/index.ts @@ -0,0 +1,84 @@ +/** + * The sandbox POLICY home (`ctx.sandboxPolicy`): the single owner of the + * deployment's sandbox default — the file-effect {@link SandboxMode} a session + * starts from and the `workspace-write` boundary root — plus the per-session + * override kit (the `sandbox/mode` event, its fold, and its write path, from + * `./session-mode.ts`). + * + * Both enforcing capability families read the SAME policy here: the sandboxed + * bash executor (`@deepseek-ai/dsh-bash-sandbox`) and the sandboxed filesystem + * provider (`@deepseek-ai/dsh-fs-sandbox`) inject `ctx.sandboxPolicy` for the + * default mode and workspace root, so bash and fs can never confine to + * different roots — the split world the sandbox RFC warns about. The default + * lives here rather than on either executor's config precisely because it is + * one fact two families share. + * + * This service holds only the DEFAULT; the per-session fold + * ({@link effectiveSandboxMode}) is a pure function the tool layers apply to + * stamp each call, so neither the executor nor the provider depends on session + * events. + * + * @module @deepseek-ai/dsh-sandbox-policy + */ + +import { resolve } from 'node:path' +import { Context, Service } from 'cordis' +import z from 'schemastery' +import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' + +export { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from './session-mode.ts' + +declare module 'cordis' { + interface Context { + sandboxPolicy: SandboxPolicyService + } +} + +/** + * Plugin config: the deployment's sandbox default. All optional — `Config` + * supplies the defaults (`mode: 'read-only'` is the fail-safe default; a + * deployment that wants a workspace-writable agent opts in explicitly). The + * runner choice is NOT here (it is the `ctx.sandbox` provider's config), nor + * is any per-family knob: this is the one shared policy home. + */ +export interface Config { + /** File-sandbox mode a session starts from (default: `read-only`). */ + mode?: SandboxMode + /** + * Absolute root directory `workspace-write` may write under (default: + * `process.cwd()`). Both enforcing families fence against this SAME root. + */ + workspaceRoot?: string +} + +/** + * The sandbox-policy service (`ctx.sandboxPolicy`). Owns the deployment + * default mode and workspace root; enforcing implementations read + * {@link defaultMode} and {@link workspaceRoot}, and the tool layers fold each + * session's `sandbox/mode` override with {@link effectiveSandboxMode} on top. + */ +export class SandboxPolicyService extends Service { + // Inline schema call: the config catalog walks `static Config` statically. + static Config: z = z.object({ + mode: z.union(['read-only', 'workspace-write', 'danger-full-access'] as const).default('read-only'), + // No schema default: process.cwd() is resolved in the constructor so the + // stored root is always absolute regardless of how it was supplied. + workspaceRoot: z.string(), + }) + + /** The deployment default mode — the fallback beneath a session override. */ + readonly defaultMode: SandboxMode + /** The absolute `workspace-write` boundary root both families fence against. */ + readonly workspaceRoot: string + + constructor(ctx: Context, config: Config) { + super(ctx, 'sandboxPolicy') + // schemastery (static Config) already filled `mode`; the cast records that + // runtime fact. `workspaceRoot` has NO schema default, so its fallback to + // the process cwd is real branching, resolved absolute either way. + this.defaultMode = config.mode as SandboxMode + this.workspaceRoot = resolve(config.workspaceRoot ?? process.cwd()) + } +} + +export default SandboxPolicyService diff --git a/packages/bash/bash/src/session-mode.ts b/packages/sandbox/sandbox-policy/src/session-mode.ts similarity index 52% rename from packages/bash/bash/src/session-mode.ts rename to packages/sandbox/sandbox-policy/src/session-mode.ts index 03ad6e3d7c..62be36501f 100644 --- a/packages/bash/bash/src/session-mode.ts +++ b/packages/sandbox/sandbox-policy/src/session-mode.ts @@ -1,18 +1,21 @@ /** * Per-session sandbox-mode override: the session log as the store. A runtime * switch (an ACP `session/set_config_option`, a test scenario) is recorded as - * one `bash/sandbox-mode` event on the session it applies to; - * `effective = fold(events) ?? the executor's configured default`, so an - * override survives restart by replay, two sessions can never see each - * other's state, and there is no external config store. The event is - * log-only (the `approval/*` precedent): the model learns the mode from the - * prompt section and the boundary notices in `@deepseek-ai/dsh-tool-bash`, - * never from the event itself. EXECUTION honors the fold in the tool layer — - * it stamps the effective mode onto each call's `BashExecRequest.sandboxMode` - * (weakest-precedence: an escalation grant for the call outranks it) — the - * executor itself stays a config-fixed default plus per-call overrides. + * one `sandbox/mode` event on the session it applies to; + * `effective = fold(events) ?? the deployment default`, so an override + * survives restart by replay, two sessions can never see each other's state, + * and there is no external config store. The event is log-only (the + * `approval/*` precedent): the model learns the mode from the boundary + * markers in the enforcing tools, never from the event itself. EXECUTION + * honors the fold in each tool layer — it stamps the effective mode onto the + * per-call policy carrier (a bash request's `sandboxMode`, an fs mutation's + * `sandboxMode`), weakest-precedence beneath an escalation grant. * - * @module dsh-bash/session-mode + * The override is policy state shared by every enforcing family (bash and + * filesystem alike), so it lives here in the policy package rather than in any + * one capability's seam. + * + * @module dsh-sandbox-policy/session-mode */ import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' @@ -28,7 +31,7 @@ declare module '@deepseek-ai/dsh-session' { * from position (an event after the log's last `request/header*` was a * runtime switch by the user; see the tool layer's narrator). */ - 'bash/sandbox-mode': { mode: SandboxMode } + 'sandbox/mode': { mode: SandboxMode } } } @@ -36,30 +39,30 @@ declare module '@deepseek-ai/dsh-session' { export const SANDBOX_MODES: readonly SandboxMode[] = ['read-only', 'workspace-write', 'danger-full-access'] /** - * The session's sandbox-mode override: the last `bash/sandbox-mode` event in - * the log, or undefined when the session never switched (callers apply the - * executor's configured default). The pure fold — resume needs no catch-up - * machinery because replaying the log IS the state. + * The session's sandbox-mode override: the last `sandbox/mode` event in the + * log, or undefined when the session never switched (callers apply the + * deployment default). The pure fold — resume needs no catch-up machinery + * because replaying the log IS the state. * @param events - session events in log order (other event types are skipped). * @returns the mode of the last switch event, or undefined without one. */ export function effectiveSandboxMode(events: readonly SessionEvent[]): SandboxMode | undefined { for (let index = events.length - 1; index >= 0; index -= 1) { const event = events[index] as SessionEvent - if (event.type === 'bash/sandbox-mode') return event.data.mode + if (event.type === 'sandbox/mode') return event.data.mode } return undefined } /** * THE write path for a session's sandbox-mode override: appends exactly one - * `bash/sandbox-mode` event — the switch IS its event; nothing mutates mode - * state out of band. Takes effect on the session's next bash call and next - * prompt assembly (the consumers fold on every read). + * `sandbox/mode` event — the switch IS its event; nothing mutates mode state + * out of band. Takes effect on the session's next confined call (bash or fs) + * — the consumers fold on every read. * @param session - the session the override belongs to. - * @param mode - the mode every subsequent bash call in this session runs + * @param mode - the mode every subsequent confined call in this session runs * under (until the next switch). */ export function setSandboxMode(session: Session, mode: SandboxMode): void { - session.append('bash/sandbox-mode', { mode }) + session.append('sandbox/mode', { mode }) } diff --git a/packages/sandbox/sandbox-policy/tests/policy.spec.ts b/packages/sandbox/sandbox-policy/tests/policy.spec.ts new file mode 100644 index 0000000000..52476fdece --- /dev/null +++ b/packages/sandbox/sandbox-policy/tests/policy.spec.ts @@ -0,0 +1,67 @@ +/** + * Tests for the sandbox-policy home: the deployment default (mode + + * workspaceRoot) the service exposes, and the per-session `sandbox/mode` + * override kit (fold + write path) both enforcing families read. + */ + +import { resolve } from 'node:path' +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { Session, SessionId } from '@deepseek-ai/dsh-session' +import SandboxPolicyService, { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-sandbox-policy' + +async function mounted(config: { mode?: 'read-only' | 'workspace-write' | 'danger-full-access'; workspaceRoot?: string } = {}) { + const ctx = new Context() + await ctx.plugin(SandboxPolicyService, config) + return ctx +} + +describe('SandboxPolicyService', () => { + it('defaults to read-only under the process cwd', async () => { + const ctx = await mounted() + expect(ctx.sandboxPolicy.defaultMode).toBe('read-only') + expect(ctx.sandboxPolicy.workspaceRoot).toBe(resolve(process.cwd())) + }) + + it('carries a configured mode and resolves the workspace root absolute', async () => { + const ctx = await mounted({ mode: 'workspace-write', workspaceRoot: '/ws/../ws/./sub' }) + expect(ctx.sandboxPolicy.defaultMode).toBe('workspace-write') + expect(ctx.sandboxPolicy.workspaceRoot).toBe(resolve('/ws/../ws/./sub')) + }) + + it('rejects a mode outside the closed vocabulary at load', async () => { + const ctx = new Context() + // schemastery rejects the union violation when the plugin loads. + await expect(ctx.plugin(SandboxPolicyService, { mode: 'yolo' as never })).rejects.toThrow() + }) + + it('unregisters cleanly from a child fiber (HMR safety)', async () => { + const ctx = new Context() + const fiber = await ctx.plugin(SandboxPolicyService, {}) + expect(ctx.sandboxPolicy).toBeDefined() + await fiber.dispose() + expect(ctx.get('sandboxPolicy')).toBeUndefined() + }) +}) + +describe('the sandbox/mode session kit', () => { + it('SANDBOX_MODES lists every mode for advertisement and validation', () => { + expect(SANDBOX_MODES).toEqual(['read-only', 'workspace-write', 'danger-full-access']) + }) + + it('effectiveSandboxMode folds to the last switch, or undefined without one', () => { + const session = new Session(SessionId('sess-fold')) + expect(effectiveSandboxMode(session.events)).toBeUndefined() + setSandboxMode(session, 'workspace-write') + setSandboxMode(session, 'read-only') + expect(effectiveSandboxMode(session.events)).toBe('read-only') + }) + + it('setSandboxMode appends exactly one sandbox/mode event per switch', () => { + const session = new Session(SessionId('sess-write')) + setSandboxMode(session, 'danger-full-access') + const modeEvents = session.events.filter(e => e.type === 'sandbox/mode') + expect(modeEvents).toHaveLength(1) + expect(modeEvents[0]?.data).toEqual({ mode: 'danger-full-access' }) + }) +}) diff --git a/packages/sandbox/sandbox-policy/tsconfig.json b/packages/sandbox/sandbox-policy/tsconfig.json new file mode 100644 index 0000000000..fc0c96c6de --- /dev/null +++ b/packages/sandbox/sandbox-policy/tsconfig.json @@ -0,0 +1,27 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cosmokit" + }, + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../../vendor/schemastery" + }, + { + "path": "../sandbox" + }, + { + "path": "../../core/session" + } + ] +} diff --git a/packages/sandbox/sandbox/src/escalation.ts b/packages/sandbox/sandbox/src/escalation.ts new file mode 100644 index 0000000000..e0b9a2ce63 --- /dev/null +++ b/packages/sandbox/sandbox/src/escalation.ts @@ -0,0 +1,189 @@ +/** + * The escalation vocabulary and choreography shared by every sandbox-enforcing + * tool family (`@deepseek-ai/dsh-tool-bash`, `@deepseek-ai/dsh-tool-fs`): the + * strictly-wider ladder, the argument-pairing validation, the model-facing + * denial/hint markers, and {@link approveEscalation} — the ordered fail-closed + * sequence that resolves a `sandbox_permissions` request through a + * user-approval channel BEFORE anything executes. One home keeps the two + * families' approval ordering and verbatim error texts from drifting apart. + * + * The channel is a minimal STRUCTURAL function shape ({@link EscalationAsk}), + * not the approval service type: the tool layer — which owns the agent, the + * call id, and the tool name — closes over `ctx.approval.request(...)` and + * hands the closure down, so this package never depends on the approval or + * agent packages. + * + * @module dsh-sandbox/escalation + */ + +import { assertNever } from '@deepseek-ai/dsh-llm' +import type { SandboxMode } from './index.ts' + +/** + * The strictly-wider table: what a call whose effective mode is the key may + * escalate TO. Checked at EXECUTION, never baked into a tool schema — the + * schema's enum is {@link ESCALATION_TARGETS}, because schemas are + * registry-global while the effective mode is per-call truth. + */ +export const WIDER_MODES: Record = { + 'read-only': ['workspace-write', 'danger-full-access'], + 'workspace-write': ['danger-full-access'], +} + +/** + * The closed escalation-target vocabulary — every mode a call could ever + * escalate TO (`read-only` is the floor; nothing escalates to it). Advertised + * whenever the mounted capability confines: cutting the enum down to the modes + * wider than the composition's DEFAULT would strand a session whose effective + * mode sits below it (a `danger-full-access` default would advertise nothing + * while a narrower-switched session stays confined with no lever). + */ +export const ESCALATION_TARGETS: readonly SandboxMode[] = ['workspace-write', 'danger-full-access'] + +/** + * Validate the escalation argument pairing a tool schema cannot express: + * `sandbox_permissions` and `justification` travel together — an approval + * prompt without a reason, or a reason driving nothing, is a malformed ask — + * and the justification must be a non-empty sentence. + * @param sandboxPermissions - the raw `sandbox_permissions` argument, if given. + * @param justification - the raw `justification` argument, if given. + */ +export function validateEscalationArgs(sandboxPermissions: string | undefined, justification: string | undefined): void { + if (sandboxPermissions !== undefined && justification === undefined) { + throw new Error('invalid escalation: sandbox_permissions requires a justification') + } + if (justification !== undefined && sandboxPermissions === undefined) { + throw new Error('invalid escalation: justification is only valid together with sandbox_permissions') + } + if (justification !== undefined && justification.trim().length === 0) { + throw new Error('invalid justification: expected a non-empty sentence') + } +} + +/** + * The model-facing denial marker — the one vocabulary both enforcing families + * teach and report, so the model recognizes a policy denial identically + * whether the kernel refused a bash file effect or the filesystem provider's + * fence refused a mutation. + * @param mode - the mode the denied call ran under. + * @returns the marker line, exactly as the model sees it. + */ +export function sandboxDenialMarker(mode: SandboxMode): string { + return `[sandbox: file access denied under ${mode} mode]` +} + +/** + * The same-turn escalation hint that rides a denial when the composition + * advertises the escalation fields — the nudge lives at the decision point so + * the sanctioned retry does not depend on the model recalling the tool + * description. + * @param subject - the family's noun for the denied action (`command` for + * bash, `operation` for a filesystem mutation). + * @returns the hint line, exactly as the model sees it. + */ +export function escalationHintMarker(subject: string): string { + return `[sandbox: escalation available — retry this exact ${subject} once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]` +} + +/** + * The closed outcome vocabulary of one escalation ask — structurally identical + * to the approval seam's `ApprovalOutcome` so an `ApprovalService.request` + * return is assignable without this package importing it. + */ +export type EscalationOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable' + +/** + * The minimal approval-request shape {@link approveEscalation} needs — + * structurally the approval seam's `ApprovalService`, generic over the agent + * type `A` and call-id type `C` so this package resolves escalations through + * `ctx.approval` without importing the approval or agent packages (the tool + * layer infers `A`/`C` as its own `Agent`/`CallId`). + */ +export interface EscalationApprover { + /** + * Ask the human to approve one action, resolving to a closed outcome. + * @param req - the audit-self-contained request (agent, tool, call id, reason, optional signal). + * @returns the human's decision as a closed {@link EscalationOutcome}. + */ + request(req: { agent: A; toolName: string; callId: C; reason: string; signal?: AbortSignal }): Promise +} + +/** + * The approval ingredients an escalating tool hands {@link approveEscalation}: + * the approval requester (`ctx.approval`, or `undefined` when none is + * composed), the calling agent (or `undefined` for an agent-less execution), + * and the call's identity. The tool layer holds all of these; this package + * only judges them. + */ +export interface EscalationApproval { + /** The approval requester (`ctx.approval`), or `undefined` when none is composed. */ + approver: EscalationApprover | undefined + /** The calling agent, or `undefined` for an agent-less execution (fails closed). */ + agent: A | undefined + /** The tool-call id the approval prompt attaches to. */ + callId: C + /** The tool name recorded on the approval request. */ + toolName: string + /** The tool-execution abort signal the approval request rides, when present. */ + signal?: AbortSignal +} + +/** One escalation request, as {@link approveEscalation} judges it. */ +export interface EscalationRequest { + /** The requested target mode (schema-pinned to {@link ESCALATION_TARGETS} when advertised). */ + requestedMode: string + /** The model's one-sentence reason, shown verbatim to the user inside the audit reason. */ + justification: string + /** The call's effective mode (session override ?? composition default) the request must strictly widen. */ + effectiveMode: SandboxMode + /** The family's noun for the escalated action in user-facing texts (`command` for bash, `operation` for fs). */ + subject: string +} + +/** + * Resolve a sandbox-escalation request BEFORE anything executes: check strict + * widening against the call's effective mode, then resolve the approval + * channel, then map every outcome — the ordered fail-closed sequence both + * enforcing families share. Returns the granted mode to stamp onto exactly + * this call; throws the distinct verbatim text for every other path (a + * non-widening request, a missing approval service, an agent-less execution, + * a rejection, a cancellation, an unanswerable ask) — the tool registry turns + * the throw into the call's isError result, and nothing has run. A + * non-widening request never prompts a human. + * @param request - the escalation to judge (see {@link EscalationRequest}). + * @param approval - the approval ingredients the tool holds (see {@link EscalationApproval}). + * @returns the granted mode, consumed by the one call that asked. + */ +export async function approveEscalation(request: EscalationRequest, approval: EscalationApproval): Promise { + const { requestedMode: mode, effectiveMode, justification, subject } = request + // Strict widening is an EXECUTION check against the call's effective mode — + // deliberately not a schema constraint (the enum is the closed target + // vocabulary; the effective mode is per-call truth). + if (!(WIDER_MODES[effectiveMode] ?? []).includes(mode as SandboxMode)) { + throw new Error(`sandbox escalation to "${mode}" is not strictly wider than this call's current "${effectiveMode}" mode`) + } + if (approval.approver === undefined) { + throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval service is composed`) + } + if (approval.agent === undefined) { + throw new Error(`sandbox escalation to "${mode}" requires approval, but the call has no agent to route it through`) + } + // Self-contained for the audit trail: approval/asked stores this reason, + // and the target mode is part of the grant's identity. + const outcome = await approval.approver.request({ + agent: approval.agent, + toolName: approval.toolName, + callId: approval.callId, + reason: `escalate sandbox to ${mode}: ${justification}`, + ...approval.signal ? { signal: approval.signal } : {}, + }) + switch (outcome) { + // The schema enum already pinned `mode` to the closed target vocabulary; + // the check above proved it is strictly wider. + case 'allowed-once': return mode as SandboxMode + case 'rejected': throw new Error(`the user rejected escalating this ${subject} to "${mode}"`) + case 'cancelled': throw new Error(`approval for escalating to "${mode}" was cancelled`) + case 'unavailable': throw new Error(`sandbox escalation to "${mode}" requires approval, but no approval channel is available`) + default: return assertNever(outcome, 'EscalationOutcome') + } +} diff --git a/packages/sandbox/sandbox/src/index.ts b/packages/sandbox/sandbox/src/index.ts index 55b9da4540..c94ee9aa0d 100644 --- a/packages/sandbox/sandbox/src/index.ts +++ b/packages/sandbox/sandbox/src/index.ts @@ -25,6 +25,17 @@ import { Context, Service } from 'cordis' import { HarnessError } from '@deepseek-ai/dsh-llm' +export { + ESCALATION_TARGETS, + WIDER_MODES, + approveEscalation, + escalationHintMarker, + sandboxDenialMarker, + validateEscalationArgs, +} from './escalation.ts' +export type { EscalationApproval, EscalationApprover, EscalationOutcome, EscalationRequest } from './escalation.ts' +export { canonicalPath, writableRoots } from './roots.ts' + /** * File-effect policy a sandbox backend enforces on confined processes. * diff --git a/packages/sandbox/sandbox/src/roots.ts b/packages/sandbox/sandbox/src/roots.ts new file mode 100644 index 0000000000..2d70148cdf --- /dev/null +++ b/packages/sandbox/sandbox/src/roots.ts @@ -0,0 +1,51 @@ +/** + * The writable-root derivation shared by every enforcement dialect that + * expresses a mode as a canonical allow-list: `workspace-write` means "the + * workspace root plus the platform temp areas", and this module is that + * meaning's one home. The Seatbelt profile + * (`@deepseek-ai/dsh-sandbox-local`) and the in-process filesystem fence + * (`@deepseek-ai/dsh-fs-sandbox`) both derive their allow-list here, so "the + * write tool cannot write /tmp but bash can" asymmetries cannot arise between + * them. The bwrap and Landlock dialects keep their own grant spellings (an + * ephemeral `/tmp` mount, launcher-owned flags) — the honest per-runner + * differences recorded in the sandbox RFC — with parity pinned by test. + * + * @module dsh-sandbox/roots + */ + +import { realpathSync } from 'node:fs' +import { tmpdir } from 'node:os' +import type { SandboxPolicy } from './index.ts' + +/** + * Resolve a granted root to the path the enforcement layer actually compares: + * canonical (symlinks resolved), because both Seatbelt filters and the fs + * fence's containment check match resolved paths — `/tmp` IS `/private/tmp` + * on darwin, and an as-spelled grant would match nothing. + * @param path - the root as configured or platform-reported. + * @returns the canonical path, or the spelling as-is when resolution fails + * (a missing root matches nothing until it exists — the conservative + * outcome; inventing a fallback would grant a path the caller never named). + */ +export function canonicalPath(path: string): string { + try { + return realpathSync(path) + } catch { + // realpathSync failed: the path (or a prefix) is missing or unreadable. + return path + } +} + +/** + * The roots one confined execution may WRITE under — the mode's meaning as a + * canonical, deduplicated allow-list. `read-only` allows nothing; + * `workspace-write` allows the policy's workspace root, the host `/tmp`, and + * the per-user platform temp dir (`os.tmpdir()` — the real temp area for + * mkstemp-family tools; omitting it would deny what the mode promises). + * @param policy - the file-effect policy to derive the allow-list from. + * @returns the canonical writable roots; empty exactly under `read-only`. + */ +export function writableRoots(policy: SandboxPolicy): string[] { + if (policy.mode !== 'workspace-write') return [] + return [...new Set([policy.workspaceRoot, '/tmp', tmpdir()].map(canonicalPath))] +} diff --git a/packages/sandbox/sandbox/tests/escalation.spec.ts b/packages/sandbox/sandbox/tests/escalation.spec.ts new file mode 100644 index 0000000000..15810d09d5 --- /dev/null +++ b/packages/sandbox/sandbox/tests/escalation.spec.ts @@ -0,0 +1,111 @@ +/** + * Tests for the shared escalation vocabulary and choreography: the strictly- + * wider ladder, the argument-pairing validation, the model-facing markers, and + * {@link approveEscalation}'s ordered fail-closed sequence. Both enforcing tool + * families (`dsh-tool-bash`, `dsh-tool-fs`) delegate here, so the ordering and + * verbatim texts are pinned once, next to the vocabulary that owns them. + */ + +import { describe, expect, it } from 'vitest' +import { + ESCALATION_TARGETS, + WIDER_MODES, + approveEscalation, + escalationHintMarker, + sandboxDenialMarker, + validateEscalationArgs, +} from '@deepseek-ai/dsh-sandbox' +import type { EscalationApprover, EscalationOutcome } from '@deepseek-ai/dsh-sandbox' + +describe('the strictly-wider ladder', () => { + it('read-only escalates to either wider mode; workspace-write only to full access', () => { + expect(WIDER_MODES['read-only']).toEqual(['workspace-write', 'danger-full-access']) + expect(WIDER_MODES['workspace-write']).toEqual(['danger-full-access']) + expect(WIDER_MODES['danger-full-access']).toBeUndefined() + }) + + it('the target enum is the closed set every session could escalate TO (read-only is the floor)', () => { + expect(ESCALATION_TARGETS).toEqual(['workspace-write', 'danger-full-access']) + }) +}) + +describe('validateEscalationArgs', () => { + it('accepts neither field, or both with a non-empty justification', () => { + expect(() => { validateEscalationArgs(undefined, undefined) }).not.toThrow() + expect(() => { validateEscalationArgs('workspace-write', 'because the workspace needs it') }).not.toThrow() + }) + + it('rejects one field without the other, and a blank justification', () => { + expect(() => { validateEscalationArgs('workspace-write', undefined) }).toThrow(/requires a justification/) + expect(() => { validateEscalationArgs(undefined, 'orphan reason') }).toThrow(/only valid together with sandbox_permissions/) + expect(() => { validateEscalationArgs('workspace-write', ' ') }).toThrow(/non-empty sentence/) + }) +}) + +describe('the model-facing markers', () => { + it('the denial marker names the mode', () => { + expect(sandboxDenialMarker('read-only')).toBe('[sandbox: file access denied under read-only mode]') + expect(sandboxDenialMarker('workspace-write')).toBe('[sandbox: file access denied under workspace-write mode]') + }) + + it('the hint marker names the family subject', () => { + expect(escalationHintMarker('command')).toContain('retry this exact command once with sandbox_permissions') + expect(escalationHintMarker('operation')).toContain('retry this exact operation once with sandbox_permissions') + }) +}) + +describe('approveEscalation', () => { + const req = (over: Partial[0]> = {}) => ({ + requestedMode: 'workspace-write', + justification: 'the user asked to write in the workspace', + effectiveMode: 'read-only' as const, + subject: 'command', + ...over, + }) + /** An approver that records the request and returns a fixed outcome. */ + const approver = (outcome: EscalationOutcome, sink?: (req: unknown) => void): EscalationApprover => ({ + request: async (request) => { sink?.(request); return outcome }, + }) + const ingredients = (over: Partial[1]> = {}) => ({ + approver: approver('allowed-once'), + agent: {}, + callId: 'call-1', + toolName: 'bash', + ...over, + }) + + it('grants: returns the requested mode, asking through the approver with the audit reason', async () => { + const seen: { reason?: string }[] = [] + const granted = await approveEscalation(req(), ingredients({ approver: approver('allowed-once', r => seen.push(r as { reason?: string })) })) + expect(granted).toBe('workspace-write') + expect(seen[0]?.reason).toBe('escalate sandbox to workspace-write: the user asked to write in the workspace') + }) + + it('a non-widening request fails closed with its own text and never asks', async () => { + const seen: unknown[] = [] + const spy = ingredients({ approver: approver('allowed-once', r => seen.push(r)) }) + await expect(approveEscalation(req({ requestedMode: 'read-only' }), spy)) + .rejects.toThrow(/not strictly wider than this call's current "read-only" mode/) + await expect(approveEscalation(req({ requestedMode: 'workspace-write', effectiveMode: 'danger-full-access' as never }), spy)) + .rejects.toThrow(/not strictly wider/) + expect(seen).toEqual([]) + }) + + it('a missing approval service and an agent-less call each fail closed with distinct text', async () => { + await expect(approveEscalation(req(), ingredients({ approver: undefined }))).rejects.toThrow(/no approval service is composed/) + await expect(approveEscalation(req(), ingredients({ agent: undefined }))).rejects.toThrow(/no agent to route it through/) + }) + + it('maps each non-grant outcome to its distinct verbatim text (subject in the rejection)', async () => { + await expect(approveEscalation(req({ subject: 'operation' }), ingredients({ approver: approver('rejected') }))) + .rejects.toThrow('the user rejected escalating this operation to "workspace-write"') + await expect(approveEscalation(req(), ingredients({ approver: approver('cancelled') }))) + .rejects.toThrow('approval for escalating to "workspace-write" was cancelled') + await expect(approveEscalation(req(), ingredients({ approver: approver('unavailable') }))) + .rejects.toThrow('no approval channel is available') + }) + + it('an outcome outside the closed union trips the exhaustiveness guard (defensive)', async () => { + await expect(approveEscalation(req(), ingredients({ approver: approver('bogus' as never) }))).rejects.toThrow() + }) +}) diff --git a/packages/sandbox/sandbox/tests/roots.spec.ts b/packages/sandbox/sandbox/tests/roots.spec.ts new file mode 100644 index 0000000000..fd0d2cd7bd --- /dev/null +++ b/packages/sandbox/sandbox/tests/roots.spec.ts @@ -0,0 +1,39 @@ +/** + * Tests for the writable-root derivation: the mode's meaning as a canonical + * allow-list. Pinned here so the fs fence and the Seatbelt profile — both + * deriving from `writableRoots` — cannot drift. + */ + +import { realpathSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { mkdtempSync } from 'node:fs' +import { join } from 'node:path' +import { describe, expect, it } from 'vitest' +import { canonicalPath, writableRoots } from '@deepseek-ai/dsh-sandbox' + +describe('canonicalPath', () => { + it('resolves symlinks (an existing path realpaths)', () => { + const dir = mkdtempSync(join(tmpdir(), 'dsh-roots-')) + expect(canonicalPath(dir)).toBe(realpathSync(dir)) + }) + + it('returns the spelling as-is when the path cannot be resolved (conservative — matches nothing until it exists)', () => { + expect(canonicalPath('/does/not/exist/anywhere-xyz')).toBe('/does/not/exist/anywhere-xyz') + }) +}) + +describe('writableRoots', () => { + it('read-only grants nothing', () => { + expect(writableRoots({ mode: 'read-only', workspaceRoot: process.cwd() })).toEqual([]) + }) + + it('workspace-write grants the workspace root plus the platform temp areas, canonical and deduplicated', () => { + const ws = mkdtempSync(join(tmpdir(), 'dsh-ws-')) + const roots = writableRoots({ mode: 'workspace-write', workspaceRoot: ws }) + expect(roots).toContain(realpathSync(ws)) + expect(roots).toContain(canonicalPath('/tmp')) + expect(roots).toContain(realpathSync(tmpdir())) + // Deduplicated after canonicalization (/tmp and os.tmpdir() may coincide). + expect(new Set(roots).size).toBe(roots.length) + }) +}) diff --git a/packages/ui/acp/tests/config-options.spec.ts b/packages/ui/acp/tests/config-options.spec.ts index fb39b2a0de..96db26698b 100644 --- a/packages/ui/acp/tests/config-options.spec.ts +++ b/packages/ui/acp/tests/config-options.spec.ts @@ -99,12 +99,12 @@ describe('acp bridge — session config options', () => { // Idle: nothing in the log yet — turn-enclosure forbids a bare append. const session = h.ctx.agents.list()[0]?.session - expect(session?.events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) + expect(session?.events.some(e => e.type === 'permission/preset' || e.type === 'sandbox/mode' || e.type === 'approval/policy')).toBe(false) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = session?.events ?? [] expect(events.filter(e => e.type === 'permission/preset').map(e => e.data)).toEqual([{ preset: 'danger-full-access' }]) - expect(events.filter(e => e.type === 'bash/sandbox-mode').map(e => e.data)).toEqual([{ mode: 'danger-full-access' }]) + expect(events.filter(e => e.type === 'sandbox/mode').map(e => e.data)).toEqual([{ mode: 'danger-full-access' }]) expect(events.filter(e => e.type === 'approval/policy').map(e => e.data)).toEqual([{ policy: 'never' }]) const turnStart = events.findIndex(e => e.type === 'turn/start') const anchored = events.findIndex(e => e.type === 'permission/preset') @@ -135,7 +135,7 @@ describe('acp bridge — session config options', () => { expect(back.configOptions).toEqual([permissionOption('workspace-write')]) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] - expect(events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) + expect(events.some(e => e.type === 'permission/preset' || e.type === 'sandbox/mode' || e.type === 'approval/policy')).toBe(false) }) it('a no-op switch (the value already shown) records nothing and keeps a live pending', async () => { @@ -163,7 +163,7 @@ describe('acp bridge — session config options', () => { const anchored = events.findIndex(e => e.type === 'permission/preset') expect(turnStart).toBeGreaterThanOrEqual(0) expect(anchored).toBeGreaterThan(turnStart) - expect(events.some(e => e.type === 'bash/sandbox-mode')).toBe(true) + expect(events.some(e => e.type === 'sandbox/mode')).toBe(true) expect(events.some(e => e.type === 'approval/policy')).toBe(true) await h.client.cancel({ sessionId }) await hung @@ -213,7 +213,7 @@ describe('acp bridge — session config options', () => { const agent = h.ctx.agents.list()[0] if (agent === undefined) throw new Error('expected an agent') agent.session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - agent.session.append('bash/sandbox-mode', { mode: 'read-only' }) + agent.session.append('sandbox/mode', { mode: 'read-only' }) agent.session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) // The echo of the derived current is a no-op, not an unknown-value error… const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'custom' }) diff --git a/packages/ui/permission/package.json b/packages/ui/permission/package.json index b6833791e4..c436ed0f0d 100644 --- a/packages/ui/permission/package.json +++ b/packages/ui/permission/package.json @@ -24,6 +24,7 @@ "peerDependencies": { "@deepseek-ai/dsh-bash": "^0.0.1", "@deepseek-ai/dsh-sandbox": "^0.0.1", + "@deepseek-ai/dsh-sandbox-policy": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-user-approval": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -34,6 +35,7 @@ "devDependencies": { "@deepseek-ai/dsh-bash": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", + "@deepseek-ai/dsh-sandbox-policy": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-user-approval": "workspace:^", "cordis": "^4.0.0-rc.6" diff --git a/packages/ui/permission/src/index.ts b/packages/ui/permission/src/index.ts index 67e623052b..4f7d29e590 100644 --- a/packages/ui/permission/src/index.ts +++ b/packages/ui/permission/src/index.ts @@ -1,7 +1,7 @@ /** * User-facing PERMISSION PRESETS: one product-level knob over the two * mechanism knobs. A preset names a bundle — its sandbox mode - * (`bash/sandbox-mode`) and its approval policy (`approval/policy`) — so a + * (`sandbox/mode`) and its approval policy (`approval/policy`) — so a * user picks `workspace-write` or `danger-full-access` while the mechanism * tiers stay orthogonal capabilities. Switching a preset WRITES THROUGH: one `permission/preset` event * records the chosen bundle (the audit fact reverse-mapping cannot recover — @@ -19,7 +19,10 @@ import { Context, Service } from 'cordis' import z from 'schemastery' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import type { SandboxMode } from '@deepseek-ai/dsh-sandbox' -import { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-bash' +import { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-sandbox-policy' +// Side-effect type import: declaration-merges `ctx.bash` (the capability fact +// `sandboxMode` this service reads), without a value dependency on the seam. +import type {} from '@deepseek-ai/dsh-bash' import type { ApprovalPolicy } from '@deepseek-ai/dsh-user-approval' import { APPROVAL_POLICIES, effectiveApprovalPolicy, setApprovalPolicy } from '@deepseek-ai/dsh-user-approval' @@ -33,7 +36,7 @@ declare module '@deepseek-ai/dsh-session' { interface SessionEventMap { /** * The session's permission preset was switched — log-only (the - * `bash/sandbox-mode` precedent): durable and replayable, never in the + * `sandbox/mode` precedent): durable and replayable, never in the * model transcript. The LAST such event is the session's preset * ({@link effectivePermissionPreset}); the knob events the switch wrote * through follow it in the same turn, and they — not this record of the @@ -48,7 +51,7 @@ declare module '@deepseek-ai/dsh-session' { * runs under while the preset is active — plus its presentation. */ export interface PresetSpec { - /** The `bash/sandbox-mode` value the preset writes through. */ + /** The `sandbox/mode` value the preset writes through. */ sandbox: SandboxMode /** The `approval/policy` value the preset writes through. */ approval: ApprovalPolicy diff --git a/packages/ui/permission/tests/permission.spec.ts b/packages/ui/permission/tests/permission.spec.ts index 2852b2d96b..3e8f63121b 100644 --- a/packages/ui/permission/tests/permission.spec.ts +++ b/packages/ui/permission/tests/permission.spec.ts @@ -53,7 +53,7 @@ describe('PermissionService', () => { it('a knob state matching no table entry derives custom — a state, not an error', async () => { const ctx = await mounted() const session = freshSession('sess-custom') - session.append('bash/sandbox-mode', { mode: 'read-only' }) + session.append('sandbox/mode', { mode: 'read-only' }) expect(ctx.permission.current(session.events)).toBe(CUSTOM_PRESET) // Switching FROM custom is an ordinary write-through; custom itself is // never a target. @@ -80,7 +80,7 @@ describe('PermissionService', () => { expect(ctx.permission.current(session.events)).toBe('agentish') // A knob drifts: the fold's bundle no longer matches → reverse map wins. session.append('approval/policy', { policy: 'never' }) - session.append('bash/sandbox-mode', { mode: 'danger-full-access' }) + session.append('sandbox/mode', { mode: 'danger-full-access' }) expect(ctx.permission.current(session.events)).toBe('danger-full-access') }) @@ -90,7 +90,7 @@ describe('PermissionService', () => { ctx.permission.set(session, 'danger-full-access') expect(session.events.map(e => [e.type, e.data])).toEqual([ ['permission/preset', { preset: 'danger-full-access' }], - ['bash/sandbox-mode', { mode: 'danger-full-access' }], + ['sandbox/mode', { mode: 'danger-full-access' }], ['approval/policy', { policy: 'never' }], ]) }) @@ -109,12 +109,12 @@ describe('PermissionService', () => { // A knob drifts out from under the preset (a direct setter call, a test // scenario): the session derives custom, and re-asserting the preset is // a real switch again — choice re-recorded, only the drifted knob moves. - session.append('bash/sandbox-mode', { mode: 'read-only' }) + session.append('sandbox/mode', { mode: 'read-only' }) ctx.permission.set(session, 'danger-full-access') const tail = session.events.slice(4) expect(tail.map(e => [e.type, e.data])).toEqual([ ['permission/preset', { preset: 'danger-full-access' }], - ['bash/sandbox-mode', { mode: 'danger-full-access' }], + ['sandbox/mode', { mode: 'danger-full-access' }], ]) }) diff --git a/packages/ui/permission/tsconfig.json b/packages/ui/permission/tsconfig.json index 8b9cff62b4..fa31f71f69 100644 --- a/packages/ui/permission/tsconfig.json +++ b/packages/ui/permission/tsconfig.json @@ -23,6 +23,9 @@ { "path": "../../sandbox/sandbox" }, + { + "path": "../../sandbox/sandbox-policy" + }, { "path": "../../bash/bash" }, diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index e6b0d4519c..dd55bcae72 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -89,9 +89,6 @@ importers: '@deepseek-ai/dsh-sandbox': specifier: workspace:^ version: link:../../sandbox/sandbox - '@deepseek-ai/dsh-session': - specifier: workspace:^ - version: link:../../core/session cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -113,10 +110,6 @@ importers: version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) packages/bash/bash-sandbox: - dependencies: - schemastery: - specifier: ^3.18.0 - version: 3.18.0 devDependencies: '@deepseek-ai/dsh-bash': specifier: workspace:^ @@ -130,6 +123,9 @@ importers: '@deepseek-ai/dsh-sandbox-local': specifier: workspace:^ version: link:../../sandbox/sandbox-local + '@deepseek-ai/dsh-sandbox-policy': + specifier: workspace:^ + version: link:../../sandbox/sandbox-policy cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -163,6 +159,9 @@ importers: '@deepseek-ai/dsh-sandbox-local': specifier: workspace:^ version: link:../../sandbox/sandbox-local + '@deepseek-ai/dsh-sandbox-policy': + specifier: workspace:^ + version: link:../../sandbox/sandbox-policy '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session @@ -457,6 +456,9 @@ importers: '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm + '@deepseek-ai/dsh-sandbox': + specifier: workspace:^ + version: link:../../sandbox/sandbox cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -489,6 +491,24 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/fs/fs-sandbox: + devDependencies: + '@deepseek-ai/dsh-fs': + specifier: workspace:^ + version: link:../fs + '@deepseek-ai/dsh-fs-local': + specifier: workspace:^ + version: link:../fs-local + '@deepseek-ai/dsh-sandbox': + specifier: workspace:^ + version: link:../../sandbox/sandbox + '@deepseek-ai/dsh-sandbox-policy': + specifier: workspace:^ + version: link:../../sandbox/sandbox-policy + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/fs/tool-fs: dependencies: diff: @@ -519,6 +539,12 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-sandbox': + specifier: workspace:^ + version: link:../../sandbox/sandbox + '@deepseek-ai/dsh-sandbox-policy': + specifier: workspace:^ + version: link:../../sandbox/sandbox-policy '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session @@ -528,6 +554,9 @@ importers: '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../../ui/user-approval cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) @@ -718,6 +747,22 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/sandbox/sandbox-policy: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@deepseek-ai/dsh-sandbox': + specifier: workspace:^ + version: link:../sandbox + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/session-persistence/session-persistence: devDependencies: '@deepseek-ai/dsh-session': @@ -1280,28 +1325,6 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) - packages/ui/permission: - dependencies: - schemastery: - specifier: ^3.18.0 - version: 3.18.0 - devDependencies: - '@deepseek-ai/dsh-bash': - specifier: workspace:^ - version: link:../../bash/bash - '@deepseek-ai/dsh-sandbox': - specifier: workspace:^ - version: link:../../sandbox/sandbox - '@deepseek-ai/dsh-session': - specifier: workspace:^ - version: link:../../core/session - '@deepseek-ai/dsh-user-approval': - specifier: workspace:^ - version: link:../user-approval - cordis: - specifier: ^4.0.0-rc.6 - version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) - packages/ui/jsonrpc: dependencies: schemastery: @@ -1346,6 +1369,31 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/permission: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@deepseek-ai/dsh-bash': + specifier: workspace:^ + version: link:../../bash/bash + '@deepseek-ai/dsh-sandbox': + specifier: workspace:^ + version: link:../../sandbox/sandbox + '@deepseek-ai/dsh-sandbox-policy': + specifier: workspace:^ + version: link:../../sandbox/sandbox-policy + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-user-approval': + specifier: workspace:^ + version: link:../user-approval + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.6(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.4) + packages/ui/stdio-agent: devDependencies: '@cordisjs/plugin-include': @@ -1762,6 +1810,9 @@ importers: '@deepseek-ai/dsh-sandbox': specifier: workspace:^ version: link:../../packages/sandbox/sandbox + '@deepseek-ai/dsh-sandbox-policy': + specifier: workspace:^ + version: link:../../packages/sandbox/sandbox-policy '@deepseek-ai/dsh-scope': specifier: workspace:^ version: link:../../packages/core/scope diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index a843b2f04a..5a961ae355 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -35,6 +35,7 @@ "@deepseek-ai/dsh-permission": "workspace:^", "@deepseek-ai/dsh-repeat-tool-guard": "workspace:^", "@deepseek-ai/dsh-sandbox": "workspace:^", + "@deepseek-ai/dsh-sandbox-policy": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence": "workspace:^", diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json index 235b8f21fa..27e1234a86 100644 --- a/scripts/doc-budgets.manifest.json +++ b/scripts/doc-budgets.manifest.json @@ -1,7 +1,7 @@ { "AGENTS.md": 1802, "docs/AGENTS.md": 1315, - "docs/architecture.md": 1790, + "docs/architecture.md": 1800, "docs/cordis-primer.md": 550, "docs/defensive-patterns.md": 550, "docs/testing.md": 800, diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index a970499268..c09a9e1bda 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -180,6 +180,15 @@ const SERVICE_ROLES: ServiceRole[] = [ consumers: ['bash-sandbox'], note: 'Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement.', }, + { + key: 'sandboxPolicy', + pkg: 'sandbox', + title: 'Sandbox policy home', + mode: 'core', + implementations: [], + consumers: ['bash-sandbox', 'fs-sandbox', 'tool-bash', 'tool-fs'], + note: 'The one home for the deployment default mode + workspace root and the per-session `sandbox/mode` override; both enforcing families read it so bash and fs cannot confine to different roots.', + }, { key: 'approval', pkg: 'approval', @@ -212,10 +221,10 @@ const SERVICE_ROLES: ServiceRole[] = [ pkg: 'fs', title: 'Filesystem provider seam', mode: 'seam', - implementations: ['fs-local'], + implementations: ['fs-local', 'fs-sandbox'], consumers: ['tool-fs'], companions: ['fs-policy'], - note: 'tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate.', + note: 'tool-fs executes read/write/edit through ctx.fs; fs-sandbox fences mutations by the shared sandbox mode; fs-policy contributes observed-state checks through the fs/* event gate.', }, { key: 'compact', diff --git a/tsconfig.build.json b/tsconfig.build.json index 6deb2c6e01..57d94221a6 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -41,11 +41,13 @@ { "path": "./packages/bash/bash-local" }, { "path": "./packages/sandbox/sandbox" }, { "path": "./packages/sandbox/sandbox-local" }, + { "path": "./packages/sandbox/sandbox-policy" }, { "path": "./packages/bash/bash-sandbox" }, { "path": "./packages/bash/tool-bash" }, { "path": "./packages/fs/fs" }, { "path": "./packages/fs/fs-local" }, { "path": "./packages/fs/fs-policy" }, + { "path": "./packages/fs/fs-sandbox" }, { "path": "./packages/fs/tool-fs" }, { "path": "./packages/web/web" }, { "path": "./packages/web/web-search-exa" }, diff --git a/tsconfig.json b/tsconfig.json index dd283ec5d7..572b8ee31c 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -50,11 +50,13 @@ { "path": "./packages/bash/bash-local" }, { "path": "./packages/sandbox/sandbox" }, { "path": "./packages/sandbox/sandbox-local" }, + { "path": "./packages/sandbox/sandbox-policy" }, { "path": "./packages/bash/bash-sandbox" }, { "path": "./packages/bash/tool-bash" }, { "path": "./packages/fs/fs" }, { "path": "./packages/fs/fs-local" }, { "path": "./packages/fs/fs-policy" }, + { "path": "./packages/fs/fs-sandbox" }, { "path": "./packages/fs/tool-fs" }, { "path": "./packages/compact/compact" }, { "path": "./packages/compact/compact-basic" }, From 8be096c540c6b82187051eab9febd461a46e4fc2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:08:37 +0800 Subject: [PATCH 087/323] fix: preserve master bash guidance wording --- packages/bash/tool-bash/src/index.ts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index 662b7a065f..4c699cd6c0 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -173,15 +173,15 @@ function bashDescription(escalationModes: readonly SandboxMode[]): string { + 'poll it with `bash_output` and stop it with `bash_kill`.' if (escalationModes.length === 0) return base return base + ' Attempting a command the sandbox may deny is safe and expected: run it and read the ' - + 'marker rather than assuming the denial. When a command IS denied and a wider mode would let it ' - + 'succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry ' + + 'marker rather than assuming the denial. When a command is denied and a wider mode would let it ' + + 'succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry ' + 'the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) ' + 'plus a one-sentence `justification`. Do not detour through chat to ask permission first — the ' - + 'approval prompt raised by that retry IS how the user consents. If the session states approval ' + + 'approval prompt raised by that retry is how the user consents. If the session states approval ' + 'prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. ' - + 'Never escalate speculatively: ground the request in a real denial — normally the one THIS command ' + + 'Never escalate speculatively: ground the request in a real denial — normally the one this command ' + 'just hit; escalating up front is fine only when this session already denied the same access. ' - + 'A rejected escalation is final for THAT command — stop and explain, never work around ' + + 'A rejected escalation is final for that command — stop and explain, never work around ' + 'it — but it does not forbid attempting or escalating other commands later.' } From 5a1194bf301ecd9f2ab007a599a2e121e57b72e6 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:18:24 +0800 Subject: [PATCH 088/323] test: refresh snapshots after bash guidance merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../acp-agent/tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/permission-switching/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- 10 files changed, 10 insertions(+), 10 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index cdc09c92c0..991806d74b 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 79d9b94ad9..a6a3371913 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index 7155b1c2a6..c6213cd558 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 6e8f157ace..5ad12cddff 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index 66cdecedfb..a68bb37f9f 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 98b4f97fee..ed60d52258 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 98b4f97fee..ed60d52258 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ + /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 1f33766ec9..07cd6233b3 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 1c85ee81ba..9a26fa2efe 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index c66f5676cc..0643740e4f 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} From 10fd0b4504b47285b67aed611e4cc0a2e86c5db4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:22:37 +0800 Subject: [PATCH 089/323] docs: align unified identity translation --- docs/cookbook/extension-cookbook.i18n.yaml | 4 ++-- docs/cookbook/extension-cookbook.zh.md | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index ef1d8d606f..2761b419e9 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 40ee22b352c884d7f295c87726c54ab8e166c844 -extension-cookbook.zh.md: 4e5bc68c973649574bcb2404bea00096eb9ca41f +extension-cookbook.md: 0b95866515efa1b28a95ed48de0fe20d76a62b82 +extension-cookbook.zh.md: 038bf093ce2d289fb59be165a154cbe4df831d9e diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 4e5bc68c97..038bf093ce 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -40,7 +40,7 @@ UI 插件从 `session/event` 事件流渲染（助手 token 流以 `assistant/ch ```ts import type { Context } from 'cordis' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' declare function render(text: string): void declare function onUserInput(handler: (text: string) => void): void @@ -54,7 +54,7 @@ export function apply(ctx: Context) { render(event.data.chunk.text) } }) - onUserInput(text => ctx.agents.get(AgentId('main'))?.send([{ type: 'text', text }])) + onUserInput(text => ctx.agents.get(SessionId('client-session'))?.send([{ type: 'text', text }])) } ``` From 9745a0d43a979d34c44c2a42d8a485d03a25de71 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:36:04 +0800 Subject: [PATCH 090/323] fix: reject empty configured session ids --- packages/core/agent-loop/src/index.ts | 2 +- packages/core/agent-loop/tests/config-session-id.spec.ts | 9 +++++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 8d9a184cc7..325ba7b92d 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -377,7 +377,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), - sessionId: z.string(), + sessionId: z.string().min(1), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 096a6eff9e..bd2a5522df 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -35,6 +35,15 @@ async function makeCoreContext(): Promise { } describe('config-driven session id', () => { + it('rejects an empty exact id before publishing an agent', async () => { + const ctx = await makeCoreContext() + await expect(ctx.plugin(AgentLoop, { + agents: [{ id: 'main', sessionId: SessionId(''), model: 'mock' }], + })).rejects.toThrow('expected string length >= 1') + expect(ctx.agents.get(SessionId(''))).toBeUndefined() + await ctx.fiber.dispose() + }) + it('accepts one exact fresh id and rejects it alongside a resume id', async () => { const exact = await makeCoreContext() await exact.plugin(AgentLoop, { From ed3654da00fd14597b79e8e97bf61f09c5981ced Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:38:53 +0800 Subject: [PATCH 091/323] docs: reconcile hidden internals with prose standard --- ...t-variables-and-tool-guidance-ownership.md | 16 ++--- .../subagent/subagent-subprocess/src/index.ts | 61 +++++-------------- packages/subagent/tool-subagent/src/index.ts | 49 +++------------ 3 files changed, 31 insertions(+), 95 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index aae4564513..854807c109 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -24,21 +24,21 @@ The assembled system prompt had four defects, all of one family: facts the harne ### Prompt variables -Plugins contribute named values via `ctx.systemPrompt.variable(name, provider)`; prompt text references them as `{{name}}`. Providers are functions of the `AssembleContext` and may return `undefined` — "no value for THIS assembly". `assemble()` resolves every registered variable into `PromptAssembly.variables` (waterfall listeners can see, add, or override); `renderPrompt` interpolates. Rendering is STRICT — fail loud beats shipping a malformed prompt: a reference to an unregistered name throws (listing what exists; lookup is `Object.hasOwn`, so a prototype property like `{{constructor}}` is unknown, not a function spliced into the prompt), a registered-but-valueless reference throws, a complete `{{…}}` group that is not a well-formed name (`[a-z][a-z0-9_]*`, e.g. `{{ model }}`) throws, and a `{{` that opens no complete group while a `}}` still follows (`{{{model}}}`, `{{a{b}}`) throws. A lone `{{` with no `}}` anywhere after it is ordinary prose and passes through verbatim; substituted values are never re-scanned. Registration rejects duplicate and unreferenceable names, mirroring the tool registry — and `section()` now rejects duplicate section names, making the documented dedup real. +Plugins register `{{name}}` values through `ctx.systemPrompt.variable(name, provider)`. Assembly resolves them into the waterfall-visible variable map. Rendering rejects unknown own-property references, registered providers that return `undefined`, malformed complete references, and unbalanced references that still contain a closing `}}`; a lone unmatched `{{` remains prose, and substituted values are not rescanned. Registration rejects invalid or duplicate variable names, and section names are unique. `dsh-agent-loop` registers the two built-ins, both pure projections of the context agent: `model` (= `options.model`) and `cwd` (= `session.header.cwd`). The example personas write `powered by the {{model}} model` — the model name is stated once, in the `model:` config key. `{{cwd}}` is demonstrated in the ACP example only: every ACP session carries the client's cwd, while config-pre-created stdio agents have none (a persona claiming `{{cwd}}` there fails the turn — by design). The variables stay on the loop plugin (unlike the sections below): they are runtime facts of the agents THIS loop drives, and a replacement loop supplies its own. ### Persona as the order-0 section -`dsh-system-prompt` itself registers the two harness-owned sections (they must survive a swapped loop plugin, so they do NOT live on `dsh-agent-loop`): the static `harness:identity` at order `-100` — every prompt opens by stating the agent is powered by the DeepSeek Harness SDK — and the global default `deployment:persona` at order 0, whose text is the plugin's own `persona` config. `AgentOptions.systemPrompt` and the loop's special-case join are gone: `fullSystemPrompt ≡ renderPrompt(assembly)`, one ordered pipeline for everything the model sees, and `agent/pre-step` (compaction's token-pressure input) measures exactly the real prompt. An agent-scoped section with the same `deployment:persona` name shadows the default for that agent; programmatic setup may register one directly, and the subagent persona feature installs one before publishing an in-process child when the selected provider supports it. Order bands are convention: harness identity `-100`, persona `0`, tool guidance `100–199`; other negative orders also render before the persona. +`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and `agent/pre-step` therefore measures the exact prompt used for compaction. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`. ### Tool guidance ownership -Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship in every request — the YAML prose was ~fully redundant with them. Sections carry only the cross-call habits a single call's description cannot: `dsh-tool-bash` contributes `tool:bash` (order 105) — check the `[exit code: N]` marker on every result; `dsh-tool-fs`'s read section gains the "not shell commands like cat" contrast. `todo_write` and the subagent tools need NO section — their descriptions already carry the whole contract. The leaf personas shrink to identity + behavior (verify your work; keep answers brief), and the welcome banner stops enumerating tools. +Per-tool semantics and selection guidance live in tool descriptions. Prompt sections carry only cross-call habits, such as checking bash exit markers or preferring filesystem tools over shell commands. `todo_write` and subagent tools need no section because their descriptions contain the full contract. Deployment personas contain only role and behavior. ### The subagent conversation-history descriptor -`SubagentProvider` gains `readonly inheritsParentContext: boolean` — a DESCRIPTIVE conversation-history fact beside `capabilities`, not in it (capabilities are start-time validation; nothing validates against this flag). Spawn and ACP declare `false`, fork declares `true`. The name refers only to conversation seeding, not Cordis scope, services, tools, or authority. `dsh-tool-subagent` derives both the tool description and the `prompt` parameter description from the flag: the fork instance now tells the model the child is seeded with the conversation's completed turns (not the in-flight turn) and that its prompt should state only what is new. Deriving the description from a provider that arrives on its own fiber is what forced the provider-lifecycle events and the tool's reactive registration — that mechanism, its Loader-concurrency rationale, and its rejected alternatives are recorded in [the provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). +`SubagentProvider.inheritsParentContext` describes conversation seeding, not scope, services, tools, or authority. Spawn and ACP set it to `false`; fork sets it to `true`. `dsh-tool-subagent` derives its tool and prompt-parameter descriptions from the flag, including that fork inherits completed turns but not the in-flight turn. Provider lifecycle events keep that wording synchronized with reactive provider registration; their rationale lives in the [provider-lifecycle-events RFC](2026-07-05-subagent-provider-lifecycle-events.md). ## Alternatives considered @@ -56,10 +56,10 @@ Per-tool semantics and when-to-use live in tool DESCRIPTIONS, which already ship ## Shipped invariants -- `renderPrompt(await assemble(assembleContextFor(agent)))` for the coding-agent example renders the harness identity, then the persona (with the agent's model name interpolated), then the fs/bash/web guidance sections; the loop has no other prompt-composition path. -- The `subagent_fork` schema description says the child inherits the conversation; the `subagent` one says it does not. The tool follows its provider: absent before the backend activates, present after, gone when the backend unloads, re-worded from the fresh provider on reload. -- Unknown/valueless/malformed/unbalanced `{{…}}` references throw with the section name in the message; duplicate section, variable, and tool-name registrations all throw. -- Snapshot goldens are prompt-independent by construction: llm-replay keys replay on (turn, step) chunk streams and never re-verifies the outgoing request. +- The coding-agent prompt renders identity, persona with the interpolated model, then fs/bash/web guidance through one assembly path. +- Fork and fresh subagent descriptions reflect whether the provider inherits completed conversation turns; the tool appears, disappears, and is reworded with provider lifecycle changes. +- Unknown, valueless, malformed, or unbalanced variable references name the section and throw; duplicate section, variable, and tool registrations also throw. +- Snapshot replay is prompt-independent: it keys recorded chunk streams by turn and step without comparing the outgoing request. ## Consequences diff --git a/packages/subagent/subagent-subprocess/src/index.ts b/packages/subagent/subagent-subprocess/src/index.ts index bd792e7f23..3831d2bb6a 100644 --- a/packages/subagent/subagent-subprocess/src/index.ts +++ b/packages/subagent/subagent-subprocess/src/index.ts @@ -1,19 +1,8 @@ /** - * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn - * an external agent as a child process and must keep the parent deployment's - * credentials out of it, tear it down to quiescence, and isolate it from the - * host user's on-disk CLI state. The pieces: credential-shaped env scrubbing - * ({@link buildChildEnv}), spawn-failure capture ({@link spawnFailure}), - * bounded child-exit waits inside the stdin-EOF → SIGTERM → SIGKILL dispose - * ladder ({@link disposeChildProcess}), and the per-run isolated config dir - * ({@link createIsolatedConfigDir}). - * - * This package owns no provider and registers nothing; it is a pure library - * the out-of-process backend packages depend on (the `subagent-inprocess` - * shape, for the process boundary). Every tunable — the ladder's grace - * periods, a pinned config dir — is a PARAMETER here: defaults belong in each - * consuming plugin's Config, per the no-hardcoded-tunables rule. - * + * Shared machinery for OUT-OF-PROCESS subagent backends — providers that spawn an external + * agent as a child process and must keep the parent deployment's credentials out of it, tear + * it down to quiescence, and isolate it from the host user's on-disk CLI state. This package + * registers no provider; consuming plugins own and validate every timing or path default. * @module @deepseek-ai/dsh-subagent-subprocess */ @@ -50,11 +39,8 @@ export function buildChildEnv(extra: Record): NodeJS.ProcessEnv } /** - * Capture the child's spawn-level failure as a promise the run's result path - * can race. A spawn failure (e.g. `ENOENT` for a bad command) is emitted as an - * `error` EVENT, not a thrown exception — and without a listener Node treats - * it as an unhandled error and crashes the parent process. Call this in the - * SAME TICK as `spawn()`, so no window exists for the event to fire unheard. + * Capture the child's spawn-level `error` event as a promise. Call in the same tick as + * `spawn()`; otherwise an early event can be unhandled and crash the parent. * @param child - the just-spawned child process. * @returns a promise that RESOLVES (never rejects) with the child's first * `error` event; for a child that spawns cleanly it never settles. @@ -123,15 +109,8 @@ export interface DisposeLadderGraces { } /** - * Tear a child process down to QUIESCENCE: resolves only once the child has - * actually exited (or was already gone), never merely after requesting it. - * Three-tier escalation — - * - * 1. stdin EOF (when stdin is piped), then wait `disposeEofGraceMs`: a - * cooperative child quiesces on its own, its teardown and flushes intact; - * 2. `SIGTERM`, then wait `disposeGraceMs`; - * 3. `SIGKILL`, then await the (now-certain) exit — a child that ignores EOF - * and traps `SIGTERM` must not wedge dispose forever. + * Tear a child process down to quiescence, resolving only after exit: close stdin and allow + * cooperative flush, then send `SIGTERM`, then `SIGKILL` and await the forced exit. * * @param child - the child process to tear down. * @param graces - the two grace periods, from the consuming plugin's Config. @@ -139,10 +118,7 @@ export interface DisposeLadderGraces { export async function disposeChildProcess(child: ChildProcess, graces: DisposeLadderGraces): Promise { // Already gone: nothing to reap. if (child.exitCode !== null || child.signalCode !== null) return - // 1. Graceful: end the request stream (stdin EOF) and let the child quiesce - // on its own. Sending SIGTERM in the same tick (or too soon) would - // default-terminate a cooperative child mid-flush, orphaning its nested - // work. A child spawned without a stdin pipe skips straight to the wait. + // 1. Close stdin and allow cooperative teardown and durable-state flush. child.stdin?.end() if (await exitsWithin(child, graces.disposeEofGraceMs)) return // 2. SIGTERM, escalating if the child still does not exit within the grace. @@ -171,16 +147,9 @@ export interface IsolatedConfigDir { } /** - * An isolated config dir for one child run, so the child's behavior is a - * function of deployment config alone — never of whatever `~/.claude` / - * `~/.codex`-style state happens to exist on the host machine. Two modes: - * - * - no `pinnedPath` (the default): creates a FRESH private (0700) `mkdtemp` - * dir under the OS temp root; {@link IsolatedConfigDir.remove} deletes it - * best-effort; - * - `pinnedPath` set (a deployment deliberately sharing state across runs): - * the pinned path is returned as-is — never created, never removed — the - * deployment owns that directory's lifecycle. + * An isolated config dir for one child run, independent of host CLI state. Without + * `pinnedPath`, creates a private temp directory and removes it best-effort; a pinned directory + * is returned unchanged and remains deployment-owned. * * @param prefix - the `mkdtemp` name prefix for a fresh dir (e.g. * `dsh-subagent-codex-`); ignored when `pinnedPath` is set. @@ -207,10 +176,8 @@ export async function createIsolatedConfigDir(prefix: string, pinnedPath?: strin try { await rm(path, { recursive: true, force: true }) } catch { - // Best-effort by contract: swallows rm failures (EACCES/EBUSY-style — - // e.g. the dead child left an unreadable entry behind). The dir lives - // under the OS temp root, which reclaims it; failing dispose over - // cleanup would be worse than a leftover temp dir. + // Best-effort by contract: swallows rm failures (EACCES/EBUSY-style — e.g. the dead + // child left an unreadable entry behind). } }, } diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index ff54bc109a..59821147af 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -1,34 +1,11 @@ /** - * The model-facing `subagent` tool: delegate a task to a child agent and return - * its final output. Pure schema + lifecycle shaping — every transport concern - * lives behind the `ctx.subagents` provider registry - * (`@deepseek-ai/dsh-subagent`), so an in-process, ACP, or future A2A backend - * swaps in without touching what the model sees. - * - * Provider selection is config, not model-facing: this plugin is bound to - * EXACTLY ONE provider name (`Config.provider`). To expose more than one - * transport, load the plugin more than once, each bound to a different provider - * — there is no provider/type parameter in the model-facing schema. The model - * sees only `{ description, prompt }`. - * - * The tool DESCRIPTION is derived from the bound provider's conversation-history - * descriptor ({@link SubagentProvider.inheritsParentContext}): a - * fresh-conversation provider (spawn, ACP) gets the standalone-prompt wording, - * while a seeded-conversation provider (fork) tells the model the child already - * sees the conversation's completed turns. This descriptor says nothing about - * Cordis scope, services, tools, or authority. The tool MIRRORS the - * provider's lifecycle via `subagent/provider-added`/`-removed` — it registers - * when the provider is (or becomes) available and unregisters when the - * provider goes away — so no load-order requirement exists and an HMR reload - * of the backend re-derives the wording from the fresh provider. - * - * Collection is SYNCHRONOUS this cut: `execute` starts a run and awaits - * `run.result` inside a `try/finally` that always disposes the run, so the - * owned child agent/session is torn down on every path (success, error, abort) - * and never leaks as a live idle child. A non-`completed` stop reason maps to an - * `isError` tool result (by throwing) rather than returning partial output as - * success. + * Model-facing delegation tool bound by configuration to one provider; transport selection is not + * exposed in its `{ description, prompt }` schema. Provider lifecycle controls registration and + * re-derives conversation-history wording after reload, so load order is irrelevant. * + * Execution synchronously awaits the child result and always disposes the run. Non-completed stop + * reasons become error results, while transport details remain behind `ctx.subagents`. Load this + * plugin more than once to expose multiple configured providers. * @module @deepseek-ai/dsh-tool-subagent */ @@ -105,16 +82,8 @@ export const Config: z = z.object({ model: z.string(), }).default(undefined as unknown as { model: string }), persona: z.string(), - // A schemastery object materializes {} (with [] for nested arrays) when the - // key is omitted — for toolFilter that would mean an EMPTY ALLOW-LIST, i.e. - // deny-everything, silently. Force the omitted key to stay absent (the same - // shape discipline as SystemPrompt's toolOrder); the cast is needed because - // .default() expects the object type. - // The NESTED arrays get the same treatment as the object itself: a partial - // filter ({deny: […]}) must not materialize allow: [] beside it — an empty - // allow-list means deny-EVERYTHING, so the materialized default would turn - // a deny-one config into deny-all. An EXPLICIT allow: [] (grant-only - // children) survives, since only the omitted key defaults to undefined. + // Schemastery otherwise materializes omitted objects and nested arrays as `{ allow: [] }`, which + // silently means deny all. Preserve omission while retaining an explicit empty allow-list. toolFilter: z.object({ allow: z.array(z.string()).default(undefined as unknown as string[]), deny: z.array(z.string()).default(undefined as unknown as string[]), @@ -290,7 +259,7 @@ export function apply(ctx: Context, config: Config): void { if (present !== undefined) { mount(present) } else { - // Not an error: the backend's fiber may simply activate after this one. + // Not an error: the backend's fiber may activate after this one. // The tool appears the moment the provider registers; a typo'd provider // name shows up as this note plus a tool that never materializes. ctx.logger.info(`subagent provider "${config.provider}" not registered yet; the "${config.toolName ?? 'subagent'}" tool will register when it appears`) From 0a486f09c91d0e5a3198bb40c22f034b52cea466 Mon Sep 17 00:00:00 2001 From: kingwl Date: Tue, 14 Jul 2026 23:34:47 +0800 Subject: [PATCH 092/323] chore: adopt node-addon-landlock-run source as native/ subtree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Bring the node-addon-landlock-run tree (tag v0.0.1, commit 614f7fd) into native/landlock-run as its source of record: launcher development happens here, next to the harness consumers, and the standalone repository becomes the release mirror the tree is exported to for packing and publishing (procedure in native/README.md). The subtree keeps its own pnpm workspace and lockfile and is NOT added to the harness workspace: harness installs, gates, and CI never touch it. The mirror's .github/ stays out of the subtree; a separate manually-dispatched workflow (.github/workflows/landlock-run.yml) runs the subtree's CI legs — the per-architecture native builds, real-kernel launcher proofs, and pack rehearsal — adapted with working-directory/cache paths. eslint ignores the subtree like vendor/; AGENTS.md gains the native/ layout line (+5 words on its budget ceiling). --- .github/workflows/landlock-run.yml | 127 +++++++ AGENTS.md | 1 + eslint.config.mjs | 1 + native/README.md | 20 + native/landlock-run/.gitignore | 13 + native/landlock-run/AGENTS.md | 50 +++ native/landlock-run/LICENSE | 28 ++ native/landlock-run/README.md | 58 +++ native/landlock-run/docs/architecture.md | 34 ++ native/landlock-run/docs/cli-contract.md | 34 ++ native/landlock-run/docs/naming.md | 30 ++ native/landlock-run/docs/packaging.md | 45 +++ native/landlock-run/docs/release.md | 57 +++ native/landlock-run/docs/support-matrix.md | 18 + native/landlock-run/package.json | 30 ++ native/landlock-run/packages/entry/README.md | 16 + .../landlock-run/packages/entry/package.json | 36 ++ .../landlock-run/packages/entry/src/index.ts | 126 +++++++ native/landlock-run/packages/entry/src/main.c | 302 +++++++++++++++ .../landlock-run/packages/entry/tsconfig.json | 11 + .../landlock-run/packages/linux-arm64/LICENSE | 28 ++ .../packages/linux-arm64/README.md | 7 + .../packages/linux-arm64/package.json | 26 ++ .../packages/linux-arm64/prebuilds.json | 10 + .../landlock-run/packages/linux-x64/LICENSE | 28 ++ .../landlock-run/packages/linux-x64/README.md | 7 + .../packages/linux-x64/package.json | 26 ++ .../packages/linux-x64/prebuilds.json | 10 + native/landlock-run/pnpm-lock.yaml | 345 ++++++++++++++++++ native/landlock-run/pnpm-workspace.yaml | 8 + .../scripts/assemble-prebuilds.mjs | 51 +++ native/landlock-run/scripts/build.ts | 86 +++++ native/landlock-run/scripts/bump-release.mjs | 90 +++++ .../landlock-run/scripts/commit-release.mjs | 42 +++ native/landlock-run/scripts/github-matrix.mjs | 66 ++++ native/landlock-run/scripts/pack-release.mjs | 76 ++++ native/landlock-run/scripts/repo.mjs | 88 +++++ .../landlock-run/scripts/verify-entry-lib.mjs | 25 ++ .../scripts/verify-launcher-binary.mjs | 31 ++ .../scripts/verify-packed-install.mjs | 223 +++++++++++ .../landlock-run/scripts/verify-release.mjs | 52 +++ native/landlock-run/test/entry.test.js | 76 ++++ native/landlock-run/test/launcher.test.js | 121 ++++++ native/landlock-run/tsconfig.base.json | 11 + native/landlock-run/tsconfig.json | 11 + scripts/doc-budgets.manifest.json | 2 +- 46 files changed, 2582 insertions(+), 1 deletion(-) create mode 100644 .github/workflows/landlock-run.yml create mode 100644 native/README.md create mode 100644 native/landlock-run/.gitignore create mode 100644 native/landlock-run/AGENTS.md create mode 100644 native/landlock-run/LICENSE create mode 100644 native/landlock-run/README.md create mode 100644 native/landlock-run/docs/architecture.md create mode 100644 native/landlock-run/docs/cli-contract.md create mode 100644 native/landlock-run/docs/naming.md create mode 100644 native/landlock-run/docs/packaging.md create mode 100644 native/landlock-run/docs/release.md create mode 100644 native/landlock-run/docs/support-matrix.md create mode 100644 native/landlock-run/package.json create mode 100644 native/landlock-run/packages/entry/README.md create mode 100644 native/landlock-run/packages/entry/package.json create mode 100644 native/landlock-run/packages/entry/src/index.ts create mode 100644 native/landlock-run/packages/entry/src/main.c create mode 100644 native/landlock-run/packages/entry/tsconfig.json create mode 100644 native/landlock-run/packages/linux-arm64/LICENSE create mode 100644 native/landlock-run/packages/linux-arm64/README.md create mode 100644 native/landlock-run/packages/linux-arm64/package.json create mode 100644 native/landlock-run/packages/linux-arm64/prebuilds.json create mode 100644 native/landlock-run/packages/linux-x64/LICENSE create mode 100644 native/landlock-run/packages/linux-x64/README.md create mode 100644 native/landlock-run/packages/linux-x64/package.json create mode 100644 native/landlock-run/packages/linux-x64/prebuilds.json create mode 100644 native/landlock-run/pnpm-lock.yaml create mode 100644 native/landlock-run/pnpm-workspace.yaml create mode 100644 native/landlock-run/scripts/assemble-prebuilds.mjs create mode 100644 native/landlock-run/scripts/build.ts create mode 100644 native/landlock-run/scripts/bump-release.mjs create mode 100644 native/landlock-run/scripts/commit-release.mjs create mode 100644 native/landlock-run/scripts/github-matrix.mjs create mode 100644 native/landlock-run/scripts/pack-release.mjs create mode 100644 native/landlock-run/scripts/repo.mjs create mode 100644 native/landlock-run/scripts/verify-entry-lib.mjs create mode 100644 native/landlock-run/scripts/verify-launcher-binary.mjs create mode 100644 native/landlock-run/scripts/verify-packed-install.mjs create mode 100644 native/landlock-run/scripts/verify-release.mjs create mode 100644 native/landlock-run/test/entry.test.js create mode 100644 native/landlock-run/test/launcher.test.js create mode 100644 native/landlock-run/tsconfig.base.json create mode 100644 native/landlock-run/tsconfig.json diff --git a/.github/workflows/landlock-run.yml b/.github/workflows/landlock-run.yml new file mode 100644 index 0000000000..8916f59a56 --- /dev/null +++ b/.github/workflows/landlock-run.yml @@ -0,0 +1,127 @@ +# Manually-dispatched CI for the landlock-run source of record +# (native/landlock-run). A separate workflow from ci.yml on purpose: the +# subtree is a self-contained pnpm workspace with its own gates, exercised on +# demand — per-architecture native legs (build + behavioral tests + pack +# rehearsal on real kernels) plus one darwin leg proving the documented +# degradation on hosts without a platform package. Legs derive from the +# subtree's checked-in package matrix (scripts/github-matrix.mjs). Packing +# for npm happens in the release mirror (node-addon-landlock-run) after an +# export — see native/README.md; this workflow never packs for release. +name: Landlock Run + +on: + workflow_dispatch: + +concurrency: + group: ${{ github.workflow }}-${{ github.ref }} + cancel-in-progress: true + +permissions: + contents: read + +defaults: + run: + working-directory: native/landlock-run + +jobs: + matrix: + name: Matrix + runs-on: ubuntu-24.04 + outputs: + ci: ${{ steps.matrix.outputs.ci }} + steps: + - uses: actions/checkout@v4 + + - id: matrix + run: echo "ci=$(node ./scripts/github-matrix.mjs ci)" >> "$GITHUB_OUTPUT" + + native: + name: ${{ matrix.platform }} + needs: matrix + runs-on: ${{ matrix.runner }} + strategy: + fail-fast: false + matrix: ${{ fromJson(needs.matrix.outputs.ci) }} + steps: + - uses: actions/checkout@v4 + + - uses: pnpm/action-setup@v4 + with: + package_json_file: native/landlock-run/package.json + + - uses: actions/setup-node@v4 + with: + node-version: 24 + cache: pnpm + cache-dependency-path: native/landlock-run/pnpm-lock.yaml + + - name: Install dependencies + run: pnpm install --frozen-lockfile + + - name: Install musl toolchain + run: | + sudo apt-get update -q + sudo apt-get install -yq musl-tools + + - name: Build TypeScript + run: pnpm build:ts + + - name: Typecheck + run: pnpm typecheck + + - name: Build native binaries (this architecture is the builder of record) + run: pnpm build:native + + - name: Entry tests (keyless) + run: node ./test/entry.test.js + + # NALR_REQUIRE_LANDLOCK: a self-skip on the very platform that exists to + # prove enforcement would be a false green, so an unenforcing kernel + # fails the leg instead of skipping. + - name: Launcher tests (real kernel enforcement) + run: node ./test/launcher.test.js + env: + NALR_REQUIRE_LANDLOCK: 1 + + - name: Pack rehearsal (pack → install → confine, this platform only) + run: | + node ./scripts/pack-release.mjs .release/npm --current-platform-only + node ./scripts/verify-packed-install.mjs .release/npm --current-platform-only + env: + NALR_REQUIRE_LANDLOCK: 1 + + darwin: + name: darwin (no platform package — degradation proof) + runs-on: macos-latest + steps: + - uses: actions/checkout@v4 + + - uses: pnpm/action-setup@v4 + with: + package_json_file: native/landlock-run/package.json + + - uses: actions/setup-node@v4 + with: + node-version: 24 + cache: pnpm + cache-dependency-path: native/landlock-run/pnpm-lock.yaml + + - name: Install dependencies + run: pnpm install --frozen-lockfile + + - name: Build TypeScript + run: pnpm build:ts + + - name: Typecheck + run: pnpm typecheck + + - name: Entry tests (keyless) + run: node ./test/entry.test.js + + - name: Launcher tests (must self-skip cleanly) + run: node ./test/launcher.test.js + + - name: Pack rehearsal (entry only — fallback resolution + unusable probe) + run: | + node ./scripts/pack-release.mjs .release/npm --current-platform-only + node ./scripts/verify-packed-install.mjs .release/npm --current-platform-only diff --git a/AGENTS.md b/AGENTS.md index 44aa15aea5..e5884ddd09 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -30,6 +30,7 @@ packages/ Harness packages at packages///, all named @deepseek-ai support/ dev/test infrastructure packages util/ zero-dependency utilities python/ Python SDK and bundled runtime (see python/README.md) +native/ node-addon-landlock-run source of record (see native/README.md) examples/ Runnable demos: thin cordis.yml leaves over the app packages (see examples/AGENTS.md) docs/ architecture, generated catalogs, RFCs, postmortems, cookbook (see docs/AGENTS.md) scripts/ repo gates and generators diff --git a/eslint.config.mjs b/eslint.config.mjs index 3f0e8ce820..2ec78d51f9 100644 --- a/eslint.config.mjs +++ b/eslint.config.mjs @@ -13,6 +13,7 @@ export default tseslint.config( '.claude/**', // harness-local state (worktrees, skills) — other checkouts, not this one's sources '**/.doc-typecheck-*/**', 'vendor/**', // vendored source keeps upstream style and idioms + 'native/**', // imported landlock-run subtree: self-contained workspace with its own gates (native/README.md) '**/*.js', '**/*.mjs', '*.config.ts', // root tool configs (vitest, tsdown) — no project service diff --git a/native/README.md b/native/README.md new file mode 100644 index 0000000000..983e67f740 --- /dev/null +++ b/native/README.md @@ -0,0 +1,20 @@ +# native/ + +Source of record for `node-addon-landlock-run`, the Landlock self-restrict-then-exec launcher the harness consumes from npm (`packages/sandbox/sandbox-local`, `packages/bash/bash-sandbox`). Launcher development happens HERE, next to the consumers; the standalone repository is the release mirror that packs and publishes the npm package family. + +## Release mirror + +| Directory | Mirror repo | Last exported release | Commit | +|---|---|---|---| +| `landlock-run/` | https://github.com/deepseek-harness/node-addon-landlock-run | `v0.0.1` | `614f7fd7dc11e6eaceefba9e7ff1fbe28b51ba22` | + +The subtree is a self-contained pnpm workspace with its own `AGENTS.md`, docs, gates, and lockfile; it is NOT part of the harness workspace (`pnpm-workspace.yaml` does not include it), so harness installs, builds, and CI gates never touch it. The mirror's `.github/` stays out of the subtree — [.github/workflows/landlock-run.yml](../.github/workflows/landlock-run.yml) (manual dispatch) runs the subtree's CI legs here, and a change to those legs is mirrored into the mirror's `ci.yml` at the next export. + +## Export procedure (cutting a release) + +1. Land the launcher change here through a normal harness PR; dispatch the `Landlock Run` workflow and get its legs green. +2. In the mirror checkout, replace everything except `.github/`: `git -C rm -rq -- . ':!.github'`, then `git -C archive HEAD:native/landlock-run | tar -x -C `, then `git -C add -A` and commit. +3. In the mirror, follow its release checklist (`docs/release.md`): `pnpm release:commit ` → merge → tag `vX.Y.Z` → two-phase `Release` workflow (`publish=false` rehearsal, then `publish=true` from the tag). +4. Update the manifest table above with the released tag/commit, and bump the harness consumers' dependency range in the same change. + +The mirror must not diverge: a change committed there directly (hotfix during a release) is ported back here before the next export. diff --git a/native/landlock-run/.gitignore b/native/landlock-run/.gitignore new file mode 100644 index 0000000000..0d7597f2db --- /dev/null +++ b/native/landlock-run/.gitignore @@ -0,0 +1,13 @@ +# Built native binaries ride npm tarballs via each package's `files` list, +# never git. Root-level rules on purpose: a package-nested ignore file would +# also steer `pnpm pack` and has silently dropped payload from tarballs before. +packages/*/bin/ +packages/*/lib/ + +/.claude/ +/.release/ +dist/ +node_modules/ +/package-lock.json +*.log +*.tsbuildinfo diff --git a/native/landlock-run/AGENTS.md b/native/landlock-run/AGENTS.md new file mode 100644 index 0000000000..31e12e177c --- /dev/null +++ b/native/landlock-run/AGENTS.md @@ -0,0 +1,50 @@ +# AGENTS.md + +This workspace builds `landlock-run`, a Landlock self-restrict-then-exec launcher: a small, auditable confinement binary distributed as prebuilt per-platform npm packages, plus the thin JS entry package that resolves it and speaks its CLI contract. The source of record is the `deepseek-harness` repository's `native/landlock-run/`; the `node-addon-landlock-run` repository is the release mirror this tree is exported to for packing and publishing (procedure: `native/README.md` in the harness repo). Make changes in the source of record, never only in the mirror. + +## Pre-release stance + +The project is pre-1.0. Prefer the correct public shape over compatibility shims: if a package name, exported field, layout, or contract detail is wrong, rename it and update all references in the same change. Do not add deprecated aliases unless a stable release already needs them. + +## Runtime safety rules + +- Every tool must fail closed. If a ruleset cannot be created or the kernel does not enforce it, exit non-zero WITHOUT exec'ing the wrapped command. Never run unconfined as a fallback. +- Runtime binaries and the entry packages take NO environment-variable overrides: which binary confines a process must never be decidable by the ambient environment. Test injection is by function parameter; the `NALR_*` prefix is for build/test orchestration only. +- Kernel UAPI is self-defined in the C source (verbatim from the kernel headers), keeping builds independent of toolchain header vintage and making the definitions part of the audit record. +- No libraries beyond libc, linked statically against musl. The audit surface of a tool is its C source plus the kernel's stable syscall contract. +- The CLI contract of each tool ([docs/cli-contract.md](docs/cli-contract.md)) is the cross-repo compatibility surface: argv grammar, exit codes, and report lines change only with a version bump and a changelog entry, and consumers parse them only through the entry package. +- There is deliberately NO install-time build fallback: a host without a matching platform package gets a nonexistent launcher path, the consumer's probe fails, and the consumer falls closed — that degradation is part of the design, not a gap to fill with node-gyp. + +## Repository layout + +```text +packages/entry/ Published entry package: JS seam (resolve/probe/grants) + the C source. +packages/linux-*/ Published per-platform packages: one prebuilt static binary, no JavaScript. +scripts/ Build, matrix derivation, prepack gates, and release orchestration. +test/ Plain-node behavioral tests (entry seam + real-kernel launcher proofs). +docs/ Architecture, packaging, CLI contract, release, support matrix, naming. +``` + +## Commands + +```sh +pnpm install +pnpm build:ts # entry packages → lib/ +pnpm build:native # this Linux architecture's binaries (needs musl-tools); fails fast elsewhere +pnpm typecheck +pnpm test # entry tests everywhere; launcher tests need linux + built binary +``` + +## Packaging invariants + +- The package matrix is explicit, checked-in metadata: `packages//package.json` (`os`, `cpu`), `packages//prebuilds.json` (the binaries that may exist there), and [docs/support-matrix.md](docs/support-matrix.md) stay synchronized when the matrix changes. `scripts/github-matrix.mjs` derives CI and release matrices from it; nothing else enumerates platforms. +- Platform package names contain platform only (`-linux-x64`), never tool variants — those stay inside `prebuilds.json`. Static musl linking is why there is no libc suffix: one binary serves glibc and musl distros. +- Platform packages ship no JavaScript; the entry package resolves them to file paths. Backends prove themselves at runtime through the functional probe, never through metadata trust. +- Builds are native-only: each architecture compiles its own binary on its own runner (CI is the builder of record); no cross toolchain enters the repo. +- Every tarball is gated at pack time: platform packages refuse to pack without their declared binaries present, executable, and in the right ELF architecture (`verify-launcher-binary.mjs`), entry packages without built `lib/` (`verify-entry-lib.mjs`), and the release pipeline byte-pins installed binaries against the workspace builds (`verify-packed-install.mjs`). +- Platform tarballs are packed with `npm pack`, never `pnpm pack`: pnpm's pack path strips the executable bit (observed on 11.7.0), shipping a launcher no consumer can spawn. `pack-release.mjs` encodes the split; the rehearsal asserts executability of the installed copy so a regression fails loudly instead of masquerading as a non-enforcing kernel. +- Generated artifacts stay out of git: `packages/*/bin/`, `packages/*/lib/`, `dist/`, `.release/`, `*.tsbuildinfo`. Ignore rules live in the ROOT `.gitignore` only — a package-nested ignore file can silently drop payload from tarballs. + +## Documentation + +User-facing docs are English. Keep the README focused on install, usage, and support status; durable design decisions belong in docs/ alongside the code, and the current implemented shape belongs in [docs/architecture.md](docs/architecture.md). diff --git a/native/landlock-run/LICENSE b/native/landlock-run/LICENSE new file mode 100644 index 0000000000..8187059c9a --- /dev/null +++ b/native/landlock-run/LICENSE @@ -0,0 +1,28 @@ +BSD 3-Clause License + +Copyright (c) 2026, node-addon-landlock-run contributors + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +1. Redistributions of source code must retain the above copyright notice, this + list of conditions and the following disclaimer. + +2. Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +3. Neither the name of the copyright holder nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE +FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR +SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER +CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, +OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/native/landlock-run/README.md b/native/landlock-run/README.md new file mode 100644 index 0000000000..2bb92843e6 --- /dev/null +++ b/native/landlock-run/README.md @@ -0,0 +1,58 @@ +# node-addon-landlock-run + +A [Landlock](https://landlock.io/) self-restrict-then-exec launcher for confining subprocesses on Linux, distributed as prebuilt per-platform npm packages plus a thin JS entry package that resolves the binary and speaks its CLI contract. Built for agent harnesses and other hosts that need to run untrusted commands under a filesystem allow-list without confining themselves. + +The first tool is **`landlock-run`** — a self-restrict-then-exec [Landlock](https://landlock.io/) launcher (~300 lines of C11 over the raw kernel UAPI, statically linked against musl). It installs a Landlock ruleset on itself and `exec`s the wrapped command; the ruleset is inherited across `execve`, so the command and every process it spawns run confined while the invoking process stays unrestricted. Fail-closed: if the kernel cannot enforce, it exits without running the command. + +## Install + +```sh +npm install node-addon-landlock-run +``` + +Published packages use an entry package plus platform optional packages: + +```text +node-addon-landlock-run +node-addon-landlock-run-linux-x64 +node-addon-landlock-run-linux-arm64 +``` + +npm's `os`/`cpu` fields make installers fetch only the matching platform package. There is no install-time build fallback on purpose: on a host without a platform package the resolved path never exists, the probe reports `unusable`, and the consumer falls closed. + +## Usage + +```js +import { grantArgs, launcherPath, probe } from 'node-addon-landlock-run'; + +const launcher = launcherPath(); +if (probe(launcher) !== 'unusable') { + const argv = [launcher, ...grantArgs({ readOnly: ['/'], readWrite: ['/tmp/work'] }), '--', 'bash', '-c', command]; + // spawn argv with your process runner of choice +} +``` + +The public API is intentionally small: + +- `launcherPath()`: absolute path of this host's launcher (existence deliberately unchecked — the probe is the availability signal). +- `probe(launcher?, { timeoutMs? })`: functional enforcement probe — `'full' | 'partial' | 'unusable'`. +- `grantArgs({ readOnly?, readWrite? })`: the launcher's grant argv; everything not granted is denied. +- `LAUNCHER_BIN`, `LAUNCHER_FAILURE_EXIT` (125): contract constants. + +The full binary contract (argv grammar, exit codes, report lines) is pinned in [docs/cli-contract.md](docs/cli-contract.md). + +## Support + +linux-x64 and linux-arm64, kernel with Landlock enabled (5.13+; ABI level determines `full` vs `partial` enforcement — see [docs/support-matrix.md](docs/support-matrix.md)). Other platforms deliberately have no package: consumers run different confinement backends there. + +## Development + +```sh +corepack enable +pnpm install +pnpm build:ts # entry packages → lib/ +pnpm build:native # this Linux architecture's binaries (apt-get install musl-tools) +pnpm test +``` + +Binaries are git-ignored and built natively per architecture — locally for your own machine, by CI's per-arch runners as the builders of record. Release flow: [docs/release.md](docs/release.md). diff --git a/native/landlock-run/docs/architecture.md b/native/landlock-run/docs/architecture.md new file mode 100644 index 0000000000..e6974f4e50 --- /dev/null +++ b/native/landlock-run/docs/architecture.md @@ -0,0 +1,34 @@ +# Architecture + +This repository owns confinement *mechanism*, not policy: consumers (agent harnesses, sandbox seams) decide which paths a run may read or write; this package family provides the launcher that enforces those grants and the JS seam that resolves and speaks to it. The packaging follows the per-platform-package model of [`node-addon-require-builtin`](https://www.npmjs.com/package/@esplus/node-addon-require-builtin) (and esbuild), adapted from Node addons to standalone static executables. + +## Two-layer package family + +The family is one entry package plus per-platform binary packages: + +- **Entry package** (`node-addon-landlock-run`): ESM JavaScript. Owns the tool's CLI contract — path resolution (`launcherPath`), the functional probe (`probe`), grant-argv construction (`grantArgs`), and the contract constants. Ships the C source in its tarball for auditability. Lists every platform package as an `optionalDependency`. +- **Platform packages** (`node-addon-landlock-run-linux-{x64,arm64}`): one prebuilt static binary under `bin/`, a `prebuilds.json` declaring it, and no JavaScript at all. npm's `os`/`cpu` fields select the matching one at install time; the entry package resolves it to a file path — there is nothing to import. + +Because the contract parser and the binary version together in one family, probe-parsing drift against the binary is structurally impossible — the failure mode the split exists to prevent. + +There is no shared loader package: platform packages have nothing to load. If a second tool ever needs shared JS, extract it then, not preemptively. + +## Resolution and availability + +`launcherPath()` resolves `node-addon-landlock-run--` and returns `/bin/landlock-run`. When the package is not resolvable it returns a deterministic fallback path inside the entry package's own `node_modules` that simply never exists. Existence is deliberately unchecked either way: `probe()` is the single availability signal, and a missing binary probes `unusable` exactly like an unenforcing kernel. Consumers get one degradation path, not two. + +The probe is functional — the launcher builds and enforces a real maximal ruleset in a short-lived child — because version checks would miss a kernel that has the syscalls but refuses enforcement. + +## Fail-closed everywhere + +The launcher exits `125` without exec'ing the command on any launcher-level failure: usage error, unenforcing kernel, unopenable grant root, failed exec. Partial enforcement (an older Landlock ABI governing only a subset of accesses) is accepted, reported on stderr, and surfaced by the probe as `partial` — the consumer decides what its mode vocabulary promises at each level. Neither the binary nor the entry package reads environment variables: which binary confines a process is never decidable by the ambient environment. + +## Build and release model + +Builds are native-only. `scripts/build.ts` compiles the running architecture's binaries with the distro `musl-gcc` (static: no loader or libc expectations on consumers, one binary for glibc and musl distros); CI's per-architecture runners are the builders of record, and no cross toolchain exists in the repo. The audit surface of a tool is its reviewed C source plus CI provenance, enforced by three gates: platform prepack refuses missing/wrong-ELF binaries, entry prepack refuses unbuilt `lib/`, and the release pipeline byte-pins installed binaries against the workspace builds they were packed from. + +The package matrix is checked-in metadata (`prebuilds.json` + `os`/`cpu` fields); `scripts/github-matrix.mjs` derives the CI and Release matrices from it, so adding a platform extends automation without editing workflows. + +## Adding a platform + +A new platform adds one `packages//` package (`package.json` with `os`/`cpu`, `prebuilds.json`, README, LICENSE), a runner entry in `scripts/github-matrix.mjs`, and a row in [support-matrix.md](support-matrix.md) — added only together with a native GitHub runner that builds and proves it (the no-cross-toolchain rule). Sibling launchers for other confinement mechanisms belong in their own repositories on this same template, not as second tools here. diff --git a/native/landlock-run/docs/cli-contract.md b/native/landlock-run/docs/cli-contract.md new file mode 100644 index 0000000000..57ab0f604c --- /dev/null +++ b/native/landlock-run/docs/cli-contract.md @@ -0,0 +1,34 @@ +# CLI contract: landlock-run + +This file pins the launcher's externally observable behavior — the cross-repo compatibility surface between the binaries and every consumer. Consumers interact with it only through the entry package (`launcherPath`/`probe`/`grantArgs`); changing anything below requires a version bump for the whole package family and a note in the release notes. + +## Invocation grammar + +```text +landlock-run [--ro ]... [--rw ]... -- ... +landlock-run --probe +``` + +- `--ro `: grant read + execute beneath ``. +- `--rw `: grant full filesystem access beneath `` (every access the negotiated kernel ABI can govern). +- Everything not granted is denied — Landlock rulesets are allow-lists. +- A grant on a non-directory keeps only its file-compatible access bits (this is how a `--rw /dev/null` grant works). +- `--`: mandatory separator; everything after it is the command argv, exec'd via `execvp` with the launcher's environment unchanged. +- `--probe`: mutually exclusive with grants and a command. +- No other flags, no environment-variable inputs. + +## Exit codes + +- `125` (`LAUNCHER_FAILURE_EXIT`): every launcher-level failure — usage error, kernel that cannot enforce Landlock, unopenable grant root, failed `exec`. The wrapped command was NOT run (fail-closed; the one exception is `exec` itself failing after restriction, which by definition never ran the command either). +- Any other status: the wrapped command's own exit status, passed through unchanged. +- `--probe`: `0` when the kernel enforces (fully or partially), `125` otherwise. + +## Report lines + +- Probe success prints exactly one stdout line: `landlock: fully enforced` or `landlock: partially enforced (older ABI)`. The entry package's `probe()` maps these to `full`/`partial`; a non-zero probe exit maps to `unusable`. +- A confined run under a partial-ABI kernel prints one stderr line `landlock-run: partial enforcement (older Landlock ABI)` and proceeds — still confined for everything the kernel supports. +- Every fatal error prints one stderr line prefixed `landlock-run: ` before exiting `125`. + +## Confinement semantics + +The launcher sets `no_new_privs`, installs the ruleset on itself, and `exec`s the command; the ruleset is inherited across `execve`, so every descendant process is equally confined. The ruleset governs the filesystem accesses of the kernel's negotiated Landlock ABI (up to ABI 5); accesses newer than the running ABI are not governed and are the difference between `full` and `partial`. diff --git a/native/landlock-run/docs/naming.md b/native/landlock-run/docs/naming.md new file mode 100644 index 0000000000..9de9f0b95f --- /dev/null +++ b/native/landlock-run/docs/naming.md @@ -0,0 +1,30 @@ +# Naming + +## npm packages + +The public package family is unscoped, using the `node-addon-landlock-run` package prefix; platform packages append platform information only: + +```text +node-addon-landlock-run +node-addon-landlock-run- +``` + +Platform suffixes carry no libc component (binaries are static musl) and no variant component — variants stay inside `prebuilds.json` and binary filenames. + +## Binaries + +The launcher executable is `landlock-run`, shipped at `bin/landlock-run` inside each platform package. + +## Environment variables + +The `NALR_` prefix (Node Addon Landlock Run) is reserved for build/test orchestration: + +```text +NALR_REQUIRE_LANDLOCK test-only: an unenforcing kernel fails instead of skipping +``` + +Runtime binaries and entry packages read NO environment variables — a runtime safety rule ([AGENTS.md](../AGENTS.md)), not a naming convention. Do not include the npm scope in environment variable names. + +## C symbols + +The launcher is a single C file with static linkage; there is no exported symbol namespace. Kernel UAPI constants keep their kernel names prefixed `LL_` where locally defined. diff --git a/native/landlock-run/docs/packaging.md b/native/landlock-run/docs/packaging.md new file mode 100644 index 0000000000..9a1be47b2a --- /dev/null +++ b/native/landlock-run/docs/packaging.md @@ -0,0 +1,45 @@ +# Packaging + +The package family uses the same broad shape as native packages such as esbuild: one JS entry package plus platform optional packages. Unlike Node addons there is no ABI or backend dimension — each platform package carries exactly the static executables its `prebuilds.json` declares. + +## Published packages + +```text +node-addon-landlock-run +node-addon-landlock-run-linux-x64 +node-addon-landlock-run-linux-arm64 +``` + +Unsupported platforms are intentionally absent from `optionalDependencies` — see [support-matrix.md](support-matrix.md). + +## Package matrix + +The matrix is explicit in checked-in metadata: + +- `packages/entry/package.json` lists the platform packages as `optionalDependencies`. +- `packages//package.json` declares `os` and `cpu`. There is no `libc` field on purpose: the binaries are statically linked against musl and run on glibc and musl distros alike. +- `packages//prebuilds.json` declares the binaries that may exist in that package (`tool`, `kind`, `path`). +- [support-matrix.md](support-matrix.md) explains why unsupported platform packages are not published. + +`scripts/github-matrix.mjs` derives the CI and Release matrices from these files. `scripts/build.ts` builds only the current host's targets, into `packages//bin/`; it is not a matrix generator. When changing the matrix, update package metadata, `prebuilds.json`, the lockfile, and the support/release docs in the same change. + +## Runtime selection + +1. npm's `os`/`cpu` fields make installers fetch only the matching platform package. +2. The entry package's `launcherPath()` resolves it to `/bin/landlock-run`; unresolvable packages yield a deterministic, never-existing fallback path. +3. `probe()` is the single availability signal: missing binary and unenforcing kernel are deliberately indistinguishable (`unusable`), so consumers have one fail-closed path. + +## No install fallback + +The entry package has NO install script and never compiles on the consumer host. A compile fallback would require a musl toolchain everywhere and turn a clean fail-closed degradation into an environment-dependent maybe. The packed-manifest check in `verify-packed-install.mjs` enforces the absence of install lifecycle scripts. + +## Pack gates + +Platform tarballs are produced by `npm pack`, entry tarballs by `pnpm pack` — deliberately split: `pnpm pack` (observed on 11.7.0) normalizes file modes and strips the executable bit, which would ship a launcher no consumer can spawn, while platform packages have no dependencies and so need none of pnpm's workspace-protocol conversion; entry packages need that conversion and carry no executables. `scripts/pack-release.mjs` encodes the split — never hand-pack a platform package with pnpm. + +Both pack paths produce the exact publish bytes behind a `prepack` gate: + +- Platform packages: `scripts/verify-launcher-binary.mjs` — every declared binary present, executable, ELF `e_machine` matching the declared `cpu`, nothing undeclared in `bin/`. +- Entry packages: `scripts/verify-entry-lib.mjs` — built `lib/` present. + +`scripts/verify-packed-install.mjs` then rehearses the consumer path from the packed tarballs: payload checks, a throwaway install, a byte-pin of the installed binary against the workspace build, an executability check on the installed copy, and a real confinement world-proof through the installed launcher. A non-executable or missing binary fails loudly here instead of masquerading as a non-enforcing kernel. diff --git a/native/landlock-run/docs/release.md b/native/landlock-run/docs/release.md new file mode 100644 index 0000000000..e43b2d188c --- /dev/null +++ b/native/landlock-run/docs/release.md @@ -0,0 +1,57 @@ +# Release + +Pre-1.0: treat this as a release checklist, not a stability policy. + +## Versioning + +One version across every package in the repo. Use the bump helper: + +```sh +pnpm release:bump patch # or minor / major / x.y.z +``` + +It updates the root and every `packages/*` manifest, refreshes the lockfile (`--ignore-scripts --lockfile-only`), and runs `release:verify`. Explicit versions accept full semver including prereleases (`pnpm release:bump 0.0.0-test.0`); the publish workflow puts prerelease versions under the `next` dist-tag, so `latest` never points at a test build. Keep `workspace:*` dependencies in source; pnpm converts them to concrete versions during pack. + +Version bumps are normal source changes: open a release PR (or commit) with the manifests and lockfile, merge it, then create the matching `vX.Y.Z` tag from that commit. The publish workflow validates that the tag matches every package version. + +```sh +pnpm release:commit patch # bump + stage + commit in one command +git tag v0.0.2 +``` + +## Preflight + +```sh +pnpm install --frozen-lockfile +pnpm build:ts +pnpm typecheck +pnpm test # launcher half needs a Linux host with the binary built +``` + +On a Linux host, also rehearse the pack path locally: + +```sh +pnpm build:native +node ./scripts/pack-release.mjs .release/npm --current-platform-only +node ./scripts/verify-packed-install.mjs .release/npm --current-platform-only +``` + +## Publish + +Use the `Release` workflow so every binary is built on its matching native runner: + +1. Run it with `publish=false` (from the release commit) to build all platform binaries, assemble and verify the payloads, pack the tarballs in publish order, rehearse the packed install, and upload the `npm-tarballs` artifact for inspection. +2. Create and push the `vX.Y.Z` tag matching the package versions. +3. Run the same workflow from that tag with `publish=true`. + +The workflow publishes only from the final packed tarballs, in `publish-order.txt` order (platform packages before the entry that optionally depends on them). It supports npm trusted publishing through GitHub OIDC; without it, provide an `NPM_TOKEN` secret in the `npm-publish` environment. Packages publish with `--access public`. + +Manual local fallback (current platform's packages only) — always through `pack-release.mjs`, never `pnpm publish` directly (pnpm's pack path strips the launcher's executable bit; see [packaging.md](packaging.md)): + +```sh +node ./scripts/pack-release.mjs dist/npm --current-platform-only +node ./scripts/verify-packed-install.mjs dist/npm --current-platform-only +while IFS= read -r tarball; do npm publish "dist/npm/${tarball}" --access public; done < dist/npm/publish-order.txt +``` + +Do not commit `.npmrc` files with tokens or registry overrides. diff --git a/native/landlock-run/docs/support-matrix.md b/native/landlock-run/docs/support-matrix.md new file mode 100644 index 0000000000..96d02b3cf6 --- /dev/null +++ b/native/landlock-run/docs/support-matrix.md @@ -0,0 +1,18 @@ +# Support matrix + +## Supported + +| Platform package | GitHub runner (builder of record) | Notes | +|---|---|---| +| `node-addon-landlock-run-linux-x64` | `ubuntu-24.04` | static musl — glibc and musl distros alike | +| `node-addon-landlock-run-linux-arm64` | `ubuntu-24.04-arm` | static musl — glibc and musl distros alike | + +Enforcement additionally requires a kernel with Landlock enabled (5.13+). The negotiated ABI level decides the probe verdict: every access this build knows governed → `full`; an older ABI governing a subset → `partial` (still confined for everything it supports); Landlock absent or disabled → `unusable`, and the launcher refuses to run commands at all. The probe — not the kernel version — is the authority: a kernel built without Landlock, or with the LSM disabled, probes `unusable` regardless of its version. + +## Deliberately unsupported + +- **darwin**: macOS consumers typically confine through `sandbox-exec`/Seatbelt, which ships with the OS — there is no binary to distribute. +- **win32**: a Windows confinement launcher would be a different mechanism in its own repository, not a port of this one. +- **Other Linux architectures** (riscv64, s390x, …): no native CI builder of record yet. The no-cross-toolchain rule means a platform package is added only together with a native runner that builds and proves it. + +A consumer on an unsupported platform resolves a nonexistent launcher path, probes `unusable`, and falls closed — the documented degradation, exercised by CI's darwin leg. diff --git a/native/landlock-run/package.json b/native/landlock-run/package.json new file mode 100644 index 0000000000..f516588f17 --- /dev/null +++ b/native/landlock-run/package.json @@ -0,0 +1,30 @@ +{ + "name": "node-addon-landlock-run-workspace", + "version": "0.0.1", + "private": true, + "type": "module", + "license": "BSD-3-Clause", + "packageManager": "pnpm@11.7.0", + "scripts": { + "build": "pnpm build:ts", + "build:ts": "tsc -b", + "build:native": "tsx ./scripts/build.ts", + "typecheck": "tsc --noEmit && tsc -b --dry", + "test": "node ./test/entry.test.js && node ./test/launcher.test.js", + "test:entry": "node ./test/entry.test.js", + "test:launcher": "node ./test/launcher.test.js", + "gha:matrix": "node ./scripts/github-matrix.mjs", + "release:bump": "node ./scripts/bump-release.mjs", + "release:commit": "node ./scripts/commit-release.mjs", + "release:assemble-prebuilds": "node ./scripts/assemble-prebuilds.mjs", + "release:verify": "node ./scripts/verify-release.mjs", + "release:pack": "node ./scripts/pack-release.mjs", + "release:verify-packed-install": "node ./scripts/verify-packed-install.mjs" + }, + "devDependencies": { + "node-addon-landlock-run": "workspace:*", + "@types/node": "^24.10.0", + "tsx": "^4.20.6", + "typescript": "^5.9.3" + } +} diff --git a/native/landlock-run/packages/entry/README.md b/native/landlock-run/packages/entry/README.md new file mode 100644 index 0000000000..789b1ddf6b --- /dev/null +++ b/native/landlock-run/packages/entry/README.md @@ -0,0 +1,16 @@ +# node-addon-landlock-run + +Landlock self-restrict-then-exec launcher for confining subprocesses on Linux: this entry package resolves the per-platform prebuilt binary, runs its functional enforcement probe, and builds its grant argv — consumers never spell launcher flags or parse launcher output themselves. + +```js +import { grantArgs, launcherPath, probe } from 'node-addon-landlock-run'; + +const launcher = launcherPath(); +if (probe(launcher) !== 'unusable') { + const argv = [launcher, ...grantArgs({ readOnly: ['/'], readWrite: ['/tmp/work'] }), '--', 'bash', '-c', command]; +} +``` + +The launcher installs a Landlock ruleset on itself and `exec`s the wrapped command; the ruleset is inherited across `execve`, so the whole process tree runs confined. Everything not granted is denied, and launcher failures exit `125` without running the command — fail-closed, never fail-open. The binary contract is pinned in the repo's `docs/cli-contract.md`; the C source rides this tarball (`src/main.c`) for audit. + +Platform packages (`os`/`cpu`-selected optional dependencies, no JavaScript inside): `node-addon-landlock-run-linux-x64`, `node-addon-landlock-run-linux-arm64`. On hosts without one, `launcherPath()` returns a deterministic nonexistent path and `probe()` reports `'unusable'` — there is deliberately no install-time compile fallback. diff --git a/native/landlock-run/packages/entry/package.json b/native/landlock-run/packages/entry/package.json new file mode 100644 index 0000000000..f05e81f06b --- /dev/null +++ b/native/landlock-run/packages/entry/package.json @@ -0,0 +1,36 @@ +{ + "name": "node-addon-landlock-run", + "version": "0.0.1", + "type": "module", + "description": "Landlock self-restrict-then-exec launcher for sandboxing subprocesses on Linux: per-platform prebuilt static binaries plus the JS seam that resolves, probes, and speaks their CLI contract", + "main": "lib/index.js", + "types": "lib/index.d.ts", + "exports": { + ".": { + "types": "./lib/index.d.ts", + "default": "./lib/index.js" + }, + "./package.json": "./package.json" + }, + "files": [ + "README.md", + "lib/", + "!lib/*.tsbuildinfo", + "src/main.c" + ], + "scripts": { + "build:js": "tsc -b", + "prepack": "node ../../scripts/verify-entry-lib.mjs" + }, + "engines": { + "node": ">=20" + }, + "license": "BSD-3-Clause", + "publishConfig": { + "access": "public" + }, + "optionalDependencies": { + "node-addon-landlock-run-linux-arm64": "workspace:*", + "node-addon-landlock-run-linux-x64": "workspace:*" + } +} diff --git a/native/landlock-run/packages/entry/src/index.ts b/native/landlock-run/packages/entry/src/index.ts new file mode 100644 index 0000000000..53de86122f --- /dev/null +++ b/native/landlock-run/packages/entry/src/index.ts @@ -0,0 +1,126 @@ +/** + * The JS seam over the prebuilt `landlock-run` launcher: resolve the + * binary for this host, build its grant argv, and run its functional probe. + * + * This module owns the launcher's CLI contract (`docs/cli-contract.md`) so + * consumers never parse launcher output or spell launcher flags themselves — + * the contract and the binaries version together in one package family, + * which makes probe-parsing drift against the binary structurally + * impossible. Policy stays with the consumer: this package does not know + * what a "sandbox mode" is, only which paths are granted read or write. + * + * Deliberately no environment-variable overrides anywhere in this module: + * which binary confines a process must never be decidable by the ambient + * environment. Test injection is by function parameter. + */ +import { spawnSync } from 'node:child_process' +import { createRequire } from 'node:module' +import { dirname, join } from 'node:path' +import { fileURLToPath } from 'node:url' + +/** The launcher binary's file name inside each platform package's `bin/`. */ +export const LAUNCHER_BIN = 'landlock-run' + +/** + * The exit code for every launcher-level failure (usage error, unenforcing + * kernel, unopenable grant root, failed exec) — chosen because the wrapped + * command itself is unlikely to use it, so a consumer can tell launcher + * failures from command failures. Part of the CLI contract. + */ +export const LAUNCHER_FAILURE_EXIT = 125 + +/** + * The probe's verdict on this host: `full` when the running kernel enforces + * every access the launcher can govern, `partial` when an older Landlock ABI + * governs only a subset (still confined for everything it supports), and + * `unusable` when nothing can be enforced — a kernel without Landlock, a + * disabled LSM, or a missing binary, all indistinguishable on purpose + * because the consumer's answer is the same: do not trust this launcher. + */ +export type LandlockEnforcement = 'full' | 'partial' | 'unusable' + +/** + * Filesystem grants for one confined run. Everything not granted is denied — + * Landlock rulesets are allow-lists. + */ +export interface LauncherGrants { + /** Roots granted read + execute beneath (the launcher's `--ro`). */ + readonly readOnly?: readonly string[] + /** Roots granted full filesystem access beneath (the launcher's `--rw`). */ + readonly readWrite?: readonly string[] +} + +/** + * Path of the launcher binary for this host: resolved from the per-platform + * npm package `node-addon-landlock-run--` (npm's + * `os`/`cpu` fields make installers fetch only the matching one). When the + * package is not resolvable — a platform without one, or an install that + * skipped the optional dependency — the returned fallback path points inside + * this package's own `node_modules` and simply never exists. Existence is + * deliberately not checked either way: {@link probe} is the single + * availability signal (a missing binary probes `unusable` the same way an + * unenforcing kernel does). + * @param resolvePackageJson - test seam over `require.resolve` (the default + * covers real installs); receives the platform package's `package.json` + * specifier and returns its absolute path, throwing when unresolvable. + * @returns the absolute launcher path to probe and exec. + */ +export function launcherPath( + resolvePackageJson: (specifier: string) => string = createRequire(import.meta.url).resolve, +): string { + const platformPackage = `node-addon-landlock-run-${process.platform}-${process.arch}` + try { + return join(dirname(resolvePackageJson(`${platformPackage}/package.json`)), 'bin', LAUNCHER_BIN) + } catch { + // Unresolvable platform package: no such package exists for this host, or + // it was not installed. Fall back to the path pnpm's layout WOULD use — + // absolute, inside this package's boundary (never cwd-relative: a + // spawnable relative path here would hand cwd control over which binary + // confines), and nonexistent exactly when the package is absent. + return fileURLToPath(new URL(`../node_modules/${platformPackage}/bin/${LAUNCHER_BIN}`, import.meta.url)) + } +} + +/** + * The launcher grant arguments for one set of filesystem grants — everything + * before the `--` argv separator. A caller spawns + * `[launcherPath(), ...grantArgs(grants), '--', ...command]`; the flag + * spellings stay private to this package. + * @param grants - the read-only and read-write roots to allow. + * @returns the `--ro ` / `--rw ` argument list, read-only roots + * first, in the caller's order. + */ +export function grantArgs(grants: LauncherGrants): string[] { + return [ + ...(grants.readOnly ?? []).flatMap(root => ['--ro', root]), + ...(grants.readWrite ?? []).flatMap(root => ['--rw', root]), + ] +} + +/** + * Functional probe: `landlock-run --probe` builds and enforces a maximal + * ruleset in a short-lived child and exits 0 only when the running kernel + * actually enforces it — `--version`-style checks would miss a kernel that + * has the syscalls but refuses enforcement. The probe's one report line is + * part of the CLI contract and distinguishes complete from per-ABI-subset + * enforcement; a zero exit without the partial marker reads as `full`. A + * failed or timed-out spawn (missing binary, wrong architecture, unenforcing + * kernel) probes `unusable`. Synchronous by design: consumers run it once + * and cache the verdict. + * @param launcher - the launcher path to probe; defaults to + * {@link launcherPath}'s resolution for this host. + * @param options - `timeoutMs` bounds the probe child (default 2000). + * @returns the enforcement verdict for this host. + */ +export function probe( + launcher: string = launcherPath(), + options: { timeoutMs?: number } = {}, +): LandlockEnforcement { + const result = spawnSync(launcher, ['--probe'], { + timeout: options.timeoutMs ?? 2000, + encoding: 'utf8', + stdio: ['ignore', 'pipe', 'ignore'], + }) + if (result.status !== 0) return 'unusable' + return /partially enforced/.test(result.stdout) ? 'partial' : 'full' +} diff --git a/native/landlock-run/packages/entry/src/main.c b/native/landlock-run/packages/entry/src/main.c new file mode 100644 index 0000000000..2535f8bc31 --- /dev/null +++ b/native/landlock-run/packages/entry/src/main.c @@ -0,0 +1,302 @@ +/* + * landlock-run: self-restrict-then-exec Landlock launcher. + * + * The Landlock rung of a consuming sandbox seam, for Linux hosts where + * `bwrap` is + * unusable (not installed, unprivileged user namespaces disabled, or an LSM + * profile that denies mount — Landlock is an independent syscall family and + * needs none of those). The launcher installs a Landlock + * ruleset on itself and `exec`s the wrapped command; the ruleset is inherited + * across `execve`, so the command (and every process it spawns) runs confined + * while the invoking process stays unrestricted. + * + * CLI contract (mirrors the `bwrap` runner argv shape the executor wraps): + * + * landlock-run [--ro ]... [--rw ]... -- ... + * landlock-run --probe + * + * `--ro` grants read+execute beneath the path; `--rw` grants full filesystem + * access beneath the path. Everything else is denied (Landlock is an + * allow-list). `--probe` builds a maximal ruleset and reports whether the + * running kernel actually enforces it — the executor's functional probe. + * + * Fail-closed: if the ruleset cannot be created or is NOT enforced by the + * kernel, the launcher exits non-zero WITHOUT exec'ing the command. A partial + * (best-effort) enforcement on an older ABI is accepted and reported on + * stderr; the consumer's mode vocabulary keeps its file-effect promises + * honest per ABI level (surfaced as `full` vs `partial` by the entry + * package's probe). + * + * Plain C11 over the raw Landlock UAPI — no libraries beyond libc (musl, + * linked statically), so the whole audit surface is this file plus the + * kernel's stable syscall contract. Built natively per architecture by + * `scripts/build.ts` into the per-platform npm packages + * (`node-addon-landlock-run-linux-{x64,arm64}`); the argv grammar, + * exit codes, and report lines are pinned in `docs/cli-contract.md`. + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * The Landlock UAPI, defined locally instead of via : the + * kernel's user-space ABI is stable by contract, self-defining it keeps the + * build independent of the toolchain's header vintage, and the definitions + * double as the audit record of exactly which kernel surface this launcher + * touches. Layouts and values are verbatim from the kernel header (the + * path-beneath struct is packed there, so it must be packed here). + */ +struct landlock_ruleset_attr { + uint64_t handled_access_fs; +}; + +struct landlock_path_beneath_attr { + uint64_t allowed_access; + int32_t parent_fd; +} __attribute__((packed)); + +#define LANDLOCK_CREATE_RULESET_VERSION (1U << 0) +#define LANDLOCK_RULE_PATH_BENEATH 1 + +/* Filesystem access bits, grouped by the Landlock ABI that introduced them. */ +#define LL_FS_EXECUTE (UINT64_C(1) << 0) /* ABI 1 */ +#define LL_FS_WRITE_FILE (UINT64_C(1) << 1) +#define LL_FS_READ_FILE (UINT64_C(1) << 2) +#define LL_FS_READ_DIR (UINT64_C(1) << 3) +#define LL_FS_REMOVE_DIR (UINT64_C(1) << 4) +#define LL_FS_REMOVE_FILE (UINT64_C(1) << 5) +#define LL_FS_MAKE_CHAR (UINT64_C(1) << 6) +#define LL_FS_MAKE_DIR (UINT64_C(1) << 7) +#define LL_FS_MAKE_REG (UINT64_C(1) << 8) +#define LL_FS_MAKE_SOCK (UINT64_C(1) << 9) +#define LL_FS_MAKE_FIFO (UINT64_C(1) << 10) +#define LL_FS_MAKE_BLOCK (UINT64_C(1) << 11) +#define LL_FS_MAKE_SYM (UINT64_C(1) << 12) +#define LL_FS_REFER (UINT64_C(1) << 13) /* ABI 2 */ +#define LL_FS_TRUNCATE (UINT64_C(1) << 14) /* ABI 3 (ABI 4 added TCP bits only) */ +#define LL_FS_IOCTL_DEV (UINT64_C(1) << 15) /* ABI 5 */ + +#define LL_ABI1_MASK (LL_FS_REFER - 1) /* bits 0..12: every ABI-1 access, nothing newer */ + +/* + * Newest ABI this build knows; the negotiation below scales the actual + * ruleset down to what the running kernel supports (the best-effort compat + * stance of the previous Rust launcher, made explicit). + */ +#define MAX_ABI 5L + +/* + * Landlock has no libc wrappers; these are the raw syscalls. The numbers are + * identical on every architecture (the post-2011 unified table) — the + * fallbacks only matter to a libc older than the feature. + */ +#ifndef __NR_landlock_create_ruleset +#define __NR_landlock_create_ruleset 444 +#define __NR_landlock_add_rule 445 +#define __NR_landlock_restrict_self 446 +#endif + +/* + * Every fatal launcher error prints `landlock-run: ` to stderr + * and exits 125 — a code the wrapped command itself is unlikely to use, so + * the executor can tell launcher failures from command failures. + */ +#define EXIT_LAUNCHER_FAILURE 125 + +static const char NOT_ENFORCED_MESSAGE[] = + "landlock is not enforced by this kernel (ABI unsupported or disabled)"; + +/* Print one fatal `landlock-run: ...` line; returns the fatal exit code. */ +static int fail(const char *prefix, const char *detail) { + if (detail == NULL) { + fprintf(stderr, "landlock-run: %s\n", prefix); + } else { + fprintf(stderr, "landlock-run: %s: %s\n", prefix, detail); + } + return EXIT_LAUNCHER_FAILURE; +} + +static int fail_usage(const char *message, const char *detail) { + fprintf(stderr, "landlock-run: usage error: %s%s\n", message, detail == NULL ? "" : detail); + return EXIT_LAUNCHER_FAILURE; +} + +/* Parsed CLI: either a probe, or grants plus the command argv after `--`. */ +struct cli { + int probe; + const char **ro; + size_t ro_count; + const char **rw; + size_t rw_count; + char **command; /* NULL-terminated tail of main's argv */ +}; + +/* + * Hand-rolled argv parsing — four flags do not justify a parsing library, + * and the previous Rust launcher made the same call for the same reason. + * Returns 0 on success, else the process exit code (message already printed). + */ +static int parse(int argc, char **argv, struct cli *cli) { + /* argc bounds each grant list; the launcher execs or exits, so no free. */ + cli->ro = calloc(argc > 0 ? (size_t)argc : 1, sizeof *cli->ro); + cli->rw = calloc(argc > 0 ? (size_t)argc : 1, sizeof *cli->rw); + if (cli->ro == NULL || cli->rw == NULL) return fail("out of memory", NULL); + + int index = 1; + while (index < argc) { + const char *arg = argv[index]; + if (strcmp(arg, "--probe") == 0) { + cli->probe = 1; + index += 1; + } else if (strcmp(arg, "--ro") == 0 || strcmp(arg, "--rw") == 0) { + if (index + 1 >= argc) { + return fail_usage(arg, " requires a path"); + } + if (strcmp(arg, "--ro") == 0) { + cli->ro[cli->ro_count++] = argv[index + 1]; + } else { + cli->rw[cli->rw_count++] = argv[index + 1]; + } + index += 2; + } else if (strcmp(arg, "--") == 0) { + cli->command = &argv[index + 1]; + break; + } else { + return fail_usage("unknown argument: ", arg); + } + } + if (cli->probe) { + if (cli->ro_count > 0 || cli->rw_count > 0 || (cli->command != NULL && cli->command[0] != NULL)) { + return fail_usage("--probe takes no other arguments", NULL); + } + } else if (cli->command == NULL || cli->command[0] == NULL) { + return fail_usage("missing `-- ...` command", NULL); + } + return 0; +} + +/* The filesystem accesses the running kernel's ABI can govern. */ +static uint64_t fs_mask_for_abi(long abi) { + uint64_t mask = LL_ABI1_MASK; + if (abi >= 2) mask |= LL_FS_REFER; + if (abi >= 3) mask |= LL_FS_TRUNCATE; + if (abi >= 5) mask |= LL_FS_IOCTL_DEV; + return mask; +} + +/* Add one path-beneath rule; 0 on success, else the exit code. */ +static int add_rule(int ruleset_fd, const char *path, uint64_t access) { + int path_fd = open(path, O_PATH | O_CLOEXEC); + if (path_fd < 0) { + /* Fail closed on an unopenable grant root: silently narrowing the + * granted set would be safe, but running with a profile the caller did + * not get is not worth the ambiguity. */ + fprintf(stderr, "landlock-run: cannot open rule path: %s: %s\n", path, strerror(errno)); + return EXIT_LAUNCHER_FAILURE; + } + /* The kernel rejects directory-only accesses on a non-directory rule + * (EINVAL), so a file grant keeps only the file-compatible bits — how the + * `--rw /dev/null` grant works. Same clamp the Rust crate's + * path_beneath_rules helper applied. */ + struct stat st; + if (fstat(path_fd, &st) == 0 && !S_ISDIR(st.st_mode)) { + access &= LL_FS_EXECUTE | LL_FS_WRITE_FILE | LL_FS_READ_FILE | LL_FS_TRUNCATE | LL_FS_IOCTL_DEV; + } + struct landlock_path_beneath_attr attr = { .allowed_access = access, .parent_fd = path_fd }; + if (syscall(__NR_landlock_add_rule, ruleset_fd, LANDLOCK_RULE_PATH_BENEATH, &attr, 0) != 0) { + int saved = errno; + close(path_fd); + return fail("landlock ruleset error", strerror(saved)); + } + close(path_fd); + return 0; +} + +/* + * Install the ruleset on the current thread, negotiating the kernel's ABI + * down from MAX_ABI. `--ro` paths get the read side of the vocabulary (read + * file/dir + execute — the wrapped `bash` and everything it spawns must + * remain executable); `--rw` paths get every filesystem access the + * negotiated ABI can grant. Sets `no_new_privs` first (mandatory for an + * unprivileged restrict, and it neutralizes setuid/setgid escalation inside + * the sandbox). On success `*partial` reports whether the kernel governs + * only a subset of MAX_ABI's accesses. Returns 0, else the exit code. + */ +static int restrict_self(const struct cli *cli, int *partial) { + long abi = syscall(__NR_landlock_create_ruleset, NULL, 0, LANDLOCK_CREATE_RULESET_VERSION); + if (abi < 0) { + /* ENOSYS: kernel built without Landlock; EOPNOTSUPP: built but disabled. + * Either way: not enforceable — fail CLOSED, never exec unconfined. */ + return fail(NOT_ENFORCED_MESSAGE, NULL); + } + *partial = abi < MAX_ABI; + uint64_t handled = fs_mask_for_abi(abi < MAX_ABI ? abi : MAX_ABI); + + struct landlock_ruleset_attr attr = { .handled_access_fs = handled }; + int ruleset_fd = (int)syscall(__NR_landlock_create_ruleset, &attr, sizeof attr, 0); + if (ruleset_fd < 0) return fail("landlock ruleset error", strerror(errno)); + + const uint64_t read_side = LL_FS_EXECUTE | LL_FS_READ_FILE | LL_FS_READ_DIR; + for (size_t i = 0; i < cli->ro_count; i++) { + int code = add_rule(ruleset_fd, cli->ro[i], read_side & handled); + if (code != 0) return code; + } + for (size_t i = 0; i < cli->rw_count; i++) { + int code = add_rule(ruleset_fd, cli->rw[i], handled); + if (code != 0) return code; + } + + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) != 0) { + return fail("landlock ruleset error", strerror(errno)); + } + if (syscall(__NR_landlock_restrict_self, ruleset_fd, 0) != 0) { + return fail("landlock ruleset error", strerror(errno)); + } + close(ruleset_fd); + return 0; +} + +int main(int argc, char **argv) { + struct cli cli = { 0 }; + int code = parse(argc, argv, &cli); + if (code != 0) return code; + + if (cli.probe) { + /* The functional probe: build and enforce a maximal ruleset in THIS + * short-lived process (the probe run exits right after). `--version` + * style checks would miss a kernel that has the syscalls but refuses + * enforcement; actually restricting is the only honest signal. The one + * report line is part of the launcher CLI contract — the executor reads + * enforcement completeness from it. */ + static const char *probe_root = "/"; + struct cli probe = { .ro = &probe_root, .ro_count = 1 }; + int partial = 0; + code = restrict_self(&probe, &partial); + if (code != 0) return code; + printf("landlock: %s\n", partial ? "partially enforced (older ABI)" : "fully enforced"); + return 0; + } + + int partial = 0; + code = restrict_self(&cli, &partial); + if (code != 0) return code; + if (partial) { + /* Older ABI: some handled accesses are not governed (e.g. truncate + * before ABI 3). Still confined for everything the kernel supports — + * report, do not refuse. */ + fprintf(stderr, "landlock-run: partial enforcement (older Landlock ABI)\n"); + } + + execvp(cli.command[0], cli.command); + /* exec only returns on failure. */ + return fail("exec failed", strerror(errno)); +} diff --git a/native/landlock-run/packages/entry/tsconfig.json b/native/landlock-run/packages/entry/tsconfig.json new file mode 100644 index 0000000000..bb991d6ceb --- /dev/null +++ b/native/landlock-run/packages/entry/tsconfig.json @@ -0,0 +1,11 @@ +{ + "extends": "../../tsconfig.base.json", + "compilerOptions": { + "composite": true, + "declaration": true, + "outDir": "lib", + "rootDir": "src", + "tsBuildInfoFile": "lib/.tsbuildinfo" + }, + "include": ["src/**/*.ts"] +} diff --git a/native/landlock-run/packages/linux-arm64/LICENSE b/native/landlock-run/packages/linux-arm64/LICENSE new file mode 100644 index 0000000000..8187059c9a --- /dev/null +++ b/native/landlock-run/packages/linux-arm64/LICENSE @@ -0,0 +1,28 @@ +BSD 3-Clause License + +Copyright (c) 2026, node-addon-landlock-run contributors + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +1. Redistributions of source code must retain the above copyright notice, this + list of conditions and the following disclaimer. + +2. Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +3. Neither the name of the copyright holder nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE +FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR +SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER +CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, +OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/native/landlock-run/packages/linux-arm64/README.md b/native/landlock-run/packages/linux-arm64/README.md new file mode 100644 index 0000000000..1921c8f4b5 --- /dev/null +++ b/native/landlock-run/packages/linux-arm64/README.md @@ -0,0 +1,7 @@ +# node-addon-landlock-run-linux-arm64 + +Prebuilt `bin/landlock-run` Landlock launcher for linux-arm64 — a static musl binary compiled natively (no cross toolchain) from the C source shipped in [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run). npm's `os`/`cpu` fields select this package at install time; the entry package resolves it to a file path — it ships no JavaScript and is never imported. + +The binary is git-ignored and rides the npm tarball via the `files` list; the `prepack` gate refuses to pack when it is missing or has the wrong ELF architecture, and the release pipeline byte-pins the packed binary against the CI build it came from. Static musl linking means one binary for glibc and musl distros alike — hence no libc suffix in the name. + +Sibling: `node-addon-landlock-run-linux-x64`. diff --git a/native/landlock-run/packages/linux-arm64/package.json b/native/landlock-run/packages/linux-arm64/package.json new file mode 100644 index 0000000000..0067f77c8b --- /dev/null +++ b/native/landlock-run/packages/linux-arm64/package.json @@ -0,0 +1,26 @@ +{ + "name": "node-addon-landlock-run-linux-arm64", + "version": "0.0.1", + "description": "Prebuilt landlock-run Landlock launcher binary for linux-arm64 (static musl) — resolved as a file path by node-addon-landlock-run, never imported", + "os": [ + "linux" + ], + "cpu": [ + "arm64" + ], + "files": [ + "README.md", + "bin/", + "prebuilds.json" + ], + "scripts": { + "prepack": "node ../../scripts/verify-launcher-binary.mjs" + }, + "engines": { + "node": ">=20" + }, + "license": "BSD-3-Clause", + "publishConfig": { + "access": "public" + } +} diff --git a/native/landlock-run/packages/linux-arm64/prebuilds.json b/native/landlock-run/packages/linux-arm64/prebuilds.json new file mode 100644 index 0000000000..81e6b429f7 --- /dev/null +++ b/native/landlock-run/packages/linux-arm64/prebuilds.json @@ -0,0 +1,10 @@ +{ + "platform": "linux-arm64", + "binaries": [ + { + "tool": "landlock-run", + "kind": "static-musl", + "path": "bin/landlock-run" + } + ] +} diff --git a/native/landlock-run/packages/linux-x64/LICENSE b/native/landlock-run/packages/linux-x64/LICENSE new file mode 100644 index 0000000000..8187059c9a --- /dev/null +++ b/native/landlock-run/packages/linux-x64/LICENSE @@ -0,0 +1,28 @@ +BSD 3-Clause License + +Copyright (c) 2026, node-addon-landlock-run contributors + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +1. Redistributions of source code must retain the above copyright notice, this + list of conditions and the following disclaimer. + +2. Redistributions in binary form must reproduce the above copyright notice, + this list of conditions and the following disclaimer in the documentation + and/or other materials provided with the distribution. + +3. Neither the name of the copyright holder nor the names of its + contributors may be used to endorse or promote products derived from + this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" +AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE +DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE +FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR +SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER +CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, +OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/native/landlock-run/packages/linux-x64/README.md b/native/landlock-run/packages/linux-x64/README.md new file mode 100644 index 0000000000..ce741eb34c --- /dev/null +++ b/native/landlock-run/packages/linux-x64/README.md @@ -0,0 +1,7 @@ +# node-addon-landlock-run-linux-x64 + +Prebuilt `bin/landlock-run` Landlock launcher for linux-x64 — a static musl binary compiled natively (no cross toolchain) from the C source shipped in [`node-addon-landlock-run`](https://www.npmjs.com/package/node-addon-landlock-run). npm's `os`/`cpu` fields select this package at install time; the entry package resolves it to a file path — it ships no JavaScript and is never imported. + +The binary is git-ignored and rides the npm tarball via the `files` list; the `prepack` gate refuses to pack when it is missing or has the wrong ELF architecture, and the release pipeline byte-pins the packed binary against the CI build it came from. Static musl linking means one binary for glibc and musl distros alike — hence no libc suffix in the name. + +Sibling: `node-addon-landlock-run-linux-arm64`. diff --git a/native/landlock-run/packages/linux-x64/package.json b/native/landlock-run/packages/linux-x64/package.json new file mode 100644 index 0000000000..8ea60b636c --- /dev/null +++ b/native/landlock-run/packages/linux-x64/package.json @@ -0,0 +1,26 @@ +{ + "name": "node-addon-landlock-run-linux-x64", + "version": "0.0.1", + "description": "Prebuilt landlock-run Landlock launcher binary for linux-x64 (static musl) — resolved as a file path by node-addon-landlock-run, never imported", + "os": [ + "linux" + ], + "cpu": [ + "x64" + ], + "files": [ + "README.md", + "bin/", + "prebuilds.json" + ], + "scripts": { + "prepack": "node ../../scripts/verify-launcher-binary.mjs" + }, + "engines": { + "node": ">=20" + }, + "license": "BSD-3-Clause", + "publishConfig": { + "access": "public" + } +} diff --git a/native/landlock-run/packages/linux-x64/prebuilds.json b/native/landlock-run/packages/linux-x64/prebuilds.json new file mode 100644 index 0000000000..27b0de360c --- /dev/null +++ b/native/landlock-run/packages/linux-x64/prebuilds.json @@ -0,0 +1,10 @@ +{ + "platform": "linux-x64", + "binaries": [ + { + "tool": "landlock-run", + "kind": "static-musl", + "path": "bin/landlock-run" + } + ] +} diff --git a/native/landlock-run/pnpm-lock.yaml b/native/landlock-run/pnpm-lock.yaml new file mode 100644 index 0000000000..88b1b3df00 --- /dev/null +++ b/native/landlock-run/pnpm-lock.yaml @@ -0,0 +1,345 @@ +lockfileVersion: '9.0' + +settings: + autoInstallPeers: true + excludeLinksFromLockfile: false + +importers: + + .: + devDependencies: + '@types/node': + specifier: ^24.10.0 + version: 24.13.2 + node-addon-landlock-run: + specifier: workspace:* + version: link:packages/entry + tsx: + specifier: ^4.20.6 + version: 4.23.0 + typescript: + specifier: ^5.9.3 + version: 5.9.3 + + packages/entry: + optionalDependencies: + node-addon-landlock-run-linux-arm64: + specifier: workspace:* + version: link:../linux-arm64 + node-addon-landlock-run-linux-x64: + specifier: workspace:* + version: link:../linux-x64 + + packages/linux-arm64: {} + + packages/linux-x64: {} + +packages: + + '@esbuild/aix-ppc64@0.28.1': + resolution: {integrity: sha512-Svl7tq8k/08+p6CXPpRjQ1fKX+1odH/BQbb48fV6fj3CWHhsoIOoY87w1oHXm0qEpkIK3ZfVgp0hed3XBXzXMQ==} + engines: {node: '>=18'} + cpu: [ppc64] + os: [aix] + + '@esbuild/android-arm64@0.28.1': + resolution: {integrity: sha512-34EGEbCIAgosYz6goLcopX6Mo7NyGv9tfwEM2/7Ce2VcVRk568iSvniGWcUXIy7wEDR1wzolcxcriFVrWYcwBg==} + engines: {node: '>=18'} + cpu: [arm64] + os: [android] + + '@esbuild/android-arm@0.28.1': + resolution: {integrity: sha512-0k2F129Xdio1TdJfzJ8sy1Q47vUD2NnwdhiAf7drUN1EBTfPf4hsFCtmMgu/6m8JSzsBrlmVjudMBQqOfG8usQ==} + engines: {node: '>=18'} + cpu: [arm] + os: [android] + + '@esbuild/android-x64@0.28.1': + resolution: {integrity: sha512-dbwY7ltSMDWsRatcRpCnES4F+im88OCUgGZjy52shC7GqHRE/cYlxNbB4Z4UpJswpcc4Qxd2oE/ufM0p61IKng==} + engines: {node: '>=18'} + cpu: [x64] + os: [android] + + '@esbuild/darwin-arm64@0.28.1': + resolution: {integrity: sha512-TZbWkQY7kvTAXbXUT7uVACR5cMHsDiSz9z7ZKAX/RTq/WJEk3QyRr0wZpNhBDX+/0CtdqUIJlOiodQcta6tY3Q==} + engines: {node: '>=18'} + cpu: [arm64] + os: [darwin] + + '@esbuild/darwin-x64@0.28.1': + resolution: {integrity: sha512-zfdzgK9ACBNZLI/CyHTOx81SyNbM6YXn7rxSgX97VjyiPl9W1i4Ka4fgKECEoFCKGpvBj5qArWIGgQjOwkgskQ==} + engines: {node: '>=18'} + cpu: [x64] + os: [darwin] + + '@esbuild/freebsd-arm64@0.28.1': + resolution: {integrity: sha512-wG2EA8ENdEI0qhkSZMjfqrdY+ziCYCPMmtZjjIwOmXFjmyzEHn+UUxk5of+SYsjtfs3VpnlC7QLzSI5hY/rOAw==} + engines: {node: '>=18'} + cpu: [arm64] + os: [freebsd] + + '@esbuild/freebsd-x64@0.28.1': + resolution: {integrity: sha512-i7dZ9vQgnvSCzi/rYCXNgtF/U+eKZNJBzu3eTQbRgHnM7tNSizLOkRFAl3qzVc/Op/u5YkHHa4pf/3DOYHthLQ==} + engines: {node: '>=18'} + cpu: [x64] + os: [freebsd] + + '@esbuild/linux-arm64@0.28.1': + resolution: {integrity: sha512-yHs+0uc8+nvEAfAfxrWQKK5peSNzBc4PegcMO0EJ2hT71uA7vB8Ihg2e77R2P7SG5uYjPbHlLLmve4LLLRCf0g==} + engines: {node: '>=18'} + cpu: [arm64] + os: [linux] + + '@esbuild/linux-arm@0.28.1': + resolution: {integrity: sha512-qVXBOHQS+d5Y722GwJzJUtOLlX7km3CraOaGormF1pDtPd2C/l1SHRPgjLunLGe51Sh5YYWKMFDyV4SxgMQYTQ==} + engines: {node: '>=18'} + cpu: [arm] + os: [linux] + + '@esbuild/linux-ia32@0.28.1': + resolution: {integrity: sha512-d1z4ZuP0ajrfz/FhGT4vv278rX8KnPPJx8i5+AtK7TYbx9Le9F1hyzurZpkEyjkGa9dUGhQow4C1NmeGvqxN2w==} + engines: {node: '>=18'} + cpu: [ia32] + os: [linux] + + '@esbuild/linux-loong64@0.28.1': + resolution: {integrity: sha512-M5sRjUVZrkm1OAPR3dlOYzNmN+loZKGVi1VUQGrwuqLcbR6qeAz+famMhjASeH3YVKvZz+zT1jlh/keC3Rj/lg==} + engines: {node: '>=18'} + cpu: [loong64] + os: [linux] + + '@esbuild/linux-mips64el@0.28.1': + resolution: {integrity: sha512-mRObBZeHh2OxcBFPWE/FjylkRgZdYuiTR3vaTozquCGOH14iP9oN4x4Ge81CoIDYQrXmIxpFumJBu5MtZpnQJQ==} + engines: {node: '>=18'} + cpu: [mips64el] + os: [linux] + + '@esbuild/linux-ppc64@0.28.1': + resolution: {integrity: sha512-slScBsMAb3GFDcdrCgLwZtPYRoH2H/youv10QiZyRjmsP48fznoveWytSgCI/R0ZcUgpc0ZhIUEx6LHts8yrfQ==} + engines: {node: '>=18'} + cpu: [ppc64] + os: [linux] + + '@esbuild/linux-riscv64@0.28.1': + resolution: {integrity: sha512-kw0owk1o0GFETUJyW0jc0G4Yzs0BHZn0JDZ8JRT088vjJYX777BAs1fDGxAC+q831qOs2DTC96mNsG2opdfyyQ==} + engines: {node: '>=18'} + cpu: [riscv64] + os: [linux] + + '@esbuild/linux-s390x@0.28.1': + resolution: {integrity: sha512-/lAIjX8aYFRByhh6L5rYtPEDRqa9de/4V/juOXcta5frjvzXO4/sqEtyytse0g3zZFuWu5cDN0MkLz2qRDD2Ag==} + engines: {node: '>=18'} + cpu: [s390x] + os: [linux] + + '@esbuild/linux-x64@0.28.1': + resolution: {integrity: sha512-u/anNYF2mmVOEDwLtnQ1wOr3EZ9sTNGLWrsYGYwHWzGA3Si84IOkHXlbWTD1NB+9/1lcnweYKO54uhxZydNzfA==} + engines: {node: '>=18'} + cpu: [x64] + os: [linux] + + '@esbuild/netbsd-arm64@0.28.1': + resolution: {integrity: sha512-oks0DYbLwWMmaakTsCb+zL4E+aHRVLom9IJZOAthMQEPiQmydXHkziYEsGYRx0uNV/IjEKGAV941JzH02pflqw==} + engines: {node: '>=18'} + cpu: [arm64] + os: [netbsd] + + '@esbuild/netbsd-x64@0.28.1': + resolution: {integrity: sha512-aeL6lAnN89Hz43Mlh1G8ARasbuoYvSITDEx0tHh5b7jJnHcssqgjy9Yx430GDpmCa6OyrKoS0aNRjKundRizGg==} + engines: {node: '>=18'} + cpu: [x64] + os: [netbsd] + + '@esbuild/openbsd-arm64@0.28.1': + resolution: {integrity: sha512-MEFJe5C3R8pwXdZ5Y21oo6m7ePiS0d9pWucn99O/wvyJZChoIQKrQDxKrGeW8F5+T0okTHesAmDeiHDTIq0V/Q==} + engines: {node: '>=18'} + cpu: [arm64] + os: [openbsd] + + '@esbuild/openbsd-x64@0.28.1': + resolution: {integrity: sha512-i/ZLIOafE0Z8cI/XANJAixoJL/uRAoS2xOA3rb0xN+KK0K177cMAsQYkzHtBrtMXAKuAc7HGgcWiZ/sRC1Nxgw==} + engines: {node: '>=18'} + cpu: [x64] + os: [openbsd] + + '@esbuild/openharmony-arm64@0.28.1': + resolution: {integrity: sha512-ge+Z7EXFNt2BO1oAMsVpiQ8EwndV9i1xXerAeTIK7AtPs3bKFXQM7nlRxDSIUIMeueR1CNXxqztLzdNeReKBJg==} + engines: {node: '>=18'} + cpu: [arm64] + os: [openharmony] + + '@esbuild/sunos-x64@0.28.1': + resolution: {integrity: sha512-BEjgtECkL3vY+SaSQ6nzVfiALUeFxpawyp8Jmf5PtYhf1Ug40N1h/hxlhts+f1FvSvarEigdxS3BlSMI2PJLcQ==} + engines: {node: '>=18'} + cpu: [x64] + os: [sunos] + + '@esbuild/win32-arm64@0.28.1': + resolution: {integrity: sha512-lCv9eK/H6ZJWbE7bh2nw54CZ9M2nupBxJcTsdk/QQnWkdSjKGuxmmH8/GWrlT1eMmZfn4dGcCjRte397WqfQXA==} + engines: {node: '>=18'} + cpu: [arm64] + os: [win32] + + '@esbuild/win32-ia32@0.28.1': + resolution: {integrity: sha512-zvb/mB2bSCoJOpoCBgYKKpX6YM6mJBlBUVUtVj41DlZJVEB6/0CKlRYxP5wWl1C1ILiCoAU5wZZ4q1P3qeS6Eg==} + engines: {node: '>=18'} + cpu: [ia32] + os: [win32] + + '@esbuild/win32-x64@0.28.1': + resolution: {integrity: sha512-bm4Mowrv+GXMlpWX++EcXw/iLyd1o3+bJkC2DkWXYVvgZCqD/bSj9ctZeAMC3cIxgjRVR2Dufaiu4YPxr5gW1A==} + engines: {node: '>=18'} + cpu: [x64] + os: [win32] + + '@types/node@24.13.2': + resolution: {integrity: sha512-fRa09kZTgu8o71KFcDjUFuc7F+dEbZYZmkI0mg5YBTRs0yMKjYHsq/c0urDKeDb+D5qVgXOdFcuu+DZPKOITwA==} + + esbuild@0.28.1: + resolution: {integrity: sha512-HrJrvZv5ayxBzPfwphOoNzkzOIIlifzk0KJrGK2c8R4+LKpMtpYLQeUdjnwjWv/LZlkH2laZk+4w78pi99D4Vw==} + engines: {node: '>=18'} + hasBin: true + + fsevents@2.3.3: + resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==} + engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0} + os: [darwin] + + tsx@4.23.0: + resolution: {integrity: sha512-eUdUIaCr963q2h5u3+QwvYp0+eqPvn+egeqZUm0hwERCqqx1E3kK5ehbGCvqSE5MQAULr67ww0cA3jKc3YkM1w==} + engines: {node: '>=18.0.0'} + hasBin: true + + typescript@5.9.3: + resolution: {integrity: sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==} + engines: {node: '>=14.17'} + hasBin: true + + undici-types@7.18.2: + resolution: {integrity: sha512-AsuCzffGHJybSaRrmr5eHr81mwJU3kjw6M+uprWvCXiNeN9SOGwQ3Jn8jb8m3Z6izVgknn1R0FTCEAP2QrLY/w==} + +snapshots: + + '@esbuild/aix-ppc64@0.28.1': + optional: true + + '@esbuild/android-arm64@0.28.1': + optional: true + + '@esbuild/android-arm@0.28.1': + optional: true + + '@esbuild/android-x64@0.28.1': + optional: true + + '@esbuild/darwin-arm64@0.28.1': + optional: true + + '@esbuild/darwin-x64@0.28.1': + optional: true + + '@esbuild/freebsd-arm64@0.28.1': + optional: true + + '@esbuild/freebsd-x64@0.28.1': + optional: true + + '@esbuild/linux-arm64@0.28.1': + optional: true + + '@esbuild/linux-arm@0.28.1': + optional: true + + '@esbuild/linux-ia32@0.28.1': + optional: true + + '@esbuild/linux-loong64@0.28.1': + optional: true + + '@esbuild/linux-mips64el@0.28.1': + optional: true + + '@esbuild/linux-ppc64@0.28.1': + optional: true + + '@esbuild/linux-riscv64@0.28.1': + optional: true + + '@esbuild/linux-s390x@0.28.1': + optional: true + + '@esbuild/linux-x64@0.28.1': + optional: true + + '@esbuild/netbsd-arm64@0.28.1': + optional: true + + '@esbuild/netbsd-x64@0.28.1': + optional: true + + '@esbuild/openbsd-arm64@0.28.1': + optional: true + + '@esbuild/openbsd-x64@0.28.1': + optional: true + + '@esbuild/openharmony-arm64@0.28.1': + optional: true + + '@esbuild/sunos-x64@0.28.1': + optional: true + + '@esbuild/win32-arm64@0.28.1': + optional: true + + '@esbuild/win32-ia32@0.28.1': + optional: true + + '@esbuild/win32-x64@0.28.1': + optional: true + + '@types/node@24.13.2': + dependencies: + undici-types: 7.18.2 + + esbuild@0.28.1: + optionalDependencies: + '@esbuild/aix-ppc64': 0.28.1 + '@esbuild/android-arm': 0.28.1 + '@esbuild/android-arm64': 0.28.1 + '@esbuild/android-x64': 0.28.1 + '@esbuild/darwin-arm64': 0.28.1 + '@esbuild/darwin-x64': 0.28.1 + '@esbuild/freebsd-arm64': 0.28.1 + '@esbuild/freebsd-x64': 0.28.1 + '@esbuild/linux-arm': 0.28.1 + '@esbuild/linux-arm64': 0.28.1 + '@esbuild/linux-ia32': 0.28.1 + '@esbuild/linux-loong64': 0.28.1 + '@esbuild/linux-mips64el': 0.28.1 + '@esbuild/linux-ppc64': 0.28.1 + '@esbuild/linux-riscv64': 0.28.1 + '@esbuild/linux-s390x': 0.28.1 + '@esbuild/linux-x64': 0.28.1 + '@esbuild/netbsd-arm64': 0.28.1 + '@esbuild/netbsd-x64': 0.28.1 + '@esbuild/openbsd-arm64': 0.28.1 + '@esbuild/openbsd-x64': 0.28.1 + '@esbuild/openharmony-arm64': 0.28.1 + '@esbuild/sunos-x64': 0.28.1 + '@esbuild/win32-arm64': 0.28.1 + '@esbuild/win32-ia32': 0.28.1 + '@esbuild/win32-x64': 0.28.1 + + fsevents@2.3.3: + optional: true + + tsx@4.23.0: + dependencies: + esbuild: 0.28.1 + optionalDependencies: + fsevents: 2.3.3 + + typescript@5.9.3: {} + + undici-types@7.18.2: {} diff --git a/native/landlock-run/pnpm-workspace.yaml b/native/landlock-run/pnpm-workspace.yaml new file mode 100644 index 0000000000..22299bfea0 --- /dev/null +++ b/native/landlock-run/pnpm-workspace.yaml @@ -0,0 +1,8 @@ +packages: + - packages/* + +# pnpm 10+ blocks any dependency shipping an install/build script until it is +# explicitly reviewed here. Deny by default; esbuild (tsx's bundled native +# binary) genuinely needs its script. +allowBuilds: + esbuild: true diff --git a/native/landlock-run/scripts/assemble-prebuilds.mjs b/native/landlock-run/scripts/assemble-prebuilds.mjs new file mode 100644 index 0000000000..4dcdb23bed --- /dev/null +++ b/native/landlock-run/scripts/assemble-prebuilds.mjs @@ -0,0 +1,51 @@ +#!/usr/bin/env node +/** + * Assemble downloaded release artifacts into the platform packages and + * verify the result. The Release workflow's build legs upload one + * `prebuild-` artifact per platform package (its `bin/` payload); + * this script copies each into `packages//bin/` and then checks + * every declared binary for presence and ELF architecture. + * + * Usage: `node scripts/assemble-prebuilds.mjs `. + */ + +import fs from 'node:fs'; +import path from 'node:path'; +import { platformDirs, root, verifyPlatformBinaries } from './repo.mjs'; + +const artifactRoot = path.resolve(process.argv[2] || '.release/prebuild-artifacts'); + +if (!fs.existsSync(artifactRoot)) { + throw new Error(`prebuild artifact directory does not exist: ${artifactRoot}`); +} + +const platforms = platformDirs().map((dir) => path.basename(dir)); + +for (const name of platforms) { + const binDir = path.join(root, 'packages', name, 'bin'); + fs.rmSync(binDir, { recursive: true, force: true }); + fs.mkdirSync(binDir, { recursive: true }); +} + +for (const artifactName of fs.readdirSync(artifactRoot)) { + const artifactDir = path.join(artifactRoot, artifactName); + if (!fs.statSync(artifactDir).isDirectory()) continue; + + const name = platforms.find((candidate) => artifactName === `prebuild-${candidate}`); + if (!name) { + throw new Error(`cannot map artifact to a platform package: ${artifactName}`); + } + + for (const file of fs.readdirSync(artifactDir)) { + const source = path.join(artifactDir, file); + const destination = path.join(root, 'packages', name, 'bin', file); + fs.copyFileSync(source, destination); + fs.chmodSync(destination, 0o755); + console.log(`Copied ${path.relative(root, source)} -> ${path.relative(root, destination)}`); + } +} + +for (const dir of platformDirs()) { + const { name, count } = verifyPlatformBinaries(path.join(root, dir)); + console.log(`Verified ${name}: ${count} binaries`); +} diff --git a/native/landlock-run/scripts/build.ts b/native/landlock-run/scripts/build.ts new file mode 100644 index 0000000000..5866cc0dc4 --- /dev/null +++ b/native/landlock-run/scripts/build.ts @@ -0,0 +1,86 @@ +/** + * Build every native tool this host can build, into its per-platform + * package. + * + * Targets are derived from the checked-in matrix: each + * `packages//prebuilds.json` whose `platform` matches this host names + * the binaries to produce; the TOOLS table below maps each `tool` to its C + * source. Builds are NATIVE-ONLY — each Linux architecture compiles its own + * binary with the distro's `musl-gcc` (static musl: runs on glibc and musl + * distros alike, no loader or libc expectations on the consumer host), and + * CI's per-arch runners are the builders of record. No cross toolchain + * exists here on purpose: native runners replace it, and the audit surface + * is the reviewed C source plus CI provenance. + * + * Binaries land in `packages//bin/` — git-ignored (root + * `.gitignore`), packed into the platform package's npm tarball behind its + * `prepack` gate (`scripts/verify-launcher-binary.mjs`). + * + * Run: `pnpm run build:native` (Linux with musl-gcc on PATH: + * `apt-get install musl-tools`). Non-Linux hosts fail fast — no platform + * package exists for them to build. + */ +import { spawnSync } from 'node:child_process' +import { existsSync, mkdirSync, readdirSync, readFileSync } from 'node:fs' +import { basename, dirname, join, resolve } from 'node:path' + +/** Each native tool's C source, keyed by the `tool` field in prebuilds.json. */ +const TOOLS: Record = { + 'landlock-run': { source: 'packages/entry/src/main.c' }, +} + +const repoRoot = resolve(import.meta.dirname, '..') + +if (process.platform !== 'linux') { + console.error(`build: native tools are built natively per Linux architecture (no cross toolchain) — nothing to build on ${process.platform}. CI's per-arch runners build and rehearse every platform package.`) + process.exit(1) +} +const hostPlatform = `linux-${process.arch}` + +/** This host's platform packages, from the checked-in matrix. */ +const targets: { packageDir: string; tool: string; binaryPath: string; kind: string }[] = [] +const packagesRoot = join(repoRoot, 'packages') +for (const name of readdirSync(packagesRoot).sort()) { + const prebuildsFile = join(packagesRoot, name, 'prebuilds.json') + if (!existsSync(prebuildsFile)) continue + const prebuilds = JSON.parse(readFileSync(prebuildsFile, 'utf8')) as { + platform: string + binaries: { tool: string; kind: string; path: string }[] + } + if (prebuilds.platform !== hostPlatform) continue + for (const binary of prebuilds.binaries) { + targets.push({ packageDir: join(packagesRoot, name), tool: binary.tool, binaryPath: binary.path, kind: binary.kind }) + } +} +if (targets.length === 0) { + console.error(`build: no platform package declares binaries for ${hostPlatform} — supported platforms are the packages/*/prebuilds.json "platform" values.`) + process.exit(1) +} + +for (const target of targets) { + const tool = TOOLS[target.tool] + if (tool === undefined) { + console.error(`build: prebuilds.json names unknown tool "${target.tool}" — add it to the TOOLS table in scripts/build.ts.`) + process.exit(1) + } + if (target.kind !== 'static-musl') { + console.error(`build: unknown binary kind "${target.kind}" — the only toolchain here is static musl.`) + process.exit(1) + } + const binary = join(target.packageDir, target.binaryPath) + mkdirSync(dirname(binary), { recursive: true }) + + // -static against musl: self-contained, no loader/libc expectations on the + // consumer host. -Werror is safe to keep hard: CI pins the builder images, + // and a new warning on a toolchain bump deserves a look, not a pass. + const result = spawnSync('musl-gcc', [ + '-std=c11', '-Os', '-Wall', '-Wextra', '-Werror', '-static', '-s', + '-o', binary, join(repoRoot, tool.source), + ], { stdio: ['ignore', 'inherit', 'inherit'] }) + if (result.error !== undefined || result.status !== 0) { + console.error('build: musl-gcc failed' + + (result.error ? ` (${result.error.message} — is musl-tools installed?)` : '')) + process.exit(1) + } + console.log(`build: built ${basename(target.packageDir)}/${target.binaryPath}`) +} diff --git a/native/landlock-run/scripts/bump-release.mjs b/native/landlock-run/scripts/bump-release.mjs new file mode 100644 index 0000000000..29a7777379 --- /dev/null +++ b/native/landlock-run/scripts/bump-release.mjs @@ -0,0 +1,90 @@ +#!/usr/bin/env node +/** + * Bump every package (workspace root + packages/*) to one version, refresh + * the lockfile, and verify. Usage: `pnpm release:bump `. + */ + +import fs from 'node:fs'; +import path from 'node:path'; +import { spawnSync } from 'node:child_process'; +import { packageDirs, readJson, root } from './repo.mjs'; + +const bump = process.argv[2]; +const releaseTypes = new Set(['major', 'minor', 'patch']); + +function writeJson(file, value) { + fs.writeFileSync(file, `${JSON.stringify(value, null, 2)}\n`); +} + +function run(command, args) { + const result = spawnSync(command, args, { + cwd: root, + stdio: 'inherit', + env: { ...process.env, CI: 'true' }, + }); + if (result.error) throw result.error; + if (result.status !== 0) { + process.exit(result.status ?? 1); + } +} + +function packageFiles() { + return ['package.json', ...packageDirs().map((dir) => path.join(dir, 'package.json'))]; +} + +function parseVersion(version) { + const match = /^(0|[1-9]\d*)\.(0|[1-9]\d*)\.(0|[1-9]\d*)$/.exec(version); + if (!match) { + throw new Error(`increment types need a plain x.y.z current version (current: ${version}) — pass an explicit target version instead`); + } + return match.slice(1).map((part) => Number(part)); +} + +/** Explicit target versions accept full semver, prereleases included (test publishes). */ +const EXPLICIT_VERSION = /^\d+\.\d+\.\d+(-[0-9A-Za-z-]+(\.[0-9A-Za-z-]+)*)?$/; + +function nextVersion(current, release) { + if (EXPLICIT_VERSION.test(release)) return release; + + if (!releaseTypes.has(release)) { + throw new Error('Usage: pnpm release:bump '); + } + + const [major, minor, patch] = parseVersion(current); + if (release === 'major') return `${major + 1}.0.0`; + if (release === 'minor') return `${major}.${minor + 1}.0`; + return `${major}.${minor}.${patch + 1}`; +} + +function currentPublishedVersion(files) { + const versions = new Set( + files + .filter((file) => file.startsWith('packages/')) + .map((file) => readJson(path.join(root, file)).version), + ); + if (versions.size !== 1) { + throw new Error(`published package versions differ: ${[...versions].join(', ')}`); + } + return [...versions][0]; +} + +if (!bump) { + console.error('Usage: pnpm release:bump '); + process.exit(1); +} + +const files = packageFiles(); +const targetVersion = nextVersion(currentPublishedVersion(files), bump); + +for (const file of files) { + const fullPath = path.join(root, file); + const json = readJson(fullPath); + json.version = targetVersion; + writeJson(fullPath, json); + console.log(`${file}: ${targetVersion}`); +} + +run('pnpm', ['install', '--ignore-scripts', '--lockfile-only']); +run('node', ['./scripts/verify-release.mjs']); + +console.log(`Release version bumped to ${targetVersion}`); diff --git a/native/landlock-run/scripts/commit-release.mjs b/native/landlock-run/scripts/commit-release.mjs new file mode 100644 index 0000000000..b7bf3e513b --- /dev/null +++ b/native/landlock-run/scripts/commit-release.mjs @@ -0,0 +1,42 @@ +#!/usr/bin/env node +/** + * Bump, stage, and commit a release in one command: + * `pnpm release:commit `. The tag stays manual — + * create it from the merged release commit. + */ + +import path from 'node:path'; +import { spawnSync } from 'node:child_process'; +import { packageDirs, readJson, root } from './repo.mjs'; + +const bump = process.argv[2]; + +function run(command, args) { + const result = spawnSync(command, args, { + cwd: root, + stdio: 'inherit', + env: { ...process.env, CI: 'true' }, + }); + if (result.error) throw result.error; + if (result.status !== 0) { + process.exit(result.status ?? 1); + } +} + +if (!bump) { + console.error('Usage: pnpm release:commit '); + process.exit(1); +} + +run('node', ['./scripts/bump-release.mjs', bump]); + +const version = readJson(path.join(root, packageDirs()[0], 'package.json')).version; +run('git', [ + 'add', + 'package.json', + 'packages/*/package.json', + 'pnpm-lock.yaml', +]); +run('git', ['commit', '-m', `release: ${version}`]); + +console.log(`Committed release ${version}. Create the tag manually: git tag v${version}`); diff --git a/native/landlock-run/scripts/github-matrix.mjs b/native/landlock-run/scripts/github-matrix.mjs new file mode 100644 index 0000000000..9566b89c8a --- /dev/null +++ b/native/landlock-run/scripts/github-matrix.mjs @@ -0,0 +1,66 @@ +#!/usr/bin/env node +/** + * Derive the GitHub Actions matrices from the checked-in package matrix + * (`packages//prebuilds.json`). Single source: adding a platform + * package extends CI and Release without editing a workflow. + * + * node scripts/github-matrix.mjs ci → one leg per distinct platform + * node scripts/github-matrix.mjs release-prebuild → one leg per platform package + */ + +import path from 'node:path'; +import { platformDirs, readJson, root } from './repo.mjs'; + +/** GitHub runner per prebuilds.json `platform` value — native builders only, no cross toolchain. */ +const RUNNERS = { + 'linux-x64': 'ubuntu-24.04', + 'linux-arm64': 'ubuntu-24.04-arm', +}; + +function runnerFor(platform) { + const runner = RUNNERS[platform]; + if (!runner) { + throw new Error(`missing GitHub runner for platform: ${platform}`); + } + return runner; +} + +function platformManifests() { + return platformDirs().map((dir) => ({ + dir, + name: path.basename(dir), + prebuilds: readJson(path.join(root, dir, 'prebuilds.json')), + })); +} + +function ciMatrix() { + const platforms = [...new Set(platformManifests().map(({ prebuilds }) => prebuilds.platform))].sort(); + return { + include: platforms.map((platform) => ({ platform, runner: runnerFor(platform) })), + }; +} + +function releasePrebuildMatrix() { + return { + include: platformManifests().map(({ dir, name, prebuilds }) => ({ + platform: prebuilds.platform, + package: name, + dir, + runner: runnerFor(prebuilds.platform), + artifact: `prebuild-${name}`, + })), + }; +} + +const target = process.argv[2]; +const matrices = { + ci: ciMatrix, + 'release-prebuild': releasePrebuildMatrix, +}; + +if (!target || !matrices[target]) { + console.error(`Usage: node scripts/github-matrix.mjs <${Object.keys(matrices).join('|')}>`); + process.exit(1); +} + +process.stdout.write(JSON.stringify(matrices[target]())); diff --git a/native/landlock-run/scripts/pack-release.mjs b/native/landlock-run/scripts/pack-release.mjs new file mode 100644 index 0000000000..fbec0b610b --- /dev/null +++ b/native/landlock-run/scripts/pack-release.mjs @@ -0,0 +1,76 @@ +#!/usr/bin/env node +/** + * Pack every published package into release tarballs, in publish order + * (platform packages first, then the entries that optionally depend on + * them), and write `publish-order.txt` next to them. `pnpm pack` produces + * the EXACT bytes `pnpm publish` would upload and runs each package's + * `prepack` gate, so a missing binary or unbuilt `lib/` refuses here. + * + * Usage: `node scripts/pack-release.mjs [dest] [--current-platform-only]`. + * The flag packs only THIS host's platform package plus the entries — for + * per-architecture CI legs, where the other architecture's binary does not + * exist (the exact refusal its prepack gate exists for). + */ + +import fs from 'node:fs'; +import path from 'node:path'; +import { spawnSync } from 'node:child_process'; +import { entryDirs, platformDirs, readJson, root } from './repo.mjs'; + +const args = process.argv.slice(2); +const currentPlatformOnly = args.includes('--current-platform-only'); +const destination = path.resolve(args.find((arg) => !arg.startsWith('--')) || path.join(root, 'dist', 'npm')); + +function hostPlatformDirs() { + const hostPlatform = `${process.platform}-${process.arch}`; + return platformDirs().filter((dir) => readJson(path.join(root, dir, 'prebuilds.json')).platform === hostPlatform); +} + +function run(command, args) { + const result = spawnSync(command, args, { + cwd: root, + stdio: 'inherit', + }); + if (result.error) throw result.error; + if (result.status !== 0) { + process.exit(result.status ?? 1); + } +} + +function tarballName(manifest) { + if (manifest.name.startsWith('@')) { + return `${manifest.name.slice(1).replace('/', '-')}-${manifest.version}.tgz`; + } + return `${manifest.name}-${manifest.version}.tgz`; +} + +fs.rmSync(destination, { recursive: true, force: true }); +fs.mkdirSync(destination, { recursive: true }); + +const dirs = [...(currentPlatformOnly ? hostPlatformDirs() : platformDirs()), ...entryDirs()]; +const platformSet = new Set(platformDirs()); +const publishOrder = []; +for (const dir of dirs) { + const manifest = readJson(path.join(root, dir, 'package.json')); + // Platform packages are packed with npm: pnpm pack (observed on 11.7.0) + // normalizes file modes and STRIPS the executable bit, which ships a + // launcher no consumer can spawn; npm pack preserves it. Platform packages + // have no dependencies by construction, so they need none of pnpm's + // workspace-protocol conversion — the entry packages do, and carry no + // executables, so they keep pnpm pack. + if (platformSet.has(dir)) { + run('npm', ['pack', `./${dir}`, '--pack-destination', destination]); + } else { + run('pnpm', ['--dir', dir, 'pack', '--pack-destination', destination]); + } + + const tarball = tarballName(manifest); + const tarballPath = path.join(destination, tarball); + if (!fs.existsSync(tarballPath)) { + throw new Error(`expected pack output not found: ${tarballPath}`); + } + publishOrder.push(tarball); +} + +fs.writeFileSync(path.join(destination, 'publish-order.txt'), `${publishOrder.join('\n')}\n`); +console.log(`Packed ${publishOrder.length} packages into ${path.relative(root, destination)}`); diff --git a/native/landlock-run/scripts/repo.mjs b/native/landlock-run/scripts/repo.mjs new file mode 100644 index 0000000000..8032d3da37 --- /dev/null +++ b/native/landlock-run/scripts/repo.mjs @@ -0,0 +1,88 @@ +#!/usr/bin/env node +/** + * Shared helpers for the repo scripts: package discovery, the checked-in + * prebuild matrix, and binary verification. The package matrix is explicit + * metadata — `packages//prebuilds.json` marks a platform package and + * declares its binaries; everything else under `packages/` is an entry + * package. Scripts derive from these files and never guess. + */ + +import fs from 'node:fs'; +import path from 'node:path'; +import { fileURLToPath } from 'node:url'; + +export const root = fileURLToPath(new URL('..', import.meta.url)); +export const packagesRoot = path.join(root, 'packages'); + +/** ELF `e_machine` (offset 18, little-endian) per platform-package `cpu` value. */ +export const E_MACHINE = { x64: 62, arm64: 183 }; + +export function readJson(file) { + return JSON.parse(fs.readFileSync(file, 'utf8')); +} + +/** Platform packages: every `packages/` carrying a `prebuilds.json`. */ +export function platformDirs() { + return fs.readdirSync(packagesRoot) + .filter((name) => fs.existsSync(path.join(packagesRoot, name, 'prebuilds.json'))) + .sort() + .map((name) => path.join('packages', name)); +} + +/** Entry packages: every other `packages/` with a `package.json`. */ +export function entryDirs() { + return fs.readdirSync(packagesRoot) + .filter((name) => !fs.existsSync(path.join(packagesRoot, name, 'prebuilds.json'))) + .filter((name) => fs.existsSync(path.join(packagesRoot, name, 'package.json'))) + .sort() + .map((name) => path.join('packages', name)); +} + +/** All published packages in publish order: platform packages before the entries that optionally depend on them. */ +export function packageDirs() { + return [...platformDirs(), ...entryDirs()]; +} + +/** + * Verify one platform package's binaries against its `prebuilds.json`: + * every declared binary exists, nothing undeclared sits in `bin/`, and each + * file's ELF `e_machine` matches the package's declared `cpu`. Throws with + * a remediation message on the first mismatch. + */ +export function verifyPlatformBinaries(packageDir) { + const manifest = readJson(path.join(packageDir, 'package.json')); + const prebuilds = readJson(path.join(packageDir, 'prebuilds.json')); + const cpu = manifest.cpu?.[0]; + if (cpu === undefined || !(cpu in E_MACHINE)) { + throw new Error(`${manifest.name}: unsupported or missing "cpu" in package.json (expected one of: ${Object.keys(E_MACHINE).join(', ')})`); + } + + for (const binary of prebuilds.binaries) { + const file = path.join(packageDir, binary.path); + if (!fs.existsSync(file)) { + throw new Error(`${manifest.name}: missing ${binary.path} — run \`pnpm build:native\` on a ${prebuilds.platform} host (or assemble release artifacts) before packing.`); + } + try { + fs.accessSync(file, fs.constants.X_OK); + } catch { + // Only reachable when the mode was mangled somewhere between build and + // here (e.g. an archive step that normalized permissions) — the build + // itself always produces 755. + throw new Error(`${manifest.name}: ${binary.path} is not executable — a pack/extract step stripped the mode bit.`); + } + const machine = fs.readFileSync(file).readUInt16LE(18); + if (machine !== E_MACHINE[cpu]) { + throw new Error(`${manifest.name}: ${binary.path} has ELF e_machine ${machine}, expected ${E_MACHINE[cpu]} for ${cpu} — the binary was built for a different architecture.`); + } + } + + const declared = prebuilds.binaries.map((binary) => path.basename(binary.path)).sort(); + const binDir = path.join(packageDir, 'bin'); + const actual = fs.existsSync(binDir) ? fs.readdirSync(binDir).sort() : []; + const extra = actual.filter((name) => !declared.includes(name)); + if (extra.length) { + throw new Error(`${manifest.name}: bin/ contains files not declared in prebuilds.json: ${extra.join(', ')}`); + } + + return { name: manifest.name, count: prebuilds.binaries.length }; +} diff --git a/native/landlock-run/scripts/verify-entry-lib.mjs b/native/landlock-run/scripts/verify-entry-lib.mjs new file mode 100644 index 0000000000..214705e2bc --- /dev/null +++ b/native/landlock-run/scripts/verify-entry-lib.mjs @@ -0,0 +1,25 @@ +#!/usr/bin/env node +/** + * Prepack gate for entry packages: refuse to pack a tarball whose built + * `lib/` is missing. Entry `files` lists use globs, and a glob matching + * nothing packs a silently JS-less tarball instead of failing — this gate + * turns that into a loud refusal on a checkout that never ran + * `pnpm build:ts`. + * + * Runs from each entry package's `prepack` hook (pnpm sets the script cwd + * to the package directory). + */ + +import fs from 'node:fs'; +import path from 'node:path'; + +const packageDir = process.cwd(); +const manifest = JSON.parse(fs.readFileSync(path.join(packageDir, 'package.json'), 'utf8')); + +for (const file of ['lib/index.js', 'lib/index.d.ts']) { + if (!fs.existsSync(path.join(packageDir, file))) { + console.error(`verify-entry-lib: ${manifest.name} has no ${file} — run \`pnpm build:ts\` before packing.`); + process.exit(1); + } +} +console.log(`verify-entry-lib: ${manifest.name} built lib/ present.`); diff --git a/native/landlock-run/scripts/verify-launcher-binary.mjs b/native/landlock-run/scripts/verify-launcher-binary.mjs new file mode 100644 index 0000000000..083cd837aa --- /dev/null +++ b/native/landlock-run/scripts/verify-launcher-binary.mjs @@ -0,0 +1,31 @@ +#!/usr/bin/env node +/** + * Prepack gate for platform packages: refuse to pack a tarball whose + * declared binaries are missing or built for the wrong architecture. + * + * Without it, `pnpm pack` on a checkout that never ran + * `pnpm run build:native` would ship an EMPTY platform package — the + * binary's absence surfacing only at runtime as a failed probe on every + * consumer — and a binary copied across packages would advertise an + * architecture it cannot execute. The check is presence + ELF `e_machine` + * against the package's declared `cpu`; byte provenance is + * `verify-packed-install.mjs`'s concern (it pins the installed tarball + * against the workspace build). + * + * Runs from each platform package's `prepack` hook (pnpm sets the script + * cwd to the package directory). Also callable directly with an explicit + * package directory: `node scripts/verify-launcher-binary.mjs packages/`. + */ + +import path from 'node:path'; +import { root, verifyPlatformBinaries } from './repo.mjs'; + +const packageDir = process.argv[2] ? path.resolve(root, process.argv[2]) : process.cwd(); + +try { + const { name, count } = verifyPlatformBinaries(packageDir); + console.log(`verify-launcher-binary: ${name} — ${count} binaries present with the right ELF architecture.`); +} catch (error) { + console.error(`verify-launcher-binary: ${error instanceof Error ? error.message : error}`); + process.exit(1); +} diff --git a/native/landlock-run/scripts/verify-packed-install.mjs b/native/landlock-run/scripts/verify-packed-install.mjs new file mode 100644 index 0000000000..60f225a9d2 --- /dev/null +++ b/native/landlock-run/scripts/verify-packed-install.mjs @@ -0,0 +1,223 @@ +#!/usr/bin/env node +/** + * Publish-path rehearsal without publishing: verify the packed tarballs are + * exactly what a consumer install needs. `pnpm pack` already produced the + * bytes `pnpm publish` would upload; this script checks the payload + * (coverage, concrete dependency versions, NO lifecycle install scripts — + * this family has no install fallback on purpose), unpacks the entry plus + * THIS host's platform tarball into a throwaway consumer OUTSIDE the repo, + * byte-pins the installed binary against the workspace build it was packed + * from, and drives the INSTALLED entry under plain `node` — resolution, + * probe, and a real confinement world-proof through the installed launcher. + * + * On non-Linux hosts (no platform package exists) it instead proves the + * documented degradation: resolution falls back to a nonexistent path and + * the probe reports `unusable`. + * + * Usage: `node scripts/verify-packed-install.mjs [tarball-dir] [--current-platform-only]`. + * The flag skips the all-platforms tarball-presence check for + * per-architecture CI legs. `NALR_REQUIRE_LANDLOCK=1` makes an unenforcing + * kernel a failure instead of a skipped world-proof (set on CI, where the + * kernel is known). + */ + +import crypto from 'node:crypto'; +import fs from 'node:fs'; +import os from 'node:os'; +import path from 'node:path'; +import { spawnSync } from 'node:child_process'; +import { entryDirs, packageDirs, platformDirs, readJson, root } from './repo.mjs'; + +const args = process.argv.slice(2); +const currentPlatformOnly = args.includes('--current-platform-only'); +const tarballDir = path.resolve(args.find((arg) => !arg.startsWith('--')) || path.join(root, 'dist', 'npm')); +const entryPackageName = 'node-addon-landlock-run'; + +function tarballName(manifest) { + if (manifest.name.startsWith('@')) { + return `${manifest.name.slice(1).replace('/', '-')}-${manifest.version}.tgz`; + } + return `${manifest.name}-${manifest.version}.tgz`; +} + +function tarballPath(manifest) { + const tarball = path.join(tarballDir, tarballName(manifest)); + if (!fs.existsSync(tarball)) { + throw new Error(`missing packed tarball: ${tarball}`); + } + return tarball; +} + +function run(command, commandArgs, options = {}) { + const result = spawnSync(command, commandArgs, { + cwd: options.cwd || root, + stdio: 'inherit', + env: { ...process.env, ...options.env }, + }); + if (result.error) throw result.error; + if (result.status !== 0) { + process.exit(result.status ?? 1); + } +} + +function runCapture(command, commandArgs) { + const result = spawnSync(command, commandArgs, { cwd: root, encoding: 'utf8', maxBuffer: 64 * 1024 * 1024 }); + if (result.error) throw result.error; + if (result.status !== 0) { + process.stderr.write(result.stderr); + process.exit(result.status ?? 1); + } + return result.stdout; +} + +function readPackedManifest(manifest) { + return JSON.parse(runCapture('tar', ['-xOf', tarballPath(manifest), 'package/package.json'])); +} + +function verifyPackedManifest(packed) { + const lifecycle = ['preinstall', 'install', 'postinstall', 'prepare']; + for (const script of lifecycle) { + if (packed.scripts?.[script]) { + throw new Error(`${packed.name}: packed manifest carries a "${script}" lifecycle script — this family has no install fallback`); + } + } + for (const field of ['dependencies', 'optionalDependencies', 'peerDependencies']) { + for (const [name, version] of Object.entries(packed[field] ?? {})) { + if (version.includes('workspace:')) { + throw new Error(`${packed.name}: packed ${field} still uses the workspace protocol: ${name}@${version}`); + } + } + } +} + +function sha256(file) { + return crypto.createHash('sha256').update(fs.readFileSync(file)).digest('hex'); +} + +function packageInstallDir(packageName) { + return path.join(tempRoot, 'node_modules', ...packageName.split('/')); +} + +function unpackTarball(manifest) { + const extractRoot = fs.mkdtempSync(path.join(tempRoot, 'extract-')); + run('tar', ['-xzf', tarballPath(manifest), '-C', extractRoot]); + + const source = path.join(extractRoot, 'package'); + const destination = packageInstallDir(manifest.name); + fs.rmSync(destination, { recursive: true, force: true }); + fs.mkdirSync(path.dirname(destination), { recursive: true }); + fs.renameSync(source, destination); + fs.rmSync(extractRoot, { recursive: true, force: true }); + console.log(`Unpacked ${manifest.name} -> ${path.relative(tempRoot, destination)}`); +} + +const manifests = packageDirs().map((dir) => ({ dir, manifest: readJson(path.join(root, dir, 'package.json')) })); +const entryManifest = manifests.find(({ manifest }) => manifest.name === entryPackageName)?.manifest; +if (!entryManifest) throw new Error(`missing source manifest for ${entryPackageName}`); + +const hostPlatform = `${process.platform}-${process.arch}`; +const currentPlatformEntry = manifests.find( + ({ dir, manifest }) => platformDirs().includes(dir) && manifest.name === `${entryPackageName}-${hostPlatform}`, +); + +// Payload checks: every expected tarball exists (full mode), the packed +// entry's optional-dependency set names exactly the platform packages, and +// no packed manifest carries workspace versions or install lifecycle. +const expectedTarballs = currentPlatformOnly + ? manifests.filter(({ dir }) => entryDirs().includes(dir) || dir === currentPlatformEntry?.dir) + : manifests; +for (const { manifest } of expectedTarballs) { + tarballPath(manifest); +} + +const packedEntry = readPackedManifest(entryManifest); +const platformPackageNames = manifests + .filter(({ dir }) => platformDirs().includes(dir)) + .map(({ manifest }) => manifest.name) + .sort(); +const optionalNames = Object.keys(packedEntry.optionalDependencies || {}).sort(); +if (optionalNames.join('\n') !== platformPackageNames.join('\n')) { + throw new Error(`packed entry optionalDependencies mismatch\nactual:\n${optionalNames.join('\n')}\nexpected:\n${platformPackageNames.join('\n')}`); +} +for (const { manifest } of expectedTarballs) { + verifyPackedManifest(readPackedManifest(manifest)); +} + +// Throwaway ESM consumer, built from local tarballs only — no registry. +const tempRoot = fs.mkdtempSync(path.join(os.tmpdir(), 'nalr-packed-install-')); +fs.writeFileSync( + path.join(tempRoot, 'package.json'), + `${JSON.stringify({ name: 'nalr-packed-install-check', version: '0.0.0', private: true, type: 'module' }, null, 2)}\n`, +); +console.log(`Verifying packed install in ${tempRoot}`); + +unpackTarball(entryManifest); +if (currentPlatformEntry) { + unpackTarball(currentPlatformEntry.manifest); + + // Byte-pin: the installed binary must be the workspace build it was packed + // from — any divergence means the tarball did not carry the built bytes. + const prebuilds = readJson(path.join(root, currentPlatformEntry.dir, 'prebuilds.json')); + for (const binary of prebuilds.binaries) { + const workspaceFile = path.join(root, currentPlatformEntry.dir, binary.path); + const installedFile = path.join(packageInstallDir(currentPlatformEntry.manifest.name), binary.path); + if (sha256(workspaceFile) !== sha256(installedFile)) { + throw new Error(`installed ${binary.path} differs from the workspace build it was packed from`); + } + console.log(`Byte-pinned ${binary.path} against the workspace build`); + } +} else if (process.platform === 'linux') { + throw new Error(`linux host without a platform package in the matrix: ${hostPlatform}`); +} + +// Drive the INSTALLED entry under plain node: resolution, probe, and (on an +// enforcing kernel) a real confinement world-proof through the installed +// launcher. +const driver = path.join(tempRoot, 'driver.mjs'); +fs.writeFileSync(driver, ` +import assert from 'node:assert/strict'; +import { spawnSync } from 'node:child_process'; +import fs from 'node:fs'; +import os from 'node:os'; +import path from 'node:path'; +import { grantArgs, launcherPath, probe } from 'node-addon-landlock-run'; + +const requireLandlock = process.env.NALR_REQUIRE_LANDLOCK === '1'; +const platformPackage = 'node-addon-landlock-run-' + process.platform + '-' + process.arch; +const resolved = launcherPath(); +assert.ok(path.isAbsolute(resolved), 'launcherPath must be absolute'); +assert.ok(resolved.includes(path.join(...platformPackage.split('/'))), 'launcherPath must point into the platform package: ' + resolved); + +if (process.platform === 'linux') { + assert.ok(fs.existsSync(resolved), 'installed launcher missing at ' + resolved); + try { + fs.accessSync(resolved, fs.constants.X_OK); + } catch { + throw new Error('installed launcher is not executable — the pack path stripped the mode bit: ' + resolved); + } + const enforcement = probe(resolved); + console.log('probe through the installed launcher: ' + enforcement); + if (enforcement === 'unusable') { + if (requireLandlock) throw new Error('NALR_REQUIRE_LANDLOCK=1 but the probe reports unusable'); + console.log('kernel does not enforce Landlock — skipping the confinement world-proof'); + } else { + const work = fs.mkdtempSync(path.join(os.tmpdir(), 'nalr-confine-')); + const denied = path.join(work, 'denied.txt'); + const deniedRun = spawnSync(resolved, [...grantArgs({ readOnly: ['/'] }), '--', '/bin/sh', '-c', 'echo x > ' + denied], { encoding: 'utf8' }); + assert.notEqual(deniedRun.status, 0, 'write outside the grants must fail'); + assert.ok(!fs.existsSync(denied), 'denied write must not land on disk'); + const granted = path.join(work, 'granted.txt'); + const grantedRun = spawnSync(resolved, [...grantArgs({ readOnly: ['/'], readWrite: [work] }), '--', '/bin/sh', '-c', 'echo ok > ' + granted], { encoding: 'utf8' }); + assert.equal(grantedRun.status, 0, 'granted write must succeed: ' + grantedRun.stderr); + assert.equal(fs.readFileSync(granted, 'utf8').trim(), 'ok'); + console.log('confinement world-proof passed through the installed launcher'); + } +} else { + assert.ok(!fs.existsSync(resolved), 'no platform package exists for this host — the fallback path must not exist'); + assert.equal(probe(resolved), 'unusable'); + console.log('non-linux host: fallback resolution and unusable probe verified'); +} +`); +run(process.execPath, [driver], { cwd: tempRoot }); + +console.log('Packed install verification passed.'); diff --git a/native/landlock-run/scripts/verify-release.mjs b/native/landlock-run/scripts/verify-release.mjs new file mode 100644 index 0000000000..e812b34a14 --- /dev/null +++ b/native/landlock-run/scripts/verify-release.mjs @@ -0,0 +1,52 @@ +#!/usr/bin/env node +/** + * Release verification. Always: every published package carries one shared + * version, and — when running from a tag or publishing — the `vX.Y.Z` tag + * matches it. With `--prebuilds`: every platform package's declared + * binaries exist with the right ELF architecture (run after + * `assemble-prebuilds.mjs` or a local `build:native`). + */ + +import path from 'node:path'; +import { packageDirs, platformDirs, readJson, root, verifyPlatformBinaries } from './repo.mjs'; + +function verifyVersions() { + const packages = packageDirs().map((dir) => ({ + dir, + manifest: readJson(path.join(root, dir, 'package.json')), + })); + const versions = new Set(packages.map((pkg) => pkg.manifest.version)); + if (versions.size !== 1) { + throw new Error([ + 'published package versions must match:', + ...packages.map((pkg) => `${pkg.dir}: ${pkg.manifest.version}`), + ].join('\n')); + } + + const version = packages[0].manifest.version; + const ref = process.env.GITHUB_REF || ''; + const publish = process.env.RELEASE_PUBLISH === 'true'; + if (publish && !ref.startsWith('refs/tags/v')) { + throw new Error('publishing requires running the workflow from a v* tag'); + } + if (ref.startsWith('refs/tags/v')) { + const tagVersion = ref.slice('refs/tags/v'.length); + if (tagVersion !== version) { + throw new Error(`tag/version mismatch: tag v${tagVersion}, packages ${version}`); + } + } + + console.log(`Verified release version ${version}`); +} + +function verifyPrebuilds() { + for (const dir of platformDirs()) { + const { name, count } = verifyPlatformBinaries(path.join(root, dir)); + console.log(`Verified ${name}: ${count} binaries`); + } +} + +verifyVersions(); +if (process.argv.includes('--prebuilds')) { + verifyPrebuilds(); +} diff --git a/native/landlock-run/test/entry.test.js b/native/landlock-run/test/entry.test.js new file mode 100644 index 0000000000..2e2cfe8f17 --- /dev/null +++ b/native/landlock-run/test/entry.test.js @@ -0,0 +1,76 @@ +/** + * Keyless entry-package tests — run on every host, no kernel or binary + * required. Cover the JS seam's pure surface: grant-argv construction, the + * resolution contract (platform package → fallback), and probe verdicts over + * fake launchers. Requires built `lib/` (`pnpm build:ts`). + */ + +import assert from 'node:assert/strict'; +import fs from 'node:fs'; +import os from 'node:os'; +import path from 'node:path'; +import { + LAUNCHER_BIN, + LAUNCHER_FAILURE_EXIT, + grantArgs, + launcherPath, + probe, +} from 'node-addon-landlock-run'; + +// --- constants are part of the CLI contract --- +assert.equal(LAUNCHER_BIN, 'landlock-run'); +assert.equal(LAUNCHER_FAILURE_EXIT, 125); + +// --- grantArgs: flag spelling, ordering, and empty grants --- +assert.deepEqual(grantArgs({}), []); +assert.deepEqual(grantArgs({ readOnly: ['/'] }), ['--ro', '/']); +assert.deepEqual( + grantArgs({ readOnly: ['/', '/opt'], readWrite: ['/tmp/work'] }), + ['--ro', '/', '--ro', '/opt', '--rw', '/tmp/work'], +); +assert.deepEqual(grantArgs({ readWrite: ['/a'], readOnly: ['/b'] }), ['--ro', '/b', '--rw', '/a']); + +// --- launcherPath: resolves the platform package next to its package.json --- +const platformPackage = `node-addon-landlock-run-${process.platform}-${process.arch}`; +const resolvedViaSeam = launcherPath((specifier) => { + assert.equal(specifier, `${platformPackage}/package.json`); + return path.join('/fake-install', specifier); +}); +assert.equal(resolvedViaSeam, path.join('/fake-install', platformPackage, 'bin', LAUNCHER_BIN)); + +// --- launcherPath: unresolvable package falls back to an absolute, package-boundary path --- +const fallback = launcherPath(() => { + throw new Error('not installed'); +}); +assert.ok(path.isAbsolute(fallback), 'fallback path must be absolute'); +assert.ok( + fallback.includes(path.join('node_modules', ...platformPackage.split('/'), 'bin', LAUNCHER_BIN)), + `fallback must point at the platform package layout: ${fallback}`, +); + +// --- launcherPath: default resolution agrees with this workspace's layout --- +const defaultPath = launcherPath(); +assert.ok(path.isAbsolute(defaultPath)); +assert.ok(defaultPath.endsWith(path.join('bin', LAUNCHER_BIN)), defaultPath); + +// --- probe: a missing launcher is unusable, indistinguishable from an unenforcing kernel --- +assert.equal(probe(path.join(os.tmpdir(), 'nalr-no-such-launcher')), 'unusable'); + +// --- probe: verdict parsing over fake launchers (POSIX shells only) --- +if (process.platform !== 'win32') { + const fakeDir = fs.mkdtempSync(path.join(os.tmpdir(), 'nalr-fake-launcher-')); + const fake = (name, script) => { + const file = path.join(fakeDir, name); + fs.writeFileSync(file, `#!/bin/sh\n${script}\n`, { mode: 0o755 }); + return file; + }; + + assert.equal(probe(fake('full', 'echo "landlock: fully enforced"; exit 0')), 'full'); + assert.equal(probe(fake('partial', 'echo "landlock: partially enforced (older ABI)"; exit 0')), 'partial'); + assert.equal(probe(fake('failing', `exit ${LAUNCHER_FAILURE_EXIT}`)), 'unusable'); + assert.equal(probe(fake('hanging', 'sleep 10'), { timeoutMs: 200 }), 'unusable'); + + fs.rmSync(fakeDir, { recursive: true, force: true }); +} + +console.log('entry.test: ok'); diff --git a/native/landlock-run/test/launcher.test.js b/native/landlock-run/test/launcher.test.js new file mode 100644 index 0000000000..4f456e2145 --- /dev/null +++ b/native/landlock-run/test/launcher.test.js @@ -0,0 +1,121 @@ +/** + * Behavioral tests against the REAL launcher binary on a real kernel: the + * CLI contract (usage errors, exit codes, argv passthrough) and the + * confinement world-proofs (denied writes stay off disk, grants land). + * + * Preconditions and their skip semantics: + * - Non-Linux host: skips entirely (exit 0) — there is nothing to build here. + * - Linux without the built binary: FAILS — run `pnpm build:native` first. + * - Linux whose kernel does not enforce Landlock: skips the enforcement + * half, unless `NALR_REQUIRE_LANDLOCK=1` (set on CI, where a silent skip on + * the very platform that exists to prove enforcement would be a false + * green). + */ + +import assert from 'node:assert/strict'; +import fs from 'node:fs'; +import os from 'node:os'; +import path from 'node:path'; +import { spawnSync } from 'node:child_process'; +import { + LAUNCHER_FAILURE_EXIT, + grantArgs, + launcherPath, + probe, +} from 'node-addon-landlock-run'; + +const requireLandlock = process.env.NALR_REQUIRE_LANDLOCK === '1'; + +if (process.platform !== 'linux') { + console.log(`launcher.test: SKIP — the launcher only exists on linux (host: ${process.platform})`); + process.exit(0); +} + +const launcher = launcherPath(); +assert.ok( + fs.existsSync(launcher), + `launcher.test: no built launcher at ${launcher} — run \`pnpm build:native\` (apt-get install musl-tools) first`, +); + +const run = (args, options = {}) => spawnSync(launcher, args, { encoding: 'utf8', ...options }); + +// --- usage errors: parse failures exit LAUNCHER_FAILURE_EXIT before any restriction --- +{ + const noCommand = run([]); + assert.equal(noCommand.status, LAUNCHER_FAILURE_EXIT); + assert.match(noCommand.stderr, /usage error: missing `-- \.\.\.` command/); + + const unknownFlag = run(['--bogus', '--', 'true']); + assert.equal(unknownFlag.status, LAUNCHER_FAILURE_EXIT); + assert.match(unknownFlag.stderr, /usage error: unknown argument: --bogus/); + + const danglingPath = run(['--ro']); + assert.equal(danglingPath.status, LAUNCHER_FAILURE_EXIT); + assert.match(danglingPath.stderr, /--ro requires a path/); + + const probeWithExtras = run(['--probe', '--ro', '/']); + assert.equal(probeWithExtras.status, LAUNCHER_FAILURE_EXIT); + assert.match(probeWithExtras.stderr, /--probe takes no other arguments/); +} + +// --- probe: the functional availability signal --- +const enforcement = probe(launcher); +console.log(`launcher.test: probe → ${enforcement}`); +if (enforcement === 'unusable') { + if (requireLandlock) { + console.error('launcher.test: NALR_REQUIRE_LANDLOCK=1 but the probe reports unusable — this kernel cannot prove enforcement'); + process.exit(1); + } + console.log('launcher.test: SKIP enforcement half — kernel does not enforce Landlock'); + process.exit(0); +} +{ + const probeRun = run(['--probe']); + assert.equal(probeRun.status, 0); + assert.match(probeRun.stdout, /^landlock: (fully enforced|partially enforced \(older ABI\))\n$/); +} + +// --- confined exec: the command runs, its exit code passes through --- +{ + const echo = run([...grantArgs({ readOnly: ['/'] }), '--', '/bin/sh', '-c', 'echo confined-ok']); + assert.equal(echo.status, 0, echo.stderr); + assert.equal(echo.stdout, 'confined-ok\n'); + + const exitCode = run([...grantArgs({ readOnly: ['/'] }), '--', '/bin/sh', '-c', 'exit 7']); + assert.equal(exitCode.status, 7, 'the wrapped command exit code must pass through unchanged'); +} + +// --- world-proofs: denied writes stay off disk, grants land, inheritance crosses exec --- +{ + const work = fs.mkdtempSync(path.join(os.tmpdir(), 'nalr-launcher-test-')); + + const denied = path.join(work, 'denied.txt'); + const deniedRun = run([...grantArgs({ readOnly: ['/'] }), '--', '/bin/sh', '-c', `echo x > ${denied}`]); + assert.notEqual(deniedRun.status, 0, 'a write outside the grants must fail'); + assert.ok(!fs.existsSync(denied), 'the denied write must not land on disk'); + + const granted = path.join(work, 'granted.txt'); + const grantedRun = run([...grantArgs({ readOnly: ['/'], readWrite: [work] }), '--', '/bin/sh', '-c', `echo ok > ${granted}`]); + assert.equal(grantedRun.status, 0, grantedRun.stderr); + assert.equal(fs.readFileSync(granted, 'utf8'), 'ok\n'); + + // The ruleset is inherited across execve: a CHILD of the wrapped command + // is confined too, not just the direct exec target. + const nested = path.join(work, 'nested.txt'); + const nestedRun = run([...grantArgs({ readOnly: ['/'] }), '--', '/bin/sh', '-c', `/bin/sh -c 'echo x > ${nested}'; true`]); + assert.equal(nestedRun.status, 0, nestedRun.stderr); + assert.ok(!fs.existsSync(nested), 'a denied write from a nested child must not land either'); + + fs.rmSync(work, { recursive: true, force: true }); +} + +// --- fail closed: an unopenable grant root refuses to exec at all --- +{ + const marker = path.join(os.tmpdir(), `nalr-should-not-exist-${process.pid}`); + const badGrant = run(['--ro', '/no/such/grant/root', '--', '/bin/sh', '-c', `echo x > ${marker}`]); + assert.equal(badGrant.status, LAUNCHER_FAILURE_EXIT); + assert.match(badGrant.stderr, /cannot open rule path/); + assert.ok(!fs.existsSync(marker), 'the command must never run when the launcher fails'); +} + +console.log('launcher.test: ok'); diff --git a/native/landlock-run/tsconfig.base.json b/native/landlock-run/tsconfig.base.json new file mode 100644 index 0000000000..a95ca64f6d --- /dev/null +++ b/native/landlock-run/tsconfig.base.json @@ -0,0 +1,11 @@ +{ + "compilerOptions": { + "target": "ES2022", + "module": "NodeNext", + "moduleResolution": "NodeNext", + "strict": true, + "esModuleInterop": true, + "skipLibCheck": true, + "types": ["node"] + } +} diff --git a/native/landlock-run/tsconfig.json b/native/landlock-run/tsconfig.json new file mode 100644 index 0000000000..3813d343cd --- /dev/null +++ b/native/landlock-run/tsconfig.json @@ -0,0 +1,11 @@ +{ + "extends": "./tsconfig.base.json", + "compilerOptions": { + "noEmit": true + }, + "files": [], + "include": ["scripts/**/*.ts"], + "references": [ + { "path": "./packages/entry" } + ] +} diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json index a03f7ca25a..1c75d8e90f 100644 --- a/scripts/doc-budgets.manifest.json +++ b/scripts/doc-budgets.manifest.json @@ -1,5 +1,5 @@ { - "AGENTS.md": 1370, + "AGENTS.md": 1375, "docs/AGENTS.md": 1100, "docs/architecture.md": 1790, "docs/cordis-primer.md": 550, From e723f233fb090fd2743f8f0dcca9db93aaf1dcbd Mon Sep 17 00:00:00 2001 From: kingwl Date: Tue, 14 Jul 2026 23:41:27 +0800 Subject: [PATCH 093/323] docs(acp-agent): fs tools ride the sandbox policy under every mode The README predated dsh-fs-sandbox and still said filesystem tools were omitted from the confined default; read/write/edit now confine under the same workspaceRoot as bash. --- examples/acp-agent/README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index 8f611b7d67..e459c31ba2 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -29,7 +29,7 @@ Add to your Zed `settings.json` under `agent_servers`: } ``` -The editor sets each session's `cwd` to the project it opens, and bash uses that directory as its workdir. The current sandbox write boundary is nevertheless fixed when the server starts (`workspaceRoot: process.cwd()`), so launch the server from the workspace it should be allowed to modify; making that root session-scoped is deferred in the [sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). Filesystem tools are omitted from the confined default because they execute in-process and do not ride the bash sandbox. +The editor sets each session's `cwd` to the project it opens, and bash uses that directory as its workdir. The current sandbox write boundary is nevertheless fixed when the server starts (`workspaceRoot: process.cwd()`), so launch the server from the workspace it should be allowed to modify; making that root session-scoped is deferred in the [sandbox RFC](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). The filesystem tools now ride the same sandbox policy through [`@deepseek-ai/dsh-fs-sandbox`](../../packages/fs/fs-sandbox/), so `read`/`write`/`edit` are available under every mode and confined to the same `workspaceRoot`. ## Snapshot tests (record-once / replay-deterministic) @@ -37,11 +37,11 @@ This example hosts the ACP snapshot suite. `dsh-llm-replay` reconstructs model s ## Permissions and sandboxing -The default tree composes [`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/), [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/), [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/), and [`@deepseek-ai/dsh-permission`](../../packages/ui/permission/). Bash starts in `workspace-write`; a denied operation returns a structured marker, and a retry with `sandbox_permissions` plus `justification` becomes a one-shot `session/request_permission` prompt in the editor. "Allow once" runs exactly that retry under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). +The default tree composes [`@deepseek-ai/dsh-sandbox-local`](../../packages/sandbox/sandbox-local/), [`@deepseek-ai/dsh-sandbox-policy`](../../packages/sandbox/sandbox-policy/), [`@deepseek-ai/dsh-bash-sandbox`](../../packages/bash/bash-sandbox/), [`@deepseek-ai/dsh-fs-sandbox`](../../packages/fs/fs-sandbox/), [`@deepseek-ai/dsh-user-approval`](../../packages/ui/user-approval/), and [`@deepseek-ai/dsh-permission`](../../packages/ui/permission/). Bash and the `read`/`write`/`edit` tools start in `workspace-write`; a denied operation returns a structured marker, and a retry with `sandbox_permissions` plus `justification` becomes a one-shot `session/request_permission` prompt in the editor. "Allow once" runs exactly that retry under the wider mode ([sandbox RFC § Escalation](../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). - **One session config option is live**: a capable client shows one `Permissions` select. `workspace-write` means workspace-confined bash plus `ask`; `danger-full-access` means unconfined file access plus `never`. Switching writes one `permission/preset` event through to the sandbox-mode and approval-policy events, and `session/load` reports the resumed value. - **Every approval is one-shot**: the choices are `Allow once` and `Reject`; a dismissal, rejection, missing editor, or unavailable runner fails closed. -- **The boundary is bash-only and config-fixed today**: in-process filesystem tools are omitted from the confined live default, while the sandbox workspace root remains the server's launch directory. +- **The boundary spans bash and the filesystem tools, and is config-fixed today**: bash confines through the OS runner and the `read`/`write`/`edit` tools through an in-process path fence ([`dsh-fs-sandbox`](../../packages/fs/fs-sandbox/)), both keyed to the same `workspaceRoot` — which remains the server's launch directory (a per-session root is deferred). `tests/escalation.e2e.ts` boots this default tree keyless, drives the permission select, and—with a key and usable runner—proves both approval outcomes against the filesystem. The snapshot suite uses the same tree: snapshot mode starts at `danger-full-access` so established fixtures remain runner-independent, while the permission-switching and escalation inputs explicitly select `workspace-write` before exercising that policy path. No fixture pins a real denial because kernel error text is backend-specific; real confinement remains covered by the sandbox packages' kernel e2e suites. From d0df50aa8eee0c98b7eacadcdbc797f7780de565 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:43:53 +0800 Subject: [PATCH 094/323] fix: retain LLM HTTP status metadata --- packages/llm/llm-deepseek/src/adapter.ts | 2 +- packages/llm/llm-deepseek/tests/adapter.spec.ts | 7 ++++++- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/index.ts | 6 ++++-- packages/llm/llm/tests/service.spec.ts | 5 ++--- packages/support/llm-replay/src/index.ts | 4 ++-- packages/support/llm-replay/tests/llm-replay.spec.ts | 10 +++++----- 7 files changed, 21 insertions(+), 15 deletions(-) diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index f6051d1ccd..30760a8fbc 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -76,7 +76,7 @@ export class DeepSeekAdapter extends LlmAdapter { // Only swallow error-body parsing: status and code are already captured, // so malformed gateway JSON must not mask the actionable HTTP failure. } - throw new LlmError(message, code) + throw new LlmError(message, code, response.status) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 1f1aef3f05..46f123a1c7 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior]) + const server = await mockServer([behavior, behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,6 +166,11 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) + // The numeric HTTP status is carried on the error for explicit handling. + await expect( + assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) + .catch((error: unknown) => (error as LlmError).status), + ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index c8f2002f9f..296fd0c3d3 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. +- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. ### Real adapters diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 8f2c9b4f39..08f3f54c51 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,10 +42,12 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; + * `status` carries the HTTP status when the error originated from a non-2xx + * provider response (absent for protocol/usage errors that have no HTTP status). */ export class LlmError extends HarnessError { - constructor(message: string, code: string, options?: ErrorOptions) { + constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 125a810261..f669069c44 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,12 +79,11 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const cause = new Error('root cause') - const err = new LlmError('boom', 'AUTH', { cause }) + const err = new LlmError('boom', 'AUTH', 401) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.cause).toBe(cause) + expect(err.status).toBe(401) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index b7e4e30a46..2e509973e5 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -20,7 +20,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -221,7 +221,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code) + throw new LlmError(entry.message, entry.code, entry.status) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index aa3fea20d5..ac52ec11c9 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From cb177090f9573b30947af31daa876d586bea844a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 23:53:23 +0800 Subject: [PATCH 095/323] docs: refresh subagent config catalog --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 093e534d23..d9e42366ba 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -915,7 +915,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) -Source: [`packages/subagent/tool-subagent/src/index.ts:47`](../packages/subagent/tool-subagent/src/index.ts) +Source: [`packages/subagent/tool-subagent/src/index.ts:24`](../packages/subagent/tool-subagent/src/index.ts) ## `@deepseek-ai/dsh-tool-web` From 0892831177c895b4139cb61b9c20a32b465fc923 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 00:01:00 +0800 Subject: [PATCH 096/323] docs: refresh LLM service catalog --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index de6bf20fd1..ca83b3c489 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` From 91247babd91749d720aa862036977592ca9f42a0 Mon Sep 17 00:00:00 2001 From: kingwl Date: Wed, 15 Jul 2026 00:17:29 +0800 Subject: [PATCH 097/323] test(acp-agent): snapshot the fs sandbox escalation arc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A recorded scenario where the model writes a workspace file in one write call with sandbox_permissions=danger-full-access + justification, the scripted client allows once, and the escalated write lands — the fs twin of escalation-approved, covering the fs escalation approval arc (only bash had a snapshot before). Uses a new workspace-internal file to avoid the read-before-edit detour, keeping the recorded path single and deterministic. --- examples/acp-agent/tests/acp.snapshot.ts | 1 + .../fs-escalation-approved/input.json | 11 ++ .../fs-escalation-approved/session.jsonl | 127 ++++++++++++++++++ .../stdout.golden.jsonl | 52 +++++++ 4 files changed, 191 insertions(+) create mode 100644 examples/acp-agent/tests/snapshots/fs-escalation-approved/input.json create mode 100644 examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.golden.jsonl diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 64c55fa179..6b8b87e1e5 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -125,6 +125,7 @@ const SCENARIOS: Scenario[] = [ { name: 'permission-switching', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderDeltas: 1, headerClass: 'sandbox' }, { name: 'escalation-approved', hasModelTurn: true, recorded: true, headerClass: 'sandbox' }, { name: 'escalation-rejected', hasModelTurn: true, recorded: true, headerClass: 'sandbox' }, + { name: 'fs-escalation-approved', hasModelTurn: true, recorded: true, headerClass: 'sandbox' }, ] defineAcpSnapshotSuite({ diff --git a/examples/acp-agent/tests/snapshots/fs-escalation-approved/input.json b/examples/acp-agent/tests/snapshots/fs-escalation-approved/input.json new file mode 100644 index 0000000000..d6d8d2b8c6 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-escalation-approved/input.json @@ -0,0 +1,11 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "setConfigOption", "configId": "permission", "value": "workspace-write" }, + { "op": "prompt", "text": "Use the write tool (NOT bash) to create escalated.md in the current directory containing exactly the single line: escalated. An equivalent write was denied earlier, so make this one single write call with sandbox_permissions set to danger-full-access and the justification 'the user asked to escalate this write'. Do not call write without sandbox_permissions first. I will approve the permission prompt. After the result, reply with exactly the single word DONE." } + ], + "permissionAnswers": [ + { "kind": "allow_once" } + ] +} diff --git a/examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl new file mode 100644 index 0000000000..16e0b8dc95 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-escalation-approved/session.jsonl @@ -0,0 +1,127 @@ +{"type":"session","version":0,"id":"977a4820-f609-4b48-9039-adcdd921c5fe","createdAt":1784045702340,"cwd":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-vmEGzd"} +{"type":"turn/start","seq":0,"time":1784045702342,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"permission/preset","seq":1,"time":1784045702343,"data":{"preset":"workspace-write"}} +{"type":"sandbox/mode","seq":2,"time":1784045702343,"data":{"mode":"workspace-write"}} +{"type":"approval/policy","seq":3,"time":1784045702343,"data":{"policy":"ask"}} +{"type":"user/message","seq":4,"time":1784045702343,"data":{"content":[{"type":"text","text":"Use the write tool (NOT bash) to create escalated.md in the current directory containing exactly the single line: escalated. An equivalent write was denied earlier, so make this one single write call with sandbox_permissions set to danger-full-access and the justification 'the user asked to escalate this write'. Do not call write without sandbox_permissions first. I will approve the permission prompt. After the result, reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":5,"time":1784045702345,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":6,"time":1784045702345,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":7,"time":1784045703046,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":8,"time":1784045703046,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":9,"time":1784045703162,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":10,"time":1784045703172,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":11,"time":1784045703172,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":12,"time":1784045703173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":13,"time":1784045703173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" create"}}} +{"type":"assistant/chunk","seq":14,"time":1784045703173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":15,"time":1784045703173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" file"}}} +{"type":"assistant/chunk","seq":16,"time":1784045703199,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} +{"type":"assistant/chunk","seq":17,"time":1784045703225,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":18,"time":1784045703251,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" write"}}} +{"type":"assistant/chunk","seq":19,"time":1784045703252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":20,"time":1784045703252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":21,"time":1784045703252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sand"}}} +{"type":"assistant/chunk","seq":22,"time":1784045703252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"box"}}} +{"type":"assistant/chunk","seq":23,"time":1784045703252,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_per"}}} +{"type":"assistant/chunk","seq":24,"time":1784045703277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"missions"}}} +{"type":"assistant/chunk","seq":25,"time":1784045703278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":26,"time":1784045703278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":27,"time":1784045703278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":28,"time":1784045703278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} +{"type":"assistant/chunk","seq":29,"time":1784045703304,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":30,"time":1784045703304,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":31,"time":1784045703356,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":32,"time":1784045703356,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":33,"time":1784045703381,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":34,"time":1784045703381,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":35,"time":1784045703381,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"file"}}} +{"type":"assistant/chunk","seq":36,"time":1784045703405,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"_path"}}} +{"type":"assistant/chunk","seq":37,"time":1784045703406,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":38,"time":1784045703406,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":39,"time":1784045703406,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":40,"time":1784045703431,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"es"}}} +{"type":"assistant/chunk","seq":41,"time":1784045703432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":42,"time":1784045703432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":43,"time":1784045703432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":".md"}}} +{"type":"assistant/chunk","seq":44,"time":1784045703432,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":45,"time":1784045703483,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":46,"time":1784045703483,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":47,"time":1784045703483,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"content"}}} +{"type":"assistant/chunk","seq":48,"time":1784045703483,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":49,"time":1784045703483,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":50,"time":1784045703509,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":51,"time":1784045703509,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"es"}}} +{"type":"assistant/chunk","seq":52,"time":1784045703509,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"cal"}}} +{"type":"assistant/chunk","seq":53,"time":1784045703509,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"ated"}}} +{"type":"assistant/chunk","seq":54,"time":1784045703509,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":55,"time":1784045703565,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":56,"time":1784045703566,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":57,"time":1784045703566,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"sand"}}} +{"type":"assistant/chunk","seq":58,"time":1784045703566,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"box"}}} +{"type":"assistant/chunk","seq":59,"time":1784045703566,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"_per"}}} +{"type":"assistant/chunk","seq":60,"time":1784045703566,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"missions"}}} +{"type":"assistant/chunk","seq":61,"time":1784045703566,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":62,"time":1784045703591,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":63,"time":1784045703591,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":64,"time":1784045703591,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"danger"}}} +{"type":"assistant/chunk","seq":65,"time":1784045703591,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"-full"}}} +{"type":"assistant/chunk","seq":66,"time":1784045703617,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"-access"}}} +{"type":"assistant/chunk","seq":67,"time":1784045703618,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":68,"time":1784045703644,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":69,"time":1784045703645,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":70,"time":1784045703645,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"just"}}} +{"type":"assistant/chunk","seq":71,"time":1784045703645,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"ification"}}} +{"type":"assistant/chunk","seq":72,"time":1784045703669,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":73,"time":1784045703669,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":74,"time":1784045703669,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":75,"time":1784045703669,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"the"}}} +{"type":"assistant/chunk","seq":76,"time":1784045703696,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":" user"}}} +{"type":"assistant/chunk","seq":77,"time":1784045703696,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":" asked"}}} +{"type":"assistant/chunk","seq":78,"time":1784045703696,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":79,"time":1784045703696,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":" escalate"}}} +{"type":"assistant/chunk","seq":80,"time":1784045703724,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":" this"}}} +{"type":"assistant/chunk","seq":81,"time":1784045703724,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":" write"}}} +{"type":"assistant/chunk","seq":82,"time":1784045703724,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":83,"time":1784045703749,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":84,"time":1784045703776,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to create a file using the write tool with sandbox_permissions. Let me do that."}}}} +{"type":"assistant/chunk","seq":85,"time":1784045703776,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","arguments":"{\"file_path\": \"escalated.md\", \"content\": \"escalated\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to escalate this write\"}"}}}} +{"type":"assistant/chunk","seq":86,"time":1784045703776,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3871,"outputTokens":132,"cacheReadTokens":0,"reasoningTokens":23}}}} +{"type":"assistant/chunk","seq":87,"time":1784045703776,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":88,"time":1784045703780,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file using the write tool with sandbox_permissions. Let me do that."},{"type":"tool-call","id":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","arguments":"{\"file_path\": \"escalated.md\", \"content\": \"escalated\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to escalate this write\"}"}],"usage":{"inputTokens":3871,"outputTokens":132,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87],"surfaceOp":"append"} +{"type":"tool/call","seq":89,"time":1784045703780,"data":{"turn":1,"step":1,"callId":"call_00_Fnymmavpr4klMDy4Fdej3227","name":"write","arguments":"{\"file_path\": \"escalated.md\", \"content\": \"escalated\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to escalate this write\"}"}} +{"type":"approval/asked","seq":90,"time":1784045703782,"data":{"id":"5b715180-e0eb-4ab6-98ff-965fd9c6f08b","toolName":"write","callId":"call_00_Fnymmavpr4klMDy4Fdej3227","reason":"escalate sandbox to danger-full-access: the user asked to escalate this write"}} +{"type":"approval/decided","seq":91,"time":1784045703786,"data":{"id":"5b715180-e0eb-4ab6-98ff-965fd9c6f08b","outcome":"allowed-once"}} +{"type":"tool/result","seq":92,"time":1784045703798,"data":{"turn":1,"step":1,"callId":"call_00_Fnymmavpr4klMDy4Fdej3227","content":[{"type":"text","text":"/var/folders/2g/b32ct0qn1d728l_v6tdkjytr0000gn/T/acp-snap-cwd-vmEGzd/escalated.md\nfile\n\nCreated file\n"}],"isError":false},"sourceEventSeqs":[89],"surfaceOp":"append"} +{"type":"step/end","seq":93,"time":1784045703798,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":94,"time":1784045703799,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":95,"time":1784045704512,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":96,"time":1784045704512,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":97,"time":1784045704620,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" file"}}} +{"type":"assistant/chunk","seq":98,"time":1784045704645,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} +{"type":"assistant/chunk","seq":99,"time":1784045704646,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" created"}}} +{"type":"assistant/chunk","seq":100,"time":1784045704646,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} +{"type":"assistant/chunk","seq":101,"time":1784045704646,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":102,"time":1784045704646,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} +{"type":"assistant/chunk","seq":103,"time":1784045704646,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":104,"time":1784045704672,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} +{"type":"assistant/chunk","seq":105,"time":1784045704673,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":106,"time":1784045704673,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":107,"time":1784045704673,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":108,"time":1784045704699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":109,"time":1784045704699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":110,"time":1784045704699,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":111,"time":1784045704726,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":112,"time":1784045704726,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":113,"time":1784045704726,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" D"}}} +{"type":"assistant/chunk","seq":114,"time":1784045704754,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":115,"time":1784045704754,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":116,"time":1784045704754,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":117,"time":1784045704754,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":118,"time":1784045704754,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":119,"time":1784045704755,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The file was created successfully. The user asked me to reply with exactly the single word DONE."}}}} +{"type":"assistant/chunk","seq":120,"time":1784045704755,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":121,"time":1784045704755,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":107,"outputTokens":23,"cacheReadTokens":3968,"reasoningTokens":20}}}} +{"type":"assistant/chunk","seq":122,"time":1784045704755,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":123,"time":1784045704755,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file was created successfully. The user asked me to reply with exactly the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":107,"outputTokens":23,"cacheReadTokens":3968,"reasoningTokens":20}},"sourceEventSeqs":[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122],"surfaceOp":"append"} +{"type":"step/end","seq":124,"time":1784045704755,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":125,"time":1784045704756,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.golden.jsonl new file mode 100644 index 0000000000..3e86a1d4e8 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/fs-escalation-approved/stdout.golden.jsonl @@ -0,0 +1,52 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" create"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" write"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sand"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"box"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_per"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"missions"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" do"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_Fnymmavpr4klMDy4Fdej3227","title":"Write escalated.md","kind":"edit","status":"in_progress","locations":[{"path":"escalated.md"}],"content":[{"type":"diff","path":"escalated.md","oldText":null,"newText":"escalated"}]}}} +{"jsonrpc":"2.0","id":1,"method":"session/request_permission","params":{"sessionId":"{{sessionId}}","toolCall":{"toolCallId":"call_00_Fnymmavpr4klMDy4Fdej3227"},"options":[{"optionId":"allow-once","name":"Allow once","kind":"allow_once"},{"optionId":"reject-once","name":"Reject","kind":"reject_once"}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_Fnymmavpr4klMDy4Fdej3227","status":"completed","content":[{"type":"diff","path":"escalated.md","oldText":null,"newText":"escalated"}],"title":"Write escalated.md"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" file"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" created"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" successfully"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} From ff064917a25fe72af8ba109847fa822220cc4330 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 00:18:04 +0800 Subject: [PATCH 098/323] docs: refresh LLM service catalog --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index de6bf20fd1..ca83b3c489 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` From e8d066f7505afe83c08ba3cb0b8693a7126558fc Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 16:03:52 +0800 Subject: [PATCH 099/323] feat(core): add post-step request recovery (PR3 phase 1) --- docs/agent-lifecycle.md | 10 +- docs/architecture.md | 58 ++- docs/cordis-catalog/events.md | 52 ++- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/core.md | 14 + docs/core-data-structures/llm-streaming.md | 3 +- docs/event-producer-consumer.md | 30 +- .../cordis/tool-cordis/src/api-catalog.ts | 12 + packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/loop.ts | 179 +++++-- packages/core/agent-loop/tests/cancel.spec.ts | 57 ++- .../tests/contract-regressions.spec.ts | 10 + .../agent-loop/tests/request-recovery.spec.ts | 442 ++++++++++++++++++ packages/core/agent/README.md | 2 +- packages/core/agent/src/types.ts | 31 ++ packages/llm/llm-deepseek/README.md | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 24 +- .../llm/llm-deepseek/tests/adapter.spec.ts | 28 +- packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm-pi-ai/src/convert.ts | 3 +- packages/llm/llm-pi-ai/tests/convert.spec.ts | 14 +- packages/llm/llm/README.md | 5 +- packages/llm/llm/src/adapter-failure.ts | 34 ++ packages/llm/llm/src/error.ts | 41 ++ packages/llm/llm/src/index.ts | 58 ++- packages/llm/llm/tests/service.spec.ts | 198 +++++++- .../invariants/src/scoped-events.generated.ts | 2 + scripts/gen-doc-graphs.ts | 10 +- scripts/type-equiv.manifest.json | 2 + 29 files changed, 1207 insertions(+), 120 deletions(-) create mode 100644 packages/core/agent-loop/tests/request-recovery.spec.ts create mode 100644 packages/llm/llm/src/adapter-failure.ts diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index b9292aa80e..e4ed315e5b 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -32,14 +32,22 @@ sequenceDiagram LLM-->>Driver: StreamChunk* Driver->>Session: assistant/chunk* Session-->>SDK: session/event assistant/chunk* + alt final adapter or terminal in-band request failure + Driver->>Session: step/end + Driver->>Hooks: agent/request-error waterfall + Hooks-->>Driver: retry in a new step or preserve the original error + else model request succeeded Driver->>Hooks: agent/step-result waterfall Driver->>Session: assistant/message Driver->>Session: tool/call Driver->>Tools: execute through pre and post waterfalls Tools-->>Session: tool-owned events when applicable - Driver->>Session: tool/result and step/end + Driver->>Session: tool/result, post-tool context, and steering + Driver->>Hooks: agent/post-step serial checkpoint + Driver->>Session: step/end Driver->>Hooks: agent/turn-continuation waterfall Driver->>Hooks: agent/turn-stop serial terminal checkpoint + end Driver->>Session: turn/end Driver->>Persistence: session/flush parallel checkpoint Driver-->>SDK: agent/status idle diff --git a/docs/architecture.md b/docs/architecture.md index 1fa0ee377c..01988a43df 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -4,7 +4,7 @@ The **DeepSeek Harness SDK** builds agent harnesses on Cordis. The principle is ## Overview -A harness is one [Cordis](cordis-primer.md) context. Packages contribute service keys, typed events, and disposable registrations: services expose stable calls (`ctx.llm`, `ctx.tools`, `ctx.sessions`), events provide interception and notifications (`agent/request`, `tools/pre-execute`, `session/event`), and registrations install prompt sections, tools, providers, adapters, or listeners. +A harness is one [Cordis](cordis-primer.md) context. Packages add services (`ctx.llm`, `ctx.tools`, `ctx.sessions`), typed interception and notification events (`agent/request`, `tools/pre-execute`, `session/event`), and disposable registrations for prompts, tools, providers, adapters, and listeners. `packages/core/` groups the default agent flow; surrounding capabilities are equally first-class Cordis plugins. @@ -43,9 +43,9 @@ Events form the service extension API; see the exhaustive [events catalog](cordi ### Event Domains -- **Session events** are durable, replayable facts. Turn and step boundaries, user input, assistant output, tool calls, tool results, steering, compaction records, and tool-owned durable facts append to the session log and flow through `session/event`. -- **Agent events** carry the live `Agent` handle for status, diagnostics, prompt admission, call-config shaping, result validation, and continuation policy. -- **Capability events** belong to the seam that owns the action. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` let policy and adapters attach without importing the loop. +- **Session events** are durable replay facts: boundaries, messages, tools, steering, compaction, and tool-owned state flow through `session/event`. +- **Agent events** carry the live `Agent` for status, diagnostics, prompt admission, request shaping, result validation, and continuation. +- **Capability events** belong to their action owner. `tools/*`, `llm/*`, `system-prompt/*`, `fs/*`, and `subagent/*` attach policy and adapters without importing the loop. ### Interception Semantics @@ -53,9 +53,9 @@ Waterfall events behave like around-middleware: a listener delegates by calling ## Default Loop Lifecycle -The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. +The shipped loop drains work, assembles requests, streams answers, executes tools, applies continuation policy, and checkpoints state through plugin-visible calls and events. -A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +A **session** is an agent's append-only log; a **turn** drains one queued batch; a **step** is one model request and its tool executions. Quoted names below are durable events, and unquoted event names are extension points ([sequence companion](agent-lifecycle.md)). ### Turn Flow @@ -76,42 +76,50 @@ forever: assemble system prompt and tool schemas agent/session-prefix (first step) agent/pre-step - 'step/start' snapshot the derived messages (the reconstruction boundary) + 'step/start' agent/request (config only) -> log request/header -> llm/stream (frozen) + on final adapter failure or terminal in-band error/aborted finish: + 'step/end' + agent/request-error(original error, consecutive retry attempt, signal) + retry in the next numbered step or preserve the original error + otherwise: 'assistant/chunk' - agent/step-result - 'assistant/message' (transformed content, or an empty successful-call anchor if step-result rejects) - each tool call: - 'tool/call' - tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result - 'tool/result' - append post-tool context and steering - 'step/end' - agent/turn-continuation - agent/turn-stop (terminal policy) - stop unless tools or continuation policy ask for another step + agent/step-result + 'assistant/message' (transformed content, or an empty successful-call anchor if step-result rejects) + each tool call: + 'tool/call' + tools/pre-execute -> monotonic guards -> tools/execute -> tools/post-execute -> tools/result + 'tool/result' + append post-tool context and steering + agent/post-step + 'step/end' + agent/turn-continuation + agent/turn-stop (terminal policy) + stop unless tools or continuation policy ask for another step 'turn/end' checkpoint persistence and notify idle/running status ``` -The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). +Each step renders one prompt assembly. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; missing values fail the turn. `dsh-system-prompt` owns harness identity and the default persona, which an agent-scoped persona may shadow. The loop supplies `model` and `cwd` ([prompt ownership](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). -Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. +Post-tool context follows all results, preserving call/result adjacency. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering while the step signal remains open. Leftover steering becomes next-turn input. `agent/turn-stop` is terminal through close and flush: later steering is discarded, while ordinary queued prompts survive. ### Failure Boundaries -The turn is the containment boundary. A throwing listener, adapter error finish, or failed step ends the current turn with an error reason and reports live diagnostics through `agent/error`; it does not kill the driver loop. `cancel()` clears queued and steering work, aborts the active model/tool boundary when possible, and records the appropriate turn end. Disposal stops the loop, awaits quiescence, unregisters the agent, and lets service disposers drain. +The turn is the containment boundary. `LlmService` preserves and privately tags errors from final adapter selection, dispatch, and iteration. Those errors and terminal in-band error/aborted finishes close the failed step before `agent/request-error`; retry reconstructs the next numbered step from the log, while decline or failed recovery preserves the provider error. Attempts count consecutive failures and reset after success. -Every session event is turn-enclosed. Reloading a crashed session preserves the interrupted tail and closes it with a synthetic `interrupted` turn end. A failure after the durable turn has closed reports through `agent/error` only because no safe in-turn position remains. A turn ends with one `TurnEndReason` (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `rejected`, or `interrupted`); per-variant semantics are in [session.md § TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). +Prompt, middleware, result, tool, post-step, and continuation failures remain ordinary `agent/error` failures. Cancellation and disposal beat recovery. Durable undispatched tool calls receive synthetic `ABORTED` results, preventing dangling replay. `cancel()` clears queues and aborts active work; disposal awaits quiescence before unregistering. + +Every session event is turn-enclosed. Reload preserves a crashed tail and closes it with synthetic `interrupted`; post-close failures report only through `agent/error`. A turn has one `TurnEndReason` (`completed`, `aborted`, `error`, `disposed`, `max-tokens`, `rejected`, or `interrupted`), detailed in [session.md](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap). ### Agent Handles -`ctx.agents` owns live agents and returns an `AgentHandle { agent, dispose() }`. `Agent` is the API other plugins drive: `send()` queues work, `steer()` injects mid-turn content, `inject()` appends context and opens a one-shot injection turn when idle, `cancel()` is the public stop primitive, and `whenIdle()` observes quiescence. The caller fiber and concrete factory provider structurally co-own programmatic lifecycles; a consumer handle is the only non-structural teardown capability, and every owner reaches the same awaited disposer. +`ctx.agents` owns live agents and returns `AgentHandle { agent, dispose() }`. Plugins use `send()`, `steer()`, `inject()`, `cancel()`, and `whenIdle()`. The caller fiber and factory provider structurally co-own programmatic lifecycles; the consumer handle is the sole non-structural teardown capability, and all owners share one awaited disposer. ### Agent Scope -Every live agent owns a scoped `agent.ctx`. Its registrations shadow same-named globals, receive only that agent's dispatches, and unwind with the agent. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. The [semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md) defines typed resolvers that derive carrier checks from merged `Events` signatures and `scopeTarget`, eliminating the handwritten event table. See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md); subagent composition controls are documented [separately](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). +Each agent owns `agent.ctx`; its registrations shadow globals, receive only that agent's dispatches, and unwind on disposal. `CreateAgentOptions.setup(agentCtx)` composes it before publication. Typed resolvers derive carrier checks from merged events and `scopeTarget` ([semantic gates](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md), [agent scope](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md), [subagent controls](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md)). ## State @@ -152,7 +160,7 @@ New behavior should attach to a documented extension point; changing the shipped | Add command execution | implement and register a `ctx.bash` backend | | Add filesystem access or policy | implement a `ctx.fs` provider or listen on `fs/*` policy events | | Confine spawned processes | a `ctx.sandbox` backend; consumers wrap their argv before spawning | -| Intercept prompts, requests, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` waterfall; use serial `agent/turn-stop` for a monotonic terminal stop | +| Intercept prompts, requests, model completion/failure, tool use, or continuation | listen on the relevant `agent/*` or `tools/*` event; use serial `agent/turn-stop` for a monotonic terminal stop | | Add a session-stable request prefix outside history | compose it on `agent/session-prefix`, once per loop instance; logged on the request header | | Add UI or editor integration | drive `ctx.agents` and render from `session/event` | | Add durable session state | add a `SessionEventMap` member and render/replay from the log | diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 5408a63720..7ce58b6140 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:139`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:145`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:148`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:154`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,19 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:283`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:314`](../../packages/core/agent/src/types.ts) + +### `agent/post-step` — serial + +Awaited serial checkpoint after the response, tool results, injected context, and steering are durable but before `step/end`. + +```ts cordis-catalog +'agent/post-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void +``` + +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent/src/types.ts:267`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -59,7 +71,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:208`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -71,7 +83,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:218`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -83,7 +95,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:167`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:173`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -95,7 +107,19 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:230`](../../packages/core/agent/src/types.ts) + +### `agent/request-error` — waterfall + +Recover a model-request failure after its failed step has closed. `retry` opens a new numbered step; `fail` preserves the original request error. Call `next()` to delegate to the next recovery listener or the default. + +```ts cordis-catalog +'agent/request-error'(this: Scoped, agent: Agent, turn: number, step: number, error: RequestError, retryAttempt: number, signal: AbortSignal, next: () => Promise): Promise +``` + +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent/src/types.ts:281`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -107,7 +131,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:245`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -119,7 +143,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:180`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:186`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -131,7 +155,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:157`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:163`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -143,7 +167,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:256`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -155,7 +179,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:260`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:291`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -167,7 +191,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:270`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:301`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -233,7 +257,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:39`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:41`](../../packages/llm/llm/src/index.ts) ## `session/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 150cd35f7f..990a2bc1bc 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -127,7 +127,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:77`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 36d007eb38..1f8dca8abc 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -381,6 +381,20 @@ type ContinuationDecision = | { action: 'continue'; reason?: HookContext } ``` +`agent/request-error` receives the original `RequestError`, whose optional provider-neutral `code` supports stable routing without message parsing: + +```ts type-equiv +type RequestError = Error & { code?: string } +``` + +It returns a `RequestErrorDecision`; `retry` opens a new numbered step after the recovery listener's durable mutation, while `fail` preserves that error: + +```ts type-equiv +type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } +``` + +`agent/post-step` is the awaited successful-step checkpoint after assistant output, tool results, buffered context, and steering are durable. Its signature is `(agent, turn, step, signal)`; replayable facts remain in the session log rather than a transient payload. + `agent/turn-stop` returns the stop-only `ContinuationStop` subset or `undefined`. The loop calls this serial checkpoint after folding the ordinary decision, its reason, and pending steering; a stop is terminal and discards pending steering. ```ts type-equiv diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index fff329310a..32174f0d03 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -26,6 +26,7 @@ Every adapter MUST obey these, and every consumer may rely on them: - **`usage` before `finish`, nothing after `finish`.** Defer both to the provider's end-of-stream marker so a trailing usage-only chunk can't violate the ordering. - **Tool-call `arguments` stay raw JSON strings end-to-end.** Partial fragments stream via `argumentsDelta`; a provider that hands back parsed objects re-stringifies at `block-end`. - **Two sanctioned error paths.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted'}` (provider in-band errors, for adapters that can't throw mid-stream). Consumers must handle *both*. The agent loop translates a finish-error/aborted into a turn error — it never logs a normal completed assistant message for a failed step. +- **Context overflow has one canonical code.** Both DeepSeek adapters classify explicit provider detail through `isContextWindowExceededError()` and surface `CONTEXT_WINDOW_EXCEEDED`, whether the failure arrives as a thrown HTTP `LlmError` or an in-band finish error. Consumers route on the code, never provider text. - **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below) - the `User-Agent` baseline - and prove it with a wire-level test (mock server asserting the received header, or the library's header hook for a library-backed adapter). This contract is why two adapters exist as a deliberate pair: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (the same endpoint through `@earendil-works/pi-ai`). Two independent internals over one contract is what pinned the protocol down — the library-backed adapter can't throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not. @@ -44,7 +45,7 @@ interface AppIdentity { ## `TokenUsage` -Per-call token accounting. Counts are **disjoint**: `inputTokens` is uncached input only; cached input is reported separately, and billed input is the sum of the three. Adapters whose providers fold cache hits into a single prompt total (DeepSeek's `prompt_tokens`) subtract them back out. +Per-call token accounting. Counts are **disjoint**: `inputTokens` is uncached input only; cached input is reported separately, and billed input is the sum of the three. Adapters whose providers fold cache hits into a single prompt total (DeepSeek's `prompt_tokens`) subtract them back out. `reasoningTokens`, when present, is informational detail already included in `outputTokens`; totals must not add it again. ```ts type-equiv interface TokenUsage { diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index e095aa4b7e..e6872669de 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,24 +7,26 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:145`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:154`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:314`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:267`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:208`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:218`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:173`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:230`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:281`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:245`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:186`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:163`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:256`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:291`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:301`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:51`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | -| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | +| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:41`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | | `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5e4f5f0b69..7aafb3ce8a 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -280,6 +280,12 @@ export const EVENT_API: readonly EventApiEntry[] = [ signature: '\'agent/error\'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void', summary: 'A step or turn errored.', }, + { + name: 'agent/post-step', + mode: 'serial', + signature: '\'agent/post-step\'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void', + summary: 'Awaited serial checkpoint after the response, tool results, injected context, and steering are durable but before `step/end`.', + }, { name: 'agent/pre-step', mode: 'serial', @@ -304,6 +310,12 @@ export const EVENT_API: readonly EventApiEntry[] = [ signature: '\'agent/request\'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise', summary: 'Replace the frozen call configuration.', }, + { + name: 'agent/request-error', + mode: 'waterfall', + signature: '\'agent/request-error\'(this: Scoped, agent: Agent, turn: number, step: number, error: RequestError, retryAttempt: number, signal: AbortSignal, next: () => Promise): Promise', + summary: 'Recover a model-request failure after its failed step has closed.', + }, { name: 'agent/session-prefix', mode: 'waterfall', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 803a35fdc5..864ff95e8c 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -52,7 +52,7 @@ The driver owns one agent for its lifetime. It records turn, step, request, stre Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. -Plugin failure ends the current turn, not the loop. Cancellation clears pending work and aborts the current step without leaking to the next prompt. Terminal continuation stops remain authoritative through turn close and durability flush. +Plugin failure ends the current turn, not the loop. Only final adapter dispatch/iteration failures and terminal in-band error or aborted finishes enter `agent/request-error`; middleware, result processing, tools, and `agent/post-step` remain ordinary turn failures. Recovery observes a closed failed step, and a retry rebuilds the request from the durable log in a new numbered step. Cancellation clears pending work and aborts the current step without leaking to the next prompt; model-requested calls that were already durable receive synthetic aborted results when cancellation prevents dispatch. Terminal continuation stops remain authoritative through turn close and durability flush. ### What belongs to plugins diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 41c5d60646..e749018f55 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -7,37 +7,42 @@ import type { Context } from 'cordis' import type { FinishReason, GenerateOptions, LlmCallConfig, Message, TokenUsage } from '@deepseek-ai/dsh-llm' -import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' +import { BlockAssembler, HarnessError, deepFreeze, isLlmAdapterFailure } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' -import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' +import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision, RequestError, RequestErrorDecision } from '@deepseek-ai/dsh-agent' import { canonicalHeader } from '@deepseek-ai/dsh-session' import type { Session, TurnEndReason, TurnTrigger } from '@deepseek-ai/dsh-session' import { createTransmissionLog, recordRequestHeader } from './request-log.ts' import type { TransmissionLog } from './request-log.ts' import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' -import type {} from '@deepseek-ai/dsh-tools' +import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools' import type { ReactLoopAgent } from './agent.ts' import type { Inbox } from './inbox.ts' -/** An Error with an optional machine-readable code (e.g., from LlmError or a throwing plugin). */ -type CodedError = Error & { code?: string } - /** Normalize thrown values while preserving an existing error code. */ -function toError(error: unknown): CodedError { +function toError(error: unknown): RequestError { return error instanceof Error ? error : new HarnessError(String(error), 'UNKNOWN', { cause: error }) } +/** Distinguishes a terminal failure finish from failures in later step processing. */ +class TerminalModelRequestFailure extends Error { + constructor(readonly requestError: RequestError) { + super(requestError.message, { cause: requestError }) + this.name = 'TerminalModelRequestFailure' + } +} + /** Convert terminal failure finishes into step errors; unknown extensible finishes remain successful. */ -function finishError(finish: FinishReason): CodedError | undefined { +function finishError(finish: FinishReason): RequestError | undefined { switch (finish.kind) { case 'error': { - const error: CodedError = new Error(finish.message) + const error: RequestError = new Error(finish.message) if (finish.code !== undefined) error.code = finish.code return error } case 'aborted': { - const error: CodedError = new Error('model stream aborted') + const error: RequestError = new Error('model stream aborted') error.code = 'ABORTED' return error } @@ -51,10 +56,19 @@ function finishError(finish: FinishReason): CodedError | undefined { * Build the `{ message, code? }` part of an error payload, omitting the * `code` key entirely when absent (exactOptionalPropertyTypes-correct). */ -function errorData(err: CodedError): { message: string; code?: string } { +function errorData(err: RequestError): { message: string; code?: string } { return { message: err.message, ...typeof err.code === 'string' ? { code: err.code } : {} } } +/** Build the durable result for a model-requested call skipped after cancellation. */ +function skippedToolResult(): ToolExecutionResult { + return { + content: [{ type: 'text', text: 'Error: tool call skipped because the step was aborted before execution' }], + isError: true, + error: { name: 'AbortError', code: 'ABORTED' }, + } +} + /** Map a successful max-token finish onto the turn reason; other successful finishes add nothing. */ function stepFinishReason(finish: FinishReason): TurnEndReason | undefined { switch (finish.kind) { @@ -168,6 +182,7 @@ async function runTurn( let reason: TurnEndReason = { kind: 'completed' } let step = 0 + let requestRetryAttempt = 0 let stepOpen = false let errorReported = false let terminalStopped = false @@ -180,7 +195,7 @@ async function runTurn( } // Record the durable turn failure once and contain the live error notification. - const failTurn = (err: CodedError): void => { + const failTurn = (err: RequestError): void => { if (errorReported) return errorReported = true reason = { kind: 'error', step, ...errorData(err) } @@ -322,14 +337,65 @@ async function runTurn( break } - let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error } + let stepOutcome: + | { hadToolCalls: boolean; finish: FinishReason } + | { requestError: RequestError } + | { error: RequestError } try { stepOutcome = await runStep( ctx, events, agent, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) } catch (error: unknown) { - stepOutcome = { error: toError(error) } - } finally { + if (isLlmAdapterFailure(error)) { + stepOutcome = { requestError: error } + } else if (error instanceof TerminalModelRequestFailure) { + stepOutcome = { requestError: error.requestError } + } else { + stepOutcome = { error: toError(error) } + } + } + + if ('requestError' in stepOutcome) { + // Recovery observes a balanced failed step and the original provider + // error while the failed step's signal remains the active owner. + closeStep() + if (handle.isDisposed() || abort.signal.aborted) { + handle.setAbort(undefined) + reason = handle.isDisposed() + ? { kind: 'disposed' } + : { kind: 'aborted', reason: String(abort.signal.reason) } + break + } + + const defaultDecision: RequestErrorDecision = { action: 'fail' } + let recoveryDecision: RequestErrorDecision = defaultDecision + try { + recoveryDecision = await events.waterfall( + 'agent/request-error', turn, step, stepOutcome.requestError, + requestRetryAttempt, abort.signal, + () => Promise.resolve(defaultDecision), + ) + } catch (recoveryError: unknown) { + ctx.logger.warn( + `agent "${agent.id}": request recovery failed at turn ${turn}, step ${step}: ${toError(recoveryError).message}`, + ) + } handle.setAbort(undefined) + + // Cancellation and disposal always win over either a recovery decision + // or a recovery-listener failure. + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition + if (handle.isDisposed() || abort.signal.aborted) { + reason = handle.isDisposed() + ? { kind: 'disposed' } + : { kind: 'aborted', reason: String(abort.signal.reason) } + break + } + if (recoveryDecision.action === 'retry') { + requestRetryAttempt += 1 + continue + } + failTurn(stepOutcome.requestError) + break } if ('error' in stepOutcome) { @@ -337,7 +403,9 @@ async function runTurn( // runLoop re-enqueues it as a queued message, so an abort-then-steer // starts a fresh turn instead of being silently consumed. closeStep() + handle.setAbort(undefined) const { error } = stepOutcome + /* v8 ignore next -- narrow race: disposal while non-request step work throws. */ if (handle.isDisposed()) { reason = { kind: 'disposed' } } else if (abort.signal.aborted) { @@ -349,6 +417,8 @@ async function runTurn( break } + requestRetryAttempt = 0 + // Preserve max-token completion unless a later disposal, abort, or error wins. const stepReason = stepFinishReason(stepOutcome.finish) if (stepReason) reason = stepReason @@ -356,7 +426,38 @@ async function runTurn( // Steering that arrived during streaming/tool execution. const steered = drainSteering(agent, handle.inbox, turn) + try { + await events.serial('agent/post-step', turn, step, abort.signal) + } catch (error: unknown) { + stepOutcome = { error: toError(error) } + } + + if ('error' in stepOutcome) { + closeStep() + handle.setAbort(undefined) + /* v8 ignore next -- narrow race: disposal while a post-step listener throws. */ + if (handle.isDisposed()) { + reason = { kind: 'disposed' } + } else if (abort.signal.aborted) { + /* v8 ignore next -- signal.reason always set by cancellation or disposal. */ + reason = { kind: 'aborted', reason: String(abort.signal.reason ?? 'aborted') } + } else { + failTurn(stepOutcome.error) + } + break + } + + if (handle.isDisposed() || abort.signal.aborted) { + reason = handle.isDisposed() + ? { kind: 'disposed' } + : { kind: 'aborted', reason: String(abort.signal.reason) } + closeStep() + handle.setAbort(undefined) + break + } + closeStep() + handle.setAbort(undefined) const defaultDecision: ContinuationDecision = { action: stepOutcome.hadToolCalls || steered ? 'continue' : 'stop' } let decision: ContinuationDecision @@ -523,7 +624,7 @@ async function runStep( // Normalize failure finish chunks into the same path as thrown stream errors. const stepError = finishError(assembler.finish) - if (stepError) throw stepError + if (stepError) throw new TerminalModelRequestFailure(stepError) if (assembler.finish.kind === 'max-tokens') { let message: Message = withoutToolCalls(assembler.message()) @@ -553,25 +654,30 @@ async function runStep( const toolCalls = message.content.filter(block => block.type === 'tool-call') // Buffer context until all results are appended to preserve call/result adjacency. const pendingContext: HookContext[] = [] + let aborted = signal.aborted for (const call of toolCalls) { - /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) const callEvent = session.append('tool/call', { turn, step, callId: call.id, name: call.name, arguments: call.arguments }) - let parsedArguments: unknown - try { - parsedArguments = call.arguments ? JSON.parse(call.arguments) : {} - } catch { - parsedArguments = call.arguments + let result: ToolExecutionResult + if (aborted || signal.aborted) { + aborted = true + result = skippedToolResult() + } else { + let parsedArguments: unknown + try { + parsedArguments = call.arguments ? JSON.parse(call.arguments) : {} + } catch { + parsedArguments = call.arguments + } + // TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned; + // see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md. + result = await ctx.tools.execute({ + callId: call.id, + name: call.name, + arguments: parsedArguments, + agent, + signal, + }) } - // TODO(pre-tool-input-rewrite): Keep logged history and live presentation aligned; - // see docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md. - const result = await ctx.tools.execute({ - callId: call.id, - name: call.name, - arguments: parsedArguments, - agent, - signal, - }) session.append('tool/result', { turn, step, // Correlation comes from the immutable execution input; the result does @@ -584,13 +690,12 @@ async function runStep( ...result.meta !== undefined ? { meta: result.meta } : {}, }, { surfaceOp: 'append', sourceEventSeqs: [callEvent.seq] }) if (result.additionalContext) pendingContext.push(result.additionalContext) - // The signal may flip while the tool is awaited. - /* v8 ignore start -- signal.reason default unreachable: cancel()/disposal always set it */ - // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - /* v8 ignore stop */ + if (signal.aborted) aborted = true } + /* v8 ignore next -- signal.reason always set by cancellation or disposal. */ + if (aborted) throw new Error(String(signal.reason ?? 'aborted')) + // Append buffered context after the complete result batch. for (const context of pendingContext) { agent.inject(context.content, { source: context.source }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index cad830e827..80284b64b5 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -12,10 +12,10 @@ import { Context } from 'cordis' import LlmService, { type Message } from '@deepseek-ai/dsh-llm' import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' -import ToolRegistry from '@deepseek-ai/dsh-tools' +import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' -import { MockAdapter, textResponse } from './mock-adapter.ts' +import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' async function harness(adapter: MockAdapter) { const ctx = new Context() @@ -139,6 +139,59 @@ describe('Agent.cancel()', () => { expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled' }]) }) + it('cancel from an assistant/message observer skips execution but balances replay', async () => { + const adapter = new MockAdapter([ + toolCallResponse('c1', 'danger', {}), + textResponse('recovered after cancellation'), + ]) + const ctx = await harness(adapter) + let executions = 0 + ctx.tools.register(defineTool({ + name: 'danger', + description: 'must not run after cancellation', + parameters: {}, + async execute() { + executions += 1 + return [{ type: 'text', text: 'ran' }] + }, + })) + const agent = ctx.agentLoop.create(AgentId('cancel-after-assistant-message'), { model: 'mock' }) + const dispose = ctx.on('session/event', (session, event) => { + if (session === agent.session && event.type === 'assistant/message') { + agent.cancel('cancelled after assistant message') + } + }) + + const reasons: TurnEndReason[] = [] + ctx.on('session/event', (_session, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + dispose() + + expect(executions).toBe(0) + expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled after assistant message' }]) + const call = agent.session.events.find(event => event.type === 'tool/call') + const result = agent.session.events.find(event => event.type === 'tool/result') + expect(call?.type === 'tool/call' ? call.data.callId : undefined).toBe('c1') + expect(result?.type === 'tool/result' ? result.data : undefined).toMatchObject({ + callId: 'c1', + isError: true, + error: { name: 'AbortError', code: 'ABORTED' }, + }) + + send(agent, 'continue safely') + await waitForIdle(ctx, agent) + const replayedResult = adapter.requests[1]!.messages + .flatMap(message => message.content) + .find(block => block.type === 'tool-result') + expect(replayedResult).toMatchObject({ toolCallId: 'c1', isError: true }) + expect(reasons).toEqual([ + { kind: 'aborted', reason: 'cancelled after assistant message' }, + { kind: 'completed' }, + ]) + }) + it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 3907434395..6ca06fc096 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -204,6 +204,16 @@ describe('abort during tool execution ends the turn', () => { expect(executed).toEqual(['aborter']) // second tool never ran expect(adapter.requests).toHaveLength(1) // no follow-up model call expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }]) + const calls = agent.session.events.filter(event => event.type === 'tool/call') + const results = agent.session.events.filter(event => event.type === 'tool/result') + expect(calls.map(event => event.data.callId)).toEqual([CallId('c1'), CallId('c2')]) + expect(results).toHaveLength(2) + expect(results[0]!.data).toMatchObject({ callId: CallId('c1'), isError: false }) + expect(results[1]!.data).toMatchObject({ + callId: CallId('c2'), + isError: true, + error: { name: 'AbortError', code: 'ABORTED' }, + }) }) }) diff --git a/packages/core/agent-loop/tests/request-recovery.spec.ts b/packages/core/agent-loop/tests/request-recovery.spec.ts new file mode 100644 index 0000000000..003c678be0 --- /dev/null +++ b/packages/core/agent-loop/tests/request-recovery.spec.ts @@ -0,0 +1,442 @@ +/** + * Agent-loop coverage for the successful post-step checkpoint and model-request + * recovery. These tests keep the recovery boundary narrower than the whole + * step and pin retry reconstruction, numbering, cancellation, and identity. + */ + +import { describe, expect, it, vi } from 'vitest' +import { Context } from 'cordis' +import LlmService, { + CallId, + CONTEXT_WINDOW_EXCEEDED_CODE, + LlmAdapter, + LlmError, +} from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import SessionStore from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' +import type { PostToolDecision } from '@deepseek-ai/dsh-tools' +import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' +import { maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' + +class FailureScriptAdapter extends LlmAdapter { + requests: GenerateOptions[] = [] + + constructor(private readonly entries: (Error | StreamChunk[])[]) { + super() + } + + async * stream(options: GenerateOptions): AsyncIterable { + this.requests.push(options) + const entry = this.entries.shift() + if (entry === undefined) throw new Error('failure script exhausted') + if (entry instanceof Error) throw entry + yield* entry + } +} + +class IteratorConstructionFailureAdapter extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + throw new LlmError('iterator construction failed', 'ITERATOR_CONSTRUCTION') + }, + } + } +} + +class SynchronousDispatchFailureAdapter extends LlmAdapter { + constructor(private readonly error: Error) { + super() + } + + stream(_options: GenerateOptions): AsyncIterable { + throw this.error + } +} + +class IteratorResultGetterFailureAdapter extends LlmAdapter { + constructor( + private readonly field: 'done' | 'value', + private readonly error: Error, + ) { + super() + } + + stream(_options: GenerateOptions): AsyncIterable { + const result = this.field === 'done' ? {} : { done: false } + Object.defineProperty(result, this.field, { get: () => { throw this.error } }) + return { + [Symbol.asyncIterator](): AsyncIterator { + return { next: () => Promise.resolve(result as unknown as IteratorResult) } + }, + } + } +} + +const streamListenerFailureCases: readonly [string, (ctx: Context) => void][] = [ + ['synchronous listener throw', (ctx) => { + ctx.on('llm/stream', () => { throw new Error('synchronous stream listener failed') }) + }], + ['invalid listener iterable', (ctx) => { + ctx.on('llm/stream', () => ({}) as AsyncIterable) + }], + ['listener wrapper iteration failure', (ctx) => { + ctx.on('llm/stream', (_options, next) => (async function * () { + for await (const chunk of next()) { + yield chunk + throw new Error('stream listener wrapper failed') + } + })()) + }], +] + +async function harness(adapter?: LlmAdapter): Promise { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + if (adapter) ctx.llm.registerAdapter(['mock'], adapter) + return ctx +} + +function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { + return new Promise((resolve) => { + const dispose = ctx.on('agent/status', (subject, status) => { + if (subject === agent && status === 'idle') { + dispose() + resolve() + } + }) + }) +} + +function send(agent: ReactLoopAgent): void { + agent.send([{ type: 'text', text: 'go' }]) +} + +function contextError(message = 'context too large'): LlmError { + return new LlmError(message, CONTEXT_WINDOW_EXCEEDED_CODE, 400) +} + +describe('agent post-step and request-error lifecycle', () => { + it('fires post-step after results, buffered context, and steering but before step/end', async () => { + const twoCalls: StreamChunk[] = [ + { type: 'block-start', index: 0, blockType: 'tool-call' }, + { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('call-1'), name: 'work', arguments: '{}' } }, + { type: 'block-start', index: 1, blockType: 'tool-call' }, + { type: 'block-end', index: 1, block: { type: 'tool-call', id: CallId('call-2'), name: 'work', arguments: '{}' } }, + { type: 'usage', usage: { inputTokens: 10, outputTokens: 5 } }, + { type: 'finish', reason: { kind: 'tool-calls' } }, + ] + const adapter = new FailureScriptAdapter([twoCalls, textResponse('done')]) + const ctx = await harness(adapter) + ctx.tools.register(defineTool({ + name: 'work', + description: 'do work', + parameters: {}, + async execute(_args, exec) { + if (exec.callId === CallId('call-2')) { + exec.agent?.steer([{ type: 'text', text: 'steered' }], { source: { kind: 'plugin', plugin: 'test' } }) + } + return [{ type: 'text', text: 'worked' }] + }, + })) + ctx.on('tools/post-execute', async (exec, _result): Promise => ({ + kind: 'accept', + additionalContext: { + content: [{ type: 'text', text: `context for ${exec.callId}` }], + source: { kind: 'plugin', plugin: 'test' }, + }, + })) + const agent = ctx.agentLoop.create(AgentId('post-step-order'), { model: 'mock' }) + const order: string[] = [] + ctx.on('session/event', (_session, event) => { + if ( + event.type === 'assistant/message' || event.type === 'tool/call' + || event.type === 'tool/result' || event.type === 'context/message' + || event.type === 'steering/message' || event.type === 'step/end' + ) { + if (!('step' in event.data) || event.data.step === 1) order.push(event.type) + } + }) + ctx.on('agent/post-step', (subject, turn, step, signal) => { + if (subject !== agent || step !== 1) return + expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: false }) + subject.inject([{ type: 'text', text: 'listener mutation' }], { source: { kind: 'plugin', plugin: 'post-step' } }) + order.push('agent/post-step') + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(order).toEqual([ + 'assistant/message', + 'tool/call', + 'tool/result', + 'tool/call', + 'tool/result', + 'context/message', + 'context/message', + 'steering/message', + 'context/message', + 'agent/post-step', + 'step/end', + ]) + }) + + it('fires post-step for max-tokens and lets cancellation override that success', async () => { + const adapter = new FailureScriptAdapter([maxTokensResponse('partial')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('cancel-post-step-max-tokens'), { model: 'mock' }) + let entered!: () => void + const postStepEntered = new Promise((resolve) => { entered = resolve }) + ctx.on('agent/post-step', async (_agent, turn, step, signal) => { + expect({ turn, step }).toEqual({ turn: 1, step: 1 }) + entered() + await new Promise((resolve) => { + signal.addEventListener('abort', () => { resolve() }, { once: true }) + }) + }) + + send(agent) + const idle = waitForIdle(ctx, agent) + await postStepEntered + agent.cancel('cancelled during max-tokens post-step') + await idle + + expect(agent.session.events.find(event => event.type === 'assistant/message')).toMatchObject({ + data: { usage: { inputTokens: 10, outputTokens: 7 } }, + }) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'aborted', reason: 'cancelled during max-tokens post-step' } }, + }) + }) + + it.each([ + ['thrown', contextError()], + ['in-band', [{ type: 'finish', reason: { kind: 'error', message: 'too large', code: CONTEXT_WINDOW_EXCEEDED_CODE } }] satisfies StreamChunk[]], + ] as const)('recovers a %s request failure in a new reconstructable step', async (_style, failure) => { + const adapter = new FailureScriptAdapter([failure, textResponse('recovered')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId(`recover-${_style}`), { model: 'mock' }) + const attempts: number[] = [] + ctx.on('agent/request-error', async (subject, turn, step, error, attempt) => { + expect(subject).toBe(agent) + expect({ turn, step, code: error.code }).toEqual({ turn: 1, step: 1, code: CONTEXT_WINDOW_EXCEEDED_CODE }) + attempts.push(attempt) + subject.session.append('context/message', { + content: [{ type: 'text', text: 'RECOVERY SURFACE MUTATION' }], + source: { kind: 'plugin', plugin: 'test-recovery' }, + }, { surfaceOp: 'append' }) + return { action: 'retry' } + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(attempts).toEqual([0]) + expect(adapter.requests).toHaveLength(2) + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('RECOVERY SURFACE MUTATION') + const starts = agent.session.events.filter(event => event.type === 'step/start') + const ends = agent.session.events.filter(event => event.type === 'step/end') + expect(starts.map(event => event.data.step)).toEqual([1, 2]) + expect(ends.map(event => event.data.step)).toEqual([1, 2]) + const recovery = agent.session.events.find(event => event.type === 'context/message')! + expect(ends[0]!.seq).toBeLessThan(recovery.seq) + expect(recovery.seq).toBeLessThan(starts[1]!.seq) + }) + + it.each(streamListenerFailureCases)('does not offer %s to request recovery', async (_name, install) => { + const ctx = await harness(new FailureScriptAdapter([textResponse('unused')])) + const agent = ctx.agentLoop.create(AgentId(`stream-plugin-${_name.replaceAll(' ', '-')}`), { model: 'mock' }) + let recoveries = 0 + install(ctx) + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => { + recoveries += 1 + return next() + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(recoveries).toBe(0) + expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } }) + }) + + it.each(['prompt-submit', 'prompt-assembly', 'pre-step', 'request'] as const)( + 'does not offer %s middleware failures to request recovery', + async (boundary) => { + const adapter = new FailureScriptAdapter([textResponse('unused')]) + const ctx = await harness(adapter) + if (boundary === 'prompt-submit') { + ctx.on('agent/prompt-submit', () => { throw new Error('prompt submit failed') }) + } else if (boundary === 'prompt-assembly') { + ctx.on('system-prompt/assemble', () => { throw new Error('prompt assembly failed') }) + } else if (boundary === 'pre-step') { + ctx.on('agent/pre-step', () => { throw new Error('pre-step failed') }) + } else { + ctx.on('agent/request', () => { throw new Error('request middleware failed') }) + } + const agent = ctx.agentLoop.create(AgentId(`${boundary}-not-recoverable`), { model: 'mock' }) + let recoveries = 0 + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => { + recoveries += 1 + return next() + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(recoveries).toBe(0) + expect(adapter.requests).toHaveLength(0) + expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } }) + }, + ) + + it('does not offer result, tool, or post-step plugin failures to request recovery', async () => { + for (const failure of ['result', 'tool', 'post-step'] as const) { + const adapter = new FailureScriptAdapter([ + failure === 'tool' ? toolCallResponse(`call-${failure}`, 'work', {}) : textResponse('done'), + ]) + const ctx = await harness(adapter) + if (failure === 'result') ctx.on('agent/step-result', () => { throw new Error('result failed') }) + if (failure === 'post-step') ctx.on('agent/post-step', () => { throw new Error('post-step failed') }) + if (failure === 'tool') { + vi.spyOn(ctx.tools, 'execute').mockRejectedValue(new Error('tool service failed')) + } + const agent = ctx.agentLoop.create(AgentId(`${failure}-not-recoverable`), { model: 'mock' }) + let recoveries = 0 + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => { + recoveries += 1 + return next() + }) + send(agent) + await waitForIdle(ctx, agent) + expect(recoveries, failure).toBe(0) + } + }) + + it.each([ + ['synchronous dispatch', (error: Error) => new SynchronousDispatchFailureAdapter(error)], + ['done getter', (error: Error) => new IteratorResultGetterFailureAdapter('done', error)], + ['value getter', (error: Error) => new IteratorResultGetterFailureAdapter('value', error)], + ] as const)('preserves original Error identity for adapter %s', async (_name, makeAdapter) => { + const original = contextError(`${_name} overflow`) + const ctx = await harness(makeAdapter(original)) + const agent = ctx.agentLoop.create(AgentId(`identity-${_name.replaceAll(' ', '-')}`), { model: 'mock' }) + let seen: Error | undefined + ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => { + seen = error + return next() + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(seen).toBe(original) + }) + + it('classifies iterator construction and explicit NO_ADAPTER as model-request failures', async () => { + for (const scenario of ['iterator', 'no-adapter'] as const) { + const ctx = scenario === 'iterator' ? await harness(new IteratorConstructionFailureAdapter()) : await harness() + const agent = ctx.agentLoop.create(AgentId(`request-boundary-${scenario}`), { model: 'mock' }) + let seen = '' + ctx.on('agent/request-error', async (_agent, _turn, _step, error, _attempt, _signal, next) => { + seen = error.code ?? '' + return next() + }) + send(agent) + await waitForIdle(ctx, agent) + expect(seen).toBe(scenario === 'iterator' ? 'ITERATOR_CONSTRUCTION' : 'NO_ADAPTER') + } + }) + + it('tracks consecutive retry attempts and resets after a successful request', async () => { + const capped = new FailureScriptAdapter([contextError('first overflow'), contextError('second overflow')]) + const cappedCtx = await harness(capped) + const cappedAgent = cappedCtx.agentLoop.create(AgentId('retry-cap'), { model: 'mock' }) + const cappedAttempts: number[] = [] + cappedCtx.on('agent/request-error', async (_agent, _turn, _step, _error, attempt, _signal, next) => { + cappedAttempts.push(attempt) + return attempt < 1 ? { action: 'retry' } : next() + }) + send(cappedAgent) + await waitForIdle(cappedCtx, cappedAgent) + expect(cappedAttempts).toEqual([0, 1]) + + const reset = new FailureScriptAdapter([ + contextError('first overflow'), + toolCallResponse('retry-reset-call', 'work', {}), + contextError('later overflow'), + ]) + const resetCtx = await harness(reset) + resetCtx.tools.register(defineTool({ + name: 'work', + description: 'continue', + parameters: {}, + async execute() { return [{ type: 'text', text: 'worked' }] }, + })) + const resetAgent = resetCtx.agentLoop.create(AgentId('retry-reset'), { model: 'mock' }) + const resetAttempts: { step: number; attempt: number }[] = [] + resetCtx.on('agent/request-error', async (_agent, _turn, step, _error, attempt, _signal, next) => { + resetAttempts.push({ step, attempt }) + return resetAttempts.length === 1 ? { action: 'retry' } : next() + }) + send(resetAgent) + await waitForIdle(resetCtx, resetAgent) + expect(resetAttempts).toEqual([{ step: 1, attempt: 0 }, { step: 3, attempt: 0 }]) + }) + + it('preserves the original provider error when recovery throws', async () => { + const adapter = new FailureScriptAdapter([contextError('original overflow')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('recovery-throws'), { model: 'mock' }) + ctx.on('agent/request-error', () => { throw new Error('recovery exploded') }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'error', message: 'original overflow', code: CONTEXT_WINDOW_EXCEEDED_CODE } }, + }) + }) + + it.each(['cancel', 'dispose'] as const)('keeps %s live through request recovery', async (action) => { + const adapter = new FailureScriptAdapter([contextError()]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId(`${action}-recovery`), { model: 'mock' }) + let entered!: () => void + const recoveryEntered = new Promise((resolve) => { entered = resolve }) + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, signal) => { + entered() + await new Promise((resolve) => { + signal.addEventListener('abort', () => { resolve() }, { once: true }) + }) + return { action: 'retry' } + }) + + send(agent) + const idle = waitForIdle(ctx, agent) + await recoveryEntered + if (action === 'cancel') { + agent.cancel('cancelled during recovery') + await idle + } else { + await ctx.fiber.dispose() + } + + expect(adapter.requests).toHaveLength(1) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: action === 'cancel' ? { kind: 'aborted', reason: 'cancelled during recovery' } : { kind: 'disposed' } }, + }) + }) +}) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 5639f30daf..d37851a681 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -31,7 +31,7 @@ The loop plugin registers `AgentFactory`, keeping consumers independent of its c `agent/created` runs after setup and both registry entries; the following `agent/session-start` is the first supported startup injection point. `agent/disposed` means the exact entry left the registry. The loop quiesces its driver first; directly registered custom agents own any stronger ordering. -Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` is a serial surface-mutation checkpoint, while `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). +Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: a retry opens a new numbered step after the failed step closes. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). Turn and step boundaries and the model token stream are durable `session/event` facts rather than mirrored `agent/*` notifications. Consumers read `turn/*`, `step/*`, and `assistant/chunk` from the session feed; tool policy and outcome observation belong to the complete pipeline documented by [`dsh-tools`](../tools/README.md). diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 3aad65a70e..1eda0df2d7 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -70,6 +70,12 @@ export type ContinuationDecision = | { action: 'stop' } | { action: 'continue'; reason?: HookContext } +/** Failed-request recovery decision; `retry` opens another numbered step while listeners delegate by calling `next()`. */ +export type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } + +/** Model-request failure with an optional machine-routable provider code. */ +export type RequestError = Error & { code?: string } + /** * The terminal subset of {@link ContinuationDecision}. A listener on * `agent/turn-stop` returns this to make the already-composed continuation @@ -248,6 +254,31 @@ declare module 'cordis' { * @mode waterfall */ 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise + /** + * Awaited serial checkpoint after the response, tool results, injected + * context, and steering are durable but before `step/end`. + * @param agent - the agent that completed the step. + * @param turn - the open turn number. + * @param step - the completed step number. + * @param signal - the turn abort signal. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode serial + */ + 'agent/post-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void + /** + * Recover a model-request failure after its failed step has closed. `retry` + * opens a new numbered step; `fail` preserves the original request error. + * Call `next()` to delegate to the next recovery listener or the default. + * @param agent - the agent whose request failed. + * @param turn - the open turn number. + * @param step - the failed step number. + * @param error - the original model-request failure. + * @param retryAttempt - zero-based number of prior recovery retries. + * @param signal - the turn abort signal. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ + 'agent/request-error'(this: Scoped, agent: Agent, turn: number, step: number, error: RequestError, retryAttempt: number, signal: AbortSignal, next: () => Promise): Promise /** * Override whether the turn continues. The default continues after tool * calls or steering and stops otherwise; a continue reason becomes steering. diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 1270ad40a5..bd4228165b 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -36,7 +36,7 @@ Every request carries the shared attribution header from dsh-llm's `attributionH ## Errors -Non-2xx responses throw `LlmError` with stable codes: `AUTH` (401/403), `RATE_LIMIT` (429), `INVALID_REQUEST` (400), `SERVER` (5xx), `HTTP_` otherwise. Protocol violations throw `STREAM_CLOSED` (no `[DONE]`) or `MALFORMED_RESPONSE` (bad JSON payload). Unknown wire `finish_reason`s (e.g. `content_filter`, `insufficient_system_resource`) become `finish {kind: 'error', code: }` chunks. +Non-2xx responses throw `LlmError` with stable codes: `AUTH` (401/403), `RATE_LIMIT` (429), `CONTEXT_WINDOW_EXCEEDED` (a 400 whose provider code, type, or message identifies context overflow), `INVALID_REQUEST` (other 400s), `SERVER` (5xx), `HTTP_` otherwise. Protocol violations throw `STREAM_CLOSED` (no `[DONE]`) or `MALFORMED_RESPONSE` (bad JSON payload). Unknown wire `finish_reason`s (e.g. `content_filter`, `insufficient_system_resource`) become `finish {kind: 'error', code: }` chunks. ## Testing diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..113cb6f25e 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -5,7 +5,7 @@ * @module dsh-llm-deepseek/adapter */ -import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' +import { attributionHeaders, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { serializeRequest } from './serialize.ts' import type { RequestDefaults } from './serialize.ts' @@ -26,12 +26,17 @@ export interface DeepSeekAdapterOptions { /** * Map an HTTP status to a stable LlmError code. * @param status - status of a non-2xx provider response. - * @returns `AUTH` (401/403), `RATE_LIMIT` (429), `INVALID_REQUEST` (400), `SERVER` (5xx), or `HTTP_` for anything else. + * @param error - parsed provider error body, when available. + * @returns the normalized harness error code. */ -export function httpErrorCode(status: number): string { +export function httpErrorCode(status: number, error?: WireError['error']): string { if (status === 401 || status === 403) return 'AUTH' if (status === 429) return 'RATE_LIMIT' - if (status === 400) return 'INVALID_REQUEST' + if (status === 400) { + const detail = [error?.code, error?.type, error?.message].filter(Boolean).join(' ') + if (isContextWindowExceededError(detail)) return CONTEXT_WINDOW_EXCEEDED_CODE + return 'INVALID_REQUEST' + } if (status >= 500) return 'SERVER' return `HTTP_${status}` } @@ -67,16 +72,17 @@ export class DeepSeekAdapter extends LlmAdapter { }) if (!response.ok) { - const code = httpErrorCode(response.status) let message = `DeepSeek API error (HTTP ${response.status})` + let providerError: WireError['error'] try { const parsed = await response.json() as WireError - if (parsed.error?.message) message = parsed.error.message + providerError = parsed.error + if (providerError?.message) message = providerError.message } catch { - // Only swallow error-body parsing: status and code are already captured, - // so malformed gateway JSON must not mask the actionable HTTP failure. + // Only swallow error-body parsing: the HTTP status still identifies the + // failure, so malformed gateway JSON must not mask it. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, httpErrorCode(response.status, providerError), response.status) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..6cca0dde17 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -2,7 +2,7 @@ import { createServer } from 'node:http' import type { IncomingMessage, Server, ServerResponse } from 'node:http' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' +import LlmService, { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek' import { assemble } from './assemble.ts' @@ -173,6 +173,32 @@ describe('DeepSeekAdapter against a mock server', () => { ).resolves.toBe(status) }) + it('classifies a thrown HTTP context-window rejection with the canonical code', async () => { + const server = await mockServer([{ + kind: 'http-error', + status: 400, + body: JSON.stringify({ + error: { + message: 'This model maximum context length is 128000 tokens; your input exceeds that limit.', + type: 'invalid_request_error', + code: 'context_length_exceeded', + }, + }), + }]) + const ctx = await harness(server.url) + const code = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + .catch((error: unknown) => (error as LlmError).code) + expect(code).toBe(CONTEXT_WINDOW_EXCEEDED_CODE) + }) + + it('classifies only context-capacity HTTP 400 details as context overflow', () => { + expect(httpErrorCode(400, { message: 'request too large for model context' })) + .toBe(CONTEXT_WINDOW_EXCEEDED_CODE) + expect(httpErrorCode(400, { message: 'invalid input: temperature exceeds maximum allowed value' })) + .toBe('INVALID_REQUEST') + expect(httpErrorCode(413, { code: 'context_length_exceeded' })).toBe('HTTP_413') + }) + it('keeps the status-line message for JSON error bodies without a message', async () => { const server = await mockServer([{ kind: 'http-error', status: 500, body: '{"error":{"type":"x"}}' }]) const ctx = await harness(server.url) diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index dd1cb5b48c..6c8fc35104 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -7,7 +7,7 @@ DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](ht `@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose: - pi-ai hands tool-call `arguments` around as **parsed objects**; the harness keeps raw JSON strings. The adapter patches replay payloads back to the original raw strings before sending them, and re-stringifies parsed output tool calls at `block-end`. -- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). +- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). Context-overflow detail maps to the same canonical `CONTEXT_WINDOW_EXCEEDED` code as the hand-rolled adapter. - pi-ai folds reasoning tokens into `usage.output`; there is no separate reasoning count to map. - pi-ai's options omit some DeepSeek/OpenAI-compatible details; the adapter uses its `onPayload` hook to preserve the harness contract (`stop`, scrubbing pi-ai's own per-tool `strict` default — the hand-rolled twin sends no such field — omitted reasoning effort, raw replayed tool arguments). diff --git a/packages/llm/llm-pi-ai/src/convert.ts b/packages/llm/llm-pi-ai/src/convert.ts index 098b93edb3..88f134c8f2 100644 --- a/packages/llm/llm-pi-ai/src/convert.ts +++ b/packages/llm/llm-pi-ai/src/convert.ts @@ -8,7 +8,7 @@ * @module dsh-llm-pi-ai/convert */ -import { CallId, LlmError } from '@deepseek-ai/dsh-llm' +import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmError } from '@deepseek-ai/dsh-llm' import type { FinishReason, GenerateOptions, Message, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, @@ -165,6 +165,7 @@ export function mapUsage(usage: PiUsage): TokenUsage { function classifyPiAiError(message: string): string { if (/\b(?:401|403)\b/.test(message)) return 'AUTH' if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' + if (isContextWindowExceededError(message)) return CONTEXT_WINDOW_EXCEEDED_CODE if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' if (/\b5\d\d\b/.test(message)) return 'SERVER' return 'PI_AI_ERROR' diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 078d2a4d3b..42576f7fed 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -1,5 +1,5 @@ import { describe, expect, it } from 'vitest' -import { CallId } from '@deepseek-ai/dsh-llm' +import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai' import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' @@ -300,6 +300,18 @@ describe('mapStopReason / mapUsage', () => { .toMatchObject({ kind: 'error', code: 'RATE_LIMIT' }) expect(mapStopReason(assistant({ stopReason: 'error', errorMessage: 'HTTP 500: backend down' }))) .toMatchObject({ kind: 'error', code: 'SERVER' }) + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'HTTP 400: input exceeds the model context window limit', + }))).toMatchObject({ kind: 'error', code: CONTEXT_WINDOW_EXCEEDED_CODE }) + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'HTTP 400: request too large for model context', + }))).toMatchObject({ kind: 'error', code: CONTEXT_WINDOW_EXCEEDED_CODE }) + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'HTTP 400: invalid input: temperature exceeds maximum allowed value', + }))).toMatchObject({ kind: 'error', code: 'INVALID_REQUEST' }) }) it('maps cache fields only when nonzero', () => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 296fd0c3d3..b7be205a97 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -12,6 +12,8 @@ An adapter registry plus a single streaming call surface, interceptable via a wa - `ctx.llm.models(): string[]` — model names with a registered adapter. - `ctx.llm.stream(options: GenerateOptions): AsyncIterable` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`. +`LlmService` preserves and privately tags errors from final adapter selection, synchronous dispatch, iterator construction, and iteration. `isLlmAdapterFailure(value)` exposes that provenance without classifying `llm/stream` middleware or downstream consumer failures as provider failures, and without replacing the adapter's original coded `Error`. + ### Events | Event | Mode | Purpose | @@ -43,6 +45,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. - `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `CONTEXT_WINDOW_EXCEEDED_CODE` — the provider-neutral code both DeepSeek adapters use when a request exceeds the model context window, regardless of thrown-HTTP versus in-band finish delivery. `isContextWindowExceededError(detail)` is their shared conservative classifier for OpenAI-compatible provider detail. ### Real adapters @@ -54,7 +57,7 @@ None, as this adapter registry forwards an already assembled request without add ## Known Limitations and Deferred Work -- **No retry/caching/rate-limit layer ships** — `llm/stream` is the intended wrap seam and has no production listener, so provider 429/5xx failures surface immediately. +- **No default retry/caching/rate-limit policy ships in this service** — `llm/stream` remains the call-wrapper seam; the agent loop separately offers proven model-request failures to `agent/request-error`, whose default preserves the original failure. - **`GenerateOptions` sampling is `temperature`/`maxTokens`/`stop` only** — no `tool_choice`, `top_p`, or penalty fields; the vocabulary grows when a producer lands ([dropped inert knobs](../../../docs/rfc/implemented/simplification/2026-07-04-drop-inert-request-knobs.md)). - **Producer-gated variants stay out until produced** — `prefill`, per-tool `strict`, block `cache` hints, and the `agent` message-source variant were pruned as producerless ([RFC](../../../docs/rfc/implemented/simplification/2026-07-04-prune-producerless-vocabulary-variants.md)). - **`BlockAssembler` handles core block kinds only** — a plugin-added block type whose stream is never closed by `block-end` makes `blocks()` throw. diff --git a/packages/llm/llm/src/adapter-failure.ts b/packages/llm/llm/src/adapter-failure.ts new file mode 100644 index 0000000000..240f934c39 --- /dev/null +++ b/packages/llm/llm/src/adapter-failure.ts @@ -0,0 +1,34 @@ +/** + * Private provider-failure tagging shared by `LlmService` and its consumers. + * + * @module @deepseek-ai/dsh-llm/adapter-failure + */ + +import { HarnessError } from './error.ts' + +/** Errors proven to originate in final adapter dispatch or iteration. */ +const adapterFailures = new WeakSet() + +/** + * Preserve an adapter's Error identity while tagging its provider origin. + * @param value - arbitrary value thrown by adapter dispatch or iteration. + * @returns the original Error, or a coded Error wrapping a non-Error throw. + * @internal + */ +export function markLlmAdapterFailure(value: unknown): Error & { code?: string } { + const error = value instanceof Error + ? value as Error & { code?: string } + : new HarnessError(String(value), 'UNKNOWN', { cause: value }) + adapterFailures.add(error) + return error +} + +/** + * Whether a failure came from final adapter dispatch, iterator construction, + * or iteration rather than from an `llm/stream` waterfall listener. + * @param value - arbitrary failure caught by a model-call consumer. + * @returns true only for errors tagged at the final adapter boundary. + */ +export function isLlmAdapterFailure(value: unknown): value is Error & { code?: string } { + return value instanceof Error && adapterFailures.has(value) +} diff --git a/packages/llm/llm/src/error.ts b/packages/llm/llm/src/error.ts index c1fdbb9ffa..8c1c736492 100644 --- a/packages/llm/llm/src/error.ts +++ b/packages/llm/llm/src/error.ts @@ -21,6 +21,47 @@ export class HarnessError extends Error { } } +/** Canonical provider-neutral code for a model request rejected because its context window was exceeded. */ +export const CONTEXT_WINDOW_EXCEEDED_CODE = 'CONTEXT_WINDOW_EXCEEDED' + +/** Structured codes and plain phrases that explicitly name a context bound being exceeded. */ +const STRUCTURED_CONTEXT_OVERFLOW = new RegExp( + String.raw`(?:^|[^a-z0-9])context[\s_-](?:length|window)[\s_-]` + + String.raw`(?:exceed(?:ed|s)?|overflow(?:ed)?|limit[\s_-]exceeded)(?:$|[^a-z0-9])`, + 'i', +) + +/** Request-size wording that ties "too large" directly to model context capacity. */ +const TOO_LARGE_FOR_CONTEXT = new RegExp( + String.raw`\b(?:request|prompt|input|messages?)\s+(?:is\s+|are\s+)?` + + String.raw`too\s+(?:large|long)\s+for\s+(?:(?:this|the)\s+)?` + + String.raw`(?:model(?:'s)?\s+)?context(?:\s+window)?\b`, + 'i', +) + +/** "Exceeds" wording is safe only when its object is explicitly the model context. */ +const EXCEEDS_MODEL_CONTEXT = new RegExp( + String.raw`\b(?:input|prompt|request|messages?)\b.{0,40}` + + String.raw`\b(?:exceed(?:s|ed)?|overflows?|is\s+larger\s+than)\b.{0,40}` + + String.raw`\b(?:the\s+)?(?:model(?:'s)?\s+)?context(?:\s+(?:length|window))?\b`, + 'i', +) + +/** + * Recognize the context-overflow wording used by OpenAI-compatible providers + * and library adapters. Adapters pass all available provider code, type, and + * message text so both thrown and in-band delivery styles share one classifier. + * @param detail - provider error code/type/message text joined into one string. + * @returns true when the detail identifies a request exceeding the model context window. + */ +export function isContextWindowExceededError(detail: string): boolean { + return STRUCTURED_CONTEXT_OVERFLOW.test(detail) + || /\b(?:maximum|max)(?:\s+(?:allowed|supported))?\s+context\s+(?:length|window)\b/i.test(detail) + || TOO_LARGE_FOR_CONTEXT.test(detail) + || /\b(?:input|prompt|request)\s+(?:is\s+)?too\s+(?:long|large)\s+for\s+(?:this|the)\s+model\b/i.test(detail) + || EXCEEDS_MODEL_CONTEXT.test(detail) +} + /** * Narrow an arbitrary thrown value to a HarnessError (for `instanceof` at seams). * @param value - the caught value (`unknown` in catch clauses). diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 08f3f54c51..0b933d12a7 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -9,6 +9,7 @@ import { Context, Service } from 'cordis' import type { GenerateOptions, StreamChunk } from './types.ts' import { HarnessError } from './error.ts' +import { markLlmAdapterFailure } from './adapter-failure.ts' export * from './attribution.ts' export * from './brand.ts' @@ -18,6 +19,7 @@ export * from './types.ts' export { BlockAssembler } from './assembler.ts' export { callConfigEquals, deepFreeze } from './call-config.ts' export type { LlmCallConfig } from './call-config.ts' +export { isLlmAdapterFailure } from './adapter-failure.ts' declare module 'cordis' { interface Context { @@ -118,17 +120,65 @@ export class LlmService extends Service { return adapter } + /** + * Final adapter boundary. It tags only failures from adapter selection, + * synchronous dispatch, iterator construction, or iteration while preserving + * the original Error object. Middleware outside this generator remains + * distinguishable as plugin work. Adapter cleanup is best-effort after an + * earlier failure or downstream close and never masks the winning error. + */ + private async * adapterStream(options: GenerateOptions): AsyncGenerator { + let iterator: AsyncIterator + try { + const stream = this.adapter(options.model).stream(options) + iterator = stream[Symbol.asyncIterator]() + } catch (error: unknown) { + throw markLlmAdapterFailure(error) + } + + let completed = false + try { + while (true) { + let value: StreamChunk + try { + const item = await iterator.next() + if (item.done) { + completed = true + return + } + value = item.value + } catch (error: unknown) { + throw markLlmAdapterFailure(error) + } + // End the adapter-owned try before yielding: consumer/middleware + // failures resumed into this generator must remain untagged. + yield value + } + } finally { + if (!completed) { + try { + const close = iterator.return?.bind(iterator) + if (close) await close() + } catch { + // Lookup and invocation are both adapter-owned cleanup following an + // existing failure/downstream close; neither can replace it. + } + } + } + } + /** * Stream one model call as raw chunks (token-level deltas). Throws * `LlmError` with code `NO_ADAPTER` if no adapter is registered for - * `options.model`. Dispatches through the `llm/stream` waterfall. + * `options.model`. Dispatches through the `llm/stream` waterfall. Final + * adapter dispatch/iteration failures retain their original Error identity + * and are tagged so the agent loop can distinguish them from middleware + * failures without widening request recovery to plugin code. * @param options - the full request; `options.model` selects the adapter. * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. */ stream(options: GenerateOptions): AsyncIterable { - return this.ctx.waterfall(this, 'llm/stream', options, () => { - return this.adapter(options.model).stream(options) - }) + return this.ctx.waterfall(this, 'llm/stream', options, () => this.adapterStream(options)) } } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..8dc46529bd 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -1,6 +1,14 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import LlmService, { GenerateOptions, LlmAdapter, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' +import LlmService, { + GenerateOptions, + HarnessError, + isContextWindowExceededError, + isLlmAdapterFailure, + LlmAdapter, + LlmError, + StreamChunk, +} from '@deepseek-ai/dsh-llm' class ScriptedAdapter extends LlmAdapter { constructor(private script: StreamChunk[]) { @@ -19,6 +27,22 @@ const SCRIPT: StreamChunk[] = [ ] describe('LlmService', () => { + it('recognizes structured and model-capacity context-window overflow details', () => { + expect(isContextWindowExceededError('context_length_exceeded maximum context length')).toBe(true) + expect(isContextWindowExceededError('context-window-overflowed')).toBe(true) + expect(isContextWindowExceededError('This model maximum context length is 128000 tokens')).toBe(true) + expect(isContextWindowExceededError('input is too long for this model')).toBe(true) + expect(isContextWindowExceededError('request too large for model context')).toBe(true) + expect(isContextWindowExceededError('input exceeds the model context window limit')).toBe(true) + }) + + it('does not mistake unrelated input validation for context-window overflow', () => { + expect(isContextWindowExceededError('invalid request: malformed tool arguments')).toBe(false) + expect(isContextWindowExceededError('invalid input: temperature exceeds maximum allowed value')).toBe(false) + expect(isContextWindowExceededError('input exceeds maximum allowed value')).toBe(false) + expect(isContextWindowExceededError('context window size must be positive')).toBe(false) + }) + it('routes stream() to the registered adapter', async () => { const ctx = new Context() await ctx.plugin(LlmService) @@ -32,9 +56,177 @@ describe('LlmService', () => { it('throws NO_ADAPTER for unregistered models', async () => { const ctx = new Context() await ctx.plugin(LlmService) - await expect((async () => { + let caught: unknown + try { for await (const _ of ctx.llm.stream({ model: 'nope', messages: [] })) { /* drain */ } - })()).rejects.toThrow('no adapter registered') + } catch (error: unknown) { + caught = error + } + expect(caught).toBeInstanceOf(LlmError) + expect((caught as LlmError).code).toBe('NO_ADAPTER') + expect((caught as LlmError).message).toContain('no adapter registered') + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it.each(['done', 'value'] as const)('tags a throwing IteratorResult.%s getter without replacing its Error', async (field) => { + const original = new LlmError(`${field} getter failed`, 'RESULT_GETTER_FAILED') + const result = field === 'done' ? {} : { done: false } + Object.defineProperty(result, field, { get: () => { throw original } }) + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + return { next: () => Promise.resolve(result as unknown as IteratorResult) } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it.each(['dispatch', 'iterator'] as const)('tags synchronous adapter %s failures without replacing their Error', async (boundary) => { + const original = new LlmError(`${boundary} failed`, 'BOUNDARY_FAILED') + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + if (boundary === 'dispatch') throw original + return { [Symbol.asyncIterator]: () => { throw original } } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it('tags adapter iteration failures without replacing the original Error or cleanup outcome', async () => { + const original = new LlmError('provider failed', 'PROVIDER_FAILED') + let cleanupCalls = 0 + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + return { + next: () => Promise.reject(original), + return: () => { + cleanupCalls += 1 + return Promise.reject(new Error('cleanup failed')) + }, + } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupCalls).toBe(1) + }) + + it('contains a throwing iterator.return getter after next fails without replacing the original Error', async () => { + const original = new LlmError('provider failed', 'PROVIDER_FAILED') + let cleanupLookups = 0 + const iterator: AsyncIterator = { next: () => Promise.reject(original) } + Object.defineProperty(iterator, 'return', { + get: () => { + cleanupLookups += 1 + throw new Error('return getter failed') + }, + }) + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { [Symbol.asyncIterator]: () => iterator } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupLookups).toBe(1) + }) + + it('normalizes and tags non-Error adapter failures once', async () => { + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + // Third-party adapters can reject with arbitrary values; normalization is under test. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + return { next: () => Promise.reject('plain provider failure') } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBeInstanceOf(HarnessError) + expect(caught).toMatchObject({ code: 'UNKNOWN', cause: 'plain provider failure' }) + expect(isLlmAdapterFailure(caught)).toBe(true) + }) + + it('does not tag a failure thrown downstream while consuming adapter output', async () => { + const downstream = new Error('consumer failed') + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter(SCRIPT)) + + let caught: unknown + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) throw downstream + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(downstream) + expect(isLlmAdapterFailure(caught)).toBe(false) }) it('unregisters adapters when the owning fiber is disposed (HMR safety)', async () => { diff --git a/packages/support/invariants/src/scoped-events.generated.ts b/packages/support/invariants/src/scoped-events.generated.ts index 06cca6bf55..36d1721945 100644 --- a/packages/support/invariants/src/scoped-events.generated.ts +++ b/packages/support/invariants/src/scoped-events.generated.ts @@ -30,10 +30,12 @@ const scopedSubjectResolvers = Object.freeze({ 'agent/created': adapt<'agent/created'>(args => args[0]), 'agent/disposed': adapt<'agent/disposed'>(args => args[0]), 'agent/error': adapt<'agent/error'>(args => args[0]), + 'agent/post-step': adapt<'agent/post-step'>(args => args[0]), 'agent/pre-step': adapt<'agent/pre-step'>(args => args[0]), 'agent/prompt-submit': adapt<'agent/prompt-submit'>(args => args[0]), 'agent/queued': adapt<'agent/queued'>(args => args[0]), 'agent/request': adapt<'agent/request'>(args => args[0]), + 'agent/request-error': adapt<'agent/request-error'>(args => args[0]), 'agent/session-prefix': adapt<'agent/session-prefix'>(args => args[0]), 'agent/session-start': adapt<'agent/session-start'>(args => args[0]), 'agent/status': adapt<'agent/status'>(args => args[0]), diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 71fe28fbe0..11168ba000 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -818,14 +818,22 @@ function renderLifecycle(): string { ' LLM-->>Driver: StreamChunk*', ` Driver->>Session: ${mermaidCode('assistant/chunk')}*`, ` Session-->>SDK: ${mermaidCode('session/event')} ${mermaidCode('assistant/chunk')}*`, + ' alt final adapter or terminal in-band request failure', + ` Driver->>Session: ${mermaidCode('step/end')}`, + ` Driver->>Hooks: ${mermaidCode('agent/request-error')} waterfall`, + ' Hooks-->>Driver: retry in a new step or preserve the original error', + ' else model request succeeded', ` Driver->>Hooks: ${mermaidCode('agent/step-result')} waterfall`, ` Driver->>Session: ${mermaidCode('assistant/message')}`, ` Driver->>Session: ${mermaidCode('tool/call')}`, ' Driver->>Tools: execute through pre and post waterfalls', ' Tools-->>Session: tool-owned events when applicable', - ` Driver->>Session: ${mermaidCode('tool/result')} and ${mermaidCode('step/end')}`, + ` Driver->>Session: ${mermaidCode('tool/result')}, post-tool context, and steering`, + ` Driver->>Hooks: ${mermaidCode('agent/post-step')} serial checkpoint`, + ` Driver->>Session: ${mermaidCode('step/end')}`, ` Driver->>Hooks: ${mermaidCode('agent/turn-continuation')} waterfall`, ` Driver->>Hooks: ${mermaidCode('agent/turn-stop')} serial terminal checkpoint`, + ' end', ` Driver->>Session: ${mermaidCode('turn/end')}`, ` Driver->>Persistence: ${mermaidCode('session/flush')} parallel checkpoint`, ` Driver-->>SDK: ${mermaidCode('agent/status')} idle`, diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 54fe328389..b0cea673ad 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -14,6 +14,8 @@ { "doc": "docs/core-data-structures/core.md", "symbol": "HookContext", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "PromptDecision", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContinuationDecision", "source": "packages/core/agent/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "RequestError", "source": "packages/core/agent/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "RequestErrorDecision", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContinuationStop", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "SessionStartSource", "source": "packages/core/agent/src/types.ts" }, From 6eddf38a77d1e88c52530c64555124e1fb47788f Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 16:42:32 +0800 Subject: [PATCH 100/323] feat(acp): enable automatic compaction --- examples/acp-agent/composition.md | 3 +++ examples/acp-agent/cordis.yml | 12 ++++++++++++ 2 files changed, 15 insertions(+) diff --git a/examples/acp-agent/composition.md b/examples/acp-agent/composition.md index b93b4cb1e2..1dc297a5fc 100644 --- a/examples/acp-agent/composition.md +++ b/examples/acp-agent/composition.md @@ -27,6 +27,8 @@ flowchart LR bundle_agent_core --> spine_sessions["ctx.sessions"] bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] + plugin_acp_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] + cfg --> plugin_acp_compact_basic plugin_acp_subagent["subagent
@deepseek-ai/dsh-subagent"] cfg --> plugin_acp_subagent plugin_acp_subagent_spawn["subagent-spawn
@deepseek-ai/dsh-subagent-spawn"] @@ -59,6 +61,7 @@ flowchart LR | `approval` | `@deepseek-ai/dsh-user-approval` | | `permission` | `@deepseek-ai/dsh-permission` | | `acp-agent` | `@deepseek-ai/dsh-acp-agent` | +| `compact-basic` | `@deepseek-ai/dsh-compact-basic` | | `subagent` | `@deepseek-ai/dsh-subagent` | | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | | `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` | diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index 201feafe41..17ed222660 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -48,6 +48,18 @@ Verify your work by running the code or tests. Keep answers brief and factual. +# Summarize an older range when derived history approaches the context window. +# This leaf consumes `ctx.llm` and the app's `agent/pre-step` seam. +- id: compact-basic + name: '@deepseek-ai/dsh-compact-basic' + config: + contextWindow: 128000 + thresholdRatio: 0.8 + retainTokens: 20480 + summarizationModel: '' + maxTokens: 8192 + compactionRetries: 1 + # Expose fresh-child `spawn` and completed-prefix `fork` through separate tool # names so multi-child scenarios exercise both transports. These leaves follow # the app because it provides `ctx.agents` and `ctx.tools`. From 5ca3eab6ceb522c5a69bb198af7d71316f87a639 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 16:46:43 +0800 Subject: [PATCH 101/323] fix(acp): use 256k compaction window --- examples/acp-agent/cordis.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index 17ed222660..1e78892113 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -53,7 +53,7 @@ - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' config: - contextWindow: 128000 + contextWindow: 256000 thresholdRatio: 0.8 retainTokens: 20480 summarizationModel: '' From 12484104c89fd614a247b1a903f3c9c7821aac3d Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 16:50:44 +0800 Subject: [PATCH 102/323] feat(compact): recover context overflow (PR3 phase 2) --- docs/agent-lifecycle.md | 2 + docs/architecture.md | 2 + docs/capability-seams.md | 2 +- docs/config-catalog.md | 4 +- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/cordis-catalog/events.md | 28 +- docs/cordis-catalog/services.md | 6 +- docs/core-data-structures/compaction.md | 10 +- docs/event-producer-consumer.md | 20 +- docs/rfc/INDEX.md | 1 + .../2026-06-11-microkernel-event-taxonomy.md | 4 +- ...t-variables-and-tool-guidance-ownership.md | 4 +- .../2026-07-05-reconstructable-requests.md | 4 +- ...n-pressure-and-overflow-recovery.i18n.yaml | 6 + ...mpaction-pressure-and-overflow-recovery.md | 63 +++ ...ction-pressure-and-overflow-recovery.zh.md | 63 +++ ...07-15-replay-token-meter-service.i18n.yaml | 4 +- .../2026-07-15-replay-token-meter-service.md | 8 +- ...026-07-15-replay-token-meter-service.zh.md | 8 +- .../2026-06-18-compaction-capability-seam.md | 42 +- .../feature/2026-07-07-session-prefix.md | 8 +- examples/coding-agent/cordis.yml | 4 +- packages/compact/compact-basic/README.md | 17 +- .../compact/compact-basic/src/automatic.ts | 58 ++- packages/compact/compact-basic/src/config.ts | 3 + packages/compact/compact-basic/src/index.ts | 64 ++-- .../compact/compact-basic/src/summarizer.ts | 2 +- packages/compact/compact-basic/src/types.ts | 5 +- .../compact-basic/tests/compact-basic.spec.ts | 360 ++++++++++++++++-- .../tests/compact-loop-repro.spec.ts | 176 ++++++++- packages/compact/compact/README.md | 7 +- packages/compact/compact/src/index.ts | 22 +- .../compact/compact/tests/compact.spec.ts | 10 +- .../cordis/tool-cordis/src/api-catalog.ts | 10 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/loop.ts | 12 +- .../agent-loop/tests/interception.spec.ts | 16 +- packages/core/agent-loop/tests/loop.spec.ts | 21 +- .../agent-loop/tests/request-recovery.spec.ts | 42 ++ packages/core/agent/src/types.ts | 18 +- .../invariants/tests/invariants.spec.ts | 2 +- .../ui/user-approval/tests/approval.spec.ts | 2 +- scripts/gen-doc-graphs.ts | 4 +- scripts/type-equiv.manifest.json | 1 + 46 files changed, 913 insertions(+), 242 deletions(-) create mode 100644 docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml create mode 100644 docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md create mode 100644 docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index e4ed315e5b..c6010d4139 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -55,6 +55,8 @@ sequenceDiagram The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set. +`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Recovery compacts between the closed failed step and a fresh retry step, and returns retry only when the surface replacement generation advances; otherwise the original request error remains authoritative. + SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors. Maintenance mode: curated Mermaid sequence; exact event signatures live in the generated Cordis catalog. diff --git a/docs/architecture.md b/docs/architecture.md index 01988a43df..387327a526 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -105,6 +105,8 @@ Each step renders one prompt assembly. Plugins contribute ordered sections, tool Post-tool context follows all results, preserving call/result adjacency. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering while the step signal remains open. Leftover steering becomes next-turn input. `agent/turn-stop` is terminal through close and flush: later steering is discarded, while ordinary queued prompts survive. +When loaded, `dsh-compact-basic` consumes that post-step checkpoint for `ctx.tokenMeter` pressure under the actual routed header. It also consumes canonical context overflow at `agent/request-error`, but authorizes retry only after a tool-balanced compaction advances `surface.replaceGeneration`. The same turn signal owns both summarization paths. + ### Failure Boundaries The turn is the containment boundary. `LlmService` preserves and privately tags errors from final adapter selection, dispatch, and iteration. Those errors and terminal in-band error/aborted finishes close the failed step before `agent/request-error`; retry reconstructs the next numbered step from the log, while decline or failed recovery preserves the provider error. Attempts count consecutive failures and reset after success. diff --git a/docs/capability-seams.md b/docs/capability-seams.md index fae89bfcfb..5f93bf0433 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -203,7 +203,7 @@ flowchart LR | `ctx.permission` | `core` | [`permission`](../packages/ui/permission) | - | [`acp`](../packages/ui/acp) | - | User-facing preset table (`workspace-write`/`danger-full-access`) bundling the sandbox-mode and approval-policy knobs; a switch writes one `permission/preset` event through to both knob events. | | `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). | | `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate. | -| `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred. | +| `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend consumes post-step pressure and request-error recovery events; a model-facing compact tool remains deferred. | | `ctx.subagents` | `seam` | [`subagent`](../packages/subagent/subagent) | [`subagent-spawn`](../packages/subagent/subagent-spawn), [`subagent-fork`](../packages/subagent/subagent-fork), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-mock`](../packages/support/subagent-mock) | [`tool-subagent`](../packages/subagent/tool-subagent) | - | Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name. | | `ctx.web` | `seam` | [`web`](../packages/web/web) | [`web-search-exa`](../packages/web/web-search-exa), [`web-search-perplexity`](../packages/web/web-search-perplexity), [`web-search-deepseek`](../packages/web/web-search-deepseek), [`web-fetch-local`](../packages/web/web-fetch-local) | [`tool-web`](../packages/web/tool-web) | - | Search and fetch providers register into one ctx.web seam; tool-web owns the stable model-facing names. | | `ctx.workflows` | `seam` | [`workflow`](../packages/workflow/workflow) | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | [`tool-workflow`](../packages/workflow/tool-workflow) | - | One engine per context (bash shape, no named-provider registry); the worker-thread engine fans agent() calls out through ctx.subagents. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 22fc421f8a..886d7a63a1 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -220,7 +220,9 @@ export interface BasicCompactConfig { maxTokens?: number /** Extra attempts after the first compaction when pressure remains above threshold. Defaults to `1`. */ compactionRetries?: number - /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */ + /** Maximum retries after canonical context overflow; `0` disables recovery. Defaults to `1`. */ + maxOverflowRetries?: number + /** Enable automatic post-step pressure and overflow-recovery listeners. Defaults to `true`. */ auto?: boolean } diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index ef1d8d606f..6408aaeea1 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 40ee22b352c884d7f295c87726c54ab8e166c844 -extension-cookbook.zh.md: 4e5bc68c973649574bcb2404bea00096eb9ca41f +extension-cookbook.md: 712e4f2f1f98cabfeea1a899c111a39957d16e21 +extension-cookbook.zh.md: 494cb559cf17f13a494e6c695a661c559a0add12 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 40ee22b352..712e4f2f1f 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -102,7 +102,7 @@ Every product feature maps to a listener on a documented extension seam — the | `/loop` | on the `turn/end` session event, `send()` the next iteration; or force-continue | | Dynamic workflow | `ctx.workflows` + the worker-thread engine + the `workflow` tool; structured in-process children enforce output with scoped prompt/tool registrations, a monotonic tool guard, final `tools/result` commit (including enclosing `run_code`), and terminal `agent/turn-stop` | | Queued + steering messages | core `Agent.send()` / `Agent.steer()` | -| Context compaction (auto + manual) | the `ctx.compact` seam + a backend (`dsh-compact-basic`) on the serial `agent/pre-step` seam; auto = token-pressure check before each step; a manual trigger invokes the same `ctx.compact` routine ([compaction RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) | +| Context compaction (auto + manual) | the `ctx.compact` seam + `dsh-compact-basic`; automatic pressure runs on serial `agent/post-step`, canonical overflow recovery runs on `agent/request-error`, and manual callers use the same compact service ([compaction RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md) — the model-facing `/compact` consumer tool is deferred) | | System prompt configurability | `ctx.systemPrompt.section()` with ordering and scope-local shadowing | | AGENTS.md (root) | a section provider reading the file | | AGENTS.md (subdir, on-touch) + file-change notices | `agent.inject()` from a watcher / tool-result listener | diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 4e5bc68c97..494cb559cf 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -102,7 +102,7 @@ export function apply(ctx: Context) { | `/loop` | 在 `turn/end` 会话事件上 `send()` 下一次迭代；或强制继续 | | 动态工作流 | `ctx.workflows` + worker-thread 引擎 + `workflow` 工具；结构化的进程内子任务通过作用域化的 prompt/工具注册、单调工具守卫、最终 `tools/result` 提交（包括外层 `run_code`）和终端 `agent/turn-stop` 来强制输出 | | 排队消息 + steering（中途引导） | 核心 `Agent.send()` / `Agent.steer()` | -| 上下文压缩（context compaction）（自动 + 手动） | `ctx.compact` seam + 串行 `agent/pre-step` seam 上的后端（`dsh-compact-basic`）；自动 = 每步之前的 token 压力检查；手动触发调用同一个 `ctx.compact` 例程（[压缩 RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟） | +| 上下文压缩（context compaction）（自动 + 手动） | `ctx.compact` seam + `dsh-compact-basic`；自动压力检查运行在串行 `agent/post-step`，规范化溢出恢复运行在 `agent/request-error`，手动调用方使用同一个压缩服务（[压缩 RFC](../rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)——面向模型的 `/compact` 消费方工具已推迟） | | 系统提示词可配置性 | `ctx.systemPrompt.section()`，支持排序与作用域局部覆盖 | | AGENTS.md（根目录） | 一个读取该文件的 section provider | | AGENTS.md（子目录，按需触发）+ 文件变更通知 | 从 watcher / tool-result 监听器调用 `agent.inject()` | diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 7ce58b6140..131297b797 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:314`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:308`](../../packages/core/agent/src/types.ts) ### `agent/post-step` — serial @@ -59,19 +59,19 @@ Awaited serial checkpoint after the response, tool results, injected context, an Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:267`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:261`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial -Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step. The loop derives history once afterward, so compaction records and replacements are included without rewriting an assembled request. The prompt and prefix are the exact pressure inputs for that request, and `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. +Awaited serial checkpoint before `step/start`; appends land outside the pending step and are included when the loop derives request history. `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog -'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void +'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void ``` -Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:208`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -83,7 +83,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:218`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -107,7 +107,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:230`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts) ### `agent/request-error` — waterfall @@ -119,11 +119,11 @@ Recover a model-request failure after its failed step has closed. `retry` opens Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:281`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:275`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall -Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request and pressure accounting sees the composed prefix. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. +Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise @@ -131,7 +131,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:245`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -167,7 +167,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:256`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -179,7 +179,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:291`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -191,7 +191,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:301`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:295`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 990a2bc1bc..02705dee99 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -89,13 +89,11 @@ Source: [`packages/code-runtime/code-runtime/src/index.ts:31`](../../packages/co Abstract compaction service. Implementations own trigger policy, retention, and summarization, and may consume a separate measurement service. A successful run replaces the selected surface span with one summary node and prevents concurrent compaction of the same session. Load one implementation per context as `ctx.compact`. ```ts cordis-catalog -abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise +abstract compactIfNeeded( agent: CompactAgentContext, trigger: CompactionTrigger, signal: AbortSignal, ): Promise abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` -Types: [Message](../core-data-structures/core.md) - -Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/compact/src/index.ts) +Source: [`packages/compact/compact/src/index.ts:40`](../../packages/compact/compact/src/index.ts) ## `ctx.fs` — `FileSystem` (abstract seam) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 50a80208a9..f60d1e3e08 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -50,8 +50,14 @@ interface CompactionResult { ## The service -`CompactService` exposes `compactIfNeeded(...)` for pressure-triggered compaction, returning `null` when no compaction is needed, and `compactRegion(...)` for an explicit inclusive surface range. The pre-step caller supplies the agent, full prompt, session prefix, and abort signal; implementations must forward that signal to summarization. The seam owns no pricing API: `dsh-compact-basic` resolves the routed model through [`ctx.tokenMeter`](token-meter.md), whose model-bound handle owns estimation and replay, while the backend owns retention, event sequencing, and summarization. +Automatic callers state why policy is running; implementations may treat confirmed overflow more aggressively than ordinary pressure. -Auto-compaction runs at serial `agent/pre-step`, before the step and request derivation, so it can replace surface nodes while keeping trace events outside the step. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns the retention and failure details. +```ts type-equiv +export type CompactionTrigger = 'pressure' | 'context-overflow' +``` + +`CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: `dsh-compact-basic` resolves the durable routed model through [`ctx.tokenMeter`](token-meter.md), whose model-bound handle owns estimation and replay, while the backend owns retention, event sequencing, and summarization. + +Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Failed-request recovery runs through `agent/request-error` after the failed step closes, and authorizes a fresh numbered-step retry only when the surface replacement generation advances. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. The seam exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for those edge checks. Both validate current surface membership, reject stale or missing seqs and orphan results, and ignore a caller-retained `node.next`; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics. diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index e6872669de..1f280d74b1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -9,19 +9,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | --- | --- | --- | --- | --- | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:145`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:154`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:314`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:267`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:208`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:218`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:308`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:261`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:173`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:230`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:281`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:245`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:275`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | | `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:186`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:163`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:256`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:291`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:301`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:285`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:295`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 4f41579a5b..0a80128a4e 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -142,6 +142,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [A shared timeout/deadline primitive, with hard-kill left to each capability](implemented/architecture/2026-07-06-timeout-deadline-library.md) | 2026-07-06 | | [Tool-call timeout policy as a plugin](implemented/architecture/2026-07-07-tool-call-timeout-policy.md) | 2026-07-07 | | [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 | +| [After-call compaction pressure and context-overflow recovery](implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) | 2026-07-10 | | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | | [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 | diff --git a/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md b/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md index 8293924d37..1d10bfa479 100644 --- a/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md +++ b/docs/rfc/implemented/architecture/2026-06-11-microkernel-event-taxonomy.md @@ -10,8 +10,8 @@ The product principle is "everything is a plugin": hooks, /goal, /loop, dynamic Pure Cordis event taxonomy. The loop's extension seams are typed events with deliberate dispatch modes: -- **waterfall** (around-middleware) where plugins transform, veto, or wrap: `agent/prompt-submit`, `agent/request`, `agent/step-result`, `agent/turn-continuation`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`. -- **serial** (awaited in listener order; a bail value stops later listeners) for ordered checkpoints: every `agent/pre-step` listener runs when all abstain, while the first stop returned from `agent/turn-stop` makes the terminal decision final. +- **waterfall** (around-middleware) where plugins transform, veto, recover, or wrap: `agent/prompt-submit`, `agent/request`, `agent/request-error`, `agent/step-result`, `agent/turn-continuation`, `tools/pre-execute`, `tools/execute`, `tools/post-execute`, `llm/stream`, `system-prompt/assemble`. +- **serial** (awaited in listener order; a bail value stops later listeners) for ordered checkpoints: every `agent/pre-step` and `agent/post-step` listener runs when all abstain, while the first stop returned from `agent/turn-stop` makes the terminal decision final. - **parallel** (awaited fan-out) where every listener must get an independent chance: the `session/flush` durability checkpoint. - **emit** (synchronous fire-and-forget) for notifications: turn/step boundaries, stream chunks, lifecycle, errors, and the contained immutable `tools/result` observation. diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 854807c109..e40759a182 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -30,7 +30,7 @@ Plugins register `{{name}}` values through `ctx.systemPrompt.variable(name, prov ### Persona as the order-0 section -`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and `agent/pre-step` therefore measures the exact prompt used for compaction. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`. +`dsh-system-prompt` owns `harness:identity` at order `-100` and the configured `deployment:persona` at order 0, so both survive a replacement loop. Prompt rendering has one path, `renderPrompt(assembly)`, and the routed request header therefore records the exact prompt later replayed by `ctx.tokenMeter` for compaction pressure. An agent-scoped `deployment:persona` shadows the global default and lets subagent providers install a persona before publication. The conventional order bands are identity `-100`, persona `0`, and tool guidance `100–199`. ### Tool guidance ownership @@ -43,7 +43,7 @@ Per-tool semantics and selection guidance live in tool descriptions. Prompt sect ## Alternatives considered - **The loop composes an identity line itself** — hardcodes model-facing prose in the one package that must stay thin ("plugins, not loop changes"), and outside the section pipeline it would be a second composition path. (The identity DOES ship as a code literal — but as an ordinary section registered by `dsh-system-prompt`, whose `system-prompt/assemble` waterfall remains the escape valve for a deployment that must drop it.) -- **Inject the model name via the `agent/request` waterfall** — prompt text composed in two places, and `agent/pre-step`'s `fullSystemPrompt` would omit it, so compaction would measure a prompt that is not what the model sees. +- **Inject the model name via the `agent/request` waterfall** — prompt text would be composed in two places and the earlier rendered persona could disagree with the final routed header. The request plugin that owns late routing must also own any earlier prompt claim about that model. - **Hand-write the model name in each persona** — duplicates the `model:` key one line above and silently lies after a config edit; the exact disease this RFC cures. - **Lenient interpolation (leave unknown refs verbatim, or substitute empty)** — a typo ships `{{modle}}` (or a hole) to the model and nobody notices until transcript review. - **Per-instance subagent wording in config** — returns model-facing prose to every deployment × instance, the P2 disease again. **Keying wording off the provider NAME** — `providerName` is itself config, so a renamed provider silently gets the wrong words. diff --git a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md index d95a709ada..34bae2a2f5 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md +++ b/docs/rfc/implemented/architecture/2026-07-05-reconstructable-requests.md @@ -22,9 +22,9 @@ Prefix-cache stability is corollary #1, not the headline: an append-only log pro `EpochHeader` records the request's non-history state: call config, rendered system prompt, tool schemas, and session prefix, with empty values canonicalized to absence. `request/header` writes a full initial, resume, or fallback snapshot. `request/header-delta` encodes system changes by common-prefix/suffix line trim, tools by name-keyed additions/removals/changes, and config or prefix by full replacement. `foldRequestHeader`, `diffHeader`, and `applyHeaderDelta` are the pure codec. Each loop instance writes a snapshot on its first request to anchor process boundaries. Deltas are only an optimization: the writer verifies round-trip equality and falls back to a full snapshot for unrepresentable changes such as pure tool reordering. -Each step rebuilds prompt assembly. On the instance's first step, `agent/session-prefix` extends a frozen empty seed with request-only opener messages; the result is frozen and cached for that loop instance. `agent/pre-step` then receives the composed prefix before messages are snapshotted immediately ahead of `step/start`. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. `agent/request` may replace only that frozen config seed, while model-visible content enters through logged channels. The loop records the owed header event—the prefix's only durable home—builds `GenerateOptions` from prefix, snapshot, and header, and deep-freezes it while leaving `AbortSignal` live. Per-instance state is only the cached prefix and whether its anchoring snapshot has been written. +Each step rebuilds prompt assembly. On the instance's first step, `agent/session-prefix` extends a frozen empty seed with request-only opener messages; the result is frozen and cached for that loop instance before the generic `agent/pre-step` checkpoint and boundary snapshot. The first call config starts from explicit `AgentOptions`, preserving fork overrides and resume reconfiguration; later calls start from the folded header. `agent/request` may replace only that frozen config seed, while model-visible content enters through logged channels. The loop records the owed header event—the prefix's only durable home—builds `GenerateOptions` from prefix, snapshot, and header, and deep-freezes it while leaving `AbortSignal` live. Per-instance state is only the cached prefix and whether its anchoring snapshot has been written. -**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step` is the seam for content needed by the current request. Header reconstruction folds through the step's own `request/header*` event, or carries the prior fold when no new header is written. +**`step/start` is the reconstruction boundary.** A step derives messages from events before that sequence. Injection after the snapshot joins the next request, and reentrant appends are rejected during event publication. `agent/pre-step(agent, turn, step, signal)` remains the generic seam for content needed by the current request. Header reconstruction folds through the step's own `request/header*` event, or carries the prior fold when no new header is written. **Enforcement.** In development, `dsh-invariants` independently rebuilds each loop request through a fresh `Session`, so the live cache cannot vouch for itself, then compares messages and folded header fields at `llm/stream`. Loop requests are identified by their frozen shape and session id; direct one-shots are excluded. Correctness depends on sequence-bounded reconstruction rather than listener order. A with-key e2e requires positive cache-read tokens after the first request; per-step usage is the production signal, and a header change or compaction appears as a cache-read drop on the next step. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml new file mode 100644 index 0000000000..dbb9c76bbf --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 92167dc7d444a3620abfbaab721260ed1c828db9 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: fe3b6617b25a58ef2c1c311df088f9c805fe9ef4 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md new file mode 100644 index 0000000000..92167dc7d4 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -0,0 +1,63 @@ +# RFC: After-call compaction pressure and context-overflow recovery + +Status: implemented + +English | [中文](2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md) + +## Problem + +Automatic compaction originally ran at `agent/pre-step` and received an assembled prompt and session prefix. That boundary was necessarily provisional: `agent/request` could still route another model or change call configuration, tool schemas were not frozen with the compaction inputs, and the next assistant output, tool results, buffered context, and steering did not exist yet. Expanding the pre-step signature could move the stale boundary but could not make it exact. + +Successful calls are not the only pressure signal. A provider can reject a request for exceeding its context window before it returns usage, and some successful calls omit usage. The system therefore needs replayable post-call pressure plus a narrow failure-recovery path that preserves the provider error whenever compaction cannot prove useful progress. + +## Decision + +### Successful pressure moves to a durable post-step checkpoint + +`agent/pre-step` is narrowed to `(agent, turn, step, signal)`. It remains a generic serial checkpoint before `step/start`, but it carries no compaction-only prompt or prefix fields. + +The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after assistant output, every dispatched or synthetic tool result, post-tool context, and steering are durable, but before `step/end`. This placement gives pressure policy the complete successful-call state without splitting an assistant tool call from its result. A listener failure is an ordinary turn failure; it never enters model-request recovery. + +`dsh-compact-basic` resolves the exact latest routed model from the durable request header and asks that model's `ctx.tokenMeter` handle to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work. A durable unknown model throws `TOKEN_METER_MODEL_UNCONFIGURED` with its exact name and fails the otherwise-successful turn; operational selection or summarization failures warn and continue with full history. + +### Request recovery is limited to the final model boundary + +`RequestError`, `RequestErrorDecision`, and the `agent/request-error` waterfall represent failures after the final adapter has been selected. Private `WeakSet` tagging preserves the original thrown error identity across dispatch, iterator construction, and iteration. Terminal in-band `error` or `aborted` finishes enter the same path. Prompt assembly, request middleware, request logging, result processing, tools, post-step listeners, and cleanup remain ordinary failures. + +The failed step closes before recovery runs. A retry opens the next numbered step and rebuilds the request from the durable log; consecutive recovery attempts reset only after a successful provider request. Both DeepSeek adapters normalize recognized provider context-limit failures to `CONTEXT_WINDOW_EXCEEDED`. + +If cancellation lands after assistant tool calls are durable but before all calls dispatch, the loop records a synthetic aborted `tool/result` for every undispatched call before following the normal abort path. The surface therefore never retains orphaned durable tool calls merely because cancellation won the race. + +### CompactService exposes intent, not token accounting + +`CompactService.compactIfNeeded(agent, trigger, signal)` accepts `trigger: 'pressure' | 'context-overflow'`. The interface gains no estimation methods or token types; `ctx.tokenMeter` remains the reusable accounting owner. + +For `pressure`, compact-basic applies the selected meter profile's threshold and retained-tail policy, compares scalar and surface `logRevision`, and uses the same meter for range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. + +For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It chooses the maximal tool-balanced head range while leaving the newest indivisible unit, then attempts exactly one shrinking compaction under the same signal. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` only when compaction succeeds and the generation increases. A backend returning a result without replacement cannot authorize retry. + +`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, missing or unknown routed models, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. + +The default summarizer still resolves explicit configuration, then the latest logged route, then agent options. Because direct `llm/stream` middleware may reroute that auxiliary call, `compact/summary.model` records the final mutable `GenerateOptions.model` observed after dispatch rather than the pre-waterfall candidate. + +## Testing + +Lifecycle tests pin post-step ordering after durable tool/context/steering work, content-less and max-token successes, final-adapter dispatch/iterator/in-band boundaries, retry numbering, attempt reset, cancellation, disposal, synthetic tool results, and original error identity. + +Compact tests pin low-friction defaults, actual routed-model selection, exact unknown-model behavior, below-threshold forced overflow, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. + +## Alternatives considered + +- **Keep provisional pre-step pressure and add more arguments** — rejected because later routing and request mutation remain outside any earlier snapshot, while generic lifecycle becomes coupled to one plugin. +- **Retry the same numbered step** — rejected because recovery appends durable events after the failed boundary. A new step preserves balanced nesting and reconstructability. +- **Retry whenever `compactIfNeeded` returns a result** — rejected because a custom backend can report success without changing model-visible state. `replaceGeneration` is the authoritative proof. +- **Let compact-basic parse provider wording** — rejected because classification belongs at adapters and must cover both thrown and in-band delivery. +- **Use a universal model/window fallback during recovery** — rejected because destructive policy under the wrong context capacity can hide the original provider failure. Unknown durable routes delegate unchanged. + +## Consequences + +Pressure now describes the actual completed routed request, including durable tool results and request-only prefix fields, rather than a provisional next-call guess. Canonical overflow supplies the backstop when no successful usage anchor exists. Recovery is bounded, cancellation-owned, and monotonic: it retries only after a visible surface generation change. + +The cost is one additional serial checkpoint on successful steps and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window or split one indivisible oversized message/tool unit. + +This RFC supersedes only the pre-step automatic-trigger portion of the [compaction capability-seam RFC](../feature/2026-06-18-compaction-capability-seam.md). The service split, standalone token meter, balanced range contract, log-recorded lock, summary replacement, and sole `summarize()` subclass hook remain unchanged. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md new file mode 100644 index 0000000000..fe3b6617b2 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -0,0 +1,63 @@ +# RFC：调用后压缩压力与上下文溢出恢复 + +Status: implemented + +[English](2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md) | 中文 + +## 问题 + +自动压缩最初运行在 `agent/pre-step`，并接收已装配提示词与会话前缀。这个边界必然只是临时状态：`agent/request` 仍可能路由到另一个模型或改变调用配置，工具 schema 没有与压缩输入在同一位置冻结，而下一次 assistant 输出、工具结果、缓冲上下文与 steering 此时还不存在。继续扩充 pre-step 签名只能移动陈旧边界，无法让它变得精确。 + +成功调用也不是唯一的压力信号。提供方可能在返回 usage 之前就因上下文窗口超限拒绝请求，一些成功调用也不提供 usage。因此，系统需要可重放的调用后压力，以及一条狭窄的失败恢复路径；当压缩无法证明取得有效进展时，必须保留原始提供方错误。 + +## 决策 + +### 成功压力移动到持久 post-step 检查点 + +`agent/pre-step` 收窄为 `(agent, turn, step, signal)`。它仍是 `step/start` 之前的通用串行检查点，但不再携带压缩专用的提示词或前缀字段。 + +循环在 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都持久化之后、`step/end` 之前，触发等待式串行 `agent/post-step(agent, turn, step, signal)`。该位置让压力策略看到完整的成功调用状态，同时不会拆开 assistant 工具调用与其结果。监听器失败属于普通 turn 失败，绝不会进入模型请求恢复。 + +`dsh-compact-basic` 从持久请求头解析精确的最新实际路由模型，并让该模型的 `ctx.tokenMeter` handle 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作。持久记录的未知模型会携带精确名称抛出 `TOKEN_METER_MODEL_UNCONFIGURED`，使原本成功的 turn 失败；操作性的选择或摘要失败则警告并继续使用完整历史。 + +### 请求恢复只覆盖最终模型边界 + +`RequestError`、`RequestErrorDecision` 与 `agent/request-error` waterfall 表示最终适配器已经选定之后的失败。私有 `WeakSet` 标记在分发、异步迭代器构造与迭代过程中保留原始抛出错误的身份。终止性的带内 `error` 或 `aborted` finish 进入同一路径。提示词装配、请求中间件、请求日志、结果处理、工具、post-step 监听器与清理仍属于普通失败。 + +恢复运行前，失败 step 已经关闭。重试会打开下一个编号 step，并从持久日志重建请求；连续恢复尝试计数只在提供方请求成功后重置。两个 DeepSeek 适配器都把识别出的提供方上下文限制错误规范化为 `CONTEXT_WINDOW_EXCEEDED`。 + +如果取消发生在 assistant 工具调用已经持久化之后、所有调用完成分发之前，循环会为每个尚未分发的调用记录合成的 aborted `tool/result`，随后进入正常中止路径。因此，表层不会仅因取消赢得竞态而留下孤立的持久工具调用。 + +### CompactService 暴露意图，而不拥有 token 核算 + +`CompactService.compactIfNeeded(agent, trigger, signal)` 接收 `trigger: 'pressure' | 'context-overflow'`。接口不增加估算方法或 token 类型；`ctx.tokenMeter` 继续作为可复用的核算所有者。 + +对于 `pressure`，compact-basic 应用所选 meter profile 的阈值与保留尾部策略，比较标量和表层的 `logRevision`，并用同一个 meter 完成范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 + +对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它在保留最新不可分割单元的同时，选择最大的工具配对平衡头部范围，并在同一 signal 下只尝试一次缩小压缩。自动监听器先记录 `session.surface.replaceGeneration`，只有压缩成功且 generation 增加时才返回 `{ action: 'retry' }`。后端若只返回结果但没有替换表层，不能授权重试。 + +`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失或未知路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 + +默认摘要器仍依次解析显式配置、最近记录的路由与 agent options。因为直接 `llm/stream` 中间件可以重新路由该辅助调用，`compact/summary.model` 记录分发后最终可变的 `GenerateOptions.model`，而不是 waterfall 之前的候选值。 + +## 测试 + +生命周期测试固定 post-step 位于持久工具、上下文与 steering 工作之后，覆盖无内容与达到 token 上限的成功、最终适配器分发/迭代器/带内边界、重试编号、尝试重置、取消、销毁、合成工具结果与原始错误身份。 + +压缩测试固定低摩擦默认值、实际路由模型选择、精确未知模型行为、低于阈值的强制溢出、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 + +## 考虑过的替代方案 + +- **保留临时 pre-step 压力并增加更多参数**——不予采纳，因为后续路由与请求变换仍在更早快照之外，同时通用生命周期会耦合到单个插件。 +- **重试相同编号的 step**——不予采纳，因为恢复会在失败边界之后追加持久事件。新 step 保持边界配对与可重建性。 +- **只要 `compactIfNeeded` 返回结果就重试**——不予采纳，因为自定义后端可能报告成功却没有改变模型可见状态。`replaceGeneration` 才是权威证明。 +- **让 compact-basic 解析提供方措辞**——不予采纳，因为分类属于适配器，而且必须同时覆盖抛出式与带内交付。 +- **恢复时使用通用模型/窗口回退**——不予采纳，因为基于错误上下文容量执行破坏性策略可能掩盖原始提供方失败。未知持久路由会原样委托。 + +## 后果 + +压力现在描述实际完成的路由请求，包括持久工具结果与仅请求前缀字段，而不是对下一次调用的临时猜测。当成功 usage 锚点不存在时，规范化溢出提供兜底路径。恢复有上限、受取消所有，并保持单调：只有模型可见的表层 generation 变化后才重试。 + +代价是成功 step 增加一个串行检查点，并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况，也不能拆分单个不可分割的超大消息或工具单元。 + +本 RFC 只取代[压缩能力接缝 RFC](../feature/2026-06-18-compaction-capability-seam.md) 中的 pre-step 自动触发部分。服务拆分、独立 token meter、平衡范围契约、日志记录锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。 diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml index 99c6301f25..dbb2a582f0 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-replay-token-meter-service.md: 4452c151e122c4a4ad72e3f0bc2616cd2fa28b9d -2026-07-15-replay-token-meter-service.zh.md: 23edc11ffd19b9cfaeb794f3608e9ced4e7dbb7b +2026-07-15-replay-token-meter-service.md: 079eb58f38a69a40b3f47a23e72d159f7025d285 +2026-07-15-replay-token-meter-service.zh.md: 7c3c9ce47ad81029b03747ddb17b87dc55def8e7 diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md index 4452c151e1..079eb58f38 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.md @@ -32,13 +32,13 @@ Usage sums the disjoint input, cache-read, cache-write, and output buckets. Reas `dsh-compact-basic` requires `ctx.tokenMeter`; `CompactService` gains no token methods or types. The backend is factored into configuration, automatic triggering, region transaction, and summarizer modules, while `summarize()` remains its sole subclass hook. The conversation model's meter consistently prices pressure, retention, shadowed content, provenance, and non-shrinking-summary rejection. -Every metered model receives a compact policy with defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra compaction attempt, and automatic triggering enabled. Per-model compact overrides merge `thresholdRatio` and `retainTokens`; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. +Every metered model receives a compact policy with defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, summarization model `''`, maximum summary output `8192`, one extra pressure-compaction attempt, one context-overflow retry, and automatic triggering enabled. Per-model compact overrides merge `thresholdRatio` and `retainTokens`; retention must remain below the resulting threshold. Empty summarization model resolves the latest logged routed model, then `AgentOptions.model`. -The pre-step trigger measures a provisional envelope: the current prompt and prefix override logged values, while the latest logged header supplies model, tools, and other call config. A model-less router-only agent skips that provisional check because `agent/request` can route later; naming an unknown model remains an error. +Automatic pressure runs at `agent/post-step` and measures the canonical durable envelope under the model actually selected by `agent/request`. A headerless session has no completed routed request to assess and produces no work; a durable unknown routed model remains an exact typed error. Canonical overflow recovery uses the same meter for forced range selection, and retries only after a proven surface replacement. ## Testing -Unit coverage pins profiles, field-wise overrides, custom and unknown models, envelope invalidation, model switching, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, routing fallback, retention, convergence, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. +Unit coverage pins profiles, field-wise overrides, custom and unknown models, envelope invalidation, model switching, usage and missing-usage paths, seeded append/replace replay, signed deltas, provenance modes, malformed boundaries, immutable snapshots, listener ordering, reload, compact defaults, actual routing, retention, convergence, forced overflow, and transaction rollback. A real Loader/Include YAML fixture loads the exact zero-config token-meter and compact-basic package names in dependency order. ## Alternatives considered @@ -54,4 +54,4 @@ Unit coverage pins profiles, field-wise overrides, custom and unknown models, en - Defaults make the bundled DeepSeek composition usable with two zero-config plugin entries, while custom models must state the one fact that cannot be guessed safely: context capacity. - Heuristic density and provider usage remain estimates of provider behavior. Maintainers must update built-in profiles and overflow wording as models evolve. - Measurements fail loudly on malformed durable boundaries. This turns corrupted replay into a named integration failure instead of silently drifting pressure. -- The pre-step compact integration can skip a router-only first check and can miss tool or routing changes applied later in request middleware. +- Post-step pressure reads the exact logged routing/tools/prefix boundary; provider overflow classification remains the adapter-maintained backstop for requests rejected before a successful usage anchor. diff --git a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md index 23edc11ffd..7c3c9ce47a 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-replay-token-meter-service.zh.md @@ -32,13 +32,13 @@ Usage 会对互不重叠的输入、缓存读取、缓存写入与输出 bucket `dsh-compact-basic` 要求 `ctx.tokenMeter`；`CompactService` 不增加 token 方法或类型。后端拆分为配置、自动触发、区域事务与摘要器模块，而 `summarize()` 仍是唯一的子类 hook。会话模型的 meter 一致用于压力、保留、被遮蔽内容、来源以及非缩小摘要拒绝。 -每个已计量模型都会获得默认压缩策略：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压缩尝试，以及启用自动触发。逐模型压缩覆盖按字段合并 `thresholdRatio` 与 `retainTokens`；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 +每个已计量模型都会获得默认压缩策略：阈值比例 `0.8`、保留尾部 `floor(contextWindow × 0.16)`、摘要模型 `''`、摘要最大输出 `8192`、一次额外压力压缩尝试、一次上下文溢出重试，以及启用自动触发。逐模型压缩覆盖按字段合并 `thresholdRatio` 与 `retainTokens`；保留值必须小于最终阈值。空摘要模型先解析最近记录的实际路由模型，再使用 `AgentOptions.model`。 -pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日志值，最近记录的请求头提供模型、工具及其他调用配置。没有模型的纯路由 agent 会跳过该临时检查，因为 `agent/request` 仍可稍后路由；显式命名未知模型仍然报错。 +自动压力检查运行在 `agent/post-step`，并使用 `agent/request` 实际选择的模型计量规范持久信封。没有请求头的会话尚无已完成的路由请求可供判断，因此不执行工作；持久记录的未知路由模型仍抛出带精确名称的类型化错误。规范化溢出恢复使用同一 meter 强制选择范围，并且只有在表层替换得到证明后才重试。 ## 测试 -单元覆盖固定 profile、按字段覆盖、自定义与未知模型、信封失效、模型切换、有无 usage 的路径、种子追加/替换重放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、路由回退、保留、收敛与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic package 名称。 +单元覆盖固定 profile、按字段覆盖、自定义与未知模型、信封失效、模型切换、有无 usage 的路径、种子追加/替换重放、有符号增量、来源模式、畸形边界、不可变快照、监听器顺序、重载、压缩默认值、实际路由、保留、收敛、强制溢出与事务回滚。真实 Loader/Include YAML fixture 按依赖顺序加载精确的零配置 token-meter 与 compact-basic package 名称。 ## 考虑过的替代方案 @@ -54,4 +54,4 @@ pre-step 触发器计量临时请求信封：当前提示词与前缀覆盖日 - 默认值让内置 DeepSeek 组合只需两个零配置插件条目即可使用，而自定义模型必须声明唯一不能安全猜测的事实：上下文容量。 - 启发式密度与提供方 usage 仍然只是提供方行为的估计。随着模型演进，维护者必须更新内置 profile 与溢出措辞。 - 遇到畸形持久边界时，计量会明确失败。这会把损坏的重放转化为具名集成错误，而不是让压力静默漂移。 -- pre-step 压缩集成可能跳过纯路由的首次检查，也可能错过请求中间件稍后应用的工具或路由变化。 +- post-step 压力检查读取精确记录的路由、工具与前缀边界；对于在成功 usage 锚点出现前就被拒绝的请求，提供方溢出分类仍是由适配器维护的兜底路径。 diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 42b93f1225..7714db14b7 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -17,7 +17,7 @@ Two forces shape the design. First, compaction policy and reusable token measure Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capability-seams.md), compaction ships as separate packages so the contract, the algorithm, and (later) the consumer surface evolve independently: 1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, and the `compact/*` session events. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. -2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, and the `agent/pre-step` auto-compaction listener. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. +2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. 3. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -30,27 +30,27 @@ This is not a coupling smell — it is the contract's domain. The "only cordis" An earlier draft put the full algorithm (the retention walk, token-summing, text extraction) as concrete methods on the interface. That recouples the contract to one strategy: a backend that wants a different retention policy or event sequence would have to fight inherited concrete code. Making both core methods abstract puts every *how* decision in the backend and keeps the interface a statement of *what*. Token measurement is not a compaction hook at all; the standalone service lets multiple consumers share one model/session replay fold. -`compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` takes required pressure inputs and cancellation. The session comes from the agent. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers and requires `session === agent.session`; implementations reject mismatch before model resolution, lock acquisition, summarization, or log mutation. The pre-step integration resolves a provisional model from the latest logged request header, then `AgentOptions.model`; a model-less router-only first step skips pressure because `agent/request` can route later. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options. +`compactIfNeeded(agent, trigger, signal)` takes an explicit `'pressure' | 'context-overflow'` trigger and cancellation. It resolves only the latest durable routed request model; no header means no work, while a named unconfigured model produces the token meter's exact typed error. `compactRegion(session, start, end, agent, signal?)` keeps an optional signal for manual callers and requires `session === agent.session`; implementations reject mismatch before model resolution, lock acquisition, summarization, or log mutation. The default summarizer resolves its model from explicit config, the latest logged routed model, then agent options, and records the model after any `llm/stream` routing. -### Auto-compaction runs on `agent/pre-step`, a dedicated surface-mutation seam +### Automatic pressure runs after successful durable step work -Compaction mutates the session surface, so it runs before the step opens and before messages are derived. `agent/request` remains a call-config transform and never needs to rebuild history after a surface change. +The original pre-step placement used a provisional envelope and could not see final `agent/request` routing, tools, provider output, tool results, buffered context, or steering. The corrected lifecycle fires serial `agent/post-step(agent, turn, step, signal)` after those successful facts are durable and before `step/end`. `dsh-compact-basic` measures the canonical logged request through `ctx.tokenMeter`, so the next request sees any replacement without a speculative envelope override. -The fix is a dedicated loop seam, **`agent/pre-step`** (`@mode serial`), fired by the loop *after* system assembly and *before* the step opens (`step/start`): +Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic forces one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases; the loop then opens a new numbered step and reconstructs its request from the durable log. No range, no replacement, recovery failure, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. The complete lifecycle decision is in the [after-call recovery RFC](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). ``` -assembly = ctx.systemPrompt.assemble() -await ctx.serial('agent/pre-step', agent, turn, step, system, prefix, signal) ⟵ compaction mutates the surface here -session('step/start') ⟵ the step opens AFTER the seam -messages = session.deriveMessages() ⟵ single derive, reflects the compaction -request = waterfall agent/request ⟵ pure request transform (hooks, model switch) -``` +assistant/message → tool/result/context/steering +await serial agent/post-step ⟵ pressure compaction inside the successful step +step/end -The loop derives messages once after `agent/pre-step`. Running before `step/start` keeps compaction records outside any half-open step, simplifying crash repair. The seam is awaited and serial so surface mutations cannot interleave; listeners return `void` and do not use Cordis bail values as vetoes. +provider overflow → step/end +await waterfall agent/request-error ⟵ forced compaction between attempts +retry → next numbered step/start ⟵ derives from the replacement surface +``` ### Retention is turn-agnostic; tool-pairing balance is the only structural guard -Auto-compaction fires before **every** step, not once per turn. This is **load-bearing for runaway-turn survival**: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows *within* a turn. A single turn can grow past the window on its own (a "runaway turn") — and the only moment to rescue it before the next model call overflows is the next step's `pre-step` checkpoint. Gating compaction to a turn's first step (or, worse, retaining the whole in-flight turn verbatim) re-opens exactly the hole compaction exists to close: the harness would die when compaction is most needed. +Auto-compaction checks after **every successful** step, not once per turn. This is load-bearing for runaway-turn survival: a tool-heavy ReAct turn appends an `assistant/message` + a `tool/result` per step, so the surface grows within a turn. The post-step check can compact early closed tool pairs before continuation opens the next step, and provider-confirmed overflow remains the backstop when a request crosses the limit first. `compactIfNeeded` retains the smallest tail of whole surface units whose estimated size reaches `retainTokens` and compacts older nodes. A unit is a complete closed step or one no-step message. If the token cutoff lands inside a step, retention expands until the cut is tool-pairing balanced. Balance is checked on surface order, not log sequence, because replacement summaries have new sequence numbers at old surface positions. `dsh-compact` exports the before/after edge helpers; their per-session cache folds only appended surface-tail nodes while `replaceGeneration` is unchanged, does no event reads for log-only growth, and rebuilds current membership, positional successors, and balances after replacement. `compactRegion` rejects boundaries that split a tool call from its result. The in-flight turn receives no special retention. @@ -64,7 +64,7 @@ Auto-compaction always starts at the surface head, merging the prior checkpoint ### Approximate convergence invariant -`resolveConfig` supplies usable common defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. Optional per-model threshold/retention fields merge over those defaults and must name a configured meter profile; retained tokens must be below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If the compacted surface remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows. +`resolveConfig` supplies usable common defaults: threshold ratio `0.8`, retained tail `floor(contextWindow × 0.16)`, empty summarization-model override, `maxTokens: 8192`, `compactionRetries: 1`, `maxOverflowRetries: 1`, and `auto: true`. Optional per-model threshold/retention fields merge over those defaults and must name a configured meter profile; retained tokens must be below the resulting threshold. Convergence remains dynamic because provider output caps can be spent on hidden or surfaced reasoning tokens and summary size is unpredictable. If pressure remains over threshold, `compactIfNeeded()` re-compacts the head checkpoint up to the configured retry count, but each committed summary must be smaller than what it shadows. Overflow bypasses threshold and retained-tail policy for one maximal balanced head reduction, leaving the newest indivisible unit. ### Surface replacement: `compact/*` events are log-only; one `user/message` carries the summary @@ -90,12 +90,12 @@ The basic backend wraps the summary as established checkpoint context and tags i The `compact/start … compact/end` bracket is justified, in order of what now does the work: 1. **Crash-detectable orphan + provenance** (primary). Summarization is a slow model call persisted *after* `compact/start`. A crash mid-summarization leaves a `compact/start` with no matching `compact/end` — a detectable orphan. Releasing the lock last (rather than first) converts the crash window from *silent corruption* into that detectable orphan. -2. **Prevents concurrent compaction.** `compactRegion` refuses to start if the current turn holds an unmatched `compact/start`. (The loop is single-threaded across the awaited `pre-step`, so this is also a re-entry tripwire — a thrown "already in progress" signals a real bug.) +2. **Prevents concurrent compaction.** `compactRegion` refuses to start if the current turn holds an unmatched `compact/start`. (The loop is single-threaded across either awaited automatic seam, so this is also a re-entry tripwire — a thrown "already in progress" signals a real bug.) Two failure paths, both documented: -- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — the surface replacement never landed, so the full, uncompacted history derives correctly. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash can't wedge future compaction. Compaction simply re-attempts at the next `pre-step`. -- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set, leaving the surface untouched, and the model call proceeds with full history. +- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — the surface replacement never landed, so the full, uncompacted history derives correctly. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash cannot wedge future compaction. +- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set and leaves the surface untouched. Post-step pressure warns and continues; overflow recovery delegates so the original provider error remains authoritative. `compact/end` keeps its `error?` field (mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling). There is no separate `compact/error` event. @@ -104,14 +104,14 @@ Two failure paths, both documented: ## Alternatives considered - **The full algorithm as concrete interface methods** — rejected because it recouples the contract to one retention strategy. Both core methods are abstract; reusable measurement is a separate LLM-family service and `summarize()` is basic's sole hook. -- **Compaction on the `agent/request` waterfall** — the earlier cut; rejected for the double-derive it forced and for handing the listener context it structurally cannot compact. The dedicated `agent/pre-step` seam makes the layering correct by construction. +- **Compaction on `agent/request` or provisional `agent/pre-step` inputs** — rejected because neither proves the final durable request and both couple generic lifecycle to compaction-specific envelope data. Post-step replay plus canonical overflow recovery covers both successful and rejected calls. - **A separate `compact/error` event** — rejected: `compact/end` keeps an `error?` field, mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling. - **Teaching core turn-repair about `compact/*`** — rejected: the log-only orphan is inert, and a core module patched for every future `xxx/start … xxx/end` plugin pair is exactly the coupling the capability-seam architecture exists to avoid. ## Consequences - **Packages**: `packages/compact/compact` supplies the interface and `compact-basic` supplies the backend. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. -- **New loop seam**: `agent/pre-step` (`@mode serial`) declared in `dsh-agent` and emitted by `dsh-agent-loop` after system assembly and before `step/start`. This is a documented change to the loop — `docs/architecture.md` records it and the generated cordis catalog carries its signature. +- **Automatic seams**: `agent/post-step` (`@mode serial`) handles successful-call pressure and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Generic `agent/pre-step` remains a four-argument checkpoint with no compaction-only prompt/prefix payload. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and resolves after-edges from its positional successor map instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. - **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. @@ -119,7 +119,7 @@ Two failure paths, both documented: ## Testing -- **Unit:** Real Loader and invariant plugins cover whole-unit retention, convergence failure, both `compact/end` outcomes, head anchoring, open-tail refusal, inert crash orphans, and compacting closed steps inside one oversized open turn. -- **Loop:** Tests pin one awaited `agent/pre-step` per step between `turn/start` and `step/start`; a surface mutation there lands outside the step and appears in the single derived request. +- **Unit:** Real Loader and invariant plugins cover whole-unit retention, convergence failure, both `compact/end` outcomes, head anchoring, open-tail refusal, inert crash orphans, forced below-threshold overflow, generation proof, caps, and original-error preservation. +- **Loop:** Tests pin post-step after durable tool results and before `step/end`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition. - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. - **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. diff --git a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md b/docs/rfc/implemented/feature/2026-07-07-session-prefix.md index f0d458368a..e6ecf69a74 100644 --- a/docs/rfc/implemented/feature/2026-07-07-session-prefix.md +++ b/docs/rfc/implemented/feature/2026-07-07-session-prefix.md @@ -16,13 +16,13 @@ Three properties carry the design: - **Request-only, header-logged.** `deriveMessages()` never returns the prefix; its one durable record is `EpochHeader.messagePrefix` on the instance's anchoring `request/header` snapshot — the channel the reconstructable-requests RFC already owns for the request's non-history half, so no new session event exists. The dev invariant ([dsh-invariants](../../../../packages/support/invariants/src/index.ts)) recomputes `messagePrefix + boundary derivation` against every loop-built request; an unlogged prefix cannot reach the wire. - **Frozen per instance.** Reuse is structural, not disciplined: the cached product cannot change mid-session, so the provider's prompt cache holds by construction and the prefix extends the cacheable region at zero marginal cost per step. A process restart or `ctx.agents.resume()` is a new instance: it recomposes, and any drift lands attributably on the `'resume'` header snapshot. This is the routing rule the seam creates: session-frozen openers ride the prefix; content that changes mid-session rides the append-only history channels (`agent.inject()`, a `tools/post-execute` decision's `additionalContext`, prompt-submit `additionalContext` — [the interception-seams RFC](2026-06-30-interception-seams.md)), each a durable `context/message` paid once and prefix-cached thereafter. -- **Composed before the pressure gate.** Composition precedes the instance's first `agent/pre-step`, and the seam hands the composed value through: `agent/pre-step` carries a `sessionPrefix` parameter and `CompactService.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` counts it in its token-pressure estimate — a gate reading the previous instance's folded prefix instead would under-gate a resumed or forked instance whose contributor grew, skipping compaction and shipping an over-window first request. A composition interrupted by a cancel/dispose landing inside the waterfall is discarded, never cached: an abort-aware listener's degraded fallback cannot leak into later requests, and the next turn recomposes under a live signal. +- **Exact in the durable request envelope.** Composition precedes the instance's first `agent/pre-step` and request boundary. The first routed request logs the current prefix on its header, so post-step token pressure reads the exact prefix together with the actual prompt, tools, and routed model; no compaction-only parameter is carried through the generic pre-step seam. A composition interrupted by cancel/dispose is discarded, never cached: an abort-aware listener's degraded fallback cannot leak into later requests, and the next turn recomposes under a live signal. Because composition runs before the boundary snapshot, a composing listener's session append joins the CURRENT request's derived history. Compaction structurally cannot touch the prefix (or the system prompt): it rewrites surface nodes, and header state never enters the surface. ## Testing -[Interception tests](../../../../packages/core/agent-loop/tests/interception.spec.ts) pin compose-once reuse with no header deltas, prepend order, empty-prefix omission, immutability, and composition before pre-step; [cancellation tests](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pin discard and recomposition. Session codec, invariant, and compaction tests cover header round trips, request reconstruction, and prefix-aware pressure accounting. Snapshot normalization preserves prefix counts, while the [pinned-header scenario](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md) owns content and the default example remains prefix-free. No prefix-specific e2e is needed because the seam is deterministic and provider-independent; the with-key [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) covers its cache economics. +[Interception tests](../../../../packages/core/agent-loop/tests/interception.spec.ts) pin compose-once reuse with no header deltas, prepend order, empty-prefix omission, immutability, composition before pre-step, and the prefix on the routed header; [cancellation tests](../../../../packages/core/agent-loop/tests/cancel.spec.ts) pin discard and recomposition. Session codec, invariant, token-meter, and compaction tests cover header round trips, request reconstruction, and durable prefix-aware pressure accounting. Snapshot normalization preserves prefix counts, while the [pinned-header scenario](../testing/2026-07-06-pin-request-header-content-in-one-scenario.md) owns content and the default example remains prefix-free. No prefix-specific e2e is needed because the seam is deterministic and provider-independent; the with-key [request-cache e2e](../../../../packages/core/agent-loop/tests/request-cache.e2e.ts) covers its cache economics. ## Alternatives considered @@ -30,12 +30,12 @@ Because composition runs before the boundary snapshot, a composing listener's se - **A system-prompt section** (`system-prompt/assemble`) — rejected for this content: the assembly renders to the single `system` string, so message-shaped openers do not fit, and the system prompt is deliberately re-assembled per step (with header deltas when it changes) while the opener wants instance-frozen semantics. - **A durable history opener** (`inject()` at session start) — rejected: permanent history is the failure mode in the problem statement — replayed everywhere, compactable, stale across resumes. - **Compose per turn instead of per instance** — rejected: a turn-boundary recompose either desyncs silently from the log or forces a header delta per change, and it busts the provider cache exactly as often as it fires; the legitimate refresh point is the instance boundary, where the `'resume'` snapshot already records drift attributably. -- **Compose lazily at the first request and let compaction read the folded header** (the shape as first merged) — superseded in review: the fold matches the live prefix only from the instance's second request on, so on a resumed/forked instance's first step the pressure gate read the PREVIOUS instance's prefix and could under-gate. Composing before the first pre-step and handing the live value through the seam makes the estimate exact at every step. +- **Carry prompt/prefix through `agent/pre-step` for provisional pressure** — superseded by post-step replay. It coupled a generic lifecycle seam to one consumer and still missed later request routing/tools; the routed header is the exact durable home for all request-envelope fields. - **A dedicated session event carrying the prefix** — rejected: the header events are the request's non-history record by design; a second event would be a second home for the same fact and another codec to keep total. ## Consequences -- `agent/pre-step` and `CompactService.compactIfNeeded` carry a `sessionPrefix` parameter: every pre-step listener and compaction backend sees the real per-instance value (all in-repo implementations updated in the same change, per the pre-release stance). +- `agent/pre-step` stays a generic `(agent, turn, step, signal)` checkpoint. Compaction receives no prefix parameter; `ctx.tokenMeter` folds the prefix from the canonical routed header at post-step. - A contributor whose content changes mid-session is not re-read until the next instance — by design. A deployment needing mid-session catalog updates routes the change notice through the append-only history channels and pays one durable `context/message`. - The dropped `after` slot leaves no request-only channel near the request tail; nothing in the repo needs one, and adding it back would re-open the every-step re-pay cost the design exists to avoid. - The `request/header-delta` `messagePrefix` arm (whole-array replacement, empty array encoding transition to absence) exists for codec totality; the loop never exercises it, because the cached prefix cannot change within an instance. diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index 1208480388..281ae3e9d1 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -49,8 +49,8 @@ - id: token-meter name: '@deepseek-ai/dsh-token-meter' -# Summarize an older range when measured history approaches the context window. -# Built-in model policies provide the ordinary threshold and retained-tail defaults. +# Summarize an older range after measured pressure or a canonical provider overflow. +# Built-in policies provide pressure, retention, and one overflow-retry default. - id: compact-basic name: '@deepseek-ai/dsh-compact-basic' diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index c9264e2e99..b3b910cfb7 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -8,13 +8,14 @@ This is the implementation tier of the compaction capability — see the [interf This backend owns the compaction policy: -- **Measurement** — the effective conversation model's `ModelTokenMeter` prices the provisional request envelope and current surface at one consumed-log revision. The current prompt and prefix override their logged values; the pre-step boundary reuses logged tools and call config. +- **Measurement** — the latest durable routed request model's `ModelTokenMeter` prices the canonical logged envelope and current surface at one consumed-log revision. Post-step pressure therefore includes the actual system prompt, tools, prefix, routing, assistant completion, tool results, buffered context, and steering. - **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. - **Framing** — the replacement user message marks established checkpoint context with `` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint. -- **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/pre-step` listener checks pressure before every step, outside an open step, so a tool-heavy turn remains compactable and the loop derives history once after mutation. -- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Recoverable failure records an error end and leaves the surface unchanged. +- **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/post-step` listener checks pressure after successful output and tool work are durable but before `step/end`. Canonical provider overflow is handled through `agent/request-error` after the failed step closes. +- **Overflow recovery** — below-threshold overflow bypasses normal retention and attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized only when `surface.replaceGeneration` advances; no range, no replacement, recovery failure, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure. +- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Operational post-step failures warn and continue, while an actually routed model without a meter profile fails the otherwise-successful turn with the typed meter error. `summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on the conversation model's meter. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. @@ -29,7 +30,8 @@ Every common setting is optional. Every model known to `ctx.tokenMeter` receives | `summarizationModel` | no (default `''`) | Empty resolves the latest logged routed model, then `AgentOptions.model`. | | `maxTokens` | no (default `8192`) | Provider generation cap for the summarization call; may include reasoning tokens. | | `compactionRetries` | no (default `1`) | Extra attempts after the first when pressure remains above threshold. | -| `auto` | no (default `true`) | Register the `agent/pre-step` automatic listener. Set `false` for manual-only. | +| `maxOverflowRetries` | no (default `1`) | Maximum retries after canonical context-window overflow; `0` disables recovery only. | +| `auto` | no (default `true`) | Register post-step pressure and overflow-recovery listeners. Set `false` for manual-only. | ## Usage @@ -39,7 +41,7 @@ import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import TokenMeterService from '@deepseek-ai/dsh-token-meter' export const name = 'compact-basic' -export const inject = ['llm'] +export const inject = ['llm', 'tokenMeter'] export function apply(ctx: Context): void { ctx.plugin(TokenMeterService) @@ -53,7 +55,7 @@ Loading the plugin registers `ctx.compact`. With `auto: true` (the default) it c ### Conversation history -**What the model sees**: Before a step whose estimated envelope and history exceed the threshold, the conversation model receives the checkpoint preamble below, a blank line, ``, the data-dependent summary, and ``. This one checkpoint replaces the selected older range and is followed by the retained recent units. +**What the model sees**: After a successful step crosses the threshold, the next request receives the checkpoint preamble below, a blank line, ``, the data-dependent summary, and ``. Overflow recovery rebuilds the immediate retry from that replacement. This one checkpoint replaces the selected older range and is followed by the retained recent units. **Token effect**: The replacement reduces future input history rather than appending a second copy. The summary remains until a later compaction replaces it; one oversized indivisible unit can still exceed the budget. @@ -115,8 +117,9 @@ Rules: ## Known Limitations and Deferred Work -- **Pre-step sees a provisional request envelope** — the current prompt and prefix are exact, but routing and tool changes made later in `agent/request` are not logged yet. A router-only agent with no provisional model skips that check. - **Meter accuracy follows the selected profile** — missing provider usage falls back to the token meter's configured character density and structural overhead. +- **Overflow classification is adapter-maintained** — provider wording can change; both DeepSeek adapters normalize currently recognized context-limit failures to `CONTEXT_WINDOW_EXCEEDED`. +- **Single-unit and envelope-only overflow remain outside surface compaction** — recovery cannot split one indivisible message/tool unit or shrink system/tools/prefix. - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting. - **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds. - **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts index 504b0d8a9f..16e71c081a 100644 --- a/packages/compact/compact-basic/src/automatic.ts +++ b/packages/compact/compact-basic/src/automatic.ts @@ -1,12 +1,12 @@ /** - * Automatic pre-step pressure listener for compact-basic. + * Automatic post-step pressure and context-overflow recovery listeners. * * @module @deepseek-ai/dsh-compact-basic/automatic */ import type { Context } from 'cordis' -import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import type { Message } from '@deepseek-ai/dsh-llm' +import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' +import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import { TOKEN_METER_MODEL_UNCONFIGURED, TokenMeterError, @@ -14,10 +14,10 @@ import { import type { Agent } from '@deepseek-ai/dsh-agent' interface AutomaticCompactor { + readonly config: { readonly maxOverflowRetries: number } compactIfNeeded( agent: Agent, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], + trigger: CompactionTrigger, signal: AbortSignal, ): Promise } @@ -31,30 +31,54 @@ export function registerAutomaticCompaction( ctx: Context, service: AutomaticCompactor, ): void { - ctx.on('agent/pre-step', async ( + const logResult = (result: CompactionResult, trigger: string): void => { + ctx.logger.info( + `compaction (${trigger}): shadowed ${result.shadowedSeqs.length} surface nodes ` + + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` + + `~${result.shadowedTokenCount} tokens)`, + ) + } + + ctx.on('agent/post-step', async ( agent: Agent, _turn: number, _step: number, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], signal: AbortSignal, ) => { try { - const result = await service.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal) - if (result !== null) { - ctx.logger.info( - `compaction: shadowed ${result.shadowedSeqs.length} surface nodes ` - + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` - + `~${result.shadowedTokenCount} tokens)`, - ) - } + const result = await service.compactIfNeeded(agent, 'pressure', signal) + if (result !== null) logResult(result, 'post-step pressure') } catch (error: unknown) { // A named routed model without a meter profile is configuration failure, // not an optional operational compaction miss. if (error instanceof TokenMeterError && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error const message = error instanceof Error ? error.message : String(error) - ctx.logger.warn(`compaction failed: ${message}; proceeding with full history`) + ctx.logger.warn(`post-step compaction failed: ${message}; continuing the turn`) } }) + + ctx.on('agent/request-error', async (agent, _turn, _step, error, retryAttempt, signal, next) => { + if (error.code !== CONTEXT_WINDOW_EXCEEDED_CODE + || retryAttempt >= service.config.maxOverflowRetries + || signal.aborted) return next() + + let generation: number + let result: CompactionResult | null + try { + generation = agent.session.surface.replaceGeneration + result = await service.compactIfNeeded(agent, 'context-overflow', signal) + } catch (recoveryError: unknown) { + const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError) + ctx.logger.warn( + `context-overflow compaction failed: ${message}; preserving the original request error`, + ) + return next() + } + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited. + if (signal.aborted || result === null + || agent.session.surface.replaceGeneration <= generation) return next() + logResult(result, 'context overflow recovery') + return { action: 'retry' } + }) } diff --git a/packages/compact/compact-basic/src/config.ts b/packages/compact/compact-basic/src/config.ts index 3169d7f5aa..e4d567da3b 100644 --- a/packages/compact/compact-basic/src/config.ts +++ b/packages/compact/compact-basic/src/config.ts @@ -47,6 +47,7 @@ export function resolveConfig( summarizationModel: '', maxTokens: 8192, compactionRetries: 1, + maxOverflowRetries: 1, auto: true, }, meter) } @@ -56,10 +57,12 @@ export function resolveConfig( summarizationModel: config.summarizationModel ?? '', maxTokens: config.maxTokens ?? 8192, compactionRetries: config.compactionRetries ?? 1, + maxOverflowRetries: config.maxOverflowRetries ?? 1, auto: config.auto ?? true, } assertPositiveInteger('maxTokens', resolved.maxTokens) assertNonNegativeInteger('compactionRetries', resolved.compactionRetries) + assertNonNegativeInteger('maxOverflowRetries', resolved.maxOverflowRetries) if (typeof resolved.summarizationModel !== 'string') { throw new Error('BasicCompactConfig: summarizationModel must be a string') } diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index cd4ea5d1d5..d420851166 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -7,10 +7,9 @@ import { Context } from 'cordis' import z from 'schemastery' import { CompactService } from '@deepseek-ai/dsh-compact' -import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import { canonicalHeader } from '@deepseek-ai/dsh-session' -import type { EpochHeader, Session } from '@deepseek-ai/dsh-session' -import type { ContentBlock, Message } from '@deepseek-ai/dsh-llm' +import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' +import type { Session } from '@deepseek-ai/dsh-session' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { ModelTokenMeter } from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' import { registerAutomaticCompaction } from './automatic.ts' @@ -36,24 +35,10 @@ function effectiveModel(agent: Agent): string | undefined { return agent.session.requestHeader()?.config.model ?? agent.options.model } -/** - * Build the provisional pre-step request envelope. Prompt and prefix are exact; - * tools and non-model call config come from the latest logged request because - * later request middleware has not run yet. - */ -function provisionalHeader( - model: string, - session: Session, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], -): EpochHeader { - const latest = session.requestHeader() - return canonicalHeader({ - config: latest === undefined ? { model } : { ...latest.config, model }, - ...fullSystemPrompt.length === 0 ? {} : { system: fullSystemPrompt }, - ...latest?.tools === undefined ? {} : { tools: latest.tools }, - ...sessionPrefix.length === 0 ? {} : { messagePrefix: [...sessionPrefix] }, - }) +/** Resolve the exact model durably routed for the latest provider request. */ +function routedModel(session: Session): string | undefined { + const model = session.requestHeader()?.config.model + return model === undefined || model.length === 0 ? undefined : model } /** @@ -75,6 +60,7 @@ export class BasicCompactService extends CompactService { summarizationModel: z.string().default(''), maxTokens: z.number().step(1).min(1).default(8192), compactionRetries: z.number().step(1).min(0).default(1), + maxOverflowRetries: z.number().step(1).min(0).default(1), auto: z.boolean().default(true), }) @@ -106,29 +92,33 @@ export class BasicCompactService extends CompactService { } /** - * Check replayed pressure for the provisional pre-step envelope and compact - * a tool-balanced head until it falls below the effective model threshold. - * A genuinely model-less router-first step skips this provisional check; - * naming an unconfigured model throws the token meter's typed error. - * @param agent - agent whose session and provisional model are measured. - * @param fullSystemPrompt - current assembled system prompt override. - * @param sessionPrefix - current request-only prefix override. - * @param signal - live step cancellation signal forwarded to summarization. + * Compact for replayed post-step pressure or one provider-confirmed context + * overflow. Both triggers price the latest durable routed request model; + * overflow bypasses the normal threshold and retained-tail policy so it can + * force one useful balanced reduction. + * @param agent - agent whose latest durable routed request is measured. + * @param trigger - normal post-step pressure or context-overflow recovery. + * @param signal - live turn cancellation signal forwarded to summarization. * @returns the latest compaction result, or `null` when no check/work applies. */ override async compactIfNeeded( agent: Agent, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], + trigger: CompactionTrigger, signal: AbortSignal, ): Promise { - const model = effectiveModel(agent) - if (model === undefined || model.length === 0) return null + const model = routedModel(agent.session) + if (model === undefined) return null const meter = this.ctx.tokenMeter.resolve(model) const policy = this._modelConfig(meter) - const requestHeader = provisionalHeader(model, agent.session, fullSystemPrompt, sessionPrefix) + if (trigger === 'context-overflow') { + const surface = meter.measureSurface(agent.session) + const range = selectCompactableRange(agent.session, surface, 0) + if (range === null) return null + return this.compactRegion(agent.session, range.start, range.end, agent, signal) + } + const threshold = Math.floor(policy.contextWindow * policy.thresholdRatio) - let measurement = meter.measure(agent.session, requestHeader) + let measurement = meter.measure(agent.session) if (measurement.totalTokens < threshold) return null let result: CompactionResult | null = null @@ -147,7 +137,7 @@ export class BasicCompactService extends CompactService { break } result = await this.compactRegion(agent.session, range.start, range.end, agent, signal) - measurement = meter.measure(agent.session, requestHeader) + measurement = meter.measure(agent.session) if (measurement.totalTokens < threshold) return result } diff --git a/packages/compact/compact-basic/src/summarizer.ts b/packages/compact/compact-basic/src/summarizer.ts index 359421f0f5..78730cc1a6 100644 --- a/packages/compact/compact-basic/src/summarizer.ts +++ b/packages/compact/compact-basic/src/summarizer.ts @@ -106,7 +106,7 @@ export async function summarizeWithLlm( if (!summary.some(block => block.text.trim().length > 0)) { throw new Error('summarization produced no text summary content') } - return { summary, model, maxTokens: config.maxTokens } + return { summary, model: options.model, maxTokens: config.maxTokens } } /** diff --git a/packages/compact/compact-basic/src/types.ts b/packages/compact/compact-basic/src/types.ts index 44ff06435d..4a3f372e08 100644 --- a/packages/compact/compact-basic/src/types.ts +++ b/packages/compact/compact-basic/src/types.ts @@ -22,7 +22,9 @@ export interface BasicCompactConfig { maxTokens?: number /** Extra attempts after the first compaction when pressure remains above threshold. Defaults to `1`. */ compactionRetries?: number - /** Enable the automatic `agent/pre-step` pressure listener. Defaults to `true`. */ + /** Maximum retries after canonical context overflow; `0` disables recovery. Defaults to `1`. */ + maxOverflowRetries?: number + /** Enable automatic post-step pressure and overflow-recovery listeners. Defaults to `true`. */ auto?: boolean } @@ -32,6 +34,7 @@ export interface ResolvedConfig { readonly summarizationModel: string readonly maxTokens: number readonly compactionRetries: number + readonly maxOverflowRetries: number readonly auto: boolean } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 98b4b2f15b..163c2b6b45 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -6,9 +6,10 @@ import BasicCompactService, { } from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' import { selectCompactableRange } from '@deepseek-ai/dsh-compact-basic/src/region.ts' +import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -import type { ContentBlock, GenerateOptions, Message, StreamChunk } from '@deepseek-ai/dsh-llm' +import LlmService, { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, LlmAdapter } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' import TokenMeterService, { TOKEN_METER_MODEL_UNCONFIGURED, @@ -43,6 +44,12 @@ function conversation(turns = 4, text = 'fixture'): Session { source: { kind: 'user' }, }, { surfaceOp: 'append' }) session.append('step/start', { turn, step: 1 }) + if (turn === 1) { + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + } session.append('assistant/message', { turn, step: 1, @@ -68,6 +75,12 @@ function toolConversation(): Session { source: { kind: 'user' }, }, { surfaceOp: 'append' }) session.append('step/start', { turn, step: 1 }) + if (turn === 1) { + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + } session.append('assistant/message', { turn, step: 1, @@ -120,11 +133,10 @@ function service( async function compactIfNeeded( compact: BasicCompactService, session: Session, + trigger: 'pressure' | 'context-overflow' = 'pressure', model: string | undefined = MODEL, - system = '', - prefix: readonly Message[] = [], ): Promise { - return compact.compactIfNeeded(agent(session, model), system, prefix, SIGNAL) + return compact.compactIfNeeded(agent(session, model), trigger, SIGNAL) } describe('compact configuration and defaults', () => { @@ -140,6 +152,7 @@ describe('compact configuration and defaults', () => { summarizationModel: '', maxTokens: 8192, compactionRetries: 1, + maxOverflowRetries: 1, auto: true, }) expect(resolveModelConfig(resolved, ctx.tokenMeter.resolve(MODEL))).toEqual({ @@ -176,6 +189,7 @@ describe('compact configuration and defaults', () => { const bad = [ [{ maxTokens: 0 }, /maxTokens/], [{ compactionRetries: -1 }, /compactionRetries/], + [{ maxOverflowRetries: -1 }, /maxOverflowRetries/], [{ auto: 'yes' }, /auto must be a boolean/], [{ summarizationModel: 1 }, /summarizationModel must be a string/], [{ models: null }, /models must be an object/], @@ -207,19 +221,57 @@ describe('pressure measurement and retention', () => { models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, } - it('skips the provisional check only when no routed or fallback model exists', async () => { + it('skips when no durable routed model exists instead of using AgentOptions fallback', async () => { const compact = service(compactConfig) - const session = conversation() - expect(await compact.compactIfNeeded(agent(session), '', [], SIGNAL)).toBeNull() + const session = new Session(SessionId('headerless')) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + await expect(compact.compactIfNeeded(agent(session, MODEL), 'pressure', SIGNAL)) + .resolves.toBeNull() expect(compact.calls).toHaveLength(0) }) it('throws for a named unconfigured model instead of swallowing it', async () => { const compact = service(compactConfig) - await expect(compactIfNeeded(compact, conversation(), 'missing')) + const session = conversation() + session.append('request/header', { + header: { config: { model: 'missing' } }, + reason: 'resume', + }) + await expect(compactIfNeeded(compact, session)) .rejects.toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED, model: 'missing' }) }) + it('declines forced overflow when the whole surface is one indivisible tool pair', async () => { + const compact = service(compactConfig) + const session = new Session(SessionId('single-tool-pair')) + const callId = CallId('single-call') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('step/start', { turn: 1, step: 1 }) + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'tool-call', id: callId, name: 'read', arguments: '{}' }], + }, { surfaceOp: 'append' }) + session.append('tool/call', { turn: 1, step: 1, callId, name: 'read', arguments: '{}' }) + session.append('tool/result', { + turn: 1, + step: 1, + callId, + content: [{ type: 'text', text: 'result' }], + isError: false, + }, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) + const generation = session.surface.replaceGeneration + + await expect(compactIfNeeded(compact, session, 'context-overflow')).resolves.toBeNull() + expect(session.surface.replaceGeneration).toBe(generation) + expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + }) + it('does nothing below threshold and compacts a priced head above threshold', async () => { const compact = service(compactConfig) expect(await compactIfNeeded(compact, conversation(2))).toBeNull() @@ -231,7 +283,7 @@ describe('pressure measurement and retention', () => { expect(session.surface.nodes.length).toBeLessThan(8) }) - it('counts the current prompt and request prefix without putting either on the surface', async () => { + it('counts the durable routed request envelope without putting its prefix on the surface', async () => { const compact = service({ auto: false, models: { [MODEL]: { thresholdRatio: 0.7, retainTokens: 9 } }, @@ -239,11 +291,16 @@ describe('pressure measurement and retention', () => { const session = conversation(2, 'x'.repeat(2_000)) expect(await compactIfNeeded(compact, session)).toBeNull() - const prefix: Message[] = [{ - role: 'user', - content: [{ type: 'text', text: 'p'.repeat(10_000) }], - }] - const result = await compactIfNeeded(compact, session, MODEL, 's'.repeat(5_000), prefix) + const prefix = [{ role: 'user' as const, content: [{ type: 'text' as const, text: 'p'.repeat(10_000) }] }] + session.append('request/header', { + header: { + config: { model: MODEL }, + system: 's'.repeat(5_000), + messagePrefix: prefix, + }, + reason: 'resume', + }) + const result = await compactIfNeeded(compact, session) expect(result).not.toBeNull() expect(prefix).toHaveLength(1) expect(session.events.some(event => event.type === 'context/message')).toBe(false) @@ -264,17 +321,26 @@ describe('pressure measurement and retention', () => { reason: 'initial', }) - const result = await compactIfNeeded(compact, session, 'fallback') + const result = await compactIfNeeded(compact, session, 'pressure', 'fallback') expect(result).not.toBeNull() }) it('declines when envelope pressure is high but the surface has no compactable range', async () => { const compact = service(compactConfig) const empty = new Session(SessionId('empty')) - expect(await compactIfNeeded(compact, empty, MODEL, 'x'.repeat(100_000))).toBeNull() + empty.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + empty.append('request/header', { + header: { config: { model: MODEL }, system: 'x'.repeat(100_000) }, + reason: 'initial', + }) + expect(await compactIfNeeded(compact, empty)).toBeNull() const retained = conversation(1) - expect(await compactIfNeeded(compact, retained, MODEL, 'x'.repeat(100_000))).toBeNull() + retained.append('request/header', { + header: { config: { model: MODEL }, system: 'x'.repeat(100_000) }, + reason: 'resume', + }) + expect(await compactIfNeeded(compact, retained)).toBeNull() }) it('detects scalar/surface revision disagreement', async () => { @@ -587,7 +653,19 @@ describe('compaction region transaction', () => { it('requires a conversation model for pricing', async () => { const compact = service() - const session = conversation(1) + const session = new Session(SessionId('model-less-region')) + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('user/message', { + content: [{ type: 'text', text: 'history' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + session.append('step/start', { turn: 1, step: 1 }) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'text', text: 'answer' }], + }, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) const nodes = session.surface.nodes await expect(compact.compactRegion( session, @@ -679,6 +757,25 @@ describe('default one-shot summarizer', () => { expect(adapter.lastOptions?.model).toBe('routed') }) + it('records the model actually dispatched after one-shot stream routing', async () => { + const { ctx, compact } = await summarizerHarness([{ type: 'text', text: 'unused' }]) + const routedAdapter = new ScriptedAdapter([{ type: 'text', text: 'routed summary' }]) + ctx.llm.registerAdapter(['routed-summary-model'], routedAdapter) + ctx.on('llm/stream', (options, next) => { + options.model = 'routed-summary-model' + return next() + }) + + const session = conversation(3, 'large history '.repeat(500)) + const nodes = session.surface.nodes + await compact.compactRegion(session, nodes[0]!.seq, nodes[3]!.seq, agent(session, MODEL), SIGNAL) + expect(session.events.findLast(event => event.type === 'compact/summary')?.data).toMatchObject({ + summary: [{ type: 'text', text: 'routed summary' }], + model: 'routed-summary-model', + }) + expect(routedAdapter.lastOptions?.model).toBe('routed-summary-model') + }) + it('fails clearly when no summarization model can be resolved', async () => { const ctx = new Context() await ctx.plugin(LlmService) @@ -717,21 +814,36 @@ describe('default one-shot summarizer', () => { }) describe('automatic listener and loader composition', () => { - function preStep(ctx: Context, owner: Agent): Promise { - return ctx.serial('agent/pre-step', owner, 1, 1, '', [], SIGNAL) + function postStep(ctx: Context, owner: Agent, signal = SIGNAL): Promise { + return ctx.serial('agent/post-step', owner, 1, 1, signal) } - it('compacts above threshold and remains idle below it', async () => { + function recover( + ctx: Context, + owner: Agent, + error: Error & { code?: string }, + retryAttempt = 0, + signal = SIGNAL, + next: () => Promise<{ action: 'fail' | 'retry' }> = () => Promise.resolve({ action: 'fail' }), + ): Promise<{ action: 'fail' | 'retry' }> { + return ctx.waterfall('agent/request-error', owner, 1, 1, error, retryAttempt, signal, next) + } + + function overflow(message = 'provider overflow'): Error & { code: string } { + return Object.assign(new Error(message), { code: CONTEXT_WINDOW_EXCEEDED_CODE }) + } + + it('compacts post-step above threshold using the durable routed model and remains idle below it', async () => { const ctx = createContext() const compact = new TestCompactService(ctx, { models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, }) const pressured = conversation(4) - await preStep(ctx, agent(pressured, MODEL)) + await postStep(ctx, agent(pressured, 'unconfigured-agent-fallback')) expect(pressured.events.some(event => event.type === 'compact/summary')).toBe(true) const small = conversation(1) - await preStep(ctx, agent(small, MODEL)) + await postStep(ctx, agent(small, MODEL)) expect(small.events.some(event => event.type === 'compact/start')).toBe(false) expect(compact.calls).toHaveLength(1) }) @@ -746,7 +858,7 @@ describe('automatic listener and loader composition', () => { compact.error = 'temporary failure' const session = conversation(4) - await expect(preStep(ctx, agent(session, MODEL))).resolves.toBeUndefined() + await expect(postStep(ctx, agent(session, MODEL))).resolves.toBeUndefined() expect(warnings).toContainEqual(expect.stringContaining('temporary failure')) expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) }) @@ -754,21 +866,210 @@ describe('automatic listener and loader composition', () => { it('propagates a named unknown-model configuration failure', async () => { const ctx = createContext() void new TestCompactService(ctx) - await expect(preStep(ctx, agent(conversation(4), 'missing'))).rejects.toMatchObject({ + const session = conversation(4) + session.append('request/header', { + header: { config: { model: 'missing' } }, + reason: 'resume', + }) + await expect(postStep(ctx, agent(session, MODEL))).rejects.toMatchObject({ code: TOKEN_METER_MODEL_UNCONFIGURED, model: 'missing', }) }) - it('auto:false installs no listener', async () => { + it('force-compacts below normal pressure for canonical overflow and retries only after replacement', async () => { + const ctx = createContext() + void new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 1, retainTokens: 90 } }, + }) + const session = conversation(3) + const beforeGeneration = session.surface.replaceGeneration + const retainedSeq = session.surface.nodes.at(-1)!.seq + const threshold = 100 + expect(ctx.tokenMeter.resolve(MODEL).measure(session).totalTokens).toBeLessThan(threshold) + const decision = await recover(ctx, agent(session, 'unconfigured-agent-fallback'), overflow()) + + expect(decision).toEqual({ action: 'retry' }) + expect(session.surface.replaceGeneration).toBe(beforeGeneration + 1) + expect(session.events.some(event => event.type === 'compact/summary')).toBe(true) + expect(session.surface.nodes.some(node => node.seq === retainedSeq)).toBe(true) + }) + + it('preserves the newest whole tool-call/result pair during forced overflow compaction', async () => { + const ctx = createContext() + void new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 1, retainTokens: 90 } }, + }) + const session = toolConversation() + const newestAssistant = session.surface.nodes.at(-2)! + const newestResult = session.surface.nodes.at(-1)! + + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' }) + const currentAssistant = session.surface.nodes.find(node => node.seq === newestAssistant.seq) + const currentResult = session.surface.nodes.find(node => node.seq === newestResult.seq) + expect(currentAssistant).toBeDefined() + expect(currentResult).toBeDefined() + expect(toolPairingBalancedBefore(session, currentAssistant!)).toBe(true) + expect(toolPairingBalancedAfter(session, currentResult!)).toBe(true) + }) + + it('does not retry when a backend reports success without replacing the surface', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx) + const session = conversation(2) + const fakeResult: CompactionResult = { + startSeq: 1, + summarySeq: 2, + endSeq: 3, + summary: [{ type: 'text', text: 'fake' }], + shadowedRange: { start: 1, end: 2 }, + shadowedSeqs: [1, 2], + shadowedTokenCount: 10, + } + vi.spyOn(compact, 'compactIfNeeded').mockResolvedValue(fakeResult) + + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) + expect(session.surface.replaceGeneration).toBe(0) + }) + + it('delegates downstream exactly once when no replacement is available', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx) + vi.spyOn(compact, 'compactIfNeeded').mockResolvedValue(null) + const downstream = new Error('downstream recovery failed') + let calls = 0 + + await expect(recover( + ctx, + agent(conversation(2), MODEL), + overflow(), + 0, + SIGNAL, + () => { + calls += 1 + return Promise.reject(downstream) + }, + )).rejects.toBe(downstream) + expect(calls).toBe(1) + }) + + it('preserves the original provider error when recovery throws', async () => { + const ctx = createContext() + const warnings: string[] = [] + ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn + const compact = new TestCompactService(ctx) + compact.error = new Error('summary unavailable') + const original = overflow('original provider overflow') + + expect(await recover(ctx, agent(conversation(3), MODEL), original)).toEqual({ action: 'fail' }) + expect(original).toMatchObject({ + message: 'original provider overflow', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + expect(warnings).toContainEqual(expect.stringContaining('preserving the original request error')) + }) + + it('delegates once when overflow recovery throws a non-Error value', async () => { + const ctx = createContext() + const warnings: string[] = [] + ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn + const compact = new TestCompactService(ctx) + compact.error = 'non-error recovery failure' + const session = conversation(3) + const generation = session.surface.replaceGeneration + const original = overflow('original provider failure') + let delegations = 0 + + const decision = await recover(ctx, agent(session, MODEL), original, 0, SIGNAL, () => { + delegations += 1 + return Promise.resolve({ action: 'fail' }) + }) + + expect(decision).toEqual({ action: 'fail' }) + expect(delegations).toBe(1) + expect(session.surface.replaceGeneration).toBe(generation) + expect(original).toMatchObject({ + message: 'original provider failure', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + expect(warnings).toContainEqual(expect.stringContaining('non-error recovery failure')) + }) + + it('delegates once and preserves the original overflow for an unknown routed meter model', async () => { + const ctx = createContext() + void new TestCompactService(ctx) + const session = conversation(2) + session.append('request/header', { + header: { config: { model: 'unknown-routed-model' } }, + reason: 'resume', + }) + const original = overflow('original unknown-model overflow') + let delegations = 0 + + const decision = await recover(ctx, agent(session, MODEL), original, 0, SIGNAL, () => { + delegations += 1 + return Promise.resolve({ action: 'fail' }) + }) + expect(decision).toEqual({ action: 'fail' }) + expect(delegations).toBe(1) + expect(original).toMatchObject({ + message: 'original unknown-model overflow', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + }) + + it('honors retry caps, non-context failures, and cancellation', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx, { maxOverflowRetries: 1 }) + const compactSpy = vi.spyOn(compact, 'compactIfNeeded') + const owner = agent(conversation(3), MODEL) + expect(await recover(ctx, owner, Object.assign(new Error('rate limit'), { code: 'RATE_LIMIT' }))) + .toEqual({ action: 'fail' }) + expect(await recover(ctx, owner, overflow(), 1)).toEqual({ action: 'fail' }) + + const controller = new AbortController() + controller.abort('cancelled') + expect(await recover(ctx, owner, overflow(), 0, controller.signal)).toEqual({ action: 'fail' }) + expect(compactSpy).not.toHaveBeenCalled() + }) + + it('does not retry when cancellation lands during an awaited compaction', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx) + const controller = new AbortController() + compact.mutateDuringSummary = () => { controller.abort('cancelled during summary') } + const session = conversation(3) + const generation = session.surface.replaceGeneration + + expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal)) + .toEqual({ action: 'fail' }) + expect(session.surface.replaceGeneration).toBe(generation + 1) + }) + + it('maxOverflowRetries:0 disables recovery without disabling post-step pressure', async () => { + const ctx = createContext() + void new TestCompactService(ctx, { + maxOverflowRetries: 0, + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + const session = conversation(4) + await postStep(ctx, agent(session, MODEL)) + const summaries = session.events.filter(event => event.type === 'compact/summary').length + expect(summaries).toBe(1) + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) + expect(session.events.filter(event => event.type === 'compact/summary')).toHaveLength(summaries) + }) + + it('auto:false installs neither automatic listener', async () => { const ctx = createContext() void new TestCompactService(ctx, { auto: false, models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, }) const session = conversation(4) - await preStep(ctx, agent(session, MODEL)) + await postStep(ctx, agent(session, MODEL)) expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) }) it('loads and disposes the real zero-config service stack', async () => { @@ -797,8 +1098,9 @@ describe('automatic listener and loader composition', () => { await fiber.dispose() const session = conversation(4) - await preStep(ctx, agent(session, MODEL)) + await postStep(ctx, agent(session, MODEL)) expect(session.events.some(event => event.type === 'compact/start')).toBe(false) + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'fail' }) }) }) diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index cc1111c5f1..2fe9725d77 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -1,7 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { toolPairingBalancedAfter, toolPairingBalancedBefore } from '@deepseek-ai/dsh-compact' -import LlmService from '@deepseek-ai/dsh-llm' +import LlmService, { CONTEXT_WINDOW_EXCEEDED_CODE, LlmError } from '@deepseek-ai/dsh-llm' import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' @@ -53,6 +53,45 @@ class StepwiseToolAdapter extends LlmAdapter { } } +/** First conversation request overflows, then the rebuilt retry succeeds. */ +class OverflowRecoveryAdapter extends LlmAdapter { + readonly conversationRequests: GenerateOptions[] = [] + readonly summaryRequests: GenerateOptions[] = [] + + constructor(private readonly delivery: 'thrown' | 'in-band') { + super() + } + + override async * stream(options: GenerateOptions): AsyncIterable { + if (options.system?.includes('You are a compaction engine')) { + this.summaryRequests.push(options) + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'block-end', index: 0, block: { type: 'text', text: 'RECOVERY CHECKPOINT' } } + yield { type: 'finish', reason: { kind: 'stop' } } + return + } + + this.conversationRequests.push(options) + if (this.conversationRequests.length === 1) { + if (this.delivery === 'thrown') { + throw new LlmError('request too large for model context', CONTEXT_WINDOW_EXCEEDED_CODE, 400) + } + yield { + type: 'finish', + reason: { + kind: 'error', + message: 'request too large for model context', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }, + } + return + } + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'block-end', index: 0, block: { type: 'text', text: 'recovered' } } + yield { type: 'finish', reason: { kind: 'stop' } } + } +} + async function harness(toolSteps: number): Promise<{ ctx: Context; compact: ReproCompactService }> { const ctx = new Context() await ctx.plugin(LlmService) @@ -98,6 +137,53 @@ function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { } describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () => { + it('uses the model actually routed by agent/request for post-step pressure', async () => { + const { ctx } = await harness(8) + ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, model: 'mock' })) + try { + const agent = ctx.agentLoop.create(AgentId('routed-pressure'), { + model: 'unconfigured-agent-fallback', + }) + agent.send([{ type: 'text', text: 'do a routed multi-step task' }]) + await waitForIdle(ctx, agent) + + expect(agent.session.requestHeader()?.config.model).toBe('mock') + expect(agent.session.events.some(event => event.type === 'compact/summary')).toBe(true) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'completed' } }, + }) + } finally { + await ctx.fiber.dispose() + } + }) + + it('runs automatic pressure after the current tool result and before step/end', async () => { + const { ctx } = await harness(4) + try { + const agent = ctx.agentLoop.create(AgentId('post-step-order'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'do tool work' }]) + await waitForIdle(ctx, agent) + + const events = [...agent.session.events] + const compactStart = events.find(event => event.type === 'compact/start') + expect(compactStart).toBeDefined() + const precedingResult = events.findLast(event => + event.type === 'tool/result' && event.seq < compactStart!.seq, + ) + if (precedingResult?.type !== 'tool/result') throw new Error('expected a durable tool result before compaction') + const stepEnd = events.find(event => + event.type === 'step/end' + && event.data.step === precedingResult.data.step + && event.seq > compactStart!.seq, + ) + expect(precedingResult.seq).toBeLessThan(compactStart!.seq) + expect(compactStart!.seq).toBeLessThan(stepEnd!.seq) + } finally { + await ctx.fiber.dispose() + } + }) + it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { @@ -130,3 +216,91 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () } }) }) + +describe('context-overflow recovery across the real loop and compact-basic', () => { + it.each(['thrown', 'in-band'] as const)( + 'force-compacts a %s overflow between failed and retry steps', + async (delivery) => { + const ctx = new Context() + const adapter = new OverflowRecoveryAdapter(delivery) + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(Invariants) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentLoop, { agents: [] }) + await ctx.plugin(TokenMeterService, { + models: { mock: { contextWindow: 128, charsPerToken: 4 } }, + }) + ctx.llm.registerAdapter(['mock'], adapter) + ctx.on('agent/request', async (_agent, _turn, _step, config) => ({ ...config, model: 'mock' })) + await ctx.plugin(BasicCompactService, { + models: { mock: { thresholdRatio: 1, retainTokens: 100 } }, + maxTokens: 64, + compactionRetries: 0, + maxOverflowRetries: 1, + }) + + try { + const agent = ctx.agentLoop.create(AgentId(`overflow-${delivery}`), { + model: 'unconfigured-agent-fallback', + }) + for (let turn = 1; turn <= 2; turn += 1) { + const sentinel = turn === 1 ? 'OLD HISTORY SENTINEL' : 'RECENT HISTORY' + agent.session.append('turn/start', { + turn, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + agent.session.append('user/message', { + content: [{ type: 'text', text: `${sentinel} ${'old context '.repeat(200)}` }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + agent.session.append('step/start', { turn, step: 1 }) + agent.session.append('assistant/message', { + turn, + step: 1, + content: [{ type: 'text', text: `historical response ${turn} ${'detail '.repeat(200)}` }], + }, { surfaceOp: 'append' }) + agent.session.append('step/end', { turn, step: 1 }) + agent.session.append('turn/end', { turn, reason: { kind: 'completed' } }) + } + + agent.send([{ type: 'text', text: 'continue from history' }]) + await agent.whenIdle() + + expect(adapter.conversationRequests).toHaveLength(2) + expect(adapter.summaryRequests).toHaveLength(1) + expect(JSON.stringify(adapter.conversationRequests[0]!.messages)).toContain('OLD HISTORY SENTINEL') + const retry = JSON.stringify(adapter.conversationRequests[1]!.messages) + expect(retry).toContain('RECOVERY CHECKPOINT') + expect(retry).not.toContain('OLD HISTORY SENTINEL') + + const events = [...agent.session.events] + const failedEnd = events.find(event => + event.type === 'step/end' && event.data.turn === 3 && event.data.step === 1, + )! + const retryStart = events.find(event => + event.type === 'step/start' && event.data.turn === 3 && event.data.step === 2, + )! + const compaction = events.filter(event => + event.type === 'compact/start' + || event.type === 'compact/summary' + || event.type === 'compact/end', + ) + expect(compaction.map(event => event.type)).toEqual([ + 'compact/start', + 'compact/summary', + 'compact/end', + ]) + expect(compaction.every(event => event.seq > failedEnd.seq && event.seq < retryStart.seq)).toBe(true) + expect(events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'completed' } }, + }) + } finally { + await ctx.fiber.dispose() + } + }, + ) +}) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 89aacbb09b..a4c94f6c3a 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -18,7 +18,7 @@ Both methods are **abstract** — the backend owns trigger policy, retention, ev | Member | Semantics | |---|---| -| `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | +| `compactIfNeeded(agent, trigger, signal)` | Consider automatic compaction for `trigger: 'pressure' \| 'context-overflow'`. A pressure trigger may apply the backend's threshold and retained-tail policy; a confirmed overflow may force a useful balanced reduction. Returns the `CompactionResult`, or `null` when no safe range exists. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | | `compactRegion(session, start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) into a single replacement node. The agent must own the exact target (`session === agent.session`); a backend rejects mismatch before model resolution, lock acquisition, summarization, or log mutation. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The turn that the `compact/*` events belong to is recoverable from the owned session's log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. @@ -72,6 +72,5 @@ Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and ## Known Limitations and Deferred Work - **No model-facing consumer tier yet** — `@deepseek-ai/dsh-tool-compact` (the `/compact` tool) is deferred; compaction is reachable only via direct `ctx.compact` calls or a backend's auto listener. -- **Single-unit overflow is out of contract** — one retained unit (a closed step or a large pasted `user/message`) alone exceeding the budget cannot be compacted; the call may go out over-budget. -- **A session prefix that alone approaches the window is a configuration error no backend fixes** — compaction shrinks derived history, never the prefix. -- **Request context injected by downstream `agent/request` listeners sits outside pressure accounting** — `compactIfNeeded` counts prefix, derived history, and system prompt only. +- **Single-unit overflow is out of contract** — one indivisible unit (a closed tool pair or a large pasted `user/message`) alone exceeding the budget cannot be compacted. +- **An envelope that alone approaches the window is not surface-compaction work** — compaction shrinks derived history, never the system prompt, tools, or session prefix. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index 7361d38ef3..80058f6145 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -8,7 +8,6 @@ */ import { Context, Service } from 'cordis' -import type { Message } from '@deepseek-ai/dsh-llm' import type { Session } from '@deepseek-ai/dsh-session' import type { CompactionResult } from './types.ts' @@ -16,6 +15,9 @@ export type { CompactionResult } from './types.ts' export { renderContentBlocks, renderTranscript } from './render.ts' export { toolPairingBalancedAfter, toolPairingBalancedBefore } from './tool-pairing.ts' +/** Why automatic policy is asking a backend to consider compaction. */ +export type CompactionTrigger = 'pressure' | 'context-overflow' + /** Minimal agent context compaction needs without depending on the agent package. */ export interface CompactAgentContext { session: Session @@ -41,24 +43,20 @@ export abstract class CompactService extends Service { } /** - * Check token pressure and compact if the conversation is too large. - * Estimate the next request, including its session prefix, derived history, - * and system prompt. Above threshold, compact a head-anchored range ending at - * a balanced tool boundary and reconsolidate any prior automatic checkpoint. - * Return `null` when no compaction is needed or an open tail leaves no safe - * cutoff. A single oversized retained unit or prefix cannot be repaired here. + * Consider automatic compaction for one explicit trigger. Pressure policy + * uses the latest durable routed request, while context-overflow policy may + * force a useful balanced reduction even below the normal threshold. Return + * `null` when no safe range can be compacted. A single oversized retained + * unit or request envelope cannot be repaired through surface compaction. * * @param agent - agent context owning the session surface and model options. - * @param fullSystemPrompt - assembled system prompt, counted toward the estimate. - * @param sessionPrefix - the instance's composed session prefix, counted toward the - * estimate. + * @param trigger - normal pressure or provider-confirmed context overflow. * @param signal - cancellation signal; model-backed implementations must forward it. * @returns the compaction result, or `null` if no compaction was needed. */ abstract compactIfNeeded( agent: CompactAgentContext, - fullSystemPrompt: string, - sessionPrefix: readonly Message[], + trigger: CompactionTrigger, signal: AbortSignal, ): Promise diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index c4daa8cc5a..946b2e8b83 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -1,8 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import { CompactService } from '@deepseek-ai/dsh-compact' -import type { CompactionResult } from '@deepseek-ai/dsh-compact' -import type { Message } from '@deepseek-ai/dsh-llm' +import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' import { Session, SessionId } from '@deepseek-ai/dsh-session' import type { CompactAgentContext } from '@deepseek-ai/dsh-compact' @@ -18,8 +17,7 @@ class StubCompactService extends CompactService { override async compactIfNeeded( _agent: CompactAgentContext, - _fullSystemPrompt: string, - _sessionPrefix: readonly Message[], + _trigger: CompactionTrigger, signal: AbortSignal, ): Promise { this.lastSignal = signal @@ -80,7 +78,7 @@ describe('CompactService seam', () => { const ctx = new Context() const svc = new StubCompactService(ctx) const session = new Session(SessionId('s')) - expect(await svc.compactIfNeeded(stubAgent(session), '', [], new AbortController().signal)).toBeNull() + expect(await svc.compactIfNeeded(stubAgent(session), 'pressure', new AbortController().signal)).toBeNull() }) it('compact/* events merge into SessionEventMap and are log-only', async () => { @@ -109,7 +107,7 @@ describe('CompactService seam', () => { await svc.compactRegion(session, 0, 0, stubAgent(session, 'm'), controller.signal) expect(svc.lastSignal).toBe(controller.signal) - await svc.compactIfNeeded(stubAgent(session), '', [], controller.signal) + await svc.compactIfNeeded(stubAgent(session), 'context-overflow', controller.signal) expect(svc.lastSignal).toBe(controller.signal) }) }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 7aafb3ce8a..fad2094fa9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -108,7 +108,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'compact', summary: 'Abstract compaction service.', methods: [ - 'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise', + 'abstract compactIfNeeded( agent: CompactAgentContext, trigger: CompactionTrigger, signal: AbortSignal, ): Promise', 'abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', ], }, @@ -289,8 +289,8 @@ export const EVENT_API: readonly EventApiEntry[] = [ { name: 'agent/pre-step', mode: 'serial', - signature: '\'agent/pre-step\'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void', - summary: 'Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step.', + signature: '\'agent/pre-step\'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void', + summary: 'Awaited serial checkpoint before `step/start`; appends land outside the pending step and are included when the loop derives request history.', }, { name: 'agent/prompt-submit', @@ -656,6 +656,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'CompactionResult', declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, + { + name: 'CompactionTrigger', + declaration: 'export type CompactionTrigger = \'pressure\' | \'context-overflow\';', + }, { name: 'ConfinedArgv', declaration: 'export interface ConfinedArgv {\n argv: string[];\n enforcement: SandboxEnforcement;\n denialSignatures: readonly string[];\n runnerFailureSignatures: readonly string[];\n}', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 864ff95e8c..70d7c16cf0 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -58,7 +58,7 @@ Plugin failure ends the current turn, not the loop. Only final adapter dispatch/ Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy: - Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → `tools/result` pipeline; exact signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md) -- Compaction: `agent/pre-step` +- Compaction: pressure on `agent/post-step`; canonical context overflow on `agent/request-error` - Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation - Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while child streaming/progress and background/poll collection remain deferred. - Persistence: `session/event` + `session/flush` diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index e749018f55..620cdd9fbc 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -276,7 +276,7 @@ async function runTurn( const abort = new AbortController() handle.setAbort(abort) - // Assemble once before pre-step so pressure checks and the request share the same prompt. + // Assemble once before pre-step so listener work and the request share one prompt value. const assembly = await ctx.systemPrompt.assemble(assembleContextFor(agent)) const fullSystemPrompt = renderPrompt(assembly) @@ -287,9 +287,9 @@ async function runTurn( break } - // Compose the request-only prefix once per loop instance before pressure - // checks. It precedes all derived history and is recorded only in the - // request header, not as session history. + // Compose the request-only prefix once per loop instance before the first + // request boundary. It precedes all derived history and is recorded only + // in the request header, not as session history. if (transmission.sessionPrefix === undefined) { const emptyPrefix: Message[] = deepFreeze([]) const composed = await events.waterfall( @@ -306,8 +306,8 @@ async function runTurn( transmission.sessionPrefix = deepFreeze(structuredClone(composed)) } - // Await surface mutations outside the step; pressure checks receive the pending prefix. - await events.serial('agent/pre-step', turn, step, fullSystemPrompt, transmission.sessionPrefix, abort.signal) + // Await surface mutations outside the step before snapshotting history. + await events.serial('agent/pre-step', turn, step, abort.signal) // Interruption landing during the pre-step seam: do not open an empty step. if (handle.isCancelled() || handle.isDisposed()) { diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 4b37210993..d89e5b0b0e 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -118,7 +118,7 @@ describe('agent/prompt-submit', () => { it('a prompt-submit rewrite + additionalContext is VISIBLE to the agent/pre-step seam (merged ordering)', async () => { // Prompt rewrites and injected context land before `agent/pre-step`, so a - // compaction listener measures the current surface before the single derive. + // surface listener sees the current state before the single derive. const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -130,8 +130,7 @@ describe('agent/prompt-submit', () => { additionalContext: { content: [{ type: 'text', text: 'injected ctx' }], source: { kind: 'plugin', plugin: 'test' } }, })) - // The pre-step seam (where compaction lives) derives the surface it would act - // on. Capture what it sees on the first step. + // Capture the surface visible at the generic pre-step seam on the first step. let preStepDerived: string | undefined ctx.on('agent/pre-step', (subject, _turn, step) => { if (subject === agent && step === 1) preStepDerived = JSON.stringify(subject.session.deriveMessages()) @@ -375,7 +374,7 @@ describe('agent/session-prefix', () => { expect(agent.session.deriveMessages()[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'go' }] }) }) - it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { + it('composes before the first pre-step and records the prefix on the request header', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -386,20 +385,15 @@ describe('agent/session-prefix', () => { order.push('compose') return [reminder, ...await next()] }) - const seen: (readonly Message[])[] = [] - ctx.on('agent/pre-step', (_agent, _turn, _step, _system, sessionPrefix) => { + ctx.on('agent/pre-step', () => { order.push('pre-step') - seen.push(sessionPrefix) }) send(agent, 'hi') await waitForIdle(ctx, agent) - // Composition precedes the pre-step seam, and the seam receives THIS - // instance's composed prefix — a token-pressure gate (compaction) counts - // what the request will actually carry, never a stale logged prefix. expect(order).toEqual(['compose', 'pre-step']) - expect(seen[0]).toEqual([reminder]) + expect(agent.session.requestHeader()?.messagePrefix).toEqual([reminder]) }) it('the canonical prepend pattern composes contributions in registration order', async () => { diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index f282301a2b..89d8cc306c 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -486,9 +486,8 @@ describe('agent loop', () => { it('agent/pre-step fires once per step before the step is opened', async () => { // Two steps (a tool call, then a final text turn) → two model calls → two - // pre-step fires, each carrying the assembled full system prompt, BEFORE - // the step is opened and its request is derived (the request the adapter - // sees reflects any surface state at fire time). + // pre-step fires BEFORE the step is opened and its request is derived (the + // request the adapter sees reflects any surface state at fire time). const adapter = new MockAdapter([ toolCallResponse('c1', 'echo', {}, 'calling echo'), textResponse('done'), @@ -500,21 +499,19 @@ describe('agent loop', () => { })) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] - ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { - if (subject === agent) fires.push({ turn, step, fullSystemPrompt }) + const fires: { turn: number; step: number; signal: AbortSignal }[] = [] + ctx.on('agent/pre-step', (subject, turn, step, signal) => { + if (subject === agent) fires.push({ turn, step, signal }) }) send(agent, 'go') await waitForIdle(ctx, agent) - // One fire per step, in order, each with the assembled system prompt - // (here just the loop's own harness-identity section — no persona set). - const HARNESS = 'You are an AI agent powered by the DeepSeek Harness SDK.' - expect(fires).toEqual([ - { turn: 1, step: 1, fullSystemPrompt: HARNESS }, - { turn: 1, step: 2, fullSystemPrompt: HARNESS }, + expect(fires.map(({ turn, step }) => ({ turn, step }))).toEqual([ + { turn: 1, step: 1 }, + { turn: 1, step: 2 }, ]) + expect(fires.every(({ signal }) => signal instanceof AbortSignal)).toBe(true) }) it('agent/pre-step fires BEFORE the step it precedes opens (events land outside the step)', async () => { diff --git a/packages/core/agent-loop/tests/request-recovery.spec.ts b/packages/core/agent-loop/tests/request-recovery.spec.ts index 003c678be0..416ede21b3 100644 --- a/packages/core/agent-loop/tests/request-recovery.spec.ts +++ b/packages/core/agent-loop/tests/request-recovery.spec.ts @@ -219,6 +219,48 @@ describe('agent post-step and request-error lifecycle', () => { }) }) + it('closes the successful step as disposed when disposal lands during post-step', async () => { + const adapter = new FailureScriptAdapter([ + toolCallResponse('dispose-call', 'work', {}), + textResponse('must not continue'), + ]) + const ctx = await harness(adapter) + ctx.tools.register(defineTool({ + name: 'work', + description: 'do work', + parameters: {}, + async execute() { return [{ type: 'text', text: 'worked' }] }, + })) + const agent = ctx.agentLoop.create(AgentId('dispose-post-step'), { model: 'mock' }) + let entered!: () => void + const postStepEntered = new Promise((resolve) => { entered = resolve }) + ctx.on('agent/post-step', async (_agent, turn, step, signal) => { + expect({ turn, step }).toEqual({ turn: 1, step: 1 }) + entered() + await new Promise((resolve) => { + signal.addEventListener('abort', () => { resolve() }, { once: true }) + }) + }) + + send(agent) + await postStepEntered + await ctx.fiber.dispose() + + expect(adapter.requests).toHaveLength(1) + const boundaries = agent.session.events.filter(event => + event.type === 'step/start' || event.type === 'step/end', + ) + expect(boundaries.map(event => event.type)).toEqual(['step/start', 'step/end']) + expect(boundaries.map(event => event.data)).toEqual([ + { turn: 1, step: 1 }, + { turn: 1, step: 1 }, + ]) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'disposed' } }, + }) + }) + it.each([ ['thrown', contextError()], ['in-band', [{ type: 'finish', reason: { kind: 'error', message: 'too large', code: CONTEXT_WINDOW_EXCEEDED_CODE } }] satisfies StreamChunk[]], diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 1eda0df2d7..05f473e07c 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -189,23 +189,17 @@ declare module 'cordis' { // ---- step/request extension seams (serial + waterfall) ---- /** - * Awaited serial checkpoint for session-surface mutation after prompt - * assembly and before `step/start`; appends land outside the pending step. - * The loop derives history once afterward, so compaction records and - * replacements are included without rewriting an assembled request. The - * prompt and prefix are the exact pressure inputs for that request, and + * Awaited serial checkpoint before `step/start`; appends land outside the + * pending step and are included when the loop derives request history. * `signal` cancels listener work. * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @param agent - the agent opening the step. * @param turn - the open turn number. * @param step - the pending step number. - * @param fullSystemPrompt - the assembled prompt. - * @param sessionPrefix - the frozen request prefix. * @param signal - the turn abort signal. * @mode serial */ - // TODO: Move prompt-pressure inputs behind a compaction-specific seam if no second consumer appears. - 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void + 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void /** * Allow, rewrite, or block one drained prompt before it becomes a user * message. Call `next()` for the unchanged default. @@ -233,9 +227,9 @@ declare module 'cordis' { * result is computed once per loop instance, logged on its anchoring request * header, and reused so the provider prefix remains stable. Interrupted * composition is discarded. Composition precedes the first `agent/pre-step` - * and request boundary, so listener appends join the current request and - * pressure accounting sees the composed prefix. Changing context belongs in - * history; contributors should prepend to `await next()` to preserve registration order. + * and request boundary, so listener appends join the current request. + * Changing context belongs in history; contributors should prepend to + * `await next()` to preserve registration order. * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @param agent - the agent whose session prefix is being composed. * @param prefix - the frozen seed; return an extended replacement. diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index 7af8d97848..af84c569b9 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -849,7 +849,7 @@ describe('scoped-dispatch invariants', () => { ['agent/status', [agent, 'idle']], ['agent/queued', [agent, [], { source: { kind: 'user' }, steering: false }]], ['agent/session-start', [agent, 'startup']], - ['agent/pre-step', [agent, 1, 1, '', new AbortController().signal]], + ['agent/pre-step', [agent, 1, 1, new AbortController().signal]], ['agent/prompt-submit', [agent, [], { kind: 'user' }, () => Promise.resolve({ kind: 'allow' })]], ['agent/request', [agent, 1, 1, { model: 'm' }, () => Promise.resolve({ model: 'm' })]], ['agent/session-prefix', [agent, [], new AbortController().signal, () => Promise.resolve([])]], diff --git a/packages/ui/user-approval/tests/approval.spec.ts b/packages/ui/user-approval/tests/approval.spec.ts index f248e5c468..0a2874499a 100644 --- a/packages/ui/user-approval/tests/approval.spec.ts +++ b/packages/ui/user-approval/tests/approval.spec.ts @@ -371,7 +371,7 @@ describe('approval policy (the approval/policy fold)', () => { } const preStep = (ctx: Context, agent: Agent): Promise => - ctx.serial('agent/pre-step', agent, 1, 1, '', [], new AbortController().signal) + ctx.serial('agent/pre-step', agent, 1, 1, new AbortController().signal) /** Append a `request/header` snapshot whose system text is exactly `system`. */ function appendHeader(session: Session, system: string): void { diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 11168ba000..05547c9b5b 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -228,7 +228,7 @@ const SERVICE_ROLES: ServiceRole[] = [ mode: 'seam', implementations: ['compact-basic'], consumers: ['compact-basic'], - note: 'The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred.', + note: 'The basic backend consumes post-step pressure and request-error recovery events; a model-facing compact tool remains deferred.', }, { key: 'subagents', @@ -841,6 +841,8 @@ function renderLifecycle(): string { '', 'The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set.', '', + '`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Recovery compacts between the closed failed step and a fresh retry step, and returns retry only when the surface replacement generation advances; otherwise the original request error remains authoritative.', + '', 'SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors.', '', ...maintenanceFooter(maintenance), diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index b0cea673ad..17bbb787dc 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -134,6 +134,7 @@ { "doc": "docs/core-data-structures/skills.md", "symbol": "Config", "source": "packages/skill/skill/src/index.ts" }, { "doc": "docs/core-data-structures/compaction.md", "symbol": "CompactionResult", "source": "packages/compact/compact/src/types.ts" }, + { "doc": "docs/core-data-structures/compaction.md", "symbol": "CompactionTrigger", "source": "packages/compact/compact/src/index.ts" }, { "doc": "docs/core-data-structures/subagent.md", "symbol": "SubagentCapabilities", "source": "packages/subagent/subagent/src/types.ts" }, { "doc": "docs/core-data-structures/subagent.md", "symbol": "SubagentStartRequest", "source": "packages/subagent/subagent/src/types.ts" }, From 8e7cf8cc10c3559ded0ee7f93f62d14ff5f18ad4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:09:18 +0800 Subject: [PATCH 103/323] Update ACP launcher example path --- packages/support/acp-snapshot/src/launcher.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/support/acp-snapshot/src/launcher.ts b/packages/support/acp-snapshot/src/launcher.ts index c0dc21dc06..95292df38a 100644 --- a/packages/support/acp-snapshot/src/launcher.ts +++ b/packages/support/acp-snapshot/src/launcher.ts @@ -27,7 +27,7 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) /** The unbuilt agent entry, leaf config, and workspace tsconfig an ACP test boots. */ export interface AgentUnderTest { - /** The agent bin entry (for example `packages/ui/acp-agent/src/bin.ts`). */ + /** The agent bin entry (for example `packages/examples/acp-demo/src/bin.ts`). */ binScript: string /** The leaf `cordis.yml` loaded by the bin. */ configPath: string From f6350ac553dc9f34b7c397eb62991e2566f1ca6b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:10:46 +0800 Subject: [PATCH 104/323] Keep root instructions within budget --- AGENTS.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index 0c5272b105..4209b0f95c 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -59,7 +59,7 @@ pnpm run demo:cordis # self-referential demo: the agent modifies its own runt pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) ``` -### Run the CI gates locally before marking a PR ready +### Run CI gates locally before marking a PR ready Run narrow checks during implementation and this CI-equivalent sequence before marking a PR ready. Fresh worktrees need `pnpm run build` before publint and NodeNext inspect `lib/`: From d25a56b431d98a6df3ff242df6386975acce05d4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:23:39 +0800 Subject: [PATCH 105/323] Restore CompactionResult diagnostics --- packages/compact/compact-basic/src/index.ts | 6 +++++- .../compact-basic/tests/compact-basic.spec.ts | 4 +++- packages/compact/compact/src/index.ts | 2 +- packages/compact/compact/src/types.ts | 8 ++++++++ packages/compact/compact/tests/compact.spec.ts | 16 ++++++++++++---- 5 files changed, 29 insertions(+), 7 deletions(-) diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 9449fc84f9..8bc21ddf5b 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -426,9 +426,13 @@ export class BasicCompactService extends CompactService { // compact/start and here leaves a detectable orphaned lock (a compact/start // with no matching compact/end) rather than a compact/end that falsely // claims compaction finished before the surface replacement landed. - session.append('compact/end', { turn: openTurn }) + const endEvent = session.append('compact/end', { turn: openTurn }) return { + startSeq: startEvent.seq, + summarySeq: summaryEvent.seq, + endSeq: endEvent.seq, + summary, shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 7cb872f274..4b06b321b7 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -346,6 +346,7 @@ describe('BasicCompactService.compactRegion', () => { expect(result.shadowedSeqs).toEqual([firstSeq, secondSeq]) expect(result.shadowedRange.start).toBe(firstSeq) expect(result.shadowedRange.end).toBe(secondSeq) + expect(result.summary).toEqual(svc.mockSummary) expect(result.shadowedTokenCount).toBe(20) const events = session.events @@ -1057,7 +1058,8 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { const session = multiTurnSession(2, 1) const nodes = session.surface.nodes - await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + const result = await compactRegion(svc, session, nodes[0]!, nodes[1]!, 'test-model') + expect(result.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) const summaryEvent = session.events.findLast(e => e.type === 'compact/summary')! expect(summaryEvent.data.summary).toEqual([{ type: 'text', text: 'CONDENSED' }]) // The raw summary is wrapped in the checkpoint framing on the surface. diff --git a/packages/compact/compact/src/index.ts b/packages/compact/compact/src/index.ts index e4baec6551..680f684ac6 100644 --- a/packages/compact/compact/src/index.ts +++ b/packages/compact/compact/src/index.ts @@ -73,7 +73,7 @@ export abstract class CompactService extends Service { * @param agent - context whose session is mutated and whose routing options guide summarization. * @param signal - optional cancellation; model-backed implementations must forward it. * @throws when compaction is active or the range is missing, reversed, or unbalanced. - * @returns the replaced range and token accounting; the durable event owns the summary. + * @returns the appended event seqs, summary, replaced range, and token accounting. */ abstract compactRegion( start: number, diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index 0d3d35ace8..10a5eabfcc 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -41,6 +41,14 @@ declare module '@deepseek-ai/dsh-session' { /** Result of a successful compaction operation. */ export interface CompactionResult { + /** The seq of the appended `compact/start` event. */ + startSeq: number + /** The seq of the appended `compact/summary` event. */ + summarySeq: number + /** The seq of the appended `compact/end` event. */ + endSeq: number + /** The summary content blocks produced by the backend. */ + summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index e34c8420d9..3d95c12249 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -34,17 +34,22 @@ class StubCompactService extends CompactService { ): Promise { this.lastSignal = signal const session = agent.session + const summary = [{ type: 'text' as const, text: 'stub' }] // Minimal stub honoring the lock + log-only event contract. - session.append('compact/start', { turn: 0 }) - session.append('compact/summary', { - summary: [{ type: 'text', text: 'stub' }], + const startEvent = session.append('compact/start', { turn: 0 }) + const summaryEvent = session.append('compact/summary', { + summary, shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, model: 'stub', }) - session.append('compact/end', { turn: 0 }) + const endEvent = session.append('compact/end', { turn: 0 }) return { + startSeq: startEvent.seq, + summarySeq: summaryEvent.seq, + endSeq: endEvent.seq, + summary, shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, @@ -92,6 +97,9 @@ describe('CompactService seam', () => { // verify the runtime value is absent. const raw = startEvent as unknown as { surfaceOp?: unknown } expect(raw.surfaceOp).toBeUndefined() + expect(result.summary).toEqual([{ type: 'text', text: 'stub' }]) + expect(result.summarySeq).toBeGreaterThan(result.startSeq) + expect(result.endSeq).toBeGreaterThan(result.summarySeq) expect(result.shadowedRange).toEqual({ start: 0, end: 0 }) expect(session.events.filter(e => e.type.startsWith('compact/')).map(e => e.type)) .toEqual(['compact/start', 'compact/summary', 'compact/end']) From 8eccd5416e58d1ea63f6dfb411a247ff6c272ced Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:25:39 +0800 Subject: [PATCH 106/323] Document restored compaction result fields --- docs/core-data-structures/compaction.md | 10 +++++++++- packages/cordis/tool-cordis/src/api-catalog.ts | 2 +- 2 files changed, 10 insertions(+), 2 deletions(-) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index d253166fcf..1075f3c985 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -20,10 +20,18 @@ These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` b ## `CompactionResult` -What a successful compaction returns to its caller: the shadowed range and seqs plus the estimated token count. The durable `compact/summary` event owns the raw summary and bookkeeping-event identity. +What a successful compaction returns to its caller: the bookkeeping-event seqs, raw summary, shadowed range and seqs, and estimated token count. ```ts type-equiv interface CompactionResult { + /** The seq of the appended `compact/start` event. */ + startSeq: number + /** The seq of the appended `compact/summary` event. */ + summarySeq: number + /** The seq of the appended `compact/end` event. */ + endSeq: number + /** The summary content blocks produced by the backend. */ + summary: ContentBlock[] /** * The surface-boundary pair that was shadowed: the seqs of the first * (`start`) and last (`end`) surface nodes of the replaced range. A diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 8e6477258e..bfa494f829 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -631,7 +631,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CompactionResult', - declaration: 'export interface CompactionResult {\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', + declaration: 'export interface CompactionResult {\n startSeq: number;\n summarySeq: number;\n endSeq: number;\n summary: ContentBlock[];\n shadowedRange: {\n start: number;\n end: number;\n };\n shadowedSeqs: number[];\n shadowedTokenCount: number;\n}', }, { name: 'ConfinedArgv', From cdeec6fc1d984adfdbd645d1a481dd0a2a9fdba8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:36:51 +0800 Subject: [PATCH 107/323] Update built JSON-RPC probe path --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index bc6642263e..ed4dfbb9db 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -33,7 +33,7 @@ const [ { SessionId }, ] = await Promise.all([ load("vendor/cordis/lib/index.js"), - load("packages/core/agent-core/lib/index.js"), + load("packages/examples/agent-spine-demo/lib/index.js"), load("packages/subagent/subagent/lib/index.js"), load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), load("packages/ui/jsonrpc/lib/index.js"), From d66c926d7a63d5416f766f2de90b16760ffb5176 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Wed, 15 Jul 2026 17:43:33 +0800 Subject: [PATCH 108/323] fix(agent): preserve lifecycle recovery boundaries (PR3 round 2) --- .../compact/compact-basic/src/automatic.ts | 1 + .../compact-basic/tests/compact-basic.spec.ts | 15 +++ packages/core/agent-loop/src/loop.ts | 6 +- .../tests/contract-regressions.spec.ts | 57 ++++++++++- packages/llm/llm/src/index.ts | 19 ++-- packages/llm/llm/tests/service.spec.ts | 95 ++++++++++++++----- 6 files changed, 151 insertions(+), 42 deletions(-) diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts index 16e71c081a..e837e076cc 100644 --- a/packages/compact/compact-basic/src/automatic.ts +++ b/packages/compact/compact-basic/src/automatic.ts @@ -45,6 +45,7 @@ export function registerAutomaticCompaction( _step: number, signal: AbortSignal, ) => { + if (signal.aborted) return try { const result = await service.compactIfNeeded(agent, 'pressure', signal) if (result !== null) logResult(result, 'post-step pressure') diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 163c2b6b45..d5e3246777 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -848,6 +848,21 @@ describe('automatic listener and loader composition', () => { expect(compact.calls).toHaveLength(1) }) + it('skips post-step pressure when the step signal is already aborted', async () => { + const ctx = createContext() + const compact = new TestCompactService(ctx, { + models: { [MODEL]: { thresholdRatio: 0.5, retainTokens: 18 } }, + }) + const pressured = conversation(4) + const compactIfNeeded = vi.spyOn(compact, 'compactIfNeeded') + + await expect(postStep(ctx, agent(pressured, MODEL), AbortSignal.abort('step aborted'))) + .resolves.toBeUndefined() + + expect(compactIfNeeded).not.toHaveBeenCalled() + expect(pressured.events.some(event => event.type === 'compact/start')).toBe(false) + }) + it('warns and continues after operational failures, including non-Errors', async () => { const ctx = createContext() const warnings: string[] = [] diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 620cdd9fbc..59b0d26088 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -650,7 +650,8 @@ async function runStep( session, turn, step, message.content, assembler.usage, chunkSeqs, ) - // Tool execution stays sequential; recheck abort around each normalized result. + // Tool execution stays sequential; cancellation latches synthetic results for + // every remaining call while preserving one complete result batch. const toolCalls = message.content.filter(block => block.type === 'tool-call') // Buffer context until all results are appended to preserve call/result adjacency. const pendingContext: HookContext[] = [] @@ -693,9 +694,6 @@ async function runStep( if (signal.aborted) aborted = true } - /* v8 ignore next -- signal.reason always set by cancellation or disposal. */ - if (aborted) throw new Error(String(signal.reason ?? 'aborted')) - // Append buffered context after the complete result batch. for (const context of pendingContext) { agent.inject(context.content, { source: context.source }) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 6ca06fc096..75afb08b0c 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -156,7 +156,7 @@ describe('successful provider completion survives agent/step-result failure', () }) describe('abort during tool execution ends the turn', () => { - it('aborting the in-flight step inside a tool prevents both remaining tools and the next model step', async () => { + it('balances an aborted tool batch through context, steering, and post-step before closing', async () => { const adapter = new MockAdapter([ // model asks for two tool calls in one step [ @@ -175,8 +175,12 @@ describe('abort during tool execution ends the turn', () => { name: 'aborter', description: '', parameters: {}, - async execute() { + async execute(_args, exec) { executed.push('aborter') + exec.agent?.steer( + [{ type: 'text', text: 'steering before abort' }], + { source: { kind: 'plugin', plugin: 'abort-test' } }, + ) // Fire the in-flight step's AbortController directly (the loop registers // it on the agent). This is the bare step-abort path — distinct from // cancel(), which would also clear the inbox; here the subject is the @@ -185,6 +189,13 @@ describe('abort during tool execution ends the turn', () => { return [{ type: 'text', text: 'done' }] }, })) + ctx.on('tools/post-execute', async exec => ({ + kind: 'accept', + additionalContext: { + content: [{ type: 'text', text: `context for ${exec.callId}` }], + source: { kind: 'plugin', plugin: 'abort-test' }, + }, + })) ctx.tools.register(defineTool({ name: 'second', description: '', @@ -196,13 +207,53 @@ describe('abort during tool execution ends the turn', () => { })) const reasons: TurnEndReason[] = [] - ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) + const order: string[] = [] + ctx.on('session/event', (session, event) => { + if (session !== agent.session) return + switch (event.type) { + case 'assistant/message': order.push('assistant/message'); break + case 'tool/call': order.push(`tool/call:${event.data.callId}`); break + case 'tool/result': { + const outcome = event.data.error?.code === 'ABORTED' ? 'synthetic-aborted' : 'real' + order.push(`tool/result:${event.data.callId}:${outcome}`) + break + } + case 'context/message': order.push('context/message'); break + case 'steering/message': order.push('steering/message'); break + case 'step/end': order.push('step/end'); break + case 'turn/end': { + reasons.push(event.data.reason) + order.push(`turn/end:${event.data.reason.kind}`) + break + } + } + }) + let postSteps = 0 + ctx.on('agent/post-step', (subject, turn, step, signal) => { + if (subject !== agent) return + postSteps += 1 + expect({ turn, step, aborted: signal.aborted }).toEqual({ turn: 1, step: 1, aborted: true }) + order.push('agent/post-step') + }) send(agent, 'go') await waitForIdle(ctx, agent) expect(executed).toEqual(['aborter']) // second tool never ran expect(adapter.requests).toHaveLength(1) // no follow-up model call + expect(postSteps).toBe(1) + expect(order).toEqual([ + 'assistant/message', + 'tool/call:c1', + 'tool/result:c1:real', + 'tool/call:c2', + 'tool/result:c2:synthetic-aborted', + 'context/message', + 'steering/message', + 'agent/post-step', + 'step/end', + 'turn/end:aborted', + ]) expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }]) const calls = agent.session.events.filter(event => event.type === 'tool/call') const results = agent.session.events.filter(event => event.type === 'tool/result') diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 0b933d12a7..1be716cbfb 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -124,8 +124,9 @@ export class LlmService extends Service { * Final adapter boundary. It tags only failures from adapter selection, * synchronous dispatch, iterator construction, or iteration while preserving * the original Error object. Middleware outside this generator remains - * distinguishable as plugin work. Adapter cleanup is best-effort after an - * earlier failure or downstream close and never masks the winning error. + * distinguishable as plugin work. An iteration failure skips adapter cleanup + * so it cannot suppress the primary provider error. A downstream close awaits + * adapter cleanup, whose failures remain ordinary untagged work. */ private async * adapterStream(options: GenerateOptions): AsyncGenerator { let iterator: AsyncIterator @@ -137,6 +138,7 @@ export class LlmService extends Service { } let completed = false + let iterationFailed = false try { while (true) { let value: StreamChunk @@ -148,6 +150,7 @@ export class LlmService extends Service { } value = item.value } catch (error: unknown) { + iterationFailed = true throw markLlmAdapterFailure(error) } // End the adapter-owned try before yielding: consumer/middleware @@ -155,14 +158,10 @@ export class LlmService extends Service { yield value } } finally { - if (!completed) { - try { - const close = iterator.return?.bind(iterator) - if (close) await close() - } catch { - // Lookup and invocation are both adapter-owned cleanup following an - // existing failure/downstream close; neither can replace it. - } + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- the iteration catch sets its latch before entering finally. + if (!completed && !iterationFailed) { + const close = iterator.return?.bind(iterator) + if (close) await close() } } } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 8dc46529bd..b488002666 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -72,11 +72,21 @@ describe('LlmService', () => { const original = new LlmError(`${field} getter failed`, 'RESULT_GETTER_FAILED') const result = field === 'done' ? {} : { done: false } Object.defineProperty(result, field, { get: () => { throw original } }) + let cleanupLookups = 0 + const iterator: AsyncIterator = { + next: () => Promise.resolve(result as unknown as IteratorResult), + } + Object.defineProperty(iterator, 'return', { + get: () => { + cleanupLookups += 1 + throw new Error('return getter must not run after iteration fails') + }, + }) const adapter = new class extends LlmAdapter { stream(_options: GenerateOptions): AsyncIterable { return { [Symbol.asyncIterator](): AsyncIterator { - return { next: () => Promise.resolve(result as unknown as IteratorResult) } + return iterator }, } } @@ -94,6 +104,7 @@ describe('LlmService', () => { expect(caught).toBe(original) expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupLookups).toBe(0) }) it.each(['dispatch', 'iterator'] as const)('tags synchronous adapter %s failures without replacing their Error', async (boundary) => { @@ -119,7 +130,7 @@ describe('LlmService', () => { expect(isLlmAdapterFailure(caught)).toBe(true) }) - it('tags adapter iteration failures without replacing the original Error or cleanup outcome', async () => { + it('propagates a rejected next promptly without awaiting a non-settling return', async () => { const original = new LlmError('provider failed', 'PROVIDER_FAILED') let cleanupCalls = 0 const adapter = new class extends LlmAdapter { @@ -130,7 +141,49 @@ describe('LlmService', () => { next: () => Promise.reject(original), return: () => { cleanupCalls += 1 - return Promise.reject(new Error('cleanup failed')) + return new Promise>(() => {}) + }, + } + }, + } + } + }() + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['test-model'], adapter) + + const failure = (async (): Promise => { + try { + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + } catch (error: unknown) { + return error + } + return new Error('expected adapter iteration to fail') + })() + let timer: ReturnType | undefined + const timeout = new Promise((resolve) => { + timer = setTimeout(() => { resolve(new Error('adapter failure did not settle promptly')) }, 100) + }) + const caught = await Promise.race([failure, timeout]) + if (timer !== undefined) clearTimeout(timer) + + expect(caught).toBe(original) + expect(isLlmAdapterFailure(caught)).toBe(true) + expect(cleanupCalls).toBe(0) + }) + + it('awaits one adapter return on downstream close and leaves its rejection unclassified', async () => { + const cleanup = new Error('cleanup failed') + let cleanupCalls = 0 + const adapter = new class extends LlmAdapter { + stream(_options: GenerateOptions): AsyncIterable { + return { + [Symbol.asyncIterator](): AsyncIterator { + return { + next: () => Promise.resolve({ done: false, value: SCRIPT[0]! }), + return: () => { + cleanupCalls += 1 + return Promise.reject(cleanup) }, } }, @@ -143,45 +196,37 @@ describe('LlmService', () => { let caught: unknown try { - for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) break } catch (error: unknown) { caught = error } - expect(caught).toBe(original) - expect(isLlmAdapterFailure(caught)).toBe(true) + expect(caught).toBe(cleanup) + expect(isLlmAdapterFailure(caught)).toBe(false) expect(cleanupCalls).toBe(1) }) - it('contains a throwing iterator.return getter after next fails without replacing the original Error', async () => { - const original = new LlmError('provider failed', 'PROVIDER_FAILED') - let cleanupLookups = 0 - const iterator: AsyncIterator = { next: () => Promise.reject(original) } - Object.defineProperty(iterator, 'return', { - get: () => { - cleanupLookups += 1 - throw new Error('return getter failed') - }, - }) + it('allows downstream close when the adapter iterator has no return method', async () => { const adapter = new class extends LlmAdapter { stream(_options: GenerateOptions): AsyncIterable { - return { [Symbol.asyncIterator]: () => iterator } + return { + [Symbol.asyncIterator](): AsyncIterator { + return { next: () => Promise.resolve({ done: false, value: SCRIPT[0]! }) } + }, + } } }() const ctx = new Context() await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], adapter) - let caught: unknown - try { - for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { /* drain */ } - } catch (error: unknown) { - caught = error + let chunks = 0 + for await (const _chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) { + chunks += 1 + break } - expect(caught).toBe(original) - expect(isLlmAdapterFailure(caught)).toBe(true) - expect(cleanupLookups).toBe(1) + expect(chunks).toBe(1) }) it('normalizes and tags non-Error adapter failures once', async () => { From 87c900dfb2a8b73f153828a01c9fbd90cd962311 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:55:48 +0800 Subject: [PATCH 109/323] Document compaction result diagnostics --- packages/compact/compact/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 51ba50382f..0e0b63d765 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -21,6 +21,8 @@ Both methods are **abstract** — the backend owns the entire strategy (token es | `compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal)` | Estimate the surface-derived history size; if over the backend's threshold, compact an older range via `compactRegion`, keeping recent context intact. Returns the `CompactionResult`, or `null` if nothing needed compacting. All parameters required — the loop's `agent/pre-step` checkpoint supplies the agent, assembled `fullSystemPrompt`, composed `sessionPrefix` (request-only messages every request carries but the derived history omits — the pressure estimate must count them), and turn `signal`. A backend's summarization request is a direct `ctx.llm.stream()` call (not a loop step), so per-call interception happens at `llm/stream`. | | `compactRegion(start, end, agent, signal?)` | Forcibly summarize surface nodes `[start, end]` (inclusive seqs) from `agent.session` into a single replacement node. **Throws** if a compaction is already in progress, if `start`/`end` aren't surface nodes, or if `start` is positioned after `end` on the surface. The range is a SURFACE-POSITION span, not a numeric seq interval — after a prior replace lands a fresh high-seq summary node at the shadowed range's position, surface order no longer tracks seq order. | +`CompactionResult` keeps the raw summary and bookkeeping-event seqs available to callers alongside the shadowed range and token accounting; its drift-checked shape lives in the [compaction data-structure reference](../../../docs/core-data-structures/compaction.md#compactionresult). + `compactIfNeeded` takes a required `signal`; `compactRegion`'s is optional. A backend that summarizes via `ctx.llm.stream()` **must** forward it into the call's `GenerateOptions.signal`, so an abort or fiber dispose tears down the in-flight summarization instead of leaving an orphaned model call running past the cancellation. The session being compacted comes from the agent context; the turn that the `compact/*` events belong to is recoverable from the log (the currently-open turn), so the backend stamps it from the log rather than trusting a caller-supplied value. ## Surface contract From 6af61c6f4e89dedeec5b60886eed16144a37cf10 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 18:08:28 +0800 Subject: [PATCH 110/323] fix(docs): align site with bilingual source pairs --- .agents/skills/dsh-doc-site-sync/SKILL.md | 6 +- docs/AGENTS.md | 2 +- docs/user/develop/basic/config.i18n.yaml | 6 + docs/user/develop/basic/config.md | 111 ++++++++++ .../config.md => develop/basic/config.zh.md} | 20 +- docs/user/develop/basic/index.i18n.yaml | 6 + docs/user/develop/basic/index.md | 151 +++++++++++++ .../index.md => develop/basic/index.zh.md} | 36 +-- docs/user/develop/basic/tool.i18n.yaml | 6 + docs/user/develop/basic/tool.md | 208 ++++++++++++++++++ .../tool.md => develop/basic/tool.zh.md} | 69 +++--- docs/user/develop/framework/events.i18n.yaml | 6 + docs/user/develop/framework/events.md | 143 ++++++++++++ .../framework/events.zh.md} | 47 ++-- docs/user/develop/framework/index.i18n.yaml | 6 + docs/user/develop/framework/index.md | 131 +++++++++++ .../framework/index.zh.md} | 26 ++- docs/user/develop/framework/service.i18n.yaml | 6 + docs/user/develop/framework/service.md | 148 +++++++++++++ .../framework/service.zh.md} | 34 +-- docs/user/develop/practice/index.i18n.yaml | 6 + docs/user/develop/practice/index.md | 158 +++++++++++++ .../index.md => develop/practice/index.zh.md} | 18 +- .../develop/practice/llm-adapter.i18n.yaml | 6 + docs/user/develop/practice/llm-adapter.md | 185 ++++++++++++++++ docs/user/develop/practice/llm-adapter.zh.md | 185 ++++++++++++++++ docs/user/guide/config.i18n.yaml | 6 + docs/user/guide/config.md | 59 +++++ .../guide/config.md => guide/config.zh.md} | 10 +- docs/user/guide/index.i18n.yaml | 6 + docs/user/guide/index.md | 49 +++++ .../guide/index.md => guide/index.zh.md} | 6 +- docs/user/guide/quickstart.i18n.yaml | 6 + docs/user/guide/quickstart.md | 99 +++++++++ .../quickstart.md => guide/quickstart.zh.md} | 14 +- docs/user/index.i18n.yaml | 6 + docs/user/index.md | 25 +++ docs/user/{zh-CN/index.md => index.zh.md} | 4 + .../zh-CN/develop/practice/llm-adapter.md | 174 --------------- scripts/project-doc-site.spec.ts | 54 ++++- scripts/project-doc-site.ts | 99 ++++++++- scripts/translation-pairing.manifest.json | 12 + website/docs.ts | 110 +++++---- 43 files changed, 2112 insertions(+), 353 deletions(-) create mode 100644 docs/user/develop/basic/config.i18n.yaml create mode 100644 docs/user/develop/basic/config.md rename docs/user/{zh-CN/develop/basic/config.md => develop/basic/config.zh.md} (90%) create mode 100644 docs/user/develop/basic/index.i18n.yaml create mode 100644 docs/user/develop/basic/index.md rename docs/user/{zh-CN/develop/basic/index.md => develop/basic/index.zh.md} (83%) create mode 100644 docs/user/develop/basic/tool.i18n.yaml create mode 100644 docs/user/develop/basic/tool.md rename docs/user/{zh-CN/develop/basic/tool.md => develop/basic/tool.zh.md} (80%) create mode 100644 docs/user/develop/framework/events.i18n.yaml create mode 100644 docs/user/develop/framework/events.md rename docs/user/{zh-CN/develop/framework/events.md => develop/framework/events.zh.md} (83%) create mode 100644 docs/user/develop/framework/index.i18n.yaml create mode 100644 docs/user/develop/framework/index.md rename docs/user/{zh-CN/develop/framework/index.md => develop/framework/index.zh.md} (80%) create mode 100644 docs/user/develop/framework/service.i18n.yaml create mode 100644 docs/user/develop/framework/service.md rename docs/user/{zh-CN/develop/framework/service.md => develop/framework/service.zh.md} (80%) create mode 100644 docs/user/develop/practice/index.i18n.yaml create mode 100644 docs/user/develop/practice/index.md rename docs/user/{zh-CN/develop/practice/index.md => develop/practice/index.zh.md} (94%) create mode 100644 docs/user/develop/practice/llm-adapter.i18n.yaml create mode 100644 docs/user/develop/practice/llm-adapter.md create mode 100644 docs/user/develop/practice/llm-adapter.zh.md create mode 100644 docs/user/guide/config.i18n.yaml create mode 100644 docs/user/guide/config.md rename docs/user/{zh-CN/guide/config.md => guide/config.zh.md} (71%) create mode 100644 docs/user/guide/index.i18n.yaml create mode 100644 docs/user/guide/index.md rename docs/user/{zh-CN/guide/index.md => guide/index.zh.md} (94%) create mode 100644 docs/user/guide/quickstart.i18n.yaml create mode 100644 docs/user/guide/quickstart.md rename docs/user/{zh-CN/guide/quickstart.md => guide/quickstart.zh.md} (88%) create mode 100644 docs/user/index.i18n.yaml create mode 100644 docs/user/index.md rename docs/user/{zh-CN/index.md => index.zh.md} (93%) delete mode 100644 docs/user/zh-CN/develop/practice/llm-adapter.md diff --git a/.agents/skills/dsh-doc-site-sync/SKILL.md b/.agents/skills/dsh-doc-site-sync/SKILL.md index 0fdd9b9398..bee1b0dfe8 100644 --- a/.agents/skills/dsh-doc-site-sync/SKILL.md +++ b/.agents/skills/dsh-doc-site-sync/SKILL.md @@ -7,6 +7,8 @@ description: Use when publishing, updating, moving, or removing DeepSeek Harness Keep repository Markdown as the only editable content source. Treat the website as a tested projection: [website/docs.ts](../../../website/docs.ts) selects public pages, [scripts/project-doc-site.ts](../../../scripts/project-doc-site.ts) rewrites them into the disposable `website/.generated/` tree, and VitePress builds that tree. +Repository translations follow the sibling pairing contract: English `foo.md`, Chinese `foo.zh.md`, and `foo.i18n.yaml` live together. Never create `zh-CN/` or other locale directories for website content. The site route trees are independent of that source layout: `foo.zh.md` projects to the root route and `foo.md` projects to the matching `/en/` route. + ## Read the owning contracts - Read [docs/AGENTS.md](../../../docs/AGENTS.md) and use [dsh-doc-standards](../dsh-doc-standards/SKILL.md) when deciding where content belongs or changing product documentation prose. @@ -28,7 +30,7 @@ Never edit or commit `website/.generated/`, `website/.cache/`, or `website/.dist Set every `DocsPage` field deliberately: -- `source`: repository-relative canonical Markdown path. +- `source`: repository-relative canonical Markdown path. For a complete bilingual pair, add the English `.md` path through `pairedPages()`; it derives the sibling `.zh.md`, the content locales, and counterpart aliases. - `route`: public VitePress path including the `.md` suffix. - `label`: sidebar label, not necessarily the document H1. - `sidebar`: reuse `zh-guide`, `zh-develop`, or `en-docs` unless the information architecture genuinely needs another collection. @@ -36,7 +38,7 @@ Set every `DocsPage` field deliberately: - `order`: stable order within the section. - `sourceAliases`: optional additional repository paths that should resolve to this page when links are projected. It does not create another public route. -Keep the manifest an explicit public allowlist. Do not publish RFCs, postmortems, testing guides, `AGENTS.md`, or maintainer workflows merely because they exist under `docs/`; add internal material only when the user explicitly changes the publication boundary. +Use `mirroredPages()` only for a source that intentionally falls back to the same available language in both route trees. Convert that entry to `pairedPages()` when its counterpart is added. Keep the manifest an explicit public allowlist. Do not publish RFCs, postmortems, testing guides, `AGENTS.md`, or maintainer workflows merely because they exist under `docs/`; add internal material only when the user explicitly changes the publication boundary. ## Preserve link behavior diff --git a/docs/AGENTS.md b/docs/AGENTS.md index 42f46b64e4..2723434e64 100644 --- a/docs/AGENTS.md +++ b/docs/AGENTS.md @@ -15,7 +15,7 @@ Each fact has one home: the tier whose job it is. Elsewhere, link to that home; | [rfc/](rfc/README.md) | Decision records: the why, what-was-given-up, and concise verification contract; `implemented/` RFCs describe shipped reality in present tense | Migration plans, acceptance-task checklists, fixture walkthroughs, and spec-speak ("should…") once the decision has shipped | | [postmortem/](postmortem/README.md) | Incident stories — the only tier where war-story narrative belongs | — | | [cookbook/](cookbook/adding-a-package.md) | Step-by-step how-tos with numbered verify steps | Design rationale (→ the RFC each guide links) | -| [user/](user/zh-CN/index.md) | Product-facing guides published by the documentation website | Generated reference tables, contributor procedures, decision history | +| [user/](user/index.md) | Product-facing guides published by the documentation website | Generated reference tables, contributor procedures, decision history | | Package README | The per-package contract: config, semantics, limitations, extension points, and [Model Experience](cookbook/adding-a-package.md#4-write-the-package-readme) | JSDoc restatement, generated-catalog restatement (event/tool tables), other packages' concerns | | [development.md](development.md) | First-stop contributor onboarding: local setup, daily workflow, and CI shape at summary level; a bilingual pair under the [i18n contract](i18n/README.md) | Runtime/version rationale (→ RFCs), gate-by-gate enumerations that drift from `package.json` scripts | | Generated catalogs: [cordis events](cordis-catalog/events.md), [cordis services](cordis-catalog/services.md), [tool-catalog](tool-catalog.md), [config-catalog](config-catalog.md), [persistence-catalog](persistence-catalog.md), [module-graph.md](module-graph.md) | Exhaustive enumerations regenerated from source, freshness-gated | Hand edits of any kind | diff --git a/docs/user/develop/basic/config.i18n.yaml b/docs/user/develop/basic/config.i18n.yaml new file mode 100644 index 0000000000..e4b71a7353 --- /dev/null +++ b/docs/user/develop/basic/config.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +config.md: 5c4e712e2ae452d30fde23bd2481f0c5260ee526 +config.zh.md: 23c97e18a119a92fe7ae883621cb9340ef54bf80 diff --git a/docs/user/develop/basic/config.md b/docs/user/develop/basic/config.md new file mode 100644 index 0000000000..5c4e712e2a --- /dev/null +++ b/docs/user/develop/basic/config.md @@ -0,0 +1,111 @@ +# Plugin configuration + +English | [中文](config.zh.md) + +Accept configuration supplied through `cordis.yml`. + +## Define the Config type + +Export a `Config` type and a same-named Schemastery schema. Put defaults directly on the schema fields: + +```ts +import type { Context } from 'cordis' +import Schema from 'schemastery' + +export const name = 'my-plugin' + +export interface Config { + greeting: string + maxRetries: number + verbose?: boolean +} + +export const Config: Schema = Schema.object({ + greeting: Schema.string().default('Hello'), + maxRetries: Schema.number().default(3), + verbose: Schema.boolean().default(false), +}) + +export function apply(ctx: Context, config: Config) { + console.log(config.greeting) // User value or schema default. +} +``` + +Configure it in `cordis.yml`: + +```yaml +- name: './src/my-plugin.ts' + config: + greeting: 'Hi there' + maxRetries: 5 +``` + +When loading the plugin, Cordis uses the exported schema to validate configuration and fill defaults. Do not export a plain object as `Config`; it does not implement the Standard Schema interface required by Cordis. + +## Schema validation + +Use Schemastery to express stricter validation: + +```ts +import type { Context } from 'cordis' +import Schema from 'schemastery' + +export const name = 'validated-plugin' + +export interface Config { + apiKey: string + timeout: number + mode: 'fast' | 'accurate' +} + +export const Config = Schema.object({ + apiKey: Schema.string().required(), + timeout: Schema.number().default(30000), + mode: Schema.union(['fast', 'accurate']).default('fast'), +}) + +export function apply(ctx: Context, config: Config) { + // config is validated and type-safe. +} +``` + +The schema runs while the plugin loads. Invalid configuration fails the load with an actionable error. + +## Design principles + +### Do not hardcode tunable values + +Harness requires **anything that two deployments may want to set differently to be a configuration field**. + +```ts +// Wrong: hardcoded timeout. +const TIMEOUT = 30000 + +// Correct: configurable. +export interface Config { + timeoutMs: number // Defaults to 30000. +} +``` + +The test is whether `cordis.yml` can change the value without a code edit. + +### Fail loudly on invalid configuration + +If configuration refers to a missing model or another nonexistent resource, fail early instead of silently skipping it: + +```ts ignore-check +export function apply(ctx: Context, config: Config) { + if (!ctx.llm.models().includes(config.model)) { + throw new Error(`Model "${config.model}" is not registered by any LLM adapter`) + } +} +``` + +## Work with HMR + +A configuration edit hot-replaces the plugin: the framework unloads the old instance and loads a new one. Because registrations are effects and clean themselves up, replacement does not retain the old instance's registrations. + +## Next steps + +- [Plugins and lifecycle](../framework/) — understand the full plugin lifecycle +- [Services and dependencies](../framework/service.md) — provide a service to other plugins diff --git a/docs/user/zh-CN/develop/basic/config.md b/docs/user/develop/basic/config.zh.md similarity index 90% rename from docs/user/zh-CN/develop/basic/config.md rename to docs/user/develop/basic/config.zh.md index 23294f7955..23c97e18a1 100644 --- a/docs/user/zh-CN/develop/basic/config.md +++ b/docs/user/develop/basic/config.zh.md @@ -1,12 +1,14 @@ # 插件配置 +[English](config.md) | 中文 + 让你的插件接受用户在 `cordis.yml` 中传入的配置。 ## 定义 Config 类型 在插件中导出一个 `Config` 类型和同名的 Schemastery schema；默认值直接写在 schema 中： -```typescript +```ts import type { Context } from 'cordis' import Schema from 'schemastery' @@ -25,7 +27,7 @@ export const Config: Schema = Schema.object({ }) export function apply(ctx: Context, config: Config) { - console.log(config.greeting) // 用户配置或默认值 + console.log(config.greeting) // User value or schema default. } ``` @@ -44,7 +46,7 @@ export function apply(ctx: Context, config: Config) { 对于需要严格校验的场景，使用 Schemastery 定义 schema： -```typescript +```ts import type { Context } from 'cordis' import Schema from 'schemastery' @@ -63,7 +65,7 @@ export const Config = Schema.object({ }) export function apply(ctx: Context, config: Config) { - // config 已经过校验，类型安全 + // config is validated and type-safe. } ``` @@ -75,13 +77,13 @@ Schema 在插件加载时执行校验。如果配置不合法，插件会加载 Harness 的约定：**任何两个部署可能想要不同值的东西，都应该是配置字段**。 -```typescript -// 错误 — 硬编码超时时间 +```ts +// Wrong: hardcoded timeout. const TIMEOUT = 30000 -// 正确 — 可配置 +// Correct: configurable. export interface Config { - timeoutMs: number // 默认 30000 + timeoutMs: number // Defaults to 30000. } ``` @@ -91,7 +93,7 @@ export interface Config { 如果配置引用了不存在的东西（比如一个不存在的模型名），应该尽早报错，而不是静默跳过： -```typescript +```ts ignore-check export function apply(ctx: Context, config: Config) { if (!ctx.llm.models().includes(config.model)) { throw new Error(`Model "${config.model}" is not registered by any LLM adapter`) diff --git a/docs/user/develop/basic/index.i18n.yaml b/docs/user/develop/basic/index.i18n.yaml new file mode 100644 index 0000000000..22b03af93e --- /dev/null +++ b/docs/user/develop/basic/index.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +index.md: 5fa46806bc195ad2566fc0a29b45eb1dd7a68179 +index.zh.md: a6d238c12841c8c25b00376ee032e5db50fc6b4e diff --git a/docs/user/develop/basic/index.md b/docs/user/develop/basic/index.md new file mode 100644 index 0000000000..5fa46806bc --- /dev/null +++ b/docs/user/develop/basic/index.md @@ -0,0 +1,151 @@ +# Your first plugin + +English | [中文](index.zh.md) + +This guide creates a minimal Harness plugin and loads it into an agent. + +## What is a plugin? + +In Harness, a plugin is a TypeScript module that exports an `apply` function. The framework calls `apply` when loading the plugin and passes a `ctx` context object through which the plugin registers capabilities: + +```ts +import type { Context } from 'cordis' + +export const name = 'my-plugin' + +export function apply(ctx: Context) { + // Register capabilities here. +} +``` + +That is the complete shape. + +## Create the plugin file + +Create `src/my-plugin.ts` in your project: + +```ts +import type { Context } from 'cordis' + +export const name = 'hello-plugin' + +export function apply(ctx: Context) { + // Required dependencies are ready before apply runs. + console.log('[hello-plugin] plugin loaded!') +} +``` + +## Register it in cordis.yml + +Add an entry to `cordis.yml`: + +```yaml +- id: hello + name: './src/my-plugin.ts' +``` + +After startup, the console prints `[hello-plugin] plugin loaded!`. + +## Automatic cleanup + +Anything registered through `ctx`—event listeners, tools, or timers—is cleaned up when the plugin unloads. You do not need to call removeListener or clearInterval manually. + +For a resource that needs explicit cleanup, such as a network connection, use `ctx.effect()` to provide its disposer: + +```ts +import type { Context } from 'cordis' + +export function apply(ctx: Context) { + ctx.effect(() => { + const timer = setInterval(() => { + console.log('heartbeat') + }, 5000) + + // The returned function runs when the plugin unloads. + return () => clearInterval(timer) + }) +} +``` + +## Declare dependencies + +If the plugin consumes another service such as `tools` or `llm`, declare it in `inject`: + +```ts ignore-check +import type { Context } from 'cordis' + +export const name = 'my-tool-plugin' +export const inject = ['tools'] + +export function apply(ctx: Context) { + // ctx.tools is ready here. + ctx.tools.register(/* ... */) +} +``` + +The framework waits for every required service before loading the plugin. + +## Three plugin forms + +In addition to a function module, a plugin can use object or class form. + +### Object form + +```ts +import type { Context } from 'cordis' + +export default { + name: 'my-plugin', + inject: ['tools'], + apply(ctx: Context) { + // ... + }, +} +``` + +### Class form + +```ts +import { Service, type Context } from 'cordis' + +export default class MyService extends Service { + static inject = ['tools'] + + constructor(ctx: Context) { + super(ctx, 'myService') + // Perform synchronous initialization in the constructor. + } +} +``` + +Function form is sufficient in most cases. Use class form when the plugin provides a service to other plugins; see [services and dependencies](../framework/service.md). + +## Complete example + +`examples/echo-agent/src/echo-tool.ts` is a plugin that registers a tool: + +```ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + +export const name = 'echo-tool' +export const inject = ['tools'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'echo', + description: 'Echo the given text back, uppercased.', + parameters: { + text: { type: 'string', required: true }, + }, + async execute(args) { + return [{ type: 'text', text: `ECHO: ${args.text.toUpperCase()}` }] + }, + })) +} +``` + +## Next steps + +- [Build a tool](./tool.md) — learn the tool definition DSL +- [Plugin configuration](./config.md) — accept user configuration diff --git a/docs/user/zh-CN/develop/basic/index.md b/docs/user/develop/basic/index.zh.md similarity index 83% rename from docs/user/zh-CN/develop/basic/index.md rename to docs/user/develop/basic/index.zh.md index c1f7ab800b..a6d238c128 100644 --- a/docs/user/zh-CN/develop/basic/index.md +++ b/docs/user/develop/basic/index.zh.md @@ -1,18 +1,20 @@ # 第一个插件 +[English](index.md) | 中文 + 本文带你编写一个最小的 Harness 插件并加载到 Agent 中。 ## 插件是什么 在 Harness 中，插件是一个导出 `apply` 函数的 TypeScript 模块。框架在加载时调用 `apply`，传入一个 `ctx`（上下文对象），你通过 `ctx` 注册能力： -```typescript +```ts import type { Context } from 'cordis' export const name = 'my-plugin' export function apply(ctx: Context) { - // 在这里注册能力 + // Register capabilities here. } ``` @@ -22,14 +24,14 @@ export function apply(ctx: Context) { 在你的项目目录下创建 `src/my-plugin.ts`： -```typescript +```ts import type { Context } from 'cordis' export const name = 'hello-plugin' export function apply(ctx: Context) { - // apply 被调用时，插件的必选依赖已就绪 - console.log('[hello-plugin] 插件已加载!') + // Required dependencies are ready before apply runs. + console.log('[hello-plugin] plugin loaded!') } ``` @@ -42,7 +44,7 @@ export function apply(ctx: Context) { name: './src/my-plugin.ts' ``` -启动后你会在控制台看到 `[hello-plugin] 插件已加载!`。 +启动后你会在控制台看到 `[hello-plugin] plugin loaded!`。 ## 自动清理 @@ -50,14 +52,16 @@ export function apply(ctx: Context) { 如果你有需要手动清理的资源（比如一个网络连接），用 `ctx.effect()` 告诉框架怎么清理： -```typescript +```ts +import type { Context } from 'cordis' + export function apply(ctx: Context) { ctx.effect(() => { const timer = setInterval(() => { console.log('heartbeat') }, 5000) - // 返回的函数会在插件卸载时被调用 + // The returned function runs when the plugin unloads. return () => clearInterval(timer) }) } @@ -67,12 +71,14 @@ export function apply(ctx: Context) { 如果你的插件需要使用其他服务（如 `tools`、`llm`），需要声明 `inject`： -```typescript +```ts ignore-check +import type { Context } from 'cordis' + export const name = 'my-tool-plugin' export const inject = ['tools'] export function apply(ctx: Context) { - // ctx.tools 现在可用 + // ctx.tools is ready here. ctx.tools.register(/* ... */) } ``` @@ -85,7 +91,9 @@ export function apply(ctx: Context) { ### 对象形式 -```typescript +```ts +import type { Context } from 'cordis' + export default { name: 'my-plugin', inject: ['tools'], @@ -97,7 +105,7 @@ export default { ### 类形式 -```typescript +```ts import { Service, type Context } from 'cordis' export default class MyService extends Service { @@ -105,7 +113,7 @@ export default class MyService extends Service { constructor(ctx: Context) { super(ctx, 'myService') - // 构造函数内完成同步初始化 + // Perform synchronous initialization in the constructor. } } ``` @@ -116,7 +124,7 @@ export default class MyService extends Service { 参考仓库中的 `examples/echo-agent/src/echo-tool.ts`，这是一个注册 tool 的插件： -```typescript +```ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' diff --git a/docs/user/develop/basic/tool.i18n.yaml b/docs/user/develop/basic/tool.i18n.yaml new file mode 100644 index 0000000000..d2f4343cf1 --- /dev/null +++ b/docs/user/develop/basic/tool.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +tool.md: 416733bcb584fa5303a8b3ba5e6e904302e7f992 +tool.zh.md: fce9a7d9b973853c8b4fb9ae2c034e749d8da999 diff --git a/docs/user/develop/basic/tool.md b/docs/user/develop/basic/tool.md new file mode 100644 index 0000000000..416733bcb5 --- /dev/null +++ b/docs/user/develop/basic/tool.md @@ -0,0 +1,208 @@ +# Build a tool + +English | [中文](tool.zh.md) + +A tool is a capability the model can call. This guide builds one with `defineTool`. + +## Minimal example + +```ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + +export const name = 'my-tool' +export const inject = ['tools'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'greet', + description: 'Greet someone by name.', + parameters: { + name: { type: 'string', required: true, description: 'The name to greet' }, + }, + async execute(args) { + // args is inferred as { name: string }. + return [{ type: 'text', text: `Hello, ${args.name}!` }] + }, + })) +} +``` + +## Parameter definitions + +`parameters` uses a compact format that the framework converts to the JSON Schema sent to the model. + +### Primitive types + +```ts +export const parameters = { + path: { type: 'string', required: true }, + limit: { type: 'number' }, + recursive: { type: 'boolean' }, +} +// Inferred type: { path: string; limit?: number; recursive?: boolean } +``` + +### Enums + +```ts +export const parameters = { + mode: { type: 'string', required: true, enum: ['read', 'write', 'append'] }, +} +// Inferred type: { mode: string } (enum values are validated at runtime) +``` + +### Nested objects + +```ts +export const parameters = { + options: { + type: 'object', + properties: { + timeout: { type: 'number' }, + retries: { type: 'number' }, + }, + }, +} +// Inferred type: { options?: { timeout?: number; retries?: number } } +``` + +### Arrays + +```ts +export const parameters = { + tags: { + type: 'array', + items: { type: 'string' }, + }, +} +// Inferred type: { tags?: string[] } +``` + +### Property fields + +| Field | Type | Meaning | +|------|------|------| +| `type` | `'string' \| 'number' \| 'boolean' \| 'object' \| 'array'` | Value type | +| `required` | `true` | Marks the property required and affects inference | +| `description` | `string` | Description sent to the model | +| `enum` | `string[]` | Allowed string values | +| `properties` | `SchemaSpec` | Nested properties for an object | +| `items` | `SchemaProp` | Element schema for an array | + +## The execute function + +`execute` receives validated, inferred `args` and an `exec` execution context: + +```ts +import { defineTool } from '@deepseek-ai/dsh-tools' + +export const tool = defineTool({ + name: 'example', + description: 'Return an example result.', + parameters: {}, + async execute(args, exec) { + // args: inferred from parameters + // exec: ToolExecution context + + // Return a ContentBlock array. + void args + void exec + return [{ type: 'text', text: 'result here' }] + }, +}) +``` + +### Return value + +`execute` returns a `ContentBlock[]` that becomes the tool result visible to the model: + +```ts ignore-check +// Text result +return [{ type: 'text', text: 'file content here...' }] + +// Multiple blocks +return [ + { type: 'text', text: 'Found 3 matches:' }, + { type: 'text', text: matchResults.join('\n') }, +] +``` + +### Argument validation + +Before calling `execute`, `defineTool` validates model-generated arguments. Invalid input raises `ToolArgsError`; the framework turns it into an `isError` result so the model can correct its call. + +Do not repeat type validation inside `execute`. + +## Presentation + +A tool can define UI presentation methods for terminal and ACP clients: + +```ts ignore-check +defineTool({ + name: 'bash', + // ... + presentCall(args) { + return { + card: 'terminal', + title: args.command, + } + }, + presentResult(args, result) { + return { + card: 'terminal', + output: result.content.map(b => b.type === 'text' ? b.text : '').join(''), + } + }, +}) +``` + +`presentCall` and `presentResult` are **pure functions**. Streaming UI and session replay may call them more than once. + +## Registration and unloading + +`ctx.tools.register()` returns a disposer, but a registration made through `ctx` is already tracked by the framework. Unloading the plugin removes the tool automatically, so the plugin does not call the disposer itself. + +```ts ignore-check +// This is sufficient: +ctx.tools.register(defineTool({ /* ... */ })) + +// No saved disposer or extra cleanup registration is needed. +``` + +## Complete example + +This tool counts files in a directory: + +```ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' +import { readdir } from 'node:fs/promises' + +export const name = 'file-counter' +export const inject = ['tools'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'count_files', + description: 'Count files in a directory.', + parameters: { + path: { type: 'string', required: true, description: 'Directory path' }, + extension: { type: 'string', description: 'Filter by extension (e.g. ".ts")' }, + }, + async execute(args) { + const entries = await readdir(args.path, { withFileTypes: true }) + let files = entries.filter(e => e.isFile()) + if (args.extension) { + files = files.filter(f => f.name.endsWith(args.extension!)) + } + return [{ type: 'text', text: `Found ${files.length} files.` }] + }, + })) +} +``` + +## Next steps + +- [Plugin configuration](./config.md) — make the tool configurable +- [Capability layering](../practice/) — understand the interface/implementation/consumer pattern diff --git a/docs/user/zh-CN/develop/basic/tool.md b/docs/user/develop/basic/tool.zh.md similarity index 80% rename from docs/user/zh-CN/develop/basic/tool.md rename to docs/user/develop/basic/tool.zh.md index 9eb4715385..fce9a7d9b9 100644 --- a/docs/user/zh-CN/develop/basic/tool.md +++ b/docs/user/develop/basic/tool.zh.md @@ -1,10 +1,12 @@ # 开发一个 Tool +[English](tool.md) | 中文 + Tool 是模型可以调用的能力。本文介绍如何用 `defineTool` 编写一个 tool。 ## 最小示例 -```typescript +```ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' @@ -19,7 +21,7 @@ export function apply(ctx: Context) { name: { type: 'string', required: true, description: 'The name to greet' }, }, async execute(args) { - // args 自动推导为 { name: string } + // args is inferred as { name: string }. return [{ type: 'text', text: `Hello, ${args.name}!` }] }, })) @@ -32,28 +34,28 @@ export function apply(ctx: Context) { ### 基本类型 -```typescript -parameters: { +```ts +export const parameters = { path: { type: 'string', required: true }, limit: { type: 'number' }, recursive: { type: 'boolean' }, } -// 推导类型: { path: string; limit?: number; recursive?: boolean } +// Inferred type: { path: string; limit?: number; recursive?: boolean } ``` ### 枚举 -```typescript -parameters: { +```ts +export const parameters = { mode: { type: 'string', required: true, enum: ['read', 'write', 'append'] }, } -// 推导类型: { mode: string } (运行时校验 enum 值) +// Inferred type: { mode: string } (enum values are validated at runtime) ``` ### 嵌套对象 -```typescript -parameters: { +```ts +export const parameters = { options: { type: 'object', properties: { @@ -62,19 +64,19 @@ parameters: { }, }, } -// 推导类型: { options?: { timeout?: number; retries?: number } } +// Inferred type: { options?: { timeout?: number; retries?: number } } ``` ### 数组 -```typescript -parameters: { +```ts +export const parameters = { tags: { type: 'array', items: { type: 'string' }, }, } -// 推导类型: { tags?: string[] } +// Inferred type: { tags?: string[] } ``` ### 每个属性的字段 @@ -92,25 +94,34 @@ parameters: { `execute` 接收经过校验的 `args`（类型自动推导）和一个 `exec` 上下文对象： -```typescript -async execute(args, exec) { - // args: 根据 parameters 自动推导的类型 - // exec: ToolExecution 对象，提供执行上下文 +```ts +import { defineTool } from '@deepseek-ai/dsh-tools' - // 返回 ContentBlock 数组 - return [{ type: 'text', text: 'result here' }] -} +export const tool = defineTool({ + name: 'example', + description: 'Return an example result.', + parameters: {}, + async execute(args, exec) { + // args: inferred from parameters + // exec: ToolExecution context + + // Return a ContentBlock array. + void args + void exec + return [{ type: 'text', text: 'result here' }] + }, +}) ``` ### 返回值 `execute` 必须返回一个 `ContentBlock[]`，告诉模型 tool 的执行结果： -```typescript -// 文本结果 +```ts ignore-check +// Text result return [{ type: 'text', text: 'file content here...' }] -// 多个 block +// Multiple blocks return [ { type: 'text', text: 'Found 3 matches:' }, { type: 'text', text: matchResults.join('\n') }, @@ -127,7 +138,7 @@ return [ Tool 可以定义 UI 渲染方法，用于在终端或 ACP 客户端中展示 tool call 和 result： -```typescript +```ts ignore-check defineTool({ name: 'bash', // ... @@ -152,18 +163,18 @@ defineTool({ `ctx.tools.register()` 返回值就是 disposer。但由于你在 `ctx` 上调用，框架已经自动追踪了这个注册——插件卸载时会自动移除 tool。你不需要手动调用 disposer。 -```typescript -// 这样就够了: +```ts ignore-check +// This is sufficient: ctx.tools.register(defineTool({ /* ... */ })) -// 不需要额外保存 disposer 或注册清理逻辑 +// No saved disposer or extra cleanup registration is needed. ``` ## 完整实战示例 一个文件计数 tool： -```typescript +```ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' import { readdir } from 'node:fs/promises' diff --git a/docs/user/develop/framework/events.i18n.yaml b/docs/user/develop/framework/events.i18n.yaml new file mode 100644 index 0000000000..9704eff7c5 --- /dev/null +++ b/docs/user/develop/framework/events.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +events.md: 0c57681a55ea0200fe8f33293176fc94f09a4ce5 +events.zh.md: 3e14739d4a97ba014d545c9f226000507aaeacef diff --git a/docs/user/develop/framework/events.md b/docs/user/develop/framework/events.md new file mode 100644 index 0000000000..0c57681a55 --- /dev/null +++ b/docs/user/develop/framework/events.md @@ -0,0 +1,143 @@ +# Event system + +English | [中文](events.zh.md) + +Events are the core communication mechanism between Cordis plugins. Harness uses them extensively for loosely coupled extension points. + +## Basic use + +### Listen for an event + +```ts ignore-check +ctx.on('event-name', (payload) => { + // Handle the event. +}) +``` + +### Emit an event + +```ts ignore-check +ctx.emit('event-name', payload) +``` + +## Event modes + +Cordis provides several event modes for different interaction contracts. + +### emit — broadcast + +Every listener runs synchronously and return values are ignored: + +```ts ignore-check +// Emit +ctx.emit('my-plugin/ready', { id: 'worker-1' }) + +// Listen +ctx.on('my-plugin/ready', ({ id }) => { + console.log(`${id} is ready`) +}) +``` + +### bail — short circuit + +Listeners run in order; the first non-`undefined` result becomes the final result: + +```ts ignore-check +// Dispatch +const result = ctx.bail('some-check', input) + +// Listen: a returned value stops later listeners. +ctx.on('some-check', (input) => { + if (shouldBlock(input)) return 'blocked' + // Return undefined to continue to the next listener. +}) +``` + +### serial — ordered execution + +Listeners run in registration order and asynchronous results are awaited. The first listener to return a non-empty value stops further execution: + +```ts ignore-check +await ctx.serial('setup-phase', context) +``` + +### waterfall — pipeline + +Each listener may wrap the downstream result to form a processing chain. A listener **must call `next()` to delegate downstream**; omitting the call vetoes the pipeline: + +```ts ignore-check +// Dispatch +const output = await ctx.waterfall('my-plugin/transform', input, async () => input) + +// Listen: next() is mandatory. +ctx.on('my-plugin/transform', async (_input, next) => { + const downstream = await next() + return downstream.trim() +}) +``` + +::: warning +A waterfall listener **must call `next()`**. Omitting it vetoes the pipeline by design, enabling interception and gateway behavior. +::: + +## Typed events + +Harness uses TypeScript declaration merging for type-safe events: + +```ts +import 'cordis' + +declare module 'cordis' { + interface Events { + 'my-plugin/ready': (payload: { id: string }) => void + 'my-plugin/check': (input: string) => boolean | undefined + 'my-plugin/transform': (input: string, next: () => Promise) => Promise + } +} + +// ctx.on('my-plugin/ready', ...) and ctx.emit('my-plugin/ready', ...) +// are now inferred correctly. +``` + +## Cordis events and session records + +Harness Cordis events use `namespace/action` names, including `agent/pre-step`, `agent/request`, `agent/step-result`, `tools/result`, and `session/event`. The generated [event catalog](../../../cordis-catalog/events.md) records complete signatures and modes. + +`turn/*`, `step/*`, `tool/call`, `tool/result`, and `compact/*` are durable session-event types, not same-named Cordis events. To observe them, listen to `session/event` and inspect `event.type`. + +## Event listeners are effects + +A listener registered with `ctx.on()` is removed automatically when its plugin unloads: + +```ts ignore-check +export function apply(ctx: Context) { + // This listener is removed when the plugin disposes. + ctx.on('tools/result', handler) +} +``` + +## Example: logging plugin + +This plugin logs tool calls and results: + +```ts +import type { Context } from 'cordis' +import '@deepseek-ai/dsh-tools' + +export const name = 'tool-logger' + +export function apply(ctx: Context) { + ctx.on('tools/result', (exec, result) => { + console.log(`[tool] ${exec.name}(${JSON.stringify(exec.arguments)})`) + const text = result.content + .map(block => block.type === 'text' ? block.text : '') + .join('') + console.log(`[tool result] ${text.slice(0, 100)}`) + }) +} +``` + +## Next steps + +- [Capability layering](../practice/) — understand events within capability interfaces +- [LLM adapters](../practice/llm-adapter.md) — implement a complete LLM backend diff --git a/docs/user/zh-CN/develop/framework/events.md b/docs/user/develop/framework/events.zh.md similarity index 83% rename from docs/user/zh-CN/develop/framework/events.md rename to docs/user/develop/framework/events.zh.md index 80f49d38dc..3e14739d4a 100644 --- a/docs/user/zh-CN/develop/framework/events.md +++ b/docs/user/develop/framework/events.zh.md @@ -1,20 +1,22 @@ # 事件系统 +[English](events.md) | 中文 + 事件是 Cordis 插件间通信的核心机制。Harness 大量使用事件来实现松耦合的扩展点。 ## 基本用法 ### 监听事件 -```typescript +```ts ignore-check ctx.on('event-name', (payload) => { - // 处理事件 + // Handle the event. }) ``` ### 触发事件 -```typescript +```ts ignore-check ctx.emit('event-name', payload) ``` @@ -26,11 +28,11 @@ Cordis 提供多种事件触发模式，适用于不同场景： 所有监听器同步执行，不关心返回值： -```typescript -// 触发 +```ts ignore-check +// Emit ctx.emit('my-plugin/ready', { id: 'worker-1' }) -// 监听 +// Listen ctx.on('my-plugin/ready', ({ id }) => { console.log(`${id} is ready`) }) @@ -40,14 +42,14 @@ ctx.on('my-plugin/ready', ({ id }) => { 依次调用监听器，第一个返回非 `undefined` 值的结果作为最终值： -```typescript -// 触发 +```ts ignore-check +// Dispatch const result = ctx.bail('some-check', input) -// 监听（返回值阻止后续监听器） +// Listen: a returned value stops later listeners. ctx.on('some-check', (input) => { if (shouldBlock(input)) return 'blocked' - // 返回 undefined 继续传递给下一个监听器 + // Return undefined to continue to the next listener. }) ``` @@ -55,7 +57,7 @@ ctx.on('some-check', (input) => { 监听器按注册顺序依次执行，并等待异步结果；第一个返回非空值的监听器会终止后续执行： -```typescript +```ts ignore-check await ctx.serial('setup-phase', context) ``` @@ -63,11 +65,11 @@ await ctx.serial('setup-phase', context) 每个监听器可以包装下游返回值，形成处理链。**必须调用 `next()` 传递给下游**，不调用即为否决： -```typescript -// 触发 +```ts ignore-check +// Dispatch const output = await ctx.waterfall('my-plugin/transform', input, async () => input) -// 监听（必须调用 next） +// Listen: next() is mandatory. ctx.on('my-plugin/transform', async (_input, next) => { const downstream = await next() return downstream.trim() @@ -82,7 +84,9 @@ Waterfall 监听器**必须调用 `next()`**。不调用 `next` 等于否决整 Harness 使用 TypeScript 声明合并来为事件提供类型安全： -```typescript +```ts +import 'cordis' + declare module 'cordis' { interface Events { 'my-plugin/ready': (payload: { id: string }) => void @@ -91,13 +95,13 @@ declare module 'cordis' { } } -// 现在 ctx.on('my-plugin/ready', ...) 和 ctx.emit('my-plugin/ready', ...) -// 都有正确的类型推导 +// ctx.on('my-plugin/ready', ...) and ctx.emit('my-plugin/ready', ...) +// are now inferred correctly. ``` ## Cordis 事件与会话记录 -Harness 的 Cordis 事件遵循 `namespace/action` 命名，例如 `agent/pre-step`、`agent/request`、`agent/step-result`、`tools/result` 和 `session/event`。完整签名与触发模式见[Events 目录](../../../../cordis-catalog/events.md)。 +Harness 的 Cordis 事件遵循 `namespace/action` 命名，例如 `agent/pre-step`、`agent/request`、`agent/step-result`、`tools/result` 和 `session/event`。完整签名与触发模式见[Events 目录](../../../cordis-catalog/events.md)。 `turn/*`、`step/*`、`tool/call`、`tool/result` 和 `compact/*` 是持久化的会话事件类型，不是同名 Cordis 事件。需要观察它们时，监听 `session/event` 并检查 `event.type`。 @@ -105,9 +109,9 @@ Harness 的 Cordis 事件遵循 `namespace/action` 命名，例如 `agent/pre-st 通过 `ctx.on()` 注册的监听器会在插件卸载时自动移除： -```typescript +```ts ignore-check export function apply(ctx: Context) { - // 这个监听器在插件 dispose 时自动清理 + // This listener is removed when the plugin disposes. ctx.on('tools/result', handler) } ``` @@ -116,8 +120,9 @@ export function apply(ctx: Context) { 一个记录所有 tool 调用的简单插件： -```typescript +```ts import type { Context } from 'cordis' +import '@deepseek-ai/dsh-tools' export const name = 'tool-logger' diff --git a/docs/user/develop/framework/index.i18n.yaml b/docs/user/develop/framework/index.i18n.yaml new file mode 100644 index 0000000000..79c947dcb9 --- /dev/null +++ b/docs/user/develop/framework/index.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +index.md: bb08e7cb3f9d3a094100806451fd33d1482003cb +index.zh.md: 4b9d6d22c8d82bece67c71032a0028b21939f98f diff --git a/docs/user/develop/framework/index.md b/docs/user/develop/framework/index.md new file mode 100644 index 0000000000..bb08e7cb3f --- /dev/null +++ b/docs/user/develop/framework/index.md @@ -0,0 +1,131 @@ +# Plugins and lifecycle + +English | [中文](index.zh.md) + +This page describes the Cordis plugin model and lifecycle state machine. + +## Fiber state machine + +Every loaded plugin owns a **Fiber** scope with the following states: + +``` +PENDING → LOADING → ACTIVE + ↘ FAILED +ACTIVE → UNLOADING → DISPOSED +``` + +| State | Meaning | +|------|------| +| PENDING | Declared, but required dependencies are not ready | +| LOADING | Dependencies are ready and `apply` is running | +| ACTIVE | The plugin is running | +| FAILED | `apply` threw an error | +| UNLOADING | The plugin is unloading and disposing resources | +| DISPOSED | The plugin is fully unloaded | + +## Dependency-driven loading + +A plugin with `inject` waits for every required service before loading: + +```ts ignore-check +export const inject = ['tools', 'llm'] + +export function apply(ctx: Context) { + // ctx.tools and ctx.llm are ready here. +} +``` + +If a required service disappears, for example during provider replacement, the plugin unloads automatically (ACTIVE → DISPOSED) and loads again when the service returns. + +## Automatic cleanup + +Every registration made through `ctx` is undone when the plugin unloads: + +```ts ignore-check +export function apply(ctx: Context) { + // Event listener: removed automatically on unload. + ctx.on('some-event', handler) + + // Custom resource: the returned disposer runs on unload. + ctx.effect(() => { + const connection = createConnection() + return () => connection.close() + }) +} +``` + +The framework tracks and disposes all of these operations: +- `ctx.on(event, handler)` — event listener +- `ctx.tools.register(tool)` — tool registration +- `ctx.llm.registerAdapter(names, adapter)` — LLM adapter registration +- `ctx.effect(() => cleanup)` — custom resource + +During unload, disposer invocation starts in reverse registration order, but multiple async disposers run concurrently and have no serial completion guarantee. Put order-dependent cleanup in one disposer returned from a single `ctx.effect()` and await its steps serially there. + +## Nested contexts + +`ctx.plugin()` creates a child Fiber that inherits the parent context but has an independent lifecycle: + +```ts ignore-check +export function apply(ctx: Context) { + // Register a child plugin. + ctx.plugin(childPlugin) + + // The child has its own Fiber and unloads with its parent. +} +``` + +## Dispose semantics + +To stop a plugin instance early: + +```ts ignore-check +const fiber = ctx.plugin(myPlugin) + +// Dispose it manually later. +fiber.dispose() +``` + +`dispose` guarantees: +1. All registrations owned by the plugin are removed. +2. Child plugins are recursively unloaded. +3. The returned promise resolves after all asynchronous cleanup finishes. + +## Hot replacement (HMR) + +With `@cordisjs/plugin-hmr` loaded from `cordis.yml`, editing a plugin source file triggers: + +1. Unload the old plugin and clean up its registrations. +2. Load the new code. +3. Run the new `apply`. + +Because plugin registrations clean themselves up, hot replacement does not retain registrations from the old instance. + +## Example lifecycle + +```ts ignore-check +export function apply(ctx: Context) { + console.log('plugin loading') + + ctx.effect(() => { + console.log('effect registered') + return () => console.log('effect cleaned up') + }) +} +``` + +Loading prints: +``` +plugin loading +effect registered +``` + +Unloading prints: +``` +effect cleaned up +``` + +## Next steps + +- [Services and dependencies](./service.md) — expose a capability to other plugins +- [Event system](./events.md) — communicate between plugins diff --git a/docs/user/zh-CN/develop/framework/index.md b/docs/user/develop/framework/index.zh.md similarity index 80% rename from docs/user/zh-CN/develop/framework/index.md rename to docs/user/develop/framework/index.zh.md index a3fdd502b5..4b9d6d22c8 100644 --- a/docs/user/zh-CN/develop/framework/index.md +++ b/docs/user/develop/framework/index.zh.md @@ -1,5 +1,7 @@ # 插件与生命周期 +[English](index.md) | 中文 + 深入了解 Cordis 插件模型和生命周期状态机。 ## Fiber 状态机 @@ -25,11 +27,11 @@ ACTIVE → UNLOADING → DISPOSED 声明了 `inject` 的插件不会立即加载，而是等待依赖的服务就绪： -```typescript +```ts ignore-check export const inject = ['tools', 'llm'] export function apply(ctx: Context) { - // 到这里时，ctx.tools 和 ctx.llm 一定存在 + // ctx.tools and ctx.llm are ready here. } ``` @@ -39,12 +41,12 @@ export function apply(ctx: Context) { 通过 `ctx` 做的任何注册，在插件卸载时都会自动撤销： -```typescript +```ts ignore-check export function apply(ctx: Context) { - // 事件监听——卸载时自动移除 + // Event listener: removed automatically on unload. ctx.on('some-event', handler) - // 自定义资源——卸载时调用返回的函数 + // Custom resource: the returned disposer runs on unload. ctx.effect(() => { const connection = createConnection() return () => connection.close() @@ -58,18 +60,18 @@ export function apply(ctx: Context) { - `ctx.llm.registerAdapter(names, adapter)` — LLM 适配器注册 - `ctx.effect(() => cleanup)` — 自定义资源 -插件卸载时，这些注册按倒序逐个撤销。 +插件卸载时，处置器按注册顺序的反向发起，但多个异步处置器会并发执行，不保证逐个完成。存在顺序依赖的清理步骤必须放进同一个 `ctx.effect()` 返回的处置器中，由该处置器负责串行等待。 ## 嵌套上下文 `ctx.plugin()` 创建子 Fiber，它继承父上下文但有独立的生命周期： -```typescript +```ts ignore-check export function apply(ctx: Context) { - // 注册一个子插件 + // Register a child plugin. ctx.plugin(childPlugin) - // 子插件有自己的 Fiber，父卸载时子也卸载 + // The child has its own Fiber and unloads with its parent. } ``` @@ -77,10 +79,10 @@ export function apply(ctx: Context) { 当你需要提前终止一个插件实例： -```typescript +```ts ignore-check const fiber = ctx.plugin(myPlugin) -// 之后可以手动 dispose +// Dispose it manually later. fiber.dispose() ``` @@ -101,7 +103,7 @@ fiber.dispose() ## 实战：理解生命周期 -```typescript +```ts ignore-check export function apply(ctx: Context) { console.log('plugin loading') diff --git a/docs/user/develop/framework/service.i18n.yaml b/docs/user/develop/framework/service.i18n.yaml new file mode 100644 index 0000000000..f0deb18959 --- /dev/null +++ b/docs/user/develop/framework/service.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +service.md: 1bf28cb3c7dfdfbd6d0babfa3b1688ac65eea01e +service.zh.md: 17785c056ab9a0a21974e6ed8bbe7f7de05fa00e diff --git a/docs/user/develop/framework/service.md b/docs/user/develop/framework/service.md new file mode 100644 index 0000000000..1bf28cb3c7 --- /dev/null +++ b/docs/user/develop/framework/service.md @@ -0,0 +1,148 @@ +# Services and dependencies + +English | [中文](service.zh.md) + +A service is a capability one plugin exposes to other plugins. `inject` declares the services a plugin requires. + +## What is a service? + +In Harness, `tools`, `llm`, and `agents` are services. Each is a named capability mounted on `ctx`: + +```ts ignore-check +ctx.tools // ToolRegistry service +ctx.llm // LLM service +ctx.agents // Agent service +``` + +Any plugin can provide a service for other plugins to consume. + +## Consume a service + +Declare `inject` to use an existing service: + +```ts ignore-check +export const inject = ['tools'] + +export function apply(ctx: Context) { + // ctx.tools exists and is ready here. + ctx.tools.register(/* ... */) +} +``` + +When `apply` runs, every service declared by `inject` is ready. If a service is not ready, the plugin waits instead of running. + +## Provide a service + +### Extend Service + +```ts +import { Service, type Context } from 'cordis' + +export default class MetricsService extends Service { + static inject = ['llm'] // A service may depend on other services. + + constructor(ctx: Context) { + super(ctx, 'metrics') // 'metrics' is the service name. + } + + // Public service method. + record(event: string, value: number) { + // ... + } +} +``` + +After loading this plugin, consumers access the service as `ctx.metrics`: + +```ts ignore-check +export const inject = ['metrics'] + +export function apply(ctx: Context) { + ctx.metrics.record('tool_call', 1) +} +``` + +### Declare its type + +Use TypeScript declaration merging to type `ctx.metrics`: + +```ts +import { Service, type Context } from 'cordis' + +declare module 'cordis' { + interface Context { + metrics: MetricsService + } +} + +export default class MetricsService extends Service { + constructor(ctx: Context) { + super(ctx, 'metrics') + } + + record(event: string, value: number) { /* ... */ } +} +``` + +## Dependency behavior + +### Required and optional dependencies + +```ts ignore-check +// Required: the plugin does not load while the service is absent. +export const inject = ['tools'] + +// Optional: omit inject and query with ctx.get() at the use site. +export function apply(ctx: Context) { + const metrics = ctx.get('metrics') + metrics?.record('plugin_loaded', 1) +} +``` + +### When a service disappears + +If a required service disappears while the application is running, for example because its provider unloads: + +1. Dependent plugins dispose automatically. +2. They load again when the service returns. + +This prevents a plugin from calling a service that no longer exists. + +## Service isolation + +`cordis.yml` can isolate services so separate plugin groups see separate instances of the same service: + +```yaml +- id: group-a + name: '@cordisjs/plugin-group' + group: true + isolate: + bash: true + config: + - name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 5000 + - name: './src/plugin-a.ts' + +- id: group-b + name: '@cordisjs/plugin-group' + group: true + isolate: + bash: true + config: + - name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 60000 + - name: './src/plugin-b.ts' +``` + +`plugin-a` and `plugin-b` each see the Bash instance in their own group, with no cross-group effect. + +## Built-in Harness services + +The repository generates the service names, public methods, and source locations in the [service catalog](../../../cordis-catalog/services.md). Use that catalog and the service's TypeScript interface while developing a plugin; do not maintain a second static list. + +## Next steps + +- [Event system](./events.md) — communicate between plugins without tight coupling +- [Capability layering](../practice/) — use services as capability interfaces diff --git a/docs/user/zh-CN/develop/framework/service.md b/docs/user/develop/framework/service.zh.md similarity index 80% rename from docs/user/zh-CN/develop/framework/service.md rename to docs/user/develop/framework/service.zh.md index 19edf4a975..17785c056a 100644 --- a/docs/user/zh-CN/develop/framework/service.md +++ b/docs/user/develop/framework/service.zh.md @@ -1,15 +1,17 @@ # 服务与依赖 +[English](service.md) | 中文 + 服务 (Service) 是插件对外暴露能力的方式。依赖 (inject) 是插件声明自己需要哪些服务。 ## 什么是服务 在 Harness 中，`tools`、`llm`、`agents` 都是服务。服务是挂载在 `ctx` 上的命名能力： -```typescript -ctx.tools // ToolRegistry 服务 -ctx.llm // LLM 服务 -ctx.agents // Agent 服务 +```ts ignore-check +ctx.tools // ToolRegistry service +ctx.llm // LLM service +ctx.agents // Agent service ``` 任何插件都可以提供一个新服务，供其他插件使用。 @@ -18,11 +20,11 @@ ctx.agents // Agent 服务 声明 `inject` 来使用已有服务： -```typescript +```ts ignore-check export const inject = ['tools'] export function apply(ctx: Context) { - // ctx.tools 在这里一定存在且就绪 + // ctx.tools exists and is ready here. ctx.tools.register(/* ... */) } ``` @@ -33,17 +35,17 @@ export function apply(ctx: Context) { ### 使用 Service 基类 -```typescript +```ts import { Service, type Context } from 'cordis' export default class MetricsService extends Service { - static inject = ['llm'] // 本服务也可以依赖其他服务 + static inject = ['llm'] // A service may depend on other services. constructor(ctx: Context) { - super(ctx, 'metrics') // 'metrics' 是服务名 + super(ctx, 'metrics') // 'metrics' is the service name. } - // 服务的公开方法 + // Public service method. record(event: string, value: number) { // ... } @@ -52,7 +54,7 @@ export default class MetricsService extends Service { 加载这个插件后，其他插件就可以通过 `ctx.metrics` 访问它： -```typescript +```ts ignore-check export const inject = ['metrics'] export function apply(ctx: Context) { @@ -64,7 +66,7 @@ export function apply(ctx: Context) { 使用 TypeScript 声明合并让 `ctx.metrics` 有正确类型： -```typescript +```ts import { Service, type Context } from 'cordis' declare module 'cordis' { @@ -86,11 +88,11 @@ export default class MetricsService extends Service { ### 必选依赖 vs 可选依赖 -```typescript -// 必选：服务不存在时，插件不会加载 +```ts ignore-check +// Required: the plugin does not load while the service is absent. export const inject = ['tools'] -// 可选：不写入 inject，使用时通过 ctx.get() 查询 +// Optional: omit inject and query with ctx.get() at the use site. export function apply(ctx: Context) { const metrics = ctx.get('metrics') metrics?.record('plugin_loaded', 1) @@ -138,7 +140,7 @@ export function apply(ctx: Context) { ## Harness 内置服务 -服务名、公开方法和源码位置由仓库自动生成，见[服务目录](../../../../cordis-catalog/services.md)。开发插件时应以该目录和服务接口的 TypeScript 类型为准，不要复制一份静态清单。 +服务名、公开方法和源码位置由仓库自动生成，见[服务目录](../../../cordis-catalog/services.md)。开发插件时应以该目录和服务接口的 TypeScript 类型为准，不要复制一份静态清单。 ## 下一步 diff --git a/docs/user/develop/practice/index.i18n.yaml b/docs/user/develop/practice/index.i18n.yaml new file mode 100644 index 0000000000..d2478abf75 --- /dev/null +++ b/docs/user/develop/practice/index.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +index.md: 0261b49b071167f7c2a33f78bbc1959cc6f1879f +index.zh.md: 5819344430fcbde31bf825e9815120983e44e3f6 diff --git a/docs/user/develop/practice/index.md b/docs/user/develop/practice/index.md new file mode 100644 index 0000000000..0261b49b07 --- /dev/null +++ b/docs/user/develop/practice/index.md @@ -0,0 +1,158 @@ +# Three-layer capability design + +English | [中文](index.zh.md) + +When a capability is general enough to need replaceable implementations, such as Bash execution, Harness splits it into three packages: an **interface**, an **implementation**, and a **consumer**. Each layer can evolve or be replaced independently. + +## Bash example + +The Bash execution capability consists of: + +- **Interface** (`dsh-bash`) — defines Bash request and result shapes +- **Implementation** (`dsh-bash-local`) — executes commands on the local machine +- **Consumer** (`dsh-tool-bash`) — exposes the capability as a model-callable tool + +``` +┌─────────────┐ ┌──────────────────┐ ┌──────────────┐ +│ dsh-bash │────▶│ dsh-bash-local │ │ dsh-tool-bash│ +│ (interface) │ │ (implementation) │ │(consumer/tool)│ +└─────────────┘ └──────────────────┘ └──────────────┘ + ▲ │ + └────────────────────────────────────────────┘ + inject: ['bash'] +``` + +## Benefits of the split + +### Replace implementations + +One interface can have multiple implementations selected through `cordis.yml`: + +```yaml +# Local execution +- name: '@deepseek-ai/dsh-bash-local' + +# Or a future remote sandbox implementation +# - name: '@deepseek-ai/dsh-bash-remote' +# config: +# endpoint: 'https://sandbox.example.com' +``` + +The interface and tool remain unchanged while the implementation changes. + +### Evolve independently + +- The interface changes rarely after its contract stabilizes. +- Implementations can improve performance and security independently. +- Consumers can change how they present the capability to the model. + +### Decouple dependencies + +- The implementation depends on the interface. +- The consumer depends on the interface. +- The implementation and consumer **do not depend on each other**. + +## Built-in three-layer capabilities + +| Capability | Interface | Implementation | Consumer | +|------|-------------|------|---------------| +| Bash | `dsh-bash` | `dsh-bash-local` | `dsh-tool-bash` | +| Filesystem | `dsh-fs` | `dsh-fs-local` + `dsh-fs-policy` | `dsh-tool-fs` | +| Web | `dsh-web` | `dsh-web-fetch-local` / `dsh-web-search-*` | `dsh-tool-web` | +| Subagent | `dsh-subagent` | `dsh-subagent-spawn` / `dsh-subagent-fork` | `dsh-tool-subagent` | +| Compaction | `dsh-compact` | `dsh-compact-basic` | The implementation consumes agent-loop extension events | + +## Develop a three-layer capability + +### Step 1: define the interface + +```ts ignore-check +// packages/my-cap/my-cap/src/index.ts +import { Service, type Context } from 'cordis' + +declare module 'cordis' { + interface Context { + myCap: MyCapService + } +} + +export abstract class MyCapService extends Service { + constructor(ctx: Context) { + super(ctx, 'myCap') + } + + /** Execute the capability. */ + abstract execute(request: MyCapRequest): Promise +} + +export interface MyCapRequest { + input: string +} + +export interface MyCapResult { + output: string +} +``` + +### Step 2: write an implementation + +```ts ignore-check +// packages/my-cap/my-cap-local/src/index.ts +import type { Context } from 'cordis' +import { MyCapService, type MyCapRequest, type MyCapResult } from '@deepseek-ai/dsh-my-cap' + +class MyCapLocal extends MyCapService { + async execute(request: MyCapRequest): Promise { + // Concrete implementation. + return { output: request.input.toUpperCase() } + } +} + +export const name = 'my-cap-local' + +export function apply(ctx: Context) { + ctx.plugin(MyCapLocal) +} +``` + +### Step 3: write a consumer + +```ts ignore-check +// packages/my-cap/tool-my-cap/src/index.ts +import type { Context } from 'cordis' +import { defineTool } from '@deepseek-ai/dsh-tools' + +export const name = 'tool-my-cap' +export const inject = ['tools', 'myCap'] + +export function apply(ctx: Context) { + ctx.tools.register(defineTool({ + name: 'my_cap', + description: 'Execute my capability.', + parameters: { + input: { type: 'string', required: true }, + }, + async execute(args) { + const result = await ctx.myCap.execute({ input: args.input }) + return [{ type: 'text', text: result.output }] + }, + })) +} +``` + +### Compose them in cordis.yml + +```yaml +- name: '@deepseek-ai/dsh-my-cap-local' +- name: '@deepseek-ai/dsh-tool-my-cap' +``` + +## Design points + +- **Do not split preemptively** — use three packages only when the capability needs replaceable implementations. A simple tool plugin does not. +- **The interface owns Request/Result types** — implementations and consumers depend only on the interface package. +- **Explicit > implicit** — resolve defaults in an explicit `resolve(request): Spec` step rather than hiding `?? default` expressions inside `run()`. + +## Next steps + +- [LLM adapter](./llm-adapter.md) — implement an LLM backend, a common capability interface extension diff --git a/docs/user/zh-CN/develop/practice/index.md b/docs/user/develop/practice/index.zh.md similarity index 94% rename from docs/user/zh-CN/develop/practice/index.md rename to docs/user/develop/practice/index.zh.md index bffa35f964..5819344430 100644 --- a/docs/user/zh-CN/develop/practice/index.md +++ b/docs/user/develop/practice/index.zh.md @@ -1,5 +1,7 @@ # 能力的三层拆分 +[English](index.md) | 中文 + 当一个能力（插件）足够通用（比如"执行 bash 命令"），Harness 会把它拆成三个包：**接口**、**实现**、**消费者**。这样可以独立替换其中任何一层。 ## 以 Bash 为例 @@ -13,7 +15,7 @@ ``` ┌─────────────┐ ┌──────────────────┐ ┌──────────────┐ │ dsh-bash │────▶│ dsh-bash-local │ │ dsh-tool-bash│ -│ (接口) │ │ (实现) │ │ (消费者/tool)│ +│ (interface) │ │ (implementation) │ │(consumer/tool)│ └─────────────┘ └──────────────────┘ └──────────────┘ ▲ │ └────────────────────────────────────────────┘ @@ -27,10 +29,10 @@ 同一个接口可以有多种实现。用户通过 `cordis.yml` 选择： ```yaml -# 本地执行 +# Local execution - name: '@deepseek-ai/dsh-bash-local' -# 或：远程沙箱执行（未来） +# Or a future remote sandbox implementation # - name: '@deepseek-ai/dsh-bash-remote' # config: # endpoint: 'https://sandbox.example.com' @@ -64,7 +66,7 @@ ### 第一步：定义接口 -```typescript +```ts ignore-check // packages/my-cap/my-cap/src/index.ts import { Service, type Context } from 'cordis' @@ -79,7 +81,7 @@ export abstract class MyCapService extends Service { super(ctx, 'myCap') } - /** 执行能力的核心方法 */ + /** Execute the capability. */ abstract execute(request: MyCapRequest): Promise } @@ -94,14 +96,14 @@ export interface MyCapResult { ### 第二步：编写实现 -```typescript +```ts ignore-check // packages/my-cap/my-cap-local/src/index.ts import type { Context } from 'cordis' import { MyCapService, type MyCapRequest, type MyCapResult } from '@deepseek-ai/dsh-my-cap' class MyCapLocal extends MyCapService { async execute(request: MyCapRequest): Promise { - // 具体实现 + // Concrete implementation. return { output: request.input.toUpperCase() } } } @@ -115,7 +117,7 @@ export function apply(ctx: Context) { ### 第三步：编写消费者 (tool) -```typescript +```ts ignore-check // packages/my-cap/tool-my-cap/src/index.ts import type { Context } from 'cordis' import { defineTool } from '@deepseek-ai/dsh-tools' diff --git a/docs/user/develop/practice/llm-adapter.i18n.yaml b/docs/user/develop/practice/llm-adapter.i18n.yaml new file mode 100644 index 0000000000..84d622dde9 --- /dev/null +++ b/docs/user/develop/practice/llm-adapter.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +llm-adapter.md: 18e05ab79f7daf9f86fe1eb27bdd4440fb9107bc +llm-adapter.zh.md: f3c1ac70f7b4c11fb9f6dcb247be342fb358bd39 diff --git a/docs/user/develop/practice/llm-adapter.md b/docs/user/develop/practice/llm-adapter.md new file mode 100644 index 0000000000..18e05ab79f --- /dev/null +++ b/docs/user/develop/practice/llm-adapter.md @@ -0,0 +1,185 @@ +# LLM adapters + +English | [中文](llm-adapter.zh.md) + +This guide connects a new LLM provider to Harness. + +## Overview + +An LLM adapter extends `LlmAdapter` and implements `stream()`, translating Harness's provider-neutral request into a provider API call and translating the response back into Harness chunks. + +## Minimal implementation + +```ts +import type { Context } from 'cordis' +import Schema from 'schemastery' +import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' + +class MyAdapter extends LlmAdapter { + private apiKey: string + + constructor(apiKey: string) { + super() + this.apiKey = apiKey + } + + async *stream(options: GenerateOptions): AsyncIterable { + // 1. Convert options.messages to the provider format. + // 2. Call the streaming API. + // 3. Convert the response into StreamChunk values. + } +} + +export interface Config { + apiKey: string + models: string[] +} + +export const Config: Schema = Schema.object({ + apiKey: Schema.string().required(), + models: Schema.array(Schema.string()).required(), +}) + +export const name = 'my-llm-adapter' +export const inject = ['llm'] + +export function apply(ctx: Context, config: Config) { + const adapter = new MyAdapter(config.apiKey) + ctx.llm.registerAdapter(config.models, adapter) +} +``` + +## StreamChunk protocol + +`stream()` yields chunks using this protocol: + +```ts +import { CallId, type StreamChunk } from '@deepseek-ai/dsh-llm' + +async function* exampleChunks(): AsyncIterable { + // 1. Start each content block with block-start. + yield { type: 'block-start', index: 0, blockType: 'text' } + + // 2. Stream text through text-delta. + yield { type: 'text-delta', index: 0, text: 'Hello' } + yield { type: 'text-delta', index: 0, text: ' world' } + + // 3. End each content block with block-end and the complete block. + yield { + type: 'block-end', + index: 0, + block: { type: 'text', text: 'Hello world' }, + } + + // 4. Tool-call block. + yield { type: 'block-start', index: 1, blockType: 'tool-call' } + yield { + type: 'tool-call-delta', + index: 1, + id: CallId('call-123'), + name: 'bash', + argumentsDelta: '{"command":"ls"}', + } + yield { + type: 'block-end', + index: 1, + block: { + type: 'tool-call', + id: CallId('call-123'), + name: 'bash', + arguments: '{"command":"ls"}', + }, + } + + // 5. Token usage. + yield { type: 'usage', usage: { inputTokens: 100, outputTokens: 50 } } + + // 6. Finish reason. + yield { type: 'finish', reason: { kind: 'stop' } } + // Alternatively, { kind: 'tool-calls' } requests tool execution. +} +``` + +### Key rules + +- Every `block-start` has a matching `block-end`. +- `index` increases from 0 and identifies content-block order. +- A `tool-call-delta` carries raw JSON text in `argumentsDelta`, either all at once or over multiple chunks. +- `finish` is the final chunk. +- Emit `usage` before `finish`. + +## GenerateOptions + +`stream()` receives the exported `GenerateOptions` type. It includes the model, conversation history, system prompt, tool schemas, generation parameters, stop sequences, and abort signal; treat the TypeScript type exported by `@deepseek-ai/dsh-llm` as authoritative. Map supported fields to the provider API. If the provider cannot honor a field, throw `LlmError` with a stable code instead of silently dropping it. + +## Register an adapter + +```ts ignore-check +ctx.llm.registerAdapter(['model-name-1', 'model-name-2'], adapter) +``` + +The first argument lists the model names handled by the adapter. If `cordis.yml` selects `model: model-name-1`, the service routes that request to this adapter. + +## Use it from cordis.yml + +```yaml +- id: my-llm + name: './src/my-llm-adapter.ts' + config: + apiKey: !!js process.env.MY_API_KEY + models: + - my-model-v1 + - my-model-v2 + +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-agent' + config: + model: my-model-v1 # References the model registered above. +``` + +## Reference implementations + +The repository contains complete implementations: + +- `packages/llm/llm-deepseek/` — DeepSeek API adapter using the OpenAI-compatible format +- `packages/llm/llm-pi-ai/` — Pi AI adapter using a different API format +- `examples/echo-agent/src/mock-llm.ts` — minimal local teaching adapter + +Start with the mock adapter to study a complete chunk sequence without network behavior. + +## Error handling + +Adapters throw transport and protocol failures as `LlmError` values with stable codes. The agent loop preserves the error and code for diagnostics and policy; it does not convert an ordinary `Error` automatically. Every provider HTTP request must also merge `attributionHeaders()` and forward `options.signal`. + +```ts +import { + attributionHeaders, + LlmAdapter, + LlmError, + type GenerateOptions, + type StreamChunk, +} from '@deepseek-ai/dsh-llm' + +class HttpAdapter extends LlmAdapter { + constructor(private readonly endpoint: string) { + super() + } + + async *stream(options: GenerateOptions): AsyncIterable { + const response = await fetch(this.endpoint, { + method: 'POST', + headers: { + 'content-type': 'application/json', + ...attributionHeaders(), + }, + body: JSON.stringify({ model: options.model, messages: options.messages }), + ...options.signal ? { signal: options.signal } : {}, + }) + if (!response.ok) { + throw new LlmError(`Provider API error: ${response.status}`, 'PROVIDER_HTTP_ERROR', response.status) + } + // A real adapter parses the response and emits the complete chunk sequence. + yield { type: 'finish', reason: { kind: 'stop' } } + } +} +``` diff --git a/docs/user/develop/practice/llm-adapter.zh.md b/docs/user/develop/practice/llm-adapter.zh.md new file mode 100644 index 0000000000..f3c1ac70f7 --- /dev/null +++ b/docs/user/develop/practice/llm-adapter.zh.md @@ -0,0 +1,185 @@ +# LLM 适配器 + +[English](llm-adapter.md) | 中文 + +本文介绍如何为 Harness 接入一个新的 LLM 提供方。 + +## 概述 + +LLM 适配器是一个继承 `LlmAdapter` 的类，实现 `stream()` 方法，将 Harness 的统一请求格式转换为具体 API 的调用。 + +## 最小实现 + +```ts +import type { Context } from 'cordis' +import Schema from 'schemastery' +import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' + +class MyAdapter extends LlmAdapter { + private apiKey: string + + constructor(apiKey: string) { + super() + this.apiKey = apiKey + } + + async *stream(options: GenerateOptions): AsyncIterable { + // 1. Convert options.messages to the provider format. + // 2. Call the streaming API. + // 3. Convert the response into StreamChunk values. + } +} + +export interface Config { + apiKey: string + models: string[] +} + +export const Config: Schema = Schema.object({ + apiKey: Schema.string().required(), + models: Schema.array(Schema.string()).required(), +}) + +export const name = 'my-llm-adapter' +export const inject = ['llm'] + +export function apply(ctx: Context, config: Config) { + const adapter = new MyAdapter(config.apiKey) + ctx.llm.registerAdapter(config.models, adapter) +} +``` + +## StreamChunk 协议 + +`stream()` 必须按以下协议 yield chunk： + +```ts +import { CallId, type StreamChunk } from '@deepseek-ai/dsh-llm' + +async function* exampleChunks(): AsyncIterable { + // 1. Start each content block with block-start. + yield { type: 'block-start', index: 0, blockType: 'text' } + + // 2. Stream text through text-delta. + yield { type: 'text-delta', index: 0, text: 'Hello' } + yield { type: 'text-delta', index: 0, text: ' world' } + + // 3. End each content block with block-end and the complete block. + yield { + type: 'block-end', + index: 0, + block: { type: 'text', text: 'Hello world' }, + } + + // 4. Tool-call block. + yield { type: 'block-start', index: 1, blockType: 'tool-call' } + yield { + type: 'tool-call-delta', + index: 1, + id: CallId('call-123'), + name: 'bash', + argumentsDelta: '{"command":"ls"}', + } + yield { + type: 'block-end', + index: 1, + block: { + type: 'tool-call', + id: CallId('call-123'), + name: 'bash', + arguments: '{"command":"ls"}', + }, + } + + // 5. Token usage. + yield { type: 'usage', usage: { inputTokens: 100, outputTokens: 50 } } + + // 6. Finish reason. + yield { type: 'finish', reason: { kind: 'stop' } } + // Alternatively, { kind: 'tool-calls' } requests tool execution. +} +``` + +### 关键规则 + +- 每个 `block-start` 必须有对应的 `block-end` +- `index` 从 0 递增，标识内容块顺序 +- `tool-call-delta` 的 `argumentsDelta` 是 JSON 字符串的增量（可以一次 yield 全部，也可以分多次） +- `finish` 必须是最后一个 chunk +- `usage` 在 `finish` 之前 yield + +## GenerateOptions + +`stream()` 接收仓库导出的 `GenerateOptions`。它包含模型名、对话历史、系统提示词、tool schema、生成参数、停止序列和中止信号；完整字段以 `@deepseek-ai/dsh-llm` 导出的 TypeScript 类型为准。适配器必须将支持的字段映射到具体 API；无法支持的字段应抛出带稳定 code 的 `LlmError`，不能静默丢弃。 + +## 注册适配器 + +```ts ignore-check +ctx.llm.registerAdapter(['model-name-1', 'model-name-2'], adapter) +``` + +第一个参数是该适配器支持的模型名列表。当用户在 `cordis.yml` 中配置 `model: model-name-1` 时，框架会路由到这个适配器。 + +## 在 cordis.yml 中使用 + +```yaml +- id: my-llm + name: './src/my-llm-adapter.ts' + config: + apiKey: !!js process.env.MY_API_KEY + models: + - my-model-v1 + - my-model-v2 + +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-agent' + config: + model: my-model-v1 # References the model registered above. +``` + +## 实战参考 + +仓库中有两个完整实现可供参考： + +- `packages/llm/llm-deepseek/` — DeepSeek API 适配器（OpenAI 兼容格式） +- `packages/llm/llm-pi-ai/` — Pi AI 适配器（不同的 API 格式） +- `examples/echo-agent/src/mock-llm.ts` — 最简 mock 适配器（教学用） + +mock 适配器是学习 StreamChunk 协议的最佳起点——它用纯本地逻辑演示了完整的 chunk 序列。 + +## 错误处理 + +适配器应将传输和协议故障作为带稳定 code 的 `LlmError` 抛出；agent loop 会保留该错误及其 code，供诊断和策略使用。不要依赖普通 `Error` 被自动转换。每个提供方 HTTP 请求还必须合并 `attributionHeaders()`，并传递 `options.signal`。 + +```ts +import { + attributionHeaders, + LlmAdapter, + LlmError, + type GenerateOptions, + type StreamChunk, +} from '@deepseek-ai/dsh-llm' + +class HttpAdapter extends LlmAdapter { + constructor(private readonly endpoint: string) { + super() + } + + async *stream(options: GenerateOptions): AsyncIterable { + const response = await fetch(this.endpoint, { + method: 'POST', + headers: { + 'content-type': 'application/json', + ...attributionHeaders(), + }, + body: JSON.stringify({ model: options.model, messages: options.messages }), + ...options.signal ? { signal: options.signal } : {}, + }) + if (!response.ok) { + throw new LlmError(`Provider API error: ${response.status}`, 'PROVIDER_HTTP_ERROR', response.status) + } + // A real adapter parses the response and emits the complete chunk sequence. + yield { type: 'finish', reason: { kind: 'stop' } } + } +} +``` diff --git a/docs/user/guide/config.i18n.yaml b/docs/user/guide/config.i18n.yaml new file mode 100644 index 0000000000..c917b46a3e --- /dev/null +++ b/docs/user/guide/config.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +config.md: 0cad49d9bd82813da230a44d526190d4e0b6a730 +config.zh.md: ee1ea9a0c1d9010be8c1a3984acdcbe870e30584 diff --git a/docs/user/guide/config.md b/docs/user/guide/config.md new file mode 100644 index 0000000000..0cad49d9bd --- /dev/null +++ b/docs/user/guide/config.md @@ -0,0 +1,59 @@ +# Configuration + +English | [中文](config.zh.md) + +Harness uses `cordis.yml` to describe which plugins an agent loads and the configuration passed to each one. The file composes capabilities; the generated configuration catalog records the fields and defaults each package actually supports, avoiding a second hand-maintained reference. + +## Start from a real configuration + +The repository examples are runnable configurations and the most reliable starting points for a new project: + +- [echo-agent](../../../examples/echo-agent/cordis.yml) uses a local mock model and needs no API key. +- [coding-agent](../../../examples/coding-agent/cordis.yml) combines the DeepSeek model, Bash, filesystem, compaction, subagents, and workflows. +- [acp-agent](../../../examples/acp-agent/cordis.yml) connects to editor clients over ACP. + +A minimal configuration is a list of plugin entries: + +```yaml +- id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + models: + - deepseek-v4-flash + +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-agent' + config: + model: deepseek-v4-flash +``` + +## Plugin entries + +`name` identifies an npm package or a local module relative to `cordis.yml`; `id` gives the plugin instance a stable identity; and `config` supplies plugin-specific configuration. Set `disabled: true` to skip an entry temporarily. + +```yaml +- id: local-tool + name: './src/my-tool.ts' + disabled: false + config: + toolName: my_tool +``` + +Plugins load in file order. Place plugins that depend on services after the applications or capability plugins that provide them. Missing models, tools, and plugins fail as early as possible instead of being silently ignored. + +## JavaScript values and environment variables + +The Cordis loader evaluates runtime expressions tagged with `!!js`. Keep API keys and other secrets in the gitignored `.env` file at the repository root, never in committed configuration. + +```yaml +config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + cwd: !!js process.cwd() +``` + +The tag is `!!js`, not `!js`. + +## Exact configuration reference + +The generated [plugin configuration catalog](../../config-catalog.md) lists every current field, type, and default. For composition concepts, continue to the [architecture](../../architecture.md) and [capability interfaces](../../capability-seams.md). To create a configuration, copy the closest entry from the [examples overview](../../../examples/README.md) and adapt it. diff --git a/docs/user/zh-CN/guide/config.md b/docs/user/guide/config.zh.md similarity index 71% rename from docs/user/zh-CN/guide/config.md rename to docs/user/guide/config.zh.md index 5e13b69d9f..ee1ea9a0c1 100644 --- a/docs/user/zh-CN/guide/config.md +++ b/docs/user/guide/config.zh.md @@ -1,14 +1,16 @@ # 配置文件 +[English](config.md) | 中文 + Harness 使用 `cordis.yml` 描述 Agent 加载哪些插件以及每个插件的参数。配置文件负责组合能力；每个包真正支持的字段和默认值由源码生成的配置目录负责记录，避免两份手写表格逐渐不一致。 ## 从真实配置开始 仓库中的示例就是可以运行的配置，也是新项目最可靠的起点： -- [echo-agent](../../../../examples/echo-agent/cordis.yml) 使用本地 mock 模型，不需要 API key。 -- [coding-agent](../../../../examples/coding-agent/cordis.yml) 组合 DeepSeek 模型、Bash、文件系统、压缩、子代理和工作流。 -- [acp-agent](../../../../examples/acp-agent/cordis.yml) 通过 ACP 接入编辑器客户端。 +- [echo-agent](../../../examples/echo-agent/cordis.yml) 使用本地 mock 模型，不需要 API key。 +- [coding-agent](../../../examples/coding-agent/cordis.yml) 组合 DeepSeek 模型、Bash、文件系统、压缩、子代理和工作流。 +- [acp-agent](../../../examples/acp-agent/cordis.yml) 通过 ACP 接入编辑器客户端。 最小配置由一组插件条目组成： @@ -54,4 +56,4 @@ config: ## 精确配置参考 -每个插件当前支持的字段、类型和默认值见自动生成的[插件配置目录](../../../config-catalog.md)。理解插件如何组合可继续阅读[架构说明](../../../architecture.md)和[能力接口](../../../capability-seams.md)；要创建自己的配置，优先复制并修改[示例目录说明](../../../../examples/README.md)中最接近的例子。 +每个插件当前支持的字段、类型和默认值见自动生成的[插件配置目录](../../config-catalog.md)。理解插件如何组合可继续阅读[架构说明](../../architecture.md)和[能力接口](../../capability-seams.md)；要创建自己的配置，优先复制并修改[示例目录说明](../../../examples/README.md)中最接近的例子。 diff --git a/docs/user/guide/index.i18n.yaml b/docs/user/guide/index.i18n.yaml new file mode 100644 index 0000000000..12ccac1bcb --- /dev/null +++ b/docs/user/guide/index.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +index.md: 4daf7fdc76b38b5d10cc8b4726d9b6239a72933f +index.zh.md: 1f41078822009234cbaf513aaa8dbc01c4b5d879 diff --git a/docs/user/guide/index.md b/docs/user/guide/index.md new file mode 100644 index 0000000000..4daf7fdc76 --- /dev/null +++ b/docs/user/guide/index.md @@ -0,0 +1,49 @@ +# Introduction + +English | [中文](index.zh.md) + +DeepSeek Harness is a **plugin-based agent development framework** built on the [Cordis](https://github.com/cordiverse/cordis) microkernel. Its central idea is simple: **everything is a plugin**. + +## What it is + +Harness implements every capability an AI agent needs—including LLM calls, tool execution, session management, and subtask delegation—as a composable plugin. A `cordis.yml` file declares which plugins to load and how to configure them, assembling a complete agent. + +```yaml +# Select the LLM backend +- name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + +# Select the application template +- name: '@deepseek-ai/dsh-stdio-agent' + config: + model: deepseek-v4-flash +``` + +## Who it is for + +### Application users + +To run an existing agent application, such as a coding assistant or conversational agent: + +1. Copy an example template. +2. Add an API key. +3. Run it. + +No code is required. See the [quick start](./quickstart.md). + +### Plugin developers + +To add a custom tool, a new LLM adapter, or another execution backend, write a plugin. Harness provides explicit extension interfaces and a type-safe development experience. See [development](../develop/basic/). + +## Core features + +- **Configuration only** — `cordis.yml` selects the capability set; changing a model or adding a tool is a configuration edit. +- **Hot replacement (HMR)** — edit plugin code during development without restarting the process. + +## Technology + +- **Runtime**: Node.js ^22.19 or >= 24 +- **Language**: TypeScript (ESM) +- **Framework**: Cordis +- **Package manager**: pnpm workspaces (the repository pins pnpm 11) diff --git a/docs/user/zh-CN/guide/index.md b/docs/user/guide/index.zh.md similarity index 94% rename from docs/user/zh-CN/guide/index.md rename to docs/user/guide/index.zh.md index 8c7f7e603a..1f41078822 100644 --- a/docs/user/zh-CN/guide/index.md +++ b/docs/user/guide/index.zh.md @@ -1,5 +1,7 @@ # 介绍 +[English](index.md) | 中文 + DeepSeek Harness 是一个**插件化的 Agent 开发框架**，基于 [Cordis](https://github.com/cordiverse/cordis) 微内核构建。它的核心理念是：**一切皆插件**。 ## 它是什么 @@ -7,12 +9,12 @@ DeepSeek Harness 是一个**插件化的 Agent 开发框架**，基于 [Cordis]( Harness 将一个 AI Agent（智能体） 所需要的所有能力——LLM 调用、工具执行、会话管理、子任务分配——全部构建为可组合的插件。你通过一个 `cordis.yml` 配置文件来声明加载哪些插件、使用什么参数，就能组装出一个完整的 Agent。 ```yaml -# 选择 LLM 后端 +# Select the LLM backend - name: '@deepseek-ai/dsh-llm-deepseek' config: apiKey: !!js process.env.DEEPSEEK_API_KEY -# 选择应用模板 +# Select the application template - name: '@deepseek-ai/dsh-stdio-agent' config: model: deepseek-v4-flash diff --git a/docs/user/guide/quickstart.i18n.yaml b/docs/user/guide/quickstart.i18n.yaml new file mode 100644 index 0000000000..310dfaa62f --- /dev/null +++ b/docs/user/guide/quickstart.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +quickstart.md: c2932cf5a5f49c3e3ddb887866b421c6e6cad7a1 +quickstart.zh.md: 54ddb50be31203e98d4cd75d0b8851f8f0e14cc5 diff --git a/docs/user/guide/quickstart.md b/docs/user/guide/quickstart.md new file mode 100644 index 0000000000..c2932cf5a5 --- /dev/null +++ b/docs/user/guide/quickstart.md @@ -0,0 +1,99 @@ +# Quick start + +English | [中文](quickstart.zh.md) + +This guide gets an agent running in five minutes. + +## Prerequisites + +- [Node.js](https://nodejs.org/) ^22.19 or >= 24 +- [pnpm](https://pnpm.io/) 11 (use Corepack to select the repository-pinned version) + +```sh +# Check versions +node -v # v22.19.x, or v24.x and newer +corepack enable +pnpm -v # 11.x +``` + +## Step 1: run echo-agent + +echo-agent needs no API key and runs after dependencies are installed. + +```sh +# Clone the repository +git clone https://github.com/deepseek-harness/deepseek-harness.git +cd deepseek-harness + +# Install dependencies +pnpm install + +# Start echo-agent +pnpm run demo:echo +``` + +The process prints: + +``` +echo-agent ready. Type a message ("echo " triggers the tool). +> +``` + +Enter: + +``` +> echo hello world +``` + +The model issues a tool call, and the echo tool returns the text in uppercase: + +``` +[tool call] echo({"text":"hello world"}) +[tool result] ECHO: HELLO WORLD +``` + +Your local environment is ready. + +## Step 2: use a real model + +Next, connect a real DeepSeek model and run the complete command-line agent. + +### Get an API key + +Get an API key from [DeepSeek Platform](https://platform.deepseek.com/). + +### Configure the environment + +Create a gitignored `.env` file in the repository root: + +```sh +DEEPSEEK_API_KEY=sk-your-key-here +``` + +### Start coding-agent + +```sh +pnpm run demo:repl +``` + +``` +agent REPL ready. Give it a coding task. +> +``` + +This is a complete coding assistant that can read and write files, run commands, and delegate subtasks. + +Try a task: + +``` +> Create hello.js in the current directory, print "Hello from Harness!", and run it +``` + +## What happened + +echo-agent and coding-agent use the same application framework (`@deepseek-ai/dsh-stdio-agent`). Their `cordis.yml` files select different plugins and configuration. Custom agents use the same composition model. + +## Next steps + +- [Configuration](./config.md) — understand the `cordis.yml` format +- [Develop a plugin](../develop/basic/) — build your own tool or backend diff --git a/docs/user/zh-CN/guide/quickstart.md b/docs/user/guide/quickstart.zh.md similarity index 88% rename from docs/user/zh-CN/guide/quickstart.md rename to docs/user/guide/quickstart.zh.md index 7ca4b19332..54ddb50be3 100644 --- a/docs/user/zh-CN/guide/quickstart.md +++ b/docs/user/guide/quickstart.zh.md @@ -1,5 +1,7 @@ # 快速开始 +[English](quickstart.md) | 中文 + 本指南带你在 5 分钟内跑起一个 Agent。 ## 环境准备 @@ -8,8 +10,8 @@ - [pnpm](https://pnpm.io/) 11（建议通过 Corepack 使用仓库固定的版本） ```sh -# 确认版本 -node -v # v22.19.x，或 v24.x 及更高版本 +# Check versions +node -v # v22.19.x, or v24.x and newer corepack enable pnpm -v # 11.x ``` @@ -19,14 +21,14 @@ pnpm -v # 11.x echo-agent 不需要 API key，装好依赖就能跑。 ```sh -# 克隆仓库 +# Clone the repository git clone https://github.com/deepseek-harness/deepseek-harness.git cd deepseek-harness -# 安装依赖 +# Install dependencies pnpm install -# 启动 echo-agent +# Start echo-agent pnpm run demo:echo ``` @@ -84,7 +86,7 @@ agent REPL ready. Give it a coding task. 试着给它一个任务： ``` -> 在当前目录创建一个 hello.js，内容是打印 "Hello from Harness!"，然后运行它 +> Create hello.js in the current directory, print "Hello from Harness!", and run it ``` ## 回头看 diff --git a/docs/user/index.i18n.yaml b/docs/user/index.i18n.yaml new file mode 100644 index 0000000000..b3fc8da2d2 --- /dev/null +++ b/docs/user/index.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +index.md: e9a1f03785c7472c47550ec59ea0165d28d3d9a6 +index.zh.md: 907f1452c9ff50d619989c18dcf2727addb2573d diff --git a/docs/user/index.md b/docs/user/index.md new file mode 100644 index 0000000000..e9a1f03785 --- /dev/null +++ b/docs/user/index.md @@ -0,0 +1,25 @@ +--- +layout: home +hero: + name: DeepSeek Harness + text: Plugin-based agent development framework + tagline: Built on the Cordis microkernel; everything is a plugin + actions: + - theme: brand + text: Quick start + link: /en/guide/quickstart + - theme: alt + text: Develop plugins + link: /en/develop/basic/ +features: + - title: Plugin architecture + details: Built on the Cordis plugin system. Every capability is registered by a plugin, takes effect when loaded, and is reverted when unloaded. + - title: Configuration as composition + details: One cordis.yml determines the agent's complete capability set. Change a model or add a tool by editing configuration. + - title: Ready to use + details: Includes LLM calls, file access, Bash execution, subagent delegation, and the rest of the core toolchain. Copy a template to get started. +--- + +# DeepSeek Harness + +English | [中文](index.zh.md) diff --git a/docs/user/zh-CN/index.md b/docs/user/index.zh.md similarity index 93% rename from docs/user/zh-CN/index.md rename to docs/user/index.zh.md index 1c495125c6..907f1452c9 100644 --- a/docs/user/zh-CN/index.md +++ b/docs/user/index.zh.md @@ -19,3 +19,7 @@ features: - title: 开箱即用 details: 内置 LLM 调用、文件读写、Bash 执行、子代理委派等完整工具链，复制模板即可运行。 --- + +# DeepSeek Harness + +[English](index.md) | 中文 diff --git a/docs/user/zh-CN/develop/practice/llm-adapter.md b/docs/user/zh-CN/develop/practice/llm-adapter.md deleted file mode 100644 index 0b0ae3cff0..0000000000 --- a/docs/user/zh-CN/develop/practice/llm-adapter.md +++ /dev/null @@ -1,174 +0,0 @@ -# LLM 适配器 - -本文介绍如何为 Harness 接入一个新的 LLM 提供方。 - -## 概述 - -LLM 适配器是一个继承 `LlmAdapter` 的类，实现 `stream()` 方法，将 Harness 的统一请求格式转换为具体 API 的调用。 - -## 最小实现 - -```typescript -import type { Context } from 'cordis' -import { LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' - -class MyAdapter extends LlmAdapter { - private apiKey: string - - constructor(apiKey: string) { - super() - this.apiKey = apiKey - } - - async *stream(options: GenerateOptions): AsyncIterable { - // 1. 将 options.messages 转换为你的 API 格式 - // 2. 调用 API（流式） - // 3. 将 API 响应转换为 StreamChunk 序列 - } -} - -export interface Config { - apiKey: string - models: string[] -} - -export const name = 'my-llm-adapter' -export const inject = ['llm'] - -export function apply(ctx: Context, config: Config) { - const adapter = new MyAdapter(config.apiKey) - ctx.llm.registerAdapter(config.models, adapter) -} -``` - -## StreamChunk 协议 - -`stream()` 必须按以下协议 yield chunk： - -```typescript -// 1. 每个内容块以 block-start 开始 -yield { type: 'block-start', index: 0, blockType: 'text' } - -// 2. 文本块使用 text-delta -yield { type: 'text-delta', index: 0, text: 'Hello' } -yield { type: 'text-delta', index: 0, text: ' world' } - -// 3. 每个内容块以 block-end 结束（携带完整 block） -yield { - type: 'block-end', - index: 0, - block: { type: 'text', text: 'Hello world' }, -} - -// 4. Tool call 块 -yield { type: 'block-start', index: 1, blockType: 'tool-call' } -yield { - type: 'tool-call-delta', - index: 1, - id: CallId('call-123'), - name: 'bash', - argumentsDelta: '{"command":"ls"}', -} -yield { - type: 'block-end', - index: 1, - block: { - type: 'tool-call', - id: CallId('call-123'), - name: 'bash', - arguments: '{"command":"ls"}', - }, -} - -// 5. Token 用量 -yield { type: 'usage', usage: { inputTokens: 100, outputTokens: 50 } } - -// 6. 结束原因 -yield { type: 'finish', reason: { kind: 'stop' } } -// 或: { kind: 'tool-calls' } 表示模型想调用 tool -``` - -### 关键规则 - -- 每个 `block-start` 必须有对应的 `block-end` -- `index` 从 0 递增，标识内容块顺序 -- `tool-call-delta` 的 `argumentsDelta` 是 JSON 字符串的增量（可以一次 yield 全部，也可以分多次） -- `finish` 必须是最后一个 chunk -- `usage` 在 `finish` 之前 yield - -## GenerateOptions - -`stream()` 接收的请求包含： - -```typescript -interface GenerateOptions { - /** 模型名 */ - model: string - /** 对话历史 */ - messages: Message[] - /** 可用的 tool 列表 */ - tools?: ToolSpec[] - /** 系统提示词 */ - system?: string - /** 最大输出 token */ - maxTokens?: number - /** 温度 */ - temperature?: number - /** 取消或卸载时中止进行中的请求 */ - signal?: AbortSignal -} -``` - -你的适配器需要将这些映射到具体 API 的参数。 - -## 注册适配器 - -```typescript -ctx.llm.registerAdapter(['model-name-1', 'model-name-2'], adapter) -``` - -第一个参数是该适配器支持的模型名列表。当用户在 `cordis.yml` 中配置 `model: model-name-1` 时，框架会路由到这个适配器。 - -## 在 cordis.yml 中使用 - -```yaml -- id: my-llm - name: './src/my-llm-adapter.ts' - config: - apiKey: !!js process.env.MY_API_KEY - models: - - my-model-v1 - - my-model-v2 - -- id: stdio-agent - name: '@deepseek-ai/dsh-stdio-agent' - config: - model: my-model-v1 # 引用上面注册的模型名 -``` - -## 实战参考 - -仓库中有两个完整实现可供参考： - -- `packages/llm/llm-deepseek/` — DeepSeek API 适配器（OpenAI 兼容格式） -- `packages/llm/llm-pi-ai/` — Pi AI 适配器（不同的 API 格式） -- `examples/echo-agent/src/mock-llm.ts` — 最简 mock 适配器（教学用） - -mock 适配器是学习 StreamChunk 协议的最佳起点——它用纯本地逻辑演示了完整的 chunk 序列。 - -## 错误处理 - -适配器中的异常会被 agent-loop 捕获并转化为 `LlmError`，告知上层。不需要在 `stream()` 内部做错误恢复——让异常冒泡即可。 - -```typescript -async *stream(options: GenerateOptions): AsyncIterable { - const response = await fetch(this.endpoint, { - // ...method、headers 和 body - signal: options.signal, - }) - if (!response.ok) { - throw new Error(`API error: ${response.status}`) - } - // ... 正常流式处理 -} -``` diff --git a/scripts/project-doc-site.spec.ts b/scripts/project-doc-site.spec.ts index 9a6162576d..19417d5d99 100644 --- a/scripts/project-doc-site.spec.ts +++ b/scripts/project-doc-site.spec.ts @@ -20,6 +20,7 @@ function fixture(): { root: string; pages: DocsPage[] } { mkdirSync(join(root, 'packages'), { recursive: true }) writeFileSync(join(root, 'docs/a.md'), '# A\n') writeFileSync(join(root, 'docs/b.md'), '# B\n') + writeFileSync(join(root, 'docs/x(y).md'), '# Parentheses\n') writeFileSync(join(root, 'packages/tool.ts'), 'one\ntwo\n') writeFileSync(join(root, 'packages/logo.svg'), '\n') return { @@ -88,6 +89,46 @@ describe('rewriteMarkdown', () => { })).toBe(source) }) + it('replaces the destination token without changing repeated titles or escapes', () => { + const { root, pages } = fixture() + const source = '[title](b.md "b.md") [escaped](x\\(y\\).md)\n' + expect(rewriteMarkdown(source, { + locale: 'en', + sourcePath: 'docs/a.md', + route: 'en/a.md', + pages, + repoRoot: root, + repositoryRef: 'abc123', + })).toBe( + '[title](./reference/b.md "b.md") ' + + '[escaped](https://github.com/deepseek-harness/deepseek-harness/blob/abc123/docs/x(y).md)\n', + ) + }) + + it('routes a pair switcher across locales while ordinary links stay in locale', () => { + const { root, pages } = fixture() + writeFileSync(join(root, 'docs/a.zh.md'), '# A\n') + const paired = pages.filter(page => page.source !== 'docs/a.md') + paired.push( + { + locale: 'root', contentLocale: 'zh-CN', source: 'docs/a.zh.md', sourceAliases: ['docs/a.md'], + route: 'guide/a.md', label: 'A', sidebar: 'zh-guide', section: 'Test', order: 1, + }, + { + locale: 'en', contentLocale: 'en-US', source: 'docs/a.md', sourceAliases: ['docs/a.zh.md'], + route: 'en/guide/a.md', label: 'A', sidebar: 'en-guide', section: 'Test', order: 1, + }, + ) + expect(rewriteMarkdown('[English](a.md) [B](b.md)\n', { + locale: 'root', + sourcePath: 'docs/a.zh.md', + route: 'guide/a.md', + pages: paired, + repoRoot: root, + repositoryRef: 'abc123', + })).toBe('[English](../en/guide/a.md) [B](../reference-root/b.md)\n') + }) + it('fails loud when a relative target is missing', () => { const { root, pages } = fixture() expect(() => rewriteMarkdown('[missing](missing.md)\n', { @@ -102,14 +143,21 @@ describe('rewriteMarkdown', () => { }) describe('docsPages locale routes', () => { - it('publishes the same canonical source at every corresponding locale route', () => { + it('publishes every route in both locales and selects paired user sources', () => { const byRoute = new Map(docsPages.map(page => [page.route, page])) for (const page of docsPages.filter(page => page.locale === 'root')) { const counterpart = byRoute.get(`en/${page.route}`) expect(counterpart, page.route).toBeDefined() expect(counterpart?.locale).toBe('en') - expect(counterpart?.source).toBe(page.source) - expect(counterpart?.contentLocale).toBe(page.contentLocale) + if (page.source.startsWith('docs/user/')) { + expect(page.source).toMatch(/\.zh\.md$/) + expect(page.contentLocale).toBe('zh-CN') + expect(counterpart?.source).toBe(page.source.replace(/\.zh\.md$/, '.md')) + expect(counterpart?.contentLocale).toBe('en-US') + } else { + expect(counterpart?.source).toBe(page.source) + expect(counterpart?.contentLocale).toBe(page.contentLocale) + } } }) }) diff --git a/scripts/project-doc-site.ts b/scripts/project-doc-site.ts index 7ef35a6d28..5c43e6f46a 100644 --- a/scripts/project-doc-site.ts +++ b/scripts/project-doc-site.ts @@ -23,6 +23,13 @@ interface Replacement { value: string } +interface DestinationRange { + start: number + end: number +} + +type RewritableNode = Extract + /** Inputs for rewriting one canonical Markdown page. */ export interface RewriteMarkdownOptions { locale: DocsLocale @@ -44,6 +51,75 @@ function isExternalOrSiteAbsolute(url: string): boolean { || /^[a-zA-Z][a-zA-Z0-9+.-]*:/.test(url) } +function skipWhitespace(source: string, start: number): number { + let index = start + while (/\s/.test(source[index] ?? '')) index += 1 + return index +} + +function labelEnd(source: string): number { + const first = source.indexOf('[') + if (first === -1) return -1 + let depth = 0 + for (let index = first; index < source.length; index += 1) { + const char = source[index] + if (char === '\\') { + index += 1 + } else if (char === '[') { + depth += 1 + } else if (char === ']') { + depth -= 1 + if (depth === 0) return index + } + } + return -1 +} + +function destinationRange(rawNode: string, type: 'link' | 'image' | 'definition'): DestinationRange { + const endOfLabel = labelEnd(rawNode) + if (endOfLabel === -1) { + throw new Error(`project-doc-site: cannot locate label end in ${JSON.stringify(rawNode)}.`) + } + + let start: number + if (type === 'definition') { + const colon = rawNode.indexOf(':', endOfLabel + 1) + if (colon === -1) { + throw new Error(`project-doc-site: cannot locate definition separator in ${JSON.stringify(rawNode)}.`) + } + start = skipWhitespace(rawNode, colon + 1) + } else { + if (rawNode[endOfLabel + 1] !== '(') { + throw new Error(`project-doc-site: cannot locate inline destination in ${JSON.stringify(rawNode)}.`) + } + start = skipWhitespace(rawNode, endOfLabel + 2) + } + + if (rawNode[start] === '<') { + for (let index = start + 1; index < rawNode.length; index += 1) { + if (rawNode[index] === '\\') index += 1 + else if (rawNode[index] === '>') return { start: start + 1, end: index } + } + throw new Error(`project-doc-site: cannot locate angle-bracket destination end in ${JSON.stringify(rawNode)}.`) + } + + let depth = 0 + for (let index = start; index < rawNode.length; index += 1) { + const char = rawNode[index] + if (char === '\\') { + index += 1 + } else if (char === '(') { + depth += 1 + } else if (char === ')') { + if (depth === 0) return { start, end: index } + depth -= 1 + } else if (/\s/.test(char ?? '') && depth === 0) { + return { start, end: index } + } + } + return { start, end: rawNode.length } +} + function splitTarget(url: string): { path: string; suffix: string } { const boundary = url.search(/[?#]/) if (boundary === -1) return { path: url, suffix: '' } @@ -78,6 +154,12 @@ function sourceMap(pages: DocsPage[]): Map> { return map } +function counterpartSource(source: string): string { + return source.endsWith('.zh.md') + ? source.replace(/\.zh\.md$/, '.md') + : source.replace(/\.md$/, '.zh.md') +} + function resolveRepositoryTarget(sourceAbs: string, rawPath: string, repoRoot: string): { absPath: string; line?: number } { const decoded = decodePath(rawPath) let absPath = resolve(dirname(sourceAbs), decoded) @@ -129,13 +211,17 @@ export function rewriteMarkdown(source: string, options: RewriteMarkdownOptions) const tree = fromMarkdown(source, { extensions: [gfm()], mdastExtensions: [gfmFromMarkdown()] }) const replacements: Replacement[] = [] - const rewrite = (node: Nodes & { url: string }): void => { + const rewrite = (node: RewritableNode): void => { if (isExternalOrSiteAbsolute(node.url)) return const { path, suffix } = splitTarget(node.url) if (path === '') return const { absPath, line } = resolveRepositoryTarget(sourceAbs, path, options.repoRoot) const targetPath = repoPath(absPath, options.repoRoot) - const page = published.get(targetPath)?.get(options.locale) + const isLanguageSwitcher = targetPath === counterpartSource(options.sourcePath) + const targetLocale: DocsLocale = isLanguageSwitcher + ? options.locale === 'root' ? 'en' : 'root' + : options.locale + const page = published.get(targetPath)?.get(targetLocale) const nextUrl = page === undefined ? githubTarget(absPath, line, suffix, options.repositoryRef, options.repoRoot, node.type === 'image') : routeTarget(options.route, page.route, suffix) @@ -146,13 +232,10 @@ export function rewriteMarkdown(source: string, options: RewriteMarkdownOptions) throw new Error(`project-doc-site: link ${JSON.stringify(node.url)} has no source offsets.`) } const rawNode = source.slice(start, end) - const urlOffset = rawNode.lastIndexOf(node.url) - if (urlOffset === -1) { - throw new Error(`project-doc-site: cannot locate raw target ${JSON.stringify(node.url)} in ${JSON.stringify(rawNode)}.`) - } + const rawDestination = destinationRange(rawNode, node.type) replacements.push({ - start: start + urlOffset, - end: start + urlOffset + node.url.length, + start: start + rawDestination.start, + end: start + rawDestination.end, value: nextUrl, }) } diff --git a/scripts/translation-pairing.manifest.json b/scripts/translation-pairing.manifest.json index 35a957e57d..c79d5c1492 100644 --- a/scripts/translation-pairing.manifest.json +++ b/scripts/translation-pairing.manifest.json @@ -11,6 +11,18 @@ "docs/development.md", "docs/i18n/README.md", "docs/i18n/translation-rules.md", + "docs/user/develop/basic/config.md", + "docs/user/develop/basic/index.md", + "docs/user/develop/basic/tool.md", + "docs/user/develop/framework/events.md", + "docs/user/develop/framework/index.md", + "docs/user/develop/framework/service.md", + "docs/user/develop/practice/index.md", + "docs/user/develop/practice/llm-adapter.md", + "docs/user/guide/config.md", + "docs/user/guide/index.md", + "docs/user/guide/quickstart.md", + "docs/user/index.md", "docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md", "docs/rfc/implemented/process/2026-07-02-bilingual-docs-and-pairing-gate.md", "python/README.md", diff --git a/website/docs.ts b/website/docs.ts index 16d53e5b8a..0e6897afe3 100644 --- a/website/docs.ts +++ b/website/docs.ts @@ -42,63 +42,93 @@ export interface DocsPage { } interface MirroredPage { - source: string + source: string | Record route: string - contentLocale: DocsPage['contentLocale'] + contentLocale: DocsPage['contentLocale'] | Record label: Record sidebar: Record section: Record order: number + sourceAliases?: string[] | Partial> +} + +type PairedPage = Omit & { + /** English side of a sibling `foo.md` / `foo.zh.md` pair. */ + source: string + /** Language-neutral repository aliases, such as the directory of an index page. */ sourceAliases?: string[] } -function mirroredPages(pages: MirroredPage[]): DocsPage[] { - return pages.flatMap(page => (['root', 'en'] as const).map(locale => ({ - locale, - contentLocale: page.contentLocale, - source: page.source, - route: locale === 'root' ? page.route : `en/${page.route}`, - label: page.label[locale], - sidebar: page.sidebar[locale], - section: page.section[locale], - order: page.order, - ...(page.sourceAliases === undefined ? {} : { sourceAliases: page.sourceAliases }), - }))) +function localized(value: T | Record, locale: DocsLocale): T { + return typeof value === 'object' && value !== null && !Array.isArray(value) + ? (value as Record)[locale] + : value } -const homeAndGuide = mirroredPages([ +function mirroredPages(pages: MirroredPage[]): DocsPage[] { + return pages.flatMap(page => (['root', 'en'] as const).map((locale) => { + const aliases = page.sourceAliases === undefined + ? undefined + : Array.isArray(page.sourceAliases) ? page.sourceAliases : page.sourceAliases[locale] + return { + locale, + contentLocale: localized(page.contentLocale, locale), + source: localized(page.source, locale), + route: locale === 'root' ? page.route : `en/${page.route}`, + label: page.label[locale], + sidebar: page.sidebar[locale], + section: page.section[locale], + order: page.order, + ...(aliases === undefined ? {} : { sourceAliases: aliases }), + } + })) +} + +function pairedPages(pages: PairedPage[]): DocsPage[] { + return mirroredPages(pages.map((page) => { + const chineseSource = page.source.replace(/\.md$/, '.zh.md') + const sharedAliases = page.sourceAliases ?? [] + return { + ...page, + source: { root: chineseSource, en: page.source }, + contentLocale: { root: 'zh-CN', en: 'en-US' }, + sourceAliases: { + root: [...sharedAliases, page.source], + en: [...sharedAliases, chineseSource], + }, + } + })) +} + +const homeAndGuide = pairedPages([ { - source: 'docs/user/zh-CN/index.md', + source: 'docs/user/index.md', route: 'index.md', - contentLocale: 'zh-CN', label: { root: 'DeepSeek Harness', en: 'DeepSeek Harness' }, sidebar: { root: null, en: null }, section: { root: '首页', en: 'Home' }, order: 0, }, { - source: 'docs/user/zh-CN/guide/index.md', + source: 'docs/user/guide/index.md', route: 'guide/index.md', - contentLocale: 'zh-CN', label: { root: '介绍', en: 'Introduction' }, sidebar: { root: 'zh-guide', en: 'en-guide' }, section: { root: '入门', en: 'Guide' }, order: 1, - sourceAliases: ['docs/user/zh-CN/guide'], + sourceAliases: ['docs/user/guide'], }, { - source: 'docs/user/zh-CN/guide/quickstart.md', + source: 'docs/user/guide/quickstart.md', route: 'guide/quickstart.md', - contentLocale: 'zh-CN', label: { root: '快速开始', en: 'Quick start' }, sidebar: { root: 'zh-guide', en: 'en-guide' }, section: { root: '入门', en: 'Guide' }, order: 2, }, { - source: 'docs/user/zh-CN/guide/config.md', + source: 'docs/user/guide/config.md', route: 'guide/config.md', - contentLocale: 'zh-CN', label: { root: '配置文件', en: 'Configuration' }, sidebar: { root: 'zh-guide', en: 'en-guide' }, section: { root: '入门', en: 'Guide' }, @@ -106,77 +136,69 @@ const homeAndGuide = mirroredPages([ }, ]) -const develop = mirroredPages([ +const develop = pairedPages([ { - source: 'docs/user/zh-CN/develop/basic/index.md', + source: 'docs/user/develop/basic/index.md', route: 'develop/basic/index.md', - contentLocale: 'zh-CN', label: { root: '第一个插件', en: 'First plugin' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '基础', en: 'Basics' }, order: 1, - sourceAliases: ['docs/user/zh-CN/develop/basic'], + sourceAliases: ['docs/user/develop/basic'], }, { - source: 'docs/user/zh-CN/develop/basic/tool.md', + source: 'docs/user/develop/basic/tool.md', route: 'develop/basic/tool.md', - contentLocale: 'zh-CN', label: { root: '开发一个 Tool', en: 'Build a tool' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '基础', en: 'Basics' }, order: 2, }, { - source: 'docs/user/zh-CN/develop/basic/config.md', + source: 'docs/user/develop/basic/config.md', route: 'develop/basic/config.md', - contentLocale: 'zh-CN', label: { root: '插件配置', en: 'Plugin configuration' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '基础', en: 'Basics' }, order: 3, }, { - source: 'docs/user/zh-CN/develop/framework/index.md', + source: 'docs/user/develop/framework/index.md', route: 'develop/framework/index.md', - contentLocale: 'zh-CN', label: { root: '插件与生命周期', en: 'Plugin lifecycle' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '框架能力', en: 'Framework' }, order: 1, - sourceAliases: ['docs/user/zh-CN/develop/framework'], + sourceAliases: ['docs/user/develop/framework'], }, { - source: 'docs/user/zh-CN/develop/framework/service.md', + source: 'docs/user/develop/framework/service.md', route: 'develop/framework/service.md', - contentLocale: 'zh-CN', label: { root: '服务与依赖', en: 'Services and dependencies' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '框架能力', en: 'Framework' }, order: 2, }, { - source: 'docs/user/zh-CN/develop/framework/events.md', + source: 'docs/user/develop/framework/events.md', route: 'develop/framework/events.md', - contentLocale: 'zh-CN', label: { root: '事件系统', en: 'Event system' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '框架能力', en: 'Framework' }, order: 3, }, { - source: 'docs/user/zh-CN/develop/practice/index.md', + source: 'docs/user/develop/practice/index.md', route: 'develop/practice/index.md', - contentLocale: 'zh-CN', label: { root: '能力的三层拆分', en: 'Capability layering' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '实战', en: 'Practice' }, order: 1, - sourceAliases: ['docs/user/zh-CN/develop/practice'], + sourceAliases: ['docs/user/develop/practice'], }, { - source: 'docs/user/zh-CN/develop/practice/llm-adapter.md', + source: 'docs/user/develop/practice/llm-adapter.md', route: 'develop/practice/llm-adapter.md', - contentLocale: 'zh-CN', label: { root: 'LLM 适配器', en: 'LLM adapter' }, sidebar: { root: 'zh-develop', en: 'en-develop' }, section: { root: '实战', en: 'Practice' }, From 54fb96ef04df12bf59c69b14de24bcba8ada98d4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 04:46:35 +0800 Subject: [PATCH 111/323] refactor: name front door defaults --- packages/examples/acp-demo/src/index.ts | 7 +++---- packages/examples/stdio-demo/src/index.ts | 12 ++++++------ 2 files changed, 9 insertions(+), 10 deletions(-) diff --git a/packages/examples/acp-demo/src/index.ts b/packages/examples/acp-demo/src/index.ts index 0439363301..a26220dbf7 100644 --- a/packages/examples/acp-demo/src/index.ts +++ b/packages/examples/acp-demo/src/index.ts @@ -18,6 +18,7 @@ import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' export const name = 'acp-demo' +const DEFAULT_PERSISTENCE_ROOT = './.sessions' /** * App config: the swappable per-deployment values. `model` configures the @@ -54,9 +55,7 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, - // TODO(single-default-literal): share this schema default and the defensive - // apply() fallback through one named constant while retaining both boundaries. - persistenceRoot: z.string().default('./.sessions'), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), skills: agentCore.SkillConfigSchema, }) /* jscpd:ignore-end */ @@ -76,6 +75,6 @@ export function apply(ctx: Context, config: Config): void { ...config.skills !== undefined ? { skills: config.skills } : {}, }) ctx.plugin(UserInteractionService) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(acp, { model: config.model }) } diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index 742371ecd5..c54f9499c6 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -23,6 +23,8 @@ import * as toolAskUser from '@deepseek-ai/dsh-tool-ask-user' import * as uiStdio from '@deepseek-ai/dsh-stdio' export const name = 'stdio-demo' +const DEFAULT_PERSISTENCE_ROOT = './.sessions' +const DEFAULT_WELCOME = 'ready.' /** * App config: the swappable per-demo values, each routed to where the app wires @@ -65,10 +67,8 @@ export const Config: z = z.object({ // schemastery's native [] default would read as an invalid configured list. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, - // TODO(single-default-literal): share these schema defaults and defensive - // apply() fallbacks through named constants while retaining both boundaries. - persistenceRoot: z.string().default('./.sessions'), - welcome: z.string().default('ready.'), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), + welcome: z.string().default(DEFAULT_WELCOME), skills: agentCore.SkillConfigSchema, resumeSessionId: z.string(), }) @@ -85,10 +85,10 @@ export function apply(ctx: Context, config: Config): void { const resumeSessionId = config.resumeSessionId === '' ? undefined : config.resumeSessionId const sessionId = SessionId(resumeSessionId ?? `main-session-${randomUUID()}`) ctx.plugin(ConsoleExporter) - ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) ctx.plugin(UserInteractionService) ctx.plugin(uiStdio, { - welcome: config.welcome ?? 'ready.', + welcome: config.welcome ?? DEFAULT_WELCOME, sessionId, }) ctx.plugin(agentCore, { From 732735b27fb23fe90ee7f6c9853c7953b8879fdc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:32:15 +0800 Subject: [PATCH 112/323] docs: align default fallback test comments --- packages/examples/acp-demo/tests/acp-agent.spec.ts | 2 +- packages/examples/stdio-demo/tests/stdio-agent.spec.ts | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/examples/acp-demo/tests/acp-agent.spec.ts b/packages/examples/acp-demo/tests/acp-agent.spec.ts index f3495c827c..ab36aa56c8 100644 --- a/packages/examples/acp-demo/tests/acp-agent.spec.ts +++ b/packages/examples/acp-demo/tests/acp-agent.spec.ts @@ -82,7 +82,7 @@ describe('dsh-acp-demo composition', () => { }) it('defaults the persistence root when omitted', async () => { - // Exercises the `?? './.sessions'` fallback for a direct-apply caller that + // Exercises the `DEFAULT_PERSISTENCE_ROOT` fallback for a direct-apply caller that // bypasses the schema's `.default(...)`: call `apply` directly (not via // `ctx.plugin`, which validates+defaults the config first) with no // persistenceRoot, so the runtime fallback is the one that fires. diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index 79681fd954..b2398fea7c 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -100,7 +100,7 @@ describe('dsh-stdio-demo app', () => { it('defaults persistenceRoot and welcome when omitted', async () => { // Direct apply (NOT via ctx.plugin, which validates+defaults the config - // first) so the runtime `?? './.sessions'` / `?? 'ready.'` fallbacks on + // first) so the runtime `DEFAULT_PERSISTENCE_ROOT` / `DEFAULT_WELCOME` fallbacks on // apply()'s last two lines are the ones that fire — covering a // schema-bypassing direct-mount caller. const ctx = new Context() From 29d545eb212e88f9589134be420eff3ed8673b81 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 19:52:45 +0800 Subject: [PATCH 113/323] Refresh front-door config catalog --- docs/config-catalog.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 29be66bbbe..5bbdbe5fd3 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -63,7 +63,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/acp-demo/src/index.ts:31`](../packages/examples/acp-demo/src/index.ts) +Source: [`packages/examples/acp-demo/src/index.ts:32`](../packages/examples/acp-demo/src/index.ts) ## `@deepseek-ai/dsh-agent-loop` @@ -722,7 +722,7 @@ export interface Config { Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) -Source: [`packages/examples/stdio-demo/src/index.ts:37`](../packages/examples/stdio-demo/src/index.ts) +Source: [`packages/examples/stdio-demo/src/index.ts:39`](../packages/examples/stdio-demo/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` From b78cdbcd51d5c397f181a71ff5b0e61063e6f791 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 21:21:24 +0800 Subject: [PATCH 114/323] feat(examples): add one-shot CLI demo --- .agents/skills/dsh-pre-push-checks/SKILL.md | 2 +- AGENTS.md | 13 +- docs/architecture.md | 2 +- docs/capability-seams.md | 7 +- docs/config-catalog.md | 24 ++ docs/event-producer-consumer.md | 2 +- docs/module-graph.md | 9 + examples/README.md | 4 +- examples/coding-agent/README.md | 22 +- examples/coding-agent/cli.cordis.yml | 24 ++ .../tests/cli-keyless-smoke.e2e.ts | 43 ++ examples/coding-agent/tests/cli.e2e.ts | 33 ++ .../tests/fixtures/cli-mock-llm.ts | 37 ++ .../tests/fixtures/cli.cordis.yml | 24 ++ knip.json | 5 + package.json | 1 + packages/README.md | 2 +- packages/examples/README.md | 3 +- packages/examples/cli-demo/README.md | 62 +++ packages/examples/cli-demo/package.json | 59 +++ packages/examples/cli-demo/src/bin.ts | 34 ++ packages/examples/cli-demo/src/cli.ts | 380 ++++++++++++++++++ packages/examples/cli-demo/src/index.ts | 63 +++ .../examples/cli-demo/tests/built-bin.e2e.ts | 172 ++++++++ .../examples/cli-demo/tests/cli-demo.spec.ts | 105 +++++ packages/examples/cli-demo/tests/cli.spec.ts | 362 +++++++++++++++++ packages/examples/cli-demo/tsconfig.json | 22 + packages/examples/cli-demo/tsdown.config.ts | 13 + packages/support/loader-smoke/README.md | 2 +- packages/support/loader-smoke/src/index.ts | 19 +- .../loader-smoke/tests/fixtures/success.ts | 1 + .../loader-smoke/tests/loader-smoke.spec.ts | 27 ++ pnpm-lock.yaml | 39 ++ scripts/gen-doc-graphs.ts | 8 +- scripts/run-gates.ts | 1 + tsconfig.build.json | 1 + tsconfig.json | 1 + 37 files changed, 1600 insertions(+), 28 deletions(-) create mode 100644 examples/coding-agent/cli.cordis.yml create mode 100644 examples/coding-agent/tests/cli-keyless-smoke.e2e.ts create mode 100644 examples/coding-agent/tests/cli.e2e.ts create mode 100644 examples/coding-agent/tests/fixtures/cli-mock-llm.ts create mode 100644 examples/coding-agent/tests/fixtures/cli.cordis.yml create mode 100644 packages/examples/cli-demo/README.md create mode 100644 packages/examples/cli-demo/package.json create mode 100644 packages/examples/cli-demo/src/bin.ts create mode 100644 packages/examples/cli-demo/src/cli.ts create mode 100644 packages/examples/cli-demo/src/index.ts create mode 100644 packages/examples/cli-demo/tests/built-bin.e2e.ts create mode 100644 packages/examples/cli-demo/tests/cli-demo.spec.ts create mode 100644 packages/examples/cli-demo/tests/cli.spec.ts create mode 100644 packages/examples/cli-demo/tsconfig.json create mode 100644 packages/examples/cli-demo/tsdown.config.ts diff --git a/.agents/skills/dsh-pre-push-checks/SKILL.md b/.agents/skills/dsh-pre-push-checks/SKILL.md index 4ce005ee79..433aa38942 100644 --- a/.agents/skills/dsh-pre-push-checks/SKILL.md +++ b/.agents/skills/dsh-pre-push-checks/SKILL.md @@ -54,7 +54,7 @@ pnpm run test:snapshot Run built-bin smoke tests after `pnpm run build` when app packages, app boot, package runtime imports, bin entries, loader behavior, or published artifact paths change. ```sh -pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/cli-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts ``` Run real e2e when behavior depends on a real model/API, tool-use loop, ACP integration, prompt injection, or end-to-end agent UX. If `.env` is available, use it; do not print secrets. diff --git a/AGENTS.md b/AGENTS.md index 23d7c0263b..b9731f2c80 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -43,8 +43,8 @@ Package groups: [packages/README.md](packages/README.md). ```sh pnpm install # pnpm workspaces, node ^22.19 || >=24 pnpm run test # vitest unit tests -pnpm run test:coverage # THE gating test run: per-file 100% coverage on packages/*/*/src -pnpm run test:e2e # real-API tests; self-skip without DEEPSEEK_API_KEY +pnpm run test:coverage # gate: per-file 100% on packages/*/*/src +pnpm run test:e2e # real API; skips without key pnpm run test:snapshot # keyless ACP replay vs goldens; filter: -t pnpm run test:snapshot:record # re-record goldens (needs key) pnpm run typecheck @@ -54,9 +54,10 @@ pnpm run build # tsc emits lib/types, tsdown bundles runtime pnpm run hygiene # knip + publint + workspace constraints + NodeNext consumer check pnpm run doc-sync # all documentation gates; see the doc-sync script in package.json pnpm run demo:echo # mock-model REPL, no key needed -pnpm run demo:repl # real REPL coding agent (needs DEEPSEEK_API_KEY) -pnpm run demo:cordis # self-referential demo: the agent modifies its own runtime (needs key) -pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) +pnpm run demo:repl # real coding REPL (needs key) +pnpm run demo:cli -- "task" # one-shot agent (needs key) +pnpm run demo:cordis # self-modifying runtime demo (needs key) +pnpm run demo:acp # ACP server (needs key) ``` ### Run the CI gates locally before marking a PR ready @@ -79,7 +80,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/examples/stdio-demo/tests/built-bin.e2e.ts packages/examples/cli-demo/tests/built-bin.e2e.ts packages/examples/acp-demo/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gate ([why](docs/testing.md)); report only commands actually run. diff --git a/docs/architecture.md b/docs/architecture.md index 4049049e25..c46e7b1619 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -138,7 +138,7 @@ Some seams bend the template deliberately. LLM keeps interface and consumer voca ### Bundles And Apps -`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` for terminal REPL, and `dsh-acp-demo` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). +`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` for terminal REPL, `dsh-cli-demo` for one headless persisted turn with format-pure stdout, and `dsh-acp-demo` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). ### Where New Behavior Goes diff --git a/docs/capability-seams.md b/docs/capability-seams.md index af22ba4c15..ff22465148 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -17,6 +17,7 @@ flowchart LR pkg_session["session"] svc_sessions["ctx.sessions
In-memory session store"] pkg_agent["agent"] + pkg_cli_demo["cli-demo"] pkg_session_persistence["session-persistence"] pkg_session_query["session-query"] pkg_subagent_inprocess["subagent-inprocess"] @@ -132,6 +133,7 @@ flowchart LR svc_agentLoop --> pkg_agent_spine_demo svc_agents --> pkg_acp svc_agents --> pkg_agent_loop + svc_agents --> pkg_cli_demo svc_agents --> pkg_invariants svc_agents --> pkg_stdio_demo svc_agents --> pkg_subagent_inprocess @@ -152,6 +154,7 @@ flowchart LR svc_sessionPersistence --> pkg_session_query svc_sessions --> pkg_agent svc_sessions --> pkg_agent_loop + svc_sessions --> pkg_cli_demo svc_sessions --> pkg_invariants svc_sessions --> pkg_session_persistence svc_sessions --> pkg_session_query @@ -183,14 +186,14 @@ flowchart LR | ctx key | Role | Owner | Implementations | Direct consumers | Companion plugins | Note | | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | -| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | +| `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`cli-demo`](../packages/examples/cli-demo), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | | `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | | `ctx.systemPrompt` | `core` | [`system-prompt`](../packages/core/system-prompt) | - | [`agent-loop`](../packages/core/agent-loop), [`tools`](../packages/core/tools), [`tool-fs`](../packages/fs/tool-fs), [`tool-web`](../packages/web/tool-web) | - | Collects prompt sections and model-facing tool schemas for each step. | | `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. | | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. | | `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. | -| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. | +| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. | | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. | | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. | | `ctx.sandbox` | `seam` | [`sandbox`](../packages/sandbox/sandbox) | [`sandbox-local`](../packages/sandbox/sandbox-local) | [`bash-sandbox`](../packages/bash/bash-sandbox) | - | Consumers hand over the exact argv they are about to spawn; same-world backends wrap it under a per-call policy and report enforcement. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index af8ef0832c..54438b0738 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -169,6 +169,30 @@ Depends on: [`LocalConfig`](#deepseek-aidsh-bash-local) · [`SandboxMode`](core- Source: [`packages/bash/bash-sandbox/src/index.ts:26`](../packages/bash/bash-sandbox/src/index.ts) +## `@deepseek-ai/dsh-cli-demo` + +```ts config-catalog +/** App config forwarded to the spine, pre-created agent, and JSONL backend. */ +export interface Config { + /** Model name for the `main` agent; a matching adapter must be registered. */ + model: string + /** Deployment persona forwarded to the system-prompt plugin. */ + persona?: string + /** Explicit model-facing tool order forwarded to the system-prompt plugin. */ + toolOrder?: string[] + /** Tool-registry presentation config forwarded through agent-spine-demo. */ + tools?: ToolsConfig + /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ + persistenceRoot?: string + /** Skill registry, local-provider, and model-facing consumer config. */ + skills?: agentCore.SkillConfig +} +``` + +Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) + +Source: [`packages/examples/cli-demo/src/index.ts:21`](../packages/examples/cli-demo/src/index.ts) + ## `@deepseek-ai/dsh-code-runtime-worker` ```ts config-catalog diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index ec2da1408d..794466b60b 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -27,7 +27,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio) | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 5d5ef1addf..6400ba89c9 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -111,6 +111,7 @@ flowchart TD subgraph group_examples["packages/examples"] pkg_acp_demo["acp-demo"] pkg_agent_spine_demo["agent-spine-demo"] + pkg_cli_demo["cli-demo"] pkg_jsonrpc_demo["jsonrpc-demo"] pkg_stdio_demo["stdio-demo"] end @@ -340,6 +341,13 @@ flowchart TD pkg_acp_demo --> pkg_session_persistence_jsonl pkg_acp_demo --> pkg_tools pkg_acp_demo --> pkg_user_interaction + pkg_cli_demo --> pkg_agent + pkg_cli_demo --> pkg_agent_spine_demo + pkg_cli_demo --> pkg_app_boot + pkg_cli_demo --> pkg_llm + pkg_cli_demo --> pkg_session + pkg_cli_demo --> pkg_session_persistence_jsonl + pkg_cli_demo --> pkg_tools pkg_stdio_demo --> pkg_agent pkg_stdio_demo --> pkg_agent_spine_demo pkg_stdio_demo --> pkg_app_boot @@ -427,4 +435,5 @@ flowchart TD | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`cli-demo`](../packages/examples/cli-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools) | | [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | diff --git a/examples/README.md b/examples/README.md index 5db1e18372..d9e3e544db 100644 --- a/examples/README.md +++ b/examples/README.md @@ -1,6 +1,6 @@ # Examples -Runnable demos (not workspaces) that showcase how the harness is wired. Each example is a **thin leaf**: a `cordis.yml` that picks the swappable backends (an LLM adapter, a bash executor), loads one app package, and may add optional product tools or demo-only mocks. The composition — the spine, the front-door cluster, and the boot glue — lives in the app packages ([`@deepseek-ai/dsh-stdio-demo`](../packages/examples/stdio-demo), [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo)) and the [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) bundle they share. There is no `start.ts`; the `demo:*` scripts invoke each app package's `bin`. +Runnable demos (not workspaces) that showcase how the harness is wired. Each example is a **thin leaf**: a `cordis.yml` that picks the swappable backends (an LLM adapter, a bash executor), loads one app package, and may add optional product tools or demo-only mocks. The composition — the spine, the front-door cluster, and the boot glue — lives in the app packages ([`@deepseek-ai/dsh-stdio-demo`](../packages/examples/stdio-demo), [`@deepseek-ai/dsh-cli-demo`](../packages/examples/cli-demo), [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo)) and the [`@deepseek-ai/dsh-agent-spine-demo`](../packages/examples/agent-spine-demo) bundle they share. There is no `start.ts`; the `demo:*` scripts invoke each app package's `bin`. ## echo-agent @@ -17,7 +17,7 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. The UI is a terminal readline REPL. -Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. +Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:cli -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index 380ab8134f..c9f606766d 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -1,6 +1,6 @@ # coding-agent -The REPL agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + stdio chat + JSONL persistence, loaded from `cordis.yml`. The UI is a terminal readline REPL. +Coding-agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + workflows + `todo_write` + JSONL persistence. `cordis.yml` runs the terminal readline REPL; `cli.cordis.yml` keeps the same coding capabilities behind a headless one-shot CLI. ## Run it @@ -17,10 +17,24 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem > fix the failing test in /path/to/project [main turn 1] (reasoning…) [tool call] bash({"command": "node --test", "workdir": "/path/to/project"}) - [tool result] … [exit code: 1] +[tool result] … [exit code: 1] … ``` +### One-shot CLI + +Run one task through all model and tool steps, flush its fresh session, print the final result, and exit: + +```sh +pnpm run demo:cli -- "fix the failing test in this workspace" +pnpm run demo:cli --output-format json -- "summarize the current implementation" +pnpm run demo:cli --output-format stream-json -- "run the focused tests" +``` + +The root command supplies `cli.cordis.yml`, which disables HMR and the REPL app and inserts [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo). Exactly one quoted positional task is required; there is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Non-completed turns retain partial output but exit nonzero; argument and boot failures leave stdout empty. + +This is non-interactive automation with the same local bash, filesystem, skill, subagent, workflow, and todo capabilities as the REPL. It can mutate the launch workspace and spend provider tokens. No prompt, approval, resume, further turn, or stdin context is available in v1; see the [CLI package contract](../../packages/examples/cli-demo/README.md). + ### Resuming a prior session Each run starts a fresh session by default (its event log lands under `./.sessions/`). To **continue** a previous conversation, set `RESUME_SESSION_ID` to that session's id — the `main` agent then rehydrates the persisted log instead of starting fresh, so the model sees the earlier turns as history: @@ -55,7 +69,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads | `hmr` (`@cordisjs/plugin-hmr`) | the dev/demo edit-reload loop — a **leaf** entry (not baked into the app) because it is Loader-only and needs `node --expose-internals`, which `demo:repl` passes | | `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin | | `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash`/`bash_output`/`bash_kill` tool schemas (`tool-bash`) come from `agent-core`, so only the executor is a leaf choice | -| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-core spine + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins | +| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the REPL app bundle: the agent-core spine + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins | | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix | | `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) | | `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a checklist in stdio | @@ -69,4 +83,4 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads - `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so the auto-compaction listener fires MID-SESSION. Verifies the WORLD — a `compact/start…end` pair landed in the real log, the surface shrank (a replace node shadowed older nodes), and the agent still produced a correct final answer after compaction. - `tests/todo-write.e2e.ts` — a real model drives the real `todo_write` tool and the test verifies the resulting `todo/write` session event. -These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. The keyless boot smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts` (the full real tree, dummy key, no prompt → no model call) and `tests/code-mode-keyless-smoke.e2e.ts` (the same guard for the Code Mode overlay). +These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. `tests/cli.e2e.ts` runs the one-shot bin with a real model and verifies its temporary file externally. The keyless Loader smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts`, `tests/code-mode-keyless-smoke.e2e.ts`, and `tests/cli-keyless-smoke.e2e.ts`; the CLI smoke mocks only the LLM boundary and asserts a real bash round trip plus persisted stream output. diff --git a/examples/coding-agent/cli.cordis.yml b/examples/coding-agent/cli.cordis.yml new file mode 100644 index 0000000000..5a58dfd889 --- /dev/null +++ b/examples/coding-agent/cli.cordis.yml @@ -0,0 +1,24 @@ +# One-shot headless overlay: keep the coding capabilities from `cordis.yml`, +# replace its REPL app with the stdout-pure CLI app, and disable dev-only HMR. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: hmr + name: '@cordisjs/plugin-hmr' + disabled: true + - id: stdio-agent + name: '@deepseek-ai/dsh-stdio-demo' + disabled: true + - insert: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + persona: | + You are coding-agent, a coding assistant powered by the {{model}} model. + + Verify your work by running the code or tests. Keep answers brief and + factual. diff --git a/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts b/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts new file mode 100644 index 0000000000..c2d0f3f946 --- /dev/null +++ b/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts @@ -0,0 +1,43 @@ +import { readdir } from 'node:fs/promises' +import { fileURLToPath } from 'node:url' +import { describe, expect, it } from 'vitest' +import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' +import type { SessionEvent } from '@deepseek-ai/dsh-session' + +const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) +const configPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url)) +const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) + +describe('coding-agent one-shot CLI keyless smoke', () => { + it('boots the real Loader tree, runs a real bash tool round trip, and persists the turn', async () => { + let persisted = false + const { stdout, stderr } = await runLoaderSmoke({ + label: 'coding-agent CLI', + tempDirPrefix: 'coding-cli-smoke-', + binScript, + configPath, + binArgs: ['--config', configPath, '--output-format', 'stream-json', 'prove the tool path'], + tsconfigPath, + inspect: async (cwd) => { + const files = await readdir(cwd, { recursive: true }) + persisted = files.some(file => file.endsWith('.jsonl')) + }, + }) + const lines = stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record) + const events = lines.slice(0, -1).map(line => line['event'] as SessionEvent) + const result = lines.at(-1) + expect(stderr).toBe('') + expect(events.some(event => event.type === 'tool/call' && event.data.name === 'bash')).toBe(true) + const toolResult = events.find(event => event.type === 'tool/result') + expect(JSON.stringify(toolResult)).toContain('CLI_TOOL_ROUND_TRIP') + expect(result).toMatchObject({ + type: 'result', + success: true, + turn: 1, + reason: { kind: 'completed' }, + usage: { inputTokens: 18, outputTokens: 8, cacheReadTokens: 2, reasoningTokens: 1 }, + }) + expect(String(result?.['result'])).toContain('CLI_TOOL_ROUND_TRIP') + expect(persisted).toBe(true) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) +}) diff --git a/examples/coding-agent/tests/cli.e2e.ts b/examples/coding-agent/tests/cli.e2e.ts new file mode 100644 index 0000000000..a05e19fc06 --- /dev/null +++ b/examples/coding-agent/tests/cli.e2e.ts @@ -0,0 +1,33 @@ +import { readFile, writeFile } from 'node:fs/promises' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { describe, expect, it } from 'vitest' +import { runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' + +const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) +const configPath = fileURLToPath(new URL('../cli.cordis.yml', import.meta.url)) +const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const hasKey = Boolean(process.env.DEEPSEEK_API_KEY) + +describe.skipIf(!hasKey)('coding-agent one-shot CLI with real model', () => { + it('modifies a temporary workspace and verifies the file outside the agent', async () => { + let verified = '' + const { stdout } = await runLoaderSmoke({ + label: 'coding-agent CLI real model', + tempDirPrefix: 'coding-cli-real-', + binScript, + configPath, + binArgs: [ + '--config', + configPath, + 'Read task.txt, replace its complete contents with exactly "value=after" followed by a newline, read it again, and report briefly.', + ], + tsconfigPath, + processTimeoutMs: 120_000, + prepare: cwd => writeFile(join(cwd, 'task.txt'), 'value=before\n'), + inspect: async (cwd) => { verified = await readFile(join(cwd, 'task.txt'), 'utf8') }, + }) + expect(verified).toBe('value=after\n') + expect(stdout.trim().length).toBeGreaterThan(0) + }, 135_000) +}) diff --git a/examples/coding-agent/tests/fixtures/cli-mock-llm.ts b/examples/coding-agent/tests/fixtures/cli-mock-llm.ts new file mode 100644 index 0000000000..6447ba1e18 --- /dev/null +++ b/examples/coding-agent/tests/fixtures/cli-mock-llm.ts @@ -0,0 +1,37 @@ +import type { Context } from 'cordis' +import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' + +/** Keyless coding smoke adapter: one real bash call followed by a final answer. */ +class CliMockAdapter extends LlmAdapter { + async * stream(options: GenerateOptions): AsyncIterable { + const toolResult = options.messages.at(-1)?.content.find(block => block.type === 'tool-result') + if (toolResult === undefined) { + const args = JSON.stringify({ command: 'printf CLI_TOOL_ROUND_TRIP', description: 'Prove the CLI tool round trip.' }) + yield { type: 'block-start', index: 0, blockType: 'tool-call' } + yield { type: 'tool-call-delta', index: 0, id: CallId('cli-smoke-call'), name: 'bash', argumentsDelta: args } + yield { type: 'block-end', index: 0, block: { type: 'tool-call', id: CallId('cli-smoke-call'), name: 'bash', arguments: args } } + yield { type: 'usage', usage: { inputTokens: 11, outputTokens: 3, cacheReadTokens: 2 } } + yield { type: 'finish', reason: { kind: 'tool-calls' } } + return + } + + const toolText = toolResult.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') + const reply = `CLI tool round trip complete: ${toolText.trim()}` + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'text-delta', index: 0, text: reply } + yield { type: 'block-end', index: 0, block: { type: 'text', text: reply } } + yield { type: 'usage', usage: { inputTokens: 7, outputTokens: 5, reasoningTokens: 1 } } + yield { type: 'finish', reason: { kind: 'stop' } } + } +} + +export const name = 'cli-mock-llm' +export const inject = ['llm'] + +/** Register the keyless `cli-mock` adapter. */ +export function apply(ctx: Context): void { + ctx.llm.registerAdapter(['cli-mock'], new CliMockAdapter()) +} diff --git a/examples/coding-agent/tests/fixtures/cli.cordis.yml b/examples/coding-agent/tests/fixtures/cli.cordis.yml new file mode 100644 index 0000000000..bdec0154c4 --- /dev/null +++ b/examples/coding-agent/tests/fixtures/cli.cordis.yml @@ -0,0 +1,24 @@ +- id: cli-mock-llm + name: './cli-mock-llm.ts' + +- id: base + name: '@cordisjs/plugin-include' + config: + path: ../../cordis.yml + patches: + - id: hmr + name: '@cordisjs/plugin-hmr' + disabled: true + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: stdio-agent + name: '@deepseek-ai/dsh-stdio-demo' + disabled: true + - insert: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: cli-mock + persistenceRoot: './.sessions' + persona: 'Keyless CLI smoke.' diff --git a/knip.json b/knip.json index 71c9d1e01d..754aace023 100644 --- a/knip.json +++ b/knip.json @@ -9,6 +9,7 @@ "examples/echo-agent/src/*.ts", "examples/echo-agent/tests/**/*.e2e.ts", "examples/coding-agent/tests/**/*.e2e.ts", + "examples/coding-agent/tests/fixtures/*.ts", "examples/cordis-agent/tests/**/*.e2e.ts", "examples/acp-agent/tests/**/*.e2e.ts", "examples/*/tests/**/*.snapshot.ts" @@ -90,6 +91,10 @@ "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, + "packages/examples/cli-demo": { + "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"] + }, "packages/ui/stdio": { "entry": ["tests/**/*.spec.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] diff --git a/package.json b/package.json index aaec1e62c4..d6f64f210b 100644 --- a/package.json +++ b/package.json @@ -74,6 +74,7 @@ "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", + "demo:cli": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", diff --git a/packages/README.md b/packages/README.md index db364421b1..fcd29c3666 100644 --- a/packages/README.md +++ b/packages/README.md @@ -28,7 +28,7 @@ Packages are grouped by modular role at `packages///`. The group dir | [`session-persistence/`](session-persistence/README.md) | Persistence capability family: the seam + JSONL/SQLite backends | Product — stable surface | | [`session-query/`](session-query/README.md) | Session retrieval family: logical corpus, surface records, and bounded exact reads | Product — stable surface | | [`ui/`](ui/README.md) | Editor/client integration surfaces: ACP bridge, JSON-RPC SDK server, user-approval/user-interaction seams, ask-user tool | Product — stable surface | -| [`examples/`](examples/README.md) | Demo bundles (agent-spine + stdio/ACP/JSON-RPC bins) the leaves load | Support — example infra | +| [`examples/`](examples/README.md) | Demo bundles (agent-spine + stdio/one-shot CLI/ACP/JSON-RPC bins) the leaves load | Support — example infra | | [`support/`](support/README.md) | Support infrastructure (invariants, replay, Loader smokes) | Support — lower compatibility expectations | | [`util/`](util/README.md) | Low-level zero-dependency utilities shared across groups (the `Branded` primitive) | Support — small, stable, harness-dep-free | diff --git a/packages/examples/README.md b/packages/examples/README.md index 5ee0206d0f..d961e38aeb 100644 --- a/packages/examples/README.md +++ b/packages/examples/README.md @@ -6,10 +6,11 @@ Pre-composed plugin bundles a thin leaf `cordis.yml` loads instead of assembling |---|---|---| | `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + invariants + `tool-bash` + `tool-skill` + `agent-loop`) | | `stdio-demo/` | `@deepseek-ai/dsh-stdio-demo` | Terminal stdio chat app: the spine + console logger + readline UI + a pre-created `main` agent, with a boot `bin` | +| `cli-demo/` | `@deepseek-ai/dsh-cli-demo` | Headless one-shot app: the spine + JSONL persistence + a pre-created `main` agent, with text and DSH-native JSON output | | `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` | | `jsonrpc-demo/` | `@deepseek-ai/dsh-jsonrpc-demo` | Bin-only runtime that boots an external `cordis.yml` for the stdio JSON-RPC SDK client | -`agent-spine-demo` is the shared bundle; `stdio-demo` and `acp-demo` compose it with opposite front-door clusters (console logger + readline UI vs the stdout-owning ACP bridge) and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches. +`agent-spine-demo` is the shared bundle; `stdio-demo`, `cli-demo`, and `acp-demo` compose it with terminal, headless one-shot, and ACP front doors and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches. These are **not** product API. The spine pieces they bundle live in [`core/`](../core/README.md), the bridges/channels/boot-glue in [`ui/`](../ui/README.md), and the swappable backends (LLM adapter, bash executor) in their capability groups; a demo bundle just picks one concrete composition of them. Swap or fork one freely. diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md new file mode 100644 index 0000000000..558c5eeff3 --- /dev/null +++ b/packages/examples/cli-demo/README.md @@ -0,0 +1,62 @@ +# @deepseek-ai/dsh-cli-demo + +Headless one-shot app and bin for running one coding-agent task without a readline or editor client. The app composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and one fresh `main` agent; the bin submits one task, waits through all model and tool steps, emits the selected result, disposes to quiescence, and exits. + +The package mounts no console logger, readline UI, user-interaction service, or `ask_user_question` tool. Stdout is reserved for the selected output format; diagnostics use stderr. + +## Config + +| Key | Default | Routed to | +|---|---|---| +| `model` | required | the pre-created `main` agent's model | +| `persona` | — | the deployment persona in `dsh-system-prompt` | +| `toolOrder` | lexicographic | explicit model-facing tool order in `dsh-system-prompt` | +| `tools` | `{ mode: 'native' }` | tool-registry presentation config through `dsh-agent-spine-demo` | +| `skills` | owner defaults | skill registry, local provider, and model-facing skill tool | +| `persistenceRoot` | `./.sessions` | JSONL session root | + +Each process creates a new session whose workspace cwd is the launch directory. The app has no resume setting. + +## CLI contract + +```sh +dsh-cli-demo [--config path] [--output-format text|json|stream-json] +``` + +`--config` defaults to `./cordis.yml`; `--output-format` defaults to `text`. Exactly one nonblank positional task is required, so quote tasks containing spaces. `--help` prints usage without booting. There is no `-p` or `--print` flag. + +The root coding demo supplies its overlay: + +```sh +pnpm run demo:cli -- "inspect the failing test and fix it" +``` + +Loader configs with bare package specifiers require `node --expose-internals` or the Loader's optional native fallback. The root command supplies the Node flag. + +### Output formats + +- `text` writes the last assistant message containing text, followed by one newline. +- `json` writes one DSH-native result record: `{ type: "result", success, sessionId, turn, result, reason, usage? }`. `usage` sums every model step in the task turn. +- `stream-json` writes each canonical event from the `main` session's task turn as `{ type: "session_event", sessionId, event }`, then the same result record. Child-agent activity appears only through the parent tool events and results. + +Only `reason.kind === "completed"` exits successfully. Other durable turn endings still emit partial text or a result record, add a stderr diagnostic, and exit nonzero. Argument and boot failures leave stdout empty. SIGINT and SIGTERM cancel active work, await disposal, and exit 130 and 143 respectively. + +The task turn is explicitly flushed before final output. Session logs remain under `persistenceRoot` after the process exits. + +## Operational safety + +The coding overlay retains local bash, filesystem, skill, subagent, workflow, and todo capabilities. A task can therefore mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. Run the CLI from the intended project directory, review the leaf's capability and sandbox configuration, and do not treat non-interactive execution as an approval boundary. + +## Model Experience + +### One-shot task turn + +**What the model sees**: The positional task becomes one user message. Through `dsh-agent-spine-demo`, the `main` agent also receives the configured persona, skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn. + +**Token effect**: The task, prompt sections, tool schemas, assistant output, and tool results consume tokens on each model step. JSON event streaming and final rendering add no model tokens; delegated child work has its own model usage and is not included in the parent result's `usage` total. + +## Known Limitations and Deferred Work + +- **One fresh main session per process** — there is no resume, second prompt, stdin context, or concurrent top-level session in this app. +- **No interactive question or approval provider** — tools that require a human answer cannot complete unless a different leaf composes a non-interactive provider with explicit policy. +- **Streaming is main-session-only** — child sessions are not flattened into the stream, and aggregate usage covers only model steps recorded on the parent task turn. diff --git a/packages/examples/cli-demo/package.json b/packages/examples/cli-demo/package.json new file mode 100644 index 0000000000..3268f9733f --- /dev/null +++ b/packages/examples/cli-demo/package.json @@ -0,0 +1,59 @@ +{ + "name": "@deepseek-ai/dsh-cli-demo", + "description": "Headless one-shot coding-agent app with text and DSH-native JSON output", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "bin": { + "dsh-cli-demo": "lib/bin.js" + }, + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./bin": { + "types": "./lib/types/bin.d.ts", + "default": "./lib/bin.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/bin.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@cordisjs/plugin-include": "^1.0.4", + "@cordisjs/plugin-loader": "^1.0.0-rc.5", + "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1", + "@deepseek-ai/dsh-app-boot": "^0.0.1", + "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1", + "@deepseek-ai/dsh-tools": "^0.0.1", + "cordis": "^4.0.0-rc.7", + "schemastery": "^3.17.0" + }, + "devDependencies": { + "@cordisjs/plugin-include": "workspace:^", + "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", + "@deepseek-ai/dsh-app-boot": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", + "@deepseek-ai/dsh-system-prompt": "workspace:^", + "@deepseek-ai/dsh-tools": "workspace:^", + "cordis": "^4.0.0-rc.7", + "schemastery": "^3.17.0" + } +} diff --git a/packages/examples/cli-demo/src/bin.ts b/packages/examples/cli-demo/src/bin.ts new file mode 100644 index 0000000000..5b6638ef72 --- /dev/null +++ b/packages/examples/cli-demo/src/bin.ts @@ -0,0 +1,34 @@ +#!/usr/bin/env node +/** + * Process wrapper for `dsh-cli-demo`; covered parsing and task execution live in + * `cli.ts` while this entry owns Unix signal-to-exit-code mapping. + * @module @deepseek-ai/dsh-cli-demo/bin + */ + +import { installFailLoud } from '@deepseek-ai/dsh-app-boot' +import { executeCli } from './cli.ts' + +const NAME = 'dsh-cli-demo' + +/* v8 ignore start -- thin self-executing process glue; built-bin tests exercise + real argv, signals, Loader boot, output, and exit codes */ +const abort = new AbortController() +let signalExitCode: number | undefined +const interrupt = (signal: 'SIGINT' | 'SIGTERM', code: number): void => { + signalExitCode ??= code + if (!abort.signal.aborted) abort.abort(`received ${signal}`) +} +const onSigint = (): void => { interrupt('SIGINT', 130) } +const onSigterm = (): void => { interrupt('SIGTERM', 143) } +const uninstallFailLoud = installFailLoud(NAME) +process.on('SIGINT', onSigint) +process.on('SIGTERM', onSigterm) +try { + const code = await executeCli(process.argv.slice(2), { signal: abort.signal }) + process.exitCode = signalExitCode ?? code +} finally { + process.off('SIGINT', onSigint) + process.off('SIGTERM', onSigterm) + uninstallFailLoud() +} +/* v8 ignore stop */ diff --git a/packages/examples/cli-demo/src/cli.ts b/packages/examples/cli-demo/src/cli.ts new file mode 100644 index 0000000000..6e42220939 --- /dev/null +++ b/packages/examples/cli-demo/src/cli.ts @@ -0,0 +1,380 @@ +/** + * Covered command parser and one-turn driver for `dsh-cli-demo`. The executable + * entry only installs process signal handlers and delegates here. + * @module @deepseek-ai/dsh-cli-demo/cli + */ + +import { parseArgs } from 'node:util' +import type { Context } from 'cordis' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import type { TokenUsage } from '@deepseek-ai/dsh-llm' +import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session' +import { boot, loadEnv, resolveConfigPath } from '@deepseek-ai/dsh-app-boot' + +const CLI_NAME = 'dsh-cli-demo' +const DEFAULT_CONFIG_PATH = './cordis.yml' +const OUTPUT_FORMATS = ['text', 'json', 'stream-json'] as const +const USAGE = `Usage: ${CLI_NAME} [--config path] [--output-format text|json|stream-json] \n` + +/** Supported CLI output encodings. */ +export type OutputFormat = typeof OUTPUT_FORMATS[number] + +/** Parsed command: help exits before boot; run carries one validated task. */ +export type CliCommand = + | { readonly kind: 'help' } + | { + readonly kind: 'run' + readonly configPath: string + readonly outputFormat: OutputFormat + readonly task: string + } + +/** DSH-native final record emitted by JSON modes. */ +export interface CliResult { + readonly type: 'result' + readonly success: boolean + readonly sessionId: string + readonly turn: number + readonly result: string + readonly reason: TurnEndReason + readonly usage?: TokenUsage +} + +/** Options for one turn against the pre-created `main` agent. */ +export interface OneShotOptions { + /** Exactly one nonblank user task. */ + readonly task: string + /** Optional cancellation signal owned by the process wrapper. */ + readonly signal?: AbortSignal + /** Synchronous observer for each canonical event in the selected task turn. */ + readonly onEvent?: (sessionId: string, event: SessionEvent) => void +} + +/** Injectable process boundaries used by {@link executeCli}. */ +export interface CliRuntime { + /** Process cwd for config resolution and `.env` loading. */ + readonly cwd?: string + /** Cancellation signal, normally aborted by SIGINT or SIGTERM. */ + readonly signal?: AbortSignal + /** Loader boot boundary. */ + readonly boot?: (name: string, absoluteConfigPath: string) => Promise + /** Optional `.env` loader boundary. */ + readonly loadEnv?: (name: string, dir: string, warn: (line: string) => void) => void + /** Stdout sink; throws are treated as output failures. */ + readonly writeStdout?: (chunk: string) => unknown + /** Stderr diagnostic sink. */ + readonly writeStderr?: (chunk: string) => unknown + /** Context disposal boundary. */ + readonly dispose?: (ctx: Context) => Promise +} + +interface ParsedArguments { + readonly values: { + readonly config?: string + readonly 'output-format'?: string + readonly help?: boolean + } + readonly positionals: string[] +} + +class CliArgumentError extends Error { + constructor(message: string) { + super(message) + this.name = 'CliArgumentError' + } +} + +class CliInterruptedError extends Error { + constructor(reason: string) { + super(reason) + this.name = 'CliInterruptedError' + } +} + +/** Convert an unknown thrown value to an Error without losing its text. */ +function toError(error: unknown): Error { + return error instanceof Error ? error : new Error(String(error)) +} + +/** Render the reason carried by an AbortSignal. */ +function interruptionReason(signal: AbortSignal): string { + return signal.reason === undefined ? 'interrupted' : String(signal.reason) +} + +/** + * Parse the bin arguments and enforce the one-positional-task contract. + * @param args - arguments after the executable name. + * @returns a help or run command. + * @throws {@link CliArgumentError} for unknown flags, invalid formats, or task cardinality. + */ +export function parseCliArgs(args: readonly string[]): CliCommand { + let parsed: ParsedArguments + try { + parsed = parseArgs({ + args: [...args], + options: { + config: { type: 'string' }, + 'output-format': { type: 'string' }, + help: { type: 'boolean' }, + }, + allowPositionals: true, + strict: true, + }) + } catch (error: unknown) { + throw new CliArgumentError(toError(error).message) + } + + if (parsed.values.help === true) return { kind: 'help' } + if (parsed.positionals.length !== 1) { + throw new CliArgumentError(`expected exactly one positional task, received ${parsed.positionals.length}`) + } + // Cardinality was checked above, so index zero exists. + // eslint-disable-next-line @typescript-eslint/no-non-null-assertion + const task = parsed.positionals[0]! + if (task.trim().length === 0) throw new CliArgumentError('task must not be blank') + + const requestedFormat = parsed.values['output-format'] ?? 'text' + if (!OUTPUT_FORMATS.some(format => format === requestedFormat)) { + throw new CliArgumentError(`unsupported output format ${JSON.stringify(requestedFormat)}`) + } + return { + kind: 'run', + configPath: parsed.values.config ?? DEFAULT_CONFIG_PATH, + outputFormat: requestedFormat as OutputFormat, + task, + } +} + +/** Add one model step's usage into a detached turn total. */ +function addUsage(total: TokenUsage | undefined, step: TokenUsage): TokenUsage { + const next: TokenUsage = { + inputTokens: (total?.inputTokens ?? 0) + step.inputTokens, + outputTokens: (total?.outputTokens ?? 0) + step.outputTokens, + } + for (const key of ['cacheReadTokens', 'cacheWriteTokens', 'reasoningTokens'] as const) { + if (total?.[key] !== undefined || step[key] !== undefined) next[key] = (total?.[key] ?? 0) + (step[key] ?? 0) + } + return next +} + +/** Select the text blocks from an assistant message, or undefined when it has none. */ +function assistantText(event: Extract): string | undefined { + const blocks = event.data.content.filter(block => block.type === 'text') + return blocks.length === 0 ? undefined : blocks.map(block => block.text).join('') +} + +/** Wait for startup quiescence while making pre-run cancellation terminal. */ +async function waitForStartupIdle(agent: Agent, signal?: AbortSignal): Promise { + if (signal === undefined) { + await agent.whenIdle() + return + } + if (signal.aborted) { + agent.cancel(interruptionReason(signal)) + throw new CliInterruptedError(interruptionReason(signal)) + } + await new Promise((resolve, reject) => { + const onAbort = (): void => { + agent.cancel(interruptionReason(signal)) + reject(new CliInterruptedError(interruptionReason(signal))) + } + signal.addEventListener('abort', onAbort, { once: true }) + void agent.whenIdle().then(resolve, reject).finally(() => { + signal.removeEventListener('abort', onAbort) + }) + }) +} + +/** + * Run one message-triggered turn on the pre-created `main` agent, aggregate its + * final text and model usage, wait for idle plus an explicit persistence flush, + * and return its durable ending. Only the exact main-session task turn reaches + * `onEvent`; startup injections and unrelated sessions are ignored. + * @param ctx - settled Loader root containing `ctx.agents` and `ctx.sessions`. + * @param options - task, optional cancellation, and optional stream observer. + * @returns the DSH-native result envelope after durable quiescence. + */ +export async function runOneShot(ctx: Context, options: OneShotOptions): Promise { + const agent = ctx.get('agents')?.get(AgentId('main')) + if (agent === undefined) throw new Error('config did not create the required "main" agent') + await waitForStartupIdle(agent, options.signal) + + let targetTurn: number | undefined + let reason: TurnEndReason | undefined + let result = '' + let usage: TokenUsage | undefined + let outputError: Error | undefined + let resolveTurn!: () => void + let rejectTurn!: (error: Error) => void + let settled = false + const turnEnded = new Promise((resolve, reject) => { + resolveTurn = resolve + rejectTurn = reject + }) + + const settleResolved = (): void => { + settled = true + resolveTurn() + } + const settleRejected = (error: Error): void => { + settled = true + rejectTurn(error) + } + const observe = (sessionId: string, event: SessionEvent): void => { + if (outputError !== undefined || options.onEvent === undefined) return + try { + options.onEvent(sessionId, event) + } catch (error: unknown) { + outputError = toError(error) + agent.cancel('stream output failed') + } + } + + const disposeListener = ctx.on('session/event', (session, event) => { + if (session !== agent.session || settled) return + if (targetTurn === undefined) { + if (event.type !== 'turn/start' || event.data.trigger.kind !== 'message') return + targetTurn = event.data.turn + } + observe(session.id, event) + if (event.type === 'assistant/message' && event.data.turn === targetTurn) { + result = assistantText(event) ?? result + if (event.data.usage !== undefined) usage = addUsage(usage, event.data.usage) + } + if (event.type === 'turn/end' && event.data.turn === targetTurn) { + reason = event.data.reason + settleResolved() + } + }) + + const signal = options.signal + let onAbort: (() => void) | undefined + if (signal !== undefined) { + onAbort = (): void => { + agent.cancel(interruptionReason(signal)) + if (targetTurn === undefined) settleRejected(new CliInterruptedError(interruptionReason(signal))) + } + signal.addEventListener('abort', onAbort, { once: true }) + /* v8 ignore next -- closes the race between startup-idle completion and listener registration */ + if (signal.aborted) onAbort() + } + + try { + /* v8 ignore next -- skips send only when cancellation wins the listener-registration race above */ + if (!settled) { // eslint-disable-line @typescript-eslint/no-unnecessary-condition + agent.send([{ type: 'text', text: options.task }]) + } + await turnEnded + } finally { + if (onAbort !== undefined) signal?.removeEventListener('abort', onAbort) + disposeListener() + await agent.whenIdle() + } + + /* v8 ignore next 3 -- turnEnded resolves only from the matching branch that assigns both values */ + if (targetTurn === undefined || reason === undefined) { + throw new Error('task ended without a correlated turn/end event') + } + await ctx.sessions.flush(agent.session) + if (outputError !== undefined) throw outputError + return { + type: 'result', + success: reason.kind === 'completed', + sessionId: agent.session.id, + turn: targetTurn, + result, + reason, + ...usage === undefined ? {} : { usage }, + } +} + +/** Render one final result in the selected output encoding. */ +function renderResult(outputFormat: OutputFormat, result: CliResult): string { + return outputFormat === 'text' ? `${result.result}\n` : `${JSON.stringify(result)}\n` +} + +/** + * Render a non-completed turn reason for stderr. + * @param reason - durable turn ending to describe. + * @returns a concise diagnostic fragment. + */ +export function formatTurnFailure(reason: TurnEndReason): string { + switch (reason.kind) { + case 'completed': return 'completed' + case 'aborted': return reason.reason === undefined ? 'was aborted' : `was aborted: ${reason.reason}` + case 'error': return `failed at step ${reason.step}: ${reason.message}` + case 'disposed': return 'was disposed' + case 'max-tokens': return 'reached the model output-token limit' + case 'rejected': return `was rejected: ${reason.reason}` + case 'interrupted': return 'was interrupted during persistence recovery' + default: return `ended with ${JSON.stringify(reason)}` + } +} + +/** + * Parse, boot, run, render, diagnose, and dispose one CLI invocation. Argument + * and boot failures never write stdout; all booted contexts are disposed before + * this promise resolves. + * @param args - arguments after the executable name. + * @param runtime - optional injected process boundaries for tests and embedding. + * @returns the ordinary process exit code; the thin bin overrides it for Unix signals. + */ +export async function executeCli(args: readonly string[], runtime: CliRuntime = {}): Promise { + /* v8 ignore next -- default process sinks are exercised by the built-bin smoke */ + const writeStdout = runtime.writeStdout ?? (chunk => process.stdout.write(chunk)) + /* v8 ignore next -- default process sinks are exercised by the built-bin smoke */ + const writeStderr = runtime.writeStderr ?? (chunk => process.stderr.write(chunk)) + let command: CliCommand + try { + command = parseCliArgs(args) + } catch (error: unknown) { + writeStderr(`${CLI_NAME}: ${toError(error).message}\n${USAGE}`) + return 1 + } + if (command.kind === 'help') { + writeStdout(USAGE) + return 0 + } + + /* v8 ignore next -- default process cwd is exercised by the built-bin smoke */ + const cwd = runtime.cwd ?? process.cwd() + /* v8 ignore next -- default env/boot boundaries are exercised by the Loader and built-bin smokes */ + const loadEnvironment = runtime.loadEnv ?? loadEnv + /* v8 ignore next -- default env/boot boundaries are exercised by the Loader and built-bin smokes */ + const bootContext = runtime.boot ?? boot + /* v8 ignore next -- default disposal is exercised by the built-bin smoke */ + const disposeContext = runtime.dispose ?? (target => target.fiber.dispose()) + let ctx: Context | undefined + let exitCode = 1 + let diagnostic: string | undefined + try { + loadEnvironment(CLI_NAME, cwd, line => writeStderr(line)) + ctx = await bootContext(CLI_NAME, resolveConfigPath(command.configPath, undefined, cwd)) + if (runtime.signal?.aborted === true) throw new CliInterruptedError(interruptionReason(runtime.signal)) + const result = await runOneShot(ctx, { + task: command.task, + ...runtime.signal === undefined ? {} : { signal: runtime.signal }, + ...command.outputFormat === 'stream-json' + ? { onEvent: (sessionId: string, event: SessionEvent) => { + writeStdout(`${JSON.stringify({ type: 'session_event', sessionId, event })}\n`) + } } + : {}, + }) + writeStdout(renderResult(command.outputFormat, result)) + exitCode = result.success ? 0 : 1 + if (!result.success) diagnostic = `${CLI_NAME}: turn ${result.turn} ${formatTurnFailure(result.reason)}\n` + } catch (error: unknown) { + diagnostic = `${CLI_NAME}: ${toError(error).message}\n` + } finally { + if (ctx !== undefined) { + try { + await disposeContext(ctx) + } catch (error: unknown) { + diagnostic ??= `${CLI_NAME}: dispose failed: ${toError(error).message}\n` + exitCode = 1 + } + } + } + if (diagnostic !== undefined) writeStderr(diagnostic) + return exitCode +} diff --git a/packages/examples/cli-demo/src/index.ts b/packages/examples/cli-demo/src/index.ts new file mode 100644 index 0000000000..a2a2271b03 --- /dev/null +++ b/packages/examples/cli-demo/src/index.ts @@ -0,0 +1,63 @@ +/** + * Headless one-shot app composition: the default agent spine, JSONL session + * persistence, and one pre-created `main` agent. The CLI driver owns task + * submission and output; the app deliberately mounts no interactive or logging + * front door so stdout remains protocol-pure. + * @module @deepseek-ai/dsh-cli-demo + */ + +import type { Context } from 'cordis' +import z from 'schemastery' +import { AgentId } from '@deepseek-ai/dsh-agent' +import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools' +import * as agentCore from '@deepseek-ai/dsh-agent-spine-demo' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' + +const DEFAULT_PERSISTENCE_ROOT = './.sessions' + +export const name = 'cli-demo' + +/** App config forwarded to the spine, pre-created agent, and JSONL backend. */ +export interface Config { + /** Model name for the `main` agent; a matching adapter must be registered. */ + model: string + /** Deployment persona forwarded to the system-prompt plugin. */ + persona?: string + /** Explicit model-facing tool order forwarded to the system-prompt plugin. */ + toolOrder?: string[] + /** Tool-registry presentation config forwarded through agent-spine-demo. */ + tools?: ToolsConfig + /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ + persistenceRoot?: string + /** Skill registry, local-provider, and model-facing consumer config. */ + skills?: agentCore.SkillConfig +} + +export const Config: z = z.object({ + model: z.string().required(), + persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), + persona: z.string(), + skills: agentCore.SkillConfigSchema, + // Absent means lexicographic order; schemastery's native array default is []. + toolOrder: z.array(z.string()).default(undefined as unknown as string[]), + tools: ToolRegistry.Config, +}) + +/** + * Compose the UI-less spine, a fresh `main` agent rooted at the process cwd, + * and JSONL persistence. Swappable adapters, executors, and product tools stay + * in the leaf `cordis.yml`. + * @param ctx - app context that owns the composed child plugins. + * @param config - validated app configuration. + */ +export function apply(ctx: Context, config: Config): void { + const spineConfig: agentCore.Config = { + agents: [{ id: AgentId('main'), model: config.model, cwd: process.cwd() }], + } + if (config.persona !== undefined) spineConfig.persona = config.persona + if (config.toolOrder !== undefined) spineConfig.toolOrder = config.toolOrder + if (config.tools !== undefined) spineConfig.tools = config.tools + if (config.skills !== undefined) spineConfig.skills = config.skills + ctx.plugin(agentCore, spineConfig) + ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) +} diff --git a/packages/examples/cli-demo/tests/built-bin.e2e.ts b/packages/examples/cli-demo/tests/built-bin.e2e.ts new file mode 100644 index 0000000000..aed7f1f2d4 --- /dev/null +++ b/packages/examples/cli-demo/tests/built-bin.e2e.ts @@ -0,0 +1,172 @@ +import { spawn } from 'node:child_process' +import { existsSync } from 'node:fs' +import { mkdtemp, mkdir, readFile, readdir, rm, symlink, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { dirname, join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { afterEach, describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const cliBin = join(repoRoot, 'packages/examples/cli-demo/lib/bin.js') +const dshPackages = [ + 'examples/agent-spine-demo', 'examples/cli-demo', 'core/agent', 'core/session', + 'core/system-prompt', 'core/tools', 'core/agent-loop', 'llm/llm', 'bash/bash', + 'bash/bash-local', 'bash/tool-bash', 'support/invariants', 'ui/app-boot', + 'session-persistence/session-persistence', 'session-persistence/session-persistence-jsonl', +] +const vendorPackages = ['cordis', 'loader', 'include', 'timer', 'schemastery', 'cosmokit'] + +async function packageName(dir: string): Promise { + return (JSON.parse(await readFile(join(dir, 'package.json'), 'utf8')) as { name: string }).name +} + +async function linkPackage(dir: string, nodeModules: string): Promise { + const target = join(nodeModules, await packageName(dir)) + await mkdir(dirname(target), { recursive: true }) + await symlink(dir, target) +} + +async function makeConsumer(): Promise { + const dir = await mkdtemp(join(tmpdir(), 'cli-built-bin-')) + const nodeModules = join(dir, 'node_modules') + for (const rel of dshPackages) await linkPackage(join(repoRoot, 'packages', rel), nodeModules) + for (const rel of vendorPackages) await linkPackage(join(repoRoot, 'vendor', rel), nodeModules) + await writeFile(join(dir, 'mock-llm.mjs'), [ + "import { LlmAdapter } from '@deepseek-ai/dsh-llm'", + 'class Mock extends LlmAdapter {', + ' async * stream(options) {', + " const text = options.messages.flatMap(message => message.content).filter(block => block.type === 'text').at(-1)?.text ?? ''", + " yield { type: 'block-start', index: 0, blockType: 'text' }", + " if (text === 'hang') {", + " yield { type: 'text-delta', index: 0, text: 'partial' }", + ' await new Promise((resolve, reject) => {', + " const timer = setTimeout(() => reject(new Error('hang timeout')), 30000)", + " const onAbort = () => { clearTimeout(timer); reject(new Error('aborted')) }", + ' if (options.signal.aborted) onAbort()', + " else options.signal.addEventListener('abort', onAbort, { once: true })", + ' })', + ' return', + ' }', + ' const reply = `BUILT: ${text}`', + " yield { type: 'text-delta', index: 0, text: reply }", + " yield { type: 'block-end', index: 0, block: { type: 'text', text: reply } }", + " yield { type: 'usage', usage: { inputTokens: 4, outputTokens: 2 } }", + " yield { type: 'finish', reason: { kind: 'stop' } }", + ' }', + '}', + "export const name = 'built-cli-mock'", + "export const inject = ['llm']", + "export function apply(ctx) { ctx.llm.registerAdapter(['built-cli-mock'], new Mock()) }", + '', + ].join('\n')) + await writeFile(join(dir, 'cordis.yml'), [ + '- id: mock-llm', + " name: './mock-llm.mjs'", + '- id: bash', + " name: '@deepseek-ai/dsh-bash-local'", + '- id: cli-agent', + " name: '@deepseek-ai/dsh-cli-demo'", + ' config:', + ' model: built-cli-mock', + " persona: 'built CLI test'", + " persistenceRoot: './.sessions'", + '', + ].join('\n')) + return dir +} + +interface BinResult { + readonly code: number + readonly signal: NodeJS.Signals | null + readonly stdout: string + readonly stderr: string +} + +function runBuiltBin(cwd: string, args: readonly string[], interrupt?: NodeJS.Signals): Promise { + return new Promise((resolveResult, reject) => { + const child = spawn(process.execPath, ['--expose-internals', cliBin, ...args], { + cwd, + env: { ...process.env, DSH_HOME: join(cwd, '.dsh'), DSH_AGENTS_HOME: join(cwd, '.agents') }, + stdio: ['ignore', 'pipe', 'pipe'], + }) + let stdout = '' + let stderr = '' + let interrupted = false + child.stdout.setEncoding('utf8') + child.stdout.on('data', (chunk: string) => { + stdout += chunk + if (interrupt !== undefined && !interrupted && stdout.includes('assistant/chunk')) { + interrupted = true + child.kill(interrupt) + } + }) + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => { stderr += chunk }) + const timer = setTimeout(() => { + child.kill('SIGKILL') + reject(new Error(`built CLI did not exit. stdout:\n${stdout}\nstderr:\n${stderr}`)) + }, 25_000) + child.once('error', (error) => { clearTimeout(timer); reject(error) }) + child.once('exit', (code, signal) => { + clearTimeout(timer) + resolveResult({ code: code ?? -1, signal, stdout, stderr }) + }) + }) +} + +let consumer: string | undefined + +afterEach(async () => { + if (consumer !== undefined) await rm(consumer, { recursive: true, force: true, maxRetries: 10, retryDelay: 100 }) + consumer = undefined +}) + +describe.skipIf(!existsSync(cliBin))('dsh-cli-demo BUILT bin', () => { + it('runs text, json, and stream-json under plain Node and persists fresh sessions', async () => { + consumer = await makeConsumer() + const text = await runBuiltBin(consumer, ['--config', './cordis.yml', 'hello']) + expect(text).toMatchObject({ code: 0, signal: null, stdout: 'BUILT: hello\n', stderr: '' }) + + const json = await runBuiltBin(consumer, ['--config', './cordis.yml', '--output-format', 'json', 'json task']) + expect(JSON.parse(json.stdout)).toMatchObject({ + type: 'result', success: true, result: 'BUILT: json task', reason: { kind: 'completed' }, + usage: { inputTokens: 4, outputTokens: 2 }, + }) + + const stream = await runBuiltBin(consumer, ['--config', './cordis.yml', '--output-format', 'stream-json', 'stream task']) + const lines = stream.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record) + expect(lines[0]).toMatchObject({ type: 'session_event', event: { type: 'turn/start' } }) + expect(lines.at(-1)).toMatchObject({ type: 'result', success: true, result: 'BUILT: stream task' }) + const files = await readdir(join(consumer, '.sessions'), { recursive: true }) + expect(files.filter(file => file.endsWith('.jsonl'))).toHaveLength(3) + }, 30_000) + + it('keeps stdout empty for invalid argv and missing config', async () => { + consumer = await makeConsumer() + for (const args of [ + ['--config', './cordis.yml'], + ['--config', './cordis.yml', 'one', 'two'], + ['--config', './missing.yml', 'task'], + ]) { + const result = await runBuiltBin(consumer, args) + expect(result.code).not.toBe(0) + expect(result.stdout).toBe('') + expect(result.stderr.length).toBeGreaterThan(0) + } + }, 30_000) + + it.each([ + ['SIGINT', 130], + ['SIGTERM', 143], + ] as const)('cancels and disposes on %s with exit %i', async (signal, code) => { + consumer = await makeConsumer() + const result = await runBuiltBin( + consumer, + ['--config', './cordis.yml', '--output-format', 'stream-json', 'hang'], + signal, + ) + expect(result, JSON.stringify(result)).toMatchObject({ code, signal: null }) + expect(result.stdout).toContain('"kind":"aborted"') + expect(result.stderr).toContain(`received ${signal}`) + }, 30_000) +}) diff --git a/packages/examples/cli-demo/tests/cli-demo.spec.ts b/packages/examples/cli-demo/tests/cli-demo.spec.ts new file mode 100644 index 0000000000..4cb7a243a5 --- /dev/null +++ b/packages/examples/cli-demo/tests/cli-demo.spec.ts @@ -0,0 +1,105 @@ +import { mkdtemp } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import { AgentId, agentEvents, type Agent } from '@deepseek-ai/dsh-agent' +import type { Message } from '@deepseek-ai/dsh-llm' +import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' +import { afterEach, describe, expect, it } from 'vitest' +import * as cliDemo from '../src/index.ts' + +const contexts: Context[] = [] + +async function skillConfig(catalogDescriptionMaxLength?: number): Promise> { + const home = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-skills-')) + return { + local: { dshHome: join(home, '.dsh'), agentsHome: join(home, '.agents') }, + ...catalogDescriptionMaxLength === undefined ? {} : { tool: { catalogDescriptionMaxLength } }, + } +} + +async function mount(config: cliDemo.Config): Promise { + const ctx = new Context() + contexts.push(ctx) + await ctx.plugin(cliDemo, config) + await new Promise(resolve => setTimeout(resolve, 80)) + return ctx +} + +async function composePrefix(ctx: Context): Promise { + const agent = { session: { header: { cwd: '/tmp' } } } as unknown as Agent + const empty: Message[] = [] + return await agentEvents(ctx, agent).waterfall( + 'agent/session-prefix', empty, new AbortController().signal, + () => Promise.resolve(empty), + ) +} + +afterEach(async () => { + await Promise.all(contexts.splice(0).map(ctx => ctx.fiber.dispose())) +}) + +describe('dsh-cli-demo app composition', () => { + it('composes the UI-less spine, JSONL persistence, and a main agent', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-compose-')) + const ctx = await mount({ + model: 'mock', + persona: 'Headless.', + tools: { mode: 'native' }, + persistenceRoot: root, + skills: await skillConfig(), + }) + const agent = ctx.get('agents')?.get(AgentId('main')) + expect(ctx.get('agentLoop')).toBeDefined() + expect(ctx.get('sessionPersistence')).toBeDefined() + expect(agent?.session.header.cwd).toBe(process.cwd()) + expect(ctx.get('userInteraction')).toBeUndefined() + expect(ctx.get('tools')?.get('ask_user_question')).toBeUndefined() + }) + + it('covers direct-apply defaults and forwards skill and tool-order config', async () => { + const oldDshHome = process.env.DSH_HOME + const oldAgentsHome = process.env.DSH_AGENTS_HOME + const home = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-defaults-')) + process.env.DSH_HOME = join(home, '.dsh') + process.env.DSH_AGENTS_HOME = join(home, '.agents') + try { + const ctx = new Context() + contexts.push(ctx) + cliDemo.apply(ctx, { model: 'mock' }) + await new Promise(resolve => setTimeout(resolve, 80)) + expect(ctx.get('sessionPersistence')).toBeDefined() + expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() + expect(await ctx.skills.list()).toEqual([]) + } finally { + if (oldDshHome === undefined) delete process.env.DSH_HOME + else process.env.DSH_HOME = oldDshHome + if (oldAgentsHome === undefined) delete process.env.DSH_AGENTS_HOME + else process.env.DSH_AGENTS_HOME = oldAgentsHome + } + + const ctx = await mount({ + model: 'mock', + toolOrder: ['zulu', TOOL_ORDER_REST], + skills: await skillConfig(6), + }) + ctx.skills.register({ name: 'cli-skill', description: 'CLI skill', source: 'runtime', content: 'body' }) + for (const name of ['alpha', 'zulu']) { + ctx.tools.register({ name, description: name, parameters: {}, execute: async () => [] }) + } + expect(JSON.stringify(await composePrefix(ctx))).toContain('- `cli-skill`: CLI...') + expect((await ctx.systemPrompt.assemble()).tools.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'skill']) + }) + + it('exposes the Loader-safe namespace plugin shape and schema', () => { + expect(cliDemo.name).toBe('cli-demo') + expect(cliDemo.Config).toBeDefined() + expect('default' in cliDemo).toBe(false) + const loader = Object.create(Loader.prototype) as Loader + const unwrapped = loader.unwrapExports(cliDemo) as Record + expect(unwrapped).toBe(cliDemo) + expect(unwrapped.name).toBe('cli-demo') + expect(typeof unwrapped.apply).toBe('function') + }) +}) diff --git a/packages/examples/cli-demo/tests/cli.spec.ts b/packages/examples/cli-demo/tests/cli.spec.ts new file mode 100644 index 0000000000..c4d46ea3da --- /dev/null +++ b/packages/examples/cli-demo/tests/cli.spec.ts @@ -0,0 +1,362 @@ +import { readdir, mkdtemp } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join, resolve } from 'node:path' +import { Context } from 'cordis' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk, type TokenUsage } from '@deepseek-ai/dsh-llm' +import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' +import { afterEach, describe, expect, it } from 'vitest' +import * as cliDemo from '../src/index.ts' +import { + executeCli, + formatTurnFailure, + parseCliArgs, + runOneShot, + type CliResult, +} from '../src/cli.ts' + +type ScriptEntry = readonly StreamChunk[] | 'hang' + +class ScriptedAdapter extends LlmAdapter { + readonly requests: GenerateOptions[] = [] + private cursor = 0 + + constructor(private readonly script: readonly ScriptEntry[]) { + super() + } + + async * stream(options: GenerateOptions): AsyncIterable { + this.requests.push(options) + const entry = this.script[this.cursor++] + if (entry === undefined) throw new Error('script exhausted') + if (entry === 'hang') { + yield { type: 'block-start', index: 0, blockType: 'text' } + yield { type: 'text-delta', index: 0, text: 'partial' } + await new Promise((_resolve, reject) => { + if (options.signal?.aborted === true) { + reject(new Error('aborted')) + return + } + options.signal?.addEventListener('abort', () => { reject(new Error('aborted')) }, { once: true }) + }) + return + } + for (const chunk of entry) yield chunk + } +} + +function textResponse(text: string, usage?: TokenUsage, finish: 'stop' | 'max-tokens' = 'stop'): StreamChunk[] { + return [ + { type: 'block-start', index: 0, blockType: 'text' }, + { type: 'text-delta', index: 0, text }, + { type: 'block-end', index: 0, block: { type: 'text', text } }, + ...usage === undefined ? [] : [{ type: 'usage', usage } as const], + { type: 'finish', reason: { kind: finish } }, + ] +} + +function toolResponse(usage: TokenUsage): StreamChunk[] { + const id = CallId('cli-call') + const args = JSON.stringify({ text: 'round trip' }) + return [ + { type: 'block-start', index: 0, blockType: 'text' }, + { type: 'text-delta', index: 0, text: 'working' }, + { type: 'block-end', index: 0, block: { type: 'text', text: 'working' } }, + { type: 'block-start', index: 1, blockType: 'tool-call' }, + { type: 'tool-call-delta', index: 1, id, name: 'echo', argumentsDelta: args }, + { type: 'block-end', index: 1, block: { type: 'tool-call', id, name: 'echo', arguments: args } }, + { type: 'usage', usage }, + { type: 'finish', reason: { kind: 'tool-calls' } }, + ] +} + +function reasoningResponse(text: string): StreamChunk[] { + return [ + { type: 'block-start', index: 0, blockType: 'reasoning' }, + { type: 'reasoning-delta', index: 0, text }, + { type: 'block-end', index: 0, block: { type: 'reasoning', text } }, + { type: 'finish', reason: { kind: 'stop' } }, + ] +} + +interface Harness { + readonly ctx: Context + readonly agent: Agent + readonly persistenceRoot: string +} + +const liveContexts: Context[] = [] + +async function harness(script: readonly ScriptEntry[]): Promise { + const root = await mkdtemp(join(tmpdir(), 'dsh-cli-runner-')) + const skillHome = await mkdtemp(join(tmpdir(), 'dsh-cli-runner-skills-')) + const ctx = new Context() + liveContexts.push(ctx) + await ctx.plugin(cliDemo, { + model: 'mock', + persistenceRoot: root, + skills: { local: { dshHome: join(skillHome, '.dsh'), agentsHome: join(skillHome, '.agents') } }, + }) + await new Promise(resolve => setTimeout(resolve, 80)) + ctx.llm.registerAdapter(['mock'], new ScriptedAdapter(script)) + ctx.tools.register({ + name: 'echo', + description: 'Echo text.', + parameters: { text: { type: 'string', required: true } }, + execute: async args => [{ type: 'text', text: `ECHO: ${(args as { text: string }).text}` }], + }) + const agent = ctx.agents.get(AgentId('main')) + if (agent === undefined) throw new Error('test main agent missing') + return { ctx, agent, persistenceRoot: root } +} + +async function invoke( + ctx: Context, + args: readonly string[], + options: { signal?: AbortSignal; failStdout?: boolean; failDispose?: boolean } = {}, +): Promise<{ code: number; stdout: string; stderr: string }> { + let stdout = '' + let stderr = '' + const code = await executeCli(args, { + cwd: '/tmp/cli-cwd', + ...options.signal === undefined ? {} : { signal: options.signal }, + boot: async () => ctx, + loadEnv: () => {}, + writeStdout: (chunk) => { + if (options.failStdout === true) throw new Error('stdout closed') + stdout += chunk + }, + writeStderr: (chunk) => { stderr += chunk }, + ...options.failDispose === true + ? { dispose: async (target: Context) => { + await target.fiber.dispose() + throw new Error('dispose exploded') + } } + : {}, + }) + return { code, stdout, stderr } +} + +afterEach(async () => { + await Promise.all(liveContexts.splice(0).map(ctx => ctx.fiber.dispose())) +}) + +describe('parseCliArgs', () => { + it('parses defaults, explicit options, spaces, and an option-like task after --', () => { + expect(parseCliArgs(['task with spaces'])).toEqual({ + kind: 'run', configPath: './cordis.yml', outputFormat: 'text', task: 'task with spaces', + }) + expect(parseCliArgs(['--config', 'custom.yml', '--output-format', 'stream-json', 'do it'])).toEqual({ + kind: 'run', configPath: 'custom.yml', outputFormat: 'stream-json', task: 'do it', + }) + expect(parseCliArgs(['--', '-task'])).toMatchObject({ task: '-task' }) + expect(parseCliArgs(['--help', 'ignored'])).toEqual({ kind: 'help' }) + }) + + it('rejects missing, blank, extra, invalid-format, and unsupported flags', () => { + expect(() => parseCliArgs([])).toThrow('received 0') + expect(() => parseCliArgs([' '])).toThrow('must not be blank') + expect(() => parseCliArgs(['one', 'two'])).toThrow('received 2') + expect(() => parseCliArgs(['--output-format', 'xml', 'task'])).toThrow('unsupported output format') + expect(() => parseCliArgs(['-p', 'task'])).toThrow('Unknown option') + }) +}) + +describe('runOneShot and executeCli', () => { + it('prints help and argument diagnostics without booting or contaminating stdout', async () => { + let booted = false + let stdout = '' + let stderr = '' + const runtime = { + boot: async (): Promise => { booted = true; throw new Error('unexpected') }, + writeStdout: (chunk: string): void => { stdout += chunk }, + writeStderr: (chunk: string): void => { stderr += chunk }, + } + expect(await executeCli(['--help'], runtime)).toBe(0) + expect(stdout).toContain('Usage: dsh-cli-demo') + stdout = '' + expect(await executeCli([], runtime)).toBe(1) + expect(stdout).toBe('') + expect(stderr).toContain('received 0') + expect(booted).toBe(false) + }) + + it('leaves stdout empty for environment and boot failures and resolves the default config', async () => { + let bootPath = '' + let stderr = '' + const code = await executeCli(['task'], { + cwd: '/tmp/cli-work', + loadEnv: (_name, _dir, warn) => { warn('env warning\n') }, + boot: async (_name, path) => { bootPath = path; throw 'boot exploded' }, + writeStdout: () => { throw new Error('stdout must stay empty') }, + writeStderr: (chunk) => { stderr += chunk }, + }) + expect(code).toBe(1) + expect(bootPath).toBe(resolve('/tmp/cli-work/cordis.yml')) + expect(stderr).toContain('env warning') + expect(stderr).toContain('boot exploded') + }) + + it('renders text, flushes a persisted fresh session, and disposes the context', async () => { + const { ctx, agent, persistenceRoot } = await harness([textResponse('final answer')]) + const output = await invoke(ctx, ['task']) + expect(output).toEqual({ code: 0, stdout: 'final answer\n', stderr: '' }) + expect(agent.status).toBe('disposed') + const files = await readdir(persistenceRoot, { recursive: true }) + expect(files.some(file => file.endsWith('.jsonl'))).toBe(true) + }) + + it('sums usage across tool steps and selects the last text-bearing assistant message', async () => { + const first = { inputTokens: 10, outputTokens: 3, cacheReadTokens: 2, cacheWriteTokens: 1 } + const second = { inputTokens: 7, outputTokens: 5, cacheReadTokens: 4, reasoningTokens: 6 } + const { ctx } = await harness([toolResponse(first), textResponse('done', second)]) + const output = await invoke(ctx, ['--output-format', 'json', 'task']) + const result = JSON.parse(output.stdout) as CliResult + expect(output.code).toBe(0) + expect(result).toMatchObject({ type: 'result', success: true, turn: 1, result: 'done', reason: { kind: 'completed' } }) + expect(result.usage).toEqual({ + inputTokens: 17, + outputTokens: 8, + cacheReadTokens: 6, + cacheWriteTokens: 1, + reasoningTokens: 6, + }) + }) + + it('keeps the prior text when a later assistant message has no text blocks', async () => { + const { ctx } = await harness([ + toolResponse({ inputTokens: 1, outputTokens: 1 }), + reasoningResponse('reasoning only'), + ]) + const result = await runOneShot(ctx, { task: 'task' }) + expect(result.result).toBe('working') + }) + + it('streams only the correlated main message turn and then the result envelope', async () => { + const { ctx, agent } = await harness([textResponse('streamed')]) + const other = ctx.sessions.create(SessionId('unrelated')) + let injected = false + ctx.on('agent/queued', (subject) => { + if (subject !== agent || injected) return + injected = true + agent.inject([{ type: 'text', text: 'startup injection' }], { source: { kind: 'plugin', plugin: 'test' } }) + other.append('turn/start', { turn: 1, trigger: { kind: 'injection', source: { kind: 'plugin', plugin: 'test' } } }) + other.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + }) + const output = await invoke(ctx, ['--output-format', 'stream-json', 'task']) + const lines = output.stdout.trimEnd().split('\n').map(line => JSON.parse(line) as Record) + const events = lines.slice(0, -1).map(line => line['event'] as SessionEvent) + expect(lines.at(-1)).toMatchObject({ type: 'result', success: true, turn: 2, result: 'streamed' }) + expect(events[0]).toMatchObject({ type: 'turn/start', data: { turn: 2, trigger: { kind: 'message' } } }) + expect(events.at(-1)).toMatchObject({ type: 'turn/end', data: { turn: 2 } }) + expect(lines.slice(0, -1).every(line => line['sessionId'] === agent.session.id)).toBe(true) + expect(events.some(event => event.type === 'context/message')).toBe(false) + }) + + it('emits partial data and a diagnostic for non-completed turns', async () => { + const { ctx } = await harness([textResponse('partial', { inputTokens: 2, outputTokens: 3 }, 'max-tokens')]) + const output = await invoke(ctx, ['--output-format', 'json', 'task']) + expect(JSON.parse(output.stdout)).toMatchObject({ success: false, result: 'partial', reason: { kind: 'max-tokens' } }) + expect(output.code).toBe(1) + expect(output.stderr).toContain('output-token limit') + }) + + it('cancels an active turn, emits its durable aborted result, and disposes', async () => { + const { ctx, agent } = await harness(['hang']) + const abort = new AbortController() + let started!: () => void + const running = new Promise((resolveStarted) => { started = resolveStarted }) + ctx.on('session/event', (session, event) => { + if (session === agent.session && event.type === 'assistant/chunk') started() + }) + const outcome = invoke(ctx, ['--output-format', 'json', 'task'], { signal: abort.signal }) + await running + abort.abort('received SIGINT') + const output = await outcome + expect(JSON.parse(output.stdout)).toMatchObject({ success: false, reason: { kind: 'aborted', reason: 'received SIGINT' } }) + expect(output.code).toBe(1) + expect(output.stderr).toContain('was aborted: received SIGINT') + expect(agent.status).toBe('disposed') + }) + + it('contains stream-writer failures, cancels, flushes, and returns the output error', async () => { + const { ctx, agent } = await harness(['hang']) + await expect(runOneShot(ctx, { + task: 'task', + onEvent: () => { throw new Error('stream sink failed') }, + })).rejects.toThrow('stream sink failed') + expect(agent.status).toBe('idle') + }) + + it('handles cancellation before submission, a missing main agent, and final-output failure', async () => { + const early = await harness([textResponse('unused')]) + const fakeSignal = { + aborted: true, + reason: undefined, + } as unknown as AbortSignal + await expect(runOneShot(early.ctx, { task: 'task', signal: fakeSignal })).rejects.toThrow('interrupted') + + const preBootAbort = new AbortController() + preBootAbort.abort('before boot completed') + const preBoot = await invoke(early.ctx, ['task'], { signal: preBootAbort.signal }) + expect(preBoot).toMatchObject({ code: 1, stdout: '' }) + expect(preBoot.stderr).toContain('before boot completed') + + const empty = new Context() + liveContexts.push(empty) + await expect(runOneShot(empty, { task: 'task' })).rejects.toThrow('required "main" agent') + + const final = await harness([textResponse('answer')]) + const output = await invoke(final.ctx, ['task'], { failStdout: true }) + expect(output.code).toBe(1) + expect(output.stdout).toBe('') + expect(output.stderr).toContain('stdout closed') + expect(final.agent.status).toBe('disposed') + + const disposal = await harness([textResponse('answer')]) + const disposalOutput = await invoke(disposal.ctx, ['task'], { failDispose: true }) + expect(disposalOutput).toMatchObject({ code: 1, stdout: 'answer\n' }) + expect(disposalOutput.stderr).toContain('dispose exploded') + }) + + it('cancels startup work and queued work before the correlated turn begins', async () => { + const startup = await harness(['hang']) + let started!: () => void + const running = new Promise((resolveStarted) => { started = resolveStarted }) + startup.ctx.on('session/event', (session, event) => { + if (session === startup.agent.session && event.type === 'assistant/chunk') started() + }) + startup.agent.send([{ type: 'text', text: 'first' }]) + await running + const startupAbort = new AbortController() + const waiting = runOneShot(startup.ctx, { task: 'second', signal: startupAbort.signal }) + startupAbort.abort('cancel startup') + await expect(waiting).rejects.toThrow('cancel startup') + await startup.agent.whenIdle() + + const queued = await harness([textResponse('unused')]) + const queuedAbort = new AbortController() + queued.ctx.on('agent/queued', (agent) => { + if (agent === queued.agent) queuedAbort.abort('cancel queued') + }) + await expect(runOneShot(queued.ctx, { task: 'task', signal: queuedAbort.signal })).rejects.toThrow('cancel queued') + await queued.agent.whenIdle() + }) +}) + +describe('formatTurnFailure', () => { + it('diagnoses every durable reason and preserves merge-extensible unknowns', () => { + const cases: [TurnEndReason, string][] = [ + [{ kind: 'completed' }, 'completed'], + [{ kind: 'aborted' }, 'was aborted'], + [{ kind: 'aborted', reason: 'stop' }, 'was aborted: stop'], + [{ kind: 'error', step: 2, message: 'bad' }, 'failed at step 2: bad'], + [{ kind: 'disposed' }, 'was disposed'], + [{ kind: 'max-tokens' }, 'output-token limit'], + [{ kind: 'rejected', reason: 'policy' }, 'was rejected: policy'], + [{ kind: 'interrupted' }, 'persistence recovery'], + ] + for (const [reason, expected] of cases) expect(formatTurnFailure(reason)).toContain(expected) + expect(formatTurnFailure({ kind: 'extension' } as unknown as TurnEndReason)).toContain('extension') + }) +}) diff --git a/packages/examples/cli-demo/tsconfig.json b/packages/examples/cli-demo/tsconfig.json new file mode 100644 index 0000000000..f25b1592ca --- /dev/null +++ b/packages/examples/cli-demo/tsconfig.json @@ -0,0 +1,22 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "composite": true, + "rootDir": "src", + "outDir": "lib/types", + "tsBuildInfoFile": "../../../.typecheck/cli-demo.tsbuildinfo" + }, + "include": ["src/**/*.ts"], + "references": [ + { "path": "../../../vendor/schemastery" }, + { "path": "../../../vendor/cordis" }, + { "path": "../../llm/llm" }, + { "path": "../../core/session" }, + { "path": "../../core/agent" }, + { "path": "../../core/system-prompt" }, + { "path": "../../core/tools" }, + { "path": "../agent-spine-demo" }, + { "path": "../../session-persistence/session-persistence-jsonl" }, + { "path": "../../ui/app-boot" } + ] +} diff --git a/packages/examples/cli-demo/tsdown.config.ts b/packages/examples/cli-demo/tsdown.config.ts new file mode 100644 index 0000000000..e5b164d46f --- /dev/null +++ b/packages/examples/cli-demo/tsdown.config.ts @@ -0,0 +1,13 @@ +import { defineConfig } from 'tsdown' + +/** Builds the plugin and executable entries from declarations emitted by `tsc -b`. */ +export default defineConfig({ + entry: ['lib/types/index.js', 'lib/types/bin.js'], + outDir: 'lib', + format: ['esm'], + platform: 'node', + target: 'es2024', + fixedExtension: false, + dts: false, + clean: false, +}) diff --git a/packages/support/loader-smoke/README.md b/packages/support/loader-smoke/README.md index ea197b25d0..4527be6430 100644 --- a/packages/support/loader-smoke/README.md +++ b/packages/support/loader-smoke/README.md @@ -1,6 +1,6 @@ # `@deepseek-ai/dsh-loader-smoke` -Shared subprocess harness for keyless example smokes that boot the real stdio-agent bin and a real `cordis.yml` through the Cordis Loader. A test supplies absolute bin/config/tsconfig paths, optional environment overrides, and stdin lines; `runLoaderSmoke` owns the isolated cwd, DSH homes, tsx path resolution, 30-second process deadline, captured diagnostics, forced kill, EOF, and cleanup. +Shared subprocess harness for keyless example smokes that boot a real app bin and `cordis.yml` through the Cordis Loader. A test supplies absolute bin/config/tsconfig paths, optional complete bin arguments, environment overrides, stdin lines, pre-run world setup, and a pre-cleanup world assertion; `runLoaderSmoke` owns the isolated cwd, DSH homes, tsx path resolution, 30-second process deadline, captured diagnostics, forced kill, EOF, and cleanup. Successful runs return stdout and stderr only after a zero exit. Non-zero exits and deadlines reject with both captured streams. `LOADER_SMOKE_TEST_TIMEOUT_MS` leaves Vitest enough room for the process-owned diagnostic timeout to fire first. diff --git a/packages/support/loader-smoke/src/index.ts b/packages/support/loader-smoke/src/index.ts index 72839c6a05..c49fe1f4cc 100644 --- a/packages/support/loader-smoke/src/index.ts +++ b/packages/support/loader-smoke/src/index.ts @@ -1,6 +1,6 @@ /** * Shared subprocess harness for keyless example smokes that boot a real - * `cordis.yml` through the stdio-agent bin and Cordis Loader. + * `cordis.yml` through an app bin and Cordis Loader. * * @module @deepseek-ai/dsh-loader-smoke */ @@ -23,10 +23,12 @@ export interface LoaderSmokeOptions { readonly label: string /** Prefix for the isolated temporary process cwd. */ readonly tempDirPrefix: string - /** Absolute stdio-agent bin path. */ + /** Absolute app-bin path. */ readonly binScript: string - /** Absolute real Loader config path. */ + /** Absolute real Loader config path, passed as the sole bin argument by default. */ readonly configPath: string + /** Complete argv after the bin path; overrides the default `[configPath]`. */ + readonly binArgs?: readonly string[] /** Absolute repo tsconfig path used for unbuilt workspace-package resolution. */ readonly tsconfigPath: string /** Environment overrides layered over the parent and isolated DSH homes. */ @@ -35,6 +37,10 @@ export interface LoaderSmokeOptions { readonly stdinLines?: readonly string[] /** Process deadline override for harness tests. */ readonly processTimeoutMs?: number + /** Optional world-state setup run in the isolated cwd before process start. */ + readonly prepare?: (cwd: string) => Promise | void + /** Optional world-state assertion run in the isolated cwd before cleanup. */ + readonly inspect?: (cwd: string) => Promise | void } /** Captured output from a Loader smoke that exited successfully. */ @@ -56,10 +62,11 @@ export async function runLoaderSmoke(options: LoaderSmokeOptions): Promise { + await options.prepare?.(cwd) + const result = await new Promise((resolve, reject) => { const child = spawn( process.execPath, - ['--expose-internals', '--import', TSX_LOADER, options.binScript, options.configPath], + ['--expose-internals', '--import', TSX_LOADER, options.binScript, ...(options.binArgs ?? [options.configPath])], { cwd, env: { @@ -111,6 +118,8 @@ export async function runLoaderSmoke(options: LoaderSmokeOptions): Promise `${line}\n`).join('')) }) + await options.inspect?.(cwd) + return result } finally { await rm(cwd, { recursive: true, force: true }) } diff --git a/packages/support/loader-smoke/tests/fixtures/success.ts b/packages/support/loader-smoke/tests/fixtures/success.ts index fed57162e2..82a63cdfd3 100644 --- a/packages/support/loader-smoke/tests/fixtures/success.ts +++ b/packages/support/loader-smoke/tests/fixtures/success.ts @@ -6,6 +6,7 @@ process.stdin.on('data', (chunk: string) => { input += chunk }) process.stdin.on('end', () => { console.log(JSON.stringify({ configPath: process.argv[2], + args: process.argv.slice(2), cwd: process.cwd(), dshHome: process.env.DSH_HOME, agentsHome: process.env.DSH_AGENTS_HOME, diff --git a/packages/support/loader-smoke/tests/loader-smoke.spec.ts b/packages/support/loader-smoke/tests/loader-smoke.spec.ts index 4cc9f878f9..e4e899d67d 100644 --- a/packages/support/loader-smoke/tests/loader-smoke.spec.ts +++ b/packages/support/loader-smoke/tests/loader-smoke.spec.ts @@ -1,4 +1,6 @@ import { existsSync } from 'node:fs' +import { readFile, writeFile } from 'node:fs/promises' +import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { describe, expect, it } from 'vitest' import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' @@ -21,6 +23,7 @@ describe('runLoaderSmoke', () => { }) const output = JSON.parse(result.stdout) as { configPath: string + args: string[] cwd: string dshHome: string agentsHome: string @@ -29,6 +32,7 @@ describe('runLoaderSmoke', () => { } expect(output).toMatchObject({ configPath, + args: [configPath], marker: 'present', input: 'one\ntwo\n', }) @@ -38,6 +42,29 @@ describe('runLoaderSmoke', () => { expect(existsSync(output.cwd)).toBe(false) }, LOADER_SMOKE_TEST_TIMEOUT_MS) + it('passes an arbitrary bin argv and inspects world state before cleanup', async () => { + let inspected = '' + let marker = '' + const result = await runLoaderSmoke({ + label: 'argv fixture', + tempDirPrefix: 'loader-smoke-argv-', + binScript: fixture('success'), + configPath, + binArgs: ['--config', configPath, '--output-format', 'json', 'task with spaces'], + tsconfigPath, + prepare: cwd => writeFile(join(cwd, 'marker.txt'), 'prepared'), + inspect: async (cwd) => { + inspected = cwd + marker = await readFile(join(cwd, 'marker.txt'), 'utf8') + }, + }) + const output = JSON.parse(result.stdout) as { args: string[]; cwd: string } + expect(output.args).toEqual(['--config', configPath, '--output-format', 'json', 'task with spaces']) + expect(canonicalTempPath(inspected)).toBe(canonicalTempPath(output.cwd)) + expect(marker).toBe('prepared') + expect(existsSync(inspected)).toBe(false) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + it('rejects a non-zero exit with captured diagnostics', async () => { await expect(runLoaderSmoke({ label: 'failure fixture', diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index ea9494fe81..5be597e52e 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -525,6 +525,45 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/examples/cli-demo: + devDependencies: + '@cordisjs/plugin-include': + specifier: workspace:^ + version: link:../../../vendor/include + '@cordisjs/plugin-loader': + specifier: workspace:^ + version: link:../../../vendor/loader + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-agent-spine-demo': + specifier: workspace:^ + version: link:../agent-spine-demo + '@deepseek-ai/dsh-app-boot': + specifier: workspace:^ + version: link:../../ui/app-boot + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl + '@deepseek-ai/dsh-system-prompt': + specifier: workspace:^ + version: link:../../core/system-prompt + '@deepseek-ai/dsh-tools': + specifier: workspace:^ + version: link:../../core/tools + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) + schemastery: + specifier: ^3.17.0 + version: 3.18.0 + packages/examples/jsonrpc-demo: dependencies: '@deepseek-ai/dsh-app-boot': diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 0e1774c2e0..2c24396e12 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -89,7 +89,7 @@ const SERVICE_ROLES: ServiceRole[] = [ pkg: 'session', title: 'In-memory session store', mode: 'core', - consumers: ['agent-loop', 'agent', 'session-persistence', 'session-query', 'subagent-inprocess', 'invariants'], + consumers: ['agent-loop', 'agent', 'cli-demo', 'session-persistence', 'session-query', 'subagent-inprocess', 'invariants'], note: 'Owns append-only Session instances and emits the durable session event feed.', }, { @@ -147,7 +147,7 @@ const SERVICE_ROLES: ServiceRole[] = [ pkg: 'agent', title: 'Agent registry', mode: 'core', - consumers: ['agent-loop', 'acp', 'subagent-inprocess', 'stdio-demo', 'invariants'], + consumers: ['agent-loop', 'acp', 'cli-demo', 'subagent-inprocess', 'stdio-demo', 'invariants'], note: 'Owns live Agent handles and the create/resume factory seam.', }, { @@ -426,6 +426,8 @@ function renderAppExpansion(lines: string[], appNode: string, pluginName: string lines.push(` ${appNode} --> ${jsonl}["@deepseek-ai/dsh-session-persistence-jsonl"]`) if (pluginName === '@deepseek-ai/dsh-stdio-demo') { lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["readline UI
console logger
pre-created main agent"]`) + } else if (pluginName === '@deepseek-ai/dsh-cli-demo') { + lines.push(` ${appNode} --> ${nodeId('frontdoor', 'cli')}["one-shot driver
format-pure stdout
pre-created main agent"]`) } else if (pluginName === '@deepseek-ai/dsh-acp-demo') { lines.push(` ${appNode} --> ${nodeId('frontdoor', 'acp')}["@deepseek-ai/dsh-acp
JSON-RPC stdio bridge
sessions created by client"]`) } @@ -452,7 +454,7 @@ function renderAppComposition(example: AppExample): string { const pluginNode = nodeId(`plugin_${example.id}`, plugin.id) lines.push(` ${pluginNode}["${escLabel(plugin.id)}
${escLabel(plugin.name)}"]`) lines.push(` cfg --> ${pluginNode}`) - if (plugin.name === '@deepseek-ai/dsh-stdio-demo' || plugin.name === '@deepseek-ai/dsh-acp-demo') { + if (plugin.name === '@deepseek-ai/dsh-stdio-demo' || plugin.name === '@deepseek-ai/dsh-cli-demo' || plugin.name === '@deepseek-ai/dsh-acp-demo') { renderAppExpansion(lines, pluginNode, plugin.name) } } diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index d103f11461..b01cb8a579 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -344,6 +344,7 @@ function builtBinSmokeGate(): Gate { '--config', 'vitest.e2e.config.ts', 'packages/examples/stdio-demo/tests/built-bin.e2e.ts', + 'packages/examples/cli-demo/tests/built-bin.e2e.ts', 'packages/examples/acp-demo/tests/built-bin.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node diff --git a/tsconfig.build.json b/tsconfig.build.json index 05725fe0ae..05f27b0849 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -32,6 +32,7 @@ { "path": "./packages/ui/tool-ask-user" }, { "path": "./packages/core/agent-loop" }, { "path": "./packages/examples/agent-spine-demo" }, + { "path": "./packages/examples/cli-demo" }, { "path": "./packages/bash/bash" }, { "path": "./packages/code-runtime/code-runtime" }, { "path": "./packages/code-runtime/code-runtime-worker" }, diff --git a/tsconfig.json b/tsconfig.json index af6e900f0f..6f39963be3 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -43,6 +43,7 @@ { "path": "./packages/ui/tool-ask-user" }, { "path": "./packages/core/agent-loop" }, { "path": "./packages/examples/agent-spine-demo" }, + { "path": "./packages/examples/cli-demo" }, { "path": "./packages/bash/bash" }, { "path": "./packages/code-runtime/code-runtime" }, { "path": "./packages/code-runtime/code-runtime-worker" }, From 7278fc21d8bfad12124fe876a61f5a6cc0ba5bc4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 21:36:42 +0800 Subject: [PATCH 115/323] fix(session-persistence): handle Windows directory fsync --- .../examples/cli-demo/tests/built-bin.e2e.ts | 30 +++++++------- .../session-persistence-jsonl/README.md | 3 +- .../session-persistence-jsonl/src/index.ts | 14 ++++++- .../tests/jsonl.spec.ts | 41 ++++++++++++++++++- 4 files changed, 70 insertions(+), 18 deletions(-) diff --git a/packages/examples/cli-demo/tests/built-bin.e2e.ts b/packages/examples/cli-demo/tests/built-bin.e2e.ts index aed7f1f2d4..7fa9bf977a 100644 --- a/packages/examples/cli-demo/tests/built-bin.e2e.ts +++ b/packages/examples/cli-demo/tests/built-bin.e2e.ts @@ -155,18 +155,20 @@ describe.skipIf(!existsSync(cliBin))('dsh-cli-demo BUILT bin', () => { } }, 30_000) - it.each([ - ['SIGINT', 130], - ['SIGTERM', 143], - ] as const)('cancels and disposes on %s with exit %i', async (signal, code) => { - consumer = await makeConsumer() - const result = await runBuiltBin( - consumer, - ['--config', './cordis.yml', '--output-format', 'stream-json', 'hang'], - signal, - ) - expect(result, JSON.stringify(result)).toMatchObject({ code, signal: null }) - expect(result.stdout).toContain('"kind":"aborted"') - expect(result.stderr).toContain(`received ${signal}`) - }, 30_000) + describe.skipIf(process.platform === 'win32')('POSIX signal delivery', () => { + it.each([ + ['SIGINT', 130], + ['SIGTERM', 143], + ] as const)('cancels and disposes on %s with exit %i', async (signal, code) => { + consumer = await makeConsumer() + const result = await runBuiltBin( + consumer, + ['--config', './cordis.yml', '--output-format', 'stream-json', 'hang'], + signal, + ) + expect(result, JSON.stringify(result)).toMatchObject({ code, signal: null }) + expect(result.stdout).toContain('"kind":"aborted"') + expect(result.stderr).toContain(`received ${signal}`) + }, 30_000) + }) }) diff --git a/packages/session-persistence/session-persistence-jsonl/README.md b/packages/session-persistence/session-persistence-jsonl/README.md index 343fb4a70a..1d00f28301 100644 --- a/packages/session-persistence/session-persistence-jsonl/README.md +++ b/packages/session-persistence/session-persistence-jsonl/README.md @@ -21,7 +21,7 @@ The JSONL durable session-persistence backend — a concrete `SessionPersistence ## Durability and crash semantics -- **Lazy materialization.** `create(meta)` writes nothing; on the first `append`, the backend writes and `fsync`s a temporary file, publishes it without overwrite via a hard link, then `fsync`s the directory. A created-but-never-appended session leaves nothing on disk and is absent from `list`. +- **Lazy materialization.** `create(meta)` writes nothing; on the first `append`, the backend writes and `fsync`s a temporary file, publishes it without overwrite via a hard link, then `fsync`s the directory when the host supports it. A created-but-never-appended session leaves nothing on disk and is absent from `list`. - **Append-only.** Committed events (at or below a flushed `turn/end`) are never rewritten. Subsequent appends are line appends at EOF + `fsync`. - **Crash recovery — preserve valid tail work.** `load` keeps the contiguous valid prefix of an interrupted final turn. It truncates from the first unparsable or sequence-gapped uncommitted record, then appends the synthetic tool, step, and turn closers required by the shared [persistence contract](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md); the same defect at or before the last committed `turn/end` rejects. - **Contiguous-seq.** `append` rejects a batch whose first `seq` does not continue the stored log, and rejects non-JSON-serializable `event.data` naming the offending event type. @@ -44,3 +44,4 @@ The plugin buffers frozen session events and drains them on flush or disposal. A - **Nothing deletes session files** — logs accumulate under `root` until removed externally (the seam has no deletion surface). - **Single-process assumption** — per-session serialization and the write cursor live in this process; two processes appending to the same `root` are not coordinated. - **Initial materialization requires hard-link support** — first append uses `link()` so same-id races fail instead of overwriting a committed log; a filesystem that cannot create hard links cannot host this backend. +- **Windows cannot `fsync` directory handles through Node** — the backend tolerates only Windows `EPERM` from directory `fsync`; file-content `fsync` remains mandatory, but a crash can lose a newly published directory entry on a host without an equivalent directory-sync primitive. diff --git a/packages/session-persistence/session-persistence-jsonl/src/index.ts b/packages/session-persistence/session-persistence-jsonl/src/index.ts index 1d13ff424e..95b8b1078c 100644 --- a/packages/session-persistence/session-persistence-jsonl/src/index.ts +++ b/packages/session-persistence/session-persistence-jsonl/src/index.ts @@ -56,6 +56,9 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi private root: string private coordinator: PersistenceCoordinator + /** Runtime-only host-platform seam for directory-sync compatibility tests. */ + readonly internals: { platform: NodeJS.Platform } = { platform: process.platform } + constructor(ctx: Context, public config: Config) { super(ctx) // Resolve once so later process.cwd() changes cannot split one backend across roots. @@ -202,11 +205,18 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi } } - /** fsync a directory so a just-created or published entry inside it is crash-durable. */ + /** fsync a directory when the host exposes that durability primitive. */ private async syncDir(dir: string): Promise { const handle = await open(dir, 'r') try { - await handle.sync() + try { + await handle.sync() + } catch (error: unknown) { + const code = (error as NodeJS.ErrnoException | null)?.code + // Node opens directories on Windows but its fsync binding rejects them. + // File-content fsync remains mandatory; only this unsupported primitive is skipped. + if (this.internals.platform !== 'win32' || code !== 'EPERM') throw error + } } finally { await handle.close() } diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index 75fcb48732..c85278f0c4 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -1,6 +1,7 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import { appendFile, mkdtemp, mkdir, rm, readFile, writeFile, readdir, stat } from 'node:fs/promises' +import { appendFile, mkdtemp, mkdir, open, rm, readFile, writeFile, readdir, stat } from 'node:fs/promises' +import type { FileHandle } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' @@ -40,9 +41,25 @@ async function freshRoot(): Promise { } afterEach(async () => { + vi.restoreAllMocks() for (const d of dirs.splice(0)) await rm(d, { recursive: true, force: true }) }) +async function rejectDirectorySync(code: string): Promise { + const handle = await open(root, 'r') + const proto = Object.getPrototypeOf(handle) as { sync: () => Promise } + await handle.close() + const realSync = proto.sync + vi.spyOn(proto, 'sync').mockImplementation(async function (this: FileHandle) { + if ((await this.stat()).isDirectory()) { + const error = new Error(`simulated directory fsync ${code}`) as NodeJS.ErrnoException + error.code = code + throw error + } + return realSync.call(this) + }) +} + function appendClosedTurn(session: Session): void { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { @@ -264,6 +281,28 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { expect(loaded.events.map(e => e.seq)).toEqual([0, 1, 2, 3, 4, 5, 6, 7]) }) + it('keeps file fsync mandatory while tolerating unsupported Windows directory fsync', async () => { + await rejectDirectorySync('EPERM') + const backend = ctx.sessionPersistence as SessionPersistenceJsonl + backend.internals.platform = 'win32' + const m = meta('windows-directory-sync') + await ctx.sessionPersistence.create(m) + await expect(ctx.sessionPersistence.append(m.id, oneTurnLog())).resolves.toBeUndefined() + expect((await ctx.sessionPersistence.load(m.id)).events).toEqual(oneTurnLog()) + }) + + it.each([ + ['linux', 'EPERM'], + ['win32', 'EIO'], + ] as const)('surfaces directory fsync errors on %s with %s', async (platform, code) => { + await rejectDirectorySync(code) + const backend = ctx.sessionPersistence as SessionPersistenceJsonl + backend.internals.platform = platform + const m = meta(`directory-sync-${platform}-${code}`) + await ctx.sessionPersistence.create(m) + await expect(ctx.sessionPersistence.append(m.id, oneTurnLog())).rejects.toMatchObject({ code }) + }) + it('load returns a meta copy: mutating it does not corrupt backend pathing', async () => { const m = meta('meta-copy', '/proj') await ctx.sessionPersistence.create(m) From 5e3da065db2cf3d2442e274dea95311d5c4cd257 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 22:43:03 +0800 Subject: [PATCH 116/323] test(examples): snapshot headless one-shot stream --- AGENTS.md | 4 +- README.i18n.yaml | 4 +- README.md | 1 + README.zh.md | 1 + docs/testing.md | 4 +- examples/README.md | 2 +- examples/acp-agent/README.md | 2 +- .../advanced-headless.cordis.snapshot.yml | 32 ++++ examples/acp-agent/tests/headless.snapshot.ts | 140 ++++++++++++++++++ .../stream-json.golden.jsonl | 64 ++++++++ examples/coding-agent/README.md | 6 +- package.json | 2 +- packages/examples/cli-demo/README.md | 2 +- 13 files changed, 251 insertions(+), 13 deletions(-) create mode 100644 examples/acp-agent/advanced-headless.cordis.snapshot.yml create mode 100644 examples/acp-agent/tests/headless.snapshot.ts create mode 100644 examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl diff --git a/AGENTS.md b/AGENTS.md index b9731f2c80..cf6d1c3e89 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -45,7 +45,7 @@ pnpm install # pnpm workspaces, node ^22.19 || >=24 pnpm run test # vitest unit tests pnpm run test:coverage # gate: per-file 100% on packages/*/*/src pnpm run test:e2e # real API; skips without key -pnpm run test:snapshot # keyless ACP replay vs goldens; filter: -t +pnpm run test:snapshot # keyless ACP/headless replay vs goldens; filter: -t pnpm run test:snapshot:record # re-record goldens (needs key) pnpm run typecheck pnpm run lint @@ -55,7 +55,7 @@ pnpm run hygiene # knip + publint + workspace constraints + NodeNext cons pnpm run doc-sync # all documentation gates; see the doc-sync script in package.json pnpm run demo:echo # mock-model REPL, no key needed pnpm run demo:repl # real coding REPL (needs key) -pnpm run demo:cli -- "task" # one-shot agent (needs key) +pnpm run demo:headless -- "task" # one-shot agent (needs key) pnpm run demo:cordis # self-modifying runtime demo (needs key) pnpm run demo:acp # ACP server (needs key) ``` diff --git a/README.i18n.yaml b/README.i18n.yaml index 790812344d..15992ac276 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 53dd3896eb15800125673e7c44f7de02daca9376 -README.zh.md: ab826f62658248249ec18c57b35c0065c0f909d1 +README.md: 4d2d2c20a27aff67d42a4555f4e0ce410dd5d6d7 +README.zh.md: 0fb307653f978143b851ef4822d93714910043af diff --git a/README.md b/README.md index 53dd3896eb..4d2d2c20a2 100644 --- a/README.md +++ b/README.md @@ -12,6 +12,7 @@ This monorepo is built on the [Cordis](https://github.com/cordiverse/cordis) fra pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/README.zh.md b/README.zh.md index ab826f6265..0fb307653f 100644 --- a/README.zh.md +++ b/README.zh.md @@ -12,6 +12,7 @@ pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/docs/testing.md b/docs/testing.md index d4acdc33c4..8d318ebd60 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -7,7 +7,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): boots the real example subprocess, replays a recorded session keyless, diffs normalized stdout + the re-persisted log against committed goldens ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). Use `pnpm run test:snapshot:record` when the model transcript should change; use `pnpm run test:snapshot:refresh` when the committed transcript is still the right mock LLM input and replay goldens need keyless rewrite. Review the golden diff. System-prompt/tool-schema content is pinned by ONE scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): real example subprocesses replay recorded model sessions keylessly and compare normalized stdout plus re-persisted logs ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). The primary suite pins ACP JSON-RPC; the headless projection reuses `advanced-toolchain` for `stream-json`. Use `pnpm run test:snapshot:record` when the model transcript changes and `pnpm run test:snapshot:refresh` when only replay outputs change; review the golden diff. One scenario per header class pins system-prompt/tool-schema content; other fixtures tokenize it ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here @@ -30,4 +30,4 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword ## When a snapshot test is required -Any change affecting the editor-facing transcript or end-to-end agent UX — the ACP bridge, the loop's observable output, tool presentation — adds or updates a scenario in the owning example's snapshot suite (`examples//tests/snapshots/`, a scenario table over the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) suite factory; `examples/acp-agent` is the primary suite), or states in the PR why none applies. New capability seams, lifecycle shapes, or transcript surfaces name their coverage at every tier at plan time and verify the harness can express it — a harness gap is scheduled work, not a mid-build surprise. +A change affecting an editor transcript, headless event stream, or agent UX adds or updates the owning `examples//tests/snapshots/` scenario, or explains its omission in the PR. `examples/acp-agent` hosts the primary [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) table and the headless `stream-json` projection. Plans for new capability seams, lifecycle shapes, or transcript surfaces identify every test tier and any required harness work before implementation. diff --git a/examples/README.md b/examples/README.md index d9e3e544db..399769992f 100644 --- a/examples/README.md +++ b/examples/README.md @@ -17,7 +17,7 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. The UI is a terminal readline REPL. -Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:cli -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. +Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:headless -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index 35218f4753..427b924d45 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -33,7 +33,7 @@ The editor sets each session's `cwd` to the project it opens, and bash uses that ## Snapshot tests (record-once / replay-deterministic) -This example hosts the ACP snapshot suite. `dsh-llm-replay` reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL, so replay is keyless. Recording runs the real agent and harvests that log; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the full design. +This example hosts the ACP snapshot suite and the headless `stream-json` snapshot. Both replay through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. The headless snapshot reuses `advanced-toolchain` to pin the one-shot stream plus its re-persisted parent and child logs; child activity appears in the stream only through parent tool events. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. ## Permissions and sandboxing diff --git a/examples/acp-agent/advanced-headless.cordis.snapshot.yml b/examples/acp-agent/advanced-headless.cordis.snapshot.yml new file mode 100644 index 0000000000..5047635ddb --- /dev/null +++ b/examples/acp-agent/advanced-headless.cordis.snapshot.yml @@ -0,0 +1,32 @@ +# Replay the advanced toolchain through the headless one-shot front door. It +# receives this replay config explicitly; unlike the ACP bin, it does not swap +# a live config for a sibling snapshot overlay. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + disabled: true + - insert: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + tools: + mode: both + persona: | + You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. + + Verify your work by running the code or tests. Keep answers brief and factual. + - id: code-runtime + name: '@deepseek-ai/dsh-code-runtime-worker' + - id: tool-cordis + name: '@deepseek-ai/dsh-tool-cordis' + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/acp-agent/tests/headless.snapshot.ts b/examples/acp-agent/tests/headless.snapshot.ts new file mode 100644 index 0000000000..a38931a8ef --- /dev/null +++ b/examples/acp-agent/tests/headless.snapshot.ts @@ -0,0 +1,140 @@ +import { readFile, readdir, writeFile } from 'node:fs/promises' +import { delimiter, dirname, join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { + normalizeSessionLog, + normalizeStdout, + scrubRequestHeaders, + type NormalizeContext, +} from '@deepseek-ai/dsh-acp-snapshot' +import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' +import { describe, expect, it } from 'vitest' + +const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') +const scenarioDir = join(snapshotsDir, 'advanced-toolchain') +const sessionFixture = join(scenarioDir, 'session.jsonl') +const streamGolden = join(scenarioDir, 'stream-json.golden.jsonl') +const configPath = fileURLToPath(new URL('../advanced-headless.cordis.snapshot.yml', import.meta.url)) +const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) +const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const refreshing = process.env.DSH_SNAPSHOT === 'refresh' + +interface JsonObject { + [key: string]: unknown +} + +interface PersistedLog { + readonly content: string + readonly header: JsonObject +} + +function parseJsonl(content: string): JsonObject[] { + return content.split('\n') + .filter(line => line.trim().length > 0) + .map(line => JSON.parse(line) as JsonObject) +} + +function contextFromLogs(contents: readonly string[]): NormalizeContext { + const headers = contents.map(content => parseJsonl(content)[0]) + return { + sessionIds: headers.flatMap(header => typeof header?.id === 'string' ? [header.id] : []), + cwd: typeof headers[0]?.cwd === 'string' ? headers[0].cwd : '\0no-cwd\0', + } +} + +function normalizeHeadlessStream(rawStdout: string, cwd: string): string { + const records = parseJsonl(rawStdout) + if (records.length === 0) throw new Error('headless snapshot emitted no stream-json records') + const final = records.at(-1) + if (final?.type !== 'result') throw new Error('headless snapshot did not end with a result record') + if (records.slice(0, -1).some(record => record.type !== 'session_event')) { + throw new Error('headless snapshot emitted a non-event record before its result') + } + + const sessionIds = [...new Set(records.flatMap(record => typeof record.sessionId === 'string' ? [record.sessionId] : []))] + if (sessionIds.length !== 1) throw new Error(`headless snapshot streamed ${sessionIds.length} main session ids`) + const context: NormalizeContext = { sessionIds, cwd } + const events = records.slice(0, -1).map((record) => { + if (record.event === null || typeof record.event !== 'object' || Array.isArray(record.event)) { + throw new Error('headless snapshot emitted an invalid session event') + } + return record.event as JsonObject + }) + const normalizedEvents = parseJsonl(scrubRequestHeaders(normalizeSessionLog( + `${events.map(event => JSON.stringify(event)).join('\n')}\n`, + context, + ))) + const normalizedRecords = records.map((record, index) => index < normalizedEvents.length + ? { ...record, event: normalizedEvents[index] } + : record) + return normalizeStdout(`${normalizedRecords.map(record => JSON.stringify(record)).join('\n')}\n`, context) +} + +async function advancedPrompt(): Promise { + const input = JSON.parse(await readFile(join(scenarioDir, 'input.json'), 'utf8')) as { + steps?: { op?: unknown; text?: unknown }[] + } + const prompt = input.steps?.find(step => step.op === 'prompt')?.text + if (typeof prompt !== 'string') throw new Error('advanced-toolchain input has no prompt step') + return prompt +} + +async function persistedLogs(cwd: string): Promise { + const root = join(cwd, '.sessions') + const files = (await readdir(root, { recursive: true })).filter(file => file.endsWith('.jsonl')) + return Promise.all(files.map(async (file) => { + const content = await readFile(join(root, file), 'utf8') + return { content, header: parseJsonl(content)[0] ?? {} } + })) +} + +describe('headless stream-json snapshots', () => { + it('replays the advanced toolchain through the one-shot app', async () => { + const prompt = await advancedPrompt() + const expectedSessions = await Promise.all([ + sessionFixture, + join(scenarioDir, 'session.1.jsonl'), + join(scenarioDir, 'session.2.jsonl'), + ].map(file => readFile(file, 'utf8'))) + let runCwd = '' + const result = await runLoaderSmoke({ + label: 'advanced headless stream-json snapshot', + tempDirPrefix: 'headless-snapshot-advanced-', + binScript, + configPath, + binArgs: ['--config', configPath, '--output-format', 'stream-json', prompt], + tsconfigPath, + env: { + DSH_SNAPSHOT: 'replay', + DSH_SNAPSHOT_FILE: sessionFixture, + DSH_SNAPSHOT_CHILD_FILES: [join(scenarioDir, 'session.1.jsonl'), join(scenarioDir, 'session.2.jsonl')].join(delimiter), + NODE_OPTIONS: [process.env.NODE_OPTIONS, '--disable-warning=ExperimentalWarning'].filter(Boolean).join(' '), + }, + prepare: (cwd) => { runCwd = cwd }, + inspect: async (cwd) => { + const logs = await persistedLogs(cwd) + expect(logs).toHaveLength(3) + const parents = logs.filter(log => typeof log.header.parentSession !== 'string') + expect(parents).toHaveLength(1) + const parent = parents[0] + if (parent === undefined) throw new Error('headless snapshot did not persist its main session') + const children = logs.filter(log => typeof log.header.parentSession === 'string') + .sort((left, right) => Number(left.header.createdAt) - Number(right.header.createdAt)) + const actualSessions = [parent, ...children] + const actualContext = contextFromLogs(actualSessions.map(log => log.content)) + const expectedContext = contextFromLogs(expectedSessions) + for (const [index, actual] of actualSessions.entries()) { + const expected = expectedSessions[index] + if (expected === undefined) throw new Error(`headless snapshot has no fixture for persisted log ${index}`) + expect(scrubRequestHeaders(normalizeSessionLog(actual.content, actualContext))) + .toBe(scrubRequestHeaders(normalizeSessionLog(expected, expectedContext))) + } + }, + }) + + expect(result.stderr).toBe('') + const normalized = normalizeHeadlessStream(result.stdout, runCwd) + if (refreshing) await writeFile(streamGolden, normalized) + expect(normalized).toBe(await readFile(streamGolden, 'utf8')) + }, LOADER_SMOKE_TEST_TIMEOUT_MS) +}) diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl new file mode 100644 index 0000000000..ea5eca3765 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl @@ -0,0 +1,64 @@ +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":13,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":14,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":15,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":20,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/code-dispatch","seq":21,"time":0,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":23,"time":0,"data":{"turn":1,"step":2}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":24,"time":0,"data":{"turn":1,"step":3}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":25,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":26,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":30,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":31,"time":0,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":33,"time":0,"data":{"turn":1,"step":3}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":34,"time":0,"data":{"turn":1,"step":4}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":35,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":42,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":43,"time":0,"data":{"turn":1,"step":4}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":44,"time":0,"data":{"turn":1,"step":5}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":45,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":46,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":50,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":51,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":52,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":53,"time":0,"data":{"turn":1,"step":5}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":54,"time":0,"data":{"turn":1,"step":6}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":55,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":56,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":58,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":59,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":61,"time":0,"data":{"turn":1,"step":6}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":62,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} +{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"ADVANCED_ACP_OK","reason":{"kind":"completed"},"usage":{"inputTokens":18,"outputTokens":18}} diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index c9f606766d..5efe939cfe 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -26,9 +26,9 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem Run one task through all model and tool steps, flush its fresh session, print the final result, and exit: ```sh -pnpm run demo:cli -- "fix the failing test in this workspace" -pnpm run demo:cli --output-format json -- "summarize the current implementation" -pnpm run demo:cli --output-format stream-json -- "run the focused tests" +pnpm run demo:headless -- "fix the failing test in this workspace" +pnpm run demo:headless --output-format json -- "summarize the current implementation" +pnpm run demo:headless --output-format stream-json -- "run the focused tests" ``` The root command supplies `cli.cordis.yml`, which disables HMR and the REPL app and inserts [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo). Exactly one quoted positional task is required; there is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Non-completed turns retain partial output but exit nonzero; argument and boot failures leave stdout empty. diff --git a/package.json b/package.json index d6f64f210b..2bf8506bf8 100644 --- a/package.json +++ b/package.json @@ -74,7 +74,7 @@ "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", - "demo:cli": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", + "demo:headless": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md index 558c5eeff3..38c38cf69c 100644 --- a/packages/examples/cli-demo/README.md +++ b/packages/examples/cli-demo/README.md @@ -28,7 +28,7 @@ dsh-cli-demo [--config path] [--output-format text|json|stream-json] The root coding demo supplies its overlay: ```sh -pnpm run demo:cli -- "inspect the failing test and fix it" +pnpm run demo:headless -- "inspect the failing test and fix it" ``` Loader configs with bare package specifiers require `node --expose-internals` or the Loader's optional native fallback. The root command supplies the Node flag. From fb7fa980b8411e285c5e396a42868b2f72d68b92 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 22:58:44 +0800 Subject: [PATCH 117/323] test(examples): include task controls in CLI composition --- packages/examples/cli-demo/tests/cli-demo.spec.ts | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/packages/examples/cli-demo/tests/cli-demo.spec.ts b/packages/examples/cli-demo/tests/cli-demo.spec.ts index 4cb7a243a5..1fb0e09999 100644 --- a/packages/examples/cli-demo/tests/cli-demo.spec.ts +++ b/packages/examples/cli-demo/tests/cli-demo.spec.ts @@ -89,7 +89,14 @@ describe('dsh-cli-demo app composition', () => { ctx.tools.register({ name, description: name, parameters: {}, execute: async () => [] }) } expect(JSON.stringify(await composePrefix(ctx))).toContain('- `cli-skill`: CLI...') - expect((await ctx.systemPrompt.assemble()).tools.map(tool => tool.name)).toEqual(['zulu', 'alpha', 'skill']) + expect((await ctx.systemPrompt.assemble()).tools.map(tool => tool.name)).toEqual([ + 'zulu', + 'alpha', + 'skill', + 'task_kill', + 'task_list', + 'task_output', + ]) }) it('exposes the Loader-safe namespace plugin shape and schema', () => { From bb1c8fa27da12f2432afaf3d5c04fd8299df73e9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:09:14 +0800 Subject: [PATCH 118/323] fix(llm): restore pruned status contract --- docs/cordis-catalog/services.md | 2 +- packages/llm/llm-deepseek/src/adapter.ts | 6 +++--- packages/llm/llm-deepseek/tests/adapter.spec.ts | 7 +------ packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm/README.md | 2 +- packages/llm/llm/src/index.ts | 6 ++---- packages/llm/llm/tests/service.spec.ts | 5 +++-- packages/support/llm-replay/src/index.ts | 4 ++-- packages/support/llm-replay/tests/llm-replay.spec.ts | 10 +++++----- 9 files changed, 19 insertions(+), 25 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 18e00b7904..48fb887d27 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -128,7 +128,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:75`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:73`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..978dec65c8 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -73,10 +73,10 @@ export class DeepSeekAdapter extends LlmAdapter { const parsed = await response.json() as WireError if (parsed.error?.message) message = parsed.error.message } catch { - // Only swallow error-body parsing: status and code are already captured, - // so malformed gateway JSON must not mask the actionable HTTP failure. + // Only swallow error-body parsing: the stable code and status-line message + // are already captured, so malformed gateway JSON must not mask the failure. } - throw new LlmError(message, code, response.status) + throw new LlmError(message, code) } if (!response.body) { throw new LlmError('DeepSeek API returned no response body', 'EMPTY_RESPONSE') diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..1f1aef3f05 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -158,7 +158,7 @@ describe('DeepSeekAdapter against a mock server', () => { status, body: JSON.stringify({ error: { message: `failed with ${status}`, type: 't', code: 'c' } }), } - const server = await mockServer([behavior, behavior, behavior]) + const server = await mockServer([behavior, behavior]) const ctx = await harness(server.url) await expect(assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] })) .rejects.toThrow(`failed with ${status}`) @@ -166,11 +166,6 @@ describe('DeepSeekAdapter against a mock server', () => { assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) .catch((error: unknown) => (error as LlmError).code), ).resolves.toBe(code) - // The numeric HTTP status is carried on the error for explicit handling. - await expect( - assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - .catch((error: unknown) => (error as LlmError).status), - ).resolves.toBe(status) }) it('keeps the status-line message for JSON error bodies without a message', async () => { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index dd1cb5b48c..281a4f13be 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -55,6 +55,6 @@ Unit suites run against a local `node:http` mock SSE server (pi-ai's openai SDK - **`tool_choice` is not mapped** — same MVP contract as llm-deepseek. - **In-history `system`-role messages fold into `user`-role wire messages** — pi-ai exposes a single `systemPrompt` slot, diverging from the hand-rolled twin's `role: 'system'` passthrough. -- **`LlmError.status` is never set** — pi-ai reports failures as in-stream events with no HTTP status, so error codes are regex-classified from the error text. +- **Provider HTTP status is unavailable** — pi-ai reports failures as in-stream events, so stable error codes are regex-classified from the error text. - **`buildModel` hardcodes descriptor metadata** — `contextWindow: 128000`, `maxTokens: 64000`, zero cost, identically for every registered model name; not configurable. - **pi-ai's built-in retries are disabled (`maxRetries: 0`)** — failures surface immediately; retry policy belongs to `llm/stream` listeners. diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 296fd0c3d3..c8f2002f9f 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -42,7 +42,7 @@ Every product adapter sends application identity on provider HTTP requests. `att - `LlmAdapter` — abstract base class for provider adapters. The only required method is `stream()`. - `BlockAssembler` — incrementally assembles raw chunks into complete content blocks and an assistant message. The agent loop feeds it raw chunks (logging them for replay) while reading the assembled blocks/message for history. - `HarnessError` — base class for the harness error taxonomy: a stable `code` string (distinct from the human `message`) plus `cause` chaining. Lives here, in the leaf package every other imports, so a single base is shared without a new dependency edge. Per-package errors (`LlmError`, `ToolArgsError`, `InvariantError`, …) extend it. `isHarnessError(value)` narrows at seams. -- `LlmError` — extends `HarnessError`; `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) plus an optional numeric `status` when the failure came from a non-2xx provider response. +- `LlmError` — extends `HarnessError`; its stable `code` string (`NO_ADAPTER`, `DUPLICATE_ADAPTER`, and adapter codes like `AUTH`/`RATE_LIMIT`) is the programmatic failure contract. ### Real adapters diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 08f3f54c51..8f2c9b4f39 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -42,12 +42,10 @@ declare module 'cordis' { /** * Typed error for LLM-related failures. Extends {@link HarnessError}, so the - * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy; - * `status` carries the HTTP status when the error originated from a non-2xx - * provider response (absent for protocol/usage errors that have no HTTP status). + * `code` string (e.g. `AUTH`, `RATE_LIMIT`, `NO_ADAPTER`) is shared taxonomy. */ export class LlmError extends HarnessError { - constructor(message: string, code: string, public status?: number, options?: ErrorOptions) { + constructor(message: string, code: string, options?: ErrorOptions) { super(message, code, options) this.name = 'LlmError' } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..125a810261 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -79,11 +79,12 @@ describe('LlmService', () => { it('LlmError extends the shared HarnessError base', async () => { const { HarnessError, isHarnessError } = await import('@deepseek-ai/dsh-llm') - const err = new LlmError('boom', 'AUTH', 401) + const cause = new Error('root cause') + const err = new LlmError('boom', 'AUTH', { cause }) expect(err).toBeInstanceOf(HarnessError) expect(isHarnessError(err)).toBe(true) expect(err.code).toBe('AUTH') - expect(err.status).toBe(401) + expect(err.cause).toBe(cause) }) it('HarnessError carries a code, names itself by subclass, and chains cause', async () => { diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 2e509973e5..b7e4e30a46 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -20,7 +20,7 @@ import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' */ export type ReplayEntry = | { kind: 'chunks'; chunks: StreamChunk[] } - | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } + | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string } | { kind: 'hang' } /** Resolved plugin configuration. */ @@ -221,7 +221,7 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) if (signal?.aborted) throw new Error('aborted') yield chunk } - throw new LlmError(entry.message, entry.code, entry.status) + throw new LlmError(entry.message, entry.code) case 'hang': // Replay a stream that stalls until cancelled (mirrors MockAdapter): one // chunk, then wait for abort and surface it as the consumer expects. diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index ac52ec11c9..aa3fea20d5 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -175,7 +175,7 @@ describe('loadReplayScript', () => { it('uses the sidecar override when present, ignoring the JSONL', () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') - const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH', status: 401 }] + const override: ReplayEntry[] = [{ kind: 'throw', chunks: [], message: '401', code: 'AUTH' }] writeFileSync(overrideFile, JSON.stringify(override), 'utf8') expect(loadReplayScript({ file, overrideFile })).toEqual(override) }) @@ -231,12 +231,12 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) }) - it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { + it('replays a sidecar throw-entry as an LlmError with its stable code, after its prefix chunks', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) @@ -245,7 +245,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) - })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) + })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH' }) expect(seen).toEqual(partial) }) @@ -350,7 +350,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const overrideFile = join(dir, 'replay.override.json') const partial: StreamChunk[] = [{ type: 'block-start', index: 0, blockType: 'text' }] writeFileSync(overrideFile, JSON.stringify([ - { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH', status: 401 }, + { kind: 'throw', chunks: partial, message: 'unauthorized', code: 'AUTH' }, ]), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) From f8cc1af99b9b8a5681f93e8939bf8e93f98a4011 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:36:57 +0800 Subject: [PATCH 119/323] test(tasks): align tool fixtures with unified identity --- .../tasks/tool-tasks/tests/tool-tasks.spec.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts index 1b5e221a3c..0a2d89431e 100644 --- a/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts +++ b/packages/tasks/tool-tasks/tests/tool-tasks.spec.ts @@ -5,6 +5,7 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' import TaskService from '@deepseek-ai/dsh-tasks' import type { TaskHooks, TaskOutcome, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' @@ -23,17 +24,17 @@ async function setup(config: ToolTasks.Config = {}) { } /** - * A fake agent whose session token is `sessionId`, registered in `ctx.agents`. - * The agent id is deliberately different so session authorization and exact - * lifecycle ownership cannot be confused in tests. + * A fake agent with the shared agent/session identity, registered in + * `ctx.agents` with a dedicated lifecycle scope. */ function fakeAgent(ctx: Context, sessionId: string, inject: (...args: unknown[]) => void = () => {}): Agent { const scopeFiber = ctx.plugin(() => {}) + const id = SessionId(sessionId) const agent = { - id: `agent-${sessionId}`, + id, ctx: scopeFiber.ctx, inject, - session: { header: { version: 0, id: sessionId, createdAt: 0 } }, + session: { id, header: { version: 0, id, createdAt: 0 } }, } as unknown as Agent agentRegistryDisposers.set(agent, ctx.agents.register(agent)) return agent @@ -276,7 +277,7 @@ describe('completion notices', () => { await tick() // Disposed owner: inject throws the disposed message — contained. - const inject = vi.fn(() => { throw new Error('agent "agent-sess-1" is disposed') }) + const inject = vi.fn(() => { throw new Error('agent "sess-1" is disposed') }) const owner = fakeAgent(ctx, 'sess-1', inject) const p = producer({ owner }) ctx.tasks.start(p.spec) @@ -287,7 +288,7 @@ describe('completion notices', () => { it('does not route an old owner completion notice to a same-session replacement', async () => { const { ctx } = await setup() - const oldInject = vi.fn(() => { throw new Error('agent "agent-shared" is disposed') }) + const oldInject = vi.fn(() => { throw new Error('agent "shared" is disposed') }) const oldOwner = fakeAgent(ctx, 'shared', oldInject) const p = producer({ owner: oldOwner }) ctx.tasks.start(p.spec) From 8e37abb6c9dffa1fa2d5a24d05aa9eef4dde88e3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:50:33 +0800 Subject: [PATCH 120/323] docs: refresh module graph for unified identity --- docs/module-graph.md | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 199f11e8d3..baa714bad1 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -205,6 +205,7 @@ flowchart TD pkg_workflow --> pkg_agent pkg_workflow --> pkg_brand pkg_workflow --> pkg_llm + pkg_workflow --> pkg_session pkg_tools --> pkg_agent pkg_tools --> pkg_code_runtime pkg_tools --> pkg_llm @@ -219,10 +220,6 @@ flowchart TD pkg_permission --> pkg_sandbox pkg_permission --> pkg_session pkg_permission --> pkg_user_approval - pkg_stdio --> pkg_agent - pkg_stdio --> pkg_llm - pkg_stdio --> pkg_session - pkg_stdio --> pkg_user_interaction pkg_agent_loop --> pkg_agent pkg_agent_loop --> pkg_llm pkg_agent_loop --> pkg_scope @@ -250,6 +247,7 @@ flowchart TD pkg_subagent --> pkg_agent pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope + pkg_subagent --> pkg_session pkg_subagent --> pkg_tools pkg_tool_web --> pkg_llm pkg_tool_web --> pkg_system_prompt @@ -296,6 +294,7 @@ flowchart TD pkg_tool_workflow --> pkg_workflow pkg_subagent_acp --> pkg_agent pkg_subagent_acp --> pkg_llm + pkg_subagent_acp --> pkg_session pkg_subagent_acp --> pkg_subagent pkg_subagent_acp --> pkg_subagent_subprocess pkg_subagent_inprocess --> pkg_agent @@ -317,12 +316,18 @@ flowchart TD pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent pkg_subagent_mock --> pkg_llm + pkg_subagent_mock --> pkg_session pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent + pkg_stdio --> pkg_agent + pkg_stdio --> pkg_agent_loop + pkg_stdio --> pkg_llm + pkg_stdio --> pkg_session + pkg_stdio --> pkg_user_interaction pkg_agent_spine_demo --> pkg_agent pkg_agent_spine_demo --> pkg_agent_loop pkg_agent_spine_demo --> pkg_invariants @@ -356,6 +361,7 @@ flowchart TD pkg_acp_demo --> pkg_tools pkg_acp_demo --> pkg_user_interaction pkg_stdio_demo --> pkg_agent + pkg_stdio_demo --> pkg_agent_loop pkg_stdio_demo --> pkg_agent_spine_demo pkg_stdio_demo --> pkg_app_boot pkg_stdio_demo --> pkg_llm @@ -412,16 +418,15 @@ flowchart TD | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`time-context`](../packages/context/time-context) | `context` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt) | | [`tasks`](../packages/tasks/tasks) | `tasks` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) | -| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | +| [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | -| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | @@ -433,15 +438,16 @@ flowchart TD | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | -| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | +| [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | +| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | From 419b0bcf7dfd9c0e88bc15ecf303c9576a92b43f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:51:45 +0800 Subject: [PATCH 121/323] docs: refresh module graph for UI identity --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index baa714bad1..83f98d734e 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -321,6 +321,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_stdio --> pkg_agent @@ -443,7 +444,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | From 828d6004ba35737a5887def0ce3c32b1c84b77ea Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:12 +0800 Subject: [PATCH 122/323] fix(sdk): share generated session identity --- packages/sdk/create-sdk/tests/create.spec.ts | 1 + packages/sdk/helper/src/features/builtin/app.ts | 7 ++++--- .../sdk/helper/src/templates/assets/index.ts.tpl | 14 +++++++------- packages/sdk/helper/tests/project.spec.ts | 15 +++++++++++++-- 4 files changed, 25 insertions(+), 12 deletions(-) diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index 9d75700bb9..04a251351d 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -257,6 +257,7 @@ describe('CreateWizard and scaffolder', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('ctx.agents.create') expect(index).toContain('agentOptions: { model: "deepseek-v4-flash" }') + expect(index).not.toContain('AgentId') const tsconfig = parseGeneratedTsConfig(await readFile(join(target, 'tsconfig.base.json'), 'utf8')) const manifest = parseGeneratedPackageManifest(await readFile(join(target, 'package.json'), 'utf8')) expect(tsconfig.compilerOptions.types).toEqual(['node']) diff --git a/packages/sdk/helper/src/features/builtin/app.ts b/packages/sdk/helper/src/features/builtin/app.ts index a89f2c84ae..e4ff11af20 100644 --- a/packages/sdk/helper/src/features/builtin/app.ts +++ b/packages/sdk/helper/src/features/builtin/app.ts @@ -4,6 +4,7 @@ * @module @deepseek-ai/dsh-helper/features/builtin/app */ +import { JsExpression } from '../../documents/cordis-yaml-file.ts' import { featureId } from '../../ids.ts' import type { ProjectProfile } from '../../project/types.ts' import { @@ -94,11 +95,11 @@ class AppOption extends FeatureOption { name: '@deepseek-ai/dsh-stdio', config: { welcome: 'agent REPL ready. Give it a coding task.', - agent: 'main', + sessionId: new JsExpression('process.env.DSH_SDK_SESSION_ID'), }, - }, ['welcome', 'agent'], config => [ + }, ['welcome', 'sessionId'], config => [ ...optionalString(config, 'welcome'), - ...requiredString(config, 'agent'), + ...config.sessionId instanceof JsExpression ? [] : requiredString(config, 'sessionId'), ]), ]) case 'embed': diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index d0315db80c..4c3099199c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -2,14 +2,12 @@ import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{else}} import { randomUUID } from 'node:crypto' -import { AgentId } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import { startSDK, type SdkBootContext } from '@deepseek-ai/dsh-scripts' {{/if}} /** Boot this project's cordis.yml when invoked by dsh-scripts. */ export async function main(boot: SdkBootContext) { - const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} const model = boot.args.model if (typeof model !== 'string' || model.length === 0) throw new Error('stdio startup requires --model=') @@ -17,24 +15,26 @@ export async function main(boot: SdkBootContext) { if (resume !== undefined && (typeof resume !== 'string' || resume.length === 0)) { throw new Error('stdio startup requires --resume=') } + const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`) + process.env.DSH_SDK_SESSION_ID = sessionId +{{/if}} + const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) +{{#if isStdio}} if (resume === undefined) { await ctx.agents.create({ - agentId: AgentId('main'), - sessionId: SessionId(`main-session-${randomUUID()}`), + sessionId, meta: { cwd: boot.cwd }, agentOptions: { model }, }) } else { await ctx.agents.resume({ - agentId: AgentId('main'), - resumeSessionId: SessionId(resume), + resumeSessionId: sessionId, agentOptions: { model }, }) } {{else}} {{#if isEmbed}} await ctx.agents.create({ - agentId: AgentId('main'), sessionId: SessionId(`main-session-${randomUUID()}`), meta: { cwd: boot.cwd }, agentOptions: { model: {{modelLiteral}} }, diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index d55bb16be9..13fc046a04 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -167,6 +167,10 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('SdkBootContext') expect(index).toContain('agents.create') expect(index).toContain('boot.args.resume') + expect(index).not.toContain('AgentId') + expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') + expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') + expect(index).toContain('resumeSessionId: sessionId') expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', @@ -175,7 +179,11 @@ describe('SdkProject and ProjectEditSession', () => { config: 'dsh-sdk config', }) expect(await readFile(join(project.root, '.env.example'), 'utf8')).toContain('EXA_API_KEY=') - expect(project.cordis.entry('stdio')?.config).toMatchObject({ agent: 'main' }) + expect(project.cordis.entry('stdio')?.config?.sessionId).toMatchObject({ + source: 'process.env.DSH_SDK_SESSION_ID', + }) + expect(await readFile(join(project.root, 'cordis.yml'), 'utf8')) + .toContain('sessionId: !!js process.env.DSH_SDK_SESSION_ID') expect(project.cordis.entry('stdio')?.config).not.toHaveProperty('model') expect(project.cordis.entry('agent-loop')?.config).toEqual({ agents: [] }) expect(project.cordis.entry('system-prompt')?.config?.persona).toContain('{{cwd}}') @@ -286,7 +294,10 @@ describe('SdkProject and ProjectEditSession', () => { const embed = (await embedEdit.commit()).project expect(embed.profile.runInterface).toBe('embed') expect(await readFile(join(embed.root, 'README.md'), 'utf8')).toContain('Embed the harness') - expect(await readFile(join(embed.root, 'index.ts'), 'utf8')).toContain('agents.create') + const embedIndex = await readFile(join(embed.root, 'index.ts'), 'utf8') + expect(embedIndex).toContain('agents.create') + expect(embedIndex).toContain("import { SessionId } from '@deepseek-ai/dsh-session'") + expect(embedIndex).not.toContain('AgentId') await writeFile(join(embed.root, 'README.md'), '# Custom README\n') const modified = await SdkProject.open(embed.root) From 336f4e51ba0b7fe0c79abbd7d617f6597f0fd7fb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:52 +0800 Subject: [PATCH 123/323] docs(acp): align identity routing contract --- packages/ui/acp/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 3650cf27d4..923c0178fa 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. +The plugin injects `agents`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -Forward and reverse indexes route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). +One id-keyed record map plus exact agent-object checks route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). ## Session config options From 2a6fef66ef3d55aff250f31f3d728f15e15f5269 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:52:49 +0800 Subject: [PATCH 124/323] test(agent-loop): remove review bookkeeping --- packages/core/agent-loop/tests/agent.spec.ts | 3 +-- .../tests/contract-regressions.spec.ts | 18 +++++++++--------- 2 files changed, 10 insertions(+), 11 deletions(-) diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7969d18200..91fc1a891d 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -401,8 +401,7 @@ describe('Agent', () => { // The waiter is internal agent state, NOT an effect-scoped ctx.on listener: // disposing the OWNING fiber runs the agent's listener disposers, which would // have dropped a ctx.on-based waiter before the 'disposed' transition and - // hung the promise. With internal waiters, the fiber disposer still settles - // it. Regression for the round-3 whenIdle finding. + // hung the promise. With internal waiters, the fiber disposer still settles it. const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) let agent!: Agent diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index ec2412aff5..00eafa18cb 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -44,7 +44,7 @@ function send(agent: Agent, text: string) { agent.send([{ type: 'text', text }]) } -describe('HIGH: session log records what agent/step-result actually produced', () => { +describe('session log records what agent/step-result actually produced', () => { it('a step-result rewrite is what the log, derived history, and tool dispatch all see', async () => { const adapter = new MockAdapter([textResponse('original'), textResponse('done')]) const ctx = await harness(adapter) @@ -94,7 +94,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( }) }) -describe('HIGH: abort during tool execution ends the turn', () => { +describe('abort during tool execution ends the turn', () => { it('aborting the in-flight step inside a tool prevents both remaining tools and the next model step', async () => { const adapter = new MockAdapter([ // model asks for two tool calls in one step @@ -146,7 +146,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { }) }) -describe('HIGH: steering from late extension points is never stranded', () => { +describe('steering from late extension points is never stranded', () => { it('steer() from an agent/turn-continuation listener overrides a stop decision', async () => { const adapter = new MockAdapter([ textResponse('no tools, would stop here'), @@ -268,7 +268,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { }) }) -describe('HIGH: plugin exceptions are contained', () => { +describe('plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) @@ -323,7 +323,7 @@ describe('HIGH: plugin exceptions are contained', () => { }) }) -describe('MEDIUM: disposed status is part of the agent/status contract', () => { +describe('disposed status is part of the agent/status contract', () => { it('disposing the fiber emits agent/status(disposed) and ends the turn with reason disposed', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) @@ -370,7 +370,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { }) }) -describe('MEDIUM: misc registry and config fixes', () => { +describe('misc registry and config fixes', () => { it('duplicate adapter registration is rejected', async () => { const ctx = new Context() await ctx.plugin(LlmService) @@ -529,7 +529,7 @@ describe('MEDIUM: misc registry and config fixes', () => { }) }) -describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () => { +describe('turn numbering continues across seeded (forked) sessions', () => { it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) @@ -567,7 +567,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () }) }) -describe('LOW: discriminated SessionEvent narrows without casts', () => { +describe('discriminated SessionEvent narrows without casts', () => { it('narrows event.data from event.type', () => { const session = new Session(SessionId('s')) const appended: SessionEvent = session.append('tool/call', { @@ -585,7 +585,7 @@ describe('LOW: discriminated SessionEvent narrows without casts', () => { }) }) -describe('HIGH: a finish-error stream chunk ends the turn as error, not completed', () => { +describe('a finish-error stream chunk ends the turn as error, not completed', () => { it('translates finish {kind:error} into a turn error with a logged error event', async () => { // The second sanctioned adapter error path (besides throwing): an // adapter that cannot throw mid-stream ends the stream with a From 60c4d523d1a868d6766b828a2e5a0771f7c42205 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:59:24 +0800 Subject: [PATCH 125/323] docs(tools): align schema default contract --- packages/core/tools/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index 0f7974e0f9..00bbb67ff5 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -142,7 +142,7 @@ The available tools: - **Native tool calls execute sequentially** — `ToolDefinition` carries no concurrency-safety metadata; adding it (and parallel execution in the loop) waits on the deferred tool-shapes review (`TODO(review)`). - **`tools/pre-execute` deliberately cannot rewrite `exec.arguments`** — logged and rendered args would desync from what ran; the rewrite design is [a proposed RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md). -- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and never applies `default` (`XXX(unused-default)` flags removing that field); raw-registered JSON-Schema tools validate their own input. +- **`defineTool`'s schema DSL is a deliberate subset** — string/number/boolean/object/array with string-only `enum`; `validateArgs` tolerates extra keys and preserves `default` as a model-visible JSON Schema annotation without applying it during validation; dynamic Cordis mounts may supply defaults even though first-party definitions do not, while raw-registered JSON-Schema tools validate their own input. - **`timeoutMs` on a definition is declarative only** — the registry never enforces deadlines; enforcement requires the `@deepseek-ai/dsh-timeout-policy` wrapper. - **Code Mode is TypeScript-only and the presentation mode is service-wide** — `mode: code`/`both` rejects prompt assembly unless `ctx.codeRuntime.language === 'typescript'`; scoped restrictions/shadows still choose each agent's visible bindings, but one tool cannot be native-only while another is code-only. - **Code Mode bindings return text only** — non-text content blocks in a sub-call result collapse to `[ content]` placeholders. From c148090961bf8de680f6b210e5d0532b23c174b8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:07:59 +0800 Subject: [PATCH 126/323] test(sdk): cover invalid generated session ids --- packages/sdk/helper/tests/project.spec.ts | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index 13fc046a04..bfaa8cbf77 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -873,6 +873,12 @@ describe('extension points', () => { resource.kind === 'cordis-config-entry' && resource.entry.id === 'acp') expect(acpEntry?.entry.id).toBe('acp') expect(acpEntry?.validateConfig?.({ model: '' })).toHaveLength(1) + const stdioEntry = builtins.get(featureId('app')).contribution(selection('app', ['stdio']), profile).resources + .find((resource): resource is CordisConfigEntryResource => + resource.kind === 'cordis-config-entry' && resource.entry.id === 'stdio') + expect(stdioEntry?.validateConfig?.({ welcome: 'ready', sessionId: 1 })).toEqual([ + 'sessionId must be a non-empty string', + ]) const embedOption = app.options.find(option => option.id === 'embed') expect(embedOption?.markerConfigEntries(profile)).toEqual([]) expect(embedOption?.contribution(profile, {}).resources.map(resource => resource.kind)).toEqual([ From a6e406a7782303ea5838007e8e85401e95ce4e01 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:16:52 +0800 Subject: [PATCH 127/323] docs(agent-loop): correct identity limitations --- packages/core/agent-loop/README.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 9a165fd66a..6028b2f97f 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -126,7 +126,6 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p ## Known Limitations and Deferred Work - **Tool calls within a step execute sequentially** — parallel execution waits on concurrency-safety metadata in the tool contract (see `dsh-tools`). -- **No resume-or-create policy on the config path** — config-driven `create()` starts a fresh `${id}-session-` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning and creates no agent. +- **Config labels are fresh by default** — omitting `sessionId` creates a fresh `${id}-session-` on every startup; exact resume-or-create behavior requires an explicit stable `sessionId`, while `resumeSessionId` requires existing persisted history. - **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options. - **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin. -- **`runLoop`/`Inbox`/`InboxMessage` stay exported with no outside consumer** — [removal is proposed](../../../docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md). From 1a111654ae13b9dd448cc7166499c45247e20731 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:17:26 +0800 Subject: [PATCH 128/323] docs(subagent): restore local run identity contract --- packages/subagent/subagent/src/types.ts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 67fcc99600..b0f228da96 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -134,9 +134,9 @@ export interface SubagentResult { */ export interface SubagentRun { /** - * Parent-scoped run id. A local run publishes a child session whose - * `parentSession` records `request.parent`; a remote provider mints an id - * unique in the parent namespace. + * Parent-scoped run id. For a local run, this MUST equal the published child + * session id, whose `parentSession` records `request.parent`; a remote + * provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 90220b235fcbdc506c6106a4c33cddd3faebacb1 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:17:46 +0800 Subject: [PATCH 129/323] docs(core): describe the public loop contract --- packages/core/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/README.md b/packages/core/README.md index 921591d85e..fdd8e3669e 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -9,7 +9,7 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | | `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | -| `agent-loop/` | The concrete loop plugin: `ReactLoopAgent` + the loop driver | `ctx.agentLoop` | +| `agent-loop/` | Concrete plugin implementing the public `Agent` contract and owning the loop driver | `ctx.agentLoop` | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. From d56cc8d42417c45c835c2f7576d16bab980eb428 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:00:56 +0800 Subject: [PATCH 130/323] fix(stdio): close startup failure gaps --- .../helper/src/templates/assets/index.ts.tpl | 31 ++++++++++++------- packages/sdk/helper/tests/project.spec.ts | 2 ++ packages/ui/stdio/README.md | 6 ++-- packages/ui/stdio/package.json | 5 +++ 4 files changed, 30 insertions(+), 14 deletions(-) diff --git a/packages/sdk/helper/src/templates/assets/index.ts.tpl b/packages/sdk/helper/src/templates/assets/index.ts.tpl index 4c3099199c..a79818908c 100644 --- a/packages/sdk/helper/src/templates/assets/index.ts.tpl +++ b/packages/sdk/helper/src/templates/assets/index.ts.tpl @@ -20,17 +20,26 @@ export async function main(boot: SdkBootContext) { {{/if}} const ctx = await startSDK(new URL('./cordis.yml', import.meta.url)) {{#if isStdio}} - if (resume === undefined) { - await ctx.agents.create({ - sessionId, - meta: { cwd: boot.cwd }, - agentOptions: { model }, - }) - } else { - await ctx.agents.resume({ - resumeSessionId: sessionId, - agentOptions: { model }, - }) + try { + if (resume === undefined) { + await ctx.agents.create({ + sessionId, + meta: { cwd: boot.cwd }, + agentOptions: { model }, + }) + } else { + await ctx.agents.resume({ + resumeSessionId: sessionId, + agentOptions: { model }, + }) + } + } catch (error) { + try { + await ctx.fiber.dispose() + } catch (disposeError) { + throw new AggregateError([error, disposeError], 'stdio startup and cleanup failed') + } + throw error } {{else}} {{#if isEmbed}} diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index bfaa8cbf77..655b308911 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -171,6 +171,8 @@ describe('SdkProject and ProjectEditSession', () => { expect(index).toContain('const sessionId = SessionId(resume ?? `main-session-${randomUUID()}`)') expect(index).toContain('process.env.DSH_SDK_SESSION_ID = sessionId') expect(index).toContain('resumeSessionId: sessionId') + expect(index).toContain('await ctx.fiber.dispose()') + expect(index).toContain("new AggregateError([error, disposeError], 'stdio startup and cleanup failed')") expect(project.packageManifest().scripts).toEqual({ dev: 'dsh-sdk dev index.ts -- --model="deepseek-v4-flash"', build: 'dsh-sdk build', diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index b7d320880d..f9cebe11e6 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -9,7 +9,7 @@ This package owns the terminal channel only. It injects `agents` and `userIntera | Key | Default | Meaning | |---|---|---| | `welcome` | `ready.` | Banner printed before the first prompt | -| `agent` | `main` | Agent id driven by stdin and observed for EOF shutdown | +| `sessionId` | `main` | Exact agent/session identity driven by stdin and observed for EOF shutdown | The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. Disposal closes readline and unregisters every listener/provider through Cordis effects. @@ -18,7 +18,7 @@ The plugin seeds display labels from the live agent registry, then tracks `agent name: '@deepseek-ai/dsh-stdio' config: welcome: 'agent REPL ready. Give it a coding task.' - agent: main + sessionId: main ``` ## Model Experience @@ -37,6 +37,6 @@ The plugin seeds display labels from the live agent registry, then tracks `agent ## Known Limitations and Deferred Work -- **One configured agent receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `agent` id rather than routing by the visible label. +- **One configured session receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `sessionId` rather than routing by the visible label. - **Terminal questions are text-only and sequential** — the provider queues asks, supports option labels plus custom text, and has no richer UI shapes such as file pickers or diff previews. - **Closed stdin ends the terminal channel** — EOF rejects active or queued questions and exits after submitted work reaches idle; there is no reconnect path for a long-lived process. diff --git a/packages/ui/stdio/package.json b/packages/ui/stdio/package.json index 1c7311d0cb..e1bffdf171 100644 --- a/packages/ui/stdio/package.json +++ b/packages/ui/stdio/package.json @@ -29,6 +29,11 @@ "@deepseek-ai/dsh-user-interaction": "^0.0.1", "cordis": "^4.0.0-rc.7" }, + "peerDependenciesMeta": { + "@deepseek-ai/dsh-agent-loop": { + "optional": true + } + }, "dependencies": { "schemastery": "^3.18.0" }, From 3855a77e7d8b779c74c53cbbe7736a6a29563ba2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:04 +0800 Subject: [PATCH 131/323] docs(approval): qualify audit guarantees --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 9f4968c3a4..0945228593 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. +- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. +- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From 3befcfc566b4deec276d600df993949f6e49facc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:47 +0800 Subject: [PATCH 132/323] Revert "docs(approval): qualify audit guarantees" This reverts commit 14439a93c2bb915441e7b59f505d94a79b22d4af. --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 0945228593..9f4968c3a4 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. +- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. +- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From 70c6c0ac39aacf14ab0b627319b192fd1ca6f03b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:04 +0800 Subject: [PATCH 133/323] docs(approval): qualify audit guarantees --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 9f4968c3a4..0945228593 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. +- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. +- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From c2cf2cbbd846f477e6b3674b095a87e5ed0aa2c0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:05:44 +0800 Subject: [PATCH 134/323] test(agent-loop): name regression contracts --- packages/core/agent-loop/tests/contract-regressions.spec.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 00eafa18cb..098a53261c 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -370,7 +370,7 @@ describe('disposed status is part of the agent/status contract', () => { }) }) -describe('misc registry and config fixes', () => { +describe('registration, request routing, and queued-input ownership contracts', () => { it('duplicate adapter registration is rejected', async () => { const ctx = new Context() await ctx.plugin(LlmService) From b2064cba10f3a0c19ca24472f0ee7d7f81c1816f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 135/323] fix(agent-loop): reject duplicate configured identities --- packages/core/agent-loop/src/index.ts | 22 ++++++++++++++++--- .../tests/config-session-id.spec.ts | 19 ++++++++++++++++ 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 325ba7b92d..7144ae8dfb 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -369,6 +369,24 @@ export interface Config { })[] } +/** Reject self-contained identity conflicts before any configured agent starts. */ +function validateConfiguredAgents(agents: Config['agents']): void { + const exactIdentities = new Map() + for (const { id, sessionId, resumeSessionId } of agents) { + const hasResumeId = resumeSessionId !== undefined && resumeSessionId !== '' + if (sessionId !== undefined && hasResumeId) { + throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) + } + const exactIdentity = hasResumeId ? resumeSessionId : sessionId + if (exactIdentity === undefined) continue + const firstId = exactIdentities.get(exactIdentity) + if (firstId !== undefined) { + throw new Error(`agents "${firstId}" and "${id}" use duplicate exact session identity "${exactIdentity}"`) + } + exactIdentities.set(exactIdentity, id) + } +} + /** Concrete ReactLoopAgent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] @@ -390,6 +408,7 @@ export class AgentLoop extends Service implements AgentFactory { constructor(ctx: Context, public config: Config) { super(ctx, 'agentLoop') + validateConfiguredAgents(config.agents) this.ownership = new FactoryOwnership(ctx.fiber) this.runtime = { ctx } ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()') @@ -412,9 +431,6 @@ export class AgentLoop extends Service implements AgentFactory { } continue } - if (sessionId !== undefined) { - throw new Error(`agent "${id}": sessionId and resumeSessionId are mutually exclusive`) - } ctx.effect(() => { const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index bd2a5522df..56cc0bee40 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -64,6 +64,25 @@ describe('config-driven session id', () => { await conflicting.fiber.dispose() }) + it('rejects duplicate exact ids before asynchronous configured startup', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-duplicate-')) + dirs.push(root) + const ctx = await makeCoreContext() + await ctx.plugin(SessionPersistenceJsonl, { root }) + + const outcome = await ctx.plugin(AgentLoop, { + agents: [ + { id: 'first', sessionId: SessionId('shared'), model: 'mock' }, + { id: 'second', sessionId: SessionId('shared'), model: 'mock' }, + ], + }).then(() => undefined, (error: unknown) => error) + const published = ctx.agents.get(SessionId('shared')) + await ctx.fiber.dispose() + + expect(outcome).toEqual(new Error('agents "first" and "second" use duplicate exact session identity "shared"')) + expect(published).toBeUndefined() + }) + it('restores a materialized exact id across an AgentLoop-only reload', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-exact-reload-')) dirs.push(root) From 042d752fd2ca7f8699011275b03a952935a0a54a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:26:57 +0800 Subject: [PATCH 136/323] docs(repeat-guard): trim module orientation --- packages/guard/repeat-tool-guard/src/index.ts | 37 ++----------------- 1 file changed, 4 insertions(+), 33 deletions(-) diff --git a/packages/guard/repeat-tool-guard/src/index.ts b/packages/guard/repeat-tool-guard/src/index.ts index d51df1d829..bd6c5a4404 100644 --- a/packages/guard/repeat-tool-guard/src/index.ts +++ b/packages/guard/repeat-tool-guard/src/index.ts @@ -1,37 +1,8 @@ /** - * Repeat-tool-call guard: advisory loop-breaker for agents stuck re-issuing - * the same tool call with identical arguments. - * - * Not a model-facing tool — it registers no tool, never vetoes or rewrites a - * call, and adds exactly one behavior: watch each agent's stream of tool calls - * through the `tools/post-execute` waterfall, count runs of consecutive calls - * to the same tool with identical canonicalized arguments, and at configured - * run lengths fold an escalating advisory reminder onto the decision's - * `additionalContext`. The loop appends that context as a logged - * `context/message` after the step's tool results, so the reminder is - * model-visible, source-attributed, and reconstructable from the session log - * with no new session event. Decision record: - * docs/rfc/implemented/feature/2026-07-08-repeat-tool-guard.md. - * - * ```yaml - * - id: repeat-tool-guard - * name: '@deepseek-ai/dsh-repeat-tool-guard' - * config: - * thresholds: [3, 5, 8] # consecutive counts that trigger a reminder - * include: [] # tool-name patterns to track; empty = all tools - * exclude: [todo_write] # tool-name patterns transparent to the chain - * ``` - * - * Chain state is keyed by the live agent object — the tool registry is a - * context-level singleton whose waterfalls interleave every agent's calls, so - * a shared counter would let one agent's repetition trip another's reminder. - * State is in-memory only: a session resumed from persistence starts with a - * fresh chain (the guard is a heuristic nudge, not a logged invariant). - * - * Plugin export shape: named exports, NO default. The cordis Loader's - * `unwrapExports` does `exports.default ?? exports`, so a stray default would - * collapse the module to the bare `apply` (see docs/postmortem/0001). - * + * Advisory per-agent repeat-call detector. It enriches post-execute decisions + * with logged model context without vetoing or rewriting calls. Configuration + * and chain semantics live in the package README; rationale lives in the + * repeat-tool-guard RFC. * @module @deepseek-ai/dsh-repeat-tool-guard */ From 68b5c716b1265590f5f2936c33f9760b12c8d1db Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:08 +0800 Subject: [PATCH 137/323] docs(catalog): refresh AgentLoop source link --- docs/cordis-catalog/services.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 85e07f8191..f83f2bf616 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:373`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:391`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From b77cfd64a1cba70c1c2168d370aeab3108989a12 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:29:32 +0800 Subject: [PATCH 138/323] docs(catalog): refresh repeat guard source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 46645b0575..29d37dd6db 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -548,7 +548,7 @@ export interface Config { } ``` -Source: [`packages/guard/repeat-tool-guard/src/index.ts:55`](../packages/guard/repeat-tool-guard/src/index.ts) +Source: [`packages/guard/repeat-tool-guard/src/index.ts:26`](../packages/guard/repeat-tool-guard/src/index.ts) ## `@deepseek-ai/dsh-sandbox-local` From 69c36e4fb5a6bceff4f44a8ba81ee8deb68fc1e8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:20 +0800 Subject: [PATCH 139/323] docs(subagent): name parent session lineage --- packages/subagent/subagent/src/types.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index b0f228da96..e5ba8fd84d 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -135,8 +135,8 @@ export interface SubagentResult { export interface SubagentRun { /** * Parent-scoped run id. For a local run, this MUST equal the published child - * session id, whose `parentSession` records `request.parent`; a remote - * provider mints an id unique in the parent namespace. + * session id, whose `parentSession` records `request.parent.session.id`; a + * remote provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 9366baf39fd84f169e1df7f42048088b5cc0c790 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:26 +0800 Subject: [PATCH 140/323] docs(acp): describe session terminal rendering --- packages/ui/acp/src/index.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 8bb25df579..d9c53cebf0 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1049,7 +1049,7 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void { * zero or more times per event (best-effort UI feed, never load-bearing). * @param presenter - resolves tool-owned render intent for tool events; * defaults to the generic-fallback {@link nullToolPresenter}. - * @param terminal - the connection's terminal-rendering context; defaults to + * @param terminal - the session's terminal-rendering context; defaults to * disabled (the plain-text console-block fallback). * @param options - `includeUserMessages` (default `true`): live streaming * passes `false` so a prompt the client just sent is not echoed back. @@ -1122,7 +1122,7 @@ export function todosToPlan(todos: TodoItem[]): Plan { } /** - * Per-connection terminal-rendering context threaded into + * Per-session terminal-rendering context threaded into * {@link streamSessionEventUpdate}: whether the client advertised the * `_meta.terminal_output` capability, and the session's workspace cwd (the * default terminal-card header when a tool doesn't supply its own). Kept out of From 2f1a40d9381aea67badc63f7c1d30e5cda5c0f02 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:35:31 +0800 Subject: [PATCH 141/323] docs(catalog): refresh AgentLoop source link --- docs/cordis-catalog/services.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 7cc00a407a..44490c39f0 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -19,7 +19,9 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Source: [`packages/core/agent-loop/src/index.ts:391`](../../packages/core/agent-loop/src/index.ts) +Types: [Agent](../core-data-structures/core.md) + +Source: [`packages/core/agent-loop/src/index.ts:390`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` From 4c08629b58ef493da1a02e0dcff9eed4d4eb1980 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:56:12 +0800 Subject: [PATCH 142/323] docs(acp): describe concurrent update routing --- packages/ui/acp/src/index.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index d9c53cebf0..7b5cb11324 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -20,11 +20,12 @@ * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; * every `session/event` and `agent/*` event is routed strictly to its owning - * session record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts use the same identity: the - * bridge answers `approval/request` for its own agents over - * `session/request_permission` (see the approval answerer below) — whether a - * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. + * session record, and each `session/update` carries that id. Concurrent updates + * may alternate on the shared connection without crossing session attribution. + * Permission prompts use the same identity: the bridge answers + * `approval/request` for its own agents over `session/request_permission` (see + * the approval answerer below) — whether a call ASKS is policy (a hook or + * plugin returning `ask`), not the bridge's. * * stdout is the protocol: this plugin must run in an example that loads NO * stdout logger (the console logger writes to stdout and would corrupt the @@ -483,8 +484,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // whose end arrives late is ignored (see // SessionRecord.inflight). A turn that ends `error` REJECTS the prompt (ACP // has no error stop reason); other reasons resolve via the codec. Demux - // strictly by session id: a `session/event` is routed to its own record, so - // two sessions streaming at once never cross-settle or interleave updates. + // strictly by session id: concurrent updates may alternate on the shared + // connection, but they retain the owning id and never cross-settle. ctx.on('session/event', (session, event: SessionEvent) => { const rec = sessions.get(session.header.id) if (rec === undefined) return From 486362d2f8a6de1aee998cee320046d5c3db1a8d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:57:32 +0800 Subject: [PATCH 143/323] docs(catalog): refresh ACP config source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4300404cfb..cb5aebbdf8 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:244`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:245`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` From f7af6a87dcf06397bb66b91fd851572e31385815 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 03:25:21 +0800 Subject: [PATCH 144/323] docs(acp): describe terminal capability lifetime --- packages/ui/acp/src/index.ts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 7b5cb11324..a12249d0b5 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -359,10 +359,10 @@ export function apply(ctx: Context, config: AcpConfig): void { // await and NOT install a record (which would resurrect a live agent/listeners // after the bridge closed). Checked after every load await. let closed = false - // Whether the client advertised the Zed `_meta.terminal_output` capability in - // `initialize`. When true, a tool's terminal presentation is rendered as a - // terminal card (content + `_meta.terminal_*`); when false, the bridge uses - // the tool's text fallback. Set once in `initialize`, read on every tool event. + // Connection-level terminal capability from the latest `initialize`; false + // before initialization. Each `session/new` or `session/load` snapshots it in + // `SessionRecord.terminalEnabled`, so later initialization affects only future + // sessions. let terminalOutputCap = false // Assigned at the bottom, before any agent event can fire (a session only From d027ea0d1003b22f36c389bf126c7dd47a598981 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 15:10:45 +0800 Subject: [PATCH 145/323] refactor(compact-basic): inline automatic listeners into the service Fold automatic.ts into BasicCompactService as a private _registerAutomaticCompaction method, removing the AutomaticCompactor structural interface the standalone module needed to avoid an import cycle. Listener behavior is unchanged; compactIfNeeded stays dynamically dispatched so subclass overrides are honored at event time. --- .../compact/compact-basic/src/automatic.ts | 85 ------------------- packages/compact/compact-basic/src/index.ts | 68 ++++++++++++++- 2 files changed, 66 insertions(+), 87 deletions(-) delete mode 100644 packages/compact/compact-basic/src/automatic.ts diff --git a/packages/compact/compact-basic/src/automatic.ts b/packages/compact/compact-basic/src/automatic.ts deleted file mode 100644 index e837e076cc..0000000000 --- a/packages/compact/compact-basic/src/automatic.ts +++ /dev/null @@ -1,85 +0,0 @@ -/** - * Automatic post-step pressure and context-overflow recovery listeners. - * - * @module @deepseek-ai/dsh-compact-basic/automatic - */ - -import type { Context } from 'cordis' -import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' -import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' -import { - TOKEN_METER_MODEL_UNCONFIGURED, - TokenMeterError, -} from '@deepseek-ai/dsh-token-meter' -import type { Agent } from '@deepseek-ai/dsh-agent' - -interface AutomaticCompactor { - readonly config: { readonly maxOverflowRetries: number } - compactIfNeeded( - agent: Agent, - trigger: CompactionTrigger, - signal: AbortSignal, - ): Promise -} - -/** - * Register the implementation-owned automatic compaction listener. - * @param ctx - context owning the listener effect and logger. - * @param service - compactor whose public methods remain dynamically dispatched. - */ -export function registerAutomaticCompaction( - ctx: Context, - service: AutomaticCompactor, -): void { - const logResult = (result: CompactionResult, trigger: string): void => { - ctx.logger.info( - `compaction (${trigger}): shadowed ${result.shadowedSeqs.length} surface nodes ` - + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` - + `~${result.shadowedTokenCount} tokens)`, - ) - } - - ctx.on('agent/post-step', async ( - agent: Agent, - _turn: number, - _step: number, - signal: AbortSignal, - ) => { - if (signal.aborted) return - try { - const result = await service.compactIfNeeded(agent, 'pressure', signal) - if (result !== null) logResult(result, 'post-step pressure') - } catch (error: unknown) { - // A named routed model without a meter profile is configuration failure, - // not an optional operational compaction miss. - if (error instanceof TokenMeterError - && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error - const message = error instanceof Error ? error.message : String(error) - ctx.logger.warn(`post-step compaction failed: ${message}; continuing the turn`) - } - }) - - ctx.on('agent/request-error', async (agent, _turn, _step, error, retryAttempt, signal, next) => { - if (error.code !== CONTEXT_WINDOW_EXCEEDED_CODE - || retryAttempt >= service.config.maxOverflowRetries - || signal.aborted) return next() - - let generation: number - let result: CompactionResult | null - try { - generation = agent.session.surface.replaceGeneration - result = await service.compactIfNeeded(agent, 'context-overflow', signal) - } catch (recoveryError: unknown) { - const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError) - ctx.logger.warn( - `context-overflow compaction failed: ${message}; preserving the original request error`, - ) - return next() - } - // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited. - if (signal.aborted || result === null - || agent.session.surface.replaceGeneration <= generation) return next() - logResult(result, 'context overflow recovery') - return { action: 'retry' } - }) -} diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index d420851166..64f8586bac 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -9,10 +9,14 @@ import z from 'schemastery' import { CompactService } from '@deepseek-ai/dsh-compact' import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' import type { Session } from '@deepseek-ai/dsh-session' +import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { + TOKEN_METER_MODEL_UNCONFIGURED, + TokenMeterError, +} from '@deepseek-ai/dsh-token-meter' import type { ModelTokenMeter } from '@deepseek-ai/dsh-token-meter' import type { Agent } from '@deepseek-ai/dsh-agent' -import { registerAutomaticCompaction } from './automatic.ts' import { resolveConfig, resolveModelConfig } from './config.ts' import { compactSurfaceRegion, selectCompactableRange } from './region.ts' import { summarizeWithLlm } from './summarizer.ts' @@ -72,7 +76,67 @@ export class BasicCompactService extends CompactService { constructor(ctx: Context, config: BasicCompactConfig = {}) { super(ctx) this.config = resolveConfig(config, ctx.tokenMeter) - if (this.config.auto) registerAutomaticCompaction(ctx, this) + if (this.config.auto) this._registerAutomaticCompaction() + } + + /** + * Register the automatic post-step pressure and context-overflow recovery + * listeners. `compactIfNeeded` stays dynamically dispatched so subclass + * overrides are honored at event time. + */ + private _registerAutomaticCompaction(): void { + const { ctx } = this + const logResult = (result: CompactionResult, trigger: string): void => { + ctx.logger.info( + `compaction (${trigger}): shadowed ${result.shadowedSeqs.length} surface nodes ` + + `(seqs ${result.shadowedRange.start}-${result.shadowedRange.end}, ` + + `~${result.shadowedTokenCount} tokens)`, + ) + } + + ctx.on('agent/post-step', async ( + agent: Agent, + _turn: number, + _step: number, + signal: AbortSignal, + ) => { + if (signal.aborted) return + try { + const result = await this.compactIfNeeded(agent, 'pressure', signal) + if (result !== null) logResult(result, 'post-step pressure') + } catch (error: unknown) { + // A named routed model without a meter profile is configuration failure, + // not an optional operational compaction miss. + if (error instanceof TokenMeterError + && error.code === TOKEN_METER_MODEL_UNCONFIGURED) throw error + const message = error instanceof Error ? error.message : String(error) + ctx.logger.warn(`post-step compaction failed: ${message}; continuing the turn`) + } + }) + + ctx.on('agent/request-error', async (agent, _turn, _step, error, retryAttempt, signal, next) => { + if (error.code !== CONTEXT_WINDOW_EXCEEDED_CODE + || retryAttempt >= this.config.maxOverflowRetries + || signal.aborted) return next() + + let generation: number + let result: CompactionResult | null + try { + generation = agent.session.surface.replaceGeneration + result = await this.compactIfNeeded(agent, 'context-overflow', signal) + } catch (recoveryError: unknown) { + const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError) + ctx.logger.warn( + `context-overflow compaction failed: ${message}; preserving the original request error`, + ) + return next() + } + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited. + if (signal.aborted || result === null + || agent.session.surface.replaceGeneration <= generation) return next() + logResult(result, 'context overflow recovery') + return { action: 'retry' } + }) } /** From 8d35092e267102827a3153d0f113f838571e7b34 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 16:12:27 +0800 Subject: [PATCH 146/323] fix(examples): isolate headless agent example --- README.i18n.yaml | 4 +- README.md | 2 +- README.zh.md | 2 +- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/graph-atlas.md | 1 + docs/testing.md | 4 +- examples/README.md | 10 +- examples/acp-agent/README.md | 2 +- .../advanced-headless.cordis.snapshot.yml | 32 ------ examples/coding-agent/README.md | 18 +--- examples/coding-agent/cli.cordis.yml | 24 ----- .../tests/fixtures/cli.cordis.yml | 24 ----- examples/headless-agent/README.md | 24 +++++ .../advanced.cordis.snapshot.yml | 12 +++ examples/headless-agent/advanced.cordis.yml | 22 +++++ examples/headless-agent/composition.md | 70 +++++++++++++ examples/headless-agent/cordis.yml | 97 +++++++++++++++++++ examples/headless-agent/package.json | 7 ++ .../tests/fixtures/cli-mock-llm.ts | 2 +- .../tests/fixtures/cli.cordis.yml | 17 ++++ .../tests/headless.snapshot.ts | 2 +- .../tests/keyless-smoke.e2e.ts} | 6 +- .../tests/real-model.e2e.ts} | 8 +- .../snapshots/advanced-toolchain/input.json | 7 ++ .../advanced-toolchain/session.1.jsonl | 13 +++ .../advanced-toolchain/session.2.jsonl | 13 +++ .../advanced-toolchain/session.jsonl | 64 ++++++++++++ .../stream-json.golden.jsonl | 20 ++-- knip.json | 3 +- package.json | 2 +- packages/examples/cli-demo/README.md | 6 +- packages/examples/cli-demo/package.json | 2 +- packages/support/llm-replay/README.md | 2 +- packages/support/loader-smoke/README.md | 2 +- scripts/gen-doc-graphs.ts | 10 ++ vitest.snapshot.config.ts | 8 +- 38 files changed, 410 insertions(+), 140 deletions(-) delete mode 100644 examples/acp-agent/advanced-headless.cordis.snapshot.yml delete mode 100644 examples/coding-agent/cli.cordis.yml delete mode 100644 examples/coding-agent/tests/fixtures/cli.cordis.yml create mode 100644 examples/headless-agent/README.md create mode 100644 examples/headless-agent/advanced.cordis.snapshot.yml create mode 100644 examples/headless-agent/advanced.cordis.yml create mode 100644 examples/headless-agent/composition.md create mode 100644 examples/headless-agent/cordis.yml create mode 100644 examples/headless-agent/package.json rename examples/{coding-agent => headless-agent}/tests/fixtures/cli-mock-llm.ts (95%) create mode 100644 examples/headless-agent/tests/fixtures/cli.cordis.yml rename examples/{acp-agent => headless-agent}/tests/headless.snapshot.ts (98%) rename examples/{coding-agent/tests/cli-keyless-smoke.e2e.ts => headless-agent/tests/keyless-smoke.e2e.ts} (93%) rename examples/{coding-agent/tests/cli.e2e.ts => headless-agent/tests/real-model.e2e.ts} (83%) create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/input.json create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl create mode 100644 examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl rename examples/{acp-agent => headless-agent}/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl (92%) diff --git a/README.i18n.yaml b/README.i18n.yaml index 15992ac276..5fa4727e00 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 4d2d2c20a27aff67d42a4555f4e0ce410dd5d6d7 -README.zh.md: 0fb307653f978143b851ef4822d93714910043af +README.md: f3b602b070f32101ebab5e11d95e4d49f7ad77a2 +README.zh.md: 0e77269c121f7e95e71bc50855f6df8da9807651 diff --git a/README.md b/README.md index 4d2d2c20a2..f3b602b070 100644 --- a/README.md +++ b/README.md @@ -12,7 +12,7 @@ This monorepo is built on the [Cordis](https://github.com/cordiverse/cordis) fra pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) -pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # headless-agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/README.zh.md b/README.zh.md index 0fb307653f..0e77269c12 100644 --- a/README.zh.md +++ b/README.zh.md @@ -12,7 +12,7 @@ pnpm install pnpm run test # vitest pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) -pnpm run demo:headless -- "task" # one-shot agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:headless -- "task" # headless-agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 207ea114e0..ce6b8a5316 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 3474bc116b43f9be57b52e947f9cf99730f7e796 -extension-cookbook.zh.md: 1a605b20fe4e171a948ac2a046193a2f4d884e44 +extension-cookbook.md: 9d583a484fca89810bf1e7062fe9aab5b2a2da5e +extension-cookbook.zh.md: afb6edee56be5aeec22957acb903a6ac3a869856 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 3474bc116b..9d583a484f 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## Runnable wirings -Three complete examples load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool — the all-mock skeleton check, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + the bash tool suite behind a terminal REPL UI, `pnpm run demo:repl`), and [`examples/acp-agent`](../../examples/acp-agent) (an agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, `pnpm run demo:acp`). Each leaf is just its swappable backends plus an app-package entry: the stdio demos load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP demo loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine via the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle. +Five complete examples load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool — the all-mock skeleton check, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + coding tools behind a terminal REPL, `pnpm run demo:repl`), [`examples/headless-agent`](../../examples/headless-agent) (the same capability class behind a one-shot positional task and DSH-native output, `pnpm run demo:headless -- "task"`), [`examples/cordis-agent`](../../examples/cordis-agent) (the self-referential runtime-inspection demo, `pnpm run demo:cordis`), and [`examples/acp-agent`](../../examples/acp-agent) (an agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, `pnpm run demo:acp`). Each leaf is its swappable backends plus one app-package entry: the stdio demos load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the headless demo loads [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo), the ACP demo loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and all three app packages share the spine through [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo). ## The feature → mechanism map diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 1a605b20fe..afb6edee56 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## 可运行的组装示例 -三个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + bash 工具套件，配合终端 REPL UI，`pnpm run demo:repl`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子只是其可替换后端加一个 app 包入口：stdio 演示加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 演示加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle 共享主干。 +五个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + coding 工具，配合终端 REPL，`pnpm run demo:repl`）、[`examples/headless-agent`](../../examples/headless-agent)（同类能力通过单次位置任务和 DSH 原生输出运行，`pnpm run demo:headless -- "task"`）、[`examples/cordis-agent`](../../examples/cordis-agent)（自引用的运行时检查演示，`pnpm run demo:cordis`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子由其可替换后端加一个 app 包入口组成：stdio 演示加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，headless 演示加载 [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo)，ACP 演示加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，三个 app 包都通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) 共享主干。 ## 功能→机制映射 diff --git a/docs/graph-atlas.md b/docs/graph-atlas.md index 60de01ef81..6645fb5ef9 100644 --- a/docs/graph-atlas.md +++ b/docs/graph-atlas.md @@ -14,6 +14,7 @@ The process decision behind this index is recorded in [the documentation graph R | [capability seams and core services](capability-seams.md) | `hybrid generated` | | [echo-agent app composition](../examples/echo-agent/composition.md) | `hybrid generated` | | [coding-agent app composition](../examples/coding-agent/composition.md) | `hybrid generated` | +| [headless-agent app composition](../examples/headless-agent/composition.md) | `hybrid generated` | | [cordis-agent app composition](../examples/cordis-agent/composition.md) | `hybrid generated` | | [acp-agent app composition](../examples/acp-agent/composition.md) | `hybrid generated` | | [event producer/consumer matrix](event-producer-consumer.md) | `hybrid generated` | diff --git a/docs/testing.md b/docs/testing.md index 8d318ebd60..cf7343f8d9 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -7,7 +7,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): real example subprocesses replay recorded model sessions keylessly and compare normalized stdout plus re-persisted logs ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). The primary suite pins ACP JSON-RPC; the headless projection reuses `advanced-toolchain` for `stream-json`. Use `pnpm run test:snapshot:record` when the model transcript changes and `pnpm run test:snapshot:refresh` when only replay outputs change; review the golden diff. One scenario per header class pins system-prompt/tool-schema content; other fixtures tokenize it ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): real example subprocesses replay recorded model sessions keylessly and compare normalized stdout plus re-persisted logs ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). `examples/acp-agent` pins ACP JSON-RPC, while `examples/headless-agent` independently pins its `stream-json` event surface. Use `pnpm run test:snapshot:record` when an ACP model transcript changes and `pnpm run test:snapshot:refresh` when replay outputs change; review the golden diff. One ACP scenario per header class pins system-prompt/tool-schema content; other ACP fixtures tokenize it ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here @@ -30,4 +30,4 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword ## When a snapshot test is required -A change affecting an editor transcript, headless event stream, or agent UX adds or updates the owning `examples//tests/snapshots/` scenario, or explains its omission in the PR. `examples/acp-agent` hosts the primary [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) table and the headless `stream-json` projection. Plans for new capability seams, lifecycle shapes, or transcript surfaces identify every test tier and any required harness work before implementation. +A change affecting an editor transcript, headless event stream, or agent UX adds or updates the owning `examples//tests/snapshots/` scenario, or explains its omission in the PR. `examples/acp-agent` owns the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) table; `examples/headless-agent` owns the `stream-json` snapshot and its replay fixtures. Plans for new capability seams, lifecycle shapes, or transcript surfaces identify every test tier and any required harness work before implementation. diff --git a/examples/README.md b/examples/README.md index 399769992f..2ee6d3eee9 100644 --- a/examples/README.md +++ b/examples/README.md @@ -17,10 +17,16 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. The UI is a terminal readline REPL. -Run interactively with `pnpm run demo:repl`, or run one headless task with `pnpm run demo:headless -- "task"` (both need `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. +Run with `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. +## headless-agent + +A non-interactive agent demo that accepts one positional task, runs one complete model/tool turn on the `@deepseek-ai/dsh-cli-demo` app, persists a fresh session, prints `text`, `json`, or `stream-json`, and exits. + +Run with: `pnpm run demo:headless -- "task"` (needs `DEEPSEEK_API_KEY`). See [headless-agent/README.md](headless-agent/README.md) for the wire contract, mutation and token risks, and the headless-owned snapshot suite. + ## cordis-agent The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one `cordis-dynamic` fiber subtree. The `ctx.fs`/`ctx.web` services ride along provider-only, as the capabilities those plugins build on. @@ -29,7 +35,7 @@ Run with: `pnpm run demo:cordis` (needs `DEEPSEEK_API_KEY`). See [cordis-agent/R ## acp-agent -An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC stdio, via the [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) app — drive it from Zed or any other ACP client. Also the home of the keyless snapshot tests. +An agent demo exposed as an **Agent Client Protocol (ACP)** server over JSON-RPC stdio, via the [`@deepseek-ai/dsh-acp-demo`](../packages/examples/acp-demo) app — drive it from Zed or any other ACP client. It owns the ACP keyless snapshot suite. Run with: `pnpm run demo:acp` (needs `DEEPSEEK_API_KEY`); `pnpm run demo:code-mode acp` boots the same server in Code Mode via the `code-mode.cordis.yml` overlay. See [acp-agent/README.md](acp-agent/README.md) for the Zed setup and the snapshot-test design. diff --git a/examples/acp-agent/README.md b/examples/acp-agent/README.md index 427b924d45..000f693941 100644 --- a/examples/acp-agent/README.md +++ b/examples/acp-agent/README.md @@ -33,7 +33,7 @@ The editor sets each session's `cwd` to the project it opens, and bash uses that ## Snapshot tests (record-once / replay-deterministic) -This example hosts the ACP snapshot suite and the headless `stream-json` snapshot. Both replay through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. The headless snapshot reuses `advanced-toolchain` to pin the one-shot stream plus its re-persisted parent and child logs; child activity appears in the stream only through parent tool events. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. +This example hosts the ACP snapshot suite. It replays through `dsh-llm-replay`, which reconstructs model streams from `assistant/chunk` events in each scenario's session JSONL. Recording runs the real ACP agent and harvests its logs; refresh keeps the committed transcript as mock input and rewrites current replay outputs. `replay.override.json` covers throw and hang cases that chunks cannot express, and an optional `workspace/` seeds files. The [snapshot RFC](../../docs/rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md) owns the ACP harness design. ## Permissions and sandboxing diff --git a/examples/acp-agent/advanced-headless.cordis.snapshot.yml b/examples/acp-agent/advanced-headless.cordis.snapshot.yml deleted file mode 100644 index 5047635ddb..0000000000 --- a/examples/acp-agent/advanced-headless.cordis.snapshot.yml +++ /dev/null @@ -1,32 +0,0 @@ -# Replay the advanced toolchain through the headless one-shot front door. It -# receives this replay config explicitly; unlike the ACP bin, it does not swap -# a live config for a sibling snapshot overlay. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - id: acp-agent - name: '@deepseek-ai/dsh-acp-demo' - disabled: true - - insert: - - id: cli-agent - name: '@deepseek-ai/dsh-cli-demo' - config: - model: deepseek-v4-flash - persistenceRoot: './.sessions' - tools: - mode: both - persona: | - You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. - - Verify your work by running the code or tests. Keep answers brief and factual. - - id: code-runtime - name: '@deepseek-ai/dsh-code-runtime-worker' - - id: tool-cordis - name: '@deepseek-ai/dsh-tool-cordis' - - id: llm-replay - name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index cf47fb2a85..8dfff33f8b 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -1,6 +1,6 @@ # coding-agent -Coding-agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + workflows + `todo_write` + JSONL persistence. `cordis.yml` runs the terminal readline REPL; `cli.cordis.yml` keeps the same coding capabilities behind a headless one-shot CLI. +Coding-agent REPL wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + workflows + `todo_write` + JSONL persistence. ## Run it @@ -21,20 +21,6 @@ Type a coding task. The agent works through the `read`/`write`/`edit` filesystem … ``` -### One-shot CLI - -Run one task through all model and tool steps, flush its fresh session, print the final result, and exit: - -```sh -pnpm run demo:headless -- "fix the failing test in this workspace" -pnpm run demo:headless --output-format json -- "summarize the current implementation" -pnpm run demo:headless --output-format stream-json -- "run the focused tests" -``` - -The root command supplies `cli.cordis.yml`, which disables HMR and the REPL app and inserts [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo). Exactly one quoted positional task is required; there is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Non-completed turns retain partial output but exit nonzero; argument and boot failures leave stdout empty. - -This is non-interactive automation with the same local bash, filesystem, skill, subagent, workflow, and todo capabilities as the REPL. It can mutate the launch workspace and spend provider tokens. No prompt, approval, resume, further turn, or stdin context is available in v1; see the [CLI package contract](../../packages/examples/cli-demo/README.md). - ### Resuming a prior session Each run starts a fresh session by default (its event log lands under `./.sessions/`). To **continue** a previous conversation, set `RESUME_SESSION_ID` to that session's id — the `main` agent then rehydrates the persisted log instead of starting fresh, so the model sees the earlier turns as history: @@ -83,4 +69,4 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads - `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so the auto-compaction listener fires MID-SESSION. Verifies the WORLD — a `compact/start…end` pair landed in the real log, the surface shrank (a replace node shadowed older nodes), and the agent still produced a correct final answer after compaction. - `tests/todo-write.e2e.ts` — a real model drives the real `todo_write` tool and the test verifies the resulting `todo/write` session event. -These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. `tests/cli.e2e.ts` runs the one-shot bin with a real model and verifies its temporary file externally. The keyless Loader smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts`, `tests/code-mode-keyless-smoke.e2e.ts`, and `tests/cli-keyless-smoke.e2e.ts`; the CLI smoke mocks only the LLM boundary and asserts a real bash round trip plus persisted stream output. +These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. The keyless Loader smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts` and `tests/code-mode-keyless-smoke.e2e.ts`. diff --git a/examples/coding-agent/cli.cordis.yml b/examples/coding-agent/cli.cordis.yml deleted file mode 100644 index 5a58dfd889..0000000000 --- a/examples/coding-agent/cli.cordis.yml +++ /dev/null @@ -1,24 +0,0 @@ -# One-shot headless overlay: keep the coding capabilities from `cordis.yml`, -# replace its REPL app with the stdout-pure CLI app, and disable dev-only HMR. -- id: base - name: '@cordisjs/plugin-include' - config: - path: ./cordis.yml - patches: - - id: hmr - name: '@cordisjs/plugin-hmr' - disabled: true - - id: stdio-agent - name: '@deepseek-ai/dsh-stdio-demo' - disabled: true - - insert: - - id: cli-agent - name: '@deepseek-ai/dsh-cli-demo' - config: - model: deepseek-v4-flash - persistenceRoot: './.sessions' - persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. - - Verify your work by running the code or tests. Keep answers brief and - factual. diff --git a/examples/coding-agent/tests/fixtures/cli.cordis.yml b/examples/coding-agent/tests/fixtures/cli.cordis.yml deleted file mode 100644 index bdec0154c4..0000000000 --- a/examples/coding-agent/tests/fixtures/cli.cordis.yml +++ /dev/null @@ -1,24 +0,0 @@ -- id: cli-mock-llm - name: './cli-mock-llm.ts' - -- id: base - name: '@cordisjs/plugin-include' - config: - path: ../../cordis.yml - patches: - - id: hmr - name: '@cordisjs/plugin-hmr' - disabled: true - - id: llm-deepseek - name: '@deepseek-ai/dsh-llm-deepseek' - disabled: true - - id: stdio-agent - name: '@deepseek-ai/dsh-stdio-demo' - disabled: true - - insert: - - id: cli-agent - name: '@deepseek-ai/dsh-cli-demo' - config: - model: cli-mock - persistenceRoot: './.sessions' - persona: 'Keyless CLI smoke.' diff --git a/examples/headless-agent/README.md b/examples/headless-agent/README.md new file mode 100644 index 0000000000..5c21855afe --- /dev/null +++ b/examples/headless-agent/README.md @@ -0,0 +1,24 @@ +# headless-agent + +Headless one-shot agent wiring: DeepSeek V4 + local bash and filesystem tools + subagent delegation + workflows + `todo_write` + JSONL persistence, with [`@deepseek-ai/dsh-cli-demo`](../../packages/examples/cli-demo) as the app front door. + +## Run it + +```sh +# repo root .env (gitignored) or exported env: +# DEEPSEEK_API_KEY=sk-… +# DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API +pnpm run demo:headless -- "fix the failing test in this workspace" +pnpm run demo:headless --output-format json -- "summarize the implementation" +pnpm run demo:headless --output-format stream-json -- "run the focused tests" +``` + +Exactly one nonblank positional task is required; quote tasks containing spaces. There is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Child sessions surface only through parent tool events and results. + +Each invocation creates and persists a fresh session, runs all model and tool steps in one turn, flushes, disposes, and exits. This is non-interactive automation: there is no prompt, approval, resume, second turn, or stdin context. The configured tools can mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. + +## Advanced and snapshot wiring + +[`advanced.cordis.yml`](advanced.cordis.yml) adds Code Mode and the Cordis tools to the shipped leaf. [`advanced.cordis.snapshot.yml`](advanced.cordis.snapshot.yml) replaces only the live LLM with replay. The tests under [`tests/`](tests/) own the keyless real-Loader smoke, key-gated world-verified smoke, and the `stream-json` replay snapshot with its parent and child session fixtures. + +The package-level [CLI contract](../../packages/examples/cli-demo/README.md) documents output records, exit status, cancellation, persistence, and model/token effects. diff --git a/examples/headless-agent/advanced.cordis.snapshot.yml b/examples/headless-agent/advanced.cordis.snapshot.yml new file mode 100644 index 0000000000..48541a1054 --- /dev/null +++ b/examples/headless-agent/advanced.cordis.snapshot.yml @@ -0,0 +1,12 @@ +# Replay counterpart to advanced.cordis.yml; only the live model is replaced. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./advanced.cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - insert: + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' diff --git a/examples/headless-agent/advanced.cordis.yml b/examples/headless-agent/advanced.cordis.yml new file mode 100644 index 0000000000..646bd8a11c --- /dev/null +++ b/examples/headless-agent/advanced.cordis.yml @@ -0,0 +1,22 @@ +# Add Code Mode and Cordis tools to the headless spawn/workflow stack. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ./cordis.yml + patches: + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + tools: + mode: both + persona: | + You are headless-agent, a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. + + Verify your work by running the code or tests. Keep answers brief and factual. + - insert: + - id: code-runtime + name: '@deepseek-ai/dsh-code-runtime-worker' + - id: tool-cordis + name: '@deepseek-ai/dsh-tool-cordis' diff --git a/examples/headless-agent/composition.md b/examples/headless-agent/composition.md new file mode 100644 index 0000000000..9a734fa2f0 --- /dev/null +++ b/examples/headless-agent/composition.md @@ -0,0 +1,70 @@ + + +# Headless Agent App Composition + +The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted main session. + +```mermaid +flowchart LR + cfg["examples/headless-agent
cordis.yml"] + plugin_headless_llm_deepseek["llm-deepseek
@deepseek-ai/dsh-llm-deepseek"] + cfg --> plugin_headless_llm_deepseek + plugin_headless_bash["bash
@deepseek-ai/dsh-bash-local"] + cfg --> plugin_headless_bash + plugin_headless_cli_agent["cli-agent
@deepseek-ai/dsh-cli-demo"] + cfg --> plugin_headless_cli_agent + plugin_headless_cli_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] + plugin_headless_cli_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] + plugin_headless_cli_agent --> frontdoor_cli["one-shot driver
format-pure stdout
pre-created main agent"] + bundle_agent_core --> spine_llm["ctx.llm"] + bundle_agent_core --> spine_sessions["ctx.sessions"] + bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] + bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] + plugin_headless_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] + cfg --> plugin_headless_compact_basic + plugin_headless_subagent["subagent
@deepseek-ai/dsh-subagent"] + cfg --> plugin_headless_subagent + plugin_headless_subagent_spawn["subagent-spawn
@deepseek-ai/dsh-subagent-spawn"] + cfg --> plugin_headless_subagent_spawn + plugin_headless_subagent_fork["subagent-fork
@deepseek-ai/dsh-subagent-fork"] + cfg --> plugin_headless_subagent_fork + plugin_headless_tool_subagent["tool-subagent
@deepseek-ai/dsh-tool-subagent"] + cfg --> plugin_headless_tool_subagent + plugin_headless_tool_subagent_fork["tool-subagent-fork
@deepseek-ai/dsh-tool-subagent"] + cfg --> plugin_headless_tool_subagent_fork + plugin_headless_workflow_workerthread["workflow-workerthread
@deepseek-ai/dsh-workflow-workerthread"] + cfg --> plugin_headless_workflow_workerthread + plugin_headless_tool_workflow["tool-workflow
@deepseek-ai/dsh-tool-workflow"] + cfg --> plugin_headless_tool_workflow + plugin_headless_tool_todo["tool-todo
@deepseek-ai/dsh-tool-todo"] + cfg --> plugin_headless_tool_todo + plugin_headless_fs_local["fs-local
@deepseek-ai/dsh-fs-local"] + cfg --> plugin_headless_fs_local + plugin_headless_fs_policy["fs-policy
@deepseek-ai/dsh-fs-policy"] + cfg --> plugin_headless_fs_policy + plugin_headless_tool_fs["tool-fs
@deepseek-ai/dsh-tool-fs"] + cfg --> plugin_headless_tool_fs +``` + +| Plugin id | Package / module | +| --- | --- | +| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` | +| `bash` | `@deepseek-ai/dsh-bash-local` | +| `cli-agent` | `@deepseek-ai/dsh-cli-demo` | +| `compact-basic` | `@deepseek-ai/dsh-compact-basic` | +| `subagent` | `@deepseek-ai/dsh-subagent` | +| `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | +| `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` | +| `tool-subagent` | `@deepseek-ai/dsh-tool-subagent` | +| `tool-subagent-fork` | `@deepseek-ai/dsh-tool-subagent` | +| `workflow-workerthread` | `@deepseek-ai/dsh-workflow-workerthread` | +| `tool-workflow` | `@deepseek-ai/dsh-tool-workflow` | +| `tool-todo` | `@deepseek-ai/dsh-tool-todo` | +| `fs-local` | `@deepseek-ai/dsh-fs-local` | +| `fs-policy` | `@deepseek-ai/dsh-fs-policy` | +| `tool-fs` | `@deepseek-ai/dsh-tool-fs` | + +Source config: [`examples/headless-agent/cordis.yml`](cordis.yml). + +Maintenance mode: hybrid: the leaf plugin list is parsed from its `cordis.yml`; app package expansion is curated from package source. diff --git a/examples/headless-agent/cordis.yml b/examples/headless-agent/cordis.yml new file mode 100644 index 0000000000..3cf1d127a2 --- /dev/null +++ b/examples/headless-agent/cordis.yml @@ -0,0 +1,97 @@ +# One-shot coding agent with format-pure stdout. The app bin loads the +# gitignored root `.env`; this file reads `DEEPSEEK_API_KEY` and optional +# `DEEPSEEK_BASE_URL` through `!!js`. + +# The DeepSeek adapter. Swap to '@deepseek-ai/dsh-llm-pi-ai' for the pi-ai-backed +# twin (same config shape; `reasoning: high` replaces thinking/reasoningEffort). +- id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + baseURL: !!js process.env.DEEPSEEK_BASE_URL + models: + - deepseek-v4-pro + - deepseek-v4-flash + +# Local executor for the app bundle's bash tool. +- id: bash + name: '@deepseek-ai/dsh-bash-local' + config: + timeoutMs: 60000 + +# The app bundle pre-creates one fresh `main` agent per invocation. +- id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: deepseek-v4-flash + persistenceRoot: './.sessions' + persona: | + You are headless-agent, a coding assistant powered by the {{model}} model. + + Verify your work by running the code or tests. Keep answers brief and + factual. + +# Summarize an older range when derived history approaches the context window. +- id: compact-basic + name: '@deepseek-ai/dsh-compact-basic' + config: + contextWindow: 128000 + thresholdRatio: 0.8 + retainTokens: 20480 + summarizationModel: '' + maxTokens: 8192 + compactionRetries: 1 + +# Expose fresh-child `spawn` and completed-prefix `fork` through independent +# in-process backends. +- id: subagent + name: '@deepseek-ai/dsh-subagent' + +- id: subagent-spawn + name: '@deepseek-ai/dsh-subagent-spawn' + config: + providerName: spawn + +- id: subagent-fork + name: '@deepseek-ai/dsh-subagent-fork' + config: + providerName: fork + +- id: tool-subagent + name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: spawn + toolName: subagent + +- id: tool-subagent-fork + name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: fork + toolName: subagent_fork + +# The worker-thread workflow engine fans a model-written JavaScript script's +# `agent()` calls out through the spawn backend. +- id: workflow-workerthread + name: '@deepseek-ai/dsh-workflow-workerthread' + config: + provider: spawn + +- id: tool-workflow + name: '@deepseek-ai/dsh-tool-workflow' + +# `todo_write` replaces the logged whole list. +- id: tool-todo + name: '@deepseek-ai/dsh-tool-todo' + +# Policy loads before the model-facing filesystem tools so writes and edits +# require an observed file. Relative paths resolve from the process cwd. +- id: fs-local + name: '@deepseek-ai/dsh-fs-local' + config: + cwd: !!js process.cwd() + +- id: fs-policy + name: '@deepseek-ai/dsh-fs-policy' + +- id: tool-fs + name: '@deepseek-ai/dsh-tool-fs' diff --git a/examples/headless-agent/package.json b/examples/headless-agent/package.json new file mode 100644 index 0000000000..c331af0f05 --- /dev/null +++ b/examples/headless-agent/package.json @@ -0,0 +1,7 @@ +{ + "name": "headless-agent-example", + "private": true, + "version": "0.0.1", + "type": "module", + "description": "Runnable demo: one complete headless coding-agent turn" +} diff --git a/examples/coding-agent/tests/fixtures/cli-mock-llm.ts b/examples/headless-agent/tests/fixtures/cli-mock-llm.ts similarity index 95% rename from examples/coding-agent/tests/fixtures/cli-mock-llm.ts rename to examples/headless-agent/tests/fixtures/cli-mock-llm.ts index 6447ba1e18..5238e67374 100644 --- a/examples/coding-agent/tests/fixtures/cli-mock-llm.ts +++ b/examples/headless-agent/tests/fixtures/cli-mock-llm.ts @@ -1,7 +1,7 @@ import type { Context } from 'cordis' import { CallId, LlmAdapter, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' -/** Keyless coding smoke adapter: one real bash call followed by a final answer. */ +/** Keyless headless-agent adapter: one real bash call followed by a final answer. */ class CliMockAdapter extends LlmAdapter { async * stream(options: GenerateOptions): AsyncIterable { const toolResult = options.messages.at(-1)?.content.find(block => block.type === 'tool-result') diff --git a/examples/headless-agent/tests/fixtures/cli.cordis.yml b/examples/headless-agent/tests/fixtures/cli.cordis.yml new file mode 100644 index 0000000000..7e042789b2 --- /dev/null +++ b/examples/headless-agent/tests/fixtures/cli.cordis.yml @@ -0,0 +1,17 @@ +- id: cli-mock-llm + name: './cli-mock-llm.ts' + +- id: base + name: '@cordisjs/plugin-include' + config: + path: ../../cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: cli-agent + name: '@deepseek-ai/dsh-cli-demo' + config: + model: cli-mock + persistenceRoot: './.sessions' + persona: 'Keyless headless-agent smoke.' diff --git a/examples/acp-agent/tests/headless.snapshot.ts b/examples/headless-agent/tests/headless.snapshot.ts similarity index 98% rename from examples/acp-agent/tests/headless.snapshot.ts rename to examples/headless-agent/tests/headless.snapshot.ts index a38931a8ef..ff27347246 100644 --- a/examples/acp-agent/tests/headless.snapshot.ts +++ b/examples/headless-agent/tests/headless.snapshot.ts @@ -14,7 +14,7 @@ const snapshotsDir = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') const scenarioDir = join(snapshotsDir, 'advanced-toolchain') const sessionFixture = join(scenarioDir, 'session.jsonl') const streamGolden = join(scenarioDir, 'stream-json.golden.jsonl') -const configPath = fileURLToPath(new URL('../advanced-headless.cordis.snapshot.yml', import.meta.url)) +const configPath = fileURLToPath(new URL('../advanced.cordis.snapshot.yml', import.meta.url)) const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) const refreshing = process.env.DSH_SNAPSHOT === 'refresh' diff --git a/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts b/examples/headless-agent/tests/keyless-smoke.e2e.ts similarity index 93% rename from examples/coding-agent/tests/cli-keyless-smoke.e2e.ts rename to examples/headless-agent/tests/keyless-smoke.e2e.ts index c2d0f3f946..57b8660c03 100644 --- a/examples/coding-agent/tests/cli-keyless-smoke.e2e.ts +++ b/examples/headless-agent/tests/keyless-smoke.e2e.ts @@ -8,12 +8,12 @@ const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src const configPath = fileURLToPath(new URL('./fixtures/cli.cordis.yml', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) -describe('coding-agent one-shot CLI keyless smoke', () => { +describe('headless-agent keyless smoke', () => { it('boots the real Loader tree, runs a real bash tool round trip, and persists the turn', async () => { let persisted = false const { stdout, stderr } = await runLoaderSmoke({ - label: 'coding-agent CLI', - tempDirPrefix: 'coding-cli-smoke-', + label: 'headless-agent', + tempDirPrefix: 'headless-agent-smoke-', binScript, configPath, binArgs: ['--config', configPath, '--output-format', 'stream-json', 'prove the tool path'], diff --git a/examples/coding-agent/tests/cli.e2e.ts b/examples/headless-agent/tests/real-model.e2e.ts similarity index 83% rename from examples/coding-agent/tests/cli.e2e.ts rename to examples/headless-agent/tests/real-model.e2e.ts index a05e19fc06..653f5ab624 100644 --- a/examples/coding-agent/tests/cli.e2e.ts +++ b/examples/headless-agent/tests/real-model.e2e.ts @@ -5,16 +5,16 @@ import { describe, expect, it } from 'vitest' import { runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' const binScript = fileURLToPath(new URL('../../../packages/examples/cli-demo/src/bin.ts', import.meta.url)) -const configPath = fileURLToPath(new URL('../cli.cordis.yml', import.meta.url)) +const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) const hasKey = Boolean(process.env.DEEPSEEK_API_KEY) -describe.skipIf(!hasKey)('coding-agent one-shot CLI with real model', () => { +describe.skipIf(!hasKey)('headless-agent with real model', () => { it('modifies a temporary workspace and verifies the file outside the agent', async () => { let verified = '' const { stdout } = await runLoaderSmoke({ - label: 'coding-agent CLI real model', - tempDirPrefix: 'coding-cli-real-', + label: 'headless-agent real model', + tempDirPrefix: 'headless-agent-real-', binScript, configPath, binArgs: [ diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/input.json b/examples/headless-agent/tests/snapshots/advanced-toolchain/input.json new file mode 100644 index 0000000000..41072a211a --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK." } + ] +} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl new file mode 100644 index 0000000000..95924ff6c6 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -0,0 +1,13 @@ +{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} +{"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl new file mode 100644 index 0000000000..5e4387ccb7 --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -0,0 +1,13 @@ +{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} +{"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl new file mode 100644 index 0000000000..a1785105cd --- /dev/null +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -0,0 +1,64 @@ +{"type":"session","version":0,"id":"11111111-1111-4111-8111-111111111111","createdAt":1783950000000,"cwd":"/tmp/advanced-headless"} +{"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} +{"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":1783950000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"tool/call","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}} +{"type":"tool/result","seq":11,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} +{"type":"step/end","seq":12,"time":1783957884489,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":13,"time":1783957884489,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":14,"time":1783950000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":15,"time":1783950000016,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}} +{"type":"assistant/chunk","seq":16,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} +{"type":"assistant/chunk","seq":17,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":18,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} +{"type":"tool/call","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}} +{"type":"tool/code-dispatch","seq":21,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}} +{"type":"tool/result","seq":22,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"} +{"type":"step/end","seq":23,"time":1783957884561,"data":{"turn":1,"step":2}} +{"type":"step/start","seq":24,"time":1783957884562,"data":{"turn":1,"step":3}} +{"type":"assistant/chunk","seq":25,"time":1783950000026,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":26,"time":1783950000027,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}} +{"type":"assistant/chunk","seq":27,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":28,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":29,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} +{"type":"tool/call","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}} +{"type":"tool/result","seq":32,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1783957884593,"data":{"turn":1,"step":3}} +{"type":"step/start","seq":34,"time":1783957884594,"data":{"turn":1,"step":4}} +{"type":"assistant/chunk","seq":35,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":36,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}} +{"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}} +{"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} +{"type":"tool/call","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}} +{"type":"tool/result","seq":42,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"} +{"type":"step/end","seq":43,"time":1783957884718,"data":{"turn":1,"step":4}} +{"type":"step/start","seq":44,"time":1783957884718,"data":{"turn":1,"step":5}} +{"type":"assistant/chunk","seq":45,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":46,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}} +{"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}} +{"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} +{"type":"tool/call","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}} +{"type":"tool/result","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} +{"type":"step/end","seq":53,"time":1783957884719,"data":{"turn":1,"step":5}} +{"type":"step/start","seq":54,"time":1783957884720,"data":{"turn":1,"step":6}} +{"type":"assistant/chunk","seq":55,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":56,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_HEADLESS_OK"}}} +{"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_HEADLESS_OK"}}}} +{"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} +{"type":"step/end","seq":61,"time":1783957884721,"data":{"turn":1,"step":6}} +{"type":"turn/end","seq":62,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl similarity index 92% rename from examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl rename to examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl index ea5eca3765..35aad5fc89 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl @@ -1,5 +1,5 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} @@ -34,13 +34,13 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":33,"time":0,"data":{"turn":1,"step":3}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":34,"time":0,"data":{"turn":1,"step":4}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":35,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":36,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":42,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":42,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":43,"time":0,"data":{"turn":1,"step":4}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":44,"time":0,"data":{"turn":1,"step":5}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":45,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} @@ -54,11 +54,11 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":53,"time":0,"data":{"turn":1,"step":5}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":54,"time":0,"data":{"turn":1,"step":6}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":55,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":56,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":56,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_HEADLESS_OK"}}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_HEADLESS_OK"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":58,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":59,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":61,"time":0,"data":{"turn":1,"step":6}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":62,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} -{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"ADVANCED_ACP_OK","reason":{"kind":"completed"},"usage":{"inputTokens":18,"outputTokens":18}} +{"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"ADVANCED_HEADLESS_OK","reason":{"kind":"completed"},"usage":{"inputTokens":18,"outputTokens":18}} diff --git a/knip.json b/knip.json index 0d367d84a6..348500575c 100644 --- a/knip.json +++ b/knip.json @@ -9,7 +9,8 @@ "examples/echo-agent/src/*.ts", "examples/echo-agent/tests/**/*.e2e.ts", "examples/coding-agent/tests/**/*.e2e.ts", - "examples/coding-agent/tests/fixtures/*.ts", + "examples/headless-agent/tests/**/*.e2e.ts", + "examples/headless-agent/tests/fixtures/*.ts", "examples/cordis-agent/tests/**/*.e2e.ts", "examples/acp-agent/tests/**/*.e2e.ts", "examples/*/tests/**/*.snapshot.ts" diff --git a/package.json b/package.json index 2bf8506bf8..b3e13479f0 100644 --- a/package.json +++ b/package.json @@ -74,7 +74,7 @@ "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", - "demo:headless": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/coding-agent/cli.cordis.yml", + "demo:headless": "node --expose-internals --import tsx packages/examples/cli-demo/src/bin.ts --config examples/headless-agent/cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md index 38c38cf69c..5334a5bcd9 100644 --- a/packages/examples/cli-demo/README.md +++ b/packages/examples/cli-demo/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-cli-demo -Headless one-shot app and bin for running one coding-agent task without a readline or editor client. The app composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and one fresh `main` agent; the bin submits one task, waits through all model and tool steps, emits the selected result, disposes to quiescence, and exits. +Headless one-shot app and bin for running one agent task without a readline or editor client. The app composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and one fresh `main` agent; the bin submits one task, waits through all model and tool steps, emits the selected result, disposes to quiescence, and exits. The package mounts no console logger, readline UI, user-interaction service, or `ask_user_question` tool. Stdout is reserved for the selected output format; diagnostics use stderr. @@ -25,7 +25,7 @@ dsh-cli-demo [--config path] [--output-format text|json|stream-json] `--config` defaults to `./cordis.yml`; `--output-format` defaults to `text`. Exactly one nonblank positional task is required, so quote tasks containing spaces. `--help` prints usage without booting. There is no `-p` or `--print` flag. -The root coding demo supplies its overlay: +The root headless-agent example supplies its leaf: ```sh pnpm run demo:headless -- "inspect the failing test and fix it" @@ -45,7 +45,7 @@ The task turn is explicitly flushed before final output. Session logs remain und ## Operational safety -The coding overlay retains local bash, filesystem, skill, subagent, workflow, and todo capabilities. A task can therefore mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. Run the CLI from the intended project directory, review the leaf's capability and sandbox configuration, and do not treat non-interactive execution as an approval boundary. +The headless-agent leaf supplies local bash, filesystem, skill, subagent, workflow, and todo capabilities. A task can therefore mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. Run the CLI from the intended project directory, review the leaf's capability and sandbox configuration, and do not treat non-interactive execution as an approval boundary. ## Model Experience diff --git a/packages/examples/cli-demo/package.json b/packages/examples/cli-demo/package.json index 3268f9733f..5f6d5d04c2 100644 --- a/packages/examples/cli-demo/package.json +++ b/packages/examples/cli-demo/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-cli-demo", - "description": "Headless one-shot coding-agent app with text and DSH-native JSON output", + "description": "Headless one-shot agent app with text and DSH-native JSON output", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index 847064b160..704173cf52 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -2,7 +2,7 @@ A replay LLM plugin for keyless snapshot tests. It installs a single `llm/stream` waterfall listener that short-circuits the waterfall (never calls `next()`) and yields model streams reconstructed from a recorded **session JSONL** fixture — so a test can boot the real agent against a fixed model transcript with no API key. -Its consumer is the ACP snapshot harness in `examples/acp-agent`, which loads this plugin (via `cordis.snapshot.yml`) in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate). +Its consumers are the ACP snapshot harness in `examples/acp-agent` and the `stream-json` snapshot in `examples/headless-agent`; each loads this plugin in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate). ## How the fixture works diff --git a/packages/support/loader-smoke/README.md b/packages/support/loader-smoke/README.md index 4527be6430..7514babb8a 100644 --- a/packages/support/loader-smoke/README.md +++ b/packages/support/loader-smoke/README.md @@ -4,7 +4,7 @@ Shared subprocess harness for keyless example smokes that boot a real app bin an Successful runs return stdout and stderr only after a zero exit. Non-zero exits and deadlines reject with both captured streams. `LOADER_SMOKE_TEST_TIMEOUT_MS` leaves Vitest enough room for the process-owned diagnostic timeout to fire first. -This is support-tier test infrastructure, not product API. The consumers are the Loader-path smokes under `examples/{echo-agent,coding-agent,cordis-agent}`. +This is support-tier test infrastructure, not product API. The consumers are the Loader-path smokes under `examples/{echo-agent,coding-agent,headless-agent,cordis-agent}`. ## Model Experience diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5996cd203e..505921ab40 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -409,6 +409,14 @@ const APP_EXAMPLES = [ config: 'examples/coding-agent/cordis.yml', summary: 'The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', }, + { + id: 'headless', + rel: 'examples/headless-agent/composition.md', + title: 'Headless Agent App Composition', + label: 'examples/headless-agent', + config: 'examples/headless-agent/cordis.yml', + summary: 'The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted main session.', + }, { id: 'cordis', rel: 'examples/cordis-agent/composition.md', @@ -944,6 +952,7 @@ function renderIndex(docs: GraphDoc[]): string { 'docs/capability-seams.md': 'capability seams and core services', 'examples/echo-agent/composition.md': 'echo-agent app composition', 'examples/coding-agent/composition.md': 'coding-agent app composition', + 'examples/headless-agent/composition.md': 'headless-agent app composition', 'examples/cordis-agent/composition.md': 'cordis-agent app composition', 'examples/acp-agent/composition.md': 'acp-agent app composition', 'docs/event-producer-consumer.md': 'event producer/consumer matrix', @@ -955,6 +964,7 @@ function renderIndex(docs: GraphDoc[]): string { 'docs/capability-seams.md': 'hybrid generated', 'examples/echo-agent/composition.md': 'hybrid generated', 'examples/coding-agent/composition.md': 'hybrid generated', + 'examples/headless-agent/composition.md': 'hybrid generated', 'examples/cordis-agent/composition.md': 'hybrid generated', 'examples/acp-agent/composition.md': 'hybrid generated', 'docs/event-producer-consumer.md': 'hybrid generated', diff --git a/vitest.snapshot.config.ts b/vitest.snapshot.config.ts index dbc51eae41..772bbf3f72 100644 --- a/vitest.snapshot.config.ts +++ b/vitest.snapshot.config.ts @@ -1,10 +1,10 @@ import tsconfigPaths from 'vite-tsconfig-paths' import { defineConfig } from 'vitest/config' -// Replay is the keyless default: boot the real ACP subprocess from recorded model scripts and diff -// normalized transcript plus persisted-log goldens. `record` calls the real API and updates fixtures -// and goldens; `refresh` replays committed scripts and updates only current goldens. Replay/refresh -// never load `.env`; only record reads a key from the environment or gitignored root `.env`. +// Replay is the keyless default: boot real example subprocesses from recorded model scripts and diff +// normalized protocol/event output plus persisted-log goldens. ACP `record` calls the real API and +// updates fixtures and goldens; `refresh` replays committed scripts and updates current goldens. +// Replay/refresh never load `.env`; only record reads a key from the environment or root `.env`. if (process.env.DSH_SNAPSHOT === 'record') { try { process.loadEnvFile(new URL('.env', import.meta.url).pathname) From 231aeabe55f3d58b5f02cd0f9a1495c529613db9 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 17:11:41 +0800 Subject: [PATCH 147/323] docs(compact): align recovery RFC with singleton meter --- ...compaction-pressure-and-overflow-recovery.i18n.yaml | 4 ++-- ...r-call-compaction-pressure-and-overflow-recovery.md | 10 +++++----- ...all-compaction-pressure-and-overflow-recovery.zh.md | 10 +++++----- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index dbb9c76bbf..7cfb11d29d 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 92167dc7d444a3620abfbaab721260ed1c828db9 -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: fe3b6617b25a58ef2c1c311df088f9c805fe9ef4 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 7d68bc32d3860bf5edd94c4eda76922c91ae6af2 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 2315bd4d9ca9b93eb9a8d4850f917e6aa1bc6476 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index 92167dc7d4..7d68bc32d3 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -18,7 +18,7 @@ Successful calls are not the only pressure signal. A provider can reject a reque The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after assistant output, every dispatched or synthetic tool result, post-tool context, and steering are durable, but before `step/end`. This placement gives pressure policy the complete successful-call state without splitting an assistant tool call from its result. A listener failure is an ordinary turn failure; it never enters model-request recovery. -`dsh-compact-basic` resolves the exact latest routed model from the durable request header and asks that model's `ctx.tokenMeter` handle to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work. A durable unknown model throws `TOKEN_METER_MODEL_UNCONFIGURED` with its exact name and fails the otherwise-successful turn; operational selection or summarization failures warn and continue with full history. +`dsh-compact-basic` reads the exact latest routed model from the durable request header only to establish that a completed route exists, then asks the singleton `ctx.tokenMeter` to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work; any durable non-empty model name uses the same estimator. Operational measurement or summarization failures warn and continue with full history. ### Request recovery is limited to the final model boundary @@ -32,11 +32,11 @@ If cancellation lands after assistant tool calls are durable but before all call `CompactService.compactIfNeeded(agent, trigger, signal)` accepts `trigger: 'pressure' | 'context-overflow'`. The interface gains no estimation methods or token types; `ctx.tokenMeter` remains the reusable accounting owner. -For `pressure`, compact-basic applies the selected meter profile's threshold and retained-tail policy, compares scalar and surface `logRevision`, and uses the same meter for range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. +For `pressure`, compact-basic applies the service-wide threshold and retained-tail policy to one unified `ctx.tokenMeter.measure()` result. The same singleton meter owns range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It chooses the maximal tool-balanced head range while leaving the newest indivisible unit, then attempts exactly one shrinking compaction under the same signal. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` only when compaction succeeds and the generation increases. A backend returning a result without replacement cannot authorize retry. -`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, missing or unknown routed models, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. +`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, a missing routed model, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. The default summarizer still resolves explicit configuration, then the latest logged route, then agent options. Because direct `llm/stream` middleware may reroute that auxiliary call, `compact/summary.model` records the final mutable `GenerateOptions.model` observed after dispatch rather than the pre-waterfall candidate. @@ -44,7 +44,7 @@ The default summarizer still resolves explicit configuration, then the latest lo Lifecycle tests pin post-step ordering after durable tool/context/steering work, content-less and max-token successes, final-adapter dispatch/iterator/in-band boundaries, retry numbering, attempt reset, cancellation, disposal, synthetic tool results, and original error identity. -Compact tests pin low-friction defaults, actual routed-model selection, exact unknown-model behavior, below-threshold forced overflow, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. +Compact tests pin low-friction service-wide defaults, actual routed-model selection, unlisted-model measurement, unified pressure-and-retention decisions, below-threshold forced overflow, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. ## Alternatives considered @@ -52,7 +52,7 @@ Compact tests pin low-friction defaults, actual routed-model selection, exact un - **Retry the same numbered step** — rejected because recovery appends durable events after the failed boundary. A new step preserves balanced nesting and reconstructability. - **Retry whenever `compactIfNeeded` returns a result** — rejected because a custom backend can report success without changing model-visible state. `replaceGeneration` is the authoritative proof. - **Let compact-basic parse provider wording** — rejected because classification belongs at adapters and must cover both thrown and in-band delivery. -- **Use a universal model/window fallback during recovery** — rejected because destructive policy under the wrong context capacity can hide the original provider failure. Unknown durable routes delegate unchanged. +- **Fall back to `AgentOptions.model` when no durable route exists** — rejected because automatic policy must describe a completed logged request. Headerless pressure and recovery delegate unchanged. ## Consequences diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index fe3b6617b2..2315bd4d9c 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -18,7 +18,7 @@ Status: implemented 循环在 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都持久化之后、`step/end` 之前，触发等待式串行 `agent/post-step(agent, turn, step, signal)`。该位置让压力策略看到完整的成功调用状态，同时不会拆开 assistant 工具调用与其结果。监听器失败属于普通 turn 失败，绝不会进入模型请求恢复。 -`dsh-compact-basic` 从持久请求头解析精确的最新实际路由模型，并让该模型的 `ctx.tokenMeter` handle 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作。持久记录的未知模型会携带精确名称抛出 `TOKEN_METER_MODEL_UNCONFIGURED`，使原本成功的 turn 失败；操作性的选择或摘要失败则警告并继续使用完整历史。 +`dsh-compact-basic` 从持久请求头读取精确的最新实际路由模型，只用它确认已经存在完整路由，随后让单例 `ctx.tokenMeter` 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作；任意持久记录的非空模型名都使用同一个估算器。操作性的计量或摘要失败会发出警告，并继续使用完整历史。 ### 请求恢复只覆盖最终模型边界 @@ -32,11 +32,11 @@ Status: implemented `CompactService.compactIfNeeded(agent, trigger, signal)` 接收 `trigger: 'pressure' | 'context-overflow'`。接口不增加估算方法或 token 类型；`ctx.tokenMeter` 继续作为可复用的核算所有者。 -对于 `pressure`，compact-basic 应用所选 meter profile 的阈值与保留尾部策略，比较标量和表层的 `logRevision`，并用同一个 meter 完成范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 +对于 `pressure`，compact-basic 把服务级阈值与保留尾部策略应用到一次统一的 `ctx.tokenMeter.measure()` 结果。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它在保留最新不可分割单元的同时，选择最大的工具配对平衡头部范围，并在同一 signal 下只尝试一次缩小压缩。自动监听器先记录 `session.surface.replaceGeneration`，只有压缩成功且 generation 增加时才返回 `{ action: 'retry' }`。后端若只返回结果但没有替换表层，不能授权重试。 -`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失或未知路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 +`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 默认摘要器仍依次解析显式配置、最近记录的路由与 agent options。因为直接 `llm/stream` 中间件可以重新路由该辅助调用，`compact/summary.model` 记录分发后最终可变的 `GenerateOptions.model`，而不是 waterfall 之前的候选值。 @@ -44,7 +44,7 @@ Status: implemented 生命周期测试固定 post-step 位于持久工具、上下文与 steering 工作之后，覆盖无内容与达到 token 上限的成功、最终适配器分发/迭代器/带内边界、重试编号、尝试重置、取消、销毁、合成工具结果与原始错误身份。 -压缩测试固定低摩擦默认值、实际路由模型选择、精确未知模型行为、低于阈值的强制溢出、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 +压缩测试固定低摩擦服务级默认值、实际路由模型选择、未列出模型计量、统一压力与保留决策、低于阈值的强制溢出、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 ## 考虑过的替代方案 @@ -52,7 +52,7 @@ Status: implemented - **重试相同编号的 step**——不予采纳，因为恢复会在失败边界之后追加持久事件。新 step 保持边界配对与可重建性。 - **只要 `compactIfNeeded` 返回结果就重试**——不予采纳，因为自定义后端可能报告成功却没有改变模型可见状态。`replaceGeneration` 才是权威证明。 - **让 compact-basic 解析提供方措辞**——不予采纳，因为分类属于适配器，而且必须同时覆盖抛出式与带内交付。 -- **恢复时使用通用模型/窗口回退**——不予采纳，因为基于错误上下文容量执行破坏性策略可能掩盖原始提供方失败。未知持久路由会原样委托。 +- **没有持久路由时回退到 `AgentOptions.model`**——不予采纳，因为自动策略必须描述已完成且已记录的请求。没有请求头的压力检查与恢复会原样委托。 ## 后果 From ce96104a774120c72097d8a89755ec1eb3cfb001 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 18:02:15 +0800 Subject: [PATCH 148/323] feat(compact): prune tool results before summarization (round 1) --- docs/agent-lifecycle.md | 2 +- docs/architecture.md | 3 +- docs/capability-seams.md | 5 + docs/config-catalog.md | 16 ++ docs/cordis-catalog/services.md | 14 ++ docs/core-data-structures/compaction.md | 2 +- docs/module-graph.md | 7 +- ...n-pressure-and-overflow-recovery.i18n.yaml | 4 +- ...mpaction-pressure-and-overflow-recovery.md | 8 +- ...ction-pressure-and-overflow-recovery.zh.md | 8 +- .../2026-06-18-compaction-capability-seam.md | 15 +- docs/tool-catalog.md | 4 +- examples/coding-agent/README.md | 3 +- examples/coding-agent/composition.md | 5 +- examples/coding-agent/cordis.yml | 4 + examples/coding-agent/tests/harness.ts | 2 + packages/compact/README.md | 5 +- packages/compact/compact-basic/README.md | 9 +- packages/compact/compact-basic/package.json | 7 + packages/compact/compact-basic/src/index.ts | 24 +- .../compact-basic/tests/compact-basic.spec.ts | 147 +++++++++++ .../tests/loader-composition.spec.ts | 10 +- packages/compact/compact-basic/tsconfig.json | 3 +- packages/compact/tool-result-prune/README.md | 50 ++++ .../compact/tool-result-prune/package.json | 40 +++ .../compact/tool-result-prune/src/config.ts | 77 ++++++ .../compact/tool-result-prune/src/index.ts | 157 ++++++++++++ .../compact/tool-result-prune/src/types.ts | 40 +++ .../tests/loader-composition.spec.ts | 67 +++++ .../tests/tool-result-prune.spec.ts | 237 ++++++++++++++++++ .../compact/tool-result-prune/tsconfig.json | 15 ++ .../cordis/tool-cordis/src/api-catalog.ts | 17 ++ .../core/tools/tests/gen-tool-catalog.spec.ts | 5 + packages/support/invariants/README.md | 2 +- packages/support/invariants/src/index.ts | 11 + .../invariants/tests/invariants.spec.ts | 45 ++++ pnpm-lock.yaml | 31 +++ python/sdk-runtime/package.json | 1 + scripts/gen-doc-graphs.ts | 12 +- scripts/gen-tool-catalog.ts | 29 ++- tsconfig.build.json | 1 + tsconfig.json | 1 + 42 files changed, 1093 insertions(+), 52 deletions(-) create mode 100644 packages/compact/tool-result-prune/README.md create mode 100644 packages/compact/tool-result-prune/package.json create mode 100644 packages/compact/tool-result-prune/src/config.ts create mode 100644 packages/compact/tool-result-prune/src/index.ts create mode 100644 packages/compact/tool-result-prune/src/types.ts create mode 100644 packages/compact/tool-result-prune/tests/loader-composition.spec.ts create mode 100644 packages/compact/tool-result-prune/tests/tool-result-prune.spec.ts create mode 100644 packages/compact/tool-result-prune/tsconfig.json diff --git a/docs/agent-lifecycle.md b/docs/agent-lifecycle.md index c6010d4139..274d6d9c87 100644 --- a/docs/agent-lifecycle.md +++ b/docs/agent-lifecycle.md @@ -55,7 +55,7 @@ sequenceDiagram The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set. -`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Recovery compacts between the closed failed step and a fresh retry step, and returns retry only when the surface replacement generation advances; otherwise the original request error remains authoritative. +`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Once either trigger qualifies, optional tool-result pruning runs before summary selection. Recovery works between the closed failed step and a fresh retry step, and returns retry only when pruning or summarization advances the surface replacement generation; otherwise the original request error remains authoritative. SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors. diff --git a/docs/architecture.md b/docs/architecture.md index 9750ea598c..d2289ff731 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -32,6 +32,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages add services (`ctx | `ctx.skills` | [`skill/`](../packages/skill/README.md) | skill provider registry and progressive disclosure | | `ctx.web` | [`web/`](../packages/web/README.md) | search/fetch provider registries | | `ctx.compact` | [`compact/`](../packages/compact/README.md) | session-log compaction | +| `ctx.toolResultPrune` | [`compact/tool-result-prune`](../packages/compact/tool-result-prune/README.md) | optional model-free tool-result pruning | | `ctx.subagents` | [`subagent/`](../packages/subagent/README.md) | named delegation providers | | `ctx.tasks` | [`tasks/`](../packages/tasks/README.md) | background task registry + generic `task_*` control tools | | `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | script-driven multi-agent orchestration | @@ -106,7 +107,7 @@ Each step renders one prompt assembly. Plugins contribute ordered sections, tool Post-tool context follows all results, preserving call/result adjacency. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering while the step signal remains open. Leftover steering becomes next-turn input. `agent/turn-stop` is terminal through close and flush: later steering is discarded, while ordinary queued prompts survive. -When loaded, `dsh-compact-basic` consumes that post-step checkpoint for `ctx.tokenMeter` pressure under the actual routed header. It also consumes canonical context overflow at `agent/request-error`, but authorizes retry only after a tool-balanced compaction advances `surface.replaceGeneration`. The same turn signal owns both summarization paths. +When loaded, `dsh-compact-basic` consumes that post-step checkpoint for `ctx.tokenMeter` pressure under the actual routed header. Once pressure or canonical context overflow qualifies, it runs optional `ctx.toolResultPrune` rewriting before summary selection and remeasures the replayed surface. Overflow recovery authorizes retry after either pruning or tool-balanced summary compaction advances `surface.replaceGeneration`. The same turn signal owns both paths. ### Failure Boundaries diff --git a/docs/capability-seams.md b/docs/capability-seams.md index eb59f27f32..816fc0ea3b 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -16,6 +16,8 @@ flowchart LR pkg_compact_basic["compact-basic"] pkg_token_meter["token-meter"] svc_tokenMeter["ctx.tokenMeter
Replay token measurement"] + pkg_tool_result_prune["tool-result-prune"] + svc_toolResultPrune["ctx.toolResultPrune
Model-free tool-result pruning"] pkg_session["session"] svc_sessions["ctx.sessions
In-memory session store"] pkg_agent["agent"] @@ -127,6 +129,7 @@ flowchart LR pkg_system_prompt --> svc_systemPrompt pkg_tasks --> svc_tasks pkg_token_meter --> svc_tokenMeter + pkg_tool_result_prune --> svc_toolResultPrune pkg_tools --> svc_tools pkg_user_interaction --> svc_userInteraction pkg_web --> svc_web @@ -173,6 +176,7 @@ flowchart LR svc_tasks --> pkg_tool_subagent svc_tasks --> pkg_tool_tasks svc_tokenMeter --> pkg_compact_basic + svc_toolResultPrune --> pkg_compact_basic svc_tools --> pkg_acp svc_tools --> pkg_agent_loop svc_tools --> pkg_tool_ask_user @@ -195,6 +199,7 @@ flowchart LR | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | | `ctx.tokenMeter` | `core` | [`token-meter`](../packages/llm/token-meter) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements. | +| `ctx.toolResultPrune` | `core` | [`tool-result-prune`](../packages/compact/tool-result-prune) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Rewrites oversized current tool results through replayable single-node surface replacements before summary compaction. | | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | | `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 7adaf791ad..cb266a8119 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -930,6 +930,22 @@ export interface Config { Source: [`packages/fs/tool-fs/src/index.ts:22`](../packages/fs/tool-fs/src/index.ts) +## `@deepseek-ai/dsh-tool-result-prune` + +```ts config-catalog +/** Character-budget policy for deterministic tool-result pruning. */ +export interface ToolResultPruneConfig { + /** Prune when total text exceeds this many Unicode code points. Defaults to `8192`. */ + thresholdChars?: number + /** Maximum leading Unicode code points retained. Defaults to `4096`. */ + headChars?: number + /** Maximum trailing Unicode code points retained. Defaults to `1024`. */ + tailChars?: number +} +``` + +Source: [`packages/compact/tool-result-prune/src/types.ts:4`](../packages/compact/tool-result-prune/src/types.ts) + ## `@deepseek-ai/dsh-tool-skill` Requires: `tools` · `skills` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 951881a8a7..e2fc41b943 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -272,6 +272,20 @@ Types: [Message](../core-data-structures/core.md) Source: [`packages/llm/token-meter/src/index.ts:106`](../../packages/llm/token-meter/src/index.ts) +## `ctx.toolResultPrune` — `ToolResultPruneService` + +Deterministic head/middle/tail pruning for current tool-result surface nodes. + +```ts cordis-catalog +measureContent(blocks: readonly ContentBlock[]): number +pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null +pruneSession(session: Session): PruneResult +``` + +Types: [ContentBlock](../core-data-structures/core.md) + +Source: [`packages/compact/tool-result-prune/src/index.ts:39`](../../packages/compact/tool-result-prune/src/index.ts) + ## `ctx.tools` — `ToolRegistry` Tool registry and execution pipeline. Scoped registrations shadow globals; one visibility resolver feeds presentation, lookup, and dispatch. diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 6d3ae30071..3a008a0b95 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -58,6 +58,6 @@ export type CompactionTrigger = 'pressure' | 'context-overflow' `CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration. -Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Failed-request recovery runs through `agent/request-error` after the failed step closes, and authorizes a fresh numbered-step retry only when the surface replacement generation advances. Region boundaries preserve tool-call/result pairing but do not preserve whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. +Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and authorizes a fresh numbered-step retry only when the surface replacement generation advances. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. The seam exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for those edge checks. Both validate current surface membership, reject stale or missing seqs and orphan results, and ignore a caller-retained `node.next`; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics. diff --git a/docs/module-graph.md b/docs/module-graph.md index 990692b6e5..fbe9afd59b 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -45,6 +45,7 @@ flowchart TD subgraph group_compact["packages/compact"] pkg_compact["compact"] pkg_compact_basic["compact-basic"] + pkg_tool_result_prune["tool-result-prune"] end subgraph group_subagent["packages/subagent"] pkg_subagent["subagent"] @@ -168,6 +169,8 @@ flowchart TD pkg_skill_local --> pkg_skill pkg_compact --> pkg_llm pkg_compact --> pkg_session + pkg_tool_result_prune --> pkg_llm + pkg_tool_result_prune --> pkg_session pkg_web_fetch_local --> pkg_timeout pkg_web_fetch_local --> pkg_web pkg_web_search_deepseek --> pkg_web @@ -185,6 +188,7 @@ flowchart TD pkg_compact_basic --> pkg_llm pkg_compact_basic --> pkg_session pkg_compact_basic --> pkg_token_meter + pkg_compact_basic --> pkg_tool_result_prune pkg_hook_protocol --> pkg_bash pkg_hook_protocol --> pkg_session pkg_session_persistence_jsonl --> pkg_session @@ -407,6 +411,7 @@ flowchart TD | [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) | | [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) | | [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | +| [`tool-result-prune`](../packages/compact/tool-result-prune) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) | | [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) | | [`web-search-exa`](../packages/web/web-search-exa) | `web` | [`web`](../packages/web/web) | @@ -415,7 +420,7 @@ flowchart TD | [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | | [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) | -| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) | +| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter), [`tool-result-prune`](../packages/compact/tool-result-prune) | | [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) | | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | | [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index 7cfb11d29d..bd13a336f1 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 7d68bc32d3860bf5edd94c4eda76922c91ae6af2 -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 2315bd4d9ca9b93eb9a8d4850f917e6aa1bc6476 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 99dc7625b8e185464d7a8a1ea8eda5baf0674df7 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 4f84d4435341005c058e32582e6d26b2a9f29bc1 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index 7d68bc32d3..99dc7625b8 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -32,9 +32,9 @@ If cancellation lands after assistant tool calls are durable but before all call `CompactService.compactIfNeeded(agent, trigger, signal)` accepts `trigger: 'pressure' | 'context-overflow'`. The interface gains no estimation methods or token types; `ctx.tokenMeter` remains the reusable accounting owner. -For `pressure`, compact-basic applies the service-wide threshold and retained-tail policy to one unified `ctx.tokenMeter.measure()` result. The same singleton meter owns range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. +For `pressure`, compact-basic applies the service-wide threshold and retained-tail policy to one unified `ctx.tokenMeter.measure()` result. Below pressure it returns without pruning. Once pressure qualifies, optional `ctx.toolResultPrune` rewrites oversized current results and compact-basic remeasures through the same meter; safe pressure skips the model call, while remaining pressure selects and summarizes from the pruned surface. The same singleton meter owns range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. -For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It chooses the maximal tool-balanced head range while leaving the newest indivisible unit, then attempts exactly one shrinking compaction under the same signal. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` only when compaction succeeds and the generation increases. A backend returning a result without replacement cannot authorize retry. +For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It prunes first, then chooses the maximal tool-balanced head range while leaving the newest indivisible unit and attempts one shrinking summary compaction under the same signal when a range exists. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` whenever pruning or summarization increases it. A backend returning a result without replacement cannot authorize retry, while pruning-only progress can authorize a retry without a `CompactionResult`. `maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, a missing routed model, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. @@ -44,7 +44,7 @@ The default summarizer still resolves explicit configuration, then the latest lo Lifecycle tests pin post-step ordering after durable tool/context/steering work, content-less and max-token successes, final-adapter dispatch/iterator/in-band boundaries, retry numbering, attempt reset, cancellation, disposal, synthetic tool results, and original error identity. -Compact tests pin low-friction service-wide defaults, actual routed-model selection, unlisted-model measurement, unified pressure-and-retention decisions, below-threshold forced overflow, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. +Compact tests pin low-friction service-wide defaults, actual routed-model selection, unlisted-model measurement, unified pressure-and-retention decisions, pressure-gated pruning, pruning-only relief, summarization from pruned input, optional-plugin fallback, pruning-only and summarized overflow recovery, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. ## Alternatives considered @@ -56,7 +56,7 @@ Compact tests pin low-friction service-wide defaults, actual routed-model select ## Consequences -Pressure now describes the actual completed routed request, including durable tool results and request-only prefix fields, rather than a provisional next-call guess. Canonical overflow supplies the backstop when no successful usage anchor exists. Recovery is bounded, cancellation-owned, and monotonic: it retries only after a visible surface generation change. +Pressure describes the actual completed routed request, including durable tool results and request-only prefix fields, rather than a provisional next-call guess. Optional model-free pruning removes predictable tool-output bulk before summary selection and can independently create retry-worthy progress. Canonical overflow supplies the backstop when no successful usage anchor exists. Recovery is bounded, cancellation-owned, and monotonic: it retries only after a visible surface generation change. The cost is one additional serial checkpoint on successful steps and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window or split one indivisible oversized message/tool unit. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index 2315bd4d9c..4f84d44353 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -32,9 +32,9 @@ Status: implemented `CompactService.compactIfNeeded(agent, trigger, signal)` 接收 `trigger: 'pressure' | 'context-overflow'`。接口不增加估算方法或 token 类型；`ctx.tokenMeter` 继续作为可复用的核算所有者。 -对于 `pressure`，compact-basic 把服务级阈值与保留尾部策略应用到一次统一的 `ctx.tokenMeter.measure()` 结果。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 +对于 `pressure`，compact-basic 把服务级阈值与保留尾部策略应用到一次统一的 `ctx.tokenMeter.measure()` 结果。低于压力时直接返回，不执行剪枝。压力达到条件后，可选的 `ctx.toolResultPrune` 会改写当前表层中过大的工具结果，compact-basic 再通过同一个 meter 重新计量；若压力恢复安全则跳过模型调用，否则从已剪枝表层选择范围并生成摘要。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 -对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它在保留最新不可分割单元的同时，选择最大的工具配对平衡头部范围，并在同一 signal 下只尝试一次缩小压缩。自动监听器先记录 `session.surface.replaceGeneration`，只有压缩成功且 generation 增加时才返回 `{ action: 'retry' }`。后端若只返回结果但没有替换表层，不能授权重试。 +对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它先执行剪枝，再在保留最新不可分割单元的同时选择最大的工具配对平衡头部范围；存在范围时，才在同一 signal 下尝试一次缩小摘要压缩。自动监听器先记录 `session.surface.replaceGeneration`，剪枝或摘要让 generation 增加时就返回 `{ action: 'retry' }`。后端若只返回结果但没有替换表层，不能授权重试；只有剪枝取得进展时，即使没有 `CompactionResult` 也可以授权重试。 `maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 @@ -44,7 +44,7 @@ Status: implemented 生命周期测试固定 post-step 位于持久工具、上下文与 steering 工作之后，覆盖无内容与达到 token 上限的成功、最终适配器分发/迭代器/带内边界、重试编号、尝试重置、取消、销毁、合成工具结果与原始错误身份。 -压缩测试固定低摩擦服务级默认值、实际路由模型选择、未列出模型计量、统一压力与保留决策、低于阈值的强制溢出、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 +压缩测试固定低摩擦服务级默认值、实际路由模型选择、未列出模型计量、统一压力与保留决策、压力门控剪枝、剪枝独立解除压力、从已剪枝输入生成摘要、可选插件回退、仅剪枝与剪枝后摘要两类溢出恢复、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 ## 考虑过的替代方案 @@ -56,7 +56,7 @@ Status: implemented ## 后果 -压力现在描述实际完成的路由请求，包括持久工具结果与仅请求前缀字段，而不是对下一次调用的临时猜测。当成功 usage 锚点不存在时，规范化溢出提供兜底路径。恢复有上限、受取消所有，并保持单调：只有模型可见的表层 generation 变化后才重试。 +压力描述实际完成的路由请求，包括持久工具结果与仅请求前缀字段，而不是对下一次调用的临时猜测。可选的无模型剪枝会在选择摘要前移除可预测的工具输出体积，也能独立产生足以重试的进展。当成功 usage 锚点不存在时，规范化溢出提供兜底路径。恢复有上限、受取消所有，并保持单调：只有模型可见的表层 generation 变化后才重试。 代价是成功 step 增加一个串行检查点，并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况，也不能拆分单个不可分割的超大消息或工具单元。 diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index ecbf401428..0f210cbd8e 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -18,7 +18,8 @@ Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capabil 1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, and the `compact/*` session events. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. 2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. -3. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. +3. **Model-free companion** — `@deepseek-ai/dsh-tool-result-prune`: a concrete optional service that rewrites oversized current `tool/result` nodes before the backend selects a summary range. It is not a second compaction implementation and does not implement `CompactService`. +4. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -34,9 +35,9 @@ An earlier draft put the full algorithm (the retention walk, token-summing, text ### Automatic pressure runs after successful durable step work -The original pre-step placement used a provisional envelope and could not see final `agent/request` routing, tools, provider output, tool results, buffered context, or steering. The corrected lifecycle fires serial `agent/post-step(agent, turn, step, signal)` after those successful facts are durable and before `step/end`. `dsh-compact-basic` measures the canonical logged request through `ctx.tokenMeter`, so the next request sees any replacement without a speculative envelope override. +The original pre-step placement used a provisional envelope and could not see final `agent/request` routing, tools, provider output, tool results, buffered context, or steering. The corrected lifecycle fires serial `agent/post-step(agent, turn, step, signal)` after those successful facts are durable and before `step/end`. `dsh-compact-basic` measures the canonical logged request through `ctx.tokenMeter`, so the next request sees any replacement without a speculative envelope override. Once pressure qualifies, it invokes optional `ctx.toolResultPrune`, remeasures the durable surface, and summarizes only if pruning did not restore safe pressure. -Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic forces one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases; the loop then opens a new numbered step and reconstructs its request from the durable log. No range, no replacement, recovery failure, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. The complete lifecycle decision is in the [after-call recovery RFC](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). +Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic prunes before forcing one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases, including pruning-only progress when no summary range exists; the loop then opens a new numbered step and reconstructs its request from the durable log. No replacement, recovery failure, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. The complete lifecycle decision is in the [after-call recovery RFC](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). ``` assistant/message → tool/result/context/steering @@ -110,16 +111,16 @@ Two failure paths, both documented: ## Consequences -- **Packages**: `packages/compact/compact` supplies the interface and `compact-basic` supplies the backend. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. +- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, and `tool-result-prune` supplies optional deterministic rewriting. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. - **Automatic seams**: `agent/post-step` (`@mode serial`) handles successful-call pressure and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Generic `agent/pre-step` remains a four-argument checkpoint with no compaction-only prompt/prefix payload. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and answers both edges from one per-cut balance sequence instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. -- **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement node at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. -- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter` before `dsh-compact-basic`; the service-wide window and compact defaults make the pair usable without repeated numeric policy. +- **`dsh-invariants`** treats fresh appended tool results as executions that require an open step and pending call, while provenance-backed replacements are turn-enclosed surface rewrites. Positional replacement and complete-source checks validate the rewritten node. +- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-tool-result-prune`, then `dsh-compact-basic`; service-wide defaults make the composition usable without repeated numeric policy. ## Testing -- **Unit:** Real Loader and invariant plugins cover whole-unit retention, convergence failure, both `compact/end` outcomes, head anchoring, open-tail refusal, inert crash orphans, forced below-threshold overflow, generation proof, caps, and original-error preservation. +- **Unit:** Real Loader and invariant plugins cover whole-unit retention, pruning configuration and replay, rich-block ordering, metadata preservation, convergence, both `compact/end` outcomes, open-tail refusal, pruning-only and summarized overflow recovery, generation proof, caps, and original-error preservation. - **Loop:** Tests pin post-step after durable tool results and before `step/end`, actual `agent/request` routing, closed failed steps, fresh retry numbering, and complete thrown/in-band overflow → compaction → reconstructed retry composition. - **With-key e2e:** A real model and bash session with lowered limits triggers compaction, records a complete `compact/start…end` pair, shrinks the surface, and finishes the task. - **Snapshot gap:** Runaway-turn compaction cannot yet replay because the summarization call records no `assistant/chunk` events or `sessionId`; interleaved summarization-call replay remains follow-up work. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 121bfd09f7..085b165a2f 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -5,9 +5,9 @@ Every model-facing tool a shipped plugin contributes to `ctx.tools`: the `name`, `description`, and JSON-Schema `parameters` the model receives via the system-prompt assembly. It complements the cordis [events](cordis-catalog/events.md) & [services](cordis-catalog/services.md) catalogs (the wiring a plugin listens to and calls) and [core-data-structures/](core-data-structures/core.md) (the types those signatures move) — this page is the *tools* the agent is offered. -This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator's boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md). +This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any model-facing package is missing from the generator's boot manifest; service-only packages that share the prefix are explicitly excluded. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md). -Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog's packages-only scope. +Scope: shipped model-facing product tools under `packages/*/tool-*`, each booted with its DEFAULT config. Runtime service packages such as `tool-result-prune` do not register `ctx.tools` schemas and are explicitly excluded. The registered tool NAME can be a load-time config (e.g. `tool-subagent`'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog's packages-only scope. ## Tool Package Map diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index 9e627324d4..869f9eb625 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -56,6 +56,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads | `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin | | `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash` schema (`tool-bash`) and generic `task_*` controls (`tool-tasks`) come from `dsh-agent-spine-demo`, so only the executor is a leaf choice | | `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins | +| `token-meter`, `tool-result-prune`, `compact-basic` | replay-aware pressure, model-free oversized tool-result pruning, and LLM summary compaction. Pruning runs only after a compaction trigger qualifies and can avoid the summarization call | | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix | | `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) | | `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a checklist in stdio | @@ -66,7 +67,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads - `tests/full-loop.e2e.ts` — the canary: real model runs `echo e2e-ok` through the real bash tool; asserts `tool/call`/`tool/result` session events and the final answer. - `tests/coding-task.e2e.ts` — the swebench-style smoke: a temp dir holds `add.js` (with `a - b` where `a + b` belongs) and a failing `add.test.js`; the agent must fix the bug and verify. The test re-runs `node add.test.js` ITSELF and inspects the files — agent claims are not trusted. - `tests/resume.e2e.ts` — durable continuity across processes: run 1 tells the real model a secret code and persists the turn to a temp JSONL root, then the whole context is disposed; run 2 is a fresh context over the same root that RESUMES the session id and asks the model to recall the code. The recall can only come from the rehydrated log. -- `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so the auto-compaction listener fires MID-SESSION. Verifies the WORLD — a `compact/start…end` pair landed in the real log, the surface shrank (a replace node shadowed older nodes), and the agent still produced a correct final answer after compaction. +- `tests/compaction.e2e.ts` — the compaction smoke: a real multi-step bash task runs with a deliberately tiny context window so automatic pruning or summary compaction fires mid-session. It verifies the world: a replayable surface replacement lands, summary brackets are complete when summarization is needed, the surface shrinks, and the agent still produces a correct final answer. - `tests/todo-write.e2e.ts` — a real model drives the real `todo_write` tool and the test verifies the resulting `todo/write` session event. These self-skip without `DEEPSEEK_API_KEY`. `tests/code-mode.e2e.ts` is the with-key Code Mode proof — a real model, a two-tool task, asserting the wire tool list was exactly `[run_code]`, the `tool/code-dispatch` events landed under the parent call, and the curated answer came back. The keyless boot smokes run in the default e2e gate: `tests/keyless-smoke.e2e.ts` (the full real tree, dummy key, no prompt → no model call) and `tests/code-mode-keyless-smoke.e2e.ts` (the same guard for the Code Mode overlay). diff --git a/examples/coding-agent/composition.md b/examples/coding-agent/composition.md index c9a68810d2..5f35097603 100644 --- a/examples/coding-agent/composition.md +++ b/examples/coding-agent/composition.md @@ -3,7 +3,7 @@ # Coding Agent App Composition -The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package. +The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, tool-result pruning, compaction, and both subagent transports on top of the stdio app package. ```mermaid flowchart LR @@ -25,6 +25,8 @@ flowchart LR bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] plugin_coding_token_meter["token-meter
@deepseek-ai/dsh-token-meter"] cfg --> plugin_coding_token_meter + plugin_coding_tool_result_prune["tool-result-prune
@deepseek-ai/dsh-tool-result-prune"] + cfg --> plugin_coding_tool_result_prune plugin_coding_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] cfg --> plugin_coding_compact_basic plugin_coding_subagent["subagent
@deepseek-ai/dsh-subagent"] @@ -58,6 +60,7 @@ flowchart LR | `bash` | `@deepseek-ai/dsh-bash-local` | | `stdio-agent` | `@deepseek-ai/dsh-stdio-demo` | | `token-meter` | `@deepseek-ai/dsh-token-meter` | +| `tool-result-prune` | `@deepseek-ai/dsh-tool-result-prune` | | `compact-basic` | `@deepseek-ai/dsh-compact-basic` | | `subagent` | `@deepseek-ai/dsh-subagent` | | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index 2e9aa17786..ba86b99e81 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -50,6 +50,10 @@ - id: token-meter name: '@deepseek-ai/dsh-token-meter' +# Prune oversized tool output without a model call before summary compaction. +- id: tool-result-prune + name: '@deepseek-ai/dsh-tool-result-prune' + # Summarize an older range after measured pressure or a canonical provider overflow. # Service-wide policy provides pressure, retention, and one overflow-retry default. - id: compact-basic diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index cf79809f0c..6c06202a30 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -12,6 +12,7 @@ import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import TokenMeterService from '@deepseek-ai/dsh-token-meter' import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' +import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' @@ -68,6 +69,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio // backend, with a lower context window so a short real session crosses the threshold. if (options.compact !== undefined) { await ctx.plugin(TokenMeterService, options.tokenMeter) + await ctx.plugin(ToolResultPruneService) await ctx.plugin(BasicCompactService, options.compact) } // Durable JSONL persistence is opt-in: only the resume e2e needs it, and the diff --git a/packages/compact/README.md b/packages/compact/README.md index b5f5987571..e251bfe442 100644 --- a/packages/compact/README.md +++ b/packages/compact/README.md @@ -1,11 +1,12 @@ # compact/ — compaction capability family -A three-package capability seam (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract compaction interface, a backend that summarizes, and the model-facing tool that consumes it. The interface and a first backend (`compact-basic/`) exist; the consumer tool is deferred. All **product** packages. +A compaction capability family (see [capability seams](../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)): an abstract interface, a summarizing backend, a model-free tool-result pruning companion, and a deferred model-facing consumer. All **product** packages. | Package | Role | ctx key | |---|---|---| | `compact/` | Abstract compaction seam (interface + `compact/*` events + `CompactionResult`) | `ctx.compact` | | `compact-basic/` | A backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) | +| `tool-result-prune/` | Optional model-free head/middle/tail rewriting before summary compaction | `ctx.toolResultPrune` | | `tool-compact/` (deferred) | Model-facing `/compact` tool over `ctx.compact` | (registers on `ctx.tools`) | -The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`. Unlike the bash seam, it depends on `dsh-session` and `dsh-llm` — its verbs are defined over a `Session` and its output is the `ContentBlock` vocabulary, so the contract cannot be expressed without naming them. That deviation from the "interface depends only on cordis" guidance is intentional and recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement is a reusable LLM-family service rather than a `CompactService` method; a template- or model-backed compactor can replace `compact-basic` without changing the meter or callers. +The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`, and deterministic pruning at `compact/tool-result-prune/`. Unlike the bash seam, the interface depends on `dsh-session` and `dsh-llm` because its verbs are defined over a `Session` and its output uses `ContentBlock`. That deviation is recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement remains a reusable LLM-family service; a template- or model-backed compactor can replace `compact-basic` without changing the meter, pruner, or callers. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index 2afd955f35..75be39aa1b 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -9,12 +9,13 @@ This is the implementation tier of the compaction capability — see the [interf This backend owns the compaction policy: - **Measurement** — the singleton `ctx.tokenMeter` prices the latest canonical logged envelope and current surface at one consumed-log revision. Post-step pressure therefore includes the actual system prompt, tools, prefix, routing, assistant completion, tool results, buffered context, and steering. +- **Model-free pruning** — after pressure or canonical overflow qualifies, the optional [`ctx.toolResultPrune`](../tool-result-prune/README.md) service rewrites oversized tool results before range selection. Compact-basic remeasures through `ctx.tokenMeter`, skips summarization when pressure becomes safe, and otherwise summarizes the pruned surface. Below-pressure post-step checks never prune. - **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. - **Framing** — the replacement user message marks established checkpoint context with `` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint. - **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/post-step` listener checks pressure after successful output and tool work are durable but before `step/end`. Canonical provider overflow is handled through `agent/request-error` after the failed step closes. -- **Overflow recovery** — below-threshold overflow bypasses normal retention and attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized only when `surface.replaceGeneration` advances; no range, no replacement, recovery failure, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure. +- **Overflow recovery** — below-threshold overflow bypasses normal retention and first prunes, then attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized whenever `surface.replaceGeneration` advances, including pruning-only progress on an otherwise indivisible surface; no replacement, recovery failure, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure. - **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Operational post-step failures warn and continue; overflow-recovery failure preserves the original provider error. `summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on `ctx.tokenMeter`. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. @@ -49,15 +50,15 @@ export function apply(ctx: Context): void { } ``` -Loading the plugin registers `ctx.compact`. With `auto: true` (the default) it compacts automatically under token pressure; a consumer (a future `/compact` tool) can also call `ctx.compact.compactIfNeeded(...)` or `ctx.compact.compactRegion(...)` directly. +Loading the plugin registers `ctx.compact`. Add [`dsh-tool-result-prune`](../tool-result-prune/README.md) as a sibling before this plugin to enable the optional model-free pass. With `auto: true` (the default) it compacts automatically under token pressure; a consumer (a future `/compact` tool) can also call `ctx.compact.compactIfNeeded(...)` or `ctx.compact.compactRegion(...)` directly. ## Model Experience ### Conversation history -**What the model sees**: After a successful step crosses the threshold, the next request receives the checkpoint preamble below, a blank line, ``, the data-dependent summary, and ``. Overflow recovery rebuilds the immediate retry from that replacement. This one checkpoint replaces the selected older range and is followed by the retained recent units. +**What the model sees**: After a successful step crosses the threshold, oversized tool results are first rewritten when the optional pruner is loaded. If summarization remains necessary, the next request receives the checkpoint preamble below, a blank line, ``, the data-dependent summary, and ``. Overflow recovery rebuilds the immediate retry from whatever replacement advanced the surface. -**Token effect**: The replacement reduces future input history rather than appending a second copy. The summary remains until a later compaction replaces it; one oversized indivisible unit can still exceed the budget. +**Token effect**: Model-free pruning can avoid the auxiliary call entirely; otherwise it reduces that call's transcript before the summary replaces an older range. A summary remains until a later compaction replaces it, while an indivisible non-tool unit can still exceed the budget. #### Conversation checkpoint preamble diff --git a/packages/compact/compact-basic/package.json b/packages/compact/compact-basic/package.json index d50fa45777..55ca301878 100644 --- a/packages/compact/compact-basic/package.json +++ b/packages/compact/compact-basic/package.json @@ -27,8 +27,14 @@ "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-token-meter": "^0.0.1", + "@deepseek-ai/dsh-tool-result-prune": "^0.0.1", "cordis": "^4.0.0-rc.7" }, + "peerDependenciesMeta": { + "@deepseek-ai/dsh-tool-result-prune": { + "optional": true + } + }, "dependencies": { "schemastery": "^3.18.0" }, @@ -43,6 +49,7 @@ "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-token-meter": "workspace:^", + "@deepseek-ai/dsh-tool-result-prune": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.7" } diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index b694b08194..91e8ad0cea 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -12,6 +12,8 @@ import type { Session } from '@deepseek-ai/dsh-session' import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' +// Type-only: makes the optional sibling service available to `ctx.get()`. +import type {} from '@deepseek-ai/dsh-tool-result-prune' import { resolveConfig } from './config.ts' import { compactSurfaceRegion, selectCompactableRange } from './region.ts' import { summarizeWithLlm } from './summarizer.ts' @@ -111,9 +113,9 @@ export class BasicCompactService extends CompactService { return next() } // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while compaction is awaited. - if (signal.aborted || result === null + if (signal.aborted || agent.session.surface.replaceGeneration <= generation) return next() - logResult(result, 'context overflow recovery') + if (result !== null) logResult(result, 'context overflow recovery') return { action: 'retry' } }) } @@ -142,7 +144,7 @@ export class BasicCompactService extends CompactService { * @param agent - agent whose latest durable routed request is measured. * @param trigger - normal post-step pressure or context-overflow recovery. * @param signal - live turn cancellation signal forwarded to summarization. - * @returns the latest compaction result, or `null` when no check/work applies. + * @returns the latest summary compaction result, or `null` when no summary ran. */ override async compactIfNeeded( agent: Agent, @@ -152,15 +154,25 @@ export class BasicCompactService extends CompactService { const model = routedModel(agent.session) if (model === undefined) return null const meter = this.ctx.tokenMeter + const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio) + let measurement = meter.measure(agent.session) + if (trigger === 'pressure' && measurement.totalTokens < threshold) return null + + // Pruning is optional so compact-basic remains independently composable. + // Once either trigger qualifies, land the model-free pass before choosing + // a summary range, then remeasure through the singleton replay fold. + const prune = this.ctx.get('toolResultPrune') + if (prune !== undefined) { + prune.pruneSession(agent.session) + measurement = meter.measure(agent.session) + } + if (trigger === 'context-overflow') { - const measurement = meter.measure(agent.session) const range = selectCompactableRange(agent.session, measurement, 0) if (range === null) return null return this.compactRegion(agent.session, range.start, range.end, agent, signal) } - const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio) - let measurement = meter.measure(agent.session) if (measurement.totalTokens < threshold) return null let result: CompactionResult | null = null diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 3d049608b7..190fb026e7 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -9,6 +9,7 @@ import LlmService, { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, LlmAdapter } from '@d import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' import TokenMeterService from '@deepseek-ai/dsh-token-meter' +import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' import type { Agent } from '@deepseek-ai/dsh-agent' const SIGNAL = new AbortController().signal @@ -94,6 +95,42 @@ function toolConversation(): Session { return session } +/** One closed routed tool step followed by an open turn for rewrite events. */ +function oversizedToolResult(chars = 3_000, withCompactablePrompt = false): Session { + const session = new Session(SessionId(`oversized-tool-${chars}`)) + const callId = CallId('oversized') + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + if (withCompactablePrompt) { + session.append('user/message', { + content: [{ type: 'text', text: 'older history '.repeat(200) }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + } + session.append('step/start', { turn: 1, step: 1 }) + session.append('request/header', { + header: { config: { model: MODEL } }, + reason: 'initial', + }) + session.append('assistant/message', { + turn: 1, + step: 1, + content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }], + }, { surfaceOp: 'append' }) + session.append('tool/call', { turn: 1, step: 1, callId, name: 'bash', arguments: '{}' }) + session.append('tool/result', { + turn: 1, + step: 1, + callId, + content: [{ type: 'text', text: 'X'.repeat(chars) }], + isError: false, + meta: { presentation: 'preserved' }, + }, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) + return session +} + class TestCompactService extends BasicCompactService { summary: ContentBlock[] = [{ type: 'text', text: 'small checkpoint' }] summaryModel = 'summary-model' @@ -401,6 +438,78 @@ describe('pressure measurement and retention', () => { }) }) +describe('optional model-free tool-result pruning', () => { + const pruneConfig = { thresholdChars: 100, headChars: 20, tailChars: 10 } + + it('does not prune a below-pressure session opportunistically', async () => { + const ctx = createContext(10_000) + const prune = new ToolResultPruneService(ctx, pruneConfig) + const compact = new TestCompactService(ctx, { + auto: false, + thresholdRatio: 0.8, + retainTokens: 100, + }) + const session = oversizedToolResult() + const pruneSession = vi.spyOn(prune, 'pruneSession') + + expect(await compactIfNeeded(compact, session)).toBeNull() + expect(pruneSession).not.toHaveBeenCalled() + expect(compact.calls).toHaveLength(0) + expect(session.surface.replaceGeneration).toBe(0) + }) + + it('skips LLM summarization when pruning alone clears pressure', async () => { + const ctx = createContext(1_000) + void new ToolResultPruneService(ctx, pruneConfig) + const compact = new TestCompactService(ctx, { + auto: false, + thresholdRatio: 0.5, + retainTokens: 50, + }) + const session = oversizedToolResult() + + expect(ctx.tokenMeter.measure(session).totalTokens).toBeGreaterThanOrEqual(500) + expect(await compactIfNeeded(compact, session)).toBeNull() + expect(ctx.tokenMeter.measure(session).totalTokens).toBeLessThan(500) + expect(compact.calls).toHaveLength(0) + expect(session.surface.replaceGeneration).toBe(1) + }) + + it('summarizes the pruned surface when pruning is insufficient', async () => { + const ctx = createContext(2_000) + void new ToolResultPruneService(ctx, pruneConfig) + const compact = new TestCompactService(ctx, { + auto: false, + thresholdRatio: 0.5, + retainTokens: 50, + }) + const session = toolConversation() + + expect(await compactIfNeeded(compact, session)).not.toBeNull() + expect(compact.calls).toHaveLength(1) + expect(compact.calls[0]!.text).toContain('tool result middle pruned') + expect(compact.calls[0]!.text).not.toContain('result 1 '.repeat(300)) + }) + + it('retains the original compact-basic behavior without the optional plugin', async () => { + const ctx = createContext(2_000) + const compact = new TestCompactService(ctx, { + auto: false, + thresholdRatio: 0.5, + retainTokens: 50, + }) + const session = oversizedToolResult(3_000, true) + + expect(await compactIfNeeded(compact, session)).not.toBeNull() + expect(compact.calls).toHaveLength(1) + const original = session.events.find(event => event.type === 'tool/result') + expect(original?.type === 'tool/result' && original.data.content[0]) + .toEqual({ type: 'text', text: 'X'.repeat(3_000) }) + expect(session.events.filter(event => + event.type === 'tool/result' && event.surfaceOp !== 'append')).toHaveLength(0) + }) +}) + describe('compaction region transaction', () => { it('rejects an agent that does not own the exact target session before mutation', async () => { const compact = service() @@ -875,6 +984,44 @@ describe('automatic listener and loader composition', () => { expect(session.surface.nodes.some(node => node.seq === retainedSeq)).toBe(true) }) + it('authorizes overflow retry when pruning alone advances an indivisible surface', async () => { + const ctx = createContext(10_000) + void new ToolResultPruneService(ctx, { + thresholdChars: 100, + headChars: 20, + tailChars: 10, + }) + const compact = new TestCompactService(ctx, { + thresholdRatio: 1, + retainTokens: 900, + }) + const session = oversizedToolResult() + + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' }) + expect(session.surface.replaceGeneration).toBe(1) + expect(session.events.some(event => event.type === 'compact/summary')).toBe(false) + expect(compact.calls).toHaveLength(0) + }) + + it('continues overflow recovery with summarization on the pruned surface', async () => { + const ctx = createContext(10_000) + void new ToolResultPruneService(ctx, { + thresholdChars: 100, + headChars: 20, + tailChars: 10, + }) + const compact = new TestCompactService(ctx, { + thresholdRatio: 1, + retainTokens: 900, + }) + const session = toolConversation() + + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' }) + expect(session.events.some(event => event.type === 'compact/summary')).toBe(true) + expect(compact.calls).toHaveLength(1) + expect(compact.calls[0]!.text).toContain('tool result middle pruned') + }) + it('preserves the newest whole tool-call/result pair during forced overflow compaction', async () => { const ctx = createContext() void new TestCompactService(ctx, { diff --git a/packages/compact/compact-basic/tests/loader-composition.spec.ts b/packages/compact/compact-basic/tests/loader-composition.spec.ts index b13e8f8b67..7294224452 100644 --- a/packages/compact/compact-basic/tests/loader-composition.spec.ts +++ b/packages/compact/compact-basic/tests/loader-composition.spec.ts @@ -9,6 +9,7 @@ import Include from '@cordisjs/plugin-include' import LlmService from '@deepseek-ai/dsh-llm' import TokenMeterService from '@deepseek-ai/dsh-token-meter' import BasicCompactService from '@deepseek-ai/dsh-compact-basic' +import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' let root: string | undefined let context: Context | undefined @@ -32,6 +33,7 @@ async function loadYaml(lines: readonly string[]): Promise { const modules = new Map([ ['@deepseek-ai/dsh-llm', LlmService], ['@deepseek-ai/dsh-token-meter', TokenMeterService], + ['@deepseek-ai/dsh-tool-result-prune', ToolResultPruneService], ['@deepseek-ai/dsh-compact-basic', BasicCompactService], ]) context.loader.internal = { @@ -50,12 +52,17 @@ async function loadYaml(lines: readonly string[]): Promise { } describe('real Loader composition', () => { - it('loads the flat token-meter and compact-basic YAML shape', async () => { + it('loads the shipped token-meter, pruning, and compact-basic YAML order', async () => { const loaded = await loadYaml([ "- name: '@deepseek-ai/dsh-llm'", "- name: '@deepseek-ai/dsh-token-meter'", ' config:', ' contextWindow: 4096', + "- name: '@deepseek-ai/dsh-tool-result-prune'", + ' config:', + ' thresholdChars: 100', + ' headChars: 20', + ' tailChars: 10', "- name: '@deepseek-ai/dsh-compact-basic'", ' config:', ' thresholdRatio: 0.5', @@ -68,6 +75,7 @@ describe('real Loader composition', () => { .map(entry => entry.options.name) expect(unloaded).toEqual([]) expect(loaded.tokenMeter.contextWindow).toBe(4096) + expect(loaded.get('toolResultPrune')).toBeInstanceOf(ToolResultPruneService) expect(loaded.get('compact')).toBeInstanceOf(BasicCompactService) expect((loaded.compact as BasicCompactService).config).toMatchObject({ thresholdRatio: 0.5, diff --git a/packages/compact/compact-basic/tsconfig.json b/packages/compact/compact-basic/tsconfig.json index 0103ad82a8..5dd00b83f1 100644 --- a/packages/compact/compact-basic/tsconfig.json +++ b/packages/compact/compact-basic/tsconfig.json @@ -13,6 +13,7 @@ { "path": "../../llm/token-meter" }, { "path": "../../core/session" }, { "path": "../../core/agent" }, - { "path": "../compact" } + { "path": "../compact" }, + { "path": "../tool-result-prune" } ] } diff --git a/packages/compact/tool-result-prune/README.md b/packages/compact/tool-result-prune/README.md new file mode 100644 index 0000000000..e6d50f229c --- /dev/null +++ b/packages/compact/tool-result-prune/README.md @@ -0,0 +1,50 @@ +# @deepseek-ai/dsh-tool-result-prune + +The replay-safe model-free pruning service (`ctx.toolResultPrune`). It rewrites over-budget `tool/result` surface nodes to a bounded head, a fixed omission marker, and a bounded tail while retaining the full original event in the append-only session log. + +This is a concrete companion to [`dsh-compact-basic`](../compact-basic/README.md), not a compaction backend or model-facing tool. Compact-basic reads it through optional `ctx.get('toolResultPrune')`, so either package remains independently composable. + +## Service API + +`pruneSession(session)` scans one stable snapshot of the current surface. Every over-budget tool result is replaced by one newly appended `tool/result` carrying `{ surfaceOp: { op: 'replace', start: originalSeq, end: originalSeq }, sourceEventSeqs: [originalSeq] }`. The replacement spreads the complete original data and changes only `content`, preserving `turn`, `step`, `callId`, error fields, `meta`, and later data additions. The original event remains available for persistence, replay, and exact-log inspection. + +`measureContent(blocks)` counts Unicode code points in `text` blocks. `pruneContent(blocks)` returns the bounded replacement or `null` when content is already within the threshold. Non-text blocks are retained at their original relative positions; text slicing never splits a UTF-16 surrogate pair, though it can split a multi-code-point grapheme cluster. + +Every emitted result has exactly the configured head budget, fixed marker, and tail budget in text code points, is no larger than `thresholdChars`, and is strictly smaller than the triggering input. A second pass therefore emits no replacement. + +## Config + +Unrecognized keys fail at plugin construction. Resolved config is detached and deeply immutable. + +| Key | Required | Meaning | +|---|---|---| +| `thresholdChars` | no (default `8192`) | Prune when combined text exceeds this many Unicode code points. | +| `headChars` | no (default `4096`) | Leading Unicode code points retained. | +| `tailChars` | no (default `1024`) | Trailing Unicode code points retained. | + +All values are integers; the threshold is positive and head/tail are non-negative. `headChars + marker + tailChars` must fit within `thresholdChars`, so a valid configuration can prune every over-budget result without growth or repeated rewriting. + +## Usage + +```ts +import type { Context } from 'cordis' +import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' + +export function apply(ctx: Context): void { + ctx.plugin(ToolResultPruneService) +} +``` + +## Model Experience + +### Pruned tool result + +**What the model sees**: Once a compaction trigger qualifies, future requests see the retained head, `\n\n[... tool result middle pruned ...]\n\n`, and retained tail in place of the removed text. Rich blocks keep their order. The model does not see a second copy of the original. + +**Token effect**: Each rewritten tool result has at most `thresholdChars` text code points. Pruning itself makes no model call; compact-basic skips summarization when the remeasured request falls below pressure, otherwise the summarizer reads the pruned surface. + +## Known Limitations and Deferred Work + +- **Character budgets are not token budgets** — provider token density varies, so `ctx.tokenMeter` remains the authority for deciding whether pruning relieved request pressure. +- **Pruning is syntactic** — it retains the beginning and end without interpreting which middle lines are semantically important. +- **Grapheme clusters can split** — code-point slicing protects surrogate pairs but does not perform locale-aware grapheme segmentation. diff --git a/packages/compact/tool-result-prune/package.json b/packages/compact/tool-result-prune/package.json new file mode 100644 index 0000000000..6b7ac89742 --- /dev/null +++ b/packages/compact/tool-result-prune/package.json @@ -0,0 +1,40 @@ +{ + "name": "@deepseek-ai/dsh-tool-result-prune", + "description": "Replay-safe model-free head/middle/tail pruning for tool-result surface nodes", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "dependencies": { + "schemastery": "^3.18.0" + }, + "devDependencies": { + "@cordisjs/plugin-include": "workspace:^", + "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/compact/tool-result-prune/src/config.ts b/packages/compact/tool-result-prune/src/config.ts new file mode 100644 index 0000000000..a2d33ac76e --- /dev/null +++ b/packages/compact/tool-result-prune/src/config.ts @@ -0,0 +1,77 @@ +/** Configuration resolution for deterministic tool-result pruning. */ + +import { deepFreeze } from '@deepseek-ai/dsh-llm' +import type { ResolvedConfig, ToolResultPruneConfig } from './types.ts' + +/** Fixed marker substituted for every removed middle span. */ +export const PRUNE_MARKER = '\n\n[... tool result middle pruned ...]\n\n' + +/** Low-friction defaults for coding-agent tool output. */ +export const DEFAULTS: ResolvedConfig = deepFreeze({ + thresholdChars: 8192, + headChars: 4096, + tailChars: 1024, +}) + +const CONFIG_KEYS: ReadonlySet = new Set([ + 'thresholdChars', + 'headChars', + 'tailChars', +]) + +/** + * Count Unicode code points without splitting surrogate pairs. + * @param text - text to measure. + * @returns the Unicode code-point count. + */ +export function codePointLength(text: string): number { + return Array.from(text).length +} + +/** + * Resolve and validate pruning budgets. + * @param config - raw plugin configuration. + * @returns a detached deeply immutable configuration. + */ +export function resolveConfig(config: ToolResultPruneConfig = {}): ResolvedConfig { + for (const key of Object.keys(config)) { + if (!CONFIG_KEYS.has(key)) { + throw new Error( + `ToolResultPruneConfig: unknown key "${key}" ` + + '(allowed: thresholdChars, headChars, tailChars)', + ) + } + } + + const resolved: ResolvedConfig = { + thresholdChars: config.thresholdChars ?? DEFAULTS.thresholdChars, + headChars: config.headChars ?? DEFAULTS.headChars, + tailChars: config.tailChars ?? DEFAULTS.tailChars, + } + assertPositiveInteger('thresholdChars', resolved.thresholdChars) + assertNonNegativeInteger('headChars', resolved.headChars) + assertNonNegativeInteger('tailChars', resolved.tailChars) + + const emittedChars = resolved.headChars + + codePointLength(PRUNE_MARKER) + + resolved.tailChars + if (emittedChars > resolved.thresholdChars) { + throw new Error( + `ToolResultPruneConfig: headChars + marker + tailChars (${emittedChars}) ` + + `must be at most thresholdChars (${resolved.thresholdChars})`, + ) + } + return deepFreeze(structuredClone(resolved)) +} + +function assertPositiveInteger(name: string, value: number): void { + if (!Number.isInteger(value) || value <= 0) { + throw new Error(`ToolResultPruneConfig: ${name} (${value}) must be a positive integer`) + } +} + +function assertNonNegativeInteger(name: string, value: number): void { + if (!Number.isInteger(value) || value < 0) { + throw new Error(`ToolResultPruneConfig: ${name} (${value}) must be a non-negative integer`) + } +} diff --git a/packages/compact/tool-result-prune/src/index.ts b/packages/compact/tool-result-prune/src/index.ts new file mode 100644 index 0000000000..287b0f2500 --- /dev/null +++ b/packages/compact/tool-result-prune/src/index.ts @@ -0,0 +1,157 @@ +/** + * Replay-safe, model-free tool-result pruning service. + * + * @module @deepseek-ai/dsh-tool-result-prune + */ + +import { Context, Service } from 'cordis' +import z from 'schemastery' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import { codePointLength, DEFAULTS, PRUNE_MARKER, resolveConfig } from './config.ts' +import type { + PrunedEntry, + PruneResult, + ResolvedConfig, + ToolResultPruneConfig, +} from './types.ts' + +export { codePointLength, DEFAULTS, PRUNE_MARKER, resolveConfig } from './config.ts' +export type { + PrunedEntry, + PruneResult, + ResolvedConfig, + ToolResultPruneConfig, +} from './types.ts' + +declare module 'cordis' { + interface Context { + toolResultPrune: ToolResultPruneService + } +} + +interface SnapshotCandidate { + readonly seq: number + readonly event: SessionEvent<'tool/result'> +} + +/** Deterministic head/middle/tail pruning for current tool-result surface nodes. */ +export class ToolResultPruneService extends Service { + static Config: z = z.object({ + thresholdChars: z.number().step(1).min(1).default(DEFAULTS.thresholdChars), + headChars: z.number().step(1).min(0).default(DEFAULTS.headChars), + tailChars: z.number().step(1).min(0).default(DEFAULTS.tailChars), + }) + + /** Resolved and immutable character budgets. */ + readonly config: ResolvedConfig + + constructor(ctx: Context, config: ToolResultPruneConfig = {}) { + super(ctx, 'toolResultPrune') + this.config = resolveConfig(config) + } + + /** + * Measure text content in Unicode code points; non-text blocks cost zero. + * @param blocks - tool-result content to measure. + * @returns total Unicode code points across text blocks. + */ + measureContent(blocks: readonly ContentBlock[]): number { + let chars = 0 + for (const block of blocks) { + if (block.type === 'text') chars += codePointLength(block.text) + } + return chars + } + + /** + * Replace an over-budget text middle while retaining rich-block order. + * Text slicing is by Unicode code point, not UTF-16 code unit, so a retained + * boundary cannot split a surrogate pair. Grapheme clusters may still split. + * @param blocks - original tool-result content. + * @returns pruned content, or `null` when the text is within budget. + */ + pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null { + const totalChars = this.measureContent(blocks) + if (totalChars <= this.config.thresholdChars) return null + + const removedStart = this.config.headChars + const removedEnd = totalChars - this.config.tailChars + const pruned: ContentBlock[] = [] + let consumed = 0 + let markerInserted = false + + for (const block of blocks) { + if (block.type !== 'text') { + pruned.push(block) + continue + } + + const points = Array.from(block.text) + const blockStart = consumed + const blockEnd = blockStart + points.length + const headEnd = Math.min(points.length, Math.max(0, removedStart - blockStart)) + const tailStart = Math.min(points.length, Math.max(0, removedEnd - blockStart)) + const intersectsRemoved = blockStart < removedEnd && blockEnd > removedStart + const marker = intersectsRemoved && !markerInserted ? PRUNE_MARKER : '' + if (marker.length > 0) markerInserted = true + const text = points.slice(0, headEnd).join('') + + marker + + points.slice(tailStart).join('') + if (text.length > 0) pruned.push({ ...block, text }) + consumed = blockEnd + } + + /* v8 ignore next -- totalChars > threshold and valid budgets guarantee a removed text span. */ + if (!markerInserted) throw new Error('tool-result prune: failed to locate the removed text span') + const charsAfter = this.measureContent(pruned) + /* v8 ignore next -- config validation fixes the emitted head + marker + tail budget. */ + if (charsAfter > this.config.thresholdChars || charsAfter >= totalChars) { + throw new Error('tool-result prune: replacement must be smaller and within threshold') + } + return pruned + } + + /** + * Prune every over-budget tool result from one stable current-surface snapshot. + * Each replacement preserves the complete event data except for `content`, + * and points at the shadowed node for durable provenance and replay. + * @param session - session whose current surface is rewritten. + * @returns landed replacements and aggregate Unicode-code-point savings. + */ + pruneSession(session: Session): PruneResult { + const candidates: SnapshotCandidate[] = [] + for (const node of [...session.surface.nodes]) { + const event = session.events[node.seq] + /* v8 ignore next -- surface seqs are validated contiguous log references. */ + if (event?.type === 'tool/result') candidates.push({ seq: node.seq, event }) + } + + const pruned: PrunedEntry[] = [] + let charsRemoved = 0 + for (const { seq, event } of candidates) { + const content = this.pruneContent(event.data.content) + if (content === null) continue + const charsBefore = this.measureContent(event.data.content) + const charsAfter = this.measureContent(content) + const replacement = session.append('tool/result', { + ...event.data, + content, + }, { + surfaceOp: { op: 'replace', start: seq, end: seq }, + sourceEventSeqs: [seq], + }) + pruned.push({ + originalSeq: seq, + replacementSeq: replacement.seq, + callId: event.data.callId, + charsBefore, + charsAfter, + }) + charsRemoved += charsBefore - charsAfter + } + return { pruned, charsRemoved } + } +} + +export default ToolResultPruneService diff --git a/packages/compact/tool-result-prune/src/types.ts b/packages/compact/tool-result-prune/src/types.ts new file mode 100644 index 0000000000..f9dd846f35 --- /dev/null +++ b/packages/compact/tool-result-prune/src/types.ts @@ -0,0 +1,40 @@ +import type { CallId } from '@deepseek-ai/dsh-llm' + +/** Character-budget policy for deterministic tool-result pruning. */ +export interface ToolResultPruneConfig { + /** Prune when total text exceeds this many Unicode code points. Defaults to `8192`. */ + thresholdChars?: number + /** Maximum leading Unicode code points retained. Defaults to `4096`. */ + headChars?: number + /** Maximum trailing Unicode code points retained. Defaults to `1024`. */ + tailChars?: number +} + +/** Validated, detached, deeply immutable pruning configuration. */ +export interface ResolvedConfig { + readonly thresholdChars: number + readonly headChars: number + readonly tailChars: number +} + +/** Provenance and size accounting for one landed surface replacement. */ +export interface PrunedEntry { + /** Full-fidelity tool-result event shadowed by the replacement. */ + readonly originalSeq: number + /** Newly appended pruned tool-result event. */ + readonly replacementSeq: number + /** Tool call shared by the original and replacement. */ + readonly callId: CallId + /** Original text size in Unicode code points. */ + readonly charsBefore: number + /** Replacement text size in Unicode code points. */ + readonly charsAfter: number +} + +/** Aggregate outcome of one stable-surface pruning pass. */ +export interface PruneResult { + /** Replacements in the snapshotted surface order. */ + readonly pruned: readonly PrunedEntry[] + /** Total Unicode code points removed across replacements. */ + readonly charsRemoved: number +} diff --git a/packages/compact/tool-result-prune/tests/loader-composition.spec.ts b/packages/compact/tool-result-prune/tests/loader-composition.spec.ts new file mode 100644 index 0000000000..fef9326d2a --- /dev/null +++ b/packages/compact/tool-result-prune/tests/loader-composition.spec.ts @@ -0,0 +1,67 @@ +import { mkdtemp, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { pathToFileURL } from 'node:url' +import { afterEach, describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import Loader from '@cordisjs/plugin-loader' +import Include from '@cordisjs/plugin-include' +import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' + +let root: string | undefined +let context: Context | undefined + +afterEach(async () => { + await context?.fiber.dispose() + context = undefined + if (root !== undefined) await rm(root, { recursive: true, force: true }) + root = undefined +}) + +describe('tool-result-prune real Loader composition', () => { + it('loads and resolves the flat YAML plugin shape', async () => { + root = await mkdtemp(join(tmpdir(), 'dsh-tool-result-prune-loader-')) + const configPath = join(root, 'cordis.yml') + await writeFile(configPath, [ + "- name: '@deepseek-ai/dsh-tool-result-prune'", + ' config:', + ' thresholdChars: 100', + ' headChars: 20', + ' tailChars: 10', + '', + ].join('\n')) + + context = new Context() + context.baseUrl = pathToFileURL(root).href + '/' + await context.plugin(Loader) + context.loader.builtins.include = Include + context.loader.internal = { + version: 'v2', + async import(specifier: string) { + if (specifier !== '@deepseek-ai/dsh-tool-result-prune') { + throw new Error(`unexpected Loader import: ${specifier}`) + } + return ToolResultPruneService + }, + } as unknown as NonNullable + await context.loader.create({ + name: 'cordis:include', + config: { path: pathToFileURL(configPath).href }, + }) + await context.loader.await() + + expect(context.get('toolResultPrune')).toBeInstanceOf(ToolResultPruneService) + expect(context.toolResultPrune.config).toEqual({ + thresholdChars: 100, + headChars: 20, + tailChars: 10, + }) + }) + + it('rejects stale config after plugin schema normalization', async () => { + context = new Context() + await expect(context.plugin(ToolResultPruneService, { + maxChars: 100, + } as never)).rejects.toThrow(/unknown key "maxChars"/) + }) +}) diff --git a/packages/compact/tool-result-prune/tests/tool-result-prune.spec.ts b/packages/compact/tool-result-prune/tests/tool-result-prune.spec.ts new file mode 100644 index 0000000000..235ecdab52 --- /dev/null +++ b/packages/compact/tool-result-prune/tests/tool-result-prune.spec.ts @@ -0,0 +1,237 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { CallId } from '@deepseek-ai/dsh-llm' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import SessionStore, { Session, SessionId } from '@deepseek-ai/dsh-session' +import type { SurfaceEvent } from '@deepseek-ai/dsh-session' +import * as Invariants from '@deepseek-ai/dsh-invariants' +import ToolResultPruneService, { + codePointLength, + DEFAULTS, + PRUNE_MARKER, + resolveConfig, +} from '@deepseek-ai/dsh-tool-result-prune' +import type { ToolResultPruneConfig } from '@deepseek-ai/dsh-tool-result-prune' + +const SMALL: ToolResultPruneConfig = { + thresholdChars: 50, + headChars: 4, + tailChars: 3, +} + +function service(config: ToolResultPruneConfig = SMALL): ToolResultPruneService { + return new ToolResultPruneService(new Context(), config) +} + +function appendToolStep( + session: Session, + turn: number, + call: string, + content: ContentBlock[], + extra: Record = {}, +): number { + const callId = CallId(call) + session.append('turn/start', { + turn, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + session.append('step/start', { turn, step: 1 }) + session.append('assistant/message', { + turn, + step: 1, + content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }], + }, { surfaceOp: 'append' }) + session.append('tool/call', { turn, step: 1, callId, name: 'bash', arguments: '{}' }) + const result = session.append('tool/result', { + turn, + step: 1, + callId, + content, + isError: false, + ...extra, + }, { surfaceOp: 'append' }) + session.append('step/end', { turn, step: 1 }) + session.append('turn/end', { turn, reason: { kind: 'completed' } }) + return result.seq +} + +describe('tool-result pruning configuration', () => { + it('resolves detached immutable defaults and partial overrides', () => { + const raw = { thresholdChars: 100, headChars: 20, tailChars: 10 } + const resolved = resolveConfig(raw) + raw.headChars = 1 + expect(resolved).toEqual({ thresholdChars: 100, headChars: 20, tailChars: 10 }) + expect(Object.isFrozen(resolved)).toBe(true) + expect(DEFAULTS).toEqual({ thresholdChars: 8192, headChars: 4096, tailChars: 1024 }) + expect(Object.isFrozen(DEFAULTS)).toBe(true) + }) + + it('rejects stale keys, invalid scalars, and an output budget above threshold', () => { + const bad = [ + [{ thresholdChars: 0 }, /thresholdChars .* positive integer/], + [{ headChars: -1 }, /headChars .* non-negative integer/], + [{ tailChars: 1.5 }, /tailChars .* non-negative integer/], + [{ thresholdChars: 50, headChars: 20, tailChars: 20 }, /headChars \+ marker \+ tailChars/], + [{ threshold: 10 }, /unknown key "threshold"/], + ] as Array<[unknown, RegExp]> + for (const [config, pattern] of bad) { + expect(() => resolveConfig(config as ToolResultPruneConfig)).toThrow(pattern) + } + }) +}) + +describe('ToolResultPruneService content transform', () => { + it('measures text code points only and skips content within threshold', () => { + const prune = service() + const blocks = [ + { type: 'text', text: 'a😀b' }, + { type: 'reasoning', text: 'not measured' }, + ] satisfies ContentBlock[] + expect(prune.measureContent(blocks)).toBe(3) + expect(prune.pruneContent(blocks)).toBeNull() + expect(codePointLength('a😀b')).toBe(3) + }) + + it('keeps configured head and tail without splitting surrogate pairs', () => { + const prune = service() + const result = prune.pruneContent([{ type: 'text', text: '😀'.repeat(60) }]) + expect(result).toEqual([{ + type: 'text', + text: `${'😀'.repeat(4)}${PRUNE_MARKER}${'😀'.repeat(3)}`, + }]) + expect(prune.measureContent(result!)).toBeLessThanOrEqual(50) + expect(result![0]).toMatchObject({ type: 'text' }) + expect((result![0] as { text: string }).text).not.toContain('\uFFFD') + }) + + it('preserves non-text blocks and their relative ordering across removed text', () => { + const prune = service() + const reasoning: ContentBlock = { type: 'reasoning', text: 'private-rich-block' } + const call: ContentBlock = { + type: 'tool-call', + id: CallId('nested'), + name: 'nested', + arguments: '{}', + } + const result = prune.pruneContent([ + { type: 'text', text: 'A'.repeat(40) }, + reasoning, + { type: 'text', text: 'B'.repeat(30) }, + call, + { type: 'text', text: 'C'.repeat(30) }, + ]) + expect(result).toEqual([ + { type: 'text', text: `AAAA${PRUNE_MARKER}` }, + reasoning, + call, + { type: 'text', text: 'CCC' }, + ]) + expect(prune.measureContent(result!)).toBeLessThanOrEqual(50) + }) + + it('supports zero-sized head and tail while still shrinking', () => { + const prune = service({ + thresholdChars: codePointLength(PRUNE_MARKER), + headChars: 0, + tailChars: 0, + }) + const result = prune.pruneContent([{ type: 'text', text: 'x'.repeat(100) }]) + expect(result).toEqual([{ type: 'text', text: PRUNE_MARKER }]) + expect(prune.measureContent(result!)).toBe(prune.config.thresholdChars) + }) +}) + +describe('ToolResultPruneService session transaction', () => { + it('prunes a stable snapshot, preserves all data, and records provenance', () => { + const session = new Session(SessionId('preserve')) + const originalSeq = appendToolStep(session, 1, 'one', [{ + type: 'text', + text: 'x'.repeat(100), + }], { + isError: true, + error: { name: 'ExitError', code: 'EXIT_1' }, + meta: { diff: ['a', 'b'] }, + futureField: { nested: true }, + }) + session.append('turn/start', { + turn: 2, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + + const result = service().pruneSession(session) + expect(result.pruned).toHaveLength(1) + expect(result.charsRemoved).toBeGreaterThan(0) + const entry = result.pruned[0]! + expect(entry).toMatchObject({ originalSeq, callId: CallId('one'), charsBefore: 100 }) + expect(entry.charsAfter).toBeLessThanOrEqual(50) + + const original = session.events[originalSeq]! + const replacement = session.events[entry.replacementSeq]! as SurfaceEvent + expect(original).toMatchObject({ + type: 'tool/result', + data: { content: [{ type: 'text', text: 'x'.repeat(100) }] }, + }) + expect(replacement).toMatchObject({ + type: 'tool/result', + data: { + turn: 1, + step: 1, + callId: CallId('one'), + isError: true, + error: { name: 'ExitError', code: 'EXIT_1' }, + meta: { diff: ['a', 'b'] }, + futureField: { nested: true }, + }, + surfaceOp: { op: 'replace', start: originalSeq, end: originalSeq }, + sourceEventSeqs: [originalSeq], + }) + expect(session.surface.nodes.some(node => node.seq === originalSeq)).toBe(false) + }) + + it('prunes multiple results, skips short ones, and converges in one pass', () => { + const session = new Session(SessionId('multiple')) + appendToolStep(session, 1, 'a', [{ type: 'text', text: 'A'.repeat(100) }]) + appendToolStep(session, 2, 'b', [{ type: 'text', text: 'short' }]) + appendToolStep(session, 3, 'c', [{ type: 'text', text: 'C'.repeat(80) }]) + session.append('turn/start', { + turn: 4, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + const prune = service() + const first = prune.pruneSession(session) + const second = prune.pruneSession(session) + expect(first.pruned.map(entry => entry.callId)).toEqual([CallId('a'), CallId('c')]) + expect(first.charsRemoved).toBe( + first.pruned.reduce((sum, entry) => sum + entry.charsBefore - entry.charsAfter, 0), + ) + expect(second).toEqual({ pruned: [], charsRemoved: 0 }) + }) + + it('replays to the identical pruned model messages', () => { + const session = new Session(SessionId('replay')) + appendToolStep(session, 1, 'a', [{ type: 'text', text: 'A'.repeat(100) }]) + session.append('turn/start', { + turn: 2, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + service().pruneSession(session) + const replay = new Session(session.id, [...session.events]) + expect(replay.deriveMessages()).toEqual(session.deriveMessages()) + expect(replay.surface.replaceGeneration).toBe(session.surface.replaceGeneration) + }) + + it('runs under real invariants between closed steps but not outside a turn', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(Invariants) + const prune = new ToolResultPruneService(ctx, SMALL) + const session = ctx.sessions.create(SessionId('invariants')) + appendToolStep(session, 1, 'a', [{ type: 'text', text: 'A'.repeat(100) }]) + expect(() => prune.pruneSession(session)).toThrow(/outside any open turn/) + session.append('turn/start', { + turn: 2, + trigger: { kind: 'message', source: { kind: 'user' } }, + }) + expect(() => prune.pruneSession(session)).not.toThrow() + }) +}) diff --git a/packages/compact/tool-result-prune/tsconfig.json b/packages/compact/tool-result-prune/tsconfig.json new file mode 100644 index 0000000000..e021fa336e --- /dev/null +++ b/packages/compact/tool-result-prune/tsconfig.json @@ -0,0 +1,15 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": ["src"], + "references": [ + { "path": "../../../vendor/cosmokit" }, + { "path": "../../../vendor/cordis" }, + { "path": "../../../vendor/schemastery" }, + { "path": "../../llm/llm" }, + { "path": "../../core/session" } + ] +} diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 89103923e2..e257991832 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -230,6 +230,15 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'estimateMessage(message: Message): number', ], }, + { + key: 'toolResultPrune', + summary: 'Deterministic head/middle/tail pruning for current tool-result surface nodes.', + methods: [ + 'measureContent(blocks: readonly ContentBlock[]): number', + 'pruneContent(blocks: readonly ContentBlock[]): ContentBlock[] | null', + 'pruneSession(session: Session): PruneResult', + ], + }, { key: 'tools', summary: 'Tool registry and execution pipeline.', @@ -793,6 +802,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'PromptSection', declaration: 'export interface PromptSection {\n readonly name: string;\n readonly order: number;\n readonly text: string | ((context: AssembleContext) => string);\n}', }, + { + name: 'PrunedEntry', + declaration: 'export interface PrunedEntry {\n readonly originalSeq: number;\n readonly replacementSeq: number;\n readonly callId: CallId;\n readonly charsBefore: number;\n readonly charsAfter: number;\n}', + }, + { + name: 'PruneResult', + declaration: 'export interface PruneResult {\n readonly pruned: readonly PrunedEntry[];\n readonly charsRemoved: number;\n}', + }, { name: 'ReasoningBlock', declaration: 'export interface ReasoningBlock {\n type: \'reasoning\';\n text: string;\n}', diff --git a/packages/core/tools/tests/gen-tool-catalog.spec.ts b/packages/core/tools/tests/gen-tool-catalog.spec.ts index 1ba64f6326..8657dca3ca 100644 --- a/packages/core/tools/tests/gen-tool-catalog.spec.ts +++ b/packages/core/tools/tests/gen-tool-catalog.spec.ts @@ -69,6 +69,11 @@ describe('gen-tool-catalog assertManifestComplete', () => { // is unlisted, so the guard must fire and name them. expect(() => { assertManifestComplete([]) }).toThrow(/not in the boot manifest/) expect(() => { assertManifestComplete([]) }).toThrow(/tool-bash/) + try { + assertManifestComplete([]) + } catch (error) { + expect(String(error)).not.toContain('tool-result-prune') + } }) }) diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index 43e2b93bef..5ef2139db2 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -31,7 +31,7 @@ Session log (per session): - **turns pair and nest** — `turn/start` opens a turn, `turn/end` closes the matching one; no overlapping turns. - **steps nest in turns** — `step/start` opens a step in the open turn; `step/end` closes the matching step. - **chunks belong to an open step** — `step/start` precedes its `assistant/chunk`s. -- **a `tool/result` needs a prior `tool/call`** — but NOT the converse: a `tool/call` may have no result (a thrown tool-execution pipeline step ends the turn with no `tool/result`, which is legal). +- **an appended `tool/result` needs a prior `tool/call`** — fresh `surfaceOp: 'append'` results name the open step and consume its pending call, while a provenance-backed single-node `replace` is a turn-enclosed surface rewrite of an already-executed result. A `tool/call` may still have no result when the execution pipeline throws. - **provenance sources are valid and unambiguous** — `sourceEventSeqs` contains unique earlier known seqs; only `assistant/message` may carry an explicit empty list, which denotes a known empty provider stream rather than absent legacy provenance. Agent status (per agent): diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index 14134984ba..f33f7b4cec 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -232,6 +232,17 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr break } case 'tool/result': { + // A replacement rewrites an already-executed result whose recorded + // turn/step can be closed. Surface provenance above validates the rewrite; + // only fresh appends consume an open step's pending call. + if (se.surfaceOp !== undefined && se.surfaceOp !== 'append') { + if (trace.openTurn === null) { + throw new InvariantError( + 'tool/result surface replacement appended outside any open turn', + ) + } + break + } requireOpenStep(trace, 'tool/result', event.data.turn, event.data.step) // A result needs a prior matching call in the same step. (The converse // does NOT hold: a call may have no result — a throwing tool-execution diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index af84c569b9..986cd93e7c 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -189,6 +189,19 @@ describe('session-log invariants', () => { .toThrow(/no prior tool\/call/) }) + it('keeps fresh tool-result appends open-step and pending-call checked', async () => { + const { ctx } = await setup() + const session = ctx.sessions.create() + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + expect(() => session.append('tool/result', { + turn: 1, + step: 1, + callId: CallId('closed'), + content: [], + isError: false, + }, { surfaceOp: 'append' })).toThrow(/open is turn 1\/step null/) + }) + it('allows a synthetic interrupted tool/result from crash repair without a prior tool/call event', async () => { const { ctx } = await setup() const session = ctx.sessions.create() @@ -487,6 +500,38 @@ describe('surface invariants', () => { // no throw — well-formed replace op }) + it('treats a provenance-backed tool-result replacement as a turn-enclosed rewrite', async () => { + const { ctx } = await setup() + const session = ctx.sessions.create() + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('step/start', { turn: 1, step: 1 }) + session.append('tool/call', { + turn: 1, + step: 1, + callId: CallId('rewrite'), + name: 'echo', + arguments: '{}', + }) + const original = session.append('tool/result', { + turn: 1, + step: 1, + callId: CallId('rewrite'), + content: [{ type: 'text', text: 'original' }], + isError: false, + }, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) + + expect(() => session.append('tool/result', { + ...original.data, + content: [{ type: 'text', text: 'pruned' }], + }, { + surfaceOp: { op: 'replace', start: original.seq, end: original.seq }, + sourceEventSeqs: [original.seq], + })).not.toThrow() + }) + it('accepts known-empty assistant provenance and rejects empty provenance elsewhere', async () => { const { ctx } = await setup() const session = ctx.sessions.create() diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 334a95346d..b0935bde01 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -256,6 +256,9 @@ importers: '@deepseek-ai/dsh-token-meter': specifier: workspace:^ version: link:../../llm/token-meter + '@deepseek-ai/dsh-tool-result-prune': + specifier: workspace:^ + version: link:../tool-result-prune '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -263,6 +266,31 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) + packages/compact/tool-result-prune: + dependencies: + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@cordisjs/plugin-include': + specifier: workspace:^ + version: link:../../../vendor/include + '@cordisjs/plugin-loader': + specifier: workspace:^ + version: link:../../../vendor/loader + '@deepseek-ai/dsh-invariants': + specifier: workspace:^ + version: link:../../support/invariants + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) + packages/context/time-context: dependencies: schemastery: @@ -2112,6 +2140,9 @@ importers: '@deepseek-ai/dsh-tool-fs': specifier: workspace:^ version: link:../../packages/fs/tool-fs + '@deepseek-ai/dsh-tool-result-prune': + specifier: workspace:^ + version: link:../../packages/compact/tool-result-prune '@deepseek-ai/dsh-tool-skill': specifier: workspace:^ version: link:../../packages/skill/tool-skill diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index 297a76d8d5..a436f859fc 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -31,6 +31,7 @@ "@deepseek-ai/dsh-jsonrpc-demo": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-token-meter": "workspace:^", + "@deepseek-ai/dsh-tool-result-prune": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", "@deepseek-ai/dsh-llm-pi-ai": "workspace:^", "@deepseek-ai/dsh-permission": "workspace:^", diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index e532eaa3c3..db6acf2c43 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -94,6 +94,14 @@ const SERVICE_ROLES: ServiceRole[] = [ consumers: ['compact-basic'], note: 'Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements.', }, + { + key: 'toolResultPrune', + pkg: 'tool-result-prune', + title: 'Model-free tool-result pruning', + mode: 'core', + consumers: ['compact-basic'], + note: 'Rewrites oversized current tool results through replayable single-node surface replacements before summary compaction.', + }, { key: 'sessions', pkg: 'session', @@ -415,7 +423,7 @@ const APP_EXAMPLES = [ title: 'Coding Agent App Composition', label: 'examples/coding-agent', config: 'examples/coding-agent/cordis.yml', - summary: 'The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', + summary: 'The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, tool-result pruning, compaction, and both subagent transports on top of the stdio app package.', }, { id: 'cordis', @@ -851,7 +859,7 @@ function renderLifecycle(): string { '', 'The `assistant/message` edge records every successful provider call, including content-less and `max-tokens` finishes. Empty content stays out of derived history while the durable anchor retains usage and exact chunk provenance, including an explicit empty source set.', '', - '`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Recovery compacts between the closed failed step and a fresh retry step, and returns retry only when the surface replacement generation advances; otherwise the original request error remains authoritative.', + '`dsh-compact-basic` uses `agent/post-step` for pressure after those durable facts and `agent/request-error` only for canonical context overflow. Once either trigger qualifies, optional tool-result pruning runs before summary selection. Recovery works between the closed failed step and a fresh retry step, and returns retry only when pruning or summarization advances the surface replacement generation; otherwise the original request error remains authoritative.', '', 'SDK users that need replayable transcript data should consume `session/event`; `agent/*` is the live coordination surface for queue/status, prompt interception, request shaping, steering, continuation, and errors.', '', diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 3e3a0ce81b..4a0efe66a7 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -1,8 +1,9 @@ /** * Generate `docs/tool-catalog.md` from schemas collected by booting each tool * plugin. Runtime registration is the source of truth for computed schemas; - * the manifest is checked against every on-disk `tool-*` package. `--check` - * verifies the committed artifact. Rationale and ownership live in + * the manifest is checked against every on-disk model-facing `tool-*` package; + * non-model service packages with that prefix are explicitly excluded. + * `--check` verifies the committed artifact. Rationale and ownership live in * `docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md`. */ @@ -38,6 +39,9 @@ import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' const root = resolve(import.meta.dirname, '..') const OUT = 'docs/tool-catalog.md' +/** `tool-*` leaves that are runtime services, not contributors to `ctx.tools`. */ +const NON_MODEL_TOOL_PACKAGES = new Set(['tool-result-prune']) + /** * Tool package plus its hand-maintained boot recipe. The caller mounts the * prompt and registry; each recipe supplies only package-specific seams and @@ -77,9 +81,10 @@ interface ToolPackage { } /** - * The boot manifest: every shipped tool package (a `tool-*` leaf under - * `packages/`). Ordered by package name (the render order); the completeness - * guard proves it is exhaustive against the on-disk glob. + * The boot manifest: every shipped model-facing tool package (a `tool-*` leaf + * under `packages/`, excluding {@link NON_MODEL_TOOL_PACKAGES}). Ordered by + * package name (the render order); the completeness guard proves it is + * exhaustive against the filtered on-disk glob. */ const TOOL_PACKAGES: ToolPackage[] = [ { @@ -256,8 +261,9 @@ interface CatalogPackage { export type ToolCatalog = CatalogPackage[] /** - * Assert the boot manifest covers every shipped tool package on disk (a - * `tool-*` leaf under `packages/`). + * Assert the boot manifest covers every shipped model-facing tool package on + * disk (a `tool-*` leaf under `packages/`, excluding explicit service-only + * entries in {@link NON_MODEL_TOOL_PACKAGES}). * Booting has no source declaration to enumerate, so this glob restores the * "a new tool cannot be silently undocumented" guarantee: an unlisted package * fails the generator (and the freshness gate) until it is added to @@ -266,7 +272,10 @@ export type ToolCatalog = CatalogPackage[] * `scanRoot` defaults to the repo root; a test may point it at a fixture tree. */ export function assertManifestComplete(packages: ToolPackage[] = TOOL_PACKAGES, scanRoot: string = root): void { - const onDisk = globSync('packages/*/tool-*', { cwd: scanRoot }).map(p => basename(p)).sort() + const onDisk = globSync('packages/*/tool-*', { cwd: scanRoot }) + .map(p => basename(p)) + .filter(dir => !NON_MODEL_TOOL_PACKAGES.has(dir)) + .sort() const listed = new Set(packages.map(p => p.dir)) const missing = onDisk.filter(dir => !listed.has(dir)) if (missing.length > 0) { @@ -339,9 +348,9 @@ export function render(catalog: ToolCatalog): string { '', 'Every model-facing tool a shipped plugin contributes to `ctx.tools`: the `name`, `description`, and JSON-Schema `parameters` the model receives via the system-prompt assembly. It complements the cordis [events](cordis-catalog/events.md) & [services](cordis-catalog/services.md) catalogs (the wiring a plugin listens to and calls) and [core-data-structures/](core-data-structures/core.md) (the types those signatures move) — this page is the *tools* the agent is offered.', '', - 'This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator\'s boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md).', + 'This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any model-facing package is missing from the generator\'s boot manifest; service-only packages that share the prefix are explicitly excluded. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md).', '', - 'Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`\'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog\'s packages-only scope.', + 'Scope: shipped model-facing product tools under `packages/*/tool-*`, each booted with its DEFAULT config. Runtime service packages such as `tool-result-prune` do not register `ctx.tools` schemas and are explicitly excluded. The registered tool NAME can be a load-time config (e.g. `tool-subagent`\'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog\'s packages-only scope.', '', '## Tool Package Map', '', diff --git a/tsconfig.build.json b/tsconfig.build.json index 40d57030cb..a099fc3a23 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -38,6 +38,7 @@ { "path": "./packages/code-runtime/code-runtime-worker" }, { "path": "./packages/compact/compact" }, { "path": "./packages/compact/compact-basic" }, + { "path": "./packages/compact/tool-result-prune" }, { "path": "./packages/llm/llm-deepseek" }, { "path": "./packages/llm/llm-pi-ai" }, { "path": "./packages/bash/bash-local" }, diff --git a/tsconfig.json b/tsconfig.json index f39c097809..1decda2db0 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -60,6 +60,7 @@ { "path": "./packages/fs/tool-fs" }, { "path": "./packages/compact/compact" }, { "path": "./packages/compact/compact-basic" }, + { "path": "./packages/compact/tool-result-prune" }, { "path": "./packages/web/web" }, { "path": "./packages/web/web-search-exa" }, { "path": "./packages/web/web-search-perplexity" }, From 171bae5c20ee23abfafaf7a244e13ce1a2692649 Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 18:28:31 +0800 Subject: [PATCH 149/323] fix(compact): harden pruning integration (round 2) --- docs/architecture.md | 4 +- docs/core-data-structures/compaction.md | 2 +- ...n-pressure-and-overflow-recovery.i18n.yaml | 4 +- ...mpaction-pressure-and-overflow-recovery.md | 6 +- ...ction-pressure-and-overflow-recovery.zh.md | 6 +- packages/compact/compact-basic/README.md | 4 +- packages/compact/compact-basic/src/index.ts | 19 +++- .../compact-basic/tests/compact-basic.spec.ts | 45 +++++++++ packages/support/invariants/README.md | 2 +- packages/support/invariants/src/index.ts | 73 ++++++++++---- .../invariants/tests/invariants.spec.ts | 96 +++++++++++++++---- packages/ui/acp/README.md | 2 +- packages/ui/acp/acp-feature-support.md | 2 +- packages/ui/acp/src/index.ts | 7 +- packages/ui/acp/tests/load.spec.ts | 47 +++++++++ packages/ui/acp/tests/stream-update.spec.ts | 74 +++++++++++++- packages/ui/stdio/README.md | 2 +- packages/ui/stdio/src/index.ts | 4 + packages/ui/stdio/tests/stdio.spec.ts | 37 +++++++ 19 files changed, 372 insertions(+), 64 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index d2289ff731..ff45d38389 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -107,11 +107,11 @@ Each step renders one prompt assembly. Plugins contribute ordered sections, tool Post-tool context follows all results, preserving call/result adjacency. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering while the step signal remains open. Leftover steering becomes next-turn input. `agent/turn-stop` is terminal through close and flush: later steering is discarded, while ordinary queued prompts survive. -When loaded, `dsh-compact-basic` consumes that post-step checkpoint for `ctx.tokenMeter` pressure under the actual routed header. Once pressure or canonical context overflow qualifies, it runs optional `ctx.toolResultPrune` rewriting before summary selection and remeasures the replayed surface. Overflow recovery authorizes retry after either pruning or tool-balanced summary compaction advances `surface.replaceGeneration`. The same turn signal owns both paths. +When loaded, `dsh-compact-basic` consumes that post-step checkpoint for `ctx.tokenMeter` pressure under the actual routed header. Once pressure or canonical context overflow qualifies, it runs optional `ctx.toolResultPrune` rewriting before summary selection and remeasures the replayed surface. Overflow recovery authorizes retry after either pruning or tool-balanced summary compaction advances `surface.replaceGeneration`, including when later summary work fails after a prune. The same turn signal owns both paths, and cancellation still wins. ### Failure Boundaries -The turn is the containment boundary. `LlmService` preserves and privately tags errors from final adapter selection, dispatch, and iteration. Those errors and terminal in-band error/aborted finishes close the failed step before `agent/request-error`; retry reconstructs the next numbered step from the log, while decline or failed recovery preserves the provider error. Attempts count consecutive failures and reset after success. +The turn is the containment boundary. `LlmService` preserves and privately tags errors from final adapter selection, dispatch, and iteration. Those errors and terminal in-band error/aborted finishes close the failed step before `agent/request-error`; retry reconstructs the next numbered step from the log, while decline or recovery failure before any replacement preserves the provider error. Attempts count consecutive failures and reset after success. Prompt, middleware, result, tool, post-step, and continuation failures remain ordinary `agent/error` failures. Cancellation and disposal beat recovery. Durable undispatched tool calls receive synthetic `ABORTED` results, preventing dangling replay. `cancel()` clears queues and aborts active work; disposal awaits quiescence before unregistering. diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 3a008a0b95..e3774b87cd 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -58,6 +58,6 @@ export type CompactionTrigger = 'pressure' | 'context-overflow' `CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration. -Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and authorizes a fresh numbered-step retry only when the surface replacement generation advances. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. +Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and authorizes a fresh numbered-step retry only when the surface replacement generation advances, even if later summary work throws after pruning; cancellation still wins. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. The seam exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for those edge checks. Both validate current surface membership, reject stale or missing seqs and orphan results, and ignore a caller-retained `node.next`; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index bd13a336f1..c8eef0f1c9 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: 99dc7625b8e185464d7a8a1ea8eda5baf0674df7 -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 4f84d4435341005c058e32582e6d26b2a9f29bc1 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: deedb81f8cf75ab80b70e2ef3148ba76d1278886 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 51d28fa243f522eedcac29002670575889d48369 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index 99dc7625b8..deedb81f8c 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -34,9 +34,9 @@ If cancellation lands after assistant tool calls are durable but before all call For `pressure`, compact-basic applies the service-wide threshold and retained-tail policy to one unified `ctx.tokenMeter.measure()` result. Below pressure it returns without pruning. Once pressure qualifies, optional `ctx.toolResultPrune` rewrites oversized current results and compact-basic remeasures through the same meter; safe pressure skips the model call, while remaining pressure selects and summarizes from the pruned surface. The same singleton meter owns range pricing, provenance, shadowed token counts, and non-shrinking-summary rejection. The common defaults remain threshold ratio `0.8`, retained history `floor(contextWindow × 0.16)`, summarization model `''`, `maxTokens: 8192`, `compactionRetries: 1`, and `auto: true`. -For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It prunes first, then chooses the maximal tool-balanced head range while leaving the newest indivisible unit and attempts one shrinking summary compaction under the same signal when a range exists. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` whenever pruning or summarization increases it. A backend returning a result without replacement cannot authorize retry, while pruning-only progress can authorize a retry without a `CompactionResult`. +For canonical overflow, compact-basic bypasses scalar pressure and the normal retained-token budget. It prunes first, then chooses the maximal tool-balanced head range while leaving the newest indivisible unit and attempts one shrinking summary compaction under the same signal when a range exists. The automatic listener snapshots `session.surface.replaceGeneration` and returns `{ action: 'retry' }` whenever pruning or summarization increases it. This remains true when pruning lands before later summary work throws; cancellation still wins. A backend returning a result without replacement cannot authorize retry, while pruning-only progress can authorize a retry without a `CompactionResult`. -`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, a missing routed model, no safe range, no generation change, and recovery throws all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. Cancellation or disposal remains authoritative even if recovery work completes concurrently. +`maxOverflowRetries` is optional and defaults to `1`; `0` disables overflow recovery without disabling pressure. `auto: false` registers neither automatic listener. Noncanonical errors, exhausted attempts, an already-aborted signal, a missing routed model, no safe range, no generation change, and recovery throws before any replacement all delegate to the next listener. With no later recovery, the loop reports the original provider error object and code. A recovery throw after generation advances authorizes retry from durable progress; cancellation or disposal remains authoritative even if recovery work completes concurrently. The default summarizer still resolves explicit configuration, then the latest logged route, then agent options. Because direct `llm/stream` middleware may reroute that auxiliary call, `compact/summary.model` records the final mutable `GenerateOptions.model` observed after dispatch rather than the pre-waterfall candidate. @@ -44,7 +44,7 @@ The default summarizer still resolves explicit configuration, then the latest lo Lifecycle tests pin post-step ordering after durable tool/context/steering work, content-less and max-token successes, final-adapter dispatch/iterator/in-band boundaries, retry numbering, attempt reset, cancellation, disposal, synthetic tool results, and original error identity. -Compact tests pin low-friction service-wide defaults, actual routed-model selection, unlisted-model measurement, unified pressure-and-retention decisions, pressure-gated pruning, pruning-only relief, summarization from pruned input, optional-plugin fallback, pruning-only and summarized overflow recovery, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. +Compact tests pin low-friction service-wide defaults, actual routed-model selection, unlisted-model measurement, unified pressure-and-retention decisions, pressure-gated pruning, pruning-only relief, summarization from pruned input, optional-plugin fallback, pruning-only and summarized overflow recovery, prune-then-summary-failure progress, newest tool-pair retention, non-shrinking rejection, generation proof, caps, disabled listeners, single downstream delegation, and auxiliary summary routing provenance. Real-loop composition covers both thrown and in-band overflow: the failed step closes, compaction lands between attempts, and the next numbered request is reconstructed from the replacement surface. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index 4f84d44353..51d28fa243 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -34,9 +34,9 @@ Status: implemented 对于 `pressure`，compact-basic 把服务级阈值与保留尾部策略应用到一次统一的 `ctx.tokenMeter.measure()` 结果。低于压力时直接返回，不执行剪枝。压力达到条件后，可选的 `ctx.toolResultPrune` 会改写当前表层中过大的工具结果，compact-basic 再通过同一个 meter 重新计量；若压力恢复安全则跳过模型调用，否则从已剪枝表层选择范围并生成摘要。范围定价、来源、被遮蔽 token 数与非缩小摘要拒绝也由同一个单例 meter 完成。通用默认值保持为阈值比例 `0.8`、保留历史 `floor(contextWindow × 0.16)`、摘要模型 `''`、`maxTokens: 8192`、`compactionRetries: 1` 与 `auto: true`。 -对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它先执行剪枝，再在保留最新不可分割单元的同时选择最大的工具配对平衡头部范围；存在范围时，才在同一 signal 下尝试一次缩小摘要压缩。自动监听器先记录 `session.surface.replaceGeneration`，剪枝或摘要让 generation 增加时就返回 `{ action: 'retry' }`。后端若只返回结果但没有替换表层，不能授权重试；只有剪枝取得进展时，即使没有 `CompactionResult` 也可以授权重试。 +对于规范化溢出，compact-basic 绕过标量压力与普通保留 token 预算。它先执行剪枝，再在保留最新不可分割单元的同时选择最大的工具配对平衡头部范围；存在范围时，才在同一 signal 下尝试一次缩小摘要压缩。自动监听器先记录 `session.surface.replaceGeneration`，剪枝或摘要让 generation 增加时就返回 `{ action: 'retry' }`。即使剪枝先落盘而后续摘要工作抛错，这条规则仍然成立；取消依然优先。后端若只返回结果但没有替换表层，不能授权重试；只有剪枝取得进展时，即使没有 `CompactionResult` 也可以授权重试。 -`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失路由模型、没有安全范围、generation 未变化，以及恢复抛错都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。即使恢复工作并发完成，取消或销毁仍具有最终优先级。 +`maxOverflowRetries` 可选且默认为 `1`；`0` 只禁用溢出恢复，不会禁用压力检查。`auto: false` 不注册任何自动监听器。非规范化错误、尝试耗尽、已经中止的 signal、缺失路由模型、没有安全范围、generation 未变化，以及在任何替换之前恢复抛错，都会委托给下一个监听器。若没有后续恢复，循环报告原始提供方错误对象与代码。generation 增加后的恢复抛错会基于持久进展授权重试；即使恢复工作并发完成，取消或销毁仍具有最终优先级。 默认摘要器仍依次解析显式配置、最近记录的路由与 agent options。因为直接 `llm/stream` 中间件可以重新路由该辅助调用，`compact/summary.model` 记录分发后最终可变的 `GenerateOptions.model`，而不是 waterfall 之前的候选值。 @@ -44,7 +44,7 @@ Status: implemented 生命周期测试固定 post-step 位于持久工具、上下文与 steering 工作之后，覆盖无内容与达到 token 上限的成功、最终适配器分发/迭代器/带内边界、重试编号、尝试重置、取消、销毁、合成工具结果与原始错误身份。 -压缩测试固定低摩擦服务级默认值、实际路由模型选择、未列出模型计量、统一压力与保留决策、压力门控剪枝、剪枝独立解除压力、从已剪枝输入生成摘要、可选插件回退、仅剪枝与剪枝后摘要两类溢出恢复、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 +压缩测试固定低摩擦服务级默认值、实际路由模型选择、未列出模型计量、统一压力与保留决策、压力门控剪枝、剪枝独立解除压力、从已剪枝输入生成摘要、可选插件回退、仅剪枝与剪枝后摘要两类溢出恢复、剪枝后摘要失败的持久进展、最新工具配对保留、非缩小拒绝、generation 证明、上限、禁用监听器、单次下游委托与辅助摘要路由来源。真实循环组合同时覆盖抛出式和带内溢出：失败 step 关闭，压缩落在两次尝试之间，下一个编号请求从替换表层重建。 ## 考虑过的替代方案 diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index 75be39aa1b..7acc1d0351 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -15,8 +15,8 @@ This backend owns the compaction policy: - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. - **Framing** — the replacement user message marks established checkpoint context with `` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint. - **Lifecycle** — `compactRegion()` requires its agent to own the exact target session and rejects mismatch before resolution or mutation; a valid call records its start, summary, replacement, and end. The serial `agent/post-step` listener checks pressure after successful output and tool work are durable but before `step/end`. Canonical provider overflow is handled through `agent/request-error` after the failed step closes. -- **Overflow recovery** — below-threshold overflow bypasses normal retention and first prunes, then attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized whenever `surface.replaceGeneration` advances, including pruning-only progress on an otherwise indivisible surface; no replacement, recovery failure, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure. -- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no replacement landed. Operational post-step failures warn and continue; overflow-recovery failure preserves the original provider error. +- **Overflow recovery** — below-threshold overflow bypasses normal retention and first prunes, then attempts one maximal balanced head reduction while leaving the newest indivisible unit. Retry is authorized whenever `surface.replaceGeneration` advances, including when pruning lands before later summary work throws. No replacement, an exhausted cap, cancellation, or an unknown/noncanonical error preserves the original provider failure. +- **Failure handling** — an unmatched `compact/start` is an inert crash marker because no summary replacement landed. Operational post-step failures warn and continue; overflow-recovery failure preserves the original provider error only when no earlier replacement advanced the surface. Cancellation remains authoritative after any progress. `summarize()` is the sole subclass hook. A template- or remote-summarizer subclass can override it while pressure, retention, provenance, shrink validation, and shadowed-token accounting stay on `ctx.tokenMeter`. The hook returns the summary blocks together with the call envelope it used (`{ summary, model, maxTokens? }`), which is logged on `compact/summary`. diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 91e8ad0cea..34567f7e07 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -100,15 +100,28 @@ export class BasicCompactService extends CompactService { || retryAttempt >= this.config.maxOverflowRetries || signal.aborted) return next() - let generation: number + const generation = agent.session.surface.replaceGeneration let result: CompactionResult | null try { - generation = agent.session.surface.replaceGeneration result = await this.compactIfNeeded(agent, 'context-overflow', signal) } catch (recoveryError: unknown) { const message = recoveryError instanceof Error ? recoveryError.message : String(recoveryError) + // A model-free prune can land before later summary work fails. That + // durable reduction is sufficient retry proof; do not discard it just + // because the optional second phase threw. Cancellation still wins. + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited. + if (!signal.aborted && agent.session.surface.replaceGeneration > generation) { + ctx.logger.warn( + `context-overflow compaction failed after durable surface progress: ${message}; ` + + 'retrying from the replacement surface', + ) + return { action: 'retry' } + } ctx.logger.warn( - `context-overflow compaction failed: ${message}; preserving the original request error`, + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition -- signal can abort while recovery is awaited. + `context-overflow compaction failed: ${message}; ${signal.aborted + ? 'cancellation prevents retry' + : 'preserving the original request error'}`, ) return next() } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 190fb026e7..094a22a11e 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -1022,6 +1022,51 @@ describe('automatic listener and loader composition', () => { expect(compact.calls[0]!.text).toContain('tool result middle pruned') }) + it('retries from a durable prune when later overflow summarization throws', async () => { + const ctx = createContext(10_000) + const warnings: string[] = [] + ctx.logger.warn = ((message: string) => void warnings.push(message)) as typeof ctx.logger.warn + void new ToolResultPruneService(ctx, { + thresholdChars: 100, + headChars: 20, + tailChars: 10, + }) + const compact = new TestCompactService(ctx, { + thresholdRatio: 1, + retainTokens: 900, + }) + compact.error = new Error('summary unavailable after prune') + const session = oversizedToolResult(3_000, true) + + expect(await recover(ctx, agent(session, MODEL), overflow())).toEqual({ action: 'retry' }) + expect(session.surface.replaceGeneration).toBe(1) + expect(session.events.filter(event => event.type === 'tool/result')).toHaveLength(2) + expect(session.events.findLast(event => event.type === 'compact/end')?.data) + .toMatchObject({ error: 'summary unavailable after prune' }) + expect(warnings).toContainEqual(expect.stringContaining('retrying from the replacement surface')) + }) + + it('lets cancellation win when summary throws after a durable prune', async () => { + const ctx = createContext(10_000) + const controller = new AbortController() + void new ToolResultPruneService(ctx, { + thresholdChars: 100, + headChars: 20, + tailChars: 10, + }) + const compact = new TestCompactService(ctx, { + thresholdRatio: 1, + retainTokens: 900, + }) + compact.mutateDuringSummary = () => { controller.abort('cancelled during summary') } + compact.error = new Error('summary cancelled after prune') + const session = oversizedToolResult(3_000, true) + + expect(await recover(ctx, agent(session, MODEL), overflow(), 0, controller.signal)) + .toEqual({ action: 'fail' }) + expect(session.surface.replaceGeneration).toBe(1) + }) + it('preserves the newest whole tool-call/result pair during forced overflow compaction', async () => { const ctx = createContext() void new TestCompactService(ctx, { diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index 5ef2139db2..d80905e6ec 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -31,7 +31,7 @@ Session log (per session): - **turns pair and nest** — `turn/start` opens a turn, `turn/end` closes the matching one; no overlapping turns. - **steps nest in turns** — `step/start` opens a step in the open turn; `step/end` closes the matching step. - **chunks belong to an open step** — `step/start` precedes its `assistant/chunk`s. -- **an appended `tool/result` needs a prior `tool/call`** — fresh `surfaceOp: 'append'` results name the open step and consume its pending call, while a provenance-backed single-node `replace` is a turn-enclosed surface rewrite of an already-executed result. A `tool/call` may still have no result when the execution pipeline throws. +- **an appended `tool/result` needs a prior `tool/call`** — fresh `surfaceOp: 'append'` results name the open step and consume its pending call. A replacement exemption applies only to a provenance-backed rewrite of one current `tool/result` node whose complete data is identical except for `content`; it must still be turn-enclosed. A `tool/call` may still have no result when the execution pipeline throws. - **provenance sources are valid and unambiguous** — `sourceEventSeqs` contains unique earlier known seqs; only `assistant/message` may carry an explicit empty list, which denotes a known empty provider stream rather than absent legacy provenance. Agent status (per agent): diff --git a/packages/support/invariants/src/index.ts b/packages/support/invariants/src/index.ts index f33f7b4cec..0e12bfa246 100644 --- a/packages/support/invariants/src/index.ts +++ b/packages/support/invariants/src/index.ts @@ -7,6 +7,7 @@ * @module @deepseek-ai/dsh-invariants */ +import { isDeepStrictEqual } from 'node:util' import type { Context } from 'cordis' import { carrierKeyOf, isScopeCarrier } from '@deepseek-ai/dsh-scope' import { assertNever, HarnessError } from '@deepseek-ai/dsh-llm' @@ -50,13 +51,14 @@ interface SessionTrace { pendingCalls: Set /** Every seq seen so far — validates `sourceEventSeqs` references. */ knownSeqs: Set - /** - * The seqs currently on the surface linked list, in linked-list order - * (head to tail). A replace reorders this relative to seq order (the new - * node takes the replaced range's position), so range validation is - * positional, not by seq comparison. - */ - surface: number[] + /** Current surface nodes in linked-list order, with immutable event identity. */ + surface: SurfaceTraceNode[] +} + +/** Immutable identity retained only while an event is on the current surface. */ +interface SurfaceTraceNode { + seq: number + event: SessionEvent } /** One accepted event's deferred mutation of a live session trace. */ @@ -70,8 +72,9 @@ interface SessionTraceTransition { | { kind: 'clear' } /** The event's mutation of the derived surface order. */ surface: - | { kind: 'none' | 'append' } - | { kind: 'replace'; start: number; count: number } + | { kind: 'none' } + | { kind: 'append'; node: SurfaceTraceNode } + | { kind: 'replace'; start: number; count: number; node: SurfaceTraceNode } /** The committed event sequence to add to the known-sequence set. */ seq: number } @@ -85,6 +88,18 @@ function requireOpenStep(trace: SessionTrace, kind: string, turn: number, step: } } +/** Compare future-safe tool-result data while deliberately excluding content. */ +function sameToolResultDataExceptContent( + original: SessionEvent<'tool/result'>['data'], + replacement: SessionEvent<'tool/result'>['data'], +): boolean { + const originalRest = { ...original } as Record + const replacementRest = { ...replacement } as Record + delete originalRest['content'] + delete replacementRest['content'] + return isDeepStrictEqual(originalRest, replacementRest) +} + /** Validate one candidate event without mutating the committed session trace. */ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTransition { // seq is strictly monotonic — the spine of replay equivalence. lastSeq @@ -139,14 +154,14 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr // positional range — every shadowed node must appear in sourceEventSeqs. if (se.surfaceOp !== undefined) { if (se.surfaceOp === 'append') { - surface = { kind: 'append' } + surface = { kind: 'append', node: { seq: event.seq, event: se } } } else { const { start, end } = se.surfaceOp - const startIdx = trace.surface.indexOf(start) + const startIdx = trace.surface.findIndex(node => node.seq === start) if (startIdx === -1) { throw new InvariantError(`surface replace: start seq ${start} is not on the surface`) } - const endIdx = trace.surface.indexOf(end) + const endIdx = trace.surface.findIndex(node => node.seq === end) if (endIdx === -1) { throw new InvariantError(`surface replace: end seq ${end} is not on the surface`) } @@ -155,13 +170,18 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr } // Every node the replace shadows (surface positions [startIdx, endIdx] // inclusive) must appear in sourceEventSeqs — the provenance contract. - const shadowed = trace.surface.slice(startIdx, endIdx + 1) + const shadowed = trace.surface.slice(startIdx, endIdx + 1).map(node => node.seq) const recorded = new Set(se.sourceEventSeqs ?? []) const missing = shadowed.filter(seq => !recorded.has(seq)) if (missing.length > 0) { throw new InvariantError(`surface replace: sourceEventSeqs must include every shadowed surface node; missing ${missing.join(', ')}`) } - surface = { kind: 'replace', start: startIdx, count: shadowed.length } + surface = { + kind: 'replace', + start: startIdx, + count: shadowed.length, + node: { seq: event.seq, event: se }, + } } } @@ -232,15 +252,26 @@ function validateEvent(trace: SessionTrace, event: SessionEvent): SessionTraceTr break } case 'tool/result': { - // A replacement rewrites an already-executed result whose recorded - // turn/step can be closed. Surface provenance above validates the rewrite; - // only fresh appends consume an open step's pending call. + // Only a content-only rewrite of one CURRENT tool-result node may bypass + // open-step/pending-call checks. The trace retains immutable surface event + // identity, so this validation never indexes a mutable or stale session. if (se.surfaceOp !== undefined && se.surfaceOp !== 'append') { if (trace.openTurn === null) { throw new InvariantError( 'tool/result surface replacement appended outside any open turn', ) } + const { start, end } = se.surfaceOp + if (start !== end) { + throw new InvariantError('tool/result surface replacement must rewrite exactly one current node') + } + const original = trace.surface.find(node => node.seq === start)?.event + if (original?.type !== 'tool/result') { + throw new InvariantError('tool/result surface replacement must target a current tool/result') + } + if (!sameToolResultDataExceptContent(original.data, event.data)) { + throw new InvariantError('tool/result surface replacement may change only content') + } break } requireOpenStep(trace, 'tool/result', event.data.turn, event.data.step) @@ -302,10 +333,14 @@ function applyTransition(trace: SessionTrace, transition: SessionTraceTransition case 'none': break case 'append': - trace.surface.push(transition.seq) + trace.surface.push(transition.surface.node) break case 'replace': - trace.surface.splice(transition.surface.start, transition.surface.count, transition.seq) + trace.surface.splice( + transition.surface.start, + transition.surface.count, + transition.surface.node, + ) break /* v8 ignore next -- validateEvent produces this closed transition union */ default: diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index 986cd93e7c..c55f3f1147 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -478,6 +478,39 @@ describe('HMR safety', () => { }) describe('surface invariants', () => { + async function toolResultRewriteFixture() { + const { ctx } = await setup() + const session = ctx.sessions.create() + session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) + const unrelated = session.append('user/message', { + content: [{ type: 'text', text: 'request' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + session.append('step/start', { turn: 1, step: 1 }) + session.append('tool/call', { + turn: 1, + step: 1, + callId: CallId('rewrite'), + name: 'echo', + arguments: '{}', + }) + const originalData = { + turn: 1, + step: 1, + callId: CallId('rewrite'), + content: [{ type: 'text' as const, text: 'original' }], + isError: true, + error: { name: 'ExitError', code: 'EXIT_1' }, + meta: { presentation: { kind: 'terminal', output: 'full output' } }, + futureField: { nested: ['preserve', 1] }, + } + const original = session.append('tool/result', originalData, { surfaceOp: 'append' }) + session.append('step/end', { turn: 1, step: 1 }) + session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) + session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) + return { session, unrelated, original } + } + it('accepts well-formed surface metadata', async () => { const { ctx } = await setup() const session = ctx.sessions.create() @@ -501,27 +534,7 @@ describe('surface invariants', () => { }) it('treats a provenance-backed tool-result replacement as a turn-enclosed rewrite', async () => { - const { ctx } = await setup() - const session = ctx.sessions.create() - session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('step/start', { turn: 1, step: 1 }) - session.append('tool/call', { - turn: 1, - step: 1, - callId: CallId('rewrite'), - name: 'echo', - arguments: '{}', - }) - const original = session.append('tool/result', { - turn: 1, - step: 1, - callId: CallId('rewrite'), - content: [{ type: 'text', text: 'original' }], - isError: false, - }, { surfaceOp: 'append' }) - session.append('step/end', { turn: 1, step: 1 }) - session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) - session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) + const { session, original } = await toolResultRewriteFixture() expect(() => session.append('tool/result', { ...original.data, @@ -532,6 +545,47 @@ describe('surface invariants', () => { })).not.toThrow() }) + it('rejects a tool-result replacement targeting an unrelated current node', async () => { + const { session, unrelated, original } = await toolResultRewriteFixture() + expect(() => session.append('tool/result', { + ...original.data, + content: [{ type: 'text', text: 'forged' }], + }, { + surfaceOp: { op: 'replace', start: unrelated.seq, end: unrelated.seq }, + sourceEventSeqs: [unrelated.seq], + })).toThrow(/must target a current tool\/result/) + }) + + it('rejects a multi-node tool-result replacement even with complete provenance', async () => { + const { session, unrelated, original } = await toolResultRewriteFixture() + expect(() => session.append('tool/result', { + ...original.data, + content: [{ type: 'text', text: 'forged' }], + }, { + surfaceOp: { op: 'replace', start: unrelated.seq, end: original.seq }, + sourceEventSeqs: [unrelated.seq, original.seq], + })).toThrow(/must rewrite exactly one current node/) + }) + + it.each([ + ['callId', { callId: CallId('forged') }], + ['turn', { turn: 2 }], + ['step', { step: 2 }], + ['error', { error: { name: 'ExitError', code: 'DIFFERENT' } }], + ['meta', { meta: { presentation: { kind: 'generic' } } }], + ['future data', { futureField: { nested: ['changed'] } }], + ])('rejects a content rewrite with altered %s', async (_label, altered) => { + const { session, original } = await toolResultRewriteFixture() + expect(() => session.append('tool/result', { + ...original.data, + ...altered, + content: [{ type: 'text', text: 'pruned' }], + }, { + surfaceOp: { op: 'replace', start: original.seq, end: original.seq }, + sourceEventSeqs: [original.seq], + })).toThrow(/may change only content/) + }) + it('accepts known-empty assistant provenance and rejects empty provenance elsewhere', async () => { const { ctx } = await setup() const session = ctx.sessions.create() diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 3650cf27d4..15733cb9d9 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -99,7 +99,7 @@ The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loa **What the model sees**: When optional consumers are loaded, ACP form answers become the exact JSON shape documented by `dsh-tool-ask-user`. Failures become `Error: ACP user questions must come from an agent-owned request`, `Error: ACP user question has no matching session`, `Error: ACP elicitation request failed`, `Error: ask_user_question was cancelled by the user`, `Error: ask_user_question returned no answer`, or `Error: ask_user_question was aborted before the user answered`. Permission decisions control whether another tool yields success or denial. ACP tool cards, terminal output, diffs, and streamed session updates are UI-only. -**Token effect**: Answer, error, and denial text enters context only through the owning tool result; presentation metadata adds zero model tokens. +**Token effect**: Answer, error, and denial text enters context only through the owning tool result; presentation metadata adds zero model tokens. A replacement `tool/result` still changes the model-facing session surface, but live and replayed ACP feeds ignore it as an execution update so the original terminal or diff completion is not overwritten. ### Permission preset switches diff --git a/packages/ui/acp/acp-feature-support.md b/packages/ui/acp/acp-feature-support.md index 29b0abc073..f1c3a918d5 100644 --- a/packages/ui/acp/acp-feature-support.md +++ b/packages/ui/acp/acp-feature-support.md @@ -82,7 +82,7 @@ These are capabilities the bridge would *drive* on the editor. The harness runs | `agent_thought_chunk` | S | ✅ | ✅ | ✅ | From `assistant/chunk` reasoning-delta. | | `user_message_chunk` | S | ✅ | ✅ | ✅ | Emitted during `session/load` replay to reconstruct the user side. | | `tool_call` | S | ✅ | ✅ | ✅ | Tool-owned presentation (`presentCall`); see [§5](#5-tool-call-rendering). | -| `tool_call_update` | S | ✅ | ✅ | ✅ | From `tool/result` via `presentResult`. | +| `tool_call_update` | S | ✅ | ✅ | ✅ | From appended `tool/result` via `presentResult`; replacement results rewrite model context and do not duplicate or overwrite execution presentation. | | `plan` | S | ❌ | ✅ | ✅ | No agent plan emitted. Both adapters emit real plan entries (Codex's `CodexEventHandler.updatePlan` maps `turn/plan/updated` → `{ sessionUpdate: 'plan', entries }`). | | `available_commands_update` | S | ❌ | ✅ | ✅ | No slash commands advertised. | | `current_mode_update` | S | ❌ | ✅ | ✅ | No session modes. | diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index c464ffd22b..66719d0ddd 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -904,7 +904,8 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void { * loaded transcript reconstructs the USER side of each turn without echoing * a live `session/prompt` back to the client * - `tool/call` → `tool_call` (pending) - * - `tool/result` → `tool_call_update` (completed/failed) + * - appended `tool/result` → `tool_call_update` (completed/failed) + * - replacement `tool/result` → no update (context rewrite, not execution) * * Tool-call presentation (title/kind/rawInput, and the completed-state content) * is owned by each TOOL via `presentCall`/`presentResult` — the bridge never @@ -965,6 +966,10 @@ export function streamSessionEventUpdate( return } case 'tool/result': { + // Replacements (for example model-free pruning) are transcript rewrites, + // not repeated tool executions. Re-presenting one would consume no + // pending call and could clobber the original terminal/diff completion. + if (event.surfaceOp !== undefined && event.surfaceOp !== 'append') return const view = presenter.result(event.data.callId, event.data.content, event.data.isError, event.data.meta) notify({ sessionId, update: toolResultUpdate(event.data.callId, view, event.data.isError, terminal) }) return diff --git a/packages/ui/acp/tests/load.spec.ts b/packages/ui/acp/tests/load.spec.ts index f57767fb38..4c22681b79 100644 --- a/packages/ui/acp/tests/load.spec.ts +++ b/packages/ui/acp/tests/load.spec.ts @@ -162,6 +162,53 @@ describe('acp bridge — session/load replay', () => { expect(meta.terminal_exit?.exit_code).toBe(0) }) + it('keeps one terminal completion live and on replay when a pruning replacement is logged', async () => { + live = await makeBridgeHarness({ + storageDir, + withBash: true, + script: [toolCallResponse('c1', 'bash', { command: 'echo full', description: 'Print full output' }), textResponse('done')], + }) + await live.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: { _meta: { terminal_output: true } } }) + const { sessionId } = await live.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await live.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'run it' }] }) + + const session = live.ctx.agents.get(AgentId(sessionId))!.session + const original = session.events.find(event => event.type === 'tool/result') + if (original?.type !== 'tool/result') throw new Error('expected original tool/result') + const liveCompletions = () => live!.updates.filter(update => + update.sessionUpdate === 'tool_call_update' && update.toolCallId === 'c1') + expect(liveCompletions()).toHaveLength(1) + expect((liveCompletions()[0] as { _meta?: { terminal_output?: { data: string } } })._meta?.terminal_output?.data) + .toBe('full\n') + + session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) + session.append('tool/result', { + ...original.data, + content: [{ type: 'text', text: '[... tool result middle pruned ...]' }], + }, { + surfaceOp: { op: 'replace', start: original.seq, end: original.seq }, + sourceEventSeqs: [original.seq], + }) + session.append('turn/end', { turn: 2, reason: { kind: 'completed' } }) + + // The replacement is durable but is not another live completion. + expect(session.events.filter(event => event.type === 'tool/result')).toHaveLength(2) + expect(JSON.stringify(session.deriveMessages())).toContain('tool result middle pruned') + expect(liveCompletions()).toHaveLength(1) + await live.dispose() + live = undefined + + loader = await makeBridgeHarness({ storageDir, withBash: true, script: [] }) + await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: { _meta: { terminal_output: true } } }) + await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) + + const replayed = loader.updates.filter(update => + update.sessionUpdate === 'tool_call_update' && update.toolCallId === 'c1') + expect(replayed).toHaveLength(1) + expect((replayed[0] as { _meta?: { terminal_output?: { data: string } } })._meta?.terminal_output?.data) + .toBe('full\n') + }) + it('a load whose resume finishes after a client disconnect leaks no live session', async () => { // Stall persistence so transport closes while resume is pending. Whether the SDK rejects first // or the bridge's post-await guard fires, no agent may survive for the dead connection. diff --git a/packages/ui/acp/tests/stream-update.spec.ts b/packages/ui/acp/tests/stream-update.spec.ts index 2afa49e1d4..c2884e0b1f 100644 --- a/packages/ui/acp/tests/stream-update.spec.ts +++ b/packages/ui/acp/tests/stream-update.spec.ts @@ -105,6 +105,22 @@ describe('streamSessionEventUpdate', () => { expect((failed[0] as { status: string }).status).toBe('failed') }) + it('emits no execution update for a tool-result surface replacement', () => { + const replacement = { + ...evt('tool/result', { + turn: 1, + step: 1, + callId: CallId('c1'), + content: [{ type: 'text', text: '[... tool result middle pruned ...]' }], + isError: false, + }), + seq: 2, + surfaceOp: { op: 'replace', start: 1, end: 1 }, + sourceEventSeqs: [1], + } as SessionEvent + expect(updatesFor(replacement)).toEqual([]) + }) + it('drops non-text tool-result content (text-only)', () => { const update = updatesFor(evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), @@ -450,6 +466,16 @@ describe('terminal-card mapping (capability-gated)', () => { const callEvent = evt('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'bash', arguments: JSON.stringify({ command: 'echo hi', description: 'Greet' }) }) const resultEvent = evt('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'hi\n' }], isError: false }) + const prunedResultEvent = { + ...resultEvent, + seq: 2, + data: { + ...resultEvent.data, + content: [{ type: 'text', text: '[... tool result middle pruned ...]' }], + }, + surfaceOp: { op: 'replace', start: 1, end: 1 }, + sourceEventSeqs: [1], + } as SessionEvent function termUpdates(tool: ToolDefinition, enabled: boolean, cwd: string | undefined, ...events: SessionEvent[]): SessionNotification['update'][] { const presenter = new ToolPresenter(registryOf(tool)) @@ -477,6 +503,27 @@ describe('terminal-card mapping (capability-gated)', () => { }) }) + it('live/replay translation preserves the original terminal completion across a pruning rewrite', () => { + const updates = termUpdates( + termTool({ card: 'terminal' }, { output: 'hi\n', exitCode: 0 }), + true, + '/work/proj', + callEvent, + resultEvent, + prunedResultEvent, + ) + expect(updates).toHaveLength(2) + expect(updates[1]).toEqual({ + sessionUpdate: 'tool_call_update', + toolCallId: 'c1', + status: 'completed', + _meta: { + terminal_output: { terminal_id: 'c1', data: 'hi\n' }, + terminal_exit: { terminal_id: 'c1', exit_code: 0 }, + }, + }) + }) + it('capability ON: an ABSOLUTE tool cwd wins; a RELATIVE one resolves against the session cwd', () => { const [absCall] = termUpdates(termTool({ card: 'terminal', cwd: '/explicit/abs' }, { output: 'x' }), true, '/work/proj', callEvent) expect((absCall as unknown as { _meta: { terminal_info: { cwd: string } } })._meta.terminal_info.cwd).toBe('/explicit/abs') @@ -633,17 +680,38 @@ describe('result-time diff card (REAL fs edit tool → tool_call_update diff blo // call-time snippet, then the tool/result carries the tool's computed applied-hunk `meta`, // which presentResult narrows into a `diff` result card the bridge forwards as `{ type: // 'diff' }` content blocks. The real tool is required because its result metadata is the contract. - it('forwards the applied-hunk meta onto the wire as tool_call_update diff content', async () => { + it('live/replay translation keeps the applied diff when a pruning rewrite follows', async () => { const ctx = await fsCtx() const presenter = new ToolPresenter(ctx.tools) const args = JSON.stringify({ file_path: 'src/b.ts', old_string: 'OLD', new_string: 'NEW' }) // The applied hunk the tool would compute and persist on the result meta. const meta = { diffs: [{ path: 'src/b.ts', oldText: 'a\nOLD\nb', newText: 'a\nNEW\nb' }] } - const [, resultUpdate] = updatesWith( + const originalResult = evt('tool/result', { + turn: 1, + step: 1, + callId: CallId('e1'), + content: [{ type: 'text', text: 'ok' }], + isError: false, + meta, + }) + const replacement = { + ...originalResult, + seq: 3, + data: { + ...originalResult.data, + content: [{ type: 'text', text: '[... tool result middle pruned ...]' }], + }, + surfaceOp: { op: 'replace', start: 2, end: 2 }, + sourceEventSeqs: [2], + } as SessionEvent + const updates = updatesWith( presenter, evt('tool/call', { turn: 1, step: 1, callId: CallId('e1'), name: 'edit', arguments: args }), - evt('tool/result', { turn: 1, step: 1, callId: CallId('e1'), content: [{ type: 'text', text: 'ok' }], isError: false, meta }), + originalResult, + replacement, ) + expect(updates).toHaveLength(2) + const resultUpdate = updates[1] expect(resultUpdate).toEqual({ sessionUpdate: 'tool_call_update', toolCallId: 'e1', diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index b7d320880d..2327857b82 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -27,7 +27,7 @@ The plugin seeds display labels from the live agent registry, then tracks `agent **What the model sees**: Each non-empty terminal line outside an active question becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running. -**Token effect**: Submitted text is retained under the agent loop's normal session-history and compaction rules. The welcome banner, `> ` prompt, rendered transcript, and `[tool call]` / `[tool result]` terminal lines add no tokens. +**Token effect**: Submitted text is retained under the agent loop's normal session-history and compaction rules. The welcome banner, `> ` prompt, rendered transcript, and `[tool call]` / `[tool result]` terminal lines add no tokens. A replacement `tool/result` remains model-visible through the session surface but is not rendered as a second execution; stdio keeps the original full-fidelity result line. ### Terminal user-interaction answers diff --git a/packages/ui/stdio/src/index.ts b/packages/ui/stdio/src/index.ts index 1e665381ce..aea10827c7 100644 --- a/packages/ui/stdio/src/index.ts +++ b/packages/ui/stdio/src/index.ts @@ -124,6 +124,10 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt inReasoning = false output.write(`\n [tool call] ${toolName}(${args})`) } else if (event.type === 'tool/result') { + // A surface replacement changes future model context; it is not another + // execution. Keep the original full-fidelity terminal presentation and + // suppress duplicate output during live delivery or log replay. + if (event.surfaceOp !== undefined && event.surfaceOp !== 'append') return const { content } = event.data const text = content.filter(block => block.type === 'text').map(block => block.text).join('') output.write(`\n [tool result] ${text}\n `) diff --git a/packages/ui/stdio/tests/stdio.spec.ts b/packages/ui/stdio/tests/stdio.spec.ts index 7bb6a6f245..f757f62401 100644 --- a/packages/ui/stdio/tests/stdio.spec.ts +++ b/packages/ui/stdio/tests/stdio.spec.ts @@ -288,6 +288,43 @@ describe('createStdioChat rendering', () => { expect(out.text()).toContain('[tool result] file.txt') }) + it('renders one full-fidelity result whether the event feed is live or replayed', async () => { + const { ctx, out } = await setup() + const session = makeSession('main') + const original = { + type: 'tool/result', + seq: 2, + time: 0, + data: { + turn: 1, + step: 1, + callId: 'c1', + content: [{ type: 'text', text: 'full terminal output' }], + isError: false, + meta: { terminal: { output: 'full terminal output' } }, + }, + surfaceOp: 'append', + } as SessionEvent + const replacement = { + ...original, + seq: 3, + data: { + ...original.data, + content: [{ type: 'text', text: '[... tool result middle pruned ...]' }], + }, + surfaceOp: { op: 'replace', start: 2, end: 2 }, + sourceEventSeqs: [2], + } as SessionEvent + + // Stdio consumes the same session/event shape whether a host forwards a + // live append or replays a stored log through the rendering feed. + for (const event of [original, replacement]) ctx.emit('session/event', session, event) + + expect(out.text().match(/\[tool result\]/g)).toHaveLength(1) + expect(out.text()).toContain('full terminal output') + expect(out.text()).not.toContain('tool result middle pruned') + }) + it('renders a todo/write session event as a glyphed checklist', async () => { const { ctx, out } = await setup() const session = {} as Session From ba4a57c7d19c3119f1f3876a8472b758902ddc9d Mon Sep 17 00:00:00 2001 From: Hypatia May Date: Thu, 16 Jul 2026 18:51:26 +0800 Subject: [PATCH 150/323] refactor(compact): align pruning contracts (round 3) --- docs/architecture.md | 2 +- docs/capability-seams.md | 6 ++-- docs/config-catalog.md | 32 +++++++++---------- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/compaction.md | 2 +- docs/module-graph.md | 12 +++---- .../2026-06-18-session-surface.md | 2 +- ...n-pressure-and-overflow-recovery.i18n.yaml | 4 +-- ...mpaction-pressure-and-overflow-recovery.md | 6 ++-- ...ction-pressure-and-overflow-recovery.zh.md | 6 ++-- .../2026-06-18-compaction-capability-seam.md | 14 ++++---- docs/tool-catalog.md | 4 +-- examples/coding-agent/composition.md | 4 +-- examples/coding-agent/cordis.yml | 2 +- examples/coding-agent/tests/harness.ts | 2 +- packages/compact/README.md | 4 +-- packages/compact/compact-basic/README.md | 10 +++--- packages/compact/compact-basic/package.json | 6 ++-- packages/compact/compact-basic/src/index.ts | 2 +- .../compact-basic/tests/compact-basic.spec.ts | 2 +- .../tests/loader-composition.spec.ts | 6 ++-- packages/compact/compact-basic/tsconfig.json | 2 +- .../README.md | 4 +-- .../package.json | 2 +- .../src/config.ts | 0 .../src/index.ts | 2 +- .../src/types.ts | 0 .../tests/loader-composition.spec.ts | 10 +++--- .../tests/tool-result-prune.spec.ts | 4 +-- .../tsconfig.json | 0 packages/compact/compact/README.md | 2 +- .../core/tools/tests/gen-tool-catalog.spec.ts | 5 --- pnpm-lock.yaml | 10 +++--- python/sdk-runtime/package.json | 2 +- scripts/gen-doc-graphs.ts | 2 +- scripts/gen-tool-catalog.ts | 29 ++++++----------- tsconfig.build.json | 2 +- tsconfig.json | 2 +- 38 files changed, 97 insertions(+), 111 deletions(-) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/README.md (96%) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/package.json (94%) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/src/config.ts (100%) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/src/index.ts (99%) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/src/types.ts (100%) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/tests/loader-composition.spec.ts (84%) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/tests/tool-result-prune.spec.ts (98%) rename packages/compact/{tool-result-prune => compact-tool-result-prune}/tsconfig.json (100%) diff --git a/docs/architecture.md b/docs/architecture.md index ff45d38389..6c4fd39622 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -32,7 +32,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages add services (`ctx | `ctx.skills` | [`skill/`](../packages/skill/README.md) | skill provider registry and progressive disclosure | | `ctx.web` | [`web/`](../packages/web/README.md) | search/fetch provider registries | | `ctx.compact` | [`compact/`](../packages/compact/README.md) | session-log compaction | -| `ctx.toolResultPrune` | [`compact/tool-result-prune`](../packages/compact/tool-result-prune/README.md) | optional model-free tool-result pruning | +| `ctx.toolResultPrune` | [`compact/compact-tool-result-prune`](../packages/compact/compact-tool-result-prune/README.md) | optional model-free tool-result pruning | | `ctx.subagents` | [`subagent/`](../packages/subagent/README.md) | named delegation providers | | `ctx.tasks` | [`tasks/`](../packages/tasks/README.md) | background task registry + generic `task_*` control tools | | `ctx.workflows` | [`workflow/`](../packages/workflow/README.md) | script-driven multi-agent orchestration | diff --git a/docs/capability-seams.md b/docs/capability-seams.md index 816fc0ea3b..4ce3619025 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -16,7 +16,7 @@ flowchart LR pkg_compact_basic["compact-basic"] pkg_token_meter["token-meter"] svc_tokenMeter["ctx.tokenMeter
Replay token measurement"] - pkg_tool_result_prune["tool-result-prune"] + pkg_compact_tool_result_prune["compact-tool-result-prune"] svc_toolResultPrune["ctx.toolResultPrune
Model-free tool-result pruning"] pkg_session["session"] svc_sessions["ctx.sessions
In-memory session store"] @@ -104,6 +104,7 @@ flowchart LR pkg_code_runtime_worker --> svc_codeRuntime pkg_compact --> svc_compact pkg_compact_basic --> svc_compact + pkg_compact_tool_result_prune --> svc_toolResultPrune pkg_fs --> svc_fs pkg_fs_local --> svc_fs pkg_llm --> svc_llm @@ -129,7 +130,6 @@ flowchart LR pkg_system_prompt --> svc_systemPrompt pkg_tasks --> svc_tasks pkg_token_meter --> svc_tokenMeter - pkg_tool_result_prune --> svc_toolResultPrune pkg_tools --> svc_tools pkg_user_interaction --> svc_userInteraction pkg_web --> svc_web @@ -199,7 +199,7 @@ flowchart LR | --- | --- | --- | --- | --- | --- | --- | | `ctx.llm` | `seam` | [`llm`](../packages/llm/llm) | [`llm-deepseek`](../packages/llm/llm-deepseek), [`llm-pi-ai`](../packages/llm/llm-pi-ai), [`llm-replay`](../packages/support/llm-replay) | [`agent-loop`](../packages/core/agent-loop), [`compact-basic`](../packages/compact/compact-basic) | - | Adapters register provider implementations; the loop and compaction call the provider-neutral stream service. | | `ctx.tokenMeter` | `core` | [`token-meter`](../packages/llm/token-meter) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Owns isolated per-session replay folds; pressure consumers share immutable revisioned measurements. | -| `ctx.toolResultPrune` | `core` | [`tool-result-prune`](../packages/compact/tool-result-prune) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Rewrites oversized current tool results through replayable single-node surface replacements before summary compaction. | +| `ctx.toolResultPrune` | `core` | [`compact-tool-result-prune`](../packages/compact/compact-tool-result-prune) | - | [`compact-basic`](../packages/compact/compact-basic) | - | Rewrites oversized current tool results through replayable single-node surface replacements before summary compaction. | | `ctx.sessions` | `core` | [`session`](../packages/core/session) | - | [`agent-loop`](../packages/core/agent-loop), [`agent`](../packages/core/agent), [`session-persistence`](../packages/session-persistence/session-persistence), [`session-query`](../packages/session-query/session-query), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`invariants`](../packages/support/invariants) | - | Owns append-only Session instances and emits the durable session event feed. | | `ctx.sessionPersistence` | `seam` | [`session-persistence`](../packages/session-persistence/session-persistence) | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`session-query`](../packages/session-query/session-query) | - | Backends persist the same SessionEvent vocabulary; apps choose a backend at composition time. | | `ctx.sessionQuery` | `seam` | [`session-query`](../packages/session-query/session-query) | - | - | - | Resolves live and optional persisted logs into one logical corpus for exact reads. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index cb266a8119..cb338a9c75 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -245,6 +245,22 @@ export interface BasicCompactConfig { Source: [`packages/compact/compact-basic/src/types.ts:8`](../packages/compact/compact-basic/src/types.ts) +## `@deepseek-ai/dsh-compact-tool-result-prune` + +```ts config-catalog +/** Character-budget policy for deterministic tool-result pruning. */ +export interface ToolResultPruneConfig { + /** Prune when total text exceeds this many Unicode code points. Defaults to `8192`. */ + thresholdChars?: number + /** Maximum leading Unicode code points retained. Defaults to `4096`. */ + headChars?: number + /** Maximum trailing Unicode code points retained. Defaults to `1024`. */ + tailChars?: number +} +``` + +Source: [`packages/compact/compact-tool-result-prune/src/types.ts:4`](../packages/compact/compact-tool-result-prune/src/types.ts) + ## `@deepseek-ai/dsh-fs-local` ```ts config-catalog @@ -930,22 +946,6 @@ export interface Config { Source: [`packages/fs/tool-fs/src/index.ts:22`](../packages/fs/tool-fs/src/index.ts) -## `@deepseek-ai/dsh-tool-result-prune` - -```ts config-catalog -/** Character-budget policy for deterministic tool-result pruning. */ -export interface ToolResultPruneConfig { - /** Prune when total text exceeds this many Unicode code points. Defaults to `8192`. */ - thresholdChars?: number - /** Maximum leading Unicode code points retained. Defaults to `4096`. */ - headChars?: number - /** Maximum trailing Unicode code points retained. Defaults to `1024`. */ - tailChars?: number -} -``` - -Source: [`packages/compact/tool-result-prune/src/types.ts:4`](../packages/compact/tool-result-prune/src/types.ts) - ## `@deepseek-ai/dsh-tool-skill` Requires: `tools` · `skills` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index e2fc41b943..2a5f37cacb 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -284,7 +284,7 @@ pruneSession(session: Session): PruneResult Types: [ContentBlock](../core-data-structures/core.md) -Source: [`packages/compact/tool-result-prune/src/index.ts:39`](../../packages/compact/tool-result-prune/src/index.ts) +Source: [`packages/compact/compact-tool-result-prune/src/index.ts:39`](../../packages/compact/compact-tool-result-prune/src/index.ts) ## `ctx.tools` — `ToolRegistry` diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index e3774b87cd..5981ed2d0a 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -58,6 +58,6 @@ export type CompactionTrigger = 'pressure' | 'context-overflow' `CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration. -Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and authorizes a fresh numbered-step retry only when the surface replacement generation advances, even if later summary work throws after pruning; cancellation still wins. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. +Pressure compaction runs at serial `agent/post-step`, after successful assistant output, tool results, buffered context, and steering are durable but before `step/end`. Once pressure or canonical overflow qualifies, compact-basic invokes optional [`ctx.toolResultPrune`](../../packages/compact/compact-tool-result-prune/README.md) before range selection, remeasures through `ctx.tokenMeter`, and can advance the surface without a summary. Failed-request recovery runs through `agent/request-error` after the failed step closes and authorizes a fresh numbered-step retry only when the surface replacement generation advances, even if later summary work throws after pruning; cancellation still wins. Region boundaries preserve tool-call/result pairing but not whole turns, allowing early closed steps of one oversized turn to compact. `dsh-compact-basic` owns thresholds, retained-tail policy, overflow caps, and failure handling. The seam exports `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)` for those edge checks. Both validate current surface membership, reject stale or missing seqs and orphan results, and ignore a caller-retained `node.next`; the [package contract](../../packages/compact/compact/README.md#tool-pairing-boundaries) owns their cache semantics. diff --git a/docs/module-graph.md b/docs/module-graph.md index fbe9afd59b..685bd810ce 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -45,7 +45,7 @@ flowchart TD subgraph group_compact["packages/compact"] pkg_compact["compact"] pkg_compact_basic["compact-basic"] - pkg_tool_result_prune["tool-result-prune"] + pkg_compact_tool_result_prune["compact-tool-result-prune"] end subgraph group_subagent["packages/subagent"] pkg_subagent["subagent"] @@ -169,8 +169,8 @@ flowchart TD pkg_skill_local --> pkg_skill pkg_compact --> pkg_llm pkg_compact --> pkg_session - pkg_tool_result_prune --> pkg_llm - pkg_tool_result_prune --> pkg_session + pkg_compact_tool_result_prune --> pkg_llm + pkg_compact_tool_result_prune --> pkg_session pkg_web_fetch_local --> pkg_timeout pkg_web_fetch_local --> pkg_web pkg_web_search_deepseek --> pkg_web @@ -185,10 +185,10 @@ flowchart TD pkg_bash_local --> pkg_timeout pkg_compact_basic --> pkg_agent pkg_compact_basic --> pkg_compact + pkg_compact_basic --> pkg_compact_tool_result_prune pkg_compact_basic --> pkg_llm pkg_compact_basic --> pkg_session pkg_compact_basic --> pkg_token_meter - pkg_compact_basic --> pkg_tool_result_prune pkg_hook_protocol --> pkg_bash pkg_hook_protocol --> pkg_session pkg_session_persistence_jsonl --> pkg_session @@ -411,7 +411,7 @@ flowchart TD | [`fs-policy`](../packages/fs/fs-policy) | `fs` | [`fs`](../packages/fs/fs) | | [`skill-local`](../packages/skill/skill-local) | `skill` | [`fs`](../packages/fs/fs), [`skill`](../packages/skill/skill) | | [`compact`](../packages/compact/compact) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | -| [`tool-result-prune`](../packages/compact/tool-result-prune) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | +| [`compact-tool-result-prune`](../packages/compact/compact-tool-result-prune) | `compact` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`web-fetch-local`](../packages/web/web-fetch-local) | `web` | [`timeout`](../packages/util/timeout), [`web`](../packages/web/web) | | [`web-search-deepseek`](../packages/web/web-search-deepseek) | `web` | [`web`](../packages/web/web) | | [`web-search-exa`](../packages/web/web-search-exa) | `web` | [`web`](../packages/web/web) | @@ -420,7 +420,7 @@ flowchart TD | [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | | [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) | -| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter), [`tool-result-prune`](../packages/compact/tool-result-prune) | +| [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`compact-tool-result-prune`](../packages/compact/compact-tool-result-prune), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) | | [`hook-protocol`](../packages/hooks/hook-protocol) | `hooks` | [`bash`](../packages/bash/bash), [`session`](../packages/core/session) | | [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | | [`session-persistence-sqlite`](../packages/session-persistence/session-persistence-sqlite) | `session-persistence` | [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence) | diff --git a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md index 3a8805ddb6..38f1085b81 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md +++ b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md @@ -66,4 +66,4 @@ Every surface-eligible event must carry `surfaceOp` or it would disappear from d - **`packages/session-persistence/session-persistence-jsonl`**: No changes required. - **`packages/session-persistence/session-persistence`**: Abstract interface unchanged. -The surface is the foundation for future history manipulation. A compaction or tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed nodes — the new node takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically. +The surface is the foundation for future history manipulation. A compaction or compact-tool-result-prune plugin appends one of the existing message-producing event types (a `user/message` carrying the summary, say) with `surfaceOp: { op: 'replace', start, end }` and `sourceEventSeqs` covering the shadowed nodes — the new node takes the range's place on the surface while the plugin's own trace events (e.g. `compaction/start`, `compaction/end`) stay off it. Replay preserves the decision deterministically. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index c8eef0f1c9..6f6ca74dd2 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: deedb81f8cf75ab80b70e2ef3148ba76d1278886 -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 51d28fa243f522eedcac29002670575889d48369 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: ea1e2b21c8036ab4d89c022792f252becc3826f6 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 594f396aaf891dccb9d6545e78039f0dbba51d1a diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index deedb81f8c..ea1e2b21c8 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -16,9 +16,9 @@ Successful calls are not the only pressure signal. A provider can reject a reque `agent/pre-step` is narrowed to `(agent, turn, step, signal)`. It remains a generic serial checkpoint before `step/start`, but it carries no compaction-only prompt or prefix fields. -The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after assistant output, every dispatched or synthetic tool result, post-tool context, and steering are durable, but before `step/end`. This placement gives pressure policy the complete successful-call state without splitting an assistant tool call from its result. A listener failure is an ordinary turn failure; it never enters model-request recovery. +The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after assistant output, every dispatched or synthetic tool result, post-tool context, and steering are durable, but before `step/end`. This placement gives pressure policy the complete successful-call state without splitting an assistant tool call from its result. A propagated listener failure is an ordinary turn failure; it never enters model-request recovery. Compact-basic contains its expected operational failures as described below. -`dsh-compact-basic` reads the exact latest routed model from the durable request header only to establish that a completed route exists, then asks the singleton `ctx.tokenMeter` to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work; any durable non-empty model name uses the same estimator. Operational measurement or summarization failures warn and continue with full history. +`dsh-compact-basic` reads the exact latest routed model from the durable request header only to establish that a completed route exists, then asks the singleton `ctx.tokenMeter` to measure the canonical logged envelope and current surface. It does not fall back to `AgentOptions.model` for automatic pressure. A headerless session has no completed routed request to assess and produces no work; any durable non-empty model name uses the same estimator. Operational measurement or summarization failures warn and continue from the latest durable surface: full history before any replacement, or the pruned surface if pruning already landed. ### Request recovery is limited to the final model boundary @@ -58,6 +58,6 @@ Compact tests pin low-friction service-wide defaults, actual routed-model select Pressure describes the actual completed routed request, including durable tool results and request-only prefix fields, rather than a provisional next-call guess. Optional model-free pruning removes predictable tool-output bulk before summary selection and can independently create retry-worthy progress. Canonical overflow supplies the backstop when no successful usage anchor exists. Recovery is bounded, cancellation-owned, and monotonic: it retries only after a visible surface generation change. -The cost is one additional serial checkpoint on successful steps and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window or split one indivisible oversized message/tool unit. +The cost is one additional serial checkpoint on successful steps and adapter-maintained overflow classification. Provider wording and heuristic character density remain maintenance risks. Surface compaction still cannot repair an envelope that alone exceeds the window, split an indivisible non-tool node, or repair a tool unit whose non-prunable remainder remains oversized. The optional pruner can repair an otherwise indivisible tool pair when removable text-bearing tool-result content is the bulk. This RFC supersedes only the pre-step automatic-trigger portion of the [compaction capability-seam RFC](../feature/2026-06-18-compaction-capability-seam.md). The service split, standalone token meter, balanced range contract, log-recorded lock, summary replacement, and sole `summarize()` subclass hook remain unchanged. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index 51d28fa243..594f396aaf 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -16,9 +16,9 @@ Status: implemented `agent/pre-step` 收窄为 `(agent, turn, step, signal)`。它仍是 `step/start` 之前的通用串行检查点，但不再携带压缩专用的提示词或前缀字段。 -循环在 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都持久化之后、`step/end` 之前，触发等待式串行 `agent/post-step(agent, turn, step, signal)`。该位置让压力策略看到完整的成功调用状态，同时不会拆开 assistant 工具调用与其结果。监听器失败属于普通 turn 失败，绝不会进入模型请求恢复。 +循环在 assistant 输出、所有已分发或合成的工具结果、工具后上下文与 steering 都持久化之后、`step/end` 之前，触发等待式串行 `agent/post-step(agent, turn, step, signal)`。该位置让压力策略看到完整的成功调用状态，同时不会拆开 assistant 工具调用与其结果。向外传播的监听器失败属于普通 turn 失败，绝不会进入模型请求恢复；compact-basic 会按下文所述在内部处理其预期的操作性失败。 -`dsh-compact-basic` 从持久请求头读取精确的最新实际路由模型，只用它确认已经存在完整路由，随后让单例 `ctx.tokenMeter` 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作；任意持久记录的非空模型名都使用同一个估算器。操作性的计量或摘要失败会发出警告，并继续使用完整历史。 +`dsh-compact-basic` 从持久请求头读取精确的最新实际路由模型，只用它确认已经存在完整路由，随后让单例 `ctx.tokenMeter` 计量规范日志信封与当前表层。自动压力不会回退到 `AgentOptions.model`。没有请求头的会话尚无已完成路由请求可供判断，因此不执行工作；任意持久记录的非空模型名都使用同一个估算器。操作性的计量或摘要失败会发出警告，并从最新持久表层继续：任何替换发生前使用完整历史；若剪枝已经落盘，则使用已剪枝表层。 ### 请求恢复只覆盖最终模型边界 @@ -58,6 +58,6 @@ Status: implemented 压力描述实际完成的路由请求，包括持久工具结果与仅请求前缀字段，而不是对下一次调用的临时猜测。可选的无模型剪枝会在选择摘要前移除可预测的工具输出体积，也能独立产生足以重试的进展。当成功 usage 锚点不存在时，规范化溢出提供兜底路径。恢复有上限、受取消所有，并保持单调：只有模型可见的表层 generation 变化后才重试。 -代价是成功 step 增加一个串行检查点，并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况，也不能拆分单个不可分割的超大消息或工具单元。 +代价是成功 step 增加一个串行检查点，并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况，也不能拆分不可分割的非工具节点，或修复非可剪枝剩余部分仍然过大的工具单元。若可移除的文本工具结果是主要体积，可选剪枝器仍可修复原本不可分割的工具配对。 本 RFC 只取代[压缩能力接缝 RFC](../feature/2026-06-18-compaction-capability-seam.md) 中的 pre-step 自动触发部分。服务拆分、独立 token meter、平衡范围契约、日志记录锁、摘要替换与唯一 `summarize()` 子类 hook 均保持不变。 diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 0f210cbd8e..67129e9bd7 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -18,7 +18,7 @@ Per the [capability-seams RFC](../../implemented/architecture/2026-06-13-capabil 1. **Interface** — `@deepseek-ai/dsh-compact`: an abstract `CompactService` owning the `ctx.compact` key, the `CompactionResult` vocabulary, and the `compact/*` session events. It declares `compactIfNeeded()` and `compactRegion()` as **abstract** — the contract states *what* compaction does, not *how*. 2. **Implementation** — `@deepseek-ai/dsh-compact-basic`: a concrete `BasicCompactService` that consumes `ctx.tokenMeter` and owns the tail→head retention walk, summarization via `ctx.llm.stream()`, the surface replacement, the lock, post-step pressure, and canonical context-overflow recovery. `summarize()` is its sole subclass hook; pricing and replay stay with the meter. -3. **Model-free companion** — `@deepseek-ai/dsh-tool-result-prune`: a concrete optional service that rewrites oversized current `tool/result` nodes before the backend selects a summary range. It is not a second compaction implementation and does not implement `CompactService`. +3. **Model-free companion** — `@deepseek-ai/dsh-compact-tool-result-prune`: a concrete optional service that rewrites oversized current `tool/result` nodes before the backend selects a summary range. It is not a second compaction implementation and does not implement `CompactService`. 4. **Consumer** — deferred. A `/compact` tool and slash command will `inject: ['compact']` and call the contract; they are intentionally out of scope here so the seam settles first. ### The contract depends on `dsh-session` and `dsh-llm` — a deliberate deviation @@ -37,7 +37,7 @@ An earlier draft put the full algorithm (the retention walk, token-summing, text The original pre-step placement used a provisional envelope and could not see final `agent/request` routing, tools, provider output, tool results, buffered context, or steering. The corrected lifecycle fires serial `agent/post-step(agent, turn, step, signal)` after those successful facts are durable and before `step/end`. `dsh-compact-basic` measures the canonical logged request through `ctx.tokenMeter`, so the next request sees any replacement without a speculative envelope override. Once pressure qualifies, it invokes optional `ctx.toolResultPrune`, remeasures the durable surface, and summarizes only if pruning did not restore safe pressure. -Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic prunes before forcing one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases, including pruning-only progress when no summary range exists; the loop then opens a new numbered step and reconstructs its request from the durable log. No replacement, recovery failure, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. The complete lifecycle decision is in the [after-call recovery RFC](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). +Canonical provider context overflow takes a separate path. The failed step closes, `agent/request-error` receives the original request error and consecutive retry count, and compact-basic prunes before forcing one useful balanced reduction. It returns retry only if `session.surface.replaceGeneration` increases, including pruning-only progress when no summary range exists; the loop then opens a new numbered step and reconstructs its request from the durable log. No replacement, a recovery failure before any replacement, cancellation, an exhausted cap, or an unrelated error preserves the original provider failure. If pruning already advanced the generation before later summary work fails, recovery retries from that durable pruned surface unless cancellation or disposal wins. The complete lifecycle decision is in the [after-call recovery RFC](../../implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md). ``` assistant/message → tool/result/context/steering @@ -57,7 +57,7 @@ Auto-compaction checks after **every successful** step, not once per turn. This A runaway turn thus compacts exactly like any other history: its early *closed* steps get summarized while its recent steps stay verbatim. When the only compactable content left is an un-splittable open tail step (its tool-calls have no results yet), compaction declines (`null`) and retries once that step closes. -**Single-unit overflow is out of scope, by design.** If a single retained unit — one closed step, or a large free node such as a pasted `user/message` — *alone* exceeds the budget, compaction cannot help and the next model call may go out over-budget. Bounding an individual unit's size is a separate concern (output truncation), handled elsewhere; compaction makes no promise about it, and the harness without such a mechanism can still break on a single oversized unit. This is named honestly rather than papered over. +**Some single-unit overflow remains out of scope, by design.** Summary range selection cannot split an indivisible unit. The optional pruning companion can nevertheless repair a closed tool pair when text-bearing tool-result content is the removable bulk and the pruned remainder fits. Envelope-only pressure, an oversized indivisible non-tool node such as a pasted `user/message`, and a tool unit whose non-prunable remainder is still oversized remain outside compaction. Bounding those individual units is a separate concern; the harness can still break on them. This is named honestly rather than papered over. ### Head-anchoring: one auto checkpoint, always at the head @@ -95,8 +95,8 @@ The `compact/start … compact/end` bracket is justified, in order of what now d Two failure paths, both documented: -- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — the surface replacement never landed, so the full, uncompacted history derives correctly. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash cannot wedge future compaction. -- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set and leaves the surface untouched. Post-step pressure warns and continues; overflow recovery delegates so the original provider error remains authoritative. +- **Crash** (the loop dies mid-summarization): a dangling `compact/start`, no closer. Because `compact/*` are **log-only**, the orphan is **inert** — no summary replacement lands. The derived surface remains the durable surface present at `compact/start`: full history when pruning made no replacement, or the already-pruned history when it did. Generic turn-repair (`interruptedTurnClosers`) closes the turn with a synthetic `turn/end`; the orphan sits *before* that `turn/end`, so the turn-scoped in-progress check never sees it and a crash cannot wedge future compaction. +- **Recoverable** (summarization throws but the loop survives): the backend appends `compact/end` with its **`error`** field set and lands no summary replacement. Post-step pressure warns and continues from the latest durable surface — full history if no replacement preceded the attempt, or the pruned surface if pruning already landed. Overflow recovery delegates only before any replacement; generation progress from earlier pruning authorizes a retry from that durable surface unless cancellation or disposal wins. `compact/end` keeps its `error?` field (mirroring `tool/result`'s self-contained error — one event tells success from failure without correlating a sibling). There is no separate `compact/error` event. @@ -111,12 +111,12 @@ Two failure paths, both documented: ## Consequences -- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, and `tool-result-prune` supplies optional deterministic rewriting. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. +- **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, and `compact-tool-result-prune` supplies optional deterministic rewriting. `packages/llm/token-meter` owns replay-aware measurement independently. The consumer tier is deferred. - **Automatic seams**: `agent/post-step` (`@mode serial`) handles successful-call pressure and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Generic `agent/pre-step` remains a four-argument checkpoint with no compaction-only prompt/prefix payload. - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `toolPairingBalancedBefore(session, node)` and `toolPairingBalancedAfter(session, node)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and answers both edges from one per-cut balance sequence instead of trusting a caller-retained `node.next`; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, positional nodes, and rewrite generation. - **`dsh-invariants`** treats fresh appended tool results as executions that require an open step and pending call, while provenance-backed replacements are turn-enclosed surface rewrites. Positional replacement and complete-source checks validate the rewritten node. -- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-tool-result-prune`, then `dsh-compact-basic`; service-wide defaults make the composition usable without repeated numeric policy. +- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter`, `dsh-compact-tool-result-prune`, then `dsh-compact-basic`; service-wide defaults make the composition usable without repeated numeric policy. ## Testing diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 085b165a2f..121bfd09f7 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -5,9 +5,9 @@ Every model-facing tool a shipped plugin contributes to `ctx.tools`: the `name`, `description`, and JSON-Schema `parameters` the model receives via the system-prompt assembly. It complements the cordis [events](cordis-catalog/events.md) & [services](cordis-catalog/services.md) catalogs (the wiring a plugin listens to and calls) and [core-data-structures/](core-data-structures/core.md) (the types those signatures move) — this page is the *tools* the agent is offered. -This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any model-facing package is missing from the generator's boot manifest; service-only packages that share the prefix are explicitly excluded. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md). +This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator's boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md). -Scope: shipped model-facing product tools under `packages/*/tool-*`, each booted with its DEFAULT config. Runtime service packages such as `tool-result-prune` do not register `ctx.tools` schemas and are explicitly excluded. The registered tool NAME can be a load-time config (e.g. `tool-subagent`'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog's packages-only scope. +Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog's packages-only scope. ## Tool Package Map diff --git a/examples/coding-agent/composition.md b/examples/coding-agent/composition.md index 5f35097603..c86aaa6c45 100644 --- a/examples/coding-agent/composition.md +++ b/examples/coding-agent/composition.md @@ -25,7 +25,7 @@ flowchart LR bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] plugin_coding_token_meter["token-meter
@deepseek-ai/dsh-token-meter"] cfg --> plugin_coding_token_meter - plugin_coding_tool_result_prune["tool-result-prune
@deepseek-ai/dsh-tool-result-prune"] + plugin_coding_tool_result_prune["tool-result-prune
@deepseek-ai/dsh-compact-tool-result-prune"] cfg --> plugin_coding_tool_result_prune plugin_coding_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] cfg --> plugin_coding_compact_basic @@ -60,7 +60,7 @@ flowchart LR | `bash` | `@deepseek-ai/dsh-bash-local` | | `stdio-agent` | `@deepseek-ai/dsh-stdio-demo` | | `token-meter` | `@deepseek-ai/dsh-token-meter` | -| `tool-result-prune` | `@deepseek-ai/dsh-tool-result-prune` | +| `tool-result-prune` | `@deepseek-ai/dsh-compact-tool-result-prune` | | `compact-basic` | `@deepseek-ai/dsh-compact-basic` | | `subagent` | `@deepseek-ai/dsh-subagent` | | `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index ba86b99e81..3b246fe825 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -52,7 +52,7 @@ # Prune oversized tool output without a model call before summary compaction. - id: tool-result-prune - name: '@deepseek-ai/dsh-tool-result-prune' + name: '@deepseek-ai/dsh-compact-tool-result-prune' # Summarize an older range after measured pressure or a canonical provider overflow. # Service-wide policy provides pressure, retention, and one overflow-retry default. diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index 6c06202a30..70ac92eafc 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -12,7 +12,7 @@ import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import TokenMeterService from '@deepseek-ai/dsh-token-meter' import type { TokenMeterConfig } from '@deepseek-ai/dsh-token-meter' -import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' +import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' diff --git a/packages/compact/README.md b/packages/compact/README.md index e251bfe442..d19343dc60 100644 --- a/packages/compact/README.md +++ b/packages/compact/README.md @@ -6,7 +6,7 @@ A compaction capability family (see [capability seams](../../docs/rfc/implemente |---|---|---| | `compact/` | Abstract compaction seam (interface + `compact/*` events + `CompactionResult`) | `ctx.compact` | | `compact-basic/` | A backend: `ctx.tokenMeter` pressure + token-budget retention + `llm.stream()` summarization | (registers `ctx.compact`) | -| `tool-result-prune/` | Optional model-free head/middle/tail rewriting before summary compaction | `ctx.toolResultPrune` | +| `compact-tool-result-prune/` | Optional model-free head/middle/tail rewriting before summary compaction | `ctx.toolResultPrune` | | `tool-compact/` (deferred) | Model-facing `/compact` tool over `ctx.compact` | (registers on `ctx.tools`) | -The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`, and deterministic pruning at `compact/tool-result-prune/`. Unlike the bash seam, the interface depends on `dsh-session` and `dsh-llm` because its verbs are defined over a `Session` and its output uses `ContentBlock`. That deviation is recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement remains a reusable LLM-family service; a template- or model-backed compactor can replace `compact-basic` without changing the meter, pruner, or callers. +The interface lives at `compact/compact/`, the backend at `compact/compact-basic/`, and deterministic pruning at `compact/compact-tool-result-prune/`. Unlike the bash seam, the interface depends on `dsh-session` and `dsh-llm` because its verbs are defined over a `Session` and its output uses `ContentBlock`. That deviation is recorded in the [compaction capability-seam RFC](../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md). Token measurement remains a reusable LLM-family service; a template- or model-backed compactor can replace `compact-basic` without changing the meter, pruner, or callers. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index 7acc1d0351..197fcd6ab6 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -9,8 +9,8 @@ This is the implementation tier of the compaction capability — see the [interf This backend owns the compaction policy: - **Measurement** — the singleton `ctx.tokenMeter` prices the latest canonical logged envelope and current surface at one consumed-log revision. Post-step pressure therefore includes the actual system prompt, tools, prefix, routing, assistant completion, tool results, buffered context, and steering. -- **Model-free pruning** — after pressure or canonical overflow qualifies, the optional [`ctx.toolResultPrune`](../tool-result-prune/README.md) service rewrites oversized tool results before range selection. Compact-basic remeasures through `ctx.tokenMeter`, skips summarization when pressure becomes safe, and otherwise summarizes the pruned surface. Below-pressure post-step checks never prune. -- **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes; a single unit larger than the budget remains out of scope. +- **Model-free pruning** — after pressure or canonical overflow qualifies, the optional [`ctx.toolResultPrune`](../compact-tool-result-prune/README.md) service rewrites oversized tool results before range selection. Compact-basic remeasures through `ctx.tokenMeter`, skips summarization when pressure becomes safe, and otherwise summarizes the pruned surface. Below-pressure post-step checks never prune. +- **Retention** — compact the oldest whole surface units while preserving a recent tail and balanced tool-call/result cuts through the [`dsh-compact` boundary helpers](../compact/README.md#tool-pairing-boundaries). Turn boundaries do not protect old steps inside a runaway turn. An open indivisible tail declines until it closes. The optional pruner can repair an oversized closed tool unit when its text-bearing result is the removable bulk; indivisible non-tool units and non-prunable tool remainders remain out of scope. - **Convergence** — retry head-checkpoint compaction up to `compactionRetries`; reject a summary that does not shrink its source, and throw if retries cannot return below threshold. - **Summarization** — a direct `llm/stream` call uses the configured model and cap without running the loop-only `agent/request` seam. The input transcript preserves non-text blocks as tagged placeholders; only returned text enters the checkpoint, excluding reasoning and tool calls that would leak private reasoning or create an orphaned call. - **Framing** — the replacement user message marks established checkpoint context with `` tags. The raw summary remains on the provenance event, and later automatic cycles merge the prior checkpoint. @@ -50,7 +50,7 @@ export function apply(ctx: Context): void { } ``` -Loading the plugin registers `ctx.compact`. Add [`dsh-tool-result-prune`](../tool-result-prune/README.md) as a sibling before this plugin to enable the optional model-free pass. With `auto: true` (the default) it compacts automatically under token pressure; a consumer (a future `/compact` tool) can also call `ctx.compact.compactIfNeeded(...)` or `ctx.compact.compactRegion(...)` directly. +Loading the plugin registers `ctx.compact`. Add [`dsh-compact-tool-result-prune`](../compact-tool-result-prune/README.md) as a sibling before this plugin to enable the optional model-free pass. With `auto: true` (the default) it compacts automatically under token pressure; a consumer (a future `/compact` tool) can also call `ctx.compact.compactIfNeeded(...)` or `ctx.compact.compactRegion(...)` directly. ## Model Experience @@ -120,7 +120,7 @@ Rules: - **Meter accuracy follows the fixed heuristic** — missing reusable provider usage falls back to character count plus structural overhead rather than exact tokenization. - **Overflow classification is adapter-maintained** — provider wording can change; both DeepSeek adapters normalize currently recognized context-limit failures to `CONTEXT_WINDOW_EXCEEDED`. -- **Single-unit and envelope-only overflow remain outside surface compaction** — recovery cannot split one indivisible message/tool unit or shrink system/tools/prefix. +- **Some indivisible-unit and envelope-only overflow remains outside surface compaction** — recovery cannot shrink system/tools/prefix, split an indivisible non-tool node, or repair a tool unit whose non-prunable remainder still exceeds the window. The optional pruner can shrink text-bearing tool-result bulk inside an otherwise indivisible pair. - **`compactRegion` requires an open turn** — a manual call on a fully-closed session throws ("no open turn") rather than compacting. -- **Summarization failure fails closed with full, over-budget history** — including truncation at the summarization `maxTokens`, which hidden reasoning tokens can consume; the auto path logs a warning and proceeds. +- **Summarization failure preserves the latest durable surface** — before any replacement, the auto path logs a warning and proceeds with full over-budget history. If pruning already landed, a later summarization failure proceeds from that durable pruned surface. Summarization truncation at `maxTokens`, which hidden reasoning tokens can consume, follows the same rule. - **The summarization call has no transcript-snapshot coverage** — `dsh-llm-replay` derives calls from `assistant/chunk` events, so this chunk-less direct `ctx.llm.stream()` call cannot replay (named deferred replay infrastructure in [the seam RFC](../../../docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md)). diff --git a/packages/compact/compact-basic/package.json b/packages/compact/compact-basic/package.json index 55ca301878..d242e3bed0 100644 --- a/packages/compact/compact-basic/package.json +++ b/packages/compact/compact-basic/package.json @@ -27,11 +27,11 @@ "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-token-meter": "^0.0.1", - "@deepseek-ai/dsh-tool-result-prune": "^0.0.1", + "@deepseek-ai/dsh-compact-tool-result-prune": "^0.0.1", "cordis": "^4.0.0-rc.7" }, "peerDependenciesMeta": { - "@deepseek-ai/dsh-tool-result-prune": { + "@deepseek-ai/dsh-compact-tool-result-prune": { "optional": true } }, @@ -49,7 +49,7 @@ "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-token-meter": "workspace:^", - "@deepseek-ai/dsh-tool-result-prune": "workspace:^", + "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.7" } diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index 34567f7e07..bd33e84355 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -13,7 +13,7 @@ import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' // Type-only: makes the optional sibling service available to `ctx.get()`. -import type {} from '@deepseek-ai/dsh-tool-result-prune' +import type {} from '@deepseek-ai/dsh-compact-tool-result-prune' import { resolveConfig } from './config.ts' import { compactSurfaceRegion, selectCompactableRange } from './region.ts' import { summarizeWithLlm } from './summarizer.ts' diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index 094a22a11e..c2e09a5081 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -9,7 +9,7 @@ import LlmService, { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, LlmAdapter } from '@d import type { ContentBlock, GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { Session, SessionId } from '@deepseek-ai/dsh-session' import TokenMeterService from '@deepseek-ai/dsh-token-meter' -import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' +import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune' import type { Agent } from '@deepseek-ai/dsh-agent' const SIGNAL = new AbortController().signal diff --git a/packages/compact/compact-basic/tests/loader-composition.spec.ts b/packages/compact/compact-basic/tests/loader-composition.spec.ts index 7294224452..2035627f64 100644 --- a/packages/compact/compact-basic/tests/loader-composition.spec.ts +++ b/packages/compact/compact-basic/tests/loader-composition.spec.ts @@ -9,7 +9,7 @@ import Include from '@cordisjs/plugin-include' import LlmService from '@deepseek-ai/dsh-llm' import TokenMeterService from '@deepseek-ai/dsh-token-meter' import BasicCompactService from '@deepseek-ai/dsh-compact-basic' -import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' +import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune' let root: string | undefined let context: Context | undefined @@ -33,7 +33,7 @@ async function loadYaml(lines: readonly string[]): Promise { const modules = new Map([ ['@deepseek-ai/dsh-llm', LlmService], ['@deepseek-ai/dsh-token-meter', TokenMeterService], - ['@deepseek-ai/dsh-tool-result-prune', ToolResultPruneService], + ['@deepseek-ai/dsh-compact-tool-result-prune', ToolResultPruneService], ['@deepseek-ai/dsh-compact-basic', BasicCompactService], ]) context.loader.internal = { @@ -58,7 +58,7 @@ describe('real Loader composition', () => { "- name: '@deepseek-ai/dsh-token-meter'", ' config:', ' contextWindow: 4096', - "- name: '@deepseek-ai/dsh-tool-result-prune'", + "- name: '@deepseek-ai/dsh-compact-tool-result-prune'", ' config:', ' thresholdChars: 100', ' headChars: 20', diff --git a/packages/compact/compact-basic/tsconfig.json b/packages/compact/compact-basic/tsconfig.json index 5dd00b83f1..47d552c3f0 100644 --- a/packages/compact/compact-basic/tsconfig.json +++ b/packages/compact/compact-basic/tsconfig.json @@ -14,6 +14,6 @@ { "path": "../../core/session" }, { "path": "../../core/agent" }, { "path": "../compact" }, - { "path": "../tool-result-prune" } + { "path": "../compact-tool-result-prune" } ] } diff --git a/packages/compact/tool-result-prune/README.md b/packages/compact/compact-tool-result-prune/README.md similarity index 96% rename from packages/compact/tool-result-prune/README.md rename to packages/compact/compact-tool-result-prune/README.md index e6d50f229c..9c405af12f 100644 --- a/packages/compact/tool-result-prune/README.md +++ b/packages/compact/compact-tool-result-prune/README.md @@ -1,4 +1,4 @@ -# @deepseek-ai/dsh-tool-result-prune +# @deepseek-ai/dsh-compact-tool-result-prune The replay-safe model-free pruning service (`ctx.toolResultPrune`). It rewrites over-budget `tool/result` surface nodes to a bounded head, a fixed omission marker, and a bounded tail while retaining the full original event in the append-only session log. @@ -28,7 +28,7 @@ All values are integers; the threshold is positive and head/tail are non-negativ ```ts import type { Context } from 'cordis' -import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' +import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune' export function apply(ctx: Context): void { ctx.plugin(ToolResultPruneService) diff --git a/packages/compact/tool-result-prune/package.json b/packages/compact/compact-tool-result-prune/package.json similarity index 94% rename from packages/compact/tool-result-prune/package.json rename to packages/compact/compact-tool-result-prune/package.json index 6b7ac89742..81c81eb894 100644 --- a/packages/compact/tool-result-prune/package.json +++ b/packages/compact/compact-tool-result-prune/package.json @@ -1,5 +1,5 @@ { - "name": "@deepseek-ai/dsh-tool-result-prune", + "name": "@deepseek-ai/dsh-compact-tool-result-prune", "description": "Replay-safe model-free head/middle/tail pruning for tool-result surface nodes", "version": "0.0.1", "private": true, diff --git a/packages/compact/tool-result-prune/src/config.ts b/packages/compact/compact-tool-result-prune/src/config.ts similarity index 100% rename from packages/compact/tool-result-prune/src/config.ts rename to packages/compact/compact-tool-result-prune/src/config.ts diff --git a/packages/compact/tool-result-prune/src/index.ts b/packages/compact/compact-tool-result-prune/src/index.ts similarity index 99% rename from packages/compact/tool-result-prune/src/index.ts rename to packages/compact/compact-tool-result-prune/src/index.ts index 287b0f2500..c03fa81724 100644 --- a/packages/compact/tool-result-prune/src/index.ts +++ b/packages/compact/compact-tool-result-prune/src/index.ts @@ -1,7 +1,7 @@ /** * Replay-safe, model-free tool-result pruning service. * - * @module @deepseek-ai/dsh-tool-result-prune + * @module @deepseek-ai/dsh-compact-tool-result-prune */ import { Context, Service } from 'cordis' diff --git a/packages/compact/tool-result-prune/src/types.ts b/packages/compact/compact-tool-result-prune/src/types.ts similarity index 100% rename from packages/compact/tool-result-prune/src/types.ts rename to packages/compact/compact-tool-result-prune/src/types.ts diff --git a/packages/compact/tool-result-prune/tests/loader-composition.spec.ts b/packages/compact/compact-tool-result-prune/tests/loader-composition.spec.ts similarity index 84% rename from packages/compact/tool-result-prune/tests/loader-composition.spec.ts rename to packages/compact/compact-tool-result-prune/tests/loader-composition.spec.ts index fef9326d2a..db4c29ebdb 100644 --- a/packages/compact/tool-result-prune/tests/loader-composition.spec.ts +++ b/packages/compact/compact-tool-result-prune/tests/loader-composition.spec.ts @@ -6,7 +6,7 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import Include from '@cordisjs/plugin-include' -import ToolResultPruneService from '@deepseek-ai/dsh-tool-result-prune' +import ToolResultPruneService from '@deepseek-ai/dsh-compact-tool-result-prune' let root: string | undefined let context: Context | undefined @@ -18,12 +18,12 @@ afterEach(async () => { root = undefined }) -describe('tool-result-prune real Loader composition', () => { +describe('compact-tool-result-prune real Loader composition', () => { it('loads and resolves the flat YAML plugin shape', async () => { - root = await mkdtemp(join(tmpdir(), 'dsh-tool-result-prune-loader-')) + root = await mkdtemp(join(tmpdir(), 'dsh-compact-tool-result-prune-loader-')) const configPath = join(root, 'cordis.yml') await writeFile(configPath, [ - "- name: '@deepseek-ai/dsh-tool-result-prune'", + "- name: '@deepseek-ai/dsh-compact-tool-result-prune'", ' config:', ' thresholdChars: 100', ' headChars: 20', @@ -38,7 +38,7 @@ describe('tool-result-prune real Loader composition', () => { context.loader.internal = { version: 'v2', async import(specifier: string) { - if (specifier !== '@deepseek-ai/dsh-tool-result-prune') { + if (specifier !== '@deepseek-ai/dsh-compact-tool-result-prune') { throw new Error(`unexpected Loader import: ${specifier}`) } return ToolResultPruneService diff --git a/packages/compact/tool-result-prune/tests/tool-result-prune.spec.ts b/packages/compact/compact-tool-result-prune/tests/tool-result-prune.spec.ts similarity index 98% rename from packages/compact/tool-result-prune/tests/tool-result-prune.spec.ts rename to packages/compact/compact-tool-result-prune/tests/tool-result-prune.spec.ts index 235ecdab52..b72c894891 100644 --- a/packages/compact/tool-result-prune/tests/tool-result-prune.spec.ts +++ b/packages/compact/compact-tool-result-prune/tests/tool-result-prune.spec.ts @@ -10,8 +10,8 @@ import ToolResultPruneService, { DEFAULTS, PRUNE_MARKER, resolveConfig, -} from '@deepseek-ai/dsh-tool-result-prune' -import type { ToolResultPruneConfig } from '@deepseek-ai/dsh-tool-result-prune' +} from '@deepseek-ai/dsh-compact-tool-result-prune' +import type { ToolResultPruneConfig } from '@deepseek-ai/dsh-compact-tool-result-prune' const SMALL: ToolResultPruneConfig = { thresholdChars: 50, diff --git a/packages/compact/tool-result-prune/tsconfig.json b/packages/compact/compact-tool-result-prune/tsconfig.json similarity index 100% rename from packages/compact/tool-result-prune/tsconfig.json rename to packages/compact/compact-tool-result-prune/tsconfig.json diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 40bbed7eba..1ee37e5b47 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -72,5 +72,5 @@ Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and ## Known Limitations and Deferred Work - **No model-facing consumer tier yet** — `@deepseek-ai/dsh-tool-compact` (the `/compact` tool) is deferred; compaction is reachable only via direct `ctx.compact` calls or a backend's auto listener. -- **Single-unit overflow is out of contract** — one indivisible unit (a closed tool pair or a large pasted `user/message`) alone exceeding the budget cannot be compacted. +- **Some single-unit overflow is out of contract** — balanced summary compaction cannot split one indivisible unit. The optional pruning companion can still repair a closed tool pair when text-bearing tool-result bulk is removable; a large non-tool node or a tool unit whose non-prunable remainder is oversized cannot be compacted. - **An envelope that alone approaches the window is not surface-compaction work** — compaction shrinks derived history, never the system prompt, tools, or session prefix. diff --git a/packages/core/tools/tests/gen-tool-catalog.spec.ts b/packages/core/tools/tests/gen-tool-catalog.spec.ts index 8657dca3ca..1ba64f6326 100644 --- a/packages/core/tools/tests/gen-tool-catalog.spec.ts +++ b/packages/core/tools/tests/gen-tool-catalog.spec.ts @@ -69,11 +69,6 @@ describe('gen-tool-catalog assertManifestComplete', () => { // is unlisted, so the guard must fire and name them. expect(() => { assertManifestComplete([]) }).toThrow(/not in the boot manifest/) expect(() => { assertManifestComplete([]) }).toThrow(/tool-bash/) - try { - assertManifestComplete([]) - } catch (error) { - expect(String(error)).not.toContain('tool-result-prune') - } }) }) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index b0935bde01..5de2ae6d61 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -256,9 +256,9 @@ importers: '@deepseek-ai/dsh-token-meter': specifier: workspace:^ version: link:../../llm/token-meter - '@deepseek-ai/dsh-tool-result-prune': + '@deepseek-ai/dsh-compact-tool-result-prune': specifier: workspace:^ - version: link:../tool-result-prune + version: link:../compact-tool-result-prune '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -266,7 +266,7 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@vendor+include)(@cordisjs/plugin-loader@vendor+loader) - packages/compact/tool-result-prune: + packages/compact/compact-tool-result-prune: dependencies: schemastery: specifier: ^3.18.0 @@ -2140,9 +2140,9 @@ importers: '@deepseek-ai/dsh-tool-fs': specifier: workspace:^ version: link:../../packages/fs/tool-fs - '@deepseek-ai/dsh-tool-result-prune': + '@deepseek-ai/dsh-compact-tool-result-prune': specifier: workspace:^ - version: link:../../packages/compact/tool-result-prune + version: link:../../packages/compact/compact-tool-result-prune '@deepseek-ai/dsh-tool-skill': specifier: workspace:^ version: link:../../packages/skill/tool-skill diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index a436f859fc..7b0f6b6a56 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -31,7 +31,7 @@ "@deepseek-ai/dsh-jsonrpc-demo": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-token-meter": "workspace:^", - "@deepseek-ai/dsh-tool-result-prune": "workspace:^", + "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", "@deepseek-ai/dsh-llm-pi-ai": "workspace:^", "@deepseek-ai/dsh-permission": "workspace:^", diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index db6acf2c43..bfbaef1df6 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -96,7 +96,7 @@ const SERVICE_ROLES: ServiceRole[] = [ }, { key: 'toolResultPrune', - pkg: 'tool-result-prune', + pkg: 'compact-tool-result-prune', title: 'Model-free tool-result pruning', mode: 'core', consumers: ['compact-basic'], diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 4a0efe66a7..3e3a0ce81b 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -1,9 +1,8 @@ /** * Generate `docs/tool-catalog.md` from schemas collected by booting each tool * plugin. Runtime registration is the source of truth for computed schemas; - * the manifest is checked against every on-disk model-facing `tool-*` package; - * non-model service packages with that prefix are explicitly excluded. - * `--check` verifies the committed artifact. Rationale and ownership live in + * the manifest is checked against every on-disk `tool-*` package. `--check` + * verifies the committed artifact. Rationale and ownership live in * `docs/rfc/implemented/process/2026-07-02-tool-schema-catalog.md`. */ @@ -39,9 +38,6 @@ import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' const root = resolve(import.meta.dirname, '..') const OUT = 'docs/tool-catalog.md' -/** `tool-*` leaves that are runtime services, not contributors to `ctx.tools`. */ -const NON_MODEL_TOOL_PACKAGES = new Set(['tool-result-prune']) - /** * Tool package plus its hand-maintained boot recipe. The caller mounts the * prompt and registry; each recipe supplies only package-specific seams and @@ -81,10 +77,9 @@ interface ToolPackage { } /** - * The boot manifest: every shipped model-facing tool package (a `tool-*` leaf - * under `packages/`, excluding {@link NON_MODEL_TOOL_PACKAGES}). Ordered by - * package name (the render order); the completeness guard proves it is - * exhaustive against the filtered on-disk glob. + * The boot manifest: every shipped tool package (a `tool-*` leaf under + * `packages/`). Ordered by package name (the render order); the completeness + * guard proves it is exhaustive against the on-disk glob. */ const TOOL_PACKAGES: ToolPackage[] = [ { @@ -261,9 +256,8 @@ interface CatalogPackage { export type ToolCatalog = CatalogPackage[] /** - * Assert the boot manifest covers every shipped model-facing tool package on - * disk (a `tool-*` leaf under `packages/`, excluding explicit service-only - * entries in {@link NON_MODEL_TOOL_PACKAGES}). + * Assert the boot manifest covers every shipped tool package on disk (a + * `tool-*` leaf under `packages/`). * Booting has no source declaration to enumerate, so this glob restores the * "a new tool cannot be silently undocumented" guarantee: an unlisted package * fails the generator (and the freshness gate) until it is added to @@ -272,10 +266,7 @@ export type ToolCatalog = CatalogPackage[] * `scanRoot` defaults to the repo root; a test may point it at a fixture tree. */ export function assertManifestComplete(packages: ToolPackage[] = TOOL_PACKAGES, scanRoot: string = root): void { - const onDisk = globSync('packages/*/tool-*', { cwd: scanRoot }) - .map(p => basename(p)) - .filter(dir => !NON_MODEL_TOOL_PACKAGES.has(dir)) - .sort() + const onDisk = globSync('packages/*/tool-*', { cwd: scanRoot }).map(p => basename(p)).sort() const listed = new Set(packages.map(p => p.dir)) const missing = onDisk.filter(dir => !listed.has(dir)) if (missing.length > 0) { @@ -348,9 +339,9 @@ export function render(catalog: ToolCatalog): string { '', 'Every model-facing tool a shipped plugin contributes to `ctx.tools`: the `name`, `description`, and JSON-Schema `parameters` the model receives via the system-prompt assembly. It complements the cordis [events](cordis-catalog/events.md) & [services](cordis-catalog/services.md) catalogs (the wiring a plugin listens to and calls) and [core-data-structures/](core-data-structures/core.md) (the types those signatures move) — this page is the *tools* the agent is offered.', '', - 'This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any model-facing package is missing from the generator\'s boot manifest; service-only packages that share the prefix are explicitly excluded. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md).', + 'This file is GENERATED and verified fresh by `pnpm run verify-tool-catalog` (part of `doc-sync`) — do not edit it by hand. Unlike the cordis catalog (a pure source-AST pass), this generator BOOTS each tool plugin on a real context and reads `ctx.tools.schemas()`, because a tool schema is not statically knowable (runtime-spread enums, concatenated descriptions, config-driven names, raw-JSON-Schema MCP tools). A completeness guard globs `packages/*/tool-*` and fails if any package is missing from the generator\'s boot manifest, so a new tool cannot be silently undocumented. See [the tool-schema-catalog RFC](rfc/implemented/process/2026-07-02-tool-schema-catalog.md).', '', - 'Scope: shipped model-facing product tools under `packages/*/tool-*`, each booted with its DEFAULT config. Runtime service packages such as `tool-result-prune` do not register `ctx.tools` schemas and are explicitly excluded. The registered tool NAME can be a load-time config (e.g. `tool-subagent`\'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog\'s packages-only scope.', + 'Scope: shipped product tools under `packages/*/tool-*`, each booted with its DEFAULT config. The registered tool NAME can be a load-time config (e.g. `tool-subagent`\'s `toolName`), so a deployment may surface a package under a different or additional name — a per-package note records those shipped aliases where they exist. The `examples/` demo tools (e.g. `echo`) are excluded, matching the cordis catalog\'s packages-only scope.', '', '## Tool Package Map', '', diff --git a/tsconfig.build.json b/tsconfig.build.json index a099fc3a23..6cdef1f6c9 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -38,7 +38,7 @@ { "path": "./packages/code-runtime/code-runtime-worker" }, { "path": "./packages/compact/compact" }, { "path": "./packages/compact/compact-basic" }, - { "path": "./packages/compact/tool-result-prune" }, + { "path": "./packages/compact/compact-tool-result-prune" }, { "path": "./packages/llm/llm-deepseek" }, { "path": "./packages/llm/llm-pi-ai" }, { "path": "./packages/bash/bash-local" }, diff --git a/tsconfig.json b/tsconfig.json index 1decda2db0..9cc7c5ce83 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -60,7 +60,7 @@ { "path": "./packages/fs/tool-fs" }, { "path": "./packages/compact/compact" }, { "path": "./packages/compact/compact-basic" }, - { "path": "./packages/compact/tool-result-prune" }, + { "path": "./packages/compact/compact-tool-result-prune" }, { "path": "./packages/web/web" }, { "path": "./packages/web/web-search-exa" }, { "path": "./packages/web/web-search-perplexity" }, From 96975f3840ba0dc64327a306e4044e9694858767 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 17 Jul 2026 10:15:19 +0800 Subject: [PATCH 151/323] fix(session-persistence): create SQLite databases owner-only --- docs/config-catalog.md | 6 +-- .../session-persistence-sqlite/README.md | 2 +- .../session-persistence-sqlite/src/index.ts | 17 +++++-- .../tests/sqlite.spec.ts | 50 ++++++++++++++++++- 4 files changed, 66 insertions(+), 9 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 91fe7c6497..9474a4877b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -603,8 +603,8 @@ Requires: `sessions` export interface Config { /** * Filesystem path to the SQLite database file. The special value `:memory:` - * opens an in-process database (tests); a file path is created (with parent - * dirs) on construction. + * opens an in-process database (tests). Missing directories and the database + * are created with owner-only permissions; existing path modes are preserved. */ path: string /** @@ -627,7 +627,7 @@ export interface Config { export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' ``` -Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:38`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) +Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:48`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) ## `@deepseek-ai/dsh-session-query` diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index 1411e177be..1dd480bc38 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -8,7 +8,7 @@ A SQLite durable session-persistence backend — a second `SessionPersistence` i Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, type, time, data, source_event_seqs, surface_op)` — `data` is the event payload as JSON text, so the row shape is the event verbatim (including `assistant/chunk`, keeping `seq` contiguous). The two `TEXT` columns `source_event_seqs` and `surface_op` are nullable; they store the event's optional surface-metadata fields (see [session surface](../../../docs/rfc/implemented/architecture/2026-06-18-session-surface.md)). Out-of-log metadata (`SessionHeader`) lives in a `sessions` row. A `sessions` row is written only by the first `append` — its existence is the lazy-materialization signal (`list` reports exactly the sessions that have a row), so no separate column is needed. -The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. +The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). On filesystems with POSIX modes, missing directories are created as `0700` and a missing database is exclusively created as `0600` before SQLite opens it, causing new WAL sidecars to inherit owner-only access. Existing directories, database files, and sidecars keep their modes; ordinary filesystem access errors still fail initialization. `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. ## Contract semantics over rows diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts index 7d23292e9d..9f0b7cb7c4 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/index.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts @@ -8,7 +8,7 @@ import { Context } from 'cordis' import z from 'schemastery' import { DatabaseSync } from 'node:sqlite' -import { mkdir } from 'node:fs/promises' +import { mkdir, open } from 'node:fs/promises' import { dirname, resolve } from 'node:path' import { SessionPersistence, PersistenceCoordinator, @@ -34,12 +34,22 @@ function surfaceBindings(event: SessionEvent): [string | null, string | null] { ] } +/** Create a missing database owner-only while preserving an existing file's mode. */ +async function createDatabaseFile(path: string): Promise { + try { + const handle = await open(path, 'wx', 0o600) + await handle.close() + } catch (error) { + if ((error as NodeJS.ErrnoException).code !== 'EEXIST') throw error + } +} + /** Plugin configuration. */ export interface Config { /** * Filesystem path to the SQLite database file. The special value `:memory:` - * opens an in-process database (tests); a file path is created (with parent - * dirs) on construction. + * opens an in-process database (tests). Missing directories and the database + * are created with owner-only permissions; existing path modes are preserved. */ path: string /** @@ -87,6 +97,7 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers if (path !== ':memory:') { const abs = resolve(path) await mkdir(dirname(abs), { recursive: true, mode: 0o700 }) + await createDatabaseFile(abs) this.db = openDatabase(abs, journalMode) } else { this.db = openDatabase(path, journalMode) diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index bae79b0a53..3606afce67 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -1,9 +1,9 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import { existsSync } from 'node:fs' -import { mkdtemp, rm } from 'node:fs/promises' +import { chmod, mkdtemp, mkdir, rm, stat, writeFile } from 'node:fs/promises' import { tmpdir } from 'node:os' -import { join } from 'node:path' +import { dirname, join } from 'node:path' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { Session, SessionEvent, SurfaceEvent, SurfaceEventType } from '@deepseek-ai/dsh-session' import SessionPersistenceSqlite, { SCHEMA_VERSION } from '@deepseek-ai/dsh-session-persistence-sqlite' @@ -348,6 +348,52 @@ describe('SessionPersistenceSqlite: durability and crash semantics', () => { }) describe('SessionPersistenceSqlite: edge cases', () => { + it('creates a new database and WAL sidecars owner-only without changing an existing directory mode', async () => { + if (process.platform === 'win32') return + const path = await freshDbPath() + const dir = dirname(path) + await chmod(dir, 0o755) + + const b = await backend(path) + await b.ctx.sessionPersistence.list() + + expect((await stat(dir)).mode & 0o777).toBe(0o755) + expect((await stat(path)).mode & 0o777).toBe(0o600) + expect((await stat(`${path}-wal`)).mode & 0o777).toBe(0o600) + expect((await stat(`${path}-shm`)).mode & 0o777).toBe(0o600) + await b.dispose() + }) + + it('preserves the mode of an existing database file', async () => { + if (process.platform === 'win32') return + const path = await freshDbPath() + await writeFile(path, '', { mode: 0o644 }) + await chmod(path, 0o644) + + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(SessionPersistenceSqlite, { path, journalMode: 'delete' }) + await ctx.sessionPersistence.list() + + expect((await stat(path)).mode & 0o777).toBe(0o644) + await fiber.dispose() + }) + + it('surfaces database pre-creation errors other than an existing file', async () => { + if (process.platform === 'win32') return + const path = await freshDbPath() + const blocked = join(dirname(path), 'blocked') + await mkdir(blocked, { mode: 0o500 }) + const b = await backend(join(blocked, 'sessions.db')) + + try { + await expect(b.ctx.sessionPersistence.list()).rejects.toMatchObject({ code: 'EACCES' }) + await b.dispose() + } finally { + await chmod(blocked, 0o700) + } + }) + it('append rolls back and rethrows when an event INSERT fails inside the transaction', async () => { const path = await freshDbPath() const m = meta('rollback-insert') From ac893f97bbbc3727beeab4034d689464dc4f2018 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 17 Jul 2026 10:47:32 +0800 Subject: [PATCH 152/323] fix(session-persistence): address permission review --- docs/config-catalog.md | 4 +++- .../session-persistence-sqlite/README.md | 2 +- .../session-persistence-sqlite/src/index.ts | 8 +++++++- .../tests/sqlite.spec.ts | 17 +++++------------ 4 files changed, 16 insertions(+), 15 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9474a4877b..49607eb494 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -605,6 +605,8 @@ export interface Config { * Filesystem path to the SQLite database file. The special value `:memory:` * opens an in-process database (tests). Missing directories and the database * are created with owner-only permissions; existing path modes are preserved. + * Parent directories writable by another principal are outside the backend's + * database-integrity boundary. */ path: string /** @@ -627,7 +629,7 @@ export interface Config { export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' ``` -Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:48`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) +Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:52`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) ## `@deepseek-ai/dsh-session-query` diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index 1dd480bc38..b5f85bd1a8 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -8,7 +8,7 @@ A SQLite durable session-persistence backend — a second `SessionPersistence` i Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, type, time, data, source_event_seqs, surface_op)` — `data` is the event payload as JSON text, so the row shape is the event verbatim (including `assistant/chunk`, keeping `seq` contiguous). The two `TEXT` columns `source_event_seqs` and `surface_op` are nullable; they store the event's optional surface-metadata fields (see [session surface](../../../docs/rfc/implemented/architecture/2026-06-18-session-surface.md)). Out-of-log metadata (`SessionHeader`) lives in a `sessions` row. A `sessions` row is written only by the first `append` — its existence is the lazy-materialization signal (`list` reports exactly the sessions that have a row), so no separate column is needed. -The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). On filesystems with POSIX modes, missing directories are created as `0700` and a missing database is exclusively created as `0600` before SQLite opens it, causing new WAL sidecars to inherit owner-only access. Existing directories, database files, and sidecars keep their modes; ordinary filesystem access errors still fail initialization. `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. +The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). On filesystems with POSIX modes, missing directories are created as `0700` and a missing database is exclusively created as `0600` before SQLite opens it, causing new WAL sidecars to inherit owner-only access. Existing directories, database files, and sidecars keep their modes; ordinary filesystem access errors still fail initialization. This default prevents incidental exposure through the process umask; it does not protect database integrity when another principal can modify entries in an existing parent directory. `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. ## Contract semantics over rows diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts index 9f0b7cb7c4..45c05f750b 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/index.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts @@ -34,7 +34,11 @@ function surfaceBindings(event: SessionEvent): [string | null, string | null] { ] } -/** Create a missing database owner-only while preserving an existing file's mode. */ +/** + * Create a missing database owner-only while preserving an existing file's + * mode. `DatabaseSync` cannot adopt this handle, so a parent directory writable + * by another principal is outside the backend's database-integrity boundary. + */ async function createDatabaseFile(path: string): Promise { try { const handle = await open(path, 'wx', 0o600) @@ -50,6 +54,8 @@ export interface Config { * Filesystem path to the SQLite database file. The special value `:memory:` * opens an in-process database (tests). Missing directories and the database * are created with owner-only permissions; existing path modes are preserved. + * Parent directories writable by another principal are outside the backend's + * database-integrity boundary. */ path: string /** diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index 3606afce67..50d761a39d 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -1,7 +1,7 @@ import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' import { existsSync } from 'node:fs' -import { chmod, mkdtemp, mkdir, rm, stat, writeFile } from 'node:fs/promises' +import { chmod, mkdtemp, rm, stat, writeFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { dirname, join } from 'node:path' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' @@ -379,19 +379,12 @@ describe('SessionPersistenceSqlite: edge cases', () => { await fiber.dispose() }) - it('surfaces database pre-creation errors other than an existing file', async () => { - if (process.platform === 'win32') return + it('surfaces database pre-creation errors independently of process privileges', async () => { const path = await freshDbPath() - const blocked = join(dirname(path), 'blocked') - await mkdir(blocked, { mode: 0o500 }) - const b = await backend(join(blocked, 'sessions.db')) + const b = await backend(`${path}\0`) - try { - await expect(b.ctx.sessionPersistence.list()).rejects.toMatchObject({ code: 'EACCES' }) - await b.dispose() - } finally { - await chmod(blocked, 0o700) - } + await expect(b.ctx.sessionPersistence.list()).rejects.toMatchObject({ code: 'ERR_INVALID_ARG_VALUE' }) + await b.dispose() }) it('append rolls back and rethrows when an event INSERT fails inside the transaction', async () => { From 1119c537d0aa52f720955e9209eb07fc2e02cd09 Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 17 Jul 2026 12:01:37 +0800 Subject: [PATCH 153/323] feat(ui): add dedicated TUI package Move the interactive pi-tui front door into @deepseek-ai/dsh-tui while keeping @deepseek-ai/dsh-stdio line-oriented for pipes. Select the terminal package in the demo app, preserve logger ownership, and cover the production Loader composition with a PTY smoke test. --- AGENTS.md | 2 +- README.i18n.yaml | 4 +- README.md | 2 +- README.zh.md | 2 +- docs/architecture.md | 2 +- docs/config-catalog.md | 57 +- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/core-data-structures/user-interaction.md | 2 +- docs/development.i18n.yaml | 4 +- docs/development.md | 2 +- docs/development.zh.md | 2 +- docs/event-producer-consumer.md | 10 +- docs/i18n/translation-prompt.md | 6 +- docs/module-graph.md | 10 +- examples/README.md | 2 +- examples/coding-agent/README.md | 20 +- examples/coding-agent/composition.md | 4 +- examples/coding-agent/cordis.yml | 11 +- .../tests/tui-keyless-smoke.e2e.ts | 101 ++ examples/cordis-agent/composition.md | 2 +- examples/echo-agent/README.md | 2 +- examples/echo-agent/composition.md | 2 +- examples/echo-agent/cordis.yml | 2 +- knip.json | 2 +- packages/examples/README.md | 4 +- packages/examples/agent-spine-demo/README.md | 2 +- packages/examples/stdio-demo/README.md | 24 +- packages/examples/stdio-demo/package.json | 8 +- packages/examples/stdio-demo/src/bin.ts | 2 +- packages/examples/stdio-demo/src/index.ts | 86 +- .../stdio-demo/tests/stdio-agent.spec.ts | 45 +- packages/examples/stdio-demo/tsconfig.json | 3 + packages/todo/README.md | 2 +- packages/todo/tool-todo/README.md | 2 +- packages/ui/README.md | 7 +- packages/ui/acp/README.md | 2 +- packages/ui/tui/README.md | 56 + packages/ui/tui/package.json | 45 + packages/ui/tui/src/index.ts | 1284 +++++++++++++++++ packages/ui/tui/tests/plugin-shape.spec.ts | 19 + packages/ui/tui/tests/tui.spec.ts | 952 ++++++++++++ packages/ui/tui/tsconfig.json | 33 + packages/ui/user-interaction/README.md | 2 +- pnpm-lock.yaml | 56 + scripts/gen-doc-graphs.ts | 4 +- tsconfig.build.json | 1 + tsconfig.json | 1 + 49 files changed, 2808 insertions(+), 93 deletions(-) create mode 100644 examples/coding-agent/tests/tui-keyless-smoke.e2e.ts create mode 100644 packages/ui/tui/README.md create mode 100644 packages/ui/tui/package.json create mode 100644 packages/ui/tui/src/index.ts create mode 100644 packages/ui/tui/tests/plugin-shape.spec.ts create mode 100644 packages/ui/tui/tests/tui.spec.ts create mode 100644 packages/ui/tui/tsconfig.json diff --git a/AGENTS.md b/AGENTS.md index 23d7c0263b..f695fbac3b 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -26,7 +26,7 @@ packages/ Harness packages at packages///, all named @deepseek-ai cordis/ self-referential toolset: the agent inspects/mounts plugins in its own runtime hooks/ Claude Code / Codex hook bridges + shared wire-protocol library session-persistence/ persistence seam + JSONL/SQLite backends - ui/ ACP/stdio/JSON-RPC bridges; boot, approval, interaction plugins + ui/ ACP/stdio/TUI/JSON-RPC bridges; boot, approval, interaction plugins examples/ demo bundles (agent-spine + stdio/ACP/JSON-RPC bins) leaves load support/ dev/test infrastructure packages util/ zero-dependency utilities diff --git a/README.i18n.yaml b/README.i18n.yaml index 790812344d..628d7168da 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 53dd3896eb15800125673e7c44f7de02daca9376 -README.zh.md: ab826f62658248249ec18c57b35c0065c0f909d1 +README.md: 92cbfaa8196b49d2b801776f0e0c178cb5f673dc +README.zh.md: 28604ad1e2926edd7d4eb91c8027785433a54d32 diff --git a/README.md b/README.md index 53dd3896eb..92cbfaa819 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,7 @@ This monorepo is built on the [Cordis](https://github.com/cordiverse/cordis) fra ```sh pnpm install pnpm run test # vitest -pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:repl # interactive pi-tui coding agent (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/README.zh.md b/README.zh.md index ab826f6265..28604ad1e2 100644 --- a/README.zh.md +++ b/README.zh.md @@ -11,7 +11,7 @@ ```sh pnpm install pnpm run test # vitest -pnpm run demo:repl # REPL agent demo (needs DEEPSEEK_API_KEY) +pnpm run demo:repl # interactive pi-tui coding agent (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/docs/architecture.md b/docs/architecture.md index 848980a45a..0f6de3af03 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -139,7 +139,7 @@ Some seams bend the template deliberately. LLM keeps interface and consumer voca ### Bundles And Apps -`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` for terminal REPL, and `dsh-acp-demo` for ACP over JSON-RPC stdio with no stdout logger ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). +`dsh-agent-spine-demo` is the default composition bundle: one plugin loading the shared spine ([README](../packages/examples/agent-spine-demo/README.md)). App packages compose it with a front door and boot `bin`: `dsh-stdio-demo` selects the `dsh-tui` package on interactive terminals and `dsh-stdio` on pipes, while `dsh-acp-demo` serves ACP over JSON-RPC stdio ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` instead boots an external `cordis.yml`; the Python SDK injects the package default only when no explicit config channel is set and drives `dsh-jsonrpc` over line-delimited stdio JSON-RPC ([Python SDK](../python/README.md)). A deployment is a thin `cordis.yml` leaf: swappable backends, one app entry, and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). ### Where New Behavior Goes diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 91fe7c6497..79aa6ce17a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -700,7 +700,7 @@ Source: [`packages/ui/stdio/src/index.ts:30`](../packages/ui/stdio/src/index.ts) * is the explicit model-facing tool order (forwarded to the system-prompt plugin); * fresh sessions use `process.cwd()` as their workspace cwd; resumed sessions * keep their persisted cwd. `persistenceRoot` is the JSONL backend's directory; - * `welcome` is the UI banner. + * `welcome` is the UI banner and `ui` configures terminal mode/presentation. */ export interface Config { /** Model name for the `main` agent (must have a registered adapter). */ @@ -713,8 +713,10 @@ export interface Config { tools?: ToolsConfig /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string - /** stdin-chat banner printed once on start. Defaults to `'ready.'`. */ + /** Terminal banner printed once on start. Defaults to `'ready.'`. */ welcome?: string + /** Terminal front-door selection and pi-tui presentation settings. */ + ui?: UiConfig /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-spine-demo. */ skills?: agentCore.SkillConfig /** Model-facing bash tool config forwarded through agent-core. */ @@ -728,11 +730,22 @@ export interface Config { */ resumeSessionId?: string } + +/** App-level terminal selection with nested TUI presentation settings. */ +export interface UiConfig { + /** Select a concrete front door or infer it from the process streams. */ + mode?: TerminalMode + /** Settings forwarded only when the pi-tui front door is selected. */ + tui?: uiTui.TuiConfig +} + +/** Terminal front door selected by the app bundle. */ +export type TerminalMode = 'auto' | 'readline' | 'tui' ``` -Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) +Depends on: [`agentCore`](../packages/examples/agent-spine-demo/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`uiTui`](../packages/ui/tui/src/index.ts) -Source: [`packages/examples/stdio-demo/src/index.ts:36`](../packages/examples/stdio-demo/src/index.ts) +Source: [`packages/examples/stdio-demo/src/index.ts:73`](../packages/examples/stdio-demo/src/index.ts) ## `@deepseek-ai/dsh-subagent-acp` @@ -1075,6 +1088,42 @@ export type ToolPresentationMode = 'native' | 'code' | 'both' Source: [`packages/core/tools/src/index.ts:307`](../packages/core/tools/src/index.ts) +## `@deepseek-ai/dsh-tui` + +Requires: `agents` · `userInteraction` · `tools` + +```ts config-catalog +/** Serializable plugin configuration. */ +export interface Config extends TuiConfig { + /** Header subtitle. Defaults to `ready.`. */ + welcome?: string + /** Agent id driven by this terminal. Defaults to `main`. */ + agent?: string +} + +/** Presentation settings for the pi-tui terminal mode. */ +export interface TuiConfig { + /** Render model reasoning blocks. */ + showReasoning?: boolean + /** Maximum tool-output lines shown before the card is collapsed. */ + maxToolOutputLines?: number + /** Maximum options visible at once in a user-question dialog. */ + maxQuestionOptions?: number + /** User-question dialog width in terminal columns. */ + questionDialogWidth?: number + /** User-question dialog maximum height in terminal rows. */ + questionDialogMaxHeight?: number + /** Show the terminal's hardware cursor at the pi editor's IME marker. */ + showHardwareCursor?: boolean + /** Apply the built-in ANSI color palette. */ + color?: boolean + /** Terminal window title while the UI is mounted. */ + title?: string +} +``` + +Source: [`packages/ui/tui/src/index.ts:100`](../packages/ui/tui/src/index.ts) + ## `@deepseek-ai/dsh-user-approval` ```ts config-catalog diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 207ea114e0..598e9827b1 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 3474bc116b43f9be57b52e947f9cf99730f7e796 -extension-cookbook.zh.md: 1a605b20fe4e171a948ac2a046193a2f4d884e44 +extension-cookbook.md: 02dc22ff72807629a89d602f49752e6f429587b5 +extension-cookbook.zh.md: a204abdf6656312aea94640c60038af9f81f4f7b diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 3474bc116b..02dc22ff72 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## Runnable wirings -Three complete examples load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool — the all-mock skeleton check, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + the bash tool suite behind a terminal REPL UI, `pnpm run demo:repl`), and [`examples/acp-agent`](../../examples/acp-agent) (an agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, `pnpm run demo:acp`). Each leaf is just its swappable backends plus an app-package entry: the stdio demos load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP demo loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine via the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle. +Three complete examples load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool — the all-mock skeleton check, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + the bash tool suite behind a pi-tui coding interface with a readline fallback, `pnpm run demo:repl`), and [`examples/acp-agent`](../../examples/acp-agent) (an agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, `pnpm run demo:acp`). Each leaf is just its swappable backends plus an app-package entry: the stdio demos load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP demo loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine via the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle. ## The feature → mechanism map diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 1a605b20fe..a204abdf66 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## 可运行的组装示例 -三个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + bash 工具套件，配合终端 REPL UI，`pnpm run demo:repl`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子只是其可替换后端加一个 app 包入口：stdio 演示加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 演示加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle 共享主干。 +三个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + bash 工具套件，配合 pi-tui 编码界面，并为管道输入保留 readline 回退，`pnpm run demo:repl`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子只是其可替换后端加一个 app 包入口：stdio 演示加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 演示加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle 共享主干。 ## 功能→机制映射 diff --git a/docs/core-data-structures/user-interaction.md b/docs/core-data-structures/user-interaction.md index 4edc415039..afe61af475 100644 --- a/docs/core-data-structures/user-interaction.md +++ b/docs/core-data-structures/user-interaction.md @@ -1,6 +1,6 @@ # User Interaction -The user-interaction seam of [dsh-user-interaction](../../packages/ui/user-interaction). It is the provider-neutral vocabulary a tool or permission plugin uses when it needs the human to answer before the agent can continue. UI surfaces provide the active `UserInteractionProvider`: `dsh-stdio-demo` renders questions in readline, and `dsh-acp` maps them to ACP form elicitations. +The user-interaction seam of [dsh-user-interaction](../../packages/ui/user-interaction). It is the provider-neutral vocabulary a tool or permission plugin uses when it needs the human to answer before the agent can continue. UI surfaces provide the active `UserInteractionProvider`: `dsh-stdio-demo` selects keyboard-driven `dsh-tui` overlays or `dsh-stdio` readline prompts, and `dsh-acp` maps questions to ACP form elicitations. Source: [`packages/ui/user-interaction/src/index.ts`](../../packages/ui/user-interaction/src/index.ts) diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index 494eb09922..1d687a3f90 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: b3c338f03f548b4de4b676850732731323d611f1 -development.zh.md: 20f5c585dd378a7b0a3bd6b0af8ebf7dc5e0fd3c +development.md: 512fdcd89b4d481dd2033bc4f4c2816a04b5feaa +development.zh.md: 9f2038a99b289d06f16d7d51f0d043caa34a300e diff --git a/docs/development.md b/docs/development.md index b3c338f03f..512fdcd89b 100644 --- a/docs/development.md +++ b/docs/development.md @@ -109,7 +109,7 @@ The echo demo does not need API credentials: pnpm run demo:echo ``` -The REPL agent demo uses the real DeepSeek adapter and needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`: +The coding-agent demo uses pi-tui interactively, falls back to readline for pipes, and needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`: ```sh pnpm run demo:repl diff --git a/docs/development.zh.md b/docs/development.zh.md index 20f5c585dd..9f2038a99b 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -109,7 +109,7 @@ echo 演示不需要 API 凭证： pnpm run demo:echo ``` -REPL agent 演示使用真实的 DeepSeek 适配器，需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`： +coding-agent 演示在交互终端中使用 pi-tui，对管道输入回退到 readline，并需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`： ```sh pnpm run demo:repl diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index d8c924b24d..b67788ea6b 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,16 +7,16 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`tui`](../packages/ui/tui) | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | | `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | | `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | | `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | @@ -27,7 +27,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio) | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:108`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:82`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | diff --git a/docs/i18n/translation-prompt.md b/docs/i18n/translation-prompt.md index 8bc15d6e8e..4dd877bea4 100644 --- a/docs/i18n/translation-prompt.md +++ b/docs/i18n/translation-prompt.md @@ -123,9 +123,9 @@ Follow the Good versions; these sentence-level examples illustrate error categor - Good: `A green gate does not mean the translation is correct.` ### Code block comments — never translate -- Source code block contains: `# REPL agent demo (needs DEEPSEEK_API_KEY)` -- Bad: `# REPL agent 演示（需要 DEEPSEEK_API_KEY）` -- Good: `# REPL agent demo (needs DEEPSEEK_API_KEY)` (byte-identical) +- Source code block contains: `# interactive pi-tui coding agent (needs DEEPSEEK_API_KEY)` +- Bad: `# 交互式 pi-tui 编码 agent（需要 DEEPSEEK_API_KEY）` +- Good: `# interactive pi-tui coding agent (needs DEEPSEEK_API_KEY)` (byte-identical) ### Language switcher — English to Chinese - Source: `English | [中文](README.zh.md)` diff --git a/docs/module-graph.md b/docs/module-graph.md index 82763bdc55..e5d56709a8 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -98,6 +98,7 @@ flowchart TD pkg_permission["permission"] pkg_stdio["stdio"] pkg_tool_ask_user["tool-ask-user"] + pkg_tui["tui"] pkg_user_approval["user-approval"] pkg_user_interaction["user-interaction"] end @@ -287,6 +288,11 @@ flowchart TD pkg_tool_ask_user --> pkg_agent pkg_tool_ask_user --> pkg_tools pkg_tool_ask_user --> pkg_user_interaction + pkg_tui --> pkg_agent + pkg_tui --> pkg_llm + pkg_tui --> pkg_session + pkg_tui --> pkg_tools + pkg_tui --> pkg_user_interaction pkg_repeat_tool_guard --> pkg_agent pkg_repeat_tool_guard --> pkg_tools pkg_mcp_client --> pkg_llm @@ -370,6 +376,7 @@ flowchart TD pkg_stdio_demo --> pkg_stdio pkg_stdio_demo --> pkg_tool_ask_user pkg_stdio_demo --> pkg_tools + pkg_stdio_demo --> pkg_tui pkg_stdio_demo --> pkg_user_interaction ``` @@ -437,6 +444,7 @@ flowchart TD | [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`tui`](../packages/ui/tui) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | | [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | | [`tool-tasks`](../packages/tasks/tool-tasks) | `tasks` | [`agent`](../packages/core/agent), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | @@ -452,4 +460,4 @@ flowchart TD | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`acp-demo`](../packages/examples/acp-demo) | `examples` | [`acp`](../packages/ui/acp), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | -| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | +| [`stdio-demo`](../packages/examples/stdio-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-spine-demo`](../packages/examples/agent-spine-demo), [`app-boot`](../packages/ui/app-boot), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence-jsonl`](../packages/session-persistence/session-persistence-jsonl), [`stdio`](../packages/ui/stdio), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tools`](../packages/core/tools), [`tui`](../packages/ui/tui), [`user-interaction`](../packages/ui/user-interaction) | diff --git a/examples/README.md b/examples/README.md index 5db1e18372..25c017824f 100644 --- a/examples/README.md +++ b/examples/README.md @@ -15,7 +15,7 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge ## coding-agent -A REPL agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. The UI is a terminal readline REPL. +A coding-agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. Interactive runs use the pi-tui coding interface; pipes use readline. Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index 9e627324d4..c1c4747a22 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -1,6 +1,6 @@ # coding-agent -The REPL agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + stdio chat + JSONL persistence, loaded from `cordis.yml`. The UI is a terminal readline REPL. +The coding-agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + terminal chat + JSONL persistence, loaded from `cordis.yml`. Interactive runs use the pi-tui coding interface; piped runs use readline. ## Run it @@ -11,15 +11,9 @@ The REPL agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem t pnpm run demo:repl ``` -Type a coding task. The agent works through the `read`/`write`/`edit` filesystem tools for ordinary file operations and `bash` (+ the generic `task_output` / `task_list` / `task_kill` for background tasks) for shell commands, searches, and test runs, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). Both the fs tools and bash resolve relative paths against the session workspace. It can also delegate with `subagent`/`subagent_fork` and track multi-step work with `todo_write` (a whole-list task tracker rendered as a checklist). Reasoning streams dimmed; tool calls/results render inline. +Type a coding task. The agent works through the `read`/`write`/`edit` filesystem tools for ordinary file operations and `bash` (+ the generic `task_output` / `task_list` / `task_kill` for background tasks) for shell commands, searches, and test runs, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). Both the fs tools and bash resolve relative paths against the session workspace. It can also delegate with `subagent`/`subagent_fork` and track multi-step work with `todo_write`. -``` -> fix the failing test in /path/to/project -[main turn 1] (reasoning…) - [tool call] bash({"command": "node --test", "workdir": "/path/to/project"}) - [tool result] … [exit code: 1] - … -``` +The TUI renders resumed Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and the latest todo list. Enter submits or steers while the agent is running; Ctrl+O expands cards, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `ask_user_question` opens a keyboard-driven overlay rather than taking over the editor. ### Resuming a prior session @@ -29,7 +23,7 @@ Each run starts a fresh session by default (its event log lands under `./.sessio RESUME_SESSION_ID= pnpm run demo:repl ``` -The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`); unset, the agent starts a new session. A missing/unreadable id is non-fatal — it logs a warning and starts no `main` agent. +The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`); unset, the agent starts a new session. A missing or unreadable id starts no `main` agent, so unset it or choose an existing session id. ## Code Mode @@ -48,17 +42,17 @@ and watch the transcript: one `run_code` call, a program looping over tools, and ## What each leaf entry demonstrates -This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads one app package, and adds product tools that are intentionally outside the shared spine. The spine (sessions, system-prompt, tools, agents, invariants, `agent-loop`) and the front-door cluster (console logger, JSONL persistence, readline UI, the pre-created `main` agent) live inside the [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo) app and the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle it loads; the leaf wires the backends and model-facing optional tools: +This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads one app package, and adds product tools that are intentionally outside the shared spine. The spine (sessions, system-prompt, tools, agents, invariants, `agent-loop`) and the front-door cluster (JSONL persistence, TTY-selected `dsh-tui`/`dsh-stdio` channels, the pre-created `main` agent) live inside the [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo) app and the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle it loads; the leaf wires the backends and model-facing optional tools: | Entry | Demonstrates | |---|---| | `hmr` (`@cordisjs/plugin-hmr`) | the dev/demo edit-reload loop — a **leaf** entry (not baked into the app) because it is Loader-only and needs `node --expose-internals`, which `demo:repl` passes | | `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin | | `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash` schema (`tool-bash`) and generic `task_*` controls (`tool-tasks`) come from `dsh-agent-spine-demo`, so only the executor is a leaf choice | -| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + console logger + JSONL persistence + readline UI + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), and `resumeSessionId` — so persistence and the agent are configured here, not wired as separate leaf plugins | +| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + JSONL persistence + TTY-selected `dsh-tui`/`dsh-stdio` channels + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), `resumeSessionId`, and optional `ui` presentation settings | | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix | | `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) | -| `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a checklist in stdio | +| `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a persistent TUI plan or readline checklist | | `fs-local`, `fs-policy`, `tool-fs` | the filesystem stack: the local `ctx.fs` provider, the read-before-write/edit policy gate (on the `fs/*` event gate), and the model-facing `read`/`write`/`edit` tools. Relative paths resolve against the session workspace | ## End-to-end tests (`pnpm run test:e2e`, key-gated) diff --git a/examples/coding-agent/composition.md b/examples/coding-agent/composition.md index 90ff8222b9..35835953ac 100644 --- a/examples/coding-agent/composition.md +++ b/examples/coding-agent/composition.md @@ -3,7 +3,7 @@ # Coding Agent App Composition -The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package. +The coding-agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package. ```mermaid flowchart LR @@ -18,7 +18,7 @@ flowchart LR cfg --> plugin_coding_stdio_agent plugin_coding_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] plugin_coding_stdio_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] - plugin_coding_stdio_agent --> frontdoor_stdio["readline UI
console logger
pre-created main agent"] + plugin_coding_stdio_agent --> frontdoor_stdio["dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent"] bundle_agent_core --> spine_llm["ctx.llm"] bundle_agent_core --> spine_sessions["ctx.sessions"] bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index 61e389ebc5..568988bd59 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -1,6 +1,6 @@ -# REPL agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo` -# supplies the agent spine, generic task controls, logging, JSONL persistence, -# readline UI, and `main` agent. +# Coding agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo` +# supplies the agent spine, generic task controls, JSONL persistence, TTY-selected +# `dsh-tui`/`dsh-stdio` terminal front doors, and `main` agent. # HMR remains a leaf because it requires Loader internals; `demo:repl` passes # `--expose-internals`. The app bin loads the gitignored root `.env`; this file # reads `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` through `!!js`. @@ -38,6 +38,11 @@ resumeSessionId: !!js process.env.RESUME_SESSION_ID persistenceRoot: './.sessions' welcome: 'agent REPL ready. Give it a coding task.' + ui: + mode: auto + tui: + showReasoning: true + maxToolOutputLines: 12 # Keep the persona to identity and behavior; tool plugins own tool guidance. # The loop resolves {{model}} from this agent's configuration. persona: | diff --git a/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts b/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts new file mode 100644 index 0000000000..a1057ba02f --- /dev/null +++ b/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts @@ -0,0 +1,101 @@ +import { spawn } from 'node:child_process' +import { mkdtemp, rm } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { describe, expect, it } from 'vitest' +import { LOADER_SMOKE_TEST_TIMEOUT_MS } from '@deepseek-ai/dsh-loader-smoke' + +const binScript = fileURLToPath(new URL('../../../packages/examples/stdio-demo/src/bin.ts', import.meta.url)) +const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) +const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) +const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) + +const PTY_DRIVER = String.raw` +import errno, os, pty, select, signal, sys, time +node, tsx_loader, bin_script, config_path, tsconfig_path, cwd = sys.argv[1:] +env = os.environ.copy() +env.update({ + "DEEPSEEK_API_KEY": "keyless-tui-no-call", + "DSH_HOME": os.path.join(cwd, ".dsh"), + "DSH_AGENTS_HOME": os.path.join(cwd, ".agents"), + "TSX_TSCONFIG_PATH": tsconfig_path, +}) +pid, fd = pty.fork() +if pid == 0: + os.chdir(cwd) + os.execvpe(node, [node, "--expose-internals", "--import", tsx_loader, bin_script, config_path], env) + +output = bytearray() +sent_exit = False +deadline = time.monotonic() + 25 +status = None +while time.monotonic() < deadline: + ready, _, _ = select.select([fd], [], [], 0.05) + if ready: + try: + chunk = os.read(fd, 65536) + except OSError as error: + if error.errno != errno.EIO: + raise + chunk = b"" + if chunk: + output.extend(chunk) + if not sent_exit and b"agent REPL ready." in output: + os.write(fd, b"/exit\r") + sent_exit = True + waited, candidate = os.waitpid(pid, os.WNOHANG) + if waited == pid: + status = candidate + break + +if status is None: + os.kill(pid, signal.SIGKILL) + _, status = os.waitpid(pid, 0) +sys.stdout.buffer.write(output) +if not sent_exit: + sys.stderr.write("TUI did not render its welcome marker before timeout\n") + sys.exit(124) +if not os.WIFEXITED(status) or os.WEXITSTATUS(status) != 0: + sys.stderr.write("TUI child did not exit cleanly\n") + sys.exit(125) +` + +async function runTuiLoaderSmoke(): Promise { + const cwd = await mkdtemp(join(tmpdir(), 'coding-tui-smoke-')) + try { + return await new Promise((resolve, reject) => { + const child = spawn('python3', [ + '-c', + PTY_DRIVER, + process.execPath, + tsxLoader, + binScript, + configPath, + tsconfigPath, + cwd, + ], { stdio: ['ignore', 'pipe', 'pipe'] }) + let stdout = '' + let stderr = '' + child.stdout.setEncoding('utf8') + child.stdout.on('data', (chunk: string) => { stdout += chunk }) + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => { stderr += chunk }) + child.once('error', reject) + child.once('exit', (code) => { + if (code === 0) resolve(stdout) + else reject(new Error(`TUI PTY smoke exited ${String(code)}. stdout:\n${stdout}\nstderr:\n${stderr}`)) + }) + }) + } finally { + await rm(cwd, { recursive: true, force: true }) + } +} + +describe('coding-agent TUI keyless smoke (real Loader tree in a PTY)', () => { + it('boots pi-tui, renders the configured banner, accepts /exit, and restores the terminal', async () => { + const output = await runTuiLoaderSmoke() + expect(output).toContain('DEEPSEEK') + expect(output).toContain('agent REPL ready.') + }, LOADER_SMOKE_TEST_TIMEOUT_MS) +}) diff --git a/examples/cordis-agent/composition.md b/examples/cordis-agent/composition.md index 6a08c379fc..499379482f 100644 --- a/examples/cordis-agent/composition.md +++ b/examples/cordis-agent/composition.md @@ -24,7 +24,7 @@ flowchart LR cfg --> plugin_cordis_stdio_agent plugin_cordis_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] plugin_cordis_stdio_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] - plugin_cordis_stdio_agent --> frontdoor_stdio["readline UI
console logger
pre-created main agent"] + plugin_cordis_stdio_agent --> frontdoor_stdio["dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent"] bundle_agent_core --> spine_llm["ctx.llm"] bundle_agent_core --> spine_sessions["ctx.sessions"] bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] diff --git a/examples/echo-agent/README.md b/examples/echo-agent/README.md index d6156130db..183268f5da 100644 --- a/examples/echo-agent/README.md +++ b/examples/echo-agent/README.md @@ -4,7 +4,7 @@ Runnable demo: stdin chat with a scripted mock model and an echo tool. The all-m ## What it shows -This example is just a leaf `cordis.yml`: it loads the [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo) app (which bundles the whole [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) spine, the console logger, JSONL persistence, the readline UI, and a pre-created `main` agent), and swaps in two example-local backends plus `hmr`: +This example is just a leaf `cordis.yml`: it loads the [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo) app (which bundles the whole [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) spine, JSONL persistence, the TTY-selected `dsh-tui`/`dsh-stdio` front doors, and a pre-created `main` agent), and swaps in two example-local backends plus `hmr`: - `mock-llm.ts` — a mock `LlmAdapter` that streams scripted responses and calls the `echo` tool when the user types "echo ". Registered with `ctx.llm.registerAdapter(['mock-echo'], …)`. - `echo-tool.ts` — a tool registered via `ctx.tools.register(defineTool(…))` with typed `execute` args; echoes text back uppercased. diff --git a/examples/echo-agent/composition.md b/examples/echo-agent/composition.md index 5160bd20b7..bdc4d7e21d 100644 --- a/examples/echo-agent/composition.md +++ b/examples/echo-agent/composition.md @@ -20,7 +20,7 @@ flowchart LR cfg --> plugin_echo_stdio_agent plugin_echo_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] plugin_echo_stdio_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] - plugin_echo_stdio_agent --> frontdoor_stdio["readline UI
console logger
pre-created main agent"] + plugin_echo_stdio_agent --> frontdoor_stdio["dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent"] bundle_agent_core --> spine_llm["ctx.llm"] bundle_agent_core --> spine_sessions["ctx.sessions"] bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] diff --git a/examples/echo-agent/cordis.yml b/examples/echo-agent/cordis.yml index fbf998e770..516c53522e 100644 --- a/examples/echo-agent/cordis.yml +++ b/examples/echo-agent/cordis.yml @@ -22,7 +22,7 @@ - id: bash name: '@deepseek-ai/dsh-bash-local' -# The app pre-creates `main` on the mock model and supplies logging, persistence, and readline UI. +# The app pre-creates `main` on the mock model and supplies persistence plus TTY-selected `dsh-tui`/`dsh-stdio` front doors. - id: stdio-agent name: '@deepseek-ai/dsh-stdio-demo' config: diff --git a/knip.json b/knip.json index b978da3a76..502ded1657 100644 --- a/knip.json +++ b/knip.json @@ -1,7 +1,7 @@ { "$schema": "https://unpkg.com/knip@5/schema.json", "exclude": ["duplicates"], - "ignoreBinaries": ["bwrap", "sandbox-exec"], + "ignoreBinaries": ["bwrap", "python3", "sandbox-exec"], "ignoreWorkspaces": ["vendor/*", "python/sdk-runtime"], "workspaces": { ".": { diff --git a/packages/examples/README.md b/packages/examples/README.md index 5ee0206d0f..558bcb205c 100644 --- a/packages/examples/README.md +++ b/packages/examples/README.md @@ -5,11 +5,11 @@ Pre-composed plugin bundles a thin leaf `cordis.yml` loads instead of assembling | Package | npm name | Role | |---|---|---| | `agent-spine-demo/` | `@deepseek-ai/dsh-agent-spine-demo` | The executor-less/UI-less agent spine as one bundle plugin (`timer` + `llm` + sessions + system-prompt + tools + skills + agents + invariants + `tool-bash` + `tool-skill` + `agent-loop`) | -| `stdio-demo/` | `@deepseek-ai/dsh-stdio-demo` | Terminal stdio chat app: the spine + console logger + readline UI + a pre-created `main` agent, with a boot `bin` | +| `stdio-demo/` | `@deepseek-ai/dsh-stdio-demo` | Terminal chat app: the spine + JSONL persistence + TTY-selected `dsh-tui`/`dsh-stdio` front door + a pre-created `main` agent, with a boot `bin` | | `acp-demo/` | `@deepseek-ai/dsh-acp-demo` | ACP server app: the spine + JSONL persistence + the [`acp`](../ui/acp/README.md) bridge (no stdout logger), with a boot `bin` | | `jsonrpc-demo/` | `@deepseek-ai/dsh-jsonrpc-demo` | Bin-only runtime that boots an external `cordis.yml` for the stdio JSON-RPC SDK client | -`agent-spine-demo` is the shared bundle; `stdio-demo` and `acp-demo` compose it with opposite front-door clusters (console logger + readline UI vs the stdout-owning ACP bridge) and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches. +`agent-spine-demo` is the shared bundle; `stdio-demo` and `acp-demo` compose it with terminal and ACP front-door clusters and own their boot bins. `jsonrpc-demo` mounts no composition of its own — it boots whatever tree the deployment's `cordis.yml` names, and is what the Python SDK runtime launches. These are **not** product API. The spine pieces they bundle live in [`core/`](../core/README.md), the bridges/channels/boot-glue in [`ui/`](../ui/README.md), and the swappable backends (LLM adapter, bash executor) in their capability groups; a demo bundle just picks one concrete composition of them. Swap or fork one freely. diff --git a/packages/examples/agent-spine-demo/README.md b/packages/examples/agent-spine-demo/README.md index eb56f9515c..a1f98d8167 100644 --- a/packages/examples/agent-spine-demo/README.md +++ b/packages/examples/agent-spine-demo/README.md @@ -33,7 +33,7 @@ The spine is everything COMMON to every front door. The swappable and front-door - **the LLM adapter** — the bundle ships the abstract `llm` service; the leaf registers a concrete adapter on `ctx.llm` (`llm-deepseek`, `llm-pi-ai`, `llm-replay`). - **the bash executor** — the bundle ships `tool-bash` (the consumer schema); the leaf provides `ctx.bash` (`bash-local` or a sandboxed impl). - **non-local skill providers** — the bundle ships the skill registry, the local filesystem provider, and the `skill` tool; deployments can add other providers such as embedded or remote catalogs as siblings. -- **presentation + per-app infra** — the stdio UI / ACP bridge, a console logger, `hmr`. These form the coupled "front-door cluster" that the app packages ([`dsh-stdio-demo`](../../examples/stdio-demo/README.md), [`dsh-acp-demo`](../../examples/acp-demo/README.md)) bake in. `timer` is in the spine (common to both, stdout-silent); a console logger is NOT (it writes to stdout, which the ACP bridge reserves for JSON-RPC). +- **presentation + per-app infra** — the terminal (`dsh-tui` / `dsh-stdio`) or ACP front door and `hmr`. These form the coupled front-door cluster that the app packages ([`dsh-stdio-demo`](../../examples/stdio-demo/README.md), [`dsh-acp-demo`](../../examples/acp-demo/README.md)) bake in. `timer` is in the spine because it is common and stdout-silent; front doors own stdout and remain outside. This is the [interface/implementation/consumer seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md) raised to the composition level: the bundle owns the shared spine, the leaf owns the backends, the app package owns the front door. diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index 98f639491e..96704998c4 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -1,8 +1,8 @@ # @deepseek-ai/dsh-stdio-demo -The **terminal stdio chat app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../../examples/agent-spine-demo/README.md)) with the front-door cluster a terminal chat needs, and a `bin` that boots a leaf `cordis.yml`. +The **terminal chat app**: a Cordis app plugin that composes the default agent spine ([`@deepseek-ai/dsh-agent-spine-demo`](../../examples/agent-spine-demo/README.md)) with JSONL persistence, human interaction, a pre-created `main` agent, and a TTY-selected pi-tui/readline terminal front door. Its `bin` boots a leaf `cordis.yml`. -It is the readline counterpart to [`@deepseek-ai/dsh-acp-demo`](../acp-demo/README.md): both consume the same spine, but each bakes in the OPPOSITE front-door cluster. +It is the terminal counterpart to [`@deepseek-ai/dsh-acp-demo`](../acp-demo/README.md): both consume the same spine, while ACP reserves stdout for JSON-RPC and creates sessions from the client. ## What it bakes in @@ -10,14 +10,15 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | Plugin | Why it is here | |---|---| -| `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) | | `@deepseek-ai/dsh-agent-spine-demo` | the spine, pre-creating a `main` agent from this app's `model` with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | -| `@deepseek-ai/dsh-stdio` | the readline UI, bound to the `main` agent | +| `@cordisjs/plugin-logger-console` | readline diagnostics for non-TTY operation; omitted from the fullscreen TUI path | +| `@deepseek-ai/dsh-stdio` | the line-oriented terminal channel, bound to `main` for pipes and automation | +| `@deepseek-ai/dsh-tui` | the interactive pi-tui channel, bound to `main` for TTY pairs | -`@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, NOT baked in here: it is a Loader-only, subprocess-only dev plugin — its constructor throws without `node --expose-internals` + a live `loader`, and the in-process test tier cannot even import it (so a package whose `apply` statically pulled it in could never carry the per-file coverage gate). Unlike the console logger, a stray `hmr` is not a stdout-purity footgun, so leaving it at the leaf costs no safety. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. +`@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, not baked in here: it is a Loader-only, subprocess-only dev plugin whose constructor needs `node --expose-internals` plus a live `loader`. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapter (`llm-deepseek` for the real model, or the mock `mock-llm` for a demo) and a bash executor (`bash-local`) — `hmr`, plus this app's [`Config`](#config). The whole plugin tree a run loads is therefore: this app's cluster, the spine inside `agent-core`, `hmr`, and the two leaf backends. @@ -33,7 +34,8 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | `toolBash` | owner defaults | model-facing bash config routed through `dsh-agent-spine-demo`, including bash's producer-local `enableRunInBackground` | | `toolTasks` | owner defaults | generic `task_output` wait bounds routed through `dsh-agent-spine-demo` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | -| `welcome` | `ready.` | the stdin-chat banner | +| `welcome` | `ready.` | terminal banner / TUI subtitle | +| `ui` | owner defaults | app mode selection and nested `dsh-tui` presentation config | | `resumeSessionId` | — | resume a persisted session id instead of starting fresh (sourced from an env var in the leaf) | Fresh stdio sessions use the process launch directory as `session.header.cwd`, so project-scoped features such as skill discovery and default bash workdir follow the directory where `dsh-stdio-demo` was started. Resumed sessions keep the cwd stored in the persisted session header. @@ -45,7 +47,7 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s ## Example leaf `cordis.yml` ```yaml -# A REPL agent demo: hmr + the DeepSeek adapter + local bash, then this app. +# A coding-agent demo: hmr + the DeepSeek adapter + local bash, then this app. - id: hmr name: '@cordisjs/plugin-hmr' config: @@ -64,6 +66,8 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s config: model: deepseek-v4-flash persona: 'You are a coding assistant powered by the {{model}} model.' + ui: + mode: auto ``` Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo — "swap the backend, keep the app". @@ -72,9 +76,9 @@ Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo — ### Composed terminal agent request -**What the model sees**: Through `dsh-agent-spine-demo`, the `main` agent receives the harness identity, configured persona, skill catalog, and visible tools; this app also composes the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user). Each readline submission becomes a user message. +**What the model sees**: Through `dsh-agent-spine-demo`, the `main` agent receives the harness identity, configured persona, skill catalog, and visible tools; this app also composes the generated [`ask_user_question` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-ask-user). Each terminal submission becomes a user message; submissions made while the agent runs steer the active turn. -**Token effect**: Child prompt and schema costs repeat per request; user input and tool history grow until compaction. The welcome banner, logger output, and rendered transcript are terminal-only and add zero model tokens. +**Token effect**: Child prompt and schema costs repeat per request; user input and tool history grow until compaction. The TUI/readline banners and rendered transcripts are terminal-only and add zero model tokens. ### Human-answer result @@ -84,6 +88,6 @@ Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo — ## Known Limitations and Deferred Work -- **One pre-created `main` agent drives the readline UI** — there is no multi-session or concurrent-agent surface in this app; a run is one conversation. +- **One pre-created `main` agent drives the terminal UI** — there is no multi-session or concurrent-agent surface in this app; a run is one conversation. - **The front-door cluster is fixed in code** — the JSONL persistence backend and the ask-user tooling are baked; a different composition is a leaf-level sibling entry or another app package. - **The question tool is not an approval answerer** — this app mounts `user-interaction` and `ask_user_question`, but not `ctx.approval`; a `tools/pre-execute` `ask` therefore fails closed unless the leaf composes an approval service and terminal answerer. diff --git a/packages/examples/stdio-demo/package.json b/packages/examples/stdio-demo/package.json index 3fe11f47a2..d20e210b8f 100644 --- a/packages/examples/stdio-demo/package.json +++ b/packages/examples/stdio-demo/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-stdio-demo", - "description": "Terminal stdio chat app: the agent-spine-demo bundle + console logger + readline UI + a pre-created main agent, with a bin to boot a leaf cordis.yml", + "description": "Terminal chat app: agent spine + JSONL persistence + TTY pi-tui/readline front-door selection + pre-created main agent", "version": "0.0.1", "private": true, "type": "module", @@ -32,14 +32,15 @@ "peerDependencies": { "@cordisjs/plugin-include": "^1.0.4", "@cordisjs/plugin-loader": "^1.0.0-rc.5", - "@deepseek-ai/dsh-app-boot": "^0.0.1", "@cordisjs/plugin-logger-console": "^1.0.0", + "@deepseek-ai/dsh-app-boot": "^0.0.1", "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-agent-spine-demo": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-session-persistence-jsonl": "^0.0.1", "@deepseek-ai/dsh-stdio": "^0.0.1", + "@deepseek-ai/dsh-tui": "^0.0.1", "@deepseek-ai/dsh-tool-ask-user": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "@deepseek-ai/dsh-user-interaction": "^0.0.1", @@ -49,8 +50,8 @@ "devDependencies": { "@cordisjs/plugin-include": "workspace:^", "@cordisjs/plugin-loader": "workspace:^", - "@deepseek-ai/dsh-app-boot": "workspace:^", "@cordisjs/plugin-logger-console": "workspace:^", + "@deepseek-ai/dsh-app-boot": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", @@ -58,6 +59,7 @@ "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-stdio": "workspace:^", + "@deepseek-ai/dsh-tui": "workspace:^", "@deepseek-ai/dsh-tool-ask-user": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "@deepseek-ai/dsh-user-interaction": "workspace:^", diff --git a/packages/examples/stdio-demo/src/bin.ts b/packages/examples/stdio-demo/src/bin.ts index 462e821e50..278bb5faca 100644 --- a/packages/examples/stdio-demo/src/bin.ts +++ b/packages/examples/stdio-demo/src/bin.ts @@ -2,7 +2,7 @@ /** * Boot a stdio app from a leaf `cordis.yml`; usage is `dsh-stdio-demo [config]`, defaulting to the * cwd file. Shared `.env` loading, fail-loud Loader guards, and settled-tree boot live in - * dsh-app-boot. The echo and REPL demos invoke this bin with their own leaf configs. + * dsh-app-boot. The echo and coding-agent demos invoke this bin with their own leaf configs. * @module @deepseek-ai/dsh-stdio-demo/bin */ diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index 73f163d7f4..055e266498 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -1,8 +1,9 @@ /** * The stdio chat app: the default agent spine ({@link @deepseek-ai/dsh-agent-spine-demo}) plus the - * coupled front-door cluster a terminal chat needs — a console logger, the independently - * packaged readline UI, JSONL session persistence, the user-interaction seam with its - * `ask_user_question` tool, and a pre-created `main` agent the UI drives. + * coupled front-door cluster a terminal chat needs — the independently packaged + * pi-tui and readline front doors, JSONL session persistence, the user-interaction + * seam with its `ask_user_question` tool, and a pre-created `main` agent the UI + * drives. Interactive terminals use `dsh-tui`; pipes use `dsh-stdio` plus logging. * Swappable adapters, executors, optional tools, and HMR stay in the leaf. This * Loader plugin intentionally exposes named exports only; a default export * would hide its `Config` schema (see docs/postmortem/0001). @@ -20,9 +21,45 @@ import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' import * as toolAskUser from '@deepseek-ai/dsh-tool-ask-user' import * as uiStdio from '@deepseek-ai/dsh-stdio' +import * as uiTui from '@deepseek-ai/dsh-tui' export const name = 'stdio-demo' +/** Terminal front door selected by the app bundle. */ +export type TerminalMode = 'auto' | 'readline' | 'tui' + +/** App-level terminal selection with nested TUI presentation settings. */ +export interface UiConfig { + /** Select a concrete front door or infer it from the process streams. */ + mode?: TerminalMode + /** Settings forwarded only when the pi-tui front door is selected. */ + tui?: uiTui.TuiConfig +} + +const terminalModeSchema = z.union(['auto', 'readline', 'tui'] as const).default('auto') + +/** Schemastery schema for the app-level terminal selection. */ +export const UiConfigSchema: z = z.object({ + mode: terminalModeSchema, + tui: uiTui.TuiConfigSchema, +}) + +/** + * Resolve the app's terminal front door. + * + * @param config - App-level terminal selection. + * @param isTTY - Whether both process streams are interactive TTYs. + * @returns The concrete UI package to mount. + */ +export function resolveTerminalMode(config: UiConfig | undefined, isTTY: boolean): Exclude { + const mode = config?.mode ?? 'auto' + if (mode === 'auto') return isTTY ? 'tui' : 'readline' + if (mode === 'tui' && !isTTY) { + throw new Error('stdio-demo: TUI mode requires both stdin and stdout to be TTYs; use mode "readline" for pipes') + } + return mode +} + /** * App config: the swappable per-demo values, each routed to where the app wires * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through @@ -31,7 +68,7 @@ export const name = 'stdio-demo' * is the explicit model-facing tool order (forwarded to the system-prompt plugin); * fresh sessions use `process.cwd()` as their workspace cwd; resumed sessions * keep their persisted cwd. `persistenceRoot` is the JSONL backend's directory; - * `welcome` is the UI banner. + * `welcome` is the UI banner and `ui` configures terminal mode/presentation. */ export interface Config { /** Model name for the `main` agent (must have a registered adapter). */ @@ -44,8 +81,10 @@ export interface Config { tools?: ToolsConfig /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string - /** stdin-chat banner printed once on start. Defaults to `'ready.'`. */ + /** Terminal banner printed once on start. Defaults to `'ready.'`. */ welcome?: string + /** Terminal front-door selection and pi-tui presentation settings. */ + ui?: UiConfig /** Skill registry, local-provider, and model-facing consumer config forwarded to agent-spine-demo. */ skills?: agentCore.SkillConfig /** Model-facing bash tool config forwarded through agent-core. */ @@ -72,6 +111,7 @@ export const Config: z = z.object({ // apply() fallbacks through named constants while retaining both boundaries. persistenceRoot: z.string().default('./.sessions'), welcome: z.string().default('ready.'), + ui: UiConfigSchema, skills: agentCore.SkillConfigSchema, toolBash: agentCore.ToolBashConfigSchema, toolTasks: agentCore.ToolTasksConfigSchema, @@ -79,14 +119,18 @@ export const Config: z = z.object({ }) /** - * Compose the spine with the stdio front door. The console logger comes first - * (infra), then the agent-spine-demo bundle pre-creating the `main` agent from this - * app's `model`/`resumeSessionId` with the deployment `persona`, then the JSONL - * backend, then the readline UI bound to `main`. The `hmr` dev-reload plugin is - * a leaf concern (see the module doc), so it is not mounted here. + * Compose the spine with one terminal front door. Interactive TTY pairs mount + * `dsh-tui` without a console exporter; pipes mount the readline `dsh-stdio` + * channel with the console logger. The `hmr` dev-reload plugin remains a leaf + * concern. + * + * @param ctx - Context receiving the app's child plugins. + * @param config - App configuration routed to the spine and front door. + * @param isTTY - Whether both terminal streams are interactive TTYs. */ -export function apply(ctx: Context, config: Config): void { - ctx.plugin(ConsoleExporter) +export function composeTerminalApp(ctx: Context, config: Config, isTTY: boolean): void { + const mode = resolveTerminalMode(config.ui, isTTY) + if (mode === 'readline') ctx.plugin(ConsoleExporter) ctx.plugin(agentCore, { ...config.persona !== undefined ? { persona: config.persona } : {}, ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, @@ -104,5 +148,21 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) ctx.plugin(UserInteractionService) ctx.plugin(toolAskUser) - ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' }) + if (mode === 'tui') { + ctx.plugin(uiTui, { + ...config.ui?.tui, + welcome: config.welcome ?? 'ready.', + agent: 'main', + }) + } else { + ctx.plugin(uiStdio, { welcome: config.welcome ?? 'ready.', agent: 'main' }) + } } + +/** Compose the configured terminal front door with the agent app. */ +/* v8 ignore start -- production stream capability wiring; composeTerminalApp is unit-covered, + and the coding-agent PTY smoke covers the interactive process path */ +export function apply(ctx: Context, config: Config): void { + composeTerminalApp(ctx, config, process.stdin.isTTY && process.stdout.isTTY) +} +/* v8 ignore stop */ diff --git a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts index b5fb0e0207..472afaa0b7 100644 --- a/packages/examples/stdio-demo/tests/stdio-agent.spec.ts +++ b/packages/examples/stdio-demo/tests/stdio-agent.spec.ts @@ -10,8 +10,8 @@ import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import * as stdioAgent from '../src/index.ts' /** - * Unit coverage for app composition and config forwarding: console logger, pre-created main agent, - * agent-core spine, JSONL backend, and readline UI. HMR is a Loader-only leaf concern covered by the + * Unit coverage for app composition and config forwarding: pre-created main agent, agent-core spine, + * JSONL backend, and adaptive terminal UI. HMR is a Loader-only leaf concern covered by the * keyless echo smoke; this tier pins the export shape because an inject-less app could otherwise * survive namespace collapse while silently losing its schema. */ @@ -65,6 +65,47 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { } describe('dsh-stdio-demo app', () => { + it('selects readline for pipes and dsh-tui for interactive terminal pairs', () => { + expect(stdioAgent.resolveTerminalMode(undefined, false)).toBe('readline') + expect(stdioAgent.resolveTerminalMode(undefined, true)).toBe('tui') + expect(stdioAgent.resolveTerminalMode({ mode: 'readline' }, true)).toBe('readline') + expect(stdioAgent.resolveTerminalMode({ mode: 'tui' }, true)).toBe('tui') + expect(() => stdioAgent.resolveTerminalMode({ mode: 'tui' }, false)).toThrow('requires both stdin and stdout') + }) + + it('composes only the selected terminal package and keeps TUI settings in dsh-tui', () => { + const calls: Array<{ name: string; config: unknown }> = [] + const ctx = { + plugin(plugin: { name?: string }, config?: unknown) { + calls.push({ name: plugin.name ?? '', config }) + }, + } as unknown as Context + + stdioAgent.composeTerminalApp(ctx, { + model: 'mock', + welcome: 'TUI ready', + ui: { mode: 'tui', tui: { color: false, maxToolOutputLines: 3 } }, + }, true) + expect(calls.map(call => call.name)).toContain('ui-tui') + expect(calls.map(call => call.name)).not.toContain('ui-stdio') + expect(calls.map(call => call.name)).not.toContain('ConsoleExporter') + expect(calls.find(call => call.name === 'ui-tui')?.config).toMatchObject({ + agent: 'main', welcome: 'TUI ready', color: false, maxToolOutputLines: 3, + }) + + calls.length = 0 + stdioAgent.composeTerminalApp(ctx, { model: 'mock', ui: { mode: 'tui' } }, true) + expect(calls.find(call => call.name === 'ui-tui')?.config).toMatchObject({ + agent: 'main', welcome: 'ready.', + }) + + calls.length = 0 + stdioAgent.composeTerminalApp(ctx, { model: 'mock', ui: { mode: 'readline' } }, false) + expect(calls.map(call => call.name)).toContain('ui-stdio') + expect(calls.map(call => call.name)).toContain('ConsoleExporter') + expect(calls.map(call => call.name)).not.toContain('ui-tui') + }) + it('composes the spine + front-door cluster and pre-creates the main agent', async () => { const ctx = await mount({ model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-demo-spec', skills: await isolatedSkillsConfig() }) // The spine services (brought up by the agent-core bundle) are all present. diff --git a/packages/examples/stdio-demo/tsconfig.json b/packages/examples/stdio-demo/tsconfig.json index bb360810a5..3145047c03 100644 --- a/packages/examples/stdio-demo/tsconfig.json +++ b/packages/examples/stdio-demo/tsconfig.json @@ -38,6 +38,9 @@ { "path": "../../ui/stdio" }, + { + "path": "../../ui/tui" + }, { "path": "../../ui/tool-ask-user" }, diff --git a/packages/todo/README.md b/packages/todo/README.md index b6a9ce2fc5..bfe5ec7503 100644 --- a/packages/todo/README.md +++ b/packages/todo/README.md @@ -6,4 +6,4 @@ The model-facing todo tool. A single **product** package — there is no interfa |---|---|---| | `tool-todo/` | Model-facing `todo_write` tool; writes the whole list to the session log (`todo/write`) | (registers on `ctx.tools`) | -The list lives on the event-sourced session log (`SessionEventMap['todo/write']`, owned by [`dsh-session`](../core/session)); this package is the thin consumer that appends the snapshot. UIs render off `session/event`: the [stdio app's readline UI](../examples/stdio-demo) prints the list, the [ACP bridge](../ui/acp) maps it to a `plan` sessionUpdate. +The list lives on the event-sourced session log (`SessionEventMap['todo/write']`, owned by [`dsh-session`](../core/session)); this package is the thin consumer that appends the snapshot. UIs render off `session/event`: the [terminal app](../examples/stdio-demo) shows a persistent TUI plan or readline checklist, while the [ACP bridge](../ui/acp) maps it to a `plan` sessionUpdate. diff --git a/packages/todo/tool-todo/README.md b/packages/todo/tool-todo/README.md index 0b07539f3d..f6097abe96 100644 --- a/packages/todo/tool-todo/README.md +++ b/packages/todo/tool-todo/README.md @@ -18,7 +18,7 @@ Beyond the schema's type/required/enum checks, `execute` rejects an empty or dup ## Rendering -The tool writes only the session event; it does not render. UIs subscribe to `session/event` and render the `todo/write` data themselves: the [stdio app's readline UI](../../examples/stdio-demo) prints a glyphed checklist, and the [ACP bridge](../../ui/acp) maps the list to a `plan` sessionUpdate (synthesizing the `priority` ACP requires). +The tool writes only the session event; it does not render. UIs subscribe to `session/event` and render the `todo/write` data themselves: the [terminal app](../../examples/stdio-demo) shows a persistent TUI plan or readline checklist, and the [ACP bridge](../../ui/acp) maps the list to a `plan` sessionUpdate (synthesizing the `priority` ACP requires). ## Export shape diff --git a/packages/ui/README.md b/packages/ui/README.md index 699a11bdb4..3dd26d80a8 100644 --- a/packages/ui/README.md +++ b/packages/ui/README.md @@ -9,12 +9,13 @@ Integrations that expose the agent to an external editor or client. These are ** | `permission/` | User-facing permission presets (`workspace-write`/`danger-full-access`): one product-level select bundling the sandbox-mode and approval-policy knobs, written through to their session events | `ctx.permission` | | `user-interaction/` | Abstract human question/answer seam used by UI-backed confirmation tools | `ctx.userInteraction` | | `tool-ask-user/` | Model-facing `ask_user_question` tool over `ctx.userInteraction` | (registers on `ctx.tools`) | -| `stdio/` | Terminal readline channel over `ctx.agents`, `session/event`, and `ctx.userInteraction`; agent lifecycle stays with app/developer code | (drives `ctx.agents`) | +| `stdio/` | Line-oriented terminal channel for pipes and automation; drives `ctx.agents`, renders `session/event`, and answers `ctx.userInteraction` | (drives `ctx.agents`) | +| `tui/` | Interactive pi-tui terminal channel for TTY sessions; renders `session/event`, tool presentation intents, and answers `ctx.userInteraction` | (drives `ctx.agents`) | | `jsonrpc/` | Stdio JSON-RPC server for out-of-process SDK clients | (drives `ctx.agents`) | | `app-boot/` | Shared boot glue for the app bins: `.env` loading, fail-loud Loader guards, snapshot-aware config resolution, the settle-the-tree boot sequence | (library for the bins) | -A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The `jsonrpc` plugin is the SDK-client sibling of the `acp` bridge (a JSON-RPC server over `ctx.agents` for out-of-process SDK clients rather than editors). The [`stdio`](stdio/README.md) plugin is the unstructured readline analogue of the `acp` bridge; app bundles and SDK projects compose it explicitly with the services and tools their product profile selects. +A UI integration is a client-driver plugin, not a loop change and not a capability seam: it consumes the existing `agent/*` event taxonomy and the `dsh-agent` factory. The `jsonrpc` plugin is the SDK-client sibling of the `acp` bridge (a JSON-RPC server over `ctx.agents` for out-of-process SDK clients rather than editors). The [`stdio`](stdio/README.md) and [`tui`](tui/README.md) plugins are the two terminal front doors: one is line-oriented for pipes, the other is interactive for TTYs. App bundles and SDK projects compose the appropriate channel explicitly with the services and tools their product profile selects. `user-approval`, `user-interaction`, and `tool-ask-user` live here because asking a human is a UI-backed product affordance, not part of the providerless core spine. `user-approval` owns the one-shot `ctx.approval` decision mechanism and its policy tier; answerers remain with their UI channel owners. `user-interaction` remains provider-neutral (`ctx.userInteraction`), while `tool-ask-user` is its model-facing consumer and the app/bridge packages provide concrete providers. -The runnable app bundles that bake these bridges into boot bins — the stdio chat app, the ACP server app, and the JSON-RPC SDK-runtime bin — live in [`examples/`](../examples/README.md) (`stdio-demo`, `acp-demo`, `jsonrpc-demo`), each composed over the [`agent-spine-demo`](../examples/agent-spine-demo/README.md) bundle. `ui/` keeps the reusable bridge/channel plugins and the `app-boot` glue; each front door owns its stdout policy, and a leaf `cordis.yml` supplies backends and optional tools. +The runnable app bundles that bake these bridges into boot bins — the terminal chat app, the ACP server app, and the JSON-RPC SDK-runtime bin — live in [`examples/`](../examples/README.md) (`stdio-demo`, `acp-demo`, `jsonrpc-demo`), each composed over the [`agent-spine-demo`](../examples/agent-spine-demo/README.md) bundle. `ui/` keeps the reusable bridge/channel plugins and the `app-boot` glue; each front door owns its stdout policy, and a leaf `cordis.yml` supplies backends and optional tools. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 3650cf27d4..27346efcec 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -2,7 +2,7 @@ Agent Client Protocol bridge over JSON-RPC stdio. Editors can create or resume agents, stream their events, answer questions and approvals, and render tool calls. One connection supports multiple isolated sessions; Zed is the primary compatibility target. -It is a **client-driver / UI plugin**, the structured analogue of the readline `stdio-chat` plugin — NOT a loop change and NOT a [capability seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`. +It is a **client-driver / UI plugin**, the structured analogue of the terminal `dsh-tui`/`dsh-stdio` channels — NOT a loop change and NOT a [capability seam](../../../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md). It consumes the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, and `dsh-session-persistence`. ## Service / plugin diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md new file mode 100644 index 0000000000..1e678beac8 --- /dev/null +++ b/packages/ui/tui/README.md @@ -0,0 +1,56 @@ +# @deepseek-ai/dsh-tui + +The interactive terminal front door for DeepSeek Harness agents, built on [`@earendil-works/pi-tui`](https://www.npmjs.com/package/@earendil-works/pi-tui). It requires stdin and stdout TTYs; scripts and Loader pipes should compose [`@deepseek-ai/dsh-stdio`](../stdio/README.md) instead. + +This package owns interactive terminal presentation and input only. It injects `agents`, `tools`, and `userInteraction`, then drives an agent created or resumed by app or developer code. Agent lifecycle, persistence, and the model-facing [`ask_user_question`](../tool-ask-user/README.md) tool remain separate composition entries. + +The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions as keyboard-driven overlays. Surface replacement events rebuild the transcript so compacted history does not reappear. + +While the agent is running, editor submissions call `agent.steer()`; otherwise they call `agent.send()`. Ctrl+C or Escape cancels a running turn. Ctrl+O expands tool cards, Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle. `/help`, `/clear`, `/cancel`, `/reasoning`, `/tools`, `/redraw`, and `/exit` provide the same actions without key chords. + +## Config + +| Key | Default | Meaning | +|---|---|---| +| `welcome` | `ready.` | Header subtitle | +| `agent` | `main` | Agent id driven by the terminal | +| `showReasoning` | `true` | Render reasoning blocks | +| `maxToolOutputLines` | `12` | Collapsed tool-card output limit | +| `maxQuestionOptions` | `8` | Visible options in a question overlay | +| `questionDialogWidth` | `72` | Question-overlay width in columns | +| `questionDialogMaxHeight` | `20` | Question-overlay maximum rows | +| `showHardwareCursor` | `false` | Show the hardware cursor at pi-tui's IME marker | +| `color` | `true` | Apply the built-in ANSI palette | +| `title` | `DeepSeek Harness` | Terminal window title | + +```yaml +- id: terminal + name: '@deepseek-ai/dsh-tui' + config: + welcome: 'Coding agent ready.' + agent: main + showReasoning: true + maxToolOutputLines: 12 +``` + +Startup fails before mounting when either process stream is not a TTY. Disposal stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR. + +## Model Experience + +### Interactive prompt input + +**What the model sees**: Each non-empty editor submission becomes one text block, sent with `agent.send()` while the target agent is idle and `agent.steer()` while it is running. Slash commands and keybindings are TUI-only. + +**Token effect**: Submitted text is retained under the agent loop's normal session-history and compaction rules. Headers, cards, Markdown rendering, status lines, plans, and help text add no tokens. + +### Interactive user-question answers + +**What the model sees**: When a consumer calls `ctx.userInteraction.ask()`, this provider presents each question in order and returns selected option labels or `custom` text. Abort, cancellation, or UI disposal becomes `Error: ask_user_question was interrupted before the user answered` through `dsh-tool-ask-user`. + +**Token effect**: Waiting and terminal overlays add no tokens; the resolved answer or error is model-visible only through the calling tool or plugin's result. + +## Known Limitations and Deferred Work + +- **One configured agent owns the transcript and editor** — questions from other agents can still use the shared overlay provider, but session rendering and prompt input remain bound to `agent`. +- **Tool cards are text terminal presentations** — terminal, diff, and generic cards use tool-owned titles/content, but session content currently has no image block for inline image rendering. +- **Non-TTY operation is intentionally unsupported** — app bundles that need automation must select `dsh-stdio` before mounting this plugin rather than expecting an internal fallback. diff --git a/packages/ui/tui/package.json b/packages/ui/tui/package.json new file mode 100644 index 0000000000..e960f33e65 --- /dev/null +++ b/packages/ui/tui/package.json @@ -0,0 +1,45 @@ +{ + "name": "@deepseek-ai/dsh-tui", + "description": "Interactive pi-tui terminal front door for DeepSeek Harness agents", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "peerDependencies": { + "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-tools": "^0.0.1", + "@deepseek-ai/dsh-user-interaction": "^0.0.1", + "cordis": "^4.0.0-rc.6" + }, + "dependencies": { + "@earendil-works/pi-tui": "0.80.7", + "schemastery": "^3.18.0" + }, + "devDependencies": { + "@cordisjs/plugin-loader": "workspace:^", + "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-llm": "workspace:^", + "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-tools": "workspace:^", + "@deepseek-ai/dsh-user-interaction": "workspace:^", + "cordis": "^4.0.0-rc.6" + } +} diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts new file mode 100644 index 0000000000..14f45242d7 --- /dev/null +++ b/packages/ui/tui/src/index.ts @@ -0,0 +1,1284 @@ +/** + * Interactive pi-tui front door for DeepSeek Harness agents. It renders the + * durable session transcript, drives one configured agent, and provides + * keyboard-driven user-interaction dialogs without owning agent lifecycle. + * @module @deepseek-ai/dsh-tui + */ + +import { homedir } from 'node:os' +import { relative, resolve, sep } from 'node:path' +import { + Box, + CombinedAutocompleteProvider, + Container, + Editor, + Input, + Key, + Loader, + Markdown, + Spacer, + Text, + TUI, + ProcessTerminal, + matchesKey, + truncateToWidth, + visibleWidth, + wrapTextWithAnsi, + type Component, + type EditorTheme, + type Focusable, + type MarkdownTheme, + type OverlayHandle, + type SelectListTheme, + type Terminal, +} from '@earendil-works/pi-tui' +import type { Context } from 'cordis' +import z from 'schemastery' +import { AgentId, type Agent, type AgentStatus } from '@deepseek-ai/dsh-agent' +import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { Session, SessionEvent, TodoItem } from '@deepseek-ai/dsh-session' +import type { + FileDiff, + TerminalCallView, + ToolCallView, + ToolDefinition, + ToolResultView, +} from '@deepseek-ai/dsh-tools' +import { + UserInteractionError, + type AskUserQuestionAnswer, + type AskUserQuestionAnswerItem, + type AskUserQuestionItem, + type AskUserQuestionRequest, +} from '@deepseek-ai/dsh-user-interaction' + +export const name = 'ui-tui' +export const inject = ['agents', 'userInteraction', 'tools'] + +/** Presentation settings for the pi-tui terminal mode. */ +export interface TuiConfig { + /** Render model reasoning blocks. */ + showReasoning?: boolean + /** Maximum tool-output lines shown before the card is collapsed. */ + maxToolOutputLines?: number + /** Maximum options visible at once in a user-question dialog. */ + maxQuestionOptions?: number + /** User-question dialog width in terminal columns. */ + questionDialogWidth?: number + /** User-question dialog maximum height in terminal rows. */ + questionDialogMaxHeight?: number + /** Show the terminal's hardware cursor at the pi editor's IME marker. */ + showHardwareCursor?: boolean + /** Apply the built-in ANSI color palette. */ + color?: boolean + /** Terminal window title while the UI is mounted. */ + title?: string +} + +const showReasoningSchema = z.boolean().default(true) +const maxToolOutputLinesSchema = z.number().step(1).min(1).default(12) +const maxQuestionOptionsSchema = z.number().step(1).min(1).default(8) +const questionDialogWidthSchema = z.number().step(1).min(20).default(72) +const questionDialogMaxHeightSchema = z.number().step(1).min(6).default(20) +const showHardwareCursorSchema = z.boolean().default(false) +const colorSchema = z.boolean().default(true) +const titleSchema = z.string().default('DeepSeek Harness') + +/** Schemastery schema for presentation settings embedded by app bundles. */ +export const TuiConfigSchema: z = z.object({ + showReasoning: showReasoningSchema, + maxToolOutputLines: maxToolOutputLinesSchema, + maxQuestionOptions: maxQuestionOptionsSchema, + questionDialogWidth: questionDialogWidthSchema, + questionDialogMaxHeight: questionDialogMaxHeightSchema, + showHardwareCursor: showHardwareCursorSchema, + color: colorSchema, + title: titleSchema, +}) + +/** Serializable plugin configuration. */ +export interface Config extends TuiConfig { + /** Header subtitle. Defaults to `ready.`. */ + welcome?: string + /** Agent id driven by this terminal. Defaults to `main`. */ + agent?: string +} + +export const Config: z = z.object({ + welcome: z.string().default('ready.'), + agent: z.string().default('main'), + showReasoning: showReasoningSchema, + maxToolOutputLines: maxToolOutputLinesSchema, + maxQuestionOptions: maxQuestionOptionsSchema, + questionDialogWidth: questionDialogWidthSchema, + questionDialogMaxHeight: questionDialogMaxHeightSchema, + showHardwareCursor: showHardwareCursorSchema, + color: colorSchema, + title: titleSchema, +}) + +/** Fully defaulted TUI presentation settings. */ +export interface ResolvedTuiConfig { + showReasoning: boolean + maxToolOutputLines: number + maxQuestionOptions: number + questionDialogWidth: number + questionDialogMaxHeight: number + showHardwareCursor: boolean + color: boolean + title: string +} + +/** Runtime boundary used by the interactive TUI. */ +export interface TuiRuntime { + /** Terminal implementation; production uses pi-tui's `ProcessTerminal`. */ + terminal: Terminal + /** Exit hook used by `/exit`, Ctrl+D, or Ctrl+C while idle. */ + exit(code: number): void +} + +/** + * Apply direct-call defaults after Loader schema validation has normally run. + * + * @param config - Deployment-provided terminal presentation settings. + * @returns Complete settings consumed by the TUI renderer. + */ +export function resolveTuiConfig(config: TuiConfig | undefined): ResolvedTuiConfig { + return { + showReasoning: config?.showReasoning ?? true, + maxToolOutputLines: config?.maxToolOutputLines ?? 12, + maxQuestionOptions: config?.maxQuestionOptions ?? 8, + questionDialogWidth: config?.questionDialogWidth ?? 72, + questionDialogMaxHeight: config?.questionDialogMaxHeight ?? 20, + showHardwareCursor: config?.showHardwareCursor ?? false, + color: config?.color ?? true, + title: config?.title ?? 'DeepSeek Harness', + } +} + +interface Palette { + accent: (text: string) => string + accent2: (text: string) => string + text: (text: string) => string + muted: (text: string) => string + dim: (text: string) => string + success: (text: string) => string + warning: (text: string) => string + error: (text: string) => string + code: (text: string) => string + added: (text: string) => string + removed: (text: string) => string + bold: (text: string) => string + italic: (text: string) => string + underline: (text: string) => string + strike: (text: string) => string + userBg: (text: string) => string + pendingBg: (text: string) => string + successBg: (text: string) => string + errorBg: (text: string) => string + selectedBg: (text: string) => string +} + +function ansi(open: string, close: string, enabled: boolean): (text: string) => string { + return enabled ? text => `\x1b[${open}m${text}\x1b[${close}m` : text => text +} + +function createPalette(enabled: boolean): Palette { + return { + accent: ansi('38;5;39', '39', enabled), + accent2: ansi('38;5;141', '39', enabled), + text: ansi('38;5;252', '39', enabled), + muted: ansi('38;5;245', '39', enabled), + dim: ansi('38;5;240', '39', enabled), + success: ansi('38;5;78', '39', enabled), + warning: ansi('38;5;221', '39', enabled), + error: ansi('38;5;203', '39', enabled), + code: ansi('38;5;215', '39', enabled), + added: ansi('38;5;78', '39', enabled), + removed: ansi('38;5;203', '39', enabled), + bold: ansi('1', '22', enabled), + italic: ansi('3', '23', enabled), + underline: ansi('4', '24', enabled), + strike: ansi('9', '29', enabled), + userBg: ansi('48;5;236', '49', enabled), + pendingBg: ansi('48;5;235', '49', enabled), + successBg: ansi('48;5;22', '49', enabled), + errorBg: ansi('48;5;52', '49', enabled), + selectedBg: ansi('48;5;24', '49', enabled), + } +} + +function markdownTheme(palette: Palette): MarkdownTheme { + return { + heading: text => palette.accent(text), + link: text => palette.accent(text), + // pi-tui requires this URL slot but its current Markdown renderer does not invoke it. + /* v8 ignore next */ + linkUrl: text => palette.dim(text), + code: text => palette.code(text), + codeBlock: text => palette.text(text), + codeBlockBorder: text => palette.dim(text), + quote: text => palette.muted(text), + quoteBorder: text => palette.accent2(text), + hr: text => palette.dim(text), + listBullet: text => palette.accent(text), + bold: text => palette.bold(text), + italic: text => palette.italic(text), + strikethrough: text => palette.strike(text), + underline: text => palette.underline(text), + } +} + +function selectTheme(palette: Palette): SelectListTheme { + return { + selectedPrefix: palette.accent, + selectedText: palette.accent, + description: palette.muted, + scrollInfo: palette.dim, + noMatch: palette.warning, + } +} + +function contentText(content: readonly ContentBlock[]): string { + const parts: string[] = [] + for (const block of content) { + switch (block.type) { + case 'text': + case 'reasoning': + parts.push(block.text) + break + case 'tool-call': + parts.push(`${block.name}(${block.arguments})`) + break + case 'tool-result': + parts.push(contentText(block.content)) + break + default: { + const rawType = (block as { type?: unknown }).type + parts.push(`[${typeof rawType === 'string' ? rawType : 'content'}]`) + break + } + } + } + return parts.join('') +} + +function textBlocks(content: readonly ContentBlock[], type: 'text' | 'reasoning'): string { + return content + .filter((block): block is Extract => block.type === type) + .map(block => block.text) + .join('\n\n') +} + +class HeaderComponent implements Component { + constructor( + private readonly agent: Agent, + private readonly welcome: string, + private readonly palette: Palette, + ) {} + + invalidate(): void {} + + render(width: number): string[] { + const usable = Math.max(1, width - 4) + const title = `${this.palette.bold(this.palette.accent('DEEPSEEK'))} ${this.palette.bold('HARNESS')}` + const model = this.agent.options.model ?? 'model unset' + const detail = `${this.agent.id} • ${model} • ${this.agent.session.id}` + const top = this.palette.accent(`╭${'─'.repeat(Math.max(0, width - 2))}╮`) + const bottom = this.palette.accent(`╰${'─'.repeat(Math.max(0, width - 2))}╯`) + const lines = [title, this.palette.muted(this.welcome), this.palette.dim(detail)] + .flatMap(line => wrapTextWithAnsi(line, usable)) + .map((line) => { + const clipped = truncateToWidth(line, usable, '') + return `${this.palette.accent('│')} ${clipped}${' '.repeat(Math.max(0, usable - visibleWidth(clipped)))} ${this.palette.accent('│')}` + }) + return [top, ...lines, bottom] + } +} + +class UserMessageComponent extends Box { + constructor(text: string, palette: Palette, mdTheme: MarkdownTheme, label = 'You') { + super(1, 1, value => palette.userBg(value)) + this.addChild(new Text(palette.bold(palette.accent(label)), 0, 0)) + this.addChild(new Markdown(text, 0, 0, mdTheme, { color: value => palette.text(value) }, { + preserveOrderedListMarkers: true, + preserveBackslashEscapes: true, + })) + } +} + +class AssistantMessageComponent extends Container { + constructor(content: readonly ContentBlock[], showReasoning: boolean, palette: Palette, mdTheme: MarkdownTheme) { + super() + const reasoning = textBlocks(content, 'reasoning').trim() + const text = textBlocks(content, 'text').trim() + if (reasoning && showReasoning) { + this.addChild(new Spacer(1)) + this.addChild(new Text(palette.italic(palette.muted('Reasoning')), 1, 0)) + this.addChild(new Markdown(reasoning, 1, 0, mdTheme, { + color: value => palette.muted(value), + italic: true, + })) + } + if (text) { + this.addChild(new Spacer(1)) + this.addChild(new Text(palette.bold(palette.accent2('Assistant')), 1, 0)) + this.addChild(new Markdown(text, 1, 0, mdTheme, { color: value => palette.text(value) })) + } + } +} + +interface StreamingBlock { + type: string + text: string +} + +class StreamingAssistantComponent extends Container { + private readonly blocks = new Map() + + constructor( + private showReasoning: boolean, + private readonly palette: Palette, + private readonly mdTheme: MarkdownTheme, + ) { + super() + } + + update(chunk: StreamChunk): void { + if (chunk.type === 'block-start') { + this.blocks.set(chunk.index, { type: chunk.blockType, text: '' }) + } else if (chunk.type === 'text-delta' || chunk.type === 'reasoning-delta') { + const type = chunk.type === 'text-delta' ? 'text' : 'reasoning' + const block = this.blocks.get(chunk.index) ?? { type, text: '' } + block.text += chunk.text + this.blocks.set(chunk.index, block) + } else if (chunk.type === 'block-end' && (chunk.block.type === 'text' || chunk.block.type === 'reasoning')) { + this.blocks.set(chunk.index, { type: chunk.block.type, text: chunk.block.text }) + } + this.rebuild() + } + + setShowReasoning(show: boolean): void { + this.showReasoning = show + this.rebuild() + } + + private rebuild(): void { + this.clear() + const content: ContentBlock[] = [...this.blocks.entries()] + .sort(([left], [right]) => left - right) + .flatMap(([, block]) => { + if (block.type === 'text') return [{ type: 'text', text: block.text }] + if (block.type === 'reasoning') return [{ type: 'reasoning', text: block.text }] + return [] + }) + const component = new AssistantMessageComponent(content, this.showReasoning, this.palette, this.mdTheme) + for (const child of component.children) this.addChild(child) + } +} + +interface ParsedArguments { + value: unknown + valid: boolean +} + +function parseArguments(raw: string): ParsedArguments { + try { + return { value: JSON.parse(raw), valid: true } + } catch { + return { value: raw, valid: false } + } +} + +function pretty(value: unknown): string { + if (typeof value === 'string') return value + // The lib declaration narrows `unknown` to a string-returning overload, but + // JSON.stringify returns undefined for runtime values such as symbols. + const serialized = JSON.stringify(value, null, 2) as string | undefined + return serialized ?? String(value) +} + +function diffLines(diff: FileDiff, palette: Palette): string[] { + const lines = [palette.bold(diff.path)] + if (diff.oldText !== null) { + for (const line of diff.oldText.split('\n')) lines.push(palette.removed(`- ${line}`)) + } + for (const line of diff.newText.split('\n')) lines.push(palette.added(`+ ${line}`)) + return lines +} + +class ToolCardComponent implements Component { + private result: { content: ContentBlock[]; isError: boolean; meta?: unknown } | undefined + private expanded = false + private callView: ToolCallView + private resultView: ToolResultView | undefined + + constructor( + private readonly name: string, + private readonly parsed: ParsedArguments, + private readonly definition: ToolDefinition | undefined, + private readonly maxOutputLines: number, + private readonly palette: Palette, + ) { + this.callView = this.presentCall() + } + + private presentCall(): ToolCallView { + if (this.parsed.valid && this.definition?.presentCall) { + try { + const view = this.definition.presentCall(this.parsed.value) + if (view !== undefined) return view + } catch (error: unknown) { + return { card: 'generic', title: this.name, rawInput: `Presenter failed: ${String(error)}` } + } + } + return { card: 'generic', title: this.name, rawInput: this.parsed.value } + } + + updateResult(event: Extract['data']): void { + this.result = { + content: [...event.content], + isError: event.isError, + ...event.meta !== undefined ? { meta: event.meta } : {}, + } + if (this.parsed.valid && this.definition?.presentResult) { + try { + const view = this.definition.presentResult(this.parsed.value, this.result) + if (view !== undefined) this.resultView = view + } catch (error: unknown) { + this.resultView = { card: 'generic', content: [{ type: 'text', text: `Presenter failed: ${String(error)}` }] } + } + } + } + + setExpanded(expanded: boolean): void { + this.expanded = expanded + } + + invalidate(): void {} + + render(width: number): string[] { + const isError = this.result?.isError ?? false + const glyph = this.result === undefined ? this.palette.warning('◌') : isError ? this.palette.error('✕') : this.palette.success('✓') + const body = this.renderBody() + const title = truncateToWidth(`${glyph} ${this.title()}`, Math.max(1, width - 4), '') + const visibleBody = this.expanded || body.length <= this.maxOutputLines + ? body + : [...body.slice(0, this.maxOutputLines), this.palette.dim(`… ${body.length - this.maxOutputLines} more lines (Ctrl+O to expand)`)] + const box = new Box(1, visibleBody.length > 0 ? 1 : 0, (value) => { + if (this.result === undefined) return this.palette.pendingBg(value) + return isError ? this.palette.errorBg(value) : this.palette.successBg(value) + }) + box.addChild(new Text(this.palette.bold(title), 0, 0)) + if (visibleBody.length > 0) box.addChild(new Text(visibleBody.join('\n'), 0, 0)) + return box.render(width) + } + + private title(): string { + return this.resultView?.title ?? this.callView.title + } + + private renderBody(): string[] { + const view = this.resultView ?? this.callView + if (view.card === 'terminal') { + const pending = this.callView.card === 'terminal' ? this.callView : undefined + const lines: string[] = [] + if (pending?.description) lines.push(this.palette.muted(pending.description)) + if (pending?.cwd) lines.push(this.palette.dim(pending.cwd)) + if (this.resultView?.card === 'terminal') { + if (this.resultView.output) lines.push(...this.resultView.output.split('\n')) + if (this.resultView.exitCode !== undefined) lines.push(this.palette.dim(`[exit ${this.resultView.exitCode}]`)) + if (this.resultView.signal !== undefined) lines.push(this.palette.error(`[signal ${this.resultView.signal}]`)) + } else if (this.result === undefined) { + // A pending terminal view is the call view itself; TerminalCallView requires a title. + lines.push(this.palette.code(`$ ${(pending as TerminalCallView).title}`)) + } else { + lines.push(...contentText(this.result.content).split('\n')) + } + return lines.filter(Boolean) + } + if (view.card === 'diff') { + return view.diffs.flatMap((diff, index) => [ + ...index > 0 ? [''] : [], + ...diffLines(diff, this.palette), + ]) + } + const content = view.content ?? this.result?.content + const lines: string[] = [] + if (content !== undefined) lines.push(...contentText(content).split('\n')) + const rawInput = this.result === undefined && this.callView.card === 'generic' + ? this.callView.rawInput + : undefined + if (rawInput !== undefined) lines.push(...pretty(rawInput).split('\n')) + return lines.filter((line, index, all) => line.length > 0 || (index > 0 && index < all.length - 1)) + } +} + +class TodoComponent implements Component { + private todos: readonly TodoItem[] = [] + + constructor(private readonly palette: Palette) {} + + update(todos: readonly TodoItem[]): void { + this.todos = todos + } + + invalidate(): void {} + + render(width: number): string[] { + if (this.todos.length === 0) return [] + const lines = [this.palette.bold(this.palette.accent('Plan'))] + for (const todo of this.todos) { + const prefix = todo.status === 'completed' + ? this.palette.success('✓') + : todo.status === 'in_progress' + ? this.palette.warning('●') + : this.palette.dim('○') + const text = todo.status === 'completed' ? this.palette.muted(todo.content) : todo.content + lines.push(truncateToWidth(` ${prefix} ${text}`, width, '')) + } + return ['', ...lines] + } +} + +function formatTokens(value: number): string { + if (value < 1_000) return String(value) + if (value < 10_000) return `${(value / 1_000).toFixed(1)}k` + if (value < 1_000_000) return `${Math.round(value / 1_000)}k` + return `${(value / 1_000_000).toFixed(1)}m` +} + +function formatCwd(cwd: string | undefined): string { + if (cwd === undefined) return 'cwd unset' + const home = homedir() + const rel = relative(resolve(home), resolve(cwd)) + if (rel === '') return '~' + if (rel !== '..' && !rel.startsWith(`..${sep}`)) return `~${sep}${rel}` + return cwd +} + +function sessionTokens(session: Session): { input: number; output: number } { + let input = 0 + let output = 0 + for (const event of session.events) { + if (event.type !== 'assistant/message' || event.data.usage === undefined) continue + input += event.data.usage.inputTokens + output += event.data.usage.outputTokens + } + return { input, output } +} + +class FooterComponent implements Component { + constructor( + private readonly agent: Agent, + private readonly palette: Palette, + private readonly toolsExpanded: () => boolean, + private readonly showReasoning: () => boolean, + private readonly tokens: () => { input: number; output: number }, + ) {} + + invalidate(): void {} + + render(width: number): string[] { + const { input, output } = this.tokens() + const left = `${formatCwd(this.agent.session.header.cwd)} ↑${formatTokens(input)} ↓${formatTokens(output)}` + const right = `${this.agent.status} reasoning:${this.showReasoning() ? 'on' : 'off'} tools:${this.toolsExpanded() ? 'expanded' : 'compact'}` + const leftStyled = this.palette.dim(left) + const available = Math.max(0, width - visibleWidth(left) - 2) + const rightClipped = truncateToWidth(right, available, '') + const gap = ' '.repeat(Math.max(1, width - visibleWidth(left) - visibleWidth(rightClipped))) + return [truncateToWidth(`${leftStyled}${gap}${this.palette.dim(rightClipped)}`, width, '')] + } +} + +interface QuestionSelection { + selected: string[] + custom?: string +} + +class QuestionDialog implements Component, Focusable { + private selectedIndex = 0 + private selected = new Set() + private mode: 'options' | 'custom' + private error = '' + private readonly input = new Input() + private readonly options: NonNullable + focused = false + + constructor( + private readonly question: AskUserQuestionItem, + private readonly maxVisible: number, + private readonly palette: Palette, + private readonly done: (selection: QuestionSelection) => void, + private readonly cancel: () => void, + ) { + this.options = question.options ?? [] + this.mode = this.options.length > 0 ? 'options' : 'custom' + this.input.onSubmit = (value) => { this.submitCustom(value) } + this.input.onEscape = () => { + if (this.options.length > 0) { + this.mode = 'options' + this.error = '' + } else { + this.cancel() + } + } + } + + invalidate(): void { + this.input.invalidate() + } + + handleInput(data: string): void { + this.invalidate() + if (this.mode === 'custom') { + this.input.focused = this.focused + this.input.handleInput(data) + return + } + const options = this.options + if (matchesKey(data, Key.up)) { + this.selectedIndex = this.selectedIndex === 0 ? options.length - 1 : this.selectedIndex - 1 + } else if (matchesKey(data, Key.down)) { + this.selectedIndex = this.selectedIndex === options.length - 1 ? 0 : this.selectedIndex + 1 + } else if (matchesKey(data, Key.space) && this.question.multiSelect) { + if (this.selected.has(this.selectedIndex)) this.selected.delete(this.selectedIndex) + else this.selected.add(this.selectedIndex) + } else if (matchesKey(data, Key.enter)) { + const indices = this.question.multiSelect ? [...this.selected].sort((a, b) => a - b) : [this.selectedIndex] + if (indices.length === 0) { + this.error = 'Select at least one option, or press C for a custom answer.' + return + } + this.done({ selected: indices.map(index => options[index]?.label).filter((label): label is string => label !== undefined) }) + } else if (data.toLowerCase() === 'c') { + this.mode = 'custom' + this.error = '' + } else if (matchesKey(data, Key.escape) || matchesKey(data, Key.ctrl('c'))) { + this.cancel() + } + } + + private submitCustom(value: string): void { + const custom = value.trim() + if (custom === '') { + this.error = 'Enter an answer before submitting.' + return + } + this.done({ selected: [], custom }) + } + + render(width: number): string[] { + this.input.focused = this.focused + const innerWidth = Math.max(1, width - 4) + const title = this.question.header ?? 'Question' + const topLabel = ` ${title} ` + const top = `╭${topLabel}${'─'.repeat(Math.max(0, width - visibleWidth(topLabel) - 2))}╮` + const lines: string[] = [this.palette.accent(top)] + const push = (line: string): void => { + const clipped = truncateToWidth(line, innerWidth, '') + lines.push(`${this.palette.accent('│')} ${clipped}${' '.repeat(Math.max(0, innerWidth - visibleWidth(clipped)))} ${this.palette.accent('│')}`) + } + for (const line of wrapTextWithAnsi(this.palette.bold(this.question.question), innerWidth)) push(line) + push('') + if (this.mode === 'custom') { + for (const line of this.input.render(innerWidth)) push(line) + push(this.palette.dim(this.options.length > 0 ? 'Enter submit • Esc options' : 'Enter submit • Esc cancel')) + } else { + const options = this.options + const start = Math.max(0, Math.min( + this.selectedIndex - Math.floor(this.maxVisible / 2), + options.length - this.maxVisible, + )) + const end = Math.min(options.length, start + this.maxVisible) + for (let index = start; index < end; index += 1) { + // `index < end <= options.length`; the options array is borrowed immutably for this dialog. + const option = options[index] as NonNullable[number] + const cursor = index === this.selectedIndex ? this.palette.accent('›') : ' ' + const mark = this.question.multiSelect + ? this.selected.has(index) ? this.palette.success('[x]') : '[ ]' + : index === this.selectedIndex ? this.palette.accent('●') : this.palette.dim('○') + const description = option.description ? this.palette.muted(` — ${option.description}`) : '' + const line = `${cursor} ${mark} ${option.label}${description}` + push(index === this.selectedIndex ? this.palette.selectedBg(line) : line) + } + if (options.length > this.maxVisible) push(this.palette.dim(`${this.selectedIndex + 1}/${options.length}`)) + push(this.palette.dim(this.question.multiSelect + ? '↑↓ navigate • Space toggle • Enter submit • C custom • Esc cancel' + : '↑↓ navigate • Enter select • C custom • Esc cancel')) + } + if (this.error) push(this.palette.error(this.error)) + lines.push(this.palette.accent(`╰${'─'.repeat(Math.max(0, width - 2))}╯`)) + return lines + } +} + +interface PendingQuestion { + request: AskUserQuestionRequest + index: number + answers: AskUserQuestionAnswerItem[] + resolve(answer: AskUserQuestionAnswer): void + reject(error: unknown): void + onAbort: () => void + overlay: OverlayHandle | undefined +} + +/** Lifecycle handle for a mounted interactive terminal channel. */ +export interface TuiController { + /** Stop rendering, restore the terminal, and reject pending questions. */ + dispose(): Promise +} + +function activeSurfaceSeqs(session: Session): Set { + return new Set(session.surface.nodes.map(node => node.seq)) +} + +function activeToolCallIds(session: Session, active: ReadonlySet): Set { + const ids = new Set() + for (const event of session.events) { + if (event.type !== 'assistant/message' || !active.has(event.seq)) continue + for (const block of event.data.content) { + if (block.type === 'tool-call') ids.add(block.id) + } + } + return ids +} + +/** + * Start the interactive pi-tui channel for an already-created target agent. + * @param ctx - agent, tools, session-event, and user-interaction context. + * @param config - target agent, banner, and TUI presentation config. + * @param runtime - terminal and process-exit boundary. + * @returns lifecycle controller used by the Cordis effect disposer. + */ +export function createTuiChat( + ctx: Context, + config: Config, + runtime: TuiRuntime, +): TuiController { + const agentId = AgentId(config.agent ?? 'main') + const agent = ctx.agents.get(agentId) + if (agent === undefined) throw new Error(`ui-tui: agent "${agentId}" is not running`) + const resolved = resolveTuiConfig(config) + const palette = createPalette(resolved.color) + const mdTheme = markdownTheme(palette) + const ui = new TUI(runtime.terminal, resolved.showHardwareCursor) + const chat = new Container() + const todoContainer = new Container() + const statusContainer = new Container() + const editor = new Editor(ui, { + borderColor: palette.dim, + selectList: selectTheme(palette), + } satisfies EditorTheme, { paddingX: 1 }) + const todo = new TodoComponent(palette) + let showReasoning = resolved.showReasoning + let toolsExpanded = false + let streaming: StreamingAssistantComponent | undefined + let statusLoader: Loader | undefined + let disposed = false + let shuttingDown: Promise | undefined + const tokens = sessionTokens(agent.session) + const toolCards = new Map() + const allToolCards = new Set() + const liveErrors = new Set() + const questionQueue: PendingQuestion[] = [] + let activeQuestion: PendingQuestion | undefined + + const welcome = config.welcome ?? 'ready.' + const header = new HeaderComponent(agent, welcome, palette) + const footer = new FooterComponent(agent, palette, () => toolsExpanded, () => showReasoning, () => tokens) + ui.addChild(header) + ui.addChild(chat) + ui.addChild(statusContainer) + todoContainer.addChild(todo) + ui.addChild(todoContainer) + ui.addChild(editor) + ui.addChild(footer) + ui.setFocus(editor) + runtime.terminal.setTitle(resolved.title) + + const requestRender = (): void => { + footer.invalidate() + ui.requestRender() + } + + const appendNotice = (message: string, kind: 'info' | 'warning' | 'error' = 'info'): void => { + const color = kind === 'error' ? palette.error : kind === 'warning' ? palette.warning : palette.muted + chat.addChild(new Spacer(1)) + chat.addChild(new Text(color(message), 1, 0)) + requestRender() + } + + const clearStatus = (): void => { + statusLoader?.stop() + statusLoader = undefined + statusContainer.clear() + runtime.terminal.setProgress(false) + } + + const setStatus = (status: AgentStatus): void => { + clearStatus() + editor.borderColor = status === 'running' ? text => palette.accent(text) : text => palette.dim(text) + if (status === 'running') { + statusLoader = new Loader(ui, text => palette.accent(text), text => palette.muted(text), 'Working — Enter sends steering, Esc cancels') + statusContainer.addChild(statusLoader) + runtime.terminal.setProgress(true) + } + requestRender() + } + + const parsedTool = (event: Extract): ToolCardComponent => { + const parsed = parseArguments(event.data.arguments) + const card = new ToolCardComponent( + event.data.name, + parsed, + ctx.tools.get(event.data.name, agent), + resolved.maxToolOutputLines, + palette, + ) + card.setExpanded(toolsExpanded) + toolCards.set(event.data.callId, card) + allToolCards.add(card) + return card + } + + const renderEvent = (event: SessionEvent, options: { addHistory: boolean; renderChunks: boolean }): void => { + switch (event.type) { + case 'user/message': { + const text = contentText(event.data.content).trim() + if (text) { + chat.addChild(new Spacer(1)) + chat.addChild(new UserMessageComponent(text, palette, mdTheme)) + if (options.addHistory) editor.addToHistory(text) + } + break + } + case 'steering/message': { + const text = contentText(event.data.content).trim() + if (text) { + chat.addChild(new Spacer(1)) + chat.addChild(new UserMessageComponent(text, palette, mdTheme, 'Steering')) + } + break + } + case 'context/message': { + const text = contentText(event.data.content).trim() + if (text) { + const source = event.data.source.kind === 'plugin' ? event.data.source.plugin : event.data.source.kind + chat.addChild(new Spacer(1)) + chat.addChild(new Text(palette.dim(`Context · ${source}`), 1, 0)) + chat.addChild(new Text(palette.muted(text), 1, 0)) + } + break + } + case 'prompt/blocked': + appendNotice(`Prompt blocked: ${event.data.reason}`, 'warning') + break + case 'assistant/chunk': + if (options.renderChunks) { + if (streaming === undefined) { + streaming = new StreamingAssistantComponent(showReasoning, palette, mdTheme) + chat.addChild(streaming) + } + streaming.update(event.data.chunk) + } + break + case 'assistant/message': { + if (streaming !== undefined) { + const index = chat.children.indexOf(streaming) + if (index >= 0) chat.children.splice(index, 1) + streaming = undefined + } + const component = new AssistantMessageComponent(event.data.content, showReasoning, palette, mdTheme) + if (component.children.length > 0) chat.addChild(component) + break + } + case 'tool/call': + chat.addChild(new Spacer(1)) + chat.addChild(parsedTool(event)) + break + case 'tool/result': { + let card = toolCards.get(event.data.callId) + if (card === undefined) { + card = new ToolCardComponent('tool', { value: {}, valid: true }, undefined, resolved.maxToolOutputLines, palette) + chat.addChild(new Spacer(1)) + chat.addChild(card) + allToolCards.add(card) + } + card.updateResult(event.data) + toolCards.delete(event.data.callId) + break + } + case 'todo/write': + todo.update(event.data.todos) + break + case 'turn/end': + if (event.data.reason.kind === 'error') { + const key = `${event.data.turn}:${event.data.reason.step}` + if (!liveErrors.delete(key)) appendNotice(event.data.reason.message, 'error') + } else if (event.data.reason.kind === 'aborted') { + appendNotice(event.data.reason.reason ?? 'Turn cancelled.', 'warning') + } else if (event.data.reason.kind === 'max-tokens') { + appendNotice('The model reached its output-token limit.', 'warning') + } else if (event.data.reason.kind === 'rejected') { + appendNotice(`Turn rejected: ${event.data.reason.reason}`, 'warning') + } else if (event.data.reason.kind === 'interrupted') { + appendNotice('The previous process ended during this turn.', 'warning') + } + break + default: + break + } + } + + const rebuildTranscript = (populateHistory: boolean): void => { + chat.clear() + toolCards.clear() + allToolCards.clear() + streaming = undefined + const active = activeSurfaceSeqs(agent.session) + const activeCalls = activeToolCallIds(agent.session, active) + for (const event of agent.session.events) { + const isSurface = event.type === 'user/message' + || event.type === 'assistant/message' + || event.type === 'tool/result' + || event.type === 'context/message' + || event.type === 'steering/message' + if (isSurface && !active.has(event.seq)) continue + if (event.type === 'tool/call' && !activeCalls.has(event.data.callId)) continue + renderEvent(event, { addHistory: populateHistory, renderChunks: false }) + } + requestRender() + } + + const removeAbortListener = (pending: PendingQuestion): void => { + pending.request.signal?.removeEventListener('abort', pending.onAbort) + } + + const rejectQuestion = (pending: PendingQuestion): void => { + pending.overlay?.hide() + pending.overlay = undefined + removeAbortListener(pending) + pending.reject(new UserInteractionError( + 'ask_user_question was interrupted before the user answered', + 'ASK_ABORTED', + )) + } + + const startNextQuestion = (): void => { + if (activeQuestion !== undefined || disposed) return + const pending = questionQueue.shift() + if (pending === undefined) return + activeQuestion = pending + const show = (): void => { + const question = pending.request.questions[pending.index] + if (question === undefined) { + activeQuestion = undefined + removeAbortListener(pending) + pending.resolve({ answers: pending.answers }) + startNextQuestion() + return + } + const dialog = new QuestionDialog( + question, + resolved.maxQuestionOptions, + palette, + (selection) => { + pending.overlay?.hide() + pending.overlay = undefined + pending.answers.push({ id: question.id, ...selection }) + pending.index += 1 + show() + }, + () => { + activeQuestion = undefined + rejectQuestion(pending) + startNextQuestion() + }, + ) + pending.overlay = ui.showOverlay(dialog, { + width: resolved.questionDialogWidth, + maxHeight: resolved.questionDialogMaxHeight, + anchor: 'center', + margin: 1, + }) + requestRender() + } + show() + } + + const disposeUserInteraction = ctx.userInteraction.registerProvider({ + ask(request) { + return new Promise((resolveAnswer, reject) => { + const pending: PendingQuestion = { + request, + index: 0, + answers: [], + resolve: resolveAnswer, + reject, + overlay: undefined, + onAbort: () => { + if (activeQuestion === pending) { + activeQuestion = undefined + rejectQuestion(pending) + startNextQuestion() + return + } + // A non-active pending ask remains in the queue until this listener settles it. + questionQueue.splice(questionQueue.indexOf(pending), 1) + rejectQuestion(pending) + }, + } + request.signal?.addEventListener('abort', pending.onAbort, { once: true }) + questionQueue.push(pending) + startNextQuestion() + }) + }, + }) + + const shutdown = (exitProcess: boolean): Promise => { + shuttingDown ??= (async () => { + disposed = true + clearStatus() + if (activeQuestion !== undefined) { + const pending = activeQuestion + activeQuestion = undefined + rejectQuestion(pending) + } + for (const pending of questionQueue.splice(0)) rejectQuestion(pending) + disposeUserInteraction() + await runtime.terminal.drainInput(100, 20) + ui.stop() + if (exitProcess) runtime.exit(0) + })() + return shuttingDown + } + + const requestExit = (): void => { + if (agent.status === 'running') { + agent.cancel('terminal exit requested') + appendNotice('Cancelling the active turn before exit…', 'warning') + void agent.whenIdle().then(() => shutdown(true)) + return + } + void shutdown(true) + } + + editor.setAutocompleteProvider(new CombinedAutocompleteProvider([ + { name: 'help', description: 'Show keyboard shortcuts and commands' }, + { name: 'clear', description: 'Clear the transcript view (session history is unchanged)' }, + { name: 'cancel', description: 'Cancel the active turn' }, + { name: 'reasoning', description: 'Toggle reasoning blocks' }, + { name: 'tools', description: 'Expand or collapse all tool cards' }, + { name: 'redraw', description: 'Invalidate components and redraw the terminal' }, + { name: 'exit', description: 'Exit after the active turn reaches idle' }, + ], agent.session.header.cwd ?? process.cwd())) + + const toggleTools = (): void => { + toolsExpanded = !toolsExpanded + for (const card of allToolCards) card.setExpanded(toolsExpanded) + appendNotice(`Tool cards ${toolsExpanded ? 'expanded' : 'collapsed'}.`) + } + + const toggleReasoning = (): void => { + showReasoning = !showReasoning + const activeStreaming = streaming + rebuildTranscript(false) + if (activeStreaming !== undefined) { + streaming = activeStreaming + streaming.setShowReasoning(showReasoning) + chat.addChild(activeStreaming) + } + appendNotice(`Reasoning blocks ${showReasoning ? 'shown' : 'hidden'}.`) + } + + const showHelp = (): void => { + chat.addChild(new Spacer(1)) + chat.addChild(new Text(palette.bold(palette.accent('Keyboard shortcuts')), 1, 0)) + chat.addChild(new Text([ + 'Enter send • Shift/Alt+Enter newline • Up/Down prompt history', + 'Esc cancel active turn • Ctrl+O expand tool cards • Ctrl+R toggle reasoning', + 'Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit', + '/help /clear /cancel /reasoning /tools /redraw /exit', + ].map(line => palette.muted(line)).join('\n'), 1, 0)) + requestRender() + } + + editor.onSubmit = (value: string) => { + const text = value.trim() + if (text === '') return + editor.addToHistory(text) + editor.setText('') + switch (text) { + case '/help': + showHelp() + return + case '/clear': + chat.clear() + requestRender() + return + case '/cancel': + if (agent.status === 'running') agent.cancel('cancelled from terminal') + else appendNotice('The agent is already idle.') + return + case '/reasoning': + toggleReasoning() + return + case '/tools': + toggleTools() + return + case '/redraw': + ui.invalidate() + ui.requestRender(true) + return + case '/exit': + requestExit() + return + default: + if (text.startsWith('/')) { + appendNotice(`Unknown command: ${text}`, 'warning') + return + } + } + if (agent.status === 'disposed') { + appendNotice(`Agent "${agent.id}" is disposed.`, 'error') + } else if (agent.status === 'running') { + agent.steer([{ type: 'text', text }]) + } else { + agent.send([{ type: 'text', text }]) + } + } + + const removeInputListener = ui.addInputListener((data) => { + if (activeQuestion !== undefined) return undefined + if (matchesKey(data, Key.ctrl('o'))) { + toggleTools() + return { consume: true } + } + if (matchesKey(data, Key.ctrl('r'))) { + toggleReasoning() + return { consume: true } + } + if (matchesKey(data, Key.ctrl('l'))) { + ui.invalidate() + ui.requestRender(true) + return { consume: true } + } + if (matchesKey(data, Key.escape) && agent.status === 'running') { + agent.cancel('cancelled from terminal') + return { consume: true } + } + if (matchesKey(data, Key.ctrl('c'))) { + if (agent.status === 'running') { + agent.cancel('cancelled from terminal') + } else if (editor.getText() !== '') { + editor.setText('') + } else { + requestExit() + } + return { consume: true } + } + if (matchesKey(data, Key.ctrl('d'))) { + if (agent.status === 'running') appendNotice('Cancel the active turn before exiting.', 'warning') + else requestExit() + return { consume: true } + } + return undefined + }) + + const disposeSessionEvents = ctx.on('session/event', (session, event) => { + if (session !== agent.session) return + if (event.type === 'assistant/message' && event.data.usage !== undefined) { + tokens.input += event.data.usage.inputTokens + tokens.output += event.data.usage.outputTokens + } + if ('surfaceOp' in event && typeof event.surfaceOp === 'object') { + rebuildTranscript(false) + return + } + renderEvent(event, { addHistory: false, renderChunks: true }) + requestRender() + }) + const disposeStatus = ctx.on('agent/status', (subject, status) => { + if (subject !== agent) return + setStatus(status) + }) + const disposeError = ctx.on('agent/error', (subject, turn, step, error) => { + if (subject !== agent) return + liveErrors.add(`${turn}:${step}`) + appendNotice(error.message, 'error') + }) + const disposeAgent = ctx.on('agent/disposed', (subject) => { + if (subject !== agent) return + clearStatus() + appendNotice(`Agent "${agent.id}" was disposed.`, 'warning') + }) + + const detachListeners = (): void => { + removeInputListener() + disposeSessionEvents() + disposeStatus() + disposeError() + disposeAgent() + } + + rebuildTranscript(true) + setStatus(agent.status) + try { + ui.start() + } catch (error: unknown) { + disposed = true + detachListeners() + clearStatus() + disposeUserInteraction() + ui.stop() + throw error + } + + return { + async dispose(): Promise { + detachListeners() + await shutdown(false) + }, + } +} + +/** + * Open the pi-tui channel once its configured agent exists. + * + * @param ctx - Context supplying the agent registry, tools, and event stream. + * @param config - Target agent and presentation configuration. + * @param runtime - Terminal and process-exit boundary. + */ +export function mountTui(ctx: Context, config: Config, runtime: TuiRuntime): void { + const agentId = AgentId(config.agent ?? 'main') + const start = (): void => { + ctx.effect(() => { + const controller = createTuiChat(ctx, config, runtime) + return () => controller.dispose() + }, 'ui-tui') + } + if (ctx.agents.get(agentId) !== undefined) { + start() + return + } + const dispose = ctx.on('agent/created', (agent) => { + if (agent.id !== agentId) return + dispose() + start() + }) +} + +/** Cordis entry point using the process terminal; explicit TUI composition requires a TTY pair. */ +/* v8 ignore start -- production process wiring; fake-terminal tests cover mountTui/createTuiChat, + and the coding-agent PTY smoke covers the real entry */ +export function apply(ctx: Context, config: Config): void { + if (!process.stdin.isTTY || !process.stdout.isTTY) { + throw new Error('ui-tui: both stdin and stdout must be TTYs; use @deepseek-ai/dsh-stdio for pipes') + } + mountTui(ctx, config, { + terminal: new ProcessTerminal(), + exit: code => process.exit(code), + }) +} +/* v8 ignore stop */ diff --git a/packages/ui/tui/tests/plugin-shape.spec.ts b/packages/ui/tui/tests/plugin-shape.spec.ts new file mode 100644 index 0000000000..d1e4b92f3d --- /dev/null +++ b/packages/ui/tui/tests/plugin-shape.spec.ts @@ -0,0 +1,19 @@ +import { describe, expect, it } from 'vitest' +import Loader from '@cordisjs/plugin-loader' +import * as tui from '../src/index.ts' + +/** Real Loader export-path guard for the namespace TUI plugin. */ +describe('dsh-tui plugin export shape', () => { + it('preserves name, inject, Config, and apply through Loader unwrapping', () => { + expect('default' in tui).toBe(false) + expect(typeof tui.apply).toBe('function') + + const loader = Object.create(Loader.prototype) as Loader + const unwrapped = loader.unwrapExports(tui) as Record + expect(unwrapped).toBe(tui) + expect(unwrapped.name).toBe('ui-tui') + expect(unwrapped.inject).toEqual(['agents', 'userInteraction', 'tools']) + expect(unwrapped.Config).toBeDefined() + expect(typeof unwrapped.apply).toBe('function') + }) +}) diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts new file mode 100644 index 0000000000..e4ffe2efd0 --- /dev/null +++ b/packages/ui/tui/tests/tui.spec.ts @@ -0,0 +1,952 @@ +import { describe, expect, it, vi } from 'vitest' +import { Context } from 'cordis' +import type { Terminal } from '@earendil-works/pi-tui' +import AgentRegistry, { AgentId, type Agent, type AgentStatus } from '@deepseek-ai/dsh-agent' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import SessionStore, { SessionId, type Session } from '@deepseek-ai/dsh-session' +import type { ToolDefinition } from '@deepseek-ai/dsh-tools' +import UserInteractionService from '@deepseek-ai/dsh-user-interaction' +import { + createTuiChat, + mountTui, + resolveTuiConfig, + type Config, + type TuiRuntime, +} from '../src/index.ts' + +class FakeTerminal implements Terminal { + columns = 88 + rows = 32 + kittyProtocolActive = false + output = '' + title = '' + progress: boolean[] = [] + started = 0 + stopped = 0 + drainInput = vi.fn(() => Promise.resolve()) + private onInput: (data: string) => void = () => {} + private onResize: () => void = () => {} + + start(onInput: (data: string) => void, onResize: () => void): void { + this.started += 1 + this.onInput = onInput + this.onResize = onResize + } + + stop(): void { + this.stopped += 1 + } + + write(data: string): void { + this.output += data + } + + moveBy(lines: number): void { + this.output += `[move:${lines}]` + } + + hideCursor(): void { + this.output += '[hide]' + } + + showCursor(): void { + this.output += '[show]' + } + + clearLine(): void { + this.output += '[clear-line]' + } + + clearFromCursor(): void { + this.output += '[clear-rest]' + } + + clearScreen(): void { + this.output += '[clear-screen]' + } + + setTitle(title: string): void { + this.title = title + } + + setProgress(active: boolean): void { + this.progress.push(active) + } + + send(data: string): void { + this.onInput(data) + } + + resize(columns: number, rows = this.rows): void { + this.columns = columns + this.rows = rows + this.onResize() + } +} + +interface FakeAgent extends Agent { + status: AgentStatus + sent: ContentBlock[][] + steered: ContentBlock[][] + cancelled: string[] +} + +async function tick(): Promise { + await new Promise(resolve => setTimeout(resolve, 25)) +} + +async function setup(options: { + status?: AgentStatus + config?: Config + tools?: Record + beforeMount?: (session: Session) => void + cwd?: string | null +} = {}) { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + const tools = options.tools ?? {} + ctx.provide('tools', { + get(name: string) { + return tools[name] + }, + } as never) + const session = ctx.sessions.create( + SessionId('main-session'), + options.cwd === null ? undefined : { meta: { cwd: options.cwd ?? process.cwd() } }, + ) + options.beforeMount?.(session) + const sent: ContentBlock[][] = [] + const steered: ContentBlock[][] = [] + const cancelled: string[] = [] + const agent: FakeAgent = { + id: AgentId('main'), + options: { model: 'deepseek-v4-flash' }, + session, + status: options.status ?? 'idle', + ctx, + sent, + steered, + cancelled, + send(content) { + sent.push(content) + }, + steer(content) { + steered.push(content) + }, + inject() {}, + cancel(reason) { + cancelled.push(reason ?? '') + }, + whenIdle() { + return Promise.resolve() + }, + } + ctx.agents.register(agent) + const terminal = new FakeTerminal() + const exit = vi.fn() + const controller = createTuiChat(ctx, Object.assign({ + welcome: 'Coding agent ready.', + agent: 'main', + color: false, + }, options.config), { terminal, exit }) + await tick() + return { ctx, session, agent, terminal, exit, controller } +} + +async function dispose(setupResult: Awaited>): Promise { + await setupResult.controller.dispose() + await setupResult.ctx.fiber.dispose() +} + +function appendUser(session: Session, text: string): void { + session.append('user/message', { + content: [{ type: 'text', text }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) +} + +function appendAssistant(session: Session, content: ContentBlock[], usage?: { inputTokens: number; outputTokens: number }): void { + session.append('assistant/message', { + turn: 1, + step: 0, + content, + ...usage === undefined ? {} : { usage }, + }, { surfaceOp: 'append' }) +} + +describe('TUI config', () => { + it('defaults every direct-call TUI option', () => { + expect(resolveTuiConfig(undefined)).toEqual({ + showReasoning: true, + maxToolOutputLines: 12, + maxQuestionOptions: 8, + questionDialogWidth: 72, + questionDialogMaxHeight: 20, + showHardwareCursor: false, + color: true, + title: 'DeepSeek Harness', + }) + expect(resolveTuiConfig({ + showReasoning: false, + maxToolOutputLines: 2, + maxQuestionOptions: 3, + questionDialogWidth: 60, + questionDialogMaxHeight: 14, + showHardwareCursor: true, + color: false, + title: 'DSH', + })).toEqual({ + showReasoning: false, + maxToolOutputLines: 2, + maxQuestionOptions: 3, + questionDialogWidth: 60, + questionDialogMaxHeight: 14, + showHardwareCursor: true, + color: false, + title: 'DSH', + }) + }) +}) + +describe('pi-tui chat lifecycle and transcript', () => { + it('renders its header, footer, replay, streaming answer, todos, and status', async () => { + const result = await setup({ + beforeMount(session) { + appendUser(session, 'restored prompt') + appendAssistant(session, [ + { type: 'reasoning', text: 'restored thought' }, + { type: 'text', text: '**restored answer**' }, + ], { inputTokens: 1_250, outputTokens: 42 }) + session.append('todo/write', { + todos: [ + { content: 'read code', status: 'completed' }, + { content: 'write tests', status: 'in_progress' }, + { content: 'ship', status: 'pending' }, + ], + }) + }, + }) + + expect(result.terminal.started).toBe(1) + expect(result.terminal.title).toBe('DeepSeek Harness') + expect(result.terminal.output).toContain('DEEPSEEK') + expect(result.terminal.output).toContain('Coding agent ready.') + expect(result.terminal.output).toContain('restored prompt') + expect(result.terminal.output).toContain('restored thought') + expect(result.terminal.output).toContain('restored answer') + expect(result.terminal.output).toContain('write tests') + expect(result.terminal.output).toContain('↑1.3k ↓42') + + result.agent.status = 'running' + result.ctx.emit('agent/status', result.agent, 'running') + result.session.append('user/message', { content: [{ type: 'text', text: ' ' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + result.session.append('steering/message', { turn: 2, content: [{ type: 'text', text: 'steering note' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + result.session.append('steering/message', { turn: 2, content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + result.session.append('context/message', { content: [{ type: 'text', text: 'user context' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + result.session.append('context/message', { content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + result.session.append('prompt/blocked', { content: [{ type: 'text', text: 'blocked' }], source: { kind: 'user' }, reason: 'test policy' }) + appendAssistant(result.session, []) + result.session.append('turn/end', { turn: 9, reason: { kind: 'aborted' } }) + result.session.append('turn/end', { turn: 10, reason: { kind: 'completed' } }) + result.session.append('step/start', { turn: 11, step: 0 }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-start', index: 0, blockType: 'reasoning' }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'reasoning-delta', index: 0, text: 'live thought' }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'reasoning-delta', index: 9, text: 'unannounced thought' }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-end', index: 0, block: { type: 'reasoning', text: 'live thought complete' } }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-start', index: 1, blockType: 'text' }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'text-delta', index: 1, text: 'live answer' }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-end', index: 1, block: { type: 'text', text: 'live answer done' } }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-start', index: 2, blockType: 'tool-call' }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-end', index: 2, block: { type: 'tool-call', id: 'stream-tool' as never, name: 'tool', arguments: '{}' } }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'tool-call-delta', index: 2, id: 'stream-tool' as never, argumentsDelta: '{}' }, + }) + result.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'usage', usage: { inputTokens: 1, outputTokens: 2 } }, + }) + await tick() + expect(result.terminal.output).toContain('live thought') + result.terminal.send('\x12') + await tick() + appendAssistant(result.session, [{ type: 'text', text: 'final live answer' }], { inputTokens: 500, outputTokens: 8 }) + await tick() + + expect(result.terminal.output).toContain('Working') + expect(result.terminal.output).toContain('Steering') + expect(result.terminal.output).toContain('user context') + expect(result.terminal.output).toContain('Prompt blocked') + expect(result.terminal.output).toContain('Turn cancelled') + expect(result.terminal.output).toContain('final live answer') + expect(result.terminal.output).toContain('↑1.8k ↓50') + expect(result.terminal.progress).toContain(true) + + result.session.append('assistant/chunk', { + turn: 3, + step: 0, + chunk: { type: 'text-delta', index: 0, text: 'cleared stream' }, + }) + result.terminal.send('/clear') + result.terminal.send('\r') + appendAssistant(result.session, [{ type: 'text', text: 'answer after clear' }]) + await tick() + expect(result.terminal.output).toContain('answer after clear') + + result.agent.status = 'idle' + result.ctx.emit('agent/status', result.agent, 'idle') + await tick() + expect(result.terminal.progress.at(-1)).toBe(false) + await dispose(result) + expect(result.terminal.stopped).toBe(1) + expect(result.terminal.drainInput).toHaveBeenCalledWith(100, 20) + }) + + it('renders the ANSI palette and every markdown/content style', async () => { + const result = await setup({ + config: { color: true }, + beforeMount(session) { + session.append('user/message', { + content: [ + { type: 'text', text: '# Heading\n\n[link](https://example.com) `code`\n\n```ts\nconst x = 1\n```\n\n> quote\n\n---\n\n- item\n\n**bold** *italic* ~~strike~~' }, + { type: 'tool-call', id: 'nested' as never, name: 'nested_tool', arguments: '{}' }, + { type: 'tool-result', toolCallId: 'nested' as never, content: [{ type: 'reasoning', text: 'nested result' }] }, + { type: 'future-block' } as never, + {} as never, + ], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + appendAssistant(session, [ + { type: 'reasoning', text: 'styled reasoning' }, + { type: 'text', text: 'styled answer' }, + ], { inputTokens: 2_000_000, outputTokens: 1_500_000 }) + session.append('todo/write', { todos: [ + { content: 'done', status: 'completed' }, + { content: 'active', status: 'in_progress' }, + { content: 'later', status: 'pending' }, + ] }) + }, + }) + result.terminal.send('/') + await tick() + result.terminal.send('zz') + await tick() + result.terminal.send('\x0c') + await tick() + + expect(result.terminal.output).toContain('\x1b[') + expect(result.terminal.output).toContain('Heading') + expect(result.terminal.output).toContain('nested_tool({})') + expect(result.terminal.output).toContain('nested result') + expect(result.terminal.output).toContain('[future-block]') + expect(result.terminal.output).toContain('[content]') + expect(result.terminal.output).toContain('↑2.0m ↓1.5m') + await dispose(result) + }) + + it('suppresses stale replay chunks and does not duplicate editor history on rebuild', async () => { + const result = await setup({ + beforeMount(session) { + appendUser(session, 'first prompt') + appendUser(session, 'second prompt') + session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'text-delta', index: 0, text: 'stale partial response' }, + }) + }, + }) + + expect(result.terminal.output).not.toContain('stale partial response') + result.terminal.send('/reasoning') + result.terminal.send('\r') + result.terminal.send('\x1b[A') + result.terminal.send('\x1b[A') + result.terminal.send('\x1b[A') + result.terminal.send('\r') + expect(result.agent.sent).toEqual([[{ type: 'text', text: 'first prompt' }]]) + await dispose(result) + }) + + it('formats large token totals and cwd variants', async () => { + const homeResult = await setup({ + cwd: process.env.HOME ?? process.cwd(), + beforeMount(session) { + appendAssistant(session, [{ type: 'text', text: 'home' }], { inputTokens: 25_000, outputTokens: 10_000 }) + }, + }) + expect(homeResult.terminal.output).toContain('~ ↑25k ↓10k') + await dispose(homeResult) + + const unsetResult = await setup({ cwd: null }) + expect(unsetResult.terminal.output).toContain('cwd unset') + await dispose(unsetResult) + + const outsideResult = await setup({ cwd: '/opt' }) + expect(outsideResult.terminal.output).toContain('/opt') + await dispose(outsideResult) + }) + + it('sends, steers, handles commands, global keys, and disposed-agent input', async () => { + const result = await setup() + + result.terminal.send('do the work') + result.terminal.send('\r') + expect(result.agent.sent).toEqual([[{ type: 'text', text: 'do the work' }]]) + + result.terminal.send(' ') + result.terminal.send('\r') + + result.agent.status = 'running' + result.terminal.send('steer it') + result.terminal.send('\r') + expect(result.agent.steered).toEqual([[{ type: 'text', text: 'steer it' }]]) + + result.terminal.send('\x1b') + result.terminal.send('\x04') + result.terminal.send('\x03') + result.terminal.send('\x12') + result.terminal.send('\x0f') + result.terminal.send('/cancel') + result.terminal.send('\r') + expect(result.agent.cancelled).toContain('cancelled from terminal') + + result.agent.status = 'idle' + for (const command of ['/help', '/reasoning', '/tools', '/redraw']) { + result.terminal.send(command) + result.terminal.send('\r') + await tick() + } + for (const command of ['/clear', '/cancel', '/wat']) { + result.terminal.send(command) + result.terminal.send('\r') + } + await tick() + result.terminal.send('draft') + result.terminal.send('\x03') + result.terminal.send('\x04') + await tick() + + expect(result.terminal.output).toContain('Keyboard shortcuts') + expect(result.terminal.output).toContain('Reasoning blocks') + expect(result.terminal.output).toContain('Tool cards') + expect(result.terminal.output).toContain('already idle') + expect(result.terminal.output).toContain('Unknown command') + expect(result.exit).toHaveBeenCalledWith(0) + await result.controller.dispose() + await result.ctx.fiber.dispose() + + const ctrlCExit = await setup() + ctrlCExit.terminal.send('\x03') + await tick() + expect(ctrlCExit.exit).toHaveBeenCalledWith(0) + await ctrlCExit.controller.dispose() + await ctrlCExit.ctx.fiber.dispose() + + const disposedAgent = await setup() + disposedAgent.agent.status = 'disposed' + disposedAgent.terminal.send('late input') + disposedAgent.terminal.send('\r') + await tick() + expect(disposedAgent.terminal.output).toContain('is disposed') + await dispose(disposedAgent) + }) + + it('cancels before /exit while running and handles agent errors/disposal', async () => { + const result = await setup({ status: 'running' }) + result.terminal.send('/exit') + result.terminal.send('\r') + await tick() + expect(result.agent.cancelled).toContain('terminal exit requested') + expect(result.exit).toHaveBeenCalledWith(0) + + const events = await setup() + const unrelatedSession = events.ctx.sessions.create(SessionId('unrelated-session')) + const unrelatedAgent = { ...events.agent, id: AgentId('unrelated'), session: unrelatedSession } + unrelatedSession.append('todo/write', { todos: [{ content: 'hidden', status: 'pending' }] }) + events.ctx.emit('agent/status', unrelatedAgent, 'running') + events.ctx.emit('agent/error', unrelatedAgent, 1, 1, new Error('hidden error')) + events.ctx.emit('agent/disposed', unrelatedAgent) + events.ctx.emit('agent/error', events.agent, 3, 2, new Error('live failure')) + events.session.append('turn/end', { turn: 3, reason: { kind: 'error', step: 2, message: 'live failure' } }) + events.session.append('turn/end', { turn: 4, reason: { kind: 'error', step: 1, message: 'durable failure' } }) + events.session.append('turn/end', { turn: 5, reason: { kind: 'aborted', reason: 'stopped' } }) + events.session.append('turn/end', { turn: 6, reason: { kind: 'max-tokens' } }) + events.session.append('turn/end', { turn: 7, reason: { kind: 'rejected', reason: 'policy' } }) + events.session.append('turn/end', { turn: 8, reason: { kind: 'interrupted' } }) + events.ctx.emit('agent/disposed', events.agent) + await tick() + expect(events.terminal.output).toContain('live failure') + expect(events.terminal.output).toContain('durable failure') + expect(events.terminal.output).toContain('stopped') + expect(events.terminal.output).toContain('output-token limit') + expect(events.terminal.output).toContain('Turn rejected') + expect(events.terminal.output).toContain('previous process ended') + expect(events.terminal.output).toContain('was disposed') + await dispose(events) + }) +}) + +describe('tool cards and surface replay', () => { + const tools: Record = { + bash: { + name: 'bash', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ card: 'terminal', title: 'printf hello', description: 'Run command', cwd: '/tmp' }), + presentResult: () => ({ card: 'terminal', output: 'hello\nworld\nthird', exitCode: 0 }), + }, + signal: { + name: 'signal', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ card: 'terminal', title: 'sleep 10' }), + presentResult: () => ({ card: 'terminal', signal: 'SIGTERM' }), + }, + edit: { + name: 'edit', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ + card: 'diff', + title: 'Edit files', + diffs: [ + { path: 'a.txt', oldText: 'old', newText: 'new' }, + { path: 'b.txt', oldText: 'before', newText: 'after' }, + ], + }), + presentResult: () => ({ card: 'diff', diffs: [{ path: 'a.txt', oldText: null, newText: 'created' }] }), + }, + generic: { + name: 'generic', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ card: 'generic', title: 'Inspect value', rawInput: { alpha: 1 } }), + presentResult: () => ({ card: 'generic', title: 'Inspected', content: [{ type: 'text', text: 'result text' }] }), + }, + throwing: { + name: 'throwing', description: '', parameters: {}, execute: async () => [], + presentCall: () => { throw new Error('call presenter boom') }, + presentResult: () => { throw new Error('result presenter boom') }, + }, + rawTerminal: { + name: 'rawTerminal', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ card: 'terminal', title: 'raw command' }), + }, + undefinedViews: { + name: 'undefinedViews', description: '', parameters: {}, execute: async () => [], + presentCall: () => undefined, + presentResult: () => undefined, + }, + empty: { + name: 'empty', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ card: 'generic', title: 'Empty card' }), + }, + terminalResult: { + name: 'terminalResult', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ card: 'generic', title: 'Becomes terminal' }), + presentResult: () => ({ card: 'terminal', output: 'converted terminal' }), + }, + symbolic: { + name: 'symbolic', description: '', parameters: {}, execute: async () => [], + presentCall: () => ({ card: 'generic', title: 'Symbol input', rawInput: Symbol('input') }), + }, + } + + it('uses terminal, diff, generic, fallback, and collapsed tool presentations', async () => { + const result = await setup({ tools, config: { maxToolOutputLines: 1 } }) + const calls = [ + ['c1', 'bash', '{"command":"printf hello"}'], + ['c2', 'signal', '{}'], + ['c3', 'edit', '{}'], + ['c4', 'generic', '{}'], + ['c5', 'throwing', '{}'], + ['c6', 'unknown', 'not-json'], + ['c7', 'rawTerminal', '{"value":"raw"}'], + ['c8', 'undefinedViews', '{"value":8}'], + ['c10', 'empty', '{}'], + ['c11', 'terminalResult', '{}'], + ['c12', 'symbolic', '{}'], + ] as const + appendAssistant(result.session, [ + { type: 'text', text: 'Calling tools' }, + ...calls.map(([id, name, args]) => ({ + type: 'tool-call' as const, id: id as never, name, arguments: args, + })), + ]) + for (const [id, name, args] of calls) { + result.session.append('tool/call', { turn: 1, step: 0, callId: id as never, name, arguments: args }) + } + await tick() + expect(result.terminal.output).toContain('$ raw command') + result.terminal.send('/reasoning') + result.terminal.send('\r') + await tick() + expect(result.terminal.output).toContain('call presenter boom') + expect(result.terminal.output).toContain('Symbol(input)') + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c1' as never, content: [{ type: 'text', text: 'raw bash' }], isError: false, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c2' as never, content: [{ type: 'text', text: 'stopped' }], isError: true, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c3' as never, content: [{ type: 'text', text: 'done' }], isError: false, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c4' as never, content: [{ type: 'text', text: 'raw generic' }], isError: false, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c5' as never, content: [{ type: 'text', text: 'raw throwing' }], isError: false, + meta: { value: 1 }, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c7' as never, + content: [ + { type: 'tool-call', id: 'inner' as never, name: 'inner', arguments: '{}' }, + { type: 'tool-result', toolCallId: 'inner' as never, content: [{ type: 'text', text: 'nested output' }] }, + { type: 'future-result' } as never, + ], + isError: false, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c8' as never, content: [{ type: 'text', text: '\nundefined presenter output\n\nkept tail\n' }], isError: false, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'c11' as never, content: [{ type: 'text', text: '\nconverted terminal\n\nfinished\n' }], isError: false, + }, { surfaceOp: 'append' }) + result.session.append('tool/result', { + turn: 1, step: 0, callId: 'orphan' as never, content: [{ type: 'text', text: 'orphan result' }], isError: false, + }, { surfaceOp: 'append' }) + await tick() + + const output = result.terminal.output + expect(output).toContain('Run command') + expect(output).toContain('printf hello') + expect(output).toContain('more lines') + expect(output).toContain('SIGTERM') + expect(output).toContain('Edit files') + expect(output).toContain('Inspected') + expect(output).toContain('result text') + expect(output).toContain('Presenter failed') + expect(output).toContain('not-json') + expect(output).toContain('nested output') + expect(output).toContain('[future-result]') + expect(output).toContain('undefined presenter output') + expect(output).toContain('Empty card') + expect(output).toContain('converted terminal') + expect(output).toContain('orphan result') + + result.terminal.send('/redraw') + result.terminal.send('\r') + await tick() + result.terminal.send('\x0f') + await tick() + expect(result.terminal.output).toContain('world') + expect(result.terminal.output).toContain('+ created') + await dispose(result) + }) + + it('rebuilds after a surface replacement and hides shadowed tool calls', async () => { + const result = await setup({ tools }) + appendUser(result.session, 'old prompt') + const assistant = result.session.append('assistant/message', { + turn: 1, + step: 0, + content: [{ type: 'tool-call', id: 'old-call' as never, name: 'bash', arguments: '{}' }], + }, { surfaceOp: 'append' }) + result.session.append('tool/call', { + turn: 1, step: 0, callId: 'old-call' as never, name: 'bash', arguments: '{}', + }) + const toolResult = result.session.append('tool/result', { + turn: 1, step: 0, callId: 'old-call' as never, content: [{ type: 'text', text: 'old output' }], isError: false, + }, { surfaceOp: 'append' }) + const start = result.session.surface.nodes[0]?.seq as number + result.session.append('context/message', { + content: [{ type: 'text', text: 'summary replacement' }], + source: { kind: 'plugin', plugin: 'compact' }, + }, { + surfaceOp: { op: 'replace', start, end: toolResult.seq }, + sourceEventSeqs: [start, assistant.seq, toolResult.seq], + }) + await tick() + + result.terminal.resize(89) + await tick() + const lastFullRender = result.terminal.output.slice(result.terminal.output.lastIndexOf('\x1b[2J')) + expect(lastFullRender).toContain('summary replacement') + expect(lastFullRender).not.toContain('old output') + await dispose(result) + }) +}) + +describe('TUI user-interaction dialogs', () => { + it('answers single-select, multi-select, custom, and optionless questions', async () => { + const result = await setup({ config: { maxQuestionOptions: 1 } }) + + const single = result.ctx.userInteraction.ask({ + questions: [{ + id: 'mode', header: 'Mode', question: 'Choose a mode', + options: [{ label: 'Safe', description: 'Use checks' }, { label: 'Fast' }], + }], + }) + await tick() + expect(result.terminal.output).toContain('Choose a mode') + expect(result.terminal.output).toContain('1/2') + result.terminal.send('\x1b[B') + result.terminal.send('\r') + await expect(single).resolves.toEqual({ answers: [{ id: 'mode', selected: ['Fast'] }] }) + + const multi = result.ctx.userInteraction.ask({ + questions: [{ id: 'targets', question: 'Pick targets', multiSelect: true, options: [{ label: 'Code' }, { label: 'Docs' }] }], + }) + await tick() + result.terminal.send(' ') + result.terminal.send('\x1b[B') + result.terminal.send(' ') + result.terminal.send('\r') + await expect(multi).resolves.toEqual({ answers: [{ id: 'targets', selected: ['Code', 'Docs'] }] }) + + const custom = result.ctx.userInteraction.ask({ + questions: [{ id: 'other', question: 'Choose or type', options: [{ label: 'Default' }] }], + }) + await tick() + result.terminal.send('c') + result.terminal.send('my choice') + result.terminal.send('\r') + await expect(custom).resolves.toEqual({ answers: [{ id: 'other', selected: [], custom: 'my choice' }] }) + + const free = result.ctx.userInteraction.ask({ questions: [{ id: 'note', question: 'Add a note' }] }) + await tick() + result.terminal.send('\r') + await tick() + expect(result.terminal.output).toContain('Enter an answer before submitting') + result.terminal.send('ship it') + result.terminal.send('\r') + await expect(free).resolves.toEqual({ answers: [{ id: 'note', selected: [], custom: 'ship it' }] }) + await dispose(result) + }) + + it('handles option wrapping, deselection errors, and returning from custom input', async () => { + const result = await setup({ config: { color: true } }) + const single = result.ctx.userInteraction.ask({ + questions: [{ id: 'single', question: 'Single options', options: [{ label: 'One' }, { label: 'Two' }] }], + }) + const singleRejected = expect(single).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + await tick() + expect(result.terminal.output).toContain('Two') + result.terminal.send('\x03') + await singleRejected + + const answer = result.ctx.userInteraction.ask({ + questions: [{ + id: 'options', + question: 'Exercise options', + multiSelect: true, + options: [{ label: 'One', description: 'first' }, { label: 'Two' }], + }], + }) + const rejected = expect(answer).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + await tick() + result.terminal.send('\x1b[A') + result.terminal.send('\x1b[B') + result.terminal.send('\x1b[B') + result.terminal.send('\x1b[A') + result.terminal.send(' ') + await tick() + result.terminal.send('x') + result.terminal.send(' ') + result.terminal.send('\r') + await tick() + expect(result.terminal.output).toContain('Select at least one option') + result.terminal.send('c') + await tick() + result.terminal.send('\x1b') + await tick() + expect(result.terminal.output).toContain('Space toggle') + result.terminal.send('\x03') + await rejected + await dispose(result) + }) + + it('asks batches in order and rejects cancelled or aborted work', async () => { + const result = await setup() + const preAborted = new AbortController() + preAborted.abort() + await expect(result.ctx.userInteraction.ask({ + questions: [{ id: 'pre-aborted', question: 'Already cancelled?' }], + signal: preAborted.signal, + })).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + + const batch = result.ctx.userInteraction.ask({ + questions: [ + { id: 'first', question: 'First?', options: [{ label: 'Yes' }] }, + { id: 'second', question: 'Second?' }, + ], + }) + await tick() + result.terminal.send('\r') + await tick() + expect(result.terminal.output).toContain('Second?') + result.terminal.send('done') + result.terminal.send('\r') + await expect(batch).resolves.toEqual({ answers: [ + { id: 'first', selected: ['Yes'] }, + { id: 'second', selected: [], custom: 'done' }, + ] }) + + const cancelled = result.ctx.userInteraction.ask({ questions: [{ id: 'cancel', question: 'Cancel?' }] }) + const cancelledExpectation = expect(cancelled).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + await tick() + result.terminal.send('\x1b') + await cancelledExpectation + + const controller = new AbortController() + const active = result.ctx.userInteraction.ask({ questions: [{ id: 'active', question: 'Active?' }], signal: controller.signal }) + const queuedController = new AbortController() + const queued = result.ctx.userInteraction.ask({ questions: [{ id: 'queued', question: 'Queued?' }], signal: queuedController.signal }) + const activeExpectation = expect(active).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + const queuedExpectation = expect(queued).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + await tick() + queuedController.abort() + controller.abort() + await activeExpectation + await queuedExpectation + await dispose(result) + }) + + it('rejects active and queued dialogs on disposal', async () => { + const result = await setup() + const active = result.ctx.userInteraction.ask({ questions: [{ id: 'active', question: 'Active?' }] }) + const queued = result.ctx.userInteraction.ask({ questions: [{ id: 'queued', question: 'Queued?' }] }) + const activeExpectation = expect(active).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + const queuedExpectation = expect(queued).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + await tick() + await result.controller.dispose() + await activeExpectation + await queuedExpectation + await expect(result.ctx.userInteraction.ask({ questions: [{ id: 'late', question: 'Late?' }] })) + .rejects.toMatchObject({ code: 'NO_PROVIDER' }) + await result.ctx.fiber.dispose() + }) +}) + +describe('terminal mounting', () => { + it('starts immediately when the configured agent already exists', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.provide('tools', { get: () => undefined } as never) + const session = ctx.sessions.create(SessionId('mounted-session')) + ctx.agents.register({ + id: AgentId('main'), options: {}, session, status: 'idle', ctx, + send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + }) + const terminal = new FakeTerminal() + mountTui(ctx, { color: false }, { terminal, exit: vi.fn() }) + await tick() + expect(terminal.started).toBe(1) + await ctx.fiber.dispose() + }) + + it('waits for its configured agent before starting the TUI', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.provide('tools', { get: () => undefined } as never) + const terminal = new FakeTerminal() + mountTui(ctx, { agent: 'main', color: false }, { terminal, exit: vi.fn() }) + expect(terminal.started).toBe(0) + + const otherSession = ctx.sessions.create(SessionId('other-session')) + ctx.agents.register({ + id: AgentId('other'), options: {}, session: otherSession, status: 'idle', ctx, + send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + }) + expect(terminal.started).toBe(0) + + const session = ctx.sessions.create(SessionId('late-session')) + const agent = { + id: AgentId('main'), options: {}, session, status: 'idle', ctx, + send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + } as Agent + ctx.agents.register(agent) + await tick() + expect(terminal.started).toBe(1) + await ctx.fiber.dispose() + }) + + it('rolls back providers, listeners, and terminal state when startup fails', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.provide('tools', { get: () => undefined } as never) + const session = ctx.sessions.create(SessionId('failed-start-session')) + ctx.agents.register({ + id: AgentId('main'), options: {}, session, status: 'running', ctx, + send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + }) + const terminal = new FakeTerminal() + terminal.start = () => { throw new Error('terminal startup failed') } + + expect(() => createTuiChat(ctx, { color: false }, { terminal, exit: vi.fn() })) + .toThrow('terminal startup failed') + expect(terminal.stopped).toBe(1) + expect(terminal.progress).toEqual([false, true, false]) + await expect(ctx.userInteraction.ask({ questions: [{ id: 'late', question: 'Late?' }] })) + .rejects.toMatchObject({ code: 'NO_PROVIDER' }) + session.append('assistant/chunk', { + turn: 1, + step: 0, + chunk: { type: 'text-delta', index: 0, text: 'must not render' }, + }) + await tick() + expect(terminal.output).not.toContain('must not render') + await ctx.fiber.dispose() + }) + + it('throws when createTuiChat is called without the configured agent', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.provide('tools', { get: () => undefined } as never) + const runtime: TuiRuntime = { terminal: new FakeTerminal(), exit: vi.fn() } + expect(() => createTuiChat(ctx, { agent: 'missing' }, runtime)).toThrow('is not running') + await ctx.fiber.dispose() + }) +}) diff --git a/packages/ui/tui/tsconfig.json b/packages/ui/tui/tsconfig.json new file mode 100644 index 0000000000..f3a85f76e4 --- /dev/null +++ b/packages/ui/tui/tsconfig.json @@ -0,0 +1,33 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cordis" + }, + { + "path": "../../../vendor/schemastery" + }, + { + "path": "../../core/agent" + }, + { + "path": "../../core/session" + }, + { + "path": "../../llm/llm" + }, + { + "path": "../../core/tools" + }, + { + "path": "../user-interaction" + } + ] +} diff --git a/packages/ui/user-interaction/README.md b/packages/ui/user-interaction/README.md index bd5c5281ca..b758ad09e0 100644 --- a/packages/ui/user-interaction/README.md +++ b/packages/ui/user-interaction/README.md @@ -21,7 +21,7 @@ When an answer includes `custom`, `selected` is empty; custom text is an overrid ## Role -This is the interface package. Model-facing consumers such as `@deepseek-ai/dsh-tool-ask-user` depend on this seam; UI front doors such as the `stdio-agent` readline module and the `acp` bridge provide the provider. The loop stays unchanged: a tool call awaits a promise, and the tool result resumes the normal agent loop. +This is the interface package. Model-facing consumers such as `@deepseek-ai/dsh-tool-ask-user` depend on this seam; UI front doors such as the interactive `dsh-tui`, line-oriented `dsh-stdio`, and structured `dsh-acp` channels provide the provider. The loop stays unchanged: a tool call awaits a promise, and the tool result resumes the normal agent loop. ## Model Experience diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index b1a3a78030..e4a9019a7f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -583,6 +583,9 @@ importers: '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools + '@deepseek-ai/dsh-tui': + specifier: workspace:^ + version: link:../../ui/tui '@deepseek-ai/dsh-user-interaction': specifier: workspace:^ version: link:../../ui/user-interaction @@ -1673,6 +1676,37 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/ui/tui: + dependencies: + '@earendil-works/pi-tui': + specifier: 0.80.7 + version: 0.80.7 + schemastery: + specifier: ^3.18.0 + version: 3.18.0 + devDependencies: + '@cordisjs/plugin-loader': + specifier: workspace:^ + version: link:../../../vendor/loader + '@deepseek-ai/dsh-agent': + specifier: workspace:^ + version: link:../../core/agent + '@deepseek-ai/dsh-llm': + specifier: workspace:^ + version: link:../../llm/llm + '@deepseek-ai/dsh-session': + specifier: workspace:^ + version: link:../../core/session + '@deepseek-ai/dsh-tools': + specifier: workspace:^ + version: link:../../core/tools + '@deepseek-ai/dsh-user-interaction': + specifier: workspace:^ + version: link:../user-interaction + cordis: + specifier: ^4.0.0-rc.6 + version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader) + packages/ui/user-approval: dependencies: schemastery: @@ -2519,6 +2553,10 @@ packages: engines: {node: '>=22.19.0'} hasBin: true + '@earendil-works/pi-tui@0.80.7': + resolution: {integrity: sha512-1B2++fLZfgI3XMzW2BTpuDuam2uyHnUUEmsOvi5R0Ne9RAt59WjFV0G8ozX6l1Xafa9P5Y3eT4aDtRr/v/CUTA==} + engines: {node: '>=22.19.0'} + '@emnapi/core@1.10.0': resolution: {integrity: sha512-yq6OkJ4p82CAfPl0u9mQebQHKPJkY7WrIuk205cTYnYe+k2Z8YBh11FrbRG/H6ihirqcacOgl2BIO8oyMQLeXw==} @@ -4293,6 +4331,10 @@ packages: resolution: {integrity: sha512-zV/5HKTfCeKWnxG0Dmrw51hEWFGfcF2xiXqcA3+J90WDuP0SvoiSO5ORvcBsifmx/FoIjgQN3oNOGaQ5PhLFkg==} engines: {node: '>=18'} + get-east-asian-width@1.6.0: + resolution: {integrity: sha512-QRbvDIbx6YklUe6RxeTeleMR0yv3cYH6PsPZHcnVn7xv7zO1BHN8r0XETu8n6Ye3Q+ahtSarc3WgtNWmehIBfA==} + engines: {node: '>=18'} + get-intrinsic@1.3.0: resolution: {integrity: sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==} engines: {node: '>= 0.4'} @@ -4773,6 +4815,11 @@ packages: engines: {node: '>= 20'} hasBin: true + marked@18.0.5: + resolution: {integrity: sha512-S6GcvALHg6K4ohtu4E7x0a1AqhAjp6cV8KhLSyN9qVapnzJkusVBxZRcIU9AeYsbe6P1hKDusSbEOzGyyuce6w==} + engines: {node: '>= 20'} + hasBin: true + math-intrinsics@1.1.0: resolution: {integrity: sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==} engines: {node: '>= 0.4'} @@ -6157,6 +6204,11 @@ snapshots: - ws - zod + '@earendil-works/pi-tui@0.80.7': + dependencies: + get-east-asian-width: 1.6.0 + marked: 18.0.5 + '@emnapi/core@1.10.0': dependencies: '@emnapi/wasi-threads': 1.2.1 @@ -7861,6 +7913,8 @@ snapshots: transitivePeerDependencies: - supports-color + get-east-asian-width@1.6.0: {} + get-intrinsic@1.3.0: dependencies: call-bind-apply-helpers: 1.0.2 @@ -8308,6 +8362,8 @@ snapshots: marked@16.4.2: {} + marked@18.0.5: {} + math-intrinsics@1.1.0: {} mdast-util-find-and-replace@3.0.2: diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 31df485e1d..cbe9272ac1 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -407,7 +407,7 @@ const APP_EXAMPLES = [ title: 'Coding Agent App Composition', label: 'examples/coding-agent', config: 'examples/coding-agent/cordis.yml', - summary: 'The coding REPL demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', + summary: 'The coding-agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', }, { id: 'cordis', @@ -435,7 +435,7 @@ function renderAppExpansion(lines: string[], appNode: string, pluginName: string lines.push(` ${appNode} --> ${agentCore}["@deepseek-ai/dsh-agent-spine-demo"]`) lines.push(` ${appNode} --> ${jsonl}["@deepseek-ai/dsh-session-persistence-jsonl"]`) if (pluginName === '@deepseek-ai/dsh-stdio-demo') { - lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["readline UI
console logger
pre-created main agent"]`) + lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent"]`) } else if (pluginName === '@deepseek-ai/dsh-acp-demo') { lines.push(` ${appNode} --> ${nodeId('frontdoor', 'acp')}["@deepseek-ai/dsh-acp
JSON-RPC stdio bridge
sessions created by client"]`) } diff --git a/tsconfig.build.json b/tsconfig.build.json index 3a57169005..7655069a29 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -61,6 +61,7 @@ { "path": "./packages/ui/app-boot" }, { "path": "./packages/ui/jsonrpc" }, { "path": "./packages/examples/jsonrpc-demo" }, + { "path": "./packages/ui/tui" }, { "path": "./packages/ui/stdio" }, { "path": "./packages/examples/stdio-demo" }, { "path": "./packages/support/llm-replay" }, diff --git a/tsconfig.json b/tsconfig.json index 6585a987d6..1f18ea3a55 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -72,6 +72,7 @@ { "path": "./packages/ui/app-boot" }, { "path": "./packages/ui/jsonrpc" }, { "path": "./packages/examples/jsonrpc-demo" }, + { "path": "./packages/ui/tui" }, { "path": "./packages/ui/stdio" }, { "path": "./packages/examples/stdio-demo" }, { "path": "./packages/support/llm-replay" }, From 12b7ac67bacd1b05e76b124163d195d9bbbde72a Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 17 Jul 2026 16:44:25 +0800 Subject: [PATCH 154/323] fix(ui): surface declarative startup failures --- docs/cordis-catalog/events.md | 32 ++++-- docs/cordis-catalog/services.md | 4 +- docs/event-producer-consumer.md | 25 +++-- examples/coding-agent/README.md | 2 +- .../tests/tui-keyless-smoke.e2e.ts | 33 ++++-- .../cordis/tool-cordis/src/api-catalog.ts | 8 ++ packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/index.ts | 17 ++- .../tests/config-session-id.spec.ts | 80 ++++++++++++- packages/core/agent/README.md | 7 +- packages/core/agent/src/index.ts | 95 ++++++++++++++++ packages/core/agent/src/types.ts | 9 ++ packages/core/agent/tests/agent.spec.ts | 106 +++++++++++++++++- packages/examples/stdio-demo/README.md | 4 +- packages/ui/stdio/README.md | 2 +- packages/ui/stdio/src/index.ts | 16 ++- packages/ui/stdio/tests/stdio.spec.ts | 38 ++++++- packages/ui/tui/README.md | 2 +- packages/ui/tui/src/index.ts | 29 +++-- packages/ui/tui/tests/tui.spec.ts | 45 ++++++++ 20 files changed, 484 insertions(+), 72 deletions(-) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index ede449cb1c..ed0a5554e5 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:283`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:292`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -59,7 +59,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:202`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:211`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -71,7 +71,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:212`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:221`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -83,7 +83,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:167`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:176`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -95,7 +95,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:224`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:233`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -107,7 +107,7 @@ Compose request-only messages placed before derived history. The frozen result i Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:239`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:248`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -119,7 +119,17 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:180`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:189`](../../packages/core/agent/src/types.ts) + +### `agent/start-failed` — emit + +Declarative startup failed before an agent could be published. Programmatic `ctx.agents.create()` / `resume()` calls report failure through rejection; this event covers the fire-and-forget config path. + +```ts cordis-catalog +'agent/start-failed'(agentId: AgentId, error: Error): void +``` + +Source: [`packages/core/agent/src/types.ts:157`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -131,7 +141,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:157`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:166`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -143,7 +153,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:250`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:259`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -155,7 +165,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:260`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:269`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -167,7 +177,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:270`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:279`](../../packages/core/agent/src/types.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 18e00b7904..aa2289ff0d 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -32,13 +32,15 @@ async resume(options: ResumeAgentOptions): Promise register(agent: Agent): () => void enter(agent: Agent): () => void announce(agent: Agent): void +reportStartFailure(id: AgentId, error: Error): () => void +getStartFailure(id: AgentId): Error | undefined get(id: AgentId): Agent | undefined list(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:133`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:187`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index b67788ea6b..de932e0999 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,20 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent`](../packages/core/agent), [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`tui`](../packages/ui/tui) | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:292`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`tui`](../packages/ui/tui) | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:211`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:221`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:176`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:233`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:248`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:189`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/start-failed` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent`](../packages/core/agent) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:166`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio), [`tui`](../packages/ui/tui) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:259`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:269`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:279`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index c1c4747a22..9fdadf809d 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -23,7 +23,7 @@ Each run starts a fresh session by default (its event log lands under `./.sessio RESUME_SESSION_ID= pnpm run demo:repl ``` -The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`); unset, the agent starts a new session. A missing or unreadable id starts no `main` agent, so unset it or choose an existing session id. +The id is wired through `cordis.yml` (`resumeSessionId: !!js process.env.RESUME_SESSION_ID`); unset, the agent starts a new session. A missing or unreadable id starts no `main` agent and emits `agent/start-failed`; both terminal front doors print the failure and exit nonzero, so unset it or choose an existing session id. ## Code Mode diff --git a/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts b/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts index a1057ba02f..f5f9c5db36 100644 --- a/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts +++ b/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts @@ -13,7 +13,7 @@ const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) const PTY_DRIVER = String.raw` import errno, os, pty, select, signal, sys, time -node, tsx_loader, bin_script, config_path, tsconfig_path, cwd = sys.argv[1:] +node, tsx_loader, bin_script, config_path, tsconfig_path, cwd, resume_session_id = sys.argv[1:] env = os.environ.copy() env.update({ "DEEPSEEK_API_KEY": "keyless-tui-no-call", @@ -21,6 +21,8 @@ env.update({ "DSH_AGENTS_HOME": os.path.join(cwd, ".agents"), "TSX_TSCONFIG_PATH": tsconfig_path, }) +if resume_session_id: + env["RESUME_SESSION_ID"] = resume_session_id pid, fd = pty.fork() if pid == 0: os.chdir(cwd) @@ -53,15 +55,23 @@ if status is None: os.kill(pid, signal.SIGKILL) _, status = os.waitpid(pid, 0) sys.stdout.buffer.write(output) -if not sent_exit: - sys.stderr.write("TUI did not render its welcome marker before timeout\n") - sys.exit(124) -if not os.WIFEXITED(status) or os.WEXITSTATUS(status) != 0: - sys.stderr.write("TUI child did not exit cleanly\n") - sys.exit(125) +if resume_session_id: + if b'ui-tui: agent "main" failed to start:' not in output: + sys.stderr.write("TUI did not render the startup failure before timeout\n") + sys.exit(126) + if not os.WIFEXITED(status) or os.WEXITSTATUS(status) != 1: + sys.stderr.write("TUI startup failure did not exit with status 1\n") + sys.exit(127) +else: + if not sent_exit: + sys.stderr.write("TUI did not render its welcome marker before timeout\n") + sys.exit(124) + if not os.WIFEXITED(status) or os.WEXITSTATUS(status) != 0: + sys.stderr.write("TUI child did not exit cleanly\n") + sys.exit(125) ` -async function runTuiLoaderSmoke(): Promise { +async function runTuiLoaderSmoke(resumeSessionId = ''): Promise { const cwd = await mkdtemp(join(tmpdir(), 'coding-tui-smoke-')) try { return await new Promise((resolve, reject) => { @@ -74,6 +84,7 @@ async function runTuiLoaderSmoke(): Promise { configPath, tsconfigPath, cwd, + resumeSessionId, ], { stdio: ['ignore', 'pipe', 'pipe'] }) let stdout = '' let stderr = '' @@ -98,4 +109,10 @@ describe('coding-agent TUI keyless smoke (real Loader tree in a PTY)', () => { expect(output).toContain('DEEPSEEK') expect(output).toContain('agent REPL ready.') }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('prints a config-resume failure and exits instead of leaving a blank terminal', async () => { + const output = await runTuiLoaderSmoke('missing-session') + expect(output).toContain('ui-tui: agent "main" failed to start:') + expect(output).toContain('missing-session') + }, LOADER_SMOKE_TEST_TIMEOUT_MS) }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 51b4a5155f..1eef429d96 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -71,6 +71,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'register(agent: Agent): () => void', 'enter(agent: Agent): () => void', 'announce(agent: Agent): void', + 'reportStartFailure(id: AgentId, error: Error): () => void', + 'getStartFailure(id: AgentId): Error | undefined', 'get(id: AgentId): Agent | undefined', 'list(): Agent[]', ], @@ -317,6 +319,12 @@ export const EVENT_API: readonly EventApiEntry[] = [ signature: '\'agent/session-start\'(this: Scoped, agent: Agent, source: SessionStartSource): void', summary: 'The session lifecycle began, once before the first turn.', }, + { + name: 'agent/start-failed', + mode: 'emit', + signature: '\'agent/start-failed\'(agentId: AgentId, error: Error): void', + summary: 'Declarative startup failed before an agent could be published.', + }, { name: 'agent/status', mode: 'emit', diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index a07aa5fa70..d46aabac0d 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -79,6 +79,6 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p ## Known Limitations and Deferred Work - **Tool calls within a step execute sequentially** — parallel execution waits on concurrency-safety metadata in the tool contract (see `dsh-tools`). -- **No resume-or-create policy on the config path** — config-driven `create()` starts a fresh `${id}-session-` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning and creates no agent. +- **No resume-or-create policy on the config path** — config-driven `create()` starts a fresh `${id}-session-` every run (`TODO(demo)`), and a config `resumeSessionId` whose resume fails logs a warning, emits and retains `agent/start-failed` while that declaration remains loaded, and creates no agent. - **Config agents have no per-agent persona field or setup hook** — they use the deployment persona; scoped persona/tool composition is available only through the programmatic `ctx.agents.create()` / `resume()` factory options. - **No built-in turn budget** — the default continuation is `continue` whenever a step had tool calls or steering; bounding a runaway turn requires an `agent/turn-continuation` force-stop plugin. diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 6cd66f622c..6d3ef8851a 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -363,18 +363,29 @@ export class AgentLoop extends Service implements AgentFactory { this.create(id, options, cwd === undefined ? {} : { cwd }) continue } - ctx.effect(() => { + ctx.effect(function* (this: AgentLoop) { + let active = true + let releaseFailure = (): void => {} const fiber = ctx.inject(['sessionPersistence'], (childCtx: Context) => { void this.resumeWith(ctx, childCtx.sessionPersistence, { agentId: id, resumeSessionId, agentOptions: options, }).catch((error: unknown) => { + if (!active) return + const failure = new Error(error instanceof Error ? error.message : String(error), { cause: error }) ctx.logger.warn(`agent "${id}": config-driven resume of "${resumeSessionId}" failed: ${String(error)}`) + releaseFailure = ctx.agents.reportStartFailure(id, failure) }) }) - return fiber.dispose - }, `agentLoop.resume(${id})`) + yield fiber.dispose + // Yielded last, disposed first: suppress teardown rejection before the + // deferred persistence child wakes and clear any retained record. + yield () => { + active = false + releaseFailure() + } + }.bind(this), `agentLoop.resume(${id})`) } } diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 8a5d9ce264..f91c7f6585 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -4,10 +4,11 @@ import { mkdtemp, rm } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId, type SessionEvent, type SessionHeader } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' +import SessionPersistence from '@deepseek-ai/dsh-session-persistence' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import AgentLoop, { ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -42,6 +43,72 @@ describe('config-driven session id', () => { await loopFiber.dispose() }) + it('drops an in-flight declarative resume when its owner is disposed', async () => { + const loadStarted = Promise.withResolvers() + const pendingLoad = Promise.withResolvers<{ meta: SessionHeader; events: SessionEvent[] }>() + class DeferredSessionPersistence extends SessionPersistence { + create(_meta: SessionHeader): Promise { return Promise.resolve() } + append(_id: SessionId, _events: readonly SessionEvent[]): Promise { return Promise.resolve() } + load(_id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> { + loadStarted.resolve(undefined) + return pendingLoad.promise + } + list(): Promise { return Promise.resolve([]) } + } + + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + const failures: Error[] = [] + ctx.on('agent/start-failed', (_id, error) => { failures.push(error) }) + const loopFiber = await ctx.plugin(AgentLoop, { + agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], + }) + await ctx.plugin(DeferredSessionPersistence) + await loadStarted.promise + + await loopFiber.dispose() + await Promise.resolve() + expect(failures).toEqual([]) + expect(ctx.agents.getStartFailure(AgentId('main'))).toBeUndefined() + await ctx.fiber.dispose() + }) + + it('normalizes a non-Error declarative resume rejection without duplicating an Error prefix', async () => { + class RejectingSessionPersistence extends SessionPersistence { + create(_meta: SessionHeader): Promise { return Promise.resolve() } + append(_id: SessionId, _events: readonly SessionEvent[]): Promise { return Promise.resolve() } + load(_id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> { + // Third-party backends can reject arbitrary values; this exercises normalization. + // eslint-disable-next-line @typescript-eslint/prefer-promise-reject-errors + return Promise.reject('plain failure') + } + list(): Promise { return Promise.resolve([]) } + } + + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(SessionStore) + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(AgentRegistry) + const failures: Error[] = [] + ctx.on('agent/start-failed', (_id, error) => { failures.push(error) }) + const loopFiber = await ctx.plugin(AgentLoop, { + agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('rejected') }], + }) + await ctx.plugin(RejectingSessionPersistence) + + await vi.waitFor(() => { expect(failures).toHaveLength(1) }) + expect(failures[0]?.message).toBe('plain failure') + expect(failures[0]?.cause).toBe('plain failure') + await loopFiber.dispose() + await ctx.fiber.dispose() + }) + it('config-driven create uses a fresh ${id}-session- per run (restart-safe)', async () => { const root = await mkdtemp(join(tmpdir(), 'dsh-cfg-session-')) dirs.push(root) @@ -137,7 +204,9 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + const failures: Array<{ id: string; error: Error }> = [] + ctx.on('agent/start-failed', (id, error) => { failures.push({ id, error }) }) + const loopFiber = await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) await ctx.plugin(SessionPersistenceJsonl, { root }) @@ -148,6 +217,13 @@ describe('config-driven session id', () => { await new Promise(r => setTimeout(r, 200)) expect(ctx.agents.get(AgentId('main'))).toBeUndefined() expect(warn).toHaveBeenCalledWith(expect.stringContaining('config-driven resume of "does-not-exist" failed')) + expect(failures).toHaveLength(1) + expect(failures[0]?.id).toBe('main') + expect(failures[0]?.error.message).toBe('session "does-not-exist" not found') + expect(failures[0]?.error.cause).toBeInstanceOf(Error) + expect(ctx.agents.getStartFailure(AgentId('main'))).toBe(failures[0]?.error) + await loopFiber.dispose() + expect(ctx.agents.getStartFailure(AgentId('main'))).toBeUndefined() warn.mockRestore() await ctx.fiber.dispose() }) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 5639f30daf..ed91da24ce 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -14,6 +14,9 @@ Tracks live agents so UI, hook, and orchestrator plugins can find them without i - Advanced factory lifecycle: `enter(agent)` publishes without announcing and returns an entry-bound detach; `announce(agent)` emits creation once. Detach during creation dispatch is deferred. Ordinary plugins use `register()`. - `ctx.agents.get(id: AgentId): Agent | undefined` - `ctx.agents.list(): Agent[]` +- `ctx.agents.reportStartFailure(id, error): () => void` announces and retains a declarative startup failure; the disposer clears that exact record without deleting a newer replacement. +- `ctx.agents.getStartFailure(id: AgentId): Error | undefined` returns a retained declarative startup failure for a configured id that never became live. Successful publication clears it. +- `observeAgentStart(ctx, id, handlers)` observes publication or declarative startup failure, including the retained-failure race for late-mounted front doors; its listeners belong to `ctx` and the returned disposer cancels the observation. #### Factory seam (creation) @@ -29,7 +32,7 @@ The loop plugin registers `AgentFactory`, keeping consumers independent of its c `dsh-agent` declares the live `agent/*` coordination vocabulary so plugins do not depend on the concrete loop. Exact signatures, dispatch modes, scope-filtering rules, and payload contracts live in the generated [Cordis event catalog](../../../docs/cordis-catalog/events.md); the [architecture turn flow](../../../docs/architecture.md#turn-flow) shows their order relative to durable session events. -`agent/created` runs after setup and both registry entries; the following `agent/session-start` is the first supported startup injection point. `agent/disposed` means the exact entry left the registry. The loop quiesces its driver first; directly registered custom agents own any stronger ordering. +`agent/created` runs after setup and both registry entries; the following `agent/session-start` is the first supported startup injection point. `agent/disposed` means the exact entry left the registry. `agent/start-failed` reports a contained declarative startup failure before publication; programmatic factory calls report failures through rejection. The loop quiesces its driver first; directly registered custom agents own any stronger ordering. Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` is a serial surface-mutation checkpoint, while `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. The full rationale is in the [agent-scope runtime-design RFC](../../../docs/rfc/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way). @@ -69,7 +72,7 @@ The handle every plugin programs against: ## Known Limitations and Deferred Work - **Inter-agent channels beyond delegation** — shared state, streaming child output, and background/poll semantics remain outside the current synchronous `ctx.subagents` seam. -- **`agent/session-start` cannot gate startup** — it remains a synchronous, veto-less notification; async composition that must finish before publication belongs in the factory's `setup(agentCtx)` transaction instead. +- **`agent/session-start` cannot gate startup** — it remains a synchronous, veto-less notification; async composition that must finish before publication belongs in the factory's `setup(agentCtx)` transaction instead. Declarative startup failures are reported separately through `agent/start-failed`. - **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface RFC](../../../docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). - **`HookContext` carries exactly one `MessageSource`** — contributions from several plugins merged onto one tool call collapse under one source; mixed provenance is unrepresentable. - **`SessionStartSource` reserves `'clear'`/`'compact'` with no emitter yet** — only `'startup'`/`'resume'` occur until the driving subsystems land (`TODO(compaction)`). diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index fc5ad371b4..fc3a59b43f 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -80,6 +80,60 @@ export interface AgentHandle { dispose(): Promise } +/** Handlers for observing one configured agent's publication or startup failure. */ +export interface AgentStartHandlers { + /** + * Handle publication of the requested agent. + * @param agent - the live agent that was published. + */ + onStarted: (agent: Agent) => void + /** + * Handle a retained or live declarative startup failure. + * @param error - the contained startup failure. + */ + onFailed: (error: Error) => void +} + +/** + * Observe one configured agent until it is published or its declarative startup fails. + * Listeners are owned by the supplied context fiber and the returned disposer is + * idempotent through Cordis's event-disposer semantics. + * @param ctx - the context whose fiber owns the observation listeners. + * @param id - the configured agent id to observe. + * @param handlers - publication and failure callbacks. + * @returns a disposer for the observation listeners. + */ +export function observeAgentStart(ctx: Context, id: AgentId, handlers: AgentStartHandlers): () => void { + const stop = (): void => { + disposeCreated() + disposeFailure() + } + const handleStarted = (agent: Agent): void => { + if (agent.id !== id) return + stop() + handlers.onStarted(agent) + } + const handleFailed = (failedId: AgentId, error: Error): void => { + if (failedId !== id) return + stop() + handlers.onFailed(error) + } + const disposeCreated = ctx.on('agent/created', handleStarted) + const disposeFailure = ctx.on('agent/start-failed', handleFailed) + const agent = ctx.agents.get(id) + if (agent !== undefined) { + stop() + handlers.onStarted(agent) + } else { + const failure = ctx.agents.getStartFailure(id) + if (failure !== undefined) { + stop() + handlers.onFailed(failure) + } + } + return stop +} + /** * The agent-creation factory the loop implementation provides to the registry * via {@link AgentRegistry.setFactory}. Kept on the `dsh-agent` interface so @@ -136,6 +190,7 @@ export class AgentRegistry extends Service { // plus entry.agent identity; this WeakMap mirrors the authoritative id map. private entries = new WeakMap() private factory: FactorySlot | undefined + private startFailures = new Map() constructor(ctx: Context) { super(ctx, 'agents') @@ -224,6 +279,7 @@ export class AgentRegistry extends Service { const carrier = scopeTarget(agent, agent) // Prepared transactions arbitrate identity at this publication boundary. if (this.entries.has(agent) || this.store.has(id)) throw new Error(`agent "${id}" is already registered`) + this.startFailures.delete(id) const entry: AgentEntry = { id, agent, @@ -316,6 +372,45 @@ export class AgentRegistry extends Service { } } + /** + * Report a contained declarative startup failure and retain it for late UI observers. + * @param id - the configured agent id that failed before publication. + * @param error - the normalized startup error. + * @returns a disposer that clears this exact failure record. + */ + reportStartFailure(id: AgentId, error: Error): () => void { + const token = {} + this.startFailures.set(id, { error, token }) + this.emitStartFailed(id, error) + return () => { + if (this.startFailures.get(id)?.token === token) this.startFailures.delete(id) + } + } + + /** + * Return a retained declarative startup failure for an id that never became live. + * @param id - the configured agent id. + * @returns the startup error, or undefined when the id has no retained failure. + */ + getStartFailure(id: AgentId): Error | undefined { + return this.startFailures.get(id)?.error + } + + /** Emit an unscoped startup failure with the same listener containment as agent lifecycle events. */ + private emitStartFailed(id: AgentId, error: Error): void { + const args: unknown[] = ['agent/start-failed', id, error] + for (const callback of this.ctx.events.dispatch('emit', args)) { + try { + const returned: unknown = callback(id, error) + void Promise.resolve(returned).catch((listenerError: unknown) => { + this.ctx.logger.warn(`agent "${id}": agent/start-failed listener rejected: ${String(listenerError)}`) + }) + } catch (listenerError: unknown) { + this.ctx.logger.warn(`agent "${id}": agent/start-failed listener threw: ${String(listenerError)}`) + } + } + } + /** * Look up a live agent. * @param id - the agent id to look up. diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 3aad65a70e..a9c16dec49 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -146,6 +146,15 @@ declare module 'cordis' { * @mode emit */ 'agent/disposed'(this: Scoped, agent: Agent): void + /** + * Declarative startup failed before an agent could be published. Programmatic + * `ctx.agents.create()` / `resume()` calls report failure through rejection; + * this event covers the fire-and-forget config path. + * @param agentId - the configured id that could not be started. + * @param error - the contained startup failure. + * @mode emit + */ + 'agent/start-failed'(agentId: AgentId, error: Error): void /** * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does * not enter `running` synchronously; drive lifecycle from this event. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index 5d541d56a8..b9acf9ef4e 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -2,7 +2,7 @@ import { describe, expect, expectTypeOf, it } from 'vitest' import { Context, Service, symbols } from 'cordis' import type { Events } from 'cordis' import { Session, SessionId } from '@deepseek-ai/dsh-session' -import AgentRegistry, { AgentId, agentEvents } from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentId, agentEvents, observeAgentStart } from '@deepseek-ai/dsh-agent' import type { Agent, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent' function stubAgent(rawId: string): Agent { @@ -85,6 +85,110 @@ describe('AgentRegistry', () => { ]) }) + it('retains declarative startup failures, contains listeners, and clears stale records', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const warnings: string[] = [] + const heard: string[] = [] + ctx.logger.warn = ((message: unknown) => { warnings.push(String(message)) }) as typeof ctx.logger.warn + ctx.on('agent/start-failed', () => { throw new Error('start sync') }) + ctx.on('agent/start-failed', () => Promise.reject(new Error('start async')) as never) + ctx.on('agent/start-failed', id => void heard.push(id)) + + const firstError = new Error('first failure') + const disposeFirst = ctx.agents.reportStartFailure(AgentId('main'), firstError) + expect(ctx.agents.getStartFailure(AgentId('main'))).toBe(firstError) + await Promise.resolve() + expect(heard).toEqual(['main']) + expect(warnings).toEqual([ + 'agent "main": agent/start-failed listener threw: Error: start sync', + 'agent "main": agent/start-failed listener rejected: Error: start async', + ]) + disposeFirst() + expect(ctx.agents.getStartFailure(AgentId('main'))).toBeUndefined() + + const disposeSecond = ctx.agents.reportStartFailure(AgentId('main'), new Error('second failure')) + const thirdError = new Error('third failure') + const disposeThird = ctx.agents.reportStartFailure(AgentId('main'), thirdError) + expect(ctx.agents.getStartFailure(AgentId('main'))).toBe(thirdError) + disposeSecond() + expect(ctx.agents.getStartFailure(AgentId('main'))).toBe(thirdError) + disposeThird() + + const disposeOccupiedAgent = ctx.agents.register(stubAgent('occupied')) + const occupiedError = new Error('occupied failure') + const disposeOccupiedFailure = ctx.agents.reportStartFailure(AgentId('occupied'), occupiedError) + expect(() => { ctx.agents.enter(stubAgent('occupied')) }).toThrow(/already registered/) + expect(ctx.agents.getStartFailure(AgentId('occupied'))).toBe(occupiedError) + disposeOccupiedFailure() + disposeOccupiedAgent() + + const disposeCleared = ctx.agents.reportStartFailure(AgentId('main'), new Error('cleared failure')) + ctx.agents.register(stubAgent('main'))() + expect(ctx.agents.getStartFailure(AgentId('main'))).toBeUndefined() + disposeCleared() + await ctx.fiber.dispose() + }) + + it('observes immediate, retained, live, unrelated, and cancelled startup outcomes', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const outcomes: string[] = [] + + const existing = stubAgent('existing') + const disposeExisting = ctx.agents.register(existing) + observeAgentStart(ctx, existing.id, { + onStarted: agent => void outcomes.push(`started:${agent.id}`), + onFailed: error => void outcomes.push(`failed:${error.message}`), + })() + + const retainedError = new Error('retained') + const disposeRetained = ctx.agents.reportStartFailure(AgentId('retained'), retainedError) + observeAgentStart(ctx, AgentId('retained'), { + onStarted: agent => void outcomes.push(`started:${agent.id}`), + onFailed: error => void outcomes.push(`failed:${error.message}`), + })() + + const stopLiveStart = observeAgentStart(ctx, AgentId('live-start'), { + onStarted: agent => void outcomes.push(`started:${agent.id}`), + onFailed: error => void outcomes.push(`failed:${error.message}`), + }) + const disposeUnrelatedAgent = ctx.agents.register(stubAgent('unrelated')) + const disposeUnrelatedFailure = ctx.agents.reportStartFailure(AgentId('unrelated'), new Error('unrelated')) + const disposeLiveAgent = ctx.agents.register(stubAgent('live-start')) + stopLiveStart() + + const stopLiveFailure = observeAgentStart(ctx, AgentId('live-failure'), { + onStarted: agent => void outcomes.push(`started:${agent.id}`), + onFailed: error => void outcomes.push(`failed:${error.message}`), + }) + const disposeLiveFailure = ctx.agents.reportStartFailure(AgentId('live-failure'), new Error('live')) + stopLiveFailure() + + const stopCancelled = observeAgentStart(ctx, AgentId('cancelled'), { + onStarted: agent => void outcomes.push(`started:${agent.id}`), + onFailed: error => void outcomes.push(`failed:${error.message}`), + }) + stopCancelled() + const disposeCancelledFailure = ctx.agents.reportStartFailure(AgentId('cancelled'), new Error('cancelled')) + + expect(outcomes).toEqual([ + 'started:existing', + 'failed:retained', + 'started:live-start', + 'failed:live', + ]) + + disposeCancelledFailure() + disposeLiveFailure() + disposeLiveAgent() + disposeUnrelatedFailure() + disposeUnrelatedAgent() + disposeRetained() + disposeExisting() + await ctx.fiber.dispose() + }) + it('separates entry from announcement and stale/idempotent detach cannot remove a replacement', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index 96704998c4..05dd4d34c2 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -15,8 +15,8 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | | `@cordisjs/plugin-logger-console` | readline diagnostics for non-TTY operation; omitted from the fullscreen TUI path | -| `@deepseek-ai/dsh-stdio` | the line-oriented terminal channel, bound to `main` for pipes and automation | -| `@deepseek-ai/dsh-tui` | the interactive pi-tui channel, bound to `main` for TTY pairs | +| `@deepseek-ai/dsh-stdio` | the line-oriented terminal channel, bound to `main` for pipes and automation; matching `agent/start-failed` errors print and exit nonzero | +| `@deepseek-ai/dsh-tui` | the interactive pi-tui channel, bound to `main` for TTY pairs; matching `agent/start-failed` startup errors are printed before fullscreen mode and exit nonzero | `@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, not baked in here: it is a Loader-only, subprocess-only dev plugin whose constructor needs `node --expose-internals` plus a live `loader`. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index b7d320880d..0ee46b3a3d 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -11,7 +11,7 @@ This package owns the terminal channel only. It injects `agents` and `userIntera | `welcome` | `ready.` | Banner printed before the first prompt | | `agent` | `main` | Agent id driven by stdin and observed for EOF shutdown | -The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. Disposal closes readline and unregisters every listener/provider through Cordis effects. +The plugin seeds display labels from the live agent registry, then tracks `agent/created` and `agent/disposed` so HMR and externally managed agents render consistently. While waiting for its configured agent, it also observes retained and live `agent/start-failed` notifications; a matching failure is printed and exits with status 1 instead of waiting forever. Disposal closes readline and unregisters every listener/provider through Cordis effects. ```yaml - id: stdio diff --git a/packages/ui/stdio/src/index.ts b/packages/ui/stdio/src/index.ts index 1e665381ce..3773a55e92 100644 --- a/packages/ui/stdio/src/index.ts +++ b/packages/ui/stdio/src/index.ts @@ -13,7 +13,7 @@ import { createInterface } from 'node:readline' import type { Readable, Writable } from 'node:stream' import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId } from '@deepseek-ai/dsh-agent' +import { AgentId, observeAgentStart } from '@deepseek-ai/dsh-agent' import { UserInteractionError, type AskUserQuestionAnswer, @@ -363,14 +363,12 @@ export function createStdioChat(ctx: Context, config: Config, runtime: StdioRunt */ export function mountStdio(ctx: Context, config: Config, runtime: StdioRuntime): void { const agentId = AgentId(config.agent ?? 'main') - if (ctx.agents.get(agentId) !== undefined) { - createStdioChat(ctx, config, runtime) - return - } - const dispose = ctx.on('agent/created', (agent) => { - if (agent.id !== agentId) return - dispose() - createStdioChat(ctx, config, runtime) + observeAgentStart(ctx, agentId, { + onStarted: () => { createStdioChat(ctx, config, runtime) }, + onFailed: (error) => { + runtime.output.write(`ui-stdio: agent "${agentId}" failed to start: ${error.message}\n`) + runtime.exit(1) + }, }) } diff --git a/packages/ui/stdio/tests/stdio.spec.ts b/packages/ui/stdio/tests/stdio.spec.ts index 7bb6a6f245..60407df416 100644 --- a/packages/ui/stdio/tests/stdio.spec.ts +++ b/packages/ui/stdio/tests/stdio.spec.ts @@ -2,7 +2,7 @@ import { Readable, Writable } from 'node:stream' import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import type { Agent, AgentStatus } from '@deepseek-ai/dsh-agent' -import AgentRegistry from '@deepseek-ai/dsh-agent' +import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' @@ -111,6 +111,42 @@ describe('mountStdio readiness', () => { await fiber.dispose() }) + it('prints a matching live startup failure and exits instead of waiting forever', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + const { runtime, out, exit } = makeRuntime() + const fiber = await ctx.plugin(Object.assign((inner: Context) => { + mountStdio(inner, CONFIG, runtime) + }, { inject: ['agents', 'userInteraction'] })) + + ctx.agents.reportStartFailure(AgentId('other'), new Error('other failed')) + expect(out.text()).toBe('') + expect(exit).not.toHaveBeenCalled() + ctx.agents.reportStartFailure(AgentId('main'), new Error('resume failed')) + expect(out.text()).toBe('ui-stdio: agent "main" failed to start: resume failed\n') + expect(exit).toHaveBeenCalledWith(1) + + ctx.agents.register(makeAgent('main')) + expect(out.text()).toBe('ui-stdio: agent "main" failed to start: resume failed\n') + await fiber.dispose() + }) + + it('prints a retained startup failure for a late-mounted stdio channel', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.agents.reportStartFailure(AgentId('main'), new Error('already failed')) + const { runtime, out, exit } = makeRuntime() + const fiber = await ctx.plugin(Object.assign((inner: Context) => { + mountStdio(inner, CONFIG, runtime) + }, { inject: ['agents', 'userInteraction'] })) + + expect(out.text()).toBe('ui-stdio: agent "main" failed to start: already failed\n') + expect(exit).toHaveBeenCalledWith(1) + await fiber.dispose() + }) + it('opens immediately when the configured agent already exists', async () => { const ctx = new Context() await ctx.plugin(AgentRegistry) diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md index 1e678beac8..7cc84cee3d 100644 --- a/packages/ui/tui/README.md +++ b/packages/ui/tui/README.md @@ -33,7 +33,7 @@ While the agent is running, editor submissions call `agent.steer()`; otherwise t maxToolOutputLines: 12 ``` -Startup fails before mounting when either process stream is not a TTY. Disposal stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR. +Startup fails before mounting when either process stream is not a TTY. While waiting for its configured agent, the front door also observes retained and live `agent/start-failed` notifications; a matching failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR. ## Model Experience diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts index 14f45242d7..13b5b3866c 100644 --- a/packages/ui/tui/src/index.ts +++ b/packages/ui/tui/src/index.ts @@ -34,7 +34,7 @@ import { } from '@earendil-works/pi-tui' import type { Context } from 'cordis' import z from 'schemastery' -import { AgentId, type Agent, type AgentStatus } from '@deepseek-ai/dsh-agent' +import { AgentId, observeAgentStart, type Agent, type AgentStatus } from '@deepseek-ai/dsh-agent' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { Session, SessionEvent, TodoItem } from '@deepseek-ai/dsh-session' import type { @@ -133,7 +133,7 @@ export interface ResolvedTuiConfig { export interface TuiRuntime { /** Terminal implementation; production uses pi-tui's `ProcessTerminal`. */ terminal: Terminal - /** Exit hook used by `/exit`, Ctrl+D, or Ctrl+C while idle. */ + /** Exit hook used by terminal shutdown or a target-agent startup failure. */ exit(code: number): void } @@ -1252,20 +1252,17 @@ export function createTuiChat( */ export function mountTui(ctx: Context, config: Config, runtime: TuiRuntime): void { const agentId = AgentId(config.agent ?? 'main') - const start = (): void => { - ctx.effect(() => { - const controller = createTuiChat(ctx, config, runtime) - return () => controller.dispose() - }, 'ui-tui') - } - if (ctx.agents.get(agentId) !== undefined) { - start() - return - } - const dispose = ctx.on('agent/created', (agent) => { - if (agent.id !== agentId) return - dispose() - start() + observeAgentStart(ctx, agentId, { + onStarted: () => { + ctx.effect(() => { + const controller = createTuiChat(ctx, config, runtime) + return () => controller.dispose() + }, 'ui-tui') + }, + onFailed: (error) => { + runtime.terminal.write(`ui-tui: agent "${agentId}" failed to start: ${error.message}\n`) + runtime.exit(1) + }, }) } diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index e4ffe2efd0..c0d1d419b8 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -910,6 +910,51 @@ describe('terminal mounting', () => { await ctx.fiber.dispose() }) + it('prints a matching live startup failure and exits instead of waiting forever', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.provide('tools', { get: () => undefined } as never) + const terminal = new FakeTerminal() + const exit = vi.fn() + mountTui(ctx, { agent: 'main', color: false }, { terminal, exit }) + + ctx.agents.reportStartFailure(AgentId('other'), new Error('other failed')) + expect(terminal.output).toBe('') + expect(exit).not.toHaveBeenCalled() + ctx.agents.reportStartFailure(AgentId('main'), new Error('resume failed')) + expect(terminal.output).toBe('ui-tui: agent "main" failed to start: resume failed\n') + expect(exit).toHaveBeenCalledWith(1) + + const session = ctx.sessions.create(SessionId('must-not-start')) + ctx.agents.register({ + id: AgentId('main'), options: {}, session, status: 'idle', ctx, + send() {}, steer() {}, inject() {}, cancel() {}, whenIdle: () => Promise.resolve(), + }) + await tick() + expect(terminal.started).toBe(0) + await ctx.fiber.dispose() + }) + + it('prints a retained startup failure for a late-mounted TUI', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + ctx.provide('tools', { get: () => undefined } as never) + ctx.agents.reportStartFailure(AgentId('main'), new Error('already failed')) + const terminal = new FakeTerminal() + const exit = vi.fn() + + mountTui(ctx, { agent: 'main', color: false }, { terminal, exit }) + + expect(terminal.started).toBe(0) + expect(terminal.output).toBe('ui-tui: agent "main" failed to start: already failed\n') + expect(exit).toHaveBeenCalledWith(1) + await ctx.fiber.dispose() + }) + it('rolls back providers, listeners, and terminal state when startup fails', async () => { const ctx = new Context() await ctx.plugin(SessionStore) From 87e25ef1fefe6b5614bf33cf5f2580f71ad2c5f0 Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 17 Jul 2026 16:50:53 +0800 Subject: [PATCH 155/323] fix(tui): make the color palette theme-agnostic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The palette used absolute 256-color indices (`38;5;252`, `48;5;236`, …) that terminals never remap to the active scheme: near-white body text vanished on light backgrounds and fixed dark bubble fills put default foreground text on dark blocks. Rebuild it from the standard 16-color ANSI foregrounds plus SGR attributes, keep body text on the terminal default foreground, replace filled background bubbles with foreground-only left-gutter bars, and use reverse video for the active selection so every grouping reads on any color scheme. --- docs/config-catalog.md | 2 +- packages/ui/tui/README.md | 6 ++- packages/ui/tui/src/index.ts | 89 ++++++++++++++++++++++++------------ 3 files changed, 66 insertions(+), 31 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 79aa6ce17a..8004a8fa43 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1122,7 +1122,7 @@ export interface TuiConfig { } ``` -Source: [`packages/ui/tui/src/index.ts:100`](../packages/ui/tui/src/index.ts) +Source: [`packages/ui/tui/src/index.ts:99`](../packages/ui/tui/src/index.ts) ## `@deepseek-ai/dsh-user-approval` diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md index 7cc84cee3d..865a20a469 100644 --- a/packages/ui/tui/README.md +++ b/packages/ui/tui/README.md @@ -20,7 +20,7 @@ While the agent is running, editor submissions call `agent.steer()`; otherwise t | `questionDialogWidth` | `72` | Question-overlay width in columns | | `questionDialogMaxHeight` | `20` | Question-overlay maximum rows | | `showHardwareCursor` | `false` | Show the hardware cursor at pi-tui's IME marker | -| `color` | `true` | Apply the built-in ANSI palette | +| `color` | `true` | Apply the built-in ANSI palette (see [Color](#color)) | | `title` | `DeepSeek Harness` | Terminal window title | ```yaml @@ -35,6 +35,10 @@ While the agent is running, editor submissions call `agent.steer()`; otherwise t Startup fails before mounting when either process stream is not a TTY. While waiting for its configured agent, the front door also observes retained and live `agent/start-failed` notifications; a matching failure is written before fullscreen mode starts and exits with status 1 instead of leaving a blank terminal. Disposal stops loaders, rejects pending questions, drains terminal input, restores terminal state, unregisters event listeners and the user-interaction provider, and never exits a replacement process during HMR. +## Color + +The palette uses the standard 16-color ANSI foregrounds and SGR attributes, which every terminal remaps to its active color scheme, so it stays readable on light and dark backgrounds alike. Body text keeps the terminal's default foreground rather than a fixed shade. Grouped regions (user prompts, tool cards) use a colored left-gutter bar instead of a filled background block, and the question overlay's active row uses reverse video; both are foreground-only, so they never collide with the terminal background. Set `color: false` to strip all styling. + ## Model Experience ### Interactive prompt input diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts index 13b5b3866c..aa8a510a32 100644 --- a/packages/ui/tui/src/index.ts +++ b/packages/ui/tui/src/index.ts @@ -8,7 +8,6 @@ import { homedir } from 'node:os' import { relative, resolve, sep } from 'node:path' import { - Box, CombinedAutocompleteProvider, Container, Editor, @@ -172,39 +171,39 @@ interface Palette { italic: (text: string) => string underline: (text: string) => string strike: (text: string) => string - userBg: (text: string) => string - pendingBg: (text: string) => string - successBg: (text: string) => string - errorBg: (text: string) => string - selectedBg: (text: string) => string + /** Reverse video for the active selection; swaps the theme's own fg/bg so it reads on any scheme. */ + selected: (text: string) => string } function ansi(open: string, close: string, enabled: boolean): (text: string) => string { return enabled ? text => `\x1b[${open}m${text}\x1b[${close}m` : text => text } +/** + * Theme-agnostic palette built from the standard 16-color ANSI set plus SGR + * attributes, which every terminal remaps to its active color scheme. Body + * `text` stays the terminal's default foreground so it reads on light and dark + * backgrounds alike; grouping uses foreground-only gutter bars and reverse + * video rather than fixed background fills. + */ function createPalette(enabled: boolean): Palette { return { - accent: ansi('38;5;39', '39', enabled), - accent2: ansi('38;5;141', '39', enabled), - text: ansi('38;5;252', '39', enabled), - muted: ansi('38;5;245', '39', enabled), - dim: ansi('38;5;240', '39', enabled), - success: ansi('38;5;78', '39', enabled), - warning: ansi('38;5;221', '39', enabled), - error: ansi('38;5;203', '39', enabled), - code: ansi('38;5;215', '39', enabled), - added: ansi('38;5;78', '39', enabled), - removed: ansi('38;5;203', '39', enabled), + accent: ansi('94', '39', enabled), + accent2: ansi('95', '39', enabled), + text: text => text, + muted: ansi('90', '39', enabled), + dim: ansi('2', '22', enabled), + success: ansi('32', '39', enabled), + warning: ansi('33', '39', enabled), + error: ansi('31', '39', enabled), + code: ansi('36', '39', enabled), + added: ansi('32', '39', enabled), + removed: ansi('31', '39', enabled), bold: ansi('1', '22', enabled), italic: ansi('3', '23', enabled), underline: ansi('4', '24', enabled), strike: ansi('9', '29', enabled), - userBg: ansi('48;5;236', '49', enabled), - pendingBg: ansi('48;5;235', '49', enabled), - successBg: ansi('48;5;22', '49', enabled), - errorBg: ansi('48;5;52', '49', enabled), - selectedBg: ansi('48;5;24', '49', enabled), + selected: ansi('7', '27', enabled), } } @@ -296,9 +295,41 @@ class HeaderComponent implements Component { } } -class UserMessageComponent extends Box { +/** + * Groups children behind a colored left-gutter bar (`▌`). Foreground-only, so + * it renders legibly on any terminal background — unlike a filled block whose + * body text would collide with the theme's default foreground. + */ +class GutterBox implements Component { + protected readonly children: Component[] = [] + + constructor(private readonly barFn: (text: string) => string, private readonly paddingY = 1) {} + + addChild(child: Component): void { + this.children.push(child) + } + + invalidate(): void { + for (const child of this.children) child.invalidate() + } + + render(width: number): string[] { + const inner = Math.max(1, width - 2) + const body: string[] = [] + for (const child of this.children) for (const line of child.render(inner)) body.push(line) + // Every caller adds a non-empty title/label child, so an all-empty box is unreachable; + // the guard preserves Box semantics (render nothing) rather than emitting stray gutter bars. + /* v8 ignore next */ + if (body.length === 0) return [] + const bar = this.barFn('▌') + const pad = Array.from({ length: this.paddingY }, () => '') + return [...pad, ...body, ...pad].map(line => `${bar} ${line}`) + } +} + +class UserMessageComponent extends GutterBox { constructor(text: string, palette: Palette, mdTheme: MarkdownTheme, label = 'You') { - super(1, 1, value => palette.userBg(value)) + super(value => palette.accent(value)) this.addChild(new Text(palette.bold(palette.accent(label)), 0, 0)) this.addChild(new Markdown(text, 0, 0, mdTheme, { color: value => palette.text(value) }, { preserveOrderedListMarkers: true, @@ -465,10 +496,10 @@ class ToolCardComponent implements Component { const visibleBody = this.expanded || body.length <= this.maxOutputLines ? body : [...body.slice(0, this.maxOutputLines), this.palette.dim(`… ${body.length - this.maxOutputLines} more lines (Ctrl+O to expand)`)] - const box = new Box(1, visibleBody.length > 0 ? 1 : 0, (value) => { - if (this.result === undefined) return this.palette.pendingBg(value) - return isError ? this.palette.errorBg(value) : this.palette.successBg(value) - }) + const barFn = this.result === undefined + ? this.palette.warning + : isError ? this.palette.error : this.palette.success + const box = new GutterBox(barFn, visibleBody.length > 0 ? 1 : 0) box.addChild(new Text(this.palette.bold(title), 0, 0)) if (visibleBody.length > 0) box.addChild(new Text(visibleBody.join('\n'), 0, 0)) return box.render(width) @@ -700,7 +731,7 @@ class QuestionDialog implements Component, Focusable { : index === this.selectedIndex ? this.palette.accent('●') : this.palette.dim('○') const description = option.description ? this.palette.muted(` — ${option.description}`) : '' const line = `${cursor} ${mark} ${option.label}${description}` - push(index === this.selectedIndex ? this.palette.selectedBg(line) : line) + push(index === this.selectedIndex ? this.palette.selected(line) : line) } if (options.length > this.maxVisible) push(this.palette.dim(`${this.selectedIndex + 1}/${options.length}`)) push(this.palette.dim(this.question.multiSelect From a425aff586a5721a4ecd39dbc1e5be183794b092 Mon Sep 17 00:00:00 2001 From: pku-xht Date: Fri, 17 Jul 2026 16:52:35 +0800 Subject: [PATCH 156/323] docs(rfc): propose one-send-one-turn simplification --- docs/rfc/INDEX.md | 1 + .../2026-07-17-one-send-one-turn.i18n.yaml | 6 ++++ .../2026-07-17-one-send-one-turn.md | 36 +++++++++++++++++++ .../2026-07-17-one-send-one-turn.zh.md | 36 +++++++++++++++++++ 4 files changed, 79 insertions(+) create mode 100644 docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md create mode 100644 docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a60579ef4c..c0992414af 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -22,6 +22,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Simplify session-log representation](proposed/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 | +| [Give each ordinary send its own turn](proposed/simplification/2026-07-17-one-send-one-turn.md) | 2026-07-17 | ### Architecture diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml new file mode 100644 index 0000000000..d485306ae6 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-17-one-send-one-turn.md: 2542b1038be07b5590ff80a02080b8872558f71c +2026-07-17-one-send-one-turn.zh.md: eefe6f2cc43c544dba4a67f95b36a27a852d7439 diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md new file mode 100644 index 0000000000..2542b1038b --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md @@ -0,0 +1,36 @@ +# RFC: Give each ordinary send its own turn + +Status: proposed + +English | [中文](2026-07-17-one-send-one-turn.zh.md) + +## Problem + +`Agent.send()` snapshots one ordinary message and appends it to a FIFO, but the agent loop drains every waiting ordinary message into one turn. Whether adjacent sends share a turn depends on when the driver happens to dequeue: calls from one synchronous stack, neighboring microtasks, event listeners, and model callbacks can observe different grouping even though callers used the same API. + +A shared turn also shares prompt admission, `turn/start`, `turn/end`, and the durability checkpoint. A later message can therefore join an earlier message's model request instead of observing the earlier turn's committed result. The batching branches for mixed allowed and blocked prompts add lifecycle states that no caller explicitly requests. + +`steer()` already expresses joining the active turn, while `inject()` records model-facing context without acting as an ordinary message. Implicit batching makes `send()` overlap both explicit operations instead of preserving a single meaning. + +## Proposal + +The inbox will dequeue at most one ordinary message for each turn start. A successful `send()` will remain synchronous: it validates agent state, snapshots and freezes content, appends one FIFO item, and publishes `agent/queued`. If two items are both claimed, the second turn will start only after the first turn ends and its durability checkpoint completes; an item discarded before turn start will not create an empty turn. + +Prompt admission will decide one message. An allowed prompt will become that turn's `user/message`; a blocked prompt will end that turn as `rejected`. The mixed-batch and all-blocked-batch branches will disappear. + +Running `steer()` will continue to append to the active turn's steering FIFO. Idle `steer()` will continue to delegate to `send()` and therefore create an independent ordinary turn. `inject()` will retain its turn-enclosure and flush behavior. `cancel()`, `status`, and `whenIdle()` will remain whole-agent operations rather than per-message controls. + +## Alternatives considered + +**Keep opportunistic batching for throughput.** Combining queued prompts can reduce model calls when producers outpace the driver, but it makes turn boundaries depend on scheduling and prevents a later message from reliably observing the preceding turn's durable result. Explicit lifecycle semantics are worth the additional model calls; a future measured batching feature would need an explicit caller-visible contract. + +## Acceptance criteria + +- Two adjacent successful sends remain distinct FIFO items and, when both are claimed, produce two turns separated by the first turn's durability checkpoint. +- Dequeue timing and reentrant sends from queued listeners, session listeners, and model callbacks do not change the one-message turn boundary. +- Prompt veto, cancellation, disposal, and turn-start failure cannot merge messages or leave the agent permanently running. +- Running and idle `steer()`, `inject()`, whole-agent status, and `whenIdle()` retain their documented meanings. + +## Risks + +Workloads that intentionally relied on coincidental batching will make more model requests and may take longer to drain. FIFO queues may also grow under sustained producers. The proposal accepts those costs because the public `send()` boundary becomes deterministic; throughput optimization can return only with an explicit measured contract. diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md new file mode 100644 index 0000000000..eefe6f2cc4 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md @@ -0,0 +1,36 @@ +# RFC: 让每次普通 send 独占一个轮次 + +Status: proposed + +[English](2026-07-17-one-send-one-turn.md) | 中文 + +## 问题 + +`Agent.send()` 会为一条普通消息创建快照，并将其追加到 FIFO，但 agent loop（智能体循环）会把所有等待中的普通消息一起取出并放入同一个轮次。相邻 send 是否共享轮次取决于 driver 何时恰好出队：即使调用方使用相同 API，来自同一个同步调用栈、相邻微任务、事件 listener 和模型 callback 的调用也可能产生不同分组。 + +共享轮次也会共享 prompt admission、`turn/start`、`turn/end` 和持久性检查点。因此，后一条消息可能加入前一条消息的模型请求，而不能观察前一轮次已经提交的结果。allowed 与 blocked prompt 混合批次的分支引入了调用方从未显式请求的生命周期状态。 + +`steer()` 已经用于表达加入当前 active turn，`inject()` 则记录面向模型的上下文而不充当普通消息。隐式批处理让 `send()` 与这两种显式操作产生语义重叠，无法保持单一含义。 + +## 提案 + +Inbox 在每次轮次开始时最多取出一条普通消息。成功的 `send()` 仍为同步调用：它会校验 agent 状态、创建并冻结内容快照、追加一个 FIFO item，然后发布 `agent/queued`。如果两个 item 都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点完成后开始；在轮次开始前被丢弃的 item 不会创建空轮次。 + +Prompt admission 将只处理一条消息。allowed prompt 会成为该轮次的 `user/message`；blocked prompt 会让该轮次以 `rejected` 结束。mixed-batch 和 all-blocked-batch 分支将被删除。 + +运行中的 `steer()` 仍会追加到 active turn 的 steering FIFO。空闲时的 `steer()` 仍会委托给 `send()`，因此会创建一个独立的普通轮次。`inject()` 保持现有的轮次封闭与 flush 行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个 agent 的操作，不变成逐消息控制。 + +## 曾考虑的替代方案 + +**为吞吐量保留机会式批处理。** 当 producer 速度快于 driver 时，合并排队的 prompt 可以减少模型调用，但会让轮次边界取决于调度，并使后一条消息无法可靠观察前一轮次的持久化结果。额外模型调用的代价低于显式生命周期语义的价值；未来若根据测量结果重新引入批处理，必须提供调用方可见的显式契约。 + +## 验收标准 + +- 相邻两次成功 send 始终是两个独立 FIFO item；如果两者都被认领，则形成两个轮次，并由第一个轮次的持久性检查点隔开。 +- 出队时机，以及 queued listener、session listener 和模型 callback 中的重入 send，都不能改变一条消息对应一个轮次的边界。 +- Prompt veto、取消、dispose 和 turn-start failure 不能合并消息，也不能让 agent 永久停留在 running 状态。 +- 运行中与空闲时的 `steer()`、`inject()`、面向整个 agent 的 status 和 `whenIdle()` 保持文档中的含义。 + +## 风险 + +依赖偶然批处理的工作负载会产生更多模型请求，队列清空时间也可能延长。持续 producer 还可能让 FIFO 队列增长。本提案接受这些成本，因为公共 `send()` 边界会变得确定；只有建立显式且经过测量的契约后，才能重新引入吞吐量优化。 From 97c5ca940d449d5a4b164984dc2ffcc6878ef841 Mon Sep 17 00:00:00 2001 From: pku-xht Date: Fri, 17 Jul 2026 16:58:56 +0800 Subject: [PATCH 157/323] review fix: preserve blocked-prompt RFC contract --- .../2026-07-17-one-send-one-turn.i18n.yaml | 4 ++-- .../simplification/2026-07-17-one-send-one-turn.md | 4 ++-- .../2026-07-17-one-send-one-turn.zh.md | 14 +++++++------- 3 files changed, 11 insertions(+), 11 deletions(-) diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml index d485306ae6..36bd0699c4 100644 --- a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml +++ b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-17-one-send-one-turn.md: 2542b1038be07b5590ff80a02080b8872558f71c -2026-07-17-one-send-one-turn.zh.md: eefe6f2cc43c544dba4a67f95b36a27a852d7439 +2026-07-17-one-send-one-turn.md: 21ab23a9ab0e7ea11fcaf44252b6e5d8e49c224b +2026-07-17-one-send-one-turn.zh.md: 07e268fcfa8651977c204baf46b499c62c27626a diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md index 2542b1038b..21ab23a9ab 100644 --- a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md +++ b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md @@ -16,7 +16,7 @@ A shared turn also shares prompt admission, `turn/start`, `turn/end`, and the du The inbox will dequeue at most one ordinary message for each turn start. A successful `send()` will remain synchronous: it validates agent state, snapshots and freezes content, appends one FIFO item, and publishes `agent/queued`. If two items are both claimed, the second turn will start only after the first turn ends and its durability checkpoint completes; an item discarded before turn start will not create an empty turn. -Prompt admission will decide one message. An allowed prompt will become that turn's `user/message`; a blocked prompt will end that turn as `rejected`. The mixed-batch and all-blocked-batch branches will disappear. +Prompt admission will decide one message. An allowed prompt will become that turn's `user/message`; a blocked prompt will append one durable `prompt/blocked` and end that one-message turn as `rejected`. The mixed-batch and all-blocked-batch branches will disappear. Running `steer()` will continue to append to the active turn's steering FIFO. Idle `steer()` will continue to delegate to `send()` and therefore create an independent ordinary turn. `inject()` will retain its turn-enclosure and flush behavior. `cancel()`, `status`, and `whenIdle()` will remain whole-agent operations rather than per-message controls. @@ -28,7 +28,7 @@ Running `steer()` will continue to append to the active turn's steering FIFO. Id - Two adjacent successful sends remain distinct FIFO items and, when both are claimed, produce two turns separated by the first turn's durability checkpoint. - Dequeue timing and reentrant sends from queued listeners, session listeners, and model callbacks do not change the one-message turn boundary. -- Prompt veto, cancellation, disposal, and turn-start failure cannot merge messages or leave the agent permanently running. +- Prompt veto appends one durable `prompt/blocked` for its `rejected` turn; cancellation, disposal, and `turn/start` failure cannot merge messages or leave the agent permanently `running`. - Running and idle `steer()`, `inject()`, whole-agent status, and `whenIdle()` retain their documented meanings. ## Risks diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md index eefe6f2cc4..07e268fcfa 100644 --- a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md +++ b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md @@ -8,27 +8,27 @@ Status: proposed `Agent.send()` 会为一条普通消息创建快照，并将其追加到 FIFO，但 agent loop（智能体循环）会把所有等待中的普通消息一起取出并放入同一个轮次。相邻 send 是否共享轮次取决于 driver 何时恰好出队：即使调用方使用相同 API，来自同一个同步调用栈、相邻微任务、事件 listener 和模型 callback 的调用也可能产生不同分组。 -共享轮次也会共享 prompt admission、`turn/start`、`turn/end` 和持久性检查点。因此，后一条消息可能加入前一条消息的模型请求，而不能观察前一轮次已经提交的结果。allowed 与 blocked prompt 混合批次的分支引入了调用方从未显式请求的生命周期状态。 +共享轮次也会共享提示词准入、`turn/start`、`turn/end` 和持久性检查点。因此，后一条消息可能加入前一条消息的模型请求，而不能观察前一轮次已经提交的结果。获准与被阻止提示词混合批次的分支引入了调用方从未显式请求的生命周期状态。 -`steer()` 已经用于表达加入当前 active turn，`inject()` 则记录面向模型的上下文而不充当普通消息。隐式批处理让 `send()` 与这两种显式操作产生语义重叠，无法保持单一含义。 +`steer()` 已经用于表达加入当前轮次，`inject()` 则记录面向模型的上下文而不充当普通消息。隐式批处理让 `send()` 与这两种显式操作产生语义重叠，无法保持单一含义。 ## 提案 Inbox 在每次轮次开始时最多取出一条普通消息。成功的 `send()` 仍为同步调用：它会校验 agent 状态、创建并冻结内容快照、追加一个 FIFO item，然后发布 `agent/queued`。如果两个 item 都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点完成后开始；在轮次开始前被丢弃的 item 不会创建空轮次。 -Prompt admission 将只处理一条消息。allowed prompt 会成为该轮次的 `user/message`；blocked prompt 会让该轮次以 `rejected` 结束。mixed-batch 和 all-blocked-batch 分支将被删除。 +提示词准入将只处理一条消息。获准提示词会成为该轮次的 `user/message`；被阻止提示词会追加一条持久的 `prompt/blocked`，并让这个单消息轮次以 `rejected` 结束。mixed-batch 和 all-blocked-batch 分支将被删除。 -运行中的 `steer()` 仍会追加到 active turn 的 steering FIFO。空闲时的 `steer()` 仍会委托给 `send()`，因此会创建一个独立的普通轮次。`inject()` 保持现有的轮次封闭与 flush 行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个 agent 的操作，不变成逐消息控制。 +运行中的 `steer()` 仍会追加到当前轮次的 steering FIFO。空闲时的 `steer()` 仍会委托给 `send()`，因此会创建一个独立的普通轮次。`inject()` 保持现有的轮次封闭与 flush 行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个 agent 的操作，不变成逐消息控制。 ## 曾考虑的替代方案 -**为吞吐量保留机会式批处理。** 当 producer 速度快于 driver 时，合并排队的 prompt 可以减少模型调用，但会让轮次边界取决于调度，并使后一条消息无法可靠观察前一轮次的持久化结果。额外模型调用的代价低于显式生命周期语义的价值；未来若根据测量结果重新引入批处理，必须提供调用方可见的显式契约。 +**为吞吐量保留机会式批处理。** 当 producer 速度快于 driver 时，合并排队的提示词可以减少模型调用，但会让轮次边界取决于调度，并使后一条消息无法可靠观察前一轮次的持久化结果。额外模型调用的代价低于显式生命周期语义的价值；未来若根据测量结果重新引入批处理，必须提供调用方可见的显式契约。 ## 验收标准 - 相邻两次成功 send 始终是两个独立 FIFO item；如果两者都被认领，则形成两个轮次，并由第一个轮次的持久性检查点隔开。 -- 出队时机，以及 queued listener、session listener 和模型 callback 中的重入 send，都不能改变一条消息对应一个轮次的边界。 -- Prompt veto、取消、dispose 和 turn-start failure 不能合并消息，也不能让 agent 永久停留在 running 状态。 +- 出队时机，以及 queued listener、会话 listener 和模型 callback 中的重入 send，都不能改变一条消息对应一个轮次的边界。 +- 提示词否决会为对应的 `rejected` 轮次追加一条持久的 `prompt/blocked`；取消、dispose（资源释放）和 `turn/start` 失败不能合并消息，也不能让 agent 永久停留在 `running` 状态。 - 运行中与空闲时的 `steer()`、`inject()`、面向整个 agent 的 status 和 `whenIdle()` 保持文档中的含义。 ## 风险 From 7f91a05ed772cee464cb450b0a69858c7fdd4cfc Mon Sep 17 00:00:00 2001 From: Turtle Date: Fri, 17 Jul 2026 17:13:41 +0800 Subject: [PATCH 158/323] docs: add TUI screenshots --- docs/assets/tui/jokes-dark.png | Bin 0 -> 66598 bytes docs/assets/tui/jokes-dynamic.gif | Bin 0 -> 78162 bytes docs/assets/tui/jokes-light.png | Bin 0 -> 70844 bytes 3 files changed, 0 insertions(+), 0 deletions(-) create mode 100644 docs/assets/tui/jokes-dark.png create mode 100644 docs/assets/tui/jokes-dynamic.gif create mode 100644 docs/assets/tui/jokes-light.png diff --git a/docs/assets/tui/jokes-dark.png b/docs/assets/tui/jokes-dark.png new file mode 100644 index 0000000000000000000000000000000000000000..876ea9c24c9422e76aa839bdead1edd6cb6df22f GIT binary patch literal 66598 zcmbTdWmFtZ)V7NR3GM^}!3j=q2rgl8cMXGkaEIXT?(Xgm3Blc6g1ft)e#rZN-#Y93 zJN;wUn(msKu3cTb?tSgu!E!PnWCVN!2nYydaWN4E2#9yzAt0c};h}&ta*ol}5D;h( z;v#}d&S^(0Fz%SfL~v)NwAcp{lGN7;4FaL9EXxZ4haaGKP<-#_VW9&oIK!&-{;Z_q zG?LQGWuI7`GB!sUTE^1IIeY0|yq_D|w;R*Wczr%)NNEWufI@#e-utu&h`b#NNKrv= zhrtKpf7b@S2#~%VF?v7$wITll5&YIhEC3SYtx+@*H2J?qc(7vs8ZrO>>nN;1Kmr@_ ztqaD_Y~F(xub9M4izNSb9#blGdG|_M;5q!+h-nI&;H&+z3JNN+^Yin|1L>qh z&1@yWWoKB^?mzR2^DPYze>-7{Y(8VOC&cW3?dA z_DfOJhl~jq_6@7cBh^s>y%}Tdolqn&uHiaX^FaL2XjazxYdr>5u?3XX9fxe<{nKIy*=it+Jf-vkIb{444KsHk=zpD{z{{50+f~mX zM3tESj5p&IyUEn9-1J zEzSri-NM85ce=P3HQXf{!U+o6>&YuEO^sE&*0jyUK$b>k6D-gAd3%U~-u`9U9$DJI zq~vs!>inE6`{Kx<&hxBjZg#jyRUO>=`gK}* z_`!#jHXH3vKeLT;JayV_@mBKrDM%mq^^A^xyv|Z&mz2Z`mOQM0Lfg_)Q>Lj`h)AY{ z7!r{!Kw-Z`lbjru(noB@)nHs7?!iDx;eo_yLGc0`JxIsa2wN-To zlkI`v%;DiOHd?PSFVPv!(7ohCT5IRB&*q{i=Odkw_EslgYPCq*5AKdfXl!i z%47uBy`b_cc->6Q+Qc9g6u>#{!tG@i%D7O@k9Q4bOE2BkWU7p+&ziMb@SyZVjywI4 zk~pjZHgwZs)5Wig$`KJ+!n+lel#~>%z(<){L!C#TjFHg}DiNQQbhNgYw=^|s)S}a# zfsxhA-uj=oI0>zEL6NH(fubBrCGi=kJTu-Ty`XUQj{SEXF;d33fjk^WmZ{_G1Ns)oLyg{a=JXJso8FIRxLFkkO3YG=YD;LTTuA4Hm zm4`N)m=Ag8{+PK~^E=?OxvHwJCKoW9Y0#FJpBT^wO{Ax#k)ol?b9E=>PwGwDHNh1( z=9@M{7r{rlve6qSGyM#K5HEG%iu~3G0r>YKE$V>*2Sx6H9IoT>$TeFUNG|K{zRaJ>kzY^%{;rQX1)SDUQzIq3 zI{OWM#YpoYyFpr{ewnp1ay~KJ`HDej%7i68MXY&Z7MkqU~77fP+Y+(2*^ z{$XKZgi8%z7G#32!@aXOnJ8`^-RV_J+^-Alj$P!^^yNK>JGXlaLp|l|5td6QYw^Q| zN8JOit}UG}%$-F|O~d8XPKO0_wR3IChZ`H<>REL3i7CYe<8f@&*XGq#hpSSSpHA(z zIRZ1#CSMaTMbF}O|%kPSU&s-)5J(sk%XRcbQ zrmo(}=ZYjmNl$+~2MX`X+`}Wp3x<3^{gl&`CMHmCHpNa$X4f}MpFamh67Kaq>&c&g zn+W*>&-C!}Q}4Ao`ugq2@bDw@hoFoWSJy?2MYYA@uwl1ba(d4^<8io6KBP#2yxpB0 z?>mv65U0b5sovR>hndpd(F`VL<}R(c>oRy@Vc}sy!O%9b!#O7xH1r55nahN7G^ZXB z5Cw&VOgqJAinSKc_GS7FrM2w|U%2!0_d0xh-qJobwY9>GS_1AE%Vo{J`n*W&26yJy z+FA;+id|M~UCV(;Uf8LBt>%xHwFV4VQM*n-%bk%Z9?%|A1cX!+blKLqqI;q)q_jyf zF+LDAz^nj^D!kbKNud}C!|Ng_s0iu3jg2!02S=Ym+98h@G;DGPrn-|3b6VVi26w+rE9+bgFLJcT3Zxii^FDb1>viSiP=0iXO^DF z(HTjYiJqQ!P}l0H4j_C$AdatJ4=#G-t{OqK9T}JxUpB5jHnre$SjA*yG??9=8m`t< zW@k@iE8_O>T^voN#CPK2V1Xrq2o73Vzc4-D()@h9J+XW_l=vNI=`{2Z;Gb_ef1D~tRXne-u{V^+AZn8htvBX-22U4Lk-?Bd=!7Z@2LkzN&a$(A zkZkiAU713purRQ&XCm)j`7<=S`m%Mt3CO9CA-l)f@(NyrgBd%~#>h%?sTM4Z91C+k z_d5Y%(wr2fV9l6}KNOC0leLTcA4)$7%oL)AEZrlNz{#DP3OaW*bOsziz9Y>U{L&a_ z@M$AYFXm1SCJ%QjQ$us9Xpd1$INI4%|0{)hjKVm_7qrLIVW=6EUd2$WP`O_c22IqvlSXRZAMvioCqHYL=ojj82lyv3K65;(M=AQ~wU z=yTIIJ9{2?H1FH6FeDF;=X?Ga;-Ozf#n`ymrF*FG-@?MerxX;KAQlIclVf5-iSq^!QiSVV`Z@;V^{_*(xC;p}}&fpu4-9qd-Pc z(Zn}*LKpnCC%=O(uH1Pm7u5N5mD}u}pPH&EcZpNJ*wE^}4+hNYwL-}FeQWrnnZ7ie4qw{hpOMFWeyqZ1S7JK={HRTA2{ zVYKs%X}qBj#o|-nyGw6RS9)f}#p1MB)LqRHuw&Db42+CUv^qU)#V}sF4~RpPQZ)}f zkwSus9E(gaihUpzq;<3!Kl5Gx5GtwpU@EJH04vAlYBI4->puw2<0XOlAkec1vuk_7 zutOCZ4d_aJ2=AaG9+U3>wt)Wb?#V$7Nl6yUuMfTT=6ghrk2nepzJcwo+mqk6+|gpw z_-vklEobl{RME|0s|Z-CWRiX-fs?7xNJz-|tQMT$tEAFI#>0bs7uQEIO3y_kIN!|yh zTwDXwbyjQMzF>VYnsAOmg;qyUq=KTt(a|xt@HE!Jm$KTQ?KgwoV4P#r@W z_h*^H;d1rgAVsZaTfF!@%fN`8ganu7W*xqmL)w$I_RoN8UZBAuQ{Ey$X7f6nD0KR? zjgx@hYk-60?%evMEA(^}*|yxqoIt};xR+bMtxKHP&YWLVHW6AITI0Fts~B8F0FDun zl^y%D^ig`ftSpQ+k>R=8u|7$LtIlifc!`6)oV+vMkDa4MHk~Isr<1rni}uCF;`=7$ z11ziw#p!B2H1F-n^7Y<2^cLJ=!ztQw8P^3n+|4mMbn0~}#hBUU`Ssy){YQU|%J=`v z0&q6_vwclu$wn@AAL_Z9xyl#oET<|wJUw3u!o6@LgYCq_BKfPV8Ece%1CeowjO5Uh zCIE#WowzrhUm9$>^7Q266`IYnp&C_#y>>muPF`PC)c$bOlj-JoBCwM;oFN1gRI2_p zH~(%wy-G7k6bb1{v%!+KXqhwwLq;Q?)zBr_d+ohjy`zB5ke8y}yps;U|t7^QjE%)ArR9TV`B zP9)G6z{kgDd$bczN=ztll#!`Ni7~_ps;FQ9H(*F=8jYop>W~(Fkf2^t2#J~-937>8 zcB`bq)7EYu4vU#H(!W=ht-7)wTu#9@umG2omipeQs|SgRTzT~jFRs6ohYs>HehyZ$ z`k8kir#bQ;T-kz*`47mjWw$|y%Mp?lcMSS`&It<2sNm&xEK$9|-3KD(A`PXLu)Jd1 zx(iB45s?{8$H#)V-;_S}F;Nlv?9%^(GzM`nVp2qJ5$*(HX;X->618vl-dn^SWY$dM zPk#`ffssr07W})CV5vUnUk^(APW%g@+XZOw$j(WS|3%=;6j0;^k#9fU+g3;>$6)zi z*b@SYG4+o^TrrpYz$gaek&FJ%ccD@>xm=y*-~aALN2um!5fmPIfXrK$R~SVCCb`r~ zk;(PG{|MBT0va^=cC?ZUlZui^(!X;`-1A&)O4m$K1Z>Kg=S*w=b2kSw;{V2l-u_+5 zpQ~s1e~A?pYE%;6KbnykbMZY8@Bag*B%sK3bpPETBNGJ)>i-$Y|Djfc2vN=+gl|@8 zzZyhvPZE6VkTj;)^{3LX6z1EN8NQkK$`UYQVXps-@+wk%7MM8y&vpY!OadF%4sSQB zWUkEhT@Uu34a9aj0doocGl182r=XlNvshclKf+?xT;fmP*8T6x{{?JeLO+$N-(gi& zzD-mPu8@ttF9Da){|DBYsF>{)I(ejrJ8k~Tj6+9_uxL` zc*Uou5sxE6k%ZwlIQc6x2)IhrT_eK{KbC&sXQW`(x+u)(kW*4~{o-Ir=y1)9qXvLC zDmtnaU15-Fxtg5n9F;y6@CR@Iv$37-pAb>ekn!6tna%h&@IQ>VbknS?%iK5h*Jf=8 zGqX_bc^T7ryANA1iL)zbFXpI~8#QKM{xhpQ{rY&5^4jU#!8Fr=v@H6bq0djT6yp-? zTjGTWR&iP9;eU^|S#y7A;hEL(KI6D#iHa7uu%JLkOO5Ic7tL6KOO>_LBfq+tDubsk zaQ_)`&tI`vAfTG@ZSwvv&`j2_L5<1IFOLu;d}CaD-@bo0qWG`VcVY|F!S`J1Zwz%J zl$e`dJS#Eo3Zr%R`OLqoZJCs>=WP~s(7xT@L$$l->B*P(6Dw;GN@^04#ct$mlx^J| zZM}2xVndc@*$tq8mGN{&%}y-Vheo!v?0MO@nP@hp7G+0SoIHF$u&rg;&_}Sf#R{C5 zoN}^Sr3T>PgGSID?f3ZfZ!#JoE*_|C4)xt0t6#sys2dv_`h!G*gndd& z%?WeAR!8dR=H#3e1_rifbaBr|gP_XxF z+A_zD(VlrJO2VF(-gA!PP{;A(Cak`>o6A@q2jj^-SYmNgj14*5yVIiP=I*wyGlKqU zV{)xi)e*-T`PBop#f#`eT=H4dX6u@Z1Cf@JT$PaloFU|77@jri2To!>h7N~Pl{>p< zqL_tne5Q-xWR|@T{GMHT1F_>a&x_ZP&yS(GPuI7)@HyQl8yg!R=PFS@eno;DZb3dg z{4gsnBVn~#mTbWF`XDJOIW*SSXt~sI>6xqx?$GZG<8|5SJ|q*BN@bUp)s;O;j!(w^ zfJQ8)Uu8IyK;j%bW_VYnhbzqZk76>y`>~k$XnYHBC&>h>CNU0tH`(8Z33o0XFt?`h zjKjgD_u4i#?te6<_&oSn*ef#lXk18XOd-xJ9~9&|dXG%l(XI>PAWc4F2_$7q7lfNs znMsCeaySYFVghdd%qV+uGWWzfREt%a1@7X$ooiJqpQp0Nvy1hHQz<0Fs-;e#PQ4gN~{zg8j83Y zO*lC_D@tttyvTMB%5=Xt&-M+BAmBDLG~C|ZE##cloGKs{R01pXL$RU0jA_(aO^K?i z;u5a3I!ca-fk3GZmOYU??c{UU9TP=Xtymf)$Ixx!n63Nrb9h zqpb*1?Hdp z92#ienz3Lyu&XjQBqJ_0D5Xl!R8#A0IBK0_dsUBE==G>m1OW~0+gKn?JHbNyML<## z(KM%uyYcx6ANj)<0VaVMy0(;*hJ-DnJP<0;fE#HF0s@MPDkGUJU^9VgGIsWp`H5Uy zhBVN$U+~dlt=kDIzr{++^60nGbfBch#Tr#j=sg7V%+zsWMRVO#1BjMg{2PXcje z{ytCYb~Za5mF5@j&N;o)!DXl8Yu+-y-wwgf^l$q}La;i+#_AU`!7-l6X$lU`@OZrb z^Z0yrR$DkmDquEI+hCUH3xquFRO&|-D1JX1S5@!C-UM0d>WX~`HGDB z==2nKgO|^HVxIQa_gMuaeVqVk;qS`p6{f^bQ9pS!YjKYo9L*`p63|whTKuy%%R%)p z==BL%wE)0*rK*)VWC9Oi@8mB5u9y*#6zjqFSX~ zYoWvAaZbmr{z|Ls&!3(MU{*s2gMuEe_E`)MQXL%~3knLno|>}_Lvh52%5~}wzeeYomnW5%Q1zrv#bQxJRkS5RFi=&hx*nFR zWBj?VGo`Aqs00>5AB^0XQyG>iY$CA!Ul? z_Ls9|`JO#0lPx4k(~CqjVXyVqNPcEPt#;49oKAE9bgwoGrhXFIcGzFUMn}K+ zW}L^&Lg6IUK3SUR{_fI6B62a~5TEhFupAy$}ZEfuxPY<+&rmhD^ z3$@K$F=#^r3-3=m8Fa$ZFusB}!9;vfd8u@C!*8jtoWu#lWWfuUZRNJ^lg&`0p~uqV z($4DBh^Mh|>#N{SGPj&xKQlQ78Qr*B%~taXnm^9^^i(5($AC=3cIXUjjkWI1*x z|4~lri7zkR^6d%K4sLOu9c3&!)~r1xSW(Z0tD@aoP{dIACL$7s&xAq9Vmv~?V<7hZ zd)CI6eZ2k0+tbs@e96w2=g#|`k1nr(OY^$lR=qHG9GVr9K0dhi$~^yK+YQgl`|SDr zaJ@gZYhzJX9Uaa22i;)01Y4QcO}>>roS!|>%m0e?rb=~088u+{#osAJrN(05 zbsRsVbKJg^-!%s$G(6>36w{wpRuog8R+d**f>G9uQE;%a_U70)>>PzTf$hk{;H6MG zxyP&0jGI$6Mr4wM?eh3JMNYh9^0QMWx0}q9-Q&%%&lN`m5;9T`pTB<$IGN3k68wQY zde!ap`E~f=JKh-1oKjY9?nk_PDkc(nZS9rW-riroAg1mgPdiUnVwVlDac}~D4h}C% zg+*Acb+ntTlm3sZ&MPoCA;n5$k*kg&(c*#1A?@-rJG@&(bqx1WMK-6N#yB_-RdIBs z+$m;4wN;4md;Qo;*?VGjf|rcv)OE78y*==FxVP8T+&#_a+$L&Ztq7mbq)y$nFN1Yr+CT~mlo%BYY5vt+TPjG zX|`4W=Y|$c6H@<07^DxKa$4NXVt_Tj!aBTV7;|vFy_4ew7>hN~i46X4ii(TX3nPd%7J-6+e{})X5fN73U>oY~ESB?<q1fB!ju?n?Oikxp&3GnkH2ilUvbV!MElnGkfnoYGR2klz3tsKHC52<%X90) z!^8XYb98j4e96+C?Wz9X*%<*XqDs@bl8FphxZ)Z!FW!R5c>5nFS37hpERYgtXeB2% zEEZazN5@M`OF8UsYpUu*GZArRhIVtLE)y(?c!P=*`-(DZ5qE-MLL*}0vU3%m1CV*I zu90G5Fc`ErV`I~mqwB|~raHY&BiuI_ke4kik0J@Vsc=#P0z^yM2~Pu7Lc-jMl`<+a zK5h7oN7+GoOCKK-l98SSKi9L?P~ch}RCV^Ab%96d&jX!u8t zshJr;C%GR(X-8=QxzPuq_QU2$c~+!O<5E4QChi2 zJlj7pBf(7n@MlAMTj3`kG`PMS!j_%w?G4%Cpd%sz|sjQud>w{7q zC3ACbM9ET62IA4K8TI_+>F9Fr#IhxYrkr4`BFw4U^JJ0YAk{TiMN~ zIa$b{%f(S;GqbW1z+T<3zyjvvYVGaoYhk|<@FTkcr6nX$nQG;vhoH2D&_p2%+cm2X zH9&^@j>AgJ%GTG{F$oNe?eLbu1TZ_xf{g188cZpxIuwl^w4?xo(A6rm^xb^h>5wM~t zNJ1hewH0@V^oFCcs%)346eGwVZ5tm?oFPh>@Q))k1D!}XMx(rpRYS-(p(cMlg?v4! z8UyG)>HwUtEiKZi^&&(pETI)Et^nVU(dr^^QQ{_%Ptw+4$j{ zMjo!>{BnQoT>Zoh_#7}%pNW}CQpz-T+^MU-zyBn*_;0lU(N`VXpn)6beEzPgKvXiM zYvfkP)9`X)PoMIYF1Me2|9rprceJN4TrYxc;u{W&*ajLeUCR*iMPMGQ}#_5 zb=sWQA7(;*$YWf3hL%n*@)7qOf7o|8aU5M0=kAFr4lge&@YSC^#f_mrZVzQA zVO>D{(IwQ^*N-$Rsi+{2x7nE2Gc5sG&X?x;Uu2DhC(b{g={ZMcJX=^CML}0b!=k=g zJY!1#a&tPhce6Ey(U=dS9nIvX*P)1yLR)JRudOwf4GIngBz<`*2eG$zK~-TQ(ZvU` ziRC6o@hBc*5(w&u!#PGo?1J+A`tz|Fm*yB^v{<1GxRJf0{=h)gW9-B>)l5N?ep10~ z3wjGn3MYc+T0^n~IF~90ZC&)h;PCL#(NWPYG)%%^{*Ntg1>~PexX6^=Z_svshNmYb z`bNww(ox!^cCpm!c!LtDug?&W_U(4$qpD<>e^#S#Uxm}@GM~pmQc6n6K3Ub1`6hn# zWAF745HObQZjs88Qc(7ut~O&6{vOfb=Hv`rAd$7^_k(-9Jr;1Pkp+{zQuYT1tqUf9 z5?RL0voVU6v%envmdzu!toH?r&z4h9k0T})LlWu7_ca-dM7Z@^^yI9aP-tS?UH}6W zc4LB+aO0TOxZi~*GWsKZxGG6)Z3IiuaMJ=s4PK#|kk&E0vI7-~v9aOUzxN>+8FhPt zIV>0H82O3fo12>U!2QkM!aC;TS?l$siE+m(!S8LHvBh@`<)fkglPM(;xO4&~`UYjd zMoMC76VhFp8Wt{n{^^!ef>sqcZ!K^{RnuQto^PVSqiJHmPN(Lom#bkBH$<)Mn*Tl*+m_pFY()6U~ zcgH7K0eiobyl$^p=$)MyU4lzglZ_=R2txb=d^L4H;|Y0GirNS_x_eVyaW^K&XXGp7 zni3mbxRg$?J-JxLVXPMDb8=$&^DmOhp}=C@PDuQX!PzdI7M!4nywIymb6o4SjtHKl zhJ=QK0vv>=;eAY@`0ukSv+Q$~;!yl~RcQ9=>I*yxR@;H7q|3Z*UmZ`-F$o<`b&{Of zvfycb_TbMAfNf-EA{stfAdj=G+>(s~v8=c>m+Y15=3KuTdZ`_dG94X)@;2xNkr4X> z5HTqF`pS?BBVDe+i8B-u<|s7A`|uLcAwCKuf-QpbAiGOjX(=ge{t)<1T2YWs-44~# z^_Pm8;MAm)>@+wePvs{?kR}{95@bwGd+L7yn!4+6DDv}+>&b8))^3=6WzmgHu1OTu zE}*0&|Jg8FKu0D*j_G1Y+eW@Rr7k`kbKRMdDz1JW;o`Cfg8E{@cQ`BzBR3S8dkY5` zA0Q#@A8(MQaEIkSBjt&f2dO zvRKyd;qUQjx7joc>muY#PR65|6#~gJo(|aJU}F!?L7fDw2>skrT2od9;Xadfox&@F z&1v6DpyOskhMScqb%TciVn9&fwdDi-VZ^VDiC@F`SC0R7IhANgtPX^9`C;Yx8!=1^bgaBk+AQ8pay ziJnIiVpf7!A~kQ&BijJv69)>x-F>|@FU1yfihM2uh4RsnR#fCXJt27(r?JP{Clk@|*n@8CFnA%UApUxv3aYih^R0vnBUaROqnG&G+H4Kd%TZ zPQrJ(#^C@S2=wQxDBiy5d{aO`K%>>mZdV&PTkTxdur(uOe^b#x`g)R0dSR75)jFEo z=`&6x_*G(t>c0TMw*5P*slX8TSIWVGfu24_0o}D!o$bh;^x)^IwYrgt;FHc>k-5^JTi2BYaN0u zqPR3T*q~gBA_QY#Xvj5ZZDMH{D)6mbqB*p!Z5h~5Mz23QJ3s90;{gtz&1!O3#1*ll zrXG#)2@%0ey|Kb&>Td!CrSs(u8yT5CFK_$Oq=1l&EWV!@RPY6^M3vnSkq)Y(8{~6` z$64esDh6yE)NosR>GGBWqeTr3wSJ6EQIX})pr*CFVhj2>mnTk)DUteO&ABp{Qb!8D z`ubXsgHS@To^a%RA5)P`krGp6uH0{Y)*pY=_&OkqoF_|(V3_K+k2eEN2G=^pgT=F7 zl9H3Tzs~frPfpVDr;J1uobt3k$+ZOpI1Cc%lnwWrkT*%`YN)Fp0lLuX-$RHe; zOj4S;(A%Wb*glkclaQ7RuI20Re!9c_TsxM=LxbXVzR^6Y zt!p|bcwzt7&yVw-SInfx(evVo3E-BV&;i-{&n?>*kF*BlmSFWvGSE$<)l{|Np(E!E zArY=7>5|+cpqS}3ot*P;A?yQJIu^!9gwrsXWq>E$YHKaeVJQMWOl-Mkvmcz5%V(aSkNE*T#HNFqw;W-YLk+bHBT)=&S-0+h<~j@LKP(Xi1e zl{EWqJ*&*I+RW63LLz+%YQ6Q+kILxI^_EFlmywZ?5ko^HmV1A`i1vzpXc9fS$6>tK z=RZ>xVFYfF!O1xdu}>(0%bbmkjZnKC5;`zYioMM!2BYt2(PA_?D54(b+0$m{84JC~;BFyC4Mj%`u@U>$CWAD__k zAxoe>CSCE58^_SgfJi;Ua^I`ai(DBo?;+i4buPU0%w#xywO9Dl4~bmS@Mv){X=w+0 z`^l*(Zm(0vZ@n~^C=>=cQI@|noLwbka`=Pp#-wrkKlKwa-G=E!M`cp4=q`Aum z_X82e$SMFZ@{95}Aj|emi-9sdB^=MTAV7oQ-*f!NCtU1&bn$mlGF(_#V7q21TU~t- z6Q-c-&g69y3U`A4kGmk|0O`v&WVO8(@UpxDsQD+o*#mAzgU+**!QV}h3aRlCl>k_UoHx^yA*Sai@D6Mipqw|y1Vh!{^EA|1!MYwNq|6G zL4SX5FN~0%fsD7E6h^sTy^TPp3}1O{!1UM8mqzQAQLhw`9U#N)>@Kga?C)dG!^5SY z@b5L$Gz!QIv9Mlt(Sv~9u*1_+tqRawX=wyDBtSC4_Heemtt}>UbZUC~?Ci{9zDm#5 zwq~PnZ>=gjHLwt*CrGkW${7MAITITbYisR9jS4tD?%mtl+m8v4Ho^MXM5#KIQft3| zPi%EwTwEgN^{7?q@G@GT0;mT_tx<@UDHcXVR?5ojMQ>Q|92_3Hxwrs`Kw4aUpnUk) z1qfSFP*93&7hXLY43aG@ET7#yuCK1;RVX~`Ao9HpBSJ%Iok#~8U=sA6{La-E7V=fq z<%KyKy?tQ;_LzS*kjw}yNON;@2Z!rriPgk;fZ1pL%`%^R@#y~?A&-ND19J}(!iL~5 z*4GEDiFCg^KLi=PP(P^i>&qFAFJe++&NV)UbF4EGszz8??8)GIap~vVXmTKyPF9*` zC3V&D5tTvZZlVV=`dJzS{oQn2*+;MkLr++(gOii96}mu?>>p60wd&r49U~;D&-MNL z_ar3ot@-c5Q9*DZZtm6)ETtKvb6e+XGpt23H4WBxwKW;D^<^g6GU+!sC|~)X@AQ4@ znionON*T0ULjp2P8o#b_Ah_QSBC1WQ49|GBTp)mOa&MW*#2ik&)qUD>AZN zop!g@*4A8R0v_kTFHXC52%Vz}q9Yr~GKxcncNUtwtlMs9x7I_m?~GV=~3~ z!s|ZxpmA_C3i`rzUPv%92?#Z|1oZBVq;{PKMiQ{qsMqcQc|j2tC1K&s-tfafAXz#x zfXC{LhJU`&;*sgZ6PkE+Ff%kahwHsjo!eJc@L4va>BozZhM9(3?cdRKZd5{c z3m~6`xGiWiV^{K73F3m?#HFvVuUxHTa%!m7cq{`N4ppPY`90skL~dX}%R`qxBA|RJ zJDKn#-M+v6o}R{9-#?sctnBm>kdUYe4lb7C6;szIosXb0=y`$vQ$>$fKMQQFUoA}J z#Lxlw4$hk;cBO~uCs{WJiRE0rXiYn&@2Tg zi;^8d#32sP{GubL_@{Y(ufHg5nZVfCxXwW)ohLZ*htb5yinOjQKL^KWIy#G?9r_E* zKZ>jFn8;-IM{AwBo*T7_g)*bp>8ER`){}YSGBP)-?T<>CnDmL+N)8&sYA_!^9=14) zTwGo<>b78E5%~440SR6JWQdP=K0g8hOhI<>Ip@xKi^E|}W**cJpN7|;-c$&LmdA0^ z)8(2CJkDnVHZ=za2f3n=lQT2ITe%wuw3^(lzkT6CSKMxnnq4*np2+GTH0rI&3kw4k zOE_JCWtoeynUDm7WBTitpc*+c@-={a=PETnXEKgbxVgIGfBXo%#+1(Kxp7sjD8#0w zsY#Zj*cMV;lVKe$kMFU)oPU7#TCVztK4N6} zmAybh3JOY>)0K~}wm3W{JZUl8QXVfh3M-@=BbD6bA47)j;e<>Be(bG*4p>M37p>{)a^oTVosT62|=K_w;q>UgB2rq=Z1 zcNghC>f9$@TM-)tY2OrAx5umv)s5^)`rbu0mTF z`y$if-r8SRR?dtA0YAP!Cvpnz6 zEt(uM^7QUO_XF{no|7LhPyQ%`U*{JWauyaFJh-ox>r62RF|Q?RM5R+n1%zlsKLzW> zS63q)en8m%oxx`EH;Y?Ouc883(%lcoeUmc$`Wm^4mXP1|2&j+&ub(b85=EollmX6@ z>?0jYm^OyZH+!YHJRa*6QSJ^a?I~O6yvZdYzw4Cq8zg99VW}V2B{N`ev97=9mHL?9 zdx-cW;!(pa11VqH-EMc>uMNL3e1^6|3|;>dxJl*B!lt3|>M5>ASgG9}u!X8%7SgHn zvQ%RT21(dn>?;;>+aK*sW_f=QN=iyW!DIe_Nk>Q3W`DkMvJ#Vd(_1~-J-=0k_0nB4 zfUB%7Ei7MWG9mOZ)eEE6%0F9)8(UpMYiFTV*7g#lWI<+Qir%QHruKa;I5=YAtdEGZ ziMrGjAoaX#2VICgC?gEqZfQO}w?rC9&CM<=ZuWh+EPM#?XJdoILi!9WEVN&$&if~F zxAZ9}C~^!V866%!C+hw5&DC#rm9bo`laZ48r7oV9tXSG>U2lIpdkv(aUF{B(1}wRh zxBpV97j^r+bEj=Ionz-C$&T*i9~IanOY83r7PikT%+E#VKOU(6`sMk!u}9A;a77f! zmpyiaRi2Y&)pM!Y^I13$rMTnu-R?B{N;bCtO<;I^eVfixI2Ym5GHo1ZFy)nC`Ft5>KN<2*7woiN9+8Wsl^ci_}PTs+zja%abgf|5d%F+|#B zM$Rpol-u>Hs0|ed<1m7LzRjf;oPBqZKeS;m5iWqsjRNJ|T@4HS3MmC*6C<^;McFeCo9}yMhzwlLQz`Ul+>5gSnBh>zdlJ8 zm6y}2kIbv3xtw2I2vM&SN@DAHH`6ZRm}~=~i&0+TT;(bA!GNbX7Aega_B!C*F&>$K zQq_tlqWdxiW@TvOK-uj*gcwJeH$l!XF3_rOP$S zv?B3)x@!ySQA%N3KqZmetM9FR5du3~FmtZMOqm zmsJmQ(wi9=T)n^%QQcUtWkYww7>}d{E9RMKtQ+veeDZp|ZmdziyL(7VnQaH$Ujn`6 zJJV0FpLKgKA9PlAlBRR~5ow)C)nWY1Om5*PxsS(9<{O5cqYHHK8^VFo<)vN#E)492s(P0CN!8fA+Ko(Y(G6eySQ-AYCu&$gm*_VM%@b|A+e)(?Ty#mB4U%;S8}YW>IDxzZ`R{1$lJ0f5Hnk8c8A1^Vdebo?2cOikd}M+F46ra0AM=sxJ{H zAAcvjzO>3g0&z=?p03w5_E$=olpsYUuO1D;3nz*<)4GqhIm#qW>J4Xjr)ynQG4=Q(Vh~;#nuC9XvGJ#*u zXN4?;fn7BtX)@BB!rdOkDBBvl?#j%vvLm{Emh|pkNR24L--34yy}|tMBT9MiBYIn$ zNs{MZ>}(w?Y=8QFn_!O7>WR3g$ylu@~cCibMD?Q**G(e;#X5Hs1!!XwcU zuzkFt7fk7sV?rbcpM9EdV$!(xxxy!*bC0Ez23)$s{sx7nW-CxBb~W)QuuwL=VssOE zQbDo$zB^Tix%Bq0ccFH!(O7c$gd~#7(cT0wdwi~UML=!PX~*m8A2`%;VywzsVPVWe z<+CrlC|d+6r67^H=F2!3ot2V zL}Jm)^%m4*!JU5H?`UZyd)_-9Ouxr|0o+2P)k@4QkNZ~t^W!ag0vXI*ZyZO*>xrA7 zE&Z%|-r|oO$VYUIB_DfLg|z8zaUg|t#qn}q*wh)?ZRClcgv4lde&0A9C#x*S8U zsHm7ne7HUhtbHjqHJ!AT6CMu6(CM@yH1fNSkF2rT6g43Hc+b%l@#Xtp0aiyFSQ09# zqV6)AcXvlqV>({XYy?sgenCE0wh~fL4MHSA=H7M$@Y?tsramm_Ev_|vs9TcO9(eqE zJ`oWpQ0xYN?(S{!{zhXNmZ#tO^}0l|vF_952OD}e`)YQfRyv7J{{9W(K@Gv(mFW6& z%1_<0H#zq%A*)O@ct)(P3e%M6|Do=!qpIxQcV86&1(62nmIi4grBS*Ylx`%XLqNK_ zyFt376cH^bL;uZhJHZJp}OmH;|FQZq@Luc4v7ukR0G5iy6Yp=MH!=c`4Ece!+Q;Z?JR);=jm zmtgJgPs)g?Y#wE_jk`ov=sT4eLMq@GX!UZ-H^wBMgIVBmErq}nJi+_YO|Eo`jTk|m~QI`%a*s2qx7*iYqk zslZ_PRqt}iuppDllaP`!UoU0Wy>4EDWVO&(Zr`t-@#!mr$6+cjD6IrWzwX8s3$pR- z<5s)f+FwUathM`22CnyVJ8TD=KN@fL+l{@R_N-OoYujuF2X6a zm}P{_T57Fcue3X{65#p)z1Sgb0rZ>u6FJ2AY=NmZ|JR$3A|Zu)>Py1h&k8~1yyA0~ zMeMXT(}mtC^I2q~SZg*zPfTSJ&KPx}#i2!PF!gvOZx&Pht%g5b4zb1c7j5Hr}#w z>4ecdzgGl>SK;fEI&pI}l~#*${{xxt?ujSD#QI&G?TL|O@A}$WdUZ&< zxxGDB;^9bfx-SYW>QXB#;(7K{SDQ~b4k#J8XRbMvi8I5KR>XClfj$92ljppSDCIT~ z1OfH9db{lvq9u>jn-DE-huBncd9+Z<5}F#HJGx-UmlToYJ|hHT?jZ(-qSv*sG(~b2 zv(=c{N?LnSaY=dCj6Px?izWa9hl6MZAvv|kHD7bxhdg!>ER)oPBX&v)t zp9Q&=x|FL!v=eD=U*cO7U?Mw>e36f9i^QtF^zk50Ub%`T6Dx zunOp6U8c>!v3y>7!r|bcC=I#YRyxE^OvD`+IFHKd!6&8^V>Xj8F~mG?N!8<}gJCDy zFf-Rr4wvmO5c8!^FNiq}I>kzyUmzY{mDOS&hlcM^Fd zM5(;zj!53TIo8}h#EwxLElYgCEN9eSmTfZX!Qx&>Tlpf#4>~x4s3UVS2zu(Y(yEh@@$ly9kVVrMfwi)SLiW+1K? z6_wJ`TKyx`4YMe(pn!&s4)U-!-~hLgTORPyY}+>TaIS8YHNT)Zgx-s)s)LS>92o}1 zBNr~D5bVXD-y{cOdFYCyD*n`{Em=D@8%gr`S^V=W7Je20kI)v$#pF0T6Mj_0nAuS( zf`mUYT8Xg#piwE8CF=hX*n--te%IM<*4yv~L* zn-Ml3A;cGHK9R#Jv=O}mXUl18=t~AqPOVQ@-`p#czO^-sZREnY0S$1m2;;v*fajk) zkve--_SqJ-J=x?~g@J@3G9-vx;`f29qN2Y~yXAPciNdylW5p4i02zCc&)GKa3w8C4 z>h|9+7%3%_jZM|TzR#^J@3jURJL2#ps~k3C`6i=zB;^lFe_*mr_V@NCerkKW8fsgX zUxs)b$8WQQ!T|Wp8h9i`y<1ngW%* zfU~7Ieh%1I#ZRNUIz#a|4t{&y1O04otPcIc*qqydEd)eQQ?cKFa31+AqKB#z6%i5k z^ zs)Sn>3&Ns@gw>c&(`jGCro{L({#has8uD#Jq?NyEK)3KY-5kg$7|xN1Yg%`!jBW1w z3KR@u6xL`oa-CC>oWbh2c-WPkFKxcnajki3(-jJn{y~YK{37U_>?imi%&|>ljI^`N zEi5#%!<0LZ{8jA_!{ws*HVEN6u8iZP$VP==+Ul17WxJPRbV} zz4dE@x}sy7E2MQ@@+W16+e$`(ByRS~_Bz{bgcZyz$l|A&{;c8sqeDYmCu`O|s-Iak z5Od^62QGUN-n}^^=9Y7{iTb?!A*Hvo73A4Mbe}geECzMQykib(4M&tC+;u7 zbW`x~RwH~GrKnb4u97*7fS2a27mDk_TzQtuAR&lqppy^2|3$(lfouJ2QVEb%X2{t)d_Eay}tD$C0HU#6$$S~Ze5rLMJ! zAyW))#9AU5#Nd?UW63nrGibkxF&gWg11Xsk!Qe-si_eYRAe2h3FNMaAouFl=UmzD6Ch!ieve>Bom&%z#G8d zll|gUM9M!XY>?qR7-`Iao}Qjul7<=4oOq3bl#EQGPf$i@aiRmRJ10+Nv^|BCf}+~4 z%=7DuV-lK{6)06xSl1^V9ey63Mp1-DZ;Lp||Iz~bz6lp(p2=?H7>0aq!pj8 z`Tes$yTNxwliX~73xy~xT&rm__r-`yU^t2JOkO)|vXVD5z&Hr-GRl3FePGJ!WMaac z##iO0LsPChBaKl@pg?|CRWs1r8{&$gri+0&`@&Y>ldOUejFLKE>|<+buy?EtxyFN) z>+Vdz)0Bcc&-c>OH}*OrQ5LEIuU+^gpfJlR2jcHGuC zY}Nal9?73*u+=x(SrzxxmfsPiUz*AnX$y7x_m9;Ft1XcAc27J`L$qbV?>)W(FkB-2 zuOJU|m3cNAK*CH)Na$}Aq;P$V;-xQOErGvNP3n!|aw<WI)~ zx8gAk5+P7;t1ot2+mc##Z@O}?aiuW(n~IU8`0R5c7Z+?@UCyl;9`2?=b}Un4O-cG& zjJ1tuCWOEF=ww)<zMHzf#K#4A8KY7M#09+eV+0#S zy?GGn3A8MDy*HW7{zkR6Z`6d7xozyAM$eiWL15)M@*n}^KL|x&vUMM*CC^`OpgF{lCEOhfgO#$t2@n5FOKQ(O=i+DRpZS0#l@q@zP)W4)G zsdI^Az&~if|2wyZ)n}7@eYpv77rXmG(%Dhv?^hDMi&Ty8(S+D;rqi{5)9I*k#eXFB z{-(kF^;0$Ay8EV^X8U|j_#FllBOM=dcjWA(c5o9lHaGS2M16zY&id)jrTQ^%|Irnd zrfm_!!GGG}Vh?{PFfvy^pbGUYZg6KtCZP4JmJD)IqwxVca@Q5 z?l?s-lp}KgVk28-;!Y7y%Is4&|S#TNQd|c37{IkiS37k6UkD63Z&iIGlA-`p->5a3S%4--ZS>Im$Q#AQ+j{URFVo-{sF};p4%(Wb;NdyfJE~ z%tS7a%YX2QXy=d5e51u8T>{OUk}xFFCW!f1HBZ_;iHL}^X3Vw^6qG0k{d+6ob=Z3( zNIgI9j*Epzl*Ot%CY3psy% z?Zd1?AOZs5M~tztRVqZ)Hu6^eDnlXCx>}uVz2gC!#LsL_>(5Mie`9UJie8B&o*(OA zFeTh&@?S9!K9xiLA{fKTYB_#+TYbXMG57}8={Q=JSGA}9H3MwjG+-M9-jB1g?y64b zi0}iR6!_W7G29$GTIe5Q=9h14IcX#Zk@K8oukIS zPou+^d(!K)kI0Ar1qmGo-_?=TOd0xH<$sHzknO)M$v*J^`jY2$w7$tgnTrldcnHWu zL+2_iXtimTixu|{cXuf-I(ruuv>j`blT+Z3alGP6QY|5!%&hP3RtJ$RW@?JNe(!SJ z4VQZGFDHx+4^Nj_3*||t{Fu@2i)RYLdMMO=G8R?G52YG=8#6QacyAQRz*5Y%GL)Mv z_q@viYv^wv{EXIA?!zva7RGET07YSriNm zJBBqL;E*&5QZ81nGS1Nb2^w(rTT=r0QZ&_dN{+YtwP9(TB#*0G4z@8o4j6i;-g9v& ze_isZvA|<-?u(I#lQ?T}I3&Db)PXh}^#Kvf^>V+~LZjMbv1Yy?iV`)W>2{$36Nia` z&l2DbK(hoJnx<%K>m3mxN6^OA@pk>;cU-0n|Gj?S*07+3yh73}ppSuw=i_IRiQxF> zS$3K`6sHc`mcne3L>?B`UE$t)}^T%A|ex>+^{=(K98O5K#@#;$ z)3mA$tIGq*rylwX6ede_DDCw=)3t#v?MoUChXhwwSEjzaG&kRa_qH49cm|oAzsG79 z1Q`q_Q|AL!o`mA^n%)i&w9u)(b2`z7c%mx0p7&3Rg%Jr&>qgwc+`+~yxIHwnnN7Ms zv|XxlV|=bXn1|9MVPn%t0#jSr1Qog~jU{z7iRhmrs;KumZq!8DkPXZETqLXwLE|n@ zA$Uxqr|6VY!ZOyU8OrH{z-Ymg0_x?=HOR9&C+I&?N3;w0P(UwtuHLOEKc9+`5t+ad z($0g$FR1X#thR)@fI1>9Q@zHtx`G+oKYdxU;@Jb3*@k^@dgL*zK&6G z?~PZ?%uKcFY%rykrII*Q^u3JnIe>h*z}S-R(i>Y`2rn%&_`63`M1<=-cU@gW_wD8G z;^F8Z9~%q6!66puv_O4B@PKy*Lu?EzvL*)^S=pgdMC=Xy%@;k0rmgJ(t8aq`2L`6A zT~uszC-W0gqUI4Q-+6uatx3|ZwR&1_Dnemqv z_sH4ImDQCbc8hx3O@?w{(fNKC$wQAs|I`0hC=I(q0yFanlcc65T|HSA=`evkw6XcnR-3)}@;vEO3`Hyq+{O5@-_ZMG2F2gt z{C{_kOX7^0UET@ljRPQsCi{Ne+?kJT`E-pd5vmi&zd12i!VKE%i!HWfV z9j+%9Mw8@I(O)d-=*S7z7TBkA)VrdCO~h-H-Ts6nS4ynPd*5eFwrHXl^3;BRDgc}L zJzw)fomJ2LJi*hBU*)SmdK@oP9Lm`UcE@KMtPZ&k8(9p`-du|%s3jC@R0)<*ibt7% z=YUA0>EwWx)nL3QpI9h?h$8jt0&`ok_dpb)L+{^a>*-i>v4xFqV+H5l^M6jwAi0xaSVmI(W$e?EEVvE&v?r9b%{7b)L>J8 zm6xAihlfH(Rn=Hue{FNu&nZKIZonDR6LV#}b@XK&7*NJ)V;Qv3u(ACvxR@~oV~8Do z&>`XWZ}E{@9B>#f(L7)zkebo%vKS5c4@aa|q}Nz2h8|R6576IQsKKTsvs>O>wQyL8 z8e`ZnVZ6i<5)!%w4$nn2?tzr|erG{RNqCVY@z8Nv6$ljmH6cp28uqf9z>>q!l7Jol zd*|ne;`8~0(3ACEK)HYq!xy#5o$Cdr^iPwBsIPYd+B~dMxZHNC-Vg*Jl9k;45rT*C zsg!7<(nbabkfjT1{y-s^eLWlz8>`$qK|kCg_np5(>D3E`$bThdVIwx3ceW&GgdXu- z-V#MdMXmD!h91Qj6;rjBIh^)NnmN=wwT-6#gDn5o@e4h89pNJA?6phzkvhl>I4k zCEbM}KXr(hbZ5>?III@bYwS$)^~d(!SFU3hzl`*Q@4?*)`1sMWwz^tMTwGWTkff*h zFUr?+-wO$OqeYERjANy~7N*l}E+UpelL_4B#_R|sWU=Ttvz%`L+(wwv>B?rROQ)Cl zXeZeQ?%M7FGBWu5C0BXB4s_qYkohD!_n{~K2NAF9)o!Lono279d}v2UWJ4X$TK`fi z3RAI}KhV(7OpJ~z?Ah*a^fPGHZ{ch)>NGd@$*rKHecd4_c-8(Y@IEU`? zsXcAyes$o|816IcvGw~%MTef_gW!-)Bgzh1t0Lg)Mz^fw>1xsgs}XNwtr=*Q3Hl#p z>mL-pDz2=oU}I&Im}D)#us;|v0KV0nP8vG8-(E2#cYiCe8APW5Elu;ECR(H2R+1OU zN7!jPjrQm2Yw)6Bxc3`l1;COG1ku@>L3W57^lnwAkx{+z7w}yLh6QswtvsLkGrE|% z0HiV2b)TM~fB=9IUfy2?erg@Pp01{!s?`-Dy|FZ+2`x);)3zH`W|Nk{PviluMwRRL zC1Lzr0V>O1ZY1gL)OJuzk+gfsxC~ym`(pc6N5ah_m>x zg^M(UjVsj*Q1^V#ZZ)lG(>4f^&3J|qRC74we!esAwRTV;MdLen zJoq~L_YjGYoG%q^w4|b9^v)Z@&QO9b$d^A}US4IUI_~%5XWOH&+n8=|CPznCH?L3U z=H|fmeL6bG-`k0nHB`rc{{|m_Z*7nKvHXm%Vbq6vsTM&Y5t|th7UxKzDr(q~9T2tA zpXO)Cs{Q6I#XA4xXJDLk>b%(Jgn*|^cGS&=R-|z%6aLznBHC2PI|M^W@~m1HqS}l*B}4qYHe2 z93A)6#oTX6jD~|)*sUa^pRYg>p7Bcy*YUV8xEVH%2de8J!9>5%b6lu&0nFdkf9(NxQ_b4ySvi_ zDgqOn%qNSktNcaE&bE4vw6whw7Bj47SabuH$E87#Fwtf{-Sr(Mt?Z-C0)+={oqFBt z6JW}(u?ox9g1>HKc|4TmOM;Bi`a`N=x$K2r|9?bO8f)XZ!o$ml4KDV_gIzhCB~C?U z)Lp*uR7zR<58>r$(EGeNIR^?o=>eFTdt0)HGu1^Dgh75H zke$U}?peYfE-trw$$LgE%ZeZP`n$WgS8{?dsi(eq{JaF-kxR3+-CgWcPA)zM0ON{I z&5JWqHpCKaMn4@*o} zKG*Bs9l)W1GMP0d72QEfm~y`H~3LR zVl;)L=4H4Ut2jAyru?fxI2&qrb-Mn8P4XfQ(tGP~>@8Sq2wtZ(7)gC>)Ct(E`+FQl z9sl+JTRrN3MRon(KWOHENh35ycp$=csVZZyY_NV9x!-#CACZTyn#+4l_i$kdAm`__ z^J})-_#W)`=2X;?Q6EFF9GXQ$5f zYMa#_Yc=aF`eyeqxK)CzlR{lp=^Dn*HemSze8^J0`ol(t+w{leL>AL_!bcZn?E*yTqZl zn^4RK8H>n4-4C~@1c?{sOG~K{Dc0u)K7&{-0jWANYPx!cep@f*i9+re$heU{W|yio zhw_$}oQ}xC_Rdal>aX5k8-tbCvoF@#wO^aHR-8|9UEuO|i^Iatau9`F||8i_-ugI@*H zOBTm@T*%~cxDHYNF2)fgzSeY4t|{Da_pP6CKH(#_C(G3P{%--BjgLI(9<7V0iDegz zNa^Gt{a{nHNd|1IRer=sCeG4Ukx6l*Q&|x2c$ckJ{oO#oY!u?(M!~`RVx%@$6`H`= zGj`}#P*6~Oty>z@l(a%u&$=6OX*(I#a((~K&hGUN*~KB}G-6xY)jpqYDn|<*uFb9; zz~Nt^$_r_P{RBP6s-I?+mKS_${wM;x&iD+##yj!{7O&-Iwa6QESacsYvQiqgp2fO1 z*5&8tuTR~)$t}y5{i~B@&J@P-K}xdD;IhZg$k!rJw1@@PHfNr@U8GJ2ItafN!&(GL z`q0dk)~o2wE!)fC{=H;#JM){1tBpfx)?@Q;``Y=O1(_?PKPVs&io<7IuI?NQ5#C%i zX9Jg3_wMHhPLO5Dfmh};JM530+2a^ZCGk0&XwMFd6Uw_uyAWmD_Xfrz$^CK}A zs;vwuB1ZCCi;~}aqy&IKXF)8SI6dCS1Kf)0uU8xWIV<}g2$C+^xks4O7@cTID5M*+ z_a~8|JHs~VoIUMUaQ-sMLN{A&5x~;cp*voArMFlSGwUIsnv+#LJJWJHQD;Oa`BUi? zztfPPxaybY_}-Ezk09P}Rd#DI*@kadoAUEj|J@dB1&deVtZY>~)4$SJuW~@p$+898 z32&Z08(Dp5l4;7p&@9ZvlQ)m84*zZU^_dA--3MtcsrxT|O_ThGGlq@3J1L06V$jcU z26olw?(=6_vjIqAeR~m+3;`C-Rk-92ihZ~^coQ*~CM&~ehp592OmWo>aW60xz;GjR zqLK8XV%ondyxhJr-l2f$@+={kp5g>H1Ox)h^G4;t8Sh3Ed0ql#w7@yi1aTqD)RIs?2nRP z&Aq?6*{l@Zyw=^M*RPh9UJ?^jFs z*!G2G7dBNE5?!dAXFNM3k9TRz}RhSX-b%+jwMTqrRd-yMUgJ zLn+L5LXC$LzZ8?Apo3pq?Xj6ULVNb^K3pS@ok*LE=p-qI$d&y-?A6}RmWgI3h8sJ9 z=5)0h5w=Th^S-Yh6QGH;n?0;ycj?wFBa`d)(2g3QT-a)0kFxQB0S`A{>%O*I~m+$X z$3J71`V9v6-=}`2QP}@vuo`aS_|?Wvk4mdJlrlJeMv?-aXP?D4L`1?~iES=*)!5FY+r_*dnWDmez8?5|=C7)!uuhr)6L^*e+>jk6Btnsx<^U)+$L%0_t6M8(x&$LdcW%mT`rRm--oI78fE0>UH~WSM?*L0ULjl2I_woVS({Ck zqBk(Ti(QVplzqvR>G8eA6+=<{Cx&+5 zc<|%))MIM(UEkyjll6%3vCl>A6nb&hyvt>}kHhW6J}4sq33*lFnu?I{z^dt7`H;^I zEeb6|sPpw!zy>pJ=S-qHkh8v7TTfTjCGY-8-gyrT3%^+BvU#-JR?k&$tUyx(Yo?C{ z)?nSYTV**pIc;r1uA{&JC%T6!mBR(Yjcpb|9u^ihRh*OI zgNZsRcV0sU_K8S~d0=tNIGGjHP{9-7HSBxCtJTzg)xJTm{xiz=E4UZ^gM(J1H6gld z#DxPJ&@Ts?(S-8yDy70HQi-f;Rr=*S)v_uo4{p~d zAQ=J#V?MW=;2;SYTU#|Ljk2#_()irKV5Wr@5B?nufU#bytf{WHj%_u>d|dB^#TVMT zezqM}Qc230n|*4PD1<;lKtQ6p3mEMX@_ns!x2t>o#CY(V`6AH1KZUPo2(y(228i6=t1);gm8F37x zib+gv&Hy+!1EL#c@04Se#X^ac_8vN-sUZ+Z2+T7kvY(TUIvbCo1X1II=M^>XrOU-( zbyXQYx8WY>%E4~mvj8#6!{TnYQidOr)8SEP#-v z*QojcugiW&`5wPL{N$N%FCL<|KBPQLET&)Z@ndZBLq67SY0h@jskZQZQX0eBeB&~@ z2(TOLF^Q4&mizUnWMZGMTka1U+*~gEZ(I$XMeAil`a^z|1K~^poAG)(FRe$bfZ3s` z=Kxz*#(XP1SE{_Pi>%sW7VCakY+4;;I@%Yi03tn%@2aeQ4zxXit*SGGK*iaF3ALO{ zsZ9RyU|XQ<0+XG@Vby(z(Q>zzT$`6ixe!OEK?4n#z)aNCO_JY3$Ht~)AAWA)-90#o z48u85F)07BDa7E*AhvE$&kN$*A+!HU}Yyl8Trwq0h)LMX-DnF~TyH2Zx-gcRwE1)-m z5Tp6vfd}A^+HZyisx|WIwpVSB4vA|1chMXfy{JGf9}Am^(cYh4LWG){TGb80r&RJL;%sk*$N>Q|lV{31?csJ+RBFFHhO_=13Yt?1?0U|iM~cd@!UjCDk8ShE{VCN8 zp#B0w16sE?wHoYW{L$ACf}p2#6<{4L&yS7S^~TZ*LK<&&zW#W+f@8PlQ&nAU=86Ss zA6>AsehMLtuJ@(lrqvKqs66}GOP?Ru+tX83U5VMi%QH7z?}mSRXuHl7#Aw*h<#aNJ z%s=p$2)2=D#_a(Vhhdf>Y(`kRFF}CHGmv`kGFxSmHZ;VV?h31F_AU6v_D;eH`O0_;=rF#)CL8eX> zQD6GgD-;{(vuD}Azkhfxu9PHVXLlAamjzuoa{x_6FfYq5I!M+jW}Z<|wg$`VtfIR> zVF4o>+Z1{=Dg(#?srL|UuQUBW$ct`aan&*BP$75}ZlJp%%Y;qaHVbziWe64N%swh` z+GTlD_skwoakpk24z?y+(xNIy@e~$RtFBZq+dA9ZLD_qBar~#w7FYuG>6L$~PYXKt z`Y~?~q=~Is0lj{Irdp#}*QqWDz|;K!z%)WA{;oqG49uvq^r4w9*Mn!K>{Tgwg@AB! zasfTrEzOllV^C~PSLAeFqe9T%uE?PZzedDLA53I3!-VhZ9!TIZLGx9kZMw7C->JU7 zzRnU00ac(PJUl$z?+K5Z0HJ|oHru@`Yj$?_r%#`X`ie3!F%=qtFYlOb;pMUz5ozUc zp;A$Pm-yPpAwJP}LuFsuF8QxM4=o7@!66HDmD}FFe%0uaM&5AV@35G;9x_73RM2CI zXr+?|YELWRDu|yfP{<=|CHqlmi3qq5lBVrl5r6s-RdgSKyk3|(kROqyT&z8=@+n*!EjB8uSoiAxEU0f*jDLkPpkQdJE~Ra zQ)j+tY!B)W41!knmleE+JKLe9KcN47F;{0xDV5A>1?6eSb9^~M3j_JH^ZtDXB$@8r`HN$7^6JVh2b1x_xAIe$gIG$foJp`b~(Nw;o zTTaV&uo$JB^?7+Nm3937y}oa*8cJK}nG8IUO@MHbiJO^g_F4Ym14M9|9vM6Ad%pj> zWv8Q~uag|_emR{QDjO<`_;UQ0OphjW5!X8~@H)fG@j(by$sUXCMc##*t6MnHFQ-+* z07Eka#6mZ}3q)-CL?*YJ1FZ(kTe3f1=yx2Jb0|b>TBuY)Vq%?T++RRlags_!;ehOb z5izw=x?~q^fk-ZdPp|`awQAwjH$jC~>5qvrwEO-2{Yu*k%(%P`C07k%A{*fO(ZRm2 zHy!T*m8(v@<40=~DM_gz77mU>X;oEiZS8SGxz)ll9jYvIdQB~@kl+wOAwdaqZgN6E z_F&MiS3SmkG_XCS{dbtVmwH`ROa4=|aZY``A-Mg~+OUX-h}t~t!A^dQlP4z7MyJ2} z;&`|zoH*l@5H6q!ve*Zgms?BP^?|M@6PGg_0wN-)&DLegABQew&U}B0)?H;X4&VV) z6z_8)O4I%x+^f40FaGP?p6B;JIk*3}(Ng~(3*HIp1jLw#UgarKB_Fji3W2?d9yo1o zx3;#PKZgUX4L~6<9A44!Nt^&!WF$O}Exaw-i{#VsIN%^sWbctVbteSDSXl}g6MEBt z-yNP*k}S3?8Iff%DqvU5wa{430aUMPu=`Ak1-~mcQ$P4!?_8h1ztTI^u9~i1+6Uv$ z3~YDFx2s`-)fuUFAUkumHO%=Lfh_~U?@wTnl1puA>0+#f1|$w(w`46CkIRGnw_xQZ zV942!`hSx|y*&VB#{TfYp-MUIcdNv6kGtb(qcqx!y{UrH`tx0IaGJ|hD#D^yf5Fzj zxVSi28Ub)#x`UukZnrn4HcbV#db9cZYT4BE^mJR2O*}T!?5R`gV#uh%hC0>i{=RoB zD-$~^%}b=_rKP1O4~ZuGALc(S@zt`ZxcKfC)fmdsH zxH9iUwQ2%9iUFX&Ol9c7XE=k1GBz4+JvgI-Z5bK9k7#26v#|I-*XdwrC<@#IC7~q% z>Qq-(2d;JZ@me97)MKB(uo5CpW7pQEBrXO*K_xJKU}JrKdTNH|!h9(G>4Ff$4?r5x za#ZdJ#`Qjw%Ww`31~kD5CiVimD%m2Qq-t>qDLigNbJZz}<@LP_`(m7n3^{XpUXU!$b@zqEh?LNjn{W@{~wEwOmk`>7XQZ~F%bxSu;yyWVV58XCq7 zl+xJP*n>V~DR5$R2IGEvaK8%A5b7`D5WqBDdq*`^0Zf5SE_$M2IGn~y*p)_zY|93` z_Q1}sYH9+vy?m{Q_x4Fs)d~h}bu1G$)qlR?TjLCtn?Y|lDTsliq0%4-H5z8toXUnW% z3_ZiXTK<}=1IMN33Y3LFiiwL5FMFphbGlp-WzpZfPij# z#A1t6A;5WPG`MRez*5X&Z4S6z-aB-4e}0ou2&?qA&taZuR}Q14RQ34u&gsqWIVxFu z7+>0Z^vaHFmo<9;(aA|nOq?PLItF5k#hn@1hSxK(9L(D^eh29IavMncMa73Zo^8pU z0Xzv>4`_gH^u+W^#L>NMaMMswP;f7vU*mYIcMuN&D=Z}?WxY)gap3+~Ec)7K2&Ipg z_}vrU@kHtFI)Sh|cxOt$}w%%x&;wsN#*!Mf{4J=D!7^yhpA3+bv zhu<0AfW}4ZfcXx4FD9Ow9UTkCXnGiZ`rR0*)AEx~uj<&wE5BM>|4}92vQw=#WV=wK zi!UuDGCc%^P2kVcDg~IET>*=vpz>DMs8q60**t4 zU*ELT#nNecSp=%UGSbo69{K|1;4^}%I^76R&$JF6pHT*~LK8o=Ztsy7vpzHF*2UBS zLr1{dRPJMO4(xAp`G*fl z`s6cQTk(K}C`u{ zj!wHi+v#*8;5Y#EYCsB9<&KJm8IAG^JmNrE$#7_5VGyG1?^Ac()Nlz>SPbliid|je zEkIb()cmO*lKCI6qDg|8=f>VaQ{=CMi{e?(EHK`QaXEh|TW$k@$WQ`a-yGAC?C#Vi zmv*Ref6K+q?iCdSpZmz#NAW*(pDMrh7-p1YgtG4fHO|aXo8!XT9Ee_g(5qFONkLe1 zPIAey@$s@BAaWLSd3p5JW4E~W-F`H!KV}FcVZG#p*RZeSN|(;&WR~E|=2MpZLCh z=9dO@;ujxk*IRmHCnjrkTHKN5=MLr@f-r%5OCkUc-zye)A9a5M5Xg&lfrA(8fK`+i zr(!25Y5IxAne>SZsJ1PnifL6!NDZf|oGM+f=5H@D)iYssjm`CW02RWH`+x9^TGtDh zW9iuf9^oQjr{PcX|6c5z6x&OEXT9?4UE|R&f3j(FWD?W?04ne*5T?dURrp%GZxs$-ylYq z0-jwtY&9!u5*%Bd!(~ZQ((F)%5af%j%)2`_@8roj&$PNTxSz`F?su4Genuq>3s zbnFJnBV7^<$q6|d$V>B>s4b438uBQn6;YU}$I@v$HLU z!!mZORG0oaMT52hviH$r)nFuIq8B5Jhld9_7m5h6^;m(e5h88x)fMOU zqbG9_h<44l)+6PB(jXRwe|?>oHdAB9ZP1fcX*j^j`c7Ek$>IVKfN3^XHg_G)dtwA& z;4|VzmiScRwKNqMT ziNq^eXL`edL?6++t%$6$qc=}B34qWTXsy(jV|BKl>FWCT6r*)7tF#- zeEw+g!;v4Zut;newG|ppSkJ>KD8y^1N>A`dYKvgBJQ*DJbd* z3Bjy`e_)_sEzgg5_H+7VPJY`9^X-o@4EayJDT*IdoG*f3gl)}K?}B2A!NDmSGdfUC zI+^o$8J_5K1a#`CvwM{?wp3HDrI}@5n&b7WXc>gfZJ1}z*0R#;;n++9qi$a4h40|- z=pO-xnLkm+alP((&s_4H=RJIWNdl?xYsY}myR%i9Ay0*Ksvq#Es9Fu;HE$Cw#c%Bn z=A6LEd&|m9uM#{-w*ksBD~P%R44b*WWkZX@avA;ac3aF-NKFSm{Ka9I0|d$$6AH1! z!Vj))!+Oe~9ZrHIWq;Af*he z499l@`$$=6E58LPJ2^Q4$o}W{LB5B(@kt$x7I)s8v;9dxHC;DXQ_5$JekD!PmFG?4 z8482|VJRU2t$Lg55RN=B6b=@KYIct1HF3}0OgTE^8td9}zUH=;j1QOSxAyOKKX4BF zfP|1a^7m^VdX6uL%+wF0McMo^=F0=id5YsZF(NlRfNwyM7K4=JwKg0!HrRH)?sPuC zIGDX1;64n-;T6p%4-T@mZ(+Fk295_*ZM2gmH16sJdXF7CnSKd(QUrjyU*|O*N(b}d zz_2cO4l_f2;~(}hSJdjjM@=Z)8IdJ+6pH@Cu@h$$_?|6!$yH>RvI#`fE=PGVD}UF0 z;B{*ProJE#fF7)z%Q0QdAX7J7(Z%Ocb%*;<%{BcmhjhQU0~b)f>ZKPQZ2n?JqfSCuy$a;rZ4C%lyh z^J!oFI7fyS>($?2ifN#a@&TQ68W-SVwnin|UJZRoKCdmS`oQ%pXKqf3^LxH>ffjPF=Ek@I7@wf1J6Y7K{yDF=t7{9`3olZ* z`EIVr6eThW*)6Zo4};vbe*B!wAI_p-4h+Z3f1* z1^k_f2v)Y0l~qV8=11#%EF#JzMS#^*uMZ@euU8A0&`*Fh`21NmoKZuN^?C0+77fBD zpH|Av!XN~MAOwo}9b8=L0cn2dodQrYV*8W8*SWX_rTtuy%;B2;M|zR90Lci~@4%>iWJ!$VLMX~Z$8-aRr+&`+ zEg46zg^Pp3<}$FyTzV=u_n}C+L{dVEfW?xI6hFIcs5OcC8cD#}Vm!+a*&0oYPhZ}q zB3(0uE3!y`)BQoHqV+TA3bo#zEXIW;y>q|&@$&ZK0P=H^x7#>|J7}Z;PXB#4K?<`$ zpvioFJ{%$z9SV)%VQN#L2guNV-t8)K1LAYMmqJZl(bp$(#qtecfK_5dx!g7sP|Zu) zOH`_>w`Ot>PdtI^*$MF8{J>PpIO&viqf#2!kCg&2aBf$}ew=2jhll*mXYtDPNaT+qF{;c8+n(qmeIx2XPJ4UY4kjvjd3i#%q^AK3 zcss+H?UBY}8)#HI6xYz#mG@q^pYJ6ISNOJSF|Qmn;`rfO2{o4cC1hDkHwQ?b&vxN+ z>pfLMmH$b znsfz_;l^a)hoA4}aOReSJOSXU1II^YcO6OK&9acDVLOwJP&{4uOJqL( zWuT6imsj4J;je%^QWefk-d{Jrw^Z~0px#MYe&4Pbe*EE621tc_?zdGY+nd?}=tbRX zTXv8?b1PI>RC$);?&aZe$eTj^KUl!8l>i+7%<8!b^-oK^8di;V6Wi*00@Y;~W#Qjj z7jJ8mGnAYD7RkZ-4L>^!fUO$@=Hlne!V``Hx8XlQyMXvro^RtBfK7m~{p1XJ-WdoO zMQR$Y^RCM}xL>2;&9!=(I3akj8WkxI85+KKfpfgX%LvE+ll`>P(PI`S8zvX%^=T)J zTZVOT21xTiQmx+{g(y)FK2+ECK9j2C0UOBq>FJek$0vP#{SL*bU%F>=l_0tqjJ5Zb z*AhVjA7wN5@+rWfun38Uc^$_$l`TIjfRbjF+<4}&e`Wk%0&cdG%SP}dyevA3Vp($N z7BowAe#{tOxG#DWC%XdK`f?S|V5&$&#y_N4;DzbaMA0dMLEDaKzSw4}vc_uf&ZV8gaSq*i4 z*^v1VaK{Lc=#)}XQ5`)nGP9u4X}0Dn;&0>YxSD6Q*-NVNFf6yE!m_?4893RK)c>9L z)gI$BUt(ZPV|E~l^s~6V*NL_6?AD_(Pb6QMU=OCfmF&==R}E;-sH%Ev&C4BG6I%`@mTaA`u+#z)M+EN5bp6}(ljc&c`>)K$-GS!TdeKV)~jE`N0W9lv5q z4&v<k=9bq5eV+|_xE?0|CN{)Wq@D?a%!8N%3Kf?d$)ld8@bSvD&Ts3 zIp^>P0fLv4bMxzxA8_K;KmMv|wDLP3glMVBR=H#JB~V-d_82I6h;>*l#@Yw;J9PeH zU&SMjfirEbudL;%h`MhVUrQBO`b0iDa`Wa8$J$E)EYqCjKPtbr zAs1jbm!x*~oZ68gZ{ED=X6r7~d9VHrm3S&15Ws5zS?e`R5!heM7Pxn(zuBPK>xk+t z2gl=z@3>u0M*B=+xd-R9l0v8_~SnT)*>$y5$mTU~Lfnz6gkuYfCMK@Krf( z4m#e#h+n>;&pI!aN!o9Yj#1ntbKgnt(OoMS9eG_{Rl?!E`wQvo=uqxg(Qo47KkRKHu!q1hf)=y42_^;~T({64(~uo%LO5LKaT{s>jsBOAqGO zd~&iNG|zshwY9Q9nE4xUIm0Qiu&-sn5}us7-_E} z50rmk0U>=7X4-LWW^bP*jv` zE`iN}K^AY=iNp~J(&QnIpF7ugYM z-YyS-Njg`R_2eXBl1tnp^x0;9x=-8YcNtk3xu=xFhQ8W~iGVTR0kfH##u?a}OxlbJSdw>z+x0DTla%LSAR0$i!xxaBpKwCgz4yb4#eeAFSmu}nG;p|SCro}R$Hg;4} zk`4g({R}I7+BxtESI@r;^q519O_s$-+4t=rF|!xWNc%+f}OH zh;>s2kny!Y(gd--I)~`2YCt_{fpLI8&~-R0oM$m5>%t23`$$Ak2ssYFvthDXy7>`& z|NFMxA*T@mvsQI^f5i1-leVDc`SyZt0eLT)!qY3Z{%cw*b4((ta~1fu3zyqTNnhL? zZUh1u+dpiD!L}j5?3Xc^(GEJ?y9&VEf&GCETRu}`8@-U^C9e~*fSj43g0KqLZChj> zO&05#+UiM+O?LG)ibFNNj7n|Qg8?EnpuS`DwX7P>&yl?9;IS=zFkC^A!0 zid0euU&_ebevAJmCo3x+Q*KE%%lJK;sggdnZb~kbk6RHaA2e{b%gf6F$Lu$Yf996s z#j!ghUbt_KzRr|++)#Y85;2MfsQ=ewj5_CzebBw-9)XYv{)d2Zt7fU}1xROH0bf&9MTIB&mTv)IVH@^C zc$o(a2$9e}UT?$3qe~qAWi?h*qhvG9H%&-L6pI|m12rRv`Bo=Gk6J*UMe@JlF7#T* ziuIWu&IAee%!k`tHWXc*E$4#*n}fam&kEK2nIv{O-tZNg!>%h*6!y> z{{-K0zzr!tr-uA=3*LZ3qY2*RD_g+z@1Or(@pVOrHCEk2<=6=@zq<{kJZo^W(lF8U znU2NYp&@=V?SY9E>kd5ik=RroAh-1yA>oe&kDmVr3$`i*g8sN|=N;Ek+CC?UtNp^X z4uEv-&DYp~voL=!1t8V0BwBwRg&2T%QNM$O%wsCzH=oPO(tU~%Lf&M8pPpA;0I_99 zp_Prz&B^f)okE(RGXkfj6SP?eFt%!2gobZ@`xb~0D8HGYi=s+M{8!@yn9X*Tz4_)o zk>9YBO|2#%Ne(3ul0j7gF6{ZyfAJEHuKOAY9eV#~g0vyaAUahX(_nec;Oo)XPk{C@ z`j7TGt&coTNL|j)#RVjrF2Pvqx>miHdVPFnW;MI-e=#6VQ6Qv_$?w|>J9z#5p4@X0 z4@3An!`(tJXC@~46w5#Kn-Q*L+_nkR1allaH~nF&;<7C?c81jD;H)H%vSPA}%jB)64TMxJIdUzJGUrAX%B91$jnl zN?=-%A8hwU^tYtcfF0U`)V$hkP6LRLQ$GLcH7WMJI?vozNa0il=Z%3z?^y_7$c?O& zhm?7q?eJy&V@o238s8c#I9MzFT8S0~m36b(f&W88rl^^nhxC%LTYq$NI`rOeiBE`p zPDy;zQLLTJV@DJ-MgL^dzBMagy0AjKf**c!&^!&pN^YzyHv$;}hqtUFwhZ%M>1~4< zzc1FG$&|N9a+mL@4AufIVdFkbx8>7oybE!`5pD}r z+WCeRBN0ZnTG0=d73v$HfO${`OAL)pEr1VNZ0GCS6h} zOU!VqI2k#)xpnH8UW7sH0O3>EttX7y6eCk{T#cX7QcjH3Zn<+I^$Ca1SEuPEE}+CN zs)j^}8#|&~`Sh4%nV1>z^e!sfL*EeP(ZVXT`{RC8qSui2*je$vu@53KOa-JT1rTS1 znR!dy9QLSRfZ+q%(%_X@i$^KB;hV;DL~HBXf815JWQ2yVa-)qu#;N}H#@ZSH4;7My z_mo$uIg3TEPY8U*%OEgCk*o3keozov46b|LYHcl@43XI};M=Wv!vk|aH#nzQ7~zaj z#0@GhU1-S5$@?H2+@|bmrtX0Csb~X~+xToCQo(wghVFT>)txhb$ETg?X^= z05wtUbK($mJHE*3`dX<@Jr?AZi(aM6kFc77j$tKJQ*f$YJ~Ctk1=xwCQw|_N1v~5% zg!s4sx604#tPDW0%=gS}0WUNOkA3J1D=SNGT5BX}r3)%mD6L@{lLQ#36|80x3|_Sn7hPepPPpUfv(f=Mi6Z zsz10XhgH@n;o8Z+J#MIoFa_;c$A?{%AwqYoBS`)S3sASkcE`t;a|7EK-WeX)l*;~P zqcRD21$>2%k56!YY-sR9@A1@f zyLq1@nmu>S`-oWj^dFjC1q9c82Tpd}Ruvwbvwh?R<1R7iv7k&#iAjl14zhQdZ}!&Q zg)Fr_tUmBVA?Y5tg8v0nIqMGO#%*u5`TY7yi#&x73oCklQM+b9U%T;qPh2_Ue#ie} z_};I9cjjQwdq1vJxfk!{*J!&h+D5usI$GejEdyEJKs5&Xn5(THPE>6$0e?5E-amZa zXUvQ&aq}Ppii`qI&FkE-q&mK=4Z(Pp-+1gVE(F@!6V_9m z0c!t1WlBv^PR0iSifd?)?*5+S)64R%Ua$)8P43N=H5~;{!$pP-{qpXlo9KP?rU`m) zK_?mH1xnr$o)pFXsQB?5N^g@$KWCUWQ0sBAX$%->e#bnFQz}70(U)G@w`kF7Xz|{C zjL@(~XQAss*CmDoc02xAG2XbPVq>6>i=g1+aGqrLVGF0=1FDv>=XdBL03oJ>5Z}9h zd8%9ERa2I}57Nh@Dx4f$-VO2O$+iAi?7aI0+_0$v?h-g>XLAmagKJDQ=2=(%LZe%I z)I)eNZw-UO1G-NjBK3OqV(L~ZC#5(7PW|T_#Lkt@-(*0vcr?tAy87zj*7^DWrkhY( z2m}Q=xsd(tFAm8Mw3rpWVC@dXqX-U=q)hqRcEp2?Cz1WYuoDPzTKHVIL$}7jLV_hC z?eL{zrm%}WA|J*jzi6oaz6Z0rzt?sli_qlxd#@Ia4(7`<1a)c6%lgtIUCw#soQq{m zZdBXDXw>R|O8sZVkHG7|11@bJ{Mf-)arO1FgyW&^=0=J63Z4X9xO2;+v3(9rd_b$t z(o4i3C`cyzb-x^m?f1SzEcIC$UW}*GSe};oYSggFZ_%s>@IDC@c2z{o)!2vNrM$wm zo!8pcM%2DzAwNvYiJ}_R*{%1ULeyFGzpH_HY(1Tg`hK9kOHBVdl(!rLL2hONu4>>g zLilp?&*6$_2mKtIT5*6@x|4~P)4#8W&q-_05n>&Sj)RCr@1mDUs8J?U|EqInqnjFi z*LUZ4pp$L^pt%8bSIQII?zw+At!+&GU4~AqD$%n2p9&V)dW-+p%fN0_PV>||*J9}V z!9Ot*ipPvz)HYjRFF`TMjG+&e-zSYG1(T+(su`eYc*i;kO zFM>YXi!@fa+(>Mky|~J#^=kl(`Q4k(Bw7e&uan)h)L8QQ57DEo41~xRF9>6iKO;n1 zM+&7^I<*tE+kW}8-o5n44e`D!SLIw1c}P>DY#e%4C&2(^d9Ev5Y`EiG-cv)<0>IhnBI zU$H@cE)e$aa-bd+8~dY5_~NaAfUcq8Cvl=dn%95mzMl(_M^U5!8vtPrkAGGPTbetc z$H8YG{^esw5VsA_FI(luU1fc<1KRLPw3~Gbn*O)@K;tg_yxZeD`c`fqBQ&~6EGA0K zs`a_Oz~@;%-pCUTi`nF{RTc%GQxg{?F+s{EL5BT z%Ar%>wlwcqvEp~(OG!D?bMdLJBam(=QfWR92 zB8$eeJ+%i?Tpp2Yw~X41DtCy}c4BG-L%P7+uH=>Q*bO zJTTzYMRm$s_xs*i(H{S9L3>C_=jG%W6{-!j4Gi4!s=LB&y9I*pRFo5)<~=U{etAy* zNRbg{E#1@8jh#tN#ZE;nBqsNi(I(NTCqM?lHe{sxxcLFFkmY2Sy#3gNx4_>C3Ehv1 zeNHC`QqGaf#?3DkN9CU37XmjJ?{fd8PoB>kpZ9tBx$y!uU)$P%U)ssTNre}~Ot_wk zqKmv=wrPHTditL#qN|l(3=ZUzh18yD`}6w{DFuZ%#k27qRnavn0TH{)Y5;4p=r(Y2 za9E$E%q&0r_6Cd*J|Tafc>}oiAW3K^1l&}8l7il6wqtqnQ`Z%EEEE;^5Tn%s;Rp@ZecYeSIG@y}mwqaTKclrPdgS;;Xo; z1-+G9{y5ynDu-_Jv6)S#j-F4`G?n21Sc{vz&*IY5$0#OT2J);MMqg;t-{2hC-|}_n$3nWrON6? zMn*5wIv(d>5}D0qy?S_h%ytaclkr)eG;15;a9Iz&cBZno0%IBbW9R?+i*4_K{Z)YlpNmtXiq z6iiEqYGV>PZw1WrYILus#hTgL7JCtO<58JBX*4yxv5TXJ_G{sgiS-J7v$nd)#~>1Y zpZT%`6(Al^q)Q7*>X~X_g8p{zPo5U!-i=NQ?EL*uH`Hzi&E@*e#G@zwj{LNzzP|iQ zXIhx#284FJdNYAO#c-y^M)L<-H{-kL*2zJQ-LnJ7F6AvJIh=;5SCnszK6_{f04pIX zsX~{>!EI|)eCVBFQ+0Or#kU73JfkBc4DK@qfMO$gfX;Ep5txJqwKt%s$=*S3)0aT- z|2ZZ98`Om6+TEvk->D5Lzx@2etB&f}omm!tIio#8l9ZIo_DHq%zoRKe$fWea$2*Qs zpX8pS>!NM$W8hOTtH}X%XIg2Rl29)e<6pIU=<7Uk({RQFl%SNoY z*Uk@{E`&6v#;gB~M{XlQ5TT0?yUk=CjOP*PtJhJ}5U&+~sAvmaWUG}j&Y!M=IDp8$ zRdks_Gly-rl1s*~H(mhLQ4`s$?MG)}amk$ejex`|Ai)5}pfE}vgMvpd5?}NbGQ<%@ z=cR3vyjCu1RV^IwRg@{nDW5Y2Tj_HSTgx9!!IkJN4A3fRvRR&Kat$IiJCE#?1HQId zQ8RDk{D^K8mO;HFq$Pd){P8EM2SM62+fmcVp_t&1lH!t8NKt7&@aY{BNu418M;C$I zXD^onww>0yOAGGss`6^BMz@k_=l+BWtsE!QuI~}1NT136r>5#C?+@B$8bTo)5&G&^ z6oup0Stg{hR#&x<%d@?ZUIyWnKcl0S^Y`An<${&Qq;7dcLffp9ij|H|QtmqD^Si$J ze!X4$#U>P`YLQM~4n|!^?cR-1{Evu;_;kV7UiA~BL7YuTYoBB_%gV)W5@rRwU0!^S zFKmawjsJ%%TyIl7=tDiU%y59$XB*!5@hYByMy4W^cO?*Eb!e`Sn#mrLb3?wYV#+z1 zWAE$cV&Z zlX>KE!s+k#_t|&Wn68iIn|#)KDTKV2mFAkvoO@2Yh{Xb;U%wGyX2w~mjZAZaSC|HY zZoN)X(~-WptG+T=5^J;gd+->1sr*`046J)TR5cD$i+yu8>&1zSge@F&tlX2;r3`JN zK1|&XK3%l$s?F`FJw?e|ki#qxmk)_CgyT9}4FKJHY!l@AC#kpWLCC+<9ZuNi8N)$# z?#rPbS=)O}ib;Zx=15e3p7Ru|O6vA1U0!8!DcnANv325BjAz(#p8uy!=ZJd^^c9%< zviHe*t#D;TB_$*jc(Ixxh=Gg*{*F@p9ve*zPVPc!X>^}0xY7!Y{QSbcLftE_!Ai*k zGQng++>pC`&bD^8gHjH%kJTm%I3~u|HH;^UVl8vSNQAai&lfwM5RMT$uxeHqs>M~> z9ZpH~+$E?n1B!-Y2vXcBrk6+!{D7dS$c*2?K(&l{Q^gT-}$I! z4F0`RKKv2D$ao9}=_es3L3WeHFD8A_7&ERNz*y8aa*Ox^z7`kDS_e@Ko#ZHNwNsv| zW}Sr2(~yqHW&@(IScnFH(`9EGldWQ?o(qM9cXWLuo7yDjjW*{p`n$7Qpe7t@xkgC%>V?KkuS?4R{lPWu?uN7U}7df|JJS zG}?qb9#-iBh|yLiZ#I)A>;800vvWKv=yVnEz3d0M1FQ8)u z4{KT)VqpFHCF@6EUUN5uK!5dTJt>3volI9e#3p{ggPVjzZfI!4f$|tD+UEE>V^17# z)c-pn8L_3`rkql8eC&oN(-aa`Q$+FI=Pt}yl&)OrfkhtBK$ z6MdR7cJ^iuT`vxn0F`!z7?VT^xAR@FrOivD{-g2q<;dV;ygWZt6OOEw`}}}G5Rx+5br85P^;wl>kqA61n_v5b#k5Sadzn@E2wIX=NMfiU_)wL(`s>}hY& z+t`J9_0PKl;|va2&0G>#x#!u{d%3nSC5>!g{$q)RUtE>JMlw=_O@S8S*OxEv{l4sC zW%Uw`D~eq6S`5ZBT8&1lP48!%?OxG2nHuLofj!7MJ$0JyJ^kkCl9l)~lE>86$ruvP9% zrS*!DK;>=^zybRZj&tmkYxi@XTP&lQ%mi+@^;iDD2LP_D{RgA zlk=3g@Kqm35mzpRu3HzG9pSW${YYc`zf)R3Cxt%MEzg$rP+ooj2tNVcj=_UVw3#?v zVM8~Fu*k8%p%f-#feANzX$l(oorP0~m>V096pBfjMLa;k+Ry>ti?WmMs@UC-)4a-x z@1&!I_?-5te@P?s!47}UE-EHQ&BC&`5+PhPF!IEQ-C4s;0WX`H55Wc^;okh8450Ov z>ijLuvKy379KqvO-ADlPrTmUQY&+33-ah2Sr zsc_p5^9*b5@@+ub=oFF)Y-4~bLC~-5L8gqg^{ul{nK{?+qI+Oqprb=vI48a?9&{{k z{^pN+K0Vv3;~|ZXXukR!k#%v!+hRqNNprIJzUTyR)H{liJmyu#XoWH6&aviQLhtu6 zuZZ47THjZ072R(>CwUq9KqYN|fpsHlUY|Ao&Jz)bmP+h5iLch;ygN8q%Pa_S`i`GIS`#>qSPg-yQ3$!ptNMX zWaz^OwQu&4U{r$|?2QfOZIf_bACGQFKlscUqi{bbyi9)obYwYBv3bOEnOF=4S9k9w zkmzL~N<&Y|XR1GB6IiAOY zgM$aa#!}%)%#aeKuAR(AqE!v?n7N#4Ee#qQ2L}b5%!^lleY>I!A;$wByjN<(kBNQ| z`5h(Zht8?}%o`x#l)HYuz?n8g??7K|P;WiKbaMqGHuSPWcjER0>ZakJ15g|Vu7ej0 z%C)vHYB+Wl)Y)ig)F6YDTp;Jvswz){QLo{d=UIPZM3g!QsGZI6+7L*OocZ)|OgN53 zwNolUhLCBZR9`@MGG@(jJ9qv0!b>Yx>C4Wb%D&XCx90SlTzBS)?uEHn?L<3F`XE~m zS!^m-8K%uq-V@$}<-S|HRafqLmal>B8VGKs)okLJwN-8mtGwi)lXjuWW=1z(tQB4q z5`gyW*UoVV#XLD(6%P9?#!JRY7jS6VdSCqhVvFwp65IudmLuRCqU84}aM|J*61?gM z-^jttcp(_0xg1qA;6@>J2eh7Q5C+0h^O3lnZ1@+8Bzwh2}blbT^VYAU(Zf0UqjNjDlP21;$ z2hm)+a)v9H8{MUzu(y2Snw%(PaW<&m2nvQx=JmD?p65=y-Xf*!Wp&4T#`u_$*x}AE zmYlIWRvU`&Bm%5p?tXOfVK;FlaXmFyKYO#o_2Gt=au zFX%eZAEay+HWuCD$mOc=K^{FSYepo%^YrI}C_QOZ^Fm=IQZ4&Mq5;8WEoatwa*3Si z&Ri-TwYX|F8Y}Dju(Pd+UD$!JtiF?lp=mUprZg_Ry@1zqT#+Kwo$Ld@7=ox z!~mD`Z-+_^VT-6>FMdj&%~qLMJE0ID?57-td>);sF5)!HkQm}H@Ao)b?a5E~vR;^V zO;epJUu3#Dhj4+gssx4=a8#supMjNpGD*7W;z$-4xP&0rC^|}CLFaWjXQW9-aP#Te z#{qbqyMvTe`Ed~i$)!?!seXIqM?Rm60}zG)g48$oww}J0X+jSQl)=tso6!g+-O}BT z5U|RI&i-=p=azm_$j$JE-e@H-3}{ZihX>owl`a6c9EH!p-M7xG00{*ZNefJDFq2;* z+0hh;z%Y_9a)Gn!FZWYPjX``i3Fk-0t~2sQpA}r^!Nf5OJPLlTA~go!$T_xbSVcGj zsc?o(ojp*FpB*3THhuiDzB^rSI{rN>(3@H^%zC0oebLABG}iNY!)6fJgYy)V^L~K1 za(Be2I02nviqeHKYnk4t3ET(mx>IY1O~hD^+Ast3MKALE@nwN`1jYGjBO7?nK*kR! zpWY~lqISh4VK@iQ$}PR^@yu*2OtdOXHyaEIk5ATaf=mVcPn1mhQc$Jk{z03*-i66v!E~FF4iX-=0iUA(Z|md`ZEmB zZ|oDXs(d_}`w6sT=z|1y#HjCC{YGyLi|Q|>rGm|Zhj5n78E6+sSmw>-HmXHyb zgxm6Y0@dwTOdW{NGsLMoD2V*C;9eII5~ADW5p_IE0y-xyrn`<;d$PC9+jh#>463IO z3QRg=*qV=``4;LFDL3%G0;LS6-6FF?TGJEaK~NR&>^RGDqxAAL-D|rL$XM~ncwdgN ztNao0JeqTlX`w!o**!9h6G7+Ll}`nk=A43n5a?QOEIux-kn>spM!GM;^QRm?XoEo4 zEO&%lA+PMwOqo9m!K{-hM^MxcI{9Y(Ba}mW0P{v{|%66S|Jrek*9*@F>d>&$LEZgY0j6Q z<7TACjd(@PW)H7Gul5ks3h{r^8WV6w5im8(W2>`-#Iq`g74Tp8PB0ZcQn~4t*;X&o zssJ={u1x%5l|^0P(RzO(G)ek+uBNe3Y9tG)S%y3w62T^9<^;yjbuseUc*Q)qLT%_| zFB}MoPbGgmeGLM^)96*3M!+$VD&SVoQ-D*fny*k<$ad{l_(_+5$xr(U1(BcPRB6)S zPl1SNRs9yzF1#=u!Q=TVEUNysi4T(!)~d4lH_s+z%bEmz{(Q&z@*Y@UMo~b0M3d|S znvV$+VTY5+6Hv{m_xM=<6l+5RLCScw5}ocJw)SG}$kB$cBp(b6gSw+@K*E;BTh~+laceX;7DkapjXy3k{KyliiR5iW zAy;R#1gwl{<0cI_6A5o&S&rSP%|AUqX9ZlX!5FjfZ-ANGYE&1+K-Al-A1ieHF1rP8 znMmcb#pdyx;k)XkMUN^!Zar(#H~lAbNI{!S>v#Ofk%wXF&B3 z1itcHNzw{KI&X`5jSOKGn?z&wVz5q)wT*dhZ!AHuI+a5rFsqxUs_hmp+N-uI2gj>@I597+Oa7cQZ}L<~Amw>|wvcNX1RW*Xkr!u<4Y=e_lN z?rN^ANIxrZ{7yLJPPeG!%B=Ol3z4afE|Y(&dbM0X7Br=vP85HLz@%II#3q-f=>K7U zf;z2_HD3A`w8(9LF}Do*kNSvp>GpKR%A~p0DCQnNo`nNnyuR0_oNg48sGzkxRhf)871!Qi^ z5(-&|aXE~<(oCBNHhmZ73!;m<3X}dx!e!41M4g8#oo0hE^|mt{ zjH*KOR_4?DwD4*t)4I|HPBfSw*ZNO~?mzmui!XiCY+iGGq~9=m**#ZnU2?I9INO_m zT6pAOtO3ua8UfVd0)4(XB|)q6a?2o;RK%d;^0Obh=1|9IB)UV$>+Hk_e_|jrTL~&L zkdW}a<2gyt)?)TmF`Iew2^cK|Z<^{qcM2`u{6#AOuYli9Nt-y9O|=DLzFsk09`!h> zVMnbQw*e9vzs2Z$w9%Iz&fhhif%G^@knE(FB4xMz#i2yka~Vb&2m;2QVG}au3||5a z#n0ks&bpxlHaSzcH&TSR3x^k(F|}XkoSwXR3mTXX(dTfwM%;K-Lu;k7mKQ1XBa?PI zOtEFK%gY&yH1^%*_1>_^;m4_jU5aFy$D0gS3i!`?l@hu4s)hz)e+g#KliTO2*BR)$ zN)#RI?nTeQ`&m6DAJt%!8;-|8^=p7(_x=5S9-qoT_MjVQmOM2V%s{}wcsb^1Qe&-7 z;A=MWHQ*Ag+6|qi1irGKqrcu$w_pDbrS=(3hyb-5aOjQdTTShv$^0l$XY-+v0?~Bu ztE816e)M2^gc51D6d!)P!Kw8GneNqCW%|T-m+Pz~Cz5|Syuk=||L3`8UE|Nm`&IDf zwKF>i`fy_i7BqRV%+eP~S}Fvuw`zz^kmSG^o>2z26 z6VDpH#Nj|AB*7?3n9Hp5tD8(rw`G~QYHko*o=Z`Tv5d)Gq8%#@xH|%FyMH|&Zv_w= zstMC)zCQc%%uY+R$<93xk2DWmWKfe-DccdAg!Y7c=~G&8`C}iy$WJG>SJGN z&h4wW=s8E!#G+dvD9pO(sgA(%JZ-mDvH>vB`7~xf1nC-pQQ2Q+S)g~QGGVPgRjNH# zt1qD6oo>j4x;rno<^Evn1W^JP_S@f1+?S9vusojk&eZm;m(}w9%{T=F#BKm*sR2UJ zLV`Fxxzh?{Ved}5UnQ=b)rG;0rbX;^S=0kp-x~Y5*>ZQ9ogD`SuQ9Qw+f_IN&o8Io zkmMT>MyLCU)XdvMhegx*t>5LAB(XIoVuX`Rl8 z58rg2CMlhl8++5Gl{hPx@K2E4D%H48K?gdwtr%-&EUb0AX&w|Hbs%-B8mE14QkOJ25VWWCcys|Zq@bezgNNno0#>@uK)J7 z87y1P$~kYN`5-OGWH=}^I*76&b;&`_i+W~LDl5zG{7Heq8_dVc%gZ1Zit}Z*jpJCS z{5proY+bKU`j^sd{~)}iW6k1=jtUB{WkP&QRo9o#$Qc})p{@FXiY-?Nf!ynjZ5Z&Z zW(Q7nevOVjd7em$8XKAvA_k)ZX9#mU9ZB!C`5;+i+ai31DZZD(9nFGpoI2! zq+mh`T^LG?+wIuow?vFSD~zzUT(sSB9Lt42$$=`z<6WPIT;rAK&TQ3et?9Vxzh&yU z|8i$)CQa7L+g(7t9eQ)!s9m*=WnODnM}eU}Vp@xBS~e|XC&@P6|KhD=SnUG3Y>>*8 z)2l^&*5}cmdf+01fU@#QDFqLYglO)3Hp7OLtn0QM@YqT@elN;B913%0&QoJG_+^=s z(vnaBVPzGbJeU9iqJba4VkA&|7S`hclnma;$~C};Ymy6|{iwLUzPoM$vM1C6)T+$G zTFw{e8Wq#y26Piximotm$hgd1cDO;;lMNI`+$pl};ntlicjkrud+q;YJ?Ps5rgJjt zZ`L0ZsAc)~>L3MdGZiySOSRmk$gMIa4a+yZ7160vA|C654zTNO)DW|_Ee}M&WA7Bq zHhku#DBs*`k+q);+aJgTKX#wX#uxQ)QP*ExFOVaEWk{DiE_Ht^i(X21v9@H-)4wC+ z##7>z&6zD-IORE+Z!XxmQaR|zFlFh6EXIWK2Ol?mJX{6~64c3*t3DY+PrzA4M$CEp zGbOjJR_*RgtT#yzyU#L0tKd-RFihHFC?!?EVsMg0my(2A?McfqF}W}1po)uYqkxsK z+wP`v*CiTlCr#H#yy&cna~Y?cRq=9fAH3ALk)U%-m4cvdwsCu(C%vd{KLZliUrRiZ zB4pa3Nw;gJw%%VGGG*wODNKi?USY)+11!vKH&I zy9q?=D4iRIkxWdiDVOTa7{=X1_Y&Q^1J8lq=~=RlDS6yuP#t4B7#X08Lf@-pMQ+E} zrJbS{QU&bJwV-~f;3@%U$8@tKKH9l2Zy*hJx)s9!0<50%_%${B6uG`I9m2l3o^xQ_ zfld`1_R!Umt}&?rpb$Ccf?fE_MDDcC+4zt ze_|S1blh(x(%9YI7g#nvVW+@pGbwjtXtbYSrd^eXfuQjDeMZ(Xywsi&uW51c-MAh1 zsu>GJaj8Tkc?S7^S~=A;95Y-L^n_d>B_}-7?&p9#13b3Xl4WV(@dOEKcWrQ#(4Mn* z+Rr4iQRXby3r$FX2#jiizbhe=7y)PISE6|=0i!40%bE(X=a%h zDh+=Cie-?#S7%%W@RtsYP1Ya$K!0S~)Gor2O}{cna){zS1|As6;82aiqDYmEqT@Mc z129s=zhZk)2-rI)0X0YvHtz(}`-DnR>8Bwd@%QJ51p*ewlTG&a>+zPAlKXhp&Z|A% z3lS(XLC1G?d6RZ?AOGpi_}O}B*p;zzYxQbS?qFfgcO+I;r+iX^g9^L5 z#d(cF$}{q8VP7w%ge}m!ZYAEXnT;NfRtH=$iD*pWK{R3_O=8n?i95yDm?f6EyHG#QvD|E^p zViA_7=;lL`!tShOX=z!z3i1A6R*D?0O82{P0`ePk#r~w4o+bx*^{@On>g3i)eE8MN z85%qaUakF7uk+KLTQCOf&Etp4opLYK2{sj*XA}3v+~#W^Z- z1e`sR^g5%Kf{h~}ki?iKWCQa+*>C>>MuYGU+wl3P1Y_!{PzoL^%D)2AB zedA+>(C?H>tQJ_W4!SZ17ZTK?OnQaZIx>t@L;>^l$i3~R;rC?d1ItuKlE-e>mheSi z_XXGZhM%rnd`au+khA(%tX#4EQ;MF{R!6Yo=ckclIbxCKJ1ND-6$M~Wog%fuuCDMs zz>Y>Bgj~L|pa$LW=X&9gp*W#AY_{g<8r`Yzv(K$yb^QuJ87Qv`d#=9UR&2bax6d7E zmx`S~-1`sJr$X}vrU*C5S|A4*0O?gP(cxlt*22s1PF~?OxL&j!hInvYtXc7@;o!5WKu6W;t6@kdFJec(awD}m(NK$ribcjzl0N8#j zcuO;qBfT=W&tn=pw)`jD%Vx9On5`LAi7a$bOzGQH&IbIF#?rSJ$_1H5!a2H)3U*y$ zow1DSlj%C#J3n_OgF{2rc#S7j!W$ESSN8(!w}~PZ7VDw)Y*bXOH9O<%#2Tz6*WRZ9 z3^e!4)vM=lrERiD)XZ|0wH%2IZCSs2C-mJq2)BByuK!#Qod33qb#TxVJYs87H0pJ& zGqilQ4->JSF6W_xnKeQfjE%fm z1%#QE^>)7uoO%lG5G~7Vz?6-DS;(^^tw|h*8LVD*iAKlW7uH)qDCi6s_?}LHa|zWE zZ@Zu7hpOn>7)mClBz9kjd;aL~Oma_XKcJ5T49FcB_%GH3Hz0r<2qWRzo@ktE3&8F_ zzo1+5iT-2Q_tE)vJB8Qg@z&VY>AuCF=UJk~t3453ZqK7t;4p!k-eR%Cp_A`ge{H1o z{iJjE55(P>PX9En8SP6v2og#87NhxlgoQKwvaZih#|RgiB_o0;{j{9Hj_z?7KrB?& zwZJ}#VFT?9qjb0yjaTqr61%BaXA|$TJR)`AvK=1Qizu}zVVs$jdA$vcNcl`AsG7`c zciK6Ao~{VWGLK@v`(YtGZ+1=1ek?wX`uFAvgpU0t$3OkPRIw}b?-uaU=8?}qrU?}~ z(Ot@mewC6!$b9x>tLQ_2I=#|^=kBNJ_ZvKxfP}qqs3P80+G&j3k>DcWqs%qt%F}rq z^LTpQQ>k7^a<^=2VteH(i^o=fPl0oOShD>=Bvm#@@Zf3ewM zF_C(kt3RISMuKgTGnT|0f&xa9e%g$o@v=nNyXyr3cPOFdh4sK}jWyzAdqx#^7f1>c zMKG6|ZuvLa20vGjq!LtE^0Po=nAWPve&N#f$K;Ck`^JG}Zb^Rhu(gz>6j*$#?bi2Q zd56lBGTRzzcA{H4-v}}{`2+}nr)&A5=2bc&y;6qbQk#JL-pTsXr=ihp$D0uPz^3Ct zEFg+ML;;}u86XX|&Vlq#N07Gu{T+v2f<*jwSVXMVX2<5#EWhO1+NF~Y1tdA~P5h@|aC}To-fXv1JKnVa!CODi_C?9fpB@5f#lR7G2C)`2S5RBn`Nd3dM}ky9DV^i+kLRJ zdD_5voYyT=*ZQuVvlsfc4GS9cy=ts)QlrVFoF4|q%~lP#@+785p{iK6c-}Rr_r@{J zK{faB$OS%heV8iNXn!}$exK&JBk$d16rbukW{}W0m=X^T4%X$9`EIIN@8s~gwt)u4 zm5ucHi4xs9=`q@E>dldXvrv~1B9>WztX6BQI_r(x`3qIUkh=LA&pH3m)q1MF5xqdC zkm9lV1rs-?@cZ$T!u=NyM^pG~ft{vgaMmKtFKP3i-(hY`ZAh6|rl~^R^X&=f4nX@Y zzfUaQ%6KMwF4 z9M-&Tg8UnqkYE|#w{uep6Maha{`Oa$!&8to@*}j#LpGZBQS{3nH#$#2h_HiVn(bfi zPkr}tUZ$G8f6pp{g@YBU_+61-;p$SDe1_nlF7iPWQqSPBbNC1u0*V|wAD>V1+ zf%vD7FQp?NNauJyy}q80bZx9RyE_U@1qR-yT>n>l-x(Cew|y%jpa`M}5(O1d1Q~wh z42q;7N|rEyl7}P=Ig0|4Gf2*ogXA0}=QKkGksODd(>rtj_xItwx^?T__u+lIRa7xG z-90_s)90MM*Is)qY|NJ(CKT1d{4c)$1PlE0^!~ROYB^!nAT(Z~Ut1f}9SzaP9M}}p zeEZ+sh5xJ1{nt0}Umtpha~QMEkz-E&X@t$|f4k@Z`jCJ9bJ_H`GXhfTP0&YgcdGcw zXYM;Q8*~K^7q_il$L^==Cn;IkvYw?wk1^e+;K#uH9#cGiy|JZY5;}DZ(1=^m&{hu? zzwz;^$`=aUpQyl{RSNAdNqG`Oi-U{P{-X6oBJF+h)s+?aX;ah5$&;8KsyjX#Mc~K4 z{Iyynh`sjgVe%oM$9yuU!mr=SR3(-?m9Jg{zvd>hq6Q<(1-`C%(|H&3;_rv*Ke<5S z``@3o?x-GVpF$)O*evTrz438w-4c_Od{JuvX zXE@?$l=ArEB&F#If}j8SS*_DPXpY>jdkvg;z|`jqRIMFm-KTcCfU*6ClxWs;nm7Oo zHmu}CIBiWn-^A%X1=fAwe#DAcC7lj{@UYxuh#iE50KlX;p611_3e#50zh~GJ)e}qS z%jdSXXLv|Q!ubB(&-&fp%7w0{UO0CtuZ@I}bkMfe)>Y2VIIehp>k@-58}u~aLPf-L z3h#qW-TP0fi*gRzc+MnFjVi7l~XRfiDl@A9F>R&5TRYB zT6M}1TQXc}Wh_fsxIiae z0-P04lj00WhD#4tZ}HDpPIR z%K%6U3@W#?&0);~M2F_)W}mI#90=u#oYXfD{b4E{h6mJj8)s8_K(ZFSHd*lg=SM88 zE8lyMllb&~7Tmvp>at3nq7Wzj!E|-0t}ENdL5_0V1Xv}!yzvu7Xj5^6_*J4`>C~An zJV%^@s1H3tb92KQ&6e<`kWs>^{`(O;}rfl@D~M5^LP+1J-p8dx++#A=gSJ%khKOO4$BoFI{Cw7tW$b;p>lTY)K& zab!>6FpVh(7z{}q>V;L~yyY~HSar-H+ixXei4)5}y{mn?8Zo7o$Ue zT{V--7N3woYsIuUAoh#MJpAKJ8^=t+?OG*4!nNB%Bw{{O(zYWdlnzps={nPhbwLji z5iT##5NY6!Y0gkj4O*sj>gvasua zVF3X9sLIp*l`)e)nSf++-7x%fth)w)JigxE$^3Ro8+Y#BJqKRUeIeoX5T!*>i&RM9 zy&6mQ;9IV{n%r1!jYF9MeoVpB$D{(wL7(_pYVEduD9r~8NINBeE!pS{Ytf9??*|Nt z-aA1X>m;fc`4~I%e7>%~IYfB-dgsV0J8fhWx(zNRL72LZx2KBsxH&l&Ks$KD z*&ee4)RFPMiV+wLN`|$$#oz(!jpaC>!}GjJY0`^cbPWcl#oO0c=9bQPyHJ9^JAtMsimIYT>bH^ zR?53(uxwZ;UCT_AY}cO`P7s6wXQ*7IcN80f6-7p0DwqUiqePJa5(f-1+N21nmkx*D zVttvi_ZR!pnaly`0BR9zjq{Ln!B1l+KbJmSo^iod#y*W86|(p}+F(NSCGxa_2F2Vm zsI#FKNzUaWCaZ~(C1#Inm|GmtJvS3T1#y^lGB#-s^d$lowWpk@exHu^kdn$CAy_$a zIUikr^0hsB8puRDb}~-OTkgtGA_bNF(o28O+yshtz`jhYrWO7=`vbDxC8YS322w;Z zM=2Aqu}E0edM~6NbOQR_#ia$AM7yk7`cwYr67>sAC!7VN>(&AT(63Vwo#7MFVt`Sh z>dzNV&E;(CjZd1E2HCjTkdAx|C^jbj>K_U!WPt4+q#D?m6H##^6LhnsfMIulTD}T2 zZcXd97E?&M88}nxusu=AvCdh0>;2V$Ho2oKRhkJu@5w{QG1jK;Qu?esHesmuY{g9cQHXkm_ zsgMg2B@)O)!3m8>mq2=yIN6B+T1mO8%2VnLle-T)RLhB+cG?THN&dzHuq2brenhXK z^0Mwl2dj8`c;>!diL%`us+Ui!!T*WmK6I6+?qyVE0j^3f-xr6j6Onf0VgqG_O)UvN zdVW)dB*E0ackhYKn15UJOD6D`8^<*=MY%fd#|4l=lrr>EJuI&W57V5*jpduoj;)>a zXwVWtRFV=BXE-Ngc@8o1Qv2z^I!C*~R)f%6CI+IOr&j+P0EvNaCx6()@yV(k|I9bk zyWAy(L|&hL1#^&QBgAAYAWi_Z9Po2&APdYOr*m(K)`5l)zbYJ=udz9)n!ITj_U!WP zSUG44c>mQLu2*Y60p!JQgARRBSgoCEsU8r94~)!y_tOi$D#oGOpG|H)Se$zEuL6;^ z2$~6m!Pxcj6s-?Zqh{~SlcMSkSnhl-!;#dmaIog0GGjKKku5gA-Hr|WDBb7gu)H~Q z303b=H83ekDhfq&$g1sS&n9jCtZ$ur8pe-J4*p1 zM4YK5GMRnZis`+l-uQXP7}B+U*jp?BVP0U=c3uV)z50{}v}Pm)LELO)@CCnTTMB=COdaws>A{DY&oB^3O5> z$%Neo$%qQkZ2Y0xdAv5&fsm+PNZr*RcPT3$>(*Z>s>+j`My=uCle~JLlESSzkyjxm z+Z)AgF~w+w{pDtq;^79*ZT#;0PHalF_h{H#Wq-Y0Fg|D@0$wVJ^#s?>T4#JKXGP72UDD7uLiZA=N|$Wrf+KRaEWtWNqpDX=|}<=iAH1rB3X0M^thw0q@txug!N2Jf_- zdRvGpL0Q91CQeO#6f{N?2SuDDh&8x60rjGEOL9U($NhWQTmb+Px*lm&1|>A5fdszO zf=cSg*I@Nly`QOeHBov!t!%wB_q0?-Yii-W5}u6P^<*b#9nULhbUU|qa7m?xco?7F zq5~a;v(~PclfhH?DPU6Cw%M2X>TI_Gk0(tdr&-JIOzcoo9n03BGY(Fm%zmj+l5zIc zmePb83JsyD4f5;QO-L74|=fT=YO+{slPSJ0GdzBdWT$Z?=9s~C% zM{5a&K1S8F+_o&&y)IC8XgRI}cxh^77gBf^+~YtX!*xs@chezx0umKXbg#jdDZ#L`c2Pchgu|NR&4fyNWBYFwCDQc(bj;zXKJ zbbmCndQt8}=LH`^KS(AxT`siDxevadoST6%1Uj(cIu&aTU+Z6m*f3} zRTrSi@NchX8dz{EnPW)va&ckdAg&!501V3L6`)F}U@x>aHFajI|F&7sZ8dKXIa?g5nCm%G`4u6k2&8ZO})MeJb*qH9V0j+P$-D^xZ%ycF}(+aL) zN{mi9N++$m50^)#n6_=Pctsd=8(jIcT#n1Oyyf8mR5{U{ekDuh(C-5zxqPeNiyCgX z9GTl5G96h`MKv-NaQ3^;x89L67zkT9CDZxzN*h4glFWVDT>v{#8DAB`+wPnX^p z%Knu!Q|oc^2d^|}2|*0vyWwk(6Zh0~=<%-r)@)g5St+yo>C#HF1=$fG?)CCz$tT-H zE<5cnjWl_8j|Nh_Rpm4T9Dyo?XGTeT!Y9k+T=~B?(|O?IOFu(Y08{7CsR-noEa$)q zW_hsr3(%Oh5hL@sKFz{a1)aApi=BU1;wvwJs!4x*f&3*wbMro|{?*ekQ2vBxOGZh8 z*qXz~NaZq-$4VGMrqYl%BE^vN!(p>Hk#9W>afMErap_&{bizYD8BLaO1TSU$*qIvL z#&dg~(?YI_xL_5S!if5qZvY-zA>u__-b7bbIQ zzwU+7Sm_ipZ20lm*fb5!x&~!lhq8FABv#w3;J>pxIraWJZfVF_E6!~(Z88pg4-{h{ z@h~8XLb~S)%lP(86}8bK89blOZn zpqF8$R-LW%j0>bBXOnqFe8R&ydre=6+B@3ZdPkb1XnSRb>uP0(I+wD0K0|Zk#Ws)W zPKC~=5z8VdV_V4_lIibpk=;!qY6T@fwhTd2g7%|VHmh?_VUwV?H{OhmM}m&!SepBSIc1vo>KZ4i2vA{k8;;#m+Ex!@|3v zNls_6V$59@Ma30XQ%2)^g7T=?{T6x1#z9${+t_ubMQPkyUm{v2^};$z4)=;Cq=iKF zV&SfS9EVHr!mqfRqTaLs$*A-gyX^vMJ5lL5E|7%Eo{k&P>10a>wr*FBxUrPm5Z6rqo^~ z07^6<>d1PUA1J}I&nBO1#O5S4dJJB^`TSY><90*6A?l4vVM6k?UD2EAx~{f>?PvYs z+EdDTR0A_QtJfe)bWu@>#3itJ``aN>>9c@aoCWXvh4)<$v0F~rTac2PIM%y=!8M`{ z$pP*x_==-^LK=&~+&Wl*avDYY7#38o3A#*WV>x1R@+$fi@8{Voe$ER9RC)CDTAJ+G zpQ&1x5Q%lt-rCJwo0p0brY5=;-<*ECZwikT&qOs@AUo9x87J!LB zpCz?`y?NW7E=YrcAMcC(!0zu|qoym4e)i_t`4mrL_l2~{UM`IbbbN)*^ipn&K8?Tl zff~w|@N{;y(+s8*nk-I+fr5+LQ==oi^VcjKmjxQ766y1lROV+v} z$(jz8h{1+Xj=STk%oSeY1WSIb2%!B;B0{rn=+2mD8!xWY4=bpg~tY=L4heIh?c0QHcwIz zxwd;p?KxvD@h0E$wv~{)&008W-%yR;{m63yw$L%X8-GegE~Rd1=xHFV`Vtg(k}pOV zD;z2X?DjGioR(^Vwa`lIh1Ck5hv7;;41jU$lH#Ojm;Gmm7M(PTF@JhvNW^%(u>zoc z_6Z~+Q_)iMAZf;MkE8wher$i*@!YCz0uWz;9m;EL3>7_mzfmoF+j6>UETQOXjbg-@ z{Ag+&r2J0mmuF0IZZe_`m-afcwg+=~K0qm`vu>vI^d-XBFYTr;XwUJ!<;w`$zr+Id zbm^MF+GxvX=%Zg{qw?ajEg^!Njz(R@cG8cp<}Qgihw>a)-DY|@FO`GZ0%O@(U^Vn> zxe|fYU=6uPiU>v@fh5m_F22&Fa8os-;Ktk2MyH5^!~CD;Ahe4M$T`emXPZBZ_j#yY zAH3`;)(VC&=Of*6I2WM>-!oYUKEqBGEtl2I2=*v!>xx4cl;uQB&fH>bErdN zSmmXhhevaiwZ2qh3IgNXt+#I%OJ{NAsc(eWm5O>t9a$(FeB^!wu!Z5T6=K-D)<1s& zT42kgN0V#$G9-R$-vy36t1?P!+`pXpY%Mpf}Q4 z%^jds%?x&2v8^BMa-|+X_>ivy~USkafOQ1P)Sn&LUoirS(;BG~A73+mt0ciVd%+8bX?F$;KKB?q_&2F_OzR|9 z#k{HzJ^)&`X6t?Ruezg{Q8#jd;navxU!)os9X=uCAIAL)zJXMVjPd>JF9dK;xU8;R zvcRT;LM$-iDpZ{jF$w+Pf%5y{ajgK*U(S*u(dx)cni~izSNUJXB8{ob`k*5Z<;kst zP7x}5HwFbICQN%o8G&x~)ZLa*XY_c=hnAh4d~tu0J9qA=`dRfCY2+CJoLTk2Y+D5{ zTW-6mIma%3l=AMGop-=}(Oth>{vc7_0TrDbta{@CAaFirBAUm(Ej0eq&G%75k!~aC zwLC!UyENHGjfGSzoSrH9w&-xY8qmp4fvk;+eF%{8)JWZpel8b(0HOgaiY0Ug zm+AD|W&?oOlZ+cT*dMpG-6fNbewE5wsvOgw`t4~_++bJ{wl|LW~)${&C3kjbl( zr&g|c2-l4I6%MO4{{mCl?Wy`33oyFKDPU2_es}#DJE4Q6eBtaGv_68QI_!l4aBx58 z%~euPi%^r4?#OlyqU4vrFv*O6V&kD26eX=nm-~DPY0;~fhs!lm4COnKX;(!)dVs{G z60@Q3xN?2Zb)%2xu}6))iWkHAU6{W*=?A!@a-snL!`}Wm0FK|IWz%N)0+5`t?ZGz- z$@~)}57*P55($Q~XxXd&=@#NJ?a+dNrdiuDn1lD%TL4Hg5mgVxn!W*HRx5S;4RT$e zqh|JrYi(=Vh-e0YU3tXAn=uo`?!YWg1Mow${S^#<6ixu6NpjO}7%>|E(a^7&NELE; zwvLN6$l_bvNAy5TWm28fWSK>JNgl8{t7$5?8OT{F?YW=u1}Bp5@uu~wwj*KB`L^<~ zBii(V*wv9=-uNp6$s!@jF{8Or73X)(54Q5^--#Q!LD6?HSE&>M$<|J0Brwgffgvi zC@dA^5?K`cwujW*Ex%-P)GD{kB-YA`Siq6-iN`0ajIce6+g2;k$}6+EU`qSqtO`mJ z1wS(SkwCc`$M|+|KqatY`Ti*(eYuC~2tA{J<)hwOjR1niIRN6KJy$(IMkqK-iMr9B zF)NjsBn!J0wYKs~U?ax_w)O{H4%bnw@(75ehC{mh-frYM9-&G|+$ld<6s3CMj9OMv z-pd?SiX)zPu|@Y$dW8`AeVB#j>;1k$Yua!rsS{&CHz3yyW*$WuGmrpM%CKoe+3^i7 zmFbY{e4sOEc`&u&*z>WV?K_;Z6)N(F^9x0~ie3PDb4kTY1_h7`^NHbNLN)Cqk>Ae# z5_0W8Omr z{||)mln$fUB``(ntsl`#JiE!PmY?mYpq`mtGUho2vUW<)i25^qE92>Z1DabjjfFl7q24 z3wcZpvo6ONV&BeiW)CGNhgCyRK!|#lC&jaMgJ52=)LkWng;9@EAC6=|^R9GAtw5Q> z*IFQYqBvVa#fhub0&A-=pV-6r)c_Ig7X=X2>y7PYUf_=gcq}MZEe`C zqpGAV09pH1_-%b$_ItKzT3=Mp1Lj()URSb+t{-}aaDO=9+xxnvvo$Z^P)0~8Sfx{6 z+k4oXD9}N@X;*03YuZtOw+^*-HIQf3E}koDB!)#@yI%HalpY?0R zpG}u^BfK25N+CR-U1Mp6Fl$fCUx>0B%Gp142sw)c%$LrqL-yg8wo#^4+%z{y$my4efPAHN+M z3II7pht4YFWaX8bVVkHZ^9v($!bUMJsjzoraTOv% z`ZWA0r+Z845ksd16O@WwfKjo((7~sZ94bv|t0XcA=#oW0OgScHj;`9~^d&<;B-y-Z zDB*;FRT*py^(O1~In$AHN@RFi%zwS38Q<90c$$*3KRP*Uj%K>UaoFVP3FLEK5IQe; zkVqRR^%|#+egLSb2QHpCJzHqkCFA*Qqkt1!!Z=iom7(?K&6`|SjPy4hT6J4?I3(o z+Z{ zgqXClgVQp=Qq}29JA!HQRI0=Gn(K&0`3|X^Vbiyaw+QBbzm-$!=ozWY_;n%Cm^%xW zoLOs|E7z}A+U}9vx`{{mAm#zp*{KE#t*&qeAei7VUK^+Gghn5QQuV!sCJhJf{ZZvd zD;=lGk5z>_u_~k;x|m!flydCQM$ll>lVW-B)~mDKX>>kZ&mq#Hs{oZ5`LmWH(=f5g zK|MW9i=Uy^J7wcSSo7>dM>9Fx^g8CI*G7-Ea3R`9=N zviv8ElYdPg`9Ih`{|PbUzlZ*Nn$drMoc}&e{~dJypJs`G#y`fG>GK8&_1|Q=qMP(0 zKCzhhF5;aikbnKZbL{@U1}kiORu6|qn2#K$+HRqc_#ejPN1{-2Y7CWfht`-Vfc(wB zVO2(x+>)wWqXPRjHOl+n{QDFBd4gy&EMkWN41@7xpytv2e_lv*B#u;F7UtciMk(pH z0Mptd>3v>x)z1S(5Td@mWX!<9YQHk_PTbmBh(D@5&yYWOwO6pq>pvif$ zVukCcFg<@hIS?X%#%#(Ua(7oxOV5WU)7+~Oel7invQSL-XrJhRj(faAbUV<`PkO?k zkjP8PE&yhWTuMnH!2QRO*q=XBd`yE-ZcskZ6^&y4y{{7YM6h; zY3lfb+bfA z8`xA(u{SE-E1iAJm}lX}w8S7MKerq5W?+zq!K)8==7QLC-6#b*; z7v`%D?}39~OEb{ZpWsR9`OFOl#)I(k#M7={?&-|Hf$ zrjC0`&ly_Di}_|!spI2$;L!lCc!gpx|KNsv4+hwCxiq>32|TG;kBReY%wAWQ7j+3M zhwH=7U+*203sJm;K2vpBxYWjMyS7>5`$8B9`lJ5=fWM@sW& zZ=qmA)7F9nA@ymdpc*vV13y~sO^xXTx(ClO$6Q;w^O($aN}d0tGqd zN$Tt{eFB@G)bH+}worA}+FsUQw)Zs-p(p*rU4s3w7%&?XcVw0cKbbya$k^($yLR22 zxgD-hHgw07>zBUeC$E(dLflBOo2OPYYgBU9Uq7jMC5XTCvJkOJbX%3l^pJN+am%uQ z`^PTvovdZXsiNVXF`ep3^z8P_i5!}B5B`cj_w73RB|wr!j&;u7pn5B{W6 zP6-ejvAy3_^?)rrEbV7nMyymPh8*lj*XL{Ix}t9z8UBZ^rSJA|BfUgT1zZMSZJRyf zTO8P9M>l#>*StQ}Qr_0!#4!No91vE>ptsBR;P<_kA4tIt!|_z^w3Bl3>+NEag*Y|3 z8lvoerzCU~727j&DbExorpJ+%^Ie!{ZQ6#X@^a(+t)#m!#JWXyI21`pD=i(a^D*!Y zY`rmCmDz&jUir+42y2*-LagQp6;DOS0G;K!`2uXc;K^(}Pg5d&e9G@?K+of4tFKSL z@O;`b=GiplA0H0SdCV&iSxmFds9zaWTUL a`$p*P1=7cj$ra$88&Gk1u|iQjum1%LHms5W literal 0 HcmV?d00001 diff --git a/docs/assets/tui/jokes-dynamic.gif b/docs/assets/tui/jokes-dynamic.gif new file mode 100644 index 0000000000000000000000000000000000000000..f0036572e8a2eeb0721d6929cafe404e0f6099ad GIT binary patch literal 78162 zcmWhzWn2?p7v9DOBR7ze9NkDW(vgl1i4lW=qDYB|N~s%c!~h9tkp@R2-HuWO6jU06 zk`@6`N%#KW`|*6Zzx#Xcea=1SdCnCxQ>3OB4m<(+3;6$HV1hwe;LLDt7$-lRTkrx8 z;sUQQkAV0^AxSP_X+B{YeuNaasGOjvtcsY7h@^t3q_U2roS>Alw3LRJ^d$iqH3?Z2 zaRn`2MJYi=Eg401Sw$^nMFSN@aXBT;i^@{M%DUppdY;Ov3aUD?Y6hBWW&vs%qUuH} z>IORM63QBS+8UM@HKoOnCi+^o>e_~qdRCfxXhS_mq`rxkzM08o7ipA@HtNb112;V* z3kxGpITJ@K6R*prb_S+as4MoiSFX#WT@2CIwrHOgGgA}utGyOzC(8gOD~~HyF3Q$8 zjCGKwwItfc)y&4}t&O?4t+R^VHGX?}OM5r0eW;D2m#xz^J14BSQ@FpAq`I@;y0e`< z#`88tY71k3!{w2NYoLScH32sTq}%O7x2s6^U}x+te{2lK<2uIEpXTYTgS+R7yLsCy z!QI>6<9f*5>q&Y(5x5%x4{oI5Zr%&KnReOtk+*LU>el1y{&yq&GkpRg9tGqY29a(B z-6I4&^SvE*GdSEo_(62=bK{T%{}6mYNL1Y2(u8~E==&*m9y|;Qdt?@#{v^EWUSxDy zRGsCcoXkg!4<09kKPE-s*7-L$f?=RPhZwQ9mixeCS~N;XH2}wlxxhI z9L|yx%|@nWKNriUH_nwHL#~FMbqL>P9Me*Q(^ps$agZIlNi>{$}mOX07~(x<8fmEg$QT zZZ&+WYG|EmJgsf+nr;3k(W3jiMIoSdp`op(vHg`~hh9+Ux7%HdEnR*8x)p&w zfc*c-@qd~CpfmskDu8Y%>WhJ1kaZt!C?1G|i<#%6UzQ9d@~ZlM9)4N+CIw+c7BFip zd;3)SYL)xj#`4i@rE4SkW=$3Eo+0mUeSX{YV!RL)!z5_lO!-iXekzL{X|DYA!nV}> zxp_;~R5hl_@5@L_^-Mi(fGlXyS~J(=`>6^$+FHBN7Q8a@+@h`SOIO&htuLc(_1|9M z>6nEq+Z&b!;xEW~jJ3a9d6Oz;QDE88_t!EInVdq9lzEmN-YY7G5{b39^;JJ z_dQ*Ie=ZIr(u8e#yN`cue5&>w@9jDLySFl0X!EM~{PgJ8_P6m@ul|FQUV0G^=JqWL z7j<6*favyC0rVH-a^m4p-mhWD1+IJ-xxkg!eqWfoKC7#U^-v>gn2KS|)B`a6cEj2b*pW2$re9v%jy7fI1bK{~n zh(`^50d&DvW-aG>)~&T%--^n$ynxnC$t-q+(kBRW_pSBkVQZD^1yO%C*9-9)30TW3 z^nM$~@sd>=B}p1v8>K=Xdmlj@hJKsnIX9{{EAsDe$&i>^udlu+%ktZ*q*PRGRVmzm z%RyiBnkKtl(>(3BT^nRxl}>kWd273#N-ww5Fc{GeNR#Pv-Dw=t*xqTHkR%(JgE{$r zw9MY9{?YpRWMj*0=APVc`)ZbdP)Bir!)C`$>-KKfUd0x`eEPNj&z_^T>PrQkdE))O z00#LzDp*biWG=y3v)9j}xzi9QfpA}DGzsoAVVA;FNK#`;D+%0)Cj_#_e38oQ0qK>_ zx)he0{DaYW(hJIkpe{f;>DXAkmdNu;w9cE zI*%Inep>f3azz~WGSbPC_eaEK00zgCi0Iw$*wXCX(;SCxQTn8mZbL(|w(W<1a(`l2 z&xk!X?U#Q8n%TdZFSo(I?1X85ni$WKQe*uf8j)OT0$5P*FtQv5_C!ACjmTzfu=0(m z-zcJK?8koC^fHVMBQe|q#2rhZ;1!X^#ftFDSE1g4YeoRB0N>(6yW!9aqJ2MThGF7j zIiitOD7=uR2>qu`149I-2*@|5>)1}2_-lKDV?8^;in_#A5?071>#PGd{t$zmj5&p; z#(pL3N5?6Bk+jF-8+#17q{fV;GJKiT$o;@eNlROjp>LSZ>mR?0970G94|B1mibD=3 zc;Gormwcu9SXf-u)DBspl0W#9)tn(Rlf4&OFI~93@#V}q*Zf$78d?#*BKHwzI;5vh}h-{tRd|(lD zR)7VqWIA4%QC_V2oXhiN0%PUN5UJ}_K{HhJQ6IH1WwBD$BMspFanh%~`ZG}x0E9vh zLw__a5=ZDY9=q<9E12N5$59{#dEaU*b`HX_WWbdCE3+Px%GWjB`?vg%OYU9OCKE|; zhhoRV29*MZ7R4P8T}nK+z{{c^#5(gDyr^2Nv{5dzrOBil#)nFqNy&*OkclM%+6al1 zBGi*7rJQUmGCJbuxxie9xO$|QJ!7Y9v%N2c(;UDO9r!|zx}sJ2N9m=m z1Tet=t=44cy=SUE3cFCIn6Jro{_o23WjdXT|FAb3-c&c?NFK$4o1MBiIYie75fj@^ z8}(z&m2*MafQ98Jov+kay>QD4Pn@CmLRs_HUWrB_zfl>8S@3$1{Jr_JV|sQmd|S_5LqoH_1D^u%6 zX${WF*#l6{rEv#-S5Aauuiemb!2N#P!u0OiQU9We$UntJJ@`-MA_pW#1UnwRQ1u}? z{2lShh0ZUG`%7H1ruf*N++h>NqcQ00CG<&`$UCMw8dSg)@k_U_n86Uv<=Z>GYFr$5 zWiU8UB8td9@~0OCi%9++@SSlghw(F8X5w>I5V6Z#>-5V@%JWD+Zkg2qMxb3$U6YvK zEnP?c(#Z*;DS%j6ME6MoH&rX?7Z!EnE$6bLE)Dg46|t=^>?Z8ea&Jnq%)_>sK~}YOtE#BQ$h#ba*}_( z`|tUXzz>3gaCqvSs{v8dyW$6OzWMltmq%ZZX}cruyyXf|}Bd2#gkiO{Fw z?y+E=(+y{rWaUb4bMbYNCcla@UOV67jRt&{;{3z>?xE2=;SUgW@Pn%LjtxPr&TkBl zi^VVe+Y6`Dy#h`N>)$S_Nlxh=;C#jY+T!0q&UjR>bUpj1|G!^FFugWpA^UjZze9@6 z!v=H;`={!EzZ+7{D>0ARXGZ`1X&--B>U*1gVf)`-Donp1%#-~aGwo>DrZ+3zhJ8hj zc07^tC_U#g`?>|~WOiIXiE@d3+n;v22zy0)lpyu*;2G^qZ26IKcgnv%U7p8VanRFm zHnfu!{eLj6)PH}+Y5z|Ds{?rPAS51)!PAG~p*eV_cKjJZ3A~4g^Ab3a1WpWrJB+}a zL*Q#C2+R_MjtB_eXi;ReI3`*$ELu7zTDCn}el}Y1C|Zd(MgxCw#QL?z2F%6=9mNLo#)Tl`YGCn>hp4=XvG#mefb`+oLOCaUI<9HLY!V+?F67t#;@@ErdkqJ<{gaRbF3`4F6 zBU5t7J{$O|S#sSGxq&ya5t%3iB{PVSn{yI7+Y`HI6MNBdt-kQ~qr^c>((ACK;hZE5 z-Xw@}(#TQL1aI<3Wb&KgBszA$dvx-Ad-CVm}ws_*yF56;n^{{*|=Ld9tk-FmzL` zx4ts3&E;9oabCsovmlxL)`Yy?guH=-{MQ%rYdi8gb91S4d2iq5b>(JG$>h8be_kG* zAECv>mYQfv3(vU7o{4fHKvA$gTh=K!+s<*p&Rf>K# zN4E-p$P}G37SfIjfK`QH*&+tMLWp@Gb5+rw+@gOMi@CImVIu{s5rr(~MHjV;F3cD6 z%9fm&l>knP`N<_hekIV661J@p0omfS$`TRTQYofVHSJO)xm1g(NSCQ}6IV>%S)wst zVscV)g|C#Ss?==06uMQme_U!MTW+ycYQ^9lg z%%X3gV33K7pp%N=&S*mvj1`r*l2Bo$6{@${kD>mu?n4A5z$Gh zIH_tNr&DATSIi2yfmQ2fguYa^m-E%VooRXFVGMl+bbQq2*j zMt!bo%(Zs9Dy4}pu|>94-mI3_7pRB_Ein=xi=efLIw%St8eF&L`hpKvCz4vn9uII! z1>Z9Vd>^S(Os(4y7>@l^>St9YQShqg_7G+QWam`=T` z=@3o_rZ%ZBK*4Y}-BT8BeEm4J=>ZC$&D^Zd+%2weYmJU@ZWi{H?dU{@aVLEwShK1neiG z+tZ)*HFKNyUJC~r;;B>T5Zv{+s14TDgUIjsvOxakRsB$+LcGL^Dg&tHhsz)-eRP`#$LsSDgG~^-3v(6{~H8t%mC#j6r61y%d^(;@o z>KmvKYTG+N-zgOa3GU|l42w{D&7TkOjD+2W6aFgo94}{^Ag&Zx2uw> z`={-ilqZ^X{Mpo4nm5gx7g0@zd(2x~?FO`GO(^E!tkEXuUZ?sgiTl2Fe)YYrV{;z$Lo!B{u{Z^0QGH< z)hP>Amx(aONrPz6^ctervfVx~ed%SV46tLM zXZ)Sp&nDR0C(bQe6n1L3rKxTH>Yj+^;_IDEQFfkj^Mb;v1LoZ5CXk@;g}>lUJ+ z`}w!WTMK2-&+Pk+N(+RQ$QV92-Cx;Qn;5#F0735ygD2;UcSgRIV%lSw*#QOZ9LPm@ z?~*`4EXQsFr^lNJ)@Z)3OOlV4-Hw)?^DejPE(^C;OAD>26p;FuY6s_+`ybZ4)n3v4 zx?+Kzsyt~FEm$cTnbCi=iY|zeeV-sNG+`{%Wcnx?UIad}0;r)tNfbKFlW2wp#KmEt z7k@OQ2+R&3ic?28hk?EYG1u6DX8+dIEW4VS7LDFl>3@k9$3Yq3gy4og8w$OfM@$5K zO_D+v8%%$Z1_j3{MMH2<8QW;vCITCPfh`CewfOO*CI-T_A)Et>XIt0oS$#IUs{3Qv zb~ie_cO4Ez+lE2agJWU}qTgSKGFubK?>C-!M0+DX^6>&=7uVpvo7`c71{;7XwrK5! zjiR7WC3Oj91v3?ji+1`1eR>9ODi9V1Fasq5-vc^<5SKhK4xdp!aYPr^Q81 zG(_B%4w&)-Z2JTI3;+AkPlwc>-T;OuiAJTx^&>w>elG#yNEZv=fZEdC1Tes8_%@n{ zg5+%i0|4v?-{t@Jp;tVeO@p<K{HB2Q{~4hy^h4Kpr4KM{xTr?TtEa`1*C(o)h@MW=X6RIbJu zkWefMYP@~6f{0)i5hcpX3pQD2C{Fj9FTy6>uH3rZb!yA8#-%0b`~1|lbA#8=6A8EJ z9hc@?Q+3bHFEP5c-lvF$x!<3dYi~B z{ZLuk*3wL_XwCtzUo60cY2OT|8_=vdY3WgT=&^d!G5@QCH3%)q>w zYJAhFiWmZt$zngC#>_(ADztf7rHm5e$jp8Bb?38!lorNbby?~%&aRu zn&IBWVWGgdc%U~EWeh+IHfdAgpzLjBQRUFRWB~0si`MEyCA!EkB_rb?i7Mg95!mH^m z$9N~I|Cvp*H@-ht?Ha0V>U*50jOTmR`LfFL3i%^pmgUYO66DvwA|jCz(1-^09|mfJ zI2ISNVa#M`{DYY8ezlM8s$?SbNe`Y9qGj=``%BI8z<-L!ufA{0?a$jhW@q0$aNrFV ztnL2x$0mK5kJHzTPzB}= zF^geSsX|@fv+#iz_}(Fm>To$d0g+!)U1(L+ttWmpP1COOK5Z5AF4Ph(H~g*Y-&?L# z#;OOR9+gT&4SnerZ}+ijZlv!!*X0CQRQd7%dJ2~q@-oZ)Dr;5eJHew=Om)eGfsr)- z=53c4mZz=#KCwnAEotvL`YPLrUZKcN%lMRac#Cv!RfB-~_sM&~cjZ5J_F3EyzU&x9E-BH~8`+fN?{~-gcDn`Ft=Q8v`;N`y&k-J@g|3&V-+0u^k z>g)C2@f{VaQK}xq=>n6wS5HB6ADg0KY}fhQ@L&$g3i)5{j{EnIIi;cMnQ|L_Kyivu zDxNc4Q)yi%7y$$+;>z&Pt2OTV^3pcWrja1`CAc~o08XOTf)yJG4Yv|F5Q{H$8B=|s z$|DN`+1h2{)#5bQCoDwHi*14mvTBHV=4ag9MpQgl`l$`aC0p%z=?xJ3WE#i)WxQjW zv6?fU`ay%M`{*#m;=DAOJ{7>EyjvM~qdeFuA@%DA|81oG44Ln~48L;~ac;;Qs zCy3ies2?JZS;EoAlJ;qGeBVSZuIqOd!CbeR*iWmX0R_Mj1P?la@NpGyt>L3Qnwy@% z)Ib38ZGs|{CN7?EXG)pNi0%^%%y+Y;7@#KRA4I79Nuh048o{v+;rTIjN)ix7lk6s9 ze1ie5yf>7!<&)TlJ^b3-$Kmyb%(#%NIE20rl)Nh1Qz=EwoRdMP26p3VD~ zJKMz7n9mN0h7NpsL(u>Ru$mlnSQPlE%7nCBRw-myWpAaPUzt8wF24T-&9sQ8Xme3S zCH!69MNAvTa@O9>%`)>*6KlE$36%S2z>36~4Em6mWDo{d`^hyR>LP2RYju1mJvRq* zI+WxSa82+OL#wXjYV;Pl1^66c-(GhKqfLPdoRnpr?k};vD&+$m7SVsSzOSHNLKS#O~a1?h-7C<7}17{G$K&Qf}?)gLjc0hZW8}uZL>y56F2mrfHVn(gKL-clBI3 zL&-tI1|OQGe>0k%c_k?d6#FNe#heNVWmAeSHth$9=`QJuhk@zPApkzzzJ4+R$Q6|Z z7tDu?upANCgUP9Msi+}2>kEtp4WH7GIOr=2fPH*~8OPpDS^h8(3sVP35aZ~?CG-|3 z1iV&Br7g0@$)X0Dqe)j?Qtfz@KJZ zqD5rWsmH!)w%lC>3sC5X`5&7gnCl(9Vgrs#Px#~eFnxBeQ1*oecN9-21#iI8Xs9Ilmvau`s+Wnm&mY8~X# z3wxmVwzpVbtlEoem0M_jB7IFSOY6OTCc&qxQ;AR1pZ!qiZL8sVKc4x^X~Qy$`V~1& zd);deLs`FX<$gpxb%?r&}f9(Ppl|9!Xc$p8B{ z+QUIP?)^AN-9E%^_>i2jGQ)(A;cqnez-O~QMs`8)e_TGYlB z&y!Ct9{pCitG83#570%^5E$u4A0ADF+w(pH$6@bkqM)65v34vlvEmt+M!_=h-NNp37kDLLK3c>~_YfX@# zlO!8Nf-{CB7YV`rYB@H#Jd>lw`xF^Ng;?|IVKIbC3YB?P!bb;e9R@MoOQypRosYmc zH%38(AxATrc~RedQU6K|p!!rb-PSaF#PLswQetz@~fTz$W8b^q|Qk$uw#Zoj+(^2D6+r#==!RbcjcE1I=P2 z6AC2xs+t`&#sp6KHjLCeq6=FPml#z0I03nuaV4hxwN)7tJ(Z;C+ebf1vKIq9z0l)4 zOf-O#{`-I}bUM14gnXC{S?&OgjIMyFB#O}h?Yc3v`hr2FuZFlBfTK&NWU<9<%p{pP znc26`fWo9lf%psf(KNa%MwKCPcJO8X9jG2~Id|lE!peVuliLp^@$;9;F5#-r;CnG~69xA4U|a zG(%28N`~J&D)9M7e;JFK!RP%$ zz-n@EVp}x@>>z*!O^}|SQnM!^vs4or`of*3?Zd|L`b{PYrOEgFO_qO+l}wPd;D-5Q zrVZ^a54Oqux|Ue5FT{#S0g$eu!p1BU9JFVl*285? z=3ykz;+tCLeo$)ryEC(LalAz$%N2nH^GWvd$TqcNaMsQkUCg^Z0 zIcDUNIHO6T0q7`3L=9?~jTIsxnsCqoAx$c!(CAFK}ryK7&8((f@BsvH*UF-$%=5 zAp=&@zZ*Ep?d58l{rxNzuo~|1S9g#jjyvoj{vCD}uk}9-Nl#Fp`o}mbHw$Tfni+gz zUY7hV$-zl3!|wA{Q`LBbFwM(DPtZOoj;Bo)qfgB@-n!^yG9LkPPtopCnl$71z=3h( z!*NHkcD{iaX9^_f?YI%{ttFKt7#{7s01Yiw%f4zC!#j~Ao>10pXL)td2xGS6-h%AG zyQ{}zxkfYtTOY}E$yg#e9URS{!NO|BV~!@WBBo0jO)VWq%&zGuW?a0Z6VG}?XK(8$ zS~InhVXpImL`xKKM$5%dPRa@fJNYWur zWhU?0v7N%h^TNnH;T$`)?@Y27h&Arh4F?xloJ%&zB{$H)zh=%Sv7y4p^^Y__dBgtU z2a?gmyzpKwjB3g#0ifq4@=qz-sY8pumpjU}1P>;(CA)Pv8c+Rdwi$k^7)CT`S37qd zsN}M#)-ylDjie#$3O@i%!@vU6g&06BoQ>=jn6z?yBhB=cOTUh3x2_+AC@dbDQhHrv&GZ- zWL9lf)`S@H!qkGWG{8ueqfMT%LLPr}Dn=yUQFPK>OD`U@XbDDq)l%{(B#n4{7)xPY zO!cWtGbv23B|nACkLkLN2N)FYH|N$~Y3p%m-Iy!1njQeLQ?3szONk@0-51Rb6&{0)O0!?vGK3B`=@}wy| z>Z**!100O8YTDUJYyG8` z#1Cq}D8_%F9tzWHs-HDP^SwdIE9I1LF*(;jVd~hX&PqmHj{t5}cJZYat_qF2=;1Qn ztgVM2m|u6Gp9NSA(B)frzb;>FX~5M!_4+BG(H_9#PJt*>0Lp*?)Td^(Crp$;wr&#e z^B~@Y;M>&$n6^w8Gr4OA2JRJbmi{Wv9)Jkk`KI>unA)g@ipIv!f$7uT!&0}Edfoe2& z(mTg$i0rKI%n{yFDVi&c?oJsi2RcT60J0;FSG4U)o^Gsy8xe>c?c~Lb3Uxq{Gj>75Q4=)zECx71JAX6KDGEK#j8lblp;gLZ?QpwU>=r=vRXyhXck zEM9Snq!}1|?UbPS5aJQ^vv@TNTDyCM0bcI06{~3e$2MT|2`Pqa*?_j03|!+PHYakb zvle2U`1KsWx6os6$3SXTqc8$lxjQhtZ*r) zZAU#u6K;-Y>L+(DG!)IR$6h;Vq;$!Lw3}XKc?7hhK?azl){W}`cNMgeb>@5Ew1ceW zgQkWMf-2JVRwI|~uPQV^TXRWOIDun?35u=-9|2%0NOtRIday*+_5)&gNVO93PJ}Kg z1Rx<>c7^A~Ri?xHB7_F!kjnxG%d!V%+94h02V3)7T`PC(9^b>H{C+ETZ&~Fx?@~Y| zdU2@}Yt3u#Lc529{rOe$d#UkvTS!`ao~k3y{TsLM-+X-ESoHpq%Kb6JKMhbi6a4+a zZ})?K-mkg?;l!x={Zw#pzJL4jgHW3X_txurE$i=OXNCN2^YMHTQU4(F)n7{LpU)8w zHpma&J$n!Z3nK`J`OZ98SpK`;_~$@0EcSL-T=qR$OuYheoY_5v3HvxKX*?`hvp)Vs zZ9>W=Qel0vaCrKqoRs7F5(W|YgZ1e8OkqZiB8J?b;f1vD z#${jx^!E?@@WX5jNI83bGpegCs=_9!qCWCE{Or9{)H_<#*sGJb zu!qA8Q4N>RYuiqO@sU&6XCE2Pr#;W-ESymdCMSMT*Y~*^f$&O2?T*5V3xg*kI`61K8sr>Bk4c zj}PnVgOIe}&W{ftJU)!09o(k<=AoTt(+*xdK4_!;Wr+6!F*vQ52IJaeKphtya%{Z@ zVqh>82TY)7Up!cut!87Q#FU6IVp?sVD0v$#eks~m>!XBm4ySWP+3~?O%Y0Rz8>@34 zZdfO1lIXu6Cw=YG-~=Jd8T*^26?(=04#U&83@Zg|t5&PjtDWmTnaQk)E!%T1g%a%L zpG_+)RCdY3DgJ*IzjjCbJ@~Qx_tGLYnqfwPowlg7JOJWW4ca+UUKvcVfY${atE`RX zY2Mx4IadAeOjn*N2A-&GO;$NK1^qZt-v6vCr4tb225JwY2n}7OB1_$ zoW-A7X&;Mc*iAnWPfz|WEs^Eo*CCOOJ)q5aWv0n&O62t?)vY`Dbp@U0H1!iSG;-pmX;(ULAE@kMOh!i&mKJo&F5NSCFMIb_P7+UF&dXOPox zmE}7{$W#;s$;wt{N62ng7U#KERaAD4_`RsF)Ap}!cx3Kh(`sHNSJCJ`eV{x0pa41Xe98m@4{7i z@(|BWf&JG4p6>f^5OGQS!?5hnF9)PA(cD$uidA^B14;fQmINKjnTao|uR`*+X zQ-A%TZs@RxcD8=Ip=b@I8pIrt^C=elP}MWjlmu>X^eu*qB{ynXp zGWY8|>aqUGCXBZ?bH&rC_hf(c^5gKGL|Vf6&Am^rF4N90-K2TTuk)NA*W>AR5dnZ% z$+PfSJTwXc7CX8KVQRRDS8Uib>aX#rS|XU#m5~Ob&9ph7L^0X8IBaRcS!8MRxUL6M)$xXHB;?+E1Qg&u|~Q}jKg)Q zZD{?&^R$f8=Ib(c;pUbe92td44l}f{feJuG>LsxM?5Bchl?or$Z2c7prE({APqqs; zdem+xy}WOka2|5&?c}`b)oDvF#j7{pm#wLioUHt1Rr3ZvOHNWdEN+Yb%KM@wrS?JQ zowv%<=bv?@hT7@Hk)1CK{**nR*>xC=JZLJsQ}W_6o$Q1vFtmtXPdbZ zQGp@vHBjOrQIVxfaGE2bCUePHp=>J~OkD&#C^qo;8}0VxYkA!R)?JTNa=zw9^owXN zk_SG~Ws+q^@fn9D5I5oS$v6v{GC^XKwN3osw8m9W!Lx<3&#pM4TEp0XVA%++znZhP zX5O)Qd|`fms-01i*huj~7bO;^b6<e6<^x8QETv9d%0v5!}iNKSI0%MOwPx!(gZ1 z{my#v+%Q%Rkd((ua^^hbt=urNl?^~=&AW7=j2azuTX&h`0*b|!d+5T>LClrzXwERI z1<=pVOXTh{!-G2jDY74!bMy}=zX+IX0-WjNC}Pb&qQ?BE=c?;m9Le3Qr5m33YO;7W`@VG@0Q$xxZQ_5lA(&`Tj04ITv@X8JUE3~ z;=9gHXj~cikf?Qk9^R;nlbL-3h>`}cn)HRCdwnf+;ekB#i-h<0WB@{;=kfH3OYD^1 zCT!#Lgh0)_PbNWoK+99cOLw&{+-cp*etPZ|^QwP1vm>-ZQ}C0UTm;+wzP4U|_v|xQ z%xkqZ6)vRmj^<^Zg2KpQh0i{d9D*7rp6F? zl)rXj&e?OUgTz$irLz=~urq*3z5@Gn66J+r`v1*0)nn zL#Waf;O5LzK^>28N8+Yj6SN$>U-IB|g}8xVx-gNQq1a2n$q0gQ&X=u)^7|FSBIF!4 zCs^lyllDDqe-O@(x^rw$3X}Xx9gn{LD3Ln%{$Y6k0?n)Y@zFry@rbV}zE$xthIs9~ zWV*$sb8T%k$&0GZldG@a0yF0^FK2fglT> zY#Kt~0Je54c3247=^;*kk$VGVUY?CD&wj%WxGMtieESriHvgc97u+BWG+xgA0+E>> zlBw{<)`*VD;1p^=bcYbnS|OPlp*zO~7)KABS>~GKRH{#oV#cxz2Wo+xr%c4z1Dfo4 zy?^y0!Sk&k&^X5dI3sVrAa|DUATov^7Glvn9*C75cB=43bQ3!bK-3ab+cLarRq7Ec z>aoWI^!3CBf5WOdMembb?}-4V=X9orV#B?x&r5GFad90kUs7BJ?uY=pm#?WW`Ywq! zrSW<3_6aymU$TG3TSia>@WlQwq0=u?sLRwSS=HrB@tYcwE15E>SYmMHQ9N?Wv+}}G zr(c_8N*{^?&&o`^uN&4CG}adU)?8h1ute6{~Sr zA0=;zs~oYH^SGQ$Fj#jVjCmIC>k`E=Zyj??)MmetDE>C#8q@o70U?lq{Q~`>7aIq4 z=B0yjv?y@GBQ+ua^6QVGWA>1TD^jWWaAmwC2jD2dT{4vR&7|Ms#xz7{dFY0@=U*T< z(4k;XqEJy6*iw7r;Lg;8OpHQQH2n=j{)`;I_g=u>HG$V_imu$48+krlFL>3&fRn5A zXFwVFx~@|}hfgL(vh3B4ql?%6E};D&2te}$s)Hyn~0ADE3l_TUddmH#%esB`rk;x^yn z`RP#JB9d7{de)fW%a?@+-<5up&chY3(a7$L5T!Yai(Ze=<32K*B1k&H&AmgSr#B^d zf#lDh9Hou!mt{CfxE7SR5L~qlQR(Sf+Pfu@j@&^Za~^v>cPd{f2KXpAWd7%6GA%BR zycGw^-@L2ghIxM-Um$V4D(C)QDnje}P z65~37)F(FzDW0@j36oxI6VR}3IW;dx`eu2SuhI) zwe}^S%|KiKMbS zsng@{+OB?n+;T?Kpvr$JVE5LGpzJ1Bnp3j|cOPU6%R5)4%P8-+e3E9nzk7KqA}nJ4B}e=*-nV`_NPJeu7|jn^ zw|ui(9o4 zvN(^>H5U~j839A07C(F%l2|9u!WD#NnVvD@UYeHhh?*I<@?Kdp*(NV6(ffM&ZH@Hw zf6}isXx)&Vz42Y7S~2PQ;;tx5SP(YK@NZ8^Ak%EwxiHXI@g}Cm*)Q<>hYhSP!L^6E9GfYqOJ9+XAe;C$d*`a-}%W_9geTq&{vT z>PvwKJmz)c9@qCwLi*{IvKI=rH#MBM{#_Gpdnsd2pli;cXe_~m0@RDgkSRg$A!V zxBB?MZjhz|fCahc&Zf%3O^&_M>`Ciegl4o?FAn zKMxUtuUqu0uLfl;^r3uQrlYj+^Da&b)TsyO_i%xLJKiOpJU4N$*15hZID#kO?N5w$ ztpW#a{Xwqcx~M-%T?5BZc5Qp==v=szk+*coWWBujr%9%pD77iwKN55axR>ivJBPKQ zh^-7saj$z5TBFDsxa~~0?IC)Eh@qeQRD$7Oc3iZOJXpm;$Z2&ZS1@3X)Z)UexHoxy z+tEh{wQe>mH~e&9S|ptD{vGc7Lv{H|VoP#pe$Pe6=G{%tM9{MXHtd_w+ceLV`@Hhp z_`7ad$6vBI=)$7&gu~XC!q%I7<}`o)Q-6~c8vXt61$Xfqr>^TCM6wl%u{<{=)iO!h zdp-i1`rm%hv}Wj0?H2U;;ZL%>d8BrVMLe!+PVI9B@T|+*w3ZUKUoQrwEW6)o<;wGgyWpirbxK`OYr zltOT~Qi{7v$madNz4v#{^|?5=>tg-ZTJwyonR))h_W5*be)orq@b-I_HGHLa!FxIV z`VdPQ9D#XpD-kw@E>s3z{qXWxoHxP~b=52RmrG$rW3x3;! zKkff-aZ|SDvRS-7y;Ib(j3ztP0uOrCyynln9tBePVS1te+pa!4FdBrmur-mLS0~3) z(6eZ|#D5ZC=O-a7B2iS?mbXt`7SkZ)D#(`#7)??FI-^R8BrH(=pNp~!$&25gLs;VF z@^skW@k)TR0@Atj%;6}}ZN&$%KpKUt64t=)G5FapRJ5iDz9X(3U=2=#%Tz%NM@i#; zn(b`#auOYj(I*ml^w+jtAA?45HO?d*^V-QOc2^ERr*Vqnb;-(_QxjjTp+~2)hzXZ@ zKK~ZFruKxG2G*ty-WyL2sZNAc7hO!JvQ)Q0kh5A-w|!F&SA5$xX}ghN>7D0)B8(LCkNBUNzdeCsj{VK zE3p)xq~}_(WcAYX!&stz>4l|W=#2E@zBGmR&2o^`5<$q^we%{WWtlZ(o+@OGUgnQz z$im~6b+K=&8ZA_t(rf0pmUBaye{L-&4l?VZEr)(G8_Bmju`-+ax0_iqTa_XI%4D`% zW&YO5>j!$o5pQTdH{uu(+JL;> zQjs|^2;F+#x~tiG>K3|f9eUt^IFAY42}B&DS}*cLchhjERl--bt*c_K*S(0ew$_^| z9HnHR(GnWF-@1T7;6Pwt7>JNo$PZ>IA4Pmm#OnfPr4UE;Q2(bNg|*TfMsc5$3kn;R zC{Da|p_kgSsu_=8*68{l*$}1(I!^xdr?OYilk`73xukN?{D6$36%L@@R8Qs8YVg`h zcYK!p?2~?V01fVyez|eI&*>G7v*9=Cw*tWdnYQBqo!%PnYg$*6de6OeX-%y+(# zGn#@-7qj*VLOPKkdJn7agt0+WpS?At7?NImTwF=-FG5UWApbl z;@-P+^}gq~3l*o^ygwpDLs^0YPPdWqthidKz{}&!soLQM?8Wr?<@q^|we9y&qiZXG zR0`G(rnzxyTO%@obwD|D(eh}9o!xdK;dyi?+2f{zY7%LtlrG8_y5tHN1*w#7TGJr@ zI%+m!iXI$;OB03ifXzul4^!|BMIXF(_FE-OloVw@N5)NDU*8{N$^q_@-0wvXkb$WK zPpaore}#Pw8tCKcW=d0|Z#{YQaCyKa?YD@sR9d~zLT=iS1Y6{f629H}v|*XXPAW-p zEK@p0{u9WHQ<~H?eMIRwGF?iJIWK)w6{5S{tYWD>HmWX-72;LV(WV~Pej$DONNXjH zdP3hcSoopdv#5+oBbPN5{U>e<8B=CY2Qu``qnI-dBT)-Kr)@Gg&!)37gK1}ta)jf? z9Lk$BM;%K#GUr^GCw!i|bu-s$xPRfKTkxtCGFb3gm`GjlUCX2E_uFiyGiTiW{dOtj z+5FTJ4h6}CEr*fH(6@zCm}OaBQoGXsiER!v{1g8)B5zLXaDQr`|YJ?^J+2Me$sWwYw~>*O9OXyoD73wexmxj&5w>o zvzuillhCbCdlm6>k71|0l`O~kQ!fwWZt<{sj?0HBS4P)&OG!C<8S52{ zZmIi2Is0$U_ZZ#daAdg$Q3Sk99%1Afxrae?ZcMNJS(9^*ytpcvJl%MQb3I>)?lXDW zBFOW+ER}hgPmMJ+@=gs5+?aiI%#-uZ)a@&o&)q^pcsJ&Q4T62KUf4W8y9h4#i$59b zr)RjeJhva0>m{s$SDWQA=Y9lft?vWpe)PIu?{!Z}Kg#v=@wqu^=4D-9oCsyT+DDSG z-d=5gUA(<9?lQ;S;xfz?PmY%WQ;@cMglH6DIwg*Jx(&jQ38N5#fjJG^Z#6OD_ln8! zg{S4H@1d2UC(F?1U2>G~VF>t>RH)XpJW)0#ivMd8Q6BY^dyAS#zOEHANu|!mGw2vO zH8fe2p~3`gB=%WQI(d7SJg3ZvluG0u>Zk0AkIX#y^}GJik`^iQgz)RCDWnax8TRb@ zjU+lo5;IIpD}AdPdE>D|#I$Cp{1r2jwdb^BS*Z$k0?hSlcK1iKhdFG7N(fb) z^mUS_x;`>j*S`?=8Ow16+lx(zslR?VlDiJJmYC>Q^r@jr*pK9*Srgabo*a9x+GQ{E zrcNV-Xe1x^*HRV|j|`{PjV4emBc^H4q!tAyaSaQ0KX0pl!>1;JtW7w1V`&%-p zu?^>(@PNL)b1@SQH~)3-FP}-Ld`S6>P@s&{o3r#nMVB$%Mx*MC$>0haE@$z_b0Rg9 zHONjE*T5R%#l6AW)(l3MFm97!N`thX>Ibi1e43ZTpQ`t<-g7Lvp5Ju+((ucc72}k% z@KAoLF`&`4t|LeJAoJXMU9obhC$QqQ;z#p7)-GsGa&GsiqVbfOJNPt533qx%XN80C zb%LcVB59`E@R9D}G`;5dy<_dp^qnS zR?6OdVrFPi$MgMIjJ?dQ{@mN(q@Ob}QK|mwtL<-nqbb}~d2LU%iFfmM z!`bYVAH=8XT*BGvdSbel%=vr93qw26>#E`C8mkiN-5&k9S#-Bg4OgR!tMTOA($JG! za&CK%&Uf={Lg)4Nd3!V!ISVyDzNBf4`#QtdF{d@PpAQ!l{PuIEuq@V|z$6KIy4>dk z%3^2WMdff_CNH9xi*yc|LvFqKKhHb-deVM+B(e6dvXX1}Dc-WDzLiquQoekn+j7KE zJ-@~q?mu`==lZVE`Jbq$){ysYYc%iCk~A0NaMU7OAzd(1S@|l)xy1|paA6btDqwu( z`dCdScgsB@V3OvicLjUjwt4>YcsI+ps<&8#z4A4rzs0AsdSMqwpc6R1E$G`Y+`H#% zud#S~EB7T-U?X_{={#hZw}nn7K2rInnXL69?&0ELYDCcAg$cibSIT-HIrrC!CK--h z^p|qE-mN1ltws{21|E`OHwp5u9$V*~x?W#Td}9nOPFW24SQ|WXseRS9f4ljEKx!up zVKTMqd)gg(Z_hJ7Xzh9JdA?|QU_LpvS0(gn!VP;`f(zU=7!;fyzCC|M8?qCae*=`c z-F}sSyH=Tx9rq1As1FVKGmNlFqCjlSCF9aJLvgvoI3avMw+4U!V?~4kd?E(Eu;V?` z(D_>lY_Ghft-?LvYkq{mSiVupfA^=$c zQG7&f{|G)+5t;K5Gb-WdU?3hk>AS~m(hPc1s%6uQ6>x=;%G z2rc@U6#9e_`ecfGX4_>m^!tX zdQ+HwjW7*UFpp_5Po*%=jW91!u&ipatf#PSkFe}hupVo%o~N*0kFeq>;2>={K`NYB zfcYW+5{Wh&T`C*nC>tx~eRl2pT&edTkKX5{WEa$C7fmImNX3a!av-%ilv6pLk8)^G za_VSv8l-a4jk0f+b6RUZuupyPYV?5{C6}i*m+yC0bIJ$)l-v>8+%c)#38UP}ln-M@ zxt5+j%o%-{Px+`w`%!7?qoUUjC(0lF(0*K-`nYlQaVzDMrNc+x1fKjFeKJh>bWHo{ z)N793)F(5PJgeF~>#023qdYG$PeYG*lFw6luSa=tlzcA*cvqkB5s&eaQ}I*j@b7x? zl{oXWQVFo@2yh+qF#hQ0rV}G;mCGTR=2tUo<97EMZKnL_n-@U+is~c+Qx(v4Hr~ z1M$){i7#UkjH6s2y#F$~p8m(^;s?|LUIAc${}^3_P$sd1{QsxX#demX;&Hz{f#N?# zmzH&RJRPCPPKo-$qsSOltL?s{rDUX)kP^ju+lq2L=+Kt3|E|*v*@v~XM<<& z8lySXY9$qMJ9|8xV2=!vqf!?P&|Uo?MCLWVT?#6UV1pDca#Zn@wfOFP!7gg$m|6l0 zDXsMCXbQy|rxRBsZD3&*L1QqRuj3lYok;hk2_ZvSI+>saC)K=1gVU`6J&En`Wt4fV zt2Haz{FjU`$l#mF(=pM?{6Dk%squk^1s#k*SW2-jtDS|hh~HN$o~1WScAvp-P6MqD zOq(ZOQk(^sRc1$o6uv*f6{UPMe;QHgELkjn_+o4o|JoGCmDjAh0eW>jhwwN;OwQI% zqGg)J&Y`4ZD*_auSlA>QbMbPUBvL?ykD0-`ul%s>zvSF|X9yj+Cl(IDey zevCP%-AqejdM;ey$L~A}1gqGv6(B6{9k!(TwD0jZ455a%Was@8sD8X;$r{kn4_rgHbMPku>*C(r+@>eD= z*}b)NB~sE2w3H&rx%L%RkuuaPEAzo@aSkw2By=i6iBU=mr~tcxJyht>b;J;fRh8MO zbn3ryvCLiW7?vV`kuXxdT=Nt7?vK>xNo64Le?lw$F0?ZKC$zZ#-=THKzd^s{cPG#h zQWpO=|0ZX}^h`FUj)oB_!*stQeBf=fnDF@N##(0zJ>kZsGH1!}sF-taj2r2Mbi*RpC5= zmy1~Uiz23$plvUDl7<1676Srizs?wqsdl?q|CYG}w}r-#tHoxjLH7~KV60FhHfGpV zFlfPoN$B6u0#~HOM}FG3ZEPZ@Ye)6$9tXpc>{}SQ!|B9Sva(04O=Y-6-#ThebTmy0+NlX6`FnOwi`>$M?6yvs zx}FK%MC!@DK3VHDMiy)$^JF0Oy3Y~U8)Kvn_9fkYG8ekCZ3r`ION=D&wn!rmrsx2p z!P3)E2R;z!{^NkD7BxhiVSnfun6v3F0&zlP$?^E&-Y`O}7%hbZ^d{{YLJ})zDT+@c zYhr}IsfCfk9;}uqlHEkSKpdw`ph1;=$F@&b{PFl)`} z*dUvnA_Fxo{u|uo@FOgVCFU`9S$0+@8R`Vfhh1(K1-8)Mn?%rX>zE;y`3>)bpQ)-A zmq-zw4aJNL_hTS8O{*9`d_6qJoRk%+0v0UhblCmHK6@Mu%JOTnrVNo`oDgk=zKPXvln0)fo? zCll9#$C$>VyTRe-w;Bua5zxe$vGu)Pg!TT#spP;0>tF~C4?T71{t^=&uFB$tzotQJ z;Pgd?uwiAs^rwbfJ%JjHe12<}rVb9wc0N5G^mgKIK4Z5PY)neF$<^bGuofcU`Wu&m zY6v9&tJ~g?mkfkzFdZ2$4BJ+QD81g3y2xm23;Hv(dy_KKHPp-`4aJsNOX*4 zhcdb?_`*kW5mTAlp@tP$>*^I}&kQ}TQggm8eSWnWx_`B4BnL504<-8>f4_ZmM9u@t zjV*)w6}L6vH>aWe30&aA$SV>{810qRc!r$N^s1&H*82er4k_(q- zrB9JntnQBlaMc|MlB=_o7>?p!ZLpJ(@`a!1{dWPd|EB=B0hNF}(E9)BIsd=vmT7-l z|Nqu4#n}`8w{EHYzWl#*OWcQLrCdg$PvD3LbdqSt9 z{6-wEwAXsWyZBe=N1T(UqtEerdrK$-s|4`FX~t6T`=!f}Q-WZwJKfTWcF}Kb<=kBR z^0ZbDwIL224>Hl3PLCwAGo+3l^l-=z*`@i9Zu!8cz>g5m5FLLiT(=y}7TpJre*E3f z)N^>^A~{i^yKFW2dZn)@TzH^v5v`y^2S<^)FZ&=!>A(3QKj6|a>8%LiW}#~M7I!|XW^3z8ty~UlQc0S(P zy+NL9C!QgHd}8~0AN648-*`o8XLu*vl)vYYU9RW6#Pn^vQ3G6U zmX%gqZGElXyV|bm<+_u!QRzi6z~6HO zX+pVS9|+e~dLY)C2O!4bm%}$VJOQD(R}|v`Psm=$M^IyHBLf}PXqc5ltG2;d7Ea>ei_XkW!4Rr z@c8!sGQ(f@>FQr-`*)UxEJHF+L*vPkJ|&UYK_7EqB3NKm>EPH1A{24F*gsg^7q~2w zRolQn+7Xf>rVe@<_5|T?;%ZmULwO!WWJ_NKhbbkX_DTL+77}#0tN}%3rhblTjYSk` z&;dL5(o2ddblfHl4Ef#%hR1XrVOAa+?n55Vw*{V$S0uDwSl z@egTm@tCV&y@L`YfM0zc={`DA8g%hYqm1+DeRI6Mg;xM=-jNXR;o-XfmKJ%gx&s3N zO*{+z7Ur|2B?a9yO881HzLaB7i5c0kY@hIKwW_hu36Y-(x-3`BQ%e zDb41|DVl$||8X$#s*PRR#ahNR{+&ZYwd;ywgYcKx@2MmjU)G-3YVH|jg{#^YDn9NJ zZ6yEmUWd?n2g%yQr^FZ{KtAxfi1m*0r{s#21<;y1?I(PJIZjFGx!i`F=2 zAIuheJvkIz`DE<6>lZq);GV)8c|Lep>8Y1kY=VqKwE?`(Wkn~9b9L@Re5b^$tzW zqlLXMVTF^>Z!|d*?MlCK9u7W4#dp6xd#%+o$s#Zm7_0ICSp0_kFJ%Eh*Y8{-Wbbh{ zUN_5)>>ltUOdaim<(jAJGuvIO78dq3dnZ6S?ek=^_htQ&-nJsksQxBH-B^`S@VCGdlKACw{EQeIlb3VPuVL|RxE_oL?N9uZ8yg2Im<*r0n^#m zhJ*~}7rBYl%0=IBsslYJg`2e^(0kx9>c@Lj4 z1C4#(DftZ_x#WG99$6U7))!nrf|bQ{u=2B>2uaHz$HDyIrL1XOLQ1PP=lC|1_JUoM zhT*Gr*Gd6}>u#vk05yCK;M)ko&WM4d0OD0$DL;OB{Xoy`Z2tOOq3h;XFY76 z4<>N_`l?FP3hs~9jJEd!;^FuSh$qN@!})Q5&@EX)w<_{&d~J3Wz(EW|;*L^-!-S^v z2n>OQ7vyTf?4(&fkE=tgq94#)P!Yh15L4vbnW7&0%+oaCSQG*H8xfWd%r-?HP{%GU zs(*xvnLfeC9zY-JMCclN7)3&*fSWt;clN%X@Nmq)aC9oZ-lBkD+sty#qdhLjz3PBi zO)_vAGqlQSh9CCig8TyG1eOKWPB=gd$gcrF8~`mXCVSdO{)2$}2;&qsNuI;)SxW0n zwHaevN`TX}AIE`1zo`IDQQl!lfFXw5a~V|$)s}n)_~G}Mu8n-ZDvU%}7K3bo| zulLQ*4xF8cgZmPP`)*b7H}ky~nbzU#7u>gc^EoDIRx8lnibvZ)c||NU;*{rycFIm! z)JBR))P^-jwKeG;v)}<^6xaATcK^o8ChC2Y(mIX_O1MF*@*d%Ppl|>!|Bq>9a zg`=Ywu5_qr_9eI`~U+<`}E_7p_?awz}_fQ!&6m0UKyJP?SGMXSh_PZIenp`)LD1F~vTOJIzCM}bZn z*jcM8ULyk!70Ne^s9Vp-C6+4~^Z)@WPgg(Rhw_2X9#ID=RVhJ)FFQmp?xYmb}(JQbvps}_zr8ekJ zx175d!dMq+T$jdQ7oAfV|LVSYLtWB!U3yp@TCzU<6+gZ z3nd#2DH@6c8_Kq+Kjt)iooi6|)=IIM+0E-GpIm9+hk!H*TH`Y@WW;EgPHX=b9IaVaJVfI$^3i-plLqs(-h7duK$FfalU#ghRc$BkMdN9Y z0DA!>*txd*;rM`DQYJVJH5$*)n|caODhQ`}f+n3>Zi7F8m%`d+mhoj%K$-3&-7q4G z11e?|w9}oW$^wL-ASie5RD)5!gc1GXBS9ZfWnzc`gT&=%C}M=52~F}?svQR-Do5cr z0f-r!0Of7OfS^u2SclOK<2ahs15H}K+yU4j87gRB(d!x4?1?;}`T%RczNWGOwEaT2 zBeZ%ba!I=nsH}6_e;rWWV`|5{Y4yz|O{(gSPGn@>A)&@Cw+rWz{*rwmi0OC;Xrmeg zJ}D@LpozgZRPszjh%j(gZo8l+pgannunLg&q#cKD&%yxHnap^X+lzzxewr`_qez!ByLN!7|dZZ^Reii!E}T;_aMFz0G<#h0ovws+l3Fv zZ3lnjmVd99V7^)c0EvXD1^rEc>@aE|dl1ozZ5|XgJi0v8*91UV;`M8G$fmR_0H`nL zFrVg!XAXve%_D%DO8kYP z_IDGegAhL4+xELfst+&dSL;r{>N=Gj8&+59lj91)1Yft~=MUc4~- z+9L!(krxKkl;cnNwlQ1xo3`pVdYhL13zWJhZ?2=9w(;p4qr1_$`y8%-ESb;jqAIA8 z#`x0<>IrYt85-)r-FXbD@po_PJzTfdTj7-Es@DxDg9Z#q0>HTAfQk*@R6lV30zKa; zy`;+TlL5fh$wHAH}$W-(8A@|L+Kbm#is|o6aECYSge4_1@*uwmb~;ikUUjwN^JT$8ES`sEir zEwo{8xDjf$7ACXKu1qaML`_DRqWUcr5$4-0Z4!P(UcN{z{c?`5ZgXg269F_uwuhC- z?3B8qkNF5VGzr5SwisOBl|3s}_>eo8y=1MoUGj;zH2a;(NM3UGX45TM3(rTeQ^9@P zoxX~l&ZIxxq<_;3%9gu#5ELak5(bJRAKi%l{^X%PN-8;VrABQPEt;(_lc^Rw(kh(Y z+kCr6L{2Tl2cFEPp8ZUHFhEVgOG`XgB{y~abjX4`gtH#qM;vjOA3X>?;?6&M z)Oz$}>4*n+#K(FpfI}P$nIDUU9*gB4OSB$KEgj3?j%8U-NfWgnL`7dlkFA*O=L}qk} z`7~DUt41lOR+e`H=2-*~oV#>c(hjOX0jQRVIuxkw3oe)dAiTyP;R1Yji_@>J5HeYa zyDTIOSA2!D0MEO5J8D1-$iaLCAU6vzV{3uEES@erRiFO?2?Xl90}TrBDOBoaZAd!a-)gv4(GW@j-;Tp|Ei$r*Iqy-t;B8A zwPEq+7qRMc*(ZL@7#f+NuZC>=RVXrHH`%*YHKAOxN+1_1p`!_#xY>)Y%nC$9YJcN*mhKYq8Ys9b#>smaH#979Y zGmR0FPH@Bj!6L&5T|etXdtrM>D=5obm$Fhj_|P*ojf3Qf4@li{db|*}ayDj(_fvdc zJ<$9y(5t1P1^s?DxNuh@Z>UT&#hlU!Q(+bk&6aWN&)afI`@Eou0VNgzXTHF&Hxc7E zbif|viYdf}^$C(o&pLOOCq*^|BFW20_!UTIs5|%L1=YG93m_}9k|Ieni{$aS@NSe7 zk4CizzYrfuy1^fHVOE+%@jH^qu@^u3(Gp$-e~1Vl{)8c;h|)IN1Sw6>LVTUno@xTW zgpSpO#&kVj{Pv6OP3*Q10|R%63I*!9!mdk2m|O{ z&HF0(?=~iqZXdp?-vUpb*1t7-LpvJF6~9-qeIf2EZo-+`E|M*ddTEzI`qJ;db#Q}E9}eVZCuH2)hIc6j zcjna4>`~8CsS~`o80LI;-FOer`;C$W7jnqSclI`N^4zuQcrwtf<@${AJE*$~FWN=t zB7LeeCb%CaZL|6c6RZ6G=N|yO!_O~ZyYbw}c8)8*!tKv#SwyLvM58gp+O4SaS$IU4 zGSW%P^mGDu@4L1)srCkp*FD8OO%5Q@b6I%~Iyo80&g<;Bq<^S1xqg4J6xl`}4VhL1ShfxNJ1~)gr$7qX zCo7+v_?P1oxA3!IRYKS@#W2r3ju$m+cz5U?UKt-(6nDFL;@5E(m4YTb3Ch&e;=j`- z{W1EtpIvGLZAs0nW9dqw4HDu~{!!vZ7)t;iPrrtdz;I~1r>+>7x;yH?$uUa${cf7f z{0N&D8n8c3Nmkngpp}Nep}O`NaM9OmKS`>k`a z2PLS3Y--ns!8h2xXLA;Q<`RxZuRR~J7Y4Tt!N?dt$Hm8gO81W}4LEp+*bOjf`lnZE zCy(0bNe_QGx()dGl?0Co)7?IM%o%OEW67)oz!6+j^G9P}S|O-XavyfRF8`Kj%lKvN zt*rj{_wkALH1ab&u|AbwY+YWNUeEg1r-Jz~AbZOM4N5>5D7J&L=&z6QGQPoo>6TOl z(YYp;Kf8bDGckM7Mcw7v4VL_0-EwZt)wlWD^dQ=xX_eE>|9|V2+qQ0j3)f~BJq9hu zC2qmHf#x^=3|g<(+(NO}<^Tf2HqZn2Fw!6kFqdIFv7LJa^Nj^m*|4LN1}N|($dcFq z)JYf86D_!7X(J0_fKOJ%Nbamqx*2wH;2*|`=30?d(sw_#`xaw+W5qB$-NQb47;Tzp zNpF79BRj;OZ_KOuX_Jo7lG*2ErB^m5oq{YUx~iJeUC zJ&gOFVD7@8gCf@zCVA*M`#fkv3HNd|>f=%2V;4)Sx&nrx2d8D7T29)Ypox!W-okYs zw)FA?CaRRGziMH(^yeDJfAUmU==^@AeH}2~W_S8E&Xm-$QDUmR$NOt`v$HkwdUAB} z^jn&Xi=B1g(<`vy$0RP4rSc zf8B}NB$We#?8gVcNdFGq$?QnFctRatSD zc|IWpyf3hu&PrF{0u+<3KU8aoL#0 zHmhq{%E&glQ#-qY97|9Kcaz-xT-nDQ)rn)$yf^ZEBuIWHq`(uTpcGO_ z4JmAb#ECc~MT3xHiAeEWq{LUGWK-wLeW2eV5v4`snh}X~P#nU&RG2MHIje#r;LeN7 zAqKFFWJT1*zm+Xc1X)Bj;E^H~6#O5eXb$fEk_9ju0x=AYGB-%UfN-t`F3LL=VZJjs z9BA4W-cx{Q%2!C^7v&tT_%b)v$S=~LAJ4Q-pL`rQV&YeEhvgtUeah>K`5iK-n1-jSrz zhLPGY74@m}$d|!d7>M?Aq?#XnP8YS7A4D3a@_GcMZ3r=BfIcxCP&3RD@&ilzLA1o^ z>y4uH{34UY0A=X|v7ZJE>Qp%om7#r+y6Lgj;}NQU5Gfcl`*Ng#Aq1ft+h`J|rt%Af z0;=ZMBwE}Ry34g8T^bN?@Lz} z@iLeJt){g>7=05XvK&bc9r*BMVDKli`oZ(I6Y74BD66i_?KI{r^E<|w7^JBAQ8&3qD(l2#_)Hgy-xe`) zLMUZ8tPEp@K2_biiQ%^BR@96IX%5wYeeV1ce0K9YwjYf7`Jsmd%~BH1D%{=8J+!Je zgr|y{&jppmju>QV#i9E1@ScCug+5x2OqHWKo@3VVcoztvDOn&Hk^ILn&U>gv95!oPI|K$3%YqFiG?&#MZ3KQVv(+iFiQB# zw27$YzkNve5!2k4+I@Q3^syiHluhA83NIm1)e}y?CloEgrWcVP#v!eRGaKJ^19u0l zZ;VazNS?r^4dBxeT9ay;lXCRX`jWY)8Omj16S~zj-fv#MSu;$|pms0UHFb|OY8%X8 z9spSY+@7eK7DR?E>zPkLESO_I?C9ZMVPpE3r^EHg-MXU4s|cgYP`xFpre&zmHlV_( zKKtvwx0;JA9eAbyva}P$w4d5JqY$u|k~$n}iY88?hC(q>%zBFh>9Kpv&`6S{n{kbL zfYPI~C_M{Qx0q5q2PFP4k@p0Zw^>)u65Nqn3u<&&J#I0S`0uY?sKgd~V^PReV`I$!!ejZOonA3$E$`EC6Pz z*OW83qoB*r%og)g`;>Z?HQ-?>HYm@ZbLuUoQOvd*UD;naR|xcDqffu6YEE09C|WY> z2ind76zu~`l#+I0jV{3PzsE&3Vm)0=-BP_arT@iLJOMC%N$etKo+a0b7LH+wX z1XK#mgg)@zx?#dZz0^oQQ+jtc)#ncQWRvhtcS>X$z^7jLenH(TU70tjKRuz>-f>mb zbvhPmw7b~F`fTn6&okdgG`Hc+eNsdoZk8Wesm}3FV)=|*S zXqTlhzs)e%WIHU%=wR=Tkp=a-f(_j9$?evB?CQE!!pV{-)KOQ9hoAyQGeWmD&M1)! zpqjAlsOj?yy9Dds;3t?czgq%J+XS|MuKW6ZeP~tMJX5pV*>2cszNx#4k9J|kLCoSd zj<{x`QN2%~*ZS-4K~bgg5NhY1Ww5~1fyRNW#L)QNjG-z;M2B7+IsMQ(n<+s=&#NYn zo5>Zxf}*##b_q*t;7`5CUE}^cv^az;avmki`&n-N`LONC(V3D#I<)*>H_6h0QJGra zgfl&Q;q3GfySIP{>DJvYXxuiuJ4o~_Zn@8y?Yx4|*F@#tPH>!We(dQ-L)F@CTnzJ& z9@^fL)7_Ll_C;QW^Vj}Ix8SH3=KdA^%ehvsrbwQg+YHl8+B*~Fn54fuSq{C3jHne? zN4YOnuSMG$z4kHmP@bI$+7nryg|YyNrunjyv$HrJr}|jVfYV8$7YPvup;G zyj%?oO|mBaPQECYMcNKrhP9bLBXCkpPK-J~(e9rBp|8RU0xazv977+omw_{Gr(AE{ zqpE$)^}Qcic+dP+lOe+_+?+9ga*q3XiS3ShWghEPayNQVy7Oz3d%{R9h;y)D1^^4# zBB;0+%s{Vdt^h#q;6YW~Ra$5CzIO?g>ofR`|B?BRdaE8hHj2OwCMx5k41>`b)VxVu zaVjU?Ot$LNfJhTd)Z5ti8b+g`kTK=p9HRtdCO3A!i1B_s>6ZgM+WMo+s?r<1`1%HU zEUISh=NWcNV819MSl-}LP}X~>Vbd{D8{VzM?fURw%xlzUDRelLFbNEO!a;v?&9z07 zB;MdeV^d`r#UsTCr~c}Y5?^6}q;9z+K)z+6Oz_%#bdi#tLL8xTBUnh>(<;;;@kj^{ znO>m*dDTpr_Rv~Ror1T`0z7tqwD@je^}Coh38~4KbR(~4uQj{%8XPP}s$(BbS6TI@ zK7DoeWcH`i)aNw?qE9TQ8hl#~2W}Ldp-`{5%X5XP=vxy}dp&(=9n&!1Z9!trToUdH4Z zl7yhsnKTkc0Zj0@v+1-}J^mH#SQWZwkxMW3~d}^YxZ8QNZ%qbYk@hVlH zTM|(qSkz{}DlescHlzS%JiU|hO!zS^XgE!u66FTd24{7dLu$F_~dq=hlEnA^vItF)rWf{045Nw33;M*GYZ zUUPo?`r?%}!v3y2$HL7Pp7;z6SAbr+nMJIPNutU1$FJ^boLVr1o9?^qIV6C)Bd1Ha z({6mjdhZhE9x)Kg;fT_D{nLn4*K3-Sk9)ifa${L=4Hh z^h3k;Gq{!Dr>!U!- zz*u*csEGv}lSM5IHBIvOTI0YUhL?`(9XOC^kAj;v4}R7pnAHEUXS@2d>J!PB$NU2F z+h>naVYS5qT2y4rW3L}d|GPo&-d`@~=&Q@xtx$P6^U0^3rz@*B(f#zfrs{GR#JZ*Y z<)3?oS>%i_+72`ikDuy(=7<%7B8YWMCxu+Xtay?1b$7VC2(fO-tMKG{{Q1fo|jilF)#lhP5 zY+@qYo}&O2-4weB*n6{Y`O@)RgzH^l`2Zf12|TEKPdLla1~hLpfTF z6-%vthd-7A>bhVM{bIUe=b0z6b(D=aT<+_X>js{cu;z)33fPypfEzZ4n`^&~=PAXo z>$KEav;H=8;5d12)A3S@O!e|5;EhxjGe-s{v}2XXrS-FjR7^5U$R@FdmU#m z8uOFtquW{*; zlA7ej$W~qo**kY+@@&M4&N^+xNp9ik$@|PVrjcGpg)sk1D}=r=bYyDWnZSD*FLmko zcbv<4tw7h5{CgElybnJG^DzE{8J9Mon2ycZ#omF7pX2BBg3_346Xf~?Ol?d^*Cxif z2w09HvC|`^6yTbV(RePwxNAn%G51i9&Q)~0 z@%puu{{uVuwdM_7(-SBmirqfVM$?Go4EIc1PWTd&E7mf7n2HQOcF2hz;3@rCGa|kt zV4y>NKAsObdaxjW#da2kw4dQ5p1UE6C{6057^Hl>VR!;^ecOxM{;gr}yEhQsfG;`W zZZpI3$HYNbl8cMK-x~;RnAZh=q2BS;1ZsRxn2gkQ7DKlwQ-`K|15OeW>pFXS1X-t&pI-6>2E7WsEm zJ~Ht!wF;$dLA=~rdu_H^=O5sw;UVa>s(j|f{ogZx*xxbc5@dueC)d)7x#iuxHc zVy@N1C#iI$a{Sc<9n+MuzESrwXTh(l@^5q=_{`Lh>*%8iLIq+Cp^bO-^L7*MYw?%U z4pcg_k%DL2Md{D|b>%606K2$E1i3TWOxgxm>&ETA%6lb#(YsF}R!(#4g{$gJi1xh? z#B+Gif9LS9OHT@3&^Y?qI}s+vIq^eA=d29GgM7y?81hPNV-|H1Ke;(}2K`-`W4{{2 zcg5n?-kj0|uH$EA;c}T`m-!!dw30-ie@Q}FkqnVP`fuv?cl~4La7WW0Qh#J_5S_5v zB$)K58V1$=a5GIEO8TQ47Cx}?>K-Q1Z)7@wG@JiE&D1A(Z`z9WG&k#M{t>A&TKY^z zkgTxg1O;`-T{oOq+IE)+S^woc39hnCyQhu`=?LK$hu zaY&QYq!gtHJKKgtJ3WaN?fq!8o!<-NbHDA1MQfXX3^$8K0jp0 z6Un?mrm_!|?Hy7t=q0|#`Ok~<}2hip(D4qX=GUoL(_d(N zdhC-FIw&X@t{e_ZP62wL#Mo*=NpJL$NC_1nO;Nz|s|}$3COK&YZU&9Bg^C*)^RVs# z%WD`RI&3Zv$vtQD){8!hCzYDo34tofYCfn^m)SzJ@RO{H4AlqDk~0?gKB?pC#5e)v zw!iU3@m?A9$z@L@hQEyYAJ^tlmpiFx%}-_>*Olm$JDUy9&$b-bSH+dPKGj;7C(Iu= zG>w)&e>uFce0JQ}MP1<@skOL%<8RY|PK9Us@Zy%#-)3A~h4*`{r5_f5TkxY5zKz36 zyZ(P$SE(!g`n8r1vi`Ph>s0#B4KE+J{B7Ths|@_6wQ@H9x8r2AGWhTC%GKH5PNf+n zkXaEx3J(LwH|6+V)nGH&@m-KRLSf{J;qVUdeOGA;9-!s}?s9*fm*1c2pF zpjMQuCqS6B2Lrm=3sX6?11y+71@9?IZ&$}Ks^R+)-__>G4#Z?*M-j;2y;yKEc?320 zO+$f!M7op&JXM&Eh>b{c{RKUjaVCcja7jKn(1bY8aoh1Zl*ZG!F3d5LFr4#YKknPl zGF4pR4H?}-BuX0=}0OUw2;i?%o6!z`|B8V6u{s zn|OCXm_{fpz_EwTnAg1tR+pnv0=(Ix|F^z2C(A>v^o^RWG=>M@w?+ zv-PaE1stTdL>^U-ipgzf)}DPUUfa)Kal90c})YSj zC$C-4MpF}UrmuD{FN_+f=Bcj8d5R21@O+$V+Y(+m9X4q9TKdcWEwJwaE)tey&i{3^ zU=d)(ZjkU2jtK6ep;I|iau05JxJ5dl_JAr@Z-;?-h^|7JAWv};A#$f^(rj1l=$!U< z=ykj;y{>1}T9aoH(}@wDB?BqsTj9^l>{cT=ya|1=5d%pUi2AKQ{ zTW|ElbKYut>PkR{FhE2{k&Fd-;-cMM<|_l5V$Xim!U|1e}ILllfx`}qv5e< zWRQ?K27en}s1_(Ad86-T0Np!?NwpN-_Rjd6_dmLhfRm~Lh+EdC4H*7C9wkl6 zn0&@R>3!LMLKhM2+(@U<6!wBkvY*sZ)RyXRo~SDB=|g62yitVa2H+bf6_|%+oF4Vl z%t6Wwb%{_Sdb4xlMG3%|ZJ@X%B0}*zAa}uQgp()Fnj)+wA|xd2&Z_PO*efh>lHn6! znj8Knwzk*8DB(Ps9DYw^Ut&JK!)W$JvN&N)-ba`7y2zTxcyoB?@Hkvf1XjZN$H|_t z^TLhoK{^@H1SELQ!Peb790UjkU-PV)2)8MTOc2L9e!BNdN&5GvXmBFz97pNr&f~^> z3%qq3zahK2p=f*(IIA94VIHOPiF+UTYD&l}%;Pa;`{l%a*sdY~Y#aPyHg1JE{t_8g zd+olVhwLRS_#OsUv`417?tk?crcpv^ItQa6@$w{#d9RB3?Swf{dtPQ9Rq7POlgS`| z0{aDkr6)$y9VZxsYQmtg6ZDRb2d?)CWcCC<6xczaZz~pr617zbaFDov=}vp%WZMl@ zzG}b_su&AwZ8!B3!6`5>k0$<;GRQ*^f`06vdS89eOJq(IGp>Oq6mlmMgoP9 zfMFw=A>&lC{6HcY|FI@htP$Q(r&-Pra?@AvHww6l&Z6O>$%eDz?`L;0I2veVf$aG@ z9=b5hi4xU#fpYYSu>&K~Vq4}@is~apucuuzh9$uHbC_b{c-e;r8HN24kq$`|Utk6( z&AvR~p)q}4(R!oJparqMkAT}hgT9$a`MA`^-#c@%>41ZOyaP) z>}~V`N~B>Hb}K#MqF30m`WlGWK`&2qNe!_1O_*1aJE`amSw5v^Ef0?cBbln9)r5bc znSE)V==MYe6mZL+MwH>P!Sr?4S;;4oLyYs}2|4t7h1YWtzC6TGNTP26X{hLWHw<|r zh9FdAZMbbotsW9!G|1<;?hgbj@<*_Tf6r@f%%h^nH_F0LP{dShdtH+%$*+z! zUiTzlWBTkEn?+y>moYG-G5}PQI70LRdg?+X;ij=49jW(8qD`ZyyOW?o;pmBsWaqcn z*8rX5qK$SS=&A!NIc@cg()d@lH8+x>7Rg~Pr3DJWrY_iH1G<*?Op9axVYTQt@-X zV)v|K??&Z;ROOLH<*|R|Nmk`qOXbCU<<(gwfTfC5x(Z}jMHWy6WqCT)R7JH=MRQ&S zXQ`%>u4W*<#sSsLZ>n#!RYq%|Icmis8-_-E6)(9-r2%gsnvDAu4 z*NR%!iW35AC5iF7)>@eb;ty3wmO4f0I%Uf`)qpznH+7n=b=nJcy61KJEcJ%c^~RR< zrU6V-e)Sdsl@D9%ZTKs#1K{53aH2qL_y#w+)u8I$pcV?C*=u+~Xcx#P|1Gw)$2$8T#!MpnG z>0UGI9>*|0{GURsYS^>;uR`RfZPU}}9A0Zo7KS4MK&d@4)v5=?(-r>^BEUf+w3+OG z5n{XI{~|uEUqf5$bakOv_f#Eyl$!0HiU4` zt+o;}4-!q{pgN+N@IQm)w%zTVAO0<++bZ*FgIRxeAGXqwX@ikMaIh_yj0z%#^a0!c zn_j;I=z-fo<=o+Sgu02t?8aq4Zf&rn6&#M}baszs66ywM`*2tF+`Z_zUDo}Sl}*aM zS3?{A#S$(x@=30({SRXU8Nm+Zvj+>*Z`K7s5h+vEtcc0*v7z(}tvC^N8SC=@Ug2#r9r42_J8mBGmYBVqv1+jAH~k27b>vg*VAjZhZT0XAR7h!hfRhJf!XG0G1f9 zy%pO0@tmWMl_ff0K#z?rGI4U)4(jhZQd|o6N0os0W{x>#5tlu2I|^FmuT-p`Pe?Z_ zxxsNPsu6&4X=}hU>RFnuSpsqv;?ZJEg(J-;t1g7-BH(0kxUSNcd6w}9ZB0OuFTi}V zNTeW?del~7^ttRb#2vb+&Eh#a_hz*7p4-?<*(p&SKyV_>wZthQSLmItRx2tH-t}?Z z0)O8{Qv^;wb$N|ihS!P8nE6U6*wGUjme$l($x|U6< z825#OqmN8s*c||ZQjNL=!kw+*1%YINd7~(U<#~@~c-0(OVP*buz)1j(k%8l5Cyam1 z|1KVY)8I@2z^ok7Q0nq~y3=ID*Uom(Kd`6BYEfTlc<^outu6FchhDYJS8n~b2_3jh z#l~#;oSZv}ZZOHL-3W{XNaqISo@mm!`pTHQe50Zp=m9O(+RPkALpe%cn31^ zGlTt6R`9k``Kaxhy^uRem6qU)AiSFeZ<@zOzPCUQxK^6`)iG${TReRw>oB|WPU+aZ zlu!e~9UQ3-BnObFBEC88Y{l^d`7ZZ4VVvXL@1GXYXO## zg=+%7I#>d-v`Jskh_S;CIQ0(T9fyH=hrvPL=En}jkdqO%0SRU0K^3^_k(ujyI50q0)z?v|G~_8tmluOO@AQD z%cc20F8J!l=l8dj6+#FA$l#77 zr4-#mg6NIi706h;_Y|O9sqTst{B?VZRQIRh6~R(RxKGqd3?9nApCo4XnPaG7!LC85aD7u zAJ-6F<=rIG8ZB;ep>55uE}5Z`_N-LRQLYrl6j708hWotY5;2EwZ%em%jG-IK4#p~% z1C1&aV!ozm5|Hh^!V`+rvPXg)?B#bR#WC8Vbz0wsy!&(_Q$-78&Z}!Q4DYC<>KW;< zF{+vvnbaB!x5j#pnLhQI88Bh`Tt9xRICbAd^I4tATnFlNy{;*S@tVnf7ug2dmf%;Y||em(D%QfzAJ-ak{lr1SL8Yx74ipN0|NZ}pnX zR^QWn=P`<#Ov`FB)J!%(1TjhLhyby<6+8OZO)KciKneTkPHQm--$*wCVj7^%uO-UP7i+mX=l9Be#94k1opy+OJ{qQx z`Cj(>>ZmwI<0>29F?F2n8T*%-&BSd#F4cL)#Vp`pC}->RC_HDkaU&(9V$Q-cWX|kZ zHs2)Y`4)eJ*~{`*j={etRRn$3x3u~L_xdz`FMZ8W>#y<}Q(1ZQyTpyKe_GfqNI0G0 zcy#f*`tE!7+4`N4H@_#C>`F7AT18?m8ooa+;_qt;%vu*Xi~ z>3*h-&gF6(TxaUzjNfy209mgf(z_BoJiIvb*Qc)ab?3YyK5z}dH#my*??fe`ExlGq z-b8e|yb|%%^0MWrotC@2l@tIAe9IehZIGL%5-sv3^N>zWNoum}wI;(G;q+I^o3}*# z6dkfp1qgq&^X*EV*aCTYULEW7g>xI*Eo^aPG{*Fw(B-tcI9$FP957Tgimr3KMfa4v z{^2Bj))r`4PVdY8w?UOJJ4ZGi*!9UV_u(>is2pXlM~|X^h&b)Lex*(QWW zdiP6)?$mc(zjecP$&Dv=?W+35$j(%pYiTWC3$t(T-#1Z=uIx;!)MA~UVR+;X*}4lwWKF|Cey z?CQXFZcZ3bHLXc0CXS&5JREsqTKi_x^(hlKsbiRFU4D6=lgc^ORI+&e0E$f1)N+2h zK)k+6%+2LdtHqbB*A0dBzg#^67N(C)8$18Fxm#OWO>OzswKA5wr)w>)-C$}O%n^K% zz+(M_bFO7Z_U=oi9jgfuiMk=`-_G5o^LYRC`njOz{`Cu1$FJww@k_e_{iVx?oJws2 zh=Gx2Abr2le`8iJxBm7pzN-oo)3!am zVcx@R>K@5)VNHpVtm}1G5VN|lXNm;&-P`Jmb#UEqb}#G`e_b8-Qf7mF+`M0sMkF?b zYJ+o%a58XDw@{-I-B=f%+|j1 zDR&EUvHE5)*Sh6H9KLh0g;?T0$wA2xRdjSh1w!|PeHE{e;jM|Qw8;~LT<*wBN>>1% zmmkn3i#io3L`r6mBwqi=5XHFN#U-zRqA}G^8srK1QuYeXZl#3Q{(6qD2@Msjs-olD z?pY)d%)9y3ZIgltEFATIz1FdLF&>p5k{0z(jy%hI@5>Y!Xz!eKe@b@8$e?LuG*E)Q z@U%!ZnR_&T;eu8b2f0TJo0WM{jzBs0S($=s>9o!If>lu6?VgRC@6CFW29$m;xJiWk zVilYK9x<%4-@$fGpYjDgqV=|@TX4R861j=*KV9${N?>_Au98W+^0ss}njf*}Q?eQ7 zU8@8P@!J@Xux*oWBwPDWSsR7s8}H^bRJ5wh126FFBYfJg#3{`XJOHwZ_KcBx&}+*3(c1db)Cssx{L1-2OyVlM)SU2{ z3xW2Zsa-}?M9S7L(1dE^7dYwXly2FCLNb{{=_}2{Yp6Ld868QFAt;jDv3ul(w)vc0 zkJ{CG^MVXyx)Jhzz5ME-kulRfhr{1`VNZIZJXqHLWHO(DB^5Bo^x>GPCbSb!_XIF9 zB{TM>Go(xI*KkZwv#sPJ^z}BlET~q^b0JL}x5yrO$ z4ufvM$#1NJgb`p0QLKcYtU(6QFQv=G54=M>9)2GAU+TNs719LwRTw5A8Md|{pS=?$ zA%w;-D-3xxGcrf1Y)hdJk;3lH4Bh{U`+JoL5baZe&H%kQr`||tRdHYORyXi!sP&lSu z8mrj_#<~NnyTTi%TG34?C8(5hD@r~O)P4@!ypMHfRkOC0O#jrRhYQy(0eN3QWbkb& z8PX0TYP8c0q*cvYQng;~dhH@_U7{XU zG>|6=O5Z?whIMjIgUuJQq_}VnAuP(MbzmACH=UTbGoXf-#Pefcr^Ysm_LsY2Ur&dp zw@LXps$rZSr2SN%i`6ECeAUiV*D)|34e@Is(%;u9RCM~4BJD7}aQSPv*Ohj(HSlW56FZfiqpzwXFFw1qjC3>p=6E@gNk<%byx zQqmyA7U~>0%1um#bIMMJ?Dc;DYQ|K_CJlg6MA6YK10lG!2tO%4lOZ#wmIz#vLY~(9 z)|Qlu{s^M}9q0)eXp@LDvPM9q;;`&0&|ZFQgMi*1gQCh37PT=Rk|#%Uw>7$M#D#La ze|z#C^^~z}JM|@mSGIY)s8yi7NAo8+R|f7irBN{hMig%dqly}*8s%q{l)Y=J!IqSV z`5fUy{Hu(HWDGNj4tcm}1b7)uj2N_k9Sf-%iO36!4jUT#8Rev7LiE4=yeJF(j{VXZ zqd$Y_y-{GelgihMwB8Tu8G$b@=R)u(c|>?!nsKUj_expsEXeYMN#|>A-83$> zh#1l^Kgn~-C~;gk&^%nLUYGn*D&iJi@B$d7Zv|JuvdLmwWU)cqmg!o6_Q&HLvY=`s z3*A41M7`Z8gH4+;tT$PpgfE9>FpTYv$ox zchpQF`De_KI3DHjM;lkC5KZ4=FV;p)F4ZYLb6Pvw?24Un(`b8)ECkQ_e>NCQ>_iI< zd2f>cELU7FA6Txp=2u>dp9VT(42(uwQ+8|&a%3Dp;|)vAl={ZQRx17sbMiAY%svZm z6Y=-7yOqNM7jA6^OL(JAwMxdQWJb;YdL8n5i81eG#xC3=@7cz@8X6Zy%fTZGd5aG8 z_P6Bht<~2#XB#2|+AZ?Pi3(VV#sMn1G_5n>$A%^-7h8g^Mk`!&_yp~XJJq|;RBb7P67a37P*Oh!&iIW7 z6&vij#9!2!Y>GXsvnb@2}E*`06yOzjm7zjk%lAGLF?pA89Yu?voRtcpD} zUU%Ew0s%-(b`Y8wj)58;s`;SHiUkT#TXJmme7q zWe7q^!_?At8teNWhxxVsEdEhZ=UjG$%-Wom>6m*I`*?=UBnB$kXBl3uGAKS9j^0zt z)_PEMtl1PcS#Baj6FU-ua4tOA#Qb`eT4%F-%XQPJP4O~PuPdBkEv)0pC^1J1?`rXE ztL4L$saNY3Yfi`GrL8oiTUeJ7A?zeLtoErT4Efwq=m2}72&UBUX%BAya1P1vempvbc~5Uv!eBibBUzuj7^j3X ze@#yIa!*wS8+;x{xLE=aaPOfE38%VwAi;aU_174XfNlIlN|!h@_bIg07)PzIDT7Bv zsA5q8;T*`p=Y{5U8Csu%pBW0FDVf7CDIPFo4K5VPXux{2wES@HG!0=dFOYnc%tAPi z#L9LHi(7JdvUB&+;N~^jB{^tGAZe?sn_iHcvmg|x<_?A&IFC-)2Z4m)3X9jG%w9~Z zn1@n#VNwdcwII7LGbCg}L!2{hqC)7`T+pw%ZPa+cyCq-l`h6PNhw9W8QO`&Ach#Az zv`;=g&nr2UPS`RNLVvoHa&A1g>m`pi3#G#^22ZcTCm=Ntcl6}ijiZ9k6jYmy4K%wP)l@%l5p3>bR+)5YgkN3X3Zp>xI^ra|!sdMt`Xc{gh# zu-lNCyn%r9`zFSOi(1nwr3U5C#jQDJ3k53rVJC{|4i|e20emWcQSoRJ_O;Q{R~kW> zVhGfl|LPL6ugRpy2O_w^!`*Q`SW3$2b#CGHP|B7qtDnqC1)t+-)Uj6GNPALd#%pr^ ze-grgQB3L#P1{}EnrZAW54g=yPsZ~k^aQo5IC)g*m^hz&^g%e`K-_R-`3>(+#!*UK zH&o7GMKhHwJ(@)Yl#1cSR{b^tsQM>*5V(|F`Jbp#-5SN2AHmz6FwgkI2f;6%tC z&6LZt^)L^`Y%N506H!efsL(8Krl0nzdB5|0nm1Sl$w}gr@ci`blGU4MEBATmwb7xJ zP(fis2SRK+ob+1#FA@yf>$1U|LQnMGN~hDjTbq*jow)n*1?UN# zMBw` z%%tu6K?2RW?I%n5JI7qnNc>MO9M@$DCPs?kic3}g%sfR;zL`T*PyTnw6wK@9QQ?3Xml-$xMIoo!K6+R7npD4^` za}1+0{*I25r36ctDX#B*{1Hid>j92~z2Na~QTyyEtj(7;%efModuP9w!OV64GeYIo zEIol6^#Q4LgmEx;y!^z7h8}t8qS18D+wxhe0*SI0-Y)_2w^&kDl$-*lWi3%eYzW_c&3@Ay`V(EGa0;<8u2_tEX?N|Pk9vxF{ETB@q$q{j#2B#CrK zf01nQiwUdDFNqE5yvVT|t^{R|r=)u7J{cbwp4@d&Ncj1lZ~6}GOfNs~Z%Tp~x->Xr zmwau#)wr+w%&wXAw8B|VBf%t5_|gjbn~!qBKNp$BF65PCFHqtvPbk9?*F9q6^uM(H z;fh7Bx5XyP{bf$QJYJ}XTRz$R<|b&dluS3Jm`*=Xal%1!&RZ04dcxj`;(-T`I3Qxr zBR8my6ZD9AQ_>H!fj4|xg9jj_m#Cy|RboRrYcEWRBL{T8ADN@$KqHh5q`6u{;NW4l zKk|B6jyYhjzf=SPGci_#Gmqk?L9Pg|)y2cJYA824;%*=QOJyv!_iY{p3>>9>H`PuK zgVTKCd3`_{PJcZxah*Dyl#w2sT<^#R3X=2ARP=X96rym9UC1I+P<;GWoKE=#@B>O@ zk0UJ?kcbKRVRAud*mwWkg!?LR76=s2S|o{;C%|*5DH|1Dt&KTuDCP4K8`6eEAPy@1 zOm=1`fp${y1SRzkb54C~Vx+yfJEbEFKZI>df(+6m2fTW_VW87VL`fE>!d4PY+w@*? zMr$7OSXgw;nl2EGSZ8Z>f=kZo#*=%%`=OH@R9Bd+1-|v>x>H#5_HTrA%p}LA3Vi#{ zcf>5{nka0NaId9^iU}B{D4%>kClqaXR~}$|z(A&{*AaWSVP{j$^T|-O#ZdvXiH>nr zHPpdzSi^JTGerq1jyEG#w*WzM+llnHtnHd^J$E8=*xwp68GE1}A|B}!PR+H7WI7U1 zC*4jZryH>g0qsPt`~5J=6W7ZGrbL_MK7JWHCZ*p6)Xn>|GC>)Co{4s?Qk2<+QFduaK|cVf^@}NQ z94W)*Q;hsmIZUNWSWakm3t{oVPERpnbk^B!*cV1V=yX}y1 z@iBfTJU;pl?oF?${jjP8BmIJsc~_9oe*vWYl1#yM#&uIaWmV2lEFnF}L`41$ z;LSTytuSSd=H%}6FE=y3D(!a)6v+1xxFLjl@{qLs`WNFb`{XO1-YE7e$}|Lv zaHs%<37o;>iE!g)NONL#7&_d!c{ei5?vACz5o_T z;Q|Lykw8SWpt}4x_-&oW#x8P1mMCW-2cHK+xh7@ipD#h9zmfvrh^OkGNF={AEV^=nhqOZS9DwF*?1C4 z&AjZ$I+a8s8p>sPww?J-P3MQ-TIGaqd!br&t|IP>&u?%>{u+E%{GnISG*kE zu{l4R>!N9>iq!dO&vK6cPjP#c80tR%f{Smcd$04$+46iIKi1IDIQr{(!1=-|O=DBP z&aUU1^TlmlVhd$-*SGb2X)nI9?VHYT|Aq7Ald;B*zoWl{&(Bu?u%<4E?jD-uVil^_ z)WbBk7qOxOv|LqCf+7KEIDm|0@I>{h8tQW`Y#o~K_xY|pRTlSGxHO^qm%Q@W0hU#9 zljhFp>O6|t!#J7)aeD|}Mf(K%)r$AVxFlHs?KGAZ$@)l2llY{bK5SrdO<#UUa9hF0 zkHP*cgtqxJ`S(@e#orBcNC5tJ0c?x=D>YGW--Gmcmh*r8MzE#-GAhXZu>@#Kf3sDk zHy8R9Z1MF(E+FvF+kBgk-O}Gpfqu`*R5j1hwIDiDfQt#oi~-6>WS--s&&A z&J%cq`}+y`t(|Lgtw>J2q@jC`H(VYCEfAwK=mBfa3bO&3pMT-qmPPD;aIL_SuDa-x zWkiDEx>B&vnRwilQmmNgb zXhHy1amS6&&$7Hv6DYIJzFxI<^Z6kS8>)?3al_zAI@^Llpa)aH`g_M71=dI*PsTh- z!DAYEeGgYfj}^O{(JzAU%c^00cXjhhoUgUte}r z_{l2G$RxFpkmq$LwwZL1o@5TW6Z9z@<3LO&=ij^t1x)8d4s1if`W~PGHm+~1xKMMc z9x87HZ)Sz=-g|1=ndfx#4Ulp$m;z$qDEYVU=`^DFmb+jF{s9rQY?}27H{P zet7`pVhX83o4%QZ4ei0~415heNI*i!%bGi+9(OX=qk$v=_WhoL>$mmsC<5-@Y#!ww zBsl{f27+JPU*k>WypviJ4g188z8?5P>;++@3$=4KOFa#L-jtu}X6}%NqsONn-9YMS>DVzUh15 zNM5=gK;EEVt11B`Qs{`!=^xzjV_*v6j7$UNr7^x2g(5wmoPM+^V!J*5zR8J*lb5^d z07H#5f^8Z|DBUMY%;Hd7&e-Fe7d{9{qf>heJXaIx{y+Uh~fgajw;&AM#+PPQyL3)bxmu%Xk*WUrKHxPeC zja2U12o)o^7DHH=1)xjivCM2Ex zg{M#d&bQ)dhW9dEg)~1h)3qAYe{^|n4T^xzU?s_P&zVAqJh;ytwsI&%(~^;|28ch6 zU;6+9A#<+=We$xpA0;KYi3Pv?kU?)24z%NDAigIb<&!6g^yqsakMd}x@~gkV<~Te- z8%ga&*M6N!qZ9$4T50sB=omycn<4D<0UXYkZ@4eT5GG5K6*Ts$m}qPk;jp(%sWZ=V zRGVQ85CZ~^Mg53Oq|m2I5iklUI7DP|Mcx5*X;eUEbr_T`UZHHw;F3j3GR7Xn?)l3e zMZE%JH%`w>cV%I3dT&BjP;!$Wn9mcODO30%?=tb3{G9K9@%bvk&?3LfOGeFO)RP0;MQlh@;Y{TSXk z%!^!#WN7urtq#6>-r{F}mUmYJ&@;tG{+YEa4DN1^Lf_V6P}4GRjOMclwcv1eyY72_ z2D@~I??FD8`c;Z1R=z&tkG|tsVlSP0t9a!Url|B0B~j@{aUV8a^_5!(gwky=_Gl9I zG%c=1M1s!=RWLt9HviL70z8O6Oo1rRAjiRkS;q>v?J`XZ1!B6plg-oI-HpehPa?mhzzIxjMj+Pyc`FsiS*QZjJA5 zm(sk*5+nA`(-pxWxX9+7VTGjenZB`F@pa8`a5G2hU6rPTu1sRP+%A-|Tis)V4h-rt zmfyUF)@t(phUV}06XwyP6a04r2CM z$U2TQb@UeFxXA~rIUWb|(C04v&^&8<60P!#yZJkLi9??3GK>KkEnZbEcN-~IrtUFV z)=FGLs*RXievtZBR}`QKBn9ES83*19{lH&OT*#o8>M2QLRy zs*dpYp22>D)7&+H3@0P|5X@BtimiWJ;^@1TOg)#Zk(l$8$eB+oz-7KSO&6E`w2f z2b@o7psB8QfBIO&;fb2+(`$c+>gEH`k;BQXufT|5Imk<+2p_G8r!6E;lVyg$1|zj2 z@DEn-muU0E?9mX8mbt#s&TQw@je&WYv4HN;*{#uJD`$uh#6xv#_hM|1b^JhP{9i>W zaQq~D{H$&KVsZTHVjRGRBbCJwi&tbpIA{)zq8+z?QA~4*gR@Q0$xbj>Ph1O{V9uGi z(LTYtG{Js3fnb{?KDOevp5zIdc=9yJ>pVj#1+hKCL;{47 z9>VZQDABju`VoEm$m0L;?Q^RCeEXNo^8fgDII}+h&qVa?m$a$?E0z2&S#DoK|LfcF zQW_o~geokNu(+37XT2g*V^^n1Z+Y{dMN?eI0CY}c;~&`~taG-Hym3GsbNLomVIz+N!9>+ zcPLpdK*|=JCJUzxDP}-Q)W!$_@$`|{+ZJFJlX6`!?U9*Wn;4(RhRGojU-H?y0 z_4$@eJUng`Qk1jwkG11=K$}15Dk0e7|7Gp&yWcx@e+j~a<=_j!WJ_1S(DCkW{lI;~ z|3%w*y*1Uo4K{=XLQ6suq=w!RqzKXi2}KCK_g6@B3M6-5zvN5ZXk|TkLPgM9R?hTRGzA(7}zXO;z z%{ka>KVS^}l|JaJKkVZELCtH}NINrXWPbXK&mPzU;Pc_Y6-FE44zFNYOV||)+!eb+ z0ReAp0;#hv3g$OY?Na637|)n?90FLkHNUha|MXW*I7GfqDKM+YvIxqO5Alkw9{ z#Vn{5DKWhO_%3}7iP$zCoBrN$m{~Jp{#3tE9v+I^Nbq2LCx=X+?B~{eu1beP+~9TB zC_l8|XWDn-?n=_><=2bwp=&=dD}Z|W6L;!$(C9UY6hL~WX1Xr?Pm?F37N2yQX|^7ph#KVONPOzAgJika8_mHYeKQJ@d;iAAmmHr1MxZ89DS+cQ1nK zfzB*e0(B<|RjypP3M#qcZRR}si!|Y%KEcN{eMnP6FXdJQv`$1WM#S>mafL$*dAOp? zUE~#RuYUkX=K!?#_DP@Lgj+xR-{D^B^Ln-{iQxe5{wyY|cQTDkAn95JDo~Q5u?@(9f*!jLjseA@<_2L`kQ?#V&>v0cJ)T?dqdM(Q{1FFqM}MmxHUn)5Tf# z6!!2MF{?nbnb4d;vSfYU17wEmIB0pZP=*F{3d@_|{thF(zDakr1MDwG(=9iPw z+jwN1&xgn<^E9O?tapaSuOsg`z+hm7EqIwctLyyvV&kho%9N;zX3p>M~-bp+1{=oFq;#1@<-WwA}riRcT$F z1j?NDIxGYY?QXRgS*xz5-+STrc=lCH#??7q_M}I!H(kF1RDs(uWXPjMtPuiYrA_dU zi;9`m&11&@3UoK&d9E~!lk5*^z8n8d<>f?g6g4 z-a>BS1M0FQKnjiDeibr?A}qgga5FAAR(Y#TtYp;rc~RX z+}-WuijDet->U$Z_DGC|PV4CfYILa)AdZ%tiNIg9+;j)T)% zNW3hgyFs&6nOy=BVqg)+UgiOo!|F2oS;X_MdQj=Lj&#rddkG?vKO|9>{52eAgq<(BC|KHj|ZM+Ry=mKot?-u&BGL(MOinRi#c z1y7C)k#tsB%bSKmELX|8;#T)k35!DfeMUwGR@sQ~RiV2VFBUb`A|5xfi{D=E)4pLP zT~f_16%YJaS@hEkf00o}!jZ%F{c!FY@5rfiGTA)k;)BY3-&n7=eQwL&9%3G?DOmUQ zd5CxAnK+8a0>J%F@53YqLGBk1s6K-(R^#T=$Gvh)x39SV%6_=+EOzPDH(*GH@xxDN+0lfsY>n8#RLbyvw6I%l zET-oVAa6;H?&&K(=8as_i~rVF9U6grJg|;L8(8|J9BEHL`s? z7X7%XKt)9yE%mwAKRdUACwkrFy3=T(OKv4R@|)F-z_UKWM2RW!s@46E6QSR2%C^d+ z)t&FyR+sFQ3559T_VP^PZ`xLx9Rymmx7fWBzF!?YdDUR)&ZpNM5qXYURnD=O?Q$O| z*WU*Fy2RcYY5Azq5Li%UdX;CA+9Q1~KS=+Z57(1%Td<8>)#jjPC}<5>1YHL4)+`i$eJ!S@fU+qGmv=`~!4z@{1| z6?v27*@20bVsugOJJ{C3zj zyY$-jRcW}?-T6(P!?(AI<@U*U7j}TTZS#|X;SZf%3cp+``eM3+w|(dOO%?lr=2#~5 z)23yum+u?ajPGjcmp$Ia9o81IP%PP7K11(5jKsTcU2nWHPFL}&US=&Q$#Khhp9kCe zT4l#pNz)e0uJ-;>noMM&@#5t;YVL=lgW8y#{>7=G2Mw1JuEi+IdLDk{>Xa||nvwis zkvH){&z8z|wz`Jv55|B_sf3!;y5M>Eta9(GS2aQAtzN3v)!*#Bsx-IDw}K|#erKE! z9@u{T1;Fc2zp)mU;BMlfC2^SBK&*dqmFcru#_dL017%d7%T=9z?)Pam7jqW})?}H~ z#*(J|pJb*|cub~paefi^YUaMC1WZ49Bi{5xVk^k(@MaI^{r!v&cRl#2W1VDX9=D9_9q-azehf2o+>S0J9ZDg{_fqt>lfI0tu5~==g;Zo z!34|s)u}t`{V$?+iw0f3%$|Olr)tf}Iq~wY*YRjBJ@k_)d*0@v8Llz*Oe_Rz+3yr< zuR1X2ca;0v^oLj7&Ef5uSD}heuMfY+zRw$Ksw_zVZrIOTUvsl5ORLt=S;L{6>v}}4 zNru-J@WBXwU2Qs5cHHOO{-mCHBx$>Kzci(F;asoGOEKoiERo1{Y{Bd2{x9a9#Gc<0 zFT6cS8#9-$p|x5}cTx4tP?%cS@tp31%SqwVhlSn+3$}}Y?QW#*9416htKK?Td>7)K zCgS?ixc6GsniD2@^ZfK_!rwBP!p(?q?nbp*SZe`h7|ir|F4_0p#lE)Nit&GcVwu~9 z?R92=<^l(A1==1^m4m{|8%wn&so#6u7fr9f|NOIe%VSel^=|Kq|Mu^F_nE#o$1q_X zNn^pEv1u2sd}CMtJMh*2pqD-xcCGO5ibU-1!PuDn3ip#u|Jc9t)R?1Q_tU+K*puzp z*yFG6)W2V2sV8TW4>OX64++d?WJS_}Fi21}9T-FM4rM#2b4HfCLRSzV55tA#vokbK10@)70gjXlISk<(q5g z+R_z>APJ#KJQ&h>G>IFn$Dr8(=^~wVqXnCEC7Jbj^7X{4I|MoOWNbPlBlLWX^n4sT zBvz5KvM4ZfB5#=CQ5BWPj$6JPP9WlSMSoXo;pY8B@UFrK1zG8Qg4RNs{O zY~^CNiE_7zPq%4=z6qh*I9K0XR^Pdr&I#0QdyKZ_(|6y}cj4%<5$&-X=ypXLxZCtt zDfc);^f(a=EPQ&rKs}yKJ%O6tzPSd0ng-Wad#=r)LyrxD_j|&cx*{Mw;nm%tX+4qo z24NFDLAkxbQQaX?y*CMlQGC78UA*eHwn%00d-*|Jx1G_T~!BH7gVo+4-r6cB|DeS{<0 zOV8Qaumt)SPYp>l>2Cp~dnxMc`5O27O4I-b+y#}*efeEEKnEIr%2TdUJZI6=-Gw>8*LXHA2-uUp+#rWtp!D*el zLo?;yo;H}Ynm5eHXjTb+F#zEXD2gqjd0U+{QD*#x&_BJ;(As2@c9zsW>Z_!fP*ZTG zeYq(!d=SfZlOjm~cQfX>14jG5liHFg|0cEZt!ZcD9n+KNxUq?x6--Jqvw8Y?^I`;z zE8LhLPP83~*Ehn{ZW%BC2AILYt_ZLhnb7Po+zTh#kHmj&;?hD8ZJW9ABp_grAa^C+ za3tOy4u1Wc{-xttRU5RehC7>SFj|h-dsyH@%^+k@4F=NspQ<)O;NPk?@gZN*IafU9 zXykuYwT)O=R4hOz^oo_1me@G_5#A6Bwj#yHoq?{D;S?mm?1)Bb33Oi}4h+8cPgUE< z%5sE(@}H`9z4=-0R}#!XH7l~@P0tk-1J8?EAZoIN(k(<(*r@-js!e#OhQoO9DvtEW zu7AW7;h+Aes*M}RV`%}LM0Ggtf2!KtoR)0*Pf!S={SiTfC7tIP;Zjms?5+h|CFRok zz1UrAM&bbHdNR-fL~^8|a?p~uL^Qbxk^l<{b;1xHkI75Yi?orC%=%|)^9qh`6Y$g` zFu6WbrSuE&4;8FWy0ci&3t7Fsf-`5CwDbjNlCAbgv=-5zWp%p~8ykF5T&)XXj%I?x z)e^6U(}zq7)nsAntwe;zzN-Q5*p621Cu?nw>$qltu;c1TXhbwPQY`7GG8^@3+X!PZ z&P-Q>(VkZ?2!c?K1Zj!P?$d733qWt%+0pqidD{@ zZA=nz4yfv0^=z>O;9&{(n2sW%umf~L_#Ku-4dM_=(*AXXyH%016&wQkf^jusB|8w8 z3s}#J*%$w5YlDs_h?}?FkCHx5KeK8jxbTZJ%C67bAGyAkn!`xW>B1rBZh9t*nXbZ} zU;6fq`7Um>Eo|8)4-!A0o+LV9t*Cq5!)JIsdBWVa2!wB*ZJi{xaYBx}X33_u;y1nM z@fepQz!rBBW997G)B7L1{_Nd>K>)IZNz$D%M#Vt3qfEAgr(-FmAd-n$J>1p8X1x^( z83Ets_YvP_aV7bfe(^E4n`kckm#wGpGo8{~A``|}>$_tj_ zMr?c1MxK%hZ7RTb6Q5&A!=1Q6>z+yb=Il;Nzpjy+;cFK>#dq&0QRl45e3JN=`HPK! zpKB3QmFu99JY=6QxrJ|m*MRrhLh{S}Wtv*=1{w?LDe%*L)^+Tf!_&3U*AFjgC$Gu@ z_PUqMGHh>gGEzmFk5)Bnp8id@Y4rJ$ChxDsGYD2^2Ap3<+{P7K;I zv`4ae3@sW6czEAj>?|Ve$<6-(GiF2mElJ?@(6Ng@MhOBQANiA<0By`D?vgjkm+y^mg+0<7P| zL9fP`x_XSAarK=Xv@Y`i)r6q3$yApqV&b$*P3zN!j4x+x?M)xt0AZ;rV`X_e5GD8U z(d(cx^up$I!g6>2o2}W3bk`r>w~WWF5g zx(;pOgz$NsX(}OAq^V4;(8y*=_%j^FBiOTYeWSrVK{gY(}CkvHNhcc-=8>2*RK2CtJR ztAF zF`t3;4w;b<()APQtkX!m(Dauj)h}ni3o{50tGbARBbt^;aP(;+EX%X`9E3Lg%7&_Y zJMoDVcHN$6<^`jt~(Fx`eQytEHbB1Y55_lL+0*NU`#rUY<-~Vn%!$6LGLJ8`1SZZ#>KaPZ2O3YD`}$3bADo{gnM(7j(K4Y_jD(} z@S&ybgCmQ?fjUeQ!*!Fu3MVB$t3L%{+#V~|Q|`{ak*?Ilkc8PT@uZR9c$rb(IErZ- zY4T%C@O07lxRJZ>UB5a+o1pyqh0g6)^mw&)t@iE?cU?$&>Kj#?`A{g+s`S%!mr2vI z`GYvM-!xx_`|6TtkG?(Hx}(4F4dbyVzy-Ea10Cnv@}5hAWiq?ee5c~ic2fF2te-f! zegU$+KQva6G~P?ZBckGP(T_5j@ryfmYm;7X<=Z-Jzdt!>l>d_Nf;osXDXd{deL$?=rqwBdCKm7QzId0Rf{rY<~Ex715KY4OLg;QJ3@aV z#^$>*M3ttdkdoLW%vRBX%QBW6I+JV=-A@(C&`?gzqAJQ+Iy&vxdE$p4(A7&+`woM( zJr6$3ZP`mSE2kF3Drg(WdV^ID|H^KD;P-Wj?n+C2*R%k1ISJDO%|k!Weum_3i9k;l zZ>CQg$BNn+OW&C6XK8_+R1v=}b~3eiD5y#8X4L{^LK(}-s6pL2iVjj%_l;R;${k-1M(2hsaBd!L+A&xK6Y%P+baN>Et8hcm7@fqtd4CYQt(;gE`N$_N& z%JVrb0WxbP>V3yw*D$@gR%)OA0xhFbZe1y^9ukUmpzyh}!yX7Yz;(|O3A|P}>X&WF zu?7n+%|)DXNXt4#3(;q(p6J?dy7BV(lhR%ng=W7Ao%j=lQE48bU1K@D6OqpnW%?Wo zXs_s>D6qo_Q6PNtWY6I4PWLS*n>J5fAnotAI287RVtu;@HW*iEV{?27jSWbCM$cfB ze3<%#lj)C&VG74pO+CXt2)L-l%~~xonI8btgss|AHJHH!&aiMJc|x zM4PL*u2{=rE_ZPGzt!zV*IQuW2LSn3NtSqS2j*w}sfsb*M(8<+6-*MZj`lNS!ROR| z=wMy$h<0)u{8|h$YH>n5hDLeakn1?0s)qT!y2kgCeC}aX7+#91)a9o0P1wao-1l&d zm-jFsFW1oNnaS;}4uzNU0T+dp;t8i;a|6vxR~O&X3)tbVmtVD|xB}H7#jm`IbAR;k z^6<0fpEGZ58n~=GpC!*?-GmQnsXu>Jt|j6xo5wlo*SyTzIVJU;EvrFIUf^Xbo*`zS zejF`l&d-$h)b){D27t$D7l&`BNU;KMf3R|Ue8;4zom@iNkl1SI*Vfp6_4WBxG_Om! zi8I6bJL4F8v2?5MYl+F(Wq)529UI=*b6V2ixu&~`54`0^zQ1o9YUxHn_WxD`8QduB z+K193;M2*H$<3~88F(1j4_Nhk@H;j6@G1f>VW>|eMNtImp1xG)3kV`t(1Z0tu#l$BecPlRUavhjX`}5(*IM0)_m?lX?jQ_WoK*~>( zr@F)p{9sWr~5uB*j>~>nuu$yO{H)Xc4lt{AFIa4Q?25v4R7%nizSx2X>-*x;t0j<30Gi}xV+upD$MvR zqWb>O?XkwE4N7`)zaU0h%^RH3O%h02=@I;teDs-B!^6-b5i+^Vns2kN$!?K)I4Fna@Bm?G5u>Dzt-2{E)h*?L~8t5A6P`Sd=2a6-+Z%**TbODnfVF6c!spX2GP5E1sN z+W=h>)%{dU>bo!GW>#rlFVOk)Uq1iU=BIk~7rvWzlqWGA(k@sPiPv4Xe?d30o-2py zP54$Qs;V8|@F9Brv1~Yw3iM0N-@KEd?HX|q|BPBd)!us7`g?DEyvqH0=*`(T)QJNb z3wZmxr__tKpC*GX+oC!k=x&Wa6FGE-5N_{G?eE8kEGTGdFA@1mt^}&xlB7JQak9HN zq@e)uNz?cqrDwr=KpAIJeRS+C81sjvt1uRDx`$FfT5U87nBE#^(mtSEf`@VN#KW}5 z5r}(g&CF%J8p3T>ncBbB^%jvIIhDPVCCUQ^0<5gA`r7SGj}L1JLjS?~841GL?lE6S z($&A89dz9x#}A9x*HX@~et0un>SzvS?C*0ga;Jcb9|d$A4nL-Y?)&945~-I2?lw&YZq_t^xqMIl$i)Jn{Sne+tkYwI zgac0qf6Oy!Z{$5xYuB&H{3rA6VsNnf3}MGb7R%5+*-r@8Ip~^9MdovNnrruPqkt`g zyL%6j^FK@NbnXdN$uYWm?E^heO|QGm6T+ntCv|)W^nvsc)z934bDnd#bfYLgI`>anz3*04hL$nd?Bfzn|us#;O#rI{(^Yj02TXMgrD zcO4H8On&rv`G)cN%8-r&B|ND%>X5p9xQOeeqtOnV8K)!mF?Q|f@C6zcY8^}72I!dj zD$_U6CQq2?xCl9CrmixAM0M?WSM!kfs}EG)7wx<=Z%i7ywf5qq$-%*#cft&Q@9MsF zDza|BR1`gG>Ok{_I*{?BH~n7zpY}Ie7007Dd&h0Bh?n44R#VRS4#=e}x6v<&xQE>ES->4<;I-HyBv z3QsEnNf_zYA1}G(2NW#3eY&u;U5h%laL|V9CBMz97vx2fzo_ZMe>-h+;Klo+c-D z{L#&lePou%hXHIZJm{8#mfb-Ciyfm^;uvB6^6x z`mh+UkYel7uUoRmT-EKl_KzH?z7D zugom0%{T_TJ+O2?d_6s7GrTK_8 zJV2D`sZpAO!NU~!@^??{H!5c`g>XSESj<)fVlUKh zcf%?VzBch_Ny;dN!_ZRNq3K>=pO`cky?v!G^Ap8c&ooA|*d2MG83N8R*n^So8kLMKBc6uG@&*21J$vL6a~DV)%l*$VUd#vpl!c!JY?u zeJfJ97CrK@9+C48W-i2|r}Gg{4Aw9I&~sGhLYJ*^+k@r1F9O5`uLkq+`Pw*tngBgFHQ!5ylZpVO(~<$8?Ua-yd+^+^4B zm!CHr;%soCt9mxNYgYbvJ^(5ElpczcE96A{e0fc7$%PQ+&tKO92zroOwWha$_qk1Q z|A)`783U3i42v8_GzxS7$_I_JWcsusG~)>XD5Hy;DtfGWQ;9&wBMo60tI1-~YH4NPsQkM`1POA%hs?NOTX>gub>$P44Z^Hk1?OQd zUSNBUZB;b;{&@EIi(2obhV~DLlKPaq-`EQfENd&D_hjA3yk%_kCzQC<*?6;E4I^KjeuTf=`B{+=F^J|!`A zkm3{IH~>h91RG1o3911kAnGyu&)nhCNwiPEJRxSW-{g1=$-b}FpLJciyk1fhnt z2Y&nz^}xbi8q+}jdn+=R7*+TOilr5BaLYP)SV(~v)Ak^s7Plbxy<-maq^I0i3q@-(5o~1Tt%u}O6#n9 ziLAD2@K2Vk_7GN`Jh*`o;Exj5!7aF@B$qXr!D9tJy~dR)3||-tqWcj|+W?#<39%l+ z2)d%Ix`{WF&N)`Xk4F6L5I#N`B_5^I)`v$Nc4j@Tlq2hpy zim{-2n3|1s#JY=`TC`!FAe}E;rW(BT9z38)_sqejr8&bmK{FRq%_a$`pIi(Ipf}~r zC`1H*1JTJL1qMlk3Z+3u`IvvCJi;+?D!BF>o!u6xAM!$Jdf?#hFj0z4FP2boBXMR` zf&E8%40rlWggh;)1#C10+K>Xfm!#dE#J&WuA;k)`XJkWo7bNKS5#T3DQDcUHUvR#} zdPdN$4l9( z7k4~k2Lk%ijZHW@1}F&v#^mk_Zqx(ikBBn6P=^tgPd4Wn!bGp=0YY}68n>g?kc{Lv z_drWhMK7gy>S-n}(eEf|_DTpg?xoyR$pJP%K+ETLcC&!(Y53nl)=g(F9Ls{e5LdPk z`A{^&Dh~7`ea}#|qzG!i3@CjGUk%8!I`k@VZ^8y(|W4VU5-} z*gQOx;3b*VAsvzpzl;?AK5`?U3K!zN1*grHxclhSb8IkO%f@9L=}E9_+XRvf{EMJ_B{x+JC#5297N zZ_N$5EC@oVo*-3Eb|EK@_dp{Na_X=P&!LJluo!iC9Yj9MQ+dBw3EZgAXU(&n4b!-S zI`Lp>v4G{)=W>zJf-P>B#sS&bxD0i%GnZ{7cBAw%3hUoHQepHmL@|(`!Vny`~-5?J3XCyBSuiA!- z+Ejq`P+0U00S_LFWhRPLhlT56J<}W*wB+seLBW^gU2E zvE~Z3R$^!X4w8gEU9{Z5F>Ta`(l@+7S{o7?p@bavh7DCnG3{SUmY-hXf%@58DsCSE zLjQreS318{DmmDNf-Jb1Z>x{f&?e{tynJfD8%O`KfRZ2j@`OdjEJZ^jioxv}zl;G# zcd`J4sK*zdsZB>vjREqvqoP#cp_fy_)^t^#(StmS+?_N)r1LE!g(fzz?aT0os65X- z*mo2FWTUN24N^YdI7hDVVD2kaH?ldx0m$}%Hfts_m!@&HFxj44&lw}Sr$bXFrS8iD zLNa2JfM+Pc=nv@K-!YU=4O5lbH@LF~vT?nK3B+&eWO~uwTVkMkbu$cUHJzFK;18?E)Q49*~_Jvr)v2at?3t;jc^S&Dn63*n%r|C_W_y}8k*Z`_;0MfkHW~v`I0ZbE_1bGY@y_;w!Vc(IA42WnV z{)N+XxC|&>J|aqyV5krp6=MvDe`X-#U7=$lJMq=uvgs1Gi;H6;t|#LCz5OC+y$X5x zp~MTA>1HFH(1!$#*D8*6b>6Q*xYtP{%%_foUqQ@=_4=}+Z**qRpdUJ1MRo3LkHR(J z2w5&+yuOpNCx5QV@{N~9({-;ycCrIk+c`OdL1 zFQ@rBhsRFQ8v#z$t%RH?WUX$PKEMm^LJz7EiA$VMbcR1=< z$g*xB*{&9QC_T3*V6{5xg2&3jZ%T1lMb=22aCLU1x5s-Pkta5g4A<*nKM{SNthDH150C7c*d;05}G#(cF$Vnfmc zh3A|xzeZlmG!BQMOh6Ehrwq-w8DBtZ8hjL)jGT z0UnjRogC0<1lWKSVXeQc=^N%~S!Y4*b|%W>;Pwkm!Sl4#A2UEthr6#PHY8i9xOwjb zJHj(KmjC>E&HQ~SeizO@x}}~UjpKidn8+6|VB33=!I}k%_OKfhiexKB%Y}>^JRgMx zI~zYS3BmZf&O6pjTIn)}!D)lD3WXHl(qzV-yA70Ox3C*DS55nKyY=5j$C}=PU>n-# z3|y!50e0uS!1TV{QzB3EWkEO};~pRDjakVTGp|HE?}pQ)!ZnxcA*@`bI?{BhH=@K1 z+_Kt$Qyw5L3yZ}1rZb=CVf+UMR+mm&7f`78$NMjdlU^5oRrpsk$sobga4=2_j_w{> zpm+a+aNh^VRDI0rJzR$T3UD1?QMa6O2z^202)ju&ZC~_XHL6{uRkR%R0BP~O|IRZ) zmT=uTdv&}I0MGXYr_;8N!wiu3jxAsz3LAqRZr@dsPH<#q%Z&=?`jyu{>NK8gbc?j@ z^U0knO#%x6W-l5_VAx$+<2XvJ=O*Bn&$%z5V8xZ{_$|M=Q7}y=Rw#q?VqEhCHY3ca z{3YPx)OMtzZ`**JE4-(HlCIb;NWNU_Nq%9-`SUn zYL~L;LB(;k$eiQfu%8x+z!_NA{MQrYck}_*#i&^GdVP=yz*my1q$lLI7JF5~ih4f- zSt7)GZ{;`N>Qm;y#6c~I2%O>z_Y(_-UaDcx(Xz&`clsw3maz)LLD3-N55I6B|K|q& zG{@6n?Lp)>Gz`NbDEQaH8=n{GuZAnO^@wwY#zdXp2@w78bH)mQ_U#0y54hcpJs*pM z)GOP>HiSVsxipLM=Ug|Aw-7?XV|%fITb%{^49@ z0Y0RLE=fX^gPZ_6i@V<|42p@^2l|FQylxABEV4hpBQpw+M~<@M(?E)r)o;(%Lqxe5 zMJs=0m8TDXc>Dn6aV%e*vax$ZiYf~S_`_dvU#EJ6&VNYWqYEEQyxt28+xrSIA1USV z3@v0TrEZizQ#xC9?92a5;KhPoZ6f2``fGjvUcgI6ov1ebSA6^6``YZM z9rw)C{lWP516hyygU3P(cVByc?oAV87cGVfKJ9y?a{bHP%%1;9v3}M zgj1D&8j0rEgk2GT67lnjWP8;GW9h1<>^`Zwi7*rSTLam`^l*zx06iv!p)!R}QtAST zFLc~g(Q;f!VpuKoYR#oZ*>qazN`(>=WFZFx&kZfD1W-}mMc09-xa__x9%A1Pu@Uug zFm37bafHeOV0k6y`Si3ac1JFc5y2)+N}3#}4zTq7(lytm3o1=O$OO3P9;<3afDG358Y4 zgCV1cp>P)UPKY+Q1SEWr%g|0p3`$c%r?_6Ni(O8?Bph!2@PwXb3#KSK@ue_xp%g@@ zqk)*)f5OAGB1YOrWtfXQl2NKB{(qKIKWOd^b_ah;x8?*{dsXrc*WLmzp6|eXXzAGc z^78WUJ`zJ2Tm0@wPh*Ng3aqr_9F?=Hh<3RRkN7lOB+w-B_VPN8(H>!R{KZ~}S-JV*?k1ABnXC=r{9E6#i{WS60ZECke!Q>>9eMipbcp~E z{}E~S*5(DHx5h&RW4xU#S;!&j0*b;CKKL?8z(ztviLHy~YBd-C`N;Y!zcZ7mp)1DX zVwV#&O@z{<2Xx{baKJ9s^uW1N6h=%1RcXfZVmzK5viuHQD{A{l1aczKA*t^>CKRX! zYCx-NDY_2(-a783f!;t7;6Jg?Fh&$ic^BUot3=Q)>ay%EDn&sW+%m=kZ@wjAFv<{~ zVQf@h@+C|2u~}r!SW@jds&A6q&%m5KCjniyFYwu9c{c_j5gr(gaxXFPk>uM2`W5Bg zaA10}!HB@2)hZd>SeJS`lc-X{4JeUI@9;PVls?bT?GALj`@h}n`HCt&l`Z?ByBO=4T{hE>Jx zm3-7k2|5`PE>|kgTPU@qE0J3dcE590uA;drcDnX)aSA|HCL1^7dmkhiPQJt`Y#W!x zo-A=pUm6uk)8vLo$xCHmmJUdIo2OC}So2WZ{ZD3^*ebj%Or~5QfK}z2E|yV9lC44A z9z<5D2~t7pBmTgsXwI;b@G@&Q#Xqd+F&7JyFK+4NeC&yBeL*Luh&JAK%JaF5PED$L zX8ObTMf-P~*E_66Y;nZ^CU~iZKsyJ^muX3~Ze&41a4>t214b-#A>+eC|8ON0L4}ffi2&?xj;+br@%JTParJ?PuoX^;@f& z0gvrpPJi}b;&d<(Qy3S1q&2}VH?r+FamHA^59|~ zdt~qk9|IfHq>Sk8K2w7i=KTZo7e!vSuc?HyWFNW5sX@zWuTi$TK(v=MJc2;#fWIC% z9EXD%)+}_qa5@;wTguV#M+~wak%fDJd_8!5fqaN4VpYtU88}17s@g=dfXCSYZP_2F z<)|ycVjfzm^lFwA9Xv zT_@RWBoT2zGLa##(Yg9{{z>-4l-W1zvVt%1%2Jtio~|(8`*LG;vIK&y5_)>|I%erf{x=u? z)&qqA`wAE1eMd%M)Z_z>0B!|(wXlAE%C*OhcSMEe-@b#bogH_SnUX)=whhi6CfKNi zVWe8ju4S-Y1Q&djxcX-(66#n~<+8c_?YYlK43K->^P7b*4SWlP>Ku#M4Dx@6Y8lD{ zRni35L+<1_4ZM$BG9iV0y}NjFdW%Hwwi_=IwZsyO?UHc&k?J3{!cWDL4c&g`R79=G z#oiw9ciVgNHR`Jt_4Y`j+kUA;^f%MkI};Ud2UY&jo37M5)4guL8Y`l=Lt^jFeRVs0 z_mvvG6P?)^19Cs=pho{l*Lk!gK|SjCKXuF2InJaoiUn9g4*m*9r+UO*oVsLE^Sk3D zFW`gp@*$G~(d)D;M@N<7uJgxtFKYQN`p@bo?Z0~^ryH|^3P*{Ie}C)5Y>a9_#WJN536-)B@R>yVc16wQB6WkaFp zm31!-2+2gHDYtoEuq^GqkpAZ*P^T2e5>1RAFW?) z;HunXY}0O$Z(z`BATQe$u&;koseg5~tBKU5Hehg5wkxN8gz+jNv1@VT=r2x~~(`;;SK1E)ZuM11eEe&zI2aNieuO zryqLeG|co8C&-aa^CCC;bkr3=ILeWMV9uI^R+iq5U?-?l+Nv&CQ8j-f8&K<2Sy%y2m0*l^h>BgYm%J(|(|qMFtk$Cek;d&jphDBDpcv7sG|jgYSuS#txem|nk++hEE60x z!zuf=XrfIgdCV(#_*n$wI}U?};9eN$ifD+9YdWdlX2?fO-$!h!^M;-8&tz0$4_ zYaiR4de>APf7bSM)y5Ii6QVN+YxcI!CR@6XiScYc~aTfq7G&9-9`*tyNsxo+F}-N|f|uQTb{Y+JXpPoA?+ z_?vPQSexv)}0cTHhog@0ki*KIk{ zZP|5U_5K2dxIlTeu-xrNnOs<0b6bse+pVG7v0d0Ob=wGW+t+gc;k)=Pa&eP?@#lT_ z{b!3`iHqCai#wCC|zIzIudLp1+LIPgG@?Ij^UZQ4RVs2jI;*M+p(bO}us8S;nyPSAL%ecaHW)`(o zB>}OZyy-NiqpG?*+IxFUR2l6QS`SceV~X7OjS`h9%x4ynv3RO29Gnv1 zbLB6iky(=Ana^N!rW}dX*ZW|;Gtpzgu9a&Jrw~-_ntfhNr?rpTgLK16@Q9Ibc{5I* za^`3F4kP>uDFi37cXk{eT!J^Lh4|lmbES4QP&?UdVRaBo>x%HMg7~HseQ`cb2{MCN z!q@JfnMIT}s~Nu@>{+@5&sa&cSNo4yL}Tu!$@{K)x)R`PkQRB9(L_FANG;&eKW35o znOQ{rM=i<|*Bt`gJNj?62o!K9AdKxFwJ7+S*gtBKno=AIm^}nC{4ceLn5s^&bs!oh z<PIRaUc zfYv{+KIoCDK1Y-=N)p5p>=EDr?i?q;w|}J~d^&~Dp%C{lrr;l`$Rfy+%n){(s7fKg zMglT^1vJ-knKf@z_i()u2VegmjotNE)A7T{{lPX^2#ii~bfM@Avcd(DumW_L33) z-Sile{)_LwcE?O6a3D^FKGygmA^9<9>VJcxtvC!YgC$<+i0yxZB5?KN)huOCa+@N^ z3=?nMzSY?4sfUSWgl(4GONutdf4Nt1R{@qP9HVtq!;J8dsa(Ajz}4`S8MiYvx^G;{ z9W6XQUw{2xUi7S^@)~M)zklqT|7$7EJ=UalE3g%^{p(N0?ZU>l&p;%f1r}eb?$}OA z$jzf|9Rzgu(0%eEK^U>3g}%Hz?Oh(?scj2dxQx37K^>3rjkKAN3LJFJIdwF4_|Miz zVM%`>uu6nvt?0k2=Z5e0D5zz+ggY7ow&uz=!`MmD7*NZ-I8~eYrYtX+qd03D(6boN zs;>{9bNe%_d5^rUm55!7zO0EbLiXL@u#2@uWspnAbNCTZkF=tC2><)`+A~4O z{R^!A&t2ha-!D-h(;4P~um6!c8W{p*N2K)o_pKdbK$T$QU+ZY9V99F-W~v8qihEfX zz=(@jRsTd^L5McO?LSh7`)aDmibBPzB=Ucx4)=X(GBwr0)_XTZM8oNLqo2Rvq+Kl|$X(wZ3+m(O=)eTkq!iZprxm}f6+w4tVGP}& zk<;;?%GWdyB=l{JnR}2K5}!`zW{+fXy#w~M-na1E2RQvFCwlr7d|&M-&IDs@6+-;8 zQXLvp)J^FX4fcM=XgmTkz6Qdf!d^!2Oponl{0T(u9^gVlG1>omix1@bkD@E%+b%+% z-Ud)rx~6^w>tXiMMM1$v!IAw}n%^CIs}|nv1HW9)jjIGSk*P0T4%iVj*FwM@zvDRR zwFJ`H8SHZW`hniz17pEU-+qIDvP>^C+Uts2yGq{CLK^Muio!y*WtGXLYkl}CN#C10V*~kh)EP@h)foo%P{E~fR~N#AYAu?ul^K=4 z+DX!qRM*-&t}iFv(luztS8Q_GmkG~)I5w{6`y>|>Sr=Sc##YD4hQEf^Ju+J%B8AIu z`?njs9^8jQ>pFV@u0S5D1=ZXYt4Tg40mZSfR@3GM&CHcwrg4iK8JUvAn~PHkNZH*H zJ{lT}PeNI)P0=!#pK$2SOa~&cyNu=EX^Oxh%-iyLsH1cRq}(=_#GkHMfZ<^C$7ycUKx- zA%IK`t{1G`Psgw;r&SqVTpx(~O&d3=3-r+$vy$pVX9;JUKL3UCx`>@sy*)*wj7+#P z`Bha%kez@kd_&G0>jrN0dCJ4vp@K6k0!#9PxfZY8KKI|JqeTWm z##OyzoL)+_9MJ(|KMdXa2a?>%z7(#1B3Y@?~isk)LVs^|F5P{A?Rp#+#LyQ$v# zPXC6_Kl@rE&HItRAL_HzPM&P%zU}jTckAEx@cYa{@oi;3xMc52CdUxtaEXx#2DcnZ zW&Kp^BlgSBUw0w}tQxVSpJ>|f@M4F;R^HPpLFxW`tI*1p#4Rd4&Qsz8~hm&o=1~&89=-d-&*)eO2=4nop_T?p_CPE_uq}WC)0-6Fj=T}1Nmn~nq zvcKu(olO%TAyG>l?IeAf5h{>!jl<`dr(5vG#Z$X!>R&HKC$%rr$D4q7oO5|WB2FKF z$Y_hE)WE1X*E3tbKk#MO{dsgjq20(8BPT2}Tjx(=Pf|pq>Uci#hzh1zu9REx1|oBW z8)32Y{pu6CE1JE}(wPLjcmtdDu0AX&;$`u?S*x@%7nOyospOBVaW}eE=`YHf(W23tY=(Vo;%oE?)_r1*mX#)YgXmRemE$7DzG?D1A#=rMLRPyl6J3P>xERN0W~rYeQx- z@{ZvVyo%>9D1#qBAJ^QQ`pQ|k5X0Q*RempB7;pdG$W zRAqP0r9$@Ogi=%IuUmfqhIHviZmJ0ks~2akE2riCkgJ$G6SU#xdA#&wFIP|~({&V*wcXRIhN*`cmfha>@u_o@IXo37r|E%FhfmL1J@0|D zwjeaX9}wD=uUlJO90#aPmU!TQo-w5kjcJmKtD+s)1w=gc&XB}R#PA@+Bbcc~`!j<4 zZ*QQgUQ-@+^4E=MyoyG<-TfHdbizU)kE&ieC%y8t;sub(E6W_c@6Gv7!PUp?j;(fQ zr+TJLJRfA8GhC42j^aZX<=K;j9F4L&&kg9&r$Nnye8X;Y&)Eey0mzQDS8zK#?+t}V zld$Uq20#X(<=?T%eL<&c#Nv`ibgNFmYv;BFhC1%fpItG0f^RC3hE7wv|Ak0}7YvPj~$+)g5hy(O_rh;;rs+W!-vMFhldWTIQraCA#>} zUmw(8OU+YF24rYXbK2%|YqB2F1Z&m%n(gNx<!_BQoVvC#!5ZsbIGqYI{&ZQ z=S~XehsE~^G`McngWawP)6q>7^^dQcyp=WI2<^R0n>npkcDU%|9~-~_{V8a`Mv{NQ z&q}%8M*LpCxPJKb+H&ZV%b~m05Dv<*ncczV6-jJtXfjoRS!iqP_FQ}5?;peA55Ob8 zpKp}z`WdN4E}a~7phjy^5$9jk{1iw90pUwq0^-HSMKaFE=rb~-^XGf-{^nNSAG!F; z{MK!lCHlyEaOU>kzFA0qzm2`>L&|f0<6A>Yq>;P8jXfj3D+=oiu?TJ966@i8zQ^tr z^q6kU`IdZIphdnA0=xO~(3k?6KDwx8!|qa$C`=GG!EdAtOridpfduB=Za#M|#OCks zy;t?w-|LSvP}o>`W}+>!ssfw5vuTz zT#sxu=w-j7L7JhXrR<7L)nFC|+Nj_-rbdo?HEreC_=f&S#tT)H# z1ZoeR7gU!>%P7@J!_BRxQEjp9W~$>hb+w}{J_OCV&4gVOd3`KZnDRKm?G<8mW<#~> zh;6NE7<^~&^_yO?OB%!?V8hgnL(GKf$$w?<}4yN5DC+li@syFgH>eR(-oIikx`+)zHySec;dFwZP$(!$#3U`itL+gdl&rXoK9$lh~bH6gLa?lv$x zEI?fjQ=WeV#B+H%aY#sBb|P;mB4~cekWZz41i_mrgU((}?5noyzt^=lbKX8$zC0~| zqy}Cne*YM#Mgr!+Eu(z2q_6Z;YRYlVjZztduKrWKpnsnK;#t4s=~nYJ?N`39XQn(c z%a#Lm+m}Q1XQU4`WeIr$SG{Ng@>&0$?TzY4o$pUt`<)-mJg7TAoDcnb{%;{c>f&f6 z+wbCdy`t{oWUKA(#VM&@ihQ;|?MFU8TB{>poPBzyCJ4BK1ZeSe0~qRKauppYv`SDE z3ZpR)0|yYhVh@a$gav*m21&X1fIUgESA&ocCA2!-V+2lsX%R}@-V1u_kCiBMfSE$x z!{3f#Wjc9i9=gA0`!$+y{WB6l_Hyq<`ljJU<(9-A=V*;XZ4lO$$dh^Ea#q4LrPv4INWuEYEsHLp`;{+!1dPkV)jf3otzDU? zQD>#Xlp<*L-LbR;CVnLI8?-j0W~7%rUlwyz`eZrYm=*oRmEZCX+V0nQcH+vaR6M(Zwq$MefI+!z z_TXnX<-Od|C*^V#y2GA#_wr^wmn*al4*Q1fy;!(Xq1dncWkzHze_gynd3x}RWXbh{ z?I#sCJC2Po+;IR95^{SFN~VwCbt#hmR)KoAWL(Y^#7}uk*n&!VoGU z6h|CEQnyn5uZL-&_df5nDKz>PVeF}LdB-{!II^sMIe(Ns4*&=7fV`J34^OqWl8C&dQ;`*DWaBALzAz}o>yCM zdm6msuzKw@S?=a4Y$Y}{)|6yPaIySt+d-U4d7D{@d6{JDoHvQZO;rUM{x<(RYu+u( zToWzeZN54*)2_f$;TkEf%J|#5jmoOwM%OD>k0Hy!u;8ZHmmB(~dDG+Cu66#mwp^%f z(>jRqHTByy1|m4CO7h*H=6k~u8e2nmV@|%dHhlL%KNOp5-)wDZi}dtXnoFw>2`Psi zZw5xc7-h+XctciD%Ys&|CEe^CsWtfZK&0>e7uCiePAr--hb6p{Rpt%@ zLYjYeiR-Y!ZI`uOI&y z_Ri;w<1ulWz_4lCbx!k>_uhXROYJ|eEgULc9^d+u@7Zlk^3IGtraCABzVN(o3mL=F zHbrVhKF|se`TFv4bFDqE2L&CGukopF{jFE`#PxG$-qtploa%bW1S$^>JpQBcmTTMI zR%QIV;ZXc^_Ka8fT>dxhq1LH?(|-T|H4gvHbGj#1^GocEZ%ICxy<=ck>0cR^$Ss&5KTs+JbyZOYs4D;pT z+kk?9`D+pn9u0d)q8LmVa&&~;#{H`H4Hddlt6Yea;fX;N#*sP3QZFUiz68Iz-<5O! ze%Q=TrM|(_f-Q`<>(`b)2eq-^x1ADHW@~7JiA`PGn33@Ls;H2fy{^9xZ@TsTf7Cuv zA;(>vzrcmZ!{Kj#atKg>(hMlIyK8v}HwLcBSurx)#3@}7>E=Vfd=B?^;15I(8k(u5 z|Hs+pe|T#vxRFwH{s$7W5UEKE04}qxP->%X)kKSx-LfwBfju~G&@Kq@_?NixOcdD{ zjX<@n2$o2Xf?3iG!1h+U0P`C#P5;m&Gfu_8yacW2qccKjH2F&4nxFZ76i4sp>_4J za#n@>ddl2-&CmT%Z4$I>L8b+h{6-PsB>j{?0s(h`sU%og4E1w!_-lMbzCV9x548IM z=nMM#r8zHWl1e~w-=Cq%Cs9=7B-P9$%?UqUIijOANi9o@Cl^2Yy#ACVoC?}WqAa1# zkAV}rq4_8->NIE`50wQQYCHiU*9~<-!Pu1$e&p_Cf;6>NKza=c_LD7TLRc;V1*;=L zk;inb(odh0sHFH1m#q@>4iygu!G{qClVAxZ30HQgN}Mu@qc_PhU?PgEXP2(iJ(2>X zqJIo~F8%b$I-U#wk}9$ESn5~=xKlVPNaP7+Iza2ubKOAzMmmks6o7Gfp1L3?dFL6G z62cUK5^PKtNlft#0LUFd{|+eS0@8S(sg{obna8ki!u0$e8NyXE(3tcF1!CncM}3m6KIJu=#|GaHYn>l~sE9u*ynAWn5*=ifvaF%%b7kHI_9L==jMjDnU? zFTQ~RWvB&?U(LZD-%*$^&8F+mIi zVL8IlQpB;IKvozY-+fa}22|qml923$2_`v*|LAOWVS#!u%JlLDk(aUr;K!U;mZXxU zeh85St*V6A2V!+M3XVly>NLIzoGqlqg72Te9IM$ybD*M%5XzmJ9z8_kqn!9kYAVmD zMO-D&vEnedqI<1$w+c?xm=HLtNAw3=@yFIw!awZNan6>wVoJsnQ-8q9okS5E{|a6c zfTtD|>_lT1b~(lR;+vaMm3mm9W5Xmm%eUmR$8CIlOlOM+kV6e#C`vEtvLa9wWQT?$ zG8!Q)h7g-;q}*wIdnc=<9(JV|L4HtL=1^*dEBi%F0O5HBh>>59=#*+29d)k}rIi(7 zji50-csi8Z6GSmn9IjCg!QtgJ3ZNmy1Vwzxd}St(^tbHXuQbTParHp#38F4ECx zB^EFLq6Cahyh9n|nis3S+zK6wy8Lg<9meZABVwx?4york)d8!iGzWI1gHGwLhx34A zDsS4>5E0L49YNvl*c=svKwcxKNfx;~Gc)h9O2f|d%f_lBiiQj%g%Q`iqN$N}YnymN z44l&p(9-?-^(OJDO6SM$&fL=u@TV5=!;&U=gom>9ZCInCB0@_Hp#!g=B&R3UJ7-w3 z*8%rBR>r%?q%KCD_6?z^v=gF2QW;ZwZFG1On1ax&j7S&b;LJ!8c51~3Lg+9Fc5L;h zD!7F7X5s?NZM~FwzIOLxD8C8*$^!1_c{#M+I5$n`oqjyIzQeDk1<&(ZI!6d-!^PU3 zFezFlFwk2iwATkDJqX7<>_hg#p4@I@$%pc|4MM}XSlI$i>G<7P9IOvkO&e2P00@RdIL?7> ztc9gv9ap3wK3goT=VM&2;oPss+S;N!6+clrf{e)~6ACmGE+=%j{LFq8kk92*&F4tF z0ltm&agNKM)6x~h`gSsjLa{Ol)bQj=L*nfdm_Qyw3leiEqDUlV0_pJ{N$*_YZK9ur z2`2Ds=RmN-BzwxF-tZ*j)zNwV_Nki#zApd@1=G}{QRhPAEc!4X67XQ7OI&e+RrFK8 z86h_Ytc-du8X@lSZS30jc>0DRU;~9(vfzt$7{CJeJP(m&j|dKrfTSg<+k6`0?>*fR zY>B8&+ksv)?4{{}`iUb(IOfR3Gf%c>gm|gOIB?gx6XRc9b5d!i$4E_Z4XE&zbtRR} z-b5seBXl4G@%r>Q&OX=1cuvGTu`SV&yxX*AJudVbq5UZOZUJ{oOseaktTdwj#;56< zuc>c$jri!7ES~m{Tu!q11CGj?DO=(bc*>CCy@(q4{hJ-6>fVZm#ABVTt}xaYwunU$ zZgO@b(6LcuaRIzo09F~4u1~~Srvyn1sOMe2v77{(68dj^a-uY72@Dr?;ISp@oh60JW~%h%iPPte-qZal zi0z8-8fjr9afusOB&CQ&8WlZ~ZHjG7L?%{p71Ec`P+a5^$JtP-)t3awxQcKVxxR?U z25=xUS6N`dE51UBg^RZr8Ipy&SbCtRD%D5lbVdHZMu>~;Y25E@`A)cSAJ3!jTnsBo z43J~sKdIyD_aK=ltOqPyP5-;HPdh?wb%P5V7zW6eMC9H^Y&^(jm7KqB5B1tA%sZP> z{W6X({bAAlgTj{2_6|Tm5_kHf^v=D23GJBru?V6sv_Vnk zd`eaX5FYgcIFV(TdJ5=0#P&a!27n;4^OirYoI4|`tX?)2$!%3h67>d2rzN%hF8V86 zw|DRFzuWX#kpPw%DvPv#GucDb*l(=Du!A>C%7gCZfY`k zHnIJa`%j4xOs+mtyge})1^i4wNUo>kjG-R;Q9V)HTcUcxN=fh>IecFYys}U#@*>H@ z0mOpgc=4x|vz{W;1l}>yNF#*^Orj3<>TTVw1WUrC>obpzHfk>rdL#R>r!Z|qpMu_L z>-`oW7ET}+1EihzvYXbO|GzKPe zAU&%!!7V+*-@%l%$~vEF^XN>EX|uQ?v)t{%Z;A&;YcNeym29?$<@8KcPdmS^X{t=j zE4=vH{A-eDF;A&m&y3+zhG%8 zJdYvDfT7(PM)USIE}L2;wUvKLG034ZrdVfXNumsn7IvsoT;rTxHj?E ztIxEy=Yy=bkTz=O_hOktY@CwiLvDe#%;?5xoK`dMJirnTChlhwi@!Nayw+shM<98y z&i3COrf{_>S#NHS&@g`0y5(b}CnKHG3ee2nWwvoiX^;8*Se8B(HauWSM-iDgeBCZC zb*f}2jin#Sz|1Rs@*uFLbq*lEY8!Lx+RH~sp@MQX4Y z$8Pz7KPK^axqNI=Gw$h{KOiJ4oVb^zD-g==a#P&!C}6AvYmqB!T2DM*HGK{9s_i&D z@v48%67JpjN#WGHdBQ5(r*$sm)TezpE8Lg(yYhb*?<{asgEcbfzZ!@2_x&u}(DUFK=j_Ok zS+BP9komyr$j~3*|IR}fVp*dwOUXAbFe}fjqaOWw5qj}xy)-*2Y_q2AB5bQ^Ix756 z$G?mJXdJ4?Q=e{-Blah(qazRJLdlUw%h}OUC%@asQD^_vI4*bKsZ3&k{06OGs{#v2<{e9BJnA z;W*c2>v^YkCZ->xYclzc{XuLQ*UH85FJu=H39CKaOVWuQvIIJ>^}?(!#AAIfPG*&X z9u}gBmlcSYIZ#o9+lk)Q(3^K)h^>e>Al(|x#25AjuPyH>o@5e1U`jpEuKU;!=MzE4 z9ayfT&`3&r{hPqHrr3WK*7!8Ru8dddNJCw4JieI|!pm8uj>gp+WC!Jf9d!`u0cNqm zugZi<@ja%rV;O`97Y&6$JrmD{TY28A3_uZG6}{cem#+jw+1b$!o9Wqa`Q4-&j`SV+ z0@7-{mt}Pysk?AwJinh`1}P;geYRGf$RT#F+9n+vdf%ORKFhUs!=8QEIio2d-NkLI z_t?mHR|el4WUpwO_zB(DRJapYA-kRUNmKM$s-DG~sz&0Ms4p2g#Is^KdfguL@}}%> zK`x?Vn>tb4&BbSvYtmp(qlBpa{1F2>l^a9)>5t`JUVUw^%BS~5?}YK?I~Md&B4Jkj4~$feo}PsXo^3ACM9L<(kQembjg!QM4CWoaytm-BRChfTej zrER*iU2R_{I`$#tph5oSno*>vzIzs98=++lHKq4y=%l43F2&1ZP|r5dX`)5*eCgiH zJl&pqSx>RSE}o&uce_~Rn=&P8{5~dr`xSQB(mDLcLPG!BlUAmJ{O>}B!*KIe^;V@~ ztvbu^UiNym3Qw>veZBpXEmwNKwlaQn_v)B4!RA@veooc;)4cd@FWO$V8?m8P6#k`$ zhk_s{$rx) zOMJc7ptwCkCHo@-ccbO|u%&($g|??)kBIF#dpM)b$W>R7=iz5R>He~nL=<|*{F`67 z*T*`@Y$W+YV*ZYw?ATl-;6Yzt$`&D|g-A&=xw)A#_^(t^IgQaYmDGxgaV)-SwT zzw;L&F4#u@zN{;g-=54g2;$eL2-2MJFo8D+c`RL%TvEH|>V|Z?Fd8nu718t63 zk8N+2rmg$IOS36MhfY569w;;C+^I;GgSPj#emjdXOd0)Z!cfm|>dv)KE`Mx(=4!n? zT8k;bOgeIi7<@DOXVd3xdZ7@~bCa~Ju(dG!)Var6e+4AQobdj8^IK@4exh;1(#VhE zZhFaUG9%NA(2<%pr(Il(2|l$FRi->!czuUEi<%>( zw@B7kVZ!FUF8V)VJ|z?FY}|06Scx-&?cdX3npvVncAF+N5oD!+&6Z`6h!5{yUfQCz zKe)B8hlNTrM;%&9C+~`*8(rU7X-8S!{hpp2>Po%wfmr^Z0^te^#hGU^HKEEsBJBPN z=QD&;Ad;hYk$Jwc+#c}*LQo9>NT)A@cSxvMF>2JzVqjC~zKQ?3Y#~UFDV`jWsnxS9 z3KwG#lb?D0_$n2%SP7Yfeh*5KE43vZ2m1r} zYa}JXfT>9$J>q}z-ob^k80s-5;+xwokUlx?cfUl71av29Ot&>$WQ8}g?Kabp9^NQG z;J+yLz9{+wMXH6I0vg`?ROX9-OP*7;0^!exd%2=lpC&$uW%V4{%r9Wcio>qQ(+ zDOU`v{zFp^P*sAQ#C&s0ii3<1=pOq{$;2SMe(-c!s$w8f@~vQw9pH>nK;gU6)g+1W zi;kR2luAc9P#15NsU}N869!Af3mAqHK2lI$%oQeCqvnu~Y<|r$Y|RbaRTAO}%zs(D zrD9g1NS8oGVar;e68`<|2QYlQT_sthvb;1E;#{+WC#zVDx44GxET9h;+SL*|E(+4j z70crs$xs$>ewpvHm=ZlAGS{sFG;w(ziFCl#{KK~*_1Xun>2Ni$V)Xd&XX=XzaTCQ~ zjfK@xz6qSQfDfAgHos%39JBp;5Q`3-=G~Wl|1;77^!Q5}WK`_0>KT`8*LMsTMz3z#h&a7j0+4YmM@U*>I&U``!eXOiY(QVvjTOcFlA3HwEc92 zzjr0!vCJ?f2Z(hRk%g&Om6-f3#LSW-2b`I*2f7sPAORL%)YP2&Tgnr8ESN-U_ahm^ zRuMr0A|k$zB@XDy9n6bXtkt9ZL=>08{#TH6Uq@bEQ(gWWH7zZG?3SFI9Od88aD2ih zrlx!Q`v<%G!QFaQ@%8cXtZ$iM-GlR^WA(`_H+Bo{vM>e)M!$XQXJce!Vq%(`nZYtQ zRm$=wdwIdboLp00W#wlYCQ@!vDH)ly@%dP}K?=mVMw*5+ge%MG7>3*HGxN_Mh!CfX zXlQ8%21F}1c5_P##$LL^wOIJQeQR4a0nFcymH&H3^*mZC&?fqnHkr9&ZTL#wuXqNL zEF9^~zOJs;(&FeNLIm`sUk6QWEWV1Sy!ZfFTZBMju1je5weBYENDgVx^m)S}A0qEJ zChnf)<<8z&vXftW=k#%Q7JY+jjCD40~LWJc^B4|{82 zfz!ma=zYWgx)51fS`u=)A&Jei5p;{%=@*&!@t4|t|Fyg8GFklX20%xR%ZOqp@*;f# zlqDAHe(I0BQ1Ki5iw)U#Jc}s|iRyOOfq5m+G!RkZ> zwY9Ocd}|%vFDMJ=oP&ZIc4lW!CF-&&;j{0E1Ul+Y77_`a#MfL`QkT~=uqduRefKg` z@3|m&tl%grQ8`hpIE@u)9v~*og&uQAcw=~UG$xZhGQx{kCIJIe1I*C2n`rPzgOUb; zB9n!sLNX+m2mdvzk25hu#>Nl!eH#lf#U(9zgna$A8#tzlgM(uhbh`APR%B^qodx)j zNbzc72}!9xlt_{wiio&pWOu@2!2f4?g~U``S)cv9O2k5QBZV+&Bp=}a?22|iVq&SA z{5M@Q0fJo7H?KcJJ^(!n>+LFbXkAN^_J+*rrTgYocK9=|rV6IDG;56HHYtQH7Zrb= zDWV@a&>y9KaJ0)o=-DO;`Q~QMbDK1LkiO7{enwi@T-BzbvdQ{ds+j?HL^=-AQ%%oJ z85Sq$?IqNP*R#SjUx9~L6DahxJcXmN{oyA8@K;12#_6WLps)@v3hT zyPR3^#-G=VSznMILk`&biI|l2Ow~rW{16ewo@PgzO4z|-C0q$IKvXk@>zZBP;nLJQkk*IvR~=qbCN`OQb==SK=)nf35u(u7Ne5klTOyttf(o~4 zTBkXvp#=b;* zMV$#JHYFt^H99>iiIxG)5)Gn_>&X~*Y`;El2r#DCVu*2(P}NA9pupcnHjE_p2d1}f zO*M!tQ9wb7D%;D38JUs&doc)ViAm!cgyzT`v2o$y{d*zWRkj02+|(R*Hv5(53GP(D zJ69+flY)Nv^G1vcQ+0I$ZL09f4*i-dCJyg&Owe*N>`W@?rwqBV!f_$9dIRRdoWM0n z;X77HFzijMLw1F_c06TE;*V}%KWJK&Jit@e(nvVs@*TJ@>NJuQ38sjdbfNa z(5*CeLV)9oYz;HKXAO%{V1g(1Eyy>tSOM9MhRQ9fs}D>3_2P}q&RL{mLAcyYOi!vg zF6@I4I&s1v)FgAvI~tm%J}Cie5UQNqKer9->yHep9A}rS06ohMQsaLGJ2mVfqtSku2D+)?!c-`vp zdTO%9Y+eKXa3)Kd_MH`G+~b_Z4^4H=$x6?o1D#UITwFXNqm}s6m2Wf`$c!WW)8xo-cOWpIc_K<7JtCu5maeB&yKLii zbD)le$wj@+Nl!_G>3IL275p%A@&Xc0`y(~UuOLp&`EbICkTV?g-y~BU18*&UGOpJ*!HZT}36AY0)ns0*i^pN+BIr|H7<>c_u z{4ld|N*;L1Nhm}|ecV~gDNA9?T))aF6G1`_;Yr~R*XRl&y`PS!Gd!B@Qd0w;^QMcg zjRPVmD%w&?_cx1>wPS<+j&i`R9?G~k{nr!BFf<=6vTy~0WV;(EMirBlEi9CP*x53Niu zAdvN~%BmAFv-uX#+WKy}-E}G>YBnpoy%|kA^EXKJhRJoQUBwOXs4(`}#|1_3ZJcr3 zU(8YyGMH{E6QMH5mcME8ikQ?uk}DLIBK^eWDeTF8%lA{b@&)MCb*7>2iy^x<<0@5XIq?RBTcfkBZeDi(Q3O z)M{BX|CbG!x2zAP0c^r=)0SBG)@roe1@^-|jHfTBg&ZA;XY}^k}ghmT9KWQ!1trStPTSt3WZpB-j(VStVg{AIs2%wQb)^%374r`=B#S|ZEW+$%9V)^GfPi|P%sa~UaJho+<^6njZ!PpYl=Pd+Cw z0C2EaBI9NXIU~mQ9S^bNCt76A-;%c#6O$FqEiae8rn6843flwz^ih!E;ovF+PG(w- z7)kBRKWC0pUXuVriB@A$cxh?qcotTB?RvMq07w?->F9WD9;)3*ch5iAON7Tb2YDMXGJdLCK2jd7uP2vDfO@tJO@-LGcn|VAjrz-i0#HkQJQCry! z-X@9)5+S+ay5FUThdc7?>RL$?`&EzWVI5k~b`c9Fr4YzuuqRq^&VoQ_Uf6MIF>|H1 zT7zYBvOSuwtgDvxK6ZNA{*G!~V@j-?*al$npy1)JX5N5Ob{mH)>D4k_;}&Yita-1&4h~G5XGhSipPh9NKE`QRSk`lY&9#ML6I7PSMo(dZG;Py zaB%UOeoc7$i*Xtg;ktyT&Q)608~z`QiHV{*!_$0UlM(R$G>N+W3_)na0e-;em@I9u zd%cE43X8W0hUlr9+#k^tl&MF12f4^;&-*I!?NJlNc&&xuAH_^fO^uYpi-P2=w0Yv< zXlaKFcOVB&Of~lY7e|^?3+dWTi;FP#&&xAznsLm|q6>FqS|c2c_4uX`h;tR_agnFe zz`DZ8x^u6vO{q*kAZNQgFU!ktBlpOcfGed~dtFwRXGocFn%SV~9UGqxf=<#BFgqGp zOE698Jgv&911@eW+>NDI{5hv9Z?C4P2dMXSBXY)Eok=)17hnJ}n10r7B}7f&!OdM> ztqBnwoYh$m?B{g4#T6FmdgoxO+AiJE6*z@wB`-s>$N0CCP=HZJ(n9aCiRHGkSZJof zASE7({dwieP4v_ZX8wD-s>wB{xn~mw%=+f$r_3Brdo}FHri%=0Y#G&o4=_-F=%ely zMasg+p#WyDi)viuThJjf#U0BAh69L5aac^%HQU>o@QWI4u?YB0?9Qb*D9WaLM0<>g zOy2w&X#Ut>YCNx~6*@iB$PxxK<5)@n#YSj=le+r$W(?lpb2b%uR}l zPcQcmCL2kdh(cFBbuzelLd@=FdZv4e8Hv;bS}oNgFFF9*mL2Lhy!(1&w^2#er?pC> z;Vy;~7?jpG?_(fd-|a4$4K5t)MZ&*1ow*k*^nS6&50Z~Vq)dK1-ySqQH40OfuD2-&HoK!{Vp8ip}K`4RdHsopFLP_R=!qd(^mkquDm49JDe* z#0%qGoF>iGL+)HZYoyw{YYQ1754YN(fsq1v&bh1Ce&qTA*MH$tim(u%%U-in2gGw; zTkB9w7uT!Wjb`*TUeDQ>rV+_d$}lJmW}L@Uh>&u;k$%ACveUHw0W<~{Tl7EI7BWa6 zPhFJ}D6Hx~%b^1X6{uTO7k#}&ebz29R=?!_s`$fh+1WvKKemGUUKf6zl-=+U zj&4f$9CrF*Tv3V3$f$hb`)aAd%;nY7*Wd3w>wAy`H8IO}qzyPFbtU=Xag>a=RQaw< zw^=z1;R;H%L_XLa@E-0&CmVKkJS!rb*gW~{i5r?c2m<7git`%gQO-G8cPhq*S5%Dp z@EsK#CP>+iBn!uKnkoD`43jPnaBNC&lzz_%mh;g&4;PNdDI{{DIBznpKlXWezi(A~ zJUi1k!Z$^S0@pFbM-rp9@S_)qfHadAdrz-X)!LZ51w$@8Z0w*qAtXdBg4o#9@`{R* z2aOD7D*6gOFprWaznrP*z|bR@OkLSluBxq#SV3*y@jdyPxP&+=>gCYUZFT?iH~)@c z>i&_Df)SOcR+UAjx3|JTU~q}Lx;g+eh$TX5nn()O(73exKKahPQMN}fk z3lGPKMIqHyU2gH&8;mfTGa>AGL*;hS0SV_wanfj-$07H|rxIyG4u?b##x}|~gfso4 zA?V}2eR5?40thd-fbzGZ(W)-mb}PlMU!7n>!G6}SZ`XzCzI0PvZv`pUi(l&{UI=ud zxXTzszBFeNL`NuZm9$d_{6Mnat55}7tFe)C!A6Ju`0B_L-^g<&Cr*6!AUjaTa{G_V zP^1AI{9z;@i|Q^m{vyXcg_lj*E&9?y7F7(}2M=Nc{IRtW7=`gdiF!Y?XBkIE^8ELw zLE~+VC|8ehr0-HoOhkC3!+(#>MA|a9p5e+k;HR@7c+k5Z=L%r%n%G*qW@hA1M z7@22aqum}U!vE&1DB)fxKS3Ea{cld@e_l9ASmeSMJTfHayJ)l?^zl!lc-Q}^tr-#W zY{K#k)gCzDS*L;7q)1@Y%i=N#B>$HKw)UkRvBvYwU>sF=}il8))Z$>G4lLQc5w2 z0x196$HH{%7`|kT1kU=wAK9KnFJmZb00i-+^hm1Kf94B>{O1ny@+Ps6>5IVDf4s$ z7-glJyQ=-p5x>%+ksi`DPD!U_WW%M7h*9~>IIb|kOWQo%sVbbCpwUrYlvONN`TiSx zNXOU8KqqGmIkCJ^*1v4kCNGaxZ-v>H0*x+a>SS5a6lt(41BDKCvp)d41F_x2@uQOU z3(L4Dx9f(eBSRlqB1XZzEDKERob8Gl8a+j+I{mSQ>aD5nLE-hmPvEzQR|&<*Z~l$* zZ#d@wJpLGi9f{Tc?5dal4R~^zotj{sLqcWOb&b~utEl2x(T-|f8;-<^s5r^ldM!Q@ zyA^XJu$#?`vGCP_j&1k4dF^V>$$Ak)zbfft7gG_D@Ob3923Ke4#dTqGB&x_3NNcZ8 zMK`f@2ZsOCQD(Bad&{$5}q`dibpGo+*?-5&p@uTI8{2`k0BUnNn5WH1*-R!LL1uF+fJX&;XYg#y(TVil<@a85~Vb^l!aQA#-3K<%^|7U}EeV4p5j zno{#jy|@U?4EPeSj0@5_Ffng8EI|FYHQxTrw0p`itZjJEZ;cp=ogjr!X5+}wE#ju> zM}}g92WuB3Qj*)%%3nE+YuTUto^-;d-P$8YQ$cV4$dS8`L8WTFQVY$E>FB5px68-c z2~>yC?_7$XPOcVlw7TcZ7kzMd2s|&d8r&tV*>-fUXZ|9LYAFWkGZ%;xk%A_3zbdR zxUg>vmtpTmbOt*1zDZCo$RqtR%La05!ZGIbE2J#Y%iQ|5r9GxjR72u|EGzbF_QO$h zSq4EWSV3|HdjQ3%BqoI(?B34K_~_RyCyd8mzDl3J8_2;r%2KGSHZbU`z1m=C-|Xmv z9?6dVK98(G-l7JyWTi5K{rN!a2-h7FQvg=KEZ|EYb>O4lQ zMaWW0V#B*zzQ%2}+rD%??oKdWvQ!{*U1-eMC!IbpFl6{|kKu|L0c+J5ay=od)`nU| zMXjJd$H^yMr$3jO(U3l*TR1U^;d}>0>1w$NJ{nF_^#1VZ?n)YW|YJ(e|-ysa_j$P@;X=!tZ51XBXst z7Fx~0a(HyhuQQgR(q6tqnc-po)S34V{r4?gP%68N(N(}P&2Vrvp9Wib{4o{=hS&rK zs8szlBt4xN-PV+fUyy8RKG+_)9gYQB3Aze z`?`~iDZkj3!E}GSSX`KQR!8azt|kqcBO?s;pHM#@hFMdbJ!PKY=60Ay zR{+XZ0G(h%6{7ea(H-iKlW_CQvBm3nvm71 zx;zkybFUO`URG1dD2;*_Q_~jG7(U4oyQZk7Emqj{-~21%ufZLBrES=i%Nv1BW*qNHJEE*)h0(Mqsmo~3QpvunCPtcYRx&U5;kyZ+ z&c156EvL2lP7h6yW|ArcDZ}FBwSs&M*;5~h?(YH9jWUyJGjoJKe}BJ zWq+IXrDnQ(Sv*FUZyVg9sn?C6aQ`h&%h;T>kVyxHyL?S?t;YU*2wte}X34#bxE0TIV}4rddZcV{ zVCgs79S^P$?U9tKxPfTQgi4xb-IuQ8nY$NLzql&9Q z1;}%0@gOg@Z5K#Gw0!=h@xsH>;~IX`Y^1O^mgf+}>*S_H&ULeCw=m@va!<}nLRD%= zSEz?BF&?2(El=)s8RtcV)0mY#Z@L(f z^eEajJhA5WSrRJBsbq75 zYhyhvwOI4wij#=VE*E_H5ldUc5}%o5=@BRH?e(22);sWU`}r@uCw}h3nL4 z)t~VBcN+~I^L*2_@w21!sIDwtUwVgVou2^l<}GEFH!jaD@L9qR=B0ThBV1xstwhQK z8?vuOPFub-Dd}{pkS_2+)v~vSSM>6Kw^&uRdrvn>Aww-owny;ytUux4;@Ww1f4yQ4 zC;l*+nc=>ixG{Jh8X>c#6U$y*$#A?{W-o5GpL9-)?J?o*dAs+{+?a`L98lJTsoVgd{zt1wpT)4%_CFNaBUFr0#>Ao`+8=T`==d`r6_;wq3aBCrj-MmY} z-xHLb&Uji}TCi!4{ukk$WXzo893Ev5))sXhYjn~;obEYDXR*X=5pmVnQminzk3CnZ zE$g!mJ$eXDBNeZaoRuhXtJ-S}jQ>2$;p5}O9KUoq<2Sj;JGcLg=;)7fw!V<$+jFAD z8SoeDmt}a*`5=dMi+d!^(bFkKr)v$qJXLg4{3$&u^m~IS>(i5B$Qpk&GsZ{4hXCTs zfAH?zkN^ukpA(1`o+~hrQDQ1wufn$gwL?g*c0ZmYX`Wr&8usK%Euou#Kg;Pi zX0yI!QUX#UrU9@M8R-Xp<=_FZ!4u%S^D`;20n;;XQeqL8`#0|;aX#Vh?ST@Cq+#K# zsSLnElzh4E{^xBn(Z4H42aPgqI=^d;kqk-6W4y7L{$|YNR8682HhF%x9wWK^88Xu4 zr9)DKg1bPpY6<)`DH1X=R*d}lkSDUL;G-*Ocd?3GAq{``fc{1=ADqOfz_RyIjZst( zrtprEYh?t{r)$9$t2GH}>6%)GgPAgqE(8$1scRFg{=RBO?OG$A%N zo!yO`{i4bboD?#J%)4!WTJ7ZUNn^{d;&`zQgjH@Vsrh&BJY9>kzR7h{+ELo7!s;lQ z&9vjuTM=kBy$^>X@knF|liD``jdYpnm^k}-ihu{Ws6}3|;-Maz26z(x1Z~wvao&7a=zv+5KL?*j%EbtF3j4iCOUmM5|+b1u`h2=~0 zeK#{bwFp^l@}4}e1+84~CyY2a7g0%;hlZzBW6CmHr<+_zJ-1ieuDd$FuBEVtE}8oI z2`^ozo2)gN#sEP{!9&A?`8fE?6@;`@RP5PG=l+_{4-fDaORug;e2sRtV97XiqVbj4 zUU^-0_0|xTR?b>eib@j>%Tb*sF>pm{s-^~EiB+1qZS(J#*wm(tH6QAty~~4HV%EZU zPT!~m-7cGsSG)sicMh6nKTWo$q%&LOkZHrxmW>#Xh0Tq*220RQ?xtE$*^$FjG@h{2 zL{*SOBC8drkl<3C*<`7h2dG4-57I9d0i(nBd2F^?f~vmII^D%$JiK>$Akl7i>6`8@ zv>roaNh4}Z|HZ%I1br(P;0NA2;pe`MVp)(o+dUEPBTGz4T0ZsqX<@+L=+&^uLImc= z&i=&i>dAL3&ErJkE6l~n$ePUHnpqbIZjzuUXW2Xn3ejYff*dOP=!iR5bpD7)u{{ln zkKgvWb0|}q`bCoK4w}k$xku>kp*-b`EKhi9<$R&qDms=_dcw1lkKDp3$@A(hXM6_( z-Tks>2(MRLAja0lf-8N}Iy@eKVh&_h=B$>h>Z|)lhT5GWetk^C!%~H%B%cUA5}*1W zCq+eFGHhYQb%ml_?9tNFaImHm);dnD!aUxpE=`a$T^6H$S;VUF!z~%0-gdKzHkrlw z?%Q?(P73&)sfpB+b~_D#B1_q_z&^psb+zUEMvR$lz~2i!t<^bA?+c{}XYe>0QESI# zff9#%=VtkHmwH`li#zma(JT7kcw19+Tl~V@@_1Z%V}nCa5?#k zPnGPlYT6jGNYtqj6_X;O!GCIyrao%SZDnA*W3#EDkqk?#`TBBi zudX7aWJU!ScHonLUrKR%|+1@xMQ+%jyXr`N^Ew(>RGxXNo44lX4*LRZddh zT{meJnI7xr%YjZ#(Jp;R22iv3=)Ca@@hV@$CBj;( zwSBCu9d4gJ%1zX)?^4oQp`h?*CQ-m*)!cFXoYwFHmL;e0hLKc6{D!uGQO~;xgL3qh z*8Fz4Dn!Lqg82rT6@`KZ#o}g%8DrVCauhdX?o!L4UaUT}Y$(LsQAoJ&)IR44MZjv$WB}M|8Z{HqFCo};{Op~$iaU7|& z?J9JPXYch3W%}wzs6J%>{zgtUZ7FPWgXKuG?FGyC&Nm6?%n&--Z%%_ijI69pwnG`) zK{%MdE_^~aCJu?)^Qjw>P#2^SPPPKUi@ znKX6jb0e8-C~`u}sAh}w?T1@@ApejN^diAASyf_L#;4^SIn;!C@wUwqodaaCSIWE- zVH}>bIayqEpDg7@y}kh~)EbJ?c5(50g|5w>;pY^~k>Sq%tKRl!#%M@<+37_SX-0JR zG=wcfY9|~%?FW1UanG;XFAkjEm{w;@ymo)1%ggD~hSk;e2LE_AY*~}6-Fvu!6rDhG zcDA_*qTj-UgN_5bF<=L4i=MTbcWh*;xbPOP)XFW7=28BQufd&0LpbtWO}Yjx5-U|M zH8ri&SbwoXU(&&`a-SLxALhDt1#TDXdZD4AY3~XJI+CHnR~Vq+vnpf!m|xn0>?p87 zKA;h`7czjOvi?+)Y{RMy@0VeTqqCcV8vNj*LS7Z?eSTT|u#OcBCr5YfSLNCV@7;dlM-Y|{PmJxxK+Z7q)4Tx=m?!%s*^rU4Ogy*P1va!z}Q z1_M+FqW3NvlS<1P;>#;wJfT<7O(le|?OF!`kRw;4jhd13oMNTo2DOF#gfHgCWi#9) z-a0vMW$OX5Y93Jy9$^anID-Fi0QU=K5LjLE*2RK7S3_A3RzADZ*1_-pZEg?miV%0 z+-ouvg*=_`Y|QqDrQhz36D!TNrm7WaYg3(_l0Rv_+uL1S8oCK;XoRdG0h7J6;RfdD zsVLbZ?#|KCl(1EnMy7_2>vcZh6n%u{s5QNr?L_G*MKso$(WP}xa`DL98hvpJ>;sgw zd7hT8K0Q14I&TQSc`IVEW}k}m*cEW`or!U=>AdhE@2A1f4vBQshzTe-v-*1oc4+`xP_m3Q1@r{ zR*qac6~?@^g8xs!>j0Cu6#inXb|(Y#5uQYh8-^B_DTK2}+C1Ugeq%<*dS#1%izs4y zCakJ?NezvAQ$>p@;AP?1X2FD{A&bSj>*0lAvOTHORZ_h1#Hmp}a8fvBQUXG@+VEPP z*|dXY%ZBZ9;_+H;)>77HRIFAOJKzhWAHAeKjf`3-MLCYu*yoDR?E;(j160Hf`ZYCn z%bHsFBlX#G9*zOn39+)e9E{XTJY<=NuM9D*md|ozE7dk#&s^ZfQk=$M!4y$QdrD4@ z*61GI2Ym4W>-i4o@)BXg!!hrBBDQLhhNmM9wmiI^pU?N8*103Nwq+T}{Y01RT=`xl zEFd&zgW6o;%z&XsGKP286li%?gKp!?TLF_FdqA+lvpg2t=xr$e9^!1B0*ya+&OAor z)Yx!$A_YA)^~@yZIeOeFRq?Tp2|k#;D7(q{LXT^Cu82(z|pj+mwXNofETleNC6gVE9ZG3e5S9ZOKXg$!fLf zdR^DI;rMZVyzikjI7C8z>ieGXb&dV`SrI8Wx5Cef!x#pCg!_op_RVLTzH}^20l`Fb z%NB+x=Aww;jg-NDh3j`u4TD939Zy1g(S-1__1_j7CcZ-tjsx;te{7BpmMmccE#Sa|JayM|$IdDvf36r~V{GqZ!LG`lRn3Uo;)y!i#-3M2Zdq&W#M#<<) zrzt)BP$8rV*`0sWe*eW{bLAEiz>Pb37ehSfZgQR9UuTnv=JZ`5J!Vw0yjj#WIKDYY zG5hr(@od))zA0e@ynZokb1C*F@+`Y^jBE8AiA#~Ki#8cXwj@VCi@(O z%%(YmwjTv*=UU&zJ z$go*(-)uIJ6wy>SSg!a^>MfgYZkfm!qp`iVy8J|Ri1ta>=M9o(0Lrd1>k>cnlc%ZI z;=bAx&^`z`IW>G+ErReOJ5$ zJY62J(Oacjpxz4GP*%EM4;SSSf}4w1^N5e>r*b5YU1+1sruY1809v3K< zmb8A96GdL~c7RKF>M?iwIQO<^(=dJ1r3fB;4d{&n{n~uLx7V(yHmpuf*%2DSTS3HA zNcnug7q#m?^Rdv%Rv8SU*mBS4sCB7dh1sx(z5Q&@OZTpn0}f|ZmhB{~vT7?1Q= zQ)9n};{Nzfn$OP>8zM@rUvIF{2P;qm`rjeg%_YEr5{R=jFtN=&t|qW=NjUWe0cUa! zLf6RHQ1QZ+CKvz~NBEN%T0bvmO0^cp^R45YHhXA&oy3XLbqh+YX4A~)C*xHl1Gok9 zE$&#BRm)_-Y;a@3Q4S#JVz5u|j;ASDFyhvs&*Er!KD9{=CnVcJY`^O6$r)!TD3bX%Q!IDfEo^$d6p_j`U-^n$(FyFsX~ zP>;<^;;FTdoOo!wh5ny)DLO%GYE*{DNyZ71{LS{Y3iXUlzkX-!ATs*b>WnO_wz&M> zaL!4&?tSFHq%Li$!M}zR$8q3m)Z=obC$ve8lG@to&9ge+ZnACO&1F9cIXRps-DOzb z)P9GXd08$_qq}+Ih$BZ{Uf$Fa85ucAg_@I+l7&U8P3!pK;h{ig?^BT6(@G`Gb_--O zxWnC}Rc1AL%C^Ag35D%vsixL_J(NOR!HW3ek9!|rX{^zH*$0f8=;-Lg`NsbK0vCGL zJ{kK=oNVEt=h`X`W;DyF&XBdR>BrquEOkZ*;`uqU3H8Fl!Wp+|=We2^`qIPi;KwI= zOJrJ_>mD6OWlAQd5JyEly=uGH2h>HTwKB}Nh@7Cl-;VDuRloyhCVR{TW%cf3rKN|# zR_us~sMl=}nzevY^5nSAkHXE#;UIT`uL>Bof}Nct1J>b9Oj3zw1EucU{Sovwp^BL7 zQ!wCGx~Wi1%e9^gNhs%-Us_mrQc>?~vODt6%k!(L0rH{@($G zT{&?~lPfaatF1p;s+*nhK%`wM5h9=FRW8lKJV9UcFeI}~_4)cs%MH!OP*0yU=OgTM zp~{9$;8i2k5eP)+E=MS`x^9@E)S39m#lamb(%{0{HeuT`n%Z0F{hC<(CN9M{s+Ud~I zc)3)28~0mJiIna0``{TQZr-VB z{e>Fyp=}5=V{%LkjHCS{5+&2v088KPj<=O{BvJ4|22vAaTkK{yZYMm|nnb@D9g7xo z0{7pin!>yw_(27p41hQKe5j8V<5W=9sN&nU-hOMBUd2c-Ox3pp0?s(tX4kPWJO3!l zE^*i&etY`>hZAy5#I9#<&aHb`h`GP&b#pQili|+ngD_#~36OQPSgVI6KVWQ$Oga#8 zEXhb1vcg)Xk(`q9HozCU;5FYrZ*ueDYRAOwa(91S)<--nC`gR+`qRAE?);q2XwDNJ zSGj?qvDf$e*EBRGQ^uoHWS9F*a*VN7^XNqL6=E^K#l^)rE^GNOtAGBq!Fb7iTuWWu zr%OEh+lE*_H~dfghlipoQ0S$4t%;erep*_Z{oUc)#U@v)@>>5`!OY!4sS;elch~I) zPRH{DHC9%j{Ta~A#6%jir$gEz%jM-Ii3rb1wdGvT&>Rqjs5>^maV{){ClrB-l%M?g z%2ES$caD>l&a-R#D4nh4?s8AeM>-uGnUK(Ml0v`R!tH+Xri?c3$y6#)%=5Yon=q;{qX)x5L2vM zu4+O!#R|{*WDvY@GDj!n`9)DoX_-Mg!yjQ0_&!l0kTC%a5-Wx^a6ij|1A^IQGJxQw zS=RA6bVStS*}52WSSfE{+jqg=UGh^?Ba%`ulby>4A$t~M6^zEkR>yHKHdv0V-MHT{ zkiiNM1}6Som$$=`q6OhczQ;lFC7GF#iHRl-5~}2jZvZ=TjK7hpr3k=l7i}xGrld`3 z{VN;!m$`&huxlx3fBJ9{Oqzj|Ne{|ca@w`xj(cBJDe6>8T|&yMv8bO=?!3K&hq5~- zA@L~VXJlkF0fjW-TmcQXrZjk*CYin;!oF5;ILLljDXo0J2UtNxM5d<$lpky_=GnV> zg89*l)-m{(OiZm-+dK|9>dYCHBIDx9L>d~E9^Y5^uO5CB-jU>6_Zc6z0o=_mE?yk2 z`iXBXe^$rhZTAixmgLB9b#=^Ze$sp{+)ae7N+c=@0RbV55PW_eO+ClI7gc#863Uz~ zS>WVkl~I75Wb*&(0wfe(EwlUFT}O?5F5=1oIBAXB`3QC*pzpfvAHMbU*p+raPS*n0 zRDnuxVTBc9Vq$gG)w%XvgOk7izJqq>uk(8!oB!xOz`78U>~#< zxHXKbRIKF+6!Uot`Kgyw!_z@fs5!E8u^RMm6%yzI;%Sp%M#KP1d^Y(I`!h`Thg})# zVWxDRwL4`f`;RJk@?XSXnVE?bC=he}fE~?PUFZG{otfj6@00EA!~t63u|JEnnvER3 zHES$3mxlqG9 z`E0VBh!KmJ+fZw@yajJe;2|`Q6BQdPNy1J?7yfYh)%|-)QqtKDy2v`dt+~W0CT*;= z{+`l85YO^-8my)puI0P+0+Xm>dJesX1}7n4Zqg|?DrzHK>%K9?i_LoVI}1~ud}&e9 zURDkzolfhhjPUizu%uK`U1{d9zsKJXqne?n^BoB}BwVMk6nLkQM?k6V!(~^XfV+4q+7(LRUw; z0!~FmIfmy(YDsDs5u}hEG0vTiEPZB|lK7D~*`xy3(?zO+Iy;JJkzU!P!H%QbmbQq9 zFn?>pJNXGI24TNPr2o6Vv8hOqfB*led&{sW-?m>AML5}el5RitU z29Q<}5RmR1y1Q#YLAtxUhVC3gO*SSp^i7cf(|5TC zb+vNj%IUsXuVB2Zu#|zZ!K$(nTDsS%l}wEEOV0{-f8_mE8z{?pEMSEY6lqx(aBEF^ z;7(SQ{G`?Gn3IE}$P-?tr^jEB9|Gf*_K~}&9kg}>=6Cv+LqRUD=OVFBGf%U6*D zztRk;f?UQ0Qo`IkAhlCdTJF8HuWhpSAK#}4D%vP6Yg-c6|(v|a@S*Jbxk=o zZ{RjMWN&Pz-h8~$Y$~?w1-r;59fAMFj`0N9eU1zXZ@0%ecIm$42HQao>MAzAWmlHD z9&iLmZ3d(H{FNk5B^yKFjlH(GbAj4zc~}uOCI__A5kZ+9@={FeHYiN(EwAg+@h-fA zQGXR<2(OR*7Wri)+oim%uMc~!de>^cHe`$0ofXFG2tgJBf6Y&UAZptm2%SsI6Yi-X zwXtX@wZMJM&W?@+F=dymJAnHKl~w$kd#%zX+LmdUZPcuWH*1N1!f ziw=p$CByAYeo#g13dq=X0MSrMX(@podm-BnE&UAb?@yeN%K`Pn^&|eYS?M$VTP^s_ zjrU7_yVQpJ0SH9O50bZuOH{7fEx&HSPN^eI@oI^sH*aR0mR%?lv+lZIf=s%`ebqJH zcUQ(3{);W3t6&#v({XRgzYexH6dtae-CqqEwCX`D9#^>xw>1@O$ck#4|9&FkfquMI zXv^;4aFnypZt?pugu24@>Lopz)6P)XlOHNFk+Ao(gsT39HPDOr+Bm}5~ zEf3eo{fB`mJO?Tb=>^YP&_8VtlSCeWI%Et``yod&m5(RNcx`tFHkHP%0z^?c-oiq! zaVeV^cQ2ko?qOR$n-x#NerDPZlvVb837pnXo*##HQ!93bhw(eS5+Ku}!n~XNe6}Vv zOW@3XdK{+Ya9B#X6Nm40+v3=t#1;Wzc{5bg4fLP{9_JIeHy&<^WnZhpU@Hr$%V&4V z6vSiXNPyarx#4~MDZ-zPOeUeHH%`3tc=9NQ_Tr7pl134Z^QZ%oeo2v1*L7t53lui& zJKQOgt4rTC+}bT6?;m0!Ys#LotHGY5e+Fb+_T_2XkB-AcXMg=ly+T#T!&j&Z%EjZ3 zBNK4pw(h!D$9{RbQTky}sW&^*!F%_eLSAV1w8BhmczoMxF`_WID0q)V;PS`nS6a-V z8XcCMm8-A9yR0j8iRLZnI12(;h~NiF_7%y;adftw9p;h&_EL zhW9Aj^rPo#X93aBl{WI!`kX3{_fLZ|>Vo7qJvlz9DJJ7HU!~uq4JE){T7LTVt4K== zS*Gd7f$>NBRFWw8W3@}cNhI3-w7Hmfo@C;kW2E4dS{6M<k_e7!TCO{1TjmGMPbC=R+g06{F= zY^wR&i>v%tXw0jeaarjtH$`u5vxKqq4oflo6!JaYo0|L1crUJ&9C>{fB>0zH&Y_ zRoJ&cg}bIIqSejK%}Y~Q#qt7inL2I(UAZ)Ui6Q=hpyul9Hq|~GdM&*-FwZQ2jO~ii z<#9eg>2D(A^Aui3<-|uL*AbU}W-1ld={Jl+=Btoqvr-~-Xo_uJ;0>Qm@5qjPnr;YE zDc(Z1MVkb4N-vS-V?qX2pWE*uKUHBaZ`Zl6~tDdh0jne!9_eo%2>t zhyvtu#_o?LIZ7IF3^A?N(&Pk7Pa*#FI{}%YP;^u6(-MuMzdHI)D1v%Y)UD^`;*TVFR4=m$K6qqxPw8>(S8! zKrI}_uuhv^tOUU}ES2C+=u$7;8n2EC4#u8+xu>T_(PaOA=xu7#4E>e_8Aq-CO%!zKp?qaZVoX>7PISpg0M7<)$+Ey7kn~AL+DPeMDZ= znag_Rs#GlG_d{kIMKa~^oqN&fDIO#$;?H7o z2eWgHKXyo~2w2EvTc-;XB^D-p@=!X^v_Ea*3JNVKH8^s5y218_T1h8*w7EHPjDwOf z5hwIGqZ)l;lx?6p+>)Ay^>E{K771EXDIuRL?tztKdnc!%(LpZH&F!Bz9tacOsBJov zi0DBoycMe(=a{&SqcwKkVmCzv@i@Y+UVD!&`0L$EjDdOTAfm1i!5H4&FK*Xx6VxPf zyqfsf=gMPC$F+gbykX7wgd|J)YO^k@fxy?_Mk?4bRm`+!Hb;`VuK9dKw>CBvB*cVR zu`-uu}_>3dDJF5f2R{8c@8Fhy$Da9sCU*o61*BrssxVArvuA|_O zo1jeF7+c6$6sfVP8NYSImS$K}Wl1Ofvt$QemdRN}-MK6thNU`+ zw>gvRkx$TTXt?aW$MtS6LbI-pTSX_wY_6?&=BhKoREIN)JSW8j0(o6>9}<-#v$m}! z?gCK>%^WWwN6r0d*RrLSiApJUDJZO~8u*D$Z;4Q~JgdA;2+xn*d?r+n;s~Qyr?O9A zfj?@LG1G@KU_hk`CYR~dg*p&u$Ps{%^Sl>7FGo=F&I34tgAG5`?0OaGf?wK-sX`gd zd@A*>a(U?)9I%{lF&BxXo|522yfKz(uIv!$5`0uB+cmJ zD|O-GW$!e1l}-2Pnv$fp-!(h1Z7f#>2TbYUb={CE%3~@)Z`k-)rse?q1*Q zJ*4gbIqSZtl+|^DL%0#~&0V**aN1d!JB+*LebBGKL1{xJ%tCV5Hxo zhtEqbEvQ&>C z5~M}l>Eq4py~{6CY|hqXiI5i<3PrwZ+COvi*_ag$dTXWGEo?f9P6$16r!V4S-p4`>Rc>NNGztc8AT>!fLr8fp{c2* zQ@14PIQ~J;VQ?k|Pi6}^Rr0=c zEG#SlU~Vqn)>01v;Rc8M7D2DO`<~Xc##<{8B-C~1i%@Sods%6z=OsHm*W1eE1cupS zc?qc@QwFrMv-4a9$Ms!!ThL5U(4$&2KW62%wKc_(_=Il$FA-63ASNm=KR>^?I2*K8 zw3x)_^NF=v&-Pa|M*tpK8%aIu&m1Mu(<77XZ5UpZ#BEFHyVjd9bI`PIcVTgqC2RI% zbD8=XLW$Pc*dRGET#RLILUCJJBRAKanA0XZBA^Sgh#Nv^uF8kmGc?RrqIu%l$59v?;JLEllF@F#LhNHXqc4WwYf7D-MLIr&i@H(5HZJ_H*Xe9jIFFxAZ#A& z)H?=s^UU){K>C6AXg~j+WUnw0g1{!B6GN{ z_U~pbbk&l`L^%#3Ay0nXkdI95lvFgzoK%zdniT`mHrRHSRxMF4PqJ2r9Dl)jpiBe& zEAgTJ!Ty=Of6ACt(|(r$(Wzp2d7`*Lbn}~$Ce>~efJ?vNb#E|2azsZ*L!}hL%PnJq z$JC;sU)*L7D=RC3aBAkHUflHljw(Rws!=!Y4`FEiUY4lixTsWhW<|~&#AJDFZ+P!! zak{y(+sDkdD7pNQ*cxNvwQ(K3n1oA<*Y&P=g;+cIEb)N@0Q7>}#_sd+RUAgx_eNy^ z5kq&ISB+@;hsL!N)R?|@6P?%XxW(8g`R5l1J8zrxCT3lAd^2GhXcRuoKW>(j0$4Zc&he1Z%W%B~+>?(ZHxC*}|-R3mX50b7K|wQEt3egQ?s zS0%odF{Xs}wzeer!msNZav#AiA7UTThTFN{Kz?sMPi2Yl$2``-h!Qw&X99cK?qK0V z<)nriw#|cO8lB-y=mM>w`JBwy{gcP1gU@h#uS$-YcJ>K|Fh4|&aN8X+o~_{HZ*6GU zI=azrA2d25w_Q$A1~&%lP1Scd9LjD76zPraXT1t11-+2Rn{)N1oQ|d{qs4*i^3gOj z4!tyQhSo%Cnn6I`wIcd9Aa6)xCbMK+PZ0EEL&LSl{cT=^=H66687_kvD|k~MU9Bgp z0*U?9J`Fk_(GA_ldU#gnm@xeXuUc6+T-(*tlYjm-%yLKTXMdz{ z?CNcK$7gM<)(8oiNAhpwOFGHuv0eyDHY9=o0X4Cw( zKY^IT#xx_Fp|Fq|r<9iLp|I*zib_QU5vG8bx{(jIR9jYBL)TBuUWwR{RL+c zjdIoch6NFm{*G+teyVrX&W!XgRBNk&2Q z*SZKU3bqJsksFQu4Mw4@N0QDQtDqtK@NZ%KdNO@OhYBJM16HqTfOPr$C2vZ98rPh#SX&ZS(T zA@C(U@MlmjL>@4h2t;yG~Q0|aTeHpXK2 zZK9$|WVSoeY?|6!X$4d&{5cU(mw=I2t8AC%U`JO|jVQ+VGHuMJ`d2awKV0c*90XU# zq9P*|=s)+}yD$+w&y|vrW;e(84$JDWKRRUW>BS>Z)XO_i15mZJd39Gy|hYM#)`R1%Qc|;!hh6 zmjff~(}z_rV%6}h@2-AD^x(pO5UW?nBP>|exh3hLH^YnRY|;E!k?N9wvVrLXm|K+Q z^I_@ZcVhH@n1HR>&tku#bwjSBTW_k~lsbIMyn^V*e20n}Pw2hM+73GY;>9&oZS4Fh z(_=1oOxO_$?dhSvO-LPu35E^+6l@AOK?j{&ctpgqn;%@W=rIY4Ri0G4k~f(gopTi8 zIlN$K(Q==tkJf`utam7i*fcv~a+7HEjR^~Wn!#fw^Sjwp_^P8xiul|Sxg$AczvV?o z18%P5L?7tj9Z%+6{p35z_^?KWo=#t_m{KFppfjkis^-iH1;GsYmL@4_h~tvH1&m-6 zM`VWZx&R5kV@z^aM4Y|<<)tgW7MY_6!@P58)Ve3Zq+3}aI|qIE*Mo#Y6gwb0-lx;^lP6E>g;tX|6^(~9$W;J; zYhklj+5GKT34KoSyT>2J5emx3$1nf+rQ_v4hGUdaq0j%giC=pEV`@SX%+g{%Vj^J6 zqR37!zVXuWwClz_Tv058uIMbDL{ z*a;u{O8U?~Vbnyv^4QA1wlpAzw^-0HB|FVa%PH5VG{Awq`tyy%BURb2q91TI?h$+u zZDB>sg#I6e;8UOd9@pLr$Y3YS&UXU;EDW63Bf0@D8pRp7q^|gyYpMP>z4Mg#;fZ|sJ zsqo(ugfjPHB>A5c^52{p^gI9LF?@dXue3-M!h8QDL7=eS|0iGKf9@3j?>^9=$y{i* zf9Cui_M>0f}aLS8%9AXpyU;c+_xz|r2OlKNBK$YlkwLejq<=BLPonP0QBnR_nzAQH-~QfdtsJ>{YL=;RDH&Oc$WDeCd7?ApVDcml*Ryyy(6e~5m| z?7Us^FEGORaJ?&??j`-VTg28iikJ~b2~H{{)ns*?($Ix|HK82_s;@)M_|+?*p$&SOL~V$&0!gW|uYjy~iW!aUj^cO@fq=+U2<1*(@p*ybgICo5oTxn}5c8N6Uu9(mWvI}2 zHQ3z~^`53YRgsCORO2^wJnicMS&%B+R=o62212Mar6AF`sB^bZnyG*I-28gR$Fjk& zB%hop;si5`l{Cj&$mU$(*`y0M7kX$(CbqscrZ*)oM{wr0b_ z@zF`_2%~>QrIk^u*{{FR&L}D_3~Ul)r{kG1!u`PVe63E{o*{7zrQ|T_M{R0ks&M0Y zE7!+ZSuKdq^Y;rpJ`7eVUH%SKo!=ENgD9+-(Ek+)9Qn}TpL^kR4{`TPE-e-i6RKZih_waw?|OI%-^X zI~Y>kEP2BTLmtR9ddXN_MSD5h&%!)eyL);fU4oR9hXEy(9-Jjhw1F^l#RKLr^}^XV zRvjsI5XUZ(i~cA}*R$=Z22JI)6Z+S$^=d6<7lf{7w#JR}f&k+9i`;-MOJ0%lZW2uh z1qF@l^KKPleD0Y)Uvponq4bfG7Ka08+BYxbRY`W(Y4PY5Xe2WhJH*6%0i0p5h>L+u z7PVKLoiB2Iba?2rI|oZjYH1K7jVY?ynlZgv!9k2>8TC_j-_X+04SsC?+T4tlP$e$j zZpM1(D?2URLdH@|0t_0x)9J~gY|N5A*qknh>=w(z4j1_%HLW84}&G?iWQvw#zK=sUnpr9YGVFD0q>&~kf6@+a> z!&L*1^WN&(Dhob~@lp-02nO3|XE*muCmkJs_1?eVm{D-5a$Rts`p7A@?f1u_thm+EMK5R2YXQc>a3{0c0< zP2*Mzb=i%asY39&tCZrqw*`^RW!O=CX(?2)(rE_XU(jwpH^&l@e&|3#l0+r&dO>`@#(f9SxoXh_%G4pt zmME?+^Zd>Std1ik<(aW@WLz{fXCsqG~otA)h{4T6ww?kq~+rB31%gEH`Ov%?QWh}+;sUP7;ncfNV^Jjp4ry})y^R->ArT$ z4`1wl|K4HEbNbEKkB5iL^Nj~)(|!BiqqTzw(`4SDXwt^g3O^gyi$rb*e)er#>xb2- zv&18AHiw`77DgkVx{1tfp*e#C@WwBVjX{<8jsx8@%|D1MJ}idcULU(*x$)57y(zcr z*3TbjVOCX8=m57n?G2ab;r5k{m)TgwAWoncHYRqe5O{!)wtedtK0bhXsM&N`_KrJZ zk0ZwqCKK>1GnqBn+#ShH+V606b*(6UtD8tSkN=Fg|E%emt=G^94v??qvb!&hObWHM z(W^Ymutg;75!g&tIgETK*NIGnh$|jkF3UG@ykU)f=NXv#ARDSYl6 zR~fXR2gY1oPR@krL7wCS2n5!fBuj`wZ`OC~zMI-YLwBUy1et|->9SayFX(&e$t*u2 z9BER&T~rBWs`meit&1G=@YvL-Iz|HQ95ckqz(8&~Au37M|Nh0zwDUGF1o1jr!J?zb z0N~{t9Q$c=+vmVY%vK~2GqCa8V$oXvmICQKlB*nuJEO=6_b^kN_qeW=pfqG(Kxiz_ z$<<~&b4cy)&;TSxI?~(9nq@D z%#208_P4s0LhOIsTX^OzWWX$J=8r$KTFCAJrT*P?O37x3_obOKPGNIIOhP z4#u5pojoTWoD?oEsra+p`bf*#T9cKDcj;i%l9Pb> zGTxGKDWbnI^@IIoh2)RR7P!R;x|`dy2(o%m#zY1-WV+B%zRvr{G2i)fUcF#8{YN!@X0!r}GJuaLe^% zzB-E``zer)!P(#eaY1I8nkdjyh-g&@4VTpxobY!2w3=z)V`1^{I<6>CV~V%CPT;f= z_JZ-cQ9phO*MTmW2`G!}Zp@2^yz;3owSkd>APz>l*XH9@s!g8oZ~3x^L?cEaJfiRV z`hp|LBgsYpDEFHC6`l{jM;C|DM1khhBKd^q-ah@B$mnRf;k<;}Te#p{fI_M`z2dy(v@qi^4-O=+UcfEQ$D zS$@aADq1Z!gPk)(_c&3Ltip0QoNRckFKeb&@t!DimsI7}%=&~sThzl)Ow5P9y~dS& zIs39c=T}$jLD}`SW02vx)h^X7*JDI8n$=yNJP{;^-|3Cp`2-zi#Enj^$**yk!{j4J z$i++?3v&33I^=e#oJ&nD`lv~hGR)F{pl9UU)*BWBo*_22prDEUp$aQ&*`Udr$V-J- zYr9f0tV`9eg+Xs)_J)QGZ>1<#*%RNHo?-wdxG(AK+-}3>c&gk;Ibn?H8%^r-AM#r9 z33P2-vPAXWO})$?Lh!1|V$1j<^h5h|#0LjE47_QA$y(1?*bR*wU+aIgzL>Xw|0&rP zR6jAGQsPo{_4GyWDG#^C-4Nj6K{s#2bf@qAT4g(R=dp_=$7uD_9 zI~?rnkLMIC9voj9EUN3fSMJY~)cc@jq_@kB7Oj>c>MurQT|zo&`n5W)*OWdeycx%R z@kGpk*tohTt7mT>hlmCG*pc^BN3cRmvaYrzF++SJ54RAGH$FjzdyS9XMa4{F9>=WQ z5#c}+C)~5Ei|C!z4A|{}sEs!0DG+e2D=8}4EqJF$J{9Z6$;1i+flj94UO-l7iz7Rj zoZ7@OHg@+2yX{iVcOlQPCQKYBCoqe zFVYK%9%D4jn8X2*TyM9kbn3R_l9TP27x>lde~jmfxQSg33z8cwc6QRa-vY_T++5?k2 zau5@U*z;5CuH2-FI>(3cOxAaqTsQi?Xdm&p%`G2KK8!S;a$c~leoZ3!3OA|`B$v1y zp98k_^^i(J^={fvf9X7Sn>LevGct5EzpHYC{N{p4oa#3`#2g;grt=2eV|E7ztHJVL zsNlc?MMu)^sQg&?di<(9t`AddDZM=mPnUC?5e1Z@@dNwc@x99Xu`8cip_iCP_*P(W zSkFqjd7t9%#F2YnK4^af$|K;+x?4CAk*!!^4yuNFgq=^=7$V&qhm^a@XuR?F?~Kn# z9H$+wpYp0AL~MH#m9Q+Z(;NL+Bn9Eshrx%D{>!9%u7`_>{kaMG53=&}>s@B&=NWZ) zkxwUa4Cy~g0CP>u)&5Qs&*@dA>vcA)=jLPIBhLYwZi3?J8poB`GZ1-HX*rEvDIHah z?B_IkNl=Qr<~;979`lPygpFKHGY2+lmefeEpI%>{DpjYar5iTgoQfCKd(@AW zn>6;{-<&UwXUIla0k}gkiy`1;F*0geO&K_#p zqUF$NI+f?PeKh^Sdn;D4C7RJFy#U8l2EMUMK_D8$(FusBX77A0a;~l13%$?Ch}HRLZXgr^$YomnbVM zdlSYXp1SD%+*~G&mzJ5CnTfC57hWh_{wb1$fu1o9OC2F!o_5u_C187(78V^Izq^7+ z=?vBdEmgj{O(Jgf*Jy_Z|J}fvBR79YptOYZLG0(v$8u zaDN>ei;gD~0{7@==O6PsTTjA@avn`f|Bi$k%m=JU%tx;ZWO&R~nm)}n?0qS{jKut=Nw0< z(r$4PR}H7*!o6527JQXd3h8I$qE(oDJ~*5{VKYY3U1omcMXSw!9~I-p)Sc><;8`RE z1&rNhY$cz0-Qt`_bU$8GGj_b_+Wza)7mz<6mvc2pwN$!`md_FC;@#IWWvLyX^78M# zilTa0rB+)02d`Q$v=YJjb67A5>VJ$_iB$aUDo|{Oh#!UymBrQL_QQm_x+4B|nxMqN z3+MQIjQ=%IBR~iri!-d{hq+#9(=dFq`1{uTzVK3%&Ni7VPqKTWe_v4udink@R`uTj z$^W}i&i_E$>AhE+l;V*q*{o}?4UODz|2|_VDN>bvFO6FzS&b-Na-U>%-E|^JzGOd( zb7uM1zl)vpzFf_gb_(gq!e&rEh}9MA*>b#@ZfJl?_V1m@CgtIYn6yjt60C0!1)|@W z|NMJK1W(jFP%|_HG^=P<70n^`xv7p(ccX$~8`W`igPh|Pp1Kt_l8QwcIiGXW(%dE8 z1^t7`H~;1$p){c7*?h+H$o_VtHS#2zk1pth*>Q{FVQ9Fpbn+*H_8GdtA%lX=0ByO^ zJdGat#zu^}ThT8AZRq@^>L<8Difdlh9i_{1C8=cv+NGJ`Ak*X-+Fh}@=eSSZLSz{fCD;tT zQ#Jgo6Z$mbTRP<;6`=1)D5{?mX$Cq(NIxtyF5i47U%adXmkvC7#j9tQx){ffV#%$S zz0B*e`Tc}>@iJu2;I~9%8ATO9eSxum5kJTe4m^)laQjfdbRK-cjR#MKM zF6RBK-fRR1QEt84dye`;Nvm5;PMM+PXwulobR*h$&tI`^xT%_se@^dbi-LG`iBeCi z8p9>pzVGyzh*!+A;Y6Ain&R6N0YPtQSud)+sx0MqsFxj2dMEZ`Xqe@`{g!B}fGRT?jr~6vdmcr`eR>c|zq9+}pK! zH~gJ>0#;-+VOiTiY9@ht=FY;(3y2Ksg1oou^<)ZSBWQ_De{FVBM-KI2W&H+JKS$mG zzm@G~`e8LrPhbCI3whpil|gS*p9&o-+}l!p#s(^Vhx-UQUv#dylj<9{M@E)`5O^{y z6Fs(#s?UY2&zy>KW-{5I7qEFY4Squvs|uR9{@JeeUYqC+{wgm{+|pj@ug95%W^@n_ z==0w1nf?@*`BIpFfdZ7AwLByI`i#dM3M^&#cK-1_h@tx-hFuS%2w3dyv~sHBDYzSc z_?016lD=^aNze)OgDdIX zJ*G!ZIU6{Ahw`)}Kyat1yfUSoZ9?;}Kwkw})%IrYGn8;?p2@m6ZhtJsiT2PZ-qOcE zMA0bLHNUZDg1xGqOb&aL|H+YhjJmd!{kC2C}*eSh}-^%bg%Hr^X37Sumlaux~1|J58b2QuT`m8xx60 z*j0-J=6mCl?TVAQ-T5u#wf0Y@skAD!-ha)aQ;|X~-w zrIdkSPD>=kMQB_Zx{F_=&8Ya727PyXk)xB@Dg!CYsL(Lnq%~o8gMR;-*8JiD?AgCC z_SU^qM}G-*72h2y!>+j!8&UfVo4B$;4I2YTW?UmPCXNaawUAxasrScV2>`nBbbZ1p0YzdY(GNRn32(2dIdV9$H#Ae3%o4JDf#s4Ogab0S`=6mJ`%^qiAq1f#wOv-xh?s1 zjrHhJ%?-dedprBA6`FQaDcX$;m;G=E-xyq(ZIa>Q)>^kG5A55T(zN4b$(w_=c!nfX z$=$tq-jc(1R(U>QAVp8tbHG}^368{WZKD|}Ugxk}Lk44?Vh$@wt;0^V*~-fsZw&v; z76J*Tji};4ht}2Kzc*Ccf*ht+l!x>@e8%jicjo#0$=bGt(a>*}L!?^Ve(Cpru=)Qx z9zP(&^=ai?G$fzh8YBdp%6WxMe~EeRHs|&D_@W`?x%u1LTc&I4nTbVNBF-oL1e+R~ znj8>>T=7gpL**8S*Slpn(dj8Z9|0N~T42o0SfxXIw>odSkx{PE8pfWvr6mm&l|J0b z=pe0lt8O%P5WzhDE4OQrA52k-Iopw6b4Mt&1m~tm={$@4P*GkjD<@U!bZr8Fmo^}> zv$UjWzz1YbcE4VY=Ws$@0*CqW22Hu6qhk)RlmAz2zh!4-qtGh)3FX|Rz- z7Q@BO{f>+4a^^HW`M<;0zr`fP$9p0W2f(ruM9T7xhsJbhM6=psuW?579ruVCLT_GB zf4*%hfE!^9F=)fNHaO^iaPXk0$kB|hT|RLUiA16SK+j_n<4-taZq0^^H`9A`KVPip z+-pJ#wtLC5lR4&Ktg%1tB1vXA$Z;-|lzp}?A};s4we1LyS~D>Ala|mD+xSs`Wm60+ z;)J9m3ITE-k$Ly(Pu*2X>0*x-rE(q;yuO&1ZyGPDcCb;{gMm~^EqE|-#Mt700DV0C zq*^$Q;JL=tWxGC|`9`JXs7|F*OT1$lroDFcj$RFdW-~`Q`xLAQYaXSax5!>RaXOt5 zEvm1m_?Fg-K-AcWh}PCQ??`yHG*7ttf;#|=gR972_c*XNadIk*f6Z`n<9DbyGCwud zH92_zkUpVbJzOC`LO)=qdD?Bi zSV+snl!UyfrjbwD8qYQbzNy_AcuWKZ&+wS_%we|;L&95gcKhE8GYvEQ-`DYZfFTZt zlwXdSyWr2tD;T9ZPh13jnxu!xm-`$Hk#bn<37e|aK@@&T{q>82rVb1i4S7rk`_zss zi;JV9kfp{WAh^ET3Q%mpxV=0w++_QxaI1Iir+m=^5`i7N9iatwyCdYKu~;PS!Gwdg zNHDvZchx3Z-2<1e&N;QI(fO+4x0W(>kn(fx6#ZgV2CwvB1mZdH_qK-+x8kJPuT=F~ zf?-7MOz}5GTJT?UbEgA0){!o;EFMy@FBJXBN3pziR<%4*aXvm=g)(YRr-w~rU1#%+ zMlj&F%r!z*R8*j2BiNw7e=D0Z{~%-gO01=#aono@&<1%)HrbRem!$RM_#zId8?WlN z#RFmx)-AqR1k4vF<+Wsr+tA@@Ka-Q$aaiE{S7NBm?PBVu# zQVeP7WkKtDHL>xB9*ELHU6{9Cw{IH0IWY^oRdMM7w z#6n7l@g!TM7{UN3y}M-ht}8w+)(mb>QhB{A(mmRogm)Lj4d)~fcMT7XrDZDk`O@J3 z*(pjkiC@AwU9Qsh)*NO%FoIXO@1l|o&EuH#uFhp;Wv#BP4DC2Hk`hJT*1RI3V0zQ~ zyKV6P`fI&Lk8v2R+^_xZ7le;a)1pVq^m=r)jjIWID<$Cu;h~6r*Q2qh~g^fy2`PJt&R5Em_qCFte_1Wci|^! zTz?4Tk89qmI>`+?k<0FL@TXPmv(Dl5jnPJ3OW8CEvEIyfmHoN}?mEZa zjwG&=t=d6)Dw^zx361<|OaSu$C$wS~EyBPIL^#m;XXNKIXb1800Ul37Nk@3y3$O?) z`6Xix4)AsDFKV>lTA+M`8>^m{JAe!>%iGIgoPIa|_cOhYat`Kn5itod(q8L5mnpgl z(eCoVH2g($=CGE{=rmhJ?CL)lea1kW{pd6Do*o^w)<6cQ?(`*!R+K}JoD?qmi3R^< zm}%UjpdZh%oFdo$umcyWLt|NG=ANE+1R|q{vK+gk^2bgPgFb-|92_P|%C62b+lG*r ziQGk2--l8?5=7i?`P{ehd?dY!bjlaD`hjAXvczoB$iT#+*)cY@gk&Qwu1&0M#6YX6 zDyz*3B(l2uOcFe6s;JYDlghE?t!2A8#N*w<#B{c`*@hn&i4O&q zF&s6XM<3b;5!b2j+A8btIb6DV73wtsoZ06%aE;zo*OsyHW7s3-Ir}&&M{S`hh>izh zpCyDL84&GhY&%yQB02+a|3f#V*oNu3Iayf@*P;FCO7<}ujDgdR4sq&`F1CwlcQ+*e z?r#UDkFXUvX?dHmf(Pkw0M#F4a^J;v)zWeWG$}|Y^{5S8`2JiGth}w%ih1uxI^ZDb zGxad7dsZ>t0h(hszDGKq6dEd#sr{OCK_-FQZl#1A=c_RP_0_bIpA#_=(FoMeB!lU( zt?C{8fxMwDKOcRMgVAO$=WPP)P_PvIn=$Y)?}9`{mW1_RBZVk@vD1Pva3*nU)}9tv z7nmIaI%A6bFKM9SZ}f|cN%o+Y^8-ao7fB#SSSereljU<>c@B4+s zyN@2N0ozKBKxQiX@t$lktgH+jH27C5g#3bOz;9orJ95w)bCl;<_2;CjfFeMJ=&k#G z{DEhTI`+&9o)#8UQTgMXHnVhZ8vjET$ei^>L@1N;1?a$?hC%s!kJ@~;4h{e2>I${_ z6)Ds81x^-kl*YaG$=1Q6x@XqHP^guh+-qgJfAIC@crOkC7b5&;WL^vVrGcdCu>pIu zcYs7AlcWr=3RC1d40l1cLIjzRxVT#@nZV#Xf!i*AX%X{3Ge`bIa0oH{RBfRUmrrc; zZ27aP(Q|WfQ#X1fj5P-m@DrH!yCw3wePJa=V!zlO%cKwuQQ;@$P1ze<&hAUBmr%Bz zs|yqkrVg4lUs>y&xI!nPrgyphOD@p6GJ?FC;a82?6@UWw2As3Cx%n@ZQ;kG!w`7x5 zk8bDrR0=*fXlh{!Eo5aPH}W0GoBrdRXg?gq;~03EW#NYmlwW7hQIA>DXmrx|Q8})A zoC0Amd&&W9nSAACWnW3luv8|ZDqY1XFwprjM2--4AKl#z9cmZo-!gejpYk0qH5-A8 z@tHoaky8gBBH>W`v`)G402cMIQQvhtqrj!wh0KeV7q-`UE&R#=F?Vs+!z!jl^`oAq zQ0~?f&ih)Qm~#VFZ0eEVmRfJO$7y|9;DSutyWpX_WPKNjb+uh4QV*5fi`^qU{{^2{ zU%^fI;F+I3Oos2pN$t=Q`UEHsH9OndBFGrjhXdzsDn6zjmWzNe{M*y+B^v_9-Jx2K zrbakNF%p^J6KLvnh{hQyPbDhe>Uq5rqT>wQ;HJIqFx-q?4coX1Cu?o5(^cmYp@ZjV z=lmC^Tm6R1Px+%b^u*nauBQZQ*EMLZSxrVtsJbV@ul?Av=8g|>17Ul5t48DvhJd6^ zNy)UMIBSZ& zM|s`wen7+us28o0u_#IYEue(?7dv;XA$^-wX*D^Y#^+GM%GYvo1sE7^$(l|N_dQ#R z;klIOpE^=J?E@7{-~G7?QcwSq1&=}r0;!&8ZYlpi$pRZ;VPQidp;S1W&{8@fIx#V?Fx}Y5x=_Jk zn~HQdAn&(hYH(elgp^cYcXzg};^Ktj5)0Ma+0MZ`0#1J8+oWspIG{eOZCc$8Z( zTp|_>hY}0^mRo>8Ol)tzxZnqvgQ6k}XpcGJ?i@C=oefsFxM5xe8oC-9l=DYGj0JLr z@)AC-?_LA7Sge$bsJ5akuN#3Z4=}aGeOmo58B73u# zN5{v!ZIYYqyC|OmRfbV=Yrb)PD$hZFozZ*f;3=Tg!+SO4czqA z!b!0c@228hF7RJZf)o%CqqW!>k=;{I#m}GG|1(TPTqg1GX4|B&9w?B?_s>%o7ok-S z#aV@QJ#lBM9|lCw^H`$DUT)4bIyjFfd&`Uh7-v4S{U><~jZDG;i^qrEN$pWW)~L(p zBRZ9Jbth0qtAawrF6!*MQVpRx*WRY-GnAjxq6xXtRr>T=o)sw`sD&AivW6-uEB_1& z@|O?Yi+c={@X}38YG?qX6^vWSx)E-XxkLd^|FllX==D2#{c3;&g9$ixjE(uaR0DJe zi-h;X(D|URuW!@!#o4^&n0)fPwwW23PxRc^T2*GJh{5Gnfol%a-K(vb{x|z_v8;A8 z-&4Kg=p|%jiP;QX0r~+#vO2oDhR%Y$OxC0&ymO9~_|fAmoE){awLRD^>tJ3eK3+ZD z`$e8kcTgI1^UObw45@BSylQd9UZN&51szFN+02Yi?MI(8ruoQ`kzc6D)>fM5goH!Y zM4Vp%af^XNR$W#R%j%NocI`T1dNL(TKwuI<6TB*RKk(D>UezoZ8?p+sbk=df<)Ik5r0!)4AN!$)M zz$xikSC=k^ebTUaJ@?xV0;wEj`g+=y)+#Vu)aZI`0`?sspY_Aql`p4vW*Dhmbyz=+ zdx+-a)8hLmBXj>c=6`@uF<)Qwrx~7(oqV&SxPUL(ZCHFzu#ITLigLztW&~+f7$&ufZ5E#KIE&Xs)f4Fs{ytce{a_Ge=$R1gDsJ-)K z#{!J@a6Q==_1LPKg;pnMFEXeXlks?R^RwhCwxE-F9e;_+q~hc!`E`vEGE=hwKHAdm z+=n%!a$*w6q}xh8_W9*Sc1A|+SP_@W@f(QEa0igXaX9tt0~xX%^5R#^V^1n(orZ0f zS)_qPY`Ia8aBbG6Sv)S!!UN$_ahyK|}{Ql$GcBQJ7iNz%7T}`wcOFhNNLhftwBoh5ZI+{Tg48~8UKCPi442+y~c~g-R=R?KHuKy zuOh-5s0K^lSgf_G7uwXFYtZ-wM-C1fJ$9FjH**Y3rO}|C%()F9&bJ)sIWDDv>O6_b z5o$K?OO^p)c>XpxUFckqMMM}DxF_0Jx*pTjS*pTjyF=E_b&;NPe*LA&K*TehC&GS8A`^ES3IgaCf zBm=$#!oc`K=JxXAT{f5BGi|n$Rba05KH9x2^c^LmKa_A2;7hCm4h zd$sCMabLyaYq0ZbVQq59&ODbX8L(5X?Oj9qZ`f7@kCpuXfG99;NeTR9hKDFEC^*Ee z8me39iLarlC3FDG&@)fPKlOhA)Qg09=h~32Aoo2fNmYh$$jz-f0N(3@uEY5&ZIs%T zRFDLQe-?D(<(8KJZ0On$CvX4+03?o7-y;F*F$=I-{(I(IQQNw@COY;&wJVg#dwUM= z9dPT`?Tge8!i!ujvpNriA4vWlEb9VGJq9VqtO>-8=SnCPii4d!?zA&)MW~ucVpU5z zS`WzNhs(=fW@VL69``YX2R_UhP*|a5psEkMcZ+TdEVSFi*g3@FL;aw&-fhKTPkw&x zJ>!Lod{JW>%j(hzil0h3z{8u1IX_vXPNaoM0;2(?vZa$bU&~MbXpps3-rD(8 z-)zyjLrz}hw(c;v({!0{VQU6X93+5Ut182t@W(8VJ%|%#BM_Ox)b!?fK|6lWhCizb z39q!wHQq*sGp?TmgvvFyBpF?$xGLtne{NW1p}slU$M((pr;f)@*crAjKN04)sqJ}I zs#61V3;PzrBx%KK^s_F$=*`qEG`sc4c%@Jdp}UC-%(wCqMhOXv$~zTc@LlLlZ|O8} z2gQk3cpd^Wb5@+lQNIL?QtN72QO@EPi0qyeTX&yrv)#5<_0teVei>fYgYbv!Pst}= znxITGnOdMxS65dsA4r*+QB4pX#~8(bFWUUJ(RuC4mD&H?OV0%OQYoWbT3Ac(W3tgo zYR{klInTc6+#4?b3GrsY(39%qZU(u-`od(AxN9LaImsJFNJ&hN(DI=Yh|+b})ZAX& z>VNW>me2D8pdu6+*J!N&>mFKc$Qq}{azSO8#�%^@#dq}3j{IDaY(s{Y&2k(r-F zXmk6+n(U*35?t)t-$tKwer}`@=O(vLM0a!l4dCZlURp9uwO;{fEUh%(v@7UIraO0T z-M($mjS!ToYjTBaNY}99q!TtJ=PoRRt#`Z^Xn1qo+8&&exuhv_a6gJ!>SrEsKo>?74Eu|I+2Kghc=}tkv`}JcxSDNv>#XYYTsU z%x4OFBIdYu*m-Ghd400R?{L_~EzOBtD0K5706CRe&DmcYSCtFyUaOjE4*C0jBJSsR zOMZa!y7q)_S1+lsX!xjmc}+8Hw3pJ;mb*M5e}In{Px_1kWTkX*jyZ<8mG->BgB?FQp;O zm)$o@6xEcZU|l9%tCSTe7j%+1I;QU?SG-XA$G|=vNZRxzjj26fJ?FJG8(mVd@mvBv%G zEpDpR3aBV!5HowZuzsG$Xls`51v_qcKb6IYu(v=)nAb(%pQF|&*Cyo*a;+LCi{cPYOo5#TDBADYEKo z9Cz2aATl!*R2QTQxHuzJmhN+_IRXEwV$WdSQisKx%@m&<$s}0@=LIm?jKcn0!Kny4 zx=^llfEU3aS_b?M`v{AnFLLVtyjd(KdJ>IADn%B$pqh6xyq2zZEG+e#0}=xVLCSUh zGaB*d3G`pLME>JV=^iyDYNt`gLx(r~Dcj2wSFWXDcce}m2FnD~X+J5c)dH_|JinE& z_i{#gqNkQ-VmHo`8?4(UPr-bpYPrlKnb@D_O-W3pI$V7RUKUXvg!7LMD?{6Csf(X!>;L}=sv8=r1u3Yi zrkyUNf%kF`vl_Z8WgP+8jzb6M?nQ_w~Hk<(y|Sva)*pH(m1~X;no4 zYdW#H?Q!?skEkdWZ(iP#96;qy>Pme73?NO{j}MlqQxTmyKbCq_b#$}ABn^TEyxKhl zmL`S1>jY?(o5_?AbklcH!Lcel(tt_}Sk%@sO@0sd_7!!c+R0z#8XNgKzSGns=YQ#N zAe^J7>>eF8I9t(WJ~5e@&S_}Xbz+X}oetaxp)VHjND}u3Lm&;eaq7p@rYOGSa`JSA z6s=}A7kJ_=9-wYgpciCcQHj3(_r95_vwnsys+Q5;U&|ewkcp&Y5gE%Idb}j6+Pj~R z@5zIRaO1A?pTY5q=zhegDCx2>R%sqqc)Y%crBR3=Fg)U@(E6!DEBNUQo3L;&iB#;h zH@0V!ey38zqjcMc^w&$Nl8Q_4fcAnhY)ste$E_<9svPb&Bg_6Yy>IJEcy+r;ee)D2 z1nm(~j@fLJig^~dq^@H|L?1tzF5BaGgOS@hTzPJ)u;KF8A~GY-J8xnX zA^f-5i>U7TDIsqeNYgMR&SHsPxE-QcCCIh3(IJw2eRVS1S&1Nwz`YR|<+$UVP;T~utTB>UPi2uoRS_r$bya|5rMajd)eb0@cV9IXiw8@)-G zPX_!F&im6dEiL*2rc@YP+k(pYulo9{P|1tW>~=S4OQgIHIpfxE0<2tb?{DKbHx2s> zv$7sf7-(H@D_~<|^BR4js~dnh{>iRhNi`}W;v#=Mob2;KGD#sLJ3HI%G5?_X4mQ2C z2`HoR-6?){DCu}y(M~5ecGTbh*TY|hq#cnQgO{(a8l2P@aK7moy5IPqW2E6LDD`-z zs;n5zG*Hdy*7v22Au1}?)P_^c4PwkjcztE{$=P?sIR!EuROuiTc1IHoM(HXm(Le!m zb#t01JF4A_M;*NCXz#jl+cNPPQMRFxMcqTSQa`c?Sd}%tJhzO7ouv#89_>uvTRC6& zzO}f_B$>QBqMXsr(z5U=kt#MD&eG+vfn2wk-3(cTr=AyP_!wl%5$ ze5qG(5ek>|9s|stYfb;Mp~I6#pYro+VyBhuxD6&<|623sLRA?o3qSUKb7^^EY&-gk zR#w`#ov{>LEWpps!D-s_5p(ChQH2W&2Xn;yXuiCz93L6wmpijGJ-t(Wusb3F{_;=z z#ICSYy0b_=|DwIvmu{eN2gX4FeGTH^B5^V(cAZ(42?+Br+?uG`xWTm!*4t)LV_s;v zLL<={^GRuRe97B>!N4Y=0;2~{F`Jp$6p2)#qQC5wo%x)z9tH-!zkX<{lz($sY2!!H z4nKd-qvx6gZP5FUY%w6p6yq?RYr;|spka0{)Y7D0Qp^R^=z&9|p!LKe2!*+9RGN7R zm@m4Cc^lY|RpS6k@fmZ#)iC8bRXXBZhbIIz}sW9!+*}6gfdFWu77_UEk z8T<|t-ggcRpu!&(M=-wf@)S%DC(1vG`$ZJ_*D&~*13Suu0ou(lVbmyZ-9dNy{47h_ z&R_Z=oZkcNtxA$hekkeEML!37AZ+q! z^SwX#0{jhNf02Cl%*U8)U|e(YUG1xR=cz$Rueh~*#Z#w_Ql;&QN_TjMSqz*eWPM1; zvO~wrVyM6oAj&~YMxcA07H|@%#XU7UO-<+b30qHWH@Xl~La2SaVSoWyKyhZ>?98H~ zCl4Nk8@q@_+bLFAFbRW383*{Z5niQk<@M~j3G2&-cEZc#JRF!6|Q12)&< zxaaRW7Q(sp{i!*0V;%@O5}uc*6~+JoOf&rJg1(@ev; zgFx=ITL!;J(XKJc@W0yxHq6>Uam{86CNFl5X{*<%dAB)rnh zf_*x76I@w?FAiS@G|%OOWZG%L_xNk=>M8DNMoCjs>v8+8bjG%`NZ-hlS?~KY~mc#{c{zR z(W|QypX*)}#-DqUHQf}|IIzDy=(}BXj1<^St(o2^yJmpgAfEqlhpA7y z#A7A2HU(h!WXG}}BhH&P)iE;y2wEspKj=EQ_Gllh=b9WlSI`CX%sU%kT%wTuD zr97tZE_a)L8sK`dqyY%(1`i6%xMCb5Mi#QG+?GZ_rfe!4KNaIRa~mRT5@X=?ETpL954TMJe2AZ&r5hrk8HpV1zl!e!YpN) z2<^Wv_i7YF;YZBFIE>MX9^d2wTK*b+ zb0?jATixO#4xz?N?WCPkKF_C|?WX^QTzuGOHuyvE_ee|5t8{;5(?MrvqeHBp4Y?ER z=>FW}V0r}QK+(hMZ02A)Nv`hhYHn`M!)EPS3Ub__jQY{Ba!PIS zjprQ1SQnJRlPdZ<4u@^P}W z0qLj@NyAB6jNnJxe)9s(Ah!e#?O&K2@dSC17)6pbb z*qf(M21@4{yb{ou|bdK8=0sU!93B_e)y+wJCxFiI)Kpm@o zee*s$`fF+FE|`yYxDK>sf$A}L7g4}TTp$RuQwnM2QhtvK>Jw(mU2;)e0l5;1L0j;| z86j(XJU2I|6{#6DS!I&ZEc)P?p1gt5PV#GQcTPxJ!t!9gkSgQ2QcOl{?p5~~grP@) z*IZDL!CUk=@0*sNP1kX!2ewy%V$BovzvWqQjnVra&GeQz7ueS)H@EeweE4uR{l|m@ z3tjdJbxs=ZMymrZ11c)d$YiqcwzKq6-v#YPdjV*kJ>CxgEB)1sTv^7Nr>@=2C=;DI z*5QlCn^-8oD_XxvQFC`#vISYS_QaQSp?UY%!}2)NG>ExbLAQ6=N6wZ>10)0&)bKl-r-4XJj@0*Ot2>w2h^ZMcsAeKSzc+ z-f+#uTsw||+y)(oux~mH3@d@gKhDJ@eI(;*e6E@C3NwTw z^5np~F>fNF`qK4f#)&HJ9kCvys*1V1*tjmE+c_Q~A$t(oqM#5cw>92TOn3aC^sj8r zT3z)uFbGz;F?)`t_pdI89VdW|yQ|dZ+p2QJPu<#u{Y2nM(e<2hpxD5*RRJ~t&Wx~GF0sg+4iZ+%LjOjzm#w8lhzO>l9Q1I2L}VJ|2=w|jb;7# z+&DmmoP#6EN{fn$%iobAC>SM^5)w4?vx3@E-O0bC6 zx*mBXvAwKncD=@5Hph8x*;O=7C7!>}0p#C~u{y{SR7v_wdvy@M2=(8vsOR0joVUI} zFOoQ-prxfJnPab{&;Rj06~I!Mlf_L*`4kKyj`id6IQ32>x#_UI=V_&r z3aA+HyD;DgR*ybCVM_27ym?D0EmK(hu5`PbM0K@2-zhCPd(|~hYj5sQ3V%5G*(U8K zD7c%dlGy>0#Xpx*CpN-koOpHTO7huTcFhj3%S|K&dCdJOf zBnB~phP;=TxVN0&7k|Dp8)UXw`n&@)C;YNVd9Afb<G)ALT?XMae(V5QAXoElFBd)w7n$GN!FRLPy>2b*WN55xREf(oXd$-i8A2>qN- zSal@B>%DI74|)!qXV?*7P6=viw+eoJH^}T-Pa;-CN;t2fvAoV&$$hhe0`wp;7}?U$ zu=;_L45-+LgNmrkMsRcnWStpLO?{7<=rsu0GhSXg!S}TQrhI|==D~f7)88iViiJfV zyDiUd!S6Yn`a$3GgBX=QF1@ zG)?Blzo{~!qERAp|BKb#cD#ihGCMn)Bnl(NW$P*`S{V(CmPmO`wzf*Yb<(fF!6+yI zk-{XPd{^+{L#Odj2_SWMsfIEE{z6O5r%jz4F!BEt*Nw0q?L94T{u<@GK|8^(vNABi z{Fe#`)@l2gIRLo*tHW){MB%`>+-tWXy;*J1*b zyzW5UVp!)+6jPT6G$WwGRrFGO?d6sW!tQ^eM4=gEg*Gj8em_W6rJ%UY8f*zXb<7e& z|Hz9Dg_;4)nfWeS$3W3EnYpEd!~q3LT4E_FA=9riG_>mn6U|eqW+uI{sZxKk1^6q= zrFn!H(g^!%h0mu$Vg30P8$VExQ(%fkT=~CF|4MIe2Trez0|2;KuBYuU-w$;WSPt1gzOfNr|Qq#s}3`mkY^10YetcqvM;dpy@CRjx|0m01iXQ0EpjPnl=G* z@md0q6`W20X>g(k$UXD#7X(4|Ku`FLiyb8s@0+@VUgb;*ciG;+HK`A?O)AN=k$2n) zm-r@=r&m{7af=)otX(O3HN&>(FJFm8PYZ4B#9i!yY^Yi_a$rA;ZGfspiCF1w&YE(pe{bIOG zC92PGXp4#3NA_rWq?J#X8z$G-0K)qFi$k$Z;e+%V$TZfHHrXq1x0-^Do2~;4>40Q0 z=v|bNkwvO8GXW5L+!c-%o}Tw?Kq?h>TD{}V0C*^B7%adc%5W5U4`V(CWt#0fVDa(k4f%2%84#bif{Yz4ZSkg z$w>auz1E;dLB=rf3kfY!eXRX&v&g+y3a1IlOBuxe`K*J3RSCXvx{6(t$(6E*B> zht8d>T4m5mzRx7C$Rx4bDFJM*uDIn@JZy6_{5JohaqY<~Evai)$+PtmgYKq#aA zSViyRO<&-+eXNow%OY#ngAOt9A=;XjJPwfyy_*mpL(jOS@K#@ctyRl>X=MdvKOBeu zpP_>3x}4VC%!k!f0LNogk_z)?pBQ;5=Egx~=BbjX4N zpNumXeZ8ICO+`&j!7zaYHJMcepeb}M)aB1Es{88H{}XgDU~wkrvjg{1C_wW#YTT5y zJ7y3D+$J}9Q*%l>$X+ZC`_|R_8D1eg~;WAFB-H#2Hc2CG#vx3 z`6@WjTE>e!V>=w{%-9((Fp9P%{DMZe>&SHKTsiu`DGKV7iq(UwdID6ROtv`LknC=dw z8^ri{dtRC#&k)G&V;7S24m;j&hPp8HN@tgZZXmnb55H&Eu69#dA1L~}NPh8`n10x5 zJH9_MHs0s`Ow0f=kx^A}qSoNk^=HsaZWy<~80R`}yP7ompD3i~~Ti2Iw- z*&x-=aZiI(JisCprli!S`k#QDhUBD%m8zK>ozpH8?|fY&hmokO1%RVvagBprojLpc zKWB#%BNLQa-}^{*R(#YEc*LI&%FOkIM`*(m(g9jI-Vekm4;b+v7hacI^p?sh?MvI4 z+%`E3{)IwNcaNQ|zB9=0+n}VtbF%V5THc*&m=5_Udc0zt=Wt^2l~C>DYBiy6xz$Q@ z4 z4xj4`0nnu0-lp>b2|1$n!yz4=(i&jDTZ~lysW>;Kg96!)%I6nHZ_5*UV)sElO5c6) zmHTa7e(N;5DA12$sj?^*JRSX3=2EXnYc*YIH|07`@o1uBz@-zdQfjjF6@&n$^gu_S z^Qm3ueeMf{GfKN+M+R*riLeu;{=CHs*zxeN2` z4n`9|Iz=3;uXIz{eZPF+QZH0gG!FG5^q!u|0`q~tsbD`3yt8S*V#Jx+ZZ9l z6U}+#YaB^Q{LmE)hF$@{Ec0Cips->FEjI>jFf?9?y3?INIM_Nu0`JkJ_|n>?sg)OV zw3+MYzW}eOm-pyL;z26TMJZ{0f)Xgry}{d|X)b4RB@6zV3Q`VFj?Rwco9h;K?{l51 zPg~6IvLVI@8I%$D8gzdAj?(e>?69`Ky_nWt6gx_R1w<12p?7#9<*x|MYU`;l%Fr)T zB6TClKvvBxD(J?+s^_;!=H)9)%yX2~=`(Kig!d(q0O*K0Aq?)hZx$WMg1sfA5sVw4Jl3u`XGP)+Qpx*Cm!v2q^) zzfO$gOh<-$$?|Z1b2saMiHq^M%tEYT)N2cHBmkEvH}*EKT(?g)z+;wTX?MMoAE=Z? zV7xsG^s9<9Dl&}5b%0AOElk7bmi|3i`BIS*bJZE81QOw#pCU819BcG>OQ;gapGy`vIt!Ii`>7^h#N^%ws(emE5eUPooOo9 zK_(5EgsY$+nv9`cl@68W8s|Id(NIaG8&3lVacb)CF8J_Y@LzmS07Y_2JjR-Ih=5KSY8b5FX_ zqPjU;Dv*XXh1@K#<|AHIYa63t@;ES%GfxH_aZ+KpAxRokvhpFJ7iHzI!EV=_6QYZB zzhio{+o*bVP1gPUaZuohoGUn{s9; zk2RioZCKuo0`U7k7^2-kO^1!4p_f1*~^M;<{9Jn_v;ptLOUEF`AVLGUL4q&eC{0{P>%#Es-x0BsL)xv_$Gw@ z0n)G1t5@FevDq-m1Ucw=mjE^48Hgo7_~1g>TX<5qrpGU)a$Ub3rk(^2wk+{h1^h}J zda-hn0@-#PUt+fckT!e*BGkuP@a>NFvHBZ9Wfl6!bHlO$`?eHoCxp#ntvioTDxEq% zBc+lhLu#b0-@S8M>sta_0%Nq7ZGD#Q9kE{TcXHp`R?=>n4=7c0f9YNB4dNatzMaJ+ z<|rrfTvIX~*le37ExsdcWhvZ&s}p5sh;aJ;+~mZg(gxGgr&-MQ9z6Sq!FgW_Iyl$4 zFEQ7=8Dt<=aU00u5(Bi>&Apf%a0E2eXZNr_l>ebQYWcim&iYUzI5O@bM1G6KrzJvz z*@KSb2@FKYkB zcjco~$LGpZ*<4v7e%x|1V0Wph_BT1ZNs*Iv_Lk8$(@6x)ZozErx%#;Bz^E0pcf0|F zGj>A8yelPUl2I3+`*ZFN;XKK8u;B+kpvz#ge0kD;xDt8>wq!TV=)m7RQ8Vw!<;5GGy?2guCMKRQnZ=R zgV8_O2*nwGe0k4m1jHFT1gf+C=2VB1%cHG=b2tpOA_3R}6a#Qp_FR@b}``odTi=el*vb$NmWW-&w3 zsUGASoD&RqZW|H`s1b9YO-5#0IW?afozd&R`_1}TOMpZP%tURJnHMu#{FLihok2GB zFyvITxqwznMZiMD`8gK<*E$~SOe4V!ow2txs&wm$?7|Xy~MS0 zR$qxqHi|l8%C{oaSnLvW zA<#Bl;>|Fn7d1Rw;L&h0?ms>^v>07kZgW4^Twq}&N88S>t;x``la$YYKxy~O(NV8; z5XiVwZ#)sK-2JN)%d$#gsUjma;*ywOb^5Txe$uE9=wZcu_ETEFIFWtyK2meCy6gv* zg5TjeG*DU4ZcNp0OiHK7-MCUz);6<}6qQd(jaP2hEu3o39-jjKC+i{GN|#YS2?<}F zziwe}sd`n05yd_idGSY_;vyolZ+a01s1(_Ll)zse98YOL6;MMzNmDMBfRvWPVVq6j zF576n`S7>fOm8~A%?ivxF~xa3I6g_bU!&4dQS?}o1v8-W?b)yf(b$9Tptus`T5DZ zDE0)|F`Apc*Ob@PAq#3+XxR#>Zl7+Cyr`Y zZiJH=@zgad(Bfn=_?-8o;sGP}33p~bX5y8oo0a^+twg?E9NKoA5d%(s;vU;0U**GH zeru}fqomr)i(QqC>+VlZG)9#_S^@rPmsTPExqQOe1N)pT+DFMx%T1Hk zVgeT%_w=61xhr z?~i9MK%Tx42MSg9&cN^o&n&UMhBNH18o#8yly>S8SxC@xG8Wu8N?yX7xn)(EyV1P$ znE32vLHs^Wf<-rbph^-t*ET8y^&`i=Ase+KUJ=bae-o}L=CLWoN&?{L_SMyv} zvmg9r5$daJU_xN6^4Zcp^?|}CD>S@eyXADgNASJT)0+KgQHKsTX+$s;MIDOt|9bamh?*aFdP+n=&#Y4`Tb-lskPizQwG*C$YnnTrEPLS20*TN){ z$jHs_6pY8i2#M}47Un)0Yl%oKF^Rg+30-fC;)FV)8Hz1>A8yp_cy{v~=A|J~^g7w6 zIo6)&Ppl5q7YebJPfDbkZ8;`lZj1juhEj*h_H5`_BRaIVE4ba(M^5_M?cittW@~6wg18Mv$6)*W6sEq^YRP6}xw`Y%eQ|>(D2uaF*2icr_LeFuV5sgK6`8C$?(z54SW)*sufpA zj^bA9kdK@Y66e|4{ok8=u_t zS1~7Rq7&)EYT_iJoo^lGg<;}3IWwey<@R z{$W--96J8ZeICPf_rp*uv4n`!o30pCu13c2ec)WJF+W4&pQFt|P4pi)k{`^@)JtFK zKX-u7QhUnlLl+f2vb&uhvJ;6E;d)SPSozE27opz6iX38=F?T^CTLE`dK8(Tr_*F7k zJ2HrRy)@b!y?4Pza+ZI0-m-X32TmxzdYwJ+copY<-@Wke5h1b8sfzno5tZF=V}JL_WW`p5&p|ngcg5u=n1F@nLc$WjPiPTT6b{gncF#?~7&Acw|x%xUNf9wfF5boF1(if_k znzG6d#dw7>QE|TR3DvA~5|15>NTFa6Xb|r|dBzNLG0GuSc~$a#=c`KW&{KF=GN(XY zNE2o*w-P^%&5KR& z1JHC7b$4<&brdUmqP=EhIH}3X_sTIpJA2LANW#mH7tWYVD=M~Sa_I}@Ky|4k&zm=5 zNhir1`i4nTa17LkAy0KrPpkPQe)#39 zXS(Rm9}@Cjr+)raB8z*;w0|JJKAQ^+m8bhVLLwrfKg^STj{O$Uw;4t&jL#%+?Eb4? zLKyzOMK8-|2--gD!gpK)GjCV}vO>Ic*mj z!M0~xCE&lOw{BsEPYQ2($#Bjt2_Ovz?xHK8W7{1<}!I7C4WogrJL#)V%%-_XddP*WdD4gnBAr-m}AnL?bC5N@jttONfga+p{cnR zJn!J(Kn>=jU1+11_(D#{b`rC5#B>>S2MW2bPc-?hDI5JbbHk#$a7_-P3=y5oc*1-V zvSAB3b85isEtq_7%y)PDSY~XA34H|Wu^iuiC!HaaiVO`+Y+vYB# zWOy&@`T*O^YFpQ{!-#}jC0^@a-`y*TrREz+&|SVW2{cZ$B7L1P^XQ{xaaVTv4XGdd zW0YH`^l=U{>4w^EFHNl;R65P&86(;XgBwTiBi@H7#W}^21hmtu23^pi@QI{P3sApZ({Let$O9T$p}k5&)jT?vpZMSkm?m!oWzY z;PuV(=Cb?UPX<>fKkPNej~l|L8@}18Nu25-F~i2rna#)efTP;qzB}_g{JbWI9U>RW zsSl>c@n}_FNzasa913M`{@(YnA!&8LWtye^&Z|q_1AF0@ckRQvG5o)pnZIEZWP@Vx z4&EHh!cW%2&fSM|lra1Q-hn}t}B&AW;J`94OgJ(QGPg3tb`{w{MqL+5${m6p0o zw?HM0t@5bj{W8T^Wpjx#t3m$ww)qYths~Z;Hxxd@OiH^QQu)mMr?AJEy^LHWr^fN8 zqYcdLbP&HR*Yn08ni_1o(fqX)Q1I?ntJdwZp_A&Rhk^`fXYRMtmdr!))KgUxgU(6O z9qia!3)%Dqal}F0c2tJP`vE??A35m`va^`IEc##vw~f*9oghj1(0hX`r`~<}FSp)R zIxqMfb?UCtzCgVgNE#!oY(#TG^@`s7raT3-6`HQg<>XlBieBUHbF6RWi3_!NmB=T4fH6%b;gX{cVR|Ip| zBW@($sK{Z{GQY;OB@d1?d&@&hq}g;9rN~Xy!`e^2Oz^`-8A`mEPu=^(KvTsi&!xr% zcAY2L+J|$)sr_ahp;N-S>5Oe0o&iQ=>G7?`v|9 zN`FB~@DGW{(r(VQ^GNEJE-opK{4(XZbe*v)j|JyeCx4Zlh;^yPbP5Xw-Q= zEb*xxPg@LE`euCs6!xlQX*yBVWGGHxWvr~GQl=_?XQA8vz-qtU|Jspv|2zVNuo!qQ zz~$^|mdk7noXMx2YqBLU3BWO!-0;a^@R_6P4C!#L+Vu~+CtubV(JVHnh{sxsux3s6bb!i>xb`U%HaazGUsdxeE$2s)?6wrpF$24(KJT#5OtaC z&gNP@k(~PUxcv{V7{-Ii(Lptnvaa>OL_!VTlELUMIC9EY?{GIinh4Bex=cb_?TxXt z>pWt493Rxj;<2aAbsfG>71tWyf3!>g)Omk`J&N53juYTp=zyQh!Lu?RVRuNU=bRZ` z9Xb=Si=D$z-ZKeCB7_Imb1j>`X<3pFW$)5P+`VnfpPv}z9~&o-x3+&-!5(vx46ojd zv!bjbGz{e!E@-@YR(o#!kh0EC{1~v@sM?m35LkqmyG%c~W@U{~ALsFXlPM3l1km6`AC8eFidh z^?p;8R(7Y2o25xqWSIDVa2|6U#-jDt9EVOBW`8-}uG((2kIGgIZyOrjTQ0s679$@@ zm%qe*e{j=dJ3}CPDIWtpUGP<-6UcFIUR#@1ZL}S!V6$01_1fA);fd-zq7!Z_B<~~h z?s()dAn&O=VZ-S9(}o5?;q4A$hIZ~l1=WJJ2QH@T{QEt&!2YY2#`ir_v1D`g1F*J8HpFOKBo`v5=~!{<;m{BjoBnG9lxe#T!%dh^ zBJ$IuWdymE5?CIOLsM7Lb zDz}FV#}7<5kbJJLRf(l`%L9eECrBFYJP3c7Y|_W1Rxox}ew9M6A2v(^Ht1?G72YF~ zIn3s1iC9}!^cADJd|jla`${L{E2Mszj;mIgUGQCzdB2#`%!mc3eGS&CQ{Q{H^J8+P z{E}=4-QeKs{nZ_v3l0P+gVfu$ zB#GiUjLWE#t0YI*;49F3U>i_XN1^OGK^8%`rMwd?eTzxZ8qv`<(kAZqC179fTolyOd&*~x

`QjiYv*g&RT8Ek@ZuaA`(gaqwh^Tr-R8XH`#GO7voRsn@Z z`TlVxQpX27S0l3Bs@HS|Ykah94|)T{<>Fd1TKflFPT)MpM#w5xxX*TEe>%~=I<<_H z_|($s&#{?=%?MH|#}eCl9kE`q@}NEfR3TJs*hMw4KMr#GXceV;2v=cH{&mTvuZS-+# zrpM8Vfm6WV`ZyAYTXOTxNPNR%K2|z94Dcr7CX_2>#9SdiiS%X_h*-j?P!3#;nEyCk zE=>0u>8R+_*e5s~ZBPG7(bdfsWk;eZ5(O^g=f z;FEAAdwXlx&YqC_Kx%RPz61oJ>GAxOr{mAd@KpBqR;{EBm_6R($Tm(BWtWJ;lQx{Y z#dAxhqvH!ty=Q+`t*_=RnKY^NsalUt^Ey8WHIE#h8Zr=Y%X_AY$hJb-PUK9bH7Ze& zjX?+E@{KbYa=3+=l_1M2JffmjUDX#qU2gH!ci3~^UEE?2bGzi7>4Q_+b?0559dV5K zjLG!gCbBZ!#gLkez(Ewfur9WD*g0%mI)mmlZOe(vKd)QxT7x;F)ZA*YpwN!LM zQ-do`C_g&$@}&=ko-*(wyzw}5Kv*!X*j6qpV;MH*uuzqb}T%a%OJ}g z$%uYmt)*+;4!)1nb;ChZ=s`1|Z$R(>x2-zTuAAp*%zR9?%qqt!pCV1aEKe<2#K1^K ziek~^K+Zzf>(p1RW6ld-5{9n4L`j#jqMunCg2Jbkm0i9s%&z?_V;(~A3pM$(tLF^1 zDNyevCO3DzM=!#{(V+l~e3uE*@u(JzPK0SR8Wfj2v^Ck8?MTpyQ* zfo`Zi@|!CzKJsA_-Mn@BCXkzeH?`|@pFB-N&xW?<(fki zo;n5+srKHp8~2UAu5@ao%Gb%C`m-hk6*!aNDkAhePv`M`GYuK%c*6EcWP|xpLm0{Z z)4Pj&?vy{KD8EBaw9{j@-I(bIeRAywC?}n^e~Jp$5h88m;Qx zH}?4E#RDi9hWwvAY8g9|!IxthA!qhQ9h+o-zir5Noa#Q?4F<8d+XNL$>(MfTqou_6gYo(sT$)Lv0cZ#F0 zuqgXy)w`W&gg^4}Y(CMlQC|>iQ-2A{Q822mkHxdhyF`VXr30l9R?1pdzC*)ROe5ep zU8->Ik$~u!kx<@wuqrm@kvyzeps6`pk)3GO(%+tDQHqD+l^tUOJHYIkTQ20%(9)GC z>W|O4-LmGuL9PGG#xJgB@Bl%Vn%8A@1uK@Kxs7u_zhVeELcmX;L+G%stmq}jM2fbb z#R1ow0pMSpkYjYqDrJ7pExp&|s^;{>ep;M%d)6FH=& z5S@)L1f7>%%=8^~p+Dpq32Wa8lSJK-MTNjS?C-h3*!9^{BjpXLqC#svsha;JH6?^z zs0V9+ve*5{Z@PS~$~0A@{&3$Zn$sxN$|b(sJFn22Z&Jm)q`0ET?FsUz)!bBVfyKcbril5cYm87RG1R6)R$npAaDry(gB(C9%wu zy6|=|Pe9aod53=zvCK3mvJ)6Z~!K#2WP?_p1E= zY45G0+Iqi#&l;sjOY!1uf#Oiy2~gZMIF#a0+zLTj3T?6A?hXlVL4&rqTX85Jw73Mg zhtKDJ*UYSS*Q~iSb7%hft;HWnNS@?8=bY!+d%s_M?*Y_o?LGki$HL+k-sKHYpS~{W zdJ@#Kb-L8{_0;~A*WoHOSKw@^ju@zypcQ)Vzj!^hb&*|puC{K-Sw9+vyX(3T=kEA( zl)tImzdy0Q_8NI3QSz1J`e<6%!7(8@`4or*=jZ7&`HdkqmVmNZDoHm-9ACBfpjT$) z_1ojwhH%U93KWs|#>4BUXk>=(eq@fOGx8>zfIa~J1SrC+Up)V=u;HZPDaFa3gOQw@ zI978N4&&-Vy{RzaHHzH>Ere`}$>g}PTvBCT_!FK&fBB_Zf!o&L2#`;KS}T@XPJS6g z(>_LsMeD?IraB5{xGS7buf~~PQ!hGx0`0FXfZ`a+q<^tpS&?;B) zq2%l>Q`OSruYl!KPiids>0o$~8hP8(MFZB>-o0F~@1X|#N}2nk=kl6R8qxeTf8TAp zFji+_5}428mG~5JZTc=D8<}-rfO*<7n8?e25b7~2k*Q=f@4#RmPps%4DDLJKCfLBS z16;Ih6#X+$E_BINqemC=7?sk3M`ry^lsY@x_r%EPyx!$Pg&|F=$fgMB7Vm9Dcdf*t z(VZasv+F9|xQfBUaU{$up@#VTv-y!MqXfuabpa9Mi#Im>D0*u25dzh$m3Z8u>fL-e z3VI-{G#5yna~}8zvbH-AtonnWOLdot8Jni*Hhm)l0yFO+;6N`@m~xa6Iy)0H$Kr+S z0>ycD<8i3O)*Ak%pLGY#V9;WcNlHyzyW9>_}<3&;(A62irJ&^ z8wuf&iyV)%%%9CJEzf6cCKpjl-?Qp9$^2lx{>tDie@3&^SCE}aaQ9}iKEswGpQ_vE zw6z=btNC`2A{;dZ*;?a2;oDKQFI?01vTnIqR8AEsDex~2`cBRZvss_8n@pnm%K|Ru zYOl|>IMOlp7X~8uC3eD|dtzkMRc-?cK8EJJ)FpAK&=ZtV^mT({Ry)Qnuhz9v8II*j zmkdd+XH&7!hMj(6|04QgY^bGZ;G{y<_lup{Z3;{oPxQC6KPrFw)5f)C!4Q|MfVJbC z%hA(I2tc+O2+xUrShe22*F)(Aa$IQ7EO3wG&;e_w0-;&>#_$1X5Uyacn3}+U#7kLf z(30hx^Ub@$sb|#XhGw&Hr-ftfAd1#w%yPAVV{aA){+sq4wSeVI0QguJGxIKEK^V@y4N$A`&#D`Z@Wi*d(ydhm4RqOrRM<-`OIuA1}|F(k~HU?6Lx@!|RU(m;< zruy)ivGJO+0RV14^|ub~v6*Bc#3$M?H=o^tXTRNynJTeUv*T^j^kGqyf-c8U zC_?)86nS#sY(*lMeZI#?qhqt}&1m2DE%shkNE7*LeBi7+MQ}`%Xwe*mg)2_B-r}p? zf;vnA)owHUcMsUeyD9Id=vgRSQ7=^aT)<|pa~^|BPk9+*IX3KGHvVk@vw%zatho2V zToaACP;cVOND6^bm*catDPy0TpHs-|n*zB9xoT^@m+1`EwkP`BV`J-^i=%nPv)0`1 zVc(w8Q` zj6cswcTe>@hIW2pmaledi)X^YfG<=AE(w{ID+0^!J2K@o?Hlth)x63A4X#CI@m*FXwr&lVxpHr^!#x*$0E+Br>CU95@^aMn;aNtf% z0wi%XW?()Y*>YZLZBtIEJw|6Qt`8W5_iKKw2*@xt@fEc>bkpv2&mI42>OWJus|;L5 z8k}B`D-RFBT@RUhsy&!C^A_dgFJmu@qiqAD5>lP&CRQh^OaH5}Vf>uedItM|P--%D zanmIsq^p0Q7T#YX?EG3~cVOLaLTui$RI8$i*%a8IgTv>Acg{eP8SO92f>Wv1Dm-gKUUPq)T+e+ayp~Yzl{Hb5c1`hk1ys$}OEQHxer+P{mRxpQ4J z%3ImXh6R`+Xs}k97%IY9KluUi1d-_a@j{5wn!3aEdk>G;cCDJAB0|f~ZcdqXrVU3= z#S~Lo872yoCUd=8N563_OAoZMv&9jhzu-|{Hs<5KcsqR4`|xa0)VBYVg{;s~O;5`+ zGKYvbmz+=|hFWqx+{Jxms)LLJq?7bUxyrg(7j*Y`J!GTwH%S67cV({W*9PQcq@&+3 z?1s~_iBHzo&SMv(*;S}l^`@7ghSDNpzv(s#|BK3v)j;#*ug1%GmjcJfXmd*<1hAil zYEZ+aeaCYO@(umxYrdG^HqbRAUTcc<;?u@>B^an%zzp-URS1kCJX-godKR6G;ANQT zOqbQ~8IQNZo*F`3h!ivTNrk87%zvVr6PLX=o$wA4Ic{=1$`7{kP74{? z7mY2G>{+T!eUcIZM39kyd6GNHBFRKpJH~Ww&PS(J`7_vn@1#RDPlVRLAm79U#K<2D|%LZj+jv?4O;Sg;PvK zI6e0t$(CM#Y@7hn2d`Z<1(@UbH}+b&Zwq=gZfcP%{YEir$isiGJGwMtuElia7ej_u zo6i+`F@wu-biT=Aw!^3~h4AY1R>j};9Cx;OqFO!&kc5sv{=S7nq@w-7c%ZqpaQ<7@ z6*eTqtlDbl@yu%ODvkfmM5-QSYpbB4*4jav{C`6x)ZCLZG55b|d~codg&@(W*&(sp z%8QcpN#EbRix+2hNX(oIJFT+?-wi6NVw0tdGYSsR?VBcSk%8hry`=)k%flm>I^6Wi zy<@7@2yW@#$jPM%D2-#c@S&Ui8btc1naia1R%FiOtKu-||haYpfWdeb?#jaW6|vzj{lwyef4Ym^fO%?h@$@H{eSgpvv2m z3L?8RT9hgHc`{b^UoOQW3}~{iQ_zQsL%Y!VE6>}G?P`VQmh%j+7KQ)t3y(JL_=OF1 zgr_y!4{zdpU`NixYkzm@sVWEZF#l4we`-KA?vHO`^x4qk1!I3xf~+Z`j@nPKb`{j`iGHV=~}2JiKvJhl5!Uc{49()y77P zYsahaArV`IVPP3EdGvhEXxo(`XD%`O{iy0cLD|PvsqQdSk(ph+qh-se{<7vQk4k`T zki8*#R6|ZJ>LIe@C}AE`hIsWK^rA7_c1px$RX2$%?{KZ}@<*}oo_FDNUbyk)MwKl^ zsTwlX_qMbd#@zHSq0F*dv*3?*$fKv9hMB4U1u-Q0{(2m5R&>Zh!Hgz+2V(QNx#lO5 zv8;OS=w@i^77*@+6}&#?{Py?n-$u_a5*G0IO-(jHPyl2{uF{sqbQ8sZfa~`w4mw_5 zchw!Fi-jTtWXnbH9gn6S-Al0}OJy0eQZa0kQ~J<#d@>_8uuC42pW0U9)c1I32inWZ zs{};ui~fo+4yhMZ*j8jEG(AvXdn|+vKp}&JM=I456_7JHC6i%cWRxg#w43+pV2p5| z>PUIg*|dzyn2H(-XzGa_`CzC6a2!Jz+<(a=+GGHuv&dGqmJ}W?#rLGVyIQ!)?COp( z+Zd#DRMinUTWK}f7)o|qUR`Y^Lwvdkt1c8#-|~sc4m;*YBGm7r9mi7o`{f1s#D#QX z&jx^!TA>Tq6F9d=c-K!;1uZ|Di~T0*76ghDPH5b0FD)x3lqB*wYvrQ??nUa^1{yV6 z8jZaP2bUNh>6M9{&Cg!^-0+PsHLP;Do~y@MxLqQwG8wrSsXdJwdGi3zMxc-H(l6oY z3TS=v*nN}s3I;CKtyRkP41Z`9PF@S~8$n109Rh^LYoP}RRxE0nt+6)Tm_E0zfB#6+ z0M^jnR?9K3{Y-Ji${TmcP8LI>#b3nMy;S`FJ*H7`D@1pPTBP#+p8^>xE46?B6ASns z!x{7m&VbA8;WHX*1Eom|6V@&l2NWN`=eamscTT)DH*5>QkSt)Jqmz-AUh9cTp_2=^ z`(rPpJEalOYS0RHjpmV$d?asZE#KL>YP+~+`EVo3mEw@bTF{oXY<-6vbtb`e--HW8Tt%#$LC1_-?K~gD^$q?jHPqMz1799ew=I zmsdfl|2bp-cYvCB*VA_uT~MkF9*g7^S%wuAV%A8Io41eT2V|2Mux4r2IDXXUt>OtW7qzZN~cUfCqY1}Pr%7pKZ9tTZuMGC#gOai=@H_k z0xA567$PPl6cXip^{UtTCNR*jo|2D_a|D5|uIBk?D6HtZ@@O@36=_`I$h-4D_=$jX zr04M<#|Eo7vwHTqsOLOTegbGH1a13&FvtGk_qMvDatc&_%5rT0I`&y8*La|<6YX33EwVwHoUWFmj0ngX%>kfdUYE(1{ZvetHJPq3+wcV49G+g$ z_;N4FK0J>RBq`>T23nS}bDIGEZ-LXYB;;(*pxmj#d3n0heLK|)C%mPS70`iQ)gL-yL5%(LgGVL~{Psx#MDcv7+!r9HH&K#@~pY*O}*tu%oBv%L!jvaQ(J2hGsHgj#lf%UNWbKiEi4Q+R_GUdZb@t2PTBU{V+@C=iW^JfKKq$Y|l;N>j z2>Ko6A`Ns{q2TAb>8(_Q1~O|E4!f6>f(?cOq!q)C#>uADyL()`Kj%Vcf)wNDAya9< zJ-8lg)OeK1Sz)))8a}fI=KeolrxjY6A z(U0I@Wb?a5xo9WAE*1HW)LrFP=y>}9s zg{DkAl>q~f*ZCqu8*;YGqEUBHxd!LS(}u&DV>zq_%LXxhZJ#Y@I=ieqE$NrG;0qQ9 zuK8c8$r`n8Me%IyQuqabR%FAefyx@`zrrba9CR1wbY^RJ)r|A)#2goz01dNg9mdkX zRcX;zE3Ft`({Ks{K)Kzy8o0*K5JXM$)>7L$00=?ujJ^S4>SFkwhan^hCO+yV<-)cT zC|}C&0A6R=Pjotx<c3 z6EggQX7~WyMvVhdx1P+K}cG)&u&a#jViPDc;^Is3aGAE z0EmDCL1;1Cj|#RS#?^IAdcR?{lTsAgh(T!_5{`*dhso-SW@6N|ZlmRO7OiXu36tT* zpHOzYNjj%nKof#&49;IFgp+HR)uVa=N(hsk?;uxMNhwv-sx97rRwX@*#R!%gZ{}FT z{tJt+p!3%r91Ji~m3ctB0k44xokW_TW_B)%o>5}@5K_2)O{M7C-XJ1{!_C+xr(h_V zkR~IN!^F75U;i1|X(Q_XnAKpg2-a@tD81sN^t`7igA1jL!!^`Yv-wQ_^o)@Zp+jA1 zoS>-xjgKw4F2ZyLd5!62Ny3=eVlef++LefFSGci*);Y_WRrl#pbSe+8$It>03}B#_ z=E*nuavi4U`r&MkO)opJ)TEK8Ki~p~l%bPh(_633Iv9Hls8Y|@(v)OCKuxA7Dfy?8 zm}RPD*6B}Y50{0)wm!RYQ{qLGLI=>H3NRHfxY^-6JXOOA#4MYd7B|eiJE@xU)&NX1 z8JaB}VlB8XwblwynYQEQHw`BgU$G4rt)VvD{0?)5*`NM4xO3>YIJ;ie^3Pt}9z^A6 zGaCA8E7k-|8qpqzZUlZdMT1FqRxyHD4woI5$z(TM2E7@g-_>fP$IEW`JNy8Pq4> zn>d7=U3pBE&I2eaPrJIG_wlB>HqUolih4TVxxwf)me?yE2dx&DHEh>)cJ$tNlbs7Z zDzR+h7YFm=L7crNwT_EXv9ZNyNy3(ky#k+$BOB`G^0T;EFeB#eO@T=qW|53BfYuHe z)K0T3Zo_Y`PWM~Tm5SOAjT`wsy`Kf53uiPUpHAY~MEMkwin&-ZD83N7dt1{Vk#@J3 zbqy|DWA02hB4omC0V5r~dQ_%0z`GHwDtBx@fA+9u!j@54MIOw{eX>A)^PDScnwukLN=JvAF0V?{$D1FI2!+IQ2_FU3S7TxmC%b+o> znDXxr_MqWLNT0aoNDX?$Le{Ahm-As$+SHXU-|ttA8IOrs^tI>_wUR%>YPhP_NtpDd zq%EUfOFzcDny3DlUv)W_Zn9+$5P&Enm%qK*cJ7lH?A)8V+9%QzRK!UG$$ScOa+_nf zjleu4yWa2|AnK1uwadWnEBOO0&!`>1QejU@LjecZcaj4@2`cybQ}`U+QzbT<9=zoi zA|OsJ`140wo{P(@CweUlQ|o7WrGz#)(R(|SY2L@P6)VW%9P{8mmpa?eiQYc+C+G^8 zc+1h_h2t*I+&57}<{`-Z6m+wLGqJQi(JUnxt?({L7XXB38;o@9S{#u&R>(h(xMkfH z+iA^`xZE!RYXM&KXH=2GPTd2a&upEt>W@K#QW0R>Ff~@ye%MFKYvxD15Y%^$3Q1Y; zZPBK-^UDR}?iN10!eck8Z8ui+g^9p!5uiYly51MsU)0@VBNH>{jD6o%3G<22GwsgA5y$nDT!wZ^f=9IkYAqK!3IVO_LH@kB;a= z-kK=@8X;+HDF10v@u?QVp9X!3GCH&=6FVK%vQZ0-dT`y!ZltW$2R~G1D*&o)e+lPw zkO!i??{3A8##egx-R_^ED>DR*Sn@-6ONE7vXU3<#7$YU?@mnImE8mSHF3k*q3ME1S z&^KkHYd`+ToOBd+a$**s1rBs}X-*u1=GC+2m_cvW@|e&2-{_E^%^UzvvJ&Kr!wCXyIe@LDdI3-k!o&tKm8(Z@YT>(^}L>Tl17v zJ=bAD+Pp8gbvX=b!=mi722L0C1a$6?V^fZExm56`I?DmuZ)IzaWkS;fO2bN?w@BQ1DcfP} zaH!U+Ns|)tiGfWu*9-7+Vt^ZtTLxRG^0yn2B8HCow6jO3?H=Wm0N6s zJ4}2wO)OG?pGTJQd|d`@KkJDKxmjdr?nl^iYbYvsJfK_q(mP74)Xr(f=`-y|bppxF z&xJu+{H_};7c4ACm~#faU|N4MUIC@Uc($(DJU6eVpzCS%!ckb)t%I81+9f42ALf%MZN+d4NmdIvfW zpCZj$6n=lcKf~+PCXjGH8bv}nQJM$MxoVu7*oON7nq9q1DOktE#!>?)8a`&#k33Dr zY6RV>7@m7O6| z3e(dwVA_|>^Ckc#v}QLq$Jj2hHRF^Geck)EOPdww2f9aAcG@1k>GCe{oh?n)=)ah+ zZ9lO3qYC<4*f64nL&@#%q0wL_u|y4UBp_=)H?;Omnl0yn0Ol?q^;ql{H*t2N=g24S zjp-UYL^f?nNkI5O3c|zMAHM8wn9_XfzHXhtU`feuBG`fie0DY9Z?wf4!diJ8v$1najntW6tmXR80)P3Ih2qNxZI2_{vu>OlaXJc_}DT{OK-f=l!{iyOq*9@R7 zoxO3hGseW9fPA@Cnu8T*BlCFQ3QP-D6zipBYXr>8ZO`1D#%4e}Ys5y-{I^`kVq&w$ zu6K!@L4rz4xtk=a%wNb}9?QHC_#Z z0$&R|@M)x5IFH?Eo%E67E|XWKjt@)W6WdW2MPRMx^cj+^ul<?gAB$s#M#>jvSFzPK>Xqsf1OQ9@<0%X#aD z=vB@3Kd0%~VAloK;Y!FCzyLn(*Nhl2sgv?$J-zM?CE?J1Gy2+0)p>V@cftUcocHHb z4PH{clCC9R@(ZpiGXhkbTEQ2um}66a!WzMO%DHU2N*D1AWbA=S1MJP?1$X)i#yDAGXxvX%Sx-C5`uZsBvr<>eEI6?m>vG#^wxl=OaxmR)>WY{Femt6C`y2K$ zSy*}OY$w8(liZ>C+m)L<$Av49VfUU7}>zZiTF@&$7;tF)t_+c;=|t#Om4zCN)o~_rLECkSAc$bu9a$KFDsZ{ z4Q`MbFAAF=;%-Oy8(F3JpBG{V*-OlON{sJV)jor1m-!hjQmF~K*NAy~Gz}CF@Bihm z*P}3ojUT(aR>P@iQlEQ|0xqyp8e(^L{^PmqhaJ$Ta#)M~=tl-{$a*N?6T~qt3wxNB zg>p**^{MRRqVN{{BaE`tNzql7O)B>P~^$+M=4Lo*!PgGazFUVPVe{<|NP+#d+ zFO#mwmiE}2v41u>Q_p?g_3#%oB{4O623?td+IpBR9m>q1Eoyv1->mIyxquD%6%uGIRTm{gD`=n^0E7JcS82XNFtJlderEhx&XH#%0&y3DqP>5;a+ z47lDtXxZN{A$l0hQYY%OTIico&%75J&#F1e0Xf?r+Sn#Vki+u_5=)+ub$wA1ie*Lx z_=OdEl#tublo@Qi{yFNMB^`IT;rx_ha;zUn519d?+?VFKx4P!ET>LflD%%GDWHsFq zv-wG;zP{RqmdZJ;dWIM_02fgsRh#sPot3xK_?`J)qi@P{N7$rhJD%MjOTcwGJ1=F_ zQJD`-d+AoJ4cj~kt`lg6u6_@;98AtR8PA@y|E*gUzyEp-X;=yUJ{H!}GG zQ<1TDuGYR0TI}5s@C-aG4|iasq8%tUJH9I9{8Clq$9))4F{2Kome?)MQuVk;DZ`eN zRB7r_AtZpzI#=#ob>l`}*aHwZh#CI|k8v_TAUzMlp^QHcgqSCq1)Tv#g?&JL1}!Z; zfeR>4g)3qJnUwZ%-8%jbiwW_@(VpUosr4@gU;F~lk$&4R#(__LzZ3(ZtAWewz@9O; zX7~`uO~7+E87V{Kn@iT85r_mxwmcRvbE9Tkfrx8cHa(pC8FQZ)f^LqBWTd|#HkOQe zaTu)iH=;#@KG*r{WhgOQiEf^wa)zKR>8GC|Yt5P<%iUBd44d`s)kq1-FDPRTS-tE- z_8Kf^Jlsnlw6Di)IUq=Wurhvvc0V35W3Xn?inIwOH}~n?OCr#R77}Yf#4RdLe*w8X zHCD+yw$FDrnsbQ!HbvCE3etRrLC=2y9FT^xyg>=wgQ>0(${zisQtgS1!+s#rR&;;- zpcq|PueJ^HXkR5}(Sh$6?_ODShEoe;ZzNG(Chl9XfSC~3z9O-ud3V^p$cKyGi3Fn= zsT0MAz*`Qr&l~V{d%@=EGKFI*mf3-6m@bUo8OI}DW$CR4)PMZpevd6^)@3gn4j=F;lOYXG z%Q$D%H8eFg`qLbZN0TMS2J-*1(&7JR$~wg}0=gyfRoliX(4$owv57}<%$p}%9PA)R ziOz)m!p;UJu6bP69hzFdNJQA$4C}hUltONwh8;Wlr$XEfOzcE)w2hv(L{OS}Ocr?* zDpZl(qZIih*X(6G^H(=K(}CzLlfX$yiaas4i@wDhy3Aj zwWSjiI<`Z&G=ef$hB|A>$KRjZ;(-9aQ~x}{w}lstpn_v`I)QAo7vT4}tR@fb&h?8* zobk`*e7nlN`U=DJ<9biFCxee74md?Pnz>(dGW9eCeO$_Xb=paq;h(S7-9hkr%Sik5 z47~m~HQWfNVtGZt1wv*kUetABC^?I|%nqUJODt^9Rq- zp-AS?xGTWl}PMNqC!z2q>4Wg@A;HEM+ygZk8m*SBInF z``TCGurQCV=H*5_zc3V(1HG~}98GISKp0a!Tl2+K_T4pE^_Ll+G%blD*}9z9_3V^e zp(y6VbF3mc#;^aM@Ps@qUFVVv{$yt@y_sNL3KC~fx4 zXO&x{S1LWw;8%8l@pbu3$gra7bS3lgbiZInX~|)=dQKOIUIQBN=${C;oYwbRTeRra zVe($Z#>jR_eSelTxC1>bM1Lxv)`vhKU$Chnd$~JYZ8ndGGQVpG>k&u7v zfJxeE{+j|oG%Qp!yk*y|`;7!mr<{5{V{PYZ%n@M*B`J&ISa?&nWCkz9(IA+~1|0=C z#WhIOM3*YGB#1VF23Qi|_lbKGAeX_i4}~cQwFs;fvL0acXCNge6Csv^x#r|4%>}|6>H@|DVz#|Mji^tBbe%*9`yH z4FA7Z3h00J)fC-xkBNE7LM!%P*i7l08hwnqqT3sir+15~j#Z@+N47h0Oq=;TxShU@}A<|6h#dsai^^frG z=L>LnJrW*Cy8fp|6MCXPNMwY}@)i5tQ>Ryd7h!Hf&;EEu-hHk$y6?)2`oUevrzP}r z;qUmLmAORjeGL-QyU*U+&|h7~eYbP>u=Nj4B;~$=OJh=SoBQ1hHw1I9$s-OJvZ?6; z{yAEI8~n$-BW)%wA$gQ0cjJja+n^de&sd8zeGMYQ0bW>YiY}oEara4ocaA|od3T82 z73~D>#voS3#8iAL8qt+>LJnHDe_tze+TX8Z$#S z?;HPF#=RTh2D|+chsyQ45&ZuBQ>LhYF9n9Vhub1zJlP$;1gWVsMn*V+&ae0Gt-i2~ zjIK%f#`7-mJC6YS$X;PcPaF#`@5J3dKU2P>rw3|KC0xwl8gN~`4YJ! zksRa5n08HJU`UL})H!6AbH?X0d)P|S|&lk3EKBq-piZ@ zZktnFO;4wS%@uh+OqS_6uO8h0XVwNoI=(;qsEg2OlUwR6pO-CFg&l!@vcG%Kmb1g< zawS3M+5onjg6_^D9OM)g|D6HVnE2#c`@V1UjkN{2f@qJZ0pV(_WRo$MX&Q(~F#D$F zmHm<%_m|w*@f=xIN~79xmpF21#aLV;(A{x&LwRU-H?zJ9BOFyid()zm$$1*sdav;p zsQW~&OHSGzl8YZps3}Ng`ZLsJv~?#N5qVJ4IkSigO1h* zXku7?y)?dC3nFc7n0lD7unJVt1^nLME_4Q-Z@vhU0e`|j#;tGt>%PTNJpG_+>H^ev zFj)?XJO=&bb(oi;b{xn%H-4cW619U+kb|dKu0lgql|tqTscIN_rK2@8$-M9E#Fwtw zIXPw@T((kS5#F##EH=b7XNPcnf+LxX7JV$Q9Tgk1HV;T6-OJ(fLbB>R^hR962@egQAUeRED zV^<;Mb~}IMwqGdwM%z?fAq0dD_Mnj3sB2${uzC{LS8vDIEZbc))s3w(Clpm&CUx{IhkJ^S;0@$*2q^;9y!!y)v=L&I7V=@=P%HQb2CnPQQTI#%a>-Mj(KEVJy9uQ@2Ut;UYAkdUdPGtBWF=1kt% z-XqY|tB+x^$iOkq=w+hS-=@*cL8sU+RI;L?s4Xy*v1W{Exi<}gBNHEt8i>Cx$5-F% zeDaQ#*36A)jgmIaIMdZUEvFQ|aw;Va!v``*|${LJQ$ zJG{PR*^$YgMJ=C3e(M&Fn!_9v1f2}B$s7*FlDK(lTI*>1e#>NiB>9!TgUOgH)jQ-# zI54QwvJ;dBw=1*#q>(x+YMG46>zGPVM$A+=fNR#*ypNceOPu{9gGOxM7`dbw9qp1O z-TsRn{Sn6P5f5V{d6~qwJ>73J2cPJwT-FA5D$3M3{h+uT_CSYJy(|iU?Qs4rPQQz_ z`3rnm*)2|0>(rH|-^aIP>GQG@@*CJQJJn$k+D@C#LR>!Szl$BSmy;3SB;b?b;u66g za@tnldeA|)ay)|LdmMm&5Y_yLte~JQ7ym{o*qj9Tj+YFfy-InLY>6&7A-Dx~-A-7N z4>qt-L&0x_u$8AOa+utdB^x6GkoceQqFos@oIKT9an<+mGPzsgOl{N$@oxAY2n9U& zK1-$o9LW1bb4TUm4%D;>mQlb8^hsiu=?5bGyFFx37XO&J9#b+)lZ%GjB9(e=Zi(NA2?=nkC+mzlWRU$6^g=P>d&XR^#w_cUEn1##+t z0+oP4`X~SemVv7{{?v=PQ7#B{-@nhxW<@;f{0mbBULSl4kUIePNiY-IGKD zn=qntVn{`nX|(8{!R{BqWKb#vnP2bL4!7mM7?{@eS(*dQup1&^=A=jg< z|3)~pX>TyQ@t+e#l|;oxEYzZ?qtUwUG|wC5MoIQ64TLW(d*8dTxNop4X4K{RD!H165P_%se@fXp@qRbt_i0K>=b*k2E~fx(?5unjPuU5hX>avA=4 zO=}3!SnWWCJ&~F8Iu^rl_|f&@DszsjtB8{h5zb>;QiA@68kcN~y^B^5J1#0?MY&Y|rv6=XL%!lgB= z0VQ1XZfw{!&V>=x5!k2zcd;aJudVW%hJU^ffzs|t0;5)Cbg}7j89pm87+;j zF| Date: Fri, 17 Jul 2026 17:14:52 +0800 Subject: [PATCH 159/323] feat(agent-loop): give each send its own turn --- docs/architecture.md | 10 +- docs/core-data-structures/core.md | 11 +- docs/core-data-structures/session.md | 12 +- docs/defensive-patterns.md | 2 +- docs/persistence-catalog.md | 4 +- docs/rfc/INDEX.md | 2 +- .../feature/2026-06-30-interception-seams.md | 6 +- .../2026-07-17-one-send-one-turn.i18n.yaml | 4 +- .../2026-07-17-one-send-one-turn.md | 38 +++++ .../2026-07-17-one-send-one-turn.zh.md | 38 +++++ .../2026-07-17-one-send-one-turn.md | 36 ----- .../2026-07-17-one-send-one-turn.zh.md | 36 ----- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/inbox.ts | 12 +- packages/core/agent-loop/src/loop.ts | 60 +++----- packages/core/agent-loop/tests/cancel.spec.ts | 9 +- .../tests/contract-regressions.spec.ts | 40 ++++-- .../agent-loop/tests/coverage-edges.spec.ts | 16 ++- packages/core/agent-loop/tests/inbox.spec.ts | 10 +- .../agent-loop/tests/interception.spec.ts | 38 ++--- packages/core/agent-loop/tests/loop.spec.ts | 130 +++++++++++++++++- .../core/agent-loop/tests/properties.spec.ts | 41 ++++-- packages/core/agent/README.md | 2 +- packages/core/agent/src/types.ts | 8 +- packages/core/session/src/types.ts | 10 +- packages/ui/acp/src/index.ts | 4 +- 26 files changed, 372 insertions(+), 209 deletions(-) rename docs/rfc/{proposed => implemented}/simplification/2026-07-17-one-send-one-turn.i18n.yaml (65%) create mode 100644 docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md create mode 100644 docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md diff --git a/docs/architecture.md b/docs/architecture.md index 848980a45a..b0449be8ce 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -55,7 +55,7 @@ Waterfall events behave like around-middleware: a listener delegates by calling The shipped loop drains work, assembles requests, streams model answers, executes tools, applies continuation policy, and checkpoints state. Every pause is a service call or event available to plugins. -A **session** is one agent's append-only event log. A **turn** drains one queued batch and runs until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. +A **session** is one agent's append-only event log. An ordinary **turn** claims one queued message; an injection turn claims none. A turn ends when the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus its tool executions. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points. ### Turn Flow @@ -64,13 +64,13 @@ prepare private session + agent.ctx -> await unpublished setup -> enter session + agent -> session/created -> agent/created -> enable driving -> agent/session-start(source) -> start driver forever: - wait for queued messages + wait for a queued message emit agent/status(running) TURN: 'turn/start' - each queued message -> agent/prompt-submit + claimed message -> agent/prompt-submit allowed prompt -> 'user/message' plus injected context - every prompt blocked -> 'turn/end'(rejected) + blocked prompt -> 'prompt/blocked' -> 'turn/end'(rejected) STEP loop: drain steering assemble system prompt and tool schemas @@ -95,7 +95,7 @@ forever: checkpoint persistence and notify idle/running status ``` -The loop renders one prompt assembly per step. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn instead of shipping a hole. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). +Each successful `send()` adds one FIFO item. Queued items run as consecutive ordinary turns under one running interval, each after the prior turn's durability checkpoint. Each step has one prompt assembly. Plugins contribute ordered sections, tool schemas, and `{{name}}` variables; unresolved references fail the turn. `dsh-system-prompt` owns the harness identity and default deployment persona; an agent-scoped persona may shadow the default. The loop supplies `model` and `cwd`. See the [prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md). Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 340212d37a..8a78dbc79c 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -262,8 +262,9 @@ interface Agent { readonly ctx: Context /** - * Queue a user message. Starts a turn when idle; otherwise waits for the next - * turn. Content and the resolved source are accepted as one detached, + * Queue one user-message FIFO item. Unless cleared before turn start, the + * item becomes the sole ordinary message in its turn and waits for every + * preceding turn's durability checkpoint. Content and the resolved source are accepted as one detached, * deeply-frozen lossless-JSON record before notification or enqueue, so * caller or `agent/queued` listener in-place mutation cannot change later * log/model input. Throws synchronously when either value is not losslessly @@ -308,8 +309,8 @@ interface Agent { * - drops a turn that is about to start (a `cancel()` landing in the * pre-step window — after a `send()` queued but before the loop flips to * `running`, or after `running` is emitted but before the first step) so - * that queued prompt does not run and cannot be batched into the cancelled - * turn. + * that queued prompt does not run; later accepted items remain independent + * queued turns. * * After `cancel()`, `whenIdle()` resolves on the post-cancel quiescent state. * `cancel()` on an idle agent with nothing queued or running is a safe no-op @@ -364,7 +365,7 @@ interface HookContext { } ``` -`agent/prompt-submit` returns a `PromptDecision` (allow a drained queued message — optionally rewriting its `content` or attaching `additionalContext` — or block it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`): +`agent/prompt-submit` returns a `PromptDecision` (allow the turn's claimed queued message — optionally rewriting its `content` or attaching `additionalContext` — or record `prompt/blocked` and end that zero-step turn as `rejected`): ```ts type-equiv type PromptDecision = diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index d8292c49b3..18d511a0a0 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -19,9 +19,8 @@ interface SessionEventMap { /** * A queued prompt an `agent/prompt-submit` listener VETOED — the durable * record of a blocked prompt and why. Appended in place of the `user/message` - * the prompt would have become, so the block survives replay even in a MIXED - * batch where another queued prompt is allowed (there the turn does not end - * `rejected`, so the boundary reason alone would not preserve it). `content` + * the prompt would have become; that one-message turn runs zero steps and + * ends `rejected`. `content` * is the original prompt the listener rejected; `reason` is the veto text * ({@link PromptDecision} `block.reason`). NOT a {@link SurfaceEventType}: a * blocked prompt produces no LLM message and never reaches `deriveMessages()`. @@ -268,9 +267,8 @@ interface TurnEndReasonMap { disposed: { kind: 'disposed' } 'max-tokens': { kind: 'max-tokens' } /** - * The turn's entire prompt batch was BLOCKED before any step ran — every - * drained queued message was vetoed by an `agent/prompt-submit` listener (a - * hook). The turn still opened (so the boundary stays balanced and the block + * The turn's claimed prompt was BLOCKED before any step ran by an + * `agent/prompt-submit` listener (a hook). The turn still opened (so the boundary stays balanced and the block * is a durable in-turn fact), but ran zero steps. `reason` carries the block * message from the vetoing decision. Distinct from `aborted` (a user-driven * cancel) and `error` (a failure): the prompt was rejected by policy, not @@ -291,7 +289,7 @@ interface TurnEndReasonMap { } ``` -`max-tokens` mirrors the model-call `FinishReason` of the same name: any `max-tokens` step in a turn makes the whole turn end `max-tokens` rather than `completed` (the cut-short fact wins over a later continuation), so a consumer can tell a clean stop from a truncated one — but only over `completed`: the `disposed`/`aborted`/`error` outcomes take precedence. `rejected` is a zero-step turn whose whole prompt batch an `agent/prompt-submit` hook blocked (the ACP bridge maps it to `cancelled`). `interrupted` is the one reason no loop emits — it is synthesized by crash recovery (see [persistence.md](persistence.md)). Both maps are merge-extensible. +`max-tokens` mirrors the model-call `FinishReason` of the same name: any `max-tokens` step in a turn makes the whole turn end `max-tokens` rather than `completed` (the cut-short fact wins over a later continuation), so a consumer can tell a clean stop from a truncated one — but only over `completed`: the `disposed`/`aborted`/`error` outcomes take precedence. `rejected` is a zero-step turn whose claimed prompt an `agent/prompt-submit` hook blocked (the ACP bridge maps it to `cancelled`). `interrupted` is the one reason no loop emits — it is synthesized by crash recovery (see [persistence.md](persistence.md)). Both maps are merge-extensible. ## The turn-enclosure invariant diff --git a/docs/defensive-patterns.md b/docs/defensive-patterns.md index cf30072094..fe74a9d19f 100644 --- a/docs/defensive-patterns.md +++ b/docs/defensive-patterns.md @@ -12,7 +12,7 @@ When an interface documents two valid ways to signal something — an adapter ma ## Async state is not synchronous state -`agent.send()` does not flip status before returning; a background task's completion races turn boundaries; `reader.close()` fires for both EOF and disposal. Never gate control flow on a status you only just requested — drive lifecycle off the events/promises that actually fire (`agent/status`, `task.done`), and observe the transition (saw `running` THEN `idle`) rather than counting actions you assume map 1:1 to turns (the loop batches queued messages). The guard cuts both ways: if the awaited transition can never occur (EOF with no work submitted → never `running`), the wait hangs — handle the "nothing to wait for" branch explicitly. +`agent.send()` does not flip status before returning; a background task's completion races turn boundaries; `reader.close()` fires for both EOF and disposal. Never gate control flow on a status you only just requested — drive lifecycle off the events/promises that actually fire (`agent/status`, `task.done`), and observe the transition (saw `running` THEN `idle`) instead of treating status as a per-send result: several queued sends run as consecutive turns under one `running` interval, while cancellation or disposal can discard unstarted items. The guard cuts both ways: if the awaited transition can never occur (EOF with no work submitted → never `running`), the wait hangs — handle the "nothing to wait for" branch explicitly. ## Dispose must reach quiescence, not just request it diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index a27b19b9a7..64a0625f36 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -169,7 +169,7 @@ Source: [`packages/ui/permission/src/index.ts:33`](../packages/ui/permission/src #### `prompt/blocked` — log-only -Durable record of a prompt veto and its reason. It is log-only: the blocked prompt never enters the model-visible surface, including in a mixed batch. +Durable record of a prompt veto and its reason. It is log-only: the blocked prompt never enters the model-visible surface, and its turn runs zero steps. ```ts persistence-catalog 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } @@ -305,7 +305,7 @@ Source: [`packages/core/session/src/types.ts:223`](../packages/core/session/src/ #### `turn/start` — log-only -Opens turn `turn`. `trigger` records what started it — a drained message batch or an idle-time injection. The turn is the durability/replay boundary: every event sits between a `turn/start` and its matching `turn/end` (the turn-enclosure invariant). +Opens turn `turn`. `trigger` records what started it — one claimed queued message or an idle-time injection. The turn is the durability/replay boundary: every event sits between a `turn/start` and its matching `turn/end` (the turn-enclosure invariant). ```ts persistence-catalog 'turn/start': { turn: number; trigger: TurnTrigger } diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index c0992414af..b382cbc945 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -22,7 +22,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Simplify session-log representation](proposed/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 | -| [Give each ordinary send its own turn](proposed/simplification/2026-07-17-one-send-one-turn.md) | 2026-07-17 | ### Architecture @@ -108,6 +107,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Trim unreachable ACP bridge surface — the branding knobs and the kind-sniffing fallback](implemented/simplification/2026-07-04-trim-acp-bridge-unreachable-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | +| [Give each ordinary send its own turn](implemented/simplification/2026-07-17-one-send-one-turn.md) | 2026-07-17 | ### Architecture diff --git a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md index ea371ad55a..669e577625 100644 --- a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md +++ b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md @@ -14,7 +14,7 @@ The canonical surface separates transformable policy, around-dispatch control, a **Agent events** (`dsh-agent`): - `agent/session-start(agent, source)` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`. -- `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired per drained queued message inside the open turn, before the `user/message` append. `allow` (optionally rewriting the prompt `content` or attaching `additionalContext`) or `block` (dropping the prompt; the loop appends a durable `prompt/blocked` in its place — see the dispatch note below). +- `agent/prompt-submit(agent, content, source, next) → PromptDecision` — waterfall, fired for the turn's single claimed queued message before the `user/message` append. `allow` optionally rewrites the prompt `content` or attaches `additionalContext`; `block` appends a durable `prompt/blocked` and rejects that zero-step turn. **`agent/turn-continuation`** receives and returns a `ContinuationDecision`. A `{action:'continue', reason?}` may carry model-facing context recorded as next-step steering in the same turn — the typed twin of the `/goal` step-end-steer pattern. @@ -30,11 +30,11 @@ Every call follows `tools/pre-execute` → guards → `tools/execute` → dispat Core dispatch and the tool body sit inside normalization boundaries, so tool, listener, malformed-result, non-JSON result, and identity-shape failures resolve as JSON-safe `isError` results rather than escaping the turn. A post-execute listener can therefore inspect a thrown tool, and a final observer sees exactly what the caller receives and the session log can persist. -**`TurnEndReason.rejected`** (`dsh-session`): a turn whose entire prompt batch was blocked by `prompt-submit`. +**`TurnEndReason.rejected`** (`dsh-session`): a zero-step turn whose claimed prompt was blocked by `prompt-submit`. ### Three load-bearing loop decisions -1. **Open the turn before prompt policy.** A fully blocked batch becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. Every veto also records `prompt/blocked` with the original prompt and reason, so mixed batches retain blocked inputs. Allowed `additionalContext` is injected into the open turn. +1. **Open the turn before prompt policy.** A blocked prompt becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. The veto records `prompt/blocked` with the original prompt and reason, while allowed `additionalContext` is injected into the open turn. Each ordinary send owns an independent turn under the [one-send-one-turn simplification](../simplification/2026-07-17-one-send-one-turn.md). 2. **Post-tool `additionalContext` is buffered and appended AFTER all `tool/result`s.** `content`/`feedback` shape the result `execute()` returns, but `additionalContext` is a SEPARATE `context/message`, and a single step can carry multiple tool calls. Appending context right after each result would interleave `result(c1) → context → result(c2)` and break tool-call/result adjacency. So `execute()` surfaces `additionalContext` on its `ToolExecutionResult`, and the loop buffers every per-call context for the step and appends them as `context/message`(s) only after every `tool/result` is appended. diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml similarity index 65% rename from docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml rename to docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml index 36bd0699c4..bcb9485da5 100644 --- a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.i18n.yaml +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-17-one-send-one-turn.md: 21ab23a9ab0e7ea11fcaf44252b6e5d8e49c224b -2026-07-17-one-send-one-turn.zh.md: 07e268fcfa8651977c204baf46b499c62c27626a +2026-07-17-one-send-one-turn.md: 34331a04b53f9ccf67db0baf201dec23e1c2a60f +2026-07-17-one-send-one-turn.zh.md: e6c4b97e826393ebca81d715ae3760c6068f84d0 diff --git a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md new file mode 100644 index 0000000000..34331a04b5 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md @@ -0,0 +1,38 @@ +# RFC: Give each ordinary send its own turn + +Status: implemented + +English | [中文](2026-07-17-one-send-one-turn.zh.md) + +## Problem + +An ordinary `Agent.send()` payload is one complete caller message. Opportunistically draining every waiting payload into one turn would make adjacent calls share a boundary according to driver timing: calls from one synchronous stack, neighboring microtasks, event listeners, and model callbacks could be grouped differently even though callers used the same API. + +A turn owns prompt admission, `turn/start`, `turn/end`, and the durability checkpoint. Combining messages would let a later message join an earlier message's model request instead of observing the earlier turn's committed result, while mixed allowed and blocked prompts would require lifecycle states no caller explicitly requested. + +`steer()` already expresses joining the active turn, while `inject()` records model-facing context without acting as an ordinary message. Implicit batching would make `send()` overlap both explicit operations instead of preserving a single meaning. + +## Decision + +Each successful `send()` synchronously validates agent state, snapshots and freezes content, appends one independent FIFO item, and publishes `agent/queued`. The loop dequeues at most one ordinary item for each turn start. If two items are both claimed, the second turn starts only after the first turn ends and its durability checkpoint settles; broad cancellation, disposal, or a pre-start failure can discard an unstarted item without creating an empty turn. + +Prompt admission decides one message. An allowed prompt becomes that turn's `user/message`; a blocked prompt appends one durable `prompt/blocked` and ends that one-message turn as `rejected`. There are no mixed-batch or all-blocked-batch branches. + +Running `steer()` appends to the active turn's steering FIFO. Idle `steer()` delegates to `send()` and therefore creates an independent ordinary turn. `inject()` retains its turn-enclosure and flush behavior. `cancel()`, `status`, and `whenIdle()` remain whole-agent operations rather than per-message controls. + +## Alternatives considered + +**Keep opportunistic batching for throughput.** Combining queued prompts can reduce model calls when producers outpace the driver, but it makes turn boundaries depend on scheduling and prevents a later message from reliably observing the preceding turn's durable result. Explicit lifecycle semantics are worth the additional model calls; any future batching feature needs an explicit caller-visible contract justified by measurements. + +## Verification + +- Unit and property coverage pins same-stack, neighboring-microtask, differently sourced, and reentrant sends as one FIFO-ordered message per turn. +- A deferred first-turn flush proves the next queued turn cannot start before the checkpoint settles and that its request sees the preceding assistant result; a rejected flush still settles before the next turn starts. +- Prompt veto and listener failure, broad cancellation, disposal, and pre-commit `turn/start` failure preserve balanced recorded turns and do not merge or strand surviving queued work. +- Running and idle `steer()`, `inject()`, whole-agent status, and `whenIdle()` retain their existing coverage. + +## Consequences + +Ordinary turn boundaries are deterministic, and a claimed FIFO successor observes the preceding turn's committed session result. Several queued items can still run under one global `running` interval, and broad cancellation can discard the entire unstarted tail, so status and quiescence remain agent-wide observations rather than per-message results. + +Workloads that relied on coincidental batching make more model requests, incur more checkpoints, and may take longer to drain; FIFO queues may grow under sustained producers. Throughput optimization can return only through an explicit measured contract. diff --git a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md new file mode 100644 index 0000000000..e6c4b97e82 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md @@ -0,0 +1,38 @@ +# RFC: 让每次普通 send 独占一个轮次 + +Status: implemented + +[English](2026-07-17-one-send-one-turn.md) | 中文 + +## 问题 + +每个普通 `Agent.send()` payload 都是一条完整的调用方消息。如果机会式地把所有等待 payload 放入同一个轮次，相邻调用是否共享边界就会取决于 driver 时机：即使调用方使用相同 API，来自同一个同步调用栈、相邻微任务、事件 listener 和模型 callback 的调用也可能产生不同分组。 + +轮次拥有提示词准入、`turn/start`、`turn/end` 和持久性检查点。合并消息会让后一条消息加入前一条消息的模型请求，而不能观察前一轮次已经提交的结果；获准与被阻止提示词的混合还会引入调用方从未显式请求的生命周期状态。 + +`steer()` 已经用于表达加入当前轮次，`inject()` 则记录面向模型的上下文而不充当普通消息。隐式批处理会让 `send()` 与这两种显式操作产生语义重叠，无法保持单一含义。 + +## 决策 + +每次成功的 `send()` 都会同步校验 agent（智能体）状态、创建并冻结内容快照、追加一个独立 FIFO item，然后发布 `agent/queued`。agent loop 在每次轮次开始时最多取出一个普通 item。如果两个 item 都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点完成后开始；广义取消、dispose（资源释放）或启动前失败可以丢弃尚未启动的 item，而不创建空轮次。 + +提示词准入只处理一条消息。获准提示词成为该轮次的 `user/message`；被阻止提示词追加一条持久的 `prompt/blocked`，并让这个单消息轮次以 `rejected` 结束。实现中没有 mixed-batch 或 all-blocked-batch 分支。 + +运行中的 `steer()` 会追加到当前轮次的 steering FIFO。空闲时的 `steer()` 委托给 `send()`，因此创建一个独立的普通轮次。`inject()` 保持现有的轮次封闭与 flush 行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个 agent 的操作，不变成逐消息控制。 + +## 曾考虑的替代方案 + +**为吞吐量保留机会式批处理。** 当 producer 速度快于 driver 时，合并排队的提示词可以减少模型调用，但会让轮次边界取决于调度，并使后一条消息无法可靠观察前一轮次的持久化结果。额外模型调用的代价低于显式生命周期语义的价值；未来的任何批处理功能都必须提供调用方可见的显式契约，并由测量结果证明其必要性。 + +## 验证 + +- 单元与性质覆盖固定了同一调用栈、相邻微任务、不同来源和重入 send 的行为：每个轮次只有一条消息，并按 FIFO 排序。 +- 延迟第一个轮次的 flush 可以证明下一个排队轮次不能在检查点完成前开始，且其请求能看到前一个 assistant result；被拒绝的 flush 也会在下一个轮次开始前完成。 +- 提示词否决与 listener failure、广义取消、dispose 和提交前 `turn/start` failure 都会保持已记录轮次边界平衡，不会合并消息或让仍应处理的排队工作滞留。 +- 运行中与空闲时的 `steer()`、`inject()`、面向整个 agent 的 status 和 `whenIdle()` 保持原有覆盖。 + +## 后果 + +普通轮次边界是确定的，被认领的 FIFO 后继项可以观察前一轮次已经提交的会话结果。多个排队 item 仍可在同一个全局 `running` 区间内执行，广义取消也可以丢弃整个未启动队尾，因此 status 和静止状态仍是面向整个 agent 的观察，而不是逐消息结果。 + +依赖偶然批处理的工作负载会产生更多模型请求和检查点，队列清空时间也可能延长；持续 producer 还可能让 FIFO 队列增长。只有建立显式且经过测量的契约后，才能重新引入吞吐量优化。 diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md deleted file mode 100644 index 21ab23a9ab..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.md +++ /dev/null @@ -1,36 +0,0 @@ -# RFC: Give each ordinary send its own turn - -Status: proposed - -English | [中文](2026-07-17-one-send-one-turn.zh.md) - -## Problem - -`Agent.send()` snapshots one ordinary message and appends it to a FIFO, but the agent loop drains every waiting ordinary message into one turn. Whether adjacent sends share a turn depends on when the driver happens to dequeue: calls from one synchronous stack, neighboring microtasks, event listeners, and model callbacks can observe different grouping even though callers used the same API. - -A shared turn also shares prompt admission, `turn/start`, `turn/end`, and the durability checkpoint. A later message can therefore join an earlier message's model request instead of observing the earlier turn's committed result. The batching branches for mixed allowed and blocked prompts add lifecycle states that no caller explicitly requests. - -`steer()` already expresses joining the active turn, while `inject()` records model-facing context without acting as an ordinary message. Implicit batching makes `send()` overlap both explicit operations instead of preserving a single meaning. - -## Proposal - -The inbox will dequeue at most one ordinary message for each turn start. A successful `send()` will remain synchronous: it validates agent state, snapshots and freezes content, appends one FIFO item, and publishes `agent/queued`. If two items are both claimed, the second turn will start only after the first turn ends and its durability checkpoint completes; an item discarded before turn start will not create an empty turn. - -Prompt admission will decide one message. An allowed prompt will become that turn's `user/message`; a blocked prompt will append one durable `prompt/blocked` and end that one-message turn as `rejected`. The mixed-batch and all-blocked-batch branches will disappear. - -Running `steer()` will continue to append to the active turn's steering FIFO. Idle `steer()` will continue to delegate to `send()` and therefore create an independent ordinary turn. `inject()` will retain its turn-enclosure and flush behavior. `cancel()`, `status`, and `whenIdle()` will remain whole-agent operations rather than per-message controls. - -## Alternatives considered - -**Keep opportunistic batching for throughput.** Combining queued prompts can reduce model calls when producers outpace the driver, but it makes turn boundaries depend on scheduling and prevents a later message from reliably observing the preceding turn's durable result. Explicit lifecycle semantics are worth the additional model calls; a future measured batching feature would need an explicit caller-visible contract. - -## Acceptance criteria - -- Two adjacent successful sends remain distinct FIFO items and, when both are claimed, produce two turns separated by the first turn's durability checkpoint. -- Dequeue timing and reentrant sends from queued listeners, session listeners, and model callbacks do not change the one-message turn boundary. -- Prompt veto appends one durable `prompt/blocked` for its `rejected` turn; cancellation, disposal, and `turn/start` failure cannot merge messages or leave the agent permanently `running`. -- Running and idle `steer()`, `inject()`, whole-agent status, and `whenIdle()` retain their documented meanings. - -## Risks - -Workloads that intentionally relied on coincidental batching will make more model requests and may take longer to drain. FIFO queues may also grow under sustained producers. The proposal accepts those costs because the public `send()` boundary becomes deterministic; throughput optimization can return only with an explicit measured contract. diff --git a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md b/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md deleted file mode 100644 index 07e268fcfa..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-17-one-send-one-turn.zh.md +++ /dev/null @@ -1,36 +0,0 @@ -# RFC: 让每次普通 send 独占一个轮次 - -Status: proposed - -[English](2026-07-17-one-send-one-turn.md) | 中文 - -## 问题 - -`Agent.send()` 会为一条普通消息创建快照，并将其追加到 FIFO，但 agent loop（智能体循环）会把所有等待中的普通消息一起取出并放入同一个轮次。相邻 send 是否共享轮次取决于 driver 何时恰好出队：即使调用方使用相同 API，来自同一个同步调用栈、相邻微任务、事件 listener 和模型 callback 的调用也可能产生不同分组。 - -共享轮次也会共享提示词准入、`turn/start`、`turn/end` 和持久性检查点。因此，后一条消息可能加入前一条消息的模型请求，而不能观察前一轮次已经提交的结果。获准与被阻止提示词混合批次的分支引入了调用方从未显式请求的生命周期状态。 - -`steer()` 已经用于表达加入当前轮次，`inject()` 则记录面向模型的上下文而不充当普通消息。隐式批处理让 `send()` 与这两种显式操作产生语义重叠，无法保持单一含义。 - -## 提案 - -Inbox 在每次轮次开始时最多取出一条普通消息。成功的 `send()` 仍为同步调用：它会校验 agent 状态、创建并冻结内容快照、追加一个 FIFO item，然后发布 `agent/queued`。如果两个 item 都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点完成后开始；在轮次开始前被丢弃的 item 不会创建空轮次。 - -提示词准入将只处理一条消息。获准提示词会成为该轮次的 `user/message`；被阻止提示词会追加一条持久的 `prompt/blocked`，并让这个单消息轮次以 `rejected` 结束。mixed-batch 和 all-blocked-batch 分支将被删除。 - -运行中的 `steer()` 仍会追加到当前轮次的 steering FIFO。空闲时的 `steer()` 仍会委托给 `send()`，因此会创建一个独立的普通轮次。`inject()` 保持现有的轮次封闭与 flush 行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个 agent 的操作，不变成逐消息控制。 - -## 曾考虑的替代方案 - -**为吞吐量保留机会式批处理。** 当 producer 速度快于 driver 时，合并排队的提示词可以减少模型调用，但会让轮次边界取决于调度，并使后一条消息无法可靠观察前一轮次的持久化结果。额外模型调用的代价低于显式生命周期语义的价值；未来若根据测量结果重新引入批处理，必须提供调用方可见的显式契约。 - -## 验收标准 - -- 相邻两次成功 send 始终是两个独立 FIFO item；如果两者都被认领，则形成两个轮次，并由第一个轮次的持久性检查点隔开。 -- 出队时机，以及 queued listener、会话 listener 和模型 callback 中的重入 send，都不能改变一条消息对应一个轮次的边界。 -- 提示词否决会为对应的 `rejected` 轮次追加一条持久的 `prompt/blocked`；取消、dispose（资源释放）和 `turn/start` 失败不能合并消息，也不能让 agent 永久停留在 `running` 状态。 -- 运行中与空闲时的 `steer()`、`inject()`、面向整个 agent 的 status 和 `whenIdle()` 保持文档中的含义。 - -## 风险 - -依赖偶然批处理的工作负载会产生更多模型请求，队列清空时间也可能延长。持续 producer 还可能让 FIFO 队列增长。本提案接受这些成本，因为公共 `send()` 边界会变得确定；只有建立显式且经过测量的契约后，才能重新引入吞吐量优化。 diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index a07aa5fa70..88efc953a7 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -44,7 +44,7 @@ Configured agents start automatically. `cwd` applies only to fresh sessions; `re - `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy. -`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. `ReactLoopAgent.send()` and running `steer()` materialize content plus resolved source once as detached, deeply frozen lossless JSON, then share that accepted record between `agent/queued` and the inbox; malformed data throws before either boundary. +`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. Each `ReactLoopAgent.send()` materializes content plus resolved source once as a detached, deeply frozen lossless-JSON FIFO item, shares that accepted record between `agent/queued` and the inbox, and gives the item its own ordinary turn after preceding checkpoints; malformed data throws before either boundary. Running `steer()` uses the same acceptance boundary but joins the active turn. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent-loop/src/inbox.ts b/packages/core/agent-loop/src/inbox.ts index abb588b919..b26a79a1ef 100644 --- a/packages/core/agent-loop/src/inbox.ts +++ b/packages/core/agent-loop/src/inbox.ts @@ -15,7 +15,7 @@ export interface InboxMessage { } /** - * Per-agent inbox: a queued FIFO (drained at turn start) and a steering FIFO + * Per-agent inbox: a queued FIFO (dequeued once per turn start) and a steering FIFO * (drained between steps of a running turn). Purely an in-memory mechanism of * the loop — the public surface is `Agent.send()` / `Agent.steer()`. */ @@ -54,11 +54,11 @@ export class Inbox { } /** - * Drain all queued messages (turn start). - * @returns the drained messages in arrival order; the queued FIFO is left empty. + * Remove the oldest queued message for one turn start. + * @returns the oldest message, or `undefined` when the queued FIFO is empty. */ - drainQueued(): InboxMessage[] { - return this.queuedMessages.splice(0) + dequeueQueued(): InboxMessage | undefined { + return this.queuedMessages.shift() } /** @@ -72,7 +72,7 @@ export class Inbox { /** * Discard all pending messages (queued + steering) without delivering them — * used by `cancel()`, which drops un-started work rather than draining it into - * a turn. Unlike `drainQueued`/`drainSteering`, the messages are thrown away. + * a turn. Unlike `dequeueQueued`/`drainSteering`, the messages are thrown away. */ clear(): void { this.queuedMessages.length = 0 diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 15cc0aa410..ebe528c5e0 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -88,7 +88,7 @@ export interface LoopHandle { } /** - * Drive queued batches as durable turns until disposal. Plugin failures end the + * Drive queued messages as independent durable turns until disposal. Plugin failures end the * current turn without terminating the driver. * @param ctx - the plugin context the loop reaches events (agent/…, session/flush) and services (systemPrompt, llm, tools) through. * @param agent - the agent this invocation drives for its whole lifetime (its inbox, session, and options). @@ -159,12 +159,11 @@ async function runTurn( ): Promise { const { session } = agent - // Drain before opening the turn, but append only after `turn/start`. - const queued = handle.inbox.drainQueued() - const first = queued[0] + // Claim one queued message before opening its turn, but append it only after `turn/start`. + const message = handle.inbox.dequeueQueued() /* v8 ignore next 3 -- invariant guard: runLoop only calls runTurn when hasQueued */ - if (!first) throw new Error('runTurn invariant violated: no queued message at turn start') - const trigger: TurnTrigger = { kind: 'message', source: first.source } + if (!message) throw new Error('runTurn invariant violated: no queued message at turn start') + const trigger: TurnTrigger = { kind: 'message', source: message.source } let reason: TurnEndReason = { kind: 'completed' } let step = 0 @@ -202,51 +201,32 @@ async function runTurn( // matter what throws below; the catch + closeTurn guarantee it. A pre-commit // veto leaves no turn/start in the log and therefore owes no turn/end. session.append('turn/start', { turn, trigger }) - // Each drained queued message runs the `agent/prompt-submit` waterfall before - // it becomes a `user/message` — a hook can rewrite the prompt or block it. + // The claimed message runs the `agent/prompt-submit` waterfall before it + // becomes a `user/message` — a hook can rewrite the prompt or block it. // Recorded INSIDE the turn (after turn/start) so every event is turn-enclosed; // turn/end is now owed, so a throwing prompt-submit listener (the waterfall // throws) is caught below and the turn still closes. - let anyAllowed = false - // Seeded with a floor (only observable if the batch were empty, which - // runTurn never allows — it is called with ≥1 queued message); each `block` - // decision carries a required `reason` and overwrites it, so a fully-blocked - // batch always reports the last vetoing reason. - let lastBlockReason = 'prompt blocked by hook' - for (const message of queued) { - const decision = await events.waterfall( - 'agent/prompt-submit', message.content, message.source, - () => Promise.resolve({ kind: 'allow' }), - ) - if (decision.kind === 'block') { - lastBlockReason = decision.reason - // Record the veto durably: `PromptDecision.reason` is the durable record - // of why a prompt was blocked, but a fully-blocked batch's `rejected` - // turn/end only preserves the LAST reason, and a MIXED batch (this prompt - // blocked, another allowed) does not end `rejected` at all — so without - // this append a blocked prompt would vanish from the log whenever any - // sibling prompt is allowed. `prompt/blocked` sits in the open turn in - // place of the `user/message` this prompt would have become. - session.append('prompt/blocked', { content: message.content, source: message.source, reason: decision.reason }) - continue - } - anyAllowed = true + const promptDecision = await events.waterfall( + 'agent/prompt-submit', message.content, message.source, + () => Promise.resolve({ kind: 'allow' }), + ) + if (promptDecision.kind === 'block') { + session.append('prompt/blocked', { content: message.content, source: message.source, reason: promptDecision.reason }) + reason = { kind: 'rejected', reason: promptDecision.reason } + } else { // `allow.content` REPLACES the prompt bytes (a rewrite); absent keeps them. - const content = decision.content ?? message.content + const content = promptDecision.content ?? message.content session.append('user/message', { content, source: message.source }, { surfaceOp: 'append' }) // `allow.additionalContext` is a SEPARATE context/message the next request // also sees. The turn is open, so inject() appends it into THIS turn. - if (decision.additionalContext) { - agent.inject(decision.additionalContext.content, { source: decision.additionalContext.source }) + if (promptDecision.additionalContext) { + agent.inject(promptDecision.additionalContext.content, { source: promptDecision.additionalContext.source }) } } while (true) { - // A fully blocked batch closes its zero-step turn as rejected. - if (!anyAllowed) { - reason = { kind: 'rejected', reason: lastBlockReason } - break - } + // A blocked prompt closes its zero-step turn as rejected. + if (promptDecision.kind === 'block') break step += 1 // Steering from the previous round's continuation listeners joins before diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index cad830e827..5ed15f1b0b 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -75,7 +75,8 @@ describe('Agent.cancel()', () => { // send() queues synchronously (status still idle, loop microtask not yet // resumed). Cancel in that pre-step window: the queued turn must not run. - send(agent, 'drop me') + send(agent, 'drop me first') + send(agent, 'drop me second') agent.cancel('pre-step') // Give the loop a chance to wake and process the cancel. @@ -106,7 +107,7 @@ describe('Agent.cancel()', () => { expect(agent.status).toBe('idle') }) - it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => { + it('cancel() mid-step aborts the active turn and drops every queued tail item', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -117,10 +118,14 @@ describe('Agent.cancel()', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) expect(agent.status).toBe('running') + send(agent, 'queued tail') agent.cancel('mid-step') await waitForIdle(ctx, agent) expect(reasons).toEqual([{ kind: 'aborted', reason: 'mid-step' }]) + expect(userTexts(agent)).toEqual(['go']) + expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1) + expect(adapter.requests).toHaveLength(1) }) it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => { diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index ee50261e9d..33e0b7de9c 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -276,15 +276,20 @@ describe('plugin exceptions are contained', () => { expect(agent.status).toBe('idle') }) - it('a rejecting session/flush listener is reported but does not kill the agent', async () => { + it('a rejecting first-turn flush settles before the queued tail starts', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - let rejectedOnce = false - ctx.on('session/flush', async () => { - if (!rejectedOnce) { - rejectedOnce = true + const firstFlush = Promise.withResolvers() + const releaseFirstFlush = Promise.withResolvers() + let flushes = 0 + ctx.on('session/flush', async (session) => { + if (session !== agent.session) return + flushes += 1 + if (flushes === 1) { + firstFlush.resolve(undefined) + await releaseFirstFlush.promise throw new Error('disk full') } }) @@ -292,18 +297,25 @@ describe('plugin exceptions are contained', () => { const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) + const idle = waitForIdle(ctx, agent) send(agent, 'first') - await waitForIdle(ctx, agent) - expect(errors.map(e => e.message)).toEqual(['disk full']) - send(agent, 'second') - await waitForIdle(ctx, agent) + + await firstFlush.promise + expect(adapter.requests).toHaveLength(1) + expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1) + + releaseFirstFlush.resolve(undefined) + await idle + + expect(errors.map(e => e.message)).toEqual(['disk full']) expect(adapter.requests).toHaveLength(2) + expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2) }) }) describe('disposed status is part of the agent/status contract', () => { - it('disposing the fiber emits agent/status(disposed) and ends the turn with reason disposed', async () => { + it('disposing the fiber ends the active turn and never starts its queued tail', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) @@ -319,11 +331,19 @@ describe('disposed status is part of the agent/status contract', () => { send(agent, 'go') await new Promise(r => setTimeout(r, 30)) + send(agent, 'queued tail') await fiber.dispose() await agent.done expect(statuses).toEqual(['running', 'disposed']) expect(reasons).toEqual([{ kind: 'disposed' }]) + expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1) + const messages = agent.session.events + .filter(event => event.type === 'user/message') + .flatMap(event => event.data.content) + .flatMap(block => block.type === 'text' ? [block.text] : []) + expect(messages).toEqual(['go']) + expect(adapter.requests).toHaveLength(1) }) it('a throwing agent/status listener cannot break disposal or leak the registry entry', async () => { diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 5deee8e159..c85c5ef949 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -141,12 +141,22 @@ describe('toError normalization', () => { const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - send(agent, 'go') + send(agent, 'fails before turn start') + send(agent, 'survives as the next item') await waitForIdle(ctx, agent) expect(errors).toHaveLength(1) expect(errors[0]).toMatchObject({ message: 'naked string error', code: 'UNKNOWN' }) - expect(adapter.requests).toEqual([]) - expect(agent.session.events.some(event => event.type === 'turn/start' || event.type === 'turn/end')).toBe(false) + expect(adapter.requests).toHaveLength(1) + const starts = agent.session.events.filter(event => event.type === 'turn/start') + const ends = agent.session.events.filter(event => event.type === 'turn/end') + const messages = agent.session.events.filter(event => event.type === 'user/message') + expect(starts).toHaveLength(1) + expect(starts[0]?.type === 'turn/start' && starts[0].data.turn).toBe(1) + expect(ends).toHaveLength(1) + expect(messages).toHaveLength(1) + expect(messages[0]?.type === 'user/message' && messages[0].data.content).toEqual([ + { type: 'text', text: 'survives as the next item' }, + ]) }) it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => { diff --git a/packages/core/agent-loop/tests/inbox.spec.ts b/packages/core/agent-loop/tests/inbox.spec.ts index 4bea62abe2..f4eea9fdd0 100644 --- a/packages/core/agent-loop/tests/inbox.spec.ts +++ b/packages/core/agent-loop/tests/inbox.spec.ts @@ -8,17 +8,17 @@ function resolverPair() { } describe('Inbox', () => { - it('enqueues and drains queued messages in FIFO order', () => { + it('dequeues one queued message at a time in FIFO order', () => { const inbox = new Inbox() inbox.enqueue({ content: [{ type: 'text', text: 'first' }], source: { kind: 'user' } }) inbox.enqueue({ content: [{ type: 'text', text: 'second' }], source: { kind: 'user' } }) expect(inbox.hasQueued).toBe(true) - const drained = inbox.drainQueued() - expect(drained).toHaveLength(2) - expect(drained[0]!.content[0]).toMatchObject({ text: 'first' }) - expect(drained[1]!.content[0]).toMatchObject({ text: 'second' }) + expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'first' }) + expect(inbox.hasQueued).toBe(true) + expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'second' }) expect(inbox.hasQueued).toBe(false) + expect(inbox.dequeueQueued()).toBeUndefined() }) it('pushes and drains steering messages separately from queued', () => { diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 4b37210993..ad0ea7d199 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -182,9 +182,7 @@ describe('agent/prompt-submit', () => { expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'rejected', reason: 'blocked by policy' }) }) - it('a mixed batch records a prompt/blocked for the vetoed prompt while the allowed one runs', async () => { - // Blocking one prompt in a mixed batch must persist its reason even though - // the allowed prompt keeps the turn from ending rejected. + it('adjacent blocked and allowed prompts keep independent turn outcomes', async () => { const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -197,13 +195,13 @@ describe('agent/prompt-submit', () => { const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) - // both sends land before the loop drains → one batched turn + // Both sends land before the driver wakes, but each remains its own turn. send(agent, 'secret') send(agent, 'safe') await waitForIdle(ctx, agent) const log = events(agent) - // the allowed prompt became a user/message and drove exactly one model call + // The allowed prompt became a user/message and drove exactly one model call. const userMsgs = log.filter(e => e.type === 'user/message') expect(userMsgs).toHaveLength(1) expect(userMsgs[0]?.type === 'user/message' && userMsgs[0].data.content).toEqual([{ type: 'text', text: 'safe' }]) @@ -215,12 +213,14 @@ describe('agent/prompt-submit', () => { content: [{ type: 'text', text: 'secret' }], reason: 'policy: no secrets', }) - // the turn did NOT reject — a sibling was allowed — so the boundary reason - // alone would not have preserved the block - expect(reasons.some(r => r.kind === 'rejected')).toBe(false) + expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2) + expect(reasons).toEqual([ + { kind: 'rejected', reason: 'policy: no secrets' }, + { kind: 'completed' }, + ]) }) - it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => { + it('a throwing prompt-submit listener ends its turn balanced while an adjacent message survives', async () => { const adapter = new MockAdapter([textResponse('after')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -233,18 +233,18 @@ describe('agent/prompt-submit', () => { const errors: Error[] = [] ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error)) + const idle = waitForIdle(ctx, agent) send(agent, 'first') - await waitForIdle(ctx, agent) - expect(errors.map(e => e.message)).toEqual(['prompt hook broke']) - // turn balanced - const log = events(agent) - expect(log.filter(e => e.type === 'turn/start')).toHaveLength(1) - expect(log.filter(e => e.type === 'turn/end')).toHaveLength(1) - - // loop survives: a second prompt runs normally send(agent, 'second') - await waitForIdle(ctx, agent) - expect(adapter.requests.length).toBeGreaterThanOrEqual(1) + await idle + expect(errors.map(e => e.message)).toEqual(['prompt hook broke']) + // The failed prompt owns one balanced error turn; the adjacent prompt owns + // the following normal turn without an intermediate idle transition. + const log = events(agent) + expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2) + expect(log.filter(e => e.type === 'turn/end')).toHaveLength(2) + expect(adapter.requests).toHaveLength(1) + expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('second') }) }) diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index fb686928b1..368ce0c6f1 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -827,7 +827,104 @@ describe('agent loop', () => { expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('completed') }) - it('chains queued messages into consecutive turns', async () => { + it('keeps same-tick sends in separate turns and checkpoints before the next starts', async () => { + const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + const firstFlush = Promise.withResolvers() + const releaseFirstFlush = Promise.withResolvers() + let flushes = 0 + ctx.on('session/flush', async (session) => { + if (session !== agent.session) return + flushes += 1 + if (flushes === 1) { + firstFlush.resolve(undefined) + await releaseFirstFlush.promise + } + }) + + const turns: number[] = [] + ctx.on('session/event', (session, event) => { + if (session === agent.session && event.type === 'turn/start') turns.push(event.data.turn) + }) + + const idle = waitForIdle(ctx, agent) + send(agent, 'first message') + send(agent, 'second message') + + await firstFlush.promise + expect(turns).toEqual([1]) + expect(adapter.requests).toHaveLength(1) + + releaseFirstFlush.resolve(undefined) + await idle + + expect(turns).toEqual([1, 2]) + expect(flushes).toBe(2) + expect(adapter.requests).toHaveLength(2) + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer') + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message') + }) + + it('keeps a reentrant agent/queued send as the next independent turn', async () => { + const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + let nested = false + ctx.on('agent/queued', (subject) => { + if (subject !== agent || nested) return + nested = true + send(agent, 'queued listener message') + }) + + const idle = waitForIdle(ctx, agent) + send(agent, 'outer message') + await idle + + const turns = agent.session.events.filter(event => event.type === 'turn/start') + const messages = agent.session.events + .filter(event => event.type === 'user/message') + .map(event => event.data.content) + expect(turns).toHaveLength(2) + expect(messages).toEqual([ + [{ type: 'text', text: 'outer message' }], + [{ type: 'text', text: 'queued listener message' }], + ]) + }) + + it('preserves independent turn sources across an adjacent microtask send', async () => { + const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + const idle = waitForIdle(ctx, agent) + agent.send([{ type: 'text', text: 'user message' }]) + await Promise.resolve() + agent.send( + [{ type: 'text', text: 'plugin message' }], + { source: { kind: 'plugin', plugin: 'test' } }, + ) + await idle + + const triggers = agent.session.events + .filter(event => event.type === 'turn/start') + .map(event => event.data.trigger) + const sources = agent.session.events + .filter(event => event.type === 'user/message') + .map(event => event.data.source) + expect(triggers).toEqual([ + { kind: 'message', source: { kind: 'user' } }, + { kind: 'message', source: { kind: 'plugin', plugin: 'test' } }, + ]) + expect(sources).toEqual([ + { kind: 'user' }, + { kind: 'plugin', plugin: 'test' }, + ]) + }) + + it('keeps a session-listener send after dequeue in the following turn', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) @@ -850,6 +947,37 @@ describe('agent loop', () => { expect(turns).toEqual([1, 2]) expect(adapter.requests).toHaveLength(2) + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first') + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message') + }) + + it('keeps a model-adapter callback send in the following turn', async () => { + const agentRef: { current?: ReactLoopAgent } = {} + const adapter = new MockAdapter([ + () => { + const agent = agentRef.current + if (agent === undefined) throw new Error('model callback ran before agent setup') + send(agent, 'model callback message') + return textResponse('first') + }, + textResponse('second'), + ]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + agentRef.current = agent + + const idle = waitForIdle(ctx, agent) + send(agent, 'outer message') + await idle + + const messages = agent.session.events + .filter(event => event.type === 'user/message') + .map(event => event.data.content) + expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2) + expect(messages).toEqual([ + [{ type: 'text', text: 'outer message' }], + [{ type: 'text', text: 'model callback message' }], + ]) }) it('awaits session/flush at turn end (persistence checkpoint)', async () => { diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index dbc43ad985..82b103d664 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -75,6 +75,21 @@ function turnNumbers(agent: ReactLoopAgent): number[] { .map(e => (e.data as { turn: number }).turn) } +function turnEndNumbers(agent: ReactLoopAgent): number[] { + return agent.session.events + .filter(e => e.type === 'turn/end') + .map(e => (e.data as { turn: number }).turn) +} + +function userMessageCountsByTurn(agent: ReactLoopAgent): number[] { + const counts: number[] = [] + for (const event of agent.session.events) { + if (event.type === 'turn/start') counts.push(0) + if (event.type === 'user/message') counts[counts.length - 1]! += 1 + } + return counts +} + /** Assert a status trace is a legal run: idle/running alternating, ending idle. */ function assertLegalStatusTrace(trace: string[]): void { for (let i = 1; i < trace.length; i++) { @@ -84,7 +99,7 @@ function assertLegalStatusTrace(trace: string[]): void { } describe('agent loop scheduling properties', () => { - it('a synchronous burst loses no message and uses strictly increasing turns', async () => { + it('a synchronous burst gives every message its own strictly increasing turn', async () => { await fc.assert(fc.asyncProperty( fc.array(fc.string({ minLength: 1 }), { minLength: 1, maxLength: 6 }), async (texts) => { @@ -99,8 +114,11 @@ describe('agent loop scheduling properties', () => { // No message lost: every send appears as a user/message, in order. expect(userMessageTexts(agent)).toEqual(texts) - // A synchronous burst batches into exactly one turn. - expect(turnNumbers(agent)).toEqual([1]) + // Every successful send owns an independent turn even before the driver wakes. + expect(turnNumbers(agent)).toEqual(texts.map((_, i) => i + 1)) + expect(turnEndNumbers(agent)).toEqual(texts.map((_, i) => i + 1)) + expect(userMessageCountsByTurn(agent)).toEqual(texts.map(() => 1)) + expect(trace).toEqual(['running', 'idle']) assertLegalStatusTrace(trace) } finally { await ctx.fiber.dispose() @@ -131,9 +149,9 @@ describe('agent loop scheduling properties', () => { ), { numRuns: 20, timeout: 2000 }) }) - it('mixed schedule (send, optionally settle) loses no message and orders turns', async () => { - // Each step is a (text, settle?) pair: settle=true awaits idle before the - // next send (own turn); settle=false sends in the same tick (batches). + it('mixed settled and same-tick sends preserve one turn per message', async () => { + // Each step optionally waits for idle before the next send; that scheduling + // choice must not change the ordinary message-to-turn mapping. const stepArb = fc.record({ text: fc.string({ minLength: 1 }), settle: fc.boolean() }) await fc.assert(fc.asyncProperty( fc.array(stepArb, { minLength: 1, maxLength: 6 }), @@ -152,14 +170,13 @@ describe('agent loop scheduling properties', () => { } await lastIdle - // No message lost or reordered, regardless of batching. + // No message is lost or reordered, regardless of driver timing. expect(userMessageTexts(agent)).toEqual(steps.map(s => s.text)) - // Turn numbers are a strictly increasing 1..N prefix (N = turn count). + // Every send owns exactly one turn, numbered in FIFO order. const turns = turnNumbers(agent) - expect(turns).toEqual(turns.map((_, i) => i + 1)) - // Every message landed in some turn; turns never exceed messages. - expect(turns.length).toBeLessThanOrEqual(steps.length) - expect(turns.length).toBeGreaterThanOrEqual(1) + expect(turns).toEqual(steps.map((_, i) => i + 1)) + expect(turnEndNumbers(agent)).toEqual(turns) + expect(userMessageCountsByTurn(agent)).toEqual(steps.map(() => 1)) } finally { await ctx.fiber.dispose() } diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 5639f30daf..e1e5b27f22 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -39,7 +39,7 @@ Turn and step boundaries and the model token stream are durable `session/event` The handle every plugin programs against: -- `agent.send(content, options?)` — queue a message; starts a turn when idle. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). +- `agent.send(content, options?)` — queue one independent FIFO item. Unless broad cancellation or disposal clears it before turn start, that item becomes the sole ordinary message in its turn; the next item waits for the preceding turn's durability checkpoint. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). - `agent.steer(content, options?)` — steer a running turn (inject between steps); uses the same owned acceptance boundary and behaves like `send` when idle - `agent.inject(content, options?)` — inject in-session context (context/message event); the next request sees it. Does not run the model. While a turn is open it joins that turn; while idle it is wrapped in a one-shot `injection` turn so every event stays turn-enclosed ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)) - `agent.cancel(reason?)` — cancel ALL pending work: clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window) so a queued-but-not-started prompt never runs. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op. diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 3aad65a70e..62d5b2695e 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -59,7 +59,7 @@ export interface HookContext { /** * Prompt interception result. `allow.content` replaces the prompt and * `additionalContext` becomes a separate context message. `block` records a - * durable `prompt/blocked`; an all-blocked batch ends a zero-step rejected turn. + * durable `prompt/blocked` and ends that prompt's zero-step turn as rejected. */ export type PromptDecision = | { kind: 'allow'; content?: ContentBlock[]; additionalContext?: HookContext } @@ -90,7 +90,7 @@ export interface Agent { readonly ctx: Context /** - * Queue detached, frozen lossless-JSON input; starts a turn when idle. + * Queue one detached, frozen lossless-JSON item; if claimed, it is the sole ordinary message in a FIFO-ordered turn. * Invalid input throws synchronously before notification or enqueue. */ send(content: ContentBlock[], options?: SendOptions): void @@ -111,8 +111,8 @@ export interface Agent { inject(content: ContentBlock[], options?: SendOptions): void /** - * Clear queued and steering work, including work waiting to start, and abort - * the active step. The supplied reason is preserved across pre-step and active + * Clear all queued and steering work, including items waiting to start, and + * abort the active step. The supplied reason is preserved across pre-step and active * cancellation windows, and `whenIdle()` resolves after cancellation reaches * quiescence. Idle cancellation is a no-op and does not arm a later cancel. */ diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index f4f42062fd..131deec325 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -105,8 +105,8 @@ export interface TurnEndReasonMap { /** At least one step reached its output-token ceiling, even if a plugin continued the turn. */ 'max-tokens': { kind: 'max-tokens' } /** - * Policy blocked every prompt before the first step. The zero-step turn still - * records a balanced durable boundary and the veto reason. + * Policy blocked the turn's claimed prompt before the first step. The + * zero-step turn still records a balanced durable boundary and veto reason. */ rejected: { kind: 'rejected'; reason: string } /** @@ -209,8 +209,8 @@ export interface ToolsDelta { */ export interface SessionEventMap { /** - * Opens turn `turn`. `trigger` records what started it — a drained message - * batch or an idle-time injection. The turn is the durability/replay + * Opens turn `turn`. `trigger` records what started it — one claimed queued + * message or an idle-time injection. The turn is the durability/replay * boundary: every event sits between a `turn/start` and its matching * `turn/end` (the turn-enclosure invariant). */ @@ -229,7 +229,7 @@ export interface SessionEventMap { 'user/message': { content: ContentBlock[]; source: MessageSource } /** * Durable record of a prompt veto and its reason. It is log-only: the blocked - * prompt never enters the model-visible surface, including in a mixed batch. + * prompt never enters the model-visible surface, and its turn runs zero steps. */ 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } /** diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index c464ffd22b..2907334b69 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -709,8 +709,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // session/cancel maps to the queue-aware agent.cancel(reason): it aborts // a RUNNING step, clears the queued + steering FIFOs, and drops a // turn that is about to start (the pre-step window) — so a queued-but- - // not-yet-started prompt never runs, and a prompt accepted right after - // cannot be batched into the cancelled turn. Scoped to THIS session's + // not-yet-started prompt never runs, while a prompt accepted afterward + // remains a separate queued turn. Scoped to THIS session's // agent — a cancel in one session never touches another's stream or // pending prompt (RFC 011 isolation). We ALSO settle the in-flight prompt // as cancelled directly here: do NOT rely on the resulting turn/end to From a6915745e068209142e68564b967b1d2a2c35e03 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 17 Jul 2026 17:21:10 +0800 Subject: [PATCH 160/323] fix(bash-local): bound inherited pipe drain and spill files --- docs/config-catalog.md | 4 +- packages/bash/bash-local/README.md | 11 +-- packages/bash/bash-local/src/index.ts | 10 ++- packages/bash/bash-local/src/run.ts | 75 ++++++++++++++---- .../bash/bash-local/tests/executor.spec.ts | 1 + packages/bash/bash-local/tests/run.spec.ts | 77 +++++++++++++++++-- 6 files changed, 151 insertions(+), 27 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index c94b5d571e..9ba1f73cf5 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -152,7 +152,9 @@ export interface Config { maxTimeoutMs?: number /** Per-stream in-memory output cap; overflow spills to a temp file. */ maxOutputBytes?: number - /** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */ + /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ + maxSpillBytes?: number + /** Grace period for kill escalation and for inherited pipes after shell exit. */ graceMs?: number } ``` diff --git a/packages/bash/bash-local/README.md b/packages/bash/bash-local/README.md index 6048f886a3..c6fc6e863d 100644 --- a/packages/bash/bash-local/README.md +++ b/packages/bash/bash-local/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-bash-local -Local-subprocess implementation of the `@deepseek-ai/dsh-bash` executor seam: `LocalBashExecutor` spawns `bash -c ` per call in its own process group, collects bounded output with full-stream spill files, and escalates kills SIGTERM→SIGKILL across the whole group. +Local-subprocess implementation of the `@deepseek-ai/dsh-bash` executor seam: `LocalBashExecutor` spawns `bash -c ` per call in its own process group, collects bounded output with size-limited full-stream spill files, and escalates kills SIGTERM→SIGKILL across the whole group. The package root exports the default and named `LocalBashExecutor` plugin plus its `Config`; subprocess plumbing stays internal to the implementation package. @@ -14,7 +14,8 @@ The package root exports the default and named `LocalBashExecutor` plugin plus i timeoutMs: 120000 # default foreground timeout maxTimeoutMs: 600000 # cap for per-call overrides maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk - graceMs: 3000 # SIGTERM→SIGKILL escalation grace on kills + maxSpillBytes: 67108864 # per-stream full-output spill cap + graceMs: 3000 # kill escalation and post-exit pipe-drain grace ``` ## Behavior (and where it came from) @@ -22,8 +23,8 @@ The package root exports the default and named `LocalBashExecutor` plugin plus i Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; the notable choices: - **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` (deterministic; no rc files). All four surveyed tools spawn per call. `XXX(stateful-shell)` in `src/run.ts` records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them. -- **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools. -- **Tail-keep truncation + spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file. +- **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). After the main shell exits, inherited stdout/stderr pipes receive the same bounded drain grace so a surviving descendant cannot hold the command open indefinitely. ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools. +- **Tail-keep truncation + bounded spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. A stream larger than `maxSpillBytes` discards its now-incomplete spill and returns only the marked truncated tail. If the final spill close reports a delayed writeback failure, the executor likewise withholds the path rather than advertising an incomplete file. - **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`), then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. This scrub is the security control that keeps the harness's *ambient* credentials out of a spawned command. A spec's `env` is merged LAST (after the scrub), so a caller's explicit entry — a value it already holds — wins even on a credential-shaped name. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null` — the exact pre-seam default, so a command that probes stdin's file type is unaffected. Both `env`/`stdin` are set by in-process plugins (the hooks bridges); the model-facing tool doesn't expose them. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). - **Background processes** — `start()` returns a live `BashProcess` handle immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), the handle's `readOutput()` is incremental with whole-stream byte offsets, and disposal kills every running process and awaits its exit. Everything task-shaped (ids, ownership, polling, notices) lives in the generic [`ctx.tasks` runtime](../../tasks/tasks/README.md), which the tool layer registers the handle with — this executor never sees a session or a registry. @@ -37,6 +38,6 @@ Indirectly, through `dsh-tool-bash`, which renders this executor's bounded stdou - **No persistent shell or PTY** — every call starts a fresh non-login `bash -c`; cwd-only persistence and interactive terminal sessions remain deferred until a real workflow requires them. - **POSIX-only** — the `bash` binary, detached process groups, group kills, and SIGTERM→SIGKILL escalation are hardcoded; Windows is unsupported. - **The credential scrub is a name heuristic** — `*KEY*`/`*SECRET*`/`*TOKEN*` only; differently-named secrets (e.g. `*PASSWORD*`) pass through, and a whitelist for over-scrubbed vars is noted future work. -- **Spill files are never deleted** — full-output recovery files (and the private per-process spill dir) accumulate under the OS tmpdir until something external cleans them. +- **Completed spill files are not deleted** — bounded full-output recovery files (and the private per-process spill dir) accumulate under the OS tmpdir until something external cleans them; oversize incomplete spills are deleted immediately. The raw process handling lives in `src/run.ts`; `src/index.ts` is the service wiring. diff --git a/packages/bash/bash-local/src/index.ts b/packages/bash/bash-local/src/index.ts index 9c2b0b4511..4e942abb06 100644 --- a/packages/bash/bash-local/src/index.ts +++ b/packages/bash/bash-local/src/index.ts @@ -10,7 +10,7 @@ import z from 'schemastery' import { BashExecutor } from '@deepseek-ai/dsh-bash' import type { BashExecRequest, BashExecSpec, BashProcess, BashProcessRead, BashRunResult } from '@deepseek-ai/dsh-bash' import { clampTimeout, deadline, timeoutOf } from '@deepseek-ai/dsh-timeout' -import { DEFAULT_GRACE_MS, runBash } from './run.ts' +import { DEFAULT_GRACE_MS, DEFAULT_MAX_SPILL_BYTES, runBash } from './run.ts' import type { RunInternals, RunningBash } from './run.ts' /** Plugin config (all optional — `static Config` supplies the defaults). */ @@ -23,7 +23,9 @@ export interface Config { maxTimeoutMs?: number /** Per-stream in-memory output cap; overflow spills to a temp file. */ maxOutputBytes?: number - /** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */ + /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ + maxSpillBytes?: number + /** Grace period for kill escalation and for inherited pipes after shell exit. */ graceMs?: number } @@ -46,6 +48,7 @@ export class LocalBashExecutor extends BashExecutor { timeoutMs: z.number().default(120_000), maxTimeoutMs: z.number().default(600_000), maxOutputBytes: z.number().default(64_000), + maxSpillBytes: z.number().default(DEFAULT_MAX_SPILL_BYTES), graceMs: z.number().default(DEFAULT_GRACE_MS), }) @@ -64,6 +67,7 @@ export class LocalBashExecutor extends BashExecutor { assertPositiveFinite('timeoutMs', this.config.timeoutMs) assertPositiveFinite('maxTimeoutMs', this.config.maxTimeoutMs) assertPositiveFinite('maxOutputBytes', this.config.maxOutputBytes) + assertPositiveFinite('maxSpillBytes', this.config.maxSpillBytes) assertPositiveFinite('graceMs', this.config.graceMs) ctx.effect(() => async () => { // Await closure so even a TERM-trapping child cannot outlive the fiber. @@ -112,6 +116,7 @@ export class LocalBashExecutor extends BashExecutor { command: spec.command, cwd: spec.workdir, maxOutputBytes: this.config.maxOutputBytes, + maxSpillBytes: this.config.maxSpillBytes, graceMs: this.config.graceMs, signal: d.signal, stdin: spec.stdin, @@ -129,6 +134,7 @@ export class LocalBashExecutor extends BashExecutor { command: spec.command, cwd: spec.workdir, maxOutputBytes: this.config.maxOutputBytes, + maxSpillBytes: this.config.maxSpillBytes, graceMs: this.config.graceMs, signal: spec.signal, stdin: spec.stdin, diff --git a/packages/bash/bash-local/src/run.ts b/packages/bash/bash-local/src/run.ts index 02e7a963be..d475bcb538 100644 --- a/packages/bash/bash-local/src/run.ts +++ b/packages/bash/bash-local/src/run.ts @@ -8,7 +8,7 @@ import { type ChildProcessByStdio, spawn } from 'node:child_process' import type { Readable, Writable } from 'node:stream' import { randomBytes } from 'node:crypto' -import { closeSync, mkdtempSync, openSync, writeSync } from 'node:fs' +import { closeSync, mkdtempSync, openSync, unlinkSync, writeSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' import type { CollectedOutput } from '@deepseek-ai/dsh-bash' @@ -54,7 +54,9 @@ export interface SpawnSpec { cwd: string /** Per-stream in-memory cap; overflow spills to disk (tail kept in memory). */ maxOutputBytes: number - /** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */ + /** Per-stream spill-file cap; larger streams retain only their in-memory tail. */ + maxSpillBytes: number + /** Grace period for kill escalation and for inherited pipes after shell exit. */ graceMs: number /** * Abort signal — kills the process group when it fires. The executor owns @@ -101,6 +103,9 @@ export interface RunInternals { /** Default SIGTERM→SIGKILL grace period (the `graceMs` config; matches OpenCode's 3s). */ export const DEFAULT_GRACE_MS = 3_000 +/** Default per-stream spill cap (the `maxSpillBytes` config). */ +export const DEFAULT_MAX_SPILL_BYTES = 64 * 1024 * 1024 + let spillCounter = 0 let defaultSpillDir: string | undefined @@ -115,9 +120,9 @@ function privateSpillDir(): string { } /** - * Collects one stream with a bounded in-memory tail. The FULL stream is - * always recoverable: on first overflow a spill file is created and every - * chunk (including those already collected) is appended there. + * Collects one stream with a bounded in-memory tail. On first overflow a + * spill file is created and every chunk (including those already collected) + * is appended there while the full stream remains within `maxSpillBytes`. * * Tail-keep rationale (pi/OpenCode): errors and final results cluster at the * end of command output; the spill file covers the head. @@ -128,11 +133,13 @@ export class OutputCollector { private dropped = false private spillFd: number | undefined private spillFile: string | undefined + private spillDisabled = false /** Total bytes ever pushed (not just retained). */ private total = 0 constructor( private readonly maxBytes: number, + private readonly maxSpillBytes: number, private readonly label: string, private readonly spillDir: string, ) {} @@ -148,7 +155,7 @@ export class OutputCollector { push(chunk: Buffer): void { this.total += chunk.length const overflows = this.bytes + chunk.length > this.maxBytes - if (overflows || this.spillFd !== undefined) this.spillAll(chunk) + if (!this.spillDisabled && (overflows || this.spillFd !== undefined)) this.spillAll(chunk) this.chunks.push(chunk) this.bytes += chunk.length while (this.bytes > this.maxBytes && this.chunks.length > 1) { @@ -170,6 +177,10 @@ export class OutputCollector { /** Open the spill file lazily and append `chunk` (and any prior chunks once). */ private spillAll(chunk: Buffer): void { + if (this.total > this.maxSpillBytes) { + this.discardSpill() + return + } if (this.spillFd === undefined) { // Random suffix + O_EXCL + no-follow-equivalent ('wx' fails on any // existing path, symlink or not) + owner-only mode: defeats spill-path @@ -184,6 +195,30 @@ export class OutputCollector { writeSync(this.spillFd, chunk) } + /** Stop spilling and remove the file once it can no longer hold the complete stream. */ + private discardSpill(): void { + const fd = this.spillFd + const file = this.spillFile + this.spillFd = undefined + this.spillFile = undefined + this.spillDisabled = true + if (fd !== undefined) { + try { + closeSync(fd) + } catch { + // Retain the descriptor so finalize can retry the failed close. + this.spillFd = fd + } + } + if (file !== undefined) { + try { + unlinkSync(file) + } catch { + // A failed unlink leaves at most maxSpillBytes behind, never an unbounded file. + } + } + } + /** * Incremental read in whole-stream byte coordinates: returns everything * pushed since `fromByte`. When `fromByte` has already slid out of the @@ -283,8 +318,8 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB ? spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['pipe', 'pipe', 'pipe'], detached: true }) : spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['ignore', 'pipe', 'pipe'], detached: true }) - const stdout = new OutputCollector(spec.maxOutputBytes, 'stdout', spillDir) - const stderr = new OutputCollector(spec.maxOutputBytes, 'stderr', spillDir) + const stdout = new OutputCollector(spec.maxOutputBytes, spec.maxSpillBytes, 'stdout', spillDir) + const stderr = new OutputCollector(spec.maxOutputBytes, spec.maxSpillBytes, 'stderr', spillDir) child.stdout.on('data', (chunk: Buffer) => { stdout.push(chunk) }) child.stderr.on('data', (chunk: Buffer) => { stderr.push(chunk) }) @@ -310,12 +345,13 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB } const done = new Promise((resolve, reject) => { - child.on('error', (error) => { - // No meaningful close outcome follows a spawn failure. - cleanup() - reject(error) - }) - child.on('close', (exitCode, signal) => { + let settled = false + let pipeDrainTimer: NodeJS.Timeout | undefined + const settle = (exitCode: number | null, signal: NodeJS.Signals | null): void => { + if (settled) return + settled = true + child.stdout.destroy() + child.stderr.destroy() cleanup() resolve({ exitCode, @@ -323,9 +359,20 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB stdout: stdout.finalize(), stderr: stderr.finalize(), }) + } + child.on('error', (error) => { + // No meaningful close outcome follows a spawn failure. + settled = true + cleanup() + reject(error) }) + child.on('exit', (exitCode, signal) => { + pipeDrainTimer = setTimeout(() => { settle(exitCode, signal) }, spec.graceMs) + }) + child.on('close', settle) function cleanup(): void { if (graceTimer !== undefined) clearTimeout(graceTimer) + if (pipeDrainTimer !== undefined) clearTimeout(pipeDrainTimer) spec.signal?.removeEventListener('abort', onAbort) } }) diff --git a/packages/bash/bash-local/tests/executor.spec.ts b/packages/bash/bash-local/tests/executor.spec.ts index b176cbaf86..4aa4f50ca1 100644 --- a/packages/bash/bash-local/tests/executor.spec.ts +++ b/packages/bash/bash-local/tests/executor.spec.ts @@ -66,6 +66,7 @@ describe('LocalBashExecutor.run', () => { await expect(setup({ timeoutMs: Number.NaN })).rejects.toThrow(/timeoutMs/) await expect(setup({ maxTimeoutMs: 0 })).rejects.toThrow(/maxTimeoutMs/) await expect(setup({ maxOutputBytes: -1 })).rejects.toThrow(/maxOutputBytes/) + await expect(setup({ maxSpillBytes: 0 })).rejects.toThrow(/maxSpillBytes/) await expect(setup({ graceMs: 0 })).rejects.toThrow(/graceMs/) const { bash } = await setup() diff --git a/packages/bash/bash-local/tests/run.spec.ts b/packages/bash/bash-local/tests/run.spec.ts index 923b3adf7b..b182575f1a 100644 --- a/packages/bash/bash-local/tests/run.spec.ts +++ b/packages/bash/bash-local/tests/run.spec.ts @@ -1,11 +1,14 @@ -import { mkdtempSync, readFileSync, statSync } from 'node:fs' +import { mkdtempSync, readFileSync, statSync, unlinkSync } from 'node:fs' import { tmpdir } from 'node:os' import { dirname, join } from 'node:path' import { describe, expect, it, vi } from 'vitest' import { killGroup, OutputCollector, runBash } from '../src/run.ts' import type { RunningBash } from '../src/run.ts' -const { failNextClose } = vi.hoisted(() => ({ failNextClose: { value: false } })) +const { failNextClose, failNextUnlink } = vi.hoisted(() => ({ + failNextClose: { value: false }, + failNextUnlink: { value: false }, +})) vi.mock('node:fs', async (importOriginal) => { const actual = await importOriginal() return { @@ -17,6 +20,13 @@ vi.mock('node:fs', async (importOriginal) => { } actual.closeSync(fd) }, + unlinkSync(path: Parameters[0]): void { + if (failNextUnlink.value) { + failNextUnlink.value = false + throw Object.assign(new Error('simulated EIO on unlink'), { code: 'EIO' }) + } + actual.unlinkSync(path) + }, } }) @@ -27,6 +37,7 @@ function spec(command: string, overrides: Partial[0]> command, cwd: process.cwd(), maxOutputBytes: 64_000, + maxSpillBytes: 64 * 1024 * 1024, graceMs: 3_000, ...overrides, } @@ -171,6 +182,22 @@ describe('runBash', () => { const result = await running.done expect(result.signal).toBe('SIGTERM') }) + + it('bounds inherited-pipe draining after the shell exits', async () => { + const pidFile = join(spillDir, `pipe-holder-${Date.now()}.pid`) + const started = Date.now() + const running = runBash(spec(`sleep 60 & echo $! > ${pidFile}; echo shell-done`, { graceMs: 100 })) + const descendant = await waitForPidFile(pidFile) + try { + const result = await running.done + expect(Date.now() - started).toBeLessThan(1_000) + expect(result.exitCode).toBe(0) + expect(result.stdout.text).toBe('shell-done\n') + } finally { + process.kill(descendant, 'SIGKILL') + await waitGone(descendant) + } + }) }) describe('stdin and extra env (set by in-process plugins)', () => { @@ -266,7 +293,7 @@ describe('output truncation and spill', () => { describe('OutputCollector', () => { it('keeps the tail of a single oversized chunk', () => { - const collector = new OutputCollector(10, 'test', spillDir) + const collector = new OutputCollector(10, 100, 'test', spillDir) collector.push(Buffer.from('0123456789abcdef')) const out = collector.finalize() expect(out.text).toBe('6789abcdef') @@ -275,7 +302,7 @@ describe('OutputCollector', () => { }) it('readFrom returns increments and flags lossy reads', () => { - const collector = new OutputCollector(10, 'test', spillDir) + const collector = new OutputCollector(10, 100, 'test', spillDir) collector.push(Buffer.from('aaaaa')) const first = collector.readFrom(0) expect(first.text).toBe('aaaaa') @@ -296,7 +323,7 @@ describe('OutputCollector', () => { }) it('contains close failures and drops the spill path', () => { - const collector = new OutputCollector(4, 'closefail', spillDir) + const collector = new OutputCollector(4, 100, 'closefail', spillDir) collector.push(Buffer.from('aaaa')) collector.push(Buffer.from('bbbb')) expect(collector.readFrom(0).spillPath).toBeDefined() @@ -310,6 +337,46 @@ describe('OutputCollector', () => { expect(out!.truncated).toBe(true) expect(out!.spillPath).toBeUndefined() }) + + it('discards a spill that exceeds its configured cap', () => { + const collector = new OutputCollector(4, 8, 'bounded', spillDir) + collector.push(Buffer.from('aaaa')) + collector.push(Buffer.from('bbbb')) + const spillPath = collector.readFrom(0).spillPath! + expect(readFileSync(spillPath, 'utf8')).toBe('aaaabbbb') + + collector.push(Buffer.from('c')) + collector.push(Buffer.from('dddd')) + const out = collector.finalize() + expect(out.text).toBe('dddd') + expect(out.truncated).toBe(true) + expect(out.spillPath).toBeUndefined() + expect(() => readFileSync(spillPath)).toThrow() + }) + + it('does not create a spill when the first overflowing chunk exceeds the cap', () => { + const collector = new OutputCollector(4, 4, 'no-spill', spillDir) + collector.push(Buffer.from('abcdefgh')) + const out = collector.finalize() + expect(out.text).toBe('efgh') + expect(out.truncated).toBe(true) + expect(out.spillPath).toBeUndefined() + }) + + it('contains cleanup failures while disabling an oversize spill', () => { + const collector = new OutputCollector(4, 8, 'cleanup-fail', spillDir) + collector.push(Buffer.from('aaaa')) + collector.push(Buffer.from('bbbb')) + const spillPath = collector.readFrom(0).spillPath! + + failNextClose.value = true + failNextUnlink.value = true + expect(() => { collector.push(Buffer.from('c')) }).not.toThrow() + expect(failNextClose.value).toBe(false) + expect(failNextUnlink.value).toBe(false) + expect(collector.finalize().spillPath).toBeUndefined() + unlinkSync(spillPath) + }) }) describe('killGroup', () => { From 2cf689301c337c53739e4cebcc37929c06e325ff Mon Sep 17 00:00:00 2001 From: pku-xht Date: Fri, 17 Jul 2026 17:27:53 +0800 Subject: [PATCH 161/323] review fix: close one-turn lifecycle gaps --- packages/core/agent-loop/src/loop.ts | 1 + packages/core/agent-loop/tests/cancel.spec.ts | 30 +++++++++ .../agent-loop/tests/interception.spec.ts | 11 ++++ packages/core/agent-loop/tests/loop.spec.ts | 65 +++++++++++++++++-- 4 files changed, 102 insertions(+), 5 deletions(-) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index b26d09e5c1..80b6b27eaf 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -117,6 +117,7 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH } handle.setStatus('running') + if (handle.isDisposed()) break // A synchronous `running` listener can cancel before `runTurn`; balance the // status only when no replacement prompt was queued by that listener. diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 5ed15f1b0b..dd02afdec7 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -88,6 +88,36 @@ describe('Agent.cancel()', () => { expect(agent.status).toBe('idle') }) + it('disposal from the running notification drops queued work before turn start', async () => { + const adapter = new MockAdapter([textResponse('should not run')]) + const ctx = await harness(adapter) + const handle = await ctx.agents.create({ + agentId: AgentId('a-dispose-running'), + sessionId: SessionId('dispose-running-session'), + agentOptions: { model: 'mock' }, + }) + const agent = handle.agent as ReactLoopAgent + + const running = Promise.withResolvers() + let disposalDone: Promise | undefined + ctx.on('agent/status', (subject, status) => { + if (subject !== agent || status !== 'running') return + disposalDone = handle.dispose() + running.resolve(undefined) + }) + + send(agent, 'drop before claim') + await running.promise + if (disposalDone === undefined) throw new Error('running listener did not start disposal') + await disposalDone + await agent.done + + expect(agent.status).toBe('disposed') + expect(agent.session.events.some(event => event.type === 'turn/start')).toBe(false) + expect(userTexts(agent)).toEqual([]) + expect(adapter.requests).toHaveLength(0) + }) + it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => { const adapter = new MockAdapter([textResponse('x')]) const ctx = await harness(adapter) diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index 57b773de8a..8663875c6b 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -239,7 +239,13 @@ describe('agent/prompt-submit', () => { return { kind: 'allow' as const } }) const errors: Error[] = [] + const reasons: TurnEndReason[] = [] + const statuses: string[] = [] ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error)) + ctx.on('agent/status', (subject, status) => { if (subject === agent) statuses.push(status) }) + ctx.on('session/event', (session, event) => { + if (session === agent.session && event.type === 'turn/end') reasons.push(event.data.reason) + }) const idle = waitForIdle(ctx, agent) send(agent, 'first') @@ -251,6 +257,11 @@ describe('agent/prompt-submit', () => { const log = events(agent) expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2) expect(log.filter(e => e.type === 'turn/end')).toHaveLength(2) + expect(reasons).toEqual([ + { kind: 'error', step: 0, message: 'prompt hook broke' }, + { kind: 'completed' }, + ]) + expect(statuses).toEqual(['running', 'idle']) expect(adapter.requests).toHaveLength(1) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('second') }) diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index aff13ddd5c..0e223563b7 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -349,14 +349,24 @@ describe('agent loop', () => { expect(flat).toContain('change of plans') }) - it('steering while idle behaves like send (starts a turn)', async () => { - const adapter = new MockAdapter([textResponse('ok')]) + it('same-tick idle steering inherits one-send-one-turn FIFO behavior', async () => { + const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - agent.steer([{ type: 'text', text: 'hello' }]) - await waitForIdle(ctx, agent) - expect(agent.session.events.some(e => e.type === 'user/message')).toBe(true) + const idle = waitForIdle(ctx, agent) + agent.steer([{ type: 'text', text: 'first idle steer' }]) + agent.steer([{ type: 'text', text: 'second idle steer' }]) + await idle + + expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2) + expect(agent.session.events + .filter(event => event.type === 'user/message') + .map(event => event.data.content)).toEqual([ + [{ type: 'text', text: 'first idle steer' }], + [{ type: 'text', text: 'second idle steer' }], + ]) + expect(adapter.requests).toHaveLength(2) }) it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => { @@ -893,6 +903,51 @@ describe('agent loop', () => { expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message') }) + it('holds a turn-end listener send behind the closing turn checkpoint', async () => { + const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + + const firstFlush = Promise.withResolvers() + const releaseFirstFlush = Promise.withResolvers() + let flushes = 0 + ctx.on('session/flush', async (session) => { + if (session !== agent.session) return + flushes += 1 + if (flushes === 1) { + firstFlush.resolve(undefined) + await releaseFirstFlush.promise + } + }) + + const turns: number[] = [] + const statuses: string[] = [] + ctx.on('agent/status', (subject, status) => { + if (subject === agent) statuses.push(status) + }) + ctx.on('session/event', (session, event) => { + if (session !== agent.session) return + if (event.type === 'turn/start') turns.push(event.data.turn) + if (event.type === 'turn/end' && event.data.turn === 1) send(agent, 'turn-end listener message') + }) + + const idle = waitForIdle(ctx, agent) + send(agent, 'first message') + await firstFlush.promise + + expect(turns).toEqual([1]) + expect(adapter.requests).toHaveLength(1) + + releaseFirstFlush.resolve(undefined) + await idle + + expect(turns).toEqual([1, 2]) + expect(statuses).toEqual(['running', 'idle']) + expect(adapter.requests).toHaveLength(2) + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer') + expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('turn-end listener message') + }) + it('keeps a reentrant agent/queued send as the next independent turn', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) From a38ff125a7a9c4d3e9fc3b0e6e86ade46e9b3876 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 17 Jul 2026 17:29:38 +0800 Subject: [PATCH 162/323] feat(dsbench): add SDK evaluation composition --- docs/config-catalog.md | 16 +- examples/README.md | 4 + examples/dsbench-coding-agent/README.md | 24 +++ examples/dsbench-coding-agent/cordis.yml | 77 +++++++++ examples/dsbench-coding-agent/package.json | 7 + .../tests/keyless-smoke.e2e.ts | 146 ++++++++++++++++++ packages/examples/acp-demo/src/index.ts | 4 +- packages/examples/agent-spine-demo/README.md | 2 +- .../examples/agent-spine-demo/src/index.ts | 20 ++- .../agent-spine-demo/tests/agent-core.spec.ts | 21 ++- packages/examples/stdio-demo/src/index.ts | 4 +- packages/llm/llm-deepseek/src/adapter.ts | 3 + .../llm/llm-deepseek/tests/adapter.spec.ts | 14 ++ packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/index.ts | 12 +- packages/ui/jsonrpc/src/server.ts | 16 +- packages/ui/jsonrpc/tests/server.spec.ts | 22 ++- 17 files changed, 365 insertions(+), 29 deletions(-) create mode 100644 examples/dsbench-coding-agent/README.md create mode 100644 examples/dsbench-coding-agent/cordis.yml create mode 100644 examples/dsbench-coding-agent/package.json create mode 100644 examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9ba1f73cf5..c888731228 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -56,7 +56,7 @@ export interface Config { skills?: agentCore.SkillConfig /** Model-facing bash tool config forwarded through agent-core. */ toolBash?: NonNullable - /** Generic background-task control-tool config forwarded through agent-core. */ + /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable } ``` @@ -120,12 +120,14 @@ export interface Config { skills?: SkillConfig /** Model-facing bash tool config, including this producer's background opt-in. */ toolBash?: toolBash.Config - /** Generic background-task control-tool wait bounds. */ - toolTasks?: toolTasks.Config + /** Generic background-task controls; set false to keep the task service without model-facing task tools. */ + toolTasks?: toolTasks.Config | false } /** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */ export interface SkillConfig { + /** Mount the bundled local skill provider and model-facing skill tool (default true). */ + enabled?: boolean /** Registry-level discovery cache settings. */ registry?: SkillRegistryConfig /** Local filesystem skill provider settings. */ @@ -137,7 +139,7 @@ export interface SkillConfig { Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts) -Source: [`packages/examples/agent-spine-demo/src/index.ts:55`](../packages/examples/agent-spine-demo/src/index.ts) +Source: [`packages/examples/agent-spine-demo/src/index.ts:57`](../packages/examples/agent-spine-demo/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -343,8 +345,10 @@ Source: [`packages/hooks/hooks-codex/src/index.ts:41`](../packages/hooks/hooks-c Requires: `agents` ```ts config-catalog -/** Runtime-only test seams; no field is configurable from `cordis.yml`. */ +/** JSON-RPC deployment config plus runtime-only test seams. */ export interface JsonRpcConfig { + /** Report max-token turn/subagent termination as a successful SDK result. */ + maxTokensAsSuccess?: boolean /** Transport input override; production uses `process.stdin`. */ input?: Readable /** Transport output override; production uses `process.stdout`. */ @@ -724,7 +728,7 @@ export interface Config { skills?: agentCore.SkillConfig /** Model-facing bash tool config forwarded through agent-core. */ toolBash?: NonNullable - /** Generic background-task control-tool config forwarded through agent-core. */ + /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable /** * If set, the `main` agent RESUMES this persisted session id instead of diff --git a/examples/README.md b/examples/README.md index 5db1e18372..556a3bf41e 100644 --- a/examples/README.md +++ b/examples/README.md @@ -21,6 +21,10 @@ Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. +## dsbench-coding-agent + +The unattended SDK composition used by DSBench: JSON-RPC stdio, foreground-only `bash`, `read` / `write` / `edit`, one foreground `subagent`, `todo_write`, JSONL persistence, and compaction. It excludes terminal UI, stdout logging, approvals, skills, and background task controls. See [dsbench-coding-agent/README.md](dsbench-coding-agent/README.md). + ## cordis-agent The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one `cordis-dynamic` fiber subtree. The `ctx.fs`/`ctx.web` services ride along provider-only, as the capabilities those plugins build on. diff --git a/examples/dsbench-coding-agent/README.md b/examples/dsbench-coding-agent/README.md new file mode 100644 index 0000000000..ff45ba36cf --- /dev/null +++ b/examples/dsbench-coding-agent/README.md @@ -0,0 +1,24 @@ +# dsbench-coding-agent + +The DSBench deployment composition for the Python SDK's bundled JSON-RPC runtime. It intentionally loads no terminal UI, console logger, approval surface, or user-interaction tool because stdout belongs to the SDK protocol and benchmark turns are unattended. + +The model-facing tools are: + +- `bash`, foreground only +- `read`, `write`, and `edit` +- `subagent`, using one foreground in-process spawn provider +- `todo_write` + +The surrounding runtime also loads JSONL session persistence and automatic context compaction. `maxTokensAsSuccess` keeps a token-limited model turn as an accepted benchmark result while preserving its `max-tokens` reason. + +## Runtime environment + +| Variable | Purpose | +|---|---| +| `DEEPSEEK_API_KEY` | Credential passed to the OpenAI-compatible host endpoint | +| `DEEPSEEK_BASE_URL` | Host endpoint used by `dsh-llm-deepseek` | +| `DSH_CWD` | Benchmark workspace for bash and filesystem tools | +| `DSH_SESSION_ROOT` | JSONL trajectory directory | +| `DSH_SYSTEM_PROMPT` | DSBench-provided coding persona | + +Pass the config path through the Python SDK's `cordis` option or `DSH_CORDIS_CONFIG`. The bundled executable already carries every plugin named by this file; the target machine does not need Node.js. diff --git a/examples/dsbench-coding-agent/cordis.yml b/examples/dsbench-coding-agent/cordis.yml new file mode 100644 index 0000000000..67e1604b07 --- /dev/null +++ b/examples/dsbench-coding-agent/cordis.yml @@ -0,0 +1,77 @@ +# DSBench deployment for the bundled dsh-jsonrpc-agent runtime. +# stdout is reserved for JSON-RPC; do not add a console logger or terminal UI. + +- id: jsonrpc + name: '@deepseek-ai/dsh-jsonrpc' + config: + maxTokensAsSuccess: true + +- id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + config: + apiKey: !!js process.env.DEEPSEEK_API_KEY + baseURL: !!js process.env.DEEPSEEK_BASE_URL + models: + - deepseek-v4-flash + - deepseek-v4-pro + +- id: bash + name: '@deepseek-ai/dsh-bash-local' + config: + cwd: !!js process.env.DSH_CWD ?? process.cwd() + timeoutMs: 60000 + +- id: agent-spine + name: '@deepseek-ai/dsh-agent-spine-demo' + config: + persona: !!js process.env.DSH_SYSTEM_PROMPT ?? 'You are a coding agent driven by DSBench.' + workspaceContext: false + skills: + enabled: false + toolBash: + enableRunInBackground: false + toolTasks: false + +- id: sessions + name: '@deepseek-ai/dsh-session-persistence-jsonl' + config: + root: !!js process.env.DSH_SESSION_ROOT ?? './.sessions' + +- id: subagent + name: '@deepseek-ai/dsh-subagent' + +- id: subagent-spawn + name: '@deepseek-ai/dsh-subagent-spawn' + config: + providerName: spawn + +- id: tool-subagent + name: '@deepseek-ai/dsh-tool-subagent' + config: + provider: spawn + toolName: subagent + enableRunInBackground: false + +- id: tool-todo + name: '@deepseek-ai/dsh-tool-todo' + +- id: fs-local + name: '@deepseek-ai/dsh-fs-local' + config: + cwd: !!js process.env.DSH_CWD ?? process.cwd() + +- id: fs-policy + name: '@deepseek-ai/dsh-fs-policy' + +- id: tool-fs + name: '@deepseek-ai/dsh-tool-fs' + +- id: compact-basic + name: '@deepseek-ai/dsh-compact-basic' + config: + contextWindow: 128000 + thresholdRatio: 0.8 + retainTokens: 20480 + summarizationModel: '' + maxTokens: 8192 + compactionRetries: 1 diff --git a/examples/dsbench-coding-agent/package.json b/examples/dsbench-coding-agent/package.json new file mode 100644 index 0000000000..900c88d69b --- /dev/null +++ b/examples/dsbench-coding-agent/package.json @@ -0,0 +1,7 @@ +{ + "name": "dsbench-coding-agent-example", + "private": true, + "version": "0.0.1", + "type": "module", + "description": "DSBench JSON-RPC coding-agent composition" +} diff --git a/examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts b/examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts new file mode 100644 index 0000000000..9bbc07a829 --- /dev/null +++ b/examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts @@ -0,0 +1,146 @@ +import { spawn } from 'node:child_process' +import { createServer } from 'node:http' +import { mkdtemp, rm } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { describe, expect, it } from 'vitest' + +const binScript = fileURLToPath(new URL('../../../packages/examples/jsonrpc-demo/src/bin.ts', import.meta.url)) +const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) +const repoRoot = fileURLToPath(new URL('../../..', import.meta.url)) + +function waitForLine( + lines: string[], + predicate: (value: Record) => boolean, + stderr: () => string, +): Promise> { + return new Promise((resolve, reject) => { + const deadline = Date.now() + 30_000 + const poll = (): void => { + while (lines.length > 0) { + const line = lines.shift()! + if (!line.trim()) continue + try { + const value = JSON.parse(line) as Record + if (predicate(value)) { + resolve(value) + return + } + } catch { + reject(new Error(`non-JSON stdout from DSBench runtime: ${line}`)) + return + } + } + if (Date.now() >= deadline) { + reject(new Error(`timed out waiting for JSON-RPC response; stderr=${stderr()}`)) + return + } + setTimeout(poll, 10) + } + poll() + }) +} + +describe('dsbench-coding-agent keyless smoke', () => { + it('boots the real Cordis tree and serves initialize/shutdown over clean stdout', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-dsbench-smoke-')) + const modelRequests: Record[] = [] + const modelServer = createServer((request, response) => { + let body = '' + request.setEncoding('utf8') + request.on('data', (chunk: string) => { body += chunk }) + request.on('end', () => { + modelRequests.push(JSON.parse(body) as Record) + response.writeHead(200, { 'content-type': 'text/event-stream' }) + response.write('data: {"choices":[{"delta":{"role":"assistant","content":null}}]}\n\n') + response.write('data: {"choices":[{"delta":{"content":"done"}}]}\n\n') + response.write('data: {"choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":3,"completion_tokens":1}}\n\n') + response.end('data: [DONE]\n\n') + }) + }) + await new Promise(resolve => modelServer.listen(0, '127.0.0.1', resolve)) + const address = modelServer.address() + if (address === null || typeof address === 'string') throw new Error('model server did not bind a TCP port') + const child = spawn(process.execPath, [ + '--expose-internals', + '--import', + 'tsx', + binScript, + configPath, + ], { + cwd: repoRoot, + env: { + ...process.env, + DEEPSEEK_API_KEY: 'keyless-smoke-no-call', + DEEPSEEK_BASE_URL: `http://127.0.0.1:${address.port}`, + DSH_CWD: root, + DSH_SESSION_ROOT: join(root, '.sessions'), + }, + stdio: ['pipe', 'pipe', 'pipe'], + }) + const lines: string[] = [] + let stdoutBuffer = '' + let stderr = '' + child.stdout.setEncoding('utf8') + child.stdout.on('data', (chunk: string) => { + stdoutBuffer += chunk + const parts = stdoutBuffer.split('\n') + stdoutBuffer = parts.pop() ?? '' + lines.push(...parts) + }) + child.stderr.setEncoding('utf8') + child.stderr.on('data', (chunk: string) => { stderr += chunk }) + + try { + child.stdin.write(`${JSON.stringify({ + jsonrpc: '2.0', + id: 1, + method: 'initialize', + params: { cwd: root, model: 'deepseek-v4-pro' }, + })}\n`) + const initialized = await waitForLine(lines, value => value.id === 1, () => stderr) + expect(initialized).toMatchObject({ + jsonrpc: '2.0', + id: 1, + result: { serverInfo: { name: 'deepseek-harness-sdk-runtime' } }, + }) + + child.stdin.write(`${JSON.stringify({ + jsonrpc: '2.0', + id: 2, + method: 'session/prompt', + params: { sessionId: 'main', contentBlocks: [{ type: 'text', text: 'inspect tools' }] }, + })}\n`) + const prompt = await waitForLine(lines, value => value.id === 2, () => stderr) + expect(prompt).toMatchObject({ jsonrpc: '2.0', id: 2, result: { accepted: true } }) + const tools = modelRequests[0]?.tools as { function?: { name?: string } }[] + expect(tools.map(tool => tool.function?.name).sort()).toEqual([ + 'bash', + 'edit', + 'read', + 'subagent', + 'todo_write', + 'write', + ]) + + child.stdin.write(`${JSON.stringify({ jsonrpc: '2.0', id: 3, method: 'shutdown' })}\n`) + const shutdown = await waitForLine(lines, value => value.id === 3, () => stderr) + expect(shutdown).toMatchObject({ jsonrpc: '2.0', id: 3, result: {} }) + if (child.exitCode === null) { + await new Promise((resolve, reject) => { + child.once('exit', (code) => { + if (code === 0) resolve() + else reject(new Error(`runtime exited ${code}; stderr=${stderr}`)) + }) + }) + } else { + expect(child.exitCode, stderr).toBe(0) + } + } finally { + if (child.exitCode === null) child.kill('SIGKILL') + await new Promise(resolve => modelServer.close(() => { resolve() })) + await rm(root, { recursive: true, force: true }) + } + }, 40_000) +}) diff --git a/packages/examples/acp-demo/src/index.ts b/packages/examples/acp-demo/src/index.ts index e52b21b9f6..ca94315093 100644 --- a/packages/examples/acp-demo/src/index.ts +++ b/packages/examples/acp-demo/src/index.ts @@ -46,7 +46,7 @@ export interface Config { skills?: agentCore.SkillConfig /** Model-facing bash tool config forwarded through agent-core. */ toolBash?: NonNullable - /** Generic background-task control-tool config forwarded through agent-core. */ + /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable } @@ -67,7 +67,7 @@ export const Config: z = z.object({ workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(), skills: agentCore.SkillConfigSchema, toolBash: agentCore.ToolBashConfigSchema, - toolTasks: agentCore.ToolTasksConfigSchema, + toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]), }) /* jscpd:ignore-end */ diff --git a/packages/examples/agent-spine-demo/README.md b/packages/examples/agent-spine-demo/README.md index 0d02d5f597..a59c741994 100644 --- a/packages/examples/agent-spine-demo/README.md +++ b/packages/examples/agent-spine-demo/README.md @@ -46,7 +46,7 @@ import type { Config } from '@deepseek-ai/dsh-agent-spine-demo' // workspaceContext requires { maxBytes } or false; the other owner schemas supply defaults. ``` -The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. `toolBash.enableRunInBackground` controls only the bash producer, while `toolTasks` controls generic `task_output` wait bounds; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields. +The bundle FORWARDS each field to the child that owns it: `agents` to `agent-loop` (default `[]`), so each app supplies its own pre-created agents — a stdio app pre-creates a `main`; the ACP app pre-creates none (it creates agents on demand at `session/new`) — `persona` and `toolOrder` to `dsh-system-prompt`; `tools` to the tool registry for its presentation mode; `skills.registry`, `skills.local`, and `skills.tool` to the skill registry, local provider, and model-facing consumer; the required `workspaceContext` choice to `dsh-workspace-context` (`{ maxBytes }` enables loading and `false` disables it); and `toolBash`/`toolTasks` to the two model-facing tool plugins the bundle owns. Set `skills.enabled: false` to omit both the local provider and model-facing skill tool, and set `toolTasks: false` to retain the task service for foreground producers without exposing `task_output` / `task_list` / `task_kill`. `toolBash.enableRunInBackground` controls only the bash producer; independently loaded producers keep their own config. Workspace instructions register before the skill catalog so their session-prefix message renders first. App packages use `pickSpineConfig()` to copy only these bundle-owned fields. ## Why a code bundle, not a shared YAML include diff --git a/packages/examples/agent-spine-demo/src/index.ts b/packages/examples/agent-spine-demo/src/index.ts index 5652078a0f..deb433eb85 100644 --- a/packages/examples/agent-spine-demo/src/index.ts +++ b/packages/examples/agent-spine-demo/src/index.ts @@ -30,6 +30,8 @@ export const name = 'agent-spine-demo' /** Skill bundle config forwarded to the registry, local provider, and model-facing consumer. */ export interface SkillConfig { + /** Mount the bundled local skill provider and model-facing skill tool (default true). */ + enabled?: boolean /** Registry-level discovery cache settings. */ registry?: SkillRegistryConfig /** Local filesystem skill provider settings. */ @@ -67,12 +69,13 @@ export interface Config { skills?: SkillConfig /** Model-facing bash tool config, including this producer's background opt-in. */ toolBash?: toolBash.Config - /** Generic background-task control-tool wait bounds. */ - toolTasks?: toolTasks.Config + /** Generic background-task controls; set false to keep the task service without model-facing task tools. */ + toolTasks?: toolTasks.Config | false } /** The skill config schema exported for app packages that forward `skills`. */ export const SkillConfigSchema: z = z.object({ + enabled: z.boolean().default(true), registry: SkillService.Config, local: SkillLocal.Config, tool: toolSkill.Config, @@ -93,7 +96,7 @@ export const Config = z.intersect([ skills: SkillConfigSchema, workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(), toolBash: ToolBashConfigSchema, - toolTasks: ToolTasksConfigSchema, + toolTasks: z.union([z.const(false), ToolTasksConfigSchema]), }) as unknown as z>, ]) as unknown as z @@ -134,8 +137,11 @@ export function apply(ctx: Context, config: Config): void { ...config.toolOrder !== undefined ? { toolOrder: config.toolOrder } : {}, }) ctx.plugin(ToolRegistry, config.tools ?? {}) - ctx.plugin(SkillService, config.skills?.registry ?? {}) - ctx.plugin(SkillLocal, config.skills?.local ?? {}) + const skillsEnabled = config.skills?.enabled ?? true + if (skillsEnabled) { + ctx.plugin(SkillService, config.skills?.registry ?? {}) + ctx.plugin(SkillLocal, config.skills?.local ?? {}) + } ctx.plugin(AgentRegistry) ctx.plugin(TaskService) ctx.plugin(invariants) @@ -145,7 +151,7 @@ export function apply(ctx: Context, config: Config): void { } // Both plugins prepend session-prefix messages. Registration order is the // rendered order, so workspace instructions must precede the skill catalog. - ctx.plugin(toolSkill, config.skills?.tool ?? {}) - ctx.plugin(toolTasks, config.toolTasks ?? {}) + if (skillsEnabled) ctx.plugin(toolSkill, config.skills?.tool ?? {}) + if (config.toolTasks !== false) ctx.plugin(toolTasks, config.toolTasks ?? {}) ctx.plugin(AgentLoop, { agents: config.agents ?? [] }) } diff --git a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index 51562f547d..e9763b3488 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -301,6 +301,21 @@ describe('dsh-agent-spine-demo bundle', () => { await ctx.fiber.dispose() }) + it('can omit skills and model-facing task controls for a foreground-only deployment', async () => { + const ctx = await mount({ + workspaceContext: false, + skills: { enabled: false }, + toolBash: { enableRunInBackground: false }, + toolTasks: false, + }, true) + + expect(ctx.tools.schemas().map(tool => tool.name)).toEqual(['bash']) + expect(ctx.get('skills')).toBeUndefined() + expect(ctx.get('tasks')).toBeDefined() + + await ctx.fiber.dispose() + }) + it('picks shared spine config without leaking front-door fields', () => { const appConfig = { model: 'front-door-only', @@ -308,9 +323,9 @@ describe('dsh-agent-spine-demo bundle', () => { toolOrder: ['zulu'], tools: { mode: 'native' as const }, workspaceContext: false as const, - skills: {}, + skills: { enabled: false }, toolBash: { enableRunInBackground: false }, - toolTasks: { waitTimeoutMs: 7, maxWaitTimeoutMs: 11 }, + toolTasks: false as const, } expect(agentCore.pickSpineConfig(appConfig)).toEqual({ @@ -318,7 +333,7 @@ describe('dsh-agent-spine-demo bundle', () => { toolOrder: appConfig.toolOrder, tools: appConfig.tools, workspaceContext: false, - skills: {}, + skills: appConfig.skills, toolBash: appConfig.toolBash, toolTasks: appConfig.toolTasks, }) diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index d7ae866b53..754dd7d8de 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -51,7 +51,7 @@ export interface Config { skills?: agentCore.SkillConfig /** Model-facing bash tool config forwarded through agent-core. */ toolBash?: NonNullable - /** Generic background-task control-tool config forwarded through agent-core. */ + /** Generic background-task controls forwarded through agent-core; set false to omit their tool surface. */ toolTasks?: NonNullable /** * If set, the `main` agent RESUMES this persisted session id instead of @@ -77,7 +77,7 @@ export const Config: z = z.object({ welcome: z.string().default('ready.'), skills: agentCore.SkillConfigSchema, toolBash: agentCore.ToolBashConfigSchema, - toolTasks: agentCore.ToolTasksConfigSchema, + toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]), resumeSessionId: z.string(), workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(), }) diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..aa169f320e 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -61,6 +61,9 @@ export class DeepSeekAdapter extends LlmAdapter { 'content-type': 'application/json', 'accept': 'text/event-stream', ...attributionHeaders(), + ...options.sessionId !== undefined + ? { 'x-deepseek-harness-session-id': String(options.sessionId) } + : {}, }, body: JSON.stringify(body), ...options.signal ? { signal: options.signal } : {}, diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..7898c62131 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -3,6 +3,7 @@ import type { IncomingMessage, Server, ServerResponse } from 'node:http' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import { DeepSeekAdapter, httpErrorCode } from '@deepseek-ai/dsh-llm-deepseek' import { assemble } from './assemble.ts' @@ -131,6 +132,19 @@ describe('DeepSeekAdapter against a mock server', () => { expect(kinds).toEqual(['block-start', 'text-delta', 'block-end', 'usage', 'finish']) }) + it('forwards the harness session id for host-side trajectory routing', async () => { + const server = await mockServer([{ kind: 'sse', events: textEvents }]) + const ctx = await harness(server.url) + + await assemble(ctx, { + model: 'deepseek-v4-flash', + messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], + sessionId: SessionId('child-session'), + }) + + expect(server.headers[0]?.['x-deepseek-harness-session-id']).toBe('child-session') + }) + it('forwards thinking config onto the wire', async () => { const server = await mockServer([{ kind: 'sse', events: textEvents }]) const ctx = await harness(server.url, { thinking: 'disabled', reasoningEffort: 'high' }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index bf686ea800..fdec9920f7 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -8,7 +8,7 @@ Stdio JSON-RPC plugin for out-of-process SDK clients such as Python `deepseek_ha ## Config -No `cordis.yml` keys. `JsonRpcConfig.input`, `output`, and `exit` are test-only runtime seams; production uses process stdio and `process.exit`. +`maxTokensAsSuccess` defaults to `false`. Set it to `true` for evaluation hosts that distinguish an accepted, token-limited agent result from an infrastructure failure. `JsonRpcConfig.input`, `output`, and `exit` are test-only runtime seams; production uses process stdio and `process.exit`. ## stdout is the protocol diff --git a/packages/ui/jsonrpc/src/index.ts b/packages/ui/jsonrpc/src/index.ts index 29fb1aeff8..fe782c934f 100644 --- a/packages/ui/jsonrpc/src/index.ts +++ b/packages/ui/jsonrpc/src/index.ts @@ -22,8 +22,10 @@ export const name = 'jsonrpc' // Only the agent factory is required; initialize reads the optional LLM seam with ctx.get(). export const inject = ['agents'] -/** Runtime-only test seams; no field is configurable from `cordis.yml`. */ +/** JSON-RPC deployment config plus runtime-only test seams. */ export interface JsonRpcConfig { + /** Report max-token turn/subagent termination as a successful SDK result. */ + maxTokensAsSuccess?: boolean /** Transport input override; production uses `process.stdin`. */ input?: Readable /** Transport output override; production uses `process.stdout`. */ @@ -32,7 +34,9 @@ export interface JsonRpcConfig { exit?: (code: number) => void } -export const Config: Schema = Schema.object({}) +export const Config: Schema = Schema.object({ + maxTokensAsSuccess: Schema.boolean().default(false), +}) /** * Serve SDK requests over the configured streams. Effect disposal shuts down @@ -51,7 +55,9 @@ export function apply(ctx: Context, config: JsonRpcConfig): void { const exit = config.exit ?? ((code: number): void => { process.exit(code) }) const transport = new JsonRpcLineTransport(input, output) - const server = new HarnessSdkServer(ctx, transport) + const server = new HarnessSdkServer(ctx, transport, { + maxTokensAsSuccess: config.maxTokensAsSuccess ?? false, + }) // Share one exit task and attempt flush and disposal independently before exiting. let exitTask: Promise | undefined diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 91ef655c0c..44b746adce 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -59,6 +59,12 @@ interface SubagentRecord { parentSessionId: string | undefined } +/** Deployment-specific status mapping for SDK turn and subagent outcomes. */ +export interface HarnessSdkServerOptions { + /** Report max-token termination as an accepted result instead of an infrastructure error. */ + maxTokensAsSuccess?: boolean +} + /** * SDK server over one booted harness context and transport peer. Construction * subscribes to session, agent, and subagent lifecycle events until shutdown; @@ -78,6 +84,7 @@ export class HarnessSdkServer { constructor( private readonly ctx: Context, private readonly transport: JsonRpcTransportPeer, + private readonly options: HarnessSdkServerOptions = {}, ) { this.disposers.push(ctx.on('session/event', (session, event) => { if (event.type === 'turn/end') { @@ -116,7 +123,7 @@ export class HarnessSdkServer { agentId: String(info.id), ...(parentSessionId === undefined ? {} : { parentSessionId }), childSessionId, - status: info.stopReason === 'completed' ? 'ok' : 'error', + status: this.successStatus(info.stopReason), stopReason: info.stopReason, ...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }), }) @@ -253,7 +260,12 @@ export class HarnessSdkServer { private finishedStatus(reason: TurnEndReason | undefined): 'ok' | 'error' { if (!reason) return 'error' - return reason.kind === 'completed' ? 'ok' : 'error' + return this.successStatus(reason.kind) + } + + private successStatus(reason: string): 'ok' | 'error' { + if (reason === 'completed') return 'ok' + return reason === 'max-tokens' && this.options.maxTokensAsSuccess === true ? 'ok' : 'error' } private hasAdapterFor(model: string): boolean { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index c993bd4e2c..c8a6bbb217 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -329,7 +329,7 @@ describe('HarnessSdkServer', () => { agentOptions: { model: 'deepseek' }, }) const transport = new FakeTransport() - const server = new HarnessSdkServer(ctx, transport) + const server = new HarnessSdkServer(ctx, transport, { maxTokensAsSuccess: true }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', @@ -355,7 +355,7 @@ describe('HarnessSdkServer', () => { agentId: 'fallback-child-agent', parentSessionId: 'fallback-parent', childSessionId: 'fallback-child-session', - status: 'error', + status: 'ok', stopReason: 'max-tokens', lastAssistantMessage: [], }, @@ -443,6 +443,24 @@ describe('HarnessSdkServer', () => { } }) + it('can report max-token turn termination as an accepted evaluation result', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-max-tokens-success-')) + const ctx = await makeHarness(storageDir) + try { + const server = new HarnessSdkServer(ctx, new FakeTransport(), { maxTokensAsSuccess: true }) as unknown as { + finishedStatus(reason: unknown): 'ok' | 'error' + shutdown(): Promise> + } + + expect(server.finishedStatus({ kind: 'max-tokens' })).toBe('ok') + expect(server.finishedStatus({ kind: 'error' })).toBe('error') + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('reports no adapter when the LLM service is absent', async () => { const ctx = new Context() try { From 0b720942dfe6e8e018d537b80364dfbd201ed27e Mon Sep 17 00:00:00 2001 From: pku-xht Date: Fri, 17 Jul 2026 17:31:35 +0800 Subject: [PATCH 163/323] review fix: qualify one-turn documentation --- docs/architecture.md | 2 +- docs/core-data-structures/core.md | 7 +++--- .../feature/2026-06-30-interception-seams.md | 2 +- .../2026-07-17-one-send-one-turn.i18n.yaml | 4 ++-- .../2026-07-17-one-send-one-turn.md | 8 +++---- .../2026-07-17-one-send-one-turn.zh.md | 24 +++++++++---------- packages/core/agent-loop/README.md | 2 +- packages/core/agent/README.md | 2 +- 8 files changed, 26 insertions(+), 25 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 063c805272..627776bbe0 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -95,7 +95,7 @@ forever: checkpoint persistence and notify idle/running status ``` -Each successful `send()` adds one FIFO item. Queued items run as consecutive ordinary turns under one running interval, each after the prior turn's durability checkpoint. Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). +Each successful `send()` adds one FIFO item. A claimed item is the sole ordinary message in its turn and waits for the prior checkpoint to settle; cancellation, disposal, or a pre-start failure may drop it without a turn. Consecutive claimed items run under one `running` interval. Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). Post-tool context lands after all tool results so tool-call/result adjacency stays stable. Steering drains between steps; ordinary leftover steering after a turn is re-queued as input. A terminal `agent/turn-stop` is the explicit exception: it runs after ordinary continuation and steering folding, then remains authoritative through turn close and flush so steering from those later listeners is discarded rather than becoming another step or turn; ordinary queued prompts are preserved. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 072ad629a6..0d8c874704 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -271,9 +271,10 @@ interface Agent { readonly ctx: Context /** - * Queue one user-message FIFO item. Unless cleared before turn start, the - * item becomes the sole ordinary message in its turn and waits for every - * preceding turn's durability checkpoint. Content and the resolved source are accepted as one detached, + * Queue one user-message FIFO item. If claimed, the item becomes the sole + * ordinary message in its turn after every preceding turn's checkpoint + * settles. Broad cancellation, disposal, or a pre-start failure can drop it + * without a turn. Content and the resolved source are accepted as one detached, * deeply-frozen lossless-JSON record before notification or enqueue, so * caller or `agent/queued` listener in-place mutation cannot change later * log/model input. Throws synchronously when either value is not losslessly diff --git a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md index 50ff4a3af6..aef2ef4eb5 100644 --- a/docs/rfc/implemented/feature/2026-06-30-interception-seams.md +++ b/docs/rfc/implemented/feature/2026-06-30-interception-seams.md @@ -34,7 +34,7 @@ Core dispatch and the tool body sit inside normalization boundaries, so tool, li ### Three load-bearing loop decisions -1. **Open the turn before prompt policy.** A blocked prompt becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. The veto records `prompt/blocked` with the original prompt and reason, while every allowed `additionalContexts` entry is injected into the open turn. Each ordinary send owns an independent turn under the [one-send-one-turn simplification](../simplification/2026-07-17-one-send-one-turn.md). +1. **Open the turn before prompt policy.** A blocked prompt becomes a zero-step `rejected` turn, preserving enclosure and giving ACP a durable terminal event. The veto records `prompt/blocked` with the original prompt and reason, while every allowed `additionalContexts` entry is injected into the open turn. Each claimed ordinary-send item is the sole message in its turn under the [one-send-one-turn simplification](../simplification/2026-07-17-one-send-one-turn.md); a pre-start drop creates no turn. 2. **Post-tool `additionalContexts` are buffered and appended AFTER all `tool/result`s.** `content`/`feedback` shape the result `execute()` returns, but each context is a SEPARATE `context/message`, and a single step or composite tool can produce many. Appending context immediately would interleave `result(c1) → context → result(c2)` or place nested context before its outer result, breaking tool-call/result adjacency. `ToolRunContext.deferContext()` therefore collects nested-dispatch context through failures, `execute()` surfaces the ordered array on `ToolExecutionResult`, and the loop appends every entry only after every `tool/result` in the step. An accepted outer call preserves deferred contexts before decision contexts; an outer block discards deferred contexts and exposes only contexts explicitly supplied by the blocking decision. diff --git a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml index bcb9485da5..1d3181bb0a 100644 --- a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-17-one-send-one-turn.md: 34331a04b53f9ccf67db0baf201dec23e1c2a60f -2026-07-17-one-send-one-turn.zh.md: e6c4b97e826393ebca81d715ae3760c6068f84d0 +2026-07-17-one-send-one-turn.md: 232e91b1d13ed07f230ffc2d0a190adafb29c6e2 +2026-07-17-one-send-one-turn.zh.md: b4dc8d37a0dc03a8aae1abfab4c9d473c7afd332 diff --git a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md index 34331a04b5..232e91b1d1 100644 --- a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.md @@ -8,7 +8,7 @@ English | [中文](2026-07-17-one-send-one-turn.zh.md) An ordinary `Agent.send()` payload is one complete caller message. Opportunistically draining every waiting payload into one turn would make adjacent calls share a boundary according to driver timing: calls from one synchronous stack, neighboring microtasks, event listeners, and model callbacks could be grouped differently even though callers used the same API. -A turn owns prompt admission, `turn/start`, `turn/end`, and the durability checkpoint. Combining messages would let a later message join an earlier message's model request instead of observing the earlier turn's committed result, while mixed allowed and blocked prompts would require lifecycle states no caller explicitly requested. +A turn owns prompt admission, `turn/start`, `turn/end`, and the durability checkpoint. Combining messages would let a later message join an earlier message's model request instead of observing the earlier turn's closed result in the same session log, while mixed allowed and blocked prompts would require lifecycle states no caller explicitly requested. `steer()` already expresses joining the active turn, while `inject()` records model-facing context without acting as an ordinary message. Implicit batching would make `send()` overlap both explicit operations instead of preserving a single meaning. @@ -18,11 +18,11 @@ Each successful `send()` synchronously validates agent state, snapshots and free Prompt admission decides one message. An allowed prompt becomes that turn's `user/message`; a blocked prompt appends one durable `prompt/blocked` and ends that one-message turn as `rejected`. There are no mixed-batch or all-blocked-batch branches. -Running `steer()` appends to the active turn's steering FIFO. Idle `steer()` delegates to `send()` and therefore creates an independent ordinary turn. `inject()` retains its turn-enclosure and flush behavior. `cancel()`, `status`, and `whenIdle()` remain whole-agent operations rather than per-message controls. +Running `steer()` appends to the active turn's steering FIFO. Idle `steer()` delegates to `send()` and therefore creates an independent ordinary queue item. `inject()` retains its turn-enclosure and flush behavior. `cancel()`, `status`, and `whenIdle()` remain whole-agent operations rather than per-message controls. ## Alternatives considered -**Keep opportunistic batching for throughput.** Combining queued prompts can reduce model calls when producers outpace the driver, but it makes turn boundaries depend on scheduling and prevents a later message from reliably observing the preceding turn's durable result. Explicit lifecycle semantics are worth the additional model calls; any future batching feature needs an explicit caller-visible contract justified by measurements. +**Keep opportunistic batching for throughput.** Combining queued prompts can reduce model calls when producers outpace the driver, but it makes turn boundaries depend on scheduling and lets a later message run before the preceding turn closes and its checkpoint settles. Explicit lifecycle semantics are worth the additional model calls; any future batching feature needs an explicit caller-visible contract justified by measurements. ## Verification @@ -33,6 +33,6 @@ Running `steer()` appends to the active turn's steering FIFO. Idle `steer()` del ## Consequences -Ordinary turn boundaries are deterministic, and a claimed FIFO successor observes the preceding turn's committed session result. Several queued items can still run under one global `running` interval, and broad cancellation can discard the entire unstarted tail, so status and quiescence remain agent-wide observations rather than per-message results. +Ordinary turn boundaries are deterministic, and a claimed FIFO successor observes the preceding turn's closed session result after its checkpoint settles; settlement does not mean a failed flush became durable. Several queued items can still run under one global `running` interval, and broad cancellation can discard the entire unstarted tail, so status and quiescence remain agent-wide observations rather than per-message results. Workloads that relied on coincidental batching make more model requests, incur more checkpoints, and may take longer to drain; FIFO queues may grow under sustained producers. Throughput optimization can return only through an explicit measured contract. diff --git a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md index e6c4b97e82..b4dc8d37a0 100644 --- a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md @@ -6,33 +6,33 @@ Status: implemented ## 问题 -每个普通 `Agent.send()` payload 都是一条完整的调用方消息。如果机会式地把所有等待 payload 放入同一个轮次，相邻调用是否共享边界就会取决于 driver 时机：即使调用方使用相同 API，来自同一个同步调用栈、相邻微任务、事件 listener 和模型 callback 的调用也可能产生不同分组。 +每次普通 `Agent.send()` 接受的载荷都是一条完整的调用方消息。如果机会式地把所有待处理载荷放入同一个轮次，相邻调用是否共享边界就会取决于驱动器的运行时机：即使调用方使用相同 API，来自同一个同步调用栈、相邻微任务、事件监听器和模型回调的调用也可能产生不同分组。 -轮次拥有提示词准入、`turn/start`、`turn/end` 和持久性检查点。合并消息会让后一条消息加入前一条消息的模型请求，而不能观察前一轮次已经提交的结果；获准与被阻止提示词的混合还会引入调用方从未显式请求的生命周期状态。 +轮次拥有提示词准入、`turn/start`、`turn/end` 和持久性检查点。合并消息会让后一条消息加入前一条消息的模型请求，无法观察前一轮次关闭后写入同一会话日志的结果；获准与被阻止提示词的混合还会引入调用方从未显式请求的生命周期状态。 `steer()` 已经用于表达加入当前轮次，`inject()` 则记录面向模型的上下文而不充当普通消息。隐式批处理会让 `send()` 与这两种显式操作产生语义重叠，无法保持单一含义。 ## 决策 -每次成功的 `send()` 都会同步校验 agent（智能体）状态、创建并冻结内容快照、追加一个独立 FIFO item，然后发布 `agent/queued`。agent loop 在每次轮次开始时最多取出一个普通 item。如果两个 item 都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点完成后开始；广义取消、dispose（资源释放）或启动前失败可以丢弃尚未启动的 item，而不创建空轮次。 +每次成功的 `send()` 都会同步校验 agent（智能体）状态、创建并冻结内容快照、追加一个独立的 FIFO 队列项，然后发布 `agent/queued`。agent loop（智能体循环）在每个轮次开始时最多取出一个普通队列项。如果两个队列项最终都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点处理结束后开始；广义取消、dispose（资源释放）或启动前失败可以丢弃尚未启动的队列项，而不创建空轮次。 -提示词准入只处理一条消息。获准提示词成为该轮次的 `user/message`；被阻止提示词追加一条持久的 `prompt/blocked`，并让这个单消息轮次以 `rejected` 结束。实现中没有 mixed-batch 或 all-blocked-batch 分支。 +提示词准入只处理一条消息。获准提示词成为该轮次的 `user/message`；被阻止提示词追加一条持久的 `prompt/blocked`，并让这个单消息轮次以 `rejected` 结束。实现中没有混合批次或全阻止批次分支。 -运行中的 `steer()` 会追加到当前轮次的 steering FIFO。空闲时的 `steer()` 委托给 `send()`，因此创建一个独立的普通轮次。`inject()` 保持现有的轮次封闭与 flush 行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个 agent 的操作，不变成逐消息控制。 +运行中的 `steer()` 会把消息追加到当前轮次的 steering（中途引导） FIFO。空闲时的 `steer()` 委托给 `send()`，因此创建一个独立的普通队列项。`inject()` 保持现有的轮次封闭与持久化刷新行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个智能体的操作，不变成逐消息控制。 ## 曾考虑的替代方案 -**为吞吐量保留机会式批处理。** 当 producer 速度快于 driver 时，合并排队的提示词可以减少模型调用，但会让轮次边界取决于调度，并使后一条消息无法可靠观察前一轮次的持久化结果。额外模型调用的代价低于显式生命周期语义的价值；未来的任何批处理功能都必须提供调用方可见的显式契约，并由测量结果证明其必要性。 +**为吞吐量保留机会式批处理。** 当消息进入队列的速度超过驱动器的处理速度时，合并排队的提示词可以减少模型调用，但会让轮次边界取决于调度，并让后一条消息在前一轮次关闭且其检查点处理结束之前就运行。额外模型调用的代价低于显式生命周期语义的价值；未来的任何批处理功能都必须提供调用方可见的显式契约，并由测量结果证明其必要性。 ## 验证 -- 单元与性质覆盖固定了同一调用栈、相邻微任务、不同来源和重入 send 的行为：每个轮次只有一条消息，并按 FIFO 排序。 -- 延迟第一个轮次的 flush 可以证明下一个排队轮次不能在检查点完成前开始，且其请求能看到前一个 assistant result；被拒绝的 flush 也会在下一个轮次开始前完成。 -- 提示词否决与 listener failure、广义取消、dispose 和提交前 `turn/start` failure 都会保持已记录轮次边界平衡，不会合并消息或让仍应处理的排队工作滞留。 -- 运行中与空闲时的 `steer()`、`inject()`、面向整个 agent 的 status 和 `whenIdle()` 保持原有覆盖。 +- 单元与性质覆盖固定了同一调用栈、相邻微任务、不同来源和重入 `send()` 的行为：每个轮次只有一条消息，并按 FIFO 排序。 +- 延迟第一个轮次的持久化刷新可以证明下一个排队轮次不能在检查点处理结束前开始，且其请求能看到前一条助手结果；刷新即使失败，下一轮次也要等它结束后才会开始。 +- 提示词否决、监听器失败、广义取消、资源释放和 `turn/start` 提交前失败都会保持已记录轮次边界平衡，不会合并消息或让仍应处理的排队工作滞留。 +- 运行中与空闲时的 `steer()`、`inject()`、面向整个智能体的状态和 `whenIdle()` 保持原有覆盖。 ## 后果 -普通轮次边界是确定的，被认领的 FIFO 后继项可以观察前一轮次已经提交的会话结果。多个排队 item 仍可在同一个全局 `running` 区间内执行，广义取消也可以丢弃整个未启动队尾，因此 status 和静止状态仍是面向整个 agent 的观察，而不是逐消息结果。 +普通轮次边界是确定的，被认领的 FIFO 后继项会在前一轮次关闭且其检查点处理结束后观察会话中的结果；检查点处理结束不表示失败的持久化刷新已经成功。多个排队项仍可在同一个全局 `running` 区间内执行，广义取消也可以丢弃整个未启动队尾，因此状态和静止性仍是面向整个智能体的观察，而不是逐消息结果。 -依赖偶然批处理的工作负载会产生更多模型请求和检查点，队列清空时间也可能延长；持续 producer 还可能让 FIFO 队列增长。只有建立显式且经过测量的契约后，才能重新引入吞吐量优化。 +依赖偶然批处理的工作负载会产生更多模型请求和检查点，队列清空时间也可能延长；持续有消息进入时，FIFO 队列还可能增长。只有建立显式且经过测量的契约后，才能重新引入吞吐量优化。 diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 88efc953a7..e899da75fc 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -44,7 +44,7 @@ Configured agents start automatically. `cwd` applies only to fresh sessions; `re - `ReactLoopAgent` — the concrete `Agent` implementation. Its inbox is a JavaScript native-private field, and one prepared session can be claimed by only one concrete driver. Everything observable happens through session events and the `agent/*` event taxonomy. -`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. Each `ReactLoopAgent.send()` materializes content plus resolved source once as a detached, deeply frozen lossless-JSON FIFO item, shares that accepted record between `agent/queued` and the inbox, and gives the item its own ordinary turn after preceding checkpoints; malformed data throws before either boundary. Running `steer()` uses the same acceptance boundary but joins the active turn. +`Inbox`, `runLoop`, and the instance-bound publication/start controls are package-internal. The package root does not export them, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than constructing or starting the driver internals. Each `ReactLoopAgent.send()` materializes content plus resolved source once as a detached, deeply frozen lossless-JSON FIFO item and shares that accepted record between `agent/queued` and the inbox. If claimed, the item becomes the sole ordinary message in a turn after preceding checkpoints settle; cancellation, disposal, or a pre-start failure can drop it first. Malformed data throws before either acceptance boundary. Running `steer()` uses the same boundary but joins the active turn. ### Loop lifecycle (`loop.ts`) diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 8e86700835..e56eb8cf94 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -41,7 +41,7 @@ Turn and step boundaries and the model token stream are durable `session/event` The handle every plugin programs against: -- `agent.send(content, options?)` — queue one independent FIFO item. Unless broad cancellation or disposal clears it before turn start, that item becomes the sole ordinary message in its turn; the next item waits for the preceding turn's durability checkpoint. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). +- `agent.send(content, options?)` — queue one independent FIFO item. If claimed, that item becomes the sole ordinary message in its turn after the preceding checkpoint settles; broad cancellation, disposal, or a pre-start failure may instead drop it without a turn. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). - `agent.steer(content, options?)` — steer a running turn (inject between steps); uses the same owned acceptance boundary and behaves like `send` when idle - `agent.inject(content, options?)` — inject in-session context (`context/message` event); the next request sees it. `options.envelope` defaults to the canonical `` framing and may be `'raw'` when the caller owns a complete familiar frame; `options.meta` persists opaque JSON state without rendering it. Does not run the model. While a turn is open it joins that turn; while idle it is wrapped in a one-shot `injection` turn so every event stays turn-enclosed ([the turn-enclosure invariant](../../../docs/rfc/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)) - `agent.cancel(reason?)` — cancel ALL pending work: clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window) so a queued-but-not-started prompt never runs. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op. From 915c727e14ceeb0b3bcbc696ca779d399c555fce Mon Sep 17 00:00:00 2001 From: pku-xht Date: Fri, 17 Jul 2026 17:38:39 +0800 Subject: [PATCH 164/323] review fix: distinguish checkpoint settlement --- docs/core-data-structures/persistence.md | 2 +- docs/persistence-catalog.md | 2 +- .../2026-07-17-one-send-one-turn.i18n.yaml | 2 +- .../2026-07-17-one-send-one-turn.zh.md | 12 ++++++------ packages/core/agent-loop/tests/properties.spec.ts | 4 ++-- packages/core/session/src/types.ts | 4 ++-- 6 files changed, 13 insertions(+), 13 deletions(-) diff --git a/docs/core-data-structures/persistence.md b/docs/core-data-structures/persistence.md index 7bf102924b..3ae22d05d1 100644 --- a/docs/core-data-structures/persistence.md +++ b/docs/core-data-structures/persistence.md @@ -6,7 +6,7 @@ The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06 ## The flush checkpoint -`session/event` is a *synchronous* notification; persistence plugins buffer it (write-behind) and drain at the awaited `session/flush` checkpoint the loop fires at every turn end. Flush is `ctx.parallel` (awaited): a turn's events are durably committed before the next turn starts, and the turn boundary is the commit boundary. A rejecting flush is reported via `agent/error` and the logger — never as a session event (it would land past the commit boundary), so the backend keeps its buffered events for the next flush. +`session/event` is a *synchronous* notification; persistence plugins buffer it (write-behind) and drain at the awaited `session/flush` checkpoint the loop fires at every turn end. The next turn waits for that checkpoint to settle. A successful flush durably commits the closed turn as one unit; a rejecting flush is reported via `agent/error` and the logger — never as a session event (it would land past the closed turn) — and does not prevent the next turn, while the backend keeps its buffered events for the next flush. ## Crash recovery preserves an interrupted turn diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 6c48285d99..9678d25594 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -293,7 +293,7 @@ Source: [`packages/core/session/src/types.ts:276`](../packages/core/session/src/ #### `turn/end` — log-only -Closes turn `turn` with the TurnEndReason that ended it. The loop fires the awaited `session/flush` checkpoint at every turn end, so the turn boundary is also the durable-commit boundary. +Closes turn `turn` with the TurnEndReason that ended it. The loop fires the awaited `session/flush` checkpoint at every turn end; the next turn waits for settlement. Success commits the closed turn; rejection is reported live and does not prevent later work. ```ts persistence-catalog 'turn/end': { turn: number; reason: TurnEndReason } diff --git a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml index 1d3181bb0a..2d926e45c3 100644 --- a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write 2026-07-17-one-send-one-turn.md: 232e91b1d13ed07f230ffc2d0a190adafb29c6e2 -2026-07-17-one-send-one-turn.zh.md: b4dc8d37a0dc03a8aae1abfab4c9d473c7afd332 +2026-07-17-one-send-one-turn.zh.md: c533e0fa35a73056b2bb5ae6ca8a53e5757c55cf diff --git a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md index b4dc8d37a0..c533e0fa35 100644 --- a/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md +++ b/docs/rfc/implemented/simplification/2026-07-17-one-send-one-turn.zh.md @@ -8,17 +8,17 @@ Status: implemented 每次普通 `Agent.send()` 接受的载荷都是一条完整的调用方消息。如果机会式地把所有待处理载荷放入同一个轮次，相邻调用是否共享边界就会取决于驱动器的运行时机：即使调用方使用相同 API，来自同一个同步调用栈、相邻微任务、事件监听器和模型回调的调用也可能产生不同分组。 -轮次拥有提示词准入、`turn/start`、`turn/end` 和持久性检查点。合并消息会让后一条消息加入前一条消息的模型请求，无法观察前一轮次关闭后写入同一会话日志的结果；获准与被阻止提示词的混合还会引入调用方从未显式请求的生命周期状态。 +轮次拥有提示词准入、`turn/start`、`turn/end` 和持久性检查点。合并消息会让后一条消息加入前一条消息的模型请求，无法观察同一会话日志中前一个已关闭轮次的结果；获准与被阻止提示词的混合还会引入调用方从未显式请求的生命周期状态。 `steer()` 已经用于表达加入当前轮次，`inject()` 则记录面向模型的上下文而不充当普通消息。隐式批处理会让 `send()` 与这两种显式操作产生语义重叠，无法保持单一含义。 ## 决策 -每次成功的 `send()` 都会同步校验 agent（智能体）状态、创建并冻结内容快照、追加一个独立的 FIFO 队列项，然后发布 `agent/queued`。agent loop（智能体循环）在每个轮次开始时最多取出一个普通队列项。如果两个队列项最终都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点处理结束后开始；广义取消、dispose（资源释放）或启动前失败可以丢弃尚未启动的队列项，而不创建空轮次。 +每次成功的 `send()` 都会同步校验 agent（智能体）状态、创建并冻结内容快照、追加一个独立的 FIFO 队列项，然后发布 `agent/queued`。agent loop 在每个轮次开始时最多取出一个普通队列项。如果两个队列项最终都被认领，第二个轮次只能在第一个轮次结束且其持久性检查点处理结束后开始；广义取消、dispose（资源释放）或启动前失败可以丢弃尚未启动的队列项，而不创建空轮次。 提示词准入只处理一条消息。获准提示词成为该轮次的 `user/message`；被阻止提示词追加一条持久的 `prompt/blocked`，并让这个单消息轮次以 `rejected` 结束。实现中没有混合批次或全阻止批次分支。 -运行中的 `steer()` 会把消息追加到当前轮次的 steering（中途引导） FIFO。空闲时的 `steer()` 委托给 `send()`，因此创建一个独立的普通队列项。`inject()` 保持现有的轮次封闭与持久化刷新行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个智能体的操作，不变成逐消息控制。 +运行中的 `steer()` 会把消息追加到当前轮次的 steering（中途引导） FIFO。空闲时的 `steer()` 委托给 `send()`，因此创建一个独立的普通队列项。`inject()` 保持现有的轮次封闭与持久化刷新行为。`cancel()`、`status` 和 `whenIdle()` 仍是面向整个 agent 的操作，不变成逐消息控制。 ## 曾考虑的替代方案 @@ -28,11 +28,11 @@ Status: implemented - 单元与性质覆盖固定了同一调用栈、相邻微任务、不同来源和重入 `send()` 的行为：每个轮次只有一条消息，并按 FIFO 排序。 - 延迟第一个轮次的持久化刷新可以证明下一个排队轮次不能在检查点处理结束前开始，且其请求能看到前一条助手结果；刷新即使失败，下一轮次也要等它结束后才会开始。 -- 提示词否决、监听器失败、广义取消、资源释放和 `turn/start` 提交前失败都会保持已记录轮次边界平衡，不会合并消息或让仍应处理的排队工作滞留。 -- 运行中与空闲时的 `steer()`、`inject()`、面向整个智能体的状态和 `whenIdle()` 保持原有覆盖。 +- 提示词否决、监听器失败、广义取消、dispose 和 `turn/start` 提交前失败都会保持已记录轮次边界平衡，不会合并消息或让仍应处理的排队工作滞留。 +- 运行中与空闲时的 `steer()`、`inject()`、面向整个 agent 的状态和 `whenIdle()` 保持原有覆盖。 ## 后果 -普通轮次边界是确定的，被认领的 FIFO 后继项会在前一轮次关闭且其检查点处理结束后观察会话中的结果；检查点处理结束不表示失败的持久化刷新已经成功。多个排队项仍可在同一个全局 `running` 区间内执行，广义取消也可以丢弃整个未启动队尾，因此状态和静止性仍是面向整个智能体的观察，而不是逐消息结果。 +普通轮次边界是确定的，被认领的 FIFO 后继项会在前一轮次关闭且其检查点处理结束后观察会话中的结果；检查点处理结束不表示失败的持久化刷新已经成功。多个排队项仍可在同一个全局 `running` 区间内执行，广义取消也可以丢弃整个未启动队尾，因此状态和静止性仍是面向整个 agent 的观察，而不是逐消息结果。 依赖偶然批处理的工作负载会产生更多模型请求和检查点，队列清空时间也可能延长；持续有消息进入时，FIFO 队列还可能增长。只有建立显式且经过测量的契约后，才能重新引入吞吐量优化。 diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 82b103d664..1dd1a0c127 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -114,7 +114,7 @@ describe('agent loop scheduling properties', () => { // No message lost: every send appears as a user/message, in order. expect(userMessageTexts(agent)).toEqual(texts) - // Every successful send owns an independent turn even before the driver wakes. + // This failure-free fixture claims every item into an independent turn. expect(turnNumbers(agent)).toEqual(texts.map((_, i) => i + 1)) expect(turnEndNumbers(agent)).toEqual(texts.map((_, i) => i + 1)) expect(userMessageCountsByTurn(agent)).toEqual(texts.map(() => 1)) @@ -172,7 +172,7 @@ describe('agent loop scheduling properties', () => { // No message is lost or reordered, regardless of driver timing. expect(userMessageTexts(agent)).toEqual(steps.map(s => s.text)) - // Every send owns exactly one turn, numbered in FIFO order. + // Every item is claimed and therefore owns one FIFO-ordered turn. const turns = turnNumbers(agent) expect(turns).toEqual(steps.map((_, i) => i + 1)) expect(turnEndNumbers(agent)).toEqual(turns) diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index f9de8962ac..dfc8a57fcd 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -221,8 +221,8 @@ export interface SessionEventMap { 'turn/start': { turn: number; trigger: TurnTrigger } /** * Closes turn `turn` with the {@link TurnEndReason} that ended it. The loop - * fires the awaited `session/flush` checkpoint at every turn end, so the turn - * boundary is also the durable-commit boundary. + * fires the awaited `session/flush` checkpoint at every turn end; the next turn waits for settlement. + * Success commits the closed turn; rejection is reported live and does not prevent later work. */ 'turn/end': { turn: number; reason: TurnEndReason } /** Opens step `step` of turn `turn` — one model call plus the tool executions it requested. */ From b50e02a2b33eae201e83b016b49aae4e50ab68ea Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Fri, 17 Jul 2026 23:33:30 +0800 Subject: [PATCH 165/323] ci: add manual pi-ai provider e2e --- .github/workflows/pi-ai-provider-e2e.yml | 77 +++++++++ .../llm/llm-pi-ai/tests/provider-apis.e2e.ts | 146 ++++++++++++++++++ vitest.e2e.config.ts | 5 +- 3 files changed, 226 insertions(+), 2 deletions(-) create mode 100644 .github/workflows/pi-ai-provider-e2e.yml create mode 100644 packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts diff --git a/.github/workflows/pi-ai-provider-e2e.yml b/.github/workflows/pi-ai-provider-e2e.yml new file mode 100644 index 0000000000..7a273c52f3 --- /dev/null +++ b/.github/workflows/pi-ai-provider-e2e.yml @@ -0,0 +1,77 @@ +name: E2E (pi-ai OpenAI and Anthropic) + +# This suite spends tokens against two external providers and is intentionally +# opt-in. It has no push, pull_request, schedule, or workflow_call trigger. +on: + workflow_dispatch: + inputs: + openai_model: + description: OpenAI model from pi-ai's installed catalog + required: true + default: gpt-5.5 + type: string + anthropic_model: + description: Anthropic model from pi-ai's installed catalog + required: true + default: claude-opus-4-8 + type: string + +permissions: + contents: read + +jobs: + e2e: + runs-on: ubuntu-latest + name: OpenAI Responses + Anthropic Messages + timeout-minutes: 20 + steps: + - uses: actions/checkout@v6 + + - uses: actions/setup-node@v6 + with: + node-version: 24 + + - name: Enable corepack (pnpm) + run: corepack enable + + - name: Resolve pnpm store path + id: pnpm-store + run: echo "path=$(pnpm store path --silent)" >> "$GITHUB_OUTPUT" + + - uses: actions/cache@v4 + with: + path: ${{ steps.pnpm-store.outputs.path }} + key: ${{ runner.os }}-node-24-pnpm-${{ hashFiles('pnpm-lock.yaml') }} + restore-keys: | + ${{ runner.os }}-node-24-pnpm- + + - name: Install (immutable) + run: pnpm install --frozen-lockfile + + # The tests self-skip locally when a credential is absent. A manually + # dispatched CI run must fail instead of reporting an all-skipped green. + - name: Preflight (require provider API keys) + env: + OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY_EXTERNAL }} + ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }} + run: | + set -euo pipefail + missing=0 + for name in OPENAI_API_KEY ANTHROPIC_API_KEY; do + if [ -z "${!name:-}" ]; then + echo "::error::${name} is empty. Configure the corresponding *_EXTERNAL repository secret." + missing=1 + fi + done + exit "$missing" + + - name: E2E tests (real OpenAI and Anthropic APIs) + env: + OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY_EXTERNAL }} + ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }} + DSH_PI_AI_OPENAI_MODEL: ${{ inputs.openai_model }} + DSH_PI_AI_ANTHROPIC_MODEL: ${{ inputs.anthropic_model }} + DSH_E2E_MAX_WORKERS: 2 + run: >- + pnpm exec vitest run --config vitest.e2e.config.ts + packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts diff --git a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts new file mode 100644 index 0000000000..7fffba4618 --- /dev/null +++ b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts @@ -0,0 +1,146 @@ +import { afterEach, describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import LlmService, { CallId } from '@deepseek-ai/dsh-llm' +import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' +import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' +import type { PiAiReplayState } from '@deepseek-ai/dsh-llm-pi-ai' +import { assemble, type AssembledResult } from './assemble.ts' + +interface ProviderCase { + provider: 'openai' | 'anthropic' + api: 'openai-responses' | 'anthropic-messages' + model: string + apiKey?: string +} + +const providerCases: ProviderCase[] = [ + { + provider: 'openai', + api: 'openai-responses', + model: process.env.DSH_PI_AI_OPENAI_MODEL ?? 'gpt-5.5', + ...process.env.OPENAI_API_KEY ? { apiKey: process.env.OPENAI_API_KEY } : {}, + }, + { + provider: 'anthropic', + api: 'anthropic-messages', + model: process.env.DSH_PI_AI_ANTHROPIC_MODEL ?? 'claude-opus-4-8', + ...process.env.ANTHROPIC_API_KEY ? { apiKey: process.env.ANTHROPIC_API_KEY } : {}, + }, +] + +const contexts: Context[] = [] + +async function harness(): Promise { + const ctx = new Context() + contexts.push(ctx) + await ctx.plugin(LlmService) + await ctx.plugin(LlmPiAi, { + providers: providerCases.map(profile => ({ + provider: profile.provider, + ...profile.apiKey === undefined ? {} : { apiKey: profile.apiKey }, + })), + }) + return ctx +} + +afterEach(async () => { + await Promise.all(contexts.splice(0).map(ctx => ctx.fiber.dispose())) +}) + +function ask(text: string): Message[] { + return [{ role: 'user', content: [{ type: 'text', text }] }] +} + +function textOf(result: AssembledResult): string { + return result.message.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') +} + +function expectNativeReplay(result: AssembledResult, profile: ProviderCase): PiAiReplayState { + const replayState = result.message.provenance?.replayState + expect(replayState).toMatchObject({ + kind: 'pi-ai', + version: 1, + api: profile.api, + provider: profile.provider, + model: profile.model, + }) + return replayState as PiAiReplayState +} + +const lookupTool: ToolSchema = { + name: 'lookup_code', + description: 'Look up the word represented by a short code.', + parameters: { + type: 'object', + properties: { code: { type: 'string', description: 'The code to look up.' } }, + required: ['code'], + }, +} + +for (const profile of providerCases) { + describe.skipIf(profile.apiKey === undefined)( + `llm-pi-ai ${profile.provider} e2e (${profile.api})`, + () => { + it('streams text with usage and native replay metadata', async () => { + const ctx = await harness() + const result = await assemble(ctx, { + provider: profile.provider, + model: profile.model, + messages: ask('Reply with exactly the word: pong'), + maxTokens: 64, + }) + + expect(result.finish.kind).toBe('stop') + expect(textOf(result).toLowerCase()).toContain('pong') + expect(result.usage?.inputTokens).toBeGreaterThan(0) + expect(result.usage?.outputTokens).toBeGreaterThan(0) + expect(expectNativeReplay(result, profile).stopReason).toBe('stop') + }) + + it('round-trips a tool call with provider-native replay metadata', async () => { + const ctx = await harness() + const prompt = ask('Use lookup_code with code "blue". Do not answer without calling the tool.') + const first = await assemble(ctx, { + provider: profile.provider, + model: profile.model, + messages: prompt, + tools: [lookupTool], + maxTokens: 256, + }) + + expect(first.finish.kind).toBe('tool-calls') + const call = first.message.content.find(block => block.type === 'tool-call') + expect(call).toBeDefined() + expect(call!.name).toBe('lookup_code') + expect(JSON.parse(call!.arguments)).toMatchObject({ code: 'blue' }) + expect(expectNativeReplay(first, profile).stopReason).toBe('toolUse') + + const second = await assemble(ctx, { + provider: profile.provider, + model: profile.model, + messages: [ + ...prompt, + first.message, + { + role: 'user', + content: [{ + type: 'tool-result', + toolCallId: CallId(call!.id), + content: [{ type: 'text', text: 'The code blue means ocean.' }], + }], + }, + ], + tools: [lookupTool], + maxTokens: 256, + }) + + expect(second.finish.kind).toBe('stop') + expect(textOf(second).toLowerCase()).toContain('ocean') + expect(expectNativeReplay(second, profile).stopReason).toBe('stop') + }) + }, + ) +} diff --git a/vitest.e2e.config.ts b/vitest.e2e.config.ts index adc8b3f3b2..6a84b13daf 100644 --- a/vitest.e2e.config.ts +++ b/vitest.e2e.config.ts @@ -2,8 +2,9 @@ import tsconfigPaths from 'vite-tsconfig-paths' import { defineConfig } from 'vitest/config' // Real-API suite, separate because it spends tokens. Each test self-skips without -// DEEPSEEK_API_KEY for keyless CI; the credentialed workflow preflights the secret. Values may come -// from the environment or gitignored root `.env`, with optional DEEPSEEK_BASE_URL. +// its provider credential for keyless CI; credentialed workflows preflight the +// secrets they require. Values may come from the environment or gitignored root +// `.env`, with provider-specific endpoint overrides where supported. try { // Node >= 21.7 native; throws when the file does not exist. process.loadEnvFile(new URL('.env', import.meta.url).pathname) From 9a25e44fbb4c192ad1912fa504d9b71e19820f36 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 12:54:45 +0800 Subject: [PATCH 166/323] test(agent-spine-demo): wait for exact agent identity --- .../examples/agent-spine-demo/tests/agent-core.spec.ts | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts index 6081fff1a1..fb74e11b7d 100644 --- a/packages/examples/agent-spine-demo/tests/agent-core.spec.ts +++ b/packages/examples/agent-spine-demo/tests/agent-core.spec.ts @@ -86,10 +86,10 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { } } -function waitForMainIdle(ctx: Context): Promise { +function waitForIdle(ctx: Context, target: Agent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (agent, status) => { - if (agent.id === 'main' && status === 'idle') { + if (agent === target && status === 'idle') { dispose() resolve() } @@ -177,7 +177,7 @@ describe('dsh-agent-spine-demo bundle', () => { const agent = handle.agent agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, agent) const sentText = adapter.requests[0]?.messages.map(messageText).join('\n') expect(sentText).toContain('hi') @@ -206,7 +206,7 @@ describe('dsh-agent-spine-demo bundle', () => { }) handle.agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, handle.agent) expect(adapter.requests[0]?.messages).toEqual([{ role: 'user', content: [{ type: 'text', text: 'hi' }] }]) await handle.dispose() @@ -295,7 +295,7 @@ describe('dsh-agent-spine-demo bundle', () => { }) handle.agent.send([{ type: 'text', text: 'hi' }]) - await waitForMainIdle(ctx) + await waitForIdle(ctx, handle.agent) expect(messageText(adapter.requests[0]?.messages[0])).toContain('workspace rule before skills') expect(messageText(adapter.requests[0]?.messages[1])).toContain('prefix-order-skill') From e846a115f29fd4fdfe7d6fc7ac303688a093a715 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 13:51:44 +0800 Subject: [PATCH 167/323] test(acp-snapshot): cover pre-spawn launch failure --- .../support/acp-snapshot/tests/harness.spec.ts | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 3436f32f96..2b9d6e032f 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -244,6 +244,23 @@ describe('runScenario', () => { )).rejects.toThrow(/agent stderr:\nfake agent requested startup failure/) }) + it('preserves launch-resolution errors when no child process exists', async () => { + const { dir, fixtureFile } = await scenario({}) + vi.stubEnv('DSH_EXAMPLE_MODE', 'lib') + try { + await expect(runScenario( + { steps: [] }, + { + agent: { ...AGENT, binScript: join(dir, 'outside-src.ts'), libBinScript: undefined }, + mode: 'replay', + fixtureFile, + }, + )).rejects.toThrow(/expected a "\/src\/" segment/) + } finally { + vi.unstubAllEnvs() + } + }) + it('drives a full turn: initialize (terminal caps), session, prompt, permission stub, harvest', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ permissionProbe: true, From 1815095579a28d5eb46ba7329f508d31b3a79d56 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 13:54:24 +0800 Subject: [PATCH 168/323] docs(api): refresh compact reference --- website/zh-CN/api/harness/compact.md | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/website/zh-CN/api/harness/compact.md b/website/zh-CN/api/harness/compact.md index 8be3b4287a..67f17cc941 100644 --- a/website/zh-CN/api/harness/compact.md +++ b/website/zh-CN/api/harness/compact.md @@ -25,20 +25,19 @@ Check token pressure and compact if the conversation is too large. Estimate the [Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L58) -### ctx.compact.compactRegion(session, start, end, agent, signal?) +### ctx.compact.compactRegion(start, end, agent, signal?) ```ts website-api -abstract compactRegion( session: Session, start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise +abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` -Forcibly compact a range of surface nodes into a single summary node. `start` and `end` name an inclusive span by surface position, not numeric seq order; replacements can make visible seqs non-monotonic. Both edges must be balanced so assistant tool calls remain paired with their results. A model- backed implementation forwards cancellation. The agent must own the exact target session object; implementations reject an ownership mismatch before model resolution, lock acquisition, summarization, or log mutation, and reject active, missing, reversed, or unbalanced ranges. Use toolPairingBalancedBefore and toolPairingBalancedAfter for the edge checks. +Forcibly compact a range of surface nodes into a single summary node. `start` and `end` name an inclusive span by surface position, not numeric seq order; replacements can make visible seqs non-monotonic. Both edges must be balanced so assistant tool calls remain paired with their results. A model- backed implementation forwards cancellation and rejects active, missing, reversed, or unbalanced ranges. The target session is `agent.session`. Use toolPairingBalancedBefore and toolPairingBalancedAfter for the edge checks. -- `session` — session to mutate; must be identical to `agent.session`. - `start` — first surface seq, inclusive. - `end` — last surface seq, inclusive. -- `agent` — owner of the target session and summarizer context. +- `agent` — context whose session is mutated and whose routing options guide summarization. - `signal` — optional cancellation; model-backed implementations must forward it. -**Returns** the replaced range and summary. +**Returns** the appended event seqs, summary, replaced range, and token accounting. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L85) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/compact/compact/src/index.ts#L82) From 9d0066440311c928a23e925fcdc34ba9da5bd184 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 13:54:48 +0800 Subject: [PATCH 169/323] docs(api): refresh agent reference --- website/zh-CN/api/harness/agents.md | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index f6c9565d37..ef20c585d7 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -20,7 +20,7 @@ Register the effect-scoped creation factory, rejecting a duplicate. Service fact **Returns** the exact Cordis effect disposer. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L152) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L149) ### ctx.agents.create(options) @@ -34,7 +34,7 @@ Create and publish an owned agent and session through the active factory. Reject **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L177) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L174) ### ctx.agents.resume(options) @@ -48,7 +48,7 @@ Load a persisted session and resume an agent on it through the registered factor **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L193) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L190) ### ctx.agents.register(agent) @@ -62,7 +62,7 @@ Register a live agent in the calling effect scope, with scope-filtered creation **Returns** the exact Cordis effect disposer for nested teardown ordering. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L207) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L204) ### ctx.agents.enter(agent) @@ -76,7 +76,7 @@ Insert an unpublished agent for an ordered factory transaction. **Returns** an idempotent closure that removes this exact entry and emits the paired disposal edge; detachment during creation dispatch is deferred. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L222) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L219) ### ctx.agents.announce(agent) @@ -88,7 +88,7 @@ Announce an agent previously inserted with enter. - `agent` — the live inserted agent to announce. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L290) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L286) ### ctx.agents.get(id) @@ -102,7 +102,7 @@ Look up a live agent. **Returns** the agent, or undefined when no live agent has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L324) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L320) ### ctx.agents.list() @@ -114,4 +114,4 @@ All live agents, in registration order. **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L332) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L328) From 0f85ae0a9df15ad0a356087715afebba12ff41b4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:26:14 +0800 Subject: [PATCH 170/323] fix(subagent): identify lifecycle runs explicitly --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 8 +- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/subagent.md | 5 +- docs/event-producer-consumer.md | 8 +- docs/module-graph.md | 3 +- .../cordis/tool-cordis/src/api-catalog.ts | 2 +- .../hooks/hooks-claude/tests/bridge.spec.ts | 7 +- .../hooks-claude/tests/coverage-cases.ts | 9 +- packages/subagent/subagent-acp/src/run.ts | 1 + .../subagent/subagent-inprocess/src/index.ts | 1 + packages/subagent/subagent/README.md | 4 +- packages/subagent/subagent/package.json | 2 + packages/subagent/subagent/src/index.ts | 25 +++- packages/subagent/subagent/src/types.ts | 19 +++ .../subagent/subagent/tests/service.spec.ts | 25 +++- .../tool-subagent/tests/tool-subagent.spec.ts | 15 ++ packages/support/subagent-mock/src/index.ts | 1 + packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 45 +----- .../jsonrpc/tests/built-scope-carrier.e2e.ts | 1 + packages/ui/jsonrpc/tests/server.spec.ts | 130 ++++++++++++++++-- .../tests/workflow-workerthread.spec.ts | 8 ++ pnpm-lock.yaml | 3 + website/zh-CN/api/harness/events.md | 8 +- website/zh-CN/api/harness/subagents.md | 10 +- 26 files changed, 253 insertions(+), 93 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a0cbac6789..f07dfcf18a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -918,7 +918,7 @@ export interface Config { Depends on: [`SubagentCapabilities`](../packages/subagent/subagent/src/index.ts) · [`SubagentStopReason`](../packages/subagent/subagent/src/index.ts) -Source: [`packages/support/subagent-mock/src/index.ts:86`](../packages/support/subagent-mock/src/index.ts) +Source: [`packages/support/subagent-mock/src/index.ts:87`](../packages/support/subagent-mock/src/index.ts) ## `@deepseek-ai/dsh-subagent-spawn` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 820a453ceb..d0ff7002b0 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -301,7 +301,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:109`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -311,7 +311,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` -Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -321,7 +321,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:89`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -331,7 +331,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:100`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 52f9cdf131..ee953e37c7 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -264,7 +264,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:142`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:153`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 18cb22c32d..815438f215 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -69,6 +69,7 @@ interface SubagentStopReasonMap { ```ts type-equiv interface SubagentRun { readonly id: SessionId + readonly localAgent: Agent | undefined readonly result: Promise dispose(): Promise sendMessage?(content: ContentBlock[]): void @@ -76,7 +77,7 @@ interface SubagentRun { } ``` -A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope; `parentSession` is the durable transport-neutral lineage. A remote provider instead returns a parent-scoped lifecycle id and does not publish a local child. +A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, expose the exact child as `localAgent`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope. A remote provider instead returns a parent-scoped lifecycle id and `localAgent: undefined`. ## The provider seam: `SubagentProvider` @@ -91,7 +92,7 @@ interface SubagentProvider { } ``` -`start()` fulfills only with a ready run. The service observes its result, emits `subagent/start`, and returns the same run; rejection implies provider cleanup and emits no lifecycle pair. In-process children are discoverable through `ctx.agents`, while remote children need not be. `subagent/end` reports final output or infrastructure failure. Both events are observe-only and contain listener exceptions. +`start()` fulfills only with a ready run. The service mints a unique `runId`, snapshots `local` from the provider's exact `localAgent`, observes the result, emits `subagent/start`, and returns the same run; rejection implies provider cleanup and emits no lifecycle pair. The paired `subagent/end` carries the same identity and the final output or infrastructure failure. Both events are observe-only and contain listener exceptions. ## In-process backends: depth and seed diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 6d75d54f3d..49e8d778cf 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -30,10 +30,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:109`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:89`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:100`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:112`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:86`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:103`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`acp`](../packages/ui/acp) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 604aa7cf7f..f49092f99d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -279,6 +279,7 @@ flowchart TD pkg_tool_skill --> pkg_skill pkg_tool_skill --> pkg_tools pkg_subagent --> pkg_agent + pkg_subagent --> pkg_brand pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope pkg_subagent --> pkg_session @@ -493,7 +494,7 @@ flowchart TD | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`spill-policy`](../packages/spill/spill-policy) | `spill` | [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`tools`](../packages/core/tools) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 71640498c9..ed5c0babe9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -1028,7 +1028,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SubagentRun', - declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', + declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly localAgent: Agent | undefined;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', }, { name: 'SubagentStartRequest', diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 136ee893c6..7bb4c0b4ea 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -9,6 +9,7 @@ import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import { SubagentRunId } from '@deepseek-ai/dsh-subagent' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -288,8 +289,8 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => // Drive the observe-only lifecycle events directly (no real child needed — the // bridge just listens). No child agent is registered, so SubagentStart's // child lookup yields undefined and it simply runs the hook. - ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) - ctx.emit('subagent/end', { provider: 'inproc', id: SessionId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) // Both hooks run async (detached .then); poll for their marker files rather // than a fixed sleep that flakes under load. @@ -324,7 +325,7 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false }) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await hooks.dispose() diff --git a/packages/hooks/hooks-claude/tests/coverage-cases.ts b/packages/hooks/hooks-claude/tests/coverage-cases.ts index 9d4004c1ff..0431486d57 100644 --- a/packages/hooks/hooks-claude/tests/coverage-cases.ts +++ b/packages/hooks/hooks-claude/tests/coverage-cases.ts @@ -9,6 +9,7 @@ import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import { SubagentRunId } from '@deepseek-ai/dsh-subagent' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -231,7 +232,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const injected: string[] = [] const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { id: SessionId('child-x'), header: { id: 'child-x' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-x'), provider: 'p', id: SessionId('child-x'), local: true }) await waitFor(() => injected.includes('child guidance')) expect(injected).toContain('child guidance') }) @@ -247,7 +248,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const warn = vi.fn(); ctx.logger.warn = warn as never const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { id: SessionId('child-y'), header: { id: 'child-y' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-y'), provider: 'p', id: SessionId('child-y'), local: true }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) @@ -291,7 +292,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: SessionId('child-z'), stopReason: 'completed' }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-z'), provider: 'p', id: SessionId('child-z'), local: false, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) }) @@ -691,7 +692,7 @@ export function defineCoverageCases(group: CoverageGroup): void { // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') const childHandle = await ctx.agents.create({ sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { provider: 'mock', model: 'mock' } }) - ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-stop'), provider: 'inproc', id: childHandle.agent.id, local: true, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) // the marker landed in the CHILD dir diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index b7b10ecb97..a10a87a940 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -294,6 +294,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { id, + localAgent: undefined, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 018f93051f..c5c85ec232 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -175,6 +175,7 @@ export async function startInProcessRun( return { id: childId, + localAgent: child, result, dispose(): Promise { request.signal.removeEventListener('abort', onAbort) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 45e0976ed7..17edd0e3c7 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -50,9 +50,9 @@ Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a `SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for the child resources to quiesce. -A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, and records `request.parent.session.id` in the child's `parentSession` header. The child may be owned by the parent scope or by a provider/root scope; durable lineage is the transport-neutral local-child relation. Remote providers instead mint a parent-scoped lifecycle id without publishing a local child. +A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, exposes the exact child as `SubagentRun.localAgent`, and records `request.parent.session.id` in the child's `parentSession` header. Remote providers instead mint a parent-scoped lifecycle id and return `localAgent: undefined`. -The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. In-process start observers can resolve the published child through `ctx.agents.get(info.id)`; remote providers need not publish a local agent. +The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. The pair shares a service-minted `runId`; its `local` flag is snapshotted from the provider's exact `localAgent`, so observers never infer run identity or locality from reusable provider/session names. Run events are scoped to the delegating parent. Every listener is independently contained: a synchronous throw or rejected returned promise is logged without starving peer listeners or changing the run. diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index 84d2c963d5..aea05553e4 100644 --- a/packages/subagent/subagent/package.json +++ b/packages/subagent/subagent/package.json @@ -23,6 +23,7 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -31,6 +32,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 00762cc413..8f3549ac7c 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -28,6 +28,7 @@ * @module @deepseek-ai/dsh-subagent */ +import { randomUUID } from 'node:crypto' import { Context, Service } from 'cordis' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' @@ -43,7 +44,9 @@ import type { SubagentRun, SubagentStartRequest, } from './types.ts' +import { SubagentRunId } from './types.ts' +export { SubagentRunId } from './types.ts' export type { SubagentCapabilities, SubagentProvider, @@ -112,18 +115,26 @@ declare module 'cordis' { /** Observe-only identifying detail for a ready subagent run. */ export interface SubagentRunInfo { + /** Unique identity shared with the paired terminal event. */ + readonly runId: SubagentRunId /** The provider that established the run. */ readonly provider: string /** The child agent's id. */ readonly id: SessionId + /** Whether the provider exposed an exact published in-process child. */ + readonly local: boolean } /** Observe-only outcome detail for a settled subagent run. */ export interface SubagentRunEndInfo { + /** Unique identity shared with the paired start event. */ + readonly runId: SubagentRunId /** The provider that ran it. */ readonly provider: string /** The child agent's id. */ readonly id: SessionId + /** Whether the provider exposed an exact published in-process child. */ + readonly local: boolean /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] /** The child's final assistant output, absent on infrastructure rejection. */ @@ -208,22 +219,28 @@ export class SubagentService extends Service { const parent = request.parent const run = await provider.start(request) + const runId = SubagentRunId(randomUUID()) + const lifecycleIdentity = { + runId, + provider: name, + id: run.id, + local: run.localAgent !== undefined, + } // Attach the terminal observer before dispatching start. Promise reactions // still run after this synchronous start emission, preserving start → end. void run.result.then( (result) => { this.emitLifecycle('subagent/end', { - provider: name, - id: run.id, + ...lifecycleIdentity, stopReason: result.stopReason, lastAssistantMessage: result.output, }, parent) }, () => { - this.emitLifecycle('subagent/end', { provider: name, id: run.id, stopReason: 'error' }, parent) + this.emitLifecycle('subagent/end', { ...lifecycleIdentity, stopReason: 'error' }, parent) }, ) - this.emitLifecycle('subagent/start', { provider: name, id: run.id }, parent) + this.emitLifecycle('subagent/start', lifecycleIdentity, parent) return run } diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index e5ba8fd84d..1b1645d89b 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -7,10 +7,23 @@ */ import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Branded } from '@deepseek-ai/dsh-brand' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { SessionId } from '@deepseek-ai/dsh-session' import type { StructuredOutputSchema, ToolRestriction } from '@deepseek-ai/dsh-tools' +/** Identifies one accepted subagent run across its lifecycle event pair. */ +export type SubagentRunId = Branded<'SubagentRunId'> + +/** + * Brand a string as a {@link SubagentRunId}. + * @param id - the raw id string (the service mints UUIDs; tests may pass fixtures). + * @returns the same string, branded. + */ +export function SubagentRunId(id: string): SubagentRunId { + return id as SubagentRunId +} + /** * Which START-TIME features a provider supports. Checked by the service before delegating to * {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks @@ -139,6 +152,12 @@ export interface SubagentRun { * remote provider mints an id unique in the parent namespace. */ readonly id: SessionId + /** + * The exact published in-process child, or `undefined` for a remote run. + * When present, its id is {@link id}; the provider retains no ownership + * implication beyond the run's ordinary {@link dispose} contract. + */ + readonly localAgent: Agent | undefined /** * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport diff --git a/packages/subagent/subagent/tests/service.spec.ts b/packages/subagent/subagent/tests/service.spec.ts index ad7dbaafff..66008a923b 100644 --- a/packages/subagent/subagent/tests/service.spec.ts +++ b/packages/subagent/subagent/tests/service.spec.ts @@ -48,6 +48,7 @@ class StubProvider implements SubagentProvider { this.startCount += 1 return { id: SessionId(`child:${this.name}:${request.parent.id}`), + localAgent: undefined, result: Promise.resolve(this.outcome), async dispose() {}, } @@ -137,13 +138,14 @@ describe('SubagentService', () => { const parent = fakeParent('delegator') const events: string[] = [] const keys: unknown[] = [] - ctx.on('subagent/start', function () { events.push('start'); keys.push(carrierKeyOf(this)) }) - ctx.on('subagent/end', function () { events.push('end'); keys.push(carrierKeyOf(this)) }) + const runIds: string[] = [] + ctx.on('subagent/start', function (info) { events.push('start'); keys.push(carrierKeyOf(this)); runIds.push(info.runId) }) + ctx.on('subagent/end', function (info) { events.push('end'); keys.push(carrierKeyOf(this)); runIds.push(info.runId) }) const starting = subagents.start('deferred', baseRequest({ parent })) await Promise.resolve() expect(events).toEqual([]) - ready.resolve({ id: SessionId('child'), result: result.promise, async dispose() {} }) + ready.resolve({ id: SessionId('child'), localAgent: undefined, result: result.promise, async dispose() {} }) const run = await starting expect(events).toEqual(['start']) result.resolve({ output: [{ type: 'text', text: 'answer' }], stopReason: 'completed' }) @@ -151,6 +153,21 @@ describe('SubagentService', () => { await Promise.resolve() expect(events).toEqual(['start', 'end']) expect(keys).toEqual([parent, parent]) + expect(runIds[0]).toBe(runIds[1]) + }) + + it('mints distinct lifecycle identities when provider and child ids repeat', async () => { + const { ctx, subagents } = await service() + subagents.registerProvider(new StubProvider('reused')) + const runIds: string[] = [] + ctx.on('subagent/start', info => void runIds.push(info.runId)) + + const first = await subagents.start('reused', baseRequest()) + const second = await subagents.start('reused', baseRequest()) + await Promise.all([first.result, second.result]) + + expect(runIds).toHaveLength(2) + expect(new Set(runIds).size).toBe(2) }) it('emits no run lifecycle when provider startup rejects', async () => { @@ -192,7 +209,7 @@ describe('SubagentService', () => { capabilities: NO_CAPS, inheritsParentContext: false, async start() { - return { id: SessionId('infra-child'), result: failure.promise, async dispose() {} } + return { id: SessionId('infra-child'), localAgent: undefined, result: failure.promise, async dispose() {} } }, }) const failedRun = await subagents.start('infra', baseRequest()) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 27a603049e..dbb78812d4 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -144,6 +144,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('weird-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }), dispose: async () => {}, }), @@ -171,6 +172,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -200,6 +202,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('bare-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -327,6 +330,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('spy-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => void disposed(), }), @@ -349,6 +353,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('spy-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'error' as const }), dispose: async () => void disposed(), }), @@ -380,6 +385,7 @@ describe('dsh-tool-subagent', () => { }, { once: true }) return { id: SessionId('spy-child'), + localAgent: undefined, result, dispose: async () => {}, } @@ -472,6 +478,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture2-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -529,6 +536,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture3-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -558,6 +566,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture4-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -732,6 +741,7 @@ describe('dsh-tool-subagent background mode', () => { }, { once: true }) return { id, + localAgent: undefined, result, dispose: () => Promise.resolve(), } @@ -771,6 +781,7 @@ describe('dsh-tool-subagent background mode', () => { const order: string[] = [] const completed = await settleRun({ id: SessionId('child-1'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text' as const, text: 'ok' }], stopReason: 'completed' as const }), dispose() { order.push('dispose'); return Promise.resolve() }, }) @@ -782,6 +793,7 @@ describe('dsh-tool-subagent background mode', () => { let disposed = false const failed = await settleRun({ id: SessionId('child-2'), + localAgent: undefined, result: Promise.reject(new Error('transport gone')), dispose() { disposed = true; return Promise.resolve() }, }) @@ -790,6 +802,7 @@ describe('dsh-tool-subagent background mode', () => { const disposeFailed = await settleRun({ id: SessionId('child-3'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'completed' }), dispose: () => Promise.reject(new Error('reap failed')), }) @@ -797,6 +810,7 @@ describe('dsh-tool-subagent background mode', () => { const bothFailed = await settleRun({ id: SessionId('child-4'), + localAgent: undefined, result: Promise.reject(new Error('result failed')), dispose: () => Promise.reject(new Error('reap failed')), }) @@ -832,6 +846,7 @@ describe('background preflight failure (no orphaned child, by construction)', () starts += 1 return { id: SessionId('probe-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'completed' as const }), dispose: () => Promise.resolve(), } diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index c2e94c521f..4ea30d166a 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -69,6 +69,7 @@ class MockSubagentProvider implements SubagentProvider { }) return { id, + localAgent: undefined, result, dispose(): Promise { flags.cancelled = true diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 6d9f007e66..3d19b601c4 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It classifies subagent completions through live parent ownership or durable parent lineage and retains parent-scoped provider/id counts after child disposal. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. +`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It forwards subagent completions only when the lifecycle payload's `local` flag was snapshotted from the provider's exact in-process child; reusable provider names, child ids, and durable lineage never establish locality. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 91cc49571a..5246795a31 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -19,7 +19,7 @@ import type { Agent, AgentHandle } from '@deepseek-ai/dsh-agent' import { carrierKeyOf, type Scoped } from '@deepseek-ai/dsh-scope' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import type SubagentService from '@deepseek-ai/dsh-subagent' -import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' +import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -68,15 +68,6 @@ function subagentParentOf(carrier: Scoped): Agent { return carrierKeyOf(carrier) as Agent } -/** Whether the live id names a local child related to this exact delegating parent. */ -function isLocalChild(ctx: Context, id: SessionId, parent: Agent): boolean { - const child = ctx.agents.get(id) - return child !== undefined && ( - ctx.agents.isOwnedBy(id, parent) - || child.session.header.parentSession === parent.session.id - ) -} - /** * The SDK server over a booted harness context. Constructing it subscribes to * session and subagent lifecycle events, forwarding durable session @@ -92,7 +83,6 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly localRuns = new Map>>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -116,36 +106,12 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // In-process providers publish the child before start. Count starts related - // by exact runtime ownership or durable parent lineage so provider-owned - // roots remain local, completions survive child disposal, and reused ids - // need no settlement-order assumption. - const localRuns = this.localRuns - this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { - const parent = subagentParentOf(this) - if (!isLocalChild(ctx, info.id, parent)) return - const providerRuns = localRuns.get(info.provider) ?? new Map>() - const parentRuns = providerRuns.get(info.id) ?? new Map() - parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) - providerRuns.set(info.id, parentRuns) - localRuns.set(info.provider, providerRuns) - })) this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { const parent = subagentParentOf(this) - const providerRuns = localRuns.get(info.provider) - const parentRuns = providerRuns?.get(info.id) - const pendingCount = parentRuns?.get(parent) - if (pendingCount !== undefined) { - if (pendingCount === 1) parentRuns?.delete(parent) - else parentRuns?.set(parent, pendingCount - 1) - if (parentRuns?.size === 0) providerRuns?.delete(info.id) - if (providerRuns?.size === 0) localRuns.delete(info.provider) - } - // This protocol reports LOCAL child sessions. A lineage-bearing child - // has the session/created-driven start notification above. A remote run - // has neither a cached local start nor a live child related to this - // parent; an unrelated local agent with the same id never makes it local. - if (pendingCount === undefined && !isLocalChild(ctx, info.id, parent)) return + // This protocol reports only in-process child sessions. The service + // snapshots the provider's exact run provenance through child disposal; + // matching ids or parent lineage alone never establishes locality. + if (!info.local) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), @@ -223,7 +189,6 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index ed4dfbb9db..54727f571b 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -71,6 +71,7 @@ try { start() { return Promise.resolve({ id: child.agent.id, + localAgent: child.agent, result: result.promise, dispose() { return Promise.resolve(); }, }); diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 3fe73c904e..5b9259dd85 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -70,7 +70,7 @@ async function makeHarness(storageDir: string) { async function settleSubagent( ctx: Context, parent: Agent, - info: SubagentRunEndInfo, + info: Omit & { localAgent: Agent | undefined }, beforeSettle?: () => Promise, ): Promise { const result = Promise.withResolvers() @@ -81,6 +81,7 @@ async function settleSubagent( async start() { return { id: info.id, + localAgent: info.localAgent, result: result.promise, dispose: () => Promise.resolve(), } @@ -294,12 +295,14 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), + localAgent: handle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }, () => handle.dispose()) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('parentless-child-session'), + localAgent: parentlessHandle.agent, stopReason: 'error', }, () => parentlessHandle.dispose()) @@ -335,7 +338,7 @@ describe('HarnessSdkServer', () => { } }) - it('ignores a remote run id that collides with an unrelated local agent', async () => { + it('ignores a remote run id that collides with a local child of the same parent', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-remote-collision-')) const ctx = await makeHarness(storageDir) try { @@ -346,24 +349,26 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const unrelatedHandle = await ctx.agents.create({ + const collidingChild = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('remote-run-id'), - meta: { cwd: storageDir }, + meta: { cwd: storageDir, parentSession: SessionId('collision-parent') }, agentOptions: { model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'remote', id: SessionId('remote-run-id'), + localAgent: undefined, stopReason: 'completed', lastAssistantMessage: [], - }, () => unrelatedHandle.dispose()) + }) expect(transport.notifications.some(notification => notification.method === 'subagent.finished' && notification.params?.agentId === 'remote-run-id', )).toBe(false) + await collidingChild.dispose() await parentHandle.dispose() await server.shutdown() } finally { @@ -392,12 +397,14 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'continuation', id: SessionId('continuation-child'), + localAgent: childHandle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'first' }], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'continuation', id: SessionId('continuation-child'), + localAgent: childHandle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'second' }], }, () => childHandle.dispose()) @@ -436,6 +443,7 @@ describe('HarnessSdkServer', () => { const replacement = Promise.withResolvers() const results = [first.promise, sameLifetime.promise, replacement.promise] let starts = 0 + let currentLocalAgent = oldChild.agent const disposeProvider = ctx.subagents.registerProvider({ name: 'reused', capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, @@ -444,7 +452,7 @@ describe('HarnessSdkServer', () => { const result = results[starts] starts += 1 if (result === undefined) throw new Error('unexpected fourth reused-id run') - return Promise.resolve({ id: SessionId('reused-child'), result, dispose: () => Promise.resolve() }) + return Promise.resolve({ id: SessionId('reused-child'), localAgent: currentLocalAgent, result, dispose: () => Promise.resolve() }) }, }) @@ -471,6 +479,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, agentOptions: { model: 'deepseek' }, }) + currentLocalAgent = newChild.agent const secondRun = await ctx.subagents.start('reused', { parent: newParent.agent, prompt: [], @@ -512,7 +521,99 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live lineage and ignores runs without a local child session', async () => { + it('keeps locality bound to the accepted run across provider re-registration', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-provider-reuse-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parent = await ctx.agents.create({ + sessionId: SessionId('provider-reuse-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const child = await parent.agent.ctx.agents.create({ + sessionId: SessionId('provider-reuse-child'), + meta: { cwd: storageDir, parentSession: SessionId('provider-reuse-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const localResult = Promise.withResolvers() + const remoteResult = Promise.withResolvers() + const unregisterLocal = ctx.subagents.registerProvider({ + name: 'reused-provider', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: () => Promise.resolve({ + id: SessionId('provider-reuse-child'), + localAgent: child.agent, + result: localResult.promise, + dispose: () => Promise.resolve(), + }), + }) + const localRun = await ctx.subagents.start('reused-provider', { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }) + unregisterLocal() + + const unregisterRemote = ctx.subagents.registerProvider({ + name: 'reused-provider', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: () => Promise.resolve({ + id: SessionId('provider-reuse-child'), + localAgent: undefined, + result: remoteResult.promise, + dispose: () => Promise.resolve(), + }), + }) + const remoteRun = await ctx.subagents.start('reused-provider', { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }) + + remoteResult.resolve({ output: [{ type: 'text', text: 'remote' }], stopReason: 'completed' }) + await remoteRun.result + await Promise.resolve() + expect(transport.notifications.some(notification => + notification.method === 'subagent.finished' + && notification.params?.lastAssistantMessage !== undefined, + )).toBe(false) + + await child.dispose() + localResult.resolve({ output: [{ type: 'text', text: 'local' }], stopReason: 'completed' }) + await localRun.result + await Promise.resolve() + expect(transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'provider-reuse-child', + )).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'reused-provider', + agentId: 'provider-reuse-child', + parentSessionId: 'provider-reuse-parent', + childSessionId: 'provider-reuse-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'local' }], + }, + }]) + + await localRun.dispose() + await remoteRun.dispose() + unregisterRemote() + await parent.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + + it('uses explicit local provenance when start was missed and ignores remote runs', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -529,6 +630,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) + const fallbackChild = handle.agent failedHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, @@ -541,12 +643,13 @@ describe('HarnessSdkServer', () => { inheritsParentContext: true, start: () => Promise.resolve({ id: SessionId('fallback-child-session'), + localAgent: fallbackChild, result: missedStartResult.promise, dispose: () => Promise.resolve(), }), }) - // Start before the server subscribes, so the terminal fallback must use - // the still-live registry entry rather than a cached start record. + // Start before the server subscribes. The terminal payload still carries + // this run's exact local child without reconstructing it from ids. const missedStartRun = await ctx.subagents.start('fork', { parent: parentHandle.agent, prompt: [], @@ -560,22 +663,25 @@ describe('HarnessSdkServer', () => { await Promise.resolve() await missedStartRun.dispose() disposeMissedStartProvider() - // The server also missed this agent's creation, but observes the start; - // recover its lineage from the still-live registry entry. + // The server also missed this agent's creation but sees the exact child + // on the run lifecycle payload. await settleSubagent(ctx, parentHandle.agent, { provider: 'fork-live-fallback', id: SessionId('fallback-child-session'), + localAgent: fallbackChild, stopReason: 'completed', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', id: SessionId('failed-child-session'), + localAgent: failedHandle.agent, stopReason: 'error', }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', id: SessionId('missing-child-agent'), + localAgent: undefined, stopReason: 'error', }) @@ -800,6 +906,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(4) + expect(on).toHaveBeenCalledTimes(3) }) }) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 5905161e6a..2f52cd7b6b 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -105,6 +105,7 @@ class StubProvider implements SubagentProvider { if (request.signal.aborted) throw new Error('child start aborted before publication') return { id: SessionId(`stub-child-${index}`), + localAgent: undefined, result: terminal.promise, dispose: () => { controlled.disposeCalls += 1 @@ -362,6 +363,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('reject-child'), + localAgent: undefined, result: Promise.reject(new Error('backend exploded')), dispose: () => Promise.resolve(), }), @@ -396,6 +398,7 @@ describe('dsh-workflow-workerthread', () => { } as unknown as SubagentResult const start = vi.spyOn(ctx.subagents, 'start').mockResolvedValue({ id: SessionId('raw-invalid-child'), + localAgent: undefined, result: Promise.resolve(invalid), dispose: () => Promise.resolve(), }) @@ -419,6 +422,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('bad-dispose-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, dispose: () => { throw new Error('dispose exploded') }, @@ -440,6 +444,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('trap-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, // The rejection VALUE's own coercion throws: a warn built with bare @@ -767,6 +772,7 @@ describe('dsh-workflow-workerthread', () => { }, { once: true }) return { id: SessionId('signal-only-child'), + localAgent: undefined, result, dispose: () => Promise.resolve(), } @@ -1088,6 +1094,7 @@ describe('dsh-workflow-workerthread', () => { ready.resolve({ id: SessionId('late-ready-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'aborted' }), dispose: () => { disposeCalls += 1 @@ -1124,6 +1131,7 @@ describe('dsh-workflow-workerthread', () => { }, { once: true }) return { id: SessionId('doomed-child'), + localAgent: undefined, result: new Promise(() => { /* never settles; the reap is the teardown */ }), dispose: () => Promise.reject(new Error('dispose exploded during reap')), } diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d7b3ab2b95..47d998fedc 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1441,6 +1441,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-brand': + specifier: workspace:^ + version: link:../../util/brand '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index aafaf28484..1301a6a508 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -383,7 +383,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c - `info` — the run identity and terminal outcome. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L109) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L112) ### subagent/provider-added @@ -397,7 +397,7 @@ A provider became resolvable in the registry. - `provider` — the registered provider. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L83) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L86) ### subagent/provider-removed @@ -411,7 +411,7 @@ A provider left the registry. Accepted runs remain holder-owned. - `name` — the provider name that no longer resolves. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L89) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L92) ### subagent/start @@ -425,7 +425,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( - `info` — the provider and ready child identity. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L100) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L103) ## system-prompt/* diff --git a/website/zh-CN/api/harness/subagents.md b/website/zh-CN/api/harness/subagents.md index 54fe5aa76e..52632e820d 100644 --- a/website/zh-CN/api/harness/subagents.md +++ b/website/zh-CN/api/harness/subagents.md @@ -6,7 +6,7 @@ Named provider registry and capability-checked start surface. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L142) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L153) ### ctx.subagents.registerProvider(provider) @@ -20,7 +20,7 @@ Register a provider under its name. Registration is effect-scoped and HMR safe; **Returns** the exact Cordis effect disposer. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L156) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L167) ### ctx.subagents.getProvider(name) @@ -34,7 +34,7 @@ Look up a provider by name. **Returns** the provider, or undefined when absent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L179) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L190) ### ctx.subagents.list() @@ -46,7 +46,7 @@ List registered provider names in insertion order. **Returns** the registered names. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L187) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L198) ### ctx.subagents.start(name, request) @@ -61,4 +61,4 @@ Establish a ready child on the named provider. Capability and semantic checks ru **Returns** the ready holder-owned run. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L200) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L211) From 1febeb8428d1c1dd4d24f812567b792d3d3f79ea Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:26:48 +0800 Subject: [PATCH 171/323] test(jsonrpc): configure built scope probe --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index 54727f571b..051b0eef20 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -43,7 +43,7 @@ const [ const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); const ctx = new Context(); try { - await ctx.plugin(agentCore); + await ctx.plugin(agentCore, { workspaceContext: false }); await ctx.plugin(SubagentService); await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); await new Promise((ready) => setTimeout(ready, 50)); From 546143048c011b30380fc135efbbde12afc8b465 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:29:29 +0800 Subject: [PATCH 172/323] docs(api): refresh llm reference --- website/zh-CN/api/harness/llm.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md index 200e926d15..a70d5bd478 100644 --- a/website/zh-CN/api/harness/llm.md +++ b/website/zh-CN/api/harness/llm.md @@ -6,7 +6,7 @@ The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L96) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L94) ### ctx.llm.registerAdapter(providers, adapter) @@ -21,7 +21,7 @@ Register an adapter for the given provider routes. Throws `LlmError` with code ` **Returns** the disposer that unregisters all of them. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L111) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L109) ### ctx.llm.listProviders() @@ -33,7 +33,7 @@ Describe provider routes with a registered adapter. **Returns** detached provider metadata in registration order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L142) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L140) ### ctx.llm.listModels(provider) @@ -47,7 +47,7 @@ Discover models advertised by one registered provider. Catalog membership is adv **Returns** detached model metadata in adapter-preferred order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L152) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L150) ### ctx.llm.stream(options) @@ -61,4 +61,4 @@ Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with **Returns** the chunk stream, possibly wrapped by `llm/stream` listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L210) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L208) From 923b04606eea08202b31eed132513b6d49628009 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 14:09:14 +0800 Subject: [PATCH 173/323] docs: DeepSeek Harness SDK follow-up work design draft --- docs/sdk-后续工作-设计.md | 197 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 197 insertions(+) create mode 100644 docs/sdk-后续工作-设计.md diff --git a/docs/sdk-后续工作-设计.md b/docs/sdk-后续工作-设计.md new file mode 100644 index 0000000000..a2096cf42f --- /dev/null +++ b/docs/sdk-后续工作-设计.md @@ -0,0 +1,197 @@ +# DeepSeek Harness SDK 后续工作设计 + +> 状态：设计成稿，供通读与评审。定案后由 ccyu 转正式 RFC 并双语化。本文件为临时设计文档，不走 doc-sync / 文档预算门禁。 +> 一句话：**SDK 初版已合并；本轮把"创建项目""创建插件""遥测""交互测试"四块补齐，核心是抽出一个既撑交互又撑 headless 的创建内核，其余三块围绕它扩展。** + +## 0. 总览（一屏读完） + +抽一个既撑交互又撑 headless 的**创建内核**（`Prompter` seam + 复用已有 `ProjectEditSession` + `CreationDriver` 发 NDJSON），四块活围绕它扩展。 + +| 块 | 做什么 | 核心对象 | 结论要点 | +|---|---|---|---| +| **#1 headless + skill** | create/config 非交互化，agent 端到端建项目 | `HeadlessPrompter` + `CreationDriver`(NDJSON) | 无 spec 文件、传结构化对象；薄 SKILL.md 入口；beyond-eve | +| **#2 建插件** | `dsh-sdk create ` 拉插件并接线 | `PluginSource` + `PluginFetcher`(giget/pacote) | 只解压不执行、锁版本、经 `ProjectEditSession` 显式接线 | +| **#3 遥测** | 每个 `dsh-sdk` 命令上报 | `TelemetryReporter` / `ConsentResolver` / `SecretRedactor` | 发 cordis.yml+package.json 全文；不发 `.env`、疑似密钥脱敏；关闭 = cordis.yml 有明确 disabled 的遥测条目（甲）| +| **#4 交互测试** | 覆盖 wizard 各分支、快照 cordis.yml | `WizardHarness` + clack mock 注入 | 注入流为主、真 PTY 仅 1–2 个可选 smoke | + +**节奏**：先做地基（`Prompter` 重构，同时解锁 #1+#4，不并行）→ 再 fan out 四棵 teammate worktree。 + +细节见下文；不想通读的话，读完本节 + §5（砍掉的路线）+ §6（节奏）即可。 + +## 1. 背景与现状 + +SDK 初版（`packages/sdk/*`）已经落地三个包： + +| 包 | 职责 | 当前局限 | +|---|---|---| +| `@deepseek-ai/create-sdk` | `npm create @deepseek-ai/sdk` 交互式建项目 | **TTY-only**：flag 只能预填问题，创建仍须交互终端；feature 配置面窄，复杂 feature 难在命令行表达 | +| `@deepseek-ai/dsh-helper` | 项目领域模型：feature 催表、蓝图、`ProjectEditSession`（唯一的改写/提交边界） | create-sdk 与 `dsh-sdk config` 共用同一套催表与 configurator，但目前只被交互式 wizard 驱动 | +| `@deepseek-ai/dsh-scripts` | `dsh-sdk` launcher：`start` / `dev` / `build` / `config` | `config` 同样 **TTY-only**；`build` 只跑 tsdown、`create` 时项目尚不存在——两者都不 boot cordis | + +四块后续工作： + +1. **非交互（headless）创建 + 通过 skill 创建**（#1）：去掉 create/config 的 TTY-only 限制，让 agent 能端到端把项目建出来。 +2. **`dsh-sdk create ` 从 github/npm 建插件**（#2）：把外部插件拉进现有项目并接线。 +3. **遥测**（#3）：每次 `dsh-sdk `（含 create/首次初始化）上报开发者周期数据。 +4. **终端交互测试**（#4）：给 clack wizard 加可回归、可核对的交互测试。 + +## 2. 边界澄清：三件事分开 + +调研 `vercel/eve` 及其引用的 `skills` CLI 后，确认三件事必须分开、不能混： + +| 轨 | 命令入口 | 产物 | +|---|---|---| +| **建项目** | `npm create @deepseek-ai/sdk`（现有 wizard）+ 其 headless 形态（本轮新增） | 一个新的 SDK 项目 | +| **建插件** | `dsh-sdk create `（现有 create-plugin 扩展） | 现有项目里多一个接好线的插件 | +| **分发 skill** | 发 SKILL.md → agent `npx skills add deepseek-ai/` | 任意 agent 拉到我们的 skill playbook | + +事实依据：`skills`（vercel-labs/skills）是 markdown SKILL.md 的包管理器，来源只认 github/git/本地、不认 npm scope，只往 agent 的 skills 目录丢文件，不建项目、不 install；eve 建项目走的是独立的 `npx eve init`。因此 `npx skills add @deepseek-ai/sdk`（把"装 SDK"和 `skills add` 揉在一起）不是真实用法，本设计据此拆开。 + +## 3. 总体架构 + +### 3.1 核心洞见：一个创建内核，四条轨围绕它 + +四块活看似独立，实则都咬合在同一组对象上。**建项目和改配置的本质是"问答 → 改项目文件"**，而 `dsh-helper` 已经有唯一的改写边界 `ProjectEditSession`。本轮把"问答"这一侧也抽成 seam，就能让交互与 headless 共用一套逻辑，测试和 skill 顺势接上去。 + +``` + ┌───────────────────────────────┐ + │ CreationDriver / SetupRunner │ 编排：问答序列 → 组装 spec → 驱动改写 + │ (emits NDJSON) │ + └───────────────┬───────────────┘ + 借助 │ 驱动 + ┌─────────────────────┐ │ ┌────────────────────────────┐ + │ Prompter (seam) │◄──────────┘ │ ProjectEditSession (已有) │ 唯一改写/提交边界 + ├─────────────────────┤ └────────────────────────────┘ + │ InteractivePrompter │ clack + 注入 input/output（解锁 #4 测试） + │ HeadlessPrompter │ 永不阻塞：答案取自结构化 spec，缺必答项→抛错/发 action-required（解锁 #1 + skill） + └─────────────────────┘ +``` + +- **`Prompter`（新 seam）**：把"向用户要一个答案"抽象出来。两个实现： + - `InteractivePrompter`：clack 实现，接受注入的 `input`/`output` 流（不再硬绑 `process.stdin/stdout`）。这正是 #4 交互测试的前置。 + - `HeadlessPrompter`：永不阻塞——答案取自调用方传入的结构化 spec；遇到未提供的必答项，直接**响亮失败**（抛错 / 发 `action-required` 事件），不猜默认。这是 #1 headless 与 skill 驱动的地基。 +- **`ProjectEditSession`（复用已有）**：唯一的改写/提交边界。create、config、以及 #2 建插件改 cordis.yml，全部经它落盘。 +- **`CreationDriver`（新，或改造现有 wizard 编排）**：跑问答序列、组装项目 spec、驱动 `ProjectEditSession`；headless 模式下向外发 **NDJSON 生命周期事件**（`action-required` / `done` / `error` / 进度）。 +- **skill 路径**：agent import 这个内核、传结构化 config 对象、读 NDJSON 事件；附一层薄 SKILL.md 教 agent 怎么驱动。 + +**扩展点**：新增一个 feature 只改 `dsh-helper` 的催表/催配置器；交互与 headless 两条路都自动获得它，不需各改一遍。 + +> **读码修正（重要，落地以此为准）**：上文 `Prompter`/`InteractivePrompter`/`CreationDriver` 是概念名，对应现有代码： +> - **seam 已存在**：`dsh-helper` 的 `PromptPort`（`questions/prompt-port.ts`）即 `Prompter`；问答走 `Question.resolve(port, prefilled?)`——给了 prefill 就不碰 port。 +> - **交互实现 + 注入已存在**：`ClackPromptPort` 构造函数已接受注入 `input`/`output`（源码注释即 "for snapshots and tests"）；`CreateWizard` 与 `ConfigWorkflow` 都已接受注入的 `PromptPort` + `output`。 +> - **⇒ #4 交互测试不被地基阻塞**：注入点今天就有，已单独开 teammate 并行做（覆盖 create + config 两个 wizard）。 +> - **地基真正要做的（比原设想小）**：新增 `HeadlessPromptPort implements PromptPort`（缺项 fail-fast + 发 NDJSON）+ 补全 prefill 覆盖——目前 feature 选择走原始 `nestedMultiselect`、`FeatureConfigurator` 的 valueInputs 无 prefill、suggests 确认无 prefill；headless 要让结构化 spec 喂满这些点。 + +### 3.2 四块如何咬合到这组对象 + +| 块 | 落在哪个对象 | 关系 | +|---|---|---| +| #1 headless + skill | `HeadlessPromptPort`（实现已有 `PromptPort`）+ prefill 补全 + NDJSON | 地基（缩小版）| +| #4 交互测试 | 注入 `ClackPromptPort(mockIn, mockOut)` 进已有 `CreateWizard`/`ConfigWorkflow` + `WizardHarness` | **注入点已存在，不阻塞，已并行开工** | +| #2 建插件 | `PluginSource` + `PluginFetcher` + 经 `ProjectEditSession` 接线 | 复用改写边界 | +| #3 遥测 | launcher 侧 `TelemetryReporter` + `ConsentResolver` + `SecretRedactor` | 独立于内核，挂在 launcher 命令生命周期 | + +## 4. 详细设计 + +### 4.1 headless 创建 + skill（#1） + +**目标**：`create-sdk`（建新项目）与 `dsh-sdk config`（改现有项目）都能非交互运行；agent 能端到端把项目建完。 + +**设计**： + +- **Prompter seam**：如 §3。交互走 `InteractivePrompter`，headless 走 `HeadlessPrompter`（fail-fast + NDJSON），二者背后是同一套 `dsh-helper` 催表和同一个 `ProjectEditSession`。 +- **输入编码**（次要、可解耦）： + - **agent 路径**：传结构化 config 对象（程序化，或 `--config-json '{...}'`）+ 读 NDJSON。**不需要 spec 文件**——与 eve 一致；我们 feature 比 eve 重（嵌套有限选项 + 密钥），结构化对象比一长串扁平 flag 干净。 + - **人 / CI 路径**（可选）：`--config `（yaml/json）或 flags，只是喂给同一内核的另一种编码。 +- **skill**：核心是 headless 内核；agent 传参直接建完，缺必答项就响亮失败让 agent 补答。附一层**薄 SKILL.md**（指向内核、教 agent 驱动），让"通过 skill 创建"字面落地。 +- **比 eve 更进一步**：eve 把 headless 原语（`runHeadless` + 非阻塞 Prompter + NDJSON）造好了，却没接到它的 skill——它的 SKILL.md 只指向半交互 CLI，且 agent 跑 `eve init` 时只打印指引、打回给人。我们把 **skill → headless 内核接通**，才真正做到"headless 为 skill 服务"。 + +### 4.2 `dsh-sdk create ` 建插件（#2） + +**目标**：从 github repo 或 npm 包拉一个插件进现有项目并接线；安全第一。 + +**设计（只解压不执行 + 锁版本 + 显式接线）**： + +- **`PluginSource`（判别联合）**：`GithubSource`（`owner/repo[/subdir]#ref`）| `NpmSource`（`pkg@version`）。由 spec 字符串解析而来。 +- **`PluginFetcher`（seam）**：把源抓进 temp 目录，**绝不执行被拉代码的生命周期脚本**。 + - `GigetFetcher`（github/git）：giget；`#ref` 先解析成 commit SHA 再下、记进 lock。 + - `PacoteFetcher`（npm）：pacote `extract`（只解包不跑 postinstall），带 `integrity` 校验。来源类型限定放在**上游 `resolvePluginSource`**（只产出 `name@version`）作为主保证，不依赖 pacote 的 `allowRegistry`（`@types/pacote` 无此选项，且 registry tarball extract 本就不跑脚本）。 +- **接线（显式可审）**： + 1. `package.json` 精确锁版本（npm：exact + integrity；github：`github:owner/repo#`）。 + 2. 经 `ProjectEditSession` 改 `cordis.yml` 挂插件——**给 diff、要确认**再写。 + 3. `install --ignore-scripts`（pnpm v10 默认亦拦依赖 build 脚本）。 + 4. 打印清单（dep spec + 锁的 ref/integrity + cordis.yml diff）。 +- **信任模型**：学 `npm create` 的手感，但把信任反过来——**confirm-before-run，而非 run-on-fetch**。 +- **repo 初始化模式**（从模板仓库整体建项目）同走 giget（优于 degit——degit 的 `degit.json` 会自动跑动作）；建远程新仓可用 `gh repo create --template`。注：eve 不支持 template-repo init，这是我们的自有取舍。 + +### 4.3 遥测（#3） + +**目标**：每次 `dsh-sdk `（create / dev / build / config / start / 首次初始化）上报当前 `cordis.yml` + `package.json` 内容。 + +**设计**： + +- **上报器位置**：在**我们自己的代码执行时机**里——`create-sdk` 进程 + `dsh-scripts` launcher 进程，包住命令生命周期。 + - 理由：`build` 只跑 tsdown、`create` 时项目还不存在，都不 boot cordis；写在 cordis.yml 里的 cordis 插件抓不到它们。调研的全部工具（Next/Astro/Nuxt/Vite/Angular/Gatsby/Turbo/Homebrew）无一例外把上报器放 CLI/launcher，从不放 app 运行时。 +- **`TelemetryReporter`（launcher 侧）**：包住命令，收集 `{command, 时长, 成败, cordis.yml 内容, package.json 内容}`。 +- **`ConsentResolver`**：在每个命令**解析（非 boot）`cordis.yml`**，读遥测插件状态当 consent。**关闭（甲，ccyu 拍板）= cordis.yml 里有一条明确 `disabled` 的遥测条目**；其余一切（无 cordis.yml / 有文件但无遥测条目 / 有 enabled 条目）都上报——唯一的关只有"存在且 disabled"，无不对称。（可选、近零成本补充，留到实现定：额外认 `DO_NOT_TRACK` / CI 自动关。） +- **`SecretRedactor`（安全硬线）**：绝不发 `.env`；cordis.yml / package.json 里若出现类似密钥的值，**脱敏替换**（redact 占位，不整段丢）。依赖 SDK 约定——密钥只进 `.env`、cordis.yml 只引用 env 不内联——脱敏是兜底。 +- **匿名 id**：全局配置里的随机 UUID；**绝不从 git remote / repo URL 派生**。 +- **endpoint**：内置在代码里。 +- **consent 承载**：遥测作为 `create` 时默认打开的 feature 写进 cordis.yml（对用户可见、随项目）。 + +**在案取舍**：发全文会把第三方（含私有 scoped）包名、cordis 配置值（base-url/路径）暴露给 endpoint 持有方；主流工具都不发这些（Turbo 排除包名、Angular 禁模块名）。ccyu 作为本 SDK 维护者接受此暴露——目的即掌握开发者用了哪些 plugin/依赖/配置。 + +### 4.4 交互测试（#4） + +**目标**：CI 仅 mac/linux；覆盖 create wizard 主流程 + config wizard 各选择分支；产出不同选择下的 `cordis.yml` 快照便于核对。 + +**设计（clack mock 注入，不上真 PTY 打头阵）**： + +- **主力**：进程内注入 mock stdin/stdout。`@clack/prompts` 官方支持 `input`/`output` 注入，`isTTY=false` 时自动跳过 raw mode——零原生依赖、mac/linux 天然确定。**前置已就绪**：`ClackPromptPort` 已接受注入流，`CreateWizard`/`ConfigWorkflow` 已接受注入 `PromptPort`。 +- **`WizardHarness`（测试工具）**：用脚本化 keypress 序列（`input.emit('keypress', …)` 走 down/space/return）驱动 wizard、写到 temp 目录、返回生成的 `cordis.yml`。 +- **断言**：`test.each(选择组合)` → `toMatchFileSnapshot('.cordis.yml')`；**快照生成的 cordis.yml**，不快照交互 transcript（transcript 脆、且是在测 clack 自己）。 +- **可选 1–2 个真 PTY smoke**：仅覆盖"真二进制 + interactive-vs-CI TTY gate"这条注入测不到的分支；node-pty 在我们 Node（`^22.19 || >=24`）上有原生编译风险，**挪出关键路径**，缺工具链 self-skip。 + +## 5. 砍掉的路线（调研依据） + +| 砍掉的路线 | 理由 | +|---|---| +| #4 用真 PTY（node-pty）打头阵 | clack 官方支持注入流，无需真 TTY；node-pty 在我们 Node 版本上有原生编译风险。真 PTY 降级为 1–2 个可选 smoke | +| #4 快照交互 transcript | transcript 受重绘/spinner/ANSI 影响脆弱，且主要在测 clack 渲染而非我们的生成逻辑 | +| #3 上报器做成 cordis 插件 | `build`/`create` 不 boot cordis，插件抓不到；无一主流工具用 app 内插件做遥测 | +| #3 匿名 id 从 git remote 派生 | 会让"匿名"变假（Next 因此挨批） | +| #1 headless 以 spec 文件为主 | eve 没有 spec 文件；agent 路径传结构化对象更干净，spec 文件退成人/CI 可选 | +| #2 从 npm/github 拉完自动 install+build | 会执行被拉代码的 postinstall，供应链风险；改为只解压 + 显式接线 + `--ignore-scripts` | +| #1 用 `npx skills add` 创建项目 | `skills` 是 markdown SKILL.md 包管理器、不建项目、不认 npm scope，属概念混淆 | + +## 6. 推进节奏：地基缩小，已并发开工 + +**读码后修正**：`PromptPort` seam + 可注入的 `ClackPromptPort` + 可注入的 `CreateWizard`/`ConfigWorkflow` 都已存在，所以地基比原设想小，且 #4 不再被它阻塞。当前并发结构： + +1. **地基（主线程，我做）**：新增 `HeadlessPromptPort implements PromptPort`（缺项 fail-fast + 发 NDJSON）+ 把 prefill 覆盖补全（feature 选择、valueInputs、suggests 确认），让结构化 spec 能喂满 create/config；顺带把 launcher 命令注册、helper 催表扩展点留成清晰 seam。这是 #1 headless 与 #2/#3 接线步的公共前置。 +2. **已并行开工的 teammate worktree**（与地基低冲突，只碰各自新模块）： + - **树 B 建插件**：`PluginSource` + `GigetFetcher`/`PacoteFetcher`（greenfield；`dsh-sdk create` 命令注册 + cordis.yml 接线等地基后再做）。 + - **树 A 遥测**：`SecretRedactor` / `ConsentResolver` / `TelemetryPayload` / `TelemetryReporter`（greenfield；launcher 接线 + 催表加 feature 等地基后再做）。 + - **树 C 交互测试**：`WizardHarness` + create/config 的 `test.each` cordis.yml 快照（注入点已就绪，可全量做）。 +3. **地基落地后的收尾**（接线，碰共享文件）：#2 的 `dsh-sdk create` 命令注册 + cordis.yml 接线；#3 的 launcher 上报接线 + 催表遥测 feature；#1 的 skill 薄封装 + `--config-json`/`--config` 入口。 +4. **合并**：stacked PR，地基在底，其余 rebase 到地基上，逐层向上同步。 + - **树 D 薄 SKILL.md**：SKILL.md + 相关文档（并入第 3 步收尾）。 + +> 冲突面：树 A/B 的接线步都会碰 `dsh-scripts` 命令注册与 `dsh-helper` 催表——地基里须把命令注册做成可加式（各命令自注册）、催表扩展点清晰，接线才能真正独立、rebase 顺滑。greenfield 模块阶段（当前）不碰这些共享文件，所以能安全并行。 + +## 7. 各轨改动清单 + +| 轨 | 主要包 | 关键改动 | +|---|---|---| +| 地基 | dsh-helper, create-sdk, dsh-scripts | `HeadlessPromptPort`（实现已有 `PromptPort`）+ prefill 补全 + NDJSON + 命令注册/催表扩展点整理 | +| #1 headless+skill | create-sdk, dsh-scripts, （新）skill 包 | 结构化 spec 入口 `--config-json`/`--config`、薄 SKILL.md | +| #2 建插件 | （新）fetcher 包, dsh-scripts, dsh-helper | `PluginSource`、`GigetFetcher`/`PacoteFetcher`、`dsh-sdk create ` 注册、经 `ProjectEditSession` 接线+diff、新依赖 giget/pacote | +| #3 遥测 | （新）telemetry 包, dsh-scripts, dsh-helper | `TelemetryReporter`/`ConsentResolver`/`SecretRedactor`、launcher 接线、催表遥测 feature、内置 endpoint、全局 UUID | +| #4 测试 | packages/support, （已可注入）create-sdk/dsh-scripts | `WizardHarness`、create/config 的 `test.each` cordis.yml 快照、可选 PTY smoke | + +## 8. 调研来源 + +- eve / skills：https://github.com/vercel/eve · https://github.com/vercel-labs/skills +- 从源拉取：https://github.com/unjs/giget · https://github.com/npm/pacote · https://github.com/Rich-Harris/degit +- 遥测规范：https://nextjs.org/telemetry · https://astro.build/telemetry/ · https://github.com/nuxt/telemetry · https://angular.dev/cli/analytics · https://turborepo.dev/docs/telemetry · https://consoledonottrack.com +- PTY / clack 测试：https://github.com/bombshell-dev/clack · https://vitest.dev/guide/snapshot · https://github.com/microsoft/node-pty From dcd886798ff93bc6f4945ad4aea6e3c8658969ef Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 14:11:07 +0800 Subject: [PATCH 174/323] feat(sdk): headless PromptPort + create/config headless plan Add HeadlessPromptPort (fail-loud non-interactive PromptPort), thread prefilled feature values through FeatureConfigurator, and let CreateWizard and ConfigWorkflow accept a headless feature plan that skips the interactive tree/suggests prompts. Per-file 100% coverage on all changed files. --- packages/sdk/create-sdk/src/create-wizard.ts | 75 ++++++------ packages/sdk/create-sdk/tests/create.spec.ts | 50 ++++++++ .../src/features/feature-configurator.ts | 9 +- packages/sdk/helper/src/index.ts | 1 + .../src/questions/headless-prompt-port.ts | 97 ++++++++++++++++ .../helper/tests/headless-prompt-port.spec.ts | 95 +++++++++++++++ packages/sdk/helper/tests/questions.spec.ts | 31 +++++ .../sdk/scripts/src/config/config-workflow.ts | 108 +++++++++++------- packages/sdk/scripts/tests/scripts.spec.ts | 25 +++- 9 files changed, 415 insertions(+), 76 deletions(-) create mode 100644 packages/sdk/helper/src/questions/headless-prompt-port.ts create mode 100644 packages/sdk/helper/tests/headless-prompt-port.spec.ts diff --git a/packages/sdk/create-sdk/src/create-wizard.ts b/packages/sdk/create-sdk/src/create-wizard.ts index 8391fae1e4..fb6849ba2a 100644 --- a/packages/sdk/create-sdk/src/create-wizard.ts +++ b/packages/sdk/create-sdk/src/create-wizard.ts @@ -48,6 +48,7 @@ export class CreateWizard { private readonly versionProbe: PackageManagerVersionProbe private readonly userAgent: string private readonly linkWorkspaceRoot: string | undefined + private readonly featurePlan: readonly FeatureSelection[] | undefined /** Bind parsed args and infrastructure to one wizard run. */ constructor(options: { @@ -57,6 +58,7 @@ export class CreateWizard { releaseVersion: string versionProbe?: PackageManagerVersionProbe userAgent?: string + features?: readonly FeatureSelection[] }) { this.args = options.args this.port = options.port @@ -68,6 +70,7 @@ export class CreateWizard { this.linkWorkspaceRoot = options.args.linkWorkspace ? fileURLToPath(new URL('../../../../', import.meta.url)) : undefined + this.featurePlan = options.features } /** Collect all answers before constructing any project files. */ @@ -129,39 +132,43 @@ export class CreateWizard { const configurable = registry.all().filter(feature => feature.id === 'bash' || feature.id === 'persistence' || (!feature.required && feature.isApplicable(profile))) - const selected = [...requireAnswer(await this.port.nestedMultiselect({ - message: 'Select features', - options: configurable.map((feature) => { - const nested = feature.mode !== 'single' - const defaults = new Set(feature.defaultOptions(profile)) - return { - value: feature.id, - label: feature.summary, - required: feature.required, - default: feature.required || feature.id === 'hmr' || feature.id === 'fs' || feature.id === 'todo' - || feature.id === 'skill', - ...nested ? { - choiceMode: feature.mode === 'multiple' ? 'multiple' as const : 'exclusive' as const, - choices: feature.options.map(option => ({ - value: option.id, - label: option.label, - default: defaults.has(option.id), - })), - } : {}, + const selected = this.featurePlan + ? this.featurePlan.map(feature => ({ value: feature.id, choices: feature.options })) + : [...requireAnswer(await this.port.nestedMultiselect({ + message: 'Select features', + options: configurable.map((feature) => { + const nested = feature.mode !== 'single' + const defaults = new Set(feature.defaultOptions(profile)) + return { + value: feature.id, + label: feature.summary, + required: feature.required, + default: feature.required || feature.id === 'hmr' || feature.id === 'fs' || feature.id === 'todo' + || feature.id === 'skill', + ...nested ? { + choiceMode: feature.mode === 'multiple' ? 'multiple' as const : 'exclusive' as const, + choices: feature.options.map(option => ({ + value: option.id, + label: option.label, + default: defaults.has(option.id), + })), + } : {}, + } + }), + }))] + if (!this.featurePlan) { + for (const { value: id } of [...selected]) { + const feature = registry.get(id) + for (const suggestedId of feature.suggests) { + if (selected.some(item => item.value === suggestedId)) continue + const suggested = registry.get(suggestedId) + const add = requireAnswer(await new ConfirmQuestion({ + id: `${feature.id}.${suggested.id}`, + message: `Add the recommended ${suggested.summary.toLowerCase()} for ${feature.summary.toLowerCase()}?`, + initialValue: true, + }).resolve(this.port)) + if (add) selected.push({ value: suggested.id, choices: suggested.defaultOptions(profile) }) } - }), - }))] - for (const { value: id } of [...selected]) { - const feature = registry.get(id) - for (const suggestedId of feature.suggests) { - if (selected.some(item => item.value === suggestedId)) continue - const suggested = registry.get(suggestedId) - const add = requireAnswer(await new ConfirmQuestion({ - id: `${feature.id}.${suggested.id}`, - message: `Add the recommended ${suggested.summary.toLowerCase()} for ${feature.summary.toLowerCase()}?`, - initialValue: true, - }).resolve(this.port)) - if (add) selected.push({ value: suggested.id, choices: suggested.defaultOptions(profile) }) } } const fixed = new Set(selections.map(selection => selection.id)) @@ -174,12 +181,16 @@ export class CreateWizard { for (const choice of selected) { choices.set(choice.value, choice.choices.length > 0 ? choice.choices : undefined) } + const plannedById = new Map((this.featurePlan ?? []).map(feature => [feature.id, feature])) for (const [id, options] of choices) { + const planned = plannedById.get(id) selections.push(await configurator.configure( registry.get(id), profile, undefined, options, + planned?.secrets ?? {}, + planned?.values ?? {}, )) } return selections diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index 9d75700bb9..f4b66dc8ff 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -5,9 +5,11 @@ import { PassThrough, Writable } from 'node:stream' import { fileURLToPath } from 'node:url' import { afterEach, describe, expect, it, vi } from 'vitest' import { + HeadlessPromptPort, LocalPluginBlueprint, featureId, NpmPackageManager, + type FeatureSelection, type NestedMultiSelectValue, type PromptPort, } from '@deepseek-ai/dsh-helper' @@ -233,6 +235,54 @@ describe('CreateWizard and scaffolder', () => { expect(resolved.request.features.find(item => item.id === 'hmr')).toMatchObject({ options: ['default'] }) }) + it('runs headlessly from a feature plan without reaching the terminal', async () => { + const cwd = await mkdtemp(join(tmpdir(), 'create-headless-')) + temporary.push(cwd) + const features: FeatureSelection[] = [ + { id: featureId('persistence'), options: ['sqlite'], values: { region: 'us' } }, + { id: featureId('web'), options: ['exa'], secrets: { apiKey: 'exa-key' } }, + ] + const resolved = await new CreateWizard({ + args: parseCreateArgs([ + 'my-agent', '--description=demo', '--provider=deepseek', '--api-key=deepseek-key', + '--model=deepseek-v4-flash', '--interface=stdio', '--pm=npm', '--no-install', + ]), + port: new HeadlessPromptPort(), + cwd, + releaseVersion: '0.0.1', + versionProbe: async () => '10.0.0', + features, + }).run() + expect(resolved.install).toBe(false) + expect(resolved.request.localPlugins).toEqual([]) + expect(resolved.request.features.find(item => item.id === 'web')).toMatchObject({ + options: ['exa'], secrets: { apiKey: 'exa-key' }, + }) + expect(resolved.request.features.find(item => item.id === 'persistence')).toMatchObject({ options: ['sqlite'] }) + expect(resolved.request.features.find(item => item.id === 'provider')).toMatchObject({ + secrets: { apiKey: 'deepseek-key' }, + }) + }) + + it('rejects a non-string feature value in a headless plan', async () => { + const cwd = await mkdtemp(join(tmpdir(), 'create-headless-bad-')) + temporary.push(cwd) + const features = [ + { id: featureId('persistence'), options: ['sqlite'], values: { bad: 1 } }, + ] as unknown as FeatureSelection[] + await expect(new CreateWizard({ + args: parseCreateArgs([ + 'my-agent', '--description=demo', '--provider=deepseek', '--api-key=k', + '--model=m', '--interface=stdio', '--pm=npm', '--no-install', + ]), + port: new HeadlessPromptPort(), + cwd, + releaseVersion: '0.0.1', + versionProbe: async () => '10.0.0', + features, + }).run()).rejects.toThrow('must be a string') + }) + it('writes the project once and refuses every existing target', async () => { const root = await mkdtemp(join(tmpdir(), 'create-scaffold-')) temporary.push(root) diff --git a/packages/sdk/helper/src/features/feature-configurator.ts b/packages/sdk/helper/src/features/feature-configurator.ts index 47cc011d16..e6e14030f9 100644 --- a/packages/sdk/helper/src/features/feature-configurator.ts +++ b/packages/sdk/helper/src/features/feature-configurator.ts @@ -26,6 +26,7 @@ export class FeatureConfigurator { * @param current - currently installed selection, when configuring. * @param prefilledOptions - options already chosen by a tree picker. * @param prefilledSecrets - non-interactive secret values supplied by creation. + * @param prefilledValues - non-interactive value inputs supplied by a headless spec. * @returns normalized selection with captured values and secrets. */ async configure( @@ -34,6 +35,7 @@ export class FeatureConfigurator { current?: FeatureSelection, prefilledOptions?: readonly string[], prefilledSecrets: Readonly> = {}, + prefilledValues: Readonly> = {}, ): Promise { let options: readonly string[] switch (feature.mode) { @@ -69,6 +71,11 @@ export class FeatureConfigurator { id: feature.id, options, } + const coercedPrefilled: Record = {} + for (const [key, value] of Object.entries(prefilledValues)) { + if (typeof value !== 'string') throw new Error(`${feature.id}.${key} value must be a string`) + coercedPrefilled[key] = value + } const values: Record = {} for (const input of feature.valueInputs(selected, profile)) { const existing = current?.values?.[input.id] @@ -81,7 +88,7 @@ export class FeatureConfigurator { ...existing === undefined ? {} : { initialValue: existing }, validate: value => value.trim().length === 0 ? 'A value is required' : undefined, }) - values[input.id] = requireAnswer(await question.resolve(this.port)) + values[input.id] = requireAnswer(await question.resolve(this.port, coercedPrefilled[input.id])) } const base: FeatureSelection = Object.keys(values).length === 0 ? selected diff --git a/packages/sdk/helper/src/index.ts b/packages/sdk/helper/src/index.ts index 98c55c3f8b..85aba58a99 100644 --- a/packages/sdk/helper/src/index.ts +++ b/packages/sdk/helper/src/index.ts @@ -43,3 +43,4 @@ export { } from './questions/question.ts' export type { Question } from './questions/question.ts' export { ClackPromptPort } from './questions/clack-prompt-port.ts' +export { HeadlessPromptError, HeadlessPromptPort } from './questions/headless-prompt-port.ts' diff --git a/packages/sdk/helper/src/questions/headless-prompt-port.ts b/packages/sdk/helper/src/questions/headless-prompt-port.ts new file mode 100644 index 0000000000..658500aed0 --- /dev/null +++ b/packages/sdk/helper/src/questions/headless-prompt-port.ts @@ -0,0 +1,97 @@ +/** + * Non-interactive prompt port for headless create/config and skill-driven runs. + * + * @module @deepseek-ai/dsh-helper/questions/headless-prompt-port + */ + +import type { + ConfirmPromptRequest, + MultiSelectPromptRequest, + NestedMultiSelectRequest, + NestedMultiSelectValue, + PromptOutcome, + PromptPort, + SecretPromptRequest, + SelectPromptRequest, + TextPromptRequest, +} from './prompt-port.ts' + +/** + * Raised when a headless run reaches a decision that was neither prefilled nor + * carries a usable default. The message names the unanswered prompt so an agent + * or CI caller can see exactly which input the spec must supply. + */ +export class HeadlessPromptError extends Error { + /** The unanswered prompt's user-facing message. */ + readonly prompt: string + + /** Build an error naming the unanswered prompt. */ + constructor(prompt: string) { + super(`headless run needs an answer for: ${prompt}`) + this.name = 'HeadlessPromptError' + this.prompt = prompt + } +} + +/** Resolve an answered outcome. */ +function answered(value: T): Promise> { + return Promise.resolve({ status: 'answered', value }) +} + +/** Reject with a named unanswered-prompt error. */ +function unanswered(message: string): Promise> { + return Promise.reject(new HeadlessPromptError(message)) +} + +/** + * A {@link PromptPort} that never blocks on a terminal. + * + * Answers are expected to arrive as prefilled values through the `Question` / + * `FeatureConfigurator` layers, so in a fully specified run this port is never + * reached. When it *is* reached, it takes the prompt's own declared default + * (`defaultValue` / `initialValue`) if one exists; otherwise it fails loud with + * {@link HeadlessPromptError}. Nested feature selection has no scalar default, + * so it always fails loud — headless callers must supply the feature set through + * the spec rather than the tree picker. + */ +export class HeadlessPromptPort implements PromptPort { + /** Answer visible text from its default, or fail loud. */ + text(request: TextPromptRequest): Promise> { + const fallback = request.initialValue ?? request.defaultValue + if (fallback === undefined) return unanswered(request.message) + const diagnostic = request.validate?.(fallback) + if (diagnostic) return unanswered(`${request.message} (${diagnostic})`) + return answered(fallback) + } + + /** A secret has no safe default: always fail loud. */ + secret(request: SecretPromptRequest): Promise> { + return unanswered(request.message) + } + + /** Answer a single choice from its initial value, or fail loud. */ + select(request: SelectPromptRequest): Promise> { + if (request.initialValue === undefined) return unanswered(request.message) + return answered(request.initialValue) + } + + /** Answer a multi-choice from its initial values, or fail loud when required. */ + multiselect(request: MultiSelectPromptRequest): Promise> { + const initial = request.initialValues ?? [] + if (request.required && initial.length === 0) return unanswered(request.message) + return answered(initial) + } + + /** Answer a confirmation from its initial value, or fail loud. */ + confirm(request: ConfirmPromptRequest): Promise> { + if (request.initialValue === undefined) return unanswered(request.message) + return answered(request.initialValue) + } + + /** Nested feature selection has no scalar default: always fail loud. */ + nestedMultiselect( + request: NestedMultiSelectRequest, + ): Promise[]>> { + return unanswered(request.message) + } +} diff --git a/packages/sdk/helper/tests/headless-prompt-port.spec.ts b/packages/sdk/helper/tests/headless-prompt-port.spec.ts new file mode 100644 index 0000000000..12febcfeff --- /dev/null +++ b/packages/sdk/helper/tests/headless-prompt-port.spec.ts @@ -0,0 +1,95 @@ +import { describe, expect, it } from 'vitest' +import { HeadlessPromptError, HeadlessPromptPort } from '../src/questions/headless-prompt-port.ts' + +/** Unwrap an answered outcome or fail the test. */ +async function answered(promise: Promise<{ status: 'answered'; value: T } | { status: 'cancelled' }>): Promise { + const outcome = await promise + if (outcome.status !== 'answered') throw new Error('expected an answered outcome') + return outcome.value +} + +describe('HeadlessPromptError', () => { + it('names the unanswered prompt', () => { + const error = new HeadlessPromptError('DeepSeek API key') + expect(error).toBeInstanceOf(Error) + expect(error.name).toBe('HeadlessPromptError') + expect(error.prompt).toBe('DeepSeek API key') + expect(error.message).toContain('DeepSeek API key') + }) +}) + +describe('HeadlessPromptPort', () => { + const port = new HeadlessPromptPort() + + describe('text', () => { + it('takes the initial value when present', async () => { + expect(await answered(port.text({ message: 'name', initialValue: 'agent' }))).toBe('agent') + }) + + it('falls back to the default value', async () => { + expect(await answered(port.text({ message: 'dir', defaultValue: 'my-agent' }))).toBe('my-agent') + }) + + it('prefers the initial value over the default value', async () => { + expect(await answered(port.text({ message: 'dir', initialValue: 'given', defaultValue: 'my-agent' }))).toBe('given') + }) + + it('fails loud when no default exists', async () => { + await expect(port.text({ message: 'base URL' })).rejects.toThrow(HeadlessPromptError) + }) + + it('fails loud when the default is invalid', async () => { + await expect(port.text({ + message: 'name', + defaultValue: '', + validate: value => value.length === 0 ? 'required' : undefined, + })).rejects.toThrow(/required/) + }) + }) + + describe('secret', () => { + it('always fails loud', async () => { + await expect(port.secret({ message: 'API key' })).rejects.toThrow(HeadlessPromptError) + }) + }) + + describe('select', () => { + it('takes the initial value when present', async () => { + expect(await answered(port.select({ message: 'pm', options: [{ value: 'npm', label: 'npm' }], initialValue: 'npm' }))).toBe('npm') + }) + + it('fails loud without an initial value', async () => { + await expect(port.select({ message: 'pm', options: [{ value: 'npm', label: 'npm' }] })).rejects.toThrow(HeadlessPromptError) + }) + }) + + describe('multiselect', () => { + it('returns the initial values', async () => { + expect(await answered(port.multiselect({ message: 'x', options: [], initialValues: ['a', 'b'] }))).toEqual(['a', 'b']) + }) + + it('returns an empty selection when none are supplied and none are required', async () => { + expect(await answered(port.multiselect({ message: 'x', options: [] }))).toEqual([]) + }) + + it('fails loud when required and nothing is preselected', async () => { + await expect(port.multiselect({ message: 'x', options: [], required: true })).rejects.toThrow(HeadlessPromptError) + }) + }) + + describe('confirm', () => { + it('takes the initial value when present', async () => { + expect(await answered(port.confirm({ message: 'install?', initialValue: false }))).toBe(false) + }) + + it('fails loud without an initial value', async () => { + await expect(port.confirm({ message: 'apply?' })).rejects.toThrow(HeadlessPromptError) + }) + }) + + describe('nestedMultiselect', () => { + it('always fails loud', async () => { + await expect(port.nestedMultiselect({ message: 'Select features', options: [] })).rejects.toThrow(HeadlessPromptError) + }) + }) +}) diff --git a/packages/sdk/helper/tests/questions.spec.ts b/packages/sdk/helper/tests/questions.spec.ts index 463f3b979f..5eb205075f 100644 --- a/packages/sdk/helper/tests/questions.spec.ts +++ b/packages/sdk/helper/tests/questions.spec.ts @@ -450,4 +450,35 @@ describe('feature configurator', () => { await expect(new FeatureConfigurator(new QueuePromptPort([])).configure(new EmptyExclusive(), profile)) .rejects.toThrow('has no default option') }) + + it('configures fully from prefilled options, values, and secrets without prompting', async () => { + const registry = createBuiltinRegistry(profile) + const port = new QueuePromptPort([]) + const result = await new FeatureConfigurator(port).configure( + registry.get(featureId('provider')), + profile, + undefined, + ['custom'], + { apiKey: 'prefilled-key' }, + { baseURL: 'https://prefilled' }, + ) + expect(result).toMatchObject({ + options: ['custom'], + values: { baseURL: 'https://prefilled' }, + secrets: { apiKey: 'prefilled-key' }, + }) + expect(port.requests).toEqual([]) + }) + + it('rejects a non-string prefilled feature value', async () => { + const registry = createBuiltinRegistry(profile) + await expect(new FeatureConfigurator(new QueuePromptPort([])).configure( + registry.get(featureId('provider')), + profile, + undefined, + ['custom'], + { apiKey: 'k' }, + { baseURL: 123 }, + )).rejects.toThrow('must be a string') + }) }) diff --git a/packages/sdk/scripts/src/config/config-workflow.ts b/packages/sdk/scripts/src/config/config-workflow.ts index 7d3d7ee43a..016d9d09b8 100644 --- a/packages/sdk/scripts/src/config/config-workflow.ts +++ b/packages/sdk/scripts/src/config/config-workflow.ts @@ -28,6 +28,17 @@ export interface ConfigWorkflowResult { installError?: Error } +/** + * Non-interactive desired end-state for a config run: the complete set of enabled + * features, with options and any secrets/values a newly installed feature needs. + * Features not listed are reconciled to disabled, exactly as an interactive tree + * selection would be. Custom (non-feature) cordis plugins keep their current state; + * toggling them headlessly is not yet supported. + */ +export interface ConfigPlan { + features: readonly FeatureSelection[] +} + function featureTarget(feature: Feature): string { return `feature:${feature.id}` } @@ -66,48 +77,58 @@ export class ConfigWorkflow { } /** Select desired state, reconcile the working copy, review, and apply. */ - async run(project: SdkProject, registry: FeatureRegistry): Promise { + async run(project: SdkProject, registry: FeatureRegistry, plan?: ConfigPlan): Promise { const edit = project.edit(registry) const configurator = new FeatureConfigurator(this.port) const features = registry.all().filter(feature => feature.isApplicable(project.profile)) const inspections = new Map(edit.inspections().map(item => [item.id, item])) const custom = edit.cordisConfigEntries().filter(entry => !registry.ownerOfPackage(entry.name, project.profile)) - const desired = requireAnswer(await this.port.nestedMultiselect({ - message: 'Configure the project', - showChanges: true, - options: [ - ...features.map((feature) => { - const installation = inspections.get(feature.id) - /* v8 ignore next -- inspections() is built from this exact feature registry */ - if (!installation) throw new Error(`feature inspection is missing: ${feature.id}`) - const inconsistent = installation.state === 'inconsistent' - const selectedOptions = new Set(installation.options.length > 0 - ? installation.options - : feature.defaultOptions(project.profile)) - return { - value: featureTarget(feature), - label: feature.summary, - required: feature.required, - default: feature.required || installation.state === 'enabled' || inconsistent, - disabled: inconsistent, - ...inconsistent ? { warning: installation.diagnostics.join('; ') } : {}, - ...feature.mode === 'single' ? {} : { - choiceMode: feature.mode, - choices: feature.options.map(option => ({ - value: option.id, - label: option.label, - default: selectedOptions.has(option.id), - })), - }, - } - }), - ...custom.map(entry => ({ - value: pluginTarget(entry.id), - label: `${entry.name} [custom]`, - default: !entry.disabled, + const desired = plan + ? [ + ...plan.features.map(selection => ({ + value: featureTarget(registry.get(selection.id)), + choices: selection.options, })), - ], - })) + ...custom + .filter(entry => !entry.disabled) + .map(entry => ({ value: pluginTarget(entry.id), choices: [] as readonly string[] })), + ] + : requireAnswer(await this.port.nestedMultiselect({ + message: 'Configure the project', + showChanges: true, + options: [ + ...features.map((feature) => { + const installation = inspections.get(feature.id) + /* v8 ignore next -- inspections() is built from this exact feature registry */ + if (!installation) throw new Error(`feature inspection is missing: ${feature.id}`) + const inconsistent = installation.state === 'inconsistent' + const selectedOptions = new Set(installation.options.length > 0 + ? installation.options + : feature.defaultOptions(project.profile)) + return { + value: featureTarget(feature), + label: feature.summary, + required: feature.required, + default: feature.required || installation.state === 'enabled' || inconsistent, + disabled: inconsistent, + ...inconsistent ? { warning: installation.diagnostics.join('; ') } : {}, + ...feature.mode === 'single' ? {} : { + choiceMode: feature.mode, + choices: feature.options.map(option => ({ + value: option.id, + label: option.label, + default: selectedOptions.has(option.id), + })), + }, + } + }), + ...custom.map(entry => ({ + value: pluginTarget(entry.id), + label: `${entry.name} [custom]`, + default: !entry.disabled, + })), + ], + })) const desiredByTarget = new Map(desired.map(item => [item.value, item])) const targetProfile = { ...project.profile, @@ -117,6 +138,9 @@ export class ConfigWorkflow { if (!feature.isApplicable(targetProfile)) desiredByTarget.delete(featureTarget(feature)) } + const plannedById = new Map( + (plan?.features ?? []).map(selection => [selection.id, selection]), + ) for (const feature of features) { const installation = inspections.get(feature.id) /* v8 ignore next -- inspections() is built from this exact feature registry */ @@ -124,7 +148,7 @@ export class ConfigWorkflow { if (installation.state === 'inconsistent') continue const choice = desiredByTarget.get(featureTarget(feature)) if (!choice && !feature.required) continue - await this.enableOrConfigure(feature, installation, choice, project, edit, configurator) + await this.enableOrConfigure(feature, installation, choice, project, edit, configurator, plannedById.get(feature.id)) } for (const feature of [...features].reverse()) { @@ -176,6 +200,7 @@ export class ConfigWorkflow { project: SdkProject, edit: ReturnType, configurator: FeatureConfigurator, + planned?: FeatureSelection, ): Promise { const options = choice?.choices.length ? choice.choices @@ -183,7 +208,9 @@ export class ConfigWorkflow { ? installation.options : feature.defaultOptions(project.profile) if (installation.state === 'absent') { - const selection = await configurator.configure(feature, project.profile, undefined, options) + const selection = await configurator.configure( + feature, project.profile, undefined, options, planned?.secrets ?? {}, planned?.values ?? {}, + ) edit.installFeature(feature, selection) return } @@ -191,10 +218,7 @@ export class ConfigWorkflow { if (!installation.selection) throw new Error(`feature ${feature.id} has no readable selection`) if (!sameOptions(installation.options, options)) { const selection: FeatureSelection = await configurator.configure( - feature, - project.profile, - installation.selection, - options, + feature, project.profile, installation.selection, options, planned?.secrets ?? {}, planned?.values ?? {}, ) edit.configureFeature(feature, selection) } diff --git a/packages/sdk/scripts/tests/scripts.spec.ts b/packages/sdk/scripts/tests/scripts.spec.ts index 8d110799ea..42c74f5631 100644 --- a/packages/sdk/scripts/tests/scripts.spec.ts +++ b/packages/sdk/scripts/tests/scripts.spec.ts @@ -5,6 +5,7 @@ import { PassThrough, Writable } from 'node:stream' import { fileURLToPath, pathToFileURL } from 'node:url' import { afterEach, describe, expect, expectTypeOf, it, vi } from 'vitest' import { + HeadlessPromptPort, LocalPluginBlueprint, NpmPackageManager, SdkProject, @@ -29,7 +30,7 @@ import { parseDshSdkArgs, parseSdkBootArgs } from '../src/args.ts' import { PluginBuild, ProjectBuild, runProjectBuild } from '../src/build.ts' import { runDshSdkCommand, type DshSdkCommandContext } from '../src/command.ts' import { runConfigCommand } from '../src/config.ts' -import { ConfigWorkflow } from '../src/config/config-workflow.ts' +import { ConfigWorkflow, type ConfigPlan } from '../src/config/config-workflow.ts' import { initialize, resolve as resolveLocalPlugin } from '../src/local-plugin-loader-hooks.ts' const temporary: string[] = [] @@ -399,6 +400,28 @@ describe('ConfigWorkflow', () => { expect(output.read()).toContain('Disable feature: todo') }) + it('reconciles a headless plan without prompting and preserves custom plugins', async () => { + const project = await committedProject([], [new LocalPluginBlueprint('plugin', 'plugin')]) + const registry = createBuiltinRegistry(project.profile) + const output = outputBuffer() + let installs = 0 + const plan: ConfigPlan = { + features: [ + { id: featureId('bash'), options: ['local'] }, + { id: featureId('persistence'), options: ['jsonl'] }, + { id: featureId('todo'), options: ['default'] }, + { id: featureId('web'), options: ['exa'], secrets: { apiKey: 'exa-key' } }, + ], + } + const result = await new ConfigWorkflow( + new HeadlessPromptPort(), output.stream, async () => { installs += 1 }, + ).run(project, registry, plan) + expect(result.commit?.project.cordis.entry('tool-todo')).toBeDefined() + // the unlisted custom local plugin keeps its enabled state (not nuked by the plan) + expect(result.commit?.project.cordis.entry('plugin')?.disabled).toBeFalsy() + expect(installs).toBe(1) + }) + it('installs once after NPM dependency changes and keeps committed files on install failure', async () => { const project = await committedProject() const registry = createBuiltinRegistry(project.profile) From 825a63ab012671864a8d831b6d180a19538a5691 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 13:20:34 +0800 Subject: [PATCH 175/323] feat(sdk): add dsh-plugin-fetch source + fetcher seam MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Greenfield #2 "建插件" modules for the forthcoming `dsh-sdk create ` command, in a new foundation-independent package so it touches none of the dsh-scripts / dsh-helper / create-sdk hotspots the foundation refactor edits. - `resolvePluginSource(spec)` parses `owner/repo[/subdir]#ref` (github) or `pkg@version` (npm) into a `PluginSource` discriminated union, failing loud on an ambiguous or malformed spec. - `PluginFetcher` seam + `fetchPlugin` tag dispatch returning a common `FetchedPlugin` (temp dir + immutable provenance). - `GigetFetcher` (github) over @bluwy/giget-core: resolve `#ref` to a commit SHA first, download that SHA; provenance pins the SHA. Chosen over unjs/giget for its single runtime dep and absent install/action surface. - `PacoteFetcher` (npm) over pacote: resolve the manifest, then extract the tarball verified against its registry integrity. Registry-only is enforced by the source resolver; extract runs no lifecycle scripts. - Branded `CommitSha`/`Integrity`; network + temp-dir boundaries are injected so the logic is unit-tested at 100% per-file coverage without network. Wiring (package.json pin, cordis.yml via ProjectEditSession with a confirmed diff, install --ignore-scripts) and the launcher command registration land later with the foundation. --- docs/module-graph.md | 3 + packages/sdk/README.md | 1 + packages/sdk/plugin-fetch/README.md | 32 + packages/sdk/plugin-fetch/package.json | 37 + packages/sdk/plugin-fetch/src/fetcher.ts | 90 ++ .../sdk/plugin-fetch/src/giget-fetcher.ts | 116 +++ packages/sdk/plugin-fetch/src/ids.ts | 39 + packages/sdk/plugin-fetch/src/index.ts | 48 + packages/sdk/plugin-fetch/src/never.ts | 19 + .../sdk/plugin-fetch/src/pacote-fetcher.ts | 129 +++ packages/sdk/plugin-fetch/src/source.ts | 126 +++ .../sdk/plugin-fetch/tests/fetcher.spec.ts | 64 ++ .../plugin-fetch/tests/giget-fetcher.spec.ts | 145 +++ packages/sdk/plugin-fetch/tests/ids.spec.ts | 39 + packages/sdk/plugin-fetch/tests/never.spec.ts | 19 + .../plugin-fetch/tests/pacote-fetcher.spec.ts | 108 +++ .../sdk/plugin-fetch/tests/source.spec.ts | 107 +++ packages/sdk/plugin-fetch/tsconfig.json | 15 + pnpm-lock.yaml | 833 +++++++++++++++++- .../verify-package-readme-model-experience.ts | 1 + tsconfig.build.json | 3 +- tsconfig.json | 3 +- 22 files changed, 1974 insertions(+), 3 deletions(-) create mode 100644 packages/sdk/plugin-fetch/README.md create mode 100644 packages/sdk/plugin-fetch/package.json create mode 100644 packages/sdk/plugin-fetch/src/fetcher.ts create mode 100644 packages/sdk/plugin-fetch/src/giget-fetcher.ts create mode 100644 packages/sdk/plugin-fetch/src/ids.ts create mode 100644 packages/sdk/plugin-fetch/src/index.ts create mode 100644 packages/sdk/plugin-fetch/src/never.ts create mode 100644 packages/sdk/plugin-fetch/src/pacote-fetcher.ts create mode 100644 packages/sdk/plugin-fetch/src/source.ts create mode 100644 packages/sdk/plugin-fetch/tests/fetcher.spec.ts create mode 100644 packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts create mode 100644 packages/sdk/plugin-fetch/tests/ids.spec.ts create mode 100644 packages/sdk/plugin-fetch/tests/never.spec.ts create mode 100644 packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts create mode 100644 packages/sdk/plugin-fetch/tests/source.spec.ts create mode 100644 packages/sdk/plugin-fetch/tsconfig.json diff --git a/docs/module-graph.md b/docs/module-graph.md index 8b67c73d27..c9439d5501 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -138,6 +138,7 @@ flowchart TD end subgraph group_sdk["packages/sdk"] pkg_helper["helper"] + pkg_plugin_fetch["plugin-fetch"] pkg_scripts["scripts"] end subgraph group_tasks["packages/tasks"] @@ -152,6 +153,7 @@ flowchart TD pkg_llm --> pkg_brand pkg_code_runtime_worker --> pkg_code_runtime pkg_helper --> pkg_brand + pkg_plugin_fetch --> pkg_brand pkg_scripts --> pkg_app_boot pkg_llm_deepseek --> pkg_llm pkg_llm_pi_ai --> pkg_llm @@ -442,6 +444,7 @@ flowchart TD | [`llm`](../packages/llm/llm) | `llm` | [`brand`](../packages/util/brand) | | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime) | | [`helper`](../packages/sdk/helper) | `sdk` | [`brand`](../packages/util/brand) | +| [`plugin-fetch`](../packages/sdk/plugin-fetch) | `sdk` | [`brand`](../packages/util/brand) | | [`scripts`](../packages/sdk/scripts) | `sdk` | [`app-boot`](../packages/ui/app-boot) | | [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`llm`](../packages/llm/llm) | | [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`llm`](../packages/llm/llm) | diff --git a/packages/sdk/README.md b/packages/sdk/README.md index 953d52ea76..92c8794e64 100644 --- a/packages/sdk/README.md +++ b/packages/sdk/README.md @@ -9,6 +9,7 @@ The [feature RFC](../../docs/rfc/proposed/feature/2026-07-14-sdk-developer-proje | [`helper`](helper/README.md) | Project aggregate, edit session, builtin features, project documents, templates, package managers, and prompt abstraction | | [`scripts`](scripts/README.md) | The `dsh-sdk` launcher: `start`, `dev`, `build`, and interactive `config` | | [`create-sdk`](create-sdk/README.md) | The `npm create @deepseek-ai/sdk` initializer | +| [`plugin-fetch`](plugin-fetch/README.md) | Fetch an external plugin (github/npm) into a temp dir — pinned and un-executed — for `dsh-sdk create` | `@deepseek-ai/create-sdk` is the one package-name exception to the repository's `@deepseek-ai/dsh-*` rule: npm's scoped initializer convention requires that name for `npm create @deepseek-ai/sdk`. diff --git a/packages/sdk/plugin-fetch/README.md b/packages/sdk/plugin-fetch/README.md new file mode 100644 index 0000000000..801dc2a2a6 --- /dev/null +++ b/packages/sdk/plugin-fetch/README.md @@ -0,0 +1,32 @@ +# `@deepseek-ai/dsh-plugin-fetch` + +Fetch an external Cordis plugin into a temp directory — pinned to an immutable commit or integrity and never executed — for the forthcoming `dsh-sdk create ` command. + +The package parses a source spec into a `PluginSource`, dispatches to the matching `PluginFetcher`, and returns a common `FetchedPlugin` (temp dir + immutable provenance) that the wiring step pins into `package.json`, mounts in `cordis.yml`, and installs with `--ignore-scripts`. + +| Export | Role | +|---|---| +| `resolvePluginSource(spec)` → `PluginSource` | Parse `owner/repo[/subdir]#ref` (github) or `pkg@version` (npm); fail loud on an ambiguous or malformed spec | +| `PluginFetcher` | The fetch seam: resolve the pin BEFORE download, extract without executing pulled code | +| `GigetFetcher` / `createGigetFetcher()` | Github fetcher over `@bluwy/giget-core`: resolve `#ref` to a commit SHA, download that SHA | +| `PacoteFetcher` / `createPacoteFetcher()` | Npm fetcher over `pacote`: resolve the manifest, then extract the tarball verified against its integrity | +| `fetchPlugin(source, fetchers)` → `FetchedPlugin` | Dispatch one source to its fetcher by discriminant tag | + +## Safety model — confirm-before-run, not run-on-fetch + +A fetch only downloads and unpacks; it runs no install, no `postinstall`/`prepare`, and no degit-style template actions. + +- **github** uses `@bluwy/giget-core` (one runtime dependency, `modern-tar`; no CLI, install, or JSON-registry surface) so a fetch can only download and untar a tarball. The commit is pinned first: `GigetFetcher` resolves `#ref` — or the default branch when absent — to an immutable SHA via the GitHub commits API, then downloads that SHA. Provenance carries the SHA so wiring pins `github:owner/repo#`. +- **npm** uses `pacote`. Registry-only is enforced upstream: `resolvePluginSource` produces only a `name@version` registry spec, so pacote never sees a git/file/dir spec whose lifecycle scripts would run, and a registry tarball extract is a plain untar. The manifest is resolved first so extract verifies the artifact against the registry-published integrity (a mismatch raises `EINTEGRITY`). Provenance carries the exact version, resolved URL, and integrity. + +Both network boundaries (giget download, GitHub ref resolution, pacote, temp-dir allocation) are constructor-injected, so the fetch logic is unit-tested without network; the `create*Fetcher()` factories wire the real libraries. + +## Model Experience + +None, as this developer tooling acquires plugin sources for the SDK launcher and registers no live agent or model surface. + +## Known Limitations and Deferred Work + +- **Wiring is not here yet** — pinning `package.json`, mounting `cordis.yml` through `ProjectEditSession` with a confirmed diff, and `install --ignore-scripts` land with the `dsh-sdk create` command. This package stops at a fetched, pinned temp directory. +- **npm registry authentication** — `PacoteFetcher` targets a public or default-configured registry; private-registry auth beyond pacote's ambient npm config is deferred. +- **Template-repo initialization** — the whole-project init mode (`dsh-sdk create` from a template repository) is out of scope; this package fetches a single plugin into an existing project. diff --git a/packages/sdk/plugin-fetch/package.json b/packages/sdk/plugin-fetch/package.json new file mode 100644 index 0000000000..e8e38090e6 --- /dev/null +++ b/packages/sdk/plugin-fetch/package.json @@ -0,0 +1,37 @@ +{ + "name": "@deepseek-ai/dsh-plugin-fetch", + "description": "Fetch an external Cordis plugin (github or npm) into a temp dir, pinned and un-executed, for dsh-sdk create", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "dependencies": { + "@bluwy/giget-core": "^0.1.7", + "pacote": "^22.0.0" + }, + "peerDependencies": { + "@deepseek-ai/dsh-brand": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "devDependencies": { + "@deepseek-ai/dsh-brand": "workspace:^", + "@types/pacote": "^11.1.8", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/sdk/plugin-fetch/src/fetcher.ts b/packages/sdk/plugin-fetch/src/fetcher.ts new file mode 100644 index 0000000000..7c3d3a763c --- /dev/null +++ b/packages/sdk/plugin-fetch/src/fetcher.ts @@ -0,0 +1,90 @@ +/** + * The `PluginFetcher` seam, its common `FetchedPlugin` result, and the + * tag-dispatched entry point. A fetcher acquires one plugin source into a fresh + * temp directory WITHOUT executing any pulled code, and reports immutable + * provenance the wiring step pins the dependency to. + * + * @module @deepseek-ai/dsh-plugin-fetch/fetcher + */ + +import { mkdtemp } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { assertNever } from './never.ts' +import type { CommitSha, Integrity } from './ids.ts' +import type { GithubSource, NpmSource, PluginSource } from './source.ts' + +/** Immutable pin for a github fetch: the resolved commit the tarball came from. */ +export interface GithubProvenance { + readonly kind: 'github' + readonly sha: CommitSha +} + +/** Immutable pin for an npm fetch: exact version, tarball URL, and integrity. */ +export interface NpmProvenance { + readonly kind: 'npm' + /** Concrete resolved version (e.g. `1.2.3`), never the requested range/tag. */ + readonly version: string + /** Tarball URL the artifact resolved to. */ + readonly resolved: string + /** Subresource integrity the artifact was verified against. */ + readonly integrity: Integrity +} + +/** Provenance a fetch records so wiring can pin an immutable dependency. */ +export type PluginProvenance = GithubProvenance | NpmProvenance + +/** The common result of fetching any plugin source. */ +export interface FetchedPlugin { + /** Absolute temp directory holding the extracted, UN-executed source. */ + readonly dir: string + /** The source that produced this fetch, echoed for the wiring step. */ + readonly source: PluginSource + /** Immutable provenance to pin the dependency during wiring. */ + readonly provenance: PluginProvenance +} + +/** + * A fetcher for one source kind. Implementations resolve the immutable pin + * BEFORE download and must never run lifecycle scripts or template actions. + */ +export interface PluginFetcher { + /** The single source kind this fetcher handles. */ + readonly kind: S['kind'] + /** + * Fetch one source into a fresh temp directory. + * @param source - the resolved source to fetch. + * @returns the temp dir plus immutable provenance. + */ + fetch(source: S): Promise +} + +/** The per-kind fetchers {@link fetchPlugin} dispatches across. */ +export interface PluginFetchers { + readonly github: PluginFetcher + readonly npm: PluginFetcher +} + +/** + * Dispatch one source to its fetcher by discriminant tag. + * @param source - the resolved plugin source. + * @param fetchers - the per-kind fetchers to route across. + * @returns the fetch result from the matching fetcher. + */ +export function fetchPlugin(source: PluginSource, fetchers: PluginFetchers): Promise { + switch (source.kind) { + case 'github': return fetchers.github.fetch(source) + case 'npm': return fetchers.npm.fetch(source) + default: return assertNever(source, 'fetchPlugin') + } +} + +/** + * Create a fresh, empty temp directory for one fetch — the default temp-dir + * seam shared by the concrete fetchers. + * @param prefix - a `mkdtemp` name prefix identifying the fetch kind. + * @returns the absolute path of the created directory. + */ +export function createTempDir(prefix: string): Promise { + return mkdtemp(join(tmpdir(), prefix)) +} diff --git a/packages/sdk/plugin-fetch/src/giget-fetcher.ts b/packages/sdk/plugin-fetch/src/giget-fetcher.ts new file mode 100644 index 0000000000..55e001063c --- /dev/null +++ b/packages/sdk/plugin-fetch/src/giget-fetcher.ts @@ -0,0 +1,116 @@ +/** + * The github {@link PluginFetcher}, backed by `@bluwy/giget-core`. + * + * `@bluwy/giget-core` is chosen over unjs `giget`: it carries a single runtime + * dependency (`modern-tar`) versus giget's CLI/registry stack, and it dropped + * the `install` and JSON-registry options entirely, so a fetch can only ever + * download and untar a tarball — never run install or degit-style actions. That + * is exactly the "extract, never execute" guarantee this feature needs. + * + * The commit is pinned BEFORE download: {@link GigetFetcher} resolves `#ref` to + * an immutable SHA (default via the GitHub commits API), then downloads that + * SHA. Provenance carries the SHA so wiring pins `github:owner/repo#`. + * + * @module @deepseek-ai/dsh-plugin-fetch/giget-fetcher + */ + +import { downloadTemplate } from '@bluwy/giget-core' +import { createTempDir, type FetchedPlugin, type PluginFetcher } from './fetcher.ts' +import { commitSha, type CommitSha } from './ids.ts' +import type { GithubSource } from './source.ts' + +/** Temp-dir name prefix for github fetches. */ +export const GITHUB_TEMP_PREFIX = 'dsh-plugin-github-' + +/** Downloads a giget input string into `dir`; the tarball-extraction seam. */ +export type DownloadTemplate = ( + input: string, + options: { dir: string; force: 'clean' }, +) => Promise<{ dir: string }> + +/** Resolves a github source's ref to an immutable commit SHA before download. */ +export type ResolveRef = (source: GithubSource) => Promise + +/** The injected collaborators a {@link GigetFetcher} needs. */ +export interface GigetFetcherDeps { + /** Downloads a pinned giget input into a directory. */ + download: DownloadTemplate + /** Resolves `source.ref` (or the default branch) to a commit SHA. */ + resolveRef: ResolveRef + /** Allocates the fresh temp directory to download into. */ + createTempDir: (prefix: string) => Promise +} + +/** Build the giget input string that pins a github source to a commit SHA. */ +function gigetInput(source: GithubSource, sha: CommitSha): string { + const path = source.subdir ? `${source.owner}/${source.repo}/${source.subdir}` : `${source.owner}/${source.repo}` + return `${path}#${sha}` +} + +/** A human-readable label for one github source, for error messages. */ +function githubLabel(source: GithubSource): string { + return `${source.owner}/${source.repo}#${source.ref ?? 'HEAD'}` +} + +/** + * Resolve a github source's ref to an immutable SHA via the GitHub commits API. + * Uses the `application/vnd.github.sha` media type, which returns the resolved + * commit id as plain text. + * @param source - the github source; an absent `ref` resolves the default branch (`HEAD`). + * @param token - optional bearer token for private repositories. + * @returns the resolved immutable commit SHA. + * @throws if the GitHub API rejects the request. + */ +export async function defaultResolveRef(source: GithubSource, token?: string): Promise { + const ref = source.ref ?? 'HEAD' + const url = `https://api.github.com/repos/${source.owner}/${source.repo}/commits/${ref}` + const headers: Record = { Accept: 'application/vnd.github.sha' } + if (token !== undefined) headers.Authorization = `Bearer ${token}` + const response = await fetch(url, { headers }) + if (!response.ok) { + throw new Error(`cannot resolve github ref ${githubLabel(source)}: HTTP ${response.status}`) + } + return commitSha((await response.text()).trim()) +} + +/** Fetches a github plugin source by pinning `#ref` to a commit SHA, then downloading it. */ +export class GigetFetcher implements PluginFetcher { + readonly kind = 'github' as const + private readonly deps: GigetFetcherDeps + + /** Construct with injected download, ref-resolution, and temp-dir seams. */ + constructor(deps: GigetFetcherDeps) { + this.deps = deps + } + + async fetch(source: GithubSource): Promise { + const sha = await this.deps.resolveRef(source) + const dir = await this.deps.createTempDir(GITHUB_TEMP_PREFIX) + await this.deps.download(gigetInput(source, sha), { dir, force: 'clean' }) + return { dir, source, provenance: { kind: 'github', sha } } + } +} + +/** Options for the production github fetcher. */ +export interface GithubFetchOptions { + /** Bearer token for private repositories; defaults to `GITHUB_TOKEN`. */ + token?: string +} + +/** + * Build the production github fetcher wired to `@bluwy/giget-core` and the + * GitHub commits API. + * @param options - optional token override (else `process.env.GITHUB_TOKEN`). + * @returns a {@link GigetFetcher} using the real download and ref-resolution seams. + */ +export function createGigetFetcher(options: GithubFetchOptions = {}): GigetFetcher { + const token = options.token ?? process.env.GITHUB_TOKEN + return new GigetFetcher({ + download: (input, downloadOptions) => downloadTemplate(input, { + ...downloadOptions, + ...token !== undefined ? { providerOptions: { auth: token } } : {}, + }), + resolveRef: source => defaultResolveRef(source, token), + createTempDir, + }) +} diff --git a/packages/sdk/plugin-fetch/src/ids.ts b/packages/sdk/plugin-fetch/src/ids.ts new file mode 100644 index 0000000000..a3a2ffa575 --- /dev/null +++ b/packages/sdk/plugin-fetch/src/ids.ts @@ -0,0 +1,39 @@ +/** + * Branded provenance identities owned by the plugin-fetch layer. Both cross the + * fetch → wiring boundary and are opaque tokens that must not be confused with + * ordinary strings (a package name, a URL) at that seam. + * + * @module @deepseek-ai/dsh-plugin-fetch/ids + */ + +import type { Branded } from '@deepseek-ai/dsh-brand' + +/** An immutable git commit object id a github fetch pins to. */ +export type CommitSha = Branded<'CommitSha'> + +/** + * Construct a {@link CommitSha}, validating the hexadecimal object-id shape. + * @param value - lowercase hex of an abbreviated or full commit id (7–64 chars, covering SHA-1 and SHA-256). + * @returns the branded commit id. + */ +export function commitSha(value: string): CommitSha { + if (!/^[0-9a-f]{7,64}$/.test(value)) { + throw new Error(`invalid commit sha: ${JSON.stringify(value)}`) + } + return value as CommitSha +} + +/** A Subresource Integrity string an npm fetch pins to. */ +export type Integrity = Branded<'Integrity'> + +/** + * Construct an {@link Integrity}, validating the SRI `-` shape. + * @param value - a single SRI entry using sha256, sha384, or sha512. + * @returns the branded integrity string. + */ +export function integrity(value: string): Integrity { + if (!/^sha(256|384|512)-[A-Za-z0-9+/]+={0,2}$/.test(value)) { + throw new Error(`invalid subresource integrity: ${JSON.stringify(value)}`) + } + return value as Integrity +} diff --git a/packages/sdk/plugin-fetch/src/index.ts b/packages/sdk/plugin-fetch/src/index.ts new file mode 100644 index 0000000000..d4b9682ff5 --- /dev/null +++ b/packages/sdk/plugin-fetch/src/index.ts @@ -0,0 +1,48 @@ +/** + * Fetch an external Cordis plugin (github or npm) into a temp directory — + * pinned to an immutable commit/integrity and never executed — for the + * `dsh-sdk create ` command. Parses a source spec, dispatches to the + * matching fetcher, and returns a common {@link FetchedPlugin} the wiring step + * pins and mounts. + * + * @module @deepseek-ai/dsh-plugin-fetch + */ + +export { resolvePluginSource } from './source.ts' +export type { GithubSource, NpmSource, PluginSource } from './source.ts' +export { commitSha, integrity } from './ids.ts' +export type { CommitSha, Integrity } from './ids.ts' +export { createTempDir, fetchPlugin } from './fetcher.ts' +export type { + FetchedPlugin, + GithubProvenance, + NpmProvenance, + PluginFetcher, + PluginFetchers, + PluginProvenance, +} from './fetcher.ts' +export { + createGigetFetcher, + defaultResolveRef, + GigetFetcher, + GITHUB_TEMP_PREFIX, +} from './giget-fetcher.ts' +export type { + DownloadTemplate, + GigetFetcherDeps, + GithubFetchOptions, + ResolveRef, +} from './giget-fetcher.ts' +export { + createPacoteFetcher, + NPM_TEMP_PREFIX, + PacoteFetcher, +} from './pacote-fetcher.ts' +export type { + NpmFetchOptions, + PacoteApi, + PacoteExtractResult, + PacoteFetcherDeps, + PacoteFetchOptions, + PacoteResolution, +} from './pacote-fetcher.ts' diff --git a/packages/sdk/plugin-fetch/src/never.ts b/packages/sdk/plugin-fetch/src/never.ts new file mode 100644 index 0000000000..664ab3293d --- /dev/null +++ b/packages/sdk/plugin-fetch/src/never.ts @@ -0,0 +1,19 @@ +/** + * Exhaustiveness helper for this package's closed unions. Kept local so the + * SDK plugin-fetch tooling stays free of the model-runtime `dsh-llm` dependency + * that owns the shared `assertNever`. + * + * @module @deepseek-ai/dsh-plugin-fetch/never + */ + +/** + * Mark an unreachable closed-union branch. A newly unhandled variant fails + * compilation at the call site; a value that escaped its type throws at runtime. + * @param value - the impossible value; typed `never` so a new variant fails to compile at every call site. + * @param context - optional label prefixed into the throw message. + * @returns never — it always throws, rendering the offending value. + */ +export function assertNever(value: never, context?: string): never { + const rendered = (JSON.stringify(value) as string | undefined) ?? String(value) + throw new Error(`unreachable variant${context ? ` in ${context}` : ''}: ${rendered}`) +} diff --git a/packages/sdk/plugin-fetch/src/pacote-fetcher.ts b/packages/sdk/plugin-fetch/src/pacote-fetcher.ts new file mode 100644 index 0000000000..dfb1d790b8 --- /dev/null +++ b/packages/sdk/plugin-fetch/src/pacote-fetcher.ts @@ -0,0 +1,129 @@ +/** + * The npm {@link PluginFetcher}, backed by `pacote`. + * + * Supply-chain safety comes from three layers: (1) {@link resolvePluginSource} + * only ever produces a registry `name@version` spec, so pacote classifies it as + * a registry source and cannot be steered to a git/file/dir spec whose + * lifecycle scripts would run; (2) a registry tarball extract is a plain untar — + * pacote runs no `prepare`/`postinstall` during {@link PacoteFetcher.fetch}; and + * (3) the later wiring step installs with `--ignore-scripts`. The manifest is + * resolved first so extract verifies the tarball against the registry-published + * integrity (a mismatch raises `EINTEGRITY`). + * + * @module @deepseek-ai/dsh-plugin-fetch/pacote-fetcher + */ + +import { extract as pacoteExtract, manifest as pacoteManifest } from 'pacote' +import { createTempDir, type FetchedPlugin, type PluginFetcher } from './fetcher.ts' +import { integrity } from './ids.ts' +import type { NpmSource } from './source.ts' + +/** Temp-dir name prefix for npm fetches. */ +export const NPM_TEMP_PREFIX = 'dsh-plugin-npm-' + +/** The subset of pacote options this fetcher passes through. */ +export interface PacoteFetchOptions { + /** Registry to resolve against; absent uses pacote's default. */ + registry?: string + /** Known resolved tarball URL, forwarded to extract. */ + resolved?: string + /** Expected integrity, forwarded to extract for `EINTEGRITY` verification. */ + integrity?: string +} + +/** The resolved registry manifest fields this fetcher pins from. */ +export interface PacoteResolution { + /** Resolved tarball URL. */ + _resolved: string + /** Registry-published integrity. */ + _integrity: string + /** Concrete resolved version. */ + version: string +} + +/** The extract result fields this fetcher pins from. */ +export interface PacoteExtractResult { + /** Resolved tarball URL of the extracted artifact. */ + resolved: string + /** Integrity of the extracted artifact. */ + integrity: string +} + +/** The pacote surface a {@link PacoteFetcher} depends on; the fetch seam. */ +export interface PacoteApi { + /** Resolve a registry spec to its pinned manifest fields. */ + manifest: (spec: string, options?: PacoteFetchOptions) => Promise + /** Untar a registry spec into `dest`, verifying integrity when supplied. */ + extract: (spec: string, dest: string, options?: PacoteFetchOptions) => Promise +} + +/** The injected collaborators a {@link PacoteFetcher} needs. */ +export interface PacoteFetcherDeps { + /** The pacote resolve/extract surface. */ + pacote: PacoteApi + /** Allocates the fresh temp directory to extract into. */ + createTempDir: (prefix: string) => Promise + /** Registry to resolve against; absent uses pacote's default. */ + registry?: string +} + +/** Fetches an npm plugin source by resolving its manifest, then extracting the verified tarball. */ +export class PacoteFetcher implements PluginFetcher { + readonly kind = 'npm' as const + private readonly deps: PacoteFetcherDeps + + /** Construct with injected pacote, temp-dir, and optional registry seams. */ + constructor(deps: PacoteFetcherDeps) { + this.deps = deps + } + + async fetch(source: NpmSource): Promise { + const spec = `${source.name}@${source.version}` + const registryOptions: PacoteFetchOptions = this.deps.registry !== undefined + ? { registry: this.deps.registry } + : {} + const resolution = await this.deps.pacote.manifest(spec, registryOptions) + const dir = await this.deps.createTempDir(NPM_TEMP_PREFIX) + const extracted = await this.deps.pacote.extract(spec, dir, { + ...registryOptions, + resolved: resolution._resolved, + integrity: resolution._integrity, + }) + return { + dir, + source, + provenance: { + kind: 'npm', + version: resolution.version, + resolved: extracted.resolved, + integrity: integrity(extracted.integrity), + }, + } + } +} + +/** Options for the production npm fetcher. */ +export interface NpmFetchOptions { + /** Registry to resolve against; absent uses pacote's default. */ + registry?: string +} + +/** + * Build the production npm fetcher wired to `pacote`. + * @param options - optional registry override. + * @returns a {@link PacoteFetcher} using the real pacote resolve/extract seam. + */ +export function createPacoteFetcher(options: NpmFetchOptions = {}): PacoteFetcher { + const pacote: PacoteApi = { + manifest: async (spec, pacoteOptions) => { + const resolved = await pacoteManifest(spec, pacoteOptions) + return { _resolved: resolved._resolved, _integrity: resolved._integrity, version: resolved.version } + }, + extract: (spec, dest, pacoteOptions) => pacoteExtract(spec, dest, pacoteOptions), + } + return new PacoteFetcher({ + pacote, + createTempDir, + ...options.registry !== undefined ? { registry: options.registry } : {}, + }) +} diff --git a/packages/sdk/plugin-fetch/src/source.ts b/packages/sdk/plugin-fetch/src/source.ts new file mode 100644 index 0000000000..7d7e3ffcc4 --- /dev/null +++ b/packages/sdk/plugin-fetch/src/source.ts @@ -0,0 +1,126 @@ +/** + * The `PluginSource` discriminated union and the resolver that parses one CLI + * spec string into it. Ambiguous or malformed specs fail loud here — the single + * earliest resolvable point — rather than surfacing as a confusing fetch error. + * + * Grammar: + * - github: `owner/repo[/subdir]#ref` — a `#` unambiguously marks a github ref; + * `ref` is optional and, when omitted, the fetcher pins the default branch. + * - npm: `pkg@version` (scoped `@scope/pkg@version`) — the `@version` is the + * only disambiguator from a bare `owner/repo` github locator. + * + * @module @deepseek-ai/dsh-plugin-fetch/source + */ + +/** A plugin pulled from a github (git tarball) repository. */ +export interface GithubSource { + readonly kind: 'github' + /** Repository owner (user or org). */ + readonly owner: string + /** Repository name. */ + readonly repo: string + /** Path within the repository to extract; absent means the repository root. */ + readonly subdir?: string + /** Branch, tag, or commit; absent means the repository's default branch. */ + readonly ref?: string +} + +/** A plugin pulled from an npm registry by exact package and version spec. */ +export interface NpmSource { + readonly kind: 'npm' + /** Package name, including any `@scope/` prefix. */ + readonly name: string + /** Registry version, range, or dist-tag (non-empty). */ + readonly version: string +} + +/** Every plugin origin `dsh-sdk create ` understands. */ +export type PluginSource = GithubSource | NpmSource + +/** One `/`-separated github name segment (owner, repo, or subdir component). */ +function isNameSegment(segment: string): boolean { + return /^[A-Za-z0-9._-]+$/.test(segment) && segment !== '.' && segment !== '..' +} + +/** A git ref: branch, tag, or commit; permits `/`-nested names, rejects traversal. */ +function isGitRef(ref: string): boolean { + return /^[A-Za-z0-9._/-]+$/.test(ref) + && !ref.includes('..') + && !ref.startsWith('/') + && !ref.endsWith('/') +} + +/** An npm package name, scoped (`@scope/name`) or unscoped. */ +function isNpmPackageName(name: string): boolean { + const segment = /^[a-z0-9][a-z0-9._-]*$/ + if (name.startsWith('@')) { + const slash = name.indexOf('/') + if (slash < 2 || slash === name.length - 1) return false + return segment.test(name.slice(1, slash)) && segment.test(name.slice(slash + 1)) + } + return segment.test(name) +} + +/** Parse a `owner/repo[/subdir]` locator with an optional already-split ref. */ +function tryParseGithubLocator(locator: string, ref: string | undefined): GithubSource | undefined { + if (!/^[^\s@#]+$/.test(locator)) return undefined + const [owner, repo, ...subdirSegments] = locator.split('/') + if (owner === undefined || repo === undefined) return undefined + if (!isNameSegment(owner) || !isNameSegment(repo)) return undefined + if (subdirSegments.some(segment => !isNameSegment(segment))) return undefined + if (ref !== undefined && !isGitRef(ref)) return undefined + const subdir = subdirSegments.join('/') + return { + kind: 'github', + owner, + repo, + ...subdir.length > 0 ? { subdir } : {}, + ...ref !== undefined ? { ref } : {}, + } +} + +/** Parse `pkg@version` (scoped or unscoped); undefined when it is not npm-shaped. */ +function tryParseNpmSource(spec: string): NpmSource | undefined { + if (/[\s#]/.test(spec)) return undefined + // A scoped spec's version `@` follows the scope's `/`; an unscoped spec's is + // the first `@`. A leading `@` with no version `@` yields index 0 (rejected). + const versionAt = spec.startsWith('@') ? spec.indexOf('@', spec.indexOf('/') + 1) : spec.indexOf('@') + if (versionAt <= 0) return undefined + const name = spec.slice(0, versionAt) + const version = spec.slice(versionAt + 1) + if (version.length === 0 || version.includes('/')) return undefined + if (!isNpmPackageName(name)) return undefined + return { kind: 'npm', name, version } +} + +/** + * Parse one `dsh-sdk create ` spec into a {@link PluginSource}. + * @param spec - the raw source argument. + * @returns the discriminated source. + * @throws if the spec is empty, malformed, or ambiguous between github and npm. + */ +export function resolvePluginSource(spec: string): PluginSource { + const trimmed = spec.trim() + if (trimmed.length === 0) throw new Error('plugin source must not be empty') + + const hashIndex = trimmed.indexOf('#') + if (hashIndex !== -1) { + const ref = trimmed.slice(hashIndex + 1) + if (ref.length === 0) { + throw new Error(`github plugin source is missing a ref after '#': ${JSON.stringify(spec)}`) + } + const source = tryParseGithubLocator(trimmed.slice(0, hashIndex), ref) + if (!source) { + throw new Error(`invalid github plugin source: ${JSON.stringify(spec)} — expected "owner/repo[/subdir]#ref"`) + } + return source + } + + const npm = tryParseNpmSource(trimmed) + if (npm) return npm + const github = tryParseGithubLocator(trimmed, undefined) + if (github) return github + throw new Error( + `unrecognized plugin source: ${JSON.stringify(spec)} — expected "owner/repo[/subdir]#ref" (github) or "pkg@version" (npm)`, + ) +} diff --git a/packages/sdk/plugin-fetch/tests/fetcher.spec.ts b/packages/sdk/plugin-fetch/tests/fetcher.spec.ts new file mode 100644 index 0000000000..b68a3d3ae1 --- /dev/null +++ b/packages/sdk/plugin-fetch/tests/fetcher.spec.ts @@ -0,0 +1,64 @@ +import { rm, stat } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { describe, expect, it, vi } from 'vitest' +import { + createTempDir, + fetchPlugin, + type FetchedPlugin, + type PluginFetchers, +} from '../src/fetcher.ts' +import { commitSha } from '../src/ids.ts' +import type { GithubSource, NpmSource, PluginSource } from '../src/source.ts' + +function stubFetchers(): { fetchers: PluginFetchers; github: ReturnType; npm: ReturnType } { + const result = (dir: string): FetchedPlugin => ({ + dir, + source: { kind: 'github', owner: 'o', repo: 'r' }, + provenance: { kind: 'github', sha: commitSha('a'.repeat(40)) }, + }) + const github = vi.fn(async (source: GithubSource) => result(`github:${source.repo}`)) + const npm = vi.fn(async (source: NpmSource) => result(`npm:${source.name}`)) + return { + fetchers: { github: { kind: 'github', fetch: github }, npm: { kind: 'npm', fetch: npm } }, + github, + npm, + } +} + +describe('fetchPlugin', () => { + it('routes a github source to the github fetcher', async () => { + const { fetchers, github, npm } = stubFetchers() + const source: GithubSource = { kind: 'github', owner: 'o', repo: 'r' } + const result = await fetchPlugin(source, fetchers) + expect(github).toHaveBeenCalledWith(source) + expect(npm).not.toHaveBeenCalled() + expect(result.dir).toBe('github:r') + }) + + it('routes an npm source to the npm fetcher', async () => { + const { fetchers, github, npm } = stubFetchers() + const source: NpmSource = { kind: 'npm', name: 'plugin', version: '1.0.0' } + const result = await fetchPlugin(source, fetchers) + expect(npm).toHaveBeenCalledWith(source) + expect(github).not.toHaveBeenCalled() + expect(result.dir).toBe('npm:plugin') + }) + + it('throws on an unknown source kind', () => { + const { fetchers } = stubFetchers() + const bogus = { kind: 'svn' } as unknown as PluginSource + expect(() => fetchPlugin(bogus, fetchers)).toThrow(/unreachable variant in fetchPlugin/) + }) +}) + +describe('createTempDir', () => { + it('creates a fresh empty directory under the OS temp root', async () => { + const dir = await createTempDir('dsh-plugin-fetch-test-') + try { + expect(dir.startsWith(tmpdir())).toBe(true) + expect((await stat(dir)).isDirectory()).toBe(true) + } finally { + await rm(dir, { recursive: true, force: true }) + } + }) +}) diff --git a/packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts b/packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts new file mode 100644 index 0000000000..c0cafb31d5 --- /dev/null +++ b/packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts @@ -0,0 +1,145 @@ +import { afterEach, beforeEach, describe, expect, it, type Mock, vi } from 'vitest' +import { downloadTemplate } from '@bluwy/giget-core' +import { + createGigetFetcher, + defaultResolveRef, + GigetFetcher, + GITHUB_TEMP_PREFIX, + type GigetFetcherDeps, +} from '../src/giget-fetcher.ts' +import type { CommitSha } from '../src/ids.ts' +import type { GithubSource } from '../src/source.ts' + +vi.mock('@bluwy/giget-core', () => ({ downloadTemplate: vi.fn(async (_input: string, options: { dir: string }) => ({ dir: options.dir, source: '', info: { name: '', tar: '' } })) })) + +const SHA = 'a'.repeat(40) + +/** A `fetch` mock typed with the call signature the assertions destructure. */ +function fetchReturning(response: Response): Mock<(url: string, init?: RequestInit) => Promise> { + return vi.fn((_url: string, _init?: RequestInit) => Promise.resolve(response)) +} + +function fakeDeps(overrides: Partial = {}): { + deps: GigetFetcherDeps + download: ReturnType + resolveRef: ReturnType + createTempDir: ReturnType +} { + const download = vi.fn(async () => ({ dir: '/tmp/x' })) + const resolveRef = vi.fn(async () => SHA as CommitSha) + const createTempDir = vi.fn(async () => '/tmp/dsh-plugin-github-abc') + return { deps: { download, resolveRef, createTempDir, ...overrides }, download, resolveRef, createTempDir } +} + +describe('GigetFetcher.fetch', () => { + it('pins the ref to a SHA, downloads that SHA, and reports provenance', async () => { + const { deps, download, resolveRef, createTempDir } = fakeDeps() + const source: GithubSource = { kind: 'github', owner: 'unjs', repo: 'template', ref: 'main' } + const result = await new GigetFetcher(deps).fetch(source) + + expect(resolveRef).toHaveBeenCalledWith(source) + expect(createTempDir).toHaveBeenCalledWith(GITHUB_TEMP_PREFIX) + expect(download).toHaveBeenCalledWith(`unjs/template#${SHA}`, { dir: '/tmp/dsh-plugin-github-abc', force: 'clean' }) + expect(result).toEqual({ + dir: '/tmp/dsh-plugin-github-abc', + source, + provenance: { kind: 'github', sha: SHA }, + }) + }) + + it('includes the subdir in the download input', async () => { + const { deps, download } = fakeDeps() + const source: GithubSource = { kind: 'github', owner: 'o', repo: 'r', subdir: 'packages/plugin' } + await new GigetFetcher(deps).fetch(source) + expect(download).toHaveBeenCalledWith(`o/r/packages/plugin#${SHA}`, expect.anything()) + }) + + it('exposes its source kind', () => { + expect(new GigetFetcher(fakeDeps().deps).kind).toBe('github') + }) +}) + +describe('defaultResolveRef', () => { + afterEach(() => vi.unstubAllGlobals()) + + it('resolves the default branch (HEAD) with no auth header', async () => { + const fetchMock = fetchReturning(new Response(`${SHA}\n`, { status: 200 })) + vi.stubGlobal('fetch', fetchMock) + const sha = await defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r' }) + expect(sha).toBe(SHA) + const [url, init] = fetchMock.mock.calls[0]! + expect(url).toBe('https://api.github.com/repos/o/r/commits/HEAD') + expect((init as RequestInit).headers).toEqual({ Accept: 'application/vnd.github.sha' }) + }) + + it('resolves an explicit ref and sends a bearer token', async () => { + const fetchMock = fetchReturning(new Response(SHA, { status: 200 })) + vi.stubGlobal('fetch', fetchMock) + const sha = await defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r', ref: 'v1.2.3' }, 'secret') + expect(sha).toBe(SHA) + const [url, init] = fetchMock.mock.calls[0]! + expect(url).toBe('https://api.github.com/repos/o/r/commits/v1.2.3') + expect((init as RequestInit).headers).toEqual({ + Accept: 'application/vnd.github.sha', + Authorization: 'Bearer secret', + }) + }) + + it('throws with the HEAD label when the API rejects an unref-ed source', async () => { + vi.stubGlobal('fetch', fetchReturning(new Response('', { status: 404 }))) + await expect(defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r' })).rejects.toThrow( + /cannot resolve github ref o\/r#HEAD: HTTP 404/, + ) + }) + + it('throws with the explicit-ref label when the API rejects', async () => { + vi.stubGlobal('fetch', fetchReturning(new Response('', { status: 403 }))) + await expect( + defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r', ref: 'main' }), + ).rejects.toThrow(/cannot resolve github ref o\/r#main: HTTP 403/) + }) +}) + +describe('createGigetFetcher', () => { + const downloadMock = vi.mocked(downloadTemplate) + let savedToken: string | undefined + + beforeEach(() => { + downloadMock.mockClear() + savedToken = process.env.GITHUB_TOKEN + delete process.env.GITHUB_TOKEN + }) + + afterEach(() => { + vi.unstubAllGlobals() + if (savedToken === undefined) delete process.env.GITHUB_TOKEN + else process.env.GITHUB_TOKEN = savedToken + }) + + it('wires the real download without provider auth when no token is present', async () => { + vi.stubGlobal('fetch', fetchReturning(new Response(SHA, { status: 200 }))) + await createGigetFetcher().fetch({ kind: 'github', owner: 'o', repo: 'r', ref: 'main' }) + const [input, options] = downloadMock.mock.calls[0]! + expect(input).toBe(`o/r#${SHA}`) + expect(options?.dir).toContain(GITHUB_TEMP_PREFIX) + expect(options?.force).toBe('clean') + expect(options?.providerOptions).toBeUndefined() + }) + + it('passes an explicit token to both ref resolution and provider auth', async () => { + const fetchMock = fetchReturning(new Response(SHA, { status: 200 })) + vi.stubGlobal('fetch', fetchMock) + await createGigetFetcher({ token: 'tok' }).fetch({ kind: 'github', owner: 'o', repo: 'r' }) + expect((fetchMock.mock.calls[0]![1] as RequestInit).headers).toMatchObject({ Authorization: 'Bearer tok' }) + const [, options] = downloadMock.mock.calls[0]! + expect(options).toMatchObject({ providerOptions: { auth: 'tok' } }) + }) + + it('reads GITHUB_TOKEN from the environment', async () => { + process.env.GITHUB_TOKEN = 'from-env' + vi.stubGlobal('fetch', fetchReturning(new Response(SHA, { status: 200 }))) + await createGigetFetcher().fetch({ kind: 'github', owner: 'o', repo: 'r' }) + const [, options] = downloadMock.mock.calls[0]! + expect(options).toMatchObject({ providerOptions: { auth: 'from-env' } }) + }) +}) diff --git a/packages/sdk/plugin-fetch/tests/ids.spec.ts b/packages/sdk/plugin-fetch/tests/ids.spec.ts new file mode 100644 index 0000000000..2f1ba6f518 --- /dev/null +++ b/packages/sdk/plugin-fetch/tests/ids.spec.ts @@ -0,0 +1,39 @@ +import { describe, expect, it } from 'vitest' +import { commitSha, integrity } from '../src/ids.ts' + +describe('commitSha', () => { + it('accepts abbreviated and full lowercase hex object ids', () => { + expect(commitSha('abc1234')).toBe('abc1234') + expect(commitSha('a'.repeat(40))).toBe('a'.repeat(40)) + expect(commitSha('0'.repeat(64))).toBe('0'.repeat(64)) + }) + + it.each([ + ['too short', 'abc123'], + ['uppercase', 'ABCDEF1'], + ['non-hex', 'ghijklm'], + ['too long', 'a'.repeat(65)], + ['empty', ''], + ])('rejects an invalid sha (%s)', (_label, value) => { + expect(() => commitSha(value)).toThrow(/invalid commit sha/) + }) +}) + +describe('integrity', () => { + it.each([ + 'sha512-abcABC123+/==', + 'sha384-abcABC123+/', + 'sha256-Zm9vYmFy', + ])('accepts a valid SRI entry (%s)', (value) => { + expect(integrity(value)).toBe(value) + }) + + it.each([ + ['missing algorithm', 'abcABC123'], + ['unsupported algorithm', 'sha1-abcABC123'], + ['illegal base64 char', 'sha512-abc*def'], + ['empty', ''], + ])('rejects an invalid integrity (%s)', (_label, value) => { + expect(() => integrity(value)).toThrow(/invalid subresource integrity/) + }) +}) diff --git a/packages/sdk/plugin-fetch/tests/never.spec.ts b/packages/sdk/plugin-fetch/tests/never.spec.ts new file mode 100644 index 0000000000..224ab66e29 --- /dev/null +++ b/packages/sdk/plugin-fetch/tests/never.spec.ts @@ -0,0 +1,19 @@ +import { describe, expect, it } from 'vitest' +import { assertNever } from '../src/never.ts' + +describe('assertNever', () => { + it('throws with the rendered value and a context label', () => { + expect(() => assertNever('surprise' as never, 'demo')).toThrow( + /unreachable variant in demo: "surprise"/, + ) + }) + + it('omits the context clause when none is given', () => { + expect(() => assertNever(7 as never)).toThrow(/unreachable variant: 7$/) + }) + + it('falls back to String() when the value is not JSON-serializable', () => { + // JSON.stringify(undefined) is undefined, exercising the String() fallback. + expect(() => assertNever(undefined as never)).toThrow(/unreachable variant: undefined$/) + }) +}) diff --git a/packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts b/packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts new file mode 100644 index 0000000000..958e56674e --- /dev/null +++ b/packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts @@ -0,0 +1,108 @@ +import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' +import { extract as pacoteExtract, manifest as pacoteManifest } from 'pacote' +import { + createPacoteFetcher, + NPM_TEMP_PREFIX, + PacoteFetcher, + type PacoteApi, + type PacoteFetcherDeps, +} from '../src/pacote-fetcher.ts' +import type { NpmSource } from '../src/source.ts' + +vi.mock('pacote', () => ({ manifest: vi.fn(), extract: vi.fn() })) + +const INTEGRITY = 'sha512-abcABC123+/==' +const RESOLVED = 'https://registry.npmjs.org/plugin/-/plugin-1.2.3.tgz' + +function fakePacote(): PacoteApi { + return { + manifest: vi.fn(async () => ({ _resolved: RESOLVED, _integrity: INTEGRITY, version: '1.2.3' })), + extract: vi.fn(async () => ({ resolved: RESOLVED, integrity: INTEGRITY })), + } +} + +function deps(overrides: Partial = {}): PacoteFetcherDeps { + return { + pacote: fakePacote(), + createTempDir: vi.fn(async () => '/tmp/dsh-plugin-npm-abc'), + ...overrides, + } +} + +const SOURCE: NpmSource = { kind: 'npm', name: 'plugin', version: '^1.0.0' } + +describe('PacoteFetcher.fetch', () => { + it('resolves the manifest, extracts with integrity, and reports provenance', async () => { + const d = deps() + const result = await new PacoteFetcher(d).fetch(SOURCE) + + expect(d.pacote.manifest).toHaveBeenCalledWith('plugin@^1.0.0', {}) + expect(d.createTempDir).toHaveBeenCalledWith(NPM_TEMP_PREFIX) + expect(d.pacote.extract).toHaveBeenCalledWith('plugin@^1.0.0', '/tmp/dsh-plugin-npm-abc', { + resolved: RESOLVED, + integrity: INTEGRITY, + }) + expect(result).toEqual({ + dir: '/tmp/dsh-plugin-npm-abc', + source: SOURCE, + provenance: { kind: 'npm', version: '1.2.3', resolved: RESOLVED, integrity: INTEGRITY }, + }) + }) + + it('forwards a configured registry to both manifest and extract', async () => { + const d = deps({ registry: 'https://npm.internal/' }) + await new PacoteFetcher(d).fetch(SOURCE) + expect(d.pacote.manifest).toHaveBeenCalledWith('plugin@^1.0.0', { registry: 'https://npm.internal/' }) + expect(d.pacote.extract).toHaveBeenCalledWith('plugin@^1.0.0', '/tmp/dsh-plugin-npm-abc', { + registry: 'https://npm.internal/', + resolved: RESOLVED, + integrity: INTEGRITY, + }) + }) + + it('rejects a registry integrity that is not a valid SRI', async () => { + const pacote = fakePacote() + pacote.extract = vi.fn(async () => ({ resolved: RESOLVED, integrity: 'not-sri' })) + await expect(new PacoteFetcher(deps({ pacote })).fetch(SOURCE)).rejects.toThrow( + /invalid subresource integrity/, + ) + }) + + it('exposes its source kind', () => { + expect(new PacoteFetcher(deps()).kind).toBe('npm') + }) +}) + +describe('createPacoteFetcher', () => { + const manifestMock = vi.mocked(pacoteManifest) + const extractMock = vi.mocked(pacoteExtract) + + beforeEach(() => { + manifestMock.mockReset() + extractMock.mockReset() + // The real overloaded pacote manifest returns a much wider shape; the fetcher reads only these fields. + manifestMock.mockResolvedValue( + { _resolved: RESOLVED, _integrity: INTEGRITY, version: '1.2.3' } as unknown as Awaited< + ReturnType + >, + ) + extractMock.mockResolvedValue({ from: 'plugin@1.2.3', resolved: RESOLVED, integrity: INTEGRITY }) + }) + + afterEach(() => vi.clearAllMocks()) + + it('wires the real pacote resolve/extract surface', async () => { + const result = await createPacoteFetcher().fetch(SOURCE) + expect(manifestMock).toHaveBeenCalledWith('plugin@^1.0.0', {}) + expect(extractMock).toHaveBeenCalledWith('plugin@^1.0.0', expect.stringContaining(NPM_TEMP_PREFIX), { + resolved: RESOLVED, + integrity: INTEGRITY, + }) + expect(result.provenance).toEqual({ kind: 'npm', version: '1.2.3', resolved: RESOLVED, integrity: INTEGRITY }) + }) + + it('forwards a configured registry through the real surface', async () => { + await createPacoteFetcher({ registry: 'https://npm.internal/' }).fetch(SOURCE) + expect(manifestMock).toHaveBeenCalledWith('plugin@^1.0.0', { registry: 'https://npm.internal/' }) + }) +}) diff --git a/packages/sdk/plugin-fetch/tests/source.spec.ts b/packages/sdk/plugin-fetch/tests/source.spec.ts new file mode 100644 index 0000000000..e585c5dfcf --- /dev/null +++ b/packages/sdk/plugin-fetch/tests/source.spec.ts @@ -0,0 +1,107 @@ +import { describe, expect, it } from 'vitest' +import { resolvePluginSource, type GithubSource, type NpmSource } from '../src/source.ts' + +describe('resolvePluginSource — github', () => { + it('parses owner/repo with a ref', () => { + expect(resolvePluginSource('unjs/template#main')).toEqual({ + kind: 'github', owner: 'unjs', repo: 'template', ref: 'main', + }) + }) + + it('parses a bare owner/repo without a ref', () => { + expect(resolvePluginSource('deepseek-ai/plugin')).toEqual({ + kind: 'github', owner: 'deepseek-ai', repo: 'plugin', + }) + }) + + it('parses a nested subdir with a ref', () => { + expect(resolvePluginSource('owner/repo/packages/plugin#v1.2.3')).toEqual({ + kind: 'github', owner: 'owner', repo: 'repo', subdir: 'packages/plugin', ref: 'v1.2.3', + }) + }) + + it('parses a subdir without a ref', () => { + expect(resolvePluginSource('owner/repo/sub')).toEqual({ + kind: 'github', owner: 'owner', repo: 'repo', subdir: 'sub', + }) + }) + + it('accepts a slash-nested ref', () => { + expect(resolvePluginSource('owner/repo#feature/x')).toEqual({ + kind: 'github', owner: 'owner', repo: 'repo', ref: 'feature/x', + }) + }) + + it('trims surrounding whitespace before parsing', () => { + expect(resolvePluginSource(' owner/repo#main ')).toEqual({ + kind: 'github', owner: 'owner', repo: 'repo', ref: 'main', + }) + }) + + it.each([ + ['empty ref after hash', 'owner/repo#'], + ['single locator segment with hash', 'owner#main'], + ['owner with @ and a hash', 'own@er/repo#main'], + ['ref with whitespace', 'owner/repo#bad ref'], + ['ref with traversal', 'owner/repo#a..b'], + ['ref with a leading slash', 'owner/repo#/main'], + ['ref with a trailing slash', 'owner/repo#main/'], + ['ref with an illegal char', 'owner/repo#ma:in'], + ])('rejects a malformed github spec (%s)', (_label, spec) => { + expect(() => resolvePluginSource(spec)).toThrow(/github plugin source|missing a ref/) + }) +}) + +describe('resolvePluginSource — npm', () => { + it('parses an unscoped name@version', () => { + expect(resolvePluginSource('react@18.2.0')).toEqual({ + kind: 'npm', name: 'react', version: '18.2.0', + }) + }) + + it('parses a scoped name@version', () => { + expect(resolvePluginSource('@deepseek-ai/dsh-tool-foo@0.0.1')).toEqual({ + kind: 'npm', name: '@deepseek-ai/dsh-tool-foo', version: '0.0.1', + }) + }) + + it('accepts a dist-tag as the version', () => { + expect(resolvePluginSource('some-plugin@latest')).toEqual({ + kind: 'npm', name: 'some-plugin', version: 'latest', + }) + }) + + it('accepts a range as the version', () => { + expect(resolvePluginSource('some-plugin@^1.0.0')).toEqual({ + kind: 'npm', name: 'some-plugin', version: '^1.0.0', + }) + }) +}) + +describe('resolvePluginSource — failures', () => { + it.each([ + ['empty', ''], + ['whitespace only', ' '], + ])('rejects a blank spec (%s)', (_label, spec) => { + expect(() => resolvePluginSource(spec)).toThrow(/must not be empty/) + }) + + it.each([ + ['bare word', 'plugin'], + ['internal whitespace', 'owner repo'], + ['empty npm version', 'pkg@'], + ['scoped without version', '@scope/pkg'], + ['scoped with empty scope', '@/pkg@1'], + ['unscoped name with slash and version', 'foo/bar@1'], + ['version containing a slash', 'foo@1/2'], + ['uppercase unscoped name', 'FOO@1.0.0'], + ['uppercase scope segment', '@Scope/pkg@1'], + ['uppercase scoped name segment', '@scope/PKG@1'], + ['empty scoped name segment', '@scope/@1'], + ['dot-only owner', './repo'], + ['traversal subdir segment', 'owner/repo/../x'], + ['double slash subdir', 'owner/repo//sub'], + ])('rejects an unrecognized/ambiguous spec (%s)', (_label, spec) => { + expect(() => resolvePluginSource(spec)).toThrow(/unrecognized plugin source|github plugin source/) + }) +}) diff --git a/packages/sdk/plugin-fetch/tsconfig.json b/packages/sdk/plugin-fetch/tsconfig.json new file mode 100644 index 0000000000..07c2567ff8 --- /dev/null +++ b/packages/sdk/plugin-fetch/tsconfig.json @@ -0,0 +1,15 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../util/brand" + } + ] +} diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 9810a9a61e..25a8fadc47 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1223,6 +1223,25 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/sdk/plugin-fetch: + dependencies: + '@bluwy/giget-core': + specifier: ^0.1.7 + version: 0.1.7 + pacote: + specifier: ^22.0.0 + version: 22.0.0 + devDependencies: + '@deepseek-ai/dsh-brand': + specifier: workspace:^ + version: link:../../util/brand + '@types/pacote': + specifier: ^11.1.8 + version: 11.1.8 + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/sdk/scripts: dependencies: '@deepseek-ai/dsh-helper': @@ -2939,6 +2958,10 @@ packages: resolution: {integrity: sha512-6zABk/ECA/QYSCQ1NGiVwwbQerUCZ+TQbp64Q3AgmfNvurHH0j8TtXa1qbShXA6qqkpAj4V5W8pP6mLe1mcMqA==} engines: {node: '>=18'} + '@bluwy/giget-core@0.1.7': + resolution: {integrity: sha512-6XG8TZt8DVYLuGDVSpFJaSMlNowOg5RGecvWbKvlgMoqVbztUAQ3AcWq6oZ5DoCnTzNAPcO7rhkwt8ZVgrS7CQ==} + engines: {node: '>=18'} + '@braintree/sanitize-url@7.1.2': resolution: {integrity: sha512-jigsZK+sMF/cuiB7sERuo9V7N9jx+dhmHHnQyDSVdpZwVutaBu7WvNYqMDLSgFgfB30n452TP3vjDAvFC973mA==} @@ -3392,6 +3415,10 @@ packages: '@noble/hashes': optional: true + '@gar/promise-retry@1.0.3': + resolution: {integrity: sha512-GmzA9ckNokPypTg10pgpeHNQe7ph+iIKKmhKu3Ob9ANkswreCx7R3cKmY781K8QK3AqVL3xVh9A42JvIAbkkSA==} + engines: {node: ^20.17.0 || >=22.9.0} + '@google/genai@1.52.0': resolution: {integrity: sha512-gwSvbpiN/17O9TbsqSsE/OzZcpv5Fo4RQjdngGgogtuB9RsyJ8ZHhX5KjHj1bp5N9snN2eK8LDGXSaWW2hof8Q==} engines: {node: '>=20.0.0'} @@ -3440,6 +3467,10 @@ packages: resolution: {integrity: sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==} engines: {node: '>=12'} + '@isaacs/fs-minipass@4.0.1': + resolution: {integrity: sha512-wgm9Ehl2jpeqP3zw/7mo3kRHFp5MEDhqAdwy1fTGkHAwnkGOVsgpvQhL8B5n1qlb01jV3n/bI0ZfZp5lWA1k4w==} + engines: {node: '>=18.0.0'} + '@jridgewell/gen-mapping@0.3.13': resolution: {integrity: sha512-2kkt/7niJ6MgEPxF0bYdQ6etZaA+fQvDcLKckhy1yIQOzaoKjBBjSj63/aLVjYE3qhRt5dvM+uUyfCg6UKCBbA==} @@ -3486,6 +3517,43 @@ packages: '@nodable/entities@2.2.0': resolution: {integrity: sha512-9uGyhaQavEUMC8AIddIjau4NsnsXhou+j5sBAGojCM1oxmQpVKTWR/9JxABD6UAv12vpIms55fPZKFQEhG6uBg==} + '@npmcli/agent@5.0.2': + resolution: {integrity: sha512-EkzGmEsgbQ1rqWkRJe2P0oQHx/ylZozDUNPMXCklLuSFL3GY+QyEfBUjhjCsgGXzh4OGpnHvkboSQgczjP/jJg==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@npmcli/fs@6.0.0': + resolution: {integrity: sha512-AheOs4swKka/XLtht6xxJDPezlQ7K2IYQ9Y8lST4JLDjnralnWuMM9AE2CdVcgQJ5omrXhsRzM7F7aYmeZBvKQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@npmcli/git@8.0.0': + resolution: {integrity: sha512-5P1oo+TbxZNAiiMBtpzHA8QyEGh5D69LYLexNWJEDXLdxnAZvT/SLitGJBXxjtCE4ftAcFOS/Tu2185MeIjooQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@npmcli/installed-package-contents@5.0.0': + resolution: {integrity: sha512-6Ay12sf2Lh7U1ifvnS1mq7TZFeh/rXHMXye+kV7jQrANIubaoVcleeh4HdFumxhsRYwm9OaHycB5lYmSwGrcIQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + hasBin: true + + '@npmcli/node-gyp@6.0.0': + resolution: {integrity: sha512-MFakpea4pcZNlHSTbMi15HK8RY8zl2UpgDtxhZCWOer+KRN3x7HFIMk/fKpOMgR55L4LIcA2qn8IHeyABhIFtw==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@npmcli/package-json@8.0.0': + resolution: {integrity: sha512-agNZzYQ18MR0wKp3Emg1q5QbcC8CXigYp3Z3CvB0Sax9Ge9aF4cVyyuSG+5SbACSrZUKTvMjVULWiE1RJA38wg==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@npmcli/promise-spawn@10.0.0': + resolution: {integrity: sha512-llZkSzeTsimFx64U+ThT2xQM2uEce8GIQUYvxgbB6ZFvBhV2LP9LeJJb3HT+syG0uCFLsTCHjV9SfC0WNU1vtA==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@npmcli/redact@5.0.0': + resolution: {integrity: sha512-3zcN5Q3yEmeyxXBzqB6fXPQFzYa2ROsGFSr69W0ArXIAGJqxl/aFECOVPD2kbkYPm0U/EHxFKgclK3UA9WQg5A==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@npmcli/run-script@11.0.0': + resolution: {integrity: sha512-leBRl6F5F0TvWut8m1/aZcMTUHi2vXjKeMJ/Ik1lW7Q7Yy16Dhtkklu+cEqQww1p1NeLnUNzV3+uwpzqRcy9vw==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + '@oxc-parser/binding-android-arm-eabi@0.133.0': resolution: {integrity: sha512-l/44caGse+VpnY9gx0yvvc5QnnG3yG1FO3KZgYvNL1GZrfK86zIwAOgGEVlxDyRymzrU/KHiblPFpevKOmJmUA==} engines: {node: ^20.19.0 || >=22.12.0} @@ -4115,6 +4183,30 @@ packages: '@shikijs/vscode-textmate@10.0.2': resolution: {integrity: sha512-83yeghZ2xxin3Nj8z1NMd/NCuca+gsYXswywDy5bHvwlWL8tpTQmzGeUuHd9FC3E/SBEMvzJRwWEOz5gGes9Qg==} + '@sigstore/bundle@5.0.0': + resolution: {integrity: sha512-wefjygudENbzbQMks1t5u34EP0fFoD0XvaEP7DOUP/sXKvogzEJYFw5E6pegGyp3onGWzVEYKVa3bNZWyTYX+A==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@sigstore/core@4.0.1': + resolution: {integrity: sha512-9v5hRjujn5NXq8o7XFEUgLyAtdr5Iisb4pzM05u3K61IS5q3hP3luWAndk0RkPPLTUFoTbg7Vb84UQ1ZQeajWQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@sigstore/protobuf-specs@0.5.1': + resolution: {integrity: sha512-/ScWUhhoFasJsSRGTVBwId1loQjjnjAfE4djL6ZhrXRpNCmPTnUKF5Jokd58ILseOMjzET3UrMOtJPS9sYeI0g==} + engines: {node: ^18.17.0 || >=20.5.0} + + '@sigstore/sign@5.0.0': + resolution: {integrity: sha512-DSFivqz9/i5AkwZ5fq0YdjaJlc4o1WeS2Zffon0kqtChx0vy4W9NOjkEet9bF2vkzOufX72eVH8kZBIGtcBp1w==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@sigstore/tuf@5.0.0': + resolution: {integrity: sha512-Zyqg9tcHps3uRAlKHLNmsW4ohsUZAjb9G+31r7lg0ICh/JOcadzmJsIRdjKljlRHpaR0K4aJ2kXXIdywdcdMlA==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + '@sigstore/verify@4.1.0': + resolution: {integrity: sha512-p/s720RiWxLG8XtmfdPfEJOlATA6H/2knFqmtQbFkHKN3IrhWGUwPfpQAf1UnQIEES9IaH6zzhfjkrhTfeSdZw==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + '@smithy/core@3.24.7': resolution: {integrity: sha512-KoUi4M1f3BG6kzN1FnCwL7oyFptTbyBJKjR6yhSib+JHRdUmM1o+VwsFtJ66NZCkCzVfJMWRHJNo0R0jznp0Pg==} engines: {node: '>=18.0.0'} @@ -4164,6 +4256,14 @@ packages: peerDependencies: eslint: ^9.0.0 || ^10.0.0 + '@tufjs/canonical-json@2.0.0': + resolution: {integrity: sha512-yVtV8zsdo8qFHe+/3kw81dSLyF7D576A5cCFCi4X7B39tWT7SekaEFUnvnWJHz+9qO7qJTah1JbrDjWKqFtdWA==} + engines: {node: ^16.14.0 || >=18.0.0} + + '@tufjs/models@5.0.0': + resolution: {integrity: sha512-U4mVcdFGOi6pt8n38LdWZp67Svn7ppnU1Pj8SGOVaBi1X4gm+G4ztQlLfkoJbKSHfjA6WeaiJp2A4V83AJF6nQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + '@tybys/wasm-util@0.10.2': resolution: {integrity: sha512-RoBvJ2X0wuKlWFIjrwffGw1IqZHKQqzIchKaadZZfnNpsAYp2mM0h36JtPCjNDAHGgYez/15uMBpfGwchhiMgg==} @@ -4311,18 +4411,36 @@ packages: '@types/ms@2.1.0': resolution: {integrity: sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA==} + '@types/node-fetch@2.6.13': + resolution: {integrity: sha512-QGpRVpzSaUs30JBSGPjOg4Uveu384erbHBoT1zeONvyCfwQxIkUshLAOqN/k9EjGviPRmWTTe6aH2qySWKTVSw==} + '@types/node@22.20.0': resolution: {integrity: sha512-QWlFW2wf3nTjC13/DqRnBpR4ZO36VJH/JVBkA/vcnmbTBNQIlnObqyqZE1tUR7+Ni23Lda8R1BxMfbXRpCUx5g==} '@types/node@25.9.3': resolution: {integrity: sha512-603BddQMv3pUcr4U2dhujk83N2tTDVr/34wII2B6bJy6g+8WD6yUb11jszNs0gdi4PesVWl7ABt8nYMVpnLUcg==} + '@types/npm-package-arg@6.1.4': + resolution: {integrity: sha512-vDgdbMy2QXHnAruzlv68pUtXCjmqUk3WrBAsRboRovsOmxbfn/WiYCjmecyKjGztnMps5dWp4Uq2prp+Ilo17Q==} + + '@types/npm-registry-fetch@8.0.9': + resolution: {integrity: sha512-7NxvodR5Yrop3pb6+n8jhJNyzwOX0+6F+iagNEoi9u1CGxruYAwZD8pvGc9prIkL0+FdX5Xp0p80J9QPrGUp/g==} + + '@types/npmlog@7.0.0': + resolution: {integrity: sha512-hJWbrKFvxKyWwSUXjZMYTINsSOY6IclhvGOZ97M8ac2tmR9hMwmTnYaMdpGhvju9ctWLTPhCS+eLfQNluiEjQQ==} + + '@types/pacote@11.1.8': + resolution: {integrity: sha512-/XLR0VoTh2JEO0jJg1q/e6Rh9bxjBq9vorJuQmtT7rRrXSiWz7e7NsvXVYJQ0i8JxMlBMPPYDTnrRe7MZRFA8Q==} + '@types/picomatch@3.0.2': resolution: {integrity: sha512-n0i8TD3UDB7paoMMxA3Y65vUncFJXjcUf7lQY7YyKGl6031FNjfsLs6pdLFCy2GNFxItPJG8GvvpbZc2skH7WA==} '@types/retry@0.12.0': resolution: {integrity: sha512-wWKOClTTiizcZhXnPY4wikVAwmdYHp8q6DmC+EJUzAMsycb7HB32Kh9RN4+0gExjmPmZSAQjgURXIGATPegAvA==} + '@types/ssri@7.1.5': + resolution: {integrity: sha512-odD/56S3B51liILSk5aXJlnYt99S6Rt9EFDDqGtJM26rKHApHcwyU/UoYHrzKkdkHMAIquGWCuHtQTbes+FRQw==} + '@types/tough-cookie@4.0.5': resolution: {integrity: sha512-/Ad8+nIOV7Rl++6f1BdKxFSMgmoqEoYbHRpPcx3JEfv8VRsQe9Z4mCXeJBzxs7mbHY/XOZZuXlRNfhpVPbs6ZA==} @@ -4537,6 +4655,10 @@ packages: resolution: {integrity: sha512-A9gOqLdi6cV4ibazAjcQufGj0B1y/vDqYrcuP6d/6x8P27gRS8643Dj9o1dEKtB6O7fwxb2FgBmJS2mX7gpvdw==} engines: {node: '>=14.6'} + abbrev@5.0.0: + resolution: {integrity: sha512-/XrFJgzQQQHpti1raDJC6m4ws6aNktmjBlhk8Fdlk7LwCEuDoieEJJY9OFHjfiFJFFRM2tK+Ky/IsfbbmlMu1w==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + accepts@2.0.0: resolution: {integrity: sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng==} engines: {node: '>= 0.6'} @@ -4555,6 +4677,10 @@ packages: resolution: {integrity: sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ==} engines: {node: '>= 14'} + agent-base@9.0.0: + resolution: {integrity: sha512-TQf59BsZnytt8GdJKLPfUZ54g/iaUL2OWDSFCCvMOhsHduDQxO8xC4PNeyIkVcA5KwL2phPSv0douC0fgWzmnA==} + engines: {node: '>= 20'} + ajv-formats@3.0.1: resolution: {integrity: sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ==} peerDependencies: @@ -4614,6 +4740,9 @@ packages: ast-v8-to-istanbul@1.0.4: resolution: {integrity: sha512-0bC0/4bTSrnwdhU3IsZDwEdojvuPrSg59OYZfKsLRtJZ0u8VBx9DebfqqG8bRdCC0I7vjgxmPi41P0lpkhJHtA==} + asynckit@0.4.0: + resolution: {integrity: sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==} + balanced-match@1.0.2: resolution: {integrity: sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==} @@ -4668,6 +4797,10 @@ packages: resolution: {integrity: sha512-tixWYgm5ZoOD+3g6UTea91eow5z6AAHaho3g0V9CNSNb45gM8SmflpAc+GRd1InC4AqN/07Unrgp56Y94N9hJQ==} engines: {node: '>=20.19.0'} + cacache@21.0.1: + resolution: {integrity: sha512-pTwz/uj3Jyp6WXdJ6fWhR+7LVxVs6RyroQSn7KJwHsSxXuyGSp0pcMVcwSwTpCFq1X2YG8QBe0W+vN+cr0SwzA==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + call-bind-apply-helpers@1.0.2: resolution: {integrity: sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==} engines: {node: '>= 0.4'} @@ -4703,6 +4836,10 @@ packages: resolution: {integrity: sha512-Qgzu8kfBvo+cA4962jnP1KkS6Dop5NS6g7R5LFYJr4b8Ub94PPQXUksCw9PvXoeXPRRddRNC5C1JQUR2SMGtnA==} engines: {node: '>= 14.16.0'} + chownr@3.0.0: + resolution: {integrity: sha512-+IxzY9BZOQd/XuYPRmrvEVjF/nqj5kgT4kEq7VofrDoM1MxoRjEWkrCC3EtLi59TVawxTAn+orJwFQcrqEN1+g==} + engines: {node: '>=18'} + color-convert@2.0.1: resolution: {integrity: sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==} engines: {node: '>=7.0.0'} @@ -4710,6 +4847,10 @@ packages: color-name@1.1.4: resolution: {integrity: sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==} + combined-stream@1.0.8: + resolution: {integrity: sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==} + engines: {node: '>= 0.8'} + comma-separated-tokens@2.0.3: resolution: {integrity: sha512-Fu4hJdvzeylCfQPp9SGWidpzrMs7tTrlu6Vb8XGaRGck8QSNZJJp538Wrb60Lax4fPwR64ViY468OIUTbRlGZg==} @@ -4997,6 +5138,10 @@ packages: delaunator@5.1.0: resolution: {integrity: sha512-AGrQ4QSgssa1NGmWmLPqN5NY2KajF5MqxetNEO+o0n3ZwZZeTmt7bBnvzHWrmkZFxGgr4HdyFgelzgi06otLuQ==} + delayed-stream@1.0.0: + resolution: {integrity: sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==} + engines: {node: '>=0.4.0'} + depd@2.0.0: resolution: {integrity: sha512-g7nH6P6dyDioJogAAGprGpCtVImJhpPk/roCzdb3fIh61/s/nPsfR6onyMwkCAR/OlC3yBC0lESvUoQEAssIrw==} engines: {node: '>= 0.8'} @@ -5090,6 +5235,10 @@ packages: resolution: {integrity: sha512-zwfzJecQ/Uej6tusMqwAqU/6KL2XaB2VZ2Jg54Je6ahNBGNH6Ek6g3jjNCF0fG9EWQKGZNddNjU5F1ZQn/sBnA==} engines: {node: '>=20.19.0'} + env-paths@2.2.1: + resolution: {integrity: sha512-+h1lkLKhZMTYjog1VEpJNG7NZJWcuc2DDk/qsqSTRRCOXiLjeQ1d1/udrUGhqMxUgAlwKNZ0cf2uqan5GLuS2A==} + engines: {node: '>=6'} + es-define-property@1.0.1: resolution: {integrity: sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==} engines: {node: '>= 0.4'} @@ -5105,6 +5254,10 @@ packages: resolution: {integrity: sha512-HWcBoN6NileqtSydK2FqHbS/LoDd2pqrnQHLyJzBj4kOp/ky2MWMN694xOfkK8/SnUsW2DH7EfyVlydKCsm1Zw==} engines: {node: '>= 0.4'} + es-set-tostringtag@2.1.0: + resolution: {integrity: sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==} + engines: {node: '>= 0.4'} + es-toolkit@1.49.0: resolution: {integrity: sha512-G5iZ6Pc/FNRY/soKZHC+TxGDD83rHUDXxzaWhGCX44vAv/tMs56WMusnm/KMNK+luUPsgA9U28cGr4RDlSzL2g==} @@ -5214,6 +5367,9 @@ packages: resolution: {integrity: sha512-knvyeauYhqjOYvQ66MznSMs83wmHrCycNEN6Ao+2AeYEfxUIkuiVxdEa1qlGEPK+We3n0THiDciYSsCcgW/DoA==} engines: {node: '>=12.0.0'} + exponential-backoff@3.1.3: + resolution: {integrity: sha512-ZgEeZXj30q+I0EN+CbSSpIyPaJ5HVQD18Z1m+u1FXbAeT94mr1zw50q4q6jiiC447Nl/YTcIYSAftiGqetwXCA==} + express-rate-limit@8.5.2: resolution: {integrity: sha512-5Kb34ipNX694DH48vN9irak1Qx30nb0PLYHXfJgw4YEjiC3ZEmZJhwOp+VfiCYwFzvFTdB9QkArYS5kXa2cx2A==} engines: {node: '>= 16'} @@ -5301,6 +5457,10 @@ packages: resolution: {integrity: sha512-gIXjKqtFuWEgzFRJA9WCQeSJLZDjgJUOMCMzxtvFq/37KojM1BFGufqsCy0r4qSQmYLsZYMeyRqzIWOMup03sw==} engines: {node: '>=14'} + form-data@4.0.6: + resolution: {integrity: sha512-vKatAh4SlVfgbv+YtmhiRjhEMJsYpsG1Y2rMQtR+SVSbytsSD1YGzDIcrAJmdFec88u/+VoGmxnl+80gL1tRCQ==} + engines: {node: '>= 6'} + formatly@0.3.0: resolution: {integrity: sha512-9XNj/o4wrRFyhSMJOvsuyMwy8aUfBaZ1VrqHVfohyXf0Sw0e+yfKG+xZaY3arGCOMdwFsqObtzVOc1gU9KiT9w==} engines: {node: '>=18.3.0'} @@ -5318,6 +5478,10 @@ packages: resolution: {integrity: sha512-Rx/WycZ60HOaqLKAi6cHRKKI7zxWbJ31MhntmtwMoaTeF7XFH9hhBp8vITaMidfljRQ6eYWCKkaTK+ykVJHP2A==} engines: {node: '>= 0.8'} + fs-minipass@3.0.3: + resolution: {integrity: sha512-XUBA9XClHbnJWSfBzjkm6RvPsyg3sryZt06BEQoXcF7EK/xpGaQYJgQKDJSUH5SGZ76Y7pFx1QBnXz09rU5Fbw==} + engines: {node: ^14.17.0 || ^16.13.0 || >=18.0.0} + fsevents@2.3.3: resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==} engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0} @@ -5361,6 +5525,10 @@ packages: deprecated: Old versions of glob are not supported, and contain widely publicized security vulnerabilities, which have been fixed in the current version. Please update. Support for old versions may be purchased (at exorbitant rates) by contacting i@izs.me hasBin: true + glob@13.0.6: + resolution: {integrity: sha512-Wjlyrolmm8uDpm/ogGyXZXb1Z+Ca2B8NbJwqBVg0axK9GbBeoS7yGV6vjXnYdGm6X53iehEuxxbyiKp8QmN4Vw==} + engines: {node: 18 || 20 || >=22} + globals@17.7.0: resolution: {integrity: sha512-Czmyns5dUsq4seFBR/Kdydhmo8y9kC79hiSkPn0YcGtNnYWnrgt0vjrSjx9tspoDGWm2CMarffRuLjM4xUz8xg==} engines: {node: '>=18'} @@ -5380,6 +5548,9 @@ packages: resolution: {integrity: sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==} engines: {node: '>= 0.4'} + graceful-fs@4.2.11: + resolution: {integrity: sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==} + hachure-fill@0.5.2: resolution: {integrity: sha512-3GKBOn+m2LX9iq+JC1064cSFprJY4jL1jCXTcpnfER5HYE2l/4EfWSGzkPa/ZDBmYI0ZOEj5VHV/eKnPGkHuOg==} @@ -5396,6 +5567,10 @@ packages: resolution: {integrity: sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==} engines: {node: '>= 0.4'} + has-tostringtag@1.0.2: + resolution: {integrity: sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==} + engines: {node: '>= 0.4'} + hasown@2.0.4: resolution: {integrity: sha512-T2UbfbBEF32wiepXIsMlTW9+dDYC6wMh/t/vYA4tuOMKqWz/n3vr1NFSxQiyP+zk2mXsoMA/i/7qV6LKut1t1A==} engines: {node: '>= 0.4'} @@ -5416,6 +5591,10 @@ packages: hookable@6.1.1: resolution: {integrity: sha512-U9LYDy1CwhMCnprUfeAZWZGByVbhd54hwepegYTK7Pi5NvqEj63ifz5z+xukznehT7i6NIZRu89Ay1AZmRsLEQ==} + hosted-git-info@10.1.1: + resolution: {integrity: sha512-DeOnSPAvOndYKfw075gt8yZzQ7S2hNztw34zBTfhIzLhmBTswIBg5/y+pqu/VD5cYWm5goAFTusDmUEmKZ0PEQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + html-encoding-sniffer@6.0.0: resolution: {integrity: sha512-CV9TW3Y3f8/wT0BRFc1/KAVQ3TUHiXmaAb6VW9vtiMFf7SLoMd1PdAc4W3KFOFETBJUb90KatHqlsZMWV+R9Gg==} engines: {node: ^20.19.0 || ^22.12.0 || >=24.0.0} @@ -5432,6 +5611,9 @@ packages: htmlparser2@6.1.0: resolution: {integrity: sha512-gyyPk6rgonLFEDGoeRgQNaEUvdJ4ktTmmUh/h2t7s+M8oPpIPxgNACWa+6ESR57kXstwqPiCut0V8NRpcwgU7A==} + http-cache-semantics@4.2.0: + resolution: {integrity: sha512-dTxcvPXqPvXBQpq5dUr6mEMJX4oIEFv6bwom3FDwKRDsuIjjJGANqhBuoAn9c1RQJIdAKav33ED65E2ys+87QQ==} + http-errors@2.0.1: resolution: {integrity: sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ==} engines: {node: '>= 0.8'} @@ -5440,10 +5622,18 @@ packages: resolution: {integrity: sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==} engines: {node: '>= 14'} + http-proxy-agent@9.1.0: + resolution: {integrity: sha512-2NxoveTT58mjYT4n3RPTEfCZGLMbidoO8XEieXfpSYxu+PQJ1qpx4ypwH6N+uF9twBPIvRRgvkvW5HUTYWENig==} + engines: {node: '>= 20'} + https-proxy-agent@7.0.6: resolution: {integrity: sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw==} engines: {node: '>= 14'} + https-proxy-agent@9.1.0: + resolution: {integrity: sha512-ag87y7cJJ9/3+GxFr8Oy4O5faDsGRGnBGsJj/YjOSsSx/5eadKLYTMPlzuR6obgoCDDm0abAAZitXXQkMOPSpA==} + engines: {node: '>= 20'} + iconv-lite@0.6.3: resolution: {integrity: sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==} engines: {node: '>=0.10.0'} @@ -5452,6 +5642,10 @@ packages: resolution: {integrity: sha512-IKXpvIzjnC9XTAUbVBcMfGS0EPaIXtW6v+zr+RRp+hqULEpo0owZax6wyRwPOJbWbzjYspQwusTsfVr0ifh4uQ==} engines: {node: '>=0.10.0'} + ignore-walk@9.0.0: + resolution: {integrity: sha512-tCBEZV2z2FNpIDl2vrhiWzIHzs4qOAuIDEO85eS02vZ3L1U3P56qpPL8GuGGAijDktAEaq2swMkO/Fmbo7YmfQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + ignore@5.3.2: resolution: {integrity: sha512-hsBTNUqQTDwkWtcdYI2i06Y/nUBEsNEDJKjWdigLvegy8kDuJAS8uRlpkkcQpyEXL0Z/pjDy5HBmMjRCJ2gq+g==} engines: {node: '>= 4'} @@ -5477,6 +5671,10 @@ packages: inherits@2.0.4: resolution: {integrity: sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==} + ini@7.0.0: + resolution: {integrity: sha512-ifK0CgjALofS5bkrcTy4RaQ9Vx2Knf/eLeIO+NaswQEpH1UblrtTSCIvN71qQDMq0PeQ/SSPojvEJp9vvvfr+w==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + internmap@1.0.1: resolution: {integrity: sha512-lDB5YccMydFBtasVtxnZ3MRBHuaoE8GKsppq+EchKL2U4nK/DmEpPHNH8MZe5HkMtpSiTSOZwfN0tzYjO/lJEw==} @@ -5520,6 +5718,10 @@ packages: isexe@2.0.0: resolution: {integrity: sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==} + isexe@4.0.0: + resolution: {integrity: sha512-FFUtZMpoZ8RqHS3XeXEmHWLA4thH+ZxCv2lOiPIn1Xc7CxrqhWzNSDzD+/chS/zbYezmiwWLdQC09JdQKmthOw==} + engines: {node: '>=20'} + istanbul-lib-coverage@3.2.2: resolution: {integrity: sha512-O8dpsF+r0WV/8MNRKfnmrtCWhuKjxrq2w+jpzBL5UZKTi2LeVWnWOmWRxFlesJONmc+wLAGvKQZEOanko0LFTg==} engines: {node: '>=8'} @@ -5610,6 +5812,10 @@ packages: json-buffer@3.0.1: resolution: {integrity: sha512-4bV5BfR2mqfQTJm+V5tPPdf+ZpuhiIvTuAB5g8kcrXOZpTT/QwwVRWBywX1ozr6lEuPdbHxwaJlm9G6mI2sfSQ==} + json-parse-even-better-errors@6.0.0: + resolution: {integrity: sha512-2/8adwnK1/+Fdjyts4r6wSpfANWw8zdNhU9U/Llk59c6O+DjSisPWPykwoL8gZmocP9Dy64S7oie2g+Mia123A==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + json-schema-to-ts@3.1.1: resolution: {integrity: sha512-+DWg8jCJG2TEnpy7kOm/7/AxaYoaRbjVB4LFZLySZlWn8exGs3A4OLJR966cVvU26N7X9TWxl+Jsw7dzAqKT6g==} engines: {node: '>=16'} @@ -5629,6 +5835,10 @@ packages: jsonc-parser@3.3.1: resolution: {integrity: sha512-HUgH65KyejrUFPvHFPbqOY0rsFip3Bo5wb4ngvdi1EpCYWUQDC5V+Y7mZws+DLkr4M//zQJoanu1SP+87Dv1oQ==} + jsonparse@1.3.1: + resolution: {integrity: sha512-POQXvpdL69+CluYsillJ7SUhKvytYjW9vG/GKpnf+xP8UWgYEM/RaMzHHofbALDiKbbP1W8UEYmgGl39WkPZsg==} + engines: {'0': node >= 0.2.0} + jsx-ast-utils-x@0.1.0: resolution: {integrity: sha512-eQQBjBnsVtGacsG9uJNB8qOr3yA8rga4wAaGG1qRcBzSIvfhERLrWxMAM1hp5fcS6Abo8M4+bUBTekYR0qTPQw==} engines: {node: ^18.18.0 || ^20.9.0 || >=21.1.0} @@ -5836,6 +6046,10 @@ packages: resolution: {integrity: sha512-hXdUTZYIVOt1Ex//jAQi+wTZZpUpwBj/0QsOzqegb3rGMMeJiSEu5xLHnYfBrRV4RH2+OCSOO95Is/7x1WJ4bw==} engines: {node: '>=10'} + make-fetch-happen@16.0.1: + resolution: {integrity: sha512-uUv1yxHzaKVVEPfcFeGSNov/Cehjv08ovlY8ImTljgL7Q+SiA0dAYLQ6SYVa2kkKqNj4Y3aZEI7xv2teadie0A==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + mark.js@8.11.1: resolution: {integrity: sha512-1I+1qpDt4idfgLQG+BNWmrqku+7/2bi5nLf4YwF8y8zXvmfiTBY3PV3ZibfrjBueCByROpuBjLLFCajqkgYoLQ==} @@ -5998,10 +6212,18 @@ packages: micromark@4.0.2: resolution: {integrity: sha512-zpe98Q6kvavpCr1NPVSCMebCKfD7CA2NqZ+rykeNhONIJBpc1tFKt9hucLGwha3jNTNI8lHpctWJWoimVF4PfA==} + mime-db@1.52.0: + resolution: {integrity: sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==} + engines: {node: '>= 0.6'} + mime-db@1.54.0: resolution: {integrity: sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ==} engines: {node: '>= 0.6'} + mime-types@2.1.35: + resolution: {integrity: sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==} + engines: {node: '>= 0.6'} + mime-types@3.0.2: resolution: {integrity: sha512-Lbgzdk0h4juoQ9fCKXW4by0UJqj+nOOrI9MJ1sSj4nI8aI2eo1qmvQEie4VD1glsS250n15LsWsYtCugiStS5A==} engines: {node: '>=18'} @@ -6022,6 +6244,30 @@ packages: minimist@1.2.8: resolution: {integrity: sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==} + minipass-collect@2.0.1: + resolution: {integrity: sha512-D7V8PO9oaz7PWGLbCACuI1qEOsq7UKfLotx/C0Aet43fCUB/wfQ7DYeq2oR/svFJGYDHPr38SHATeaj/ZoKHKw==} + engines: {node: '>=16 || 14 >=14.17'} + + minipass-fetch@6.0.0: + resolution: {integrity: sha512-AWI8bKapGmgx/J0E6IGYSKj8TiHebZkmKWSs8raPSw8KXwgEAJ+Bw3+LSdXHR6T/RHKAWCOYk2MiLrYluaUU6w==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + minipass-flush@1.0.7: + resolution: {integrity: sha512-TbqTz9cUwWyHS2Dy89P3ocAGUGxKjjLuR9z8w4WUTGAVgEj17/4nhgo2Du56i0Fm3Pm30g4iA8Lcqctc76jCzA==} + engines: {node: '>= 8'} + + minipass-pipeline@1.2.4: + resolution: {integrity: sha512-xuIq7cIOt09RPRJ19gdi4b+RiNvDFYe5JH+ggNvBqGqpQXcru3PcRmOZuHBKWK1Txf9+cQ+HMVN4d6z46LZP7A==} + engines: {node: '>=8'} + + minipass-sized@2.0.0: + resolution: {integrity: sha512-zSsHhto5BcUVM2m1LurnXY6M//cGhVaegT71OfOXoprxT6o780GZd792ea6FfrQkuU4usHZIUczAQMRUE2plzA==} + engines: {node: '>=8'} + + minipass@3.3.6: + resolution: {integrity: sha512-DxiNidxSEK+tHG6zOIklvNOwm3hvCrbUrdtzY74U6HKTJxvIDfOUL5W5P2Ghd3DTkhhKPYGqeNUIh5qcM4YBfw==} + engines: {node: '>=8'} + minipass@7.1.3: resolution: {integrity: sha512-tEBHqDnIoM/1rXME1zgka9g6Q2lcoCkxHLuc7ODJ5BxbP5d4c2Z5cGgtXAku59200Cx7diuHTOYfSBD8n6mm8A==} engines: {node: '>=16 || 14 >=14.17'} @@ -6029,12 +6275,20 @@ packages: minisearch@7.2.0: resolution: {integrity: sha512-dqT2XBYUOZOiC5t2HRnwADjhNS2cecp9u+TJRiJ1Qp/f5qjkeT5APcGPjHw+bz89Ms8Jp+cG4AlE+QZ/QnDglg==} + minizlib@3.1.0: + resolution: {integrity: sha512-KZxYo1BUkWD2TVFLr0MQoM8vUUigWD3LlD83a/75BqC+4qE0Hb1Vo5v1FgcfaNXvfXzr+5EhQ6ing/CaBijTlw==} + engines: {node: '>= 18'} + mitt@3.0.1: resolution: {integrity: sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw==} mj-context-menu@0.6.1: resolution: {integrity: sha512-7NO5s6n10TIV96d4g2uDpG7ZDpIhMh0QNfGdJw/W47JswFcosz457wqz/b5sAKvl12sxINGFCn80NZHKwxQEXA==} + modern-tar@0.7.6: + resolution: {integrity: sha512-sweCIVXzx1aIGTCdzcMlSZt1h8k5Tmk08VNAuRk3IU28XamGiOH5ypi11g6De2CH7PhYqSSnGy2A/EFhbWnVKg==} + engines: {node: '>=18.0.0'} + mri@1.2.0: resolution: {integrity: sha512-tzzskb3bG8LvYGFF/mDTpq3jpI6Q9wc3LEmBaghu+DdCssd1FakN7Bc0hVNmEyGq1bq3RgfkCb3cmQLpNPOroA==} engines: {node: '>=4'} @@ -6143,6 +6397,44 @@ packages: resolution: {integrity: sha512-dRB78srN/l6gqWulah9SrxeYnxeddIG30+GOqK/9OlLVyLg3HPnr6SqOWTWOXKRwC2eGYCkZ59NNuSgvSrpgOA==} engines: {node: ^12.20.0 || ^14.13.1 || >=16.0.0} + node-gyp@13.0.1: + resolution: {integrity: sha512-piOr0S10qy5THB+q5BdqkoOx65XL/tjTMUAit3vciPNp+snTOBnGunWH1Rz7XZUxf2T9uFrfT/Ty4+aC3yPeyg==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + hasBin: true + + nopt@10.0.1: + resolution: {integrity: sha512-df3sBr/6ax9hSGuC3CspvLlbnX8cP5L5nZwXF8cGN8l0zSWR6BvzmQ6jPUKjvo6+/xdpkNvEcucBNUdBeeV13g==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + hasBin: true + + npm-bundled@6.0.0: + resolution: {integrity: sha512-EqdodKEW6pYM+dPxA66TZQfMEqVDiuzjDM9edSjuPI1mXUbUJwVxkgqMZSJvs8RTXz2CGq8HUol/AffTZX5g8w==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + npm-install-checks@9.0.0: + resolution: {integrity: sha512-t05Izcgi7p15cpldqoiXYpjzlkTTvBw33sgjmL/JjcvtV0ydbm2O4iEXO8A6smqComu5FAQhUas86HTMQ6Z1Uw==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + npm-normalize-package-bin@6.0.0: + resolution: {integrity: sha512-tdt4aFn9QamlhdN3HV2D2ccpBwO5/fyjjbXUxYA6uBjyekMZcZvDq0aSj9t5Jo+tih6AYFnt/cuIRn9013e0Uw==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + npm-package-arg@14.0.0: + resolution: {integrity: sha512-69XQh3k+dtGa1p+7RaR57IuG3rCko96xr/nUfN4yDYBXbTYICiWcOpsFKLN2GtGE9cyIljE+f1exnaYt9MvM+Q==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + npm-packlist@11.3.0: + resolution: {integrity: sha512-cS1yVkyriZgQAbiK8PtwhZHEtsFOsKHsCg5Ww2ONckAvXIspgqd6o4WirOzvkupU24iMRZ4xtO4kb2iK2rbnag==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + npm-pick-manifest@12.0.0: + resolution: {integrity: sha512-8Fs3YLrnNOhrCdPNZy18MzNgVC58LTDAFzq1FdZO/p3BHeCC/coz+t4F5Pxabys8HJpyTUorMea26GkXsb4J/Q==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + + npm-registry-fetch@20.0.1: + resolution: {integrity: sha512-vzc1svxw/kw1IRjFsLi6gaxe1Olqm88V0tIfu2u5raL0b1gChe6ZEXNkyUlKxUC7s/egt5NxZHkbY18tMKKLfQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + nth-check@2.1.1: resolution: {integrity: sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==} @@ -6199,6 +6491,10 @@ packages: resolution: {integrity: sha512-LaNjtRWUBY++zB5nE/NwcaoMylSPk+S+ZHNB1TzdbMJMny6dynpAGt7X/tl/QYq3TIeE6nxHppbo2LGymrG5Pw==} engines: {node: '>=10'} + p-map@7.0.5: + resolution: {integrity: sha512-e8vJF4XdVkzqqSHguEMz41mQO1wKwxKm5ENrUJQUu9kLDCtn83cxbyHZcszr4QC5zEA7WffRRC4gsTecC7J9oA==} + engines: {node: '>=18'} + p-retry@4.6.2: resolution: {integrity: sha512-312Id396EbJdvRONlngUx0NydfrIQ5lsYu0znKVUzVvArzEIt08V1qhtyESbGVd1FGX7UKtiFp5uwKZdM8wIuQ==} engines: {node: '>=8'} @@ -6209,6 +6505,11 @@ packages: package-manager-detector@1.6.0: resolution: {integrity: sha512-61A5ThoTiDG/C8s8UMZwSorAGwMJ0ERVGj2OjoW5pAalsNOg15+iQiPzrLJ4jhZ1HJzmC2PIHT2oEiH3R5fzNA==} + pacote@22.0.0: + resolution: {integrity: sha512-++VqeOZeL03uGM2MFLk96jGCSt1owBGkyFKoPr+trwNlZhCpjN2RrvwYxt8nTbs1wNMqSFYurq0TafVWkAIHig==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + hasBin: true + pako@1.0.11: resolution: {integrity: sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw==} @@ -6247,6 +6548,10 @@ packages: resolution: {integrity: sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA==} engines: {node: '>=16 || 14 >=14.18'} + path-scurry@2.0.2: + resolution: {integrity: sha512-3O/iVVsJAPsOnpwWIeD+d6z/7PmqApyQePUtCndjatj/9I5LylHvt5qluFaBT3I5h3r1ejfR056c+FCv+NnNXg==} + engines: {node: 18 || 20 || >=22} + path-to-regexp@8.4.2: resolution: {integrity: sha512-qRcuIdP69NPm4qbACK+aDogI5CBDMi1jKe0ry5rSQJz8JVLsC7jV8XpiJjGRLLol3N+R5ihGYcrPLTno6pAdBA==} @@ -6289,6 +6594,10 @@ packages: resolution: {integrity: sha512-vkcDPrRZo1QZLbn5RLGPpg/WmIQ65qoWWhcGKf/b5eplkkarX0m9z8ppCat4mlOqUsWpyNuYgO3VRyrYHSzX5g==} engines: {node: '>= 0.8.0'} + proc-log@7.0.0: + resolution: {integrity: sha512-FYgfaA69XZ93zaXLoMNQ+ViDXGGBgR8aLh03txzcFhV+9xOXx7+8DLCULrKKpR9+GsH9ZfHm82aSUPpozX0Ztg==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + process-nextick-args@2.0.1: resolution: {integrity: sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag==} @@ -6303,6 +6612,15 @@ packages: resolution: {integrity: sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg==} engines: {node: '>= 0.10'} + proxy-agent-negotiate@1.1.0: + resolution: {integrity: sha512-N8IBcM3UgCVzz2L2Lqv8DVntDnnC8/hiV4nEDUPkqq72TPUgYWjQc+bdZlBPZK9LzPAvOY//gAt0S0DApoOXWQ==} + engines: {node: '>= 20'} + peerDependencies: + kerberos: ^2.0.0 + peerDependenciesMeta: + kerberos: + optional: true + publint@0.3.21: resolution: {integrity: sha512-OqejcnMV6E9zel2oCrUOJEiiFkGiAAni0A6ibfQNh1k9Gu5z4F+Yso8lllam7AzmV6Do0vp7u3UpZNRBwuXaHQ==} engines: {node: '>=18'} @@ -6495,16 +6813,32 @@ packages: resolution: {integrity: sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw==} engines: {node: '>=14'} + sigstore@5.0.0: + resolution: {integrity: sha512-hJqJfoG/e4qFQaauQL00c6J6FrHLBGKtkFvW3JbTSIEFOhLrSjdSM/gWd/yUOfYo/gsERehTXGC1VZWX+9X4Dg==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + sisteransi@1.0.5: resolution: {integrity: sha512-bLGGlR1QxBcynn2d5YmDX4MGjlZvy2MRBDRNHLJ8VI6l6+9FUiyTFNJ0IveOSP0bcXgVDPRcfGqA0pjaqUpfVg==} slick@1.12.2: resolution: {integrity: sha512-4qdtOGcBjral6YIBCWJ0ljFSKNLz9KkhbWtuGvUyRowl1kxfuE1x/Z/aJcaiilpb3do9bl5K7/1h9XC5wWpY/A==} + smart-buffer@4.2.0: + resolution: {integrity: sha512-94hK0Hh8rPqQl2xXc3HsaBoOXKV20MToPkcXvwbISWLEs+64sBq5kFgn2kJDHb1Pry9yrP0dxrCI9RRci7RXKg==} + engines: {node: '>= 6.0.0', npm: '>= 3.0.0'} + smol-toml@1.6.1: resolution: {integrity: sha512-dWUG8F5sIIARXih1DTaQAX4SsiTXhInKf1buxdY9DIg4ZYPZK5nGM1VRIYmEbDbsHt7USo99xSLFu5Q1IqTmsg==} engines: {node: '>= 18'} + socks-proxy-agent@10.1.0: + resolution: {integrity: sha512-WlMj/67cEJ6MDI1OcsnjuYKDNDoyPCCYZ249kuuXPiMDw9F8PXkVaQ7YWu3siTydfQ/4BEZcvGzu+aYvz7dDCQ==} + engines: {node: '>= 20'} + + socks@2.8.9: + resolution: {integrity: sha512-LJhUYUvItdQ0LkJTmPeaEObWXAqFyfmP85x0tch/ez9cahmhlBBLbIqDFnvBnUJGagb0JbIQrkBs1wJ+yRYpEw==} + engines: {node: '>= 10.0.0', npm: '>= 3.0.0'} + source-map-js@1.2.1: resolution: {integrity: sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==} engines: {node: '>=0.10.0'} @@ -6516,6 +6850,15 @@ packages: space-separated-tokens@2.0.2: resolution: {integrity: sha512-PEGlAwrG8yXGXRjW32fGbg66JAlOAwbObuqVoJpv/mRgoWDQfgH1wDPvtzWyUSNAXBGSk8h755YDbbcEy3SH2Q==} + spdx-exceptions@2.5.0: + resolution: {integrity: sha512-PiU42r+xO4UbUS1buo3LPJkjlO7430Xn5SVAhdpzzsPHsjbYVflnnFdATgabnLude+Cqu25p6N+g2lw/PFsa4w==} + + spdx-expression-parse@4.0.0: + resolution: {integrity: sha512-Clya5JIij/7C6bRR22+tnGXbc4VKlibKSVj2iHvVeX5iMW7s1SIQlqu699JkODJJIhh/pUu8L0/VLh8xflD+LQ==} + + spdx-license-ids@3.0.23: + resolution: {integrity: sha512-CWLcCCH7VLu13TgOH+r8p1O/Znwhqv/dbb6lqWy67G+pT1kHmeD/+V36AVb/vq8QMIQwVShJ6Ssl5FPh0fuSdw==} + speakingurl@14.0.1: resolution: {integrity: sha512-1POYv7uv2gXoyGFpBCmpDVSNV74IfsWlDW216UPjbWufNf+bSU6GdbDsxdcxtfwb4xlI3yxzOTKClUosxARYrQ==} engines: {node: '>=0.10.0'} @@ -6524,6 +6867,10 @@ packages: resolution: {integrity: sha512-i/VCLG1fvRc95pMHRqG4aQNscv+9aIsqA2oI7ZQS51sTdUcDHYX6cpT8/tqZ+enjs1tKVwbRBWgxut9SWn+f9g==} hasBin: true + ssri@14.0.0: + resolution: {integrity: sha512-jQxKI0yx0ZnTKrqjKkLDV2DXkBQn3k49JVmVqDGcDwKDtGDbImD/GXsq04KD0VVzCQQ9wZJYal3RwR1GzWTSow==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + stackback@0.0.2: resolution: {integrity: sha512-1XMJE5fQo1jGH6Y/7ebnwPOBEkIEnT4QF32d5R1+VXdXveM0IBMJt8zfaxX1P3QhVwrYe+576+jkANtSS2mBbw==} @@ -6584,6 +6931,10 @@ packages: tabbable@6.5.0: resolution: {integrity: sha512-wieBHXygIm7OyQOu5hQlkk62/WyCFYGlWg7L6/ZCUZwx0o398Zkn4pVmMyfYhfMG8kGrj/Krt8eIk6UKC6VzwA==} + tar@7.5.20: + resolution: {integrity: sha512-9FcyK4PA6+WbzlTM9WhQm6vB5W7cP7dUiPsv1g7YDwEQnQ1CGpK3MGlKk/ITVWMk05kHZuBhmVhiv8LZoy/PFQ==} + engines: {node: '>=18'} + tinybench@2.9.0: resolution: {integrity: sha512-0+DUvqWMValLmha6lr4kD8iAMK1HzV0/aKnCtWb9v9641TnP/MFb7Pc2bxoxQjTXAErryXVgUOfv2YqNllqGeg==} @@ -6694,6 +7045,10 @@ packages: engines: {node: '>=18.0.0'} hasBin: true + tuf-js@6.0.0: + resolution: {integrity: sha512-zlJVOIO68hmgo1//X4ENEcTGfuOTAtDPi8PsTsG+FyxD85E/ww1ZnwBbWo/yCEExGpI+Kilg7Z3qCdHX2BoJTQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + type-check@0.4.0: resolution: {integrity: sha512-XleUoc9uwGXqjWwXaUTZAmzMcFZ5858QA2vvx1Ur5xIcixXIP+8LnFDgRplU30us6teqdlskFfu+ae4K79Ooew==} engines: {node: '>= 0.8.0'} @@ -6739,6 +7094,10 @@ packages: resolution: {integrity: sha512-cRZYrTDwWznlnRiPjggAGxZXanty6M8RV1ff8Wm4LWXBp7/IG8v5DnOm74DtUBp9OONpK75YlPnIjQqX0dBDtA==} engines: {node: '>=20.18.1'} + undici@8.7.0: + resolution: {integrity: sha512-N7iQtfyLhIMOFgQubvmLV26svHpO0bqKnAiWotTQCVKCmWrcGbBotPuW1x+xwYZ2VHdSTVUfPQQnlEt1/LouTQ==} + engines: {node: '>=22.19.0'} + unist-util-is@6.0.1: resolution: {integrity: sha512-LsiILbtBETkDz8I9p1dQ0uyRUWuaQzd/cuEeS1hoRSyW5E5XGmTzlwY1OrNzzakGowI9Dr/I8HVaw4hTtnxy8g==} @@ -6772,6 +7131,10 @@ packages: resolution: {integrity: sha512-jOWVmzVceKlVVdwjNSenT4PbGghU0SBIizAev8ofZVgivk/TVHXSbNL8LP6M3spZvkR9/QolkyJavGSX5Cs0UA==} engines: {node: '>=10'} + validate-npm-package-name@8.0.0: + resolution: {integrity: sha512-SCv6OOV6Xj2/3cXy3dGmADluJTNcL3o7hZAglNPTe+WYuEuvxgJzxPrSDLZhF+CwyQOubqgecjMmTJGMVLWjYQ==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + vary@1.1.2: resolution: {integrity: sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg==} engines: {node: '>= 0.8'} @@ -6961,6 +7324,11 @@ packages: engines: {node: '>= 8'} hasBin: true + which@7.0.0: + resolution: {integrity: sha512-RancgH2dmbLdHl6LRhEqvklWMgl/Hdnun0Y90KhBOLkMefg8Qa7/Zel8Sm+8HEcP6DEjzsWzpkuBQEZok58isA==} + engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} + hasBin: true + why-is-node-running@2.3.0: resolution: {integrity: sha512-hUrmaWBdVDcxvYqnyh09zunKzROWjbZTiNy8dBEjkS7ehEDQibXJ7XvlmtbwuTclUiIyN+CyXQD4Vmko8fNm8w==} engines: {node: '>=8'} @@ -7010,6 +7378,13 @@ packages: xmlchars@2.2.0: resolution: {integrity: sha512-JZnDKK8B0RCDw84FNdDAIpZK+JuJw+s7Lz8nksI7SIuU3UXJJslUthsi+uWBUYOwPFwW7W7PRLRfUKpxjtjFCw==} + yallist@4.0.0: + resolution: {integrity: sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==} + + yallist@5.0.0: + resolution: {integrity: sha512-YgvUTfwqyc7UXVMrB+SImsVYSmTS8X/tSrtdNZMImM+n7+QTriRXyXim0mBrTXNeqzVF0KWGgHPeiyViFFrNDw==} + engines: {node: '>=18'} + yaml@2.9.0: resolution: {integrity: sha512-2AvhNX3mb8zd6Zy7INTtSpl1F15HW6Wnqj0srWlkKLcpYl/gMIMJiyuGq2KeI2YFxUPjdlB+3Lc10seMLtL4cA==} engines: {node: '>= 14.6'} @@ -7447,6 +7822,10 @@ snapshots: '@bcoe/v8-coverage@1.0.2': {} + '@bluwy/giget-core@0.1.7': + dependencies: + modern-tar: 0.7.6 + '@braintree/sanitize-url@7.1.2': {} '@bramus/specificity@2.4.2': @@ -7774,6 +8153,8 @@ snapshots: '@exodus/bytes@1.15.1': {} + '@gar/promise-retry@1.0.3': {} + '@google/genai@1.52.0(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))': dependencies: google-auth-library: 10.7.0 @@ -7828,6 +8209,10 @@ snapshots: wrap-ansi: 8.1.0 wrap-ansi-cjs: wrap-ansi@7.0.0 + '@isaacs/fs-minipass@4.0.1': + dependencies: + minipass: 7.1.3 + '@jridgewell/gen-mapping@0.3.13': dependencies: '@jridgewell/sourcemap-codec': 1.5.5 @@ -7915,6 +8300,63 @@ snapshots: '@nodable/entities@2.2.0': {} + '@npmcli/agent@5.0.2': + dependencies: + agent-base: 9.0.0 + http-proxy-agent: 9.1.0 + https-proxy-agent: 9.1.0 + lru-cache: 11.5.1 + socks-proxy-agent: 10.1.0 + transitivePeerDependencies: + - kerberos + - supports-color + + '@npmcli/fs@6.0.0': + dependencies: + semver: 7.8.4 + + '@npmcli/git@8.0.0': + dependencies: + '@gar/promise-retry': 1.0.3 + '@npmcli/promise-spawn': 10.0.0 + ini: 7.0.0 + lru-cache: 11.5.1 + npm-pick-manifest: 12.0.0 + proc-log: 7.0.0 + semver: 7.8.4 + which: 7.0.0 + + '@npmcli/installed-package-contents@5.0.0': + dependencies: + npm-bundled: 6.0.0 + npm-normalize-package-bin: 6.0.0 + + '@npmcli/node-gyp@6.0.0': {} + + '@npmcli/package-json@8.0.0': + dependencies: + '@npmcli/git': 8.0.0 + glob: 13.0.6 + hosted-git-info: 10.1.1 + json-parse-even-better-errors: 6.0.0 + proc-log: 7.0.0 + semver: 7.8.4 + spdx-expression-parse: 4.0.0 + + '@npmcli/promise-spawn@10.0.0': + dependencies: + which: 7.0.0 + + '@npmcli/redact@5.0.0': {} + + '@npmcli/run-script@11.0.0': + dependencies: + '@npmcli/node-gyp': 6.0.0 + '@npmcli/package-json': 8.0.0 + '@npmcli/promise-spawn': 10.0.0 + node-gyp: 13.0.1 + proc-log: 7.0.0 + '@oxc-parser/binding-android-arm-eabi@0.133.0': optional: true @@ -8288,6 +8730,39 @@ snapshots: '@shikijs/vscode-textmate@10.0.2': {} + '@sigstore/bundle@5.0.0': + dependencies: + '@sigstore/protobuf-specs': 0.5.1 + + '@sigstore/core@4.0.1': {} + + '@sigstore/protobuf-specs@0.5.1': {} + + '@sigstore/sign@5.0.0': + dependencies: + '@gar/promise-retry': 1.0.3 + '@sigstore/bundle': 5.0.0 + '@sigstore/core': 4.0.1 + '@sigstore/protobuf-specs': 0.5.1 + make-fetch-happen: 16.0.1 + proc-log: 7.0.0 + transitivePeerDependencies: + - kerberos + - supports-color + + '@sigstore/tuf@5.0.0': + dependencies: + '@sigstore/protobuf-specs': 0.5.1 + tuf-js: 6.0.0 + transitivePeerDependencies: + - supports-color + + '@sigstore/verify@4.1.0': + dependencies: + '@sigstore/bundle': 5.0.0 + '@sigstore/core': 4.0.1 + '@sigstore/protobuf-specs': 0.5.1 + '@smithy/core@3.24.7': dependencies: '@aws-crypto/crc32': 5.2.0 @@ -8354,6 +8829,13 @@ snapshots: estraverse: 5.3.0 picomatch: 4.0.4 + '@tufjs/canonical-json@2.0.0': {} + + '@tufjs/models@5.0.0': + dependencies: + '@tufjs/canonical-json': 2.0.0 + minimatch: 10.2.5 + '@tybys/wasm-util@0.10.2': dependencies: tslib: 2.8.1 @@ -8527,6 +9009,11 @@ snapshots: '@types/ms@2.1.0': {} + '@types/node-fetch@2.6.13': + dependencies: + '@types/node': 22.20.0 + form-data: 4.0.6 + '@types/node@22.20.0': dependencies: undici-types: 6.21.0 @@ -8535,10 +9022,35 @@ snapshots: dependencies: undici-types: 7.24.6 + '@types/npm-package-arg@6.1.4': {} + + '@types/npm-registry-fetch@8.0.9': + dependencies: + '@types/node': 22.20.0 + '@types/node-fetch': 2.6.13 + '@types/npm-package-arg': 6.1.4 + '@types/npmlog': 7.0.0 + '@types/ssri': 7.1.5 + + '@types/npmlog@7.0.0': + dependencies: + '@types/node': 22.20.0 + + '@types/pacote@11.1.8': + dependencies: + '@types/node': 22.20.0 + '@types/npm-registry-fetch': 8.0.9 + '@types/npmlog': 7.0.0 + '@types/ssri': 7.1.5 + '@types/picomatch@3.0.2': {} '@types/retry@0.12.0': {} + '@types/ssri@7.1.5': + dependencies: + '@types/node': 22.20.0 + '@types/tough-cookie@4.0.5': {} '@types/trusted-types@2.0.7': @@ -8815,6 +9327,8 @@ snapshots: '@xmldom/xmldom@0.9.10': {} + abbrev@5.0.0: {} + accepts@2.0.0: dependencies: mime-types: 3.0.2 @@ -8828,6 +9342,8 @@ snapshots: agent-base@7.1.4: {} + agent-base@9.0.0: {} + ajv-formats@3.0.1(ajv@8.20.0): optionalDependencies: ajv: 8.20.0 @@ -8895,6 +9411,8 @@ snapshots: estree-walker: 3.0.3 js-tokens: 10.0.0 + asynckit@0.4.0: {} + balanced-match@1.0.2: {} balanced-match@4.0.4: {} @@ -8945,6 +9463,19 @@ snapshots: cac@7.0.0: {} + cacache@21.0.1: + dependencies: + '@npmcli/fs': 6.0.0 + fs-minipass: 3.0.3 + glob: 13.0.6 + lru-cache: 11.5.1 + minipass: 7.1.3 + minipass-collect: 2.0.1 + minipass-flush: 1.0.7 + minipass-pipeline: 1.2.4 + p-map: 7.0.5 + ssri: 14.0.0 + call-bind-apply-helpers@1.0.2: dependencies: es-errors: 1.3.0 @@ -8987,12 +9518,18 @@ snapshots: dependencies: readdirp: 4.1.2 + chownr@3.0.0: {} + color-convert@2.0.1: dependencies: color-name: 1.1.4 color-name@1.1.4: {} + combined-stream@1.0.8: + dependencies: + delayed-stream: 1.0.0 + comma-separated-tokens@2.0.3: {} commander@13.1.0: {} @@ -9298,6 +9835,8 @@ snapshots: dependencies: robust-predicates: 3.0.3 + delayed-stream@1.0.0: {} + depd@2.0.0: {} dequal@2.0.3: {} @@ -9372,6 +9911,8 @@ snapshots: entities@8.0.0: {} + env-paths@2.2.1: {} + es-define-property@1.0.1: {} es-errors@1.3.0: {} @@ -9382,6 +9923,13 @@ snapshots: dependencies: es-errors: 1.3.0 + es-set-tostringtag@2.1.0: + dependencies: + es-errors: 1.3.0 + get-intrinsic: 1.3.0 + has-tostringtag: 1.0.2 + hasown: 2.0.4 + es-toolkit@1.49.0: {} esbuild@0.21.5: @@ -9556,6 +10104,8 @@ snapshots: expect-type@1.3.0: {} + exponential-backoff@3.1.3: {} + express-rate-limit@8.5.2(express@5.2.1): dependencies: express: 5.2.1 @@ -9679,6 +10229,14 @@ snapshots: cross-spawn: 7.0.6 signal-exit: 4.1.0 + form-data@4.0.6: + dependencies: + asynckit: 0.4.0 + combined-stream: 1.0.8 + es-set-tostringtag: 2.1.0 + hasown: 2.0.4 + mime-types: 2.1.35 + formatly@0.3.0: dependencies: fd-package-json: 2.0.0 @@ -9691,6 +10249,10 @@ snapshots: fresh@2.0.0: {} + fs-minipass@3.0.3: + dependencies: + minipass: 7.1.3 + fsevents@2.3.3: optional: true @@ -9753,6 +10315,12 @@ snapshots: package-json-from-dist: 1.0.1 path-scurry: 1.11.1 + glob@13.0.6: + dependencies: + minimatch: 10.2.5 + minipass: 7.1.3 + path-scurry: 2.0.2 + globals@17.7.0: {} globrex@0.1.2: {} @@ -9772,6 +10340,8 @@ snapshots: gopd@1.2.0: {} + graceful-fs@4.2.11: {} + hachure-fill@0.5.2: {} handlebars@4.7.9: @@ -9787,6 +10357,10 @@ snapshots: has-symbols@1.1.0: {} + has-tostringtag@1.0.2: + dependencies: + has-symbols: 1.1.0 + hasown@2.0.4: dependencies: function-bind: 1.1.2 @@ -9815,6 +10389,10 @@ snapshots: hookable@6.1.1: {} + hosted-git-info@10.1.1: + dependencies: + lru-cache: 11.5.1 + html-encoding-sniffer@6.0.0: dependencies: '@exodus/bytes': 1.15.1 @@ -9839,6 +10417,8 @@ snapshots: domutils: 2.8.0 entities: 2.2.0 + http-cache-semantics@4.2.0: {} + http-errors@2.0.1: dependencies: depd: 2.0.0 @@ -9854,6 +10434,15 @@ snapshots: transitivePeerDependencies: - supports-color + http-proxy-agent@9.1.0: + dependencies: + agent-base: 9.0.0 + debug: 4.4.3 + proxy-agent-negotiate: 1.1.0 + transitivePeerDependencies: + - kerberos + - supports-color + https-proxy-agent@7.0.6: dependencies: agent-base: 7.1.4 @@ -9861,6 +10450,15 @@ snapshots: transitivePeerDependencies: - supports-color + https-proxy-agent@9.1.0: + dependencies: + agent-base: 9.0.0 + debug: 4.4.3 + proxy-agent-negotiate: 1.1.0 + transitivePeerDependencies: + - kerberos + - supports-color + iconv-lite@0.6.3: dependencies: safer-buffer: 2.1.2 @@ -9869,6 +10467,10 @@ snapshots: dependencies: safer-buffer: 2.1.2 + ignore-walk@9.0.0: + dependencies: + minimatch: 10.2.5 + ignore@5.3.2: {} ignore@7.0.5: {} @@ -9883,6 +10485,8 @@ snapshots: inherits@2.0.4: {} + ini@7.0.0: {} + internmap@1.0.1: {} internmap@2.0.3: {} @@ -9909,6 +10513,8 @@ snapshots: isexe@2.0.0: {} + isexe@4.0.0: {} + istanbul-lib-coverage@3.2.2: {} istanbul-lib-report@3.0.1: @@ -10001,6 +10607,8 @@ snapshots: json-buffer@3.0.1: {} + json-parse-even-better-errors@6.0.0: {} + json-schema-to-ts@3.1.1: dependencies: '@babel/runtime': 7.29.7 @@ -10016,6 +10624,8 @@ snapshots: jsonc-parser@3.3.1: {} + jsonparse@1.3.1: {} + jsx-ast-utils-x@0.1.0: {} jszip@3.10.1: @@ -10207,6 +10817,24 @@ snapshots: dependencies: semver: 7.8.4 + make-fetch-happen@16.0.1: + dependencies: + '@gar/promise-retry': 1.0.3 + '@npmcli/agent': 5.0.2 + '@npmcli/redact': 5.0.0 + cacache: 21.0.1 + http-cache-semantics: 4.2.0 + minipass: 7.1.3 + minipass-fetch: 6.0.0 + minipass-flush: 1.0.7 + minipass-pipeline: 1.2.4 + negotiator: 1.0.0 + proc-log: 7.0.0 + ssri: 14.0.0 + transitivePeerDependencies: + - kerberos + - supports-color + mark.js@8.11.1: {} markdown-it-mathjax3@4.3.2: @@ -10568,8 +11196,14 @@ snapshots: transitivePeerDependencies: - supports-color + mime-db@1.52.0: {} + mime-db@1.54.0: {} + mime-types@2.1.35: + dependencies: + mime-db: 1.52.0 + mime-types@3.0.2: dependencies: mime-db: 1.54.0 @@ -10586,14 +11220,48 @@ snapshots: minimist@1.2.8: {} + minipass-collect@2.0.1: + dependencies: + minipass: 7.1.3 + + minipass-fetch@6.0.0: + dependencies: + minipass: 7.1.3 + minipass-sized: 2.0.0 + minizlib: 3.1.0 + optionalDependencies: + iconv-lite: 0.7.3 + + minipass-flush@1.0.7: + dependencies: + minipass: 3.3.6 + + minipass-pipeline@1.2.4: + dependencies: + minipass: 3.3.6 + + minipass-sized@2.0.0: + dependencies: + minipass: 7.1.3 + + minipass@3.3.6: + dependencies: + yallist: 4.0.0 + minipass@7.1.3: {} minisearch@7.2.0: {} + minizlib@3.1.0: + dependencies: + minipass: 7.1.3 + mitt@3.0.1: {} mj-context-menu@0.6.1: {} + modern-tar@0.7.6: {} + mri@1.2.0: {} ms@2.1.3: {} @@ -10678,6 +11346,67 @@ snapshots: fetch-blob: 3.2.0 formdata-polyfill: 4.0.10 + node-gyp@13.0.1: + dependencies: + env-paths: 2.2.1 + exponential-backoff: 3.1.3 + graceful-fs: 4.2.11 + nopt: 10.0.1 + proc-log: 7.0.0 + semver: 7.8.4 + tar: 7.5.20 + tinyglobby: 0.2.17 + undici: 8.7.0 + which: 7.0.0 + + nopt@10.0.1: + dependencies: + abbrev: 5.0.0 + + npm-bundled@6.0.0: + dependencies: + npm-normalize-package-bin: 6.0.0 + + npm-install-checks@9.0.0: + dependencies: + semver: 7.8.4 + + npm-normalize-package-bin@6.0.0: {} + + npm-package-arg@14.0.0: + dependencies: + hosted-git-info: 10.1.1 + proc-log: 7.0.0 + semver: 7.8.4 + validate-npm-package-name: 8.0.0 + + npm-packlist@11.3.0: + dependencies: + glob: 13.0.6 + ignore-walk: 9.0.0 + proc-log: 7.0.0 + + npm-pick-manifest@12.0.0: + dependencies: + npm-install-checks: 9.0.0 + npm-normalize-package-bin: 6.0.0 + npm-package-arg: 14.0.0 + semver: 7.8.4 + + npm-registry-fetch@20.0.1: + dependencies: + '@npmcli/redact': 5.0.0 + jsonparse: 1.3.1 + make-fetch-happen: 16.0.1 + minipass: 7.1.3 + minipass-fetch: 6.0.0 + minizlib: 3.1.0 + npm-package-arg: 14.0.0 + proc-log: 7.0.0 + transitivePeerDependencies: + - kerberos + - supports-color + nth-check@2.1.1: dependencies: boolbase: 1.0.0 @@ -10771,6 +11500,8 @@ snapshots: dependencies: p-limit: 3.1.0 + p-map@7.0.5: {} + p-retry@4.6.2: dependencies: '@types/retry': 0.12.0 @@ -10780,6 +11511,29 @@ snapshots: package-manager-detector@1.6.0: {} + pacote@22.0.0: + dependencies: + '@gar/promise-retry': 1.0.3 + '@npmcli/git': 8.0.0 + '@npmcli/installed-package-contents': 5.0.0 + '@npmcli/package-json': 8.0.0 + '@npmcli/promise-spawn': 10.0.0 + '@npmcli/run-script': 11.0.0 + cacache: 21.0.1 + fs-minipass: 3.0.3 + minipass: 7.1.3 + npm-package-arg: 14.0.0 + npm-packlist: 11.3.0 + npm-pick-manifest: 12.0.0 + npm-registry-fetch: 20.0.1 + proc-log: 7.0.0 + sigstore: 5.0.0 + ssri: 14.0.0 + tar: 7.5.20 + transitivePeerDependencies: + - kerberos + - supports-color + pako@1.0.11: {} parse5-htmlparser2-tree-adapter@6.0.1: @@ -10809,6 +11563,11 @@ snapshots: lru-cache: 10.4.3 minipass: 7.1.3 + path-scurry@2.0.2: + dependencies: + lru-cache: 11.5.1 + minipass: 7.1.3 + path-to-regexp@8.4.2: {} pathe@2.0.3: {} @@ -10838,6 +11597,8 @@ snapshots: prelude-ls@1.2.1: {} + proc-log@7.0.0: {} + process-nextick-args@2.0.1: {} property-information@7.2.0: {} @@ -10853,7 +11614,7 @@ snapshots: '@protobufjs/path': 1.1.2 '@protobufjs/pool': 1.1.0 '@protobufjs/utf8': 1.1.1 - '@types/node': 25.9.3 + '@types/node': 22.20.0 long: 5.3.2 proxy-addr@2.0.7: @@ -10861,6 +11622,8 @@ snapshots: forwarded: 0.2.0 ipaddr.js: 1.9.1 + proxy-agent-negotiate@1.1.0: {} + publint@0.3.21: dependencies: '@publint/pack': 0.1.4 @@ -11144,18 +11907,54 @@ snapshots: signal-exit@4.1.0: {} + sigstore@5.0.0: + dependencies: + '@sigstore/bundle': 5.0.0 + '@sigstore/core': 4.0.1 + '@sigstore/protobuf-specs': 0.5.1 + '@sigstore/sign': 5.0.0 + '@sigstore/tuf': 5.0.0 + '@sigstore/verify': 4.1.0 + transitivePeerDependencies: + - kerberos + - supports-color + sisteransi@1.0.5: {} slick@1.12.2: {} + smart-buffer@4.2.0: {} + smol-toml@1.6.1: {} + socks-proxy-agent@10.1.0: + dependencies: + agent-base: 9.0.0 + debug: 4.4.3 + socks: 2.8.9 + transitivePeerDependencies: + - supports-color + + socks@2.8.9: + dependencies: + ip-address: 10.2.0 + smart-buffer: 4.2.0 + source-map-js@1.2.1: {} source-map@0.6.1: {} space-separated-tokens@2.0.2: {} + spdx-exceptions@2.5.0: {} + + spdx-expression-parse@4.0.0: + dependencies: + spdx-exceptions: 2.5.0 + spdx-license-ids: 3.0.23 + + spdx-license-ids@3.0.23: {} + speakingurl@14.0.1: {} speech-rule-engine@4.1.4: @@ -11164,6 +11963,10 @@ snapshots: commander: 13.1.0 wicked-good-xpath: 1.3.0 + ssri@14.0.0: + dependencies: + minipass: 7.1.3 + stackback@0.0.2: {} statuses@2.0.2: {} @@ -11221,6 +12024,14 @@ snapshots: tabbable@6.5.0: {} + tar@7.5.20: + dependencies: + '@isaacs/fs-minipass': 4.0.1 + chownr: 3.0.0 + minipass: 7.1.3 + minizlib: 3.1.0 + yallist: 5.0.0 + tinybench@2.9.0: {} tinyexec@1.2.4: {} @@ -11301,6 +12112,14 @@ snapshots: optionalDependencies: fsevents: 2.3.3 + tuf-js@6.0.0: + dependencies: + '@gar/promise-retry': 1.0.3 + '@tufjs/models': 5.0.0 + debug: 4.4.3 + transitivePeerDependencies: + - supports-color + type-check@0.4.0: dependencies: prelude-ls: 1.2.1 @@ -11342,6 +12161,8 @@ snapshots: undici@7.28.0: {} + undici@8.7.0: {} + unist-util-is@6.0.1: dependencies: '@types/unist': 3.0.3 @@ -11377,6 +12198,8 @@ snapshots: valid-data-url@3.0.1: {} + validate-npm-package-name@8.0.0: {} + vary@1.1.2: {} vfile-message@4.0.3: @@ -11600,6 +12423,10 @@ snapshots: dependencies: isexe: 2.0.0 + which@7.0.0: + dependencies: + isexe: 4.0.0 + why-is-node-running@2.3.0: dependencies: siginfo: 2.0.0 @@ -11633,6 +12460,10 @@ snapshots: xmlchars@2.2.0: {} + yallist@4.0.0: {} + + yallist@5.0.0: {} + yaml@2.9.0: {} yocto-queue@0.1.0: {} diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 75fb2b75ad..4a845b4554 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -52,6 +52,7 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/sandbox/sandbox-local': { kind: 'indirect', reason: 'The provider backend delegates model rendering to dsh-bash-sandbox and dsh-tool-bash.' }, 'packages/sdk/create-sdk': { kind: 'indirect', reason: 'The initializer only writes project files; selected runtime plugins provide the generated project model surface.' }, 'packages/sdk/helper': { kind: 'none', reason: 'The project domain edits files and registers no live agent or model surface.' }, + 'packages/sdk/plugin-fetch': { kind: 'none', reason: 'The fetcher acquires plugin sources into a temp dir and registers no live agent or model surface.' }, 'packages/sdk/scripts': { kind: 'indirect', reason: 'The launcher delegates model context to the loaded project plugin tree.' }, 'packages/session-query/session-query': { kind: 'none', reason: 'The trusted query service exposes cloned records only to callers and registers no model surface.' }, 'packages/skill/skill': { kind: 'indirect', reason: 'The provider registry delegates model rendering to dsh-tool-skill.' }, diff --git a/tsconfig.build.json b/tsconfig.build.json index dd13e018c3..9a6133db36 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -98,6 +98,7 @@ { "path": "./packages/mcp/mcp-client" }, { "path": "./packages/sdk/helper" }, { "path": "./packages/sdk/scripts" }, - { "path": "./packages/sdk/create-sdk" } + { "path": "./packages/sdk/create-sdk" }, + { "path": "./packages/sdk/plugin-fetch" } ] } diff --git a/tsconfig.json b/tsconfig.json index 22451dc10f..4588c81c72 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -109,6 +109,7 @@ { "path": "./packages/mcp/mcp-client" }, { "path": "./packages/sdk/helper" }, { "path": "./packages/sdk/scripts" }, - { "path": "./packages/sdk/create-sdk" } + { "path": "./packages/sdk/create-sdk" }, + { "path": "./packages/sdk/plugin-fetch" } ] } From fe668a6dfe5c9c64453eb78b8f167eb1407c0eb9 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 13:16:51 +0800 Subject: [PATCH 176/323] feat(telemetry): greenfield dsh-sdk telemetry modules Add @deepseek-ai/dsh-telemetry, a launcher-side (non-plugin) library for the ConsentResolver (parses cordis.yml consent + DO_NOT_TRACK/CI), buildTelemetryPayload (redacted cordis.yml + package.json full content, never .env), getOrCreateAnonymousId (random UUID in a per-machine global config file), and TelemetryReporter (fire-and-forget, never blocks or crashes the command). Endpoint is a fixed .invalid placeholder pending the real endpoint. Launcher dispatch wiring and the helper feature-catalog entry are intentionally out of scope. Registers the package in tsconfig references, the module graph, and the README model-experience audit map. Per-file 100% coverage. --- docs/module-graph.md | 3 + packages/sdk/telemetry/README.md | 24 +++ packages/sdk/telemetry/package.json | 35 +++ packages/sdk/telemetry/src/anonymous-id.ts | 106 +++++++++ .../sdk/telemetry/src/consent-resolver.ts | 125 +++++++++++ packages/sdk/telemetry/src/index.ts | 45 ++++ packages/sdk/telemetry/src/payload.ts | 75 +++++++ packages/sdk/telemetry/src/reporter.ts | 149 +++++++++++++ packages/sdk/telemetry/src/secret-redactor.ts | 203 ++++++++++++++++++ .../sdk/telemetry/tests/anonymous-id.spec.ts | 100 +++++++++ .../telemetry/tests/consent-resolver.spec.ts | 131 +++++++++++ packages/sdk/telemetry/tests/payload.spec.ts | 59 +++++ packages/sdk/telemetry/tests/reporter.spec.ts | 134 ++++++++++++ .../telemetry/tests/secret-redactor.spec.ts | 169 +++++++++++++++ packages/sdk/telemetry/tsconfig.json | 13 ++ pnpm-lock.yaml | 13 ++ .../verify-package-readme-model-experience.ts | 1 + tsconfig.build.json | 3 +- tsconfig.json | 3 +- 19 files changed, 1389 insertions(+), 2 deletions(-) create mode 100644 packages/sdk/telemetry/README.md create mode 100644 packages/sdk/telemetry/package.json create mode 100644 packages/sdk/telemetry/src/anonymous-id.ts create mode 100644 packages/sdk/telemetry/src/consent-resolver.ts create mode 100644 packages/sdk/telemetry/src/index.ts create mode 100644 packages/sdk/telemetry/src/payload.ts create mode 100644 packages/sdk/telemetry/src/reporter.ts create mode 100644 packages/sdk/telemetry/src/secret-redactor.ts create mode 100644 packages/sdk/telemetry/tests/anonymous-id.spec.ts create mode 100644 packages/sdk/telemetry/tests/consent-resolver.spec.ts create mode 100644 packages/sdk/telemetry/tests/payload.spec.ts create mode 100644 packages/sdk/telemetry/tests/reporter.spec.ts create mode 100644 packages/sdk/telemetry/tests/secret-redactor.spec.ts create mode 100644 packages/sdk/telemetry/tsconfig.json diff --git a/docs/module-graph.md b/docs/module-graph.md index c9439d5501..4cc2c36eeb 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -140,6 +140,7 @@ flowchart TD pkg_helper["helper"] pkg_plugin_fetch["plugin-fetch"] pkg_scripts["scripts"] + pkg_telemetry["telemetry"] end subgraph group_tasks["packages/tasks"] pkg_tasks["tasks"] @@ -155,6 +156,7 @@ flowchart TD pkg_helper --> pkg_brand pkg_plugin_fetch --> pkg_brand pkg_scripts --> pkg_app_boot + pkg_telemetry --> pkg_brand pkg_llm_deepseek --> pkg_llm pkg_llm_pi_ai --> pkg_llm pkg_session --> pkg_brand @@ -446,6 +448,7 @@ flowchart TD | [`helper`](../packages/sdk/helper) | `sdk` | [`brand`](../packages/util/brand) | | [`plugin-fetch`](../packages/sdk/plugin-fetch) | `sdk` | [`brand`](../packages/util/brand) | | [`scripts`](../packages/sdk/scripts) | `sdk` | [`app-boot`](../packages/ui/app-boot) | +| [`telemetry`](../packages/sdk/telemetry) | `sdk` | [`brand`](../packages/util/brand) | | [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`llm`](../packages/llm/llm) | | [`llm-pi-ai`](../packages/llm/llm-pi-ai) | `llm` | [`llm`](../packages/llm/llm) | | [`session`](../packages/core/session) | `core` | [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope) | diff --git a/packages/sdk/telemetry/README.md b/packages/sdk/telemetry/README.md new file mode 100644 index 0000000000..3a8b6ac4c2 --- /dev/null +++ b/packages/sdk/telemetry/README.md @@ -0,0 +1,24 @@ +# `@deepseek-ai/dsh-telemetry` + +Launcher-side telemetry primitives for the dsh-sdk toolchain. This is a plain library the launcher imports around each command; it is **not** a Cordis plugin, because `build` and first-init `create` never boot Cordis. Wiring the reporter into the launcher command dispatch and adding the telemetry consent feature to the `dsh-helper` catalog live in their owning packages, not here. + +| Export | Role | +|---|---| +| `SecretRedactor` | Conservative safety backstop: replaces secret-shaped values (secret-like keys, known token shapes, PEM blocks, URL credentials, high-entropy opaque tokens) with a placeholder in both parsed values (`redactValue`) and raw text (`redactText`). Never drops a field or line. | +| `ConsentResolver` | Parses (never boots) a project `cordis.yml` and reads the telemetry entry's enabled/disabled state as consent; `DO_NOT_TRACK`/CI env force a hard opt-out. | +| `buildTelemetryPayload` | Assembles `{command, durationMs, success, cordisYmlContent, packageJsonContent}`, running the redactor over the full `cordis.yml` and `package.json` text. Never reads `.env`. | +| `getOrCreateAnonymousId` | Random UUID persisted in a per-user GLOBAL config file (never in the project, never derived from git). | +| `TelemetryReporter` | Fire-and-forget send: `report()` never blocks or throws; delivery resolves on every path; `flush()` optionally drains in-flight sends within a cap. | + +Consent is carried by the telemetry entry in `cordis.yml`, so disabling telemetry is disabling that entry. When `cordis.yml` does not yet exist (first `create`) consent defaults to allowed; when it exists without a telemetry entry consent defaults to denied — both are configurable on `ConsentResolver`. + +The collection endpoint is a fixed constant (`DSH_TELEMETRY_ENDPOINT`); its `.invalid` placeholder must be replaced with the real endpoint before release. + +## Model Experience + +None, as the reporter sends developer-cycle telemetry from the launcher and never reaches a model request. + +## Known Limitations and Deferred Work + +- **Placeholder endpoint** — `DSH_TELEMETRY_ENDPOINT` points at `.invalid` until the real endpoint is set. +- **Redaction is heuristic** — a conservative backstop, not a guarantee; secrets belong in `.env`, which is never read or reported. diff --git a/packages/sdk/telemetry/package.json b/packages/sdk/telemetry/package.json new file mode 100644 index 0000000000..fcb6efb797 --- /dev/null +++ b/packages/sdk/telemetry/package.json @@ -0,0 +1,35 @@ +{ + "name": "@deepseek-ai/dsh-telemetry", + "description": "Launcher-side dsh-sdk telemetry: secret redaction, consent resolution, anonymous id, payload builder, and fire-and-forget reporter", + "version": "0.0.1", + "private": true, + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "files": [ + "lib/index.js", + "lib/types/**/*.d.ts", + "lib/types/**/*.d.ts.map", + "src" + ], + "license": "BSD-3-Clause", + "dependencies": { + "yaml": "^2.9.0" + }, + "peerDependencies": { + "@deepseek-ai/dsh-brand": "^0.0.1", + "cordis": "^4.0.0-rc.7" + }, + "devDependencies": { + "@deepseek-ai/dsh-brand": "workspace:^", + "cordis": "^4.0.0-rc.7" + } +} diff --git a/packages/sdk/telemetry/src/anonymous-id.ts b/packages/sdk/telemetry/src/anonymous-id.ts new file mode 100644 index 0000000000..030fefa19f --- /dev/null +++ b/packages/sdk/telemetry/src/anonymous-id.ts @@ -0,0 +1,106 @@ +/** + * Per-machine anonymous telemetry id. + * + * The id is a random UUID persisted in a per-user GLOBAL config file — never in + * the project, and never derived from the git remote, repository URL, or any + * other identifying source (a derived id would make "anonymous" a fiction). The + * same id is reused across projects on one machine so telemetry counts machines, + * not repositories. + * + * @module @deepseek-ai/dsh-telemetry/anonymous-id + */ + +import { randomUUID } from 'node:crypto' +import { mkdir, readFile, writeFile } from 'node:fs/promises' +import { homedir } from 'node:os' +import { dirname, join } from 'node:path' +import type { Branded } from '@deepseek-ai/dsh-brand' + +/** A machine-scoped anonymous telemetry id (random UUID v4). */ +export type AnonymousId = Branded<'AnonymousId'> + +/** Config directory name owned by the DeepSeek Harness across tools. */ +const CONFIG_NAMESPACE = 'deepseek-harness' + +/** Default file, inside the global config dir, storing the anonymous id. */ +export const ANONYMOUS_ID_FILE_NAME = 'telemetry.json' + +const UUID_PATTERN = /^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$/i + +/** Ambient seams for locating and generating the id; every field has a default. */ +export interface AnonymousIdOptions { + /** Environment consulted for `DSH_CONFIG_HOME`/`XDG_CONFIG_HOME`/`APPDATA`; defaults to `process.env`. */ + env?: NodeJS.ProcessEnv + /** Platform string used to pick the Windows path; defaults to `process.platform`. */ + platform?: NodeJS.Platform + /** Home directory resolver; defaults to `os.homedir`. */ + homeDir?: () => string + /** UUID generator; defaults to `crypto.randomUUID` (test seam). */ + randomUUID?: () => string +} + +/** + * Resolve the per-user global config directory for harness tooling. + * Precedence: `DSH_CONFIG_HOME` (explicit override) > `XDG_CONFIG_HOME` > + * platform default (`%APPDATA%` on Windows, else `~/.config`). + * @param options - environment, platform, and home-directory seams. + * @returns absolute config directory path for the harness namespace. + */ +export function globalConfigDir(options: AnonymousIdOptions = {}): string { + const env = options.env ?? process.env + const platform = options.platform ?? process.platform + const home = options.homeDir ?? homedir + if (env.DSH_CONFIG_HOME !== undefined && env.DSH_CONFIG_HOME.length > 0) return env.DSH_CONFIG_HOME + if (env.XDG_CONFIG_HOME !== undefined && env.XDG_CONFIG_HOME.length > 0) { + return join(env.XDG_CONFIG_HOME, CONFIG_NAMESPACE) + } + if (platform === 'win32' && env.APPDATA !== undefined && env.APPDATA.length > 0) { + return join(env.APPDATA, CONFIG_NAMESPACE) + } + return join(home(), '.config', CONFIG_NAMESPACE) +} + +/** Read a valid persisted id from the store, or `undefined` when absent/corrupt. */ +async function readPersistedId(file: string): Promise { + let text: string + try { + text = await readFile(file, 'utf8') + } catch { + // Absent or unreadable: the caller mints and persists a fresh id. + return undefined + } + let parsed: unknown + try { + parsed = JSON.parse(text) + } catch { + // Corrupt JSON: the caller overwrites the store with a fresh id. + return undefined + } + if (parsed !== null && typeof parsed === 'object') { + const value = (parsed as Record).anonymousId + if (typeof value === 'string' && UUID_PATTERN.test(value)) return value as AnonymousId + } + return undefined +} + +/** + * Return the machine's anonymous id, creating and persisting one on first use. + * Persistence is best-effort: a write failure still returns a usable id for the + * current run so telemetry is never blocked by config-dir permissions. + * @param options - config-location and UUID-generation seams. + * @returns the stable per-machine anonymous id. + */ +export async function getOrCreateAnonymousId(options: AnonymousIdOptions = {}): Promise { + const file = join(globalConfigDir(options), ANONYMOUS_ID_FILE_NAME) + const existing = await readPersistedId(file) + if (existing !== undefined) return existing + const generate = options.randomUUID ?? randomUUID + const created = generate() as AnonymousId + try { + await mkdir(dirname(file), { recursive: true }) + await writeFile(file, `${JSON.stringify({ anonymousId: created }, null, 2)}\n`, 'utf8') + } catch { + // Best-effort persistence: return the fresh id even when the store is unwritable. + } + return created +} diff --git a/packages/sdk/telemetry/src/consent-resolver.ts b/packages/sdk/telemetry/src/consent-resolver.ts new file mode 100644 index 0000000000..1d50904f39 --- /dev/null +++ b/packages/sdk/telemetry/src/consent-resolver.ts @@ -0,0 +1,125 @@ +/** + * Consent resolution for dsh-sdk telemetry. + * + * Consent is carried by the telemetry plugin's enabled/disabled state in the + * project `cordis.yml`: an enabled entry means opt-in, a `disabled: true` entry + * means opt-out. The resolver PARSES `cordis.yml` — it never boots a Cordis + * application — because several launcher commands (`build`, `create`) never + * boot Cordis at all. `DO_NOT_TRACK` and CI environment signals force a denial + * regardless of file state. + * + * @module @deepseek-ai/dsh-telemetry/consent-resolver + */ + +import { readFile } from 'node:fs/promises' +import { join } from 'node:path' +import { parseDocument, type ScalarTag } from 'yaml' + +/** Default `cordis.yml` entry name that carries telemetry consent. */ +export const DEFAULT_TELEMETRY_PLUGIN_NAME = '@deepseek-ai/dsh-telemetry' + +/** + * Passthrough for Cordis' `!!js` expression tag so parsing consent never fails + * on projects that inline JavaScript expressions; the resolver only reads plain + * `name`/`disabled` scalars and does not evaluate expressions. + */ +const JS_EXPRESSION_TAG: ScalarTag = { + tag: 'tag:yaml.org,2002:js', + resolve: value => value, +} + +/** Why telemetry is or is not permitted for one command. */ +export type ConsentReason = + | 'enabled' + | 'disabled' + | 'absent' + | 'no-config' + | 'do-not-track' + | 'ci' + | 'unreadable' + +/** Resolved telemetry consent for one command invocation. */ +export interface ConsentDecision { + /** Whether telemetry may be sent. */ + allowed: boolean + /** The signal that determined {@link allowed}. */ + reason: ConsentReason +} + +/** Tuning for {@link ConsentResolver}; every field defaults to a documented value. */ +export interface ConsentResolverOptions { + /** `cordis.yml` entry name whose enabled state carries consent. */ + telemetryPluginName?: string + /** Environment used for `DO_NOT_TRACK`/CI checks; defaults to `process.env`. */ + env?: NodeJS.ProcessEnv + /** Honor `DO_NOT_TRACK`/CI env signals as a hard opt-out. Defaults to `true`. */ + honorEnvOptOut?: boolean + /** Consent when `cordis.yml` does not exist yet (first `create`). Defaults to `true` (telemetry is default-on). */ + allowWhenNoConfig?: boolean + /** Consent when `cordis.yml` exists but has no telemetry entry. Defaults to `false`. */ + allowWhenEntryAbsent?: boolean +} + +/** Whether an environment variable is set to a non-empty, non-"0"/"false" value. */ +function envEnabled(value: string | undefined): boolean { + if (value === undefined) return false + const normalized = value.trim().toLowerCase() + return normalized.length > 0 && normalized !== '0' && normalized !== 'false' +} + +/** Read a `cordis.yml` entry's `name`/`disabled` scalars, tolerating `!!js` tags. */ +function readTelemetryEntry(text: string, pluginName: string): { present: boolean; disabled: boolean } { + const document = parseDocument(text, { customTags: [JS_EXPRESSION_TAG] }) + const contents: unknown = document.toJS({ maxAliasCount: -1 }) + if (!Array.isArray(contents)) return { present: false, disabled: false } + for (const entry of contents) { + if (entry === null || typeof entry !== 'object') continue + const record = entry as Record + if (record.name === pluginName) return { present: true, disabled: record.disabled === true } + } + return { present: false, disabled: false } +} + +/** Resolve telemetry consent by parsing a project's `cordis.yml` and the environment. */ +export class ConsentResolver { + readonly #pluginName: string + readonly #env: NodeJS.ProcessEnv + readonly #honorEnvOptOut: boolean + readonly #allowWhenNoConfig: boolean + readonly #allowWhenEntryAbsent: boolean + + /** @param options - plugin name, environment, and default-decision knobs. */ + constructor(options: ConsentResolverOptions = {}) { + this.#pluginName = options.telemetryPluginName ?? DEFAULT_TELEMETRY_PLUGIN_NAME + this.#env = options.env ?? process.env + this.#honorEnvOptOut = options.honorEnvOptOut ?? true + this.#allowWhenNoConfig = options.allowWhenNoConfig ?? true + this.#allowWhenEntryAbsent = options.allowWhenEntryAbsent ?? false + } + + /** + * Resolve consent for a command run in the given project directory. + * @param projectDir - absolute or relative project root containing `cordis.yml`. + * @returns the consent decision and the signal that produced it. + */ + async resolve(projectDir: string): Promise { + if (this.#honorEnvOptOut) { + if (envEnabled(this.#env.DO_NOT_TRACK)) return { allowed: false, reason: 'do-not-track' } + if (envEnabled(this.#env.CI)) return { allowed: false, reason: 'ci' } + } + let text: string + try { + text = await readFile(join(projectDir, 'cordis.yml'), 'utf8') + } catch (error) { + // Missing cordis.yml is the first-init (`create`) path; any other read + // fault is treated conservatively as its own reason. + if ((error as NodeJS.ErrnoException).code === 'ENOENT') { + return { allowed: this.#allowWhenNoConfig, reason: 'no-config' } + } + return { allowed: false, reason: 'unreadable' } + } + const entry = readTelemetryEntry(text, this.#pluginName) + if (!entry.present) return { allowed: this.#allowWhenEntryAbsent, reason: 'absent' } + return entry.disabled ? { allowed: false, reason: 'disabled' } : { allowed: true, reason: 'enabled' } + } +} diff --git a/packages/sdk/telemetry/src/index.ts b/packages/sdk/telemetry/src/index.ts new file mode 100644 index 0000000000..107956fa39 --- /dev/null +++ b/packages/sdk/telemetry/src/index.ts @@ -0,0 +1,45 @@ +/** + * Launcher-side telemetry for the dsh-sdk toolchain: secret redaction, consent + * resolution, anonymous id, payload assembly, and a fire-and-forget reporter. + * + * This package is a plain library the launcher imports around each command — it + * is NOT a Cordis plugin (several commands never boot Cordis). Wiring it into + * the launcher command dispatch and the helper feature catalog lives outside + * this package. + * + * @module @deepseek-ai/dsh-telemetry + */ + +export { + DEFAULT_ENTROPY_THRESHOLD, + DEFAULT_MIN_TOKEN_LENGTH, + DEFAULT_REDACTION_PLACEHOLDER, + SecretRedactor, + keyLooksSecret, +} from './secret-redactor.ts' +export type { SecretRedactorOptions } from './secret-redactor.ts' +export { + ConsentResolver, + DEFAULT_TELEMETRY_PLUGIN_NAME, +} from './consent-resolver.ts' +export type { + ConsentDecision, + ConsentReason, + ConsentResolverOptions, +} from './consent-resolver.ts' +export { + ANONYMOUS_ID_FILE_NAME, + getOrCreateAnonymousId, + globalConfigDir, +} from './anonymous-id.ts' +export type { AnonymousId, AnonymousIdOptions } from './anonymous-id.ts' +export { buildTelemetryPayload } from './payload.ts' +export type { BuildTelemetryPayloadInput, TelemetryPayload } from './payload.ts' +export { + DEFAULT_FLUSH_TIMEOUT_MS, + DEFAULT_SEND_TIMEOUT_MS, + DSH_TELEMETRY_ENDPOINT, + TELEMETRY_SCHEMA_VERSION, + TelemetryReporter, +} from './reporter.ts' +export type { DeliveryOutcome, TelemetryReporterOptions } from './reporter.ts' diff --git a/packages/sdk/telemetry/src/payload.ts b/packages/sdk/telemetry/src/payload.ts new file mode 100644 index 0000000000..96a7b19d76 --- /dev/null +++ b/packages/sdk/telemetry/src/payload.ts @@ -0,0 +1,75 @@ +/** + * Telemetry payload assembly. + * + * The payload carries the command lifecycle plus the FULL redacted content of + * the project `cordis.yml` and `package.json`. It NEVER reads or includes `.env` + * — secrets live only in `.env`, and the redactor is the backstop for any that + * leak into the two reported files. A file that does not exist (the first + * `create` run) simply omits its field. + * + * @module @deepseek-ai/dsh-telemetry/payload + */ + +import { readFile } from 'node:fs/promises' +import { join } from 'node:path' +import { SecretRedactor } from './secret-redactor.ts' + +/** Project files whose full (redacted) content ships with the payload. */ +const REPORTED_FILES = ['cordis.yml', 'package.json'] as const + +/** One command's telemetry payload. */ +export interface TelemetryPayload { + /** The dsh-sdk command that ran (`start`/`dev`/`build`/`config`/`create`). */ + command: string + /** Wall-clock duration of the command in milliseconds. */ + durationMs: number + /** Whether the command completed without error. */ + success: boolean + /** Redacted full text of the project `cordis.yml`, absent when the file does not exist. */ + cordisYmlContent?: string + /** Redacted full text of the project `package.json`, absent when the file does not exist. */ + packageJsonContent?: string +} + +/** Inputs for {@link buildTelemetryPayload}. */ +export interface BuildTelemetryPayloadInput { + /** The dsh-sdk command that ran. */ + command: string + /** Wall-clock duration of the command in milliseconds. */ + durationMs: number + /** Whether the command completed without error. */ + success: boolean + /** Project root whose `cordis.yml` and `package.json` are read. */ + projectDir: string + /** Redactor applied to reported file content; defaults to a fresh {@link SecretRedactor}. */ + redactor?: SecretRedactor +} + +/** Read a project file's text, returning `undefined` when it cannot be read. */ +async function readReportedFile(projectDir: string, name: string): Promise { + try { + return await readFile(join(projectDir, name), 'utf8') + } catch { + // Missing/unreadable reported file: telemetry omits the field rather than fail. + return undefined + } +} + +/** + * Assemble a redacted telemetry payload for one command invocation. + * @param input - command lifecycle facts, project directory, and optional redactor. + * @returns the payload with redacted `cordis.yml`/`package.json` content. + */ +export async function buildTelemetryPayload(input: BuildTelemetryPayloadInput): Promise { + const redactor = input.redactor ?? new SecretRedactor() + const [cordisYml, packageJson] = await Promise.all( + REPORTED_FILES.map(name => readReportedFile(input.projectDir, name)), + ) + return { + command: input.command, + durationMs: input.durationMs, + success: input.success, + ...cordisYml !== undefined ? { cordisYmlContent: redactor.redactText(cordisYml) } : {}, + ...packageJson !== undefined ? { packageJsonContent: redactor.redactText(packageJson) } : {}, + } +} diff --git a/packages/sdk/telemetry/src/reporter.ts b/packages/sdk/telemetry/src/reporter.ts new file mode 100644 index 0000000000..d41c1db9b7 --- /dev/null +++ b/packages/sdk/telemetry/src/reporter.ts @@ -0,0 +1,149 @@ +/** + * Fire-and-forget telemetry reporter for the dsh-sdk launcher. + * + * The reporter must NEVER block or crash a command: {@link TelemetryReporter.report} + * schedules a detached send and returns immediately, and the underlying delivery + * resolves on every path (consent skip, network failure, non-OK status) instead + * of rejecting. {@link TelemetryReporter.flush} lets the launcher optionally + * drain in-flight sends within a cap before exit. + * + * @module @deepseek-ai/dsh-telemetry/reporter + */ + +import type { ConsentDecision } from './consent-resolver.ts' +import type { TelemetryPayload } from './payload.ts' +import { getOrCreateAnonymousId, type AnonymousId } from './anonymous-id.ts' +import { SecretRedactor } from './secret-redactor.ts' + +/** + * Placeholder collection endpoint. This is a fixed protocol constant, not a + * deployment tunable. + * + * FIXME(ccyu): replace with the real telemetry endpoint before release. The + * `.invalid` TLD guarantees delivery fails harmlessly until then. + */ +export const DSH_TELEMETRY_ENDPOINT = 'https://telemetry.example.invalid/v1/dsh-sdk' + +/** Wire-envelope schema version; bump on any incompatible body change. */ +export const TELEMETRY_SCHEMA_VERSION = 1 + +/** Default per-request send timeout in milliseconds. */ +export const DEFAULT_SEND_TIMEOUT_MS = 3000 + +/** Default cap for {@link TelemetryReporter.flush} in milliseconds. */ +export const DEFAULT_FLUSH_TIMEOUT_MS = 2000 + +/** Outcome of one delivery attempt; delivery never rejects. */ +export type DeliveryOutcome = + | { status: 'skipped'; reason: string } + | { status: 'sent' } + | { status: 'failed'; error: string } + +/** The JSON body posted to the telemetry endpoint. */ +interface TelemetryEnvelope extends TelemetryPayload { + schemaVersion: number + anonymousId: AnonymousId + sentAt: string +} + +/** Injectable seams for {@link TelemetryReporter}; every field has a default. */ +export interface TelemetryReporterOptions { + /** Collection endpoint; defaults to {@link DSH_TELEMETRY_ENDPOINT}. */ + endpoint?: string + /** `fetch` implementation; defaults to the global `fetch`. */ + fetch?: typeof globalThis.fetch + /** Anonymous-id provider; defaults to {@link getOrCreateAnonymousId}. */ + anonymousId?: () => Promise + /** Redactor applied to the assembled envelope as a final backstop; defaults to a fresh {@link SecretRedactor}. */ + redactor?: SecretRedactor + /** Per-request send timeout in milliseconds. */ + timeoutMs?: number + /** Clock for the envelope timestamp; defaults to `Date.now`. */ + now?: () => number +} + +/** Sends telemetry payloads fire-and-forget, swallowing every failure. */ +export class TelemetryReporter { + readonly #endpoint: string + readonly #fetch: typeof globalThis.fetch + readonly #anonymousId: () => Promise + readonly #redactor: SecretRedactor + readonly #timeoutMs: number + readonly #now: () => number + readonly #inflight = new Set>() + + /** @param options - endpoint, transport, id provider, and timing seams. */ + constructor(options: TelemetryReporterOptions = {}) { + this.#endpoint = options.endpoint ?? DSH_TELEMETRY_ENDPOINT + this.#fetch = options.fetch ?? globalThis.fetch + this.#anonymousId = options.anonymousId ?? getOrCreateAnonymousId + this.#redactor = options.redactor ?? new SecretRedactor() + this.#timeoutMs = options.timeoutMs ?? DEFAULT_SEND_TIMEOUT_MS + this.#now = options.now ?? Date.now + } + + /** + * Schedule a detached, non-blocking send. Returns immediately and never + * throws; the send's outcome is observable only through {@link flush}. + * @param payload - the command payload to report. + * @param consent - resolved consent; a denial short-circuits to a skip. + */ + report(payload: TelemetryPayload, consent: ConsentDecision): void { + const pending = this.#deliver(payload, consent) + this.#inflight.add(pending) + void pending.finally(() => this.#inflight.delete(pending)) + } + + /** + * Await in-flight sends up to a timeout so a caller can drain before exit. + * Resolves on the cap regardless of send progress; never rejects. + * @param timeoutMs - maximum time to wait; defaults to {@link DEFAULT_FLUSH_TIMEOUT_MS}. + */ + async flush(timeoutMs: number = DEFAULT_FLUSH_TIMEOUT_MS): Promise { + if (this.#inflight.size === 0) return + const drained = Promise.allSettled([...this.#inflight]).then(() => undefined) + let timer!: ReturnType + const capped = new Promise((resolve) => { + timer = setTimeout(resolve, timeoutMs) + }) + try { + await Promise.race([drained, capped]) + } finally { + clearTimeout(timer) + } + } + + /** Deliver one payload, resolving to an outcome on every path (never rejects). */ + async #deliver(payload: TelemetryPayload, consent: ConsentDecision): Promise { + if (!consent.allowed) return { status: 'skipped', reason: consent.reason } + try { + const envelope: TelemetryEnvelope = { + schemaVersion: TELEMETRY_SCHEMA_VERSION, + anonymousId: await this.#anonymousId(), + sentAt: new Date(this.#now()).toISOString(), + ...payload, + // Idempotent backstop over the only free-form fields, in case a caller + // built the payload without buildTelemetryPayload. Applied to content + // text only so the anonymous id and metadata are never disturbed. + ...payload.cordisYmlContent !== undefined + ? { cordisYmlContent: this.#redactor.redactText(payload.cordisYmlContent) } + : {}, + ...payload.packageJsonContent !== undefined + ? { packageJsonContent: this.#redactor.redactText(payload.packageJsonContent) } + : {}, + } + const response = await this.#fetch(this.#endpoint, { + method: 'POST', + headers: { 'content-type': 'application/json' }, + body: JSON.stringify(envelope), + signal: AbortSignal.timeout(this.#timeoutMs), + }) + if (!response.ok) return { status: 'failed', error: `HTTP ${response.status}` } + return { status: 'sent' } + } catch (error) { + // Telemetry is best-effort: network faults, aborts, and id/redaction + // errors are swallowed so the command is never affected. + return { status: 'failed', error: error instanceof Error ? error.message : String(error) } + } + } +} diff --git a/packages/sdk/telemetry/src/secret-redactor.ts b/packages/sdk/telemetry/src/secret-redactor.ts new file mode 100644 index 0000000000..5b9af5f169 --- /dev/null +++ b/packages/sdk/telemetry/src/secret-redactor.ts @@ -0,0 +1,203 @@ +/** + * Conservative secret redactor: the safety backstop that scrubs credential-like + * values from telemetry content before it leaves the machine. + * + * The redactor never drops a field or line — it only replaces the secret-shaped + * VALUE with a fixed placeholder, so the surrounding structure (keys, package + * names, base URLs, dependency pins) stays intact for the maintainer. It leans + * toward redaction on strong signals (secret-like key names, known token + * shapes, PEM blocks, URL credentials, high-entropy opaque tokens) while + * deliberately leaving low-signal values (package names, versions, git SHAs, + * plain URLs, kebab identifiers) untouched, because those are exactly the + * signal telemetry exists to capture. + * + * @module @deepseek-ai/dsh-telemetry/secret-redactor + */ + +/** Default text substituted for a detected secret. */ +export const DEFAULT_REDACTION_PLACEHOLDER = '[REDACTED]' + +/** Default minimum length for the high-entropy opaque-token heuristic. */ +export const DEFAULT_MIN_TOKEN_LENGTH = 24 + +/** Default Shannon-entropy threshold (bits/char) that marks an opaque token secret. */ +export const DEFAULT_ENTROPY_THRESHOLD = 4 + +/** Tuning for {@link SecretRedactor}; every field defaults to a documented constant. */ +export interface SecretRedactorOptions { + /** Replacement text for a detected secret. */ + placeholder?: string + /** Minimum length before the high-entropy heuristic considers an opaque token. */ + minTokenLength?: number + /** Shannon entropy (bits/char) at or above which an opaque token is treated as secret. */ + entropyThreshold?: number +} + +/** + * Regexes for well-known credential shapes. A match anywhere in a candidate + * token marks it secret regardless of length, so short-but-recognizable tokens + * are caught even when the entropy heuristic would not fire. + */ +const KNOWN_SECRET_PATTERNS: readonly RegExp[] = [ + /sk-(?:ant-)?[A-Za-z0-9_-]{10,}/, // OpenAI / DeepSeek / Anthropic style + /gh[pousr]_[A-Za-z0-9]{16,}/, // GitHub personal/oauth/server/refresh tokens + /github_pat_[A-Za-z0-9_]{20,}/, // GitHub fine-grained PAT + /xox[baprs]-[A-Za-z0-9-]{10,}/, // Slack tokens + /AKIA[0-9A-Z]{16}/, // AWS access key id + /AIza[0-9A-Za-z_-]{35}/, // Google API key + /eyJ[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{8,}/, // JWT +] + +/** + * Key names (normalized to lowercase, separators stripped) whose value is a + * secret. Split by match strategy so short/ambiguous words do not over-match: + * `author` must not trip the `auth` rule. + */ +const KEY_SUBSTRING_INDICATORS: readonly string[] = [ + 'password', 'passwd', 'passphrase', 'secret', 'apikey', 'apisecret', + 'clientsecret', 'privatekey', 'secretkey', 'accesskey', 'credential', + 'connectionstring', 'sastoken', 'xapikey', 'authtoken', 'accesstoken', + 'refreshtoken', 'idtoken', 'sessiontoken', 'bearertoken', +] +const KEY_SUFFIX_INDICATORS: readonly string[] = ['token'] +const KEY_EXACT_INDICATORS: readonly string[] = [ + 'auth', 'authorization', 'cookie', 'bearer', 'dsn', 'signature', +] + +/** + * Whether a key name marks its value as a secret. + * @param key - raw object key or assignment name. + * @returns whether the value under this key must be redacted. + */ +export function keyLooksSecret(key: string): boolean { + const normalized = key.toLowerCase().replace(/[^a-z0-9]/g, '') + if (normalized.length === 0) return false + if (KEY_SUBSTRING_INDICATORS.some(indicator => normalized.includes(indicator))) return true + if (KEY_SUFFIX_INDICATORS.some(indicator => normalized.endsWith(indicator))) return true + return KEY_EXACT_INDICATORS.includes(normalized) +} + +/** Shannon entropy in bits per character. */ +function shannonEntropy(value: string): number { + const counts = new Map() + for (const char of value) counts.set(char, (counts.get(char) ?? 0) + 1) + let entropy = 0 + for (const count of counts.values()) { + const probability = count / value.length + entropy -= probability * Math.log2(probability) + } + return entropy +} + +/** Opaque-token character set (base64/base64url plus common token punctuation). */ +const OPAQUE_TOKEN = /^[A-Za-z0-9+/=_.-]+$/ +/** Version-like leader kept visible (dependency pins, semver). */ +const VERSION_LIKE = /^v?\d+(?:\.\d+)+/ + +/** + * Conservative secret detector and redactor for telemetry content. + * Detection is a pure function of the input; construction only fixes tunables. + */ +export class SecretRedactor { + readonly #placeholder: string + readonly #minTokenLength: number + readonly #entropyThreshold: number + + /** @param options - placeholder text and heuristic thresholds. */ + constructor(options: SecretRedactorOptions = {}) { + this.#placeholder = options.placeholder ?? DEFAULT_REDACTION_PLACEHOLDER + this.#minTokenLength = options.minTokenLength ?? DEFAULT_MIN_TOKEN_LENGTH + this.#entropyThreshold = options.entropyThreshold ?? DEFAULT_ENTROPY_THRESHOLD + } + + /** + * Whether a standalone token value looks like a secret. + * @param value - candidate token, already trimmed of surrounding quotes. + * @returns whether the value should be redacted on its own merits. + */ + isSecretValue(value: string): boolean { + if (KNOWN_SECRET_PATTERNS.some(pattern => pattern.test(value))) return true + if (value.length < this.#minTokenLength) return false + if (!OPAQUE_TOKEN.test(value)) return false + // Git SHAs and integrity digests are hex and public — never a secret we hide. + if (/^[0-9a-fA-F]+$/.test(value)) return false + if (VERSION_LIKE.test(value)) return false + const classes = (/[a-z]/.test(value) ? 1 : 0) + (/[A-Z]/.test(value) ? 1 : 0) + (/[0-9]/.test(value) ? 1 : 0) + return classes >= 3 || shannonEntropy(value) >= this.#entropyThreshold + } + + /** + * Deep-redact a parsed value in place-safe fashion, returning a new structure. + * A secret-named key redacts its string value outright; every other string is + * judged on its own shape. Non-string leaves pass through untouched. + * @param value - parsed JSON-like value (object, array, or primitive). + * @returns a structurally identical value with secret strings replaced. + */ + redactValue(value: T): T { + return this.#redactNode(value, false) as T + } + + #redactNode(value: unknown, keyIsSecret: boolean): unknown { + if (typeof value === 'string') { + return keyIsSecret || this.isSecretValue(value) ? this.#placeholder : value + } + if (Array.isArray(value)) return value.map(item => this.#redactNode(item, false)) + if (value !== null && typeof value === 'object') { + return Object.fromEntries( + Object.entries(value).map(([key, child]) => [key, this.#redactNode(child, keyLooksSecret(key))]), + ) + } + return value + } + + /** + * Redact secrets embedded in raw text (YAML, JSON, or `.env`-style content), + * preserving every line and key while replacing only secret-shaped values. + * @param text - raw file or message text. + * @returns text with detected secrets replaced by the placeholder. + */ + redactText(text: string): string { + let output = this.#redactPemBlocks(text) + output = this.#redactAssignments(output) + output = this.#redactUrlCredentials(output) + output = this.#redactBearerTokens(output) + return this.#redactStandaloneTokens(output) + } + + #redactPemBlocks(text: string): string { + return text.replace( + /-----BEGIN (?:[A-Z ]+ )?PRIVATE KEY-----[\s\S]*?-----END (?:[A-Z ]+ )?PRIVATE KEY-----/g, + this.#placeholder, + ) + } + + #redactAssignments(text: string): string { + // `key: value`, `key = value`, or `"key": "value"` across YAML/JSON/.env. + return text.replace( + /("?)([A-Za-z0-9_.-]+)\1(\s*[:=]\s*)(["']?)([^\n\r"']+)\4/g, + (match, keyQuote: string, key: string, separator: string, valueQuote: string, value: string) => + keyLooksSecret(key) && value.trim().length > 0 + ? `${keyQuote}${key}${keyQuote}${separator}${valueQuote}${this.#placeholder}${valueQuote}` + : match, + ) + } + + #redactUrlCredentials(text: string): string { + // Redact only the password in `scheme://user:password@host`, keeping host visible. + return text.replace( + /([a-z][a-z0-9+.-]*:\/\/[^\s:/@]+:)([^\s/@]+)(@)/gi, + (_match, prefix: string, _password: string, at: string) => `${prefix}${this.#placeholder}${at}`, + ) + } + + #redactBearerTokens(text: string): string { + return text.replace(/(bearer\s+)([a-z0-9._-]{8,})/gi, (_match, prefix: string) => `${prefix}${this.#placeholder}`) + } + + #redactStandaloneTokens(text: string): string { + // `/` is excluded so package names, file paths, and URLs are never split or + // redacted; a secret containing `/` is still scrubbed piecewise. + return text.replace(/[A-Za-z0-9][A-Za-z0-9+=_.-]{7,}/g, token => + this.isSecretValue(token) ? this.#placeholder : token) + } +} diff --git a/packages/sdk/telemetry/tests/anonymous-id.spec.ts b/packages/sdk/telemetry/tests/anonymous-id.spec.ts new file mode 100644 index 0000000000..df8bcffea2 --- /dev/null +++ b/packages/sdk/telemetry/tests/anonymous-id.spec.ts @@ -0,0 +1,100 @@ +import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it } from 'vitest' +import { + ANONYMOUS_ID_FILE_NAME, + getOrCreateAnonymousId, + globalConfigDir, +} from '@deepseek-ai/dsh-telemetry' + +const dirs: string[] = [] + +async function tempDir(): Promise { + const dir = await mkdtemp(join(tmpdir(), 'dsh-anon-')) + dirs.push(dir) + return dir +} + +afterEach(async () => { + await Promise.all(dirs.splice(0).map(dir => rm(dir, { recursive: true, force: true }))) +}) + +const UUID = /^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$/i + +describe('globalConfigDir', () => { + it('prefers an explicit DSH_CONFIG_HOME override', () => { + expect(globalConfigDir({ env: { DSH_CONFIG_HOME: '/custom/dsh' } })).toBe('/custom/dsh') + }) + + it('falls back to XDG_CONFIG_HOME under the harness namespace', () => { + expect(globalConfigDir({ env: { XDG_CONFIG_HOME: '/xdg' } })).toBe(join('/xdg', 'deepseek-harness')) + }) + + it('uses %APPDATA% on Windows', () => { + expect(globalConfigDir({ env: { APPDATA: 'C:/Users/x/AppData/Roaming' }, platform: 'win32' })) + .toBe(join('C:/Users/x/AppData/Roaming', 'deepseek-harness')) + }) + + it('falls back to ~/.config on Windows without APPDATA and on posix', () => { + const home = () => '/home/dev' + expect(globalConfigDir({ env: {}, platform: 'win32', homeDir: home })) + .toBe(join('/home/dev', '.config', 'deepseek-harness')) + expect(globalConfigDir({ env: {}, platform: 'linux', homeDir: home })) + .toBe(join('/home/dev', '.config', 'deepseek-harness')) + }) + + it('reads process.env by default', () => { + // No override supplied: the call must not throw and must return an absolute path. + expect(globalConfigDir()).toContain('deepseek-harness') + }) +}) + +describe('getOrCreateAnonymousId', () => { + it('creates, persists, and returns a UUID on first use', async () => { + const dir = await tempDir() + const id = await getOrCreateAnonymousId({ env: { DSH_CONFIG_HOME: dir } }) + expect(id).toMatch(UUID) + const stored: unknown = JSON.parse(await readFile(join(dir, ANONYMOUS_ID_FILE_NAME), 'utf8')) + expect(stored).toEqual({ anonymousId: id }) + }) + + it('returns the same persisted id on subsequent calls', async () => { + const dir = await tempDir() + const first = await getOrCreateAnonymousId({ env: { DSH_CONFIG_HOME: dir } }) + const second = await getOrCreateAnonymousId({ env: { DSH_CONFIG_HOME: dir } }) + expect(second).toBe(first) + }) + + it('uses the injected UUID generator', async () => { + const dir = await tempDir() + const id = await getOrCreateAnonymousId({ + env: { DSH_CONFIG_HOME: dir }, + randomUUID: () => '00000000-0000-4000-8000-000000000000', + }) + expect(id).toBe('00000000-0000-4000-8000-000000000000') + }) + + it('regenerates when the stored file is corrupt JSON', async () => { + const dir = await tempDir() + await writeFile(join(dir, ANONYMOUS_ID_FILE_NAME), 'not json', 'utf8') + const id = await getOrCreateAnonymousId({ env: { DSH_CONFIG_HOME: dir } }) + expect(id).toMatch(UUID) + }) + + it('regenerates when the stored value is not a valid UUID or object', async () => { + const dir = await tempDir() + await writeFile(join(dir, ANONYMOUS_ID_FILE_NAME), JSON.stringify({ anonymousId: 'nope' }), 'utf8') + expect(await getOrCreateAnonymousId({ env: { DSH_CONFIG_HOME: dir } })).toMatch(UUID) + await writeFile(join(dir, ANONYMOUS_ID_FILE_NAME), '123', 'utf8') + expect(await getOrCreateAnonymousId({ env: { DSH_CONFIG_HOME: dir } })).toMatch(UUID) + }) + + it('returns a usable id even when persistence fails', async () => { + const dir = await tempDir() + // A regular file where a directory is expected makes mkdir/writeFile fail. + await writeFile(join(dir, 'blocker'), 'x', 'utf8') + const id = await getOrCreateAnonymousId({ env: { DSH_CONFIG_HOME: join(dir, 'blocker') } }) + expect(id).toMatch(UUID) + }) +}) diff --git a/packages/sdk/telemetry/tests/consent-resolver.spec.ts b/packages/sdk/telemetry/tests/consent-resolver.spec.ts new file mode 100644 index 0000000000..e1f5f90f81 --- /dev/null +++ b/packages/sdk/telemetry/tests/consent-resolver.spec.ts @@ -0,0 +1,131 @@ +import { mkdtemp, mkdir, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it } from 'vitest' +import { ConsentResolver, DEFAULT_TELEMETRY_PLUGIN_NAME, type ConsentDecision } from '@deepseek-ai/dsh-telemetry' + +const dirs: string[] = [] + +async function projectDir(cordisYml?: string): Promise { + const dir = await mkdtemp(join(tmpdir(), 'dsh-consent-')) + dirs.push(dir) + if (cordisYml !== undefined) await writeFile(join(dir, 'cordis.yml'), cordisYml, 'utf8') + return dir +} + +afterEach(async () => { + await Promise.all(dirs.splice(0).map(dir => import('node:fs/promises').then(fs => fs.rm(dir, { recursive: true, force: true })))) +}) + +const enabledYml = `- id: telemetry\n name: '${DEFAULT_TELEMETRY_PLUGIN_NAME}'\n` + +describe('ConsentResolver environment opt-out', () => { + it('denies when DO_NOT_TRACK is set', async () => { + const decision = await new ConsentResolver({ env: { DO_NOT_TRACK: '1' } }).resolve(await projectDir(enabledYml)) + expect(decision).toEqual({ allowed: false, reason: 'do-not-track' }) + }) + + it('denies when CI is set', async () => { + const decision = await new ConsentResolver({ env: { CI: 'true' } }).resolve(await projectDir(enabledYml)) + expect(decision).toEqual({ allowed: false, reason: 'ci' }) + }) + + it('ignores falsy env values and continues to the file', async () => { + const decision = await new ConsentResolver({ env: { DO_NOT_TRACK: '0', CI: 'false' } }) + .resolve(await projectDir(enabledYml)) + expect(decision).toEqual({ allowed: true, reason: 'enabled' }) + }) + + it('can be told to ignore env opt-out signals', async () => { + const decision = await new ConsentResolver({ env: { DO_NOT_TRACK: '1' }, honorEnvOptOut: false }) + .resolve(await projectDir(enabledYml)) + expect(decision).toEqual({ allowed: true, reason: 'enabled' }) + }) + + it('reads process.env by default', async () => { + const saved = { CI: process.env.CI, DO_NOT_TRACK: process.env.DO_NOT_TRACK } + delete process.env.CI + delete process.env.DO_NOT_TRACK + try { + const decision = await new ConsentResolver().resolve(await projectDir(enabledYml)) + expect(decision).toEqual({ allowed: true, reason: 'enabled' }) + } finally { + if (saved.CI !== undefined) process.env.CI = saved.CI + if (saved.DO_NOT_TRACK !== undefined) process.env.DO_NOT_TRACK = saved.DO_NOT_TRACK + } + }) +}) + +describe('ConsentResolver cordis.yml state', () => { + const resolver = new ConsentResolver({ env: {} }) + + it('allows when the telemetry entry is enabled', async () => { + expect(await resolver.resolve(await projectDir(enabledYml))) + .toEqual({ allowed: true, reason: 'enabled' }) + }) + + it('denies when the telemetry entry is disabled', async () => { + const yml = `- id: telemetry\n name: '${DEFAULT_TELEMETRY_PLUGIN_NAME}'\n disabled: true\n` + expect(await resolver.resolve(await projectDir(yml))) + .toEqual({ allowed: false, reason: 'disabled' }) + }) + + it('tolerates !!js expression tags while reading plain scalars', async () => { + const yml = [ + '- id: telemetry', + ` name: '${DEFAULT_TELEMETRY_PLUGIN_NAME}'`, + '- id: llm', + ' name: \'@deepseek-ai/dsh-llm-deepseek\'', + ' config:', + ' apiKey: !!js process.env.DEEPSEEK_API_KEY', + '', + ].join('\n') + expect(await resolver.resolve(await projectDir(yml))) + .toEqual({ allowed: true, reason: 'enabled' }) + }) + + it('reports absent when cordis.yml has no telemetry entry, defaulting to deny', async () => { + const yml = '- id: llm\n name: \'@deepseek-ai/dsh-llm-deepseek\'\n' + expect(await resolver.resolve(await projectDir(yml))) + .toEqual({ allowed: false, reason: 'absent' }) + }) + + it('can allow when the entry is absent', async () => { + const yml = '- id: llm\n name: \'@deepseek-ai/dsh-llm-deepseek\'\n' + const decision = await new ConsentResolver({ env: {}, allowWhenEntryAbsent: true }).resolve(await projectDir(yml)) + expect(decision).toEqual({ allowed: true, reason: 'absent' }) + }) + + it('skips non-object sequence items and a non-sequence root', async () => { + expect(await resolver.resolve(await projectDir('- just-a-string\n- id: x\n name: y\n'))) + .toEqual({ allowed: false, reason: 'absent' }) + expect(await resolver.resolve(await projectDir('root: not-a-sequence\n'))) + .toEqual({ allowed: false, reason: 'absent' }) + }) + + it('honors a custom telemetry plugin name', async () => { + const yml = '- id: t\n name: \'my-consent-marker\'\n' + const decision = await new ConsentResolver({ env: {}, telemetryPluginName: 'my-consent-marker' }) + .resolve(await projectDir(yml)) + expect(decision).toEqual({ allowed: true, reason: 'enabled' }) + }) +}) + +describe('ConsentResolver missing or unreadable cordis.yml', () => { + it('reports no-config and allows by default on first init', async () => { + expect(await new ConsentResolver({ env: {} }).resolve(await projectDir())) + .toEqual({ allowed: true, reason: 'no-config' }) + }) + + it('can deny on first init', async () => { + const decision = await new ConsentResolver({ env: {}, allowWhenNoConfig: false }).resolve(await projectDir()) + expect(decision).toEqual({ allowed: false, reason: 'no-config' }) + }) + + it('denies with an unreadable reason when cordis.yml is not a regular file', async () => { + const dir = await projectDir() + await mkdir(join(dir, 'cordis.yml')) // a directory where the resolver expects a file + expect(await new ConsentResolver({ env: {} }).resolve(dir)) + .toEqual({ allowed: false, reason: 'unreadable' }) + }) +}) diff --git a/packages/sdk/telemetry/tests/payload.spec.ts b/packages/sdk/telemetry/tests/payload.spec.ts new file mode 100644 index 0000000000..1af5139ef5 --- /dev/null +++ b/packages/sdk/telemetry/tests/payload.spec.ts @@ -0,0 +1,59 @@ +import { mkdtemp, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { afterEach, describe, expect, it } from 'vitest' +import { SecretRedactor, buildTelemetryPayload } from '@deepseek-ai/dsh-telemetry' + +const dirs: string[] = [] + +async function projectDir(files: Record): Promise { + const dir = await mkdtemp(join(tmpdir(), 'dsh-payload-')) + dirs.push(dir) + await Promise.all(Object.entries(files).map(([name, content]) => writeFile(join(dir, name), content, 'utf8'))) + return dir +} + +afterEach(async () => { + await Promise.all(dirs.splice(0).map(dir => rm(dir, { recursive: true, force: true }))) +}) + +describe('buildTelemetryPayload', () => { + it('carries lifecycle facts and redacted file content', async () => { + const dir = await projectDir({ + 'cordis.yml': '- id: llm\n name: \'@deepseek-ai/dsh-llm-deepseek\'\n config:\n apiKey: sk-abcdefghij1234567890\n', + 'package.json': '{ "name": "my-app", "config": { "token": "sk-abcdefghij1234567890" } }', + }) + const payload = await buildTelemetryPayload({ command: 'build', durationMs: 42, success: true, projectDir: dir }) + expect(payload.command).toBe('build') + expect(payload.durationMs).toBe(42) + expect(payload.success).toBe(true) + expect(payload.cordisYmlContent).toContain('@deepseek-ai/dsh-llm-deepseek') // package name preserved + expect(payload.cordisYmlContent).not.toContain('sk-abcdefghij1234567890') // secret scrubbed + expect(payload.packageJsonContent).toContain('my-app') + expect(payload.packageJsonContent).not.toContain('sk-abcdefghij1234567890') + }) + + it('omits fields whose files do not exist', async () => { + const dir = await projectDir({ 'cordis.yml': '- id: llm\n name: \'@deepseek-ai/dsh-llm-deepseek\'\n' }) + const payload = await buildTelemetryPayload({ command: 'create', durationMs: 1, success: false, projectDir: dir }) + expect(payload.cordisYmlContent).toBeDefined() + expect('packageJsonContent' in payload).toBe(false) + }) + + it('omits both fields when neither file exists', async () => { + const dir = await projectDir({}) + const payload = await buildTelemetryPayload({ command: 'create', durationMs: 0, success: true, projectDir: dir }) + expect('cordisYmlContent' in payload).toBe(false) + expect('packageJsonContent' in payload).toBe(false) + }) + + it('uses a supplied redactor', async () => { + const dir = await projectDir({ 'package.json': '{ "password": "hunter2" }' }) + const redactor = new SecretRedactor({ placeholder: '<>' }) + const payload = await buildTelemetryPayload({ + command: 'config', durationMs: 5, success: true, projectDir: dir, redactor, + }) + expect(payload.packageJsonContent).toContain('<>') + expect(payload.packageJsonContent).not.toContain('hunter2') + }) +}) diff --git a/packages/sdk/telemetry/tests/reporter.spec.ts b/packages/sdk/telemetry/tests/reporter.spec.ts new file mode 100644 index 0000000000..5d8a490b9e --- /dev/null +++ b/packages/sdk/telemetry/tests/reporter.spec.ts @@ -0,0 +1,134 @@ +import { describe, expect, it, vi } from 'vitest' +import { + DSH_TELEMETRY_ENDPOINT, + SecretRedactor, + TELEMETRY_SCHEMA_VERSION, + TelemetryReporter, + type AnonymousId, + type ConsentDecision, + type TelemetryPayload, +} from '@deepseek-ai/dsh-telemetry' + +const ALLOW: ConsentDecision = { allowed: true, reason: 'enabled' } +const DENY: ConsentDecision = { allowed: false, reason: 'disabled' } +const anon = (value = 'anon-123'): (() => Promise) => async () => value as AnonymousId + +function okResponse(): Response { + return { ok: true } as Response +} + +describe('TelemetryReporter.report', () => { + it('skips delivery when consent is denied', async () => { + const fetchMock = vi.fn(async () => okResponse()) + const reporter = new TelemetryReporter({ fetch: fetchMock, anonymousId: anon() }) + reporter.report({ command: 'build', durationMs: 1, success: true }, DENY) + await reporter.flush(50) + expect(fetchMock).not.toHaveBeenCalled() + }) + + it('posts a redacted envelope when consent is granted', async () => { + const fetchMock = vi.fn(() => Promise.resolve(okResponse())) + const reporter = new TelemetryReporter({ + endpoint: 'https://collector.test/telemetry', + fetch: fetchMock, + anonymousId: anon('anon-xyz'), + redactor: new SecretRedactor(), + now: () => 0, + timeoutMs: 100, + }) + const payload: TelemetryPayload = { + command: 'config', + durationMs: 7, + success: true, + cordisYmlContent: 'apiKey: sk-abcdefghij1234567890\nname: \'@deepseek-ai/dsh-llm-deepseek\'\n', + packageJsonContent: '{ "name": "app" }', + } + reporter.report(payload, ALLOW) + await reporter.flush(50) + + expect(fetchMock).toHaveBeenCalledTimes(1) + const call = fetchMock.mock.calls[0]! + expect(call[0]).toBe('https://collector.test/telemetry') + const init = call[1]! + expect(init.method).toBe('POST') + const body = JSON.parse(init.body as string) as Record + expect(body.schemaVersion).toBe(TELEMETRY_SCHEMA_VERSION) + expect(body.anonymousId).toBe('anon-xyz') + expect(body.sentAt).toBe('1970-01-01T00:00:00.000Z') + expect(body.command).toBe('config') + expect(body.cordisYmlContent).not.toContain('sk-abcdefghij1234567890') + expect(body.cordisYmlContent).toContain('@deepseek-ai/dsh-llm-deepseek') + expect(body.packageJsonContent).toContain('app') + }) + + it('posts an envelope without content fields when they are absent', async () => { + const fetchMock = vi.fn(() => Promise.resolve(okResponse())) + const reporter = new TelemetryReporter({ fetch: fetchMock, anonymousId: anon(), now: () => 0, timeoutMs: 100 }) + reporter.report({ command: 'start', durationMs: 2, success: true }, ALLOW) + await reporter.flush(50) + const body = JSON.parse(fetchMock.mock.calls[0]![1]!.body as string) as Record + expect('cordisYmlContent' in body).toBe(false) + expect('packageJsonContent' in body).toBe(false) + }) + + it('swallows a non-OK HTTP status', async () => { + const fetchMock = vi.fn(async () => ({ ok: false, status: 503 } as Response)) + const reporter = new TelemetryReporter({ fetch: fetchMock, anonymousId: anon(), timeoutMs: 100 }) + reporter.report({ command: 'dev', durationMs: 3, success: true }, ALLOW) + await expect(reporter.flush(50)).resolves.toBeUndefined() + expect(fetchMock).toHaveBeenCalledTimes(1) + }) + + it('swallows a transport failure', async () => { + const fetchMock = vi.fn(async () => { throw new Error('network down') }) + const reporter = new TelemetryReporter({ fetch: fetchMock, anonymousId: anon(), timeoutMs: 100 }) + reporter.report({ command: 'dev', durationMs: 3, success: false }, ALLOW) + await expect(reporter.flush(50)).resolves.toBeUndefined() + }) + + it('swallows a non-Error transport rejection', async () => { + const fetchMock = vi.fn(async () => { throw 'boom' }) + const reporter = new TelemetryReporter({ fetch: fetchMock, anonymousId: anon(), timeoutMs: 100 }) + reporter.report({ command: 'dev', durationMs: 3, success: false }, ALLOW) + await expect(reporter.flush(50)).resolves.toBeUndefined() + }) + + it('swallows a failure while resolving the anonymous id, never sending', async () => { + const fetchMock = vi.fn(async () => okResponse()) + const reporter = new TelemetryReporter({ + fetch: fetchMock, + anonymousId: async () => { throw new Error('config unwritable') }, + timeoutMs: 100, + }) + reporter.report({ command: 'build', durationMs: 1, success: true }, ALLOW) + await reporter.flush(50) + expect(fetchMock).not.toHaveBeenCalled() + }) +}) + +describe('TelemetryReporter.flush', () => { + it('returns immediately when nothing is in flight', async () => { + const reporter = new TelemetryReporter({ fetch: vi.fn(async () => okResponse()), anonymousId: anon() }) + await expect(reporter.flush()).resolves.toBeUndefined() + }) + + it('resolves on the timeout cap when a send never settles', async () => { + const reporter = new TelemetryReporter({ + fetch: () => new Promise(() => {}), + anonymousId: anon(), + timeoutMs: 10, + }) + reporter.report({ command: 'start', durationMs: 1, success: true }, ALLOW) + const started = Date.now() + await reporter.flush(15) + expect(Date.now() - started).toBeLessThan(1000) + }) +}) + +describe('TelemetryReporter defaults', () => { + it('defaults the endpoint and transport seams without options', () => { + const reporter = new TelemetryReporter() + expect(reporter).toBeInstanceOf(TelemetryReporter) + expect(DSH_TELEMETRY_ENDPOINT).toContain('.invalid') + }) +}) diff --git a/packages/sdk/telemetry/tests/secret-redactor.spec.ts b/packages/sdk/telemetry/tests/secret-redactor.spec.ts new file mode 100644 index 0000000000..c3250d9ace --- /dev/null +++ b/packages/sdk/telemetry/tests/secret-redactor.spec.ts @@ -0,0 +1,169 @@ +import { describe, expect, it } from 'vitest' +import { + DEFAULT_ENTROPY_THRESHOLD, + DEFAULT_MIN_TOKEN_LENGTH, + DEFAULT_REDACTION_PLACEHOLDER, + SecretRedactor, + keyLooksSecret, +} from '@deepseek-ai/dsh-telemetry' + +const REDACTED = DEFAULT_REDACTION_PLACEHOLDER + +describe('exported defaults', () => { + it('expose the documented tunable defaults', () => { + expect(DEFAULT_REDACTION_PLACEHOLDER).toBe('[REDACTED]') + expect(DEFAULT_MIN_TOKEN_LENGTH).toBe(24) + expect(DEFAULT_ENTROPY_THRESHOLD).toBe(4) + }) +}) + +describe('keyLooksSecret', () => { + it('matches secret substrings across casings and separators', () => { + for (const key of ['password', 'API_KEY', 'apiKey', 'clientSecret', 'x-api-key', 'privateKey', 'CREDENTIALS']) { + expect(keyLooksSecret(key)).toBe(true) + } + }) + + it('matches *token as a suffix but not tokenizer', () => { + expect(keyLooksSecret('accessToken')).toBe(true) + expect(keyLooksSecret('token')).toBe(true) + expect(keyLooksSecret('tokenizer')).toBe(false) + }) + + it('matches short ambiguous words only as whole keys', () => { + expect(keyLooksSecret('auth')).toBe(true) + expect(keyLooksSecret('authorization')).toBe(true) + expect(keyLooksSecret('cookie')).toBe(true) + expect(keyLooksSecret('author')).toBe(false) + }) + + it('does not match ordinary config keys', () => { + for (const key of ['name', 'version', 'model', 'baseURL', 'timeout', 'path', 'pass']) { + expect(keyLooksSecret(key)).toBe(false) + } + }) + + it('returns false for a key with no alphanumerics', () => { + expect(keyLooksSecret('---')).toBe(false) + }) +}) + +describe('SecretRedactor.isSecretValue', () => { + const redactor = new SecretRedactor() + + it('detects known token shapes regardless of length', () => { + expect(redactor.isSecretValue('sk-abcdefghij1234567890')).toBe(true) + expect(redactor.isSecretValue('sk-ant-abcdefghij1234567890')).toBe(true) + expect(redactor.isSecretValue('ghp_abcdefghijklmnop1234')).toBe(true) + expect(redactor.isSecretValue('github_pat_abcdefghijklmnopqrst')).toBe(true) + expect(redactor.isSecretValue('xoxb-abcdefghij-klmno')).toBe(true) + expect(redactor.isSecretValue('AKIA1234567890ABCDEF')).toBe(true) + expect(redactor.isSecretValue(`AIza${'a'.repeat(35)}`)).toBe(true) + expect(redactor.isSecretValue('eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiIxIn0.abcdefghijklmnop')).toBe(true) + }) + + it('detects high-entropy opaque tokens with three character classes', () => { + // Non-hex letters keep it off the hex-digest exemption; three classes trip the rule. + expect(redactor.isSecretValue('zX9zX9zX9zX9zX9zX9zX9zX9')).toBe(true) + }) + + it('detects high-entropy opaque tokens by entropy even within two classes', () => { + // 30 distinct lowercase+digit chars: entropy ~4.9, only two classes. + const token = 'abcdefghijklmnopqrstuvwxyz0123' + expect(token.length).toBeGreaterThanOrEqual(DEFAULT_MIN_TOKEN_LENGTH) + expect(redactor.isSecretValue(token)).toBe(true) + }) + + it('leaves short values, non-opaque text, hex digests, and versions untouched', () => { + expect(redactor.isSecretValue('deepseek-chat')).toBe(false) // short + expect(redactor.isSecretValue('a token with spaces here!!')).toBe(false) // not opaque + expect(redactor.isSecretValue('a'.repeat(40))).toBe(false) // low entropy, one class + expect(redactor.isSecretValue('abcdef0123456789abcdef0123456789abcdef01')).toBe(false) // 40-hex git SHA + expect(redactor.isSecretValue('1.2.3.4.5.6.7.8.9.10.11.12')).toBe(false) // version-like + expect(redactor.isSecretValue('ZXQPZXQPZXQPZXQPZXQPZXQP')).toBe(false) // uppercase only, low entropy + }) + + it('honors a custom entropy threshold', () => { + const strict = new SecretRedactor({ entropyThreshold: 100 }) + // Two-class token can no longer trip the entropy branch under an impossible threshold. + expect(strict.isSecretValue('abcdefghijklmnopqrstuvwxyz0123')).toBe(false) + }) +}) + +describe('SecretRedactor.redactValue', () => { + const redactor = new SecretRedactor() + + it('redacts secret-keyed strings and secret-shaped strings, keeping structure', () => { + const result = redactor.redactValue({ + apiKey: 'short-not-shaped', + name: 'my-package', + token: 'sk-abcdefghij1234567890', + count: 3, + enabled: true, + missing: null, + nested: { password: 'p', note: 'plain text value' }, + list: ['harmless', 'sk-abcdefghij1234567890'], + }) + expect(result).toEqual({ + apiKey: REDACTED, // redacted by key even though the value is not secret-shaped + name: 'my-package', + token: REDACTED, + count: 3, + enabled: true, + missing: null, + nested: { password: REDACTED, note: 'plain text value' }, + list: ['harmless', REDACTED], + }) + }) + + it('redacts a top-level secret string and passes through primitives', () => { + expect(redactor.redactValue('sk-abcdefghij1234567890')).toBe(REDACTED) + expect(redactor.redactValue('plain')).toBe('plain') + expect(redactor.redactValue(42)).toBe(42) + expect(redactor.redactValue(null)).toBeNull() + }) +}) + +describe('SecretRedactor.redactText', () => { + const redactor = new SecretRedactor() + + it('redacts PEM private key blocks', () => { + const text = '-----BEGIN RSA PRIVATE KEY-----\nMIIabc\ndef==\n-----END RSA PRIVATE KEY-----' + expect(redactor.redactText(text)).toBe(REDACTED) + }) + + it('redacts secret-keyed assignments across YAML, JSON, and .env', () => { + expect(redactor.redactText('password: hunter2')).toBe(`password: ${REDACTED}`) + expect(redactor.redactText('apiKey: "sk-abcdefghij1234567890"')).toBe(`apiKey: "${REDACTED}"`) + expect(redactor.redactText('"token": "abcdefgh"')).toBe(`"token": "${REDACTED}"`) + expect(redactor.redactText('API_KEY=sk-abcdefghij1234567890')).toBe(`API_KEY=${REDACTED}`) + }) + + it('keeps non-secret assignments and whitespace-only secret values intact', () => { + expect(redactor.redactText('model: deepseek-chat')).toBe('model: deepseek-chat') + expect(redactor.redactText('password: \n')).toBe('password: \n') + }) + + it('redacts only the password in URL credentials, keeping the host', () => { + expect(redactor.redactText('url: https://user:s3cretPass@api.deepseek.com/v1')) + .toBe(`url: https://user:${REDACTED}@api.deepseek.com/v1`) + }) + + it('redacts bearer tokens embedded in free text', () => { + expect(redactor.redactText('sending Bearer abcdefgh12345678 now')) + .toBe(`sending Bearer ${REDACTED} now`) + }) + + it('redacts standalone secret-shaped tokens while keeping package names and paths', () => { + expect(redactor.redactText('key sk-abcdefghij1234567890 end')) + .toBe(`key ${REDACTED} end`) + expect(redactor.redactText('name: @deepseek-ai/dsh-telemetry')).toBe('name: @deepseek-ai/dsh-telemetry') + expect(redactor.redactText('path: ./plugins/local-plugin/src/index.ts')) + .toBe('path: ./plugins/local-plugin/src/index.ts') + }) + + it('is idempotent on already-redacted text', () => { + const once = redactor.redactText('password: hunter2') + expect(redactor.redactText(once)).toBe(once) + }) +}) diff --git a/packages/sdk/telemetry/tsconfig.json b/packages/sdk/telemetry/tsconfig.json new file mode 100644 index 0000000000..8acc8f11c5 --- /dev/null +++ b/packages/sdk/telemetry/tsconfig.json @@ -0,0 +1,13 @@ +{ + "extends": "../../../tsconfig.base.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { "path": "../../util/brand" } + ] +} diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 25a8fadc47..0acc85fcab 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1267,6 +1267,19 @@ importers: specifier: ^4.22.4 version: 4.22.4 + packages/sdk/telemetry: + dependencies: + yaml: + specifier: ^2.9.0 + version: 2.9.0 + devDependencies: + '@deepseek-ai/dsh-brand': + specifier: workspace:^ + version: link:../../util/brand + cordis: + specifier: ^4.0.0-rc.7 + version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) + packages/session-persistence/session-persistence: devDependencies: '@deepseek-ai/dsh-session': diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 4a845b4554..004338fa2d 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -54,6 +54,7 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/sdk/helper': { kind: 'none', reason: 'The project domain edits files and registers no live agent or model surface.' }, 'packages/sdk/plugin-fetch': { kind: 'none', reason: 'The fetcher acquires plugin sources into a temp dir and registers no live agent or model surface.' }, 'packages/sdk/scripts': { kind: 'indirect', reason: 'The launcher delegates model context to the loaded project plugin tree.' }, + 'packages/sdk/telemetry': { kind: 'none', reason: 'The launcher-side reporter sends developer-cycle telemetry and registers no live agent or model surface.' }, 'packages/session-query/session-query': { kind: 'none', reason: 'The trusted query service exposes cloned records only to callers and registers no model surface.' }, 'packages/skill/skill': { kind: 'indirect', reason: 'The provider registry delegates model rendering to dsh-tool-skill.' }, 'packages/skill/skill-local': { kind: 'indirect', reason: 'The provider backend delegates model rendering to dsh-tool-skill.' }, diff --git a/tsconfig.build.json b/tsconfig.build.json index 9a6133db36..9359d7a531 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -99,6 +99,7 @@ { "path": "./packages/sdk/helper" }, { "path": "./packages/sdk/scripts" }, { "path": "./packages/sdk/create-sdk" }, - { "path": "./packages/sdk/plugin-fetch" } + { "path": "./packages/sdk/plugin-fetch" }, + { "path": "./packages/sdk/telemetry" } ] } diff --git a/tsconfig.json b/tsconfig.json index 4588c81c72..48c5187fdc 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -110,6 +110,7 @@ { "path": "./packages/sdk/helper" }, { "path": "./packages/sdk/scripts" }, { "path": "./packages/sdk/create-sdk" }, - { "path": "./packages/sdk/plugin-fetch" } + { "path": "./packages/sdk/plugin-fetch" }, + { "path": "./packages/sdk/telemetry" } ] } From a66b98d2705934cbf51c46beaa9c737b9c04176c Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 14:03:39 +0800 Subject: [PATCH 177/323] fix(telemetry): report unless telemetry entry is explicitly disabled Per ccyu's decision (option A), remove the consent asymmetry in ConsentResolver: telemetry is OFF only when cordis.yml has a telemetry entry with disabled: true. A cordis.yml with no telemetry entry now reports (allowWhenEntryAbsent defaults to true) rather than denying. No cordis.yml, an enabled entry, and DO_NOT_TRACK/CI are unchanged. Both no-config and absent-entry defaults stay configurable. Updates the module/README docs and the unit tests (file-present-but-no-entry and non-object/non-sequence roots now report). Per-file 100% coverage holds. --- packages/sdk/telemetry/README.md | 2 +- packages/sdk/telemetry/src/consent-resolver.ts | 16 ++++++++-------- .../sdk/telemetry/tests/consent-resolver.spec.ts | 16 ++++++++-------- 3 files changed, 17 insertions(+), 17 deletions(-) diff --git a/packages/sdk/telemetry/README.md b/packages/sdk/telemetry/README.md index 3a8b6ac4c2..43d13d3dcc 100644 --- a/packages/sdk/telemetry/README.md +++ b/packages/sdk/telemetry/README.md @@ -10,7 +10,7 @@ Launcher-side telemetry primitives for the dsh-sdk toolchain. This is a plain li | `getOrCreateAnonymousId` | Random UUID persisted in a per-user GLOBAL config file (never in the project, never derived from git). | | `TelemetryReporter` | Fire-and-forget send: `report()` never blocks or throws; delivery resolves on every path; `flush()` optionally drains in-flight sends within a cap. | -Consent is carried by the telemetry entry in `cordis.yml`, so disabling telemetry is disabling that entry. When `cordis.yml` does not yet exist (first `create`) consent defaults to allowed; when it exists without a telemetry entry consent defaults to denied — both are configurable on `ConsentResolver`. +Consent is carried by the telemetry entry in `cordis.yml`, so disabling telemetry is disabling that entry. Telemetry reports by default and is off only when a present telemetry entry is explicitly `disabled`: a missing `cordis.yml` (first `create`), an enabled entry, or a `cordis.yml` with no telemetry entry all report. `DO_NOT_TRACK`/CI always deny. The no-config and absent-entry defaults are configurable on `ConsentResolver`. The collection endpoint is a fixed constant (`DSH_TELEMETRY_ENDPOINT`); its `.invalid` placeholder must be replaced with the real endpoint before release. diff --git a/packages/sdk/telemetry/src/consent-resolver.ts b/packages/sdk/telemetry/src/consent-resolver.ts index 1d50904f39..a4327dc9f7 100644 --- a/packages/sdk/telemetry/src/consent-resolver.ts +++ b/packages/sdk/telemetry/src/consent-resolver.ts @@ -1,12 +1,12 @@ /** * Consent resolution for dsh-sdk telemetry. * - * Consent is carried by the telemetry plugin's enabled/disabled state in the - * project `cordis.yml`: an enabled entry means opt-in, a `disabled: true` entry - * means opt-out. The resolver PARSES `cordis.yml` — it never boots a Cordis - * application — because several launcher commands (`build`, `create`) never - * boot Cordis at all. `DO_NOT_TRACK` and CI environment signals force a denial - * regardless of file state. + * Telemetry is OFF only when `cordis.yml` contains a telemetry entry that is + * explicitly `disabled`; every other file state reports (no `cordis.yml`, an + * enabled entry, or no telemetry entry at all). The resolver PARSES `cordis.yml` + * — it never boots a Cordis application — because several launcher commands + * (`build`, `create`) never boot Cordis at all. `DO_NOT_TRACK` and CI + * environment signals force a denial regardless of file state. * * @module @deepseek-ai/dsh-telemetry/consent-resolver */ @@ -56,7 +56,7 @@ export interface ConsentResolverOptions { honorEnvOptOut?: boolean /** Consent when `cordis.yml` does not exist yet (first `create`). Defaults to `true` (telemetry is default-on). */ allowWhenNoConfig?: boolean - /** Consent when `cordis.yml` exists but has no telemetry entry. Defaults to `false`. */ + /** Consent when `cordis.yml` exists but has no telemetry entry. Defaults to `true` (report unless a present entry is disabled). */ allowWhenEntryAbsent?: boolean } @@ -94,7 +94,7 @@ export class ConsentResolver { this.#env = options.env ?? process.env this.#honorEnvOptOut = options.honorEnvOptOut ?? true this.#allowWhenNoConfig = options.allowWhenNoConfig ?? true - this.#allowWhenEntryAbsent = options.allowWhenEntryAbsent ?? false + this.#allowWhenEntryAbsent = options.allowWhenEntryAbsent ?? true } /** diff --git a/packages/sdk/telemetry/tests/consent-resolver.spec.ts b/packages/sdk/telemetry/tests/consent-resolver.spec.ts index e1f5f90f81..ca0cec3bbd 100644 --- a/packages/sdk/telemetry/tests/consent-resolver.spec.ts +++ b/packages/sdk/telemetry/tests/consent-resolver.spec.ts @@ -84,23 +84,23 @@ describe('ConsentResolver cordis.yml state', () => { .toEqual({ allowed: true, reason: 'enabled' }) }) - it('reports absent when cordis.yml has no telemetry entry, defaulting to deny', async () => { + it('reports (allows) when cordis.yml has no telemetry entry', async () => { const yml = '- id: llm\n name: \'@deepseek-ai/dsh-llm-deepseek\'\n' expect(await resolver.resolve(await projectDir(yml))) - .toEqual({ allowed: false, reason: 'absent' }) + .toEqual({ allowed: true, reason: 'absent' }) }) - it('can allow when the entry is absent', async () => { + it('can be told to deny when the entry is absent', async () => { const yml = '- id: llm\n name: \'@deepseek-ai/dsh-llm-deepseek\'\n' - const decision = await new ConsentResolver({ env: {}, allowWhenEntryAbsent: true }).resolve(await projectDir(yml)) - expect(decision).toEqual({ allowed: true, reason: 'absent' }) + const decision = await new ConsentResolver({ env: {}, allowWhenEntryAbsent: false }).resolve(await projectDir(yml)) + expect(decision).toEqual({ allowed: false, reason: 'absent' }) }) - it('skips non-object sequence items and a non-sequence root', async () => { + it('skips non-object sequence items and a non-sequence root, still reporting absent', async () => { expect(await resolver.resolve(await projectDir('- just-a-string\n- id: x\n name: y\n'))) - .toEqual({ allowed: false, reason: 'absent' }) + .toEqual({ allowed: true, reason: 'absent' }) expect(await resolver.resolve(await projectDir('root: not-a-sequence\n'))) - .toEqual({ allowed: false, reason: 'absent' }) + .toEqual({ allowed: true, reason: 'absent' }) }) it('honors a custom telemetry plugin name', async () => { From 472a683bdc76f33cee9d2dd492623f91bb0f4b48 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 15:21:37 +0800 Subject: [PATCH 178/323] feat(create-sdk): headless creation via --config/--config-json + NDJSON + skill Add a headless create path: --config / --config-json supply a structured project spec (answers + feature plan) that drives CreateWizard through a HeadlessPromptPort, bypassing the TTY. --json emits NDJSON lifecycle events (done / action-required / error) so an agent can fill a missing input and re-run. Ship a thin SKILL.md playbook for agent-driven creation. Per-file 100% coverage. --- packages/sdk/create-sdk/README.md | 6 +- packages/sdk/create-sdk/src/args.ts | 12 +++ packages/sdk/create-sdk/src/command.ts | 42 ++++++-- packages/sdk/create-sdk/src/headless.ts | 98 ++++++++++++++++++ packages/sdk/create-sdk/tests/create.spec.ts | 102 +++++++++++++++++++ skills/create-dsh-sdk-project/SKILL.md | 57 +++++++++++ 6 files changed, 307 insertions(+), 10 deletions(-) create mode 100644 packages/sdk/create-sdk/src/headless.ts create mode 100644 skills/create-dsh-sdk-project/SKILL.md diff --git a/packages/sdk/create-sdk/README.md b/packages/sdk/create-sdk/README.md index 66cddc030a..a5fa51b480 100644 --- a/packages/sdk/create-sdk/README.md +++ b/packages/sdk/create-sdk/README.md @@ -6,14 +6,14 @@ The supported package surface is the `create-sdk` bin. The package root exports The initializer rejects every existing target path, creates one `SdkProject` edit session, validates and commits it, then asks whether to install NPM dependencies and build. Install or build failures keep the generated project and print a retry command. -Public flags are `[directory]`, `--description`, `--provider`, `--base-url`, `--api-key`, `--model`, `--interface`, `--pm`, and `--install`/`--no-install`. Flags prefill matching questions, but creation always requires a TTY. +Public flags are `[directory]`, `--description`, `--provider`, `--base-url`, `--api-key`, `--model`, `--interface`, `--pm`, `--install`/`--no-install`, plus the headless flags `--config ` / `--config-json ` and `--json`. Interactive flags prefill matching questions; a headless spec (`--config`/`--config-json`) supplies every answer and its feature plan up front, so creation runs without a TTY and drives through a `HeadlessPromptPort` that fails loud on any missing required answer. `--json` emits NDJSON lifecycle events (`done` / `action-required` / `error`) so an agent can fill the named missing input and re-run. The provider choice is DeepSeek or a custom endpoint backed by `llm-pi-ai`. DeepSeek asks only for an API key and uses the public endpoint plus `deepseek-v4-flash`; custom also asks for a base URL. An empty key requires confirmation and creates a commented empty `.env` variable so provider startup fails clearly until it is filled. Existing plugin defaults are omitted; required SDK presets remain typed against the owning package's Config. ## Model Experience -Indirectly, through the generated project composition and its selected runtime plugins. +Indirectly, through the generated project composition and its selected runtime plugins; the headless `--config-json` + `--json` surface additionally lets an agent create a project end to end and react to `action-required` events. ## Known Limitations and Deferred Work -- **TTY-only creation** — flags prefill questions, but the wizard still requires an interactive terminal before it writes a project. +- **Headless local plugins** — the headless spec supplies project answers and the feature plan; scaffolding a local plugin (the interactive none/plugin/tool choice) is not yet expressible in the spec and defaults to none. diff --git a/packages/sdk/create-sdk/src/args.ts b/packages/sdk/create-sdk/src/args.ts index 521132caa9..897159bd7c 100644 --- a/packages/sdk/create-sdk/src/args.ts +++ b/packages/sdk/create-sdk/src/args.ts @@ -19,6 +19,9 @@ export interface CreateArgs { packageManager?: PackageManagerName install?: boolean linkWorkspace?: boolean + config?: string + configJson?: string + json?: boolean help: boolean } @@ -32,6 +35,9 @@ interface CommanderCreateOptions { pm?: PackageManagerName install?: boolean linkWorkspace?: boolean + config?: string + configJson?: string + json?: boolean help?: boolean } @@ -60,6 +66,9 @@ function createProgram(): Command { .addOption(new Option('--install').default(undefined)) .addOption(new Option('--no-install').default(undefined)) .option('--link-workspace') + .option('--config ') + .option('--config-json ') + .addOption(new Option('--json').default(undefined)) } /** Parse create-sdk positionals/options through Commander into a domain-neutral value. */ @@ -79,6 +88,9 @@ export function parseCreateArgs(argv: readonly string[]): CreateArgs { ...options.pm === undefined ? {} : { packageManager: options.pm }, ...options.install === undefined ? {} : { install: options.install }, ...options.linkWorkspace ? { linkWorkspace: true } : {}, + ...options.config === undefined ? {} : { config: options.config }, + ...options.configJson === undefined ? {} : { configJson: options.configJson }, + ...options.json === undefined ? {} : { json: options.json }, help: options.help ?? false, } } diff --git a/packages/sdk/create-sdk/src/command.ts b/packages/sdk/create-sdk/src/command.ts index 0c7076c90b..a7855ea027 100644 --- a/packages/sdk/create-sdk/src/command.ts +++ b/packages/sdk/create-sdk/src/command.ts @@ -7,12 +7,15 @@ import { readFile } from 'node:fs/promises' import { ClackPromptPort, + HeadlessPromptError, + HeadlessPromptPort, PromptCancelledError, type PackageManagerVersionProbe, type PromptPort, } from '@deepseek-ai/dsh-helper' -import { parseCreateArgs } from './args.ts' +import { parseCreateArgs, type CreateArgs } from './args.ts' import { CreateWizard, type ResolvedCreateRequest } from './create-wizard.ts' +import { resolveHeadless } from './headless.ts' import { scaffoldProject, type ScaffoldResult } from './project-scaffolder.ts' import { CREATE_TEMPLATES, packageManagerTemplateModel } from './templates/create-templates.ts' @@ -46,16 +49,18 @@ export async function createProject( context.stdout.write(CREATE_TEMPLATES.usage.render({})) return undefined } - if (!context.port && (!context.stdin.isTTY || !context.stdout.isTTY)) { - throw new Error('create-sdk requires an interactive TTY') + const headless = await resolveHeadless(args) + if (!headless && !context.port && (!context.stdin.isTTY || !context.stdout.isTTY)) { + throw new Error('create-sdk requires an interactive TTY, --config , or --config-json ') } const wizard = new CreateWizard({ - args, + args: headless ? headless.args : args, /* v8 ignore next -- production TTY wiring is exercised by the built-bin smoke */ - port: context.port ?? new ClackPromptPort(context.stdin, context.stdout), + port: context.port ?? (headless ? new HeadlessPromptPort() : new ClackPromptPort(context.stdin, context.stdout)), cwd: context.cwd, releaseVersion: context.releaseVersion ?? await readCreateSdkVersion(), ...context.versionProbe ? { versionProbe: context.versionProbe } : {}, + ...headless?.features ? { features: headless.features } : {}, }) const resolved = await wizard.run() const result = await scaffoldProject(resolved.directory, resolved.request) @@ -87,6 +92,17 @@ export async function createProject( return result } +/** Whether NDJSON lifecycle events were requested, tolerating unparseable argv. */ +function wantsJsonEvents(argv: readonly string[]): boolean { + let parsed: CreateArgs + try { + parsed = parseCreateArgs(argv) + } catch { + return false + } + return parsed.json === true +} + /** Run the create command with process defaults and convert cancellation to a clean exit. */ export async function runCreateCommand( argv: readonly string[] = process.argv.slice(2), @@ -97,15 +113,27 @@ export async function runCreateCommand( stderr: process.stderr, }, ): Promise { + const json = wantsJsonEvents(argv) + const emit = (event: Record): void => { + context.stdout.write(`${JSON.stringify(event)}\n`) + } try { await createProject(argv, context) + if (json) emit({ type: 'done' }) return 0 } catch (error) { if (error instanceof PromptCancelledError) { - context.stderr.write('create-sdk: cancelled\n') + if (json) emit({ type: 'error', reason: 'cancelled' }) + else context.stderr.write('create-sdk: cancelled\n') return 1 } - context.stderr.write(`create-sdk: ${error instanceof Error ? error.message : String(error)}\n`) + if (json && error instanceof HeadlessPromptError) { + emit({ type: 'action-required', prompt: error.prompt }) + return 1 + } + const message = error instanceof Error ? error.message : String(error) + if (json) emit({ type: 'error', message }) + else context.stderr.write(`create-sdk: ${message}\n`) return 1 } } diff --git a/packages/sdk/create-sdk/src/headless.ts b/packages/sdk/create-sdk/src/headless.ts new file mode 100644 index 0000000000..e32a053457 --- /dev/null +++ b/packages/sdk/create-sdk/src/headless.ts @@ -0,0 +1,98 @@ +/** + * Headless create input: a structured project spec supplied by an agent or CI + * instead of interactive prompts. + * + * @module @deepseek-ai/create-sdk/headless + */ + +import { readFile } from 'node:fs/promises' +import type { FeatureSelection, PackageManagerName, RunInterface } from '@deepseek-ai/dsh-helper' +import type { CreateArgs } from './args.ts' + +/** + * Structured, non-interactive create input. Scalar fields mirror {@link CreateArgs} + * project answers; `features` is the headless feature plan handed to `CreateWizard` + * (the interactive tree/suggests prompts are skipped). Absent required answers make + * the run fail loud through `HeadlessPromptPort` rather than blocking. + */ +export interface HeadlessCreateSpec { + directory?: string + description?: string + provider?: 'deepseek' | 'custom' + baseURL?: string + apiKey?: string + model?: string + interface?: RunInterface + pm?: PackageManagerName + install?: boolean + linkWorkspace?: boolean + features?: readonly FeatureSelection[] +} + +/** Resolved headless input: the args the wizard reads plus the feature plan. */ +export interface ResolvedHeadless { + args: CreateArgs + features: readonly FeatureSelection[] | undefined +} + +function asRecord(value: unknown, source: string): Record { + if (value === null || typeof value !== 'object' || Array.isArray(value)) { + throw new Error(`${source}: expected a JSON object`) + } + return value as Record +} + +/** Parse and shallow-validate a headless spec from JSON text. */ +export function parseHeadlessSpec(text: string, source: string): HeadlessCreateSpec { + let parsed: unknown + try { + parsed = JSON.parse(text) + } catch (error) { + /* v8 ignore next -- JSON.parse only throws Error instances; the String() branch is defensive */ + throw new Error(`${source}: invalid JSON (${error instanceof Error ? error.message : String(error)})`) + } + const record = asRecord(parsed, source) + if (record.features !== undefined && !Array.isArray(record.features)) { + throw new Error(`${source}: "features" must be an array`) + } + return record +} + +/** + * Load a headless spec from `--config-json` (inline) or `--config` (a JSON file), + * returning `undefined` when neither is supplied. + * @param args - parsed create args. + * @param readFileText - file reader seam for tests. + * @returns the resolved args + feature plan, or `undefined` for interactive runs. + */ +export async function resolveHeadless( + args: CreateArgs, + readFileText: (path: string) => Promise = path => readFile(path, 'utf8'), +): Promise { + let text: string + let source: string + if (args.configJson !== undefined) { + text = args.configJson + source = '--config-json' + } else if (args.config !== undefined) { + source = args.config + text = await readFileText(args.config) + } else { + return undefined + } + const spec = parseHeadlessSpec(text, source) + const resolvedArgs: CreateArgs = { + ...spec.directory === undefined ? {} : { directory: spec.directory }, + ...spec.description === undefined ? {} : { description: spec.description }, + ...spec.provider === undefined ? {} : { provider: spec.provider }, + ...spec.baseURL === undefined ? {} : { baseURL: spec.baseURL }, + ...spec.apiKey === undefined ? {} : { apiKey: spec.apiKey }, + ...spec.model === undefined ? {} : { model: spec.model }, + ...spec.interface === undefined ? {} : { runInterface: spec.interface }, + ...spec.pm === undefined ? {} : { packageManager: spec.pm }, + ...spec.install === undefined ? {} : { install: spec.install }, + ...spec.linkWorkspace ? { linkWorkspace: true } : {}, + help: false, + } + return { args: resolvedArgs, features: spec.features } +} diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index f4b66dc8ff..1f2cdb75fc 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -30,6 +30,7 @@ import { type CreateCommandContext, } from '../src/command.ts' import { CreateWizard } from '../src/create-wizard.ts' +import { resolveHeadless } from '../src/headless.ts' import { scaffoldProject } from '../src/project-scaffolder.ts' class ScriptedPort implements PromptPort { @@ -482,6 +483,52 @@ describe('create command composition', () => { await expect(createProject(argv('agent', false), context)).rejects.toThrow('interactive TTY') }) + it('creates headlessly from --config-json with no TTY', async () => { + const root = await mkdtemp(join(tmpdir(), 'create-headless-cmd-')) + temporary.push(root) + const spec = JSON.stringify({ + directory: 'agent', description: 'test', provider: 'deepseek', apiKey: 'key', + model: 'deepseek-v4-flash', interface: 'embed', pm: 'npm', install: false, + features: [{ id: 'persistence', options: ['jsonl'] }], + }) + const context = commandContext(root) + context.stdin.isTTY = false + context.stdout.isTTY = false + const result = await createProject(['--config-json', spec], context) + expect(result?.project.root).toBe(join(root, 'agent')) + }) + + it('emits NDJSON lifecycle events under --json', async () => { + const root = await mkdtemp(join(tmpdir(), 'create-headless-json-')) + temporary.push(root) + const base = { + description: 'test', model: 'deepseek-v4-flash', interface: 'embed', pm: 'npm', install: false, + } + const ok = commandContext(root) + ok.stdin.isTTY = false + ok.stdout.isTTY = false + const okSpec = JSON.stringify({ ...base, directory: 'done-agent', provider: 'deepseek', apiKey: 'key', features: [] }) + await expect(runCreateCommand(['--config-json', okSpec, '--json'], ok)).resolves.toBe(0) + expect(ok.readStdout()).toContain('{"type":"done"}') + + const missing = commandContext(root) + missing.stdin.isTTY = false + missing.stdout.isTTY = false + const missingSpec = JSON.stringify({ ...base, directory: 'miss-agent', provider: 'custom', baseURL: 'https://x', features: [] }) + await expect(runCreateCommand(['--config-json', missingSpec, '--json'], missing)).resolves.toBe(1) + expect(missing.readStdout()).toContain('"type":"action-required"') + + const broken = commandContext(root) + broken.stdin.isTTY = false + broken.stdout.isTTY = false + await expect(runCreateCommand(['--config-json', '{bad', '--json'], broken)).resolves.toBe(1) + expect(broken.readStdout()).toContain('"type":"error"') + + const cancelled = commandContext(root, new ScriptedPort([ScriptedPort.cancel])) + await expect(runCreateCommand(['--json', ...argv('cancel-agent', false)], cancelled)).resolves.toBe(1) + expect(cancelled.readStdout()).toContain('"reason":"cancelled"') + }) + it('creates through an injected prompt port and delegates optional setup', async () => { const root = await mkdtemp(join(tmpdir(), 'create-command-success-')) temporary.push(root) @@ -550,3 +597,58 @@ describe('create command composition', () => { await expect(runCreateCommand(['--help'], help)).resolves.toBe(0) }) }) + +describe('resolveHeadless', () => { + it('returns undefined without a config source', async () => { + expect(await resolveHeadless(parseCreateArgs(['agent']))).toBeUndefined() + }) + + it('maps every inline --config-json field into args plus the feature plan', async () => { + const spec = JSON.stringify({ + directory: 'a', description: 'd', provider: 'custom', baseURL: 'https://x', apiKey: 'k', + model: 'm', interface: 'acp', pm: 'pnpm', install: true, linkWorkspace: true, + features: [{ id: 'todo', options: ['default'] }], + }) + const resolved = await resolveHeadless(parseCreateArgs(['--config-json', spec])) + expect(resolved?.args).toMatchObject({ + directory: 'a', description: 'd', provider: 'custom', baseURL: 'https://x', apiKey: 'k', + model: 'm', runInterface: 'acp', packageManager: 'pnpm', install: true, linkWorkspace: true, help: false, + }) + expect(resolved?.features).toEqual([{ id: 'todo', options: ['default'] }]) + }) + + it('reads --config from a file via the injected reader and omits absent fields', async () => { + const resolved = await resolveHeadless( + parseCreateArgs(['--config', '/spec.json']), + async () => JSON.stringify({ description: 'from-file' }), + ) + expect(resolved?.args.description).toBe('from-file') + expect(resolved?.args.directory).toBeUndefined() + expect(resolved?.args.linkWorkspace).toBeUndefined() + expect(resolved?.features).toBeUndefined() + }) + + it('reads --config from disk with the default reader', async () => { + const dir = await mkdtemp(join(tmpdir(), 'create-headless-file-')) + temporary.push(dir) + const file = join(dir, 'spec.json') + await writeFile(file, JSON.stringify({ description: 'on-disk' })) + const resolved = await resolveHeadless(parseCreateArgs(['--config', file])) + expect(resolved?.args.description).toBe('on-disk') + }) + + it('fails loud on invalid JSON, a non-object root, or a non-array features field', async () => { + await expect(resolveHeadless(parseCreateArgs(['--config-json', '{bad']))).rejects.toThrow('invalid JSON') + await expect(resolveHeadless(parseCreateArgs(['--config-json', '[]']))).rejects.toThrow('expected a JSON object') + await expect(resolveHeadless(parseCreateArgs(['--config-json', 'null']))).rejects.toThrow('expected a JSON object') + await expect(resolveHeadless(parseCreateArgs(['--config-json', '5']))).rejects.toThrow('expected a JSON object') + await expect(resolveHeadless(parseCreateArgs(['--config-json', '{"features":1}']))).rejects.toThrow('must be an array') + }) + + it('accepts a minimal spec, leaving unspecified answers undefined', async () => { + const resolved = await resolveHeadless(parseCreateArgs(['--config-json', '{"directory":"x"}'])) + expect(resolved?.args.directory).toBe('x') + expect(resolved?.args.description).toBeUndefined() + expect(resolved?.features).toBeUndefined() + }) +}) diff --git a/skills/create-dsh-sdk-project/SKILL.md b/skills/create-dsh-sdk-project/SKILL.md new file mode 100644 index 0000000000..5b984f3b86 --- /dev/null +++ b/skills/create-dsh-sdk-project/SKILL.md @@ -0,0 +1,57 @@ +--- +name: create-dsh-sdk-project +description: Create a DeepSeek Harness SDK project non-interactively (headless), driven by an agent instead of the interactive wizard. Use when asked to scaffold a new DSH SDK project without a terminal. +--- + +# Create a DeepSeek Harness SDK project headlessly + +The `create-sdk` initializer normally runs an interactive wizard. To create a project +**without a terminal**, pass a structured spec and ask for machine-readable events: + +```sh +npm create @deepseek-ai/sdk -- --config-json '' --json +``` + +- `--config-json ''` supplies the whole spec inline (no prompts). Alternatively + `--config ` reads the same spec from a file. +- `--json` makes the command emit one NDJSON lifecycle event per line to stdout. + +## Spec shape + +All fields are optional except those a chosen feature requires. Unsupplied answers that +have a sensible default are taken from it; a *required* answer with no default (a secret, +a custom provider base URL, a required feature option) makes the run fail loud rather than +block. + +```json +{ + "directory": "my-agent", + "description": "A DeepSeek Harness agent", + "provider": "deepseek", + "apiKey": "", + "model": "deepseek-v4-flash", + "interface": "stdio", + "pm": "npm", + "install": false, + "features": [ + { "id": "persistence", "options": ["sqlite"] }, + { "id": "web", "options": ["exa"], "secrets": { "apiKey": "" } } + ] +} +``` + +`features` is the complete set of optional features to enable, each with its chosen +options and any secrets/values it needs. The interactive feature tree and its +recommended-feature prompts are skipped in headless mode. + +## Reacting to events + +Each line of stdout is one JSON object: + +- `{"type":"done"}` — the project was created (and installed, if `install` was true). +- `{"type":"action-required","prompt":""}` — a required answer was missing. + Add the corresponding field to the spec (e.g. an `apiKey`, a feature secret, a custom + `baseURL`) and re-run. +- `{"type":"error","message":""}` — the run failed for another reason. + +Iterate: read `action-required`, fill the named input into the spec, re-run until `done`. From 8052370155b4d45f1eba8764e89932962339e6a2 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 15:40:34 +0800 Subject: [PATCH 179/323] =?UTF-8?q?chore(sdk):=20drop=20dsh-plugin-fetch?= =?UTF-8?q?=20(giget/pacote)=20=E2=80=94=20#2=20will=20use=20native=20npm/?= =?UTF-8?q?pnpm=20deps?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit External-plugin creation will add a package-manager-native dependency (github:owner/repo#ref or pkg@version) plus a cordis mount instead of fetching tarballs into a temp dir, so the giget/pacote fetch package is no longer needed. --- docs/module-graph.md | 3 - packages/sdk/README.md | 1 - packages/sdk/plugin-fetch/README.md | 32 - packages/sdk/plugin-fetch/package.json | 37 - packages/sdk/plugin-fetch/src/fetcher.ts | 90 -- .../sdk/plugin-fetch/src/giget-fetcher.ts | 116 --- packages/sdk/plugin-fetch/src/ids.ts | 39 - packages/sdk/plugin-fetch/src/index.ts | 48 - packages/sdk/plugin-fetch/src/never.ts | 19 - .../sdk/plugin-fetch/src/pacote-fetcher.ts | 129 --- packages/sdk/plugin-fetch/src/source.ts | 126 --- .../sdk/plugin-fetch/tests/fetcher.spec.ts | 64 -- .../plugin-fetch/tests/giget-fetcher.spec.ts | 145 --- packages/sdk/plugin-fetch/tests/ids.spec.ts | 39 - packages/sdk/plugin-fetch/tests/never.spec.ts | 19 - .../plugin-fetch/tests/pacote-fetcher.spec.ts | 108 --- .../sdk/plugin-fetch/tests/source.spec.ts | 107 --- packages/sdk/plugin-fetch/tsconfig.json | 15 - pnpm-lock.yaml | 831 ------------------ .../verify-package-readme-model-experience.ts | 1 - tsconfig.build.json | 1 - tsconfig.json | 1 - 22 files changed, 1971 deletions(-) delete mode 100644 packages/sdk/plugin-fetch/README.md delete mode 100644 packages/sdk/plugin-fetch/package.json delete mode 100644 packages/sdk/plugin-fetch/src/fetcher.ts delete mode 100644 packages/sdk/plugin-fetch/src/giget-fetcher.ts delete mode 100644 packages/sdk/plugin-fetch/src/ids.ts delete mode 100644 packages/sdk/plugin-fetch/src/index.ts delete mode 100644 packages/sdk/plugin-fetch/src/never.ts delete mode 100644 packages/sdk/plugin-fetch/src/pacote-fetcher.ts delete mode 100644 packages/sdk/plugin-fetch/src/source.ts delete mode 100644 packages/sdk/plugin-fetch/tests/fetcher.spec.ts delete mode 100644 packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts delete mode 100644 packages/sdk/plugin-fetch/tests/ids.spec.ts delete mode 100644 packages/sdk/plugin-fetch/tests/never.spec.ts delete mode 100644 packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts delete mode 100644 packages/sdk/plugin-fetch/tests/source.spec.ts delete mode 100644 packages/sdk/plugin-fetch/tsconfig.json diff --git a/docs/module-graph.md b/docs/module-graph.md index 4cc2c36eeb..240772529b 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -138,7 +138,6 @@ flowchart TD end subgraph group_sdk["packages/sdk"] pkg_helper["helper"] - pkg_plugin_fetch["plugin-fetch"] pkg_scripts["scripts"] pkg_telemetry["telemetry"] end @@ -154,7 +153,6 @@ flowchart TD pkg_llm --> pkg_brand pkg_code_runtime_worker --> pkg_code_runtime pkg_helper --> pkg_brand - pkg_plugin_fetch --> pkg_brand pkg_scripts --> pkg_app_boot pkg_telemetry --> pkg_brand pkg_llm_deepseek --> pkg_llm @@ -446,7 +444,6 @@ flowchart TD | [`llm`](../packages/llm/llm) | `llm` | [`brand`](../packages/util/brand) | | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime) | | [`helper`](../packages/sdk/helper) | `sdk` | [`brand`](../packages/util/brand) | -| [`plugin-fetch`](../packages/sdk/plugin-fetch) | `sdk` | [`brand`](../packages/util/brand) | | [`scripts`](../packages/sdk/scripts) | `sdk` | [`app-boot`](../packages/ui/app-boot) | | [`telemetry`](../packages/sdk/telemetry) | `sdk` | [`brand`](../packages/util/brand) | | [`llm-deepseek`](../packages/llm/llm-deepseek) | `llm` | [`llm`](../packages/llm/llm) | diff --git a/packages/sdk/README.md b/packages/sdk/README.md index 92c8794e64..953d52ea76 100644 --- a/packages/sdk/README.md +++ b/packages/sdk/README.md @@ -9,7 +9,6 @@ The [feature RFC](../../docs/rfc/proposed/feature/2026-07-14-sdk-developer-proje | [`helper`](helper/README.md) | Project aggregate, edit session, builtin features, project documents, templates, package managers, and prompt abstraction | | [`scripts`](scripts/README.md) | The `dsh-sdk` launcher: `start`, `dev`, `build`, and interactive `config` | | [`create-sdk`](create-sdk/README.md) | The `npm create @deepseek-ai/sdk` initializer | -| [`plugin-fetch`](plugin-fetch/README.md) | Fetch an external plugin (github/npm) into a temp dir — pinned and un-executed — for `dsh-sdk create` | `@deepseek-ai/create-sdk` is the one package-name exception to the repository's `@deepseek-ai/dsh-*` rule: npm's scoped initializer convention requires that name for `npm create @deepseek-ai/sdk`. diff --git a/packages/sdk/plugin-fetch/README.md b/packages/sdk/plugin-fetch/README.md deleted file mode 100644 index 801dc2a2a6..0000000000 --- a/packages/sdk/plugin-fetch/README.md +++ /dev/null @@ -1,32 +0,0 @@ -# `@deepseek-ai/dsh-plugin-fetch` - -Fetch an external Cordis plugin into a temp directory — pinned to an immutable commit or integrity and never executed — for the forthcoming `dsh-sdk create ` command. - -The package parses a source spec into a `PluginSource`, dispatches to the matching `PluginFetcher`, and returns a common `FetchedPlugin` (temp dir + immutable provenance) that the wiring step pins into `package.json`, mounts in `cordis.yml`, and installs with `--ignore-scripts`. - -| Export | Role | -|---|---| -| `resolvePluginSource(spec)` → `PluginSource` | Parse `owner/repo[/subdir]#ref` (github) or `pkg@version` (npm); fail loud on an ambiguous or malformed spec | -| `PluginFetcher` | The fetch seam: resolve the pin BEFORE download, extract without executing pulled code | -| `GigetFetcher` / `createGigetFetcher()` | Github fetcher over `@bluwy/giget-core`: resolve `#ref` to a commit SHA, download that SHA | -| `PacoteFetcher` / `createPacoteFetcher()` | Npm fetcher over `pacote`: resolve the manifest, then extract the tarball verified against its integrity | -| `fetchPlugin(source, fetchers)` → `FetchedPlugin` | Dispatch one source to its fetcher by discriminant tag | - -## Safety model — confirm-before-run, not run-on-fetch - -A fetch only downloads and unpacks; it runs no install, no `postinstall`/`prepare`, and no degit-style template actions. - -- **github** uses `@bluwy/giget-core` (one runtime dependency, `modern-tar`; no CLI, install, or JSON-registry surface) so a fetch can only download and untar a tarball. The commit is pinned first: `GigetFetcher` resolves `#ref` — or the default branch when absent — to an immutable SHA via the GitHub commits API, then downloads that SHA. Provenance carries the SHA so wiring pins `github:owner/repo#`. -- **npm** uses `pacote`. Registry-only is enforced upstream: `resolvePluginSource` produces only a `name@version` registry spec, so pacote never sees a git/file/dir spec whose lifecycle scripts would run, and a registry tarball extract is a plain untar. The manifest is resolved first so extract verifies the artifact against the registry-published integrity (a mismatch raises `EINTEGRITY`). Provenance carries the exact version, resolved URL, and integrity. - -Both network boundaries (giget download, GitHub ref resolution, pacote, temp-dir allocation) are constructor-injected, so the fetch logic is unit-tested without network; the `create*Fetcher()` factories wire the real libraries. - -## Model Experience - -None, as this developer tooling acquires plugin sources for the SDK launcher and registers no live agent or model surface. - -## Known Limitations and Deferred Work - -- **Wiring is not here yet** — pinning `package.json`, mounting `cordis.yml` through `ProjectEditSession` with a confirmed diff, and `install --ignore-scripts` land with the `dsh-sdk create` command. This package stops at a fetched, pinned temp directory. -- **npm registry authentication** — `PacoteFetcher` targets a public or default-configured registry; private-registry auth beyond pacote's ambient npm config is deferred. -- **Template-repo initialization** — the whole-project init mode (`dsh-sdk create` from a template repository) is out of scope; this package fetches a single plugin into an existing project. diff --git a/packages/sdk/plugin-fetch/package.json b/packages/sdk/plugin-fetch/package.json deleted file mode 100644 index e8e38090e6..0000000000 --- a/packages/sdk/plugin-fetch/package.json +++ /dev/null @@ -1,37 +0,0 @@ -{ - "name": "@deepseek-ai/dsh-plugin-fetch", - "description": "Fetch an external Cordis plugin (github or npm) into a temp dir, pinned and un-executed, for dsh-sdk create", - "version": "0.0.1", - "private": true, - "type": "module", - "main": "lib/index.js", - "types": "lib/types/index.d.ts", - "exports": { - ".": { - "types": "./lib/types/index.d.ts", - "default": "./lib/index.js" - }, - "./src/*": "./src/*", - "./package.json": "./package.json" - }, - "files": [ - "lib/index.js", - "lib/types/**/*.d.ts", - "lib/types/**/*.d.ts.map", - "src" - ], - "license": "BSD-3-Clause", - "dependencies": { - "@bluwy/giget-core": "^0.1.7", - "pacote": "^22.0.0" - }, - "peerDependencies": { - "@deepseek-ai/dsh-brand": "^0.0.1", - "cordis": "^4.0.0-rc.7" - }, - "devDependencies": { - "@deepseek-ai/dsh-brand": "workspace:^", - "@types/pacote": "^11.1.8", - "cordis": "^4.0.0-rc.7" - } -} diff --git a/packages/sdk/plugin-fetch/src/fetcher.ts b/packages/sdk/plugin-fetch/src/fetcher.ts deleted file mode 100644 index 7c3d3a763c..0000000000 --- a/packages/sdk/plugin-fetch/src/fetcher.ts +++ /dev/null @@ -1,90 +0,0 @@ -/** - * The `PluginFetcher` seam, its common `FetchedPlugin` result, and the - * tag-dispatched entry point. A fetcher acquires one plugin source into a fresh - * temp directory WITHOUT executing any pulled code, and reports immutable - * provenance the wiring step pins the dependency to. - * - * @module @deepseek-ai/dsh-plugin-fetch/fetcher - */ - -import { mkdtemp } from 'node:fs/promises' -import { tmpdir } from 'node:os' -import { join } from 'node:path' -import { assertNever } from './never.ts' -import type { CommitSha, Integrity } from './ids.ts' -import type { GithubSource, NpmSource, PluginSource } from './source.ts' - -/** Immutable pin for a github fetch: the resolved commit the tarball came from. */ -export interface GithubProvenance { - readonly kind: 'github' - readonly sha: CommitSha -} - -/** Immutable pin for an npm fetch: exact version, tarball URL, and integrity. */ -export interface NpmProvenance { - readonly kind: 'npm' - /** Concrete resolved version (e.g. `1.2.3`), never the requested range/tag. */ - readonly version: string - /** Tarball URL the artifact resolved to. */ - readonly resolved: string - /** Subresource integrity the artifact was verified against. */ - readonly integrity: Integrity -} - -/** Provenance a fetch records so wiring can pin an immutable dependency. */ -export type PluginProvenance = GithubProvenance | NpmProvenance - -/** The common result of fetching any plugin source. */ -export interface FetchedPlugin { - /** Absolute temp directory holding the extracted, UN-executed source. */ - readonly dir: string - /** The source that produced this fetch, echoed for the wiring step. */ - readonly source: PluginSource - /** Immutable provenance to pin the dependency during wiring. */ - readonly provenance: PluginProvenance -} - -/** - * A fetcher for one source kind. Implementations resolve the immutable pin - * BEFORE download and must never run lifecycle scripts or template actions. - */ -export interface PluginFetcher { - /** The single source kind this fetcher handles. */ - readonly kind: S['kind'] - /** - * Fetch one source into a fresh temp directory. - * @param source - the resolved source to fetch. - * @returns the temp dir plus immutable provenance. - */ - fetch(source: S): Promise -} - -/** The per-kind fetchers {@link fetchPlugin} dispatches across. */ -export interface PluginFetchers { - readonly github: PluginFetcher - readonly npm: PluginFetcher -} - -/** - * Dispatch one source to its fetcher by discriminant tag. - * @param source - the resolved plugin source. - * @param fetchers - the per-kind fetchers to route across. - * @returns the fetch result from the matching fetcher. - */ -export function fetchPlugin(source: PluginSource, fetchers: PluginFetchers): Promise { - switch (source.kind) { - case 'github': return fetchers.github.fetch(source) - case 'npm': return fetchers.npm.fetch(source) - default: return assertNever(source, 'fetchPlugin') - } -} - -/** - * Create a fresh, empty temp directory for one fetch — the default temp-dir - * seam shared by the concrete fetchers. - * @param prefix - a `mkdtemp` name prefix identifying the fetch kind. - * @returns the absolute path of the created directory. - */ -export function createTempDir(prefix: string): Promise { - return mkdtemp(join(tmpdir(), prefix)) -} diff --git a/packages/sdk/plugin-fetch/src/giget-fetcher.ts b/packages/sdk/plugin-fetch/src/giget-fetcher.ts deleted file mode 100644 index 55e001063c..0000000000 --- a/packages/sdk/plugin-fetch/src/giget-fetcher.ts +++ /dev/null @@ -1,116 +0,0 @@ -/** - * The github {@link PluginFetcher}, backed by `@bluwy/giget-core`. - * - * `@bluwy/giget-core` is chosen over unjs `giget`: it carries a single runtime - * dependency (`modern-tar`) versus giget's CLI/registry stack, and it dropped - * the `install` and JSON-registry options entirely, so a fetch can only ever - * download and untar a tarball — never run install or degit-style actions. That - * is exactly the "extract, never execute" guarantee this feature needs. - * - * The commit is pinned BEFORE download: {@link GigetFetcher} resolves `#ref` to - * an immutable SHA (default via the GitHub commits API), then downloads that - * SHA. Provenance carries the SHA so wiring pins `github:owner/repo#`. - * - * @module @deepseek-ai/dsh-plugin-fetch/giget-fetcher - */ - -import { downloadTemplate } from '@bluwy/giget-core' -import { createTempDir, type FetchedPlugin, type PluginFetcher } from './fetcher.ts' -import { commitSha, type CommitSha } from './ids.ts' -import type { GithubSource } from './source.ts' - -/** Temp-dir name prefix for github fetches. */ -export const GITHUB_TEMP_PREFIX = 'dsh-plugin-github-' - -/** Downloads a giget input string into `dir`; the tarball-extraction seam. */ -export type DownloadTemplate = ( - input: string, - options: { dir: string; force: 'clean' }, -) => Promise<{ dir: string }> - -/** Resolves a github source's ref to an immutable commit SHA before download. */ -export type ResolveRef = (source: GithubSource) => Promise - -/** The injected collaborators a {@link GigetFetcher} needs. */ -export interface GigetFetcherDeps { - /** Downloads a pinned giget input into a directory. */ - download: DownloadTemplate - /** Resolves `source.ref` (or the default branch) to a commit SHA. */ - resolveRef: ResolveRef - /** Allocates the fresh temp directory to download into. */ - createTempDir: (prefix: string) => Promise -} - -/** Build the giget input string that pins a github source to a commit SHA. */ -function gigetInput(source: GithubSource, sha: CommitSha): string { - const path = source.subdir ? `${source.owner}/${source.repo}/${source.subdir}` : `${source.owner}/${source.repo}` - return `${path}#${sha}` -} - -/** A human-readable label for one github source, for error messages. */ -function githubLabel(source: GithubSource): string { - return `${source.owner}/${source.repo}#${source.ref ?? 'HEAD'}` -} - -/** - * Resolve a github source's ref to an immutable SHA via the GitHub commits API. - * Uses the `application/vnd.github.sha` media type, which returns the resolved - * commit id as plain text. - * @param source - the github source; an absent `ref` resolves the default branch (`HEAD`). - * @param token - optional bearer token for private repositories. - * @returns the resolved immutable commit SHA. - * @throws if the GitHub API rejects the request. - */ -export async function defaultResolveRef(source: GithubSource, token?: string): Promise { - const ref = source.ref ?? 'HEAD' - const url = `https://api.github.com/repos/${source.owner}/${source.repo}/commits/${ref}` - const headers: Record = { Accept: 'application/vnd.github.sha' } - if (token !== undefined) headers.Authorization = `Bearer ${token}` - const response = await fetch(url, { headers }) - if (!response.ok) { - throw new Error(`cannot resolve github ref ${githubLabel(source)}: HTTP ${response.status}`) - } - return commitSha((await response.text()).trim()) -} - -/** Fetches a github plugin source by pinning `#ref` to a commit SHA, then downloading it. */ -export class GigetFetcher implements PluginFetcher { - readonly kind = 'github' as const - private readonly deps: GigetFetcherDeps - - /** Construct with injected download, ref-resolution, and temp-dir seams. */ - constructor(deps: GigetFetcherDeps) { - this.deps = deps - } - - async fetch(source: GithubSource): Promise { - const sha = await this.deps.resolveRef(source) - const dir = await this.deps.createTempDir(GITHUB_TEMP_PREFIX) - await this.deps.download(gigetInput(source, sha), { dir, force: 'clean' }) - return { dir, source, provenance: { kind: 'github', sha } } - } -} - -/** Options for the production github fetcher. */ -export interface GithubFetchOptions { - /** Bearer token for private repositories; defaults to `GITHUB_TOKEN`. */ - token?: string -} - -/** - * Build the production github fetcher wired to `@bluwy/giget-core` and the - * GitHub commits API. - * @param options - optional token override (else `process.env.GITHUB_TOKEN`). - * @returns a {@link GigetFetcher} using the real download and ref-resolution seams. - */ -export function createGigetFetcher(options: GithubFetchOptions = {}): GigetFetcher { - const token = options.token ?? process.env.GITHUB_TOKEN - return new GigetFetcher({ - download: (input, downloadOptions) => downloadTemplate(input, { - ...downloadOptions, - ...token !== undefined ? { providerOptions: { auth: token } } : {}, - }), - resolveRef: source => defaultResolveRef(source, token), - createTempDir, - }) -} diff --git a/packages/sdk/plugin-fetch/src/ids.ts b/packages/sdk/plugin-fetch/src/ids.ts deleted file mode 100644 index a3a2ffa575..0000000000 --- a/packages/sdk/plugin-fetch/src/ids.ts +++ /dev/null @@ -1,39 +0,0 @@ -/** - * Branded provenance identities owned by the plugin-fetch layer. Both cross the - * fetch → wiring boundary and are opaque tokens that must not be confused with - * ordinary strings (a package name, a URL) at that seam. - * - * @module @deepseek-ai/dsh-plugin-fetch/ids - */ - -import type { Branded } from '@deepseek-ai/dsh-brand' - -/** An immutable git commit object id a github fetch pins to. */ -export type CommitSha = Branded<'CommitSha'> - -/** - * Construct a {@link CommitSha}, validating the hexadecimal object-id shape. - * @param value - lowercase hex of an abbreviated or full commit id (7–64 chars, covering SHA-1 and SHA-256). - * @returns the branded commit id. - */ -export function commitSha(value: string): CommitSha { - if (!/^[0-9a-f]{7,64}$/.test(value)) { - throw new Error(`invalid commit sha: ${JSON.stringify(value)}`) - } - return value as CommitSha -} - -/** A Subresource Integrity string an npm fetch pins to. */ -export type Integrity = Branded<'Integrity'> - -/** - * Construct an {@link Integrity}, validating the SRI `-` shape. - * @param value - a single SRI entry using sha256, sha384, or sha512. - * @returns the branded integrity string. - */ -export function integrity(value: string): Integrity { - if (!/^sha(256|384|512)-[A-Za-z0-9+/]+={0,2}$/.test(value)) { - throw new Error(`invalid subresource integrity: ${JSON.stringify(value)}`) - } - return value as Integrity -} diff --git a/packages/sdk/plugin-fetch/src/index.ts b/packages/sdk/plugin-fetch/src/index.ts deleted file mode 100644 index d4b9682ff5..0000000000 --- a/packages/sdk/plugin-fetch/src/index.ts +++ /dev/null @@ -1,48 +0,0 @@ -/** - * Fetch an external Cordis plugin (github or npm) into a temp directory — - * pinned to an immutable commit/integrity and never executed — for the - * `dsh-sdk create ` command. Parses a source spec, dispatches to the - * matching fetcher, and returns a common {@link FetchedPlugin} the wiring step - * pins and mounts. - * - * @module @deepseek-ai/dsh-plugin-fetch - */ - -export { resolvePluginSource } from './source.ts' -export type { GithubSource, NpmSource, PluginSource } from './source.ts' -export { commitSha, integrity } from './ids.ts' -export type { CommitSha, Integrity } from './ids.ts' -export { createTempDir, fetchPlugin } from './fetcher.ts' -export type { - FetchedPlugin, - GithubProvenance, - NpmProvenance, - PluginFetcher, - PluginFetchers, - PluginProvenance, -} from './fetcher.ts' -export { - createGigetFetcher, - defaultResolveRef, - GigetFetcher, - GITHUB_TEMP_PREFIX, -} from './giget-fetcher.ts' -export type { - DownloadTemplate, - GigetFetcherDeps, - GithubFetchOptions, - ResolveRef, -} from './giget-fetcher.ts' -export { - createPacoteFetcher, - NPM_TEMP_PREFIX, - PacoteFetcher, -} from './pacote-fetcher.ts' -export type { - NpmFetchOptions, - PacoteApi, - PacoteExtractResult, - PacoteFetcherDeps, - PacoteFetchOptions, - PacoteResolution, -} from './pacote-fetcher.ts' diff --git a/packages/sdk/plugin-fetch/src/never.ts b/packages/sdk/plugin-fetch/src/never.ts deleted file mode 100644 index 664ab3293d..0000000000 --- a/packages/sdk/plugin-fetch/src/never.ts +++ /dev/null @@ -1,19 +0,0 @@ -/** - * Exhaustiveness helper for this package's closed unions. Kept local so the - * SDK plugin-fetch tooling stays free of the model-runtime `dsh-llm` dependency - * that owns the shared `assertNever`. - * - * @module @deepseek-ai/dsh-plugin-fetch/never - */ - -/** - * Mark an unreachable closed-union branch. A newly unhandled variant fails - * compilation at the call site; a value that escaped its type throws at runtime. - * @param value - the impossible value; typed `never` so a new variant fails to compile at every call site. - * @param context - optional label prefixed into the throw message. - * @returns never — it always throws, rendering the offending value. - */ -export function assertNever(value: never, context?: string): never { - const rendered = (JSON.stringify(value) as string | undefined) ?? String(value) - throw new Error(`unreachable variant${context ? ` in ${context}` : ''}: ${rendered}`) -} diff --git a/packages/sdk/plugin-fetch/src/pacote-fetcher.ts b/packages/sdk/plugin-fetch/src/pacote-fetcher.ts deleted file mode 100644 index dfb1d790b8..0000000000 --- a/packages/sdk/plugin-fetch/src/pacote-fetcher.ts +++ /dev/null @@ -1,129 +0,0 @@ -/** - * The npm {@link PluginFetcher}, backed by `pacote`. - * - * Supply-chain safety comes from three layers: (1) {@link resolvePluginSource} - * only ever produces a registry `name@version` spec, so pacote classifies it as - * a registry source and cannot be steered to a git/file/dir spec whose - * lifecycle scripts would run; (2) a registry tarball extract is a plain untar — - * pacote runs no `prepare`/`postinstall` during {@link PacoteFetcher.fetch}; and - * (3) the later wiring step installs with `--ignore-scripts`. The manifest is - * resolved first so extract verifies the tarball against the registry-published - * integrity (a mismatch raises `EINTEGRITY`). - * - * @module @deepseek-ai/dsh-plugin-fetch/pacote-fetcher - */ - -import { extract as pacoteExtract, manifest as pacoteManifest } from 'pacote' -import { createTempDir, type FetchedPlugin, type PluginFetcher } from './fetcher.ts' -import { integrity } from './ids.ts' -import type { NpmSource } from './source.ts' - -/** Temp-dir name prefix for npm fetches. */ -export const NPM_TEMP_PREFIX = 'dsh-plugin-npm-' - -/** The subset of pacote options this fetcher passes through. */ -export interface PacoteFetchOptions { - /** Registry to resolve against; absent uses pacote's default. */ - registry?: string - /** Known resolved tarball URL, forwarded to extract. */ - resolved?: string - /** Expected integrity, forwarded to extract for `EINTEGRITY` verification. */ - integrity?: string -} - -/** The resolved registry manifest fields this fetcher pins from. */ -export interface PacoteResolution { - /** Resolved tarball URL. */ - _resolved: string - /** Registry-published integrity. */ - _integrity: string - /** Concrete resolved version. */ - version: string -} - -/** The extract result fields this fetcher pins from. */ -export interface PacoteExtractResult { - /** Resolved tarball URL of the extracted artifact. */ - resolved: string - /** Integrity of the extracted artifact. */ - integrity: string -} - -/** The pacote surface a {@link PacoteFetcher} depends on; the fetch seam. */ -export interface PacoteApi { - /** Resolve a registry spec to its pinned manifest fields. */ - manifest: (spec: string, options?: PacoteFetchOptions) => Promise - /** Untar a registry spec into `dest`, verifying integrity when supplied. */ - extract: (spec: string, dest: string, options?: PacoteFetchOptions) => Promise -} - -/** The injected collaborators a {@link PacoteFetcher} needs. */ -export interface PacoteFetcherDeps { - /** The pacote resolve/extract surface. */ - pacote: PacoteApi - /** Allocates the fresh temp directory to extract into. */ - createTempDir: (prefix: string) => Promise - /** Registry to resolve against; absent uses pacote's default. */ - registry?: string -} - -/** Fetches an npm plugin source by resolving its manifest, then extracting the verified tarball. */ -export class PacoteFetcher implements PluginFetcher { - readonly kind = 'npm' as const - private readonly deps: PacoteFetcherDeps - - /** Construct with injected pacote, temp-dir, and optional registry seams. */ - constructor(deps: PacoteFetcherDeps) { - this.deps = deps - } - - async fetch(source: NpmSource): Promise { - const spec = `${source.name}@${source.version}` - const registryOptions: PacoteFetchOptions = this.deps.registry !== undefined - ? { registry: this.deps.registry } - : {} - const resolution = await this.deps.pacote.manifest(spec, registryOptions) - const dir = await this.deps.createTempDir(NPM_TEMP_PREFIX) - const extracted = await this.deps.pacote.extract(spec, dir, { - ...registryOptions, - resolved: resolution._resolved, - integrity: resolution._integrity, - }) - return { - dir, - source, - provenance: { - kind: 'npm', - version: resolution.version, - resolved: extracted.resolved, - integrity: integrity(extracted.integrity), - }, - } - } -} - -/** Options for the production npm fetcher. */ -export interface NpmFetchOptions { - /** Registry to resolve against; absent uses pacote's default. */ - registry?: string -} - -/** - * Build the production npm fetcher wired to `pacote`. - * @param options - optional registry override. - * @returns a {@link PacoteFetcher} using the real pacote resolve/extract seam. - */ -export function createPacoteFetcher(options: NpmFetchOptions = {}): PacoteFetcher { - const pacote: PacoteApi = { - manifest: async (spec, pacoteOptions) => { - const resolved = await pacoteManifest(spec, pacoteOptions) - return { _resolved: resolved._resolved, _integrity: resolved._integrity, version: resolved.version } - }, - extract: (spec, dest, pacoteOptions) => pacoteExtract(spec, dest, pacoteOptions), - } - return new PacoteFetcher({ - pacote, - createTempDir, - ...options.registry !== undefined ? { registry: options.registry } : {}, - }) -} diff --git a/packages/sdk/plugin-fetch/src/source.ts b/packages/sdk/plugin-fetch/src/source.ts deleted file mode 100644 index 7d7e3ffcc4..0000000000 --- a/packages/sdk/plugin-fetch/src/source.ts +++ /dev/null @@ -1,126 +0,0 @@ -/** - * The `PluginSource` discriminated union and the resolver that parses one CLI - * spec string into it. Ambiguous or malformed specs fail loud here — the single - * earliest resolvable point — rather than surfacing as a confusing fetch error. - * - * Grammar: - * - github: `owner/repo[/subdir]#ref` — a `#` unambiguously marks a github ref; - * `ref` is optional and, when omitted, the fetcher pins the default branch. - * - npm: `pkg@version` (scoped `@scope/pkg@version`) — the `@version` is the - * only disambiguator from a bare `owner/repo` github locator. - * - * @module @deepseek-ai/dsh-plugin-fetch/source - */ - -/** A plugin pulled from a github (git tarball) repository. */ -export interface GithubSource { - readonly kind: 'github' - /** Repository owner (user or org). */ - readonly owner: string - /** Repository name. */ - readonly repo: string - /** Path within the repository to extract; absent means the repository root. */ - readonly subdir?: string - /** Branch, tag, or commit; absent means the repository's default branch. */ - readonly ref?: string -} - -/** A plugin pulled from an npm registry by exact package and version spec. */ -export interface NpmSource { - readonly kind: 'npm' - /** Package name, including any `@scope/` prefix. */ - readonly name: string - /** Registry version, range, or dist-tag (non-empty). */ - readonly version: string -} - -/** Every plugin origin `dsh-sdk create ` understands. */ -export type PluginSource = GithubSource | NpmSource - -/** One `/`-separated github name segment (owner, repo, or subdir component). */ -function isNameSegment(segment: string): boolean { - return /^[A-Za-z0-9._-]+$/.test(segment) && segment !== '.' && segment !== '..' -} - -/** A git ref: branch, tag, or commit; permits `/`-nested names, rejects traversal. */ -function isGitRef(ref: string): boolean { - return /^[A-Za-z0-9._/-]+$/.test(ref) - && !ref.includes('..') - && !ref.startsWith('/') - && !ref.endsWith('/') -} - -/** An npm package name, scoped (`@scope/name`) or unscoped. */ -function isNpmPackageName(name: string): boolean { - const segment = /^[a-z0-9][a-z0-9._-]*$/ - if (name.startsWith('@')) { - const slash = name.indexOf('/') - if (slash < 2 || slash === name.length - 1) return false - return segment.test(name.slice(1, slash)) && segment.test(name.slice(slash + 1)) - } - return segment.test(name) -} - -/** Parse a `owner/repo[/subdir]` locator with an optional already-split ref. */ -function tryParseGithubLocator(locator: string, ref: string | undefined): GithubSource | undefined { - if (!/^[^\s@#]+$/.test(locator)) return undefined - const [owner, repo, ...subdirSegments] = locator.split('/') - if (owner === undefined || repo === undefined) return undefined - if (!isNameSegment(owner) || !isNameSegment(repo)) return undefined - if (subdirSegments.some(segment => !isNameSegment(segment))) return undefined - if (ref !== undefined && !isGitRef(ref)) return undefined - const subdir = subdirSegments.join('/') - return { - kind: 'github', - owner, - repo, - ...subdir.length > 0 ? { subdir } : {}, - ...ref !== undefined ? { ref } : {}, - } -} - -/** Parse `pkg@version` (scoped or unscoped); undefined when it is not npm-shaped. */ -function tryParseNpmSource(spec: string): NpmSource | undefined { - if (/[\s#]/.test(spec)) return undefined - // A scoped spec's version `@` follows the scope's `/`; an unscoped spec's is - // the first `@`. A leading `@` with no version `@` yields index 0 (rejected). - const versionAt = spec.startsWith('@') ? spec.indexOf('@', spec.indexOf('/') + 1) : spec.indexOf('@') - if (versionAt <= 0) return undefined - const name = spec.slice(0, versionAt) - const version = spec.slice(versionAt + 1) - if (version.length === 0 || version.includes('/')) return undefined - if (!isNpmPackageName(name)) return undefined - return { kind: 'npm', name, version } -} - -/** - * Parse one `dsh-sdk create ` spec into a {@link PluginSource}. - * @param spec - the raw source argument. - * @returns the discriminated source. - * @throws if the spec is empty, malformed, or ambiguous between github and npm. - */ -export function resolvePluginSource(spec: string): PluginSource { - const trimmed = spec.trim() - if (trimmed.length === 0) throw new Error('plugin source must not be empty') - - const hashIndex = trimmed.indexOf('#') - if (hashIndex !== -1) { - const ref = trimmed.slice(hashIndex + 1) - if (ref.length === 0) { - throw new Error(`github plugin source is missing a ref after '#': ${JSON.stringify(spec)}`) - } - const source = tryParseGithubLocator(trimmed.slice(0, hashIndex), ref) - if (!source) { - throw new Error(`invalid github plugin source: ${JSON.stringify(spec)} — expected "owner/repo[/subdir]#ref"`) - } - return source - } - - const npm = tryParseNpmSource(trimmed) - if (npm) return npm - const github = tryParseGithubLocator(trimmed, undefined) - if (github) return github - throw new Error( - `unrecognized plugin source: ${JSON.stringify(spec)} — expected "owner/repo[/subdir]#ref" (github) or "pkg@version" (npm)`, - ) -} diff --git a/packages/sdk/plugin-fetch/tests/fetcher.spec.ts b/packages/sdk/plugin-fetch/tests/fetcher.spec.ts deleted file mode 100644 index b68a3d3ae1..0000000000 --- a/packages/sdk/plugin-fetch/tests/fetcher.spec.ts +++ /dev/null @@ -1,64 +0,0 @@ -import { rm, stat } from 'node:fs/promises' -import { tmpdir } from 'node:os' -import { describe, expect, it, vi } from 'vitest' -import { - createTempDir, - fetchPlugin, - type FetchedPlugin, - type PluginFetchers, -} from '../src/fetcher.ts' -import { commitSha } from '../src/ids.ts' -import type { GithubSource, NpmSource, PluginSource } from '../src/source.ts' - -function stubFetchers(): { fetchers: PluginFetchers; github: ReturnType; npm: ReturnType } { - const result = (dir: string): FetchedPlugin => ({ - dir, - source: { kind: 'github', owner: 'o', repo: 'r' }, - provenance: { kind: 'github', sha: commitSha('a'.repeat(40)) }, - }) - const github = vi.fn(async (source: GithubSource) => result(`github:${source.repo}`)) - const npm = vi.fn(async (source: NpmSource) => result(`npm:${source.name}`)) - return { - fetchers: { github: { kind: 'github', fetch: github }, npm: { kind: 'npm', fetch: npm } }, - github, - npm, - } -} - -describe('fetchPlugin', () => { - it('routes a github source to the github fetcher', async () => { - const { fetchers, github, npm } = stubFetchers() - const source: GithubSource = { kind: 'github', owner: 'o', repo: 'r' } - const result = await fetchPlugin(source, fetchers) - expect(github).toHaveBeenCalledWith(source) - expect(npm).not.toHaveBeenCalled() - expect(result.dir).toBe('github:r') - }) - - it('routes an npm source to the npm fetcher', async () => { - const { fetchers, github, npm } = stubFetchers() - const source: NpmSource = { kind: 'npm', name: 'plugin', version: '1.0.0' } - const result = await fetchPlugin(source, fetchers) - expect(npm).toHaveBeenCalledWith(source) - expect(github).not.toHaveBeenCalled() - expect(result.dir).toBe('npm:plugin') - }) - - it('throws on an unknown source kind', () => { - const { fetchers } = stubFetchers() - const bogus = { kind: 'svn' } as unknown as PluginSource - expect(() => fetchPlugin(bogus, fetchers)).toThrow(/unreachable variant in fetchPlugin/) - }) -}) - -describe('createTempDir', () => { - it('creates a fresh empty directory under the OS temp root', async () => { - const dir = await createTempDir('dsh-plugin-fetch-test-') - try { - expect(dir.startsWith(tmpdir())).toBe(true) - expect((await stat(dir)).isDirectory()).toBe(true) - } finally { - await rm(dir, { recursive: true, force: true }) - } - }) -}) diff --git a/packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts b/packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts deleted file mode 100644 index c0cafb31d5..0000000000 --- a/packages/sdk/plugin-fetch/tests/giget-fetcher.spec.ts +++ /dev/null @@ -1,145 +0,0 @@ -import { afterEach, beforeEach, describe, expect, it, type Mock, vi } from 'vitest' -import { downloadTemplate } from '@bluwy/giget-core' -import { - createGigetFetcher, - defaultResolveRef, - GigetFetcher, - GITHUB_TEMP_PREFIX, - type GigetFetcherDeps, -} from '../src/giget-fetcher.ts' -import type { CommitSha } from '../src/ids.ts' -import type { GithubSource } from '../src/source.ts' - -vi.mock('@bluwy/giget-core', () => ({ downloadTemplate: vi.fn(async (_input: string, options: { dir: string }) => ({ dir: options.dir, source: '', info: { name: '', tar: '' } })) })) - -const SHA = 'a'.repeat(40) - -/** A `fetch` mock typed with the call signature the assertions destructure. */ -function fetchReturning(response: Response): Mock<(url: string, init?: RequestInit) => Promise> { - return vi.fn((_url: string, _init?: RequestInit) => Promise.resolve(response)) -} - -function fakeDeps(overrides: Partial = {}): { - deps: GigetFetcherDeps - download: ReturnType - resolveRef: ReturnType - createTempDir: ReturnType -} { - const download = vi.fn(async () => ({ dir: '/tmp/x' })) - const resolveRef = vi.fn(async () => SHA as CommitSha) - const createTempDir = vi.fn(async () => '/tmp/dsh-plugin-github-abc') - return { deps: { download, resolveRef, createTempDir, ...overrides }, download, resolveRef, createTempDir } -} - -describe('GigetFetcher.fetch', () => { - it('pins the ref to a SHA, downloads that SHA, and reports provenance', async () => { - const { deps, download, resolveRef, createTempDir } = fakeDeps() - const source: GithubSource = { kind: 'github', owner: 'unjs', repo: 'template', ref: 'main' } - const result = await new GigetFetcher(deps).fetch(source) - - expect(resolveRef).toHaveBeenCalledWith(source) - expect(createTempDir).toHaveBeenCalledWith(GITHUB_TEMP_PREFIX) - expect(download).toHaveBeenCalledWith(`unjs/template#${SHA}`, { dir: '/tmp/dsh-plugin-github-abc', force: 'clean' }) - expect(result).toEqual({ - dir: '/tmp/dsh-plugin-github-abc', - source, - provenance: { kind: 'github', sha: SHA }, - }) - }) - - it('includes the subdir in the download input', async () => { - const { deps, download } = fakeDeps() - const source: GithubSource = { kind: 'github', owner: 'o', repo: 'r', subdir: 'packages/plugin' } - await new GigetFetcher(deps).fetch(source) - expect(download).toHaveBeenCalledWith(`o/r/packages/plugin#${SHA}`, expect.anything()) - }) - - it('exposes its source kind', () => { - expect(new GigetFetcher(fakeDeps().deps).kind).toBe('github') - }) -}) - -describe('defaultResolveRef', () => { - afterEach(() => vi.unstubAllGlobals()) - - it('resolves the default branch (HEAD) with no auth header', async () => { - const fetchMock = fetchReturning(new Response(`${SHA}\n`, { status: 200 })) - vi.stubGlobal('fetch', fetchMock) - const sha = await defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r' }) - expect(sha).toBe(SHA) - const [url, init] = fetchMock.mock.calls[0]! - expect(url).toBe('https://api.github.com/repos/o/r/commits/HEAD') - expect((init as RequestInit).headers).toEqual({ Accept: 'application/vnd.github.sha' }) - }) - - it('resolves an explicit ref and sends a bearer token', async () => { - const fetchMock = fetchReturning(new Response(SHA, { status: 200 })) - vi.stubGlobal('fetch', fetchMock) - const sha = await defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r', ref: 'v1.2.3' }, 'secret') - expect(sha).toBe(SHA) - const [url, init] = fetchMock.mock.calls[0]! - expect(url).toBe('https://api.github.com/repos/o/r/commits/v1.2.3') - expect((init as RequestInit).headers).toEqual({ - Accept: 'application/vnd.github.sha', - Authorization: 'Bearer secret', - }) - }) - - it('throws with the HEAD label when the API rejects an unref-ed source', async () => { - vi.stubGlobal('fetch', fetchReturning(new Response('', { status: 404 }))) - await expect(defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r' })).rejects.toThrow( - /cannot resolve github ref o\/r#HEAD: HTTP 404/, - ) - }) - - it('throws with the explicit-ref label when the API rejects', async () => { - vi.stubGlobal('fetch', fetchReturning(new Response('', { status: 403 }))) - await expect( - defaultResolveRef({ kind: 'github', owner: 'o', repo: 'r', ref: 'main' }), - ).rejects.toThrow(/cannot resolve github ref o\/r#main: HTTP 403/) - }) -}) - -describe('createGigetFetcher', () => { - const downloadMock = vi.mocked(downloadTemplate) - let savedToken: string | undefined - - beforeEach(() => { - downloadMock.mockClear() - savedToken = process.env.GITHUB_TOKEN - delete process.env.GITHUB_TOKEN - }) - - afterEach(() => { - vi.unstubAllGlobals() - if (savedToken === undefined) delete process.env.GITHUB_TOKEN - else process.env.GITHUB_TOKEN = savedToken - }) - - it('wires the real download without provider auth when no token is present', async () => { - vi.stubGlobal('fetch', fetchReturning(new Response(SHA, { status: 200 }))) - await createGigetFetcher().fetch({ kind: 'github', owner: 'o', repo: 'r', ref: 'main' }) - const [input, options] = downloadMock.mock.calls[0]! - expect(input).toBe(`o/r#${SHA}`) - expect(options?.dir).toContain(GITHUB_TEMP_PREFIX) - expect(options?.force).toBe('clean') - expect(options?.providerOptions).toBeUndefined() - }) - - it('passes an explicit token to both ref resolution and provider auth', async () => { - const fetchMock = fetchReturning(new Response(SHA, { status: 200 })) - vi.stubGlobal('fetch', fetchMock) - await createGigetFetcher({ token: 'tok' }).fetch({ kind: 'github', owner: 'o', repo: 'r' }) - expect((fetchMock.mock.calls[0]![1] as RequestInit).headers).toMatchObject({ Authorization: 'Bearer tok' }) - const [, options] = downloadMock.mock.calls[0]! - expect(options).toMatchObject({ providerOptions: { auth: 'tok' } }) - }) - - it('reads GITHUB_TOKEN from the environment', async () => { - process.env.GITHUB_TOKEN = 'from-env' - vi.stubGlobal('fetch', fetchReturning(new Response(SHA, { status: 200 }))) - await createGigetFetcher().fetch({ kind: 'github', owner: 'o', repo: 'r' }) - const [, options] = downloadMock.mock.calls[0]! - expect(options).toMatchObject({ providerOptions: { auth: 'from-env' } }) - }) -}) diff --git a/packages/sdk/plugin-fetch/tests/ids.spec.ts b/packages/sdk/plugin-fetch/tests/ids.spec.ts deleted file mode 100644 index 2f1ba6f518..0000000000 --- a/packages/sdk/plugin-fetch/tests/ids.spec.ts +++ /dev/null @@ -1,39 +0,0 @@ -import { describe, expect, it } from 'vitest' -import { commitSha, integrity } from '../src/ids.ts' - -describe('commitSha', () => { - it('accepts abbreviated and full lowercase hex object ids', () => { - expect(commitSha('abc1234')).toBe('abc1234') - expect(commitSha('a'.repeat(40))).toBe('a'.repeat(40)) - expect(commitSha('0'.repeat(64))).toBe('0'.repeat(64)) - }) - - it.each([ - ['too short', 'abc123'], - ['uppercase', 'ABCDEF1'], - ['non-hex', 'ghijklm'], - ['too long', 'a'.repeat(65)], - ['empty', ''], - ])('rejects an invalid sha (%s)', (_label, value) => { - expect(() => commitSha(value)).toThrow(/invalid commit sha/) - }) -}) - -describe('integrity', () => { - it.each([ - 'sha512-abcABC123+/==', - 'sha384-abcABC123+/', - 'sha256-Zm9vYmFy', - ])('accepts a valid SRI entry (%s)', (value) => { - expect(integrity(value)).toBe(value) - }) - - it.each([ - ['missing algorithm', 'abcABC123'], - ['unsupported algorithm', 'sha1-abcABC123'], - ['illegal base64 char', 'sha512-abc*def'], - ['empty', ''], - ])('rejects an invalid integrity (%s)', (_label, value) => { - expect(() => integrity(value)).toThrow(/invalid subresource integrity/) - }) -}) diff --git a/packages/sdk/plugin-fetch/tests/never.spec.ts b/packages/sdk/plugin-fetch/tests/never.spec.ts deleted file mode 100644 index 224ab66e29..0000000000 --- a/packages/sdk/plugin-fetch/tests/never.spec.ts +++ /dev/null @@ -1,19 +0,0 @@ -import { describe, expect, it } from 'vitest' -import { assertNever } from '../src/never.ts' - -describe('assertNever', () => { - it('throws with the rendered value and a context label', () => { - expect(() => assertNever('surprise' as never, 'demo')).toThrow( - /unreachable variant in demo: "surprise"/, - ) - }) - - it('omits the context clause when none is given', () => { - expect(() => assertNever(7 as never)).toThrow(/unreachable variant: 7$/) - }) - - it('falls back to String() when the value is not JSON-serializable', () => { - // JSON.stringify(undefined) is undefined, exercising the String() fallback. - expect(() => assertNever(undefined as never)).toThrow(/unreachable variant: undefined$/) - }) -}) diff --git a/packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts b/packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts deleted file mode 100644 index 958e56674e..0000000000 --- a/packages/sdk/plugin-fetch/tests/pacote-fetcher.spec.ts +++ /dev/null @@ -1,108 +0,0 @@ -import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' -import { extract as pacoteExtract, manifest as pacoteManifest } from 'pacote' -import { - createPacoteFetcher, - NPM_TEMP_PREFIX, - PacoteFetcher, - type PacoteApi, - type PacoteFetcherDeps, -} from '../src/pacote-fetcher.ts' -import type { NpmSource } from '../src/source.ts' - -vi.mock('pacote', () => ({ manifest: vi.fn(), extract: vi.fn() })) - -const INTEGRITY = 'sha512-abcABC123+/==' -const RESOLVED = 'https://registry.npmjs.org/plugin/-/plugin-1.2.3.tgz' - -function fakePacote(): PacoteApi { - return { - manifest: vi.fn(async () => ({ _resolved: RESOLVED, _integrity: INTEGRITY, version: '1.2.3' })), - extract: vi.fn(async () => ({ resolved: RESOLVED, integrity: INTEGRITY })), - } -} - -function deps(overrides: Partial = {}): PacoteFetcherDeps { - return { - pacote: fakePacote(), - createTempDir: vi.fn(async () => '/tmp/dsh-plugin-npm-abc'), - ...overrides, - } -} - -const SOURCE: NpmSource = { kind: 'npm', name: 'plugin', version: '^1.0.0' } - -describe('PacoteFetcher.fetch', () => { - it('resolves the manifest, extracts with integrity, and reports provenance', async () => { - const d = deps() - const result = await new PacoteFetcher(d).fetch(SOURCE) - - expect(d.pacote.manifest).toHaveBeenCalledWith('plugin@^1.0.0', {}) - expect(d.createTempDir).toHaveBeenCalledWith(NPM_TEMP_PREFIX) - expect(d.pacote.extract).toHaveBeenCalledWith('plugin@^1.0.0', '/tmp/dsh-plugin-npm-abc', { - resolved: RESOLVED, - integrity: INTEGRITY, - }) - expect(result).toEqual({ - dir: '/tmp/dsh-plugin-npm-abc', - source: SOURCE, - provenance: { kind: 'npm', version: '1.2.3', resolved: RESOLVED, integrity: INTEGRITY }, - }) - }) - - it('forwards a configured registry to both manifest and extract', async () => { - const d = deps({ registry: 'https://npm.internal/' }) - await new PacoteFetcher(d).fetch(SOURCE) - expect(d.pacote.manifest).toHaveBeenCalledWith('plugin@^1.0.0', { registry: 'https://npm.internal/' }) - expect(d.pacote.extract).toHaveBeenCalledWith('plugin@^1.0.0', '/tmp/dsh-plugin-npm-abc', { - registry: 'https://npm.internal/', - resolved: RESOLVED, - integrity: INTEGRITY, - }) - }) - - it('rejects a registry integrity that is not a valid SRI', async () => { - const pacote = fakePacote() - pacote.extract = vi.fn(async () => ({ resolved: RESOLVED, integrity: 'not-sri' })) - await expect(new PacoteFetcher(deps({ pacote })).fetch(SOURCE)).rejects.toThrow( - /invalid subresource integrity/, - ) - }) - - it('exposes its source kind', () => { - expect(new PacoteFetcher(deps()).kind).toBe('npm') - }) -}) - -describe('createPacoteFetcher', () => { - const manifestMock = vi.mocked(pacoteManifest) - const extractMock = vi.mocked(pacoteExtract) - - beforeEach(() => { - manifestMock.mockReset() - extractMock.mockReset() - // The real overloaded pacote manifest returns a much wider shape; the fetcher reads only these fields. - manifestMock.mockResolvedValue( - { _resolved: RESOLVED, _integrity: INTEGRITY, version: '1.2.3' } as unknown as Awaited< - ReturnType - >, - ) - extractMock.mockResolvedValue({ from: 'plugin@1.2.3', resolved: RESOLVED, integrity: INTEGRITY }) - }) - - afterEach(() => vi.clearAllMocks()) - - it('wires the real pacote resolve/extract surface', async () => { - const result = await createPacoteFetcher().fetch(SOURCE) - expect(manifestMock).toHaveBeenCalledWith('plugin@^1.0.0', {}) - expect(extractMock).toHaveBeenCalledWith('plugin@^1.0.0', expect.stringContaining(NPM_TEMP_PREFIX), { - resolved: RESOLVED, - integrity: INTEGRITY, - }) - expect(result.provenance).toEqual({ kind: 'npm', version: '1.2.3', resolved: RESOLVED, integrity: INTEGRITY }) - }) - - it('forwards a configured registry through the real surface', async () => { - await createPacoteFetcher({ registry: 'https://npm.internal/' }).fetch(SOURCE) - expect(manifestMock).toHaveBeenCalledWith('plugin@^1.0.0', { registry: 'https://npm.internal/' }) - }) -}) diff --git a/packages/sdk/plugin-fetch/tests/source.spec.ts b/packages/sdk/plugin-fetch/tests/source.spec.ts deleted file mode 100644 index e585c5dfcf..0000000000 --- a/packages/sdk/plugin-fetch/tests/source.spec.ts +++ /dev/null @@ -1,107 +0,0 @@ -import { describe, expect, it } from 'vitest' -import { resolvePluginSource, type GithubSource, type NpmSource } from '../src/source.ts' - -describe('resolvePluginSource — github', () => { - it('parses owner/repo with a ref', () => { - expect(resolvePluginSource('unjs/template#main')).toEqual({ - kind: 'github', owner: 'unjs', repo: 'template', ref: 'main', - }) - }) - - it('parses a bare owner/repo without a ref', () => { - expect(resolvePluginSource('deepseek-ai/plugin')).toEqual({ - kind: 'github', owner: 'deepseek-ai', repo: 'plugin', - }) - }) - - it('parses a nested subdir with a ref', () => { - expect(resolvePluginSource('owner/repo/packages/plugin#v1.2.3')).toEqual({ - kind: 'github', owner: 'owner', repo: 'repo', subdir: 'packages/plugin', ref: 'v1.2.3', - }) - }) - - it('parses a subdir without a ref', () => { - expect(resolvePluginSource('owner/repo/sub')).toEqual({ - kind: 'github', owner: 'owner', repo: 'repo', subdir: 'sub', - }) - }) - - it('accepts a slash-nested ref', () => { - expect(resolvePluginSource('owner/repo#feature/x')).toEqual({ - kind: 'github', owner: 'owner', repo: 'repo', ref: 'feature/x', - }) - }) - - it('trims surrounding whitespace before parsing', () => { - expect(resolvePluginSource(' owner/repo#main ')).toEqual({ - kind: 'github', owner: 'owner', repo: 'repo', ref: 'main', - }) - }) - - it.each([ - ['empty ref after hash', 'owner/repo#'], - ['single locator segment with hash', 'owner#main'], - ['owner with @ and a hash', 'own@er/repo#main'], - ['ref with whitespace', 'owner/repo#bad ref'], - ['ref with traversal', 'owner/repo#a..b'], - ['ref with a leading slash', 'owner/repo#/main'], - ['ref with a trailing slash', 'owner/repo#main/'], - ['ref with an illegal char', 'owner/repo#ma:in'], - ])('rejects a malformed github spec (%s)', (_label, spec) => { - expect(() => resolvePluginSource(spec)).toThrow(/github plugin source|missing a ref/) - }) -}) - -describe('resolvePluginSource — npm', () => { - it('parses an unscoped name@version', () => { - expect(resolvePluginSource('react@18.2.0')).toEqual({ - kind: 'npm', name: 'react', version: '18.2.0', - }) - }) - - it('parses a scoped name@version', () => { - expect(resolvePluginSource('@deepseek-ai/dsh-tool-foo@0.0.1')).toEqual({ - kind: 'npm', name: '@deepseek-ai/dsh-tool-foo', version: '0.0.1', - }) - }) - - it('accepts a dist-tag as the version', () => { - expect(resolvePluginSource('some-plugin@latest')).toEqual({ - kind: 'npm', name: 'some-plugin', version: 'latest', - }) - }) - - it('accepts a range as the version', () => { - expect(resolvePluginSource('some-plugin@^1.0.0')).toEqual({ - kind: 'npm', name: 'some-plugin', version: '^1.0.0', - }) - }) -}) - -describe('resolvePluginSource — failures', () => { - it.each([ - ['empty', ''], - ['whitespace only', ' '], - ])('rejects a blank spec (%s)', (_label, spec) => { - expect(() => resolvePluginSource(spec)).toThrow(/must not be empty/) - }) - - it.each([ - ['bare word', 'plugin'], - ['internal whitespace', 'owner repo'], - ['empty npm version', 'pkg@'], - ['scoped without version', '@scope/pkg'], - ['scoped with empty scope', '@/pkg@1'], - ['unscoped name with slash and version', 'foo/bar@1'], - ['version containing a slash', 'foo@1/2'], - ['uppercase unscoped name', 'FOO@1.0.0'], - ['uppercase scope segment', '@Scope/pkg@1'], - ['uppercase scoped name segment', '@scope/PKG@1'], - ['empty scoped name segment', '@scope/@1'], - ['dot-only owner', './repo'], - ['traversal subdir segment', 'owner/repo/../x'], - ['double slash subdir', 'owner/repo//sub'], - ])('rejects an unrecognized/ambiguous spec (%s)', (_label, spec) => { - expect(() => resolvePluginSource(spec)).toThrow(/unrecognized plugin source|github plugin source/) - }) -}) diff --git a/packages/sdk/plugin-fetch/tsconfig.json b/packages/sdk/plugin-fetch/tsconfig.json deleted file mode 100644 index 07c2567ff8..0000000000 --- a/packages/sdk/plugin-fetch/tsconfig.json +++ /dev/null @@ -1,15 +0,0 @@ -{ - "extends": "../../../tsconfig.base.json", - "compilerOptions": { - "rootDir": "src", - "outDir": "lib/types" - }, - "include": [ - "src" - ], - "references": [ - { - "path": "../../util/brand" - } - ] -} diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 0acc85fcab..cafebfaae6 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1223,25 +1223,6 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) - packages/sdk/plugin-fetch: - dependencies: - '@bluwy/giget-core': - specifier: ^0.1.7 - version: 0.1.7 - pacote: - specifier: ^22.0.0 - version: 22.0.0 - devDependencies: - '@deepseek-ai/dsh-brand': - specifier: workspace:^ - version: link:../../util/brand - '@types/pacote': - specifier: ^11.1.8 - version: 11.1.8 - cordis: - specifier: ^4.0.0-rc.7 - version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) - packages/sdk/scripts: dependencies: '@deepseek-ai/dsh-helper': @@ -2971,10 +2952,6 @@ packages: resolution: {integrity: sha512-6zABk/ECA/QYSCQ1NGiVwwbQerUCZ+TQbp64Q3AgmfNvurHH0j8TtXa1qbShXA6qqkpAj4V5W8pP6mLe1mcMqA==} engines: {node: '>=18'} - '@bluwy/giget-core@0.1.7': - resolution: {integrity: sha512-6XG8TZt8DVYLuGDVSpFJaSMlNowOg5RGecvWbKvlgMoqVbztUAQ3AcWq6oZ5DoCnTzNAPcO7rhkwt8ZVgrS7CQ==} - engines: {node: '>=18'} - '@braintree/sanitize-url@7.1.2': resolution: {integrity: sha512-jigsZK+sMF/cuiB7sERuo9V7N9jx+dhmHHnQyDSVdpZwVutaBu7WvNYqMDLSgFgfB30n452TP3vjDAvFC973mA==} @@ -3428,10 +3405,6 @@ packages: '@noble/hashes': optional: true - '@gar/promise-retry@1.0.3': - resolution: {integrity: sha512-GmzA9ckNokPypTg10pgpeHNQe7ph+iIKKmhKu3Ob9ANkswreCx7R3cKmY781K8QK3AqVL3xVh9A42JvIAbkkSA==} - engines: {node: ^20.17.0 || >=22.9.0} - '@google/genai@1.52.0': resolution: {integrity: sha512-gwSvbpiN/17O9TbsqSsE/OzZcpv5Fo4RQjdngGgogtuB9RsyJ8ZHhX5KjHj1bp5N9snN2eK8LDGXSaWW2hof8Q==} engines: {node: '>=20.0.0'} @@ -3480,10 +3453,6 @@ packages: resolution: {integrity: sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==} engines: {node: '>=12'} - '@isaacs/fs-minipass@4.0.1': - resolution: {integrity: sha512-wgm9Ehl2jpeqP3zw/7mo3kRHFp5MEDhqAdwy1fTGkHAwnkGOVsgpvQhL8B5n1qlb01jV3n/bI0ZfZp5lWA1k4w==} - engines: {node: '>=18.0.0'} - '@jridgewell/gen-mapping@0.3.13': resolution: {integrity: sha512-2kkt/7niJ6MgEPxF0bYdQ6etZaA+fQvDcLKckhy1yIQOzaoKjBBjSj63/aLVjYE3qhRt5dvM+uUyfCg6UKCBbA==} @@ -3530,43 +3499,6 @@ packages: '@nodable/entities@2.2.0': resolution: {integrity: sha512-9uGyhaQavEUMC8AIddIjau4NsnsXhou+j5sBAGojCM1oxmQpVKTWR/9JxABD6UAv12vpIms55fPZKFQEhG6uBg==} - '@npmcli/agent@5.0.2': - resolution: {integrity: sha512-EkzGmEsgbQ1rqWkRJe2P0oQHx/ylZozDUNPMXCklLuSFL3GY+QyEfBUjhjCsgGXzh4OGpnHvkboSQgczjP/jJg==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@npmcli/fs@6.0.0': - resolution: {integrity: sha512-AheOs4swKka/XLtht6xxJDPezlQ7K2IYQ9Y8lST4JLDjnralnWuMM9AE2CdVcgQJ5omrXhsRzM7F7aYmeZBvKQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@npmcli/git@8.0.0': - resolution: {integrity: sha512-5P1oo+TbxZNAiiMBtpzHA8QyEGh5D69LYLexNWJEDXLdxnAZvT/SLitGJBXxjtCE4ftAcFOS/Tu2185MeIjooQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@npmcli/installed-package-contents@5.0.0': - resolution: {integrity: sha512-6Ay12sf2Lh7U1ifvnS1mq7TZFeh/rXHMXye+kV7jQrANIubaoVcleeh4HdFumxhsRYwm9OaHycB5lYmSwGrcIQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - hasBin: true - - '@npmcli/node-gyp@6.0.0': - resolution: {integrity: sha512-MFakpea4pcZNlHSTbMi15HK8RY8zl2UpgDtxhZCWOer+KRN3x7HFIMk/fKpOMgR55L4LIcA2qn8IHeyABhIFtw==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@npmcli/package-json@8.0.0': - resolution: {integrity: sha512-agNZzYQ18MR0wKp3Emg1q5QbcC8CXigYp3Z3CvB0Sax9Ge9aF4cVyyuSG+5SbACSrZUKTvMjVULWiE1RJA38wg==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@npmcli/promise-spawn@10.0.0': - resolution: {integrity: sha512-llZkSzeTsimFx64U+ThT2xQM2uEce8GIQUYvxgbB6ZFvBhV2LP9LeJJb3HT+syG0uCFLsTCHjV9SfC0WNU1vtA==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@npmcli/redact@5.0.0': - resolution: {integrity: sha512-3zcN5Q3yEmeyxXBzqB6fXPQFzYa2ROsGFSr69W0ArXIAGJqxl/aFECOVPD2kbkYPm0U/EHxFKgclK3UA9WQg5A==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@npmcli/run-script@11.0.0': - resolution: {integrity: sha512-leBRl6F5F0TvWut8m1/aZcMTUHi2vXjKeMJ/Ik1lW7Q7Yy16Dhtkklu+cEqQww1p1NeLnUNzV3+uwpzqRcy9vw==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - '@oxc-parser/binding-android-arm-eabi@0.133.0': resolution: {integrity: sha512-l/44caGse+VpnY9gx0yvvc5QnnG3yG1FO3KZgYvNL1GZrfK86zIwAOgGEVlxDyRymzrU/KHiblPFpevKOmJmUA==} engines: {node: ^20.19.0 || >=22.12.0} @@ -4196,30 +4128,6 @@ packages: '@shikijs/vscode-textmate@10.0.2': resolution: {integrity: sha512-83yeghZ2xxin3Nj8z1NMd/NCuca+gsYXswywDy5bHvwlWL8tpTQmzGeUuHd9FC3E/SBEMvzJRwWEOz5gGes9Qg==} - '@sigstore/bundle@5.0.0': - resolution: {integrity: sha512-wefjygudENbzbQMks1t5u34EP0fFoD0XvaEP7DOUP/sXKvogzEJYFw5E6pegGyp3onGWzVEYKVa3bNZWyTYX+A==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@sigstore/core@4.0.1': - resolution: {integrity: sha512-9v5hRjujn5NXq8o7XFEUgLyAtdr5Iisb4pzM05u3K61IS5q3hP3luWAndk0RkPPLTUFoTbg7Vb84UQ1ZQeajWQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@sigstore/protobuf-specs@0.5.1': - resolution: {integrity: sha512-/ScWUhhoFasJsSRGTVBwId1loQjjnjAfE4djL6ZhrXRpNCmPTnUKF5Jokd58ILseOMjzET3UrMOtJPS9sYeI0g==} - engines: {node: ^18.17.0 || >=20.5.0} - - '@sigstore/sign@5.0.0': - resolution: {integrity: sha512-DSFivqz9/i5AkwZ5fq0YdjaJlc4o1WeS2Zffon0kqtChx0vy4W9NOjkEet9bF2vkzOufX72eVH8kZBIGtcBp1w==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@sigstore/tuf@5.0.0': - resolution: {integrity: sha512-Zyqg9tcHps3uRAlKHLNmsW4ohsUZAjb9G+31r7lg0ICh/JOcadzmJsIRdjKljlRHpaR0K4aJ2kXXIdywdcdMlA==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - '@sigstore/verify@4.1.0': - resolution: {integrity: sha512-p/s720RiWxLG8XtmfdPfEJOlATA6H/2knFqmtQbFkHKN3IrhWGUwPfpQAf1UnQIEES9IaH6zzhfjkrhTfeSdZw==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - '@smithy/core@3.24.7': resolution: {integrity: sha512-KoUi4M1f3BG6kzN1FnCwL7oyFptTbyBJKjR6yhSib+JHRdUmM1o+VwsFtJ66NZCkCzVfJMWRHJNo0R0jznp0Pg==} engines: {node: '>=18.0.0'} @@ -4269,14 +4177,6 @@ packages: peerDependencies: eslint: ^9.0.0 || ^10.0.0 - '@tufjs/canonical-json@2.0.0': - resolution: {integrity: sha512-yVtV8zsdo8qFHe+/3kw81dSLyF7D576A5cCFCi4X7B39tWT7SekaEFUnvnWJHz+9qO7qJTah1JbrDjWKqFtdWA==} - engines: {node: ^16.14.0 || >=18.0.0} - - '@tufjs/models@5.0.0': - resolution: {integrity: sha512-U4mVcdFGOi6pt8n38LdWZp67Svn7ppnU1Pj8SGOVaBi1X4gm+G4ztQlLfkoJbKSHfjA6WeaiJp2A4V83AJF6nQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - '@tybys/wasm-util@0.10.2': resolution: {integrity: sha512-RoBvJ2X0wuKlWFIjrwffGw1IqZHKQqzIchKaadZZfnNpsAYp2mM0h36JtPCjNDAHGgYez/15uMBpfGwchhiMgg==} @@ -4424,36 +4324,18 @@ packages: '@types/ms@2.1.0': resolution: {integrity: sha512-GsCCIZDE/p3i96vtEqx+7dBUGXrc7zeSK3wwPHIaRThS+9OhWIXRqzs4d6k1SVU8g91DrNRWxWUGhp5KXQb2VA==} - '@types/node-fetch@2.6.13': - resolution: {integrity: sha512-QGpRVpzSaUs30JBSGPjOg4Uveu384erbHBoT1zeONvyCfwQxIkUshLAOqN/k9EjGviPRmWTTe6aH2qySWKTVSw==} - '@types/node@22.20.0': resolution: {integrity: sha512-QWlFW2wf3nTjC13/DqRnBpR4ZO36VJH/JVBkA/vcnmbTBNQIlnObqyqZE1tUR7+Ni23Lda8R1BxMfbXRpCUx5g==} '@types/node@25.9.3': resolution: {integrity: sha512-603BddQMv3pUcr4U2dhujk83N2tTDVr/34wII2B6bJy6g+8WD6yUb11jszNs0gdi4PesVWl7ABt8nYMVpnLUcg==} - '@types/npm-package-arg@6.1.4': - resolution: {integrity: sha512-vDgdbMy2QXHnAruzlv68pUtXCjmqUk3WrBAsRboRovsOmxbfn/WiYCjmecyKjGztnMps5dWp4Uq2prp+Ilo17Q==} - - '@types/npm-registry-fetch@8.0.9': - resolution: {integrity: sha512-7NxvodR5Yrop3pb6+n8jhJNyzwOX0+6F+iagNEoi9u1CGxruYAwZD8pvGc9prIkL0+FdX5Xp0p80J9QPrGUp/g==} - - '@types/npmlog@7.0.0': - resolution: {integrity: sha512-hJWbrKFvxKyWwSUXjZMYTINsSOY6IclhvGOZ97M8ac2tmR9hMwmTnYaMdpGhvju9ctWLTPhCS+eLfQNluiEjQQ==} - - '@types/pacote@11.1.8': - resolution: {integrity: sha512-/XLR0VoTh2JEO0jJg1q/e6Rh9bxjBq9vorJuQmtT7rRrXSiWz7e7NsvXVYJQ0i8JxMlBMPPYDTnrRe7MZRFA8Q==} - '@types/picomatch@3.0.2': resolution: {integrity: sha512-n0i8TD3UDB7paoMMxA3Y65vUncFJXjcUf7lQY7YyKGl6031FNjfsLs6pdLFCy2GNFxItPJG8GvvpbZc2skH7WA==} '@types/retry@0.12.0': resolution: {integrity: sha512-wWKOClTTiizcZhXnPY4wikVAwmdYHp8q6DmC+EJUzAMsycb7HB32Kh9RN4+0gExjmPmZSAQjgURXIGATPegAvA==} - '@types/ssri@7.1.5': - resolution: {integrity: sha512-odD/56S3B51liILSk5aXJlnYt99S6Rt9EFDDqGtJM26rKHApHcwyU/UoYHrzKkdkHMAIquGWCuHtQTbes+FRQw==} - '@types/tough-cookie@4.0.5': resolution: {integrity: sha512-/Ad8+nIOV7Rl++6f1BdKxFSMgmoqEoYbHRpPcx3JEfv8VRsQe9Z4mCXeJBzxs7mbHY/XOZZuXlRNfhpVPbs6ZA==} @@ -4668,10 +4550,6 @@ packages: resolution: {integrity: sha512-A9gOqLdi6cV4ibazAjcQufGj0B1y/vDqYrcuP6d/6x8P27gRS8643Dj9o1dEKtB6O7fwxb2FgBmJS2mX7gpvdw==} engines: {node: '>=14.6'} - abbrev@5.0.0: - resolution: {integrity: sha512-/XrFJgzQQQHpti1raDJC6m4ws6aNktmjBlhk8Fdlk7LwCEuDoieEJJY9OFHjfiFJFFRM2tK+Ky/IsfbbmlMu1w==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - accepts@2.0.0: resolution: {integrity: sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng==} engines: {node: '>= 0.6'} @@ -4690,10 +4568,6 @@ packages: resolution: {integrity: sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ==} engines: {node: '>= 14'} - agent-base@9.0.0: - resolution: {integrity: sha512-TQf59BsZnytt8GdJKLPfUZ54g/iaUL2OWDSFCCvMOhsHduDQxO8xC4PNeyIkVcA5KwL2phPSv0douC0fgWzmnA==} - engines: {node: '>= 20'} - ajv-formats@3.0.1: resolution: {integrity: sha512-8iUql50EUR+uUcdRQ3HDqa6EVyo3docL8g5WJ3FNcWmu62IbkGUue/pEyLBW8VGKKucTPgqeks4fIU1DA4yowQ==} peerDependencies: @@ -4753,9 +4627,6 @@ packages: ast-v8-to-istanbul@1.0.4: resolution: {integrity: sha512-0bC0/4bTSrnwdhU3IsZDwEdojvuPrSg59OYZfKsLRtJZ0u8VBx9DebfqqG8bRdCC0I7vjgxmPi41P0lpkhJHtA==} - asynckit@0.4.0: - resolution: {integrity: sha512-Oei9OH4tRh0YqU3GxhX79dM/mwVgvbZJaSNaRk+bshkj0S5cfHcgYakreBjrHwatXKbz+IoIdYLxrKim2MjW0Q==} - balanced-match@1.0.2: resolution: {integrity: sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==} @@ -4810,10 +4681,6 @@ packages: resolution: {integrity: sha512-tixWYgm5ZoOD+3g6UTea91eow5z6AAHaho3g0V9CNSNb45gM8SmflpAc+GRd1InC4AqN/07Unrgp56Y94N9hJQ==} engines: {node: '>=20.19.0'} - cacache@21.0.1: - resolution: {integrity: sha512-pTwz/uj3Jyp6WXdJ6fWhR+7LVxVs6RyroQSn7KJwHsSxXuyGSp0pcMVcwSwTpCFq1X2YG8QBe0W+vN+cr0SwzA==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - call-bind-apply-helpers@1.0.2: resolution: {integrity: sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==} engines: {node: '>= 0.4'} @@ -4849,10 +4716,6 @@ packages: resolution: {integrity: sha512-Qgzu8kfBvo+cA4962jnP1KkS6Dop5NS6g7R5LFYJr4b8Ub94PPQXUksCw9PvXoeXPRRddRNC5C1JQUR2SMGtnA==} engines: {node: '>= 14.16.0'} - chownr@3.0.0: - resolution: {integrity: sha512-+IxzY9BZOQd/XuYPRmrvEVjF/nqj5kgT4kEq7VofrDoM1MxoRjEWkrCC3EtLi59TVawxTAn+orJwFQcrqEN1+g==} - engines: {node: '>=18'} - color-convert@2.0.1: resolution: {integrity: sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==} engines: {node: '>=7.0.0'} @@ -4860,10 +4723,6 @@ packages: color-name@1.1.4: resolution: {integrity: sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==} - combined-stream@1.0.8: - resolution: {integrity: sha512-FQN4MRfuJeHf7cBbBMJFXhKSDq+2kAArBlmRBvcvFE5BB1HZKXtSFASDhdlz9zOYwxh8lDdnvmMOe/+5cdoEdg==} - engines: {node: '>= 0.8'} - comma-separated-tokens@2.0.3: resolution: {integrity: sha512-Fu4hJdvzeylCfQPp9SGWidpzrMs7tTrlu6Vb8XGaRGck8QSNZJJp538Wrb60Lax4fPwR64ViY468OIUTbRlGZg==} @@ -5151,10 +5010,6 @@ packages: delaunator@5.1.0: resolution: {integrity: sha512-AGrQ4QSgssa1NGmWmLPqN5NY2KajF5MqxetNEO+o0n3ZwZZeTmt7bBnvzHWrmkZFxGgr4HdyFgelzgi06otLuQ==} - delayed-stream@1.0.0: - resolution: {integrity: sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==} - engines: {node: '>=0.4.0'} - depd@2.0.0: resolution: {integrity: sha512-g7nH6P6dyDioJogAAGprGpCtVImJhpPk/roCzdb3fIh61/s/nPsfR6onyMwkCAR/OlC3yBC0lESvUoQEAssIrw==} engines: {node: '>= 0.8'} @@ -5248,10 +5103,6 @@ packages: resolution: {integrity: sha512-zwfzJecQ/Uej6tusMqwAqU/6KL2XaB2VZ2Jg54Je6ahNBGNH6Ek6g3jjNCF0fG9EWQKGZNddNjU5F1ZQn/sBnA==} engines: {node: '>=20.19.0'} - env-paths@2.2.1: - resolution: {integrity: sha512-+h1lkLKhZMTYjog1VEpJNG7NZJWcuc2DDk/qsqSTRRCOXiLjeQ1d1/udrUGhqMxUgAlwKNZ0cf2uqan5GLuS2A==} - engines: {node: '>=6'} - es-define-property@1.0.1: resolution: {integrity: sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==} engines: {node: '>= 0.4'} @@ -5267,10 +5118,6 @@ packages: resolution: {integrity: sha512-HWcBoN6NileqtSydK2FqHbS/LoDd2pqrnQHLyJzBj4kOp/ky2MWMN694xOfkK8/SnUsW2DH7EfyVlydKCsm1Zw==} engines: {node: '>= 0.4'} - es-set-tostringtag@2.1.0: - resolution: {integrity: sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==} - engines: {node: '>= 0.4'} - es-toolkit@1.49.0: resolution: {integrity: sha512-G5iZ6Pc/FNRY/soKZHC+TxGDD83rHUDXxzaWhGCX44vAv/tMs56WMusnm/KMNK+luUPsgA9U28cGr4RDlSzL2g==} @@ -5380,9 +5227,6 @@ packages: resolution: {integrity: sha512-knvyeauYhqjOYvQ66MznSMs83wmHrCycNEN6Ao+2AeYEfxUIkuiVxdEa1qlGEPK+We3n0THiDciYSsCcgW/DoA==} engines: {node: '>=12.0.0'} - exponential-backoff@3.1.3: - resolution: {integrity: sha512-ZgEeZXj30q+I0EN+CbSSpIyPaJ5HVQD18Z1m+u1FXbAeT94mr1zw50q4q6jiiC447Nl/YTcIYSAftiGqetwXCA==} - express-rate-limit@8.5.2: resolution: {integrity: sha512-5Kb34ipNX694DH48vN9irak1Qx30nb0PLYHXfJgw4YEjiC3ZEmZJhwOp+VfiCYwFzvFTdB9QkArYS5kXa2cx2A==} engines: {node: '>= 16'} @@ -5470,10 +5314,6 @@ packages: resolution: {integrity: sha512-gIXjKqtFuWEgzFRJA9WCQeSJLZDjgJUOMCMzxtvFq/37KojM1BFGufqsCy0r4qSQmYLsZYMeyRqzIWOMup03sw==} engines: {node: '>=14'} - form-data@4.0.6: - resolution: {integrity: sha512-vKatAh4SlVfgbv+YtmhiRjhEMJsYpsG1Y2rMQtR+SVSbytsSD1YGzDIcrAJmdFec88u/+VoGmxnl+80gL1tRCQ==} - engines: {node: '>= 6'} - formatly@0.3.0: resolution: {integrity: sha512-9XNj/o4wrRFyhSMJOvsuyMwy8aUfBaZ1VrqHVfohyXf0Sw0e+yfKG+xZaY3arGCOMdwFsqObtzVOc1gU9KiT9w==} engines: {node: '>=18.3.0'} @@ -5491,10 +5331,6 @@ packages: resolution: {integrity: sha512-Rx/WycZ60HOaqLKAi6cHRKKI7zxWbJ31MhntmtwMoaTeF7XFH9hhBp8vITaMidfljRQ6eYWCKkaTK+ykVJHP2A==} engines: {node: '>= 0.8'} - fs-minipass@3.0.3: - resolution: {integrity: sha512-XUBA9XClHbnJWSfBzjkm6RvPsyg3sryZt06BEQoXcF7EK/xpGaQYJgQKDJSUH5SGZ76Y7pFx1QBnXz09rU5Fbw==} - engines: {node: ^14.17.0 || ^16.13.0 || >=18.0.0} - fsevents@2.3.3: resolution: {integrity: sha512-5xoDfX+fL7faATnagmWPpbFtwh/R77WmMMqqHGS65C3vvB0YHrgF+B1YmZ3441tMj5n63k0212XNoJwzlhffQw==} engines: {node: ^8.16.0 || ^10.6.0 || >=11.0.0} @@ -5538,10 +5374,6 @@ packages: deprecated: Old versions of glob are not supported, and contain widely publicized security vulnerabilities, which have been fixed in the current version. Please update. Support for old versions may be purchased (at exorbitant rates) by contacting i@izs.me hasBin: true - glob@13.0.6: - resolution: {integrity: sha512-Wjlyrolmm8uDpm/ogGyXZXb1Z+Ca2B8NbJwqBVg0axK9GbBeoS7yGV6vjXnYdGm6X53iehEuxxbyiKp8QmN4Vw==} - engines: {node: 18 || 20 || >=22} - globals@17.7.0: resolution: {integrity: sha512-Czmyns5dUsq4seFBR/Kdydhmo8y9kC79hiSkPn0YcGtNnYWnrgt0vjrSjx9tspoDGWm2CMarffRuLjM4xUz8xg==} engines: {node: '>=18'} @@ -5561,9 +5393,6 @@ packages: resolution: {integrity: sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==} engines: {node: '>= 0.4'} - graceful-fs@4.2.11: - resolution: {integrity: sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==} - hachure-fill@0.5.2: resolution: {integrity: sha512-3GKBOn+m2LX9iq+JC1064cSFprJY4jL1jCXTcpnfER5HYE2l/4EfWSGzkPa/ZDBmYI0ZOEj5VHV/eKnPGkHuOg==} @@ -5580,10 +5409,6 @@ packages: resolution: {integrity: sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==} engines: {node: '>= 0.4'} - has-tostringtag@1.0.2: - resolution: {integrity: sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==} - engines: {node: '>= 0.4'} - hasown@2.0.4: resolution: {integrity: sha512-T2UbfbBEF32wiepXIsMlTW9+dDYC6wMh/t/vYA4tuOMKqWz/n3vr1NFSxQiyP+zk2mXsoMA/i/7qV6LKut1t1A==} engines: {node: '>= 0.4'} @@ -5604,10 +5429,6 @@ packages: hookable@6.1.1: resolution: {integrity: sha512-U9LYDy1CwhMCnprUfeAZWZGByVbhd54hwepegYTK7Pi5NvqEj63ifz5z+xukznehT7i6NIZRu89Ay1AZmRsLEQ==} - hosted-git-info@10.1.1: - resolution: {integrity: sha512-DeOnSPAvOndYKfw075gt8yZzQ7S2hNztw34zBTfhIzLhmBTswIBg5/y+pqu/VD5cYWm5goAFTusDmUEmKZ0PEQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - html-encoding-sniffer@6.0.0: resolution: {integrity: sha512-CV9TW3Y3f8/wT0BRFc1/KAVQ3TUHiXmaAb6VW9vtiMFf7SLoMd1PdAc4W3KFOFETBJUb90KatHqlsZMWV+R9Gg==} engines: {node: ^20.19.0 || ^22.12.0 || >=24.0.0} @@ -5624,9 +5445,6 @@ packages: htmlparser2@6.1.0: resolution: {integrity: sha512-gyyPk6rgonLFEDGoeRgQNaEUvdJ4ktTmmUh/h2t7s+M8oPpIPxgNACWa+6ESR57kXstwqPiCut0V8NRpcwgU7A==} - http-cache-semantics@4.2.0: - resolution: {integrity: sha512-dTxcvPXqPvXBQpq5dUr6mEMJX4oIEFv6bwom3FDwKRDsuIjjJGANqhBuoAn9c1RQJIdAKav33ED65E2ys+87QQ==} - http-errors@2.0.1: resolution: {integrity: sha512-4FbRdAX+bSdmo4AUFuS0WNiPz8NgFt+r8ThgNWmlrjQjt1Q7ZR9+zTlce2859x4KSXrwIsaeTqDoKQmtP8pLmQ==} engines: {node: '>= 0.8'} @@ -5635,18 +5453,10 @@ packages: resolution: {integrity: sha512-T1gkAiYYDWYx3V5Bmyu7HcfcvL7mUrTWiM6yOfa3PIphViJ/gFPbvidQ+veqSOHci/PxBcDabeUNCzpOODJZig==} engines: {node: '>= 14'} - http-proxy-agent@9.1.0: - resolution: {integrity: sha512-2NxoveTT58mjYT4n3RPTEfCZGLMbidoO8XEieXfpSYxu+PQJ1qpx4ypwH6N+uF9twBPIvRRgvkvW5HUTYWENig==} - engines: {node: '>= 20'} - https-proxy-agent@7.0.6: resolution: {integrity: sha512-vK9P5/iUfdl95AI+JVyUuIcVtd4ofvtrOr3HNtM2yxC9bnMbEdp3x01OhQNnjb8IJYi38VlTE3mBXwcfvywuSw==} engines: {node: '>= 14'} - https-proxy-agent@9.1.0: - resolution: {integrity: sha512-ag87y7cJJ9/3+GxFr8Oy4O5faDsGRGnBGsJj/YjOSsSx/5eadKLYTMPlzuR6obgoCDDm0abAAZitXXQkMOPSpA==} - engines: {node: '>= 20'} - iconv-lite@0.6.3: resolution: {integrity: sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==} engines: {node: '>=0.10.0'} @@ -5655,10 +5465,6 @@ packages: resolution: {integrity: sha512-IKXpvIzjnC9XTAUbVBcMfGS0EPaIXtW6v+zr+RRp+hqULEpo0owZax6wyRwPOJbWbzjYspQwusTsfVr0ifh4uQ==} engines: {node: '>=0.10.0'} - ignore-walk@9.0.0: - resolution: {integrity: sha512-tCBEZV2z2FNpIDl2vrhiWzIHzs4qOAuIDEO85eS02vZ3L1U3P56qpPL8GuGGAijDktAEaq2swMkO/Fmbo7YmfQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - ignore@5.3.2: resolution: {integrity: sha512-hsBTNUqQTDwkWtcdYI2i06Y/nUBEsNEDJKjWdigLvegy8kDuJAS8uRlpkkcQpyEXL0Z/pjDy5HBmMjRCJ2gq+g==} engines: {node: '>= 4'} @@ -5684,10 +5490,6 @@ packages: inherits@2.0.4: resolution: {integrity: sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==} - ini@7.0.0: - resolution: {integrity: sha512-ifK0CgjALofS5bkrcTy4RaQ9Vx2Knf/eLeIO+NaswQEpH1UblrtTSCIvN71qQDMq0PeQ/SSPojvEJp9vvvfr+w==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - internmap@1.0.1: resolution: {integrity: sha512-lDB5YccMydFBtasVtxnZ3MRBHuaoE8GKsppq+EchKL2U4nK/DmEpPHNH8MZe5HkMtpSiTSOZwfN0tzYjO/lJEw==} @@ -5731,10 +5533,6 @@ packages: isexe@2.0.0: resolution: {integrity: sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==} - isexe@4.0.0: - resolution: {integrity: sha512-FFUtZMpoZ8RqHS3XeXEmHWLA4thH+ZxCv2lOiPIn1Xc7CxrqhWzNSDzD+/chS/zbYezmiwWLdQC09JdQKmthOw==} - engines: {node: '>=20'} - istanbul-lib-coverage@3.2.2: resolution: {integrity: sha512-O8dpsF+r0WV/8MNRKfnmrtCWhuKjxrq2w+jpzBL5UZKTi2LeVWnWOmWRxFlesJONmc+wLAGvKQZEOanko0LFTg==} engines: {node: '>=8'} @@ -5825,10 +5623,6 @@ packages: json-buffer@3.0.1: resolution: {integrity: sha512-4bV5BfR2mqfQTJm+V5tPPdf+ZpuhiIvTuAB5g8kcrXOZpTT/QwwVRWBywX1ozr6lEuPdbHxwaJlm9G6mI2sfSQ==} - json-parse-even-better-errors@6.0.0: - resolution: {integrity: sha512-2/8adwnK1/+Fdjyts4r6wSpfANWw8zdNhU9U/Llk59c6O+DjSisPWPykwoL8gZmocP9Dy64S7oie2g+Mia123A==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - json-schema-to-ts@3.1.1: resolution: {integrity: sha512-+DWg8jCJG2TEnpy7kOm/7/AxaYoaRbjVB4LFZLySZlWn8exGs3A4OLJR966cVvU26N7X9TWxl+Jsw7dzAqKT6g==} engines: {node: '>=16'} @@ -5848,10 +5642,6 @@ packages: jsonc-parser@3.3.1: resolution: {integrity: sha512-HUgH65KyejrUFPvHFPbqOY0rsFip3Bo5wb4ngvdi1EpCYWUQDC5V+Y7mZws+DLkr4M//zQJoanu1SP+87Dv1oQ==} - jsonparse@1.3.1: - resolution: {integrity: sha512-POQXvpdL69+CluYsillJ7SUhKvytYjW9vG/GKpnf+xP8UWgYEM/RaMzHHofbALDiKbbP1W8UEYmgGl39WkPZsg==} - engines: {'0': node >= 0.2.0} - jsx-ast-utils-x@0.1.0: resolution: {integrity: sha512-eQQBjBnsVtGacsG9uJNB8qOr3yA8rga4wAaGG1qRcBzSIvfhERLrWxMAM1hp5fcS6Abo8M4+bUBTekYR0qTPQw==} engines: {node: ^18.18.0 || ^20.9.0 || >=21.1.0} @@ -6059,10 +5849,6 @@ packages: resolution: {integrity: sha512-hXdUTZYIVOt1Ex//jAQi+wTZZpUpwBj/0QsOzqegb3rGMMeJiSEu5xLHnYfBrRV4RH2+OCSOO95Is/7x1WJ4bw==} engines: {node: '>=10'} - make-fetch-happen@16.0.1: - resolution: {integrity: sha512-uUv1yxHzaKVVEPfcFeGSNov/Cehjv08ovlY8ImTljgL7Q+SiA0dAYLQ6SYVa2kkKqNj4Y3aZEI7xv2teadie0A==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - mark.js@8.11.1: resolution: {integrity: sha512-1I+1qpDt4idfgLQG+BNWmrqku+7/2bi5nLf4YwF8y8zXvmfiTBY3PV3ZibfrjBueCByROpuBjLLFCajqkgYoLQ==} @@ -6225,18 +6011,10 @@ packages: micromark@4.0.2: resolution: {integrity: sha512-zpe98Q6kvavpCr1NPVSCMebCKfD7CA2NqZ+rykeNhONIJBpc1tFKt9hucLGwha3jNTNI8lHpctWJWoimVF4PfA==} - mime-db@1.52.0: - resolution: {integrity: sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg==} - engines: {node: '>= 0.6'} - mime-db@1.54.0: resolution: {integrity: sha512-aU5EJuIN2WDemCcAp2vFBfp/m4EAhWJnUNSSw0ixs7/kXbd6Pg64EmwJkNdFhB8aWt1sH2CTXrLxo/iAGV3oPQ==} engines: {node: '>= 0.6'} - mime-types@2.1.35: - resolution: {integrity: sha512-ZDY+bPm5zTTF+YpCrAU9nK0UgICYPT0QtT1NZWFv4s++TNkcgVaT0g6+4R2uI4MjQjzysHB1zxuWL50hzaeXiw==} - engines: {node: '>= 0.6'} - mime-types@3.0.2: resolution: {integrity: sha512-Lbgzdk0h4juoQ9fCKXW4by0UJqj+nOOrI9MJ1sSj4nI8aI2eo1qmvQEie4VD1glsS250n15LsWsYtCugiStS5A==} engines: {node: '>=18'} @@ -6257,30 +6035,6 @@ packages: minimist@1.2.8: resolution: {integrity: sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==} - minipass-collect@2.0.1: - resolution: {integrity: sha512-D7V8PO9oaz7PWGLbCACuI1qEOsq7UKfLotx/C0Aet43fCUB/wfQ7DYeq2oR/svFJGYDHPr38SHATeaj/ZoKHKw==} - engines: {node: '>=16 || 14 >=14.17'} - - minipass-fetch@6.0.0: - resolution: {integrity: sha512-AWI8bKapGmgx/J0E6IGYSKj8TiHebZkmKWSs8raPSw8KXwgEAJ+Bw3+LSdXHR6T/RHKAWCOYk2MiLrYluaUU6w==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - minipass-flush@1.0.7: - resolution: {integrity: sha512-TbqTz9cUwWyHS2Dy89P3ocAGUGxKjjLuR9z8w4WUTGAVgEj17/4nhgo2Du56i0Fm3Pm30g4iA8Lcqctc76jCzA==} - engines: {node: '>= 8'} - - minipass-pipeline@1.2.4: - resolution: {integrity: sha512-xuIq7cIOt09RPRJ19gdi4b+RiNvDFYe5JH+ggNvBqGqpQXcru3PcRmOZuHBKWK1Txf9+cQ+HMVN4d6z46LZP7A==} - engines: {node: '>=8'} - - minipass-sized@2.0.0: - resolution: {integrity: sha512-zSsHhto5BcUVM2m1LurnXY6M//cGhVaegT71OfOXoprxT6o780GZd792ea6FfrQkuU4usHZIUczAQMRUE2plzA==} - engines: {node: '>=8'} - - minipass@3.3.6: - resolution: {integrity: sha512-DxiNidxSEK+tHG6zOIklvNOwm3hvCrbUrdtzY74U6HKTJxvIDfOUL5W5P2Ghd3DTkhhKPYGqeNUIh5qcM4YBfw==} - engines: {node: '>=8'} - minipass@7.1.3: resolution: {integrity: sha512-tEBHqDnIoM/1rXME1zgka9g6Q2lcoCkxHLuc7ODJ5BxbP5d4c2Z5cGgtXAku59200Cx7diuHTOYfSBD8n6mm8A==} engines: {node: '>=16 || 14 >=14.17'} @@ -6288,20 +6042,12 @@ packages: minisearch@7.2.0: resolution: {integrity: sha512-dqT2XBYUOZOiC5t2HRnwADjhNS2cecp9u+TJRiJ1Qp/f5qjkeT5APcGPjHw+bz89Ms8Jp+cG4AlE+QZ/QnDglg==} - minizlib@3.1.0: - resolution: {integrity: sha512-KZxYo1BUkWD2TVFLr0MQoM8vUUigWD3LlD83a/75BqC+4qE0Hb1Vo5v1FgcfaNXvfXzr+5EhQ6ing/CaBijTlw==} - engines: {node: '>= 18'} - mitt@3.0.1: resolution: {integrity: sha512-vKivATfr97l2/QBCYAkXYDbrIWPM2IIKEl7YPhjCvKlG3kE2gm+uBo6nEXK3M5/Ffh/FLpKExzOQ3JJoJGFKBw==} mj-context-menu@0.6.1: resolution: {integrity: sha512-7NO5s6n10TIV96d4g2uDpG7ZDpIhMh0QNfGdJw/W47JswFcosz457wqz/b5sAKvl12sxINGFCn80NZHKwxQEXA==} - modern-tar@0.7.6: - resolution: {integrity: sha512-sweCIVXzx1aIGTCdzcMlSZt1h8k5Tmk08VNAuRk3IU28XamGiOH5ypi11g6De2CH7PhYqSSnGy2A/EFhbWnVKg==} - engines: {node: '>=18.0.0'} - mri@1.2.0: resolution: {integrity: sha512-tzzskb3bG8LvYGFF/mDTpq3jpI6Q9wc3LEmBaghu+DdCssd1FakN7Bc0hVNmEyGq1bq3RgfkCb3cmQLpNPOroA==} engines: {node: '>=4'} @@ -6410,44 +6156,6 @@ packages: resolution: {integrity: sha512-dRB78srN/l6gqWulah9SrxeYnxeddIG30+GOqK/9OlLVyLg3HPnr6SqOWTWOXKRwC2eGYCkZ59NNuSgvSrpgOA==} engines: {node: ^12.20.0 || ^14.13.1 || >=16.0.0} - node-gyp@13.0.1: - resolution: {integrity: sha512-piOr0S10qy5THB+q5BdqkoOx65XL/tjTMUAit3vciPNp+snTOBnGunWH1Rz7XZUxf2T9uFrfT/Ty4+aC3yPeyg==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - hasBin: true - - nopt@10.0.1: - resolution: {integrity: sha512-df3sBr/6ax9hSGuC3CspvLlbnX8cP5L5nZwXF8cGN8l0zSWR6BvzmQ6jPUKjvo6+/xdpkNvEcucBNUdBeeV13g==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - hasBin: true - - npm-bundled@6.0.0: - resolution: {integrity: sha512-EqdodKEW6pYM+dPxA66TZQfMEqVDiuzjDM9edSjuPI1mXUbUJwVxkgqMZSJvs8RTXz2CGq8HUol/AffTZX5g8w==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - npm-install-checks@9.0.0: - resolution: {integrity: sha512-t05Izcgi7p15cpldqoiXYpjzlkTTvBw33sgjmL/JjcvtV0ydbm2O4iEXO8A6smqComu5FAQhUas86HTMQ6Z1Uw==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - npm-normalize-package-bin@6.0.0: - resolution: {integrity: sha512-tdt4aFn9QamlhdN3HV2D2ccpBwO5/fyjjbXUxYA6uBjyekMZcZvDq0aSj9t5Jo+tih6AYFnt/cuIRn9013e0Uw==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - npm-package-arg@14.0.0: - resolution: {integrity: sha512-69XQh3k+dtGa1p+7RaR57IuG3rCko96xr/nUfN4yDYBXbTYICiWcOpsFKLN2GtGE9cyIljE+f1exnaYt9MvM+Q==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - npm-packlist@11.3.0: - resolution: {integrity: sha512-cS1yVkyriZgQAbiK8PtwhZHEtsFOsKHsCg5Ww2ONckAvXIspgqd6o4WirOzvkupU24iMRZ4xtO4kb2iK2rbnag==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - npm-pick-manifest@12.0.0: - resolution: {integrity: sha512-8Fs3YLrnNOhrCdPNZy18MzNgVC58LTDAFzq1FdZO/p3BHeCC/coz+t4F5Pxabys8HJpyTUorMea26GkXsb4J/Q==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - - npm-registry-fetch@20.0.1: - resolution: {integrity: sha512-vzc1svxw/kw1IRjFsLi6gaxe1Olqm88V0tIfu2u5raL0b1gChe6ZEXNkyUlKxUC7s/egt5NxZHkbY18tMKKLfQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - nth-check@2.1.1: resolution: {integrity: sha512-lqjrjmaOoAnWfMmBPL+XNnynZh2+swxiX3WUE0s4yEHI6m+AwrK2UZOimIRl3X/4QctVqS8AiZjFqyOGrMXb/w==} @@ -6504,10 +6212,6 @@ packages: resolution: {integrity: sha512-LaNjtRWUBY++zB5nE/NwcaoMylSPk+S+ZHNB1TzdbMJMny6dynpAGt7X/tl/QYq3TIeE6nxHppbo2LGymrG5Pw==} engines: {node: '>=10'} - p-map@7.0.5: - resolution: {integrity: sha512-e8vJF4XdVkzqqSHguEMz41mQO1wKwxKm5ENrUJQUu9kLDCtn83cxbyHZcszr4QC5zEA7WffRRC4gsTecC7J9oA==} - engines: {node: '>=18'} - p-retry@4.6.2: resolution: {integrity: sha512-312Id396EbJdvRONlngUx0NydfrIQ5lsYu0znKVUzVvArzEIt08V1qhtyESbGVd1FGX7UKtiFp5uwKZdM8wIuQ==} engines: {node: '>=8'} @@ -6518,11 +6222,6 @@ packages: package-manager-detector@1.6.0: resolution: {integrity: sha512-61A5ThoTiDG/C8s8UMZwSorAGwMJ0ERVGj2OjoW5pAalsNOg15+iQiPzrLJ4jhZ1HJzmC2PIHT2oEiH3R5fzNA==} - pacote@22.0.0: - resolution: {integrity: sha512-++VqeOZeL03uGM2MFLk96jGCSt1owBGkyFKoPr+trwNlZhCpjN2RrvwYxt8nTbs1wNMqSFYurq0TafVWkAIHig==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - hasBin: true - pako@1.0.11: resolution: {integrity: sha512-4hLB8Py4zZce5s4yd9XzopqwVv/yGNhV1Bl8NTmCq1763HeK2+EwVTv+leGeL13Dnh2wfbqowVPXCIO0z4taYw==} @@ -6561,10 +6260,6 @@ packages: resolution: {integrity: sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA==} engines: {node: '>=16 || 14 >=14.18'} - path-scurry@2.0.2: - resolution: {integrity: sha512-3O/iVVsJAPsOnpwWIeD+d6z/7PmqApyQePUtCndjatj/9I5LylHvt5qluFaBT3I5h3r1ejfR056c+FCv+NnNXg==} - engines: {node: 18 || 20 || >=22} - path-to-regexp@8.4.2: resolution: {integrity: sha512-qRcuIdP69NPm4qbACK+aDogI5CBDMi1jKe0ry5rSQJz8JVLsC7jV8XpiJjGRLLol3N+R5ihGYcrPLTno6pAdBA==} @@ -6607,10 +6302,6 @@ packages: resolution: {integrity: sha512-vkcDPrRZo1QZLbn5RLGPpg/WmIQ65qoWWhcGKf/b5eplkkarX0m9z8ppCat4mlOqUsWpyNuYgO3VRyrYHSzX5g==} engines: {node: '>= 0.8.0'} - proc-log@7.0.0: - resolution: {integrity: sha512-FYgfaA69XZ93zaXLoMNQ+ViDXGGBgR8aLh03txzcFhV+9xOXx7+8DLCULrKKpR9+GsH9ZfHm82aSUPpozX0Ztg==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - process-nextick-args@2.0.1: resolution: {integrity: sha512-3ouUOpQhtgrbOa17J7+uxOTpITYWaGP7/AhoR3+A+/1e9skrzelGi/dXzEYyvbxubEF6Wn2ypscTKiKJFFn1ag==} @@ -6625,15 +6316,6 @@ packages: resolution: {integrity: sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg==} engines: {node: '>= 0.10'} - proxy-agent-negotiate@1.1.0: - resolution: {integrity: sha512-N8IBcM3UgCVzz2L2Lqv8DVntDnnC8/hiV4nEDUPkqq72TPUgYWjQc+bdZlBPZK9LzPAvOY//gAt0S0DApoOXWQ==} - engines: {node: '>= 20'} - peerDependencies: - kerberos: ^2.0.0 - peerDependenciesMeta: - kerberos: - optional: true - publint@0.3.21: resolution: {integrity: sha512-OqejcnMV6E9zel2oCrUOJEiiFkGiAAni0A6ibfQNh1k9Gu5z4F+Yso8lllam7AzmV6Do0vp7u3UpZNRBwuXaHQ==} engines: {node: '>=18'} @@ -6826,32 +6508,16 @@ packages: resolution: {integrity: sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw==} engines: {node: '>=14'} - sigstore@5.0.0: - resolution: {integrity: sha512-hJqJfoG/e4qFQaauQL00c6J6FrHLBGKtkFvW3JbTSIEFOhLrSjdSM/gWd/yUOfYo/gsERehTXGC1VZWX+9X4Dg==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - sisteransi@1.0.5: resolution: {integrity: sha512-bLGGlR1QxBcynn2d5YmDX4MGjlZvy2MRBDRNHLJ8VI6l6+9FUiyTFNJ0IveOSP0bcXgVDPRcfGqA0pjaqUpfVg==} slick@1.12.2: resolution: {integrity: sha512-4qdtOGcBjral6YIBCWJ0ljFSKNLz9KkhbWtuGvUyRowl1kxfuE1x/Z/aJcaiilpb3do9bl5K7/1h9XC5wWpY/A==} - smart-buffer@4.2.0: - resolution: {integrity: sha512-94hK0Hh8rPqQl2xXc3HsaBoOXKV20MToPkcXvwbISWLEs+64sBq5kFgn2kJDHb1Pry9yrP0dxrCI9RRci7RXKg==} - engines: {node: '>= 6.0.0', npm: '>= 3.0.0'} - smol-toml@1.6.1: resolution: {integrity: sha512-dWUG8F5sIIARXih1DTaQAX4SsiTXhInKf1buxdY9DIg4ZYPZK5nGM1VRIYmEbDbsHt7USo99xSLFu5Q1IqTmsg==} engines: {node: '>= 18'} - socks-proxy-agent@10.1.0: - resolution: {integrity: sha512-WlMj/67cEJ6MDI1OcsnjuYKDNDoyPCCYZ249kuuXPiMDw9F8PXkVaQ7YWu3siTydfQ/4BEZcvGzu+aYvz7dDCQ==} - engines: {node: '>= 20'} - - socks@2.8.9: - resolution: {integrity: sha512-LJhUYUvItdQ0LkJTmPeaEObWXAqFyfmP85x0tch/ez9cahmhlBBLbIqDFnvBnUJGagb0JbIQrkBs1wJ+yRYpEw==} - engines: {node: '>= 10.0.0', npm: '>= 3.0.0'} - source-map-js@1.2.1: resolution: {integrity: sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==} engines: {node: '>=0.10.0'} @@ -6863,15 +6529,6 @@ packages: space-separated-tokens@2.0.2: resolution: {integrity: sha512-PEGlAwrG8yXGXRjW32fGbg66JAlOAwbObuqVoJpv/mRgoWDQfgH1wDPvtzWyUSNAXBGSk8h755YDbbcEy3SH2Q==} - spdx-exceptions@2.5.0: - resolution: {integrity: sha512-PiU42r+xO4UbUS1buo3LPJkjlO7430Xn5SVAhdpzzsPHsjbYVflnnFdATgabnLude+Cqu25p6N+g2lw/PFsa4w==} - - spdx-expression-parse@4.0.0: - resolution: {integrity: sha512-Clya5JIij/7C6bRR22+tnGXbc4VKlibKSVj2iHvVeX5iMW7s1SIQlqu699JkODJJIhh/pUu8L0/VLh8xflD+LQ==} - - spdx-license-ids@3.0.23: - resolution: {integrity: sha512-CWLcCCH7VLu13TgOH+r8p1O/Znwhqv/dbb6lqWy67G+pT1kHmeD/+V36AVb/vq8QMIQwVShJ6Ssl5FPh0fuSdw==} - speakingurl@14.0.1: resolution: {integrity: sha512-1POYv7uv2gXoyGFpBCmpDVSNV74IfsWlDW216UPjbWufNf+bSU6GdbDsxdcxtfwb4xlI3yxzOTKClUosxARYrQ==} engines: {node: '>=0.10.0'} @@ -6880,10 +6537,6 @@ packages: resolution: {integrity: sha512-i/VCLG1fvRc95pMHRqG4aQNscv+9aIsqA2oI7ZQS51sTdUcDHYX6cpT8/tqZ+enjs1tKVwbRBWgxut9SWn+f9g==} hasBin: true - ssri@14.0.0: - resolution: {integrity: sha512-jQxKI0yx0ZnTKrqjKkLDV2DXkBQn3k49JVmVqDGcDwKDtGDbImD/GXsq04KD0VVzCQQ9wZJYal3RwR1GzWTSow==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - stackback@0.0.2: resolution: {integrity: sha512-1XMJE5fQo1jGH6Y/7ebnwPOBEkIEnT4QF32d5R1+VXdXveM0IBMJt8zfaxX1P3QhVwrYe+576+jkANtSS2mBbw==} @@ -6944,10 +6597,6 @@ packages: tabbable@6.5.0: resolution: {integrity: sha512-wieBHXygIm7OyQOu5hQlkk62/WyCFYGlWg7L6/ZCUZwx0o398Zkn4pVmMyfYhfMG8kGrj/Krt8eIk6UKC6VzwA==} - tar@7.5.20: - resolution: {integrity: sha512-9FcyK4PA6+WbzlTM9WhQm6vB5W7cP7dUiPsv1g7YDwEQnQ1CGpK3MGlKk/ITVWMk05kHZuBhmVhiv8LZoy/PFQ==} - engines: {node: '>=18'} - tinybench@2.9.0: resolution: {integrity: sha512-0+DUvqWMValLmha6lr4kD8iAMK1HzV0/aKnCtWb9v9641TnP/MFb7Pc2bxoxQjTXAErryXVgUOfv2YqNllqGeg==} @@ -7058,10 +6707,6 @@ packages: engines: {node: '>=18.0.0'} hasBin: true - tuf-js@6.0.0: - resolution: {integrity: sha512-zlJVOIO68hmgo1//X4ENEcTGfuOTAtDPi8PsTsG+FyxD85E/ww1ZnwBbWo/yCEExGpI+Kilg7Z3qCdHX2BoJTQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - type-check@0.4.0: resolution: {integrity: sha512-XleUoc9uwGXqjWwXaUTZAmzMcFZ5858QA2vvx1Ur5xIcixXIP+8LnFDgRplU30us6teqdlskFfu+ae4K79Ooew==} engines: {node: '>= 0.8.0'} @@ -7107,10 +6752,6 @@ packages: resolution: {integrity: sha512-cRZYrTDwWznlnRiPjggAGxZXanty6M8RV1ff8Wm4LWXBp7/IG8v5DnOm74DtUBp9OONpK75YlPnIjQqX0dBDtA==} engines: {node: '>=20.18.1'} - undici@8.7.0: - resolution: {integrity: sha512-N7iQtfyLhIMOFgQubvmLV26svHpO0bqKnAiWotTQCVKCmWrcGbBotPuW1x+xwYZ2VHdSTVUfPQQnlEt1/LouTQ==} - engines: {node: '>=22.19.0'} - unist-util-is@6.0.1: resolution: {integrity: sha512-LsiILbtBETkDz8I9p1dQ0uyRUWuaQzd/cuEeS1hoRSyW5E5XGmTzlwY1OrNzzakGowI9Dr/I8HVaw4hTtnxy8g==} @@ -7144,10 +6785,6 @@ packages: resolution: {integrity: sha512-jOWVmzVceKlVVdwjNSenT4PbGghU0SBIizAev8ofZVgivk/TVHXSbNL8LP6M3spZvkR9/QolkyJavGSX5Cs0UA==} engines: {node: '>=10'} - validate-npm-package-name@8.0.0: - resolution: {integrity: sha512-SCv6OOV6Xj2/3cXy3dGmADluJTNcL3o7hZAglNPTe+WYuEuvxgJzxPrSDLZhF+CwyQOubqgecjMmTJGMVLWjYQ==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - vary@1.1.2: resolution: {integrity: sha512-BNGbWLfd0eUPabhkXUVm0j8uuvREyTh5ovRa/dyow/BqAbZJyC+5fU+IzQOzmAKzYqYRAISoRhdQr3eIZ/PXqg==} engines: {node: '>= 0.8'} @@ -7337,11 +6974,6 @@ packages: engines: {node: '>= 8'} hasBin: true - which@7.0.0: - resolution: {integrity: sha512-RancgH2dmbLdHl6LRhEqvklWMgl/Hdnun0Y90KhBOLkMefg8Qa7/Zel8Sm+8HEcP6DEjzsWzpkuBQEZok58isA==} - engines: {node: ^22.22.2 || ^24.15.0 || >=26.0.0} - hasBin: true - why-is-node-running@2.3.0: resolution: {integrity: sha512-hUrmaWBdVDcxvYqnyh09zunKzROWjbZTiNy8dBEjkS7ehEDQibXJ7XvlmtbwuTclUiIyN+CyXQD4Vmko8fNm8w==} engines: {node: '>=8'} @@ -7391,13 +7023,6 @@ packages: xmlchars@2.2.0: resolution: {integrity: sha512-JZnDKK8B0RCDw84FNdDAIpZK+JuJw+s7Lz8nksI7SIuU3UXJJslUthsi+uWBUYOwPFwW7W7PRLRfUKpxjtjFCw==} - yallist@4.0.0: - resolution: {integrity: sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==} - - yallist@5.0.0: - resolution: {integrity: sha512-YgvUTfwqyc7UXVMrB+SImsVYSmTS8X/tSrtdNZMImM+n7+QTriRXyXim0mBrTXNeqzVF0KWGgHPeiyViFFrNDw==} - engines: {node: '>=18'} - yaml@2.9.0: resolution: {integrity: sha512-2AvhNX3mb8zd6Zy7INTtSpl1F15HW6Wnqj0srWlkKLcpYl/gMIMJiyuGq2KeI2YFxUPjdlB+3Lc10seMLtL4cA==} engines: {node: '>= 14.6'} @@ -7835,10 +7460,6 @@ snapshots: '@bcoe/v8-coverage@1.0.2': {} - '@bluwy/giget-core@0.1.7': - dependencies: - modern-tar: 0.7.6 - '@braintree/sanitize-url@7.1.2': {} '@bramus/specificity@2.4.2': @@ -8166,8 +7787,6 @@ snapshots: '@exodus/bytes@1.15.1': {} - '@gar/promise-retry@1.0.3': {} - '@google/genai@1.52.0(@modelcontextprotocol/sdk@1.29.0(zod@4.4.3))': dependencies: google-auth-library: 10.7.0 @@ -8222,10 +7841,6 @@ snapshots: wrap-ansi: 8.1.0 wrap-ansi-cjs: wrap-ansi@7.0.0 - '@isaacs/fs-minipass@4.0.1': - dependencies: - minipass: 7.1.3 - '@jridgewell/gen-mapping@0.3.13': dependencies: '@jridgewell/sourcemap-codec': 1.5.5 @@ -8313,63 +7928,6 @@ snapshots: '@nodable/entities@2.2.0': {} - '@npmcli/agent@5.0.2': - dependencies: - agent-base: 9.0.0 - http-proxy-agent: 9.1.0 - https-proxy-agent: 9.1.0 - lru-cache: 11.5.1 - socks-proxy-agent: 10.1.0 - transitivePeerDependencies: - - kerberos - - supports-color - - '@npmcli/fs@6.0.0': - dependencies: - semver: 7.8.4 - - '@npmcli/git@8.0.0': - dependencies: - '@gar/promise-retry': 1.0.3 - '@npmcli/promise-spawn': 10.0.0 - ini: 7.0.0 - lru-cache: 11.5.1 - npm-pick-manifest: 12.0.0 - proc-log: 7.0.0 - semver: 7.8.4 - which: 7.0.0 - - '@npmcli/installed-package-contents@5.0.0': - dependencies: - npm-bundled: 6.0.0 - npm-normalize-package-bin: 6.0.0 - - '@npmcli/node-gyp@6.0.0': {} - - '@npmcli/package-json@8.0.0': - dependencies: - '@npmcli/git': 8.0.0 - glob: 13.0.6 - hosted-git-info: 10.1.1 - json-parse-even-better-errors: 6.0.0 - proc-log: 7.0.0 - semver: 7.8.4 - spdx-expression-parse: 4.0.0 - - '@npmcli/promise-spawn@10.0.0': - dependencies: - which: 7.0.0 - - '@npmcli/redact@5.0.0': {} - - '@npmcli/run-script@11.0.0': - dependencies: - '@npmcli/node-gyp': 6.0.0 - '@npmcli/package-json': 8.0.0 - '@npmcli/promise-spawn': 10.0.0 - node-gyp: 13.0.1 - proc-log: 7.0.0 - '@oxc-parser/binding-android-arm-eabi@0.133.0': optional: true @@ -8743,39 +8301,6 @@ snapshots: '@shikijs/vscode-textmate@10.0.2': {} - '@sigstore/bundle@5.0.0': - dependencies: - '@sigstore/protobuf-specs': 0.5.1 - - '@sigstore/core@4.0.1': {} - - '@sigstore/protobuf-specs@0.5.1': {} - - '@sigstore/sign@5.0.0': - dependencies: - '@gar/promise-retry': 1.0.3 - '@sigstore/bundle': 5.0.0 - '@sigstore/core': 4.0.1 - '@sigstore/protobuf-specs': 0.5.1 - make-fetch-happen: 16.0.1 - proc-log: 7.0.0 - transitivePeerDependencies: - - kerberos - - supports-color - - '@sigstore/tuf@5.0.0': - dependencies: - '@sigstore/protobuf-specs': 0.5.1 - tuf-js: 6.0.0 - transitivePeerDependencies: - - supports-color - - '@sigstore/verify@4.1.0': - dependencies: - '@sigstore/bundle': 5.0.0 - '@sigstore/core': 4.0.1 - '@sigstore/protobuf-specs': 0.5.1 - '@smithy/core@3.24.7': dependencies: '@aws-crypto/crc32': 5.2.0 @@ -8842,13 +8367,6 @@ snapshots: estraverse: 5.3.0 picomatch: 4.0.4 - '@tufjs/canonical-json@2.0.0': {} - - '@tufjs/models@5.0.0': - dependencies: - '@tufjs/canonical-json': 2.0.0 - minimatch: 10.2.5 - '@tybys/wasm-util@0.10.2': dependencies: tslib: 2.8.1 @@ -9022,11 +8540,6 @@ snapshots: '@types/ms@2.1.0': {} - '@types/node-fetch@2.6.13': - dependencies: - '@types/node': 22.20.0 - form-data: 4.0.6 - '@types/node@22.20.0': dependencies: undici-types: 6.21.0 @@ -9035,35 +8548,10 @@ snapshots: dependencies: undici-types: 7.24.6 - '@types/npm-package-arg@6.1.4': {} - - '@types/npm-registry-fetch@8.0.9': - dependencies: - '@types/node': 22.20.0 - '@types/node-fetch': 2.6.13 - '@types/npm-package-arg': 6.1.4 - '@types/npmlog': 7.0.0 - '@types/ssri': 7.1.5 - - '@types/npmlog@7.0.0': - dependencies: - '@types/node': 22.20.0 - - '@types/pacote@11.1.8': - dependencies: - '@types/node': 22.20.0 - '@types/npm-registry-fetch': 8.0.9 - '@types/npmlog': 7.0.0 - '@types/ssri': 7.1.5 - '@types/picomatch@3.0.2': {} '@types/retry@0.12.0': {} - '@types/ssri@7.1.5': - dependencies: - '@types/node': 22.20.0 - '@types/tough-cookie@4.0.5': {} '@types/trusted-types@2.0.7': @@ -9340,8 +8828,6 @@ snapshots: '@xmldom/xmldom@0.9.10': {} - abbrev@5.0.0: {} - accepts@2.0.0: dependencies: mime-types: 3.0.2 @@ -9355,8 +8841,6 @@ snapshots: agent-base@7.1.4: {} - agent-base@9.0.0: {} - ajv-formats@3.0.1(ajv@8.20.0): optionalDependencies: ajv: 8.20.0 @@ -9424,8 +8908,6 @@ snapshots: estree-walker: 3.0.3 js-tokens: 10.0.0 - asynckit@0.4.0: {} - balanced-match@1.0.2: {} balanced-match@4.0.4: {} @@ -9476,19 +8958,6 @@ snapshots: cac@7.0.0: {} - cacache@21.0.1: - dependencies: - '@npmcli/fs': 6.0.0 - fs-minipass: 3.0.3 - glob: 13.0.6 - lru-cache: 11.5.1 - minipass: 7.1.3 - minipass-collect: 2.0.1 - minipass-flush: 1.0.7 - minipass-pipeline: 1.2.4 - p-map: 7.0.5 - ssri: 14.0.0 - call-bind-apply-helpers@1.0.2: dependencies: es-errors: 1.3.0 @@ -9531,18 +9000,12 @@ snapshots: dependencies: readdirp: 4.1.2 - chownr@3.0.0: {} - color-convert@2.0.1: dependencies: color-name: 1.1.4 color-name@1.1.4: {} - combined-stream@1.0.8: - dependencies: - delayed-stream: 1.0.0 - comma-separated-tokens@2.0.3: {} commander@13.1.0: {} @@ -9848,8 +9311,6 @@ snapshots: dependencies: robust-predicates: 3.0.3 - delayed-stream@1.0.0: {} - depd@2.0.0: {} dequal@2.0.3: {} @@ -9924,8 +9385,6 @@ snapshots: entities@8.0.0: {} - env-paths@2.2.1: {} - es-define-property@1.0.1: {} es-errors@1.3.0: {} @@ -9936,13 +9395,6 @@ snapshots: dependencies: es-errors: 1.3.0 - es-set-tostringtag@2.1.0: - dependencies: - es-errors: 1.3.0 - get-intrinsic: 1.3.0 - has-tostringtag: 1.0.2 - hasown: 2.0.4 - es-toolkit@1.49.0: {} esbuild@0.21.5: @@ -10117,8 +9569,6 @@ snapshots: expect-type@1.3.0: {} - exponential-backoff@3.1.3: {} - express-rate-limit@8.5.2(express@5.2.1): dependencies: express: 5.2.1 @@ -10242,14 +9692,6 @@ snapshots: cross-spawn: 7.0.6 signal-exit: 4.1.0 - form-data@4.0.6: - dependencies: - asynckit: 0.4.0 - combined-stream: 1.0.8 - es-set-tostringtag: 2.1.0 - hasown: 2.0.4 - mime-types: 2.1.35 - formatly@0.3.0: dependencies: fd-package-json: 2.0.0 @@ -10262,10 +9704,6 @@ snapshots: fresh@2.0.0: {} - fs-minipass@3.0.3: - dependencies: - minipass: 7.1.3 - fsevents@2.3.3: optional: true @@ -10328,12 +9766,6 @@ snapshots: package-json-from-dist: 1.0.1 path-scurry: 1.11.1 - glob@13.0.6: - dependencies: - minimatch: 10.2.5 - minipass: 7.1.3 - path-scurry: 2.0.2 - globals@17.7.0: {} globrex@0.1.2: {} @@ -10353,8 +9785,6 @@ snapshots: gopd@1.2.0: {} - graceful-fs@4.2.11: {} - hachure-fill@0.5.2: {} handlebars@4.7.9: @@ -10370,10 +9800,6 @@ snapshots: has-symbols@1.1.0: {} - has-tostringtag@1.0.2: - dependencies: - has-symbols: 1.1.0 - hasown@2.0.4: dependencies: function-bind: 1.1.2 @@ -10402,10 +9828,6 @@ snapshots: hookable@6.1.1: {} - hosted-git-info@10.1.1: - dependencies: - lru-cache: 11.5.1 - html-encoding-sniffer@6.0.0: dependencies: '@exodus/bytes': 1.15.1 @@ -10430,8 +9852,6 @@ snapshots: domutils: 2.8.0 entities: 2.2.0 - http-cache-semantics@4.2.0: {} - http-errors@2.0.1: dependencies: depd: 2.0.0 @@ -10447,15 +9867,6 @@ snapshots: transitivePeerDependencies: - supports-color - http-proxy-agent@9.1.0: - dependencies: - agent-base: 9.0.0 - debug: 4.4.3 - proxy-agent-negotiate: 1.1.0 - transitivePeerDependencies: - - kerberos - - supports-color - https-proxy-agent@7.0.6: dependencies: agent-base: 7.1.4 @@ -10463,15 +9874,6 @@ snapshots: transitivePeerDependencies: - supports-color - https-proxy-agent@9.1.0: - dependencies: - agent-base: 9.0.0 - debug: 4.4.3 - proxy-agent-negotiate: 1.1.0 - transitivePeerDependencies: - - kerberos - - supports-color - iconv-lite@0.6.3: dependencies: safer-buffer: 2.1.2 @@ -10480,10 +9882,6 @@ snapshots: dependencies: safer-buffer: 2.1.2 - ignore-walk@9.0.0: - dependencies: - minimatch: 10.2.5 - ignore@5.3.2: {} ignore@7.0.5: {} @@ -10498,8 +9896,6 @@ snapshots: inherits@2.0.4: {} - ini@7.0.0: {} - internmap@1.0.1: {} internmap@2.0.3: {} @@ -10526,8 +9922,6 @@ snapshots: isexe@2.0.0: {} - isexe@4.0.0: {} - istanbul-lib-coverage@3.2.2: {} istanbul-lib-report@3.0.1: @@ -10620,8 +10014,6 @@ snapshots: json-buffer@3.0.1: {} - json-parse-even-better-errors@6.0.0: {} - json-schema-to-ts@3.1.1: dependencies: '@babel/runtime': 7.29.7 @@ -10637,8 +10029,6 @@ snapshots: jsonc-parser@3.3.1: {} - jsonparse@1.3.1: {} - jsx-ast-utils-x@0.1.0: {} jszip@3.10.1: @@ -10830,24 +10220,6 @@ snapshots: dependencies: semver: 7.8.4 - make-fetch-happen@16.0.1: - dependencies: - '@gar/promise-retry': 1.0.3 - '@npmcli/agent': 5.0.2 - '@npmcli/redact': 5.0.0 - cacache: 21.0.1 - http-cache-semantics: 4.2.0 - minipass: 7.1.3 - minipass-fetch: 6.0.0 - minipass-flush: 1.0.7 - minipass-pipeline: 1.2.4 - negotiator: 1.0.0 - proc-log: 7.0.0 - ssri: 14.0.0 - transitivePeerDependencies: - - kerberos - - supports-color - mark.js@8.11.1: {} markdown-it-mathjax3@4.3.2: @@ -11209,14 +10581,8 @@ snapshots: transitivePeerDependencies: - supports-color - mime-db@1.52.0: {} - mime-db@1.54.0: {} - mime-types@2.1.35: - dependencies: - mime-db: 1.52.0 - mime-types@3.0.2: dependencies: mime-db: 1.54.0 @@ -11233,48 +10599,14 @@ snapshots: minimist@1.2.8: {} - minipass-collect@2.0.1: - dependencies: - minipass: 7.1.3 - - minipass-fetch@6.0.0: - dependencies: - minipass: 7.1.3 - minipass-sized: 2.0.0 - minizlib: 3.1.0 - optionalDependencies: - iconv-lite: 0.7.3 - - minipass-flush@1.0.7: - dependencies: - minipass: 3.3.6 - - minipass-pipeline@1.2.4: - dependencies: - minipass: 3.3.6 - - minipass-sized@2.0.0: - dependencies: - minipass: 7.1.3 - - minipass@3.3.6: - dependencies: - yallist: 4.0.0 - minipass@7.1.3: {} minisearch@7.2.0: {} - minizlib@3.1.0: - dependencies: - minipass: 7.1.3 - mitt@3.0.1: {} mj-context-menu@0.6.1: {} - modern-tar@0.7.6: {} - mri@1.2.0: {} ms@2.1.3: {} @@ -11359,67 +10691,6 @@ snapshots: fetch-blob: 3.2.0 formdata-polyfill: 4.0.10 - node-gyp@13.0.1: - dependencies: - env-paths: 2.2.1 - exponential-backoff: 3.1.3 - graceful-fs: 4.2.11 - nopt: 10.0.1 - proc-log: 7.0.0 - semver: 7.8.4 - tar: 7.5.20 - tinyglobby: 0.2.17 - undici: 8.7.0 - which: 7.0.0 - - nopt@10.0.1: - dependencies: - abbrev: 5.0.0 - - npm-bundled@6.0.0: - dependencies: - npm-normalize-package-bin: 6.0.0 - - npm-install-checks@9.0.0: - dependencies: - semver: 7.8.4 - - npm-normalize-package-bin@6.0.0: {} - - npm-package-arg@14.0.0: - dependencies: - hosted-git-info: 10.1.1 - proc-log: 7.0.0 - semver: 7.8.4 - validate-npm-package-name: 8.0.0 - - npm-packlist@11.3.0: - dependencies: - glob: 13.0.6 - ignore-walk: 9.0.0 - proc-log: 7.0.0 - - npm-pick-manifest@12.0.0: - dependencies: - npm-install-checks: 9.0.0 - npm-normalize-package-bin: 6.0.0 - npm-package-arg: 14.0.0 - semver: 7.8.4 - - npm-registry-fetch@20.0.1: - dependencies: - '@npmcli/redact': 5.0.0 - jsonparse: 1.3.1 - make-fetch-happen: 16.0.1 - minipass: 7.1.3 - minipass-fetch: 6.0.0 - minizlib: 3.1.0 - npm-package-arg: 14.0.0 - proc-log: 7.0.0 - transitivePeerDependencies: - - kerberos - - supports-color - nth-check@2.1.1: dependencies: boolbase: 1.0.0 @@ -11513,8 +10784,6 @@ snapshots: dependencies: p-limit: 3.1.0 - p-map@7.0.5: {} - p-retry@4.6.2: dependencies: '@types/retry': 0.12.0 @@ -11524,29 +10793,6 @@ snapshots: package-manager-detector@1.6.0: {} - pacote@22.0.0: - dependencies: - '@gar/promise-retry': 1.0.3 - '@npmcli/git': 8.0.0 - '@npmcli/installed-package-contents': 5.0.0 - '@npmcli/package-json': 8.0.0 - '@npmcli/promise-spawn': 10.0.0 - '@npmcli/run-script': 11.0.0 - cacache: 21.0.1 - fs-minipass: 3.0.3 - minipass: 7.1.3 - npm-package-arg: 14.0.0 - npm-packlist: 11.3.0 - npm-pick-manifest: 12.0.0 - npm-registry-fetch: 20.0.1 - proc-log: 7.0.0 - sigstore: 5.0.0 - ssri: 14.0.0 - tar: 7.5.20 - transitivePeerDependencies: - - kerberos - - supports-color - pako@1.0.11: {} parse5-htmlparser2-tree-adapter@6.0.1: @@ -11576,11 +10822,6 @@ snapshots: lru-cache: 10.4.3 minipass: 7.1.3 - path-scurry@2.0.2: - dependencies: - lru-cache: 11.5.1 - minipass: 7.1.3 - path-to-regexp@8.4.2: {} pathe@2.0.3: {} @@ -11610,8 +10851,6 @@ snapshots: prelude-ls@1.2.1: {} - proc-log@7.0.0: {} - process-nextick-args@2.0.1: {} property-information@7.2.0: {} @@ -11635,8 +10874,6 @@ snapshots: forwarded: 0.2.0 ipaddr.js: 1.9.1 - proxy-agent-negotiate@1.1.0: {} - publint@0.3.21: dependencies: '@publint/pack': 0.1.4 @@ -11920,54 +11157,18 @@ snapshots: signal-exit@4.1.0: {} - sigstore@5.0.0: - dependencies: - '@sigstore/bundle': 5.0.0 - '@sigstore/core': 4.0.1 - '@sigstore/protobuf-specs': 0.5.1 - '@sigstore/sign': 5.0.0 - '@sigstore/tuf': 5.0.0 - '@sigstore/verify': 4.1.0 - transitivePeerDependencies: - - kerberos - - supports-color - sisteransi@1.0.5: {} slick@1.12.2: {} - smart-buffer@4.2.0: {} - smol-toml@1.6.1: {} - socks-proxy-agent@10.1.0: - dependencies: - agent-base: 9.0.0 - debug: 4.4.3 - socks: 2.8.9 - transitivePeerDependencies: - - supports-color - - socks@2.8.9: - dependencies: - ip-address: 10.2.0 - smart-buffer: 4.2.0 - source-map-js@1.2.1: {} source-map@0.6.1: {} space-separated-tokens@2.0.2: {} - spdx-exceptions@2.5.0: {} - - spdx-expression-parse@4.0.0: - dependencies: - spdx-exceptions: 2.5.0 - spdx-license-ids: 3.0.23 - - spdx-license-ids@3.0.23: {} - speakingurl@14.0.1: {} speech-rule-engine@4.1.4: @@ -11976,10 +11177,6 @@ snapshots: commander: 13.1.0 wicked-good-xpath: 1.3.0 - ssri@14.0.0: - dependencies: - minipass: 7.1.3 - stackback@0.0.2: {} statuses@2.0.2: {} @@ -12037,14 +11234,6 @@ snapshots: tabbable@6.5.0: {} - tar@7.5.20: - dependencies: - '@isaacs/fs-minipass': 4.0.1 - chownr: 3.0.0 - minipass: 7.1.3 - minizlib: 3.1.0 - yallist: 5.0.0 - tinybench@2.9.0: {} tinyexec@1.2.4: {} @@ -12125,14 +11314,6 @@ snapshots: optionalDependencies: fsevents: 2.3.3 - tuf-js@6.0.0: - dependencies: - '@gar/promise-retry': 1.0.3 - '@tufjs/models': 5.0.0 - debug: 4.4.3 - transitivePeerDependencies: - - supports-color - type-check@0.4.0: dependencies: prelude-ls: 1.2.1 @@ -12174,8 +11355,6 @@ snapshots: undici@7.28.0: {} - undici@8.7.0: {} - unist-util-is@6.0.1: dependencies: '@types/unist': 3.0.3 @@ -12211,8 +11390,6 @@ snapshots: valid-data-url@3.0.1: {} - validate-npm-package-name@8.0.0: {} - vary@1.1.2: {} vfile-message@4.0.3: @@ -12436,10 +11613,6 @@ snapshots: dependencies: isexe: 2.0.0 - which@7.0.0: - dependencies: - isexe: 4.0.0 - why-is-node-running@2.3.0: dependencies: siginfo: 2.0.0 @@ -12473,10 +11646,6 @@ snapshots: xmlchars@2.2.0: {} - yallist@4.0.0: {} - - yallist@5.0.0: {} - yaml@2.9.0: {} yocto-queue@0.1.0: {} diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 004338fa2d..125b06c28c 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -52,7 +52,6 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/sandbox/sandbox-local': { kind: 'indirect', reason: 'The provider backend delegates model rendering to dsh-bash-sandbox and dsh-tool-bash.' }, 'packages/sdk/create-sdk': { kind: 'indirect', reason: 'The initializer only writes project files; selected runtime plugins provide the generated project model surface.' }, 'packages/sdk/helper': { kind: 'none', reason: 'The project domain edits files and registers no live agent or model surface.' }, - 'packages/sdk/plugin-fetch': { kind: 'none', reason: 'The fetcher acquires plugin sources into a temp dir and registers no live agent or model surface.' }, 'packages/sdk/scripts': { kind: 'indirect', reason: 'The launcher delegates model context to the loaded project plugin tree.' }, 'packages/sdk/telemetry': { kind: 'none', reason: 'The launcher-side reporter sends developer-cycle telemetry and registers no live agent or model surface.' }, 'packages/session-query/session-query': { kind: 'none', reason: 'The trusted query service exposes cloned records only to callers and registers no model surface.' }, diff --git a/tsconfig.build.json b/tsconfig.build.json index 9359d7a531..386728bf3b 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -99,7 +99,6 @@ { "path": "./packages/sdk/helper" }, { "path": "./packages/sdk/scripts" }, { "path": "./packages/sdk/create-sdk" }, - { "path": "./packages/sdk/plugin-fetch" }, { "path": "./packages/sdk/telemetry" } ] } diff --git a/tsconfig.json b/tsconfig.json index 48c5187fdc..47d1067e88 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -110,7 +110,6 @@ { "path": "./packages/sdk/helper" }, { "path": "./packages/sdk/scripts" }, { "path": "./packages/sdk/create-sdk" }, - { "path": "./packages/sdk/plugin-fetch" }, { "path": "./packages/sdk/telemetry" } ] } From 16485392e48dc7fed028d948be6339e89dcc1d53 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 15:43:56 +0800 Subject: [PATCH 180/323] docs(sdk): retarget #2 to native npm/pnpm dependency + cordis mount --- docs/sdk-后续工作-设计.md | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) diff --git a/docs/sdk-后续工作-设计.md b/docs/sdk-后续工作-设计.md index a2096cf42f..d281052cee 100644 --- a/docs/sdk-后续工作-设计.md +++ b/docs/sdk-后续工作-设计.md @@ -10,7 +10,7 @@ | 块 | 做什么 | 核心对象 | 结论要点 | |---|---|---|---| | **#1 headless + skill** | create/config 非交互化，agent 端到端建项目 | `HeadlessPrompter` + `CreationDriver`(NDJSON) | 无 spec 文件、传结构化对象；薄 SKILL.md 入口；beyond-eve | -| **#2 建插件** | `dsh-sdk create ` 拉插件并接线 | `PluginSource` + `PluginFetcher`(giget/pacote) | 只解压不执行、锁版本、经 `ProjectEditSession` 显式接线 | +| **#2 建插件** | `dsh-sdk create ` 加依赖并挂载 | PM 原生 `add` + `ProjectEditSession` cordis 挂载 | npm/pnpm 原生依赖（`github:#sha` / `pkg@version`），不用 giget/pacote | | **#3 遥测** | 每个 `dsh-sdk` 命令上报 | `TelemetryReporter` / `ConsentResolver` / `SecretRedactor` | 发 cordis.yml+package.json 全文；不发 `.env`、疑似密钥脱敏；关闭 = cordis.yml 有明确 disabled 的遥测条目（甲）| | **#4 交互测试** | 覆盖 wizard 各分支、快照 cordis.yml | `WizardHarness` + clack mock 注入 | 注入流为主、真 PTY 仅 1–2 个可选 smoke | @@ -106,23 +106,17 @@ SDK 初版（`packages/sdk/*`）已经落地三个包： - **skill**：核心是 headless 内核；agent 传参直接建完，缺必答项就响亮失败让 agent 补答。附一层**薄 SKILL.md**（指向内核、教 agent 驱动），让"通过 skill 创建"字面落地。 - **比 eve 更进一步**：eve 把 headless 原语（`runHeadless` + 非阻塞 Prompter + NDJSON）造好了，却没接到它的 skill——它的 SKILL.md 只指向半交互 CLI，且 agent 跑 `eve init` 时只打印指引、打回给人。我们把 **skill → headless 内核接通**，才真正做到"headless 为 skill 服务"。 -### 4.2 `dsh-sdk create ` 建插件（#2） +### 4.2 `dsh-sdk create ` 建插件（#2，简单版） -**目标**：从 github repo 或 npm 包拉一个插件进现有项目并接线；安全第一。 +**目标**：把一个 github repo 或 npm 包当**依赖**加进现有项目并挂载；用包管理器原生能力，**不引 giget/pacote**。 -**设计（只解压不执行 + 锁版本 + 显式接线）**： +**设计（PM 原生依赖 + cordis 挂载）**： -- **`PluginSource`（判别联合）**：`GithubSource`（`owner/repo[/subdir]#ref`）| `NpmSource`（`pkg@version`）。由 spec 字符串解析而来。 -- **`PluginFetcher`（seam）**：把源抓进 temp 目录，**绝不执行被拉代码的生命周期脚本**。 - - `GigetFetcher`（github/git）：giget；`#ref` 先解析成 commit SHA 再下、记进 lock。 - - `PacoteFetcher`（npm）：pacote `extract`（只解包不跑 postinstall），带 `integrity` 校验。来源类型限定放在**上游 `resolvePluginSource`**（只产出 `name@version`）作为主保证，不依赖 pacote 的 `allowRegistry`（`@types/pacote` 无此选项，且 registry tarball extract 本就不跑脚本）。 -- **接线（显式可审）**： - 1. `package.json` 精确锁版本（npm：exact + integrity；github：`github:owner/repo#`）。 - 2. 经 `ProjectEditSession` 改 `cordis.yml` 挂插件——**给 diff、要确认**再写。 - 3. `install --ignore-scripts`（pnpm v10 默认亦拦依赖 build 脚本）。 - 4. 打印清单（dep spec + 锁的 ref/integrity + cordis.yml diff）。 -- **信任模型**：学 `npm create` 的手感，但把信任反过来——**confirm-before-run，而非 run-on-fetch**。 -- **repo 初始化模式**（从模板仓库整体建项目）同走 giget（优于 degit——degit 的 `degit.json` 会自动跑动作）；建远程新仓可用 `gh repo create --template`。注：eve 不支持 template-repo init，这是我们的自有取舍。 +- **来源**：npm（`pkg@version`）或 github（`github:owner/repo#ref`，推荐锁 commit SHA）。npm/pnpm/yarn 原生支持这两种依赖来源，自己解析包名、把 commit/integrity 钉进 lockfile。 +- **流程**：`dsh-sdk create ` → 确认（TTY guard 同 config）→ 用项目的包管理器 `add `（PM 解析名字 / 装依赖 / 写 lockfile）→ 读回新增依赖名 → 经 `ProjectEditSession` 挂一条 cordis 条目引用它 → commit。 +- **不落 `plugins/`**：外部插件是 node_modules 依赖，不是本地生成插件（后者才走 `LocalPluginBlueprint` + 文件生成）。 +- **构建张力（暂缓）**：源码型 github 插件装时要 `prepare` build（pnpm 10.26 默认禁、需 `allowBuilds` 放行）——"预编译-only vs 允许构建"的取舍留到以后；先做能跑的简单版，交给 PM 默认行为。 +- **弃用**：早期设计的 `PluginSource`/`GigetFetcher`/`PacoteFetcher`（抓 tarball 到 temp 再接线）已随 `dsh-plugin-fetch` 包一起撤掉——PM 原生依赖覆盖了它。 ### 4.3 遥测（#3） @@ -185,7 +179,7 @@ SDK 初版（`packages/sdk/*`）已经落地三个包： |---|---|---| | 地基 | dsh-helper, create-sdk, dsh-scripts | `HeadlessPromptPort`（实现已有 `PromptPort`）+ prefill 补全 + NDJSON + 命令注册/催表扩展点整理 | | #1 headless+skill | create-sdk, dsh-scripts, （新）skill 包 | 结构化 spec 入口 `--config-json`/`--config`、薄 SKILL.md | -| #2 建插件 | （新）fetcher 包, dsh-scripts, dsh-helper | `PluginSource`、`GigetFetcher`/`PacoteFetcher`、`dsh-sdk create ` 注册、经 `ProjectEditSession` 接线+diff、新依赖 giget/pacote | +| #2 建插件 | dsh-scripts, dsh-helper | `dsh-sdk create ` 命令、PM `add`、经 `ProjectEditSession` 挂 cordis 条目、无新依赖 | | #3 遥测 | （新）telemetry 包, dsh-scripts, dsh-helper | `TelemetryReporter`/`ConsentResolver`/`SecretRedactor`、launcher 接线、催表遥测 feature、内置 endpoint、全局 UUID | | #4 测试 | packages/support, （已可注入）create-sdk/dsh-scripts | `WizardHarness`、create/config 的 `test.each` cordis.yml 快照、可选 PTY smoke | From ca7533880e8c90ef7e812d426e82cc2838c5aeb1 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 16:01:48 +0800 Subject: [PATCH 181/323] =?UTF-8?q?feat(dsh-sdk):=20create=20=20?= =?UTF-8?q?=E2=80=94=20add=20external=20plugin=20as=20native=20PM=20depend?= =?UTF-8?q?ency=20+=20cordis=20mount?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit dsh-sdk create adds a github (github:owner/repo#ref) or npm (pkg@version) plugin as a package-manager-native dependency, then mounts the resolved dependency in cordis.yml through ProjectEditSession. Adds PackageManager.add(spec) and ProjectEditSession.addExternalPlugin(id, packageName). No giget/pacote. Per-file 100% coverage on the new/changed files. --- .../src/package-managers/package-manager.ts | 24 +++++ .../src/project/project-edit-session.ts | 17 ++++ packages/sdk/helper/tests/documents.spec.ts | 5 + packages/sdk/helper/tests/project.spec.ts | 22 +++++ packages/sdk/scripts/README.md | 1 + packages/sdk/scripts/src/args.ts | 6 +- packages/sdk/scripts/src/command.ts | 5 + packages/sdk/scripts/src/create-plugin.ts | 91 +++++++++++++++++++ packages/sdk/scripts/tests/scripts.spec.ts | 60 ++++++++++++ 9 files changed, 230 insertions(+), 1 deletion(-) create mode 100644 packages/sdk/scripts/src/create-plugin.ts diff --git a/packages/sdk/helper/src/package-managers/package-manager.ts b/packages/sdk/helper/src/package-managers/package-manager.ts index a6f2fdd103..6e6eda478a 100644 --- a/packages/sdk/helper/src/package-managers/package-manager.ts +++ b/packages/sdk/helper/src/package-managers/package-manager.ts @@ -148,6 +148,25 @@ export abstract class PackageManager { await this.runChecked(runner, this.buildCommand(), cwd, 'build') } + /** + * Build add-dependency command arguments for one already-normalized source spec. + * @param spec - a package-manager-native dependency source (`pkg@version` or `github:owner/repo#ref`). + * @returns arguments following the manager executable. + */ + addCommand(spec: string): readonly string[] { + return ['add', spec] + } + + /** + * Add one dependency from a native source spec and fail on non-zero or signalled exit. + * @param spec - a package-manager-native dependency source. + * @param cwd - project directory. + * @param runner - optional subprocess boundary. + */ + async add(spec: string, cwd: string, runner: CommandRunner = new NodeCommandRunner()): Promise { + await this.runChecked(runner, this.addCommand(spec), cwd, 'add') + } + private async runChecked(runner: CommandRunner, args: readonly string[], cwd: string, operation: string): Promise { const result = await runner.run(this.name, args, cwd) if (result.signal !== null) { @@ -184,6 +203,11 @@ export class NpmPackageManager extends PackageManager { override linkSpec(relativePath: string): string { return `file:${relativePath}` } + + /** npm adds a dependency through `install ` rather than an `add` verb. */ + override addCommand(spec: string): readonly string[] { + return ['install', spec] + } } /** pnpm workspace behavior. */ diff --git a/packages/sdk/helper/src/project/project-edit-session.ts b/packages/sdk/helper/src/project/project-edit-session.ts index 9b2c885ac5..0d0a1cb6dd 100644 --- a/packages/sdk/helper/src/project/project-edit-session.ts +++ b/packages/sdk/helper/src/project/project-edit-session.ts @@ -220,6 +220,23 @@ export class ProjectEditSession implements FeatureProjectView { this.addedPlugins.add(entry.id) } + /** + * Mount a Cordis entry for an external dependency the package manager has already + * added (github or npm), without generating files or re-adding the dependency. + * @param id - stable Cordis config entry id. + * @param packageName - the installed dependency's package name. + */ + addExternalPlugin(id: string, packageName: string): void { + this.assertOpen() + if (!this.manifest().npmDependency(packageName)) { + throw new Error(`external plugin dependency is not installed: ${packageName}`) + } + const cordis = this.cordis() + if (cordis.entry(id)) throw new Error(`Cordis config entry already exists: ${id}`) + cordis.addEntry({ id, name: packageName }) + this.addedPlugins.add(id) + } + /** Enable or disable one custom/manual Cordis config entry by stable id. */ setCustomPluginDisabled(id: string, disabled: boolean): void { this.assertOpen() diff --git a/packages/sdk/helper/tests/documents.spec.ts b/packages/sdk/helper/tests/documents.spec.ts index 1ba8b9bd68..3ce5eeccea 100644 --- a/packages/sdk/helper/tests/documents.spec.ts +++ b/packages/sdk/helper/tests/documents.spec.ts @@ -298,6 +298,11 @@ describe('package manager strategies', () => { await npm.install('/tmp', runner) await npm.build('/tmp', runner) expect(calls).toEqual([['npm', 'install'], ['npm', 'run', 'build']]) + await npm.add('some-pkg@1.0.0', '/tmp', runner) + const pnpm = createPackageManager('pnpm', '10.0.0') + await pnpm.add('github:o/r#sha', '/tmp', runner) + expect(calls).toContainEqual(['npm', 'install', 'some-pkg@1.0.0']) + expect(calls).toContainEqual(['pnpm', 'add', 'github:o/r#sha']) const failed: CommandRunner = { run: async () => ({ exitCode: 2, signal: null }) } await expect(npm.install('/tmp', failed)).rejects.toThrow('exited with code 2') const killed: CommandRunner = { run: async () => ({ exitCode: null, signal: 'SIGTERM' }) } diff --git a/packages/sdk/helper/tests/project.spec.ts b/packages/sdk/helper/tests/project.spec.ts index d55bb16be9..6a6268b554 100644 --- a/packages/sdk/helper/tests/project.spec.ts +++ b/packages/sdk/helper/tests/project.spec.ts @@ -690,6 +690,28 @@ describe('SdkProject and ProjectEditSession', () => { expect(committed.packageManifest().dependencies?.['@deepseek-ai/dsh-subagent']).toMatch(/^file:/) expect(createBuiltinRegistry(committed.profile).get(featureId('subagent')).inspect(committed).state).toBe('absent') }) + + it('mounts an external plugin dependency and rejects missing deps or duplicate entries', async () => { + const root = await mkdtemp(join(tmpdir(), 'dsh-external-plugin-')) + temporary.push(root) + const creation = request() + const project = SdkProject.create(root, creation) + const registry = createBuiltinRegistry(project.profile) + const edit = project.edit(registry) + for (const item of creation.features) edit.installFeature(registry.get(item.id), item) + await edit.commit() + const manifestPath = join(root, 'package.json') + const manifest = JSON.parse(await readFile(manifestPath, 'utf8')) as { dependencies?: Record } + manifest.dependencies = { ...manifest.dependencies, 'ext-plugin': 'github:o/r#sha' } + await writeFile(manifestPath, JSON.stringify(manifest, null, 2)) + const reopened = await SdkProject.open(root) + const edit2 = reopened.edit(createBuiltinRegistry(reopened.profile)) + edit2.addExternalPlugin('ext-plugin', 'ext-plugin') + expect(() => { edit2.addExternalPlugin('ext-plugin', 'ext-plugin') }).toThrow('already exists') + expect(() => { edit2.addExternalPlugin('missing', 'not-a-dep') }).toThrow('not installed') + const commit = await edit2.commit() + expect(commit.project.cordis.entry('ext-plugin')?.name).toBe('ext-plugin') + }) }) describe('extension points', () => { diff --git a/packages/sdk/scripts/README.md b/packages/sdk/scripts/README.md index e87c375a4f..39d706177e 100644 --- a/packages/sdk/scripts/README.md +++ b/packages/sdk/scripts/README.md @@ -8,6 +8,7 @@ The `dsh-sdk` launcher owns SDK project startup and configuration. | `dsh-sdk dev [target] [-- args…]` | Register TypeScript and local-workspace source resolution, then use the start path | | `dsh-sdk build [args…]` | Invoke the project's installed tsdown with the project arguments | | `dsh-sdk config` | Open one interactive edit session, review accumulated changes, commit once, and install once when NPM dependencies changed | +| `dsh-sdk create ` | Add an external Cordis plugin from a native package-manager source (`pkg@version` or `github:owner/repo#ref`): confirm, ` add `, then mount the resolved dependency in `cordis.yml`. No giget/pacote; the package manager resolves and pins the source (github deps build via their own `prepare` under the manager's policy) | `ProjectBuild(tsdownConfig)` and `PluginBuild(tsdownConfig)` are exported only from `@deepseek-ai/dsh-scripts/dev/tsdown-config`. Development and production read the same `cordis.yml`. diff --git a/packages/sdk/scripts/src/args.ts b/packages/sdk/scripts/src/args.ts index 1b91269592..4d1ce867de 100644 --- a/packages/sdk/scripts/src/args.ts +++ b/packages/sdk/scripts/src/args.ts @@ -8,12 +8,13 @@ import { parseArgs as parseNodeArgs } from 'node:util' import { Command } from 'commander' /** Commands implemented by the dsh-sdk launcher. */ -type DshSdkCommand = 'start' | 'dev' | 'build' | 'config' +type DshSdkCommand = 'start' | 'dev' | 'build' | 'config' | 'create' /** Parsed dsh-sdk invocation. */ export interface DshSdkArgs { command?: DshSdkCommand target?: string + source?: string forwarded: readonly string[] help: boolean } @@ -60,6 +61,9 @@ export function parseDshSdkArgs(argv: readonly string[]): DshSdkArgs { program.command('config').helpOption(false).action(() => { parsed = { command: 'config', forwarded: [], help: false } }) + program.command('create ').helpOption(false).action((source: string) => { + parsed = { command: 'create', source, forwarded: [], help: false } + }) program.parse([...launcherArgv], { from: 'user' }) /* v8 ignore next -- every registered Commander action above assigns parsed or Commander throws */ if (!parsed) throw new Error('dsh-sdk command did not resolve') diff --git a/packages/sdk/scripts/src/command.ts b/packages/sdk/scripts/src/command.ts index 9351cfa39c..5174ec5ded 100644 --- a/packages/sdk/scripts/src/command.ts +++ b/packages/sdk/scripts/src/command.ts @@ -7,6 +7,7 @@ import { parseDshSdkArgs } from './args.ts' import { runProjectBuild } from './build.ts' import { runConfigCommand, type ConfigCommandContext } from './config.ts' +import { runCreatePluginCommand } from './create-plugin.ts' import { runSDK } from './runtime.ts' import { DSH_SDK_TEMPLATES } from './templates/dsh-sdk-templates.ts' @@ -19,6 +20,7 @@ export interface DshSdkCommandContext extends ConfigCommandContext { run?: typeof runSDK build?: typeof runProjectBuild config?: typeof runConfigCommand + createPlugin?: typeof runCreatePluginCommand } /** Run one parsed dsh-sdk command and return its process exit code. */ @@ -40,6 +42,7 @@ export async function runDshSdkCommand( const run = context.run ?? runSDK const build = context.build ?? runProjectBuild const config = context.config ?? runConfigCommand + const createPlugin = context.createPlugin ?? runCreatePluginCommand switch (args.command) { case 'start': await run(args.target, { cwd: context.cwd, argv: args.forwarded }); break case 'dev': await run(args.target, { cwd: context.cwd, dev: true, argv: args.forwarded }); break @@ -49,6 +52,8 @@ export async function runDshSdkCommand( if (result.installError) return 1 break } + /* v8 ignore next -- Commander requires , so create never dispatches without it */ + case 'create': await createPlugin(args.source ?? '', context); break } return 0 } catch (error) { diff --git a/packages/sdk/scripts/src/create-plugin.ts b/packages/sdk/scripts/src/create-plugin.ts new file mode 100644 index 0000000000..f658451fde --- /dev/null +++ b/packages/sdk/scripts/src/create-plugin.ts @@ -0,0 +1,91 @@ +/** + * dsh-sdk create command: add an external Cordis plugin (github or npm) as a + * native package-manager dependency and mount it in cordis.yml. + * + * @module @deepseek-ai/dsh-scripts/create-plugin + */ + +import { readFile } from 'node:fs/promises' +import { join } from 'node:path' +import { + ClackPromptPort, + ConfirmQuestion, + SdkProject, + createBuiltinRegistry, + requireAnswer, + type PackageManager, + type ProjectCommitResult, + type PromptPort, +} from '@deepseek-ai/dsh-helper' + +/** Process and interaction slice required by dsh-sdk create. */ +export interface CreatePluginContext { + cwd: string + stdin: NodeJS.ReadStream + stdout: NodeJS.WriteStream + port?: PromptPort + add?: (manager: PackageManager, spec: string, cwd: string) => Promise +} + +/** Result of a create run; `undefined` when the confirmation was declined. */ +export type CreatePluginResult = ProjectCommitResult | undefined + +/** Derive a stable cordis entry id from a package name's last path segment. */ +function pluginId(packageName: string): string { + const base = packageName.startsWith('@') ? packageName.slice(packageName.indexOf('/') + 1) : packageName + const id = base.toLowerCase().replace(/[^a-z0-9]+/g, '-').replace(/^-|-$/g, '') + /* v8 ignore next -- a valid npm package name always yields a non-empty id */ + if (!id) throw new Error(`cannot derive a plugin id from package name: ${packageName}`) + return id +} + +/** Read the direct dependency names declared in a project's package.json. */ +async function dependencyNames(cwd: string): Promise> { + const manifest = JSON.parse(await readFile(join(cwd, 'package.json'), 'utf8')) as { + dependencies?: Record + } + /* v8 ignore next -- generated projects always declare a dependencies map */ + return new Set(Object.keys(manifest.dependencies ?? {})) +} + +/** + * Add one external plugin dependency to the current project and mount it. + * @param source - a package-manager-native source (`pkg@version` or `github:owner/repo#ref`). + * @param context - process, interaction, and dependency-add boundaries. + * @returns the commit result, or `undefined` when the confirmation was declined. + */ +export async function runCreatePluginCommand( + source: string, + context: CreatePluginContext, +): Promise { + const spec = source.trim() + if (!spec) throw new Error('dsh-sdk create requires a plugin source (pkg@version or github:owner/repo#ref)') + if (!context.port && (!context.stdin.isTTY || !context.stdout.isTTY)) { + throw new Error('dsh-sdk create requires an interactive TTY') + } + const project = await SdkProject.open(context.cwd) + /* v8 ignore next -- production TTY wiring is exercised by the built-bin smoke */ + const port = context.port ?? new ClackPromptPort(context.stdin, context.stdout) + const confirmed = requireAnswer(await new ConfirmQuestion({ + id: 'create.confirm', + message: `Add plugin '${spec}' as a dependency and mount it in cordis.yml?`, + initialValue: true, + }).resolve(port)) + if (!confirmed) return undefined + + const before = await dependencyNames(context.cwd) + /* v8 ignore next -- production package-manager wiring is exercised by the built-bin smoke */ + const add = context.add ?? ((manager, source, cwd) => manager.add(source, cwd)) + await add(project.profile.packageManager, spec, context.cwd) + const after = await dependencyNames(context.cwd) + const added = [...after].filter(name => !before.has(name)) + if (added.length === 0) throw new Error(`dsh-sdk create: '${spec}' added no new dependency`) + + const reopened = await SdkProject.open(context.cwd) + const registry = createBuiltinRegistry(reopened.profile) + const edit = reopened.edit(registry) + for (const packageName of added) edit.addExternalPlugin(pluginId(packageName), packageName) + const commit = await edit.commit() + context.stdout.write(`Mounted ${added.join(', ')} in cordis.yml.\n`) + return commit +} diff --git a/packages/sdk/scripts/tests/scripts.spec.ts b/packages/sdk/scripts/tests/scripts.spec.ts index 42c74f5631..faa025926e 100644 --- a/packages/sdk/scripts/tests/scripts.spec.ts +++ b/packages/sdk/scripts/tests/scripts.spec.ts @@ -31,6 +31,7 @@ import { PluginBuild, ProjectBuild, runProjectBuild } from '../src/build.ts' import { runDshSdkCommand, type DshSdkCommandContext } from '../src/command.ts' import { runConfigCommand } from '../src/config.ts' import { ConfigWorkflow, type ConfigPlan } from '../src/config/config-workflow.ts' +import { runCreatePluginCommand } from '../src/create-plugin.ts' import { initialize, resolve as resolveLocalPlugin } from '../src/local-plugin-loader-hooks.ts' const temporary: string[] = [] @@ -559,3 +560,62 @@ describe('ConfigWorkflow', () => { expect(output.read()).toContain('Disable feature: ask-user') }) }) + +describe('dsh-sdk create', () => { + const writeDependency = (name: string) => async (_m: unknown, spec: string, cwd: string): Promise => { + const path = join(cwd, 'package.json') + const manifest = JSON.parse(await readFile(path, 'utf8')) as { dependencies?: Record } + manifest.dependencies = { ...manifest.dependencies, [name]: spec } + await writeFile(path, JSON.stringify(manifest, null, 2)) + } + + it('adds a dependency and mounts it after confirmation', async () => { + const project = await committedProject() + const context = { ...commandContext(project.root), port: new QueuePort([true]), add: writeDependency('my-ext-plugin') } + const result = await runCreatePluginCommand('github:o/r#sha', context) + expect(result?.project.cordis.entry('my-ext-plugin')?.name).toBe('my-ext-plugin') + expect(context.readStdout()).toContain('Mounted my-ext-plugin') + }) + + it('derives the cordis id from a scoped package name', async () => { + const project = await committedProject() + const context = { ...commandContext(project.root), port: new QueuePort([true]), add: writeDependency('@acme/cool-plugin') } + const result = await runCreatePluginCommand('@acme/cool-plugin@1.0.0', context) + expect(result?.project.cordis.entry('cool-plugin')?.name).toBe('@acme/cool-plugin') + }) + + it('returns undefined and adds nothing when declined', async () => { + const project = await committedProject() + let added = false + const context = { + ...commandContext(project.root), + port: new QueuePort([false]), + add: async () => { added = true }, + } + await expect(runCreatePluginCommand('pkg@1.0.0', context)).resolves.toBeUndefined() + expect(added).toBe(false) + }) + + it('rejects an empty source, a non-TTY session, and a no-op add', async () => { + const project = await committedProject() + await expect(runCreatePluginCommand(' ', { ...commandContext(project.root), port: new QueuePort([]) })) + .rejects.toThrow('requires a plugin source') + const noTty = commandContext(project.root) + noTty.stdin.isTTY = false + noTty.stdout.isTTY = false + await expect(runCreatePluginCommand('pkg@1.0.0', noTty)).rejects.toThrow('interactive TTY') + const noOutTty = commandContext(project.root) + noOutTty.stdout.isTTY = false + await expect(runCreatePluginCommand('pkg@1.0.0', noOutTty)).rejects.toThrow('interactive TTY') + await expect(runCreatePluginCommand('pkg@1.0.0', { + ...commandContext(project.root), port: new QueuePort([true]), add: async () => {}, + })).rejects.toThrow('added no new dependency') + }) + + it('dispatches create through the launcher', async () => { + const project = await committedProject() + const context = commandContext(project.root) + context.createPlugin = async () => undefined + await expect(runDshSdkCommand(['create', 'pkg@1.0.0'], context)).resolves.toBe(0) + }) +}) From 560ce3b539bc24ea994cfbe9476c21ecd834162e Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Fri, 17 Jul 2026 20:28:31 +0800 Subject: [PATCH 182/323] feat(dsh-sdk): launcher telemetry reporting around every command Wrap runDshSdkCommand so each command times itself and, in a finally block, resolves consent (option A) and sends one best-effort, fire-and-forget telemetry event (redacted cordis.yml + package.json content; never reads .env). Never affects the command's exit code. Adds dsh-scripts -> dsh-telemetry dependency. Default-on via absent consent entry; opt-out by a disabled telemetry entry. The config/create wizard opt-out toggle is deferred (see design doc). --- docs/sdk-后续工作-设计.md | 3 ++ packages/sdk/scripts/package.json | 1 + packages/sdk/scripts/src/command.ts | 15 +++++- packages/sdk/scripts/src/telemetry.ts | 63 ++++++++++++++++++++++ packages/sdk/scripts/tests/scripts.spec.ts | 47 ++++++++++++++++ packages/sdk/scripts/tsconfig.json | 1 + pnpm-lock.yaml | 3 ++ 7 files changed, 132 insertions(+), 1 deletion(-) create mode 100644 packages/sdk/scripts/src/telemetry.ts diff --git a/docs/sdk-后续工作-设计.md b/docs/sdk-后续工作-设计.md index d281052cee..1395ece5e0 100644 --- a/docs/sdk-后续工作-设计.md +++ b/docs/sdk-后续工作-设计.md @@ -133,6 +133,9 @@ SDK 初版（`packages/sdk/*`）已经落地三个包： - **endpoint**：内置在代码里。 - **consent 承载**：遥测作为 `create` 时默认打开的 feature 写进 cordis.yml（对用户可见、随项目）。 +> **接线现状（读码修正）**：launcher 上报已接通——`runDshSdkCommand` 计时包住每条命令，`finally` 里 resolve consent（甲）→ 建 redacted payload（cordis.yml+package.json 全文、不读 .env）→ fire-and-forget 上报 + flush，best-effort 永不影响命令结果。**默认开**：无遥测条目 → 甲 → 上报。**opt-out 现状**：在 cordis.yml 手动加一条 `disabled` 的 `@deepseek-ai/dsh-telemetry` 条目即关（`ConsentResolver` 读到 disabled → 不报；disabled 条目 cordis 不加载，故不会因"它不是运行时插件"而 boot 失败）。 +> **暂缓（催表 opt-out 开关）**：把"关遥测"做成 config/create 向导里的勾选项还没做。关键约束：`@deepseek-ai/dsh-telemetry` 是 **launcher 库、不是 cordis 运行时插件**，所以 consent 条目只能以 **disabled 形态**存在（enabled=无条目=甲默认报；要关才写 disabled 条目），不能像普通 feature 那样挂一个 enabled 的可 boot 条目。向导化这个"只在关闭时才出现条目"的特殊语义留作后续。 + **在案取舍**：发全文会把第三方（含私有 scoped）包名、cordis 配置值（base-url/路径）暴露给 endpoint 持有方；主流工具都不发这些（Turbo 排除包名、Angular 禁模块名）。ccyu 作为本 SDK 维护者接受此暴露——目的即掌握开发者用了哪些 plugin/依赖/配置。 ### 4.4 交互测试（#4） diff --git a/packages/sdk/scripts/package.json b/packages/sdk/scripts/package.json index ba441a528c..6fdbcbc3da 100644 --- a/packages/sdk/scripts/package.json +++ b/packages/sdk/scripts/package.json @@ -32,6 +32,7 @@ "license": "BSD-3-Clause", "dependencies": { "@deepseek-ai/dsh-helper": "workspace:^", + "@deepseek-ai/dsh-telemetry": "workspace:^", "commander": "^15.0.0", "node-addon-require-builtin": "^0.1.0" }, diff --git a/packages/sdk/scripts/src/command.ts b/packages/sdk/scripts/src/command.ts index 5174ec5ded..ebf9b06846 100644 --- a/packages/sdk/scripts/src/command.ts +++ b/packages/sdk/scripts/src/command.ts @@ -9,6 +9,7 @@ import { runProjectBuild } from './build.ts' import { runConfigCommand, type ConfigCommandContext } from './config.ts' import { runCreatePluginCommand } from './create-plugin.ts' import { runSDK } from './runtime.ts' +import { reportCommandTelemetry, type CommandTelemetryEvent } from './telemetry.ts' import { DSH_SDK_TEMPLATES } from './templates/dsh-sdk-templates.ts' /** Injectable process and command boundaries used by the dsh-sdk bin. */ @@ -21,6 +22,7 @@ export interface DshSdkCommandContext extends ConfigCommandContext { build?: typeof runProjectBuild config?: typeof runConfigCommand createPlugin?: typeof runCreatePluginCommand + telemetry?: (event: CommandTelemetryEvent) => Promise } /** Run one parsed dsh-sdk command and return its process exit code. */ @@ -33,12 +35,16 @@ export async function runDshSdkCommand( stderr: process.stderr, }, ): Promise { + const startedAt = Date.now() + let command: string | undefined + let success = true try { const args = parseDshSdkArgs(argv) if (args.help || !args.command) { context.stdout.write(DSH_SDK_TEMPLATES.usage.render({})) return 0 } + command = args.command const run = context.run ?? runSDK const build = context.build ?? runProjectBuild const config = context.config ?? runConfigCommand @@ -49,7 +55,7 @@ export async function runDshSdkCommand( case 'build': await build(args.forwarded, context.cwd); break case 'config': { const result = await config(context) - if (result.installError) return 1 + if (result.installError) { success = false; return 1 } break } /* v8 ignore next -- Commander requires , so create never dispatches without it */ @@ -57,7 +63,14 @@ export async function runDshSdkCommand( } return 0 } catch (error) { + success = false context.stderr.write(`dsh-sdk: ${error instanceof Error ? error.message : String(error)}\n`) return 1 + } finally { + if (command !== undefined) { + /* v8 ignore next -- production telemetry wiring is exercised by the built-bin smoke */ + const telemetry = context.telemetry ?? reportCommandTelemetry + await telemetry({ command, cwd: context.cwd, durationMs: Date.now() - startedAt, success }) + } } } diff --git a/packages/sdk/scripts/src/telemetry.ts b/packages/sdk/scripts/src/telemetry.ts new file mode 100644 index 0000000000..1ef74fdbb7 --- /dev/null +++ b/packages/sdk/scripts/src/telemetry.ts @@ -0,0 +1,63 @@ +/** + * Launcher-side telemetry wiring: resolve consent and send one fire-and-forget + * event around each dsh-sdk command. Best-effort — never affects the command's + * outcome or exit code. + * + * @module @deepseek-ai/dsh-scripts/telemetry + */ + +import { + ConsentResolver, + TelemetryReporter, + buildTelemetryPayload, + type ConsentDecision, +} from '@deepseek-ai/dsh-telemetry' + +/** One command's telemetry lifecycle facts. */ +export interface CommandTelemetryEvent { + /** The dsh-sdk command that ran. */ + command: string + /** Project directory whose consent, `cordis.yml`, and `package.json` are read. */ + cwd: string + /** Wall-clock duration in milliseconds. */ + durationMs: number + /** Whether the command completed without error. */ + success: boolean +} + +/** Injectable consent and delivery seams for tests. */ +export interface CommandTelemetryDeps { + resolve?: (cwd: string) => Promise + reporter?: Pick +} + +/** + * Resolve consent for the project and, when allowed, assemble and send one + * telemetry event, draining in-flight sends before returning. Swallows every + * error so telemetry can never change a command's result. + * @param event - the command lifecycle facts. + * @param deps - consent and delivery seams; defaults hit the real endpoint. + */ +export async function reportCommandTelemetry( + event: CommandTelemetryEvent, + deps: CommandTelemetryDeps = {}, +): Promise { + try { + /* v8 ignore next -- the production ConsentResolver is exercised by the built-bin smoke */ + const resolve = deps.resolve ?? (cwd => new ConsentResolver().resolve(cwd)) + const consent = await resolve(event.cwd) + if (!consent.allowed) return + const payload = await buildTelemetryPayload({ + command: event.command, + durationMs: event.durationMs, + success: event.success, + projectDir: event.cwd, + }) + /* v8 ignore next -- the production TelemetryReporter is exercised by the built-bin smoke */ + const reporter = deps.reporter ?? new TelemetryReporter() + reporter.report(payload, consent) + await reporter.flush() + } catch { + // Telemetry is best-effort; a consent, payload, or delivery fault never reaches the command. + } +} diff --git a/packages/sdk/scripts/tests/scripts.spec.ts b/packages/sdk/scripts/tests/scripts.spec.ts index faa025926e..3ab59f13d8 100644 --- a/packages/sdk/scripts/tests/scripts.spec.ts +++ b/packages/sdk/scripts/tests/scripts.spec.ts @@ -32,6 +32,7 @@ import { runDshSdkCommand, type DshSdkCommandContext } from '../src/command.ts' import { runConfigCommand } from '../src/config.ts' import { ConfigWorkflow, type ConfigPlan } from '../src/config/config-workflow.ts' import { runCreatePluginCommand } from '../src/create-plugin.ts' +import { reportCommandTelemetry, type CommandTelemetryEvent } from '../src/telemetry.ts' import { initialize, resolve as resolveLocalPlugin } from '../src/local-plugin-loader-hooks.ts' const temporary: string[] = [] @@ -619,3 +620,49 @@ describe('dsh-sdk create', () => { await expect(runDshSdkCommand(['create', 'pkg@1.0.0'], context)).resolves.toBe(0) }) }) + +describe('command telemetry', () => { + it('reports when consent allows and skips when denied or faulting', async () => { + const dir = await mkdtemp(join(tmpdir(), 'dsh-telemetry-')) + temporary.push(dir) + const sent: unknown[] = [] + const reporter = { report: () => { sent.push(1) }, flush: async () => {} } + await reportCommandTelemetry( + { command: 'build', cwd: dir, durationMs: 5, success: true }, + { resolve: async () => ({ allowed: true, reason: 'absent' }), reporter }, + ) + expect(sent).toHaveLength(1) + await reportCommandTelemetry( + { command: 'build', cwd: dir, durationMs: 5, success: true }, + { resolve: async () => ({ allowed: false, reason: 'disabled' }), reporter }, + ) + expect(sent).toHaveLength(1) + await expect(reportCommandTelemetry( + { command: 'build', cwd: dir, durationMs: 5, success: true }, + { resolve: async () => { throw new Error('boom') }, reporter }, + )).resolves.toBeUndefined() + expect(sent).toHaveLength(1) + }) + + it('emits a telemetry event carrying each command outcome', async () => { + const project = await committedProject() + const events: CommandTelemetryEvent[] = [] + const context = commandContext(project.root) + context.telemetry = async (event) => { events.push(event) } + context.build = async () => {} + await expect(runDshSdkCommand(['build'], context)).resolves.toBe(0) + expect(events).toHaveLength(1) + expect(events[0]).toMatchObject({ command: 'build', cwd: project.root, success: true }) + + await runDshSdkCommand([], context) + expect(events).toHaveLength(1) + + context.build = async () => { throw new Error('boom') } + await expect(runDshSdkCommand(['build'], context)).resolves.toBe(1) + expect(events[1]).toMatchObject({ command: 'build', success: false }) + + context.config = async () => ({ installError: new Error('offline') }) + await expect(runDshSdkCommand(['config'], context)).resolves.toBe(1) + expect(events.at(-1)).toMatchObject({ command: 'config', success: false }) + }) +}) diff --git a/packages/sdk/scripts/tsconfig.json b/packages/sdk/scripts/tsconfig.json index 848de9a314..461c86c06d 100644 --- a/packages/sdk/scripts/tsconfig.json +++ b/packages/sdk/scripts/tsconfig.json @@ -7,6 +7,7 @@ "include": ["src"], "references": [ { "path": "../helper" }, + { "path": "../telemetry" }, { "path": "../../ui/app-boot" }, { "path": "../../../vendor/cordis" } ] diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index cafebfaae6..68ee8e2640 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1228,6 +1228,9 @@ importers: '@deepseek-ai/dsh-helper': specifier: workspace:^ version: link:../helper + '@deepseek-ai/dsh-telemetry': + specifier: workspace:^ + version: link:../telemetry commander: specifier: ^15.0.0 version: 15.0.0 From ed418827c28845bc5e5d44ea9a5bcb6c275c24d9 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Sat, 18 Jul 2026 16:32:08 +0800 Subject: [PATCH 183/323] =?UTF-8?q?chore(sdk):=20satisfy=20CI=20gates=20?= =?UTF-8?q?=E2=80=94=20config=20catalog,=20md-wrap,=20knip?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Regenerate docs/config-catalog.md for the telemetry package, unwrap the design doc's multi-line blockquote paragraphs, and stop exporting the create-sdk headless spec internals that have no external consumer. --- docs/config-catalog.md | 1 + docs/sdk-后续工作-设计.md | 2 ++ packages/sdk/create-sdk/src/headless.ts | 4 ++-- 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 3e3d8141fa..7cccb69e0a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1432,4 +1432,5 @@ Imported as libraries by other packages; a `cordis.yml` cannot load them. - `@deepseek-ai/dsh-scripts` ([`packages/sdk/scripts/src/index.ts`](../packages/sdk/scripts/src/index.ts)) - `@deepseek-ai/dsh-subagent-inprocess` ([`packages/subagent/subagent-inprocess/src/index.ts`](../packages/subagent/subagent-inprocess/src/index.ts)) - `@deepseek-ai/dsh-subagent-subprocess` ([`packages/subagent/subagent-subprocess/src/index.ts`](../packages/subagent/subagent-subprocess/src/index.ts)) +- `@deepseek-ai/dsh-telemetry` ([`packages/sdk/telemetry/src/index.ts`](../packages/sdk/telemetry/src/index.ts)) - `@deepseek-ai/dsh-timeout` ([`packages/util/timeout/src/index.ts`](../packages/util/timeout/src/index.ts)) diff --git a/docs/sdk-后续工作-设计.md b/docs/sdk-后续工作-设计.md index 1395ece5e0..5f968c27ee 100644 --- a/docs/sdk-后续工作-设计.md +++ b/docs/sdk-后续工作-设计.md @@ -1,6 +1,7 @@ # DeepSeek Harness SDK 后续工作设计 > 状态：设计成稿，供通读与评审。定案后由 ccyu 转正式 RFC 并双语化。本文件为临时设计文档，不走 doc-sync / 文档预算门禁。 +> > 一句话：**SDK 初版已合并；本轮把"创建项目""创建插件""遥测""交互测试"四块补齐，核心是抽出一个既撑交互又撑 headless 的创建内核，其余三块围绕它扩展。** ## 0. 总览（一屏读完） @@ -134,6 +135,7 @@ SDK 初版（`packages/sdk/*`）已经落地三个包： - **consent 承载**：遥测作为 `create` 时默认打开的 feature 写进 cordis.yml（对用户可见、随项目）。 > **接线现状（读码修正）**：launcher 上报已接通——`runDshSdkCommand` 计时包住每条命令，`finally` 里 resolve consent（甲）→ 建 redacted payload（cordis.yml+package.json 全文、不读 .env）→ fire-and-forget 上报 + flush，best-effort 永不影响命令结果。**默认开**：无遥测条目 → 甲 → 上报。**opt-out 现状**：在 cordis.yml 手动加一条 `disabled` 的 `@deepseek-ai/dsh-telemetry` 条目即关（`ConsentResolver` 读到 disabled → 不报；disabled 条目 cordis 不加载，故不会因"它不是运行时插件"而 boot 失败）。 +> > **暂缓（催表 opt-out 开关）**：把"关遥测"做成 config/create 向导里的勾选项还没做。关键约束：`@deepseek-ai/dsh-telemetry` 是 **launcher 库、不是 cordis 运行时插件**，所以 consent 条目只能以 **disabled 形态**存在（enabled=无条目=甲默认报；要关才写 disabled 条目），不能像普通 feature 那样挂一个 enabled 的可 boot 条目。向导化这个"只在关闭时才出现条目"的特殊语义留作后续。 **在案取舍**：发全文会把第三方（含私有 scoped）包名、cordis 配置值（base-url/路径）暴露给 endpoint 持有方；主流工具都不发这些（Turbo 排除包名、Angular 禁模块名）。ccyu 作为本 SDK 维护者接受此暴露——目的即掌握开发者用了哪些 plugin/依赖/配置。 diff --git a/packages/sdk/create-sdk/src/headless.ts b/packages/sdk/create-sdk/src/headless.ts index e32a053457..164405e14f 100644 --- a/packages/sdk/create-sdk/src/headless.ts +++ b/packages/sdk/create-sdk/src/headless.ts @@ -15,7 +15,7 @@ import type { CreateArgs } from './args.ts' * (the interactive tree/suggests prompts are skipped). Absent required answers make * the run fail loud through `HeadlessPromptPort` rather than blocking. */ -export interface HeadlessCreateSpec { +interface HeadlessCreateSpec { directory?: string description?: string provider?: 'deepseek' | 'custom' @@ -43,7 +43,7 @@ function asRecord(value: unknown, source: string): Record { } /** Parse and shallow-validate a headless spec from JSON text. */ -export function parseHeadlessSpec(text: string, source: string): HeadlessCreateSpec { +function parseHeadlessSpec(text: string, source: string): HeadlessCreateSpec { let parsed: unknown try { parsed = JSON.parse(text) From 6ce407259927bd73dffdf0a3643111b45651af87 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sat, 18 Jul 2026 21:53:30 +0800 Subject: [PATCH 184/323] fix(ci): avoid concurrent docs site builds --- scripts/run-gates.ts | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 9eb82b5e15..4da4998723 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -214,7 +214,6 @@ function ciPrimaryGates(): Gate[] { ...docSyncLeafGates(), pnpmScript('module-graph', 'verify-module-graph', { label: 'module graph' }), pnpmScript('knip', 'knip'), - pnpmScript('website-build', 'website:build', { label: 'website build' }), pnpmScript('build', 'build', { needs: ['typecheck'] }), pnpmScript('publint', 'publint', { needs: ['build'] }), pnpmScript('node-next-types', 'verify-node-next-types', { @@ -234,7 +233,6 @@ function ciStaticGates(): Gate[] { ...docSyncLeafGates(), pnpmScript('module-graph', 'verify-module-graph', { label: 'module graph' }), pnpmScript('knip', 'knip'), - pnpmScript('website-build', 'website:build', { label: 'website build' }), ] } @@ -349,6 +347,7 @@ function docSyncLeafGates(options: { pnpmScript('translation-prompt', 'verify-translation-prompt', { label: 'translation prompt' }), pnpmScript('translation-pairing', 'verify-translation-pairing', { label: 'translation pairing' }), pnpmScript('doc-budgets', 'verify-doc-budgets', { label: 'doc budgets' }), + // Keep the VitePress build in this single gate because projection rewrites website/.generated. pnpmScript('docs-site', 'docs:check', { label: 'documentation site' }), pnpmScript('package-readme-limitations', 'verify-package-readme-limitations', { label: 'package README limitations' }), ] From 78f21bf703df0b32c1a4196b489565e30c6319e2 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Sat, 18 Jul 2026 21:25:56 +0800 Subject: [PATCH 185/323] fix(sdk): list create and headless flags in usage help dsh-sdk's usage template predates the create command and create-sdk's predates --config/--config-json/--json, so --help hid both surfaces the README already documents. Pin each with a help-output assertion. --- packages/sdk/create-sdk/src/templates/assets/usage.txt.tpl | 3 +++ packages/sdk/create-sdk/tests/create.spec.ts | 1 + packages/sdk/scripts/src/templates/assets/usage.txt.tpl | 1 + packages/sdk/scripts/tests/scripts.spec.ts | 1 + 4 files changed, 6 insertions(+) diff --git a/packages/sdk/create-sdk/src/templates/assets/usage.txt.tpl b/packages/sdk/create-sdk/src/templates/assets/usage.txt.tpl index 2b734eb753..32f4d5c6d2 100644 --- a/packages/sdk/create-sdk/src/templates/assets/usage.txt.tpl +++ b/packages/sdk/create-sdk/src/templates/assets/usage.txt.tpl @@ -9,3 +9,6 @@ Options: --interface --pm --install / --no-install + --config + --config-json + --json diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index 1f2cdb75fc..0e4abd37c4 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -477,6 +477,7 @@ describe('create command composition', () => { context.stdout.isTTY = false await expect(createProject(['--help'], context)).resolves.toBeUndefined() expect(context.readStdout()).toContain('Usage: create-sdk') + expect(context.readStdout()).toContain('--config-json ') expect(context.readStdout()).not.toContain('--link-workspace') await expect(createProject(argv('agent', false), context)).rejects.toThrow('interactive TTY') context.stdin.isTTY = true diff --git a/packages/sdk/scripts/src/templates/assets/usage.txt.tpl b/packages/sdk/scripts/src/templates/assets/usage.txt.tpl index d4122198f5..b372c65d17 100644 --- a/packages/sdk/scripts/src/templates/assets/usage.txt.tpl +++ b/packages/sdk/scripts/src/templates/assets/usage.txt.tpl @@ -5,3 +5,4 @@ Commands: dev [target] [-- args...] Start with TypeScript and local-plugin source resolution build [args...] Run the project's installed tsdown config Interactively edit project features + create Add an external plugin dependency (pkg@version or github:owner/repo#ref) and mount it in cordis.yml diff --git a/packages/sdk/scripts/tests/scripts.spec.ts b/packages/sdk/scripts/tests/scripts.spec.ts index 3ab59f13d8..8b887d74db 100644 --- a/packages/sdk/scripts/tests/scripts.spec.ts +++ b/packages/sdk/scripts/tests/scripts.spec.ts @@ -168,6 +168,7 @@ describe('Commander launcher arguments', () => { await expect(runDshSdkCommand(['unknown'], context)).resolves.toBe(1) await expect(runDshSdkCommand([], context)).resolves.toBe(0) expect(context.readStdout()).toContain('Usage: dsh-sdk') + expect(context.readStdout()).toContain('create ') const defaults = commandContext(root) await writeFile(join(root, 'main.mjs'), 'export function main() { return "ok" }\n') From 013db6e8f02eb8f4c6c0bdd0f21f62d69f2483da Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Sat, 18 Jul 2026 21:50:46 +0800 Subject: [PATCH 186/323] fix(create-sdk): keep --json stdout pure NDJSON The SKILL.md contract says every stdout line is one JSON event, but createProject wrote the Created/Next-steps templates to stdout and the default install/build path inherited the launcher's stdio, so package- manager child output interleaved with the event stream. Under --json, route human progress to stderr and run install/build through a NodeCommandRunner that redirects child stdout+stderr to stderr. --- packages/sdk/create-sdk/src/command.ts | 13 ++++++--- packages/sdk/create-sdk/tests/create.spec.ts | 18 +++++++++++++ .../src/package-managers/package-manager.ts | 27 ++++++++++++++++--- packages/sdk/helper/tests/documents.spec.ts | 14 ++++++++++ 4 files changed, 65 insertions(+), 7 deletions(-) diff --git a/packages/sdk/create-sdk/src/command.ts b/packages/sdk/create-sdk/src/command.ts index a7855ea027..9897db2a21 100644 --- a/packages/sdk/create-sdk/src/command.ts +++ b/packages/sdk/create-sdk/src/command.ts @@ -9,6 +9,7 @@ import { ClackPromptPort, HeadlessPromptError, HeadlessPromptPort, + NodeCommandRunner, PromptCancelledError, type PackageManagerVersionProbe, type PromptPort, @@ -45,6 +46,9 @@ export async function createProject( context: CreateCommandContext, ): Promise { const args = parseCreateArgs(argv) + // Under --json, stdout carries only NDJSON events: human-readable progress + // and package-manager child output move to stderr. + const progress = args.json === true ? context.stderr : context.stdout if (args.help) { context.stdout.write(CREATE_TEMPLATES.usage.render({})) return undefined @@ -64,7 +68,7 @@ export async function createProject( }) const resolved = await wizard.run() const result = await scaffoldProject(resolved.directory, resolved.request) - context.stdout.write(CREATE_TEMPLATES.created.render({ + progress.write(CREATE_TEMPLATES.created.render({ name: resolved.request.name, directory: resolved.directory, })) @@ -72,8 +76,9 @@ export async function createProject( try { if (context.setup) await context.setup(resolved) else { - await resolved.request.packageManager.install(resolved.directory) - await resolved.request.packageManager.build(resolved.directory) + const runner = args.json === true ? new NodeCommandRunner(context.stderr) : new NodeCommandRunner() + await resolved.request.packageManager.install(resolved.directory, runner) + await resolved.request.packageManager.build(resolved.directory, runner) } } catch (error) { context.stderr.write(CREATE_TEMPLATES.setupFailure.render({ @@ -84,7 +89,7 @@ export async function createProject( throw error } } - context.stdout.write(CREATE_TEMPLATES.nextSteps.render({ + progress.write(CREATE_TEMPLATES.nextSteps.render({ directory: resolved.directory, setupRequired: !resolved.install, ...packageManagerTemplateModel(resolved.request.packageManager), diff --git a/packages/sdk/create-sdk/tests/create.spec.ts b/packages/sdk/create-sdk/tests/create.spec.ts index 0e4abd37c4..362e5046f9 100644 --- a/packages/sdk/create-sdk/tests/create.spec.ts +++ b/packages/sdk/create-sdk/tests/create.spec.ts @@ -8,6 +8,7 @@ import { HeadlessPromptPort, LocalPluginBlueprint, featureId, + NodeCommandRunner, NpmPackageManager, type FeatureSelection, type NestedMultiSelectValue, @@ -511,6 +512,12 @@ describe('create command composition', () => { const okSpec = JSON.stringify({ ...base, directory: 'done-agent', provider: 'deepseek', apiKey: 'key', features: [] }) await expect(runCreateCommand(['--config-json', okSpec, '--json'], ok)).resolves.toBe(0) expect(ok.readStdout()).toContain('{"type":"done"}') + // stdout stays pure NDJSON: every line parses, human progress goes to stderr + for (const line of ok.readStdout().split('\n').filter(line => line.length > 0)) { + expect(() => { JSON.parse(line) }).not.toThrow() + } + expect(ok.readStderr()).toContain('Created done-agent') + expect(ok.readStderr()).toContain('Next: cd') const missing = commandContext(root) missing.stdin.isTTY = false @@ -564,6 +571,17 @@ describe('create command composition', () => { await createProject(argv('agent', true), context) expect(install).toHaveBeenCalledOnce() expect(build).toHaveBeenCalledOnce() + const spec = JSON.stringify({ + directory: 'json-agent', description: 'test', provider: 'deepseek', apiKey: 'key', + model: 'deepseek-v4-flash', interface: 'embed', pm: 'npm', install: true, features: [], + }) + const json = commandContext(root) + json.stdin.isTTY = false + json.stdout.isTTY = false + await createProject(['--config-json', spec, '--json'], json) + // json mode hands install/build a runner that redirects child output to stderr + expect(install).toHaveBeenCalledTimes(2) + expect(install.mock.calls[1]?.[1]).toBeInstanceOf(NodeCommandRunner) install.mockRestore() build.mockRestore() }) diff --git a/packages/sdk/helper/src/package-managers/package-manager.ts b/packages/sdk/helper/src/package-managers/package-manager.ts index 6e6eda478a..8d6b617977 100644 --- a/packages/sdk/helper/src/package-managers/package-manager.ts +++ b/packages/sdk/helper/src/package-managers/package-manager.ts @@ -58,17 +58,38 @@ export function scrubEnvironment(environment: NodeJS.ProcessEnv = process.env): /** Node child-process command runner with inherited stdio and quiescent completion. */ export class NodeCommandRunner implements CommandRunner { - /** Spawn one child and settle only after its exit. */ + private readonly output: NodeJS.WritableStream | undefined + + /** + * @param output - redirect target for child stdout+stderr; the child inherits + * this process's stdio when absent. Callers whose own stdout carries a machine + * protocol (create-sdk --json NDJSON) redirect child output to keep the + * protocol stream pure. + */ + constructor(output?: NodeJS.WritableStream) { + this.output = output + } + + /** Spawn one child and settle only after exit, with redirected stdio drained. */ run(command: string, args: readonly string[], cwd: string): Promise { return new Promise((resolve, reject) => { + const output = this.output + if (output === undefined) { + const child = spawn(command, [...args], { cwd, env: scrubEnvironment(), stdio: 'inherit', shell: false }) + child.once('error', reject) + child.once('exit', (exitCode, signal) => { resolve({ exitCode, signal }) }) + return + } const child = spawn(command, [...args], { cwd, env: scrubEnvironment(), - stdio: 'inherit', + stdio: ['inherit', 'pipe', 'pipe'], shell: false, }) + child.stdout.pipe(output, { end: false }) + child.stderr.pipe(output, { end: false }) child.once('error', reject) - child.once('exit', (exitCode, signal) => { resolve({ exitCode, signal }) }) + child.once('close', (exitCode, signal) => { resolve({ exitCode, signal }) }) }) } } diff --git a/packages/sdk/helper/tests/documents.spec.ts b/packages/sdk/helper/tests/documents.spec.ts index 3ce5eeccea..469887036a 100644 --- a/packages/sdk/helper/tests/documents.spec.ts +++ b/packages/sdk/helper/tests/documents.spec.ts @@ -1,6 +1,7 @@ import { chmod, mkdtemp, mkdir, readFile, rm, writeFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' +import { Writable } from 'node:stream' import { afterEach, describe, expect, it } from 'vitest' import { CordisYamlFile, JsExpression } from '../src/documents/cordis-yaml-file.ts' import { EnvFile } from '../src/documents/env-file.ts' @@ -325,6 +326,19 @@ describe('package manager strategies', () => { const runner = new NodeCommandRunner() await expect(runner.run(process.execPath, ['-e', ''], root)).resolves.toEqual({ exitCode: 0, signal: null }) await expect(runner.run('missing-dsh-command', [], root)).rejects.toThrow() + let redirected = '' + const output = new Writable({ + write(chunk, _encoding, callback) { redirected += String(chunk); callback() }, + }) + const redirecting = new NodeCommandRunner(output) + await expect(redirecting.run( + process.execPath, + ['-e', 'process.stdout.write("child-out"); process.stderr.write("child-err")'], + root, + )).resolves.toEqual({ exitCode: 0, signal: null }) + expect(redirected).toContain('child-out') + expect(redirected).toContain('child-err') + await expect(redirecting.run('missing-dsh-command', [], root)).rejects.toThrow() }) it('discovers and rewrites a repository-local NPM dependency closure', async () => { From e674f4c20e21710b8b9ea14706c0955a2b681706 Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Sat, 18 Jul 2026 21:53:47 +0800 Subject: [PATCH 187/323] fix(telemetry): withhold package.json when cordis.yml is absent MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit buildTelemetryPayload read the two reported files independently, so a dsh-sdk command mistakenly run in an arbitrary non-SDK directory (no cordis.yml, e.g. any unrelated repo) still uploaded that directory's package.json — dependency names and metadata of a project that never opted into the SDK toolchain. Gate the manifest on cordis.yml presence: without the config the directory is not an SDK project and its manifest is not ours to report. Consent semantics are unchanged. --- packages/sdk/telemetry/README.md | 2 +- packages/sdk/telemetry/src/payload.ts | 13 ++++++++++--- packages/sdk/telemetry/tests/payload.spec.ts | 12 +++++++++++- 3 files changed, 22 insertions(+), 5 deletions(-) diff --git a/packages/sdk/telemetry/README.md b/packages/sdk/telemetry/README.md index 43d13d3dcc..8ec3da2c78 100644 --- a/packages/sdk/telemetry/README.md +++ b/packages/sdk/telemetry/README.md @@ -6,7 +6,7 @@ Launcher-side telemetry primitives for the dsh-sdk toolchain. This is a plain li |---|---| | `SecretRedactor` | Conservative safety backstop: replaces secret-shaped values (secret-like keys, known token shapes, PEM blocks, URL credentials, high-entropy opaque tokens) with a placeholder in both parsed values (`redactValue`) and raw text (`redactText`). Never drops a field or line. | | `ConsentResolver` | Parses (never boots) a project `cordis.yml` and reads the telemetry entry's enabled/disabled state as consent; `DO_NOT_TRACK`/CI env force a hard opt-out. | -| `buildTelemetryPayload` | Assembles `{command, durationMs, success, cordisYmlContent, packageJsonContent}`, running the redactor over the full `cordis.yml` and `package.json` text. Never reads `.env`. | +| `buildTelemetryPayload` | Assembles `{command, durationMs, success, cordisYmlContent, packageJsonContent}`, running the redactor over the full `cordis.yml` and `package.json` text. Never reads `.env`; `package.json` ships only alongside a `cordis.yml`, so a command run in a non-SDK directory never uploads that directory's unrelated manifest. | | `getOrCreateAnonymousId` | Random UUID persisted in a per-user GLOBAL config file (never in the project, never derived from git). | | `TelemetryReporter` | Fire-and-forget send: `report()` never blocks or throws; delivery resolves on every path; `flush()` optionally drains in-flight sends within a cap. | diff --git a/packages/sdk/telemetry/src/payload.ts b/packages/sdk/telemetry/src/payload.ts index 96a7b19d76..505cedb872 100644 --- a/packages/sdk/telemetry/src/payload.ts +++ b/packages/sdk/telemetry/src/payload.ts @@ -5,7 +5,9 @@ * the project `cordis.yml` and `package.json`. It NEVER reads or includes `.env` * — secrets live only in `.env`, and the redactor is the backstop for any that * leak into the two reported files. A file that does not exist (the first - * `create` run) simply omits its field. + * `create` run) simply omits its field, and `package.json` ships only when + * `cordis.yml` is present: without it the directory is not an SDK project, and + * its manifest belongs to whatever unrelated project the command ran in. * * @module @deepseek-ai/dsh-telemetry/payload */ @@ -27,7 +29,7 @@ export interface TelemetryPayload { success: boolean /** Redacted full text of the project `cordis.yml`, absent when the file does not exist. */ cordisYmlContent?: string - /** Redacted full text of the project `package.json`, absent when the file does not exist. */ + /** Redacted full text of the project `package.json`, absent when it or `cordis.yml` does not exist. */ packageJsonContent?: string } @@ -70,6 +72,11 @@ export async function buildTelemetryPayload(input: BuildTelemetryPayloadInput): durationMs: input.durationMs, success: input.success, ...cordisYml !== undefined ? { cordisYmlContent: redactor.redactText(cordisYml) } : {}, - ...packageJson !== undefined ? { packageJsonContent: redactor.redactText(packageJson) } : {}, + // package.json is an SDK-project manifest only alongside cordis.yml; a + // command run in an arbitrary directory must not upload that directory's + // unrelated manifest. + ...cordisYml !== undefined && packageJson !== undefined + ? { packageJsonContent: redactor.redactText(packageJson) } + : {}, } } diff --git a/packages/sdk/telemetry/tests/payload.spec.ts b/packages/sdk/telemetry/tests/payload.spec.ts index 1af5139ef5..ed3ab2f82f 100644 --- a/packages/sdk/telemetry/tests/payload.spec.ts +++ b/packages/sdk/telemetry/tests/payload.spec.ts @@ -47,8 +47,18 @@ describe('buildTelemetryPayload', () => { expect('packageJsonContent' in payload).toBe(false) }) + it('withholds package.json when cordis.yml is absent (not an SDK project)', async () => { + const dir = await projectDir({ 'package.json': '{ "name": "unrelated-repo" }' }) + const payload = await buildTelemetryPayload({ command: 'build', durationMs: 3, success: false, projectDir: dir }) + expect('cordisYmlContent' in payload).toBe(false) + expect('packageJsonContent' in payload).toBe(false) + }) + it('uses a supplied redactor', async () => { - const dir = await projectDir({ 'package.json': '{ "password": "hunter2" }' }) + const dir = await projectDir({ + 'cordis.yml': '- id: llm\n name: \'@deepseek-ai/dsh-llm-deepseek\'\n', + 'package.json': '{ "password": "hunter2" }', + }) const redactor = new SecretRedactor({ placeholder: '<>' }) const payload = await buildTelemetryPayload({ command: 'config', durationMs: 5, success: true, projectDir: dir, redactor, From 7a5d3ae5ce9bf7b1354decba22d7e0dd9ca7a22d Mon Sep 17 00:00:00 2001 From: imccyu <276526105+imccyu@users.noreply.github.com> Date: Sat, 18 Jul 2026 21:56:52 +0800 Subject: [PATCH 188/323] fix(telemetry): stop bearer redaction from eating plain prose The bearer rule matched any 8+ run of letters after the word, so package.json prose like "uses bearer authentication" lost its following word to the placeholder. Real bearer credentials always carry a digit; require one in the candidate token. --- packages/sdk/telemetry/src/secret-redactor.ts | 7 ++++++- packages/sdk/telemetry/tests/secret-redactor.spec.ts | 7 +++++++ 2 files changed, 13 insertions(+), 1 deletion(-) diff --git a/packages/sdk/telemetry/src/secret-redactor.ts b/packages/sdk/telemetry/src/secret-redactor.ts index 5b9af5f169..087ba2284a 100644 --- a/packages/sdk/telemetry/src/secret-redactor.ts +++ b/packages/sdk/telemetry/src/secret-redactor.ts @@ -191,7 +191,12 @@ export class SecretRedactor { } #redactBearerTokens(text: string): string { - return text.replace(/(bearer\s+)([a-z0-9._-]{8,})/gi, (_match, prefix: string) => `${prefix}${this.#placeholder}`) + // The candidate must contain a digit: real bearer credentials are never + // letters-only, while prose like "bearer authentication" is. + return text.replace( + /(bearer\s+)((?=[a-z._-]*[0-9])[a-z0-9._-]{8,})/gi, + (_match, prefix: string) => `${prefix}${this.#placeholder}`, + ) } #redactStandaloneTokens(text: string): string { diff --git a/packages/sdk/telemetry/tests/secret-redactor.spec.ts b/packages/sdk/telemetry/tests/secret-redactor.spec.ts index c3250d9ace..77d89d968e 100644 --- a/packages/sdk/telemetry/tests/secret-redactor.spec.ts +++ b/packages/sdk/telemetry/tests/secret-redactor.spec.ts @@ -154,6 +154,13 @@ describe('SecretRedactor.redactText', () => { .toBe(`sending Bearer ${REDACTED} now`) }) + it('keeps letters-only prose after the word bearer intact', () => { + expect(redactor.redactText('uses bearer authentication for requests')) + .toBe('uses bearer authentication for requests') + expect(redactor.redactText('"description": "bearer token-helper middleware"')) + .toBe('"description": "bearer token-helper middleware"') + }) + it('redacts standalone secret-shaped tokens while keeping package names and paths', () => { expect(redactor.redactText('key sk-abcdefghij1234567890 end')) .toBe(`key ${REDACTED} end`) From 8e366c3071f88d4c66c0bfae0fcbea45bd61b78f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 22:31:04 +0800 Subject: [PATCH 189/323] test(tui): snapshot semantic terminal state --- docs/rfc/INDEX.md | 1 + ...-18-tui-terminal-state-snapshots.i18n.yaml | 6 + ...2026-07-18-tui-terminal-state-snapshots.md | 57 +++ ...6-07-18-tui-terminal-state-snapshots.zh.md | 57 +++ docs/testing.md | 4 +- .../tests/fixtures/tui-scripted-llm.ts | 60 +++ .../tests/fixtures/tui-scripted.cordis.yml | 27 + .../tests/tui-keyless-smoke.e2e.ts | 87 +++- knip.json | 5 + packages/ui/tui/package.json | 5 + packages/ui/tui/tests/harness.ts | 130 +++++ packages/ui/tui/tests/headless-terminal.ts | 318 ++++++++++++ .../advanced-cards-collapsed.golden.txt | 107 ++++ .../advanced-cards-expanded.golden.txt | 127 +++++ .../snapshots/code-mode-complete.golden.txt | 50 ++ .../snapshots/code-mode-pending.golden.txt | 52 ++ .../conversation-complete.golden.txt | 75 +++ .../snapshots/conversation-replay.golden.txt | 73 +++ .../conversation-streaming.golden.txt | 75 +++ .../cordis-tools-complete.golden.txt | 73 +++ .../snapshots/cordis-tools-pending.golden.txt | 59 +++ .../snapshots/disposed-terminal.golden.txt | 52 ++ .../dynamic-workflow-complete.golden.txt | 53 ++ .../dynamic-workflow-pending.golden.txt | 55 ++ .../snapshots/errors-and-help.golden.txt | 52 ++ .../question-dialog-validation.golden.txt | 69 +++ .../snapshots/question-dialog.golden.txt | 67 +++ ...surface-after-compaction-narrow.golden.txt | 45 ++ .../surface-after-compaction-wide.golden.txt | 37 ++ .../surface-before-compaction.golden.txt | 67 +++ packages/ui/tui/tests/tui.snapshot.ts | 472 ++++++++++++++++++ packages/ui/tui/tests/tui.spec.ts | 101 +--- pnpm-lock.yaml | 20 + vitest.snapshot.config.ts | 6 +- 34 files changed, 2437 insertions(+), 107 deletions(-) create mode 100644 docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml create mode 100644 docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md create mode 100644 docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md create mode 100644 examples/coding-agent/tests/fixtures/tui-scripted-llm.ts create mode 100644 examples/coding-agent/tests/fixtures/tui-scripted.cordis.yml create mode 100644 packages/ui/tui/tests/harness.ts create mode 100644 packages/ui/tui/tests/headless-terminal.ts create mode 100644 packages/ui/tui/tests/snapshots/advanced-cards-collapsed.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/advanced-cards-expanded.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/code-mode-pending.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/conversation-complete.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/conversation-replay.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/cordis-tools-pending.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/disposed-terminal.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/dynamic-workflow-pending.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/errors-and-help.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/question-dialog-validation.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/question-dialog.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/surface-after-compaction-narrow.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/surface-after-compaction-wide.golden.txt create mode 100644 packages/ui/tui/tests/snapshots/surface-before-compaction.golden.txt create mode 100644 packages/ui/tui/tests/tui.snapshot.ts diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index ecb66326b3..434df9f305 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -209,6 +209,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Single-source the acp-agent replay config](implemented/testing/2026-07-04-single-source-acp-replay-config.md) | 2026-07-04 | | [Pin request-header content in one snapshot scenario](implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md) | 2026-07-06 | | [Extract the ACP snapshot suite into a support package](implemented/testing/2026-07-08-shared-acp-snapshot-package.md) | 2026-07-08 | +| [Snapshot semantic terminal state for the TUI](implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) | 2026-07-18 | ## Rejected diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml new file mode 100644 index 0000000000..5b682b642b --- /dev/null +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-18-tui-terminal-state-snapshots.md: 225efe8de95973ecae3f9bf73308e7ae879dddbb +2026-07-18-tui-terminal-state-snapshots.zh.md: b7399a31b0abf41905f495a1ea3b4ecd0c858526 diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md new file mode 100644 index 0000000000..225efe8de9 --- /dev/null +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md @@ -0,0 +1,57 @@ +# RFC: Snapshot semantic terminal state for the TUI + +Status: implemented + +English | [中文](2026-07-18-tui-terminal-state-snapshots.zh.md) + +## Problem + +The TUI is a stateful renderer. Its user-visible result depends on ANSI parsing, differential frames, wrapping, scrollback, viewport position, terminal width, focus, cursor state, and each tool's presentation intent. Unit tests that collect `Terminal.write()` fragments can prove event handling, but they cannot prove the final screen a terminal displays. The same screen may also be emitted through different write fragments, so pinning those fragments creates false regressions. + +Component-line snapshots stop before ANSI reaches a terminal and miss cursor movement, clearing, styling, overlay composition, and reflow. Raster screenshots include font and platform rendering noise that is unrelated to the TUI contract. The TUI therefore needs a deterministic, reviewable representation of terminal state plus a smaller test at the real process and PTY boundary. + +## Decision + +TUI coverage has three complementary layers: + +1. `tui.spec.ts` tests event mapping, input routing, disposal, and error behavior directly. +2. `tui.snapshot.ts` mounts the production TUI against a headless terminal emulator and compares semantic terminal-state goldens. +3. `tui-keyless-smoke.e2e.ts` boots the real Loader composition in a PTY, drives a complete scripted conversation through streaming and `ask_user_question`, exits through `/exit`, and verifies terminal teardown. The production coding-agent configuration also retains its banner/exit and startup-failure PTY cases. + +The package-local `HeadlessTerminal` implements the same pi-tui `Terminal` interface as the process terminal and feeds every ANSI write into the pinned `@xterm/headless` parser. A snapshot waits for pi-tui's synchronized-output end marker before reading state. This makes a checkpoint represent a completed frame rather than a timer-dependent write prefix. + +Each golden projects terminal state into text: dimensions, active-buffer and viewport coordinates, lifecycle and cursor state, rows, wrap markers, and non-default style ranges. Scroll-heavy cards capture the used buffer; overlays capture the visible viewport. Text and style remain separate so a reviewer can distinguish content changes from presentation changes without decoding ANSI bytes. + +Every checkpoint also enforces theme independence across the complete terminal state: no RGB colors, no palette entries beyond ANSI 0–15, and no explicit background colors. Reverse video remains valid for selection because it uses terminal defaults. The suite owns a closed checkpoint list: its type rejects undeclared names, and its inventory checks reject missing checkpoints and orphaned `.golden.txt` files. + +### Required scenario matrix + +| Area | Representative checkpoints | Contract pinned | +|---|---|---| +| Conversation | replay, streaming, completion | Resumed Markdown and reasoning, live deltas, plans, token usage, and max-token completion | +| Code Mode | pending and completed `run_code` | The production Code Mode registry and presenter, source program, captured logs, and result | +| Dynamic workflows | pending and completed `workflow` | The production workflow presenter, metadata, phases, parallel agents, script, and structured result | +| Cordis tools | pending and completed inspect/mount/unmount | The production `cordis_inspect`, `cordis_mount`, and `cordis_unmount` presenters and lifecycle results | +| Advanced tool cards | collapsed and expanded | Terminal, diff, generic, subagent, background-task, and skill card shapes plus output truncation | +| Interaction | question and validation | Constrained multi-select overlay composition, focus, scrolling, selection, and validation errors | +| Surface and layout | before compaction, narrow replacement, wide replacement | Surface replacement removes retired content; resize reflows the surviving surface without resurrection | +| Failure and shutdown | errors/help and disposed terminal | Help and unknown commands, live/turn error de-duplication, interruption, cursor restoration, and terminal stop | + +The explicitly model-facing advanced cases use the real `ToolRegistry` configuration and the production Code Mode, workflow, and Cordis tool presenters. Synthetic presenter fixtures are limited to the generic card-shape matrix, where the TUI's input contract is the presenter view itself. Session events remain the driver so replay, streaming, result arrival, surface replacement, and lifecycle ordering exercise the same projection path as production. + +The TUI suite is included by `vitest.snapshot.config.ts`, so `pnpm run test:snapshot` compares it keylessly. `pnpm run test:snapshot:refresh` rewrites its derived terminal goldens without contacting a model; `test:snapshot:record` remains meaningful for suites whose transcript source requires recording. Both refresh paths still compare the resulting files in the same run. + +## Alternatives considered + +- **Snapshot raw terminal writes** — rejected because differential rendering may change write boundaries without changing the screen, while cursor and clear sequences are unreadable in review. +- **Snapshot component render lines before terminal output** — rejected because it does not test ANSI parsing, cursor movement, overlays, viewport behavior, or the interaction between independent components in one frame. +- **Commit raster screenshots** — rejected because fonts, glyph metrics, antialiasing, and host terminal themes make them platform-sensitive and make semantic style changes difficult to review. +- **Use only PTY end-to-end tests** — rejected because raw PTY output is a stream of historical drawing operations, not queryable final state. PTY tests retain the real Loader/input/teardown boundary, while the emulator owns broad state coverage. +- **Copy pi-tui's unpublished virtual-terminal test helper** — rejected because the installed package does not export that helper. A small adapter around the public `@xterm/headless` API keeps the dependency explicit and the projection owned by this package. + +## Consequences + +- TUI visual regressions produce readable cell-and-style diffs, and the required matrix makes advanced features first-class rather than incidental coverage. +- The test dependency is pinned to the xterm version used by pi-tui. The adapter uses xterm's proposed buffer API, so an xterm upgrade requires rerunning and reviewing the semantic projection. +- The emulator models ANSI terminal state but cannot prove behavior unique to every terminal implementation. The real PTY conversation covers process selection, keyboard input, user interaction, and teardown without duplicating the full matrix. +- Goldens deliberately encode wrapping and viewport behavior at fixed sizes. Intentional layout changes update them through the keyless refresh command and receive ordinary snapshot review. diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md new file mode 100644 index 0000000000..b7399a31b0 --- /dev/null +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md @@ -0,0 +1,57 @@ +# RFC: TUI 语义终端状态快照 + +Status: implemented + +[English](2026-07-18-tui-terminal-state-snapshots.md) | 中文 + +## 问题 + +TUI 是有状态的渲染器。用户最终看到的结果取决于 ANSI 解析、差分帧、换行、回滚缓冲、视口位置、终端宽度、焦点、光标状态，以及各工具的呈现意图。收集 `Terminal.write()` 片段的单元测试可以验证事件处理，却无法验证终端最终显示的画面。同一画面也可能由不同的写入片段产生，因此固定这些片段会制造误报。 + +组件行快照止于 ANSI 进入终端之前，无法覆盖光标移动、清屏、样式、浮层组合和重排。栅格截图会带入与 TUI 契约无关的字体和平台渲染噪声。因此，TUI 既需要一种确定、便于评审的终端状态表示，也需要一项范围更小、覆盖真实进程与 PTY 边界的测试。 + +## 决策 + +TUI 覆盖分为三个互补层次： + +1. `tui.spec.ts` 直接测试事件映射、输入路由、资源释放和错误行为。 +2. `tui.snapshot.ts` 将生产 TUI 挂载到无界面终端模拟器，并比较语义终端状态金标。 +3. `tui-keyless-smoke.e2e.ts` 在 PTY 中启动真实 Loader 组合，驱动一段完整的脚本化会话，使其依次经过流式输出和 `ask_user_question`，再通过 `/exit` 退出并验证终端清理。生产 coding-agent 配置还保留欢迎信息与退出，以及启动失败两类 PTY 场景。 + +包内的 `HeadlessTerminal` 实现与进程终端相同的 pi-tui `Terminal` 接口，并把每次 ANSI 写入交给固定版本的 `@xterm/headless` 解析器。快照会等待 pi-tui 的同步输出结束标记，再读取状态。因此，每个检查点表示已经完成的帧，而不是依赖计时的写入前缀。 + +每份金标把终端状态投影为文本：尺寸、活动缓冲区和视口坐标、生命周期与光标状态、各行、换行标记，以及非默认样式区间。滚动内容较多的卡片捕获已使用缓冲区；浮层捕获可见视口。文本和样式相互分离，评审人无需解码 ANSI 字节即可区分内容变化与呈现变化。 + +每个检查点还会对完整终端状态强制执行主题无关性：禁止 RGB 颜色、禁止 ANSI 0–15 以外的调色板项，也禁止显式背景色。选择行使用终端默认色进行反显，因此仍然有效。测试套件拥有封闭的检查点清单：类型会拒绝未声明的名称，清单检查会拒绝缺失的检查点和遗留的 `.golden.txt` 文件。 + +### 必需场景矩阵 + +| 范围 | 代表性检查点 | 固定的契约 | +|---|---|---| +| 会话 | 回放、流式输出、完成 | 恢复后的 Markdown 与推理、实时增量、计划、token 用量，以及达到 token 上限时的完成状态 | +| Code Mode | `run_code` 待完成与已完成 | 生产 Code Mode 注册表与呈现器、源程序、捕获日志和结果 | +| 动态工作流 | `workflow` 待完成与已完成 | 生产工作流呈现器、元数据、阶段、并行 agent、脚本和结构化结果 | +| Cordis 工具 | inspect/mount/unmount 待完成与已完成 | 生产 `cordis_inspect`、`cordis_mount` 和 `cordis_unmount` 呈现器及其生命周期结果 | +| 高级工具卡片 | 折叠与展开 | 终端、diff、通用、subagent、后台任务和 skill 卡片形态，以及输出截断 | +| 交互 | 问题与校验 | 受限多选浮层的组合、焦点、滚动、选择和校验错误 | +| 表层与布局 | 压缩前、窄幅替换、宽幅替换 | 表层替换会移除退役内容；调整尺寸只会重排保留的表层，不会让旧内容重新出现 | +| 失败与关闭 | 错误与帮助、终端已释放 | 帮助与未知命令、实时错误和轮次错误去重、中断、光标恢复及终端停止 | + +面向模型的高级场景明确使用真实 `ToolRegistry` 配置，以及生产 Code Mode、工作流和 Cordis 工具呈现器。只有通用卡片形态矩阵使用合成呈现器 fixture；在这里，呈现器视图本身就是 TUI 的输入契约。测试仍由会话事件驱动，因此回放、流式输出、结果到达、表层替换和生命周期顺序都会经过与生产环境相同的投影路径。 + +`vitest.snapshot.config.ts` 会包含 TUI 测试套件，因此 `pnpm run test:snapshot` 可以无密钥比较快照。`pnpm run test:snapshot:refresh` 会重写从终端状态派生的金标，而不会联系模型；对于 transcript（文本记录）来源需要录制的测试套件，`test:snapshot:record` 仍有其原有含义。两条刷新路径都会在同一次运行中继续比较生成后的文件。 + +## 曾考虑的替代方案 + +- **快照原始终端写入**：不予采纳，因为差分渲染可能在画面不变时改变写入边界，而且光标与清屏序列难以评审。 +- **快照进入终端输出之前的组件渲染行**：不予采纳，因为它无法测试 ANSI 解析、光标移动、浮层、视口行为，也无法测试独立组件在同一帧中的相互作用。 +- **提交栅格截图**：不予采纳，因为字体、字形度量、抗锯齿和宿主终端主题会使结果依赖平台，也会增加语义样式变更的评审难度。 +- **只使用 PTY 端到端测试**：不予采纳，因为原始 PTY 输出是一系列历史绘制操作，而不是可查询的最终状态。PTY 测试保留真实 Loader、输入与清理边界，模拟器负责广泛的状态覆盖。 +- **复制 pi-tui 未发布的虚拟终端测试 helper**：不予采纳，因为已安装的包并未导出该 helper。围绕公开 `@xterm/headless` API 编写小型适配器，可以显式声明依赖，并让本包拥有状态投影。 + +## 后果 + +- TUI 视觉回归会产生便于阅读的单元格和样式 diff；必需场景矩阵也让高级功能成为一等测试对象，而不是偶然覆盖。 +- 测试依赖固定到 pi-tui 使用的 xterm 版本。适配器使用 xterm 的拟议缓冲区 API，因此升级 xterm 时必须重新运行并评审语义投影。 +- 模拟器可以建模 ANSI 终端状态，但无法证明每种终端实现独有的行为。真实 PTY 会话覆盖进程选择、键盘输入、用户交互和清理，无需复制完整矩阵。 +- 金标有意固定指定尺寸下的换行与视口行为。布局的预期变更通过无密钥刷新命令更新，并接受常规快照评审。 diff --git a/docs/testing.md b/docs/testing.md index 8d4f0f554f..5f10e1741c 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -7,7 +7,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): boots the real example subprocess, replays a recorded session keyless, diffs normalized stdout + the re-persisted log against committed goldens ([snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). Use `pnpm run test:snapshot:record` when the model transcript should change; use `pnpm run test:snapshot:refresh` when the committed transcript is still the right mock LLM input and replay goldens need keyless rewrite. Review the golden diff. System-prompt/tool-schema content is pinned by ONE scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless goldens cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized stdout plus the re-persisted log ([ACP snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)); the TUI suite parses real ANSI output into semantic terminal-state goldens and retains a real PTY conversation at the process boundary ([TUI snapshot RFC](rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when the committed transcript or scripted events remain correct; review every golden diff. System-prompt/tool-schema content is pinned by ONE ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here @@ -35,4 +35,4 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword ## When a snapshot test is required -Any change affecting the editor-facing transcript or end-to-end agent UX — the ACP bridge, the loop's observable output, tool presentation — adds or updates a scenario in the owning example's snapshot suite (`examples//tests/snapshots/`, a scenario table over the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) suite factory; `examples/acp-agent` is the primary suite), or states in the PR why none applies. New capability seams, lifecycle shapes, or transcript surfaces name their coverage at every tier at plan time and verify the harness can express it — a harness gap is scheduled work, not a mid-build surprise. +Any change affecting an editor-facing transcript or end-to-end agent UX adds or updates a scenario in the owning snapshot suite, or states in the PR why none applies. ACP surfaces use `examples//tests/snapshots/`, a scenario table over the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) suite factory (`examples/acp-agent` is primary); interactive-terminal presentation uses the semantic TUI matrix, with a PTY case when input, Loader selection, or terminal teardown changes. New capability seams, lifecycle shapes, or transcript surfaces name their coverage at every tier at plan time and verify the harness can express it — a harness gap is scheduled work, not a mid-build surprise. diff --git a/examples/coding-agent/tests/fixtures/tui-scripted-llm.ts b/examples/coding-agent/tests/fixtures/tui-scripted-llm.ts new file mode 100644 index 0000000000..2147dfb222 --- /dev/null +++ b/examples/coding-agent/tests/fixtures/tui-scripted-llm.ts @@ -0,0 +1,60 @@ +import type { Context } from 'cordis' +import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' + +const INITIAL_TEXT = 'I need one decision before I continue.' +const FINAL_TEXT = 'Decision received. Scripted TUI run complete.' + +function textChunks(text: string): StreamChunk[] { + return [ + { type: 'block-start', index: 0, blockType: 'text' }, + ...Array.from(text, (char): StreamChunk => ({ type: 'text-delta', index: 0, text: char })), + { type: 'block-end', index: 0, block: { type: 'text', text } }, + { type: 'usage', usage: { inputTokens: 20, outputTokens: text.length } }, + { type: 'finish', reason: { kind: 'stop' } }, + ] +} + +/** Keyless two-step adapter for the real-PTY TUI conversation test. */ +class ScriptedTuiAdapter extends LlmAdapter { + async * stream(options: GenerateOptions): AsyncIterable { + const hasToolResult = options.messages.at(-1)?.content.some(block => block.type === 'tool-result') ?? false + if (hasToolResult) { + for (const chunk of textChunks(FINAL_TEXT)) yield chunk + return + } + + const args = JSON.stringify({ + questions: [{ + id: 'mode', + header: 'Execution mode', + question: 'How should the scripted run proceed?', + options: [ + { label: 'Safe', description: 'Use the guarded path.' }, + { label: 'Fast', description: 'Use the shorter path.' }, + ], + }], + }) + const callId = CallId('call-ask-mode') + yield { type: 'block-start', index: 0, blockType: 'text' } + for (const char of INITIAL_TEXT) yield { type: 'text-delta', index: 0, text: char } + yield { type: 'block-end', index: 0, block: { type: 'text', text: INITIAL_TEXT } } + yield { type: 'block-start', index: 1, blockType: 'tool-call' } + yield { type: 'tool-call-delta', index: 1, id: callId, name: 'ask_user_question', argumentsDelta: args } + yield { + type: 'block-end', + index: 1, + block: { type: 'tool-call', id: callId, name: 'ask_user_question', arguments: args }, + } + yield { type: 'usage', usage: { inputTokens: 20, outputTokens: 10 } } + yield { type: 'finish', reason: { kind: 'tool-calls' } } + } +} + +export const name = 'tui-scripted-llm' +export const inject = ['llm'] + +/** Register the network-free adapter used by the PTY fixture. */ +export function apply(ctx: Context): void { + ctx.llm.registerAdapter(['tui-scripted'], new ScriptedTuiAdapter()) +} diff --git a/examples/coding-agent/tests/fixtures/tui-scripted.cordis.yml b/examples/coding-agent/tests/fixtures/tui-scripted.cordis.yml new file mode 100644 index 0000000000..e40405524e --- /dev/null +++ b/examples/coding-agent/tests/fixtures/tui-scripted.cordis.yml @@ -0,0 +1,27 @@ +# Real Loader composition for the keyless conversational PTY test. The app +# bundle supplies the production agent/TUI/user-question stack; only the model +# is scripted so the terminal interaction is deterministic and network-free. +- id: scripted-llm + name: './tui-scripted-llm.ts' + +- id: bash + name: '@deepseek-ai/dsh-bash-local' + +- id: fs-local + name: '@deepseek-ai/dsh-fs-local' + config: + cwd: !!js process.cwd() + +- id: stdio-agent + name: '@deepseek-ai/dsh-stdio-demo' + config: + provider: tui-scripted + model: tui-scripted-model + persistenceRoot: './.sessions' + workspaceContext: + maxBytes: 65536 + welcome: 'scripted TUI ready.' + ui: + mode: tui + tui: + showReasoning: true diff --git a/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts b/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts index f5f9c5db36..cc2397c069 100644 --- a/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts +++ b/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts @@ -4,31 +4,32 @@ import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' import { describe, expect, it } from 'vitest' -import { LOADER_SMOKE_TEST_TIMEOUT_MS } from '@deepseek-ai/dsh-loader-smoke' +import { LOADER_SMOKE_TEST_TIMEOUT_MS, resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke' const binScript = fileURLToPath(new URL('../../../packages/examples/stdio-demo/src/bin.ts', import.meta.url)) const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) +const scriptedConfigPath = fileURLToPath(new URL('./fixtures/tui-scripted.cordis.yml', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) -const tsxLoader = fileURLToPath(import.meta.resolve('tsx')) const PTY_DRIVER = String.raw` -import errno, os, pty, select, signal, sys, time -node, tsx_loader, bin_script, config_path, tsconfig_path, cwd, resume_session_id = sys.argv[1:] +import errno, json, os, pty, select, signal, sys, time +node, launch_args_json, launch_env_json, cwd, resume_session_id, scenario = sys.argv[1:] env = os.environ.copy() +env.update(json.loads(launch_env_json)) env.update({ - "DEEPSEEK_API_KEY": "keyless-tui-no-call", - "DSH_HOME": os.path.join(cwd, ".dsh"), - "DSH_AGENTS_HOME": os.path.join(cwd, ".agents"), - "TSX_TSCONFIG_PATH": tsconfig_path, + "COLUMNS": "100", + "LINES": "30", }) if resume_session_id: env["RESUME_SESSION_ID"] = resume_session_id pid, fd = pty.fork() if pid == 0: os.chdir(cwd) - os.execvpe(node, [node, "--expose-internals", "--import", tsx_loader, bin_script, config_path], env) + os.execvpe(node, [node, *json.loads(launch_args_json)], env) output = bytearray() +answered_question = False +sent_prompt = False sent_exit = False deadline = time.monotonic() + 25 status = None @@ -43,7 +44,16 @@ while time.monotonic() < deadline: chunk = b"" if chunk: output.extend(chunk) - if not sent_exit and b"agent REPL ready." in output: + if scenario == "conversation" and not sent_prompt and b"scripted TUI ready." in output: + os.write(fd, b"exercise the TUI\r") + sent_prompt = True + if scenario == "conversation" and sent_prompt and not answered_question and b"How should the scripted run proceed?" in output: + os.write(fd, b"\r") + answered_question = True + if scenario == "conversation" and answered_question and not sent_exit and b"Decision received. Scripted TUI run complete." in output: + os.write(fd, b"/exit\r") + sent_exit = True + if scenario == "boot" and not sent_exit and b"agent REPL ready." in output: os.write(fd, b"/exit\r") sent_exit = True waited, candidate = os.waitpid(pid, os.WNOHANG) @@ -55,13 +65,26 @@ if status is None: os.kill(pid, signal.SIGKILL) _, status = os.waitpid(pid, 0) sys.stdout.buffer.write(output) -if resume_session_id: +if scenario == "resume-failure": if b'ui-tui: agent "main" failed to start:' not in output: sys.stderr.write("TUI did not render the startup failure before timeout\n") sys.exit(126) if not os.WIFEXITED(status) or os.WEXITSTATUS(status) != 1: sys.stderr.write("TUI startup failure did not exit with status 1\n") sys.exit(127) +elif scenario == "conversation": + if not sent_prompt: + sys.stderr.write("TUI did not render the scripted welcome marker before timeout\n") + sys.exit(128) + if not answered_question: + sys.stderr.write("TUI did not render the user-question dialog before timeout\n") + sys.exit(129) + if not sent_exit: + sys.stderr.write("TUI did not finish the scripted tool round-trip before timeout\n") + sys.exit(130) + if not os.WIFEXITED(status) or os.WEXITSTATUS(status) != 0: + sys.stderr.write("TUI scripted conversation did not exit cleanly\n") + sys.exit(131) else: if not sent_exit: sys.stderr.write("TUI did not render its welcome marker before timeout\n") @@ -71,20 +94,36 @@ else: sys.exit(125) ` -async function runTuiLoaderSmoke(resumeSessionId = ''): Promise { +interface TuiLoaderSmokeOptions { + config?: string + resumeSessionId?: string + scenario?: 'boot' | 'conversation' | 'resume-failure' +} + +async function runTuiLoaderSmoke(options: TuiLoaderSmokeOptions = {}): Promise { const cwd = await mkdtemp(join(tmpdir(), 'coding-tui-smoke-')) try { + const launch = resolveExampleLaunch({ + srcBin: binScript, + configArgs: [options.config ?? configPath], + tsconfigPath, + exposeInternals: true, + env: { + DEEPSEEK_API_KEY: 'keyless-tui-no-call', + DSH_HOME: join(cwd, '.dsh'), + DSH_AGENTS_HOME: join(cwd, '.agents'), + }, + }) return await new Promise((resolve, reject) => { const child = spawn('python3', [ '-c', PTY_DRIVER, - process.execPath, - tsxLoader, - binScript, - configPath, - tsconfigPath, + launch.command, + JSON.stringify(launch.args), + JSON.stringify(launch.env), cwd, - resumeSessionId, + options.resumeSessionId ?? '', + options.scenario ?? 'boot', ], { stdio: ['ignore', 'pipe', 'pipe'] }) let stdout = '' let stderr = '' @@ -108,10 +147,20 @@ describe('coding-agent TUI keyless smoke (real Loader tree in a PTY)', () => { const output = await runTuiLoaderSmoke() expect(output).toContain('DEEPSEEK') expect(output).toContain('agent REPL ready.') + expect(output).toContain('\u001B[?2004l') + }, LOADER_SMOKE_TEST_TIMEOUT_MS) + + it('streams a response, answers a user-question dialog, completes the tool round-trip, and exits cleanly', async () => { + const output = await runTuiLoaderSmoke({ config: scriptedConfigPath, scenario: 'conversation' }) + expect(output).toContain('I need one decision before I continue.') + expect(output).toContain('How should the scripted run proceed?') + expect(output).toContain('Safe') + expect(output).toContain('Decision received. Scripted TUI run complete.') + expect(output).toContain('\u001B[?2004l') }, LOADER_SMOKE_TEST_TIMEOUT_MS) it('prints a config-resume failure and exits instead of leaving a blank terminal', async () => { - const output = await runTuiLoaderSmoke('missing-session') + const output = await runTuiLoaderSmoke({ resumeSessionId: 'missing-session', scenario: 'resume-failure' }) expect(output).toContain('ui-tui: agent "main" failed to start:') expect(output).toContain('missing-session') }, LOADER_SMOKE_TEST_TIMEOUT_MS) diff --git a/knip.json b/knip.json index 16f83b918b..03fae14896 100644 --- a/knip.json +++ b/knip.json @@ -10,6 +10,7 @@ "examples": { "entry": [ "echo-agent/src/*.ts", + "coding-agent/tests/fixtures/tui-scripted-llm.ts", "*/tests/**/*.e2e.ts", "*/tests/**/*.snapshot.ts" ], @@ -113,6 +114,10 @@ "entry": ["tests/**/*.spec.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, + "packages/ui/tui": { + "entry": ["tests/**/*.spec.ts", "tests/**/*.snapshot.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"] + }, "packages/examples/jsonrpc-demo": { "project": ["src/**/*.ts"] }, diff --git a/packages/ui/tui/package.json b/packages/ui/tui/package.json index e960f33e65..a7ed458ca5 100644 --- a/packages/ui/tui/package.json +++ b/packages/ui/tui/package.json @@ -38,8 +38,13 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-system-prompt": "workspace:^", + "@deepseek-ai/dsh-tool-cordis": "workspace:^", + "@deepseek-ai/dsh-tool-workflow": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "@deepseek-ai/dsh-user-interaction": "workspace:^", + "@deepseek-ai/dsh-workflow": "workspace:^", + "@xterm/headless": "5.5.0", "cordis": "^4.0.0-rc.6" } } diff --git a/packages/ui/tui/tests/harness.ts b/packages/ui/tui/tests/harness.ts new file mode 100644 index 0000000000..52f4159b72 --- /dev/null +++ b/packages/ui/tui/tests/harness.ts @@ -0,0 +1,130 @@ +import { Context } from 'cordis' +import type { Terminal } from '@earendil-works/pi-tui' +import AgentRegistry, { AgentId, type Agent, type AgentStatus } from '@deepseek-ai/dsh-agent' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import SessionStore, { SessionId, type Session } from '@deepseek-ai/dsh-session' +import type { ToolDefinition } from '@deepseek-ai/dsh-tools' +import UserInteractionService from '@deepseek-ai/dsh-user-interaction' +import { createTuiChat, type Config } from '../src/index.ts' + +interface FakeAgent extends Agent { + status: AgentStatus + sent: ContentBlock[][] + steered: ContentBlock[][] + cancelled: string[] +} + +export interface TuiHarnessOptions { + status?: AgentStatus + config?: Config + tools?: Record + configureContext?: (ctx: Context) => Promise + beforeMount?: (session: Session) => void + cwd?: string | null +} + +export interface TuiHarness void> { + ctx: Context + session: Session + agent: FakeAgent + terminal: TerminalType + exit: Exit + controller: ReturnType +} + +/** + * Compose the production TUI around an in-memory session and controllable agent. + * @param terminal - Terminal boundary driven by the test. + * @param exit - Process-exit observer. + * @param options - Initial session, agent, tool, and TUI configuration. + * @returns The mounted TUI and every boundary the test may drive or inspect. + */ +export async function createTuiTestHarness void>( + terminal: TerminalType, + exit: Exit, + options: TuiHarnessOptions = {}, +): Promise> { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) + await ctx.plugin(UserInteractionService) + if (options.configureContext === undefined) { + const tools = options.tools ?? {} + ctx.provide('tools', { + get(name: string) { + return tools[name] + }, + } as never) + } else { + await options.configureContext(ctx) + } + const session = ctx.sessions.create( + SessionId('main-session'), + options.cwd === null ? undefined : { meta: { cwd: options.cwd ?? '/workspace' } }, + ) + options.beforeMount?.(session) + const sent: ContentBlock[][] = [] + const steered: ContentBlock[][] = [] + const cancelled: string[] = [] + const agent: FakeAgent = { + id: AgentId('main'), + options: { model: 'deepseek-v4-flash' }, + session, + status: options.status ?? 'idle', + ctx, + sent, + steered, + cancelled, + send(content) { + sent.push(content) + }, + steer(content) { + steered.push(content) + }, + inject() {}, + cancel(reason) { + cancelled.push(reason ?? '') + }, + whenIdle() { + return Promise.resolve() + }, + } + ctx.agents.register(agent) + const controller = createTuiChat(ctx, Object.assign({ + welcome: 'Coding agent ready.', + agent: 'main', + color: false, + }, options.config), { terminal, exit }) + return { ctx, session, agent, terminal, exit, controller } +} + +/** Dispose the mounted TUI before its owning Cordis context. */ +export async function disposeTuiTestHarness( + setup: Pick void>, 'controller' | 'ctx'>, +): Promise { + await setup.controller.dispose() + await setup.ctx.fiber.dispose() +} + +/** Append a production-shaped user message to the active session surface. */ +export function appendUser(session: Session, text: string): void { + session.append('user/message', { + content: [{ type: 'text', text }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) +} + +/** Append a production-shaped assistant message to the active session surface. */ +export function appendAssistant( + session: Session, + content: ContentBlock[], + usage?: { inputTokens: number; outputTokens: number }, +): void { + session.append('assistant/message', { + turn: 1, + step: 0, + provenance: { provider: 'mock', model: 'deepseek-v4-flash' }, + content, + ...usage === undefined ? {} : { usage }, + }, { surfaceOp: 'append' }) +} diff --git a/packages/ui/tui/tests/headless-terminal.ts b/packages/ui/tui/tests/headless-terminal.ts new file mode 100644 index 0000000000..1155016ab7 --- /dev/null +++ b/packages/ui/tui/tests/headless-terminal.ts @@ -0,0 +1,318 @@ +import type { Terminal } from '@earendil-works/pi-tui' +import { Terminal as XtermTerminal, type IBufferCell } from '@xterm/headless' + +const FRAME_END = '\x1b[?2026l' +const FRAME_TIMEOUT_MS = 2_000 + +const ANSI_COLORS = [ + 'black', + 'red', + 'green', + 'yellow', + 'blue', + 'magenta', + 'cyan', + 'white', + 'bright-black', + 'bright-red', + 'bright-green', + 'bright-yellow', + 'bright-blue', + 'bright-magenta', + 'bright-cyan', + 'bright-white', +] as const + +interface FrameWaiter { + target: number + resolve: () => void + reject: (error: Error) => void + timer: ReturnType +} + +interface RowSnapshot { + text: string + wrapped: boolean + styles: string[] +} + +export interface TerminalSnapshotOptions { + /** Include the whole active buffer instead of only the visible viewport. */ + includeScrollback?: boolean +} + +function occurrenceCount(value: string, needle: string): number { + let count = 0 + let offset = 0 + while (true) { + const match = value.indexOf(needle, offset) + if (match < 0) return count + count += 1 + offset = match + needle.length + } +} + +function colorLabel(cell: IBufferCell, kind: 'fg' | 'bg'): string | undefined { + const isDefault = kind === 'fg' ? cell.isFgDefault() : cell.isBgDefault() + if (isDefault) return undefined + const isRgb = kind === 'fg' ? cell.isFgRGB() : cell.isBgRGB() + const value = kind === 'fg' ? cell.getFgColor() : cell.getBgColor() + if (isRgb) return `${kind}=#${value.toString(16).padStart(6, '0')}` + const name = ANSI_COLORS[value] + return `${kind}=${name ?? `ansi-${value}`}` +} + +function styleLabel(cell: IBufferCell): string { + const labels = [ + colorLabel(cell, 'fg'), + colorLabel(cell, 'bg'), + cell.isBold() !== 0 ? 'bold' : undefined, + cell.isDim() !== 0 ? 'dim' : undefined, + cell.isItalic() !== 0 ? 'italic' : undefined, + cell.isUnderline() !== 0 ? 'underline' : undefined, + cell.isBlink() !== 0 ? 'blink' : undefined, + cell.isInverse() !== 0 ? 'inverse' : undefined, + cell.isInvisible() !== 0 ? 'invisible' : undefined, + cell.isStrikethrough() !== 0 ? 'strike' : undefined, + cell.isOverline() !== 0 ? 'overline' : undefined, + ].filter((label): label is string => label !== undefined) + return labels.join(' ') +} + +function snapshotRow(terminal: XtermTerminal, row: number): RowSnapshot { + const line = terminal.buffer.active.getLine(row) + if (line === undefined) return { text: '', wrapped: false, styles: [] } + const styles: string[] = [] + let activeStyle = '' + let activeStart = 0 + for (let column = 0; column <= terminal.cols; column++) { + const cell = column < terminal.cols ? line.getCell(column) : undefined + const style = cell === undefined ? '' : styleLabel(cell) + if (style === activeStyle) continue + if (activeStyle !== '') styles.push(`${activeStart}-${column - 1} ${activeStyle}`) + activeStyle = style + activeStart = column + } + return { + text: line.translateToString(true), + wrapped: line.isWrapped, + styles, + } +} + +function renderRows(rows: readonly RowSnapshot[], firstRow: number): string[] { + const rendered: string[] = [] + let blankStart: number | undefined + const flushBlanks = (end: number): void => { + if (blankStart === undefined) return + rendered.push(blankStart === end ? `${blankStart}| ` : `${blankStart}-${end}| `) + blankStart = undefined + } + for (let index = 0; index < rows.length; index++) { + const absoluteRow = firstRow + index + const row = rows[index] as RowSnapshot + if (row.text === '' && row.styles.length === 0 && !row.wrapped) { + blankStart ??= absoluteRow + continue + } + flushBlanks(absoluteRow - 1) + rendered.push(`${absoluteRow}${row.wrapped ? '~' : ''}| ${JSON.stringify(row.text)}`) + for (const style of row.styles) rendered.push(` style ${style}`) + } + flushBlanks(firstRow + rows.length - 1) + return rendered +} + +/** + * Terminal emulator used by TUI snapshots. It consumes the same ANSI stream as + * a real terminal and exposes completed synchronized frames as an awaitable boundary. + */ +export class HeadlessTerminal implements Terminal { + readonly kittyProtocolActive = false + readonly drainInput = (): Promise => Promise.resolve() + started = 0 + stopped = 0 + title = '' + progress = false + cursorVisible = true + frames = 0 + private readonly emulator: XtermTerminal + private onInput: (data: string) => void = () => {} + private onResize: () => void = () => {} + private pendingWrite: Promise = Promise.resolve() + private readonly frameWaiters = new Set() + + constructor(columns = 80, rows = 24) { + this.emulator = new XtermTerminal({ + cols: columns, + rows, + scrollback: 1_000, + allowProposedApi: true, + drawBoldTextInBrightColors: false, + logLevel: 'off', + }) + } + + get columns(): number { + return this.emulator.cols + } + + get rows(): number { + return this.emulator.rows + } + + start(onInput: (data: string) => void, onResize: () => void): void { + this.started += 1 + this.onInput = onInput + this.onResize = onResize + } + + stop(): void { + this.stopped += 1 + } + + write(data: string): void { + const completedFrames = occurrenceCount(data, FRAME_END) + this.pendingWrite = new Promise((resolve) => { + this.emulator.write(data, () => { + this.frames += completedFrames + for (const waiter of this.frameWaiters) { + if (this.frames < waiter.target) continue + clearTimeout(waiter.timer) + this.frameWaiters.delete(waiter) + waiter.resolve() + } + resolve() + }) + }) + } + + moveBy(lines: number): void { + if (lines > 0) this.write(`\x1b[${lines}B`) + if (lines < 0) this.write(`\x1b[${-lines}A`) + } + + hideCursor(): void { + this.cursorVisible = false + this.write('\x1b[?25l') + } + + showCursor(): void { + this.cursorVisible = true + this.write('\x1b[?25h') + } + + clearLine(): void { + this.write('\x1b[K') + } + + clearFromCursor(): void { + this.write('\x1b[J') + } + + clearScreen(): void { + this.write('\x1b[2J\x1b[H') + } + + setTitle(title: string): void { + this.title = title + this.write(`\x1b]0;${title}\x07`) + } + + setProgress(active: boolean): void { + this.progress = active + } + + send(data: string): void { + this.onInput(data) + } + + resize(columns: number, rows = this.rows): void { + this.emulator.resize(columns, rows) + this.onResize() + } + + /** Wait until pi-tui completes a synchronized frame newer than `after`. */ + async waitForFrame(after = this.frames): Promise { + if (this.frames <= after) { + await new Promise((resolve, reject) => { + const waiter: FrameWaiter = { + target: after + 1, + resolve, + reject, + timer: setTimeout(() => { + this.frameWaiters.delete(waiter) + reject(new Error(`TUI did not complete frame ${after + 1} within ${FRAME_TIMEOUT_MS}ms`)) + }, FRAME_TIMEOUT_MS), + } + this.frameWaiters.add(waiter) + }) + } + await this.flush() + } + + /** Await every terminal write queued through the current task. */ + async flush(): Promise { + let pending: Promise + do { + pending = this.pendingWrite + await pending + } while (pending !== this.pendingWrite) + } + + /** + * Reject palette output that would become theme-specific in a user's terminal. + * @returns One location per RGB, extended-palette, or explicit-background cell. + */ + themeViolations(): string[] { + const violations: string[] = [] + const buffer = this.emulator.buffer.active + for (let row = 0; row < buffer.length; row++) { + const line = buffer.getLine(row) + if (line === undefined) continue + for (let column = 0; column < this.columns; column++) { + const cell = line.getCell(column) + if (cell === undefined) continue + const reasons = [ + cell.isFgRGB() ? 'rgb-fg' : undefined, + cell.isBgRGB() ? 'rgb-bg' : undefined, + cell.isFgPalette() && cell.getFgColor() > 15 ? `extended-fg-${cell.getFgColor()}` : undefined, + cell.isBgPalette() && cell.getBgColor() > 15 ? `extended-bg-${cell.getBgColor()}` : undefined, + !cell.isBgDefault() ? 'explicit-bg' : undefined, + ].filter((reason): reason is string => reason !== undefined) + if (reasons.length > 0) violations.push(`${row}:${column} ${reasons.join(',')}`) + } + } + return violations + } + + /** Serialize terminal cells and metadata into a stable, reviewable golden. */ + async snapshot(options: TerminalSnapshotOptions = {}): Promise { + await this.flush() + const buffer = this.emulator.buffer.active + const firstRow = options.includeScrollback === true ? 0 : buffer.viewportY + const rowCount = options.includeScrollback === true ? buffer.length : this.rows + const rows = Array.from({ length: rowCount }, (_, index) => snapshotRow(this.emulator, firstRow + index)) + const cursorBufferRow = buffer.baseY + buffer.cursorY + const cursorViewportRow = cursorBufferRow - buffer.viewportY + return [ + `terminal ${this.columns}x${this.rows} buffer=${buffer.type} length=${buffer.length} base=${buffer.baseY} viewport=${buffer.viewportY}`, + `lifecycle started=${this.started} stopped=${this.stopped} progress=${this.progress ? 'active' : 'inactive'}`, + `title ${JSON.stringify(this.title)}`, + `cursor ${this.cursorVisible ? 'visible' : 'hidden'} column=${buffer.cursorX} viewportRow=${cursorViewportRow} bufferRow=${cursorBufferRow}`, + options.includeScrollback === true ? 'buffer' : 'viewport', + ...renderRows(rows, firstRow), + '', + ].join('\n') + } + + async dispose(): Promise { + await this.flush() + for (const waiter of this.frameWaiters) { + clearTimeout(waiter.timer) + waiter.reject(new Error('terminal disposed before the requested frame completed')) + } + this.frameWaiters.clear() + this.emulator.dispose() + } +} diff --git a/packages/ui/tui/tests/snapshots/advanced-cards-collapsed.golden.txt b/packages/ui/tui/tests/snapshots/advanced-cards-collapsed.golden.txt new file mode 100644 index 0000000000..10e6e250b4 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/advanced-cards-collapsed.golden.txt @@ -0,0 +1,107 @@ +terminal 100x40 buffer=normal length=41 base=1 viewport=1 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=37 bufferRow=38 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=green +7| "▌ ✓ pnpm run test:coverage " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-25 bold +8| "▌ Run the coverage gate " + style 0-0 fg=green + style 2-22 fg=bright-black +9| "▌ /workspace/project " + style 0-0 fg=green + style 2-19 dim +10| "▌ packages/ui/tui 100% " + style 0-0 fg=green +11| "▌ … 4 more lines (Ctrl+O to expand) " + style 0-0 fg=green + style 2-34 dim +12| "▌ " + style 0-0 fg=green +13| +14| "▌ " + style 0-0 fg=green +15| "▌ ✓ Edit renderer " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-16 bold +16| "▌ src/view.ts " + style 0-0 fg=green + style 2-12 bold +17| "▌ - old line " + style 0-0 fg=green + style 2-11 fg=red +18| "▌ - keep " + style 0-0 fg=green + style 2-7 fg=red +19| "▌ … 5 more lines (Ctrl+O to expand) " + style 0-0 fg=green + style 2-34 dim +20| "▌ " + style 0-0 fg=green +21| +22| "▌ " + style 0-0 fg=green +23| "▌ ✓ Delegate renderer audit " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-26 bold +24| "▌ The renderer has explicit lifecycle ownership. " + style 0-0 fg=green +25| "▌ " + style 0-0 fg=green +26| +27| "▌ " + style 0-0 fg=green +28| "▌ ✓ Read output from background task subagent-7 " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-46 bold +29| "▌ audit complete " + style 0-0 fg=green +30| "▌ [status: completed] " + style 0-0 fg=green +31| "▌ " + style 0-0 fg=green +32| +33| "▌ " + style 0-0 fg=green +34| "▌ ✓ Load skill dsh-code-review " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-29 bold +35| "▌ Loaded review instructions. " + style 0-0 fg=green +36| "▌ " + style 0-0 fg=green +37| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +38| " " + style 1-1 inverse +39| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +40| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 67-99 dim diff --git a/packages/ui/tui/tests/snapshots/advanced-cards-expanded.golden.txt b/packages/ui/tui/tests/snapshots/advanced-cards-expanded.golden.txt new file mode 100644 index 0000000000..42822d3720 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/advanced-cards-expanded.golden.txt @@ -0,0 +1,127 @@ +terminal 100x40 buffer=normal length=50 base=10 viewport=10 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=37 bufferRow=47 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=green +7| "▌ ✓ pnpm run test:coverage " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-25 bold +8| "▌ Run the coverage gate " + style 0-0 fg=green + style 2-22 fg=bright-black +9| "▌ /workspace/project " + style 0-0 fg=green + style 2-19 dim +10| "▌ packages/ui/tui 100% " + style 0-0 fg=green +11| "▌ 4016 tests passed " + style 0-0 fg=green +12| "▌ 1 test skipped " + style 0-0 fg=green +13| "▌ coverage complete " + style 0-0 fg=green +14| "▌ [exit 0] " + style 0-0 fg=green + style 2-9 dim +15| "▌ " + style 0-0 fg=green +16| +17| "▌ " + style 0-0 fg=green +18| "▌ ✓ Edit renderer " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-16 bold +19| "▌ src/view.ts " + style 0-0 fg=green + style 2-12 bold +20| "▌ - old line " + style 0-0 fg=green + style 2-11 fg=red +21| "▌ - keep " + style 0-0 fg=green + style 2-7 fg=red +22| "▌ + new line " + style 0-0 fg=green + style 2-11 fg=green +23| "▌ + keep " + style 0-0 fg=green + style 2-7 fg=green +24| "▌ " + style 0-0 fg=green +25| "▌ tests/view.spec.ts " + style 0-0 fg=green + style 2-19 bold +26| "▌ + expect(screen).toMatchSnapshot() " + style 0-0 fg=green + style 2-35 fg=green +27| "▌ " + style 0-0 fg=green +28| +29| "▌ " + style 0-0 fg=green +30| "▌ ✓ Delegate renderer audit " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-26 bold +31| "▌ The renderer has explicit lifecycle ownership. " + style 0-0 fg=green +32| "▌ " + style 0-0 fg=green +33| +34| "▌ " + style 0-0 fg=green +35| "▌ ✓ Read output from background task subagent-7 " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-46 bold +36| "▌ audit complete " + style 0-0 fg=green +37| "▌ [status: completed] " + style 0-0 fg=green +38| "▌ " + style 0-0 fg=green +39| +40| "▌ " + style 0-0 fg=green +41| "▌ ✓ Load skill dsh-code-review " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-29 bold +42| "▌ Loaded review instructions. " + style 0-0 fg=green +43| "▌ " + style 0-0 fg=green +44| +45| " Tool cards expanded. " + style 1-20 fg=bright-black +46| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +47| " " + style 1-1 inverse +48| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +49| "/workspace/project ↑0 ↓0 idle reasoning:on tools:expanded" + style 0-24 dim + style 66-99 dim diff --git a/packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt b/packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt new file mode 100644 index 0000000000..72f7fce352 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt @@ -0,0 +1,50 @@ +terminal 96x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=14 bufferRow=14 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=green +7| "▌ ✓ const first = await tools.bash({ command: 'echo CODE_ONE' }) " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-95 bold +8| "▌ const second = await tools.bas " + style 0-0 fg=green + style 2-31 bold +9| "▌ CODE_ONE " + style 0-0 fg=green +10| "▌ CODE_TWO " + style 0-0 fg=green +11| "▌ combined: CODE_ONE+CODE_TWO " + style 0-0 fg=green +12| "▌ " + style 0-0 fg=green +13| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +14| " " + style 1-1 inverse +15| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +16| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 63-95 dim +17-35| diff --git a/packages/ui/tui/tests/snapshots/code-mode-pending.golden.txt b/packages/ui/tui/tests/snapshots/code-mode-pending.golden.txt new file mode 100644 index 0000000000..6908b69890 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/code-mode-pending.golden.txt @@ -0,0 +1,52 @@ +terminal 96x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=15 bufferRow=15 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=yellow +7| "▌ ◌ const first = await tools.bash({ command: 'echo CODE_ONE' }) " + style 0-0 fg=yellow + style 2-2 fg=yellow bold + style 3-95 bold +8| "▌ const second = await tools.bas " + style 0-0 fg=yellow + style 2-31 bold +9| "▌ const first = await tools.bash({ command: 'echo CODE_ONE' }) " + style 0-0 fg=yellow +10| "▌ const second = await tools.bash({ command: 'echo CODE_TWO' }) " + style 0-0 fg=yellow +11| "▌ console.log(first, second) " + style 0-0 fg=yellow +12| "▌ return `${first}+${second}` " + style 0-0 fg=yellow +13| "▌ " + style 0-0 fg=yellow +14| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +15| " " + style 1-1 inverse +16| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +17| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 63-95 dim +18-35| diff --git a/packages/ui/tui/tests/snapshots/conversation-complete.golden.txt b/packages/ui/tui/tests/snapshots/conversation-complete.golden.txt new file mode 100644 index 0000000000..8642d2ffa1 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/conversation-complete.golden.txt @@ -0,0 +1,75 @@ +terminal 96x36 buffer=normal length=43 base=7 viewport=7 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=33 bufferRow=40 +viewport +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Explain snapshot fidelity with cells. " + style 0-0 fg=bright-blue + style 10-26 bold + style 33-37 fg=cyan +9| "▌ " + style 0-0 fg=bright-blue +10| +11| " Reasoning " + style 1-9 fg=bright-black italic +12| " Compare the terminal state, not write fragments. " + style 1-48 fg=bright-black italic +13| +14| " Assistant " + style 1-9 fg=bright-magenta bold +15| " Result " + style 1-6 fg=bright-blue bold +16| " " +17| " - final viewport " + style 1-2 fg=bright-blue +18| " - semantic styles " + style 1-2 fg=bright-blue +19| " " +20| " │ deterministic and reviewable " + style 1-2 fg=bright-magenta + style 3-30 fg=bright-black italic +21| +22| "▌ " + style 0-0 fg=bright-blue +23| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +24| "▌ Show the live update. " + style 0-0 fg=bright-blue +25| "▌ " + style 0-0 fg=bright-blue +26| +27| " Reasoning " + style 1-9 fg=bright-black italic +28| " Inspecting width and styles. " + style 1-28 fg=bright-black italic +29| +30| " Assistant " + style 1-9 fg=bright-magenta bold +31| " Streaming visible state is complete. " + style 11-23 bold +32| +33| " The model reached its output-token limit. " + style 1-41 fg=yellow +34| +35| "Plan" + style 0-3 fg=bright-blue bold +36| " ✓ model the terminal" + style 2-2 fg=green + style 4-21 fg=bright-black +37| " ● capture advanced states" + style 2-2 fg=yellow +38| " ○ verify PTY cleanup" + style 2-2 dim +39| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +40| " " + style 1-1 inverse +41| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +42| "/workspace/project ↑13k ↓760 idle reasoning:on tools:compact" + style 0-28 dim + style 63-95 dim diff --git a/packages/ui/tui/tests/snapshots/conversation-replay.golden.txt b/packages/ui/tui/tests/snapshots/conversation-replay.golden.txt new file mode 100644 index 0000000000..2395db555b --- /dev/null +++ b/packages/ui/tui/tests/snapshots/conversation-replay.golden.txt @@ -0,0 +1,73 @@ +terminal 96x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=27 bufferRow=27 +viewport +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Explain snapshot fidelity with cells. " + style 0-0 fg=bright-blue + style 10-26 bold + style 33-37 fg=cyan +9| "▌ " + style 0-0 fg=bright-blue +10| +11| " Reasoning " + style 1-9 fg=bright-black italic +12| " Compare the terminal state, not write fragments. " + style 1-48 fg=bright-black italic +13| +14| " Assistant " + style 1-9 fg=bright-magenta bold +15| " Result " + style 1-6 fg=bright-blue bold +16| " " +17| " - final viewport " + style 1-2 fg=bright-blue +18| " - semantic styles " + style 1-2 fg=bright-blue +19| " " +20| " │ deterministic and reviewable " + style 1-2 fg=bright-magenta + style 3-30 fg=bright-black italic +21| +22| "Plan" + style 0-3 fg=bright-blue bold +23| " ✓ model the terminal" + style 2-2 fg=green + style 4-21 fg=bright-black +24| " ● capture advanced states" + style 2-2 fg=yellow +25| " ○ verify PTY cleanup" + style 2-2 dim +26| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +27| " " + style 1-1 inverse +28| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +29| "/workspace/project ↑13k ↓640 idle reasoning:on tools:compact" + style 0-28 dim + style 63-95 dim +30-35| diff --git a/packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt b/packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt new file mode 100644 index 0000000000..55044a44f9 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt @@ -0,0 +1,75 @@ +terminal 96x36 buffer=normal length=41 base=5 viewport=5 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=33 bufferRow=38 +viewport +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Explain snapshot fidelity with cells. " + style 0-0 fg=bright-blue + style 10-26 bold + style 33-37 fg=cyan +9| "▌ " + style 0-0 fg=bright-blue +10| +11| " Reasoning " + style 1-9 fg=bright-black italic +12| " Compare the terminal state, not write fragments. " + style 1-48 fg=bright-black italic +13| +14| " Assistant " + style 1-9 fg=bright-magenta bold +15| " Result " + style 1-6 fg=bright-blue bold +16| " " +17| " - final viewport " + style 1-2 fg=bright-blue +18| " - semantic styles " + style 1-2 fg=bright-blue +19| " " +20| " │ deterministic and reviewable " + style 1-2 fg=bright-magenta + style 3-30 fg=bright-black italic +21| +22| "▌ " + style 0-0 fg=bright-blue +23| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +24| "▌ Show the live update. " + style 0-0 fg=bright-blue +25| "▌ " + style 0-0 fg=bright-blue +26| +27| " Reasoning " + style 1-9 fg=bright-black italic +28| " Inspecting width and styles. " + style 1-28 fg=bright-black italic +29| +30| " Assistant " + style 1-9 fg=bright-magenta bold +31| " Streaming visible state… " + style 11-23 bold +32| +33| "Plan" + style 0-3 fg=bright-blue bold +34| " ✓ model the terminal" + style 2-2 fg=green + style 4-21 fg=bright-black +35| " ● capture advanced states" + style 2-2 fg=yellow +36| " ○ verify PTY cleanup" + style 2-2 dim +37| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +38| " " + style 1-1 inverse +39| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +40| "/workspace/project ↑13k ↓640 idle reasoning:on tools:compact" + style 0-28 dim + style 63-95 dim diff --git a/packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt b/packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt new file mode 100644 index 0000000000..d33b56d7ce --- /dev/null +++ b/packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt @@ -0,0 +1,73 @@ +terminal 96x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=25 bufferRow=25 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=green +7| "▌ ✓ Inspect cordis runtime: tools " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-32 bold +8| "▌ ## tools " + style 0-0 fg=green +9| "▌ run_code " + style 0-0 fg=green +10| "▌ workflow " + style 0-0 fg=green +11| "▌ cordis_mount " + style 0-0 fg=green +12| "▌ cordis_unmount " + style 0-0 fg=green +13| "▌ " + style 0-0 fg=green +14| +15| "▌ " + style 0-0 fg=green +16| "▌ ✓ Mount plugin into live cordis runtime " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-40 bold +17| "▌ mounted dyn-1 (plugin \"snapshot-marker\", state: active) " + style 0-0 fg=green +18| "▌ " + style 0-0 fg=green +19| +20| "▌ " + style 0-0 fg=green +21| "▌ ✓ Unmount dyn-1 " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-16 bold +22| "▌ unmounted dyn-1 (plugin \"snapshot-marker\") " + style 0-0 fg=green +23| "▌ " + style 0-0 fg=green +24| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +25| " " + style 1-1 inverse +26| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +27| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 63-95 dim +28-35| diff --git a/packages/ui/tui/tests/snapshots/cordis-tools-pending.golden.txt b/packages/ui/tui/tests/snapshots/cordis-tools-pending.golden.txt new file mode 100644 index 0000000000..eb44cb6b94 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/cordis-tools-pending.golden.txt @@ -0,0 +1,59 @@ +terminal 96x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=18 bufferRow=18 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue +5| +6| "▌ ◌ Inspect cordis runtime: tools " + style 0-0 fg=yellow + style 2-2 fg=yellow bold + style 3-32 bold +7| +8| "▌ " + style 0-0 fg=yellow +9| "▌ ◌ Mount plugin into live cordis runtime " + style 0-0 fg=yellow + style 2-2 fg=yellow bold + style 3-40 bold +10| "▌ { " + style 0-0 fg=yellow +11| "▌ \"code\": \"return { name: 'snapshot-marker', apply(ctx) { ctx.provide('snapshotMarker', { " + style 0-0 fg=yellow +12| "▌ ready: true }) } }\" " + style 0-0 fg=yellow +13| "▌ } " + style 0-0 fg=yellow +14| "▌ " + style 0-0 fg=yellow +15| +16| "▌ ◌ Unmount dyn-1 " + style 0-0 fg=yellow + style 2-2 fg=yellow bold + style 3-16 bold +17| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +18| " " + style 1-1 inverse +19| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +20| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 63-95 dim +21-35| diff --git a/packages/ui/tui/tests/snapshots/disposed-terminal.golden.txt b/packages/ui/tui/tests/snapshots/disposed-terminal.golden.txt new file mode 100644 index 0000000000..6a008f4032 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/disposed-terminal.golden.txt @@ -0,0 +1,52 @@ +terminal 92x32 buffer=normal length=32 base=0 viewport=0 +lifecycle started=1 stopped=1 progress=inactive +title "DSH snapshot" +cursor visible column=0 viewportRow=22 bufferRow=22 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-91 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 91-91 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 91-91 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 91-91 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-91 fg=bright-blue +5| +6| " Keyboard shortcuts " + style 1-18 fg=bright-blue bold +7| " Enter send • Shift/Alt+Enter newline • Up/Down prompt history " + style 1-61 fg=bright-black +8| " Esc cancel active turn • Ctrl+O expand tool cards • Ctrl+R toggle reasoning " + style 1-75 fg=bright-black +9| " Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit " + style 1-73 fg=bright-black +10| " /help /clear /cancel /reasoning /tools /redraw /exit " + style 1-52 fg=bright-black +11| +12| " Unknown command: /unknown-advanced-command " + style 1-42 fg=yellow +13| +14| " provider stream failed after partial output " + style 1-43 fg=red +15| +16| " The previous process ended during this turn. " + style 1-44 fg=yellow +17| "────────────────────────────────────────────────────────────────────────────────────────────" + style 0-91 dim +18| " " + style 1-1 inverse +19| "────────────────────────────────────────────────────────────────────────────────────────────" + style 0-91 dim +20| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 59-91 dim +21-31| diff --git a/packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt b/packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt new file mode 100644 index 0000000000..00da73a956 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt @@ -0,0 +1,53 @@ +terminal 96x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=16 bufferRow=16 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=green +7| "▌ ✓ workflow: tui-matrix " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-23 bold +8| "▌ workflow \"tui-matrix\" completed (2 agents). " + style 0-0 fg=green +9| "▌ Return value: " + style 0-0 fg=green +10| "▌ { " + style 0-0 fg=green +11| "▌ \"reports\": [\"layout ok\", \"lifecycle ok\"], " + style 0-0 fg=green +12| "▌ \"verdict\": \"covered\" " + style 0-0 fg=green +13| "▌ } " + style 0-0 fg=green +14| "▌ " + style 0-0 fg=green +15| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +16| " " + style 1-1 inverse +17| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +18| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 63-95 dim +19-35| diff --git a/packages/ui/tui/tests/snapshots/dynamic-workflow-pending.golden.txt b/packages/ui/tui/tests/snapshots/dynamic-workflow-pending.golden.txt new file mode 100644 index 0000000000..0e9849bc76 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/dynamic-workflow-pending.golden.txt @@ -0,0 +1,55 @@ +terminal 96x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=17 bufferRow=17 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=yellow +7| "▌ ◌ workflow: tui-matrix " + style 0-0 fg=yellow + style 2-2 fg=yellow bold + style 3-23 bold +8| "▌ phase('Inspect') " + style 0-0 fg=yellow +9| "▌ const reports = await parallel([ " + style 0-0 fg=yellow +10| "▌ () => agent('Audit layout', { label: 'layout', phase: 'Inspect' }), " + style 0-0 fg=yellow +11| "▌ () => agent('Audit lifecycle', { label: 'lifecycle', phase: 'Inspect' }), " + style 0-0 fg=yellow +12| "▌ ]) " + style 0-0 fg=yellow +13| "▌ phase('Verify') " + style 0-0 fg=yellow +14| "▌ return { reports, verdict: 'covered' } " + style 0-0 fg=yellow +15| "▌ " + style 0-0 fg=yellow +16| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +17| " " + style 1-1 inverse +18| "────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-95 dim +19| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 63-95 dim +20-35| diff --git a/packages/ui/tui/tests/snapshots/errors-and-help.golden.txt b/packages/ui/tui/tests/snapshots/errors-and-help.golden.txt new file mode 100644 index 0000000000..fb7a119735 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/errors-and-help.golden.txt @@ -0,0 +1,52 @@ +terminal 92x32 buffer=normal length=32 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=18 bufferRow=18 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-91 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 91-91 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 91-91 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 91-91 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-91 fg=bright-blue +5| +6| " Keyboard shortcuts " + style 1-18 fg=bright-blue bold +7| " Enter send • Shift/Alt+Enter newline • Up/Down prompt history " + style 1-61 fg=bright-black +8| " Esc cancel active turn • Ctrl+O expand tool cards • Ctrl+R toggle reasoning " + style 1-75 fg=bright-black +9| " Ctrl+C cancel while running; clear input or exit while idle • Ctrl+D exit " + style 1-73 fg=bright-black +10| " /help /clear /cancel /reasoning /tools /redraw /exit " + style 1-52 fg=bright-black +11| +12| " Unknown command: /unknown-advanced-command " + style 1-42 fg=yellow +13| +14| " provider stream failed after partial output " + style 1-43 fg=red +15| +16| " The previous process ended during this turn. " + style 1-44 fg=yellow +17| "────────────────────────────────────────────────────────────────────────────────────────────" + style 0-91 dim +18| " " + style 1-1 inverse +19| "────────────────────────────────────────────────────────────────────────────────────────────" + style 0-91 dim +20| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 59-91 dim +21-31| diff --git a/packages/ui/tui/tests/snapshots/question-dialog-validation.golden.txt b/packages/ui/tui/tests/snapshots/question-dialog-validation.golden.txt new file mode 100644 index 0000000000..3704b8e510 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/question-dialog-validation.golden.txt @@ -0,0 +1,69 @@ +terminal 56x20 buffer=normal length=20 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=56 viewportRow=13 bufferRow=13 +viewport +0| "╭──────────────────────────────────────────────────────╮" + style 0-55 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 55-55 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 55-55 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 55-55 fg=bright-blue +4| "╰───╭ Coverage ────────────────────────────────────╮───╯" + style 0-55 fg=bright-blue +5| "────│ Which advanced TUI states belong in the │────" + style 0-3 dim + style 4-4 fg=bright-blue + style 6-50 bold + style 51-51 fg=bright-blue bold + style 52-55 dim +6| " │ required matrix? │ " + style 1-1 inverse + style 4-4 fg=bright-blue + style 6-21 bold + style 51-51 fg=bright-blue +7| "────│ │────" + style 0-3 dim + style 4-4 fg=bright-blue + style 51-51 fg=bright-blue + style 52-55 dim +8| "/wor│ › [ ] Code Mode — run_code programs and capt │:com" + style 0-3 dim + style 4-4 fg=bright-blue + style 6-6 fg=bright-blue inverse + style 7-20 inverse + style 21-49 fg=bright-black inverse + style 51-51 fg=bright-blue + style 52-55 dim +9| " │ [ ] Workflows — phases and parallel agents │ " + style 4-4 fg=bright-blue + style 21-49 fg=bright-black + style 51-51 fg=bright-blue +10| " │ [ ] Cordis tools — inspect, mount, and unm │ " + style 4-4 fg=bright-blue + style 24-49 fg=bright-black + style 51-51 fg=bright-blue +11| " │ 1/4 │ " + style 4-4 fg=bright-blue + style 6-8 dim + style 51-51 fg=bright-blue +12| " │ ↑↓ navigate • Space toggle • Enter submit • │ " + style 4-4 fg=bright-blue + style 6-49 dim + style 51-51 fg=bright-blue +13| " │ Select at least one option, or press C for a │ " + style 4-4 fg=bright-blue + style 6-49 fg=red + style 51-51 fg=bright-blue +14| " ╰──────────────────────────────────────────────╯ " + style 4-51 fg=bright-blue +15-19| diff --git a/packages/ui/tui/tests/snapshots/question-dialog.golden.txt b/packages/ui/tui/tests/snapshots/question-dialog.golden.txt new file mode 100644 index 0000000000..8c1565fdda --- /dev/null +++ b/packages/ui/tui/tests/snapshots/question-dialog.golden.txt @@ -0,0 +1,67 @@ +terminal 56x20 buffer=normal length=20 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=0 viewportRow=19 bufferRow=19 +viewport +0| "╭──────────────────────────────────────────────────────╮" + style 0-55 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 55-55 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 55-55 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 55-55 fg=bright-blue +4| "╰──────────────────────────────────────────────────────╯" + style 0-55 fg=bright-blue +5| "────╭ Coverage ────────────────────────────────────╮────" + style 0-3 dim + style 4-51 fg=bright-blue + style 52-55 dim +6| " │ Which advanced TUI states belong in the │ " + style 1-1 inverse + style 4-4 fg=bright-blue + style 6-50 bold + style 51-51 fg=bright-blue bold +7| "────│ required matrix? │────" + style 0-3 dim + style 4-4 fg=bright-blue + style 6-21 bold + style 51-51 fg=bright-blue + style 52-55 dim +8| "/wor│ │:com" + style 0-3 dim + style 4-4 fg=bright-blue + style 51-51 fg=bright-blue + style 52-55 dim +9| " │ › [ ] Code Mode — run_code programs and capt │ " + style 4-4 fg=bright-blue + style 6-6 fg=bright-blue inverse + style 7-20 inverse + style 21-49 fg=bright-black inverse + style 51-51 fg=bright-blue +10| " │ [ ] Workflows — phases and parallel agents │ " + style 4-4 fg=bright-blue + style 21-49 fg=bright-black + style 51-51 fg=bright-blue +11| " │ [ ] Cordis tools — inspect, mount, and unm │ " + style 4-4 fg=bright-blue + style 24-49 fg=bright-black + style 51-51 fg=bright-blue +12| " │ 1/4 │ " + style 4-4 fg=bright-blue + style 6-8 dim + style 51-51 fg=bright-blue +13| " │ ↑↓ navigate • Space toggle • Enter submit • │ " + style 4-4 fg=bright-blue + style 6-49 dim + style 51-51 fg=bright-blue +14| " ╰──────────────────────────────────────────────╯ " + style 4-51 fg=bright-blue +15-19| diff --git a/packages/ui/tui/tests/snapshots/surface-after-compaction-narrow.golden.txt b/packages/ui/tui/tests/snapshots/surface-after-compaction-narrow.golden.txt new file mode 100644 index 0000000000..429cebfb84 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/surface-after-compaction-narrow.golden.txt @@ -0,0 +1,45 @@ +terminal 44x18 buffer=normal length=18 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=12 bufferRow=12 +buffer +0| "╭──────────────────────────────────────────╮" + style 0-43 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 43-43 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 43-43 fg=bright-blue +3| "│ main • deepseek-v4-flash • │" + style 0-0 fg=bright-blue + style 2-42 dim + style 43-43 fg=bright-blue dim +4| "│ main-session │" + style 0-0 fg=bright-blue + style 2-13 dim + style 43-43 fg=bright-blue +5| "╰──────────────────────────────────────────╯" + style 0-43 fg=bright-blue +6| +7| " Context · compact " + style 1-17 dim +8| " Compacted summary: the prior command " + style 1-43 fg=bright-black +9| " completed and its details were retired " + style 1-43 fg=bright-black +10| " from the active surface. " + style 1-24 fg=bright-black +11| "────────────────────────────────────────────" + style 0-43 dim +12| " " + style 1-1 inverse +13| "────────────────────────────────────────────" + style 0-43 dim +14| "/workspace/project ↑0 ↓0 idle reasoning:o" + style 0-24 dim + style 27-43 dim +15-17| diff --git a/packages/ui/tui/tests/snapshots/surface-after-compaction-wide.golden.txt b/packages/ui/tui/tests/snapshots/surface-after-compaction-wide.golden.txt new file mode 100644 index 0000000000..06380259af --- /dev/null +++ b/packages/ui/tui/tests/snapshots/surface-after-compaction-wide.golden.txt @@ -0,0 +1,37 @@ +terminal 104x30 buffer=normal length=30 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=9 bufferRow=9 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-103 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 103-103 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 103-103 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 103-103 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-103 fg=bright-blue +5| +6| " Context · compact " + style 1-17 dim +7| " Compacted summary: the prior command completed and its details were retired from the active surface. " + style 1-100 fg=bright-black +8| "────────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-103 dim +9| " " + style 1-1 inverse +10| "────────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-103 dim +11| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 71-103 dim +12-29| diff --git a/packages/ui/tui/tests/snapshots/surface-before-compaction.golden.txt b/packages/ui/tui/tests/snapshots/surface-before-compaction.golden.txt new file mode 100644 index 0000000000..eaad66daf8 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/surface-before-compaction.golden.txt @@ -0,0 +1,67 @@ +terminal 80x24 buffer=normal length=25 base=1 viewport=1 +lifecycle started=1 stopped=0 progress=inactive +title "DSH snapshot" +cursor hidden column=1 viewportRow=21 bufferRow=22 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────╮" + style 0-79 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 79-79 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 79-79 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 79-79 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────╯" + style 0-79 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Old prompt with a long line that exercises wrapping before compaction. " + style 0-0 fg=bright-blue +9| "▌ " + style 0-0 fg=bright-blue +10| +11| "▌ " + style 0-0 fg=green +12| "▌ ✓ pnpm run test:coverage " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-25 bold +13| "▌ Run the coverage gate " + style 0-0 fg=green + style 2-22 fg=bright-black +14| "▌ /workspace/project " + style 0-0 fg=green + style 2-19 dim +15| "▌ packages/ui/tui 100% " + style 0-0 fg=green +16| "▌ 4016 tests passed " + style 0-0 fg=green +17| "▌ 1 test skipped " + style 0-0 fg=green +18| "▌ coverage complete " + style 0-0 fg=green +19| "▌ [exit 0] " + style 0-0 fg=green + style 2-9 dim +20| "▌ " + style 0-0 fg=green +21| "────────────────────────────────────────────────────────────────────────────────" + style 0-79 dim +22| " " + style 1-1 inverse +23| "────────────────────────────────────────────────────────────────────────────────" + style 0-79 dim +24| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 47-79 dim diff --git a/packages/ui/tui/tests/tui.snapshot.ts b/packages/ui/tui/tests/tui.snapshot.ts new file mode 100644 index 0000000000..eb6d5e9965 --- /dev/null +++ b/packages/ui/tui/tests/tui.snapshot.ts @@ -0,0 +1,472 @@ +import { mkdir, readdir, writeFile } from 'node:fs/promises' +import { dirname, join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { afterAll, describe, expect, it } from 'vitest' +import type { Context } from 'cordis' +import { CallId, type ContentBlock } from '@deepseek-ai/dsh-llm' +import type { Session } from '@deepseek-ai/dsh-session' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { type ToolDefinition, type ToolResultView } from '@deepseek-ai/dsh-tools' +import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis' +import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' +import { + appendAssistant, + appendUser, + createTuiTestHarness, + disposeTuiTestHarness, + type TuiHarness, + type TuiHarnessOptions, +} from './harness.ts' +import { HeadlessTerminal, type TerminalSnapshotOptions } from './headless-terminal.ts' + +const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') +const REFRESHING = process.env.DSH_SNAPSHOT === 'refresh' + +const CHECKPOINTS = [ + 'conversation-replay', + 'conversation-streaming', + 'conversation-complete', + 'code-mode-pending', + 'code-mode-complete', + 'dynamic-workflow-pending', + 'dynamic-workflow-complete', + 'cordis-tools-pending', + 'cordis-tools-complete', + 'advanced-cards-collapsed', + 'advanced-cards-expanded', + 'question-dialog', + 'question-dialog-validation', + 'surface-before-compaction', + 'surface-after-compaction-narrow', + 'surface-after-compaction-wide', + 'errors-and-help', + 'disposed-terminal', +] as const + +type Checkpoint = typeof CHECKPOINTS[number] +type SnapshotHarness = TuiHarness void> + +const observedCheckpoints = new Set() + +async function checkpoint( + name: Checkpoint, + terminal: HeadlessTerminal, + options: TerminalSnapshotOptions = {}, +): Promise { + observedCheckpoints.add(name) + expect(terminal.themeViolations(), `${name} must remain theme-agnostic`).toEqual([]) + const snapshot = await terminal.snapshot(options) + const path = join(SNAPSHOTS_DIR, `${name}.golden.txt`) + if (REFRESHING) { + await mkdir(SNAPSHOTS_DIR, { recursive: true }) + await writeFile(path, snapshot) + } + await expect(snapshot).toMatchFileSnapshot(path) +} + +async function setupSnapshot( + options: TuiHarnessOptions = {}, + size: { columns?: number; rows?: number } = {}, +): Promise { + const terminal = new HeadlessTerminal(size.columns ?? 96, size.rows ?? 36) + const before = terminal.frames + const result = await createTuiTestHarness(terminal, () => {}, { + ...options, + cwd: options.cwd === undefined ? '/workspace/project' : options.cwd, + config: Object.assign({ + welcome: 'Snapshot agent ready.', + color: true, + title: 'DSH snapshot', + }, options.config), + }) + await terminal.waitForFrame(before) + return result +} + +async function renderAfter(harness: SnapshotHarness, action: () => void): Promise { + const before = harness.terminal.frames + action() + await harness.terminal.waitForFrame(before) +} + +async function disposeSnapshot(harness: SnapshotHarness): Promise { + await disposeTuiTestHarness(harness) + await harness.terminal.dispose() +} + +async function configureAdvancedTools(ctx: Context): Promise { + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry, { mode: 'code' }) + ctx.provide('workflows', {} as never) + await ctx.plugin(ToolWorkflow, { toolName: 'workflow', maxResultChars: 50_000 }) + await ctx.plugin(ToolCordis, { vmTimeoutMs: 5_000 }) +} + +interface ToolCallFixture { + id: string + name: string + arguments: unknown +} + +function appendToolCalls(session: Session, calls: readonly ToolCallFixture[]): void { + appendAssistant(session, calls.map(call => ({ + type: 'tool-call', + id: CallId(call.id), + name: call.name, + arguments: JSON.stringify(call.arguments), + }))) + for (const call of calls) { + session.append('tool/call', { + turn: 1, + step: 0, + callId: CallId(call.id), + name: call.name, + arguments: JSON.stringify(call.arguments), + }) + } +} + +function appendToolResult( + session: Session, + id: string, + content: ContentBlock[], + options: { isError?: boolean; meta?: unknown } = {}, +): void { + session.append('tool/result', { + turn: 1, + step: 0, + callId: CallId(id), + content, + isError: options.isError ?? false, + ...options.meta === undefined ? {} : { meta: options.meta }, + }, { surfaceOp: 'append' }) +} + +function visualTool( + name: string, + call: NonNullable, + result?: NonNullable, +): ToolDefinition { + return { + name, + description: `${name} snapshot fixture`, + parameters: {}, + execute: () => Promise.resolve([]), + presentCall: call, + ...result === undefined ? {} : { presentResult: result }, + } +} + +const ADVANCED_CARD_TOOLS: Record = { + bash: visualTool( + 'bash', + () => ({ card: 'terminal', title: 'pnpm run test:coverage', description: 'Run the coverage gate', cwd: '/workspace/project' }), + () => ({ card: 'terminal', output: 'packages/ui/tui 100%\n4016 tests passed\n1 test skipped\ncoverage complete', exitCode: 0 }), + ), + edit: visualTool( + 'edit', + () => ({ card: 'diff', title: 'Edit renderer', diffs: [{ path: 'src/view.ts', oldText: 'old line', newText: 'new line' }] }), + (): ToolResultView => ({ + card: 'diff', + diffs: [ + { path: 'src/view.ts', oldText: 'old line\nkeep', newText: 'new line\nkeep' }, + { path: 'tests/view.spec.ts', oldText: null, newText: 'expect(screen).toMatchSnapshot()' }, + ], + }), + ), + subagent: visualTool('subagent', args => ({ + card: 'generic', + title: 'Delegate renderer audit', + rawInput: (args as { prompt: string }).prompt, + })), + task_output: visualTool('task_output', args => ({ + card: 'generic', + kind: 'read', + title: `Read output from background task ${(args as { task_id: string }).task_id}`, + rawInput: (args as { task_id: string }).task_id, + })), + skill: visualTool('skill', args => ({ + card: 'generic', + kind: 'read', + title: `Load skill ${(args as { name: string }).name}`, + rawInput: (args as { name: string }).name, + })), +} + +describe('TUI terminal-state snapshots', () => { + it('pins resumed conversation, streaming, completion, plans, tokens, and Markdown', async () => { + const harness = await setupSnapshot({ + beforeMount(session) { + appendUser(session, 'Explain **snapshot fidelity** with `cells`.') + appendAssistant(session, [ + { type: 'reasoning', text: 'Compare the terminal state, not write fragments.' }, + { type: 'text', text: '## Result\n\n- final viewport\n- semantic styles\n\n> deterministic and reviewable' }, + ], { inputTokens: 12_500, outputTokens: 640 }) + session.append('todo/write', { + todos: [ + { content: 'model the terminal', status: 'completed' }, + { content: 'capture advanced states', status: 'in_progress' }, + { content: 'verify PTY cleanup', status: 'pending' }, + ], + }) + }, + }) + await checkpoint('conversation-replay', harness.terminal) + + await renderAfter(harness, () => { + appendUser(harness.session, 'Show the live update.') + harness.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-start', index: 0, blockType: 'reasoning' }, + }) + harness.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'reasoning-delta', index: 0, text: 'Inspecting width and styles.' }, + }) + harness.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'block-start', index: 1, blockType: 'text' }, + }) + harness.session.append('assistant/chunk', { + turn: 2, + step: 0, + chunk: { type: 'text-delta', index: 1, text: 'Streaming **visible state**…' }, + }) + }) + await checkpoint('conversation-streaming', harness.terminal) + + await renderAfter(harness, () => { + appendAssistant(harness.session, [ + { type: 'reasoning', text: 'Inspecting width and styles.' }, + { type: 'text', text: 'Streaming **visible state** is complete.' }, + ], { inputTokens: 800, outputTokens: 120 }) + harness.session.append('turn/end', { turn: 2, reason: { kind: 'max-tokens' } }) + }) + await checkpoint('conversation-complete', harness.terminal) + await disposeSnapshot(harness) + }) + + it('pins Code Mode run_code with its production presenter', async () => { + const harness = await setupSnapshot({ configureContext: configureAdvancedTools }) + const call = { + id: 'code-1', + name: 'run_code', + arguments: { + code: "const first = await tools.bash({ command: 'echo CODE_ONE' })\nconst second = await tools.bash({ command: 'echo CODE_TWO' })\nconsole.log(first, second)\nreturn `${first}+${second}`", + }, + } + await renderAfter(harness, () => { appendToolCalls(harness.session, [call]) }) + await checkpoint('code-mode-pending', harness.terminal, { includeScrollback: true }) + + await renderAfter(harness, () => { + appendToolResult(harness.session, call.id, [{ type: 'text', text: 'CODE_ONE\n+CODE_TWO' }], { + meta: { logs: ['CODE_ONE', 'CODE_TWO', 'combined: CODE_ONE+CODE_TWO'] }, + }) + }) + await checkpoint('code-mode-complete', harness.terminal, { includeScrollback: true }) + await disposeSnapshot(harness) + }) + + it('pins a dynamic workflow with phases, parallel agents, and structured output', async () => { + const harness = await setupSnapshot({ configureContext: configureAdvancedTools }) + const call = { + id: 'workflow-1', + name: 'workflow', + arguments: { + meta: { + name: 'tui-matrix', + description: 'Audit terminal states from independent angles', + phases: [ + { title: 'Inspect', detail: 'Map renderer branches' }, + { title: 'Verify', detail: 'Challenge missing states', provider: 'deepseek', model: 'deepseek-v4-flash' }, + ], + }, + args: { packages: ['ui/tui', 'workflow/tool-workflow'] }, + script: "phase('Inspect')\nconst reports = await parallel([\n () => agent('Audit layout', { label: 'layout', phase: 'Inspect' }),\n () => agent('Audit lifecycle', { label: 'lifecycle', phase: 'Inspect' }),\n])\nphase('Verify')\nreturn { reports, verdict: 'covered' }", + }, + } + await renderAfter(harness, () => { appendToolCalls(harness.session, [call]) }) + await checkpoint('dynamic-workflow-pending', harness.terminal, { includeScrollback: true }) + + await renderAfter(harness, () => { + appendToolResult(harness.session, call.id, [{ + type: 'text', + text: 'workflow "tui-matrix" completed (2 agents).\nReturn value:\n{\n "reports": ["layout ok", "lifecycle ok"],\n "verdict": "covered"\n}', + }]) + }) + await checkpoint('dynamic-workflow-complete', harness.terminal, { includeScrollback: true }) + await disposeSnapshot(harness) + }) + + it('pins cordis inspect, dynamic mount, and unmount cards with production presenters', async () => { + const harness = await setupSnapshot({ configureContext: configureAdvancedTools }) + const calls = [ + { id: 'cordis-1', name: 'cordis_inspect', arguments: { what: 'tools' } }, + { + id: 'cordis-2', + name: 'cordis_mount', + arguments: { code: "return { name: 'snapshot-marker', apply(ctx) { ctx.provide('snapshotMarker', { ready: true }) } }" }, + }, + { id: 'cordis-3', name: 'cordis_unmount', arguments: { id: 'dyn-1' } }, + ] + await renderAfter(harness, () => { appendToolCalls(harness.session, calls) }) + await checkpoint('cordis-tools-pending', harness.terminal, { includeScrollback: true }) + + await renderAfter(harness, () => { + appendToolResult(harness.session, 'cordis-1', [{ type: 'text', text: '## tools\nrun_code\nworkflow\ncordis_mount\ncordis_unmount' }]) + appendToolResult(harness.session, 'cordis-2', [{ type: 'text', text: 'mounted dyn-1 (plugin "snapshot-marker", state: active)' }]) + appendToolResult(harness.session, 'cordis-3', [{ type: 'text', text: 'unmounted dyn-1 (plugin "snapshot-marker")' }]) + }) + await checkpoint('cordis-tools-complete', harness.terminal, { includeScrollback: true }) + await disposeSnapshot(harness) + }) + + it('pins terminal, diff, subagent, task, skill, collapsed, and expanded cards', async () => { + const harness = await setupSnapshot({ + tools: ADVANCED_CARD_TOOLS, + config: { maxToolOutputLines: 3 }, + }, { columns: 100, rows: 40 }) + const calls = [ + { id: 'advanced-1', name: 'bash', arguments: { command: 'pnpm run test:coverage' } }, + { id: 'advanced-2', name: 'edit', arguments: { file_path: 'src/view.ts' } }, + { id: 'advanced-3', name: 'subagent', arguments: { prompt: 'Review renderer ownership and report only gaps.' } }, + { id: 'advanced-4', name: 'task_output', arguments: { task_id: 'subagent-7', wait: true } }, + { id: 'advanced-5', name: 'skill', arguments: { name: 'dsh-code-review' } }, + ] + await renderAfter(harness, () => { + appendToolCalls(harness.session, calls) + appendToolResult(harness.session, 'advanced-1', [{ type: 'text', text: 'raw process output' }]) + appendToolResult(harness.session, 'advanced-2', [{ type: 'text', text: 'edit complete' }]) + appendToolResult(harness.session, 'advanced-3', [{ type: 'text', text: 'The renderer has explicit lifecycle ownership.' }]) + appendToolResult(harness.session, 'advanced-4', [{ type: 'text', text: 'audit complete\n[status: completed]' }]) + appendToolResult(harness.session, 'advanced-5', [{ type: 'text', text: 'Loaded review instructions.' }]) + }) + await checkpoint('advanced-cards-collapsed', harness.terminal, { includeScrollback: true }) + + await renderAfter(harness, () => { harness.terminal.send('\x0f') }) + await checkpoint('advanced-cards-expanded', harness.terminal, { includeScrollback: true }) + await disposeSnapshot(harness) + }) + + it('pins a constrained multi-select question and its validation state', async () => { + const harness = await setupSnapshot({ + config: { + maxQuestionOptions: 3, + questionDialogWidth: 48, + questionDialogMaxHeight: 16, + }, + }, { columns: 56, rows: 20 }) + const controller = new AbortController() + const beforeQuestion = harness.terminal.frames + const answer = harness.ctx.userInteraction.ask({ + questions: [{ + id: 'coverage', + header: 'Coverage', + question: 'Which advanced TUI states belong in the required matrix?', + multiSelect: true, + options: [ + { label: 'Code Mode', description: 'run_code programs and captured output' }, + { label: 'Workflows', description: 'phases and parallel agents' }, + { label: 'Cordis tools', description: 'inspect, mount, and unmount' }, + { label: 'Compaction', description: 'surface replacement and reflow' }, + ], + }], + signal: controller.signal, + }) + const rejected = expect(answer).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + await harness.terminal.waitForFrame(beforeQuestion) + await checkpoint('question-dialog', harness.terminal) + + await renderAfter(harness, () => { harness.terminal.send('\r') }) + await checkpoint('question-dialog-validation', harness.terminal) + controller.abort() + await rejected + await disposeSnapshot(harness) + }) + + it('pins compaction surface replacement and narrow-to-wide reflow', async () => { + let replacementStart = 0 + let replacementEnd = 0 + let replacementSources: number[] = [] + const harness = await setupSnapshot({ + tools: ADVANCED_CARD_TOOLS, + beforeMount(session) { + const user = session.append('user/message', { + content: [{ type: 'text', text: 'Old prompt with a long line that exercises wrapping before compaction.' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + const assistant = session.append('assistant/message', { + turn: 1, + step: 0, + provenance: { provider: 'mock', model: 'deepseek-v4-flash' }, + content: [{ type: 'tool-call', id: CallId('old-tool'), name: 'bash', arguments: '{}' }], + }, { surfaceOp: 'append' }) + session.append('tool/call', { turn: 1, step: 0, callId: CallId('old-tool'), name: 'bash', arguments: '{}' }) + const result = session.append('tool/result', { + turn: 1, + step: 0, + callId: CallId('old-tool'), + content: [{ type: 'text', text: 'obsolete output that must disappear' }], + isError: false, + }, { surfaceOp: 'append' }) + replacementStart = user.seq + replacementEnd = result.seq + replacementSources = [user.seq, assistant.seq, result.seq] + }, + }, { columns: 80, rows: 24 }) + await checkpoint('surface-before-compaction', harness.terminal, { includeScrollback: true }) + + await renderAfter(harness, () => { + harness.session.append('context/message', { + content: [{ type: 'text', text: 'Compacted summary: the prior command completed and its details were retired from the active surface.' }], + source: { kind: 'plugin', plugin: 'compact' }, + }, { + surfaceOp: { op: 'replace', start: replacementStart, end: replacementEnd }, + sourceEventSeqs: replacementSources, + }) + harness.terminal.resize(44, 18) + }) + await checkpoint('surface-after-compaction-narrow', harness.terminal, { includeScrollback: true }) + + await renderAfter(harness, () => { harness.terminal.resize(104, 30) }) + await checkpoint('surface-after-compaction-wide', harness.terminal, { includeScrollback: true }) + await disposeSnapshot(harness) + }) + + it('pins help, unknown commands, live errors, turn failures, and terminal restoration', async () => { + const harness = await setupSnapshot({}, { columns: 92, rows: 32 }) + await renderAfter(harness, () => { + harness.terminal.send('/help') + harness.terminal.send('\r') + harness.terminal.send('/unknown-advanced-command') + harness.terminal.send('\r') + harness.ctx.emit('agent/error', harness.agent, 3, 1, new Error('provider stream failed after partial output')) + harness.session.append('turn/end', { + turn: 3, + reason: { kind: 'error', step: 1, message: 'provider stream failed after partial output' }, + }) + harness.session.append('turn/end', { + turn: 4, + reason: { kind: 'interrupted' }, + }) + }) + await checkpoint('errors-and-help', harness.terminal, { includeScrollback: true }) + + await harness.controller.dispose() + await harness.terminal.flush() + await checkpoint('disposed-terminal', harness.terminal, { includeScrollback: true }) + await harness.ctx.fiber.dispose() + await harness.terminal.dispose() + }) +}) + +afterAll(async () => { + expect([...observedCheckpoints].sort()).toEqual([...CHECKPOINTS].sort()) + const files = (await readdir(SNAPSHOTS_DIR)) + .filter(file => file.endsWith('.golden.txt')) + .sort() + expect(files).toEqual(CHECKPOINTS.map(name => `${name}.golden.txt`).sort()) +}) diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index 6cc8e60243..5fc11cbe40 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -1,18 +1,23 @@ import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import type { Terminal } from '@earendil-works/pi-tui' -import AgentRegistry, { AgentId, type Agent, type AgentStatus } from '@deepseek-ai/dsh-agent' -import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import SessionStore, { SessionId, type Session } from '@deepseek-ai/dsh-session' +import AgentRegistry, { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { ToolDefinition } from '@deepseek-ai/dsh-tools' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' import { createTuiChat, mountTui, resolveTuiConfig, - type Config, type TuiRuntime, } from '../src/index.ts' +import { + appendAssistant, + appendUser, + createTuiTestHarness, + disposeTuiTestHarness, + type TuiHarnessOptions, +} from './harness.ts' class FakeTerminal implements Terminal { columns = 88 @@ -84,97 +89,23 @@ class FakeTerminal implements Terminal { } } -interface FakeAgent extends Agent { - status: AgentStatus - sent: ContentBlock[][] - steered: ContentBlock[][] - cancelled: string[] -} - async function tick(): Promise { await new Promise(resolve => setTimeout(resolve, 25)) } -async function setup(options: { - status?: AgentStatus - config?: Config - tools?: Record - beforeMount?: (session: Session) => void - cwd?: string | null -} = {}) { - const ctx = new Context() - await ctx.plugin(SessionStore) - await ctx.plugin(AgentRegistry) - await ctx.plugin(UserInteractionService) - const tools = options.tools ?? {} - ctx.provide('tools', { - get(name: string) { - return tools[name] - }, - } as never) - const session = ctx.sessions.create( - SessionId('main-session'), - options.cwd === null ? undefined : { meta: { cwd: options.cwd ?? process.cwd() } }, - ) - options.beforeMount?.(session) - const sent: ContentBlock[][] = [] - const steered: ContentBlock[][] = [] - const cancelled: string[] = [] - const agent: FakeAgent = { - id: AgentId('main'), - options: { model: 'deepseek-v4-flash' }, - session, - status: options.status ?? 'idle', - ctx, - sent, - steered, - cancelled, - send(content) { - sent.push(content) - }, - steer(content) { - steered.push(content) - }, - inject() {}, - cancel(reason) { - cancelled.push(reason ?? '') - }, - whenIdle() { - return Promise.resolve() - }, - } - ctx.agents.register(agent) +async function setup(options: TuiHarnessOptions = {}) { const terminal = new FakeTerminal() const exit = vi.fn() - const controller = createTuiChat(ctx, Object.assign({ - welcome: 'Coding agent ready.', - agent: 'main', - color: false, - }, options.config), { terminal, exit }) + const result = await createTuiTestHarness(terminal, exit, { + ...options, + cwd: options.cwd === undefined ? process.cwd() : options.cwd, + }) await tick() - return { ctx, session, agent, terminal, exit, controller } + return result } async function dispose(setupResult: Awaited>): Promise { - await setupResult.controller.dispose() - await setupResult.ctx.fiber.dispose() -} - -function appendUser(session: Session, text: string): void { - session.append('user/message', { - content: [{ type: 'text', text }], - source: { kind: 'user' }, - }, { surfaceOp: 'append' }) -} - -function appendAssistant(session: Session, content: ContentBlock[], usage?: { inputTokens: number; outputTokens: number }): void { - session.append('assistant/message', { - turn: 1, - step: 0, - provenance: { provider: 'mock', model: 'deepseek-v4-flash' }, - content, - ...usage === undefined ? {} : { usage }, - }, { surfaceOp: 'append' }) + await disposeTuiTestHarness(setupResult) } describe('TUI config', () => { diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 2dccd293c9..164fbed86f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -2069,12 +2069,27 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session + '@deepseek-ai/dsh-system-prompt': + specifier: workspace:^ + version: link:../../core/system-prompt + '@deepseek-ai/dsh-tool-cordis': + specifier: workspace:^ + version: link:../../cordis/tool-cordis + '@deepseek-ai/dsh-tool-workflow': + specifier: workspace:^ + version: link:../../workflow/tool-workflow '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools '@deepseek-ai/dsh-user-interaction': specifier: workspace:^ version: link:../user-interaction + '@deepseek-ai/dsh-workflow': + specifier: workspace:^ + version: link:../../workflow/workflow + '@xterm/headless': + specifier: 5.5.0 + version: 5.5.0 cordis: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@vendor+loader) @@ -4575,6 +4590,9 @@ packages: resolution: {integrity: sha512-A9gOqLdi6cV4ibazAjcQufGj0B1y/vDqYrcuP6d/6x8P27gRS8643Dj9o1dEKtB6O7fwxb2FgBmJS2mX7gpvdw==} engines: {node: '>=14.6'} + '@xterm/headless@5.5.0': + resolution: {integrity: sha512-5xXB7kdQlFBP82ViMJTwwEc3gKCLGKR/eoxQm4zge7GPBl86tCdI0IdPJjoKd8mUSFXz5V7i/25sfsEkP4j46g==} + accepts@2.0.0: resolution: {integrity: sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng==} engines: {node: '>= 0.6'} @@ -8867,6 +8885,8 @@ snapshots: '@xmldom/xmldom@0.9.10': {} + '@xterm/headless@5.5.0': {} + accepts@2.0.0: dependencies: mime-types: 3.0.2 diff --git a/vitest.snapshot.config.ts b/vitest.snapshot.config.ts index 9753176f9d..18127b55ee 100644 --- a/vitest.snapshot.config.ts +++ b/vitest.snapshot.config.ts @@ -39,7 +39,11 @@ export default defineConfig({ // through the root tsconfig paths map; the native option cannot do this. plugins: [tsconfigPaths({ projects: ['./tsconfig.json'] })], test: { - include: ['examples/*/tests/**/*.snapshot.ts', 'packages/sdk/*/tests/**/*.snapshot.ts'], + include: [ + 'examples/*/tests/**/*.snapshot.ts', + 'packages/sdk/*/tests/**/*.snapshot.ts', + 'packages/ui/tui/tests/**/*.snapshot.ts', + ], // Each test boots a subprocess; give it room and keep the worker file singular. Replay tests // opt into bounded in-file concurrency, while record/refresh stay serial because they write // fixtures. The environment knob restores serial replay with value 1 on constrained machines. From bea6a74ea0f44d1d9e0f0b5dde331a23f4c552ff Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 01:09:20 +0800 Subject: [PATCH 190/323] refactor(examples): give TUI its own agent leaf --- docs/graph-atlas.md | 1 + examples/README.md | 8 ++++- examples/coding-agent/README.md | 8 ++--- examples/coding-agent/code-mode.cordis.yml | 2 ++ examples/coding-agent/composition.md | 2 +- examples/coding-agent/cordis.yml | 12 +++----- examples/tui-agent/README.md | 19 ++++++++++++ examples/tui-agent/code-mode.cordis.yml | 30 +++++++++++++++++++ examples/tui-agent/composition.md | 28 +++++++++++++++++ examples/tui-agent/cordis.yml | 28 +++++++++++++++++ examples/tui-agent/package.json | 7 +++++ .../tests/fixtures/tui-scripted-llm.ts | 0 .../tests/fixtures/tui-scripted.cordis.yml | 0 .../tests/tui-keyless-smoke.e2e.ts | 8 ++--- knip.json | 2 +- package.json | 1 + scripts/demo-code-mode.mjs | 7 +++-- scripts/gen-doc-graphs.ts | 21 +++++++++++-- 18 files changed, 159 insertions(+), 25 deletions(-) create mode 100644 examples/tui-agent/README.md create mode 100644 examples/tui-agent/code-mode.cordis.yml create mode 100644 examples/tui-agent/composition.md create mode 100644 examples/tui-agent/cordis.yml create mode 100644 examples/tui-agent/package.json rename examples/{coding-agent => tui-agent}/tests/fixtures/tui-scripted-llm.ts (100%) rename examples/{coding-agent => tui-agent}/tests/fixtures/tui-scripted.cordis.yml (100%) rename examples/{coding-agent => tui-agent}/tests/tui-keyless-smoke.e2e.ts (95%) diff --git a/docs/graph-atlas.md b/docs/graph-atlas.md index 60de01ef81..5220cfa81f 100644 --- a/docs/graph-atlas.md +++ b/docs/graph-atlas.md @@ -14,6 +14,7 @@ The process decision behind this index is recorded in [the documentation graph R | [capability seams and core services](capability-seams.md) | `hybrid generated` | | [echo-agent app composition](../examples/echo-agent/composition.md) | `hybrid generated` | | [coding-agent app composition](../examples/coding-agent/composition.md) | `hybrid generated` | +| [tui-agent app composition](../examples/tui-agent/composition.md) | `hybrid generated` | | [cordis-agent app composition](../examples/cordis-agent/composition.md) | `hybrid generated` | | [acp-agent app composition](../examples/acp-agent/composition.md) | `hybrid generated` | | [event producer/consumer matrix](event-producer-consumer.md) | `hybrid generated` | diff --git a/examples/README.md b/examples/README.md index 25c017824f..03b798e164 100644 --- a/examples/README.md +++ b/examples/README.md @@ -15,12 +15,18 @@ Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigge ## coding-agent -A coding-agent demo: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the same `@deepseek-ai/dsh-stdio-demo` app. Interactive runs use the pi-tui coding interface; pipes use readline. +A coding-agent REPL: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the `@deepseek-ai/dsh-stdio-demo` app's readline front door. Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. +## tui-agent + +The full-screen terminal sibling of `coding-agent`: it reuses the same coding backends and tools while forcing the shared terminal app to `dsh-tui`. It is the home of TUI PTY and snapshot scenarios. + +Run with: `pnpm run demo:tui` (needs `DEEPSEEK_API_KEY`). See [tui-agent/README.md](tui-agent/README.md) for controls and composition. + ## cordis-agent The **self-referential** demo: the coding spine plus [`@deepseek-ai/dsh-tool-cordis`](../packages/cordis/tool-cordis), whose three tools (`cordis_inspect` / `cordis_mount` / `cordis_unmount`) let the agent inspect the live cordis runtime it runs inside, mount model-written plugins into it (an event listener, a brand-new tool for itself, or a service another mount injects), and dispose them again — all dynamic mounts grouped under one `cordis-dynamic` fiber subtree. The `ctx.fs`/`ctx.web` services ride along provider-only, as the capabilities those plugins build on. diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index 9fdadf809d..f94cd31adb 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -1,6 +1,6 @@ # coding-agent -The coding-agent demo wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + terminal chat + JSONL persistence, loaded from `cordis.yml`. Interactive runs use the pi-tui coding interface; piped runs use readline. +The coding-agent REPL wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + readline chat + JSONL persistence, loaded from `cordis.yml`. The sibling [`tui-agent`](../tui-agent/README.md) fixes the same agent composition to the full-screen terminal front door. ## Run it @@ -13,7 +13,7 @@ pnpm run demo:repl Type a coding task. The agent works through the `read`/`write`/`edit` filesystem tools for ordinary file operations and `bash` (+ the generic `task_output` / `task_list` / `task_kill` for background tasks) for shell commands, searches, and test runs, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). Both the fs tools and bash resolve relative paths against the session workspace. It can also delegate with `subagent`/`subagent_fork` and track multi-step work with `todo_write`. -The TUI renders resumed Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and the latest todo list. Enter submits or steers while the agent is running; Ctrl+O expands cards, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `ask_user_question` opens a keyboard-driven overlay rather than taking over the editor. +The REPL renders reasoning, tool calls/results, and the latest todo list as line-oriented output suitable for terminals and pipes. Use `pnpm run demo:tui` for the interactive Markdown/card interface. ### Resuming a prior session @@ -42,14 +42,14 @@ and watch the transcript: one `run_code` call, a program looping over tools, and ## What each leaf entry demonstrates -This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads one app package, and adds product tools that are intentionally outside the shared spine. The spine (sessions, system-prompt, tools, agents, invariants, `agent-loop`) and the front-door cluster (JSONL persistence, TTY-selected `dsh-tui`/`dsh-stdio` channels, the pre-created `main` agent) live inside the [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo) app and the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle it loads; the leaf wires the backends and model-facing optional tools: +This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads one app package, and adds product tools that are intentionally outside the shared spine. The spine (sessions, system-prompt, tools, agents, invariants, `agent-loop`) and the front-door cluster (JSONL persistence, the selected terminal channel, the pre-created `main` agent) live inside the [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo) app and the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle it loads; the leaf wires the backends and model-facing optional tools: | Entry | Demonstrates | |---|---| | `hmr` (`@cordisjs/plugin-hmr`) | the dev/demo edit-reload loop — a **leaf** entry (not baked into the app) because it is Loader-only and needs `node --expose-internals`, which `demo:repl` passes | | `llm-deepseek` | real `LlmAdapter` via config (`!!js process.env.…` secrets); swap one line to `@deepseek-ai/dsh-llm-pi-ai` for the library-backed twin | | `bash` (`dsh-bash-local`) | the executor implementation — the swappable half of the bash seam. The model-facing `bash` schema (`tool-bash`) and generic `task_*` controls (`tool-tasks`) come from `dsh-agent-spine-demo`, so only the executor is a leaf choice | -| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + JSONL persistence + TTY-selected `dsh-tui`/`dsh-stdio` channels + a pre-created `main` agent. Its config carries the model, system prompt, `persistenceRoot` (`./.sessions`), `resumeSessionId`, and optional `ui` presentation settings | +| `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + JSONL persistence + the configured terminal channel + a pre-created `main` agent. This leaf fixes `ui.mode` to `readline`; `tui-agent` owns the corresponding TUI leaf | | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix | | `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) | | `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a persistent TUI plan or readline checklist | diff --git a/examples/coding-agent/code-mode.cordis.yml b/examples/coding-agent/code-mode.cordis.yml index 3fec40e0f3..b1f62829bc 100644 --- a/examples/coding-agent/code-mode.cordis.yml +++ b/examples/coding-agent/code-mode.cordis.yml @@ -20,6 +20,8 @@ tools: mode: code welcome: 'code-mode agent ready. Give it a multi-tool task.' + ui: + mode: readline persona: | You are coding-agent, a coding assistant powered by the {{model}} model. diff --git a/examples/coding-agent/composition.md b/examples/coding-agent/composition.md index d0411e43d9..2956291dc8 100644 --- a/examples/coding-agent/composition.md +++ b/examples/coding-agent/composition.md @@ -18,7 +18,7 @@ flowchart LR cfg --> plugin_coding_stdio_agent plugin_coding_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] plugin_coding_stdio_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] - plugin_coding_stdio_agent --> frontdoor_stdio["dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent"] + plugin_coding_stdio_agent --> frontdoor_stdio["@deepseek-ai/dsh-stdio
pre-created main agent"] bundle_agent_core --> spine_llm["ctx.llm"] bundle_agent_core --> spine_sessions["ctx.sessions"] bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index d3da67ce29..497e2a80c8 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -1,7 +1,6 @@ -# Coding agent with swappable DeepSeek and local-bash backends. `dsh-stdio-demo` -# supplies the agent spine, workspace instructions, generic task controls, -# JSONL persistence, TTY-selected `dsh-tui`/`dsh-stdio` terminal front doors, -# readline logging, and `main` agent. +# Readline coding REPL with swappable DeepSeek and local-bash backends. +# `dsh-stdio-demo` supplies the agent spine, workspace instructions, generic +# task controls, JSONL persistence, the line-oriented front door, and `main`. # HMR remains a leaf because it requires Loader internals; `demo:repl` passes # `--expose-internals`. The app bin loads the gitignored root `.env`; this file # reads `DEEPSEEK_API_KEY` and optional `DEEPSEEK_BASE_URL` through `!!js`. @@ -39,10 +38,7 @@ maxBytes: 65536 welcome: 'agent REPL ready. Give it a coding task.' ui: - mode: auto - tui: - showReasoning: true - maxToolOutputLines: 12 + mode: readline # Keep the persona to identity and behavior; tool plugins own tool guidance. # The loop resolves {{model}} from this agent's configuration. persona: | diff --git a/examples/tui-agent/README.md b/examples/tui-agent/README.md new file mode 100644 index 0000000000..909ccf700d --- /dev/null +++ b/examples/tui-agent/README.md @@ -0,0 +1,19 @@ +# tui-agent + +The full-screen terminal counterpart to the [`coding-agent`](../coding-agent/README.md) readline REPL and [`acp-agent`](../acp-agent/README.md) server. It reuses the coding agent's backends and tool composition, then fixes the shared terminal app to the `dsh-tui` front door. + +## Run it + +```sh +pnpm run demo:tui +``` + +The command needs `DEEPSEEK_API_KEY` in the environment or the gitignored repository-root `.env`. Set `RESUME_SESSION_ID` to reopen a persisted conversation under `./.sessions`. + +The TUI renders Markdown history, reasoning, tool-owned terminal/diff/generic cards, token totals, and the latest todo list. Enter submits or steers while the agent is running; Ctrl+O expands cards, Ctrl+R toggles reasoning, Escape cancels, and `/help` lists commands. `ask_user_question` opens a keyboard-driven overlay. + +Run `pnpm run demo:code-mode tui` for the sibling Code Mode overlay. + +## Composition + +[`cordis.yml`](cordis.yml) includes the readline coding-agent leaf so the LLM, bash, filesystem, compaction, subagent, workflow, todo, timeout, and spill choices have one owner. Its asserted patch replaces only the terminal app config and forces `ui.mode: tui`; [`code-mode.cordis.yml`](code-mode.cordis.yml) applies the same front-door patch to the coding agent's Code Mode overlay. diff --git a/examples/tui-agent/code-mode.cordis.yml b/examples/tui-agent/code-mode.cordis.yml new file mode 100644 index 0000000000..7bb7932ba0 --- /dev/null +++ b/examples/tui-agent/code-mode.cordis.yml @@ -0,0 +1,30 @@ +# Code Mode keeps the TUI front door while reusing the coding-agent overlay's +# worker runtime and one-tool registry composition. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ../coding-agent/code-mode.cordis.yml + patches: + - id: stdio-agent + name: '@deepseek-ai/dsh-stdio-demo' + config: + provider: deepseek + model: deepseek-v4-flash + resumeSessionId: !!js process.env.RESUME_SESSION_ID + persistenceRoot: './.sessions' + workspaceContext: + maxBytes: 65536 + tools: + mode: code + welcome: 'TUI Code Mode ready. Give it a multi-tool task.' + ui: + mode: tui + tui: + showReasoning: true + maxToolOutputLines: 12 + persona: | + You are coding-agent, a coding assistant powered by the {{model}} model. + + You work by writing TypeScript programs for run_code: batch related + tool work into one program, loop and branch where it helps, and print + or return ONLY the findings that matter. diff --git a/examples/tui-agent/composition.md b/examples/tui-agent/composition.md new file mode 100644 index 0000000000..511f76d41e --- /dev/null +++ b/examples/tui-agent/composition.md @@ -0,0 +1,28 @@ + + +# TUI Agent App Composition + +The TUI agent reuses the coding-agent backend and tool composition while fixing the shared terminal app to the full-screen dsh-tui front door. + +```mermaid +flowchart LR + cfg["examples/tui-agent
cordis.yml"] + plugin_tui_base["base
@deepseek-ai/dsh-stdio-demo"] + cfg --> plugin_tui_base + plugin_tui_base --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] + plugin_tui_base --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] + plugin_tui_base --> frontdoor_stdio["@deepseek-ai/dsh-tui
pre-created main agent"] + bundle_agent_core --> spine_llm["ctx.llm"] + bundle_agent_core --> spine_sessions["ctx.sessions"] + bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] + bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] +``` + +| Plugin id | Package / module | +| --- | --- | +| `base` | `@deepseek-ai/dsh-stdio-demo` | + +Source config: [`examples/tui-agent/cordis.yml`](cordis.yml). + +Maintenance mode: hybrid: the leaf plugin list is parsed from its `cordis.yml`; app package expansion is curated from package source. diff --git a/examples/tui-agent/cordis.yml b/examples/tui-agent/cordis.yml new file mode 100644 index 0000000000..0f329c38e2 --- /dev/null +++ b/examples/tui-agent/cordis.yml @@ -0,0 +1,28 @@ +# Full-screen TUI front door over the same coding-agent composition used by the +# readline REPL. The include keeps backends and optional tools aligned; the +# patch owns only the terminal-specific app config. +- id: base + name: '@cordisjs/plugin-include' + config: + path: ../coding-agent/cordis.yml + patches: + - id: stdio-agent + name: '@deepseek-ai/dsh-stdio-demo' + config: + provider: deepseek + model: deepseek-v4-flash + resumeSessionId: !!js process.env.RESUME_SESSION_ID + persistenceRoot: './.sessions' + workspaceContext: + maxBytes: 65536 + welcome: 'TUI agent ready. Give it a coding task.' + ui: + mode: tui + tui: + showReasoning: true + maxToolOutputLines: 12 + persona: | + You are coding-agent, a coding assistant powered by the {{model}} model. + + Verify your work by running the code or tests. Keep answers brief and + factual. diff --git a/examples/tui-agent/package.json b/examples/tui-agent/package.json new file mode 100644 index 0000000000..f45e6746a3 --- /dev/null +++ b/examples/tui-agent/package.json @@ -0,0 +1,7 @@ +{ + "name": "tui-agent-example", + "private": true, + "version": "0.0.1", + "type": "module", + "description": "Runnable demo: the coding agent through the full-screen terminal UI" +} diff --git a/examples/coding-agent/tests/fixtures/tui-scripted-llm.ts b/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts similarity index 100% rename from examples/coding-agent/tests/fixtures/tui-scripted-llm.ts rename to examples/tui-agent/tests/fixtures/tui-scripted-llm.ts diff --git a/examples/coding-agent/tests/fixtures/tui-scripted.cordis.yml b/examples/tui-agent/tests/fixtures/tui-scripted.cordis.yml similarity index 100% rename from examples/coding-agent/tests/fixtures/tui-scripted.cordis.yml rename to examples/tui-agent/tests/fixtures/tui-scripted.cordis.yml diff --git a/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts b/examples/tui-agent/tests/tui-keyless-smoke.e2e.ts similarity index 95% rename from examples/coding-agent/tests/tui-keyless-smoke.e2e.ts rename to examples/tui-agent/tests/tui-keyless-smoke.e2e.ts index cc2397c069..26cee8aea2 100644 --- a/examples/coding-agent/tests/tui-keyless-smoke.e2e.ts +++ b/examples/tui-agent/tests/tui-keyless-smoke.e2e.ts @@ -53,7 +53,7 @@ while time.monotonic() < deadline: if scenario == "conversation" and answered_question and not sent_exit and b"Decision received. Scripted TUI run complete." in output: os.write(fd, b"/exit\r") sent_exit = True - if scenario == "boot" and not sent_exit and b"agent REPL ready." in output: + if scenario == "boot" and not sent_exit and b"TUI agent ready." in output: os.write(fd, b"/exit\r") sent_exit = True waited, candidate = os.waitpid(pid, os.WNOHANG) @@ -101,7 +101,7 @@ interface TuiLoaderSmokeOptions { } async function runTuiLoaderSmoke(options: TuiLoaderSmokeOptions = {}): Promise { - const cwd = await mkdtemp(join(tmpdir(), 'coding-tui-smoke-')) + const cwd = await mkdtemp(join(tmpdir(), 'tui-agent-smoke-')) try { const launch = resolveExampleLaunch({ srcBin: binScript, @@ -142,11 +142,11 @@ async function runTuiLoaderSmoke(options: TuiLoaderSmokeOptions = {}): Promise { +describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => { it('boots pi-tui, renders the configured banner, accepts /exit, and restores the terminal', async () => { const output = await runTuiLoaderSmoke() expect(output).toContain('DEEPSEEK') - expect(output).toContain('agent REPL ready.') + expect(output).toContain('TUI agent ready.') expect(output).toContain('\u001B[?2004l') }, LOADER_SMOKE_TEST_TIMEOUT_MS) diff --git a/knip.json b/knip.json index 03fae14896..db77587b48 100644 --- a/knip.json +++ b/knip.json @@ -10,7 +10,7 @@ "examples": { "entry": [ "echo-agent/src/*.ts", - "coding-agent/tests/fixtures/tui-scripted-llm.ts", + "tui-agent/tests/fixtures/tui-scripted-llm.ts", "*/tests/**/*.e2e.ts", "*/tests/**/*.snapshot.ts" ], diff --git a/package.json b/package.json index 39d6a53161..ca85fd32d2 100644 --- a/package.json +++ b/package.json @@ -80,6 +80,7 @@ "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", + "demo:tui": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/tui-agent/cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", diff --git a/scripts/demo-code-mode.mjs b/scripts/demo-code-mode.mjs index edfc26b4d5..7a5e054cc0 100644 --- a/scripts/demo-code-mode.mjs +++ b/scripts/demo-code-mode.mjs @@ -1,7 +1,7 @@ /** - * Boot the REPL or ACP Code Mode overlay, defaulting to REPL. Each overlay + * Boot the REPL, TUI, or ACP Code Mode overlay, defaulting to REPL. Each overlay * includes its base example, selects Code Mode, and adds the worker runtime. - * Both require a DeepSeek API key; unsupported arguments fail with usage. + * All require a DeepSeek API key; unsupported arguments fail with usage. */ import { spawn } from 'node:child_process' @@ -10,13 +10,14 @@ import { spawn } from 'node:child_process' // Loader's HMR path). const UIS = new Map([ ['repl', ['--expose-internals', '--import', 'tsx', 'packages/examples/stdio-demo/src/bin.ts', 'examples/coding-agent/code-mode.cordis.yml']], + ['tui', ['--expose-internals', '--import', 'tsx', 'packages/examples/stdio-demo/src/bin.ts', 'examples/tui-agent/code-mode.cordis.yml']], ['acp', ['--import', 'tsx', 'packages/examples/acp-demo/src/bin.ts', '--config', 'examples/acp-agent/code-mode.cordis.yml']], ]) const ui = process.argv[2] ?? 'repl' const args = UIS.get(ui) if (!args || process.argv.length > 3) { - console.error('usage: pnpm run demo:code-mode [repl|acp]') + console.error('usage: pnpm run demo:code-mode [repl|tui|acp]') process.exit(2) } diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 5bf0a9456c..29cea3f9a0 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -434,6 +434,14 @@ const APP_EXAMPLES = [ config: 'examples/coding-agent/cordis.yml', summary: 'The coding-agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', }, + { + id: 'tui', + rel: 'examples/tui-agent/composition.md', + title: 'TUI Agent App Composition', + label: 'examples/tui-agent', + config: 'examples/tui-agent/cordis.yml', + summary: 'The TUI agent reuses the coding-agent backend and tool composition while fixing the shared terminal app to the full-screen dsh-tui front door.', + }, { id: 'cordis', rel: 'examples/cordis-agent/composition.md', @@ -454,13 +462,18 @@ const APP_EXAMPLES = [ type AppExample = typeof APP_EXAMPLES[number] -function renderAppExpansion(lines: string[], appNode: string, pluginName: string): void { +function renderAppExpansion(lines: string[], appNode: string, pluginName: string, exampleId: string): void { const agentCore = nodeId('bundle', 'agent_core') const jsonl = nodeId('bundle', 'jsonl') lines.push(` ${appNode} --> ${agentCore}["@deepseek-ai/dsh-agent-spine-demo"]`) lines.push(` ${appNode} --> ${jsonl}["@deepseek-ai/dsh-session-persistence-jsonl"]`) if (pluginName === '@deepseek-ai/dsh-stdio-demo') { - lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent"]`) + const frontDoor = exampleId === 'tui' + ? '@deepseek-ai/dsh-tui
pre-created main agent' + : exampleId === 'coding' + ? '@deepseek-ai/dsh-stdio
pre-created main agent' + : 'dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent' + lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["${frontDoor}"]`) } else if (pluginName === '@deepseek-ai/dsh-acp-demo') { lines.push(` ${appNode} --> ${nodeId('frontdoor', 'acp')}["@deepseek-ai/dsh-acp
JSON-RPC stdio bridge
sessions created by client"]`) } @@ -488,7 +501,7 @@ function renderAppComposition(example: AppExample): string { lines.push(` ${pluginNode}["${escLabel(plugin.id)}
${escLabel(plugin.name)}"]`) lines.push(` cfg --> ${pluginNode}`) if (plugin.name === '@deepseek-ai/dsh-stdio-demo' || plugin.name === '@deepseek-ai/dsh-acp-demo') { - renderAppExpansion(lines, pluginNode, plugin.name) + renderAppExpansion(lines, pluginNode, plugin.name, example.id) } } lines.push( @@ -978,6 +991,7 @@ function renderIndex(docs: GraphDoc[]): string { 'docs/capability-seams.md': 'capability seams and core services', 'examples/echo-agent/composition.md': 'echo-agent app composition', 'examples/coding-agent/composition.md': 'coding-agent app composition', + 'examples/tui-agent/composition.md': 'tui-agent app composition', 'examples/cordis-agent/composition.md': 'cordis-agent app composition', 'examples/acp-agent/composition.md': 'acp-agent app composition', 'docs/event-producer-consumer.md': 'event producer/consumer matrix', @@ -989,6 +1003,7 @@ function renderIndex(docs: GraphDoc[]): string { 'docs/capability-seams.md': 'hybrid generated', 'examples/echo-agent/composition.md': 'hybrid generated', 'examples/coding-agent/composition.md': 'hybrid generated', + 'examples/tui-agent/composition.md': 'hybrid generated', 'examples/cordis-agent/composition.md': 'hybrid generated', 'examples/acp-agent/composition.md': 'hybrid generated', 'docs/event-producer-consumer.md': 'hybrid generated', From e68cef1be1dff8cde8a04556969af400ecb964fa Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 01:31:55 +0800 Subject: [PATCH 191/323] test(tui): replay recorded sessions through real tools --- ...-18-tui-terminal-state-snapshots.i18n.yaml | 4 +- ...2026-07-18-tui-terminal-state-snapshots.md | 67 ++-- ...6-07-18-tui-terminal-state-snapshots.zh.md | 65 ++-- docs/testing.md | 4 +- examples/tui-agent/README.md | 4 + .../bash-terminal-card/session.jsonl | 98 ++++++ .../bash-terminal-card/terminal.golden.txt | 72 ++++ .../tests/snapshots/code-mode/session.jsonl | 150 ++++++++ .../snapshots/code-mode/terminal.golden.txt | 79 +++++ .../cordis-dynamic-toolchain/session.1.jsonl | 13 + .../cordis-dynamic-toolchain/session.2.jsonl | 13 + .../cordis-dynamic-toolchain/session.jsonl | 64 ++++ .../terminal.golden.txt | 115 ++++++ .../dynamic-workflow/session.1.jsonl | 36 ++ .../snapshots/dynamic-workflow/session.jsonl | 209 +++++++++++ .../dynamic-workflow/terminal.golden.txt | 105 ++++++ .../multi-turn-conversation/session.jsonl | 65 ++++ .../terminal.golden.txt | 69 ++++ .../parallel-file-reads/session.jsonl | 28 ++ .../parallel-file-reads/terminal.golden.txt | 94 +++++ .../parallel-file-reads/workspace/a.txt | 1 + .../parallel-file-reads/workspace/b.txt | 1 + .../tests/snapshots/todo-plan/session.jsonl | 134 +++++++ .../snapshots/todo-plan/terminal.golden.txt | 81 +++++ examples/tui-agent/tests/tui.snapshot.ts | 329 ++++++++++++++++++ .../snapshots/code-mode-complete.golden.txt | 50 --- .../conversation-complete.golden.txt | 75 ---- .../snapshots/conversation-replay.golden.txt | 73 ---- .../conversation-streaming.golden.txt | 81 ++--- .../cordis-tools-complete.golden.txt | 73 ---- .../dynamic-workflow-complete.golden.txt | 53 --- packages/ui/tui/tests/tui.snapshot.ts | 57 +-- 32 files changed, 1874 insertions(+), 488 deletions(-) create mode 100644 examples/tui-agent/tests/snapshots/bash-terminal-card/session.jsonl create mode 100644 examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt create mode 100644 examples/tui-agent/tests/snapshots/code-mode/session.jsonl create mode 100644 examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt create mode 100644 examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.1.jsonl create mode 100644 examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.2.jsonl create mode 100644 examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.jsonl create mode 100644 examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt create mode 100644 examples/tui-agent/tests/snapshots/dynamic-workflow/session.1.jsonl create mode 100644 examples/tui-agent/tests/snapshots/dynamic-workflow/session.jsonl create mode 100644 examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt create mode 100644 examples/tui-agent/tests/snapshots/multi-turn-conversation/session.jsonl create mode 100644 examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt create mode 100644 examples/tui-agent/tests/snapshots/parallel-file-reads/session.jsonl create mode 100644 examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt create mode 100644 examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/a.txt create mode 100644 examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/b.txt create mode 100644 examples/tui-agent/tests/snapshots/todo-plan/session.jsonl create mode 100644 examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt create mode 100644 examples/tui-agent/tests/tui.snapshot.ts delete mode 100644 packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt delete mode 100644 packages/ui/tui/tests/snapshots/conversation-complete.golden.txt delete mode 100644 packages/ui/tui/tests/snapshots/conversation-replay.golden.txt delete mode 100644 packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt delete mode 100644 packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml index 5b682b642b..b68f7e7e78 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-18-tui-terminal-state-snapshots.md: 225efe8de95973ecae3f9bf73308e7ae879dddbb -2026-07-18-tui-terminal-state-snapshots.zh.md: b7399a31b0abf41905f495a1ea3b4ecd0c858526 +2026-07-18-tui-terminal-state-snapshots.md: 280c2b4faec3bd5e14a24a5df7bc901ad31718cd +2026-07-18-tui-terminal-state-snapshots.zh.md: d1c609c6ce511bba1f498b72444af662b4444578 diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md index 225efe8de9..280c2b4fae 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md @@ -8,50 +8,63 @@ English | [中文](2026-07-18-tui-terminal-state-snapshots.zh.md) The TUI is a stateful renderer. Its user-visible result depends on ANSI parsing, differential frames, wrapping, scrollback, viewport position, terminal width, focus, cursor state, and each tool's presentation intent. Unit tests that collect `Terminal.write()` fragments can prove event handling, but they cannot prove the final screen a terminal displays. The same screen may also be emitted through different write fragments, so pinning those fragments creates false regressions. -Component-line snapshots stop before ANSI reaches a terminal and miss cursor movement, clearing, styling, overlay composition, and reflow. Raster screenshots include font and platform rendering noise that is unrelated to the TUI contract. The TUI therefore needs a deterministic, reviewable representation of terminal state plus a smaller test at the real process and PTY boundary. +Component-line snapshots stop before ANSI reaches a terminal and miss cursor movement, clearing, styling, overlay composition, and reflow. Raster screenshots include font and platform rendering noise that is unrelated to the TUI contract. A completed flow built by directly appending plausible session events has another blind spot: it proves the renderer accepts those shapes, not that the production agent loop and tool implementations produce them. + +The TUI therefore needs a deterministic, reviewable representation of terminal state, recorded model journeys that execute the real downstream stack, and a smaller test at the real process and PTY boundary. ## Decision -TUI coverage has three complementary layers: +TUI coverage has four complementary layers: -1. `tui.spec.ts` tests event mapping, input routing, disposal, and error behavior directly. -2. `tui.snapshot.ts` mounts the production TUI against a headless terminal emulator and compares semantic terminal-state goldens. -3. `tui-keyless-smoke.e2e.ts` boots the real Loader composition in a PTY, drives a complete scripted conversation through streaming and `ask_user_question`, exits through `/exit`, and verifies terminal teardown. The production coding-agent configuration also retains its banner/exit and startup-failure PTY cases. +1. `packages/ui/tui/tests/tui.spec.ts` tests event mapping, input routing, disposal, and error behavior directly. +2. `packages/ui/tui/tests/tui.snapshot.ts` mounts the production TUI against a headless terminal emulator for transient states that a completed session log cannot retain: in-flight streaming, pending tool calls, overlays, expansion, compaction reflow, errors, and shutdown. +3. `examples/tui-agent/tests/tui.snapshot.ts` replays committed JSONL session logs through the production agent loop and real tools, then compares the resulting semantic terminal state. +4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` boots the real Loader composition in a PTY, drives a scripted conversation through streaming and `ask_user_question`, and verifies startup, input, exit, failure reporting, and terminal restoration. -The package-local `HeadlessTerminal` implements the same pi-tui `Terminal` interface as the process terminal and feeds every ANSI write into the pinned `@xterm/headless` parser. A snapshot waits for pi-tui's synchronized-output end marker before reading state. This makes a checkpoint represent a completed frame rather than a timer-dependent write prefix. +The runnable TUI has its own `examples/tui-agent` leaf beside the readline `coding-agent` and `acp-agent` leaves. It reuses the coding agent's backend and tool composition through an asserted include patch while fixing the shared terminal app to `ui.mode: tui`; TUI snapshots and PTY tests live with that leaf. -Each golden projects terminal state into text: dimensions, active-buffer and viewport coordinates, lifecycle and cursor state, rows, wrap markers, and non-default style ranges. Scroll-heavy cards capture the used buffer; overlays capture the visible viewport. Text and style remain separate so a reviewer can distinguish content changes from presentation changes without decoding ANSI bytes. +### Recorded-session replay -Every checkpoint also enforces theme independence across the complete terminal state: no RGB colors, no palette entries beyond ANSI 0–15, and no explicit background colors. Reverse video remains valid for selection because it uses terminal defaults. The suite owns a closed checkpoint list: its type rejects undeclared names, and its inventory checks reject missing checkpoints and orphaned `.golden.txt` files. +Each example-level scenario directory owns `session.jsonl`, optional child logs `session..jsonl`, and `terminal.golden.txt`. The primary log supplies user-authored `user/message` prompts and the recorded `assistant/chunk` sequence. `dsh-llm-replay` derives one model-call script per session, binds child logs to fresh child sessions, and is the only mocked boundary. The agent loop, bash and filesystem implementations, Code Mode worker, subagent provider, workflow worker, Cordis tools, presenters, and TUI are production implementations. + +The suite rejects a journey when its tool-call sequence differs, an expected event count is missing, a tool result is an error, a turn ends in error, a workflow lifecycle is incomplete, or the live child-session count differs from the fixture set. These assertions prevent an attractive terminal golden from hiding a failed or bypassed production path. + +The live-model fixtures use `DSH_SNAPSHOT=record`; record mode rewrites their primary and child JSONL logs and terminal goldens. The deterministic Cordis toolchain keeps an authored complete JSONL script because reliably coercing a live model through five exact tool boundaries and two children is not a stable recording contract. `DSH_SNAPSHOT=refresh` replays every committed script keylessly and rewrites only derived terminal goldens. Plain replay compares without writing, and unknown mode values fail loud. + +### Semantic terminal projection + +The package-local `HeadlessTerminal` implements the same pi-tui `Terminal` interface as the process terminal and feeds every ANSI write into the pinned `@xterm/headless` parser. Snapshot code waits for synchronized frames to quiesce before reading state, so a checkpoint represents a completed screen rather than a timer-dependent write prefix. + +Each golden projects dimensions, active-buffer and viewport coordinates, lifecycle and cursor state, rows, wrap markers, and non-default style ranges into text. Scroll-heavy cards capture the used buffer; overlays capture the visible viewport. Text and style remain separate so a reviewer can distinguish content changes from presentation changes without decoding ANSI bytes. + +Every checkpoint enforces theme independence across the complete terminal state: no RGB colors, no palette entries beyond ANSI 0–15, and no explicit background colors. Reverse video remains valid for selection because it uses terminal defaults. Both suites own closed inventories that reject missing scenarios, missing checkpoints, and orphaned golden files. ### Required scenario matrix -| Area | Representative checkpoints | Contract pinned | +| Layer | Scenario | Contract pinned | |---|---|---| -| Conversation | replay, streaming, completion | Resumed Markdown and reasoning, live deltas, plans, token usage, and max-token completion | -| Code Mode | pending and completed `run_code` | The production Code Mode registry and presenter, source program, captured logs, and result | -| Dynamic workflows | pending and completed `workflow` | The production workflow presenter, metadata, phases, parallel agents, script, and structured result | -| Cordis tools | pending and completed inspect/mount/unmount | The production `cordis_inspect`, `cordis_mount`, and `cordis_unmount` presenters and lifecycle results | -| Advanced tool cards | collapsed and expanded | Terminal, diff, generic, subagent, background-task, and skill card shapes plus output truncation | -| Interaction | question and validation | Constrained multi-select overlay composition, focus, scrolling, selection, and validation errors | -| Surface and layout | before compaction, narrow replacement, wide replacement | Surface replacement removes retired content; resize reflows the surviving surface without resurrection | -| Failure and shutdown | errors/help and disposed terminal | Help and unknown commands, live/turn error de-duplication, interruption, cursor restoration, and terminal stop | - -The explicitly model-facing advanced cases use the real `ToolRegistry` configuration and the production Code Mode, workflow, and Cordis tool presenters. Synthetic presenter fixtures are limited to the generic card-shape matrix, where the TUI's input contract is the presenter view itself. Session events remain the driver so replay, streaming, result arrival, surface replacement, and lifecycle ordering exercise the same projection path as production. - -The TUI suite is included by `vitest.snapshot.config.ts`, so `pnpm run test:snapshot` compares it keylessly. `pnpm run test:snapshot:refresh` rewrites its derived terminal goldens without contacting a model; `test:snapshot:record` remains meaningful for suites whose transcript source requires recording. Both refresh paths still compare the resulting files in the same run. +| Recorded journey | Multi-turn conversation | Recorded reasoning/text chunks, two input turns, retained history, token totals, and idle editor state | +| Recorded journey | Todo plan | Real `todo_write` execution, result card, and persistent plan rendering | +| Recorded journey | Bash terminal card | Real local executor output, description, exit status, and completed terminal card | +| Recorded journey | Parallel filesystem reads | Two calls from one assistant message, real file contents, ordering, and separate completed cards | +| Recorded journey | Code Mode | Real `run_code` worker execution, two `tool/code-dispatch` events, captured program output, and completed card | +| Recorded journey | Dynamic workflow | Real workflow worker, phase lifecycle, replayed child session, structured return value, and completed card | +| Recorded journey | Cordis dynamic toolchain | Real mount, Code Mode inspect, direct subagent, workflow child, unmount, and all production presenters | +| Transient state | Streaming and pending advanced calls | In-flight reasoning/text plus pending Code Mode, workflow, and Cordis cards that disappear from completed logs | +| Transient state | Cards, interaction, layout, failure, and shutdown | Collapsed/expanded card families, question validation, compaction replacement, resize reflow, help/errors, cursor restoration, and terminal stop | ## Alternatives considered - **Snapshot raw terminal writes** — rejected because differential rendering may change write boundaries without changing the screen, while cursor and clear sequences are unreadable in review. -- **Snapshot component render lines before terminal output** — rejected because it does not test ANSI parsing, cursor movement, overlays, viewport behavior, or the interaction between independent components in one frame. +- **Snapshot component render lines before terminal output** — rejected because it does not test ANSI parsing, cursor movement, overlays, viewport behavior, or independent components in one frame. +- **Build every completed flow by appending session events** — rejected because a hand-authored event sequence can drift from the agent loop, tool execution, child-session binding, or worker behavior while its presentation test stays green. Direct event construction remains limited to transient renderer states. +- **Reuse ACP stdout goldens as the TUI oracle** — rejected because a recorded model journey is transport-neutral but its presentation is not. TUI scenarios own terminal goldens while using the same JSONL replay vocabulary. - **Commit raster screenshots** — rejected because fonts, glyph metrics, antialiasing, and host terminal themes make them platform-sensitive and make semantic style changes difficult to review. - **Use only PTY end-to-end tests** — rejected because raw PTY output is a stream of historical drawing operations, not queryable final state. PTY tests retain the real Loader/input/teardown boundary, while the emulator owns broad state coverage. -- **Copy pi-tui's unpublished virtual-terminal test helper** — rejected because the installed package does not export that helper. A small adapter around the public `@xterm/headless` API keeps the dependency explicit and the projection owned by this package. ## Consequences -- TUI visual regressions produce readable cell-and-style diffs, and the required matrix makes advanced features first-class rather than incidental coverage. -- The test dependency is pinned to the xterm version used by pi-tui. The adapter uses xterm's proposed buffer API, so an xterm upgrade requires rerunning and reviewing the semantic projection. -- The emulator models ANSI terminal state but cannot prove behavior unique to every terminal implementation. The real PTY conversation covers process selection, keyboard input, user interaction, and teardown without duplicating the full matrix. -- Goldens deliberately encode wrapping and viewport behavior at fixed sizes. Intentional layout changes update them through the keyless refresh command and receive ordinary snapshot review. +- Completed advanced snapshots now fail when the real Code Mode, workflow, subagent, filesystem, bash, or Cordis path breaks, rather than accepting a fabricated result event. +- TUI visual regressions produce readable cell-and-style diffs, while JSONL fixtures retain the exact model chunks that made the production path execute. +- The emulator uses xterm's proposed buffer API. An xterm upgrade requires rerunning and reviewing the semantic projection; terminal-specific behavior still needs the PTY smoke. +- Goldens deliberately encode wrapping and viewport behavior at fixed sizes. Intentional layout changes use keyless refresh, while model-journey changes use record mode and review both JSONL and terminal diffs. diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md index b7399a31b0..d1c609c6ce 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md @@ -8,50 +8,63 @@ Status: implemented TUI 是有状态的渲染器。用户最终看到的结果取决于 ANSI 解析、差分帧、换行、回滚缓冲、视口位置、终端宽度、焦点、光标状态，以及各工具的呈现意图。收集 `Terminal.write()` 片段的单元测试可以验证事件处理，却无法验证终端最终显示的画面。同一画面也可能由不同的写入片段产生，因此固定这些片段会制造误报。 -组件行快照止于 ANSI 进入终端之前，无法覆盖光标移动、清屏、样式、浮层组合和重排。栅格截图会带入与 TUI 契约无关的字体和平台渲染噪声。因此，TUI 既需要一种确定、便于评审的终端状态表示，也需要一项范围更小、覆盖真实进程与 PTY 边界的测试。 +组件行快照止于 ANSI 进入终端之前，无法覆盖光标移动、清屏、样式、浮层组合和重排。栅格截图会带入与 TUI 契约无关的字体和平台渲染噪声。直接追加看似合理的会话事件来构造完整流程还存在另一处盲区：这种测试只能证明渲染器接受这些数据形态，无法证明生产环境的 agent loop（智能体循环）和工具实现会生成这些事件。 + +因此，TUI 既需要确定、便于评审的终端状态表示，也需要通过已录制模型流程执行真实下游组件，并保留一项范围更小、覆盖真实进程与 PTY 边界的测试。 ## 决策 -TUI 覆盖分为三个互补层次： +TUI 覆盖分为四个互补层次： -1. `tui.spec.ts` 直接测试事件映射、输入路由、资源释放和错误行为。 -2. `tui.snapshot.ts` 将生产 TUI 挂载到无界面终端模拟器，并比较语义终端状态金标。 -3. `tui-keyless-smoke.e2e.ts` 在 PTY 中启动真实 Loader 组合，驱动一段完整的脚本化会话，使其依次经过流式输出和 `ask_user_question`，再通过 `/exit` 退出并验证终端清理。生产 coding-agent 配置还保留欢迎信息与退出，以及启动失败两类 PTY 场景。 +1. `packages/ui/tui/tests/tui.spec.ts` 直接测试事件映射、输入路由、资源释放和错误行为。 +2. `packages/ui/tui/tests/tui.snapshot.ts` 将生产 TUI 挂载到无界面终端模拟器，覆盖完整会话日志无法保留的瞬态：进行中的流式输出、待完成工具调用、浮层、展开状态、压缩重排、错误和关闭过程。 +3. `examples/tui-agent/tests/tui.snapshot.ts` 通过生产 agent loop 和真实工具回放已提交的 JSONL 会话日志，再比较生成的语义终端状态。 +4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 在 PTY 中启动真实 Loader 组合，驱动一段经过流式输出和 `ask_user_question` 的脚本化会话，并验证启动、输入、退出、失败报告和终端恢复。 -包内的 `HeadlessTerminal` 实现与进程终端相同的 pi-tui `Terminal` 接口，并把每次 ANSI 写入交给固定版本的 `@xterm/headless` 解析器。快照会等待 pi-tui 的同步输出结束标记，再读取状态。因此，每个检查点表示已经完成的帧，而不是依赖计时的写入前缀。 +可运行 TUI 在 `examples/tui-agent` 中拥有独立叶节点，与 readline `coding-agent` 和 `acp-agent` 叶节点并列。它通过带断言的 include patch 复用 coding agent 的后端与工具组合，只把共享终端应用固定为 `ui.mode: tui`；TUI 快照和 PTY 测试也归属这个叶节点。 -每份金标把终端状态投影为文本：尺寸、活动缓冲区和视口坐标、生命周期与光标状态、各行、换行标记，以及非默认样式区间。滚动内容较多的卡片捕获已使用缓冲区；浮层捕获可见视口。文本和样式相互分离，评审人无需解码 ANSI 字节即可区分内容变化与呈现变化。 +### 已录制会话回放 -每个检查点还会对完整终端状态强制执行主题无关性：禁止 RGB 颜色、禁止 ANSI 0–15 以外的调色板项，也禁止显式背景色。选择行使用终端默认色进行反显，因此仍然有效。测试套件拥有封闭的检查点清单：类型会拒绝未声明的名称，清单检查会拒绝缺失的检查点和遗留的 `.golden.txt` 文件。 +每个示例级场景目录都包含 `session.jsonl`、可选的子会话日志 `session..jsonl`，以及 `terminal.golden.txt`。主日志提供用户来源的 `user/message` 提示词和已录制的 `assistant/chunk` 序列。`dsh-llm-replay` 为每个会话派生一份模型调用脚本，并将子日志绑定到新建的子会话；这是测试中唯一的 mock 边界。agent loop、bash 与文件系统实现、Code Mode worker、subagent 提供方、工作流 worker、Cordis 工具、呈现器和 TUI 都使用生产实现。 + +如果工具调用顺序不符、预期事件数量不足、工具结果报错、轮次以错误结束、工作流生命周期不完整，或者实时子会话数量与 fixture（测试前置数据）集合不一致，测试都会失败。即使终端金标表面正确，这些断言也能阻止失败或被绕过的生产路径混入结果。 + +真实模型 fixture 通过 `DSH_SNAPSHOT=record` 更新；录制模式会重写其主会话与子会话 JSONL 日志以及终端金标。确定性的 Cordis 工具链保留一份人工编写的完整 JSONL 脚本，因为要求真实模型稳定经过五个指定工具边界和两个子会话并不是可靠的录制契约。`DSH_SNAPSHOT=refresh` 会无密钥回放所有已提交脚本，并且只重写派生的终端金标。普通回放只比较而不写入，未知模式值会快速失败。 + +### 语义终端投影 + +包内的 `HeadlessTerminal` 实现与进程终端相同的 pi-tui `Terminal` 接口，并把每次 ANSI 写入交给固定版本的 `@xterm/headless` 解析器。读取状态前，快照代码会等待同步帧稳定，因此每个检查点表示已经完成的画面，而不是依赖计时的写入前缀。 + +每份金标把终端尺寸、活动缓冲区和视口坐标、生命周期与光标状态、各行、换行标记以及非默认样式区间投影为文本。滚动内容较多的卡片捕获已使用缓冲区；浮层捕获可见视口。文本和样式相互分离，评审人无需解码 ANSI 字节即可区分内容变化与呈现变化。 + +每个检查点还会对完整终端状态强制执行主题无关性：禁止 RGB 颜色、禁止 ANSI 0–15 以外的调色板项，也禁止显式背景色。选择行使用终端默认色进行反显，因此仍然有效。两套测试都拥有封闭清单，会拒绝缺失的场景、缺失的检查点和遗留金标文件。 ### 必需场景矩阵 -| 范围 | 代表性检查点 | 固定的契约 | +| 层次 | 场景 | 固定的契约 | |---|---|---| -| 会话 | 回放、流式输出、完成 | 恢复后的 Markdown 与推理、实时增量、计划、token 用量，以及达到 token 上限时的完成状态 | -| Code Mode | `run_code` 待完成与已完成 | 生产 Code Mode 注册表与呈现器、源程序、捕获日志和结果 | -| 动态工作流 | `workflow` 待完成与已完成 | 生产工作流呈现器、元数据、阶段、并行 agent、脚本和结构化结果 | -| Cordis 工具 | inspect/mount/unmount 待完成与已完成 | 生产 `cordis_inspect`、`cordis_mount` 和 `cordis_unmount` 呈现器及其生命周期结果 | -| 高级工具卡片 | 折叠与展开 | 终端、diff、通用、subagent、后台任务和 skill 卡片形态，以及输出截断 | -| 交互 | 问题与校验 | 受限多选浮层的组合、焦点、滚动、选择和校验错误 | -| 表层与布局 | 压缩前、窄幅替换、宽幅替换 | 表层替换会移除退役内容；调整尺寸只会重排保留的表层，不会让旧内容重新出现 | -| 失败与关闭 | 错误与帮助、终端已释放 | 帮助与未知命令、实时错误和轮次错误去重、中断、光标恢复及终端停止 | - -面向模型的高级场景明确使用真实 `ToolRegistry` 配置，以及生产 Code Mode、工作流和 Cordis 工具呈现器。只有通用卡片形态矩阵使用合成呈现器 fixture；在这里，呈现器视图本身就是 TUI 的输入契约。测试仍由会话事件驱动，因此回放、流式输出、结果到达、表层替换和生命周期顺序都会经过与生产环境相同的投影路径。 - -`vitest.snapshot.config.ts` 会包含 TUI 测试套件，因此 `pnpm run test:snapshot` 可以无密钥比较快照。`pnpm run test:snapshot:refresh` 会重写从终端状态派生的金标，而不会联系模型；对于 transcript（文本记录）来源需要录制的测试套件，`test:snapshot:record` 仍有其原有含义。两条刷新路径都会在同一次运行中继续比较生成后的文件。 +| 已录制流程 | 多轮会话 | 已录制的推理与文本分片、两轮输入、保留历史、token 总量和空闲编辑器状态 | +| 已录制流程 | Todo 计划 | 真实 `todo_write` 执行、结果卡片和持久计划渲染 | +| 已录制流程 | Bash 终端卡片 | 真实本地执行器输出、说明、退出状态和已完成终端卡片 | +| 已录制流程 | 并行文件读取 | 同一条 assistant 消息中的两次调用、真实文件内容、顺序和两个独立完成卡片 | +| 已录制流程 | Code Mode | 真实 `run_code` worker 执行、两条 `tool/code-dispatch` 事件、捕获的程序输出和已完成卡片 | +| 已录制流程 | 动态工作流 | 真实工作流 worker、阶段生命周期、回放的子会话、结构化返回值和已完成卡片 | +| 已录制流程 | Cordis 动态工具链 | 真实挂载、Code Mode 检查、直接 subagent、工作流子会话、卸载和全部生产呈现器 | +| 瞬态 | 流式输出与待完成高级调用 | 进行中的推理和文本，以及完整日志中不会保留的待完成 Code Mode、工作流和 Cordis 卡片 | +| 瞬态 | 卡片、交互、布局、失败和关闭 | 折叠与展开的卡片族、问题校验、压缩替换、尺寸重排、帮助与错误、光标恢复和终端停止 | ## 曾考虑的替代方案 - **快照原始终端写入**：不予采纳，因为差分渲染可能在画面不变时改变写入边界，而且光标与清屏序列难以评审。 - **快照进入终端输出之前的组件渲染行**：不予采纳，因为它无法测试 ANSI 解析、光标移动、浮层、视口行为，也无法测试独立组件在同一帧中的相互作用。 +- **通过追加会话事件构造所有完整流程**：不予采纳，因为人工编写的事件序列可能与 agent loop、工具执行、子会话绑定或 worker 行为发生偏差，但呈现测试仍然保持绿色。直接构造事件只用于渲染器瞬态。 +- **复用 ACP stdout 金标作为 TUI 判定依据**：不予采纳，因为已录制模型流程与传输方式无关，其呈现方式却并非如此。TUI 场景使用同一套 JSONL 回放词汇，但拥有独立的终端金标。 - **提交栅格截图**：不予采纳，因为字体、字形度量、抗锯齿和宿主终端主题会使结果依赖平台，也会增加语义样式变更的评审难度。 - **只使用 PTY 端到端测试**：不予采纳，因为原始 PTY 输出是一系列历史绘制操作，而不是可查询的最终状态。PTY 测试保留真实 Loader、输入与清理边界，模拟器负责广泛的状态覆盖。 -- **复制 pi-tui 未发布的虚拟终端测试 helper**：不予采纳，因为已安装的包并未导出该 helper。围绕公开 `@xterm/headless` API 编写小型适配器，可以显式声明依赖，并让本包拥有状态投影。 ## 后果 -- TUI 视觉回归会产生便于阅读的单元格和样式 diff；必需场景矩阵也让高级功能成为一等测试对象，而不是偶然覆盖。 -- 测试依赖固定到 pi-tui 使用的 xterm 版本。适配器使用 xterm 的拟议缓冲区 API，因此升级 xterm 时必须重新运行并评审语义投影。 -- 模拟器可以建模 ANSI 终端状态，但无法证明每种终端实现独有的行为。真实 PTY 会话覆盖进程选择、键盘输入、用户交互和清理，无需复制完整矩阵。 -- 金标有意固定指定尺寸下的换行与视口行为。布局的预期变更通过无密钥刷新命令更新，并接受常规快照评审。 +- 当真实 Code Mode、工作流、subagent、文件系统、bash 或 Cordis 路径损坏时，已完成高级快照会失败，不会继续接受伪造的结果事件。 +- TUI 视觉回归会产生便于阅读的单元格和样式 diff，而 JSONL fixture 会保留触发生产路径的确切模型分片。 +- 模拟器使用 xterm 的拟议缓冲区 API。升级 xterm 时必须重新运行并评审语义投影；终端特有行为仍需由 PTY 冒烟测试覆盖。 +- 金标有意固定指定尺寸下的换行与视口行为。预期布局变更使用无密钥刷新；模型流程变更使用录制模式，并同时评审 JSONL 与终端 diff。 diff --git a/docs/testing.md b/docs/testing.md index 5f10e1741c..e8b32fac80 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -7,7 +7,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless goldens cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized stdout plus the re-persisted log ([ACP snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)); the TUI suite parses real ANSI output into semantic terminal-state goldens and retains a real PTY conversation at the process boundary ([TUI snapshot RFC](rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when the committed transcript or scripted events remain correct; review every golden diff. System-prompt/tool-schema content is pinned by ONE ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless goldens cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized stdout plus the re-persisted log ([ACP snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)). TUI completed journeys replay recorded primary/child JSONL through the real agent loop and tools before projecting ANSI into semantic terminal-state goldens; package-local snapshots retain transient renderer states, and a real PTY conversation covers the process boundary ([TUI snapshot RFC](rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when committed replay input remains correct; review every JSONL and golden diff. System-prompt/tool-schema content is pinned by ONE ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here @@ -35,4 +35,4 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword ## When a snapshot test is required -Any change affecting an editor-facing transcript or end-to-end agent UX adds or updates a scenario in the owning snapshot suite, or states in the PR why none applies. ACP surfaces use `examples//tests/snapshots/`, a scenario table over the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) suite factory (`examples/acp-agent` is primary); interactive-terminal presentation uses the semantic TUI matrix, with a PTY case when input, Loader selection, or terminal teardown changes. New capability seams, lifecycle shapes, or transcript surfaces name their coverage at every tier at plan time and verify the harness can express it — a harness gap is scheduled work, not a mid-build surprise. +Any change affecting an editor-facing transcript or end-to-end agent UX adds or updates a scenario in the owning snapshot suite, or states in the PR why none applies. ACP surfaces use `examples//tests/snapshots/`, a scenario table over the [`dsh-acp-snapshot`](../packages/support/acp-snapshot/README.md) suite factory (`examples/acp-agent` is primary). Completed interactive-terminal journeys use JSONL-driven scenarios under `examples/tui-agent/tests/snapshots/`; transient presentation uses the package-local semantic matrix, with a PTY case when input, Loader selection, or terminal teardown changes. New capability seams, lifecycle shapes, or transcript surfaces name their coverage at every tier at plan time and verify the harness can express it — a harness gap is scheduled work, not a mid-build surprise. diff --git a/examples/tui-agent/README.md b/examples/tui-agent/README.md index 909ccf700d..ee5b610d53 100644 --- a/examples/tui-agent/README.md +++ b/examples/tui-agent/README.md @@ -17,3 +17,7 @@ Run `pnpm run demo:code-mode tui` for the sibling Code Mode overlay. ## Composition [`cordis.yml`](cordis.yml) includes the readline coding-agent leaf so the LLM, bash, filesystem, compaction, subagent, workflow, todo, timeout, and spill choices have one owner. Its asserted patch replaces only the terminal app config and forces `ui.mode: tui`; [`code-mode.cordis.yml`](code-mode.cordis.yml) applies the same front-door patch to the coding agent's Code Mode overlay. + +## Snapshot tests + +`tests/snapshots//session.jsonl` supplies recorded user prompts and model chunks; sibling child logs drive subagents and workflows. The keyless suite executes those scripts through the real loop and tool implementations, then compares readable terminal cell/style goldens. Use `pnpm run test:snapshot:refresh` for presentation-only changes and `pnpm run test:snapshot:record` with a DeepSeek key when a recorded model journey changes. The implemented [TUI snapshot RFC](../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns the scenario matrix and the split between recorded journeys, transient package snapshots, and PTY coverage. diff --git a/examples/tui-agent/tests/snapshots/bash-terminal-card/session.jsonl b/examples/tui-agent/tests/snapshots/bash-terminal-card/session.jsonl new file mode 100644 index 0000000000..e53f4b3da3 --- /dev/null +++ b/examples/tui-agent/tests/snapshots/bash-terminal-card/session.jsonl @@ -0,0 +1,98 @@ +{"type":"session","version":0,"id":"e128dda9-ed11-4868-8266-0ef90d03c3d6","createdAt":1783352050748,"cwd":"/tmp/acp-snap-cwd-mrFUuk"} +{"type":"turn/start","seq":0,"time":1783352050753,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783352050753,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo TERMINAL_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783352050755,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783352050756,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783352051421,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783352051422,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783352051590,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783352051618,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783352051618,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783352051619,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783352051619,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":11,"time":1783352051619,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":12,"time":1783352051645,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" simple"}}} +{"type":"assistant/chunk","seq":13,"time":1783352051675,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} +{"type":"assistant/chunk","seq":14,"time":1783352051675,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} +{"type":"assistant/chunk","seq":15,"time":1783352051675,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":16,"time":1783352051676,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":17,"time":1783352051676,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":18,"time":1783352051703,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":19,"time":1783352051704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":20,"time":1783352051704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":21,"time":1783352051704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":22,"time":1783352051704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":23,"time":1783352051790,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":24,"time":1783352051791,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":25,"time":1783352051820,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":26,"time":1783352051820,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":27,"time":1783352051820,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"command"}}} +{"type":"assistant/chunk","seq":28,"time":1783352051820,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":29,"time":1783352051820,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":30,"time":1783352051848,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":31,"time":1783352051848,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"echo"}}} +{"type":"assistant/chunk","seq":32,"time":1783352051848,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":" TER"}}} +{"type":"assistant/chunk","seq":33,"time":1783352051848,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"MIN"}}} +{"type":"assistant/chunk","seq":34,"time":1783352051877,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"AL"}}} +{"type":"assistant/chunk","seq":35,"time":1783352051877,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"_OK"}}} +{"type":"assistant/chunk","seq":36,"time":1783352051877,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":37,"time":1783352051905,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":38,"time":1783352051906,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":39,"time":1783352051906,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":40,"time":1783352051935,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":41,"time":1783352051935,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":42,"time":1783352051935,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":43,"time":1783352051935,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"E"}}} +{"type":"assistant/chunk","seq":44,"time":1783352051967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"cho"}}} +{"type":"assistant/chunk","seq":45,"time":1783352051967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":" TER"}}} +{"type":"assistant/chunk","seq":46,"time":1783352051967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"MIN"}}} +{"type":"assistant/chunk","seq":47,"time":1783352051967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"AL"}}} +{"type":"assistant/chunk","seq":48,"time":1783352051967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"_OK"}}} +{"type":"assistant/chunk","seq":49,"time":1783352051967,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":" to"}}} +{"type":"assistant/chunk","seq":50,"time":1783352052041,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":" verify"}}} +{"type":"assistant/chunk","seq":51,"time":1783352052041,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":" terminal"}}} +{"type":"assistant/chunk","seq":52,"time":1783352052041,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":" access"}}} +{"type":"assistant/chunk","seq":53,"time":1783352052054,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":54,"time":1783352052054,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":55,"time":1783352052117,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."}}}} +{"type":"assistant/chunk","seq":56,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}}}} +{"type":"assistant/chunk","seq":57,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":58,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":59,"time":1783352052121,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58],"surfaceOp":"append"} +{"type":"tool/call","seq":60,"time":1783352052121,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}} +{"type":"tool/result","seq":61,"time":1783352052136,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","content":[{"type":"text","text":"TERMINAL_OK\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"} +{"type":"step/end","seq":62,"time":1783352052137,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":63,"time":1783352052137,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":64,"time":1783352052701,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":65,"time":1783352052702,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":66,"time":1783352052780,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" command"}}} +{"type":"assistant/chunk","seq":67,"time":1783352052809,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ran"}}} +{"type":"assistant/chunk","seq":68,"time":1783352052838,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} +{"type":"assistant/chunk","seq":69,"time":1783352052838,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":70,"time":1783352052838,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} +{"type":"assistant/chunk","seq":71,"time":1783352052867,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":72,"time":1783352052867,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"TER"}}} +{"type":"assistant/chunk","seq":73,"time":1783352052867,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"MIN"}}} +{"type":"assistant/chunk","seq":74,"time":1783352052867,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":75,"time":1783352052867,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} +{"type":"assistant/chunk","seq":76,"time":1783352052867,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":77,"time":1783352052895,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":78,"time":1783352052896,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} +{"type":"assistant/chunk","seq":79,"time":1783352052924,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" now"}}} +{"type":"assistant/chunk","seq":80,"time":1783352052925,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":81,"time":1783352052925,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":82,"time":1783352052925,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} +{"type":"assistant/chunk","seq":83,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":84,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":85,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":86,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":87,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":88,"time":1783352052957,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":89,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":90,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."}}}} +{"type":"assistant/chunk","seq":91,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":92,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}}}} +{"type":"assistant/chunk","seq":93,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":94,"time":1783352052987,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"surfaceOp":"append"} +{"type":"step/end","seq":95,"time":1783352052987,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":96,"time":1783352052987,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt b/examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt new file mode 100644 index 0000000000..30770dcccb --- /dev/null +++ b/examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt @@ -0,0 +1,72 @@ +terminal 100x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH TUI snapshot" +cursor hidden column=1 viewportRow=27 bufferRow=27 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Recorded replay: bash-terminal-card │" + style 0-0 fg=bright-blue + style 2-36 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Use the bash tool to run exactly: echo TERMINAL_OK. Then reply with the single word DONE and stop." + style 0-0 fg=bright-blue +9| "▌ " + style 0-0 fg=bright-blue +10| +11| " Reasoning " + style 1-9 fg=bright-black italic +12| " The user wants me to run a simple bash command and then reply with \"DONE\". " + style 1-74 fg=bright-black italic +13| +14| "▌ " + style 0-0 fg=green +15| "▌ ✓ echo TERMINAL_OK " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-19 bold +16| "▌ Echo TERMINAL_OK to verify terminal access " + style 0-0 fg=green + style 2-43 fg=bright-black +17| "▌ TERMINAL_OK " + style 0-0 fg=green +18| "▌ [exit 0] " + style 0-0 fg=green + style 2-9 dim +19| "▌ " + style 0-0 fg=green +20| +21| " Reasoning " + style 1-9 fg=bright-black italic +22| " The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\". " + style 1-91 fg=bright-black italic +23| +24| " Assistant " + style 1-9 fg=bright-magenta bold +25| " DONE " +26| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +27| " " + style 1-1 inverse +28| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +29| "/workspace/project ↑3.0k ↓" + style 0-99 dim +30-35| diff --git a/examples/tui-agent/tests/snapshots/code-mode/session.jsonl b/examples/tui-agent/tests/snapshots/code-mode/session.jsonl new file mode 100644 index 0000000000..0fe57055e8 --- /dev/null +++ b/examples/tui-agent/tests/snapshots/code-mode/session.jsonl @@ -0,0 +1,150 @@ +{"type":"session","version":0,"id":"94cd1ae4-e1d1-4ec8-9d27-50a1f849b6b3","createdAt":1783611771392,"cwd":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-BteTVR"} +{"type":"turn/start","seq":0,"time":1783611771394,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783611771394,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO` — and return the two outputs joined with a plus sign. Then reply with that joined string only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783611771396,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783611771978,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783611772007,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783611772008,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":9,"time":1783611772036,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":10,"time":1783611772036,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":11,"time":1783611772036,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_code"}}} +{"type":"assistant/chunk","seq":12,"time":1783611772036,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" program"}}} +{"type":"assistant/chunk","seq":13,"time":1783611772036,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":14,"time":1783611772089,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" calls"}}} +{"type":"assistant/chunk","seq":15,"time":1783611772089,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} +{"type":"assistant/chunk","seq":16,"time":1783611772089,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" twice"}}} +{"type":"assistant/chunk","seq":17,"time":1783611772096,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":18,"time":1783611772124,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":19,"time":1783611772153,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" returns"}}} +{"type":"assistant/chunk","seq":20,"time":1783611772183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":21,"time":1783611772183,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" two"}}} +{"type":"assistant/chunk","seq":22,"time":1783611772211,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" outputs"}}} +{"type":"assistant/chunk","seq":23,"time":1783611772212,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" joined"}}} +{"type":"assistant/chunk","seq":24,"time":1783611772212,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":25,"time":1783611772212,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":26,"time":1783611772212,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" plus"}}} +{"type":"assistant/chunk","seq":27,"time":1783611772212,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sign"}}} +{"type":"assistant/chunk","seq":28,"time":1783611772241,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":29,"time":1783611772241,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":30,"time":1783611772241,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":31,"time":1783611772241,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" write"}}} +{"type":"assistant/chunk","seq":32,"time":1783611772270,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} +{"type":"assistant/chunk","seq":33,"time":1783611772270,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":34,"time":1783611772361,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":35,"time":1783611772361,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":36,"time":1783611772361,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":37,"time":1783611772362,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":38,"time":1783611772390,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"code"}}} +{"type":"assistant/chunk","seq":39,"time":1783611772390,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":40,"time":1783611772390,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":41,"time":1783611772390,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":42,"time":1783611772420,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"const"}}} +{"type":"assistant/chunk","seq":43,"time":1783611772420,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":44,"time":1783611772420,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"1"}}} +{"type":"assistant/chunk","seq":45,"time":1783611772420,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" ="}}} +{"type":"assistant/chunk","seq":46,"time":1783611772421,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" await"}}} +{"type":"assistant/chunk","seq":47,"time":1783611772421,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" tools"}}} +{"type":"assistant/chunk","seq":48,"time":1783611772449,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":".b"}}} +{"type":"assistant/chunk","seq":49,"time":1783611772449,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"ash"}}} +{"type":"assistant/chunk","seq":50,"time":1783611772449,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"({"}}} +{"type":"assistant/chunk","seq":51,"time":1783611772449,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" command"}}} +{"type":"assistant/chunk","seq":52,"time":1783611772478,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":":"}}} +{"type":"assistant/chunk","seq":53,"time":1783611772479,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" \\\""}}} +{"type":"assistant/chunk","seq":54,"time":1783611772479,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"echo"}}} +{"type":"assistant/chunk","seq":55,"time":1783611772479,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" CODE"}}} +{"type":"assistant/chunk","seq":56,"time":1783611772479,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"_"}}} +{"type":"assistant/chunk","seq":57,"time":1783611772508,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"ONE"}}} +{"type":"assistant/chunk","seq":58,"time":1783611772510,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\\\","}}} +{"type":"assistant/chunk","seq":59,"time":1783611772510,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" description"}}} +{"type":"assistant/chunk","seq":60,"time":1783611772510,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":":"}}} +{"type":"assistant/chunk","seq":61,"time":1783611772510,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" \\\""}}} +{"type":"assistant/chunk","seq":62,"time":1783611772510,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"First"}}} +{"type":"assistant/chunk","seq":63,"time":1783611772538,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" echo"}}} +{"type":"assistant/chunk","seq":64,"time":1783611772538,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\\\""}}} +{"type":"assistant/chunk","seq":65,"time":1783611772566,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" });\\n"}}} +{"type":"assistant/chunk","seq":66,"time":1783611772567,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"const"}}} +{"type":"assistant/chunk","seq":67,"time":1783611772567,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":68,"time":1783611772567,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"2"}}} +{"type":"assistant/chunk","seq":69,"time":1783611772567,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" ="}}} +{"type":"assistant/chunk","seq":70,"time":1783611772567,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" await"}}} +{"type":"assistant/chunk","seq":71,"time":1783611772597,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" tools"}}} +{"type":"assistant/chunk","seq":72,"time":1783611772597,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":".b"}}} +{"type":"assistant/chunk","seq":73,"time":1783611772597,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"ash"}}} +{"type":"assistant/chunk","seq":74,"time":1783611772598,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"({"}}} +{"type":"assistant/chunk","seq":75,"time":1783611772598,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" command"}}} +{"type":"assistant/chunk","seq":76,"time":1783611772598,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":":"}}} +{"type":"assistant/chunk","seq":77,"time":1783611772625,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" \\\""}}} +{"type":"assistant/chunk","seq":78,"time":1783611772625,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"echo"}}} +{"type":"assistant/chunk","seq":79,"time":1783611772625,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" CODE"}}} +{"type":"assistant/chunk","seq":80,"time":1783611772626,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"_T"}}} +{"type":"assistant/chunk","seq":81,"time":1783611772626,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"WO"}}} +{"type":"assistant/chunk","seq":82,"time":1783611772626,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\\\","}}} +{"type":"assistant/chunk","seq":83,"time":1783611772654,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" description"}}} +{"type":"assistant/chunk","seq":84,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":":"}}} +{"type":"assistant/chunk","seq":85,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" \\\""}}} +{"type":"assistant/chunk","seq":86,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"Second"}}} +{"type":"assistant/chunk","seq":87,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" echo"}}} +{"type":"assistant/chunk","seq":88,"time":1783611772655,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\\\""}}} +{"type":"assistant/chunk","seq":89,"time":1783611772684,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" });\\n"}}} +{"type":"assistant/chunk","seq":90,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"return"}}} +{"type":"assistant/chunk","seq":91,"time":1783611772685,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":92,"time":1783611772713,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"1"}}} +{"type":"assistant/chunk","seq":93,"time":1783611772714,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":".trim"}}} +{"type":"assistant/chunk","seq":94,"time":1783611772714,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"()"}}} +{"type":"assistant/chunk","seq":95,"time":1783611772714,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" +"}}} +{"type":"assistant/chunk","seq":96,"time":1783611772714,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" \\\"+"}}} +{"type":"assistant/chunk","seq":97,"time":1783611772744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\\\""}}} +{"type":"assistant/chunk","seq":98,"time":1783611772744,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" +"}}} +{"type":"assistant/chunk","seq":99,"time":1783611772745,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":" out"}}} +{"type":"assistant/chunk","seq":100,"time":1783611772745,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"2"}}} +{"type":"assistant/chunk","seq":101,"time":1783611772745,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":".trim"}}} +{"type":"assistant/chunk","seq":102,"time":1783611772745,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"();"}}} +{"type":"assistant/chunk","seq":103,"time":1783611772772,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":104,"time":1783611772773,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":105,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."}}}} +{"type":"assistant/chunk","seq":106,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}}}} +{"type":"assistant/chunk","seq":107,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}}}} +{"type":"assistant/chunk","seq":108,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"tool/call","seq":110,"time":1783611772840,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}} +{"type":"tool/code-dispatch","seq":111,"time":1783611772933,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"First echo"},"isError":false,"resultSummary":"CODE_ONE\n"}} +{"type":"tool/code-dispatch","seq":112,"time":1783611772936,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Second echo"},"isError":false,"resultSummary":"CODE_TWO\n"}} +{"type":"tool/result","seq":113,"time":1783611772937,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","content":[{"type":"text","text":"CODE_ONE+CODE_TWO"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[110],"surfaceOp":"append"} +{"type":"step/end","seq":114,"time":1783611772938,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":115,"time":1783611772938,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":116,"time":1783611773376,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":117,"time":1783611773376,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":118,"time":1783611773480,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" output"}}} +{"type":"assistant/chunk","seq":119,"time":1783611773511,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} +{"type":"assistant/chunk","seq":120,"time":1783611773512,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":121,"time":1783611773540,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} +{"type":"assistant/chunk","seq":122,"time":1783611773541,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":123,"time":1783611773541,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":124,"time":1783611773569,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} +{"type":"assistant/chunk","seq":125,"time":1783611773570,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" for"}}} +{"type":"assistant/chunk","seq":126,"time":1783611773570,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} +{"type":"assistant/chunk","seq":127,"time":1783611773597,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" CODE"}}} +{"type":"assistant/chunk","seq":128,"time":1783611773597,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_"}}} +{"type":"assistant/chunk","seq":129,"time":1783611773597,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":130,"time":1783611773626,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"+"}}} +{"type":"assistant/chunk","seq":131,"time":1783611773627,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"CODE"}}} +{"type":"assistant/chunk","seq":132,"time":1783611773627,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_T"}}} +{"type":"assistant/chunk","seq":133,"time":1783611773627,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"WO"}}} +{"type":"assistant/chunk","seq":134,"time":1783611773654,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":135,"time":1783611773655,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"CODE"}}} +{"type":"assistant/chunk","seq":136,"time":1783611773655,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_"}}} +{"type":"assistant/chunk","seq":137,"time":1783611773656,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":138,"time":1783611773656,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"+"}}} +{"type":"assistant/chunk","seq":139,"time":1783611773656,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"CODE"}}} +{"type":"assistant/chunk","seq":140,"time":1783611773657,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_T"}}} +{"type":"assistant/chunk","seq":141,"time":1783611773685,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"WO"}}} +{"type":"assistant/chunk","seq":142,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The output is exactly what the user asked for: CODE_ONE+CODE_TWO"}}}} +{"type":"assistant/chunk","seq":143,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CODE_ONE+CODE_TWO"}}}} +{"type":"assistant/chunk","seq":144,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}}}} +{"type":"assistant/chunk","seq":145,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":146,"time":1783611773687,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is exactly what the user asked for: CODE_ONE+CODE_TWO"},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145],"surfaceOp":"append"} +{"type":"step/end","seq":147,"time":1783611773687,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":148,"time":1783611773687,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt b/examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt new file mode 100644 index 0000000000..a7f1457d7a --- /dev/null +++ b/examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt @@ -0,0 +1,79 @@ +terminal 100x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH TUI snapshot" +cursor hidden column=1 viewportRow=29 bufferRow=29 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Recorded replay: code-mode │" + style 0-0 fg=bright-blue + style 2-27 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Using ONE run_code program: call the bash tool twice — exactly echo CODE_ONE then exactly echo " + style 0-0 fg=bright-blue + style 65-77 fg=cyan + style 92-99 fg=cyan +9| "▌ CODE_TWO — and return the two outputs joined with a plus sign. Then reply with that joined string " + style 0-0 fg=bright-blue + style 2-9 fg=cyan +10| "▌ only and stop. " + style 0-0 fg=bright-blue +11| "▌ " + style 0-0 fg=bright-blue +12| +13| " Reasoning " + style 1-9 fg=bright-black italic +14| " The user wants a single run_code program that calls bash twice, then returns the two outputs " + style 1-99 fg=bright-black italic +15| " joined with a plus sign. Let me write this. " + style 1-43 fg=bright-black italic +16| +17| "▌ " + style 0-0 fg=green +18| "▌ ✓ const out1 = await tools.bash({ command: \"echo CODE_ONE\", description: \"First echo\" }); " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-99 bold +19| "▌ const o " + style 0-0 fg=green + style 2-8 bold +20| "▌ CODE_ONE+CODE_TWO " + style 0-0 fg=green +21| "▌ " + style 0-0 fg=green +22| +23| " Reasoning " + style 1-9 fg=bright-black italic +24| " The output is exactly what the user asked for: CODE_ONE+CODE_TWO " + style 1-64 fg=bright-black italic +25| +26| " Assistant " + style 1-9 fg=bright-magenta bold +27| " CODE_ONE+CODE_TWO " +28| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +29| " " + style 1-1 inverse +30| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +31| "/workspace/project ↑3.1k ↓158 idle" + style 0-93 dim + style 96-99 dim +32-35| diff --git a/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.1.jsonl b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.1.jsonl new file mode 100644 index 0000000000..25a6f76411 --- /dev/null +++ b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.1.jsonl @@ -0,0 +1,13 @@ +{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"/tmp/advanced-acp","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} +{"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.2.jsonl b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.2.jsonl new file mode 100644 index 0000000000..45d9043a4a --- /dev/null +++ b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.2.jsonl @@ -0,0 +1,13 @@ +{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"/tmp/advanced-acp","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} +{"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.jsonl b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.jsonl new file mode 100644 index 0000000000..39f867984a --- /dev/null +++ b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/session.jsonl @@ -0,0 +1,64 @@ +{"type":"session","version":0,"id":"11111111-1111-4111-8111-111111111111","createdAt":1783950000000,"cwd":"/tmp/advanced-acp"} +{"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} +{"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":1783950000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"tool/call","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}} +{"type":"tool/result","seq":11,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} +{"type":"step/end","seq":12,"time":1783957884489,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":13,"time":1783957884489,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":14,"time":1783950000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":15,"time":1783950000016,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-code","name":"run_code","argumentsDelta":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}} +{"type":"assistant/chunk","seq":16,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} +{"type":"assistant/chunk","seq":17,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":18,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} +{"type":"tool/call","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}} +{"type":"tool/code-dispatch","seq":21,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}} +{"type":"tool/result","seq":22,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"} +{"type":"step/end","seq":23,"time":1783957884561,"data":{"turn":1,"step":2}} +{"type":"step/start","seq":24,"time":1783957884562,"data":{"turn":1,"step":3}} +{"type":"assistant/chunk","seq":25,"time":1783950000026,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":26,"time":1783950000027,"data":{"turn":1,"step":3,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-direct-child","name":"subagent","argumentsDelta":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}} +{"type":"assistant/chunk","seq":27,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":28,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":29,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} +{"type":"tool/call","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}} +{"type":"tool/result","seq":32,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1783957884593,"data":{"turn":1,"step":3}} +{"type":"step/start","seq":34,"time":1783957884594,"data":{"turn":1,"step":4}} +{"type":"assistant/chunk","seq":35,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":36,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-workflow","name":"workflow","argumentsDelta":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}} +{"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}} +{"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} +{"type":"tool/call","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}} +{"type":"tool/result","seq":42,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"} +{"type":"step/end","seq":43,"time":1783957884718,"data":{"turn":1,"step":4}} +{"type":"step/start","seq":44,"time":1783957884718,"data":{"turn":1,"step":5}} +{"type":"assistant/chunk","seq":45,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":46,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-unmount","name":"cordis_unmount","argumentsDelta":"{\"id\":\"dyn-1\"}"}}} +{"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}} +{"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} +{"type":"tool/call","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}} +{"type":"tool/result","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} +{"type":"step/end","seq":53,"time":1783957884719,"data":{"turn":1,"step":5}} +{"type":"step/start","seq":54,"time":1783957884720,"data":{"turn":1,"step":6}} +{"type":"assistant/chunk","seq":55,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":56,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"text-delta","index":0,"text":"ADVANCED_ACP_OK"}}} +{"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}} +{"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} +{"type":"step/end","seq":61,"time":1783957884721,"data":{"turn":1,"step":6}} +{"type":"turn/end","seq":62,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt new file mode 100644 index 0000000000..5c5afc10ca --- /dev/null +++ b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt @@ -0,0 +1,115 @@ +terminal 100x36 buffer=normal length=50 base=14 viewport=14 +lifecycle started=1 stopped=0 progress=inactive +title "DSH TUI snapshot" +cursor hidden column=1 viewportRow=33 bufferRow=47 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Recorded replay: cordis-dynamic-toolchain │" + style 0-0 fg=bright-blue + style 2-42 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use " + style 0-0 fg=bright-blue +9| "▌ run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a " + style 0-0 fg=bright-blue +10| "▌ direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then " + style 0-0 fg=bright-blue +11| "▌ reply with exactly ADVANCED_ACP_OK. " + style 0-0 fg=bright-blue +12| "▌ " + style 0-0 fg=bright-blue +13| +14| "▌ " + style 0-0 fg=green +15| "▌ ✓ Mount plugin into live cordis runtime " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-40 bold +16| "▌ mounted dyn-1 (plugin \"snapshot-marker\", state: active) " + style 0-0 fg=green +17| "▌ " + style 0-0 fg=green +18| +19| "▌ " + style 0-0 fg=green +20| "▌ ✓ return await tools.cordis_inspect({ what: 'dynamic' }) " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-57 bold +21| "▌ ## dynamic " + style 0-0 fg=green +22| "▌ - dyn-1: snapshot-marker [active] " + style 0-0 fg=green +23| "▌ " + style 0-0 fg=green +24| +25| "▌ " + style 0-0 fg=green +26| "▌ ✓ subagent " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-11 bold +27| "▌ DIRECT_CHILD_OK " + style 0-0 fg=green +28| "▌ " + style 0-0 fg=green +29| +30| "▌ " + style 0-0 fg=green +31| "▌ ✓ workflow: advanced-acp-snapshot " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-34 bold +32| "▌ workflow \"advanced-acp-snapshot\" completed (1 agent). " + style 0-0 fg=green +33| "▌ Return value: " + style 0-0 fg=green +34| "▌ { " + style 0-0 fg=green +35| "▌ \"reply\": \"WORKFLOW_CHILD_OK\" " + style 0-0 fg=green +36| "▌ } " + style 0-0 fg=green +37| "▌ " + style 0-0 fg=green +38| +39| "▌ " + style 0-0 fg=green +40| "▌ ✓ Unmount dyn-1 " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-16 bold +41| "▌ unmounted dyn-1 (plugin \"snapshot-marker\") " + style 0-0 fg=green +42| "▌ " + style 0-0 fg=green +43| +44| " Assistant " + style 1-9 fg=bright-magenta bold +45| " ADVANCED_ACP_OK " +46| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +47| " " + style 1-1 inverse +48| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +49| "/workspace/project ↑" + style 0-99 dim diff --git a/examples/tui-agent/tests/snapshots/dynamic-workflow/session.1.jsonl b/examples/tui-agent/tests/snapshots/dynamic-workflow/session.1.jsonl new file mode 100644 index 0000000000..3d89428bbd --- /dev/null +++ b/examples/tui-agent/tests/snapshots/dynamic-workflow/session.1.jsonl @@ -0,0 +1,36 @@ +{"type":"session","version":0,"id":"583a4db2-3350-436c-b4a5-5615fd159052","createdAt":1783600636316,"cwd":"/var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-vdJYjz","parentSession":"3fd7d599-56b1-493a-930d-f1fc5e1556e8"} +{"type":"turn/start","seq":0,"time":1783600636316,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783600636316,"data":{"content":[{"type":"text","text":"Reply with exactly the word WF_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783600636316,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783600636317,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783600638173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":14,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"WF"}}} +{"type":"assistant/chunk","seq":15,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_CH"}}} +{"type":"assistant/chunk","seq":16,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} +{"type":"assistant/chunk","seq":17,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} +{"type":"assistant/chunk","seq":18,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":19,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":20,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":21,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":22,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":23,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":24,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"WF"}}} +{"type":"assistant/chunk","seq":25,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_CH"}}} +{"type":"assistant/chunk","seq":26,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ILD"}}} +{"type":"assistant/chunk","seq":27,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_OK"}}} +{"type":"assistant/chunk","seq":28,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."}}}} +{"type":"assistant/chunk","seq":29,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WF_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":30,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":31,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":32,"time":1783600638281,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1783600638281,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":34,"time":1783600638281,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/dynamic-workflow/session.jsonl b/examples/tui-agent/tests/snapshots/dynamic-workflow/session.jsonl new file mode 100644 index 0000000000..3e0ae3da73 --- /dev/null +++ b/examples/tui-agent/tests/snapshots/dynamic-workflow/session.jsonl @@ -0,0 +1,209 @@ +{"type":"session","version":0,"id":"3fd7d599-56b1-493a-930d-f1fc5e1556e8","createdAt":1783600631835,"cwd":"/var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-vdJYjz"} +{"type":"turn/start","seq":0,"time":1783600631838,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783600631838,"data":{"content":[{"type":"text","text":"Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim):\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\nAfter the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783600631839,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783600631839,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":11,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":12,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" workflow"}}} +{"type":"assistant/chunk","seq":13,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":14,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":15,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} +{"type":"assistant/chunk","seq":16,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":17,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":18,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" parameters"}}} +{"type":"assistant/chunk","seq":19,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":20,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":21,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":22,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" carefully"}}} +{"type":"assistant/chunk","seq":23,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" follow"}}} +{"type":"assistant/chunk","seq":24,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":25,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" instructions"}}} +{"type":"assistant/chunk","seq":26,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":\n\n"}}} +{"type":"assistant/chunk","seq":27,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} +{"type":"assistant/chunk","seq":28,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":29,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" args"}}} +{"type":"assistant/chunk","seq":30,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" omitted"}}} +{"type":"assistant/chunk","seq":31,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} +{"type":"assistant/chunk","seq":32,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"so"}}} +{"type":"assistant/chunk","seq":33,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":34,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" don"}}} +{"type":"assistant/chunk","seq":35,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'t"}}} +{"type":"assistant/chunk","seq":36,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" include"}}} +{"type":"assistant/chunk","seq":37,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":38,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":")\n"}}} +{"type":"assistant/chunk","seq":39,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"2"}}} +{"type":"assistant/chunk","seq":40,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":41,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" meta"}}} +{"type":"assistant/chunk","seq":42,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ="}}} +{"type":"assistant/chunk","seq":43,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" {"}}} +{"type":"assistant/chunk","seq":44,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":45,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"name"}}} +{"type":"assistant/chunk","seq":46,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\":"}}} +{"type":"assistant/chunk","seq":47,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":48,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"sn"}}} +{"type":"assistant/chunk","seq":49,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"apshot"}}} +{"type":"assistant/chunk","seq":50,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-flow"}}} +{"type":"assistant/chunk","seq":51,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\","}}} +{"type":"assistant/chunk","seq":52,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":53,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"description"}}} +{"type":"assistant/chunk","seq":54,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\":"}}} +{"type":"assistant/chunk","seq":55,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":56,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"one"}}} +{"type":"assistant/chunk","seq":57,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} +{"type":"assistant/chunk","seq":58,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" for"}}} +{"type":"assistant/chunk","seq":59,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":60,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" snapshot"}}} +{"type":"assistant/chunk","seq":61,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":62,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" }\n"}}} +{"type":"assistant/chunk","seq":63,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"3"}}} +{"type":"assistant/chunk","seq":64,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":65,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" script"}}} +{"type":"assistant/chunk","seq":66,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ="}}} +{"type":"assistant/chunk","seq":67,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} +{"type":"assistant/chunk","seq":68,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" given"}}} +{"type":"assistant/chunk","seq":69,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} +{"type":"assistant/chunk","seq":70,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} +{"type":"assistant/chunk","seq":71,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\n"}}} +{"type":"assistant/chunk","seq":72,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"4"}}} +{"type":"assistant/chunk","seq":73,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":74,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" After"}}} +{"type":"assistant/chunk","seq":75,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":76,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" returns"}}} +{"type":"assistant/chunk","seq":77,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":78,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":79,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":80,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":81,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"WORK"}}} +{"type":"assistant/chunk","seq":82,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"FL"}}} +{"type":"assistant/chunk","seq":83,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"OW"}}} +{"type":"assistant/chunk","seq":84,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":85,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":86,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"\n\n"}}} +{"type":"assistant/chunk","seq":87,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Let"}}} +{"type":"assistant/chunk","seq":88,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":89,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} +{"type":"assistant/chunk","seq":90,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":91,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":92,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":93,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":94,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":95,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":96,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":97,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"meta"}}} +{"type":"assistant/chunk","seq":98,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":99,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":100,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"{\""}}} +{"type":"assistant/chunk","seq":101,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"name"}}} +{"type":"assistant/chunk","seq":102,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":103,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":104,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"sn"}}} +{"type":"assistant/chunk","seq":105,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"apshot"}}} +{"type":"assistant/chunk","seq":106,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"-flow"}}} +{"type":"assistant/chunk","seq":107,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":108,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":109,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":110,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":111,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":112,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"one"}}} +{"type":"assistant/chunk","seq":113,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" child"}}} +{"type":"assistant/chunk","seq":114,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" for"}}} +{"type":"assistant/chunk","seq":115,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":116,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" snapshot"}}} +{"type":"assistant/chunk","seq":117,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":118,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":119,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":120,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":121,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"script"}}} +{"type":"assistant/chunk","seq":122,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":123,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":124,"time":1783600635764,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":125,"time":1783600635764,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\\n"}}} +{"type":"assistant/chunk","seq":126,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"phase"}}} +{"type":"assistant/chunk","seq":127,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"('"}}} +{"type":"assistant/chunk","seq":128,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"Run"}}} +{"type":"assistant/chunk","seq":129,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"')\\n"}}} +{"type":"assistant/chunk","seq":130,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"const"}}} +{"type":"assistant/chunk","seq":131,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" reply"}}} +{"type":"assistant/chunk","seq":132,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" ="}}} +{"type":"assistant/chunk","seq":133,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" await"}}} +{"type":"assistant/chunk","seq":134,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" agent"}}} +{"type":"assistant/chunk","seq":135,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"('"}}} +{"type":"assistant/chunk","seq":136,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":137,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":138,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":139,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":140,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":141,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" WF"}}} +{"type":"assistant/chunk","seq":142,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"_CH"}}} +{"type":"assistant/chunk","seq":143,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"ILD"}}} +{"type":"assistant/chunk","seq":144,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"_OK"}}} +{"type":"assistant/chunk","seq":145,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":146,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":147,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":148,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":".')\\n"}}} +{"type":"assistant/chunk","seq":149,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"return"}}} +{"type":"assistant/chunk","seq":150,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" {"}}} +{"type":"assistant/chunk","seq":151,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" reply"}}} +{"type":"assistant/chunk","seq":152,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" }\\n"}}} +{"type":"assistant/chunk","seq":153,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":154,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":155,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."}}}} +{"type":"assistant/chunk","seq":156,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}}}} +{"type":"assistant/chunk","seq":157,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}}}} +{"type":"assistant/chunk","seq":158,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":159,"time":1783600636247,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."},{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} +{"type":"tool/call","seq":160,"time":1783600636247,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}} +{"type":"tool/result","seq":161,"time":1783600638304,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","content":[{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"} +{"type":"step/end","seq":162,"time":1783600638304,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":163,"time":1783600638305,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":164,"time":1783600640028,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":165,"time":1783600640028,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":166,"time":1783600640134,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" workflow"}}} +{"type":"assistant/chunk","seq":167,"time":1783600640162,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":168,"time":1783600640195,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} +{"type":"assistant/chunk","seq":169,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":170,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":171,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":172,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":173,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"WF"}}} +{"type":"assistant/chunk","seq":174,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_CH"}}} +{"type":"assistant/chunk","seq":175,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} +{"type":"assistant/chunk","seq":176,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} +{"type":"assistant/chunk","seq":177,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":178,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":179,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":180,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":181,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":182,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":183,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":184,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":185,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":186,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"WORK"}}} +{"type":"assistant/chunk","seq":187,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"FL"}}} +{"type":"assistant/chunk","seq":188,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"OW"}}} +{"type":"assistant/chunk","seq":189,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":190,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":191,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":192,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":193,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":194,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":195,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":196,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"WORK"}}} +{"type":"assistant/chunk","seq":197,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"FL"}}} +{"type":"assistant/chunk","seq":198,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"OW"}}} +{"type":"assistant/chunk","seq":199,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} +{"type":"assistant/chunk","seq":200,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":201,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."}}}} +{"type":"assistant/chunk","seq":202,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WORKFLOW_DONE"}}}} +{"type":"assistant/chunk","seq":203,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}}}} +{"type":"assistant/chunk","seq":204,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":205,"time":1783600640865,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} +{"type":"step/end","seq":206,"time":1783600640865,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":207,"time":1783600640865,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt b/examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt new file mode 100644 index 0000000000..8589ac94ea --- /dev/null +++ b/examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt @@ -0,0 +1,105 @@ +terminal 100x36 buffer=normal length=47 base=11 viewport=11 +lifecycle started=1 stopped=0 progress=inactive +title "DSH TUI snapshot" +cursor hidden column=1 viewportRow=33 bufferRow=44 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Recorded replay: dynamic-workflow │" + style 0-0 fg=bright-blue + style 2-34 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", " + style 0-0 fg=bright-blue +9| "▌ \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim): " + style 0-0 fg=bright-blue +10| "▌ phase('Run') " + style 0-0 fg=bright-blue +11| "▌ const reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.') " + style 0-0 fg=bright-blue +12| "▌ return { reply } " + style 0-0 fg=bright-blue +13| "▌ After the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any " + style 0-0 fg=bright-blue +14| "▌ other tool. " + style 0-0 fg=bright-blue +15| "▌ " + style 0-0 fg=bright-blue +16| +17| " Reasoning " + style 1-9 fg=bright-black italic +18| " The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully " + style 1-99 fg=bright-black italic +19| " follow the instructions: " + style 1-24 fg=bright-black italic +20| " " +21| " 1. args omitted (so I don't include it) " + style 1-3 fg=bright-blue + style 4-39 fg=bright-black italic +22| " 2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" } " + style 1-3 fg=bright-blue + style 4-82 fg=bright-black italic +23| " 3. script = as given verbatim " + style 1-3 fg=bright-blue + style 4-29 fg=bright-black italic +24| " 4. After it returns, reply with \"WORKFLOW_DONE\" " + style 1-3 fg=bright-blue + style 4-47 fg=bright-black italic +25| " " +26| " Let me do exactly that. " + style 1-23 fg=bright-black italic +27| +28| "▌ " + style 0-0 fg=green +29| "▌ ✓ workflow: snapshot-flow " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-26 bold +30| "▌ workflow \"snapshot-flow\" completed (1 agent). " + style 0-0 fg=green +31| "▌ Return value: " + style 0-0 fg=green +32| "▌ { " + style 0-0 fg=green +33| "▌ \"reply\": \"WF_CHILD_OK\" " + style 0-0 fg=green +34| "▌ } " + style 0-0 fg=green +35| "▌ " + style 0-0 fg=green +36| +37| " Reasoning " + style 1-9 fg=bright-black italic +38| " The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly " + style 1-99 fg=bright-black italic +39| " \"WORKFLOW_DONE\" and stop. " + style 1-25 fg=bright-black italic +40| +41| " Assistant " + style 1-9 fg=bright-magenta bold +42| " WORKFLOW_DONE " +43| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +44| " " + style 1-1 inverse +45| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +46| "/workspace/project ↑3.5k ↓22" + style 0-99 dim diff --git a/examples/tui-agent/tests/snapshots/multi-turn-conversation/session.jsonl b/examples/tui-agent/tests/snapshots/multi-turn-conversation/session.jsonl new file mode 100644 index 0000000000..cd32072eaa --- /dev/null +++ b/examples/tui-agent/tests/snapshots/multi-turn-conversation/session.jsonl @@ -0,0 +1,65 @@ +{"type":"session","version":0,"id":"228b7b82-84ed-49b7-a567-981c03b28c77","createdAt":1783352113760,"cwd":"/tmp/acp-snap-cwd-aN2GRR"} +{"type":"turn/start","seq":0,"time":1783352113765,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783352113765,"data":{"content":[{"type":"text","text":"Reply with exactly the word: ONE. No tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783352113767,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783352113768,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783352114428,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783352114428,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783352114542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783352114570,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783352114571,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783352114571,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783352114571,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1783352114572,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1783352114600,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1783352114601,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":14,"time":1783352114602,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":15,"time":1783352114602,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":16,"time":1783352114602,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":17,"time":1783352114603,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":18,"time":1783352114627,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":19,"time":1783352114628,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":20,"time":1783352114657,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" no"}}} +{"type":"assistant/chunk","seq":21,"time":1783352114658,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":22,"time":1783352114658,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":23,"time":1783352114658,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":24,"time":1783352114658,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":25,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."}}}} +{"type":"assistant/chunk","seq":26,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ONE"}}}} +{"type":"assistant/chunk","seq":27,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":28,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":29,"time":1783352114690,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} +{"type":"step/end","seq":30,"time":1783352114690,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":31,"time":1783352114690,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":32,"time":1783352114699,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":33,"time":1783352114699,"data":{"content":[{"type":"text","text":"Reply with exactly the word: TWO. No tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":34,"time":1783352114700,"data":{"turn":2,"step":1}} +{"type":"assistant/chunk","seq":35,"time":1783352115341,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":36,"time":1783352115341,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":37,"time":1783352115465,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":38,"time":1783352115492,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":39,"time":1783352115493,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":40,"time":1783352115493,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":41,"time":1783352115493,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":42,"time":1783352115521,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":43,"time":1783352115521,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":44,"time":1783352115521,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":45,"time":1783352115552,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":46,"time":1783352115552,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":47,"time":1783352115552,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"T"}}} +{"type":"assistant/chunk","seq":48,"time":1783352115552,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"WO"}}} +{"type":"assistant/chunk","seq":49,"time":1783352115552,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":50,"time":1783352115580,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":51,"time":1783352115580,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" no"}}} +{"type":"assistant/chunk","seq":52,"time":1783352115580,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":53,"time":1783352115580,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":54,"time":1783352115609,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":55,"time":1783352115609,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"T"}}} +{"type":"assistant/chunk","seq":56,"time":1783352115609,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"WO"}}} +{"type":"assistant/chunk","seq":57,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."}}}} +{"type":"assistant/chunk","seq":58,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"TWO"}}}} +{"type":"assistant/chunk","seq":59,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":60,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":61,"time":1783352115611,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"step/end","seq":62,"time":1783352115611,"data":{"turn":2,"step":1}} +{"type":"turn/end","seq":63,"time":1783352115611,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt b/examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt new file mode 100644 index 0000000000..fca6c6dd4a --- /dev/null +++ b/examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt @@ -0,0 +1,69 @@ +terminal 100x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH TUI snapshot" +cursor hidden column=1 viewportRow=28 bufferRow=28 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Recorded replay: multi-turn-conversation │" + style 0-0 fg=bright-blue + style 2-41 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Reply with exactly the word: ONE. No tools. " + style 0-0 fg=bright-blue +9| "▌ " + style 0-0 fg=bright-blue +10| +11| " Reasoning " + style 1-9 fg=bright-black italic +12| " The user wants me to reply with exactly the word \"ONE\" and use no tools. " + style 1-72 fg=bright-black italic +13| +14| " Assistant " + style 1-9 fg=bright-magenta bold +15| " ONE " +16| +17| "▌ " + style 0-0 fg=bright-blue +18| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +19| "▌ Reply with exactly the word: TWO. No tools. " + style 0-0 fg=bright-blue +20| "▌ " + style 0-0 fg=bright-blue +21| +22| " Reasoning " + style 1-9 fg=bright-black italic +23| " The user wants me to reply with exactly the word \"TWO\" and no tools. " + style 1-68 fg=bright-black italic +24| +25| " Assistant " + style 1-9 fg=bright-magenta bold +26| " TWO " +27| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +28| " " + style 1-1 inverse +29| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +30| "/workspace/project ↑2" + style 0-99 dim +31-35| diff --git a/examples/tui-agent/tests/snapshots/parallel-file-reads/session.jsonl b/examples/tui-agent/tests/snapshots/parallel-file-reads/session.jsonl new file mode 100644 index 0000000000..81503dc4cf --- /dev/null +++ b/examples/tui-agent/tests/snapshots/parallel-file-reads/session.jsonl @@ -0,0 +1,28 @@ +{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"} +{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Use the read tool twice in the same assistant message: read a.txt and b.txt. Then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_read_a","name":"read","argumentsDelta":"{\"file_path\":\"a.txt\"}"}}} +{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_read_b","name":"read","argumentsDelta":"{\"file_path\":\"b.txt\"}"}}} +{"type":"assistant/chunk","seq":9,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}}}} +{"type":"assistant/chunk","seq":10,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} +{"type":"assistant/chunk","seq":11,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":12,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"},{"type":"tool-call","id":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"} +{"type":"tool/call","seq":13,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_a","name":"read","arguments":"{\"file_path\":\"a.txt\"}"}} +{"type":"tool/call","seq":14,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_b","name":"read","arguments":"{\"file_path\":\"b.txt\"}"}} +{"type":"tool/result","seq":15,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_a","content":[{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[13],"surfaceOp":"append"} +{"type":"tool/result","seq":16,"time":0,"data":{"turn":1,"step":1,"callId":"call_read_b","content":[{"type":"text","text":"{{cwd}}/b.txt\nfile\n\n1: beta\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[14],"surfaceOp":"append"} +{"type":"step/end","seq":17,"time":0,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":18,"time":0,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":20,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"DONE"}}} +{"type":"assistant/chunk","seq":21,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":22,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":1}}}} +{"type":"assistant/chunk","seq":23,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":24,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":1}},"sourceEventSeqs":[19,20,21,22,23],"surfaceOp":"append"} +{"type":"step/end","seq":25,"time":0,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":26,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt b/examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt new file mode 100644 index 0000000000..7906694d0a --- /dev/null +++ b/examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt @@ -0,0 +1,94 @@ +terminal 100x36 buffer=normal length=41 base=5 viewport=5 +lifecycle started=1 stopped=0 progress=inactive +title "DSH TUI snapshot" +cursor hidden column=1 viewportRow=33 bufferRow=38 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Recorded replay: parallel-file-reads │" + style 0-0 fg=bright-blue + style 2-37 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Use the read tool twice in the same assistant message: read a.txt and b.txt. Then reply DONE. " + style 0-0 fg=bright-blue +9| "▌ " + style 0-0 fg=bright-blue +10| +11| "▌ " + style 0-0 fg=green +12| "▌ ✓ Read a.txt " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-13 bold +13| "▌ /workspace/project" + style 0-0 fg=green +14| "▌ /a.txt " + style 0-0 fg=green +15| "▌ file " + style 0-0 fg=green +16| "▌ " + style 0-0 fg=green +17| "▌ 1: alpha " + style 0-0 fg=green +18| "▌ " + style 0-0 fg=green +19| "▌ (End of file - total 1 lines) " + style 0-0 fg=green +20| "▌ " + style 0-0 fg=green +21| "▌ " + style 0-0 fg=green +22| +23| "▌ " + style 0-0 fg=green +24| "▌ ✓ Read b.txt " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-13 bold +25| "▌ /workspace/project" + style 0-0 fg=green +26| "▌ /b.txt " + style 0-0 fg=green +27| "▌ file " + style 0-0 fg=green +28| "▌ " + style 0-0 fg=green +29| "▌ 1: beta " + style 0-0 fg=green +30| "▌ " + style 0-0 fg=green +31| "▌ (End of file - total 1 lines) " + style 0-0 fg=green +32| "▌ " + style 0-0 fg=green +33| "▌ " + style 0-0 fg=green +34| +35| " Assistant " + style 1-9 fg=bright-magenta bold +36| " DONE " +37| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +38| " " + style 1-1 inverse +39| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +40| "/workspace/project ↑20 ↓6" + style 0-99 dim diff --git a/examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/a.txt b/examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/a.txt new file mode 100644 index 0000000000..4a58007052 --- /dev/null +++ b/examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/a.txt @@ -0,0 +1 @@ +alpha diff --git a/examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/b.txt b/examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/b.txt new file mode 100644 index 0000000000..65b2df87f7 --- /dev/null +++ b/examples/tui-agent/tests/snapshots/parallel-file-reads/workspace/b.txt @@ -0,0 +1 @@ +beta diff --git a/examples/tui-agent/tests/snapshots/todo-plan/session.jsonl b/examples/tui-agent/tests/snapshots/todo-plan/session.jsonl new file mode 100644 index 0000000000..909afc44cd --- /dev/null +++ b/examples/tui-agent/tests/snapshots/todo-plan/session.jsonl @@ -0,0 +1,134 @@ +{"type":"session","version":0,"id":"b0f1f758-dcf0-474e-851d-e62c11ec0a09","createdAt":1783352057652,"cwd":"/tmp/acp-snap-cwd-AYilT7"} +{"type":"turn/start","seq":0,"time":1783352057655,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1783352057655,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1783352057657,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1783352057657,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783352058320,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1783352058320,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1783352058426,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1783352058466,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1783352058467,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1783352058467,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1783352058467,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":11,"time":1783352058467,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":12,"time":1783352058484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" todo"}}} +{"type":"assistant/chunk","seq":13,"time":1783352058484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_write"}}} +{"type":"assistant/chunk","seq":14,"time":1783352058484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":15,"time":1783352058484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":16,"time":1783352058485,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" record"}}} +{"type":"assistant/chunk","seq":17,"time":1783352058511,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":18,"time":1783352058512,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" plan"}}} +{"type":"assistant/chunk","seq":19,"time":1783352058513,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":20,"time":1783352058513,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":21,"time":1783352058513,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" three"}}} +{"type":"assistant/chunk","seq":22,"time":1783352058514,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" todos"}}} +{"type":"assistant/chunk","seq":23,"time":1783352058540,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} +{"type":"assistant/chunk","seq":24,"time":1783352058540,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":25,"time":1783352058571,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specified"}}} +{"type":"assistant/chunk","seq":26,"time":1783352058572,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" status"}}} +{"type":"assistant/chunk","seq":27,"time":1783352058597,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"es"}}} +{"type":"assistant/chunk","seq":28,"time":1783352058597,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":29,"time":1783352058597,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":30,"time":1783352058597,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":31,"time":1783352058626,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":32,"time":1783352058626,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":33,"time":1783352058626,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":34,"time":1783352058626,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":35,"time":1783352058626,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":36,"time":1783352058717,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":37,"time":1783352058717,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":38,"time":1783352058746,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":39,"time":1783352058747,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":40,"time":1783352058747,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"t"}}} +{"type":"assistant/chunk","seq":41,"time":1783352058747,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"odos"}}} +{"type":"assistant/chunk","seq":42,"time":1783352058775,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":43,"time":1783352058775,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":44,"time":1783352058776,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"["}}} +{"type":"assistant/chunk","seq":45,"time":1783352058805,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"{\""}}} +{"type":"assistant/chunk","seq":46,"time":1783352058806,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"content"}}} +{"type":"assistant/chunk","seq":47,"time":1783352058806,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":48,"time":1783352058806,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":49,"time":1783352058806,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"read"}}} +{"type":"assistant/chunk","seq":50,"time":1783352058806,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":51,"time":1783352058832,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" code"}}} +{"type":"assistant/chunk","seq":52,"time":1783352058832,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":53,"time":1783352058832,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":54,"time":1783352058832,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"status"}}} +{"type":"assistant/chunk","seq":55,"time":1783352058832,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":56,"time":1783352058832,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":57,"time":1783352058862,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"in"}}} +{"type":"assistant/chunk","seq":58,"time":1783352058863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"_pro"}}} +{"type":"assistant/chunk","seq":59,"time":1783352058863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"gress"}}} +{"type":"assistant/chunk","seq":60,"time":1783352058863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\"},"}}} +{"type":"assistant/chunk","seq":61,"time":1783352058863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" {\""}}} +{"type":"assistant/chunk","seq":62,"time":1783352058863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"content"}}} +{"type":"assistant/chunk","seq":63,"time":1783352058889,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":64,"time":1783352058890,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":65,"time":1783352058890,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"write"}}} +{"type":"assistant/chunk","seq":66,"time":1783352058890,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":67,"time":1783352058890,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" fix"}}} +{"type":"assistant/chunk","seq":68,"time":1783352058890,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":69,"time":1783352058918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":70,"time":1783352058918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"status"}}} +{"type":"assistant/chunk","seq":71,"time":1783352058918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":72,"time":1783352058918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":73,"time":1783352058918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"pending"}}} +{"type":"assistant/chunk","seq":74,"time":1783352058918,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\"},"}}} +{"type":"assistant/chunk","seq":75,"time":1783352058947,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" {\""}}} +{"type":"assistant/chunk","seq":76,"time":1783352058947,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"content"}}} +{"type":"assistant/chunk","seq":77,"time":1783352058947,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":78,"time":1783352058947,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":79,"time":1783352058947,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"run"}}} +{"type":"assistant/chunk","seq":80,"time":1783352058948,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":81,"time":1783352058976,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" tests"}}} +{"type":"assistant/chunk","seq":82,"time":1783352058976,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":83,"time":1783352058976,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":84,"time":1783352058976,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"status"}}} +{"type":"assistant/chunk","seq":85,"time":1783352058977,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":86,"time":1783352058977,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":87,"time":1783352059004,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"pending"}}} +{"type":"assistant/chunk","seq":88,"time":1783352059005,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":89,"time":1783352059005,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"}]"}}} +{"type":"assistant/chunk","seq":90,"time":1783352059033,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":91,"time":1783352059095,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."}}}} +{"type":"assistant/chunk","seq":92,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}}} +{"type":"assistant/chunk","seq":93,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}}}} +{"type":"assistant/chunk","seq":94,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":95,"time":1783352059099,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"surfaceOp":"append"} +{"type":"tool/call","seq":96,"time":1783352059099,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}} +{"type":"todo/write","seq":97,"time":1783352059100,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}} +{"type":"tool/result","seq":98,"time":1783352059101,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","content":[{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[96],"surfaceOp":"append"} +{"type":"step/end","seq":99,"time":1783352059101,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":100,"time":1783352059102,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":101,"time":1783352059732,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":102,"time":1783352059733,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":103,"time":1783352059835,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" todos"}}} +{"type":"assistant/chunk","seq":104,"time":1783352059863,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" have"}}} +{"type":"assistant/chunk","seq":105,"time":1783352059863,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" been"}}} +{"type":"assistant/chunk","seq":106,"time":1783352059864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" written"}}} +{"type":"assistant/chunk","seq":107,"time":1783352059864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} +{"type":"assistant/chunk","seq":108,"time":1783352059892,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":109,"time":1783352059892,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":110,"time":1783352059893,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":111,"time":1783352059893,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} +{"type":"assistant/chunk","seq":112,"time":1783352059920,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":113,"time":1783352059920,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":114,"time":1783352059921,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":115,"time":1783352059921,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":116,"time":1783352059921,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":117,"time":1783352059950,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":118,"time":1783352059950,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":119,"time":1783352059950,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":120,"time":1783352059950,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"D"}}} +{"type":"assistant/chunk","seq":121,"time":1783352059951,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":122,"time":1783352059951,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":123,"time":1783352059979,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":124,"time":1783352059979,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"D"}}} +{"type":"assistant/chunk","seq":125,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":126,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."}}}} +{"type":"assistant/chunk","seq":127,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":128,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}}}} +{"type":"assistant/chunk","seq":129,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":130,"time":1783352059981,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} +{"type":"step/end","seq":131,"time":1783352059981,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":132,"time":1783352059981,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt b/examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt new file mode 100644 index 0000000000..2d6520f067 --- /dev/null +++ b/examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt @@ -0,0 +1,81 @@ +terminal 100x36 buffer=normal length=36 base=0 viewport=0 +lifecycle started=1 stopped=0 progress=inactive +title "DSH TUI snapshot" +cursor hidden column=1 viewportRow=33 bufferRow=33 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Recorded replay: todo-plan │" + style 0-0 fg=bright-blue + style 2-27 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), " + style 0-0 fg=bright-blue +9| "▌ \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then " + style 0-0 fg=bright-blue +10| "▌ reply with the single word DONE and stop. " + style 0-0 fg=bright-blue +11| "▌ " + style 0-0 fg=bright-blue +12| +13| " Reasoning " + style 1-9 fg=bright-black italic +14| " The user wants me to use the todo_write tool to record a plan with exactly three todos in the " + style 1-99 fg=bright-black italic +15| " specified statuses, then reply with \"DONE\". " + style 1-43 fg=bright-black italic +16| +17| "▌ " + style 0-0 fg=green +18| "▌ ✓ Update todo list " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-19 bold +19| "▌ Updated todo list: 2 pending, 1 in progress, 0 completed. " + style 0-0 fg=green +20| "▌ " + style 0-0 fg=green +21| +22| " Reasoning " + style 1-9 fg=bright-black italic +23| " The todos have been written successfully. Now I just need to reply with the single word \"DONE\". " + style 1-95 fg=bright-black italic +24| +25| " Assistant " + style 1-9 fg=bright-magenta bold +26| " DONE " +27| +28| "Plan" + style 0-3 fg=bright-blue bold +29| " ● read the code" + style 2-2 fg=yellow +30| " ○ write the fix" + style 2-2 dim +31| " ○ run the tests" + style 2-2 dim +32| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +33| " " + style 1-1 inverse +34| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +35| "/workspace/project ↑3.1k ↓145 idle" + style 0-93 dim + style 96-99 dim diff --git a/examples/tui-agent/tests/tui.snapshot.ts b/examples/tui-agent/tests/tui.snapshot.ts new file mode 100644 index 0000000000..453c587c2a --- /dev/null +++ b/examples/tui-agent/tests/tui.snapshot.ts @@ -0,0 +1,329 @@ +import { cp, mkdir, mkdtemp, readFile, readdir, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { basename, dirname, join } from 'node:path' +import { fileURLToPath } from 'node:url' +import { afterAll, describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { scrubRequestHeaders } from '@deepseek-ai/dsh-acp-snapshot' +import { AgentId, type Agent } from '@deepseek-ai/dsh-agent' +import * as AgentCore from '@deepseek-ai/dsh-agent-spine-demo' +import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import WorkerCodeRuntime from '@deepseek-ai/dsh-code-runtime-worker' +import LocalFileSystem from '@deepseek-ai/dsh-fs-local' +import * as FsPolicy from '@deepseek-ai/dsh-fs-policy' +import * as ToolFs from '@deepseek-ai/dsh-tool-fs' +import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' +import { installLlmReplay, parseSessionLog } from '@deepseek-ai/dsh-llm-replay' +import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' +import { SessionId } from '@deepseek-ai/dsh-session' +import SubagentService from '@deepseek-ai/dsh-subagent' +import * as SubagentSpawn from '@deepseek-ai/dsh-subagent-spawn' +import * as ToolSubagent from '@deepseek-ai/dsh-tool-subagent' +import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis' +import * as ToolTodo from '@deepseek-ai/dsh-tool-todo' +import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' +import { createTuiChat } from '@deepseek-ai/dsh-tui' +import UserInteractionService from '@deepseek-ai/dsh-user-interaction' +import WorkerWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread' +import { HeadlessTerminal } from '../../../packages/ui/tui/tests/headless-terminal.ts' + +const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') +const PROVIDERS = [{ id: 'deepseek', models: [{ id: 'deepseek-v4-flash' }] }] +const UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}/gi + +type SnapshotMode = 'replay' | 'record' | 'refresh' +type Composition = 'native' | 'code' | 'advanced' + +interface Scenario { + name: string + composition: Composition + expectedTools: string[] + expectedEventCounts?: Record + childSessions?: number + recorded: boolean + seedWorkspace?: boolean +} + +const SCENARIOS: Scenario[] = [ + { + name: 'multi-turn-conversation', + composition: 'native', + expectedTools: [], + recorded: true, + }, + { + name: 'todo-plan', + composition: 'native', + expectedTools: ['todo_write'], + expectedEventCounts: { 'todo/write': 1 }, + recorded: true, + }, + { + name: 'bash-terminal-card', + composition: 'native', + expectedTools: ['bash'], + recorded: true, + }, + { + name: 'parallel-file-reads', + composition: 'native', + expectedTools: ['read', 'read'], + recorded: true, + seedWorkspace: true, + }, + { + name: 'code-mode', + composition: 'code', + expectedTools: ['run_code'], + expectedEventCounts: { 'tool/code-dispatch': 2 }, + recorded: true, + }, + { + name: 'dynamic-workflow', + composition: 'native', + expectedTools: ['workflow'], + childSessions: 1, + recorded: true, + }, + { + name: 'cordis-dynamic-toolchain', + composition: 'advanced', + expectedTools: ['cordis_mount', 'run_code', 'subagent', 'workflow', 'cordis_unmount'], + expectedEventCounts: { 'tool/code-dispatch': 1 }, + childSessions: 2, + recorded: false, + }, +] + +function snapshotModeFromEnv(value: string | undefined): SnapshotMode { + if (value === undefined || value === '' || value === 'replay') return 'replay' + if (value === 'record' || value === 'refresh') return value + throw new Error(`DSH_SNAPSHOT must be replay, record, or refresh; got ${JSON.stringify(value)}`) +} + +const MODE = snapshotModeFromEnv(process.env.DSH_SNAPSHOT) +const observedScenarios = new Set() + +function scenarioDir(scenario: Scenario): string { + return join(SNAPSHOTS_DIR, scenario.name) +} + +function childFixturePaths(scenario: Scenario): string[] { + return Array.from( + { length: scenario.childSessions ?? 0 }, + (_, index) => join(scenarioDir(scenario), `session.${index + 1}.jsonl`), + ) +} + +function userPrompts(rawLog: string): string[] { + return parseSessionLog(rawLog).flatMap((event) => { + if (event.type !== 'user/message' || event.data.source.kind !== 'user') return [] + const text = event.data.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') + return text.length > 0 ? [text] : [] + }) +} + +function rawSessionLog(session: Session): string { + return [ + JSON.stringify({ type: 'session', ...session.header }), + ...session.events.map(event => JSON.stringify(event)), + '', + ].join('\n') +} + +function normalizeTerminalSnapshot(snapshot: string, cwd: string): string { + return snapshot + .split(`/private${cwd}`).join('/workspace/project') + .split(cwd).join('/workspace/project') + .replace(UUID_RE, '{{uuid}}') +} + +async function settleTerminal(terminal: HeadlessTerminal): Promise { + let stable = 0 + for (let attempt = 0; attempt < 20 && stable < 3; attempt++) { + const before = terminal.frames + await new Promise(resolve => setTimeout(resolve, 10)) + await terminal.flush() + stable = terminal.frames === before ? stable + 1 : 0 + } + if (stable < 3) throw new Error('TUI frames did not quiesce within 200ms') +} + +async function mountScenarioContext( + scenario: Scenario, + cwd: string, + fixtureFile: string, + childFiles: string[], +): Promise { + const ctx = new Context() + await ctx.plugin(AgentCore, { + agents: [], + dshHome: join(cwd, '.dsh'), + workspaceContext: false, + tools: { mode: scenario.composition === 'code' ? 'code' : scenario.composition === 'advanced' ? 'both' : 'native' }, + skills: { local: { agentsHome: join(cwd, '.agents') } }, + }) + await ctx.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 }) + await ctx.plugin(LocalFileSystem, { cwd: '/' }) + await ctx.plugin(FsPolicy) + await ctx.plugin(ToolFs) + await ctx.plugin(UserInteractionService) + await ctx.plugin(ToolTodo) + await ctx.plugin(SubagentService) + await ctx.plugin(SubagentSpawn, { providerName: 'spawn' }) + await ctx.plugin(ToolSubagent, { provider: 'spawn', toolName: 'subagent', enableRunInBackground: false }) + await ctx.plugin(WorkerWorkflowEngine, { provider: 'spawn' }) + await ctx.plugin(ToolWorkflow) + if (scenario.composition === 'code' || scenario.composition === 'advanced') { + await ctx.plugin(WorkerCodeRuntime, {}) + } + if (scenario.composition === 'advanced') await ctx.plugin(ToolCordis, { vmTimeoutMs: 5_000 }) + if (MODE === 'record' && scenario.recorded) { + await ctx.plugin(LlmDeepSeek) + } else { + installLlmReplay(ctx, { file: fixtureFile, childFiles, providers: PROVIDERS }) + } + return ctx +} + +interface ScenarioResult { + terminal: string + parent: Session + children: Session[] + workflowEvents: string[] +} + +async function runScenario(scenario: Scenario): Promise { + const dir = scenarioDir(scenario) + const fixtureFile = join(dir, 'session.jsonl') + const childFiles = childFixturePaths(scenario) + const fixture = await readFile(fixtureFile, 'utf8') + const prompts = userPrompts(fixture) + expect(prompts.length, `${scenario.name} must carry at least one recorded user prompt`).toBeGreaterThan(0) + + const cwd = await mkdtemp(join(tmpdir(), `dsh-tui-snapshot-${scenario.name}-`)) + let ctx: Context | undefined + let controller: ReturnType | undefined + const terminal = new HeadlessTerminal(100, 36) + try { + if (scenario.seedWorkspace === true) { + const source = join(scenarioDir(scenario), 'workspace') + await cp(source, cwd, { recursive: true }) + } + ctx = await mountScenarioContext(scenario, cwd, fixtureFile, childFiles) + const disposedSessions: Session[] = [] + ctx.on('session/disposed', (session) => { disposedSessions.push(session) }) + const workflowEvents: string[] = [] + for (const name of ['workflow/start', 'workflow/phase', 'workflow/agent-start', 'workflow/agent-end', 'workflow/end'] as const) { + ctx.on(name, () => { workflowEvents.push(name) }) + } + const handle = await ctx.agents.create({ + agentId: AgentId('main'), + sessionId: SessionId('main-session'), + meta: { cwd }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, + }) + const agent: Agent = handle.agent + controller = createTuiChat(ctx, { + agent: 'main', + color: true, + showReasoning: true, + title: 'DSH TUI snapshot', + welcome: `Recorded replay: ${scenario.name}`, + maxToolOutputLines: 8, + }, { terminal, exit: () => {} }) + await settleTerminal(terminal) + + for (const prompt of prompts) { + terminal.send(prompt) + terminal.send('\r') + await agent.whenIdle() + await settleTerminal(terminal) + } + + const events: SessionEvent[] = [...agent.session.events] + expect(events.filter(event => event.type === 'tool/call').map(event => event.data.name)).toEqual(scenario.expectedTools) + for (const [type, count] of Object.entries(scenario.expectedEventCounts ?? {})) { + expect(events.filter(event => event.type === type), `${scenario.name} must emit ${type}`).toHaveLength(count) + } + expect(events.filter(event => event.type === 'tool/result').every(event => !event.data.isError)).toBe(true) + expect(events.filter(event => event.type === 'turn/end').every(event => event.data.reason.kind !== 'error')).toBe(true) + if (scenario.name === 'dynamic-workflow' || scenario.name === 'cordis-dynamic-toolchain') { + expect(workflowEvents).toEqual([ + 'workflow/start', + 'workflow/phase', + 'workflow/agent-start', + 'workflow/agent-end', + 'workflow/end', + ]) + } + + expect(terminal.themeViolations(), `${scenario.name} must remain theme-agnostic`).toEqual([]) + const snapshot = normalizeTerminalSnapshot( + await terminal.snapshot({ includeScrollback: true }), + cwd, + ) + await handle.dispose() + const children = disposedSessions + .filter(session => session !== agent.session) + .sort((a, b) => a.header.createdAt - b.header.createdAt) + expect(children).toHaveLength(scenario.childSessions ?? 0) + return { terminal: snapshot, parent: agent.session, children, workflowEvents } + } finally { + await controller?.dispose() + await ctx?.fiber.dispose() + await terminal.dispose() + await rm(cwd, { recursive: true, force: true }) + } +} + +async function writeRecording(scenario: Scenario, result: ScenarioResult): Promise { + const dir = scenarioDir(scenario) + await mkdir(dir, { recursive: true }) + await writeFile(join(dir, 'session.jsonl'), scrubRequestHeaders(rawSessionLog(result.parent))) + expect(result.children).toHaveLength(scenario.childSessions ?? 0) + for (const [index, child] of result.children.entries()) { + await writeFile(join(dir, `session.${index + 1}.jsonl`), scrubRequestHeaders(rawSessionLog(child))) + } +} + +describe('TUI recorded-session terminal snapshots', () => { + for (const scenario of SCENARIOS) { + it(scenario.name, async () => { + observedScenarios.add(scenario.name) + const result = await runScenario(scenario) + const terminalFile = join(scenarioDir(scenario), 'terminal.golden.txt') + if (MODE === 'record' || MODE === 'refresh') { + await mkdir(scenarioDir(scenario), { recursive: true }) + await writeFile(terminalFile, result.terminal) + } + if (MODE === 'record' && scenario.recorded) await writeRecording(scenario, result) + await expect(result.terminal).toMatchFileSnapshot(terminalFile) + }, 120_000) + } +}) + +afterAll(async () => { + expect([...observedScenarios].sort()).toEqual(SCENARIOS.map(scenario => scenario.name).sort()) + const directories = (await readdir(SNAPSHOTS_DIR, { withFileTypes: true })) + .filter(entry => entry.isDirectory()) + .map(entry => entry.name) + .sort() + expect(directories).toEqual(SCENARIOS.map(scenario => scenario.name).sort()) + for (const scenario of SCENARIOS) { + const expected = [ + 'session.jsonl', + 'terminal.golden.txt', + ...scenario.seedWorkspace === true ? ['workspace'] : [], + ...Array.from({ length: scenario.childSessions ?? 0 }, (_, index) => `session.${index + 1}.jsonl`), + ].sort() + expect((await readdir(scenarioDir(scenario))).sort()).toEqual(expected) + for (const fixture of ['session.jsonl', ...childFixturePaths(scenario).map(path => basename(path))]) { + const content = await readFile(join(scenarioDir(scenario), fixture), 'utf8') + expect(scrubRequestHeaders(content), `${scenario.name}/${fixture} carries request-header bulk`).toBe(content) + } + } +}) diff --git a/packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt b/packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt deleted file mode 100644 index 72f7fce352..0000000000 --- a/packages/ui/tui/tests/snapshots/code-mode-complete.golden.txt +++ /dev/null @@ -1,50 +0,0 @@ -terminal 96x36 buffer=normal length=36 base=0 viewport=0 -lifecycle started=1 stopped=0 progress=inactive -title "DSH snapshot" -cursor hidden column=1 viewportRow=14 bufferRow=14 -buffer -0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" - style 0-95 fg=bright-blue -1| "│ DEEPSEEK HARNESS │" - style 0-0 fg=bright-blue - style 2-9 fg=bright-blue bold - style 11-17 bold - style 95-95 fg=bright-blue -2| "│ Snapshot agent ready. │" - style 0-0 fg=bright-blue - style 2-22 fg=bright-black - style 95-95 fg=bright-blue -3| "│ main • deepseek-v4-flash • main-session │" - style 0-0 fg=bright-blue - style 2-44 dim - style 95-95 fg=bright-blue -4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" - style 0-95 fg=bright-blue -5| -6| "▌ " - style 0-0 fg=green -7| "▌ ✓ const first = await tools.bash({ command: 'echo CODE_ONE' }) " - style 0-0 fg=green - style 2-2 fg=green bold - style 3-95 bold -8| "▌ const second = await tools.bas " - style 0-0 fg=green - style 2-31 bold -9| "▌ CODE_ONE " - style 0-0 fg=green -10| "▌ CODE_TWO " - style 0-0 fg=green -11| "▌ combined: CODE_ONE+CODE_TWO " - style 0-0 fg=green -12| "▌ " - style 0-0 fg=green -13| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -14| " " - style 1-1 inverse -15| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -16| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" - style 0-24 dim - style 63-95 dim -17-35| diff --git a/packages/ui/tui/tests/snapshots/conversation-complete.golden.txt b/packages/ui/tui/tests/snapshots/conversation-complete.golden.txt deleted file mode 100644 index 8642d2ffa1..0000000000 --- a/packages/ui/tui/tests/snapshots/conversation-complete.golden.txt +++ /dev/null @@ -1,75 +0,0 @@ -terminal 96x36 buffer=normal length=43 base=7 viewport=7 -lifecycle started=1 stopped=0 progress=inactive -title "DSH snapshot" -cursor hidden column=1 viewportRow=33 bufferRow=40 -viewport -7| "▌ You " - style 0-0 fg=bright-blue - style 2-4 fg=bright-blue bold -8| "▌ Explain snapshot fidelity with cells. " - style 0-0 fg=bright-blue - style 10-26 bold - style 33-37 fg=cyan -9| "▌ " - style 0-0 fg=bright-blue -10| -11| " Reasoning " - style 1-9 fg=bright-black italic -12| " Compare the terminal state, not write fragments. " - style 1-48 fg=bright-black italic -13| -14| " Assistant " - style 1-9 fg=bright-magenta bold -15| " Result " - style 1-6 fg=bright-blue bold -16| " " -17| " - final viewport " - style 1-2 fg=bright-blue -18| " - semantic styles " - style 1-2 fg=bright-blue -19| " " -20| " │ deterministic and reviewable " - style 1-2 fg=bright-magenta - style 3-30 fg=bright-black italic -21| -22| "▌ " - style 0-0 fg=bright-blue -23| "▌ You " - style 0-0 fg=bright-blue - style 2-4 fg=bright-blue bold -24| "▌ Show the live update. " - style 0-0 fg=bright-blue -25| "▌ " - style 0-0 fg=bright-blue -26| -27| " Reasoning " - style 1-9 fg=bright-black italic -28| " Inspecting width and styles. " - style 1-28 fg=bright-black italic -29| -30| " Assistant " - style 1-9 fg=bright-magenta bold -31| " Streaming visible state is complete. " - style 11-23 bold -32| -33| " The model reached its output-token limit. " - style 1-41 fg=yellow -34| -35| "Plan" - style 0-3 fg=bright-blue bold -36| " ✓ model the terminal" - style 2-2 fg=green - style 4-21 fg=bright-black -37| " ● capture advanced states" - style 2-2 fg=yellow -38| " ○ verify PTY cleanup" - style 2-2 dim -39| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -40| " " - style 1-1 inverse -41| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -42| "/workspace/project ↑13k ↓760 idle reasoning:on tools:compact" - style 0-28 dim - style 63-95 dim diff --git a/packages/ui/tui/tests/snapshots/conversation-replay.golden.txt b/packages/ui/tui/tests/snapshots/conversation-replay.golden.txt deleted file mode 100644 index 2395db555b..0000000000 --- a/packages/ui/tui/tests/snapshots/conversation-replay.golden.txt +++ /dev/null @@ -1,73 +0,0 @@ -terminal 96x36 buffer=normal length=36 base=0 viewport=0 -lifecycle started=1 stopped=0 progress=inactive -title "DSH snapshot" -cursor hidden column=1 viewportRow=27 bufferRow=27 -viewport -0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" - style 0-95 fg=bright-blue -1| "│ DEEPSEEK HARNESS │" - style 0-0 fg=bright-blue - style 2-9 fg=bright-blue bold - style 11-17 bold - style 95-95 fg=bright-blue -2| "│ Snapshot agent ready. │" - style 0-0 fg=bright-blue - style 2-22 fg=bright-black - style 95-95 fg=bright-blue -3| "│ main • deepseek-v4-flash • main-session │" - style 0-0 fg=bright-blue - style 2-44 dim - style 95-95 fg=bright-blue -4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" - style 0-95 fg=bright-blue -5| -6| "▌ " - style 0-0 fg=bright-blue -7| "▌ You " - style 0-0 fg=bright-blue - style 2-4 fg=bright-blue bold -8| "▌ Explain snapshot fidelity with cells. " - style 0-0 fg=bright-blue - style 10-26 bold - style 33-37 fg=cyan -9| "▌ " - style 0-0 fg=bright-blue -10| -11| " Reasoning " - style 1-9 fg=bright-black italic -12| " Compare the terminal state, not write fragments. " - style 1-48 fg=bright-black italic -13| -14| " Assistant " - style 1-9 fg=bright-magenta bold -15| " Result " - style 1-6 fg=bright-blue bold -16| " " -17| " - final viewport " - style 1-2 fg=bright-blue -18| " - semantic styles " - style 1-2 fg=bright-blue -19| " " -20| " │ deterministic and reviewable " - style 1-2 fg=bright-magenta - style 3-30 fg=bright-black italic -21| -22| "Plan" - style 0-3 fg=bright-blue bold -23| " ✓ model the terminal" - style 2-2 fg=green - style 4-21 fg=bright-black -24| " ● capture advanced states" - style 2-2 fg=yellow -25| " ○ verify PTY cleanup" - style 2-2 dim -26| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -27| " " - style 1-1 inverse -28| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -29| "/workspace/project ↑13k ↓640 idle reasoning:on tools:compact" - style 0-28 dim - style 63-95 dim -30-35| diff --git a/packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt b/packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt index 55044a44f9..12a4251bb9 100644 --- a/packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt +++ b/packages/ui/tui/tests/snapshots/conversation-streaming.golden.txt @@ -1,75 +1,52 @@ -terminal 96x36 buffer=normal length=41 base=5 viewport=5 +terminal 96x36 buffer=normal length=36 base=0 viewport=0 lifecycle started=1 stopped=0 progress=inactive title "DSH snapshot" -cursor hidden column=1 viewportRow=33 bufferRow=38 +cursor hidden column=1 viewportRow=17 bufferRow=17 viewport +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-95 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 95-95 fg=bright-blue +2| "│ Snapshot agent ready. │" + style 0-0 fg=bright-blue + style 2-22 fg=bright-black + style 95-95 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 95-95 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-95 fg=bright-blue 5| 6| "▌ " style 0-0 fg=bright-blue 7| "▌ You " style 0-0 fg=bright-blue style 2-4 fg=bright-blue bold -8| "▌ Explain snapshot fidelity with cells. " +8| "▌ Show the live update. " style 0-0 fg=bright-blue - style 10-26 bold - style 33-37 fg=cyan 9| "▌ " style 0-0 fg=bright-blue 10| 11| " Reasoning " style 1-9 fg=bright-black italic -12| " Compare the terminal state, not write fragments. " - style 1-48 fg=bright-black italic +12| " Inspecting width and styles. " + style 1-28 fg=bright-black italic 13| 14| " Assistant " style 1-9 fg=bright-magenta bold -15| " Result " - style 1-6 fg=bright-blue bold -16| " " -17| " - final viewport " - style 1-2 fg=bright-blue -18| " - semantic styles " - style 1-2 fg=bright-blue -19| " " -20| " │ deterministic and reviewable " - style 1-2 fg=bright-magenta - style 3-30 fg=bright-black italic -21| -22| "▌ " - style 0-0 fg=bright-blue -23| "▌ You " - style 0-0 fg=bright-blue - style 2-4 fg=bright-blue bold -24| "▌ Show the live update. " - style 0-0 fg=bright-blue -25| "▌ " - style 0-0 fg=bright-blue -26| -27| " Reasoning " - style 1-9 fg=bright-black italic -28| " Inspecting width and styles. " - style 1-28 fg=bright-black italic -29| -30| " Assistant " - style 1-9 fg=bright-magenta bold -31| " Streaming visible state… " +15| " Streaming visible state… " style 11-23 bold -32| -33| "Plan" - style 0-3 fg=bright-blue bold -34| " ✓ model the terminal" - style 2-2 fg=green - style 4-21 fg=bright-black -35| " ● capture advanced states" - style 2-2 fg=yellow -36| " ○ verify PTY cleanup" - style 2-2 dim -37| "────────────────────────────────────────────────────────────────────────────────────────────────" +16| "────────────────────────────────────────────────────────────────────────────────────────────────" style 0-95 dim -38| " " +17| " " style 1-1 inverse -39| "────────────────────────────────────────────────────────────────────────────────────────────────" +18| "────────────────────────────────────────────────────────────────────────────────────────────────" style 0-95 dim -40| "/workspace/project ↑13k ↓640 idle reasoning:on tools:compact" - style 0-28 dim +19| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim style 63-95 dim +20-35| diff --git a/packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt b/packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt deleted file mode 100644 index d33b56d7ce..0000000000 --- a/packages/ui/tui/tests/snapshots/cordis-tools-complete.golden.txt +++ /dev/null @@ -1,73 +0,0 @@ -terminal 96x36 buffer=normal length=36 base=0 viewport=0 -lifecycle started=1 stopped=0 progress=inactive -title "DSH snapshot" -cursor hidden column=1 viewportRow=25 bufferRow=25 -buffer -0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" - style 0-95 fg=bright-blue -1| "│ DEEPSEEK HARNESS │" - style 0-0 fg=bright-blue - style 2-9 fg=bright-blue bold - style 11-17 bold - style 95-95 fg=bright-blue -2| "│ Snapshot agent ready. │" - style 0-0 fg=bright-blue - style 2-22 fg=bright-black - style 95-95 fg=bright-blue -3| "│ main • deepseek-v4-flash • main-session │" - style 0-0 fg=bright-blue - style 2-44 dim - style 95-95 fg=bright-blue -4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" - style 0-95 fg=bright-blue -5| -6| "▌ " - style 0-0 fg=green -7| "▌ ✓ Inspect cordis runtime: tools " - style 0-0 fg=green - style 2-2 fg=green bold - style 3-32 bold -8| "▌ ## tools " - style 0-0 fg=green -9| "▌ run_code " - style 0-0 fg=green -10| "▌ workflow " - style 0-0 fg=green -11| "▌ cordis_mount " - style 0-0 fg=green -12| "▌ cordis_unmount " - style 0-0 fg=green -13| "▌ " - style 0-0 fg=green -14| -15| "▌ " - style 0-0 fg=green -16| "▌ ✓ Mount plugin into live cordis runtime " - style 0-0 fg=green - style 2-2 fg=green bold - style 3-40 bold -17| "▌ mounted dyn-1 (plugin \"snapshot-marker\", state: active) " - style 0-0 fg=green -18| "▌ " - style 0-0 fg=green -19| -20| "▌ " - style 0-0 fg=green -21| "▌ ✓ Unmount dyn-1 " - style 0-0 fg=green - style 2-2 fg=green bold - style 3-16 bold -22| "▌ unmounted dyn-1 (plugin \"snapshot-marker\") " - style 0-0 fg=green -23| "▌ " - style 0-0 fg=green -24| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -25| " " - style 1-1 inverse -26| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -27| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" - style 0-24 dim - style 63-95 dim -28-35| diff --git a/packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt b/packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt deleted file mode 100644 index 00da73a956..0000000000 --- a/packages/ui/tui/tests/snapshots/dynamic-workflow-complete.golden.txt +++ /dev/null @@ -1,53 +0,0 @@ -terminal 96x36 buffer=normal length=36 base=0 viewport=0 -lifecycle started=1 stopped=0 progress=inactive -title "DSH snapshot" -cursor hidden column=1 viewportRow=16 bufferRow=16 -buffer -0| "╭──────────────────────────────────────────────────────────────────────────────────────────────╮" - style 0-95 fg=bright-blue -1| "│ DEEPSEEK HARNESS │" - style 0-0 fg=bright-blue - style 2-9 fg=bright-blue bold - style 11-17 bold - style 95-95 fg=bright-blue -2| "│ Snapshot agent ready. │" - style 0-0 fg=bright-blue - style 2-22 fg=bright-black - style 95-95 fg=bright-blue -3| "│ main • deepseek-v4-flash • main-session │" - style 0-0 fg=bright-blue - style 2-44 dim - style 95-95 fg=bright-blue -4| "╰──────────────────────────────────────────────────────────────────────────────────────────────╯" - style 0-95 fg=bright-blue -5| -6| "▌ " - style 0-0 fg=green -7| "▌ ✓ workflow: tui-matrix " - style 0-0 fg=green - style 2-2 fg=green bold - style 3-23 bold -8| "▌ workflow \"tui-matrix\" completed (2 agents). " - style 0-0 fg=green -9| "▌ Return value: " - style 0-0 fg=green -10| "▌ { " - style 0-0 fg=green -11| "▌ \"reports\": [\"layout ok\", \"lifecycle ok\"], " - style 0-0 fg=green -12| "▌ \"verdict\": \"covered\" " - style 0-0 fg=green -13| "▌ } " - style 0-0 fg=green -14| "▌ " - style 0-0 fg=green -15| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -16| " " - style 1-1 inverse -17| "────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-95 dim -18| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" - style 0-24 dim - style 63-95 dim -19-35| diff --git a/packages/ui/tui/tests/tui.snapshot.ts b/packages/ui/tui/tests/tui.snapshot.ts index eb6d5e9965..0967e7f64c 100644 --- a/packages/ui/tui/tests/tui.snapshot.ts +++ b/packages/ui/tui/tests/tui.snapshot.ts @@ -23,15 +23,10 @@ const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') const REFRESHING = process.env.DSH_SNAPSHOT === 'refresh' const CHECKPOINTS = [ - 'conversation-replay', 'conversation-streaming', - 'conversation-complete', 'code-mode-pending', - 'code-mode-complete', 'dynamic-workflow-pending', - 'dynamic-workflow-complete', 'cordis-tools-pending', - 'cordis-tools-complete', 'advanced-cards-collapsed', 'advanced-cards-expanded', 'question-dialog', @@ -194,25 +189,8 @@ const ADVANCED_CARD_TOOLS: Record = { } describe('TUI terminal-state snapshots', () => { - it('pins resumed conversation, streaming, completion, plans, tokens, and Markdown', async () => { - const harness = await setupSnapshot({ - beforeMount(session) { - appendUser(session, 'Explain **snapshot fidelity** with `cells`.') - appendAssistant(session, [ - { type: 'reasoning', text: 'Compare the terminal state, not write fragments.' }, - { type: 'text', text: '## Result\n\n- final viewport\n- semantic styles\n\n> deterministic and reviewable' }, - ], { inputTokens: 12_500, outputTokens: 640 }) - session.append('todo/write', { - todos: [ - { content: 'model the terminal', status: 'completed' }, - { content: 'capture advanced states', status: 'in_progress' }, - { content: 'verify PTY cleanup', status: 'pending' }, - ], - }) - }, - }) - await checkpoint('conversation-replay', harness.terminal) - + it('pins an in-flight reasoning and Markdown stream', async () => { + const harness = await setupSnapshot() await renderAfter(harness, () => { appendUser(harness.session, 'Show the live update.') harness.session.append('assistant/chunk', { @@ -237,15 +215,6 @@ describe('TUI terminal-state snapshots', () => { }) }) await checkpoint('conversation-streaming', harness.terminal) - - await renderAfter(harness, () => { - appendAssistant(harness.session, [ - { type: 'reasoning', text: 'Inspecting width and styles.' }, - { type: 'text', text: 'Streaming **visible state** is complete.' }, - ], { inputTokens: 800, outputTokens: 120 }) - harness.session.append('turn/end', { turn: 2, reason: { kind: 'max-tokens' } }) - }) - await checkpoint('conversation-complete', harness.terminal) await disposeSnapshot(harness) }) @@ -260,13 +229,6 @@ describe('TUI terminal-state snapshots', () => { } await renderAfter(harness, () => { appendToolCalls(harness.session, [call]) }) await checkpoint('code-mode-pending', harness.terminal, { includeScrollback: true }) - - await renderAfter(harness, () => { - appendToolResult(harness.session, call.id, [{ type: 'text', text: 'CODE_ONE\n+CODE_TWO' }], { - meta: { logs: ['CODE_ONE', 'CODE_TWO', 'combined: CODE_ONE+CODE_TWO'] }, - }) - }) - await checkpoint('code-mode-complete', harness.terminal, { includeScrollback: true }) await disposeSnapshot(harness) }) @@ -290,14 +252,6 @@ describe('TUI terminal-state snapshots', () => { } await renderAfter(harness, () => { appendToolCalls(harness.session, [call]) }) await checkpoint('dynamic-workflow-pending', harness.terminal, { includeScrollback: true }) - - await renderAfter(harness, () => { - appendToolResult(harness.session, call.id, [{ - type: 'text', - text: 'workflow "tui-matrix" completed (2 agents).\nReturn value:\n{\n "reports": ["layout ok", "lifecycle ok"],\n "verdict": "covered"\n}', - }]) - }) - await checkpoint('dynamic-workflow-complete', harness.terminal, { includeScrollback: true }) await disposeSnapshot(harness) }) @@ -314,13 +268,6 @@ describe('TUI terminal-state snapshots', () => { ] await renderAfter(harness, () => { appendToolCalls(harness.session, calls) }) await checkpoint('cordis-tools-pending', harness.terminal, { includeScrollback: true }) - - await renderAfter(harness, () => { - appendToolResult(harness.session, 'cordis-1', [{ type: 'text', text: '## tools\nrun_code\nworkflow\ncordis_mount\ncordis_unmount' }]) - appendToolResult(harness.session, 'cordis-2', [{ type: 'text', text: 'mounted dyn-1 (plugin "snapshot-marker", state: active)' }]) - appendToolResult(harness.session, 'cordis-3', [{ type: 'text', text: 'unmounted dyn-1 (plugin "snapshot-marker")' }]) - }) - await checkpoint('cordis-tools-complete', harness.terminal, { includeScrollback: true }) await disposeSnapshot(harness) }) From 81ca81e23dea201a92b9cc6de38dddf5d8cb790c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 01:42:16 +0800 Subject: [PATCH 192/323] test(tui): stabilize snapshot workspace width --- .../bash-terminal-card/terminal.golden.txt | 5 +- .../snapshots/code-mode/terminal.golden.txt | 6 +- .../terminal.golden.txt | 5 +- .../dynamic-workflow/terminal.golden.txt | 5 +- .../terminal.golden.txt | 5 +- .../parallel-file-reads/terminal.golden.txt | 65 +++++++++---------- .../snapshots/todo-plan/terminal.golden.txt | 6 +- examples/tui-agent/tests/tui.snapshot.ts | 4 +- 8 files changed, 52 insertions(+), 49 deletions(-) diff --git a/examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt b/examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt index 30770dcccb..ca123479dc 100644 --- a/examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt +++ b/examples/tui-agent/tests/snapshots/bash-terminal-card/terminal.golden.txt @@ -67,6 +67,7 @@ buffer style 1-1 inverse 28| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -29| "/workspace/project ↑3.0k ↓" - style 0-99 dim +29| "/workspace/project ↑3.0k ↓115 idle reasoning:on tools:compact" + style 0-58 dim + style 67-99 dim 30-35| diff --git a/examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt b/examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt index a7f1457d7a..428bdf80b4 100644 --- a/examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt +++ b/examples/tui-agent/tests/snapshots/code-mode/terminal.golden.txt @@ -73,7 +73,7 @@ buffer style 1-1 inverse 30| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -31| "/workspace/project ↑3.1k ↓158 idle" - style 0-93 dim - style 96-99 dim +31| "/workspace/project ↑3.1k ↓158 idle reasoning:on tools:compact" + style 0-49 dim + style 67-99 dim 32-35| diff --git a/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt index 5c5afc10ca..3359f54ca5 100644 --- a/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt +++ b/examples/tui-agent/tests/snapshots/cordis-dynamic-toolchain/terminal.golden.txt @@ -111,5 +111,6 @@ buffer style 1-1 inverse 48| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -49| "/workspace/project ↑" - style 0-99 dim +49| "/workspace/project ↑18 ↓18 idle reasoning:on tools:compact" + style 0-61 dim + style 67-99 dim diff --git a/examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt b/examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt index 8589ac94ea..1970a3761d 100644 --- a/examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt +++ b/examples/tui-agent/tests/snapshots/dynamic-workflow/terminal.golden.txt @@ -101,5 +101,6 @@ buffer style 1-1 inverse 45| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -46| "/workspace/project ↑3.5k ↓22" - style 0-99 dim +46| "/workspace/project ↑3.5k ↓227 idle reasoning:on tools:compact" + style 0-56 dim + style 67-99 dim diff --git a/examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt b/examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt index fca6c6dd4a..4c1f3b2c62 100644 --- a/examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt +++ b/examples/tui-agent/tests/snapshots/multi-turn-conversation/terminal.golden.txt @@ -64,6 +64,7 @@ buffer style 1-1 inverse 29| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -30| "/workspace/project ↑2" - style 0-99 dim +30| "/workspace/project ↑2.9k ↓41 idle reasoning:on tools:compact" + style 0-62 dim + style 67-99 dim 31-35| diff --git a/examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt b/examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt index 7906694d0a..5fe973c177 100644 --- a/examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt +++ b/examples/tui-agent/tests/snapshots/parallel-file-reads/terminal.golden.txt @@ -1,7 +1,7 @@ -terminal 100x36 buffer=normal length=41 base=5 viewport=5 +terminal 100x36 buffer=normal length=39 base=3 viewport=3 lifecycle started=1 stopped=0 progress=inactive title "DSH TUI snapshot" -cursor hidden column=1 viewportRow=33 bufferRow=38 +cursor hidden column=1 viewportRow=33 bufferRow=36 buffer 0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" style 0-99 fg=bright-blue @@ -37,58 +37,55 @@ buffer style 0-0 fg=green style 2-2 fg=green bold style 3-13 bold -13| "▌ /workspace/project" +13| "▌ /workspace/project/a.txt " style 0-0 fg=green -14| "▌ /a.txt " +14| "▌ file " style 0-0 fg=green -15| "▌ file " +15| "▌ " style 0-0 fg=green -16| "▌ " +16| "▌ 1: alpha " style 0-0 fg=green -17| "▌ 1: alpha " +17| "▌ " style 0-0 fg=green -18| "▌ " +18| "▌ (End of file - total 1 lines) " style 0-0 fg=green -19| "▌ (End of file - total 1 lines) " +19| "▌ " style 0-0 fg=green -20| "▌ " +20| "▌ " style 0-0 fg=green -21| "▌ " +21| +22| "▌ " style 0-0 fg=green -22| -23| "▌ " - style 0-0 fg=green -24| "▌ ✓ Read b.txt " +23| "▌ ✓ Read b.txt " style 0-0 fg=green style 2-2 fg=green bold style 3-13 bold -25| "▌ /workspace/project" +24| "▌ /workspace/project/b.txt " style 0-0 fg=green -26| "▌ /b.txt " +25| "▌ file " style 0-0 fg=green -27| "▌ file " +26| "▌ " style 0-0 fg=green -28| "▌ " +27| "▌ 1: beta " style 0-0 fg=green -29| "▌ 1: beta " +28| "▌ " style 0-0 fg=green -30| "▌ " +29| "▌ (End of file - total 1 lines) " style 0-0 fg=green -31| "▌ (End of file - total 1 lines) " +30| "▌ " style 0-0 fg=green -32| "▌ " +31| "▌ " style 0-0 fg=green -33| "▌ " - style 0-0 fg=green -34| -35| " Assistant " +32| +33| " Assistant " style 1-9 fg=bright-magenta bold -36| " DONE " +34| " DONE " +35| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +36| " " + style 1-1 inverse 37| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -38| " " - style 1-1 inverse -39| "────────────────────────────────────────────────────────────────────────────────────────────────────" - style 0-99 dim -40| "/workspace/project ↑20 ↓6" - style 0-99 dim +38| "/workspace/project ↑20 ↓6 idle reasoning:on tools:compact" + style 0-55 dim + style 67-99 dim diff --git a/examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt b/examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt index 2d6520f067..278015e244 100644 --- a/examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt +++ b/examples/tui-agent/tests/snapshots/todo-plan/terminal.golden.txt @@ -76,6 +76,6 @@ buffer style 1-1 inverse 34| "────────────────────────────────────────────────────────────────────────────────────────────────────" style 0-99 dim -35| "/workspace/project ↑3.1k ↓145 idle" - style 0-93 dim - style 96-99 dim +35| "/workspace/project ↑3.1k ↓145 idle reasoning:on tools:compact" + style 0-49 dim + style 67-99 dim diff --git a/examples/tui-agent/tests/tui.snapshot.ts b/examples/tui-agent/tests/tui.snapshot.ts index 453c587c2a..276c9c5f03 100644 --- a/examples/tui-agent/tests/tui.snapshot.ts +++ b/examples/tui-agent/tests/tui.snapshot.ts @@ -28,6 +28,8 @@ import WorkerWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread' import { HeadlessTerminal } from '../../../packages/ui/tui/tests/headless-terminal.ts' const SNAPSHOTS_DIR = join(dirname(fileURLToPath(import.meta.url)), 'snapshots') +// Keep pre-normalization layout widths identical across macOS and Linux. +const SNAPSHOT_TMP_ROOT = process.platform === 'win32' ? tmpdir() : '/tmp' const PROVIDERS = [{ id: 'deepseek', models: [{ id: 'deepseek-v4-flash' }] }] const UUID_RE = /[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}/gi @@ -204,7 +206,7 @@ async function runScenario(scenario: Scenario): Promise { const prompts = userPrompts(fixture) expect(prompts.length, `${scenario.name} must carry at least one recorded user prompt`).toBeGreaterThan(0) - const cwd = await mkdtemp(join(tmpdir(), `dsh-tui-snapshot-${scenario.name}-`)) + const cwd = await mkdtemp(join(SNAPSHOT_TMP_ROOT, `dsh-tui-snapshot-${scenario.name}-`)) let ctx: Context | undefined let controller: ReturnType | undefined const terminal = new HeadlessTerminal(100, 36) From 39b9c25b8992bbb9623a58820a7a8a3bab6d3175 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 01:59:54 +0800 Subject: [PATCH 193/323] test: refresh parallel tool call permission snapshot --- .../tests/snapshots/parallel-tool-calls/stdout.golden.jsonl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl index 6d7bc199e8..8680db3d30 100644 --- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_a","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}}]}}} From 3d19252e9643df4875b43669e7e22a32865ba857 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 02:03:35 +0800 Subject: [PATCH 194/323] test: refresh parallel tool call permission snapshot --- .../tests/snapshots/parallel-tool-calls/stdout.golden.jsonl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl index 6d7bc199e8..8680db3d30 100644 --- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_a","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}}]}}} From 3760f198f39222613f0079ff18be9b02af864c10 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 02:16:43 +0800 Subject: [PATCH 195/323] docs: distinguish readline and TUI demos --- AGENTS.md | 1 + README.i18n.yaml | 4 ++-- README.md | 5 ++++- README.zh.md | 5 ++++- docs/cookbook/extension-cookbook.i18n.yaml | 4 ++-- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/development.i18n.yaml | 4 ++-- docs/development.md | 14 +++++++++++++- docs/development.zh.md | 14 +++++++++++++- docs/i18n/translation-prompt.md | 6 +++--- packages/examples/stdio-demo/README.md | 4 ++-- 12 files changed, 48 insertions(+), 17 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 50d157e191..3aed94d364 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -58,6 +58,7 @@ pnpm run doc-sync # all documentation gates; see the doc-sync script in pa pnpm run website:build # VitePress build (doubles as the site's dead-link check) pnpm run demo:echo # mock-model REPL, no key needed pnpm run demo:repl # real REPL coding agent (needs DEEPSEEK_API_KEY) +pnpm run demo:tui # full-screen TUI coding agent (needs DEEPSEEK_API_KEY) pnpm run demo:cordis # self-referential demo: the agent modifies its own runtime (needs key) pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) ``` diff --git a/README.i18n.yaml b/README.i18n.yaml index 628d7168da..19c4ccf72d 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 92cbfaa8196b49d2b801776f0e0c178cb5f673dc -README.zh.md: 28604ad1e2926edd7d4eb91c8027785433a54d32 +README.md: aaa129272ee9346cebe2d59774d742fbe21af80a +README.zh.md: 42f2ed9b57bf008210042083977b7adbb7f1ab0e diff --git a/README.md b/README.md index 92cbfaa819..aaa129272e 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,10 @@ This monorepo is built on the [Cordis](https://github.com/cordiverse/cordis) fra ```sh pnpm install pnpm run test # vitest -pnpm run demo:repl # interactive pi-tui coding agent (needs DEEPSEEK_API_KEY) +pnpm run demo:echo # keyless mock-model REPL +pnpm run demo:repl # readline coding agent (needs DEEPSEEK_API_KEY) +pnpm run demo:tui # full-screen TUI coding agent (needs DEEPSEEK_API_KEY) +pnpm run demo:cordis # self-referential agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/README.zh.md b/README.zh.md index 28604ad1e2..42f2ed9b57 100644 --- a/README.zh.md +++ b/README.zh.md @@ -11,7 +11,10 @@ ```sh pnpm install pnpm run test # vitest -pnpm run demo:repl # interactive pi-tui coding agent (needs DEEPSEEK_API_KEY) +pnpm run demo:echo # keyless mock-model REPL +pnpm run demo:repl # readline coding agent (needs DEEPSEEK_API_KEY) +pnpm run demo:tui # full-screen TUI coding agent (needs DEEPSEEK_API_KEY) +pnpm run demo:cordis # self-referential agent demo (needs DEEPSEEK_API_KEY) pnpm run demo:acp # ACP server agent demo (needs DEEPSEEK_API_KEY) ``` diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 598e9827b1..4ebefda6eb 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 02dc22ff72807629a89d602f49752e6f429587b5 -extension-cookbook.zh.md: a204abdf6656312aea94640c60038af9f81f4f7b +extension-cookbook.md: c500aac230b6efc224c9d9e54bce75ef09b7173a +extension-cookbook.zh.md: d886b8ed40e32b2697e82172a86ca3b9653f287d diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 02dc22ff72..c500aac230 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## Runnable wirings -Three complete examples load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool — the all-mock skeleton check, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + the bash tool suite behind a pi-tui coding interface with a readline fallback, `pnpm run demo:repl`), and [`examples/acp-agent`](../../examples/acp-agent) (an agent exposed as an ACP server over JSON-RPC stdio — the client-driver shape, `pnpm run demo:acp`). Each leaf is just its swappable backends plus an app-package entry: the stdio demos load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP demo loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine via the [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle. +Five runnable leaves load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + coding tools through a line-oriented readline REPL, `pnpm run demo:repl`), [`examples/tui-agent`](../../examples/tui-agent) (the same coding composition through full-screen pi-tui, `pnpm run demo:tui`), [`examples/cordis-agent`](../../examples/cordis-agent) (self-inspection and dynamic plugin mounting, `pnpm run demo:cordis`), and [`examples/acp-agent`](../../examples/acp-agent) (an ACP server over JSON-RPC stdio, `pnpm run demo:acp`). The terminal leaves load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP leaf loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine through [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo). ## The feature → mechanism map diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index a204abdf66..d886b8ed40 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## 可运行的组装示例 -三个完整示例从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具——全 mock 骨架检查，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + bash 工具套件，配合 pi-tui 编码界面，并为管道输入保留 readline 回退，`pnpm run demo:repl`）、[`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露为 ACP 服务器的 agent——客户端驱动形态，`pnpm run demo:acp`）。每个叶子只是其可替换后端加一个 app 包入口：stdio 演示加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 演示加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) bundle 共享主干。 +五个可运行叶子从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + coding 工具，通过面向行的 readline REPL 交互，`pnpm run demo:repl`）、[`examples/tui-agent`](../../examples/tui-agent)（通过全屏 pi-tui 复用相同的 coding 组装，`pnpm run demo:tui`）、[`examples/cordis-agent`](../../examples/cordis-agent)（自我检查和动态插件挂载，`pnpm run demo:cordis`）与 [`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露的 ACP 服务器，`pnpm run demo:acp`）。终端叶子加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 叶子加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) 共享主干。 ## 功能→机制映射 diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index 1d687a3f90..3630b63815 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: 512fdcd89b4d481dd2033bc4f4c2816a04b5feaa -development.zh.md: 9f2038a99b289d06f16d7d51f0d043caa34a300e +development.md: 79caf482d0d104ed170a57812dd4f34e2329de8b +development.zh.md: 75781932acedabd2e3593a89aed8360a9a18ca5b diff --git a/docs/development.md b/docs/development.md index 512fdcd89b..79caf482d0 100644 --- a/docs/development.md +++ b/docs/development.md @@ -109,12 +109,24 @@ The echo demo does not need API credentials: pnpm run demo:echo ``` -The coding-agent demo uses pi-tui interactively, falls back to readline for pipes, and needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`: +The coding-agent REPL uses the line-oriented readline front door and needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`: ```sh pnpm run demo:repl ``` +The full-screen TUI reuses the coding-agent composition through the pi-tui front door and needs the same credentials: + +```sh +pnpm run demo:tui +``` + +The self-referential cordis-agent demo can inspect and modify its live plugin runtime and needs the same credentials: + +```sh +pnpm run demo:cordis +``` + The ACP server agent demo exposes the agent over JSON-RPC stdio and also needs `DEEPSEEK_API_KEY`: ```sh diff --git a/docs/development.zh.md b/docs/development.zh.md index 9f2038a99b..75781932ac 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -109,12 +109,24 @@ echo 演示不需要 API 凭证： pnpm run demo:echo ``` -coding-agent 演示在交互终端中使用 pi-tui，对管道输入回退到 readline，并需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`： +coding-agent REPL 使用面向行的 readline 前端，并需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`： ```sh pnpm run demo:repl ``` +全屏 TUI 通过 pi-tui 前端复用 coding-agent 组装，并需要相同的凭证： + +```sh +pnpm run demo:tui +``` + +自指的 cordis-agent 演示可以检查并修改其实时插件运行时，并需要相同的凭证： + +```sh +pnpm run demo:cordis +``` + ACP 服务器 agent 演示通过 JSON-RPC stdio 暴露 agent，同样需要 `DEEPSEEK_API_KEY`： ```sh diff --git a/docs/i18n/translation-prompt.md b/docs/i18n/translation-prompt.md index 4dd877bea4..cd87c161de 100644 --- a/docs/i18n/translation-prompt.md +++ b/docs/i18n/translation-prompt.md @@ -123,9 +123,9 @@ Follow the Good versions; these sentence-level examples illustrate error categor - Good: `A green gate does not mean the translation is correct.` ### Code block comments — never translate -- Source code block contains: `# interactive pi-tui coding agent (needs DEEPSEEK_API_KEY)` -- Bad: `# 交互式 pi-tui 编码 agent（需要 DEEPSEEK_API_KEY）` -- Good: `# interactive pi-tui coding agent (needs DEEPSEEK_API_KEY)` (byte-identical) +- Source code block contains: `# readline coding agent (needs DEEPSEEK_API_KEY)` +- Bad: `# readline 编码 agent（需要 DEEPSEEK_API_KEY）` +- Good: `# readline coding agent (needs DEEPSEEK_API_KEY)` (byte-identical) ### Language switcher — English to Chinese - Source: `English | [中文](README.zh.md)` diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index f1d4ecd212..3721116a22 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -18,7 +18,7 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | `@deepseek-ai/dsh-stdio` | the line-oriented terminal channel, bound to `main` for pipes and automation; matching `agent/start-failed` errors print and exit nonzero | | `@deepseek-ai/dsh-tui` | the interactive pi-tui channel, bound to `main` for TTY pairs; matching `agent/start-failed` startup errors are printed before fullscreen mode and exit nonzero | -`@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, not baked in here: it is a Loader-only, subprocess-only dev plugin whose constructor needs `node --expose-internals` plus a live `loader`. The `demo:echo` / `demo:repl` leaves load it and pass `--expose-internals`. +`@cordisjs/plugin-hmr` (the dev/demo edit-reload loop) is deliberately a **leaf** entry, not baked in here: it is a Loader-only, subprocess-only dev plugin whose constructor needs `node --expose-internals` plus a live `loader`. The repository's terminal demo trees load it and their scripts pass `--expose-internals`. The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapter (`llm-deepseek` for the real model, or the mock `mock-llm` for a demo) and a bash executor (`bash-local`) — `hmr`, plus this app's [`Config`](#config). The whole plugin tree a run loads is therefore: this app's cluster, the spine inside `agent-spine-demo`, `hmr`, and the two leaf backends. @@ -45,7 +45,7 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s ## The bin -`dsh-stdio-demo [path-to-cordis.yml]` (default `./cordis.yml`) loads a gitignored `.env` from the cwd (`DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`), then drives the cordis Loader against the config and awaits the whole plugin tree before returning. Run it under `node --expose-internals`, or install the Loader's optional `node-addon-require-builtin` fallback, so the Loader can resolve the config's bare plugin specifiers (`@deepseek-ai/dsh-*`, npm packages). The `demo:echo` / `demo:repl` scripts use `--expose-internals`. +`dsh-stdio-demo [path-to-cordis.yml]` (default `./cordis.yml`) loads a gitignored `.env` from the cwd (`DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`), then drives the cordis Loader against the config and awaits the whole plugin tree before returning. Run it under `node --expose-internals`, or install the Loader's optional `node-addon-require-builtin` fallback, so the Loader can resolve the config's bare plugin specifiers (`@deepseek-ai/dsh-*`, npm packages). The repository's demo scripts using this bin pass `--expose-internals`. ## Example leaf `cordis.yml` From 9f1a69366bb4644f781df1508cd2879d205f343e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 02:18:59 +0800 Subject: [PATCH 196/323] docs: tighten identity bridge prose --- docs/config-catalog.md | 10 +- .../feature/2026-07-06-approval-seam.md | 32 +-- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/subagent/subagent/src/index.ts | 4 +- packages/ui/acp/src/index.ts | 267 +++--------------- packages/ui/jsonrpc/README.md | 12 +- packages/ui/jsonrpc/src/server.ts | 59 ++-- 7 files changed, 86 insertions(+), 300 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 3b3e034601..c8e1a04036 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -20,20 +20,14 @@ export interface AcpConfig { provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string - /** - * Transport stream override. Production omits this (the plugin wires - * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an - * in-memory `Stream` (e.g. an `ndJsonStream` over a `Duplex` pair) to drive - * the bridge without a subprocess. Not part of the schemastery `Config` — - * it is a runtime-only seam, never set from a `cordis.yml`. - */ + /** Runtime-only transport override; production uses stdio. */ stream?: Stream } ``` Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:247`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:206`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 0945228593..81e60a726f 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -49,39 +49,39 @@ The `escalation-rejected` twin ends in `{"outcome": "rejected"}` instead: nothin #### The seam: mechanism and policy split -After request validation and a successful `approval/asked` append, the answerer phase always resolves to a closed `ApprovalOutcome` — `allowed-once` / `rejected` / `cancelled` / `unavailable`. `ApprovalRequest` is a readonly same-process contract, so the service borrows its routing identity and cancellation signal instead of copying the record or capturing a parallel callback bundle. It dispatches the `approval/request` waterfall, races the request signal (abort settles `cancelled`; a late answer is discarded, never double-audited), contains a throwing answerer as `unavailable`, normalizes a rogue non-vocabulary return to `unavailable`, and lands the log-only audit pair `approval/asked`/`approval/decided` (paired by the branded `ApprovalRequestId`) on the request agent's session log. Request acceptance and either pre-commit audit append may still reject; returning a decision that could not be logged would violate the pair. Session owns post-commit observer containment, so a callback failure cannot turn an authoritative audit append into a rejected request or suppress the matching event. Grants are one-shot by definition: `allowed-once` authorizes the single asked-about action, never a class of future ones, and the service stores nothing between requests. `request()` also throws before appending anything when the agent's session has no open turn — the audit pair must be turn-enclosed, the turn being the durable log's commit/replay boundary (a bare event between turns is dropped as crash tail on reload); every ask path runs mid-turn already, and idle asks are a deferred design. +After validation and a successful `approval/asked` append, the service resolves the `approval/request` waterfall to `allowed-once`, `rejected`, `cancelled`, or `unavailable`. It borrows the readonly request identity and signal, treats abort as `cancelled`, contains answerer failures and invalid returns as `unavailable`, discards late answers, and appends the paired `approval/decided` event. Pre-commit audit failures reject; post-append observer failures cannot undo an authoritative event. `allowed-once` authorizes only the asked action, and `request()` rejects outside an open turn so the audit pair remains inside the durable commit boundary. -Answerers are the policy, and they are `approval/request` waterfall listeners. The waterfall buys exactly what the seam needs: with zero listeners the dispatch falls through to the caller-supplied default — `unavailable`, so fail-closed needs no configuration and no code in any deployment; a listener that recognizes the request's agent answers by returning an outcome without calling `next()` (the decision slot is single-occupancy, first answer wins — the same documented semantics as the `fs/write-intent` gate); a listener that does not recognize the agent MUST delegate via `next()` so another answerer or the default gets the question; and listeners dispose with their owning fiber, so an unloaded UI plugin degrades the next ask to `unavailable` instead of leaving a dangling channel. Registration order across sibling plugins is not load-order deterministic (the loader starts siblings concurrently), so a deployment composes ONE terminal answerer and reserves `prepend` listeners for decide-or-delegate gates. +Answerers are `approval/request` waterfall listeners. Zero listeners fall through to `unavailable`; a recognizing listener occupies the first-wins decision slot, while an unrecognized agent must delegate with `next()`. Listeners dispose with their fibers, so an unloaded channel fails closed. Because sibling registration order is not deterministic, a deployment composes one terminal answerer and reserves `prepend` for decide-or-delegate gates. -`ApprovalRequest` carries the asking `agent` (routes the question; receives the audit events), the `toolName`, the optional exact `callId`, the asker's human-readable `reason`, and the optional `signal`. The caller retains ownership and honors the readonly contract for the duration of `request()`. The vocabulary is deliberately self-contained — it names the tool-call by the `CallId` brand from `dsh-llm` and never imports `dsh-tools` — because `dsh-tools` depends on `dsh-user-approval` (the ask routing) and a `ToolCallView` import would close a package cycle. It deliberately does NOT carry tool arguments: a UI answerer attaches the prompt to the already-streamed tool call via `callId` instead of re-rendering the call. +`ApprovalRequest` carries the asking `agent`, `toolName`, optional exact `callId`, human-readable `reason`, and optional `signal`. It uses the `CallId` brand without importing `dsh-tools`, which depends on this seam. Tool arguments stay on the already-streamed call that a UI references by `callId`. #### Ask routing in dsh-tools -`ToolRegistry.execute()` resolves an `ask` decision through the seam before the shared deny path: `allowed-once` proceeds to guards and dispatch, and the three non-grants deny with distinct reasons — "the user rejected…", "…was cancelled", "…no approval channel is available" — so the model can tell a human "no" from an absent channel. The seam is consumed opportunistically (`ctx.get('approval')`, the `tool-bash`/`agent-loop` pattern), not statically injected: with no ApprovalService, or after one unmounts, the next ask fails closed without gating the registry's fiber. An agent-less execution also fails closed — without an agent there is no session to audit to and no UI to route to. +`ToolRegistry.execute()` resolves `ask` before dispatch: `allowed-once` proceeds, while rejection, cancellation, and channel absence produce distinct deny reasons. Opportunistic `ctx.get('approval')` consumption lets an absent or unmounted service fail closed without gating the registry fiber. Agent-less execution also fails closed because it has neither an audit session nor a UI owner. #### The per-session policy tier -The seam also owns the session-scoped approval policy — the approval knob of the two-knob per-session switching design ([the sandbox RFC](2026-07-06-sandbox.md) § Per-session modes is the pattern's home: one log-only event per knob, a pure fold, THE write path, ACP config-option advertisement, and turn-anchoring). `ApprovalPolicy` is `'ask' | 'never'`, and `effectiveApprovalPolicy(events) ?? Config.policy` (default `'ask'`) decides every request BEFORE any interactive answerer: the service resolves a `'never'` session to `'rejected'` INSIDE `request()`, before dispatching the waterfall at all — no listener registration, including a later `prepend`, can sit ahead of it — while `'ask'` dispatches unchanged and falls through to fail-closed `'unavailable'` when nobody answers. Visibility follows the switching design's two layers with one asymmetry: the prompt section states ONLY `'never'` (deterministic, availability-independent — "you will be prompted" would overclaim in a composition with no answerer, and absence under a logged header is exactly how the narrator reads `'ask'` back), the narrator injects at most one coalesced notice per switch, and the audit pair still lands on every ask, including the policy's auto-rejections. +The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox RFC](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. The prompt states only deterministic `'never'`, switch narration is coalesced, and every request still records the audit pair. #### The ACP answerer -The bridge registers the first real answerer: it resolves the owning session through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. +The ACP bridge answers only for an exact agent object owned by its forward session map. It attaches `session/request_permission` to the existing `callId`, advertises one-shot allow/reject options, maps cancellation separately, and never grants an unknown option. Foreign or call-less requests delegate; a failed client RPC becomes `unavailable`. Hooks and `tools/pre-execute` decide whether a call asks at all. The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. +`approval/asked` and `approval/decided` are durable log-only events; the model sees only the ordinary tool result derived from the outcome. Successful completion commits one `decided` per `asked`, including cancellation and contained answerer failure. Idle requests append neither event; a pre-commit failure rejects, while failure of the second append can leave an already-committed `asked` unmatched. #### Entities and dependencies -One package, no cycles: `dsh-user-approval` peers on `cordis`, `dsh-session` (event-map merge + append), `dsh-agent` (the `Agent` type), `dsh-llm` (`CallId`, via `dsh-brand`). `dsh-tools` and `dsh-acp` each peer on it; the escalation phase's asker lives in `dsh-tool-bash` (see [the sandbox RFC](2026-07-06-sandbox.md) § Escalation), so the sandbox family keeps its ZERO-edge relation (the executor contributes the per-call override mechanism, and transport seams never ask humans questions). The seam is one package, not the capability-seam three: the service body (dispatch + audit) has no replaceable implementation — the replaceable part is the answerer listeners, and those live with their owners (the bridge; future terminal UIs; test scripts). `@cordisjs/plugin-capability` stays orthogonal (a static grant registry answers "is this already authorized", not "ask the user now"), and `subagent-acp`'s child-side `permission` auto-answer is untouched — routing a child's approvals to the parent session is deferred (§ Deferred). +`dsh-user-approval` depends on Cordis plus the session, agent, and branded-call contracts; `dsh-tools` and `dsh-acp` consume it. The sandbox executor stays independent because `dsh-tool-bash` owns escalation requests. The fixed dispatch-and-audit service remains one package; replaceable answerers live with their channel owners. Static capability grants and `subagent-acp` child-side permission answers remain separate concerns. ### Testing -Unit tier: the service's outcome branches (fail-closed default, first-wins slot, delegation, containment, rogue-value normalization, abort-before and abort-during with late-answer discard, fresh ids, fiber-disposal degradation), scoped routing, post-append observer throws on both audit events, and the policy tier (both values × dispatch/decide, a `'never'` decision unbypassable even by an answerer prepended AFTER the service, audit pair intact) in `dsh-user-approval`; the ask routing matrix (grant dispatches; three non-grant reasons pinned verbatim; unmounted and agent-less degrades; the registry's own exhaustiveness backstop against a non-conforming stand-in) in `dsh-tools`; the answerer (wire shape of the prompt, outcome mapping, unknown-option conservatism, foreign-agent and call-less delegation) driven through a real bridge + scripted client in `dsh-acp`. +Unit tests pin outcomes, first-wins delegation, containment, cancellation, scoped routing, audit pairing, the unbypassable `'never'` policy, tool deny reasons, and ACP ownership/outcome mapping through a real scripted bridge. -Snapshot tier: the harness accepts scripted permission answers (`permissionAnswers` in a scenario's `input.json`, consumed FIFO; an unscripted prompt answers `cancelled`, fail closed). The seam's wire is recorded end to end in the sandbox example's suite: both escalation branches drive `session/request_permission` through this seam over scripted answers (grant and rejection), and the recorded `mode-switching` scenario pins the `'never'` prompt sentence and the policy-switch notice ([the sandbox RFC](2026-07-06-sandbox.md) § Testing). +Snapshots record allowed and rejected sandbox escalation through `session/request_permission`, plus the `'never'` prompt and policy-switch notice. Unscripted permission prompts cancel and fail closed. ## Deferred @@ -102,12 +102,10 @@ Snapshot tier: the harness accepts scripted permission answers (`permissionAnswe The implemented contract is pinned by the suites in Testing: -- With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. -- A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). -- Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. -- Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. -- A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. +- `allowed-once` dispatches one action; every other outcome denies with a distinct reason, and `'never'` rejects before prompting. +- Missing, foreign, agent-less, throwing, invalid, and disconnected answer paths fail closed. +- Successful requests route by exact agent ownership and append one replayable, model-invisible audit pair; idle and pre-commit failures reject. +- ACP ownership keeps prompts inside their session, while a deployment without the service emits no prompt or audit events. Costs and accepted limits: @@ -117,8 +115,6 @@ Costs and accepted limits: ## FAQ -Behavioral and usage questions only — every "why not X?" design question lives in [Alternatives considered](#alternatives-considered), whose job is exactly that. - - **What happens in a deployment with no answerer at all (headless, CI)?** Every ask falls through the empty waterfall to `unavailable` and the tool call denies with the "no approval channel is available" reason. Fail-closed is the zero-listener default, not a configuration. - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 896e019779..9084befad5 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only local disposable-child parent lineage while leaving remote runs outside its local-session notification pair. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC forwards only lifecycle events whose service-snapshotted `local` flag is true, obtains the delegating parent from the scoped event carrier, and keeps no child identity or lineage cache. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 8f3549ac7c..19779f9137 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -121,7 +121,7 @@ export interface SubagentRunInfo { readonly provider: string /** The child agent's id. */ readonly id: SessionId - /** Whether the provider exposed an exact published in-process child. */ + /** Snapshot of whether `SubagentRun.localAgent` was present when start fulfilled. */ readonly local: boolean } @@ -133,7 +133,7 @@ export interface SubagentRunEndInfo { readonly provider: string /** The child agent's id. */ readonly id: SessionId - /** Whether the provider exposed an exact published in-process child. */ + /** Snapshot of whether `SubagentRun.localAgent` was present when start fulfilled. */ readonly local: boolean /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 95c5abb0d6..e20cd40f10 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1,36 +1,7 @@ /** - * The Agent Client Protocol (ACP) bridge: a client-driver / UI plugin that - * exposes the harness agent as an ACP server over JSON-RPC stdio, so editors - * (Zed and other ACP clients) can drive it. The structured analogue of the - * readline `stdio-chat` plugin. - * - * This is NOT a loop change and NOT an ADR-0009 capability seam: it consumes - * the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, - * and `dsh-session-persistence` (for `session/load`). It maps: - * - * - `initialize` → protocol-version negotiation, text-only capabilities - * - `session/new` → `ctx.agents.create({ sessionId, meta:{cwd} })` - * - `session/load` → `ctx.agents.resume(...)` then replay the event log - * - `session/prompt` → `agent.send()`, settle on the owning turn's end (a turn - * that ends in `error` rejects the RPC) - * - `session/cancel` → `agent.cancel()` (the queue-aware cancel: aborts a - * running step, clears queued + steering work, and drops a - * turn about to start) + settle the in-flight prompt - * - * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; - * every `session/event` and `agent/*` event is routed strictly to its owning - * session record, and each `session/update` carries that id. Concurrent updates - * may alternate on the shared connection without crossing session attribution. - * Permission prompts use the same identity: the bridge answers - * `approval/request` for its own agents over `session/request_permission` (see - * the approval answerer below) — whether a call ASKS is policy (a hook or - * plugin returning `ask`), not the bridge's. - * - * stdout is the protocol: this plugin must run in an example that loads NO - * stdout logger (the console logger writes to stdout and would corrupt the - * JSON-RPC frames). The guarantee is config-only — see the package README and - * RFC 010 § Risks. + * Multi-session ACP bridge over JSON-RPC stdio. Creates or resumes agents, + * routes session-scoped events and approvals, and settles prompts by turn. + * Stdout is reserved for protocol frames. * * @module @deepseek-ai/dsh-acp */ @@ -104,27 +75,15 @@ import { } from './codec.ts' export const name = 'acp' -// Interface services back advertised loading, tool-owned presentation with a generic fallback, and interaction. -// TODO(acp-session-inject): remove `sessions`; the bridge never reads it, and ownership is already behind `agents`. +// Interface services back loading, presentation, interaction, and prompt assembly. export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction', 'llm', 'systemPrompt'] -/** - * Build an ACP "invalid params" error whose human detail rides in the message. - * `RequestError.invalidParams(data, additionalMessage)` keeps the standard - * "Invalid params" message and appends `additionalMessage`, so we pass the - * detail as `additionalMessage` (and no structured `data`). - */ +/** Preserve invalid-parameter detail in the SDK wire error message. */ function invalidParams(detail: string): RequestError { return RequestError.invalidParams(undefined, detail) } -/** - * Build an ACP "internal error" whose human detail rides in the message. Used - * to reject a `session/prompt` whose turn ended in failure: a plain `Error` - * thrown from a method handler is flattened to a generic "Internal error" on - * the wire, so we wrap the detail in the SDK's `RequestError.internalError` - * (which appends `additionalMessage`) to surface *why* the turn failed. - */ +/** Preserve failed-turn detail; plain handler errors become a generic wire internal error. */ function internalError(detail: string): RequestError { return RequestError.internalError(undefined, detail) } @@ -249,13 +208,7 @@ export interface AcpConfig { provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string - /** - * Transport stream override. Production omits this (the plugin wires - * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an - * in-memory `Stream` (e.g. an `ndJsonStream` over a `Duplex` pair) to drive - * the bridge without a subprocess. Not part of the schemastery `Config` — - * it is a runtime-only seam, never set from a `cordis.yml`. - */ + /** Runtime-only transport override; production uses stdio. */ stream?: Stream } @@ -292,30 +245,11 @@ interface ModelCatalogEntry { /** Per-session bridge state keyed by ACP session id. */ interface SessionRecord { agent: Agent - /** - * The owned-agent disposer (from the {@link AgentHandle} the factory returned). - * Teardown calls it to unregister this ONE agent, stop its loop, await - * quiescence, and remove its session — instead of leaving it for the bridge - * fiber to reclaim. - */ + /** Exact owned-agent disposer; resolves after registry, loop, and session teardown. */ dispose: () => Promise - /** - * Resolves tool-owned presentation for THIS session's tool calls and remembers - * each in-flight call's `(name, args)` so the matching `tool/result` can find - * its tool. Per-session so two concurrent sessions never cross their in-flight - * tool state. - */ + /** Per-session tool presentation and call/result correlation. */ presenter: ToolPresenter - /** - * Whether THIS session renders shell tools as terminal cards — snapshotted - * from the client's `_meta.terminal_output` capability at session creation - * (`session/new`/`session/load`), NOT re-read live. A capability snapshot per - * session means the `tool_call` (which registers the terminal) and the matching - * `tool_call_update` (which streams its output) ALWAYS agree, even if a later - * `initialize` mutates the connection-level capability between them — otherwise - * a re-`initialize` mid-call could orphan a `terminal_output` (call non-terminal, - * result terminal) or clobber the card (call terminal, result non-terminal). - */ + /** Terminal capability snapshot shared by matching call and result updates. */ terminalEnabled: boolean /** Session-local provider/model selection and the current step snapshot. */ target: LlmTargetRef @@ -325,18 +259,7 @@ interface SessionRecord { reject: (error: Error) => void turn: number | undefined } | undefined - /** - * Config switches accepted while the session was IDLE, not yet anchored in - * its log. The turn-enclosure contract makes a bare between-turns append - * invalid (the JSONL backend treats a post-`turn/end` tail as crash - * garbage, and dev invariants throw), so an idle switch waits here and is - * anchored at the next turn's prompt-submit — before anything in that - * turn assembles a prompt or runs a call, and last write - * per knob wins (an idle flip-flop anchors as one event). Until anchored, - * the switch lives only in bridge memory: the set/new/load responses - * overlay it truthfully, and a restart before the next turn reverts it — - * which `session/load` then reports honestly from the log's fold. - */ + /** Last idle switch per knob, anchored before the next prompt assembles. */ pendingSwitches: { preset?: string } } @@ -347,21 +270,15 @@ interface SessionRecord { * correlation in a `finally` so presentation failure cannot starve settlement. */ export function apply(ctx: Context, config: AcpConfig): void { - // Capture the injected services NOW, during apply(), while we are inside this - // plugin's fiber (where `inject` grants access). The ACP method handlers run - // LATER, from the AgentSideConnection's JSON-RPC read loop — a context that is - // NOT this fiber's injection scope — so reading `ctx.agents` / `ctx.logger` / - // `ctx.sessionPersistence` lazily inside a handler throws "cannot get property - // … without inject". Resolving the references here and closing over them keeps - // the handlers working regardless of which fiber later invokes them. + // ACP handlers execute outside this plugin's injection scope, so capture + // injected services during apply(); lazy service reads in a handler fail. const agents = ctx.agents const llm = ctx.llm const sessionPersistence = ctx.sessionPersistence const logger = ctx.logger const tools = ctx.tools const userInteraction = ctx.userInteraction - // A new ToolPresenter per session (and a throwaway per load replay), each given - // this warn sink so a throwing tool presenter is logged, not propagated. + // Presenter callbacks are contained so display failures cannot break protocol handling. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) /** Resolve a complete target only; partial config remains available to other request listeners. */ @@ -459,23 +376,12 @@ export function apply(ctx: Context, config: AcpConfig): void { } } - // TODO(derive-acp-session-id): derive event ids from `agent.session`, verify ownership, then remove the reverse map. - // Agent events currently carry only the Agent, so retain `SessionRecord.sessionId` and update both indexes together. - // Dropping the forward record lets the weak reverse entry expire. const sessions = new Map() - // Session ids whose `session/load` is mid-`resume()` (the slot is reserved - // before the async resume so a pipelined load/new for the SAME id can't create - // two agents). Distinct ids load concurrently; a given id loads once at a time. + // Reserve an id before resume so pipelined load/new requests cannot duplicate it. const loadingIds = new Set() - // Set once the bridge has torn down (disposal or client disconnect). An async - // `session/load` mid-`resume()` when teardown ran must observe this after its - // await and NOT install a record (which would resurrect a live agent/listeners - // after the bridge closed). Checked after every load await. + // Async creation checks this after awaits to avoid publishing after teardown. let closed = false - // Connection-level terminal capability from the latest `initialize`; false - // before initialization. Each `session/new` or `session/load` snapshots it in - // `SessionRecord.terminalEnabled`, so later initialization affects only future - // sessions. + // Each new or loaded session snapshots the latest connection capability. let terminalOutputCap = false // Assigned at the bottom, before any agent event can fire (a session only @@ -674,22 +580,13 @@ export function apply(ctx: Context, config: AcpConfig): void { currentValue, options: [ ...presets.names.map((name: string) => presets.optionOf(name)), - // The derived not-a-preset state: visible exactly while it IS the - // current value (a knob state outside the table), switchable FROM, - // never a target — set() below rejects it like any unknown name. + // `custom` echoes the current derived state but is never a target. ...currentValue === 'custom' ? [presets.optionOf('custom')] : [], ], }] } - /** - * Whether the session's log currently has an open turn — the last boundary - * event is a `turn/start`. Decides whether a config switch may append NOW - * (enclosed) or must wait for the next turn (see - * {@link SessionRecord.pendingSwitches}). Read from the LOG, not - * `agent.status`: status stays `running` across the gap between two queued - * turns, where a bare append would still land outside any turn. - */ + /** Whether the log has an open turn in which a config switch can be enclosed. */ const isTurnOpen = (agent: Agent): boolean => { const events = agent.session.events for (let index = events.length - 1; index >= 0; index -= 1) { @@ -700,12 +597,7 @@ export function apply(ctx: Context, config: AcpConfig): void { return false } - /** - * Anchor a record's pending switches into its (just-opened) turn, last - * write per knob — skipping a value the session already effectively has, - * so a net-zero idle flip-flop anchors NOTHING (the log records switches, - * not select clicks). - */ + /** Anchor last-write-wins idle switches into a just-opened turn. */ const flushPendingSwitches = (rec: SessionRecord): void => { const pending = rec.pendingSwitches rec.pendingSwitches = {} @@ -717,15 +609,8 @@ export function apply(ctx: Context, config: AcpConfig): void { presets.set(rec.agent.session, pending.preset) } - // Idle-accepted switches anchor at the next turn's prompt-submit: the turn - // is open (the seam fires inside it, per drained message — the first flush - // empties the slot, later ones no-op), the loop has not yet assembled - // anything for it, and — unlike appending from inside a `session/event` - // listener — this seam fires OUTSIDE any log emit, so peer listeners - // (the dev invariants, persistence) observe the anchored events in strict - // log order. A turn with no prompt (an idle inject's one-shot injection - // turn) leaves the switch pending — it runs no step, so nothing executes - // or assembles under a stale value. + // Prompt-submit is inside the new turn but before prompt assembly. Promptless + // injection turns leave the switch pending because they execute no request. ctx.on('agent/prompt-submit', (agent, _content, _source, next) => { const rec = ownedRecord(agent) if (rec !== undefined) flushPendingSwitches(rec) @@ -780,10 +665,8 @@ export function apply(ctx: Context, config: AcpConfig): void { agentOptions: agentOptions(config), setup: (agentCtx) => { installTarget(agentCtx, target) }, }) - // Creation is now asynchronous because it awaits the unpublished setup - // transaction. A client disconnect can therefore close this bridge - // after the entry check but before the handle resolves; never install a - // post-close record that quiesce() could not have seen. + // Agent creation may resolve after the bridge closes; dispose the handle + // instead of publishing a record that teardown could not observe. /* v8 ignore next 4 -- the in-memory transport rejects the in-flight RPC immediately on close; real stdio may let the handler resume */ if (closed) { @@ -991,10 +874,7 @@ export function apply(ctx: Context, config: AcpConfig): void { if (presets === undefined) { throw invalidParams(`unknown permission value ${JSON.stringify(params.value)}`) } - // A no-op switch (the value the session already shows — pending, - // else derived) is acknowledged FIRST and records nothing: - // clients re-push current selections on session start, and the - // derived 'custom' current is only ever valid as such an echo. + // A current-value echo is acknowledged without recording a switch. const current = rec.pendingSwitches.preset ?? presets.current(rec.agent.session.events) if (params.value === current) break if (!presets.names.includes(params.value)) { @@ -1236,27 +1116,16 @@ export function streamSessionEventUpdate( } /** - * Map a harness todo list to an ACP `plan` body. ACP's `PlanEntry` requires - * `content` + `priority` + `status`, but a {@link TodoItem} carries no priority, - * so synthesize a constant `'medium'` on every entry; `status` maps 1:1 (the - * harness status triple IS `PlanEntryStatus`). The ACP client REPLACES its whole - * plan on each `plan` update, matching the harness's whole-list-replace - * semantics, so no per-entry diffing is needed. - * @param todos - the harness todo list (the whole list, not a diff). - * @returns the ACP plan body, one entry per todo. + * Map a whole harness todo list to an ACP replacement plan, using medium + * priority because harness todos do not carry one. + * @param todos - complete harness todo list. + * @returns one ACP plan entry per todo. */ export function todosToPlan(todos: TodoItem[]): Plan { return { entries: todos.map((todo): PlanEntry => ({ content: todo.content, priority: 'medium', status: todo.status })) } } -/** - * Per-session terminal-rendering context threaded into - * {@link streamSessionEventUpdate}: whether the client advertised the - * `_meta.terminal_output` capability, and the session's workspace cwd (the - * default terminal-card header when a tool doesn't supply its own). Kept out of - * the pure translator's required params so the no-capability / no-presenter - * tests stay terse. - */ +/** Per-session terminal capability and workspace used while translating updates. */ export interface TerminalRendering { enabled: boolean /** The session workspace cwd (terminal-card header default); `undefined` when the session has none. */ @@ -1267,47 +1136,21 @@ export interface TerminalRendering { const noTerminalRendering: TerminalRendering = { enabled: false, cwd: undefined } /** - * Resolves tool-owned presentation for a session's tool-call events. A tool - * declares `presentCall`/`presentResult` (see `dsh-tools`) returning a - * `card`-tagged {@link ToolCallView}/{@link ToolResultView}; this looks them up - * by name in the registry and applies a generic fallback when a tool defines - * neither. The returned view is what {@link streamSessionEventUpdate} switches on. - * - * The `tool/result` session event does NOT carry the tool name or args — so to - * call a tool's `presentResult` (which needs both), the presenter remembers each - * `tool/call`'s `{ name, args, card }` keyed by callId and looks it up on the - * matching result. The map is bridge-LOCAL (not a change to the event schema or a - * core service): one presenter per live session - * (and a throwaway per `session/load` replay), and each entry is removed when its - * result arrives. In the normal loop a `tool/call` is always followed by a - * `tool/result` (the registry turns even a thrown tool into an isError result), - * so the map holds only currently-in-flight calls. The one exception is a step - * torn down mid-tool (an abort between `tool/call` and `tool/result`), which can - * leave a single stale entry per such call; this is bounded by the session - * lifetime (the whole presenter is dropped on teardown) and never affects - * correctness — a later result for a different callId is unaffected, and the - * stale entry's only cost is one map slot until the session ends. + * Resolve tool-owned call/result views with a generic fallback. Per-session + * state correlates results with call arguments; interrupted calls may retain an + * entry only until that session's presenter is discarded. */ export class ToolPresenter { private readonly pending = new Map() /** - * @param tools the registry to resolve tool definitions by name. - * @param onError invoked when a tool's `presentCall`/`presentResult` THROWS; - * the presenter swallows the error and falls back to the generic - * presentation so a buggy display callback can never fail a live turn or a - * `session/load` replay (docs/defensive-patterns.md "contain callback exceptions at the - * boundary"). Defaults to a no-op for callers that don't supply a logger. + * @param tools - registry used to resolve executing definitions. + * @param onError - contained presenter-error sink before generic fallback. + * @param agent - optional scoped registry view for the executing agent. */ constructor( private readonly tools: Pick, private readonly onError: (message: string) => void = () => {}, - /** - * The agent whose view resolves tool presentations: a scoped/shadowed - * tool presents with ITS OWN presentCall/presentResult — the same - * definition that executed — not a same-named global's. Absent (a replay - * with no live agent) the global view presents. - */ private readonly agent?: Agent, ) {} @@ -1316,10 +1159,8 @@ export class ToolPresenter { * for the matching result. * @param callId - the call id the matching `tool/result` will look up. * @param name - the tool name, resolved against the registry for `presentCall`. - * @param argsJson - the raw arguments JSON from the event; parsed for the view - * (a non-JSON string is surfaced raw). - * @returns the tool-owned view, or the generic fallback (title = tool name, - * kind `other`, parsed args as raw input) when the tool defines none or threw. + * @param argsJson - raw event arguments parsed for presentation. + * @returns the tool-owned view or generic fallback. */ call(callId: CallId, name: string, argsJson: string): ToolCallView { const args = parseToolArguments(argsJson) @@ -1331,10 +1172,7 @@ export class ToolPresenter { this.onError(`acp: tool "${name}" presentCall threw, using generic presentation: ${String(error)}`) present = undefined } - // No tool-owned presentation: fall back to the tool name as the title, the - // full parsed args as the raw input, and kind `other` (the generic card). - // The kind is never sniffed from the name — the bridge does not special-case - // tool names; a tool that wants a richer kind declares `presentCall`. + // Tool names never imply presentation kind; richer cards are tool-owned. const view: ToolCallView = present ?? { card: 'generic', title: name, kind: 'other', rawInput: args } this.pending.set(callId, { name, args, card: view.card }) return view @@ -1343,14 +1181,11 @@ export class ToolPresenter { /** * Completed-state render intent for a `tool/result`; consumes the remembered * `(name, args, card)`. - * @param callId - the id of the matching `tool/call`; an unknown or late id - * falls back to the raw content. - * @param content - the result's content blocks (the fallback and fill-in body). + * @param callId - matching call id; unknown or late ids use raw content. + * @param content - result content used by the fallback and fill-in body. * @param isError - whether the result is an error, forwarded to `presentResult`. * @param meta - the result's machine-readable meta, forwarded when present. - * @returns the tool-owned view — an orphaned `terminal` result (no terminal - * call side) and a content-less `generic` are normalized — or the raw-content - * generic card when the tool defines no `presentResult` or threw. + * @returns a normalized tool-owned view or raw-content fallback. */ result(callId: CallId, content: ContentBlock[], isError: boolean, meta?: unknown): ToolResultView { const call = this.pending.get(callId) @@ -1420,25 +1255,11 @@ type AcpToolCallContent = | { type: 'diff'; path: string; oldText: string | null; newText: string } | { type: 'terminal'; terminalId: string } -/** - * Relativize a file card's TITLE path against the session workspace cwd, so a - * card reads `Read src/foo.ts` rather than `/abs/proj/src/foo.ts` — matching the - * reference ACP adapter's `toDisplayPath`. Only the TITLE is relativized; the - * card's `locations`/`diff` paths stay RAW (the editor opens the real path). The - * pure tool presenter can't see the session cwd, so this happens here where the - * bridge knows it. The rewrite is an exact substring replace of the known raw - * path (a card carries the same path in `locations[0]`/`diffs[0]`), never a - * heuristic. A path outside the workspace, or an absent/relative session cwd, is - * left unchanged. - */ +/** Relativize only in-workspace title text; location and diff paths stay raw. */ function displayTitle(title: string, rawPath: string | undefined, sessionCwd: string | undefined): string { if (rawPath === undefined || sessionCwd === undefined || !isAbsolute(rawPath) || !isAbsolute(sessionCwd)) return title const rel = relativePath(sessionCwd, rawPath) - // Only relativize a target that stays INSIDE the workspace. `relative` prefixes - // a `..` SEGMENT for a target above the cwd — test for the segment (`..` alone - // or `..…`), NOT a bare `..` char prefix, so a sibling like `..cache/x` - // (a real in-workspace name) still relativizes. Never relativize to the empty - // string (rawPath === cwd — a non-file target). + // Test the `..` segment, not a character prefix: `..cache/x` is in-workspace. if (rel.length === 0 || rel === '..' || rel.startsWith(`..${pathSep}`)) return title return title.split(rawPath).join(rel) } diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 3d19b601c4..6666867598 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -1,26 +1,26 @@ # @deepseek-ai/dsh-jsonrpc -The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC server that lets an out-of-process SDK client (e.g. the Python `deepseek_harness` package) drive DeepSeek Harness agents without touching Cordis. The client speaks newline-delimited JSON-RPC on the process stdin/stdout ([`HarnessSdkServer`](src/server.ts): `initialize` → `session/prompt` → `shutdown`, with `session.event` / `session.finished` / `subagent.*` notifications over [`JsonRpcLineTransport`](src/transport.ts)). The SDK-client analogue of the [`acp`](../acp/README.md) bridge, split the same way: this package is the protocol plugin, while [`jsonrpc-demo`](../../examples/jsonrpc-demo/README.md) is the app bin that boots a `cordis.yml` around it — which process serves this protocol is a config decision, not a hardcoded bin. This plugin is the serving face of the [single-executable distribution plan](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). +The `jsonrpc` plugin serves newline-delimited JSON-RPC over stdio so out-of-process SDK clients can drive harness agents. [`HarnessSdkServer`](src/server.ts) owns the protocol methods and notifications; [`jsonrpc-demo`](../../examples/jsonrpc-demo/README.md) supplies the surrounding `cordis.yml` application. ## Wiring -`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It forwards subagent completions only when the lifecycle payload's `local` flag was snapshotted from the provider's exact in-process child; reusable provider names, child ids, and durable lineage never establish locality. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. +`inject: ['agents']`. The server gets or creates one agent per `sessionId`. It forwards subagent completions only when the service-snapshotted lifecycle `local` flag is true; provider names, child ids, and durable lineage never establish locality. A registered adapter wins, an unowned `deepseek` route mounts `dsh-llm-deepseek`, and any other unowned provider fails initialization. Other capabilities come from the surrounding `cordis.yml`. ## Config -No `cordis.yml`-settable keys. The `JsonRpcConfig` fields (`input`, `output`, `exit`) are runtime-only test seams so a spec can drive the server over in-memory streams without a subprocess or a killed test process; production always serves the process stdio and exits via `process.exit`. +There are no `cordis.yml` keys. `JsonRpcConfig.input`, `output`, and `exit` are runtime-only transport seams; production uses process stdio and `process.exit`. ## stdout is the protocol -The process stdout this plugin runs in carries only JSON-RPC frames. The tree that loads it must load NO stdout logger (a console logger corrupts the frames) — the guarantee is config-only, same as the ACP bridge. Diagnostics go to stderr. +Stdout carries only JSON-RPC frames. The deployment must not compose a stdout logger; diagnostics belong on stderr. ## Shutdown and exit semantics -The plugin owns the PROTOCOL-level exit: a `shutdown` request is answered first (the response frame flushes), then the plugin disposes its own fiber — running the effect disposer: an idempotent `server.shutdown()` (every SDK-created agent disposed to quiescence, event subscriptions detached) plus `transport.close()` — and exits the process with code 0. Own-fiber disposal is deliberate: the request's `server.shutdown()` already flushed all SDK-owned session state, and the process exit that follows is the teardown of the rest of the tree. Process-level exits (stdin EOF → 0, SIGTERM → 0, SIGINT → 130) belong to the app bin, which disposes the whole root context. Fiber disposal WITHOUT a `shutdown` request (HMR-style unload) just stops serving — it never exits the process. +The plugin answers `shutdown`, disposes SDK-owned agents and subscriptions to quiescence, closes the transport, then exits with code 0. EOF and signal exits belong to the app bin, which disposes the root context. Unloading only this plugin stops serving without exiting the process. ## Wire notes -`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime` (SDK clients key on it, independent of this package's name). A session accepts at most one in-flight `session/prompt`; an overlapping prompt for the same `sessionId` fails immediately through the standard handler-error response, while other sessions remain independent and the same session can be reused after the active prompt settles. Persistence roots and the deployment persona come from `cordis.yml`; the wire exposes only parameters the server applies. +`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime`. A session accepts one in-flight prompt; overlap fails immediately, other sessions remain independent, and the session is reusable after settlement. Persistence roots and persona come from `cordis.yml`. ## Model Experience diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 5246795a31..8949ccb06a 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -1,13 +1,6 @@ /** - * `HarnessSdkServer`: the JSON-RPC method surface the `dsh-jsonrpc` plugin - * serves to out-of-process SDK clients (e.g. the Python `deepseek_harness` - * package). Requests: `initialize` → `session/prompt`* → `shutdown`. - * Notifications pushed to the host: `session.event` (every durable session - * event, verbatim), `session.finished` (per prompt turn settle), - * `subagent.started` / `subagent.finished` (child-session lineage and run - * outcomes). The server owns only the SDK-facing session map — the harness - * itself is the context the plugin mounts in; plugins, persistence, and - * the LLM adapter set all come from the external `cordis.yml`. + * JSON-RPC method and notification surface for out-of-process harness SDKs. + * The surrounding context owns plugins, persistence, and configured adapters. * * @module @deepseek-ai/dsh-jsonrpc/server */ @@ -23,7 +16,7 @@ import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' -/** Parameters of the `initialize` request (once per process, before any prompt). */ +/** Parameters for the process-wide SDK handshake. */ export interface InitializeParams { /** Working directory recorded on every SDK-created session's header. */ cwd: string @@ -33,16 +26,13 @@ export interface InitializeParams { model: string } -/** Result of the `initialize` request: the server's identity for the SDK handshake. */ +/** Wire-stable server identity returned by initialization. */ export interface InitializeResult { /** Wire-stable server identity (`deepseek-harness-sdk-runtime`) and version. */ serverInfo: { name: string; version: string } } -/** - * Parameters of a `session/prompt` request: one user turn on one SDK session, - * with at most one in flight per session. - */ +/** One user turn on one SDK session. */ export interface SessionPromptParams { /** The SDK-side session id; an unknown id lazily creates the agent+session pair. */ sessionId: string @@ -50,7 +40,7 @@ export interface SessionPromptParams { contentBlocks: ContentBlock[] } -/** Result of a `session/prompt` request: the prompt ran to turn settle (outcome rides on `session.finished`). */ +/** Prompt acceptance after turn settlement; outcome rides on `session.finished`. */ export interface SessionPromptResult { /** Always `true`; the turn outcome is the paired `session.finished` notification. */ accepted: true @@ -62,20 +52,12 @@ interface SessionRecord { activePrompt: boolean } -/** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ +/** Recover the delegating parent from the service-owned scoped carrier. */ function subagentParentOf(carrier: Scoped): Agent { - // SubagentService emits this lifecycle pair only through scopeTarget(this, parent). return carrierKeyOf(carrier) as Agent } -/** - * The SDK server over a booted harness context. Constructing it subscribes to - * session and subagent lifecycle events, forwarding durable session - * events and SDK-facing completion notifications while retaining local-run - * identity across child disposal. The subscriptions live until - * {@link shutdown}. One instance serves one transport peer for the process - * lifetime — there is no re-`initialize`. - */ +/** SDK server whose subscriptions and created agents live until {@link shutdown}. */ export class HarnessSdkServer { private cwd = process.cwd() private provider = 'deepseek' @@ -125,10 +107,9 @@ export class HarnessSdkServer { } /** - * Record cwd and provider/model, mounting the DeepSeek adapter only when the - * `deepseek` provider route has no configured owner. - * @param params - the SDK handshake parameters. - * @returns the server identity for the handshake. + * Configure the SDK route, mounting the DeepSeek fallback only when unowned. + * @param params - SDK handshake parameters. + * @returns server identity for the handshake. */ async initialize(params: InitializeParams): Promise { this.cwd = resolve(params.cwd) @@ -142,13 +123,9 @@ export class HarnessSdkServer { } /** - * Handle `session/prompt`: get-or-create the session's agent, send the - * content as the user message, await turn settle (quiescence), then notify - * `session.finished` with the settled turn's outcome. A session accepts at - * most one prompt at a time; an overlapping request fails immediately while - * other sessions remain independent. - * @param params - the target session id and prompt content. - * @returns `{ accepted: true }` after the turn settled. + * Run one prompt to settlement; overlap on the same session fails. + * @param params - target session and user content. + * @returns acceptance after the turn settled. */ async prompt(params: SessionPromptParams): Promise { const rec = await this.getOrCreateSession(params.sessionId) @@ -171,11 +148,9 @@ export class HarnessSdkServer { } /** - * Handle `shutdown`: dispose every SDK-created agent handle (awaiting loop - * quiescence), unmount the adapter fiber this server mounted (if any), and - * detach the event subscriptions. The CONTEXT stays up — the bin disposes it - * as part of process exit. - * @returns an empty object (the JSON-RPC result). + * Dispose server-owned agents, adapter, and subscriptions to quiescence. + * The surrounding context remains running. + * @returns empty JSON-RPC result. */ shutdown(): Promise> { this.shutdownTask ??= this.performShutdown() From 1e4de0deaa5d9fbe0b725c90b098001a3fd8ecf9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 03:02:42 +0800 Subject: [PATCH 197/323] fix(sdk): pin generated project build tool --- packages/sdk/helper/src/project/npm-dependency-policy.ts | 2 +- packages/sdk/helper/tests/documents.spec.ts | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/packages/sdk/helper/src/project/npm-dependency-policy.ts b/packages/sdk/helper/src/project/npm-dependency-policy.ts index a8877826e2..727bd6648a 100644 --- a/packages/sdk/helper/src/project/npm-dependency-policy.ts +++ b/packages/sdk/helper/src/project/npm-dependency-policy.ts @@ -23,7 +23,7 @@ const EXTERNAL_NPM_DEPENDENCY_SPECS: Readonly> = { '@cordisjs/plugin-timer': '^1.1.2', '@types/node': '^22.20.0', cordis: '^4.0.0-rc.7', - tsdown: '^0.22.2', + tsdown: '0.22.2', tsx: '^4.22.4', typescript: '^6.0.3', } diff --git a/packages/sdk/helper/tests/documents.spec.ts b/packages/sdk/helper/tests/documents.spec.ts index 1ba8b9bd68..1b8050b90f 100644 --- a/packages/sdk/helper/tests/documents.spec.ts +++ b/packages/sdk/helper/tests/documents.spec.ts @@ -282,6 +282,7 @@ describe('package manager strategies', () => { section: 'devDependencies', spec: '^4.0.0-rc.7', }) expect(resolveNpmDependency('@cordisjs/plugin-hmr', 'dependencies', '0.0.1').spec).toBe('^1.0.15') + expect(resolveNpmDependency('tsdown', 'devDependencies', '0.0.1').spec).toBe('0.22.2') expect(resolveNpmDependency('@deepseek-ai/dsh-tools', 'dependencies', '1.2.3').spec).toBe('^1.2.3') expect(() => resolveNpmDependency('unknown', 'dependencies', '0.0.1')).toThrow('no generated-project') }) From 4851d9570496a8ed5573873c85d18c054a78fad3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 03:49:18 +0800 Subject: [PATCH 198/323] docs: propose follow-up simplification RFCs --- docs/rfc/INDEX.md | 4 ++ ...026-07-04-prune-dead-core-spine-surface.md | 1 + ...19-fold-compaction-package-split.i18n.yaml | 6 +++ ...026-07-19-fold-compaction-package-split.md | 37 ++++++++++++++++++ ...-07-19-fold-compaction-package-split.zh.md | 37 ++++++++++++++++++ ...6-07-19-make-jsonrpc-directional.i18n.yaml | 6 +++ .../2026-07-19-make-jsonrpc-directional.md | 38 +++++++++++++++++++ .../2026-07-19-make-jsonrpc-directional.zh.md | 38 +++++++++++++++++++ ...-19-retire-subagent-mock-package.i18n.yaml | 6 +++ ...2026-07-19-retire-subagent-mock-package.md | 35 +++++++++++++++++ ...6-07-19-retire-subagent-mock-package.zh.md | 35 +++++++++++++++++ ...-use-one-session-surface-manager.i18n.yaml | 6 +++ ...6-07-19-use-one-session-surface-manager.md | 35 +++++++++++++++++ ...7-19-use-one-session-surface-manager.zh.md | 35 +++++++++++++++++ 14 files changed, 319 insertions(+) create mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml create mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md create mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index fba361469c..99ea97d16a 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -21,6 +21,10 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | +| [Fold the single compaction backend into its service package](proposed/simplification/2026-07-19-fold-compaction-package-split.md) | 2026-07-19 | +| [Make JSON-RPC completion and transport directional](proposed/simplification/2026-07-19-make-jsonrpc-directional.md) | 2026-07-19 | +| [Retire the standalone subagent mock package](proposed/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | +| [Use one surface manager per session](proposed/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | ### Architecture diff --git a/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md b/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md index cca7c57b34..f874784a6d 100644 --- a/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md +++ b/docs/rfc/proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md @@ -25,6 +25,7 @@ The production corpus is `packages/*/*/src`, example sources/config, and runtime | `CompactionResult.startSeq`, `summarySeq`, `endSeq`, and `summary` | The production consumer reads only shadowed range/seq/token accounting; the durable log owns summary and event identity. | Remove the four result echoes while keeping both shared transcript renderers. | | `BasicCompactService` estimation/summarization visibility | No outside production caller invokes the five methods; the implemented RFC names only `estimateContentTokens()` and `summarize()` as subclass hooks. | Make those two `protected` and the three orchestration-only estimators private. | | `CodeLogEntry.source`/`level` and `RunCodeMeta.dispatches` | Every production consumer maps logs to text; no presenter/model path reads the other fields or the persisted dispatch count. | Make code-runtime logs strings (or text-only entries) and remove result-meta dispatch plumbing; keep the local counter that mints deterministic dispatch ids. | +| `CodeRuntime.language` and `CodeRuntime.isolation` | The worker backend supplies the only production values, while Code Mode and every other production caller invoke only `run()`. | Remove the unread descriptors while preserving the worker's language, isolation, budgets, cancellation, and disposal behavior. | | `ToolNotFoundError.toolName`, `SystemPrompt.config`, and `BashTask.command` | Each stored public value has no production reader. | Drop the unread field while retaining error messages, resolved configuration behavior, and task lifecycle. | | Backend package-root implementation helpers | The exact inventory below is called only through relative same-package imports. Production namespace imports mount the retained plugin contract without reading these properties; named root consumers are tests. | Retain each adapter/provider/service and its config/error contract; stop exporting the listed helper functions/constants at package roots. | | Consumer package-root implementation helpers | The exact inventory below has only same-package production callers. Production namespace imports mount plugin contracts without reading helper properties; named root consumers are tests. | Retain plugin contracts and stable error codes; move tests to package-local modules or public behavior and stop exporting the listed helpers at package roots. | diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml new file mode 100644 index 0000000000..2aabfdf8cc --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-fold-compaction-package-split.md: 37be6de84356549d27a8fc32b6589130eb1f27b8 +2026-07-19-fold-compaction-package-split.zh.md: f6609add00826ba472f8c82e0a67613ca201fd30 diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md new file mode 100644 index 0000000000..37be6de843 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md @@ -0,0 +1,37 @@ +# RFC: Fold the single compaction backend into its service package + +Status: proposed + +English | [中文](2026-07-19-fold-compaction-package-split.zh.md) + +## Problem + +Compaction is split between `@deepseek-ai/dsh-compact`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compact-basic`, which owns the only complete implementation. Shipped configurations load only the basic package, and no production package independently consumes the interface package except that implementation. + +The split adds a package manifest, README, project boundary, dependency edge, abstract forwarding class, generated catalog entries, and composition wiring without demonstrating backend substitution. The [capability-seam decision](../../implemented/architecture/2026-06-13-capability-seams.md) requires a real interface, implementation, and consumer rather than a preemptive split; the [compaction decision](../../implemented/feature/2026-06-18-compaction-capability-seam.md) records that its independent consumer was deferred. + +## Proposal + +Move the basic implementation into `@deepseek-ai/dsh-compact` and remove `@deepseek-ai/dsh-compact-basic`. Keep `ctx.compact`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package. + +Preserve `summarize()` as a protected customization hook. A deployment-specific summarizer can subclass or intercept the existing LLM call without requiring a second capability package. Reintroduce an interface package only when a second complete backend and an independent consumer need substitution. + +Amend the implemented compaction decision and the [recallable-compaction proposal](../feature/2026-07-06-recallable-compaction.md) if this proposal is accepted so package ownership has one durable description. + +## Alternatives considered + +**Keep the split because a remote or recall backend may arrive.** A possible future implementation does not justify the current package boundary. Recall adds a consumer of compaction results, not necessarily another implementation, and a remote summarizer can use the protected hook. + +**Move the implementation package name onto the interface package.** Keeping `compact-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compact` and is the clearer single-package owner. + +## Acceptance criteria + +- `@deepseek-ai/dsh-compact-basic` and its workspace/package metadata are removed. +- `@deepseek-ai/dsh-compact` owns the current configuration, plugin class, algorithm, types, events, and shared helpers. +- Existing deployments can load the surviving package with equivalent configuration and model-visible behavior. +- Automatic and manual compaction preserve cancellation, locking, token accounting, tool pairing, durable events, provenance, retry convergence, and transcript rendering. +- Loader composition, unit, runaway-turn, cancellation, snapshot, and real-model compaction tests pass; generated catalogs and module graphs are current. + +## Risks + +This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compact-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first. diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md new file mode 100644 index 0000000000..f6609add00 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md @@ -0,0 +1,37 @@ +# RFC: 将唯一的压缩后端并入服务包 + +Status: proposed + +[English](2026-07-19-fold-compaction-package-split.md) | 中文 + +## 问题 + +压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compact` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compact-basic` 拥有唯一的完整实现。交付配置只加载 basic 包，除了该实现外，没有生产包独立消费接口包。 + +该拆分增加了一份包（package）manifest（元数据清单）、README、项目边界、依赖边、抽象转发类、生成目录项和组合接线，却没有体现后端替换需求。[能力服务边界决策](../../implemented/architecture/2026-06-13-capability-seams.md)要求接口、实现和消费方都必须真实存在，而不能预先拆分；[压缩决策](../../implemented/feature/2026-06-18-compaction-capability-seam.md)也记录了独立消费方仍被推迟。 + +## 提案 + +把 basic 实现移入 `@deepseek-ai/dsh-compact`，并删除 `@deepseek-ai/dsh-compact-basic`。`ctx.compact`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。 + +保留 `summarize()` 作为受保护的自定义钩子。部署专用的摘要器可以通过继承或拦截现有 LLM（大语言模型）调用完成定制，无需第二个能力包。只有在第二个完整后端与独立消费方确实需要替换实现时，才重新提取接口包。 + +如果本提案获准，应同步修订已实现的压缩决策与[可回忆压缩提案](../feature/2026-07-06-recallable-compaction.md)，使包所有权只有一处持久说明。 + +## 备选方案 + +**为可能出现的远程或回忆后端保留拆分。** 一种可能的未来实现不足以支撑当前包边界。回忆功能会增加压缩结果的消费方，但不一定增加另一种实现；远程摘要器也可以使用受保护钩子。 + +**让接口包并入实现包名。** 如果保留 `compact-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compact` 使用的稳定服务标识，更适合作为单包所有者。 + +## 验收标准 + +- 删除 `@deepseek-ai/dsh-compact-basic` 及其工作区和包元数据。 +- `@deepseek-ai/dsh-compact` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。 +- 现有部署可以使用等效配置加载保留的包，模型可见行为不变。 +- 自动压缩和手动压缩保留取消、锁、token 用量、工具配对、持久事件、来源、重试收敛和 transcript 渲染行为。 +- Loader 组合、单元、失控轮次、取消、快照和真实模型压缩测试全部通过；生成目录与模块图保持最新。 + +## 风险 + +这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compact-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml new file mode 100644 index 0000000000..b515d611f5 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-make-jsonrpc-directional.md: 4531cb251c4d12c9f2d700c9297bdee87e284779 +2026-07-19-make-jsonrpc-directional.zh.md: fb9bd06a9817357112b1eba2f41130ce2368d0b9 diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md new file mode 100644 index 0000000000..4531cb251c --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md @@ -0,0 +1,38 @@ +# RFC: Make JSON-RPC completion and transport directional + +Status: proposed + +English | [中文](2026-07-19-make-jsonrpc-directional.zh.md) + +## Problem + +The JSON-RPC bridge models both endpoints as symmetric peers although the shipped protocol is directional. The TypeScript server accepts requests and emits responses or notifications, but its transport also implements unused outbound requests and inbound notification dispatch. The Python SDK sends requests and receives responses or notifications, but it also queues unused inbound server requests and exposes response helpers. + +`session/prompt` also reports one settled turn through two protocol shapes. The server emits `session.finished` and then returns the constant `{ accepted: true }`; the Python SDK discards that response and waits for the notification to recover the status. Because the response is written only after the handler returns, the notification necessarily precedes the constant response on the same stream. + +The unused halves add pending-request maps, generated IDs, request queues, close-time rejection paths, response helpers, and a second completion waiter without serving a production caller. + +## Proposal + +Specialize each endpoint to its actual role. The TypeScript transport will retain inbound requests, outbound responses, and outbound notifications. The Python client will retain outbound requests and inbound responses or notifications. Delete the opposite-direction request machinery from each side. + +Return the settled outcome directly from `session/prompt` as `{ status, reason }` after `agent.whenIdle()`. Delete `session.finished`, the constant acceptance response, and the Python post-response completion loop. `session.event` and subagent notifications still stream before the response, and durable session events remain the source for final-response reconstruction. + +## Alternatives considered + +**Keep a generic symmetric JSON-RPC peer for future methods.** Server-initiated requests may eventually support interactive permissions, but no typed method or production consumer exists. The pre-release protocol can add the smallest required direction when that feature is designed instead of carrying an unexercised peer today. + +**Keep `session.finished` for streaming clients.** Turn settlement is not incremental data: the request response already marks the same boundary and follows all earlier notifications on the ordered stream. A second terminal notification creates two representations that clients must reconcile. + +## Acceptance criteria + +- The TypeScript endpoint cannot originate requests or consume notifications. +- The Python endpoint cannot originate notifications or consume server requests. +- `session/prompt` returns the authoritative `ok`, `error`, or `aborted` outcome and reason after turn settlement. +- Session events and subagent lifecycle notifications emitted during the turn arrive before the response. +- Same-session overlap rejection, framing, multibyte input, handler errors, flush, shutdown ordering, and final-response reconstruction retain their behavior. +- TypeScript bridge tests, Python SDK tests, built JSON-RPC coverage, snapshots, and generated API documentation pass. + +## Risks + +This deliberately narrows the pre-release wire protocol. Raw clients listening only for `session.finished`, or embedders using the unused symmetric transport methods, must move to the prompt response. A future server-initiated request requires a new typed protocol addition rather than reusing generic dormant machinery. diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md new file mode 100644 index 0000000000..fb9bd06a98 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md @@ -0,0 +1,38 @@ +# RFC: 让 JSON-RPC 完成结果与传输方向单一化 + +Status: proposed + +[English](2026-07-19-make-jsonrpc-directional.md) | 中文 + +## 问题 + +JSON-RPC 桥接层把两个端点都建模为对称的对等端，但实际协议具有固定方向。TypeScript 服务端接收请求并发出响应或通知，其传输层却还实现了未使用的出站请求和入站通知分发。Python SDK 发送请求并接收响应或通知，却还会把未使用的服务端入站请求放入队列，并公开响应辅助方法。 + +`session/prompt` 还会用两种协议结构报告同一个已结束轮次。服务端先发出 `session.finished`，再返回常量 `{ accepted: true }`；Python SDK 丢弃该响应，转而等待通知以取得状态。响应只有在处理函数返回后才会写入，因此在同一条有序流上，通知必然先于这个常量响应。 + +这些未使用的双向能力引入了待处理请求表、生成 ID、请求队列、关闭时的拒绝路径、响应辅助方法和第二套完成等待逻辑，却没有任何生产调用方使用。 + +## 提案 + +按实际角色收窄两个端点。TypeScript 传输层只保留入站请求、出站响应和出站通知。Python 客户端只保留出站请求以及入站响应或通知。删除两侧与实际方向相反的请求机制。 + +在 `agent.whenIdle()` 完成后，由 `session/prompt` 直接返回 `{ status, reason }` 作为轮次结果。删除 `session.finished`、常量接纳响应以及 Python 中响应后的完成等待循环。`session.event` 与 subagent 通知仍在响应前流式发出，持久会话事件仍是最终响应重建的真源。 + +## 备选方案 + +**为未来方法保留通用的对称 JSON-RPC 对等端。** 服务端发起的请求将来可能用于交互式权限，但当前没有类型化方法或生产消费方。该功能完成设计后，预发布协议可以增加所需的最小方向，无需提前保留未使用的对等端能力。 + +**为流式客户端保留 `session.finished`。** 轮次结束不是增量数据：请求响应已经标识同一个边界，并且在有序流中位于先前所有通知之后。第二条终止通知会产生两种结果表示，迫使客户端进行协调。 + +## 验收标准 + +- TypeScript 端点无法发起请求，也不消费通知。 +- Python 端点无法发起通知，也不消费服务端请求。 +- 轮次结束后，`session/prompt` 返回权威的 `ok`、`error` 或 `aborted` 状态及其原因。 +- 轮次中发出的会话事件与 subagent 生命周期通知都先于响应到达。 +- 同一会话的重叠拒绝、分帧、多字节输入、处理器错误、flush、关闭顺序与最终响应重建保持原有行为。 +- TypeScript 桥接测试、Python SDK 测试、构建后 JSON-RPC 覆盖、快照和生成的 API 文档全部通过。 + +## 风险 + +本提案会刻意收窄预发布协议格式。仅监听 `session.finished` 的原始客户端，以及使用未使用对称传输方法的嵌入方，都必须改为读取请求响应。未来若需要服务端发起请求，应新增类型化协议，而不是复用休眠的通用机制。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml new file mode 100644 index 0000000000..37c3c8b508 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-retire-subagent-mock-package.md: 2731d35448cbc4dc9db4c92579c35202a53eefdd +2026-07-19-retire-subagent-mock-package.zh.md: 919c56502227157465277cc07c23fb7096763684 diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md new file mode 100644 index 0000000000..2731d35448 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md @@ -0,0 +1,35 @@ +# RFC: Retire the standalone subagent mock package + +Status: proposed + +English | [中文](2026-07-19-retire-subagent-mock-package.zh.md) + +## Problem + +`@deepseek-ai/dsh-subagent-mock` is a configurable test double packaged as a workspace plugin. Its only external consumers are the `tool-subagent` unit suite and the tool-catalog generator. No runtime package, example, snapshot configuration, or real provider loads it. + +That narrow fixture carries a manifest, exports, peer and development dependencies, project references, package README obligations, Loader composition tests, module-graph membership, and documentation-gate exceptions. The tool-catalog generator mounts it only to make the real subagent tool register its schema; it never executes a child. + +## Proposal + +Delete `packages/support/subagent-mock`. Move the scripted provider behavior actually used by `tool-subagent` into a package-local test fixture while continuing to exercise the real `SubagentService`, provider registry, and tool implementation. + +Have the tool-catalog generator register the minimal provider descriptor required before mounting `ToolSubagent`. Remove the package references, manifest dependency, graph node, README allowlists, and mock-specific Loader tests. + +## Alternatives considered + +**Keep a reusable mock package for future tests.** Reuse has not materialized outside one test file and one generator. A future second consumer can extract a fixture once its shared contract is known; packaging all configurable reply, cancellation, result, and Loader behavior today makes test infrastructure look like a supported backend. + +**Generate the subagent schema without mounting the real tool.** Hand-constructing or importing the schema would weaken the catalog's check that the production registry and tool composition expose the documented shape. The generator should keep mounting the real service and tool with only the child boundary replaced. + +## Acceptance criteria + +- `packages/support/subagent-mock` and every workspace, graph, dependency, and documentation entry for it are removed. +- `tool-subagent` tests retain every scripted reply, structured-result, cancellation, foreground/background, and task-integration case they currently exercise through the real service and tool. +- Tool-catalog generation mounts the production subagent registry and tool with a minimal local provider and produces a byte-identical catalog. +- No runtime or example package gains a dependency on test-only fixtures. +- Focused subagent tests, catalog and graph generation, module-graph verification, build, hygiene, and the full pre-push suite pass. + +## Risks + +Relocating the fixture could accidentally replace too much production composition with a stub. The local fixture must implement only the nondeterministic child boundary; capability checks, lifecycle, task handling, and tool output remain under production code. Mock Loader and HMR coverage can disappear because no deployed composition consumes the package afterward. diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md new file mode 100644 index 0000000000..919c565022 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md @@ -0,0 +1,35 @@ +# RFC: 撤销独立的 subagent mock 包 + +Status: proposed + +[English](2026-07-19-retire-subagent-mock-package.md) | 中文 + +## 问题 + +`@deepseek-ai/dsh-subagent-mock` 是一个以工作区插件形式发布的可配置测试替身。它仅有两个外部消费方：`tool-subagent` 单元测试和工具目录生成器。运行时包、示例、快照配置和真实提供方都不会加载它。 + +这个用途狭窄的 fixture（测试前置数据）需要维护 manifest（元数据清单）、导出、对等依赖（peer dependency）与开发依赖、项目引用、包（package）README 契约、Loader 组合测试、模块图成员关系以及文档门禁例外。工具目录生成器挂载它，只是为了让真实 subagent 工具注册 schema；生成器从不执行子 agent。 + +## 提案 + +删除 `packages/support/subagent-mock`。把 `tool-subagent` 实际使用的脚本化提供方行为移入该包的本地测试 fixture，同时继续测试真实的 `SubagentService`、提供方注册表和工具实现。 + +工具目录生成器在挂载 `ToolSubagent` 前，只注册所需的最小提供方描述。删除该包的项目引用、manifest 依赖、图节点、README 允许列表和 mock 专用 Loader 测试。 + +## 备选方案 + +**为未来测试保留可复用 mock 包。** 除一个测试文件和一个生成器外，复用需求并未出现。未来产生第二个消费方时，可以在共享契约明确后再提取 fixture；当前把所有可配置回复、取消、结果与 Loader 行为打包，会使测试基础设施看起来像受支持的后端。 + +**不挂载真实工具，直接生成 subagent schema。** 手工构造或直接导入 schema，会削弱目录生成器对生产注册表与工具组合是否公开文档结构的校验。生成器应继续挂载真实服务与工具，只替换不确定的子 agent 边界。 + +## 验收标准 + +- 删除 `packages/support/subagent-mock`，并移除其全部工作区、图、依赖和文档条目。 +- `tool-subagent` 测试保留当前通过真实服务与工具覆盖的全部脚本化回复、结构化结果、取消、前台与后台运行以及任务集成用例。 +- 工具目录生成器使用最小本地提供方挂载生产 subagent 注册表与工具，并生成字节级一致的目录。 +- 运行时包与示例包都不会新增对测试专用 fixture 的依赖。 +- 聚焦 subagent 测试、目录与图生成、模块图校验、构建、hygiene 和完整 pre-push 门禁全部通过。 + +## 风险 + +迁移 fixture 时，可能会误将过多生产组合替换成测试替身。本地 fixture 只能实现不确定的 subagent 边界；能力检查、生命周期、任务处理与工具输出仍由生产代码负责。由于之后不再有部署组合消费该包，可以删除 mock 的 Loader 与 HMR 覆盖。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml new file mode 100644 index 0000000000..adee0c347d --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-use-one-session-surface-manager.md: f351c05cf5cb5d408aeb22c8c3e6ac5c575fc24a +2026-07-19-use-one-session-surface-manager.zh.md: 20c1f04f7b4197549f23145aa2c6015cd44f38cc diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md new file mode 100644 index 0000000000..f351c05cf5 --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md @@ -0,0 +1,35 @@ +# RFC: Use one surface manager per session + +Status: proposed + +English | [中文](2026-07-19-use-one-session-surface-manager.zh.md) + +## Problem + +`Session` maintains two `SurfaceManager` instances over the same append-only event log. `surfaceValidator` eagerly validates seed and append candidates, while the lazy `_surface` independently folds committed events for `session.surface`, derived messages, compaction, and workspace context. Once the public surface is read, every later event advances duplicate node and replacement-generation state. + +The [session surface decision](../../implemented/architecture/2026-06-18-session-surface.md) calls for one ordered surface and one representation to validate. The second manager does not create an independent authority or protect a different failure boundary; it repeats the canonical fold and gives the two views a state-drift opportunity. + +## Proposal + +Keep one `SurfaceManager` per `Session`. Seed and append acceptance continue to call `validateNext()` before committing an event, and the public surface view reads `nodes` and `replaceGeneration` from that same manager. + +Expose only the readonly surface contract from `Session.surface`; candidate validation remains owned by `Session`. Retain `foldSurface()` as the detached full-log replay function used by offline validation and reconstruction. + +## Alternatives considered + +**Keep acceptance and projection state separate.** Separate instances appear to isolate public reads from validation, but ordinary callers already receive borrowed surface state and cannot mutate it through the declared readonly contract. A cast that mutates the returned node array already corrupts derived history; duplicating the manager is not a sound runtime trust boundary. + +**Recompute the public surface from the full log on every access.** This removes cached duplicate state but gives up incremental derivation and makes repeated request construction scale with complete session history. + +## Acceptance criteria + +- A live `Session` owns exactly one incremental `SurfaceManager`. +- Seed and append candidates are validated before publication with no partial surface mutation on rejection. +- `session.surface`, derived messages, compaction, and workspace context observe the same nodes and replacement generation as the acceptance path. +- `foldSurface()` remains available for detached replay and agrees with the live manager for every accepted prefix. +- Session surface, seed, request reconstruction, compaction tool-pairing, and workspace-context tests pass. + +## Risks + +Sharing one manager makes the readonly borrowed-state contract more important because a hostile cast could corrupt both validation and projection state. The implementation should return a narrowed view and keep mutation methods inaccessible through `Session.surface`; JavaScript callers that deliberately bypass the type contract remain outside the supported same-process boundary. diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md new file mode 100644 index 0000000000..20c1f04f7b --- /dev/null +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md @@ -0,0 +1,35 @@ +# RFC: 每个会话只使用一个表层管理器 + +Status: proposed + +[English](2026-07-19-use-one-session-surface-manager.md) | 中文 + +## 问题 + +`Session` 针对同一份仅追加事件日志维护两个 `SurfaceManager` 实例。`surfaceValidator` 主动校验种子事件与追加候选事件，延迟创建的 `_surface` 则独立折叠已提交事件，供 `session.surface`、派生消息、压缩（compaction）和工作区上下文使用。一旦读取公共表层，之后的每个事件都会推进两份重复的节点状态与替换代数状态。 + +[会话表层决策](../../implemented/architecture/2026-06-18-session-surface.md)要求系统只保留一个有序表层，并使用一种表示完成校验。第二个管理器既不形成独立真源，也不保护不同的失败边界；它只会重复规范折叠，并使两个视图可能出现状态偏差。 + +## 提案 + +每个 `Session` 只保留一个 `SurfaceManager`。种子事件与追加事件的接纳流程仍在提交事件之前调用 `validateNext()`，公共表层视图则从同一个管理器读取 `nodes` 与 `replaceGeneration`。 + +`Session.surface` 只公开只读表层契约，候选事件校验仍由 `Session` 负责。保留 `foldSurface()`，用于离线校验与重建时执行分离的完整日志回放。 + +## 备选方案 + +**继续分离接纳状态与投影视图。** 两个独立实例看似能够隔离公共读取和校验，但普通调用方目前取得的就是借用的表层状态，无法通过声明的只读契约修改它。通过类型断言修改返回的节点数组，本就会破坏派生历史；复制管理器并不能构成可靠的运行时信任边界。 + +**每次读取都根据完整日志重新计算公共表层。** 该方案不再缓存重复状态，但会放弃增量派生，使每次请求构造都随完整会话历史增长。 + +## 验收标准 + +- 每个活跃 `Session` 只拥有一个增量 `SurfaceManager`。 +- 种子事件与追加候选事件都在发布前完成校验，拒绝事件时不会留下只修改一半的表层状态。 +- `session.surface`、派生消息、压缩和工作区上下文观察到的节点与替换代数，和接纳路径使用的状态完全一致。 +- `foldSurface()` 仍可用于分离回放，并且对任意已接纳前缀都与活跃管理器一致。 +- 会话表层、种子、请求重建、压缩工具配对和工作区上下文测试全部通过。 + +## 风险 + +共享一个管理器会提高只读借用状态契约的重要性，因为恶意类型断言可能同时破坏校验状态和投影视图。实现应返回收窄后的视图，避免通过 `Session.surface` 暴露修改方法；刻意绕过类型契约的 JavaScript 调用方不属于受支持的同进程边界。 From 0c911172e959d16fdf54a0cd1d927f4cb23c997b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 10:45:04 +0800 Subject: [PATCH 199/323] docs: drop rejected compaction RFC --- docs/rfc/INDEX.md | 1 - ...19-fold-compaction-package-split.i18n.yaml | 6 --- ...026-07-19-fold-compaction-package-split.md | 37 ------------------- ...-07-19-fold-compaction-package-split.zh.md | 37 ------------------- 4 files changed, 81 deletions(-) delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 99ea97d16a..4dc9b229ff 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -21,7 +21,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | -| [Fold the single compaction backend into its service package](proposed/simplification/2026-07-19-fold-compaction-package-split.md) | 2026-07-19 | | [Make JSON-RPC completion and transport directional](proposed/simplification/2026-07-19-make-jsonrpc-directional.md) | 2026-07-19 | | [Retire the standalone subagent mock package](proposed/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | | [Use one surface manager per session](proposed/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml deleted file mode 100644 index 2aabfdf8cc..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml +++ /dev/null @@ -1,6 +0,0 @@ -# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each -# side as of the last confirmed-consistent state. Both languages carry equal authority; -# after editing either side, bring the other along and re-record with: -# pnpm run verify-translation-pairing --write -2026-07-19-fold-compaction-package-split.md: 37be6de84356549d27a8fc32b6589130eb1f27b8 -2026-07-19-fold-compaction-package-split.zh.md: f6609add00826ba472f8c82e0a67613ca201fd30 diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md deleted file mode 100644 index 37be6de843..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.md +++ /dev/null @@ -1,37 +0,0 @@ -# RFC: Fold the single compaction backend into its service package - -Status: proposed - -English | [中文](2026-07-19-fold-compaction-package-split.zh.md) - -## Problem - -Compaction is split between `@deepseek-ai/dsh-compact`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compact-basic`, which owns the only complete implementation. Shipped configurations load only the basic package, and no production package independently consumes the interface package except that implementation. - -The split adds a package manifest, README, project boundary, dependency edge, abstract forwarding class, generated catalog entries, and composition wiring without demonstrating backend substitution. The [capability-seam decision](../../implemented/architecture/2026-06-13-capability-seams.md) requires a real interface, implementation, and consumer rather than a preemptive split; the [compaction decision](../../implemented/feature/2026-06-18-compaction-capability-seam.md) records that its independent consumer was deferred. - -## Proposal - -Move the basic implementation into `@deepseek-ai/dsh-compact` and remove `@deepseek-ai/dsh-compact-basic`. Keep `ctx.compact`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package. - -Preserve `summarize()` as a protected customization hook. A deployment-specific summarizer can subclass or intercept the existing LLM call without requiring a second capability package. Reintroduce an interface package only when a second complete backend and an independent consumer need substitution. - -Amend the implemented compaction decision and the [recallable-compaction proposal](../feature/2026-07-06-recallable-compaction.md) if this proposal is accepted so package ownership has one durable description. - -## Alternatives considered - -**Keep the split because a remote or recall backend may arrive.** A possible future implementation does not justify the current package boundary. Recall adds a consumer of compaction results, not necessarily another implementation, and a remote summarizer can use the protected hook. - -**Move the implementation package name onto the interface package.** Keeping `compact-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compact` and is the clearer single-package owner. - -## Acceptance criteria - -- `@deepseek-ai/dsh-compact-basic` and its workspace/package metadata are removed. -- `@deepseek-ai/dsh-compact` owns the current configuration, plugin class, algorithm, types, events, and shared helpers. -- Existing deployments can load the surviving package with equivalent configuration and model-visible behavior. -- Automatic and manual compaction preserve cancellation, locking, token accounting, tool pairing, durable events, provenance, retry convergence, and transcript rendering. -- Loader composition, unit, runaway-turn, cancellation, snapshot, and real-model compaction tests pass; generated catalogs and module graphs are current. - -## Risks - -This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compact-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first. diff --git a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md b/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md deleted file mode 100644 index f6609add00..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-fold-compaction-package-split.zh.md +++ /dev/null @@ -1,37 +0,0 @@ -# RFC: 将唯一的压缩后端并入服务包 - -Status: proposed - -[English](2026-07-19-fold-compaction-package-split.md) | 中文 - -## 问题 - -压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compact` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compact-basic` 拥有唯一的完整实现。交付配置只加载 basic 包，除了该实现外，没有生产包独立消费接口包。 - -该拆分增加了一份包（package）manifest（元数据清单）、README、项目边界、依赖边、抽象转发类、生成目录项和组合接线，却没有体现后端替换需求。[能力服务边界决策](../../implemented/architecture/2026-06-13-capability-seams.md)要求接口、实现和消费方都必须真实存在，而不能预先拆分；[压缩决策](../../implemented/feature/2026-06-18-compaction-capability-seam.md)也记录了独立消费方仍被推迟。 - -## 提案 - -把 basic 实现移入 `@deepseek-ai/dsh-compact`，并删除 `@deepseek-ai/dsh-compact-basic`。`ctx.compact`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。 - -保留 `summarize()` 作为受保护的自定义钩子。部署专用的摘要器可以通过继承或拦截现有 LLM（大语言模型）调用完成定制，无需第二个能力包。只有在第二个完整后端与独立消费方确实需要替换实现时，才重新提取接口包。 - -如果本提案获准，应同步修订已实现的压缩决策与[可回忆压缩提案](../feature/2026-07-06-recallable-compaction.md)，使包所有权只有一处持久说明。 - -## 备选方案 - -**为可能出现的远程或回忆后端保留拆分。** 一种可能的未来实现不足以支撑当前包边界。回忆功能会增加压缩结果的消费方，但不一定增加另一种实现；远程摘要器也可以使用受保护钩子。 - -**让接口包并入实现包名。** 如果保留 `compact-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compact` 使用的稳定服务标识，更适合作为单包所有者。 - -## 验收标准 - -- 删除 `@deepseek-ai/dsh-compact-basic` 及其工作区和包元数据。 -- `@deepseek-ai/dsh-compact` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。 -- 现有部署可以使用等效配置加载保留的包，模型可见行为不变。 -- 自动压缩和手动压缩保留取消、锁、token 用量、工具配对、持久事件、来源、重试收敛和 transcript 渲染行为。 -- Loader 组合、单元、失控轮次、取消、快照和真实模型压缩测试全部通过；生成目录与模块图保持最新。 - -## 风险 - -这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compact-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。 From b5e8e4e9c1a7a96f88a33e40fe45f9c039b12b5d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 10:49:59 +0800 Subject: [PATCH 200/323] fix(tui): neutralize terminal controls at display boundary Model responses, replayed session data, tool presenter output, question metadata, configuration, and diagnostics all cross into ANSI-aware pi-tui renderers. Passing their C0 or C1 controls through unchanged lets an otherwise ordinary transcript emit OSC, CSI, cursor, or title operations in the user terminal. Introduce one displayText boundary that preserves line-feed layout but renders every other C0/C1 control as visible \\xNN text before application styling is applied. Route transcript blocks, streaming output, tool cards, diffs, plans, dialogs, headers, cwd/title data, notices, errors, and pre-mount startup failures through that boundary while leaving pi-tui and the theme responsible for legitimate terminal control sequences. Pin the contract at three levels: a settled headless-terminal golden spans the main untrusted display sources, unit coverage checks the pre-fullscreen failure path, and the real Loader/PTY conversation streams hostile OSC, cursor, and C1 probes and proves only their inert textual forms reach the terminal stream. --- .../tests/fixtures/tui-scripted-llm.ts | 3 +- .../tui-agent/tests/tui-keyless-smoke.e2e.ts | 6 + packages/ui/tui/README.md | 2 + packages/ui/tui/src/index.ts | 88 +++++++++------ .../snapshots/untrusted-controls.golden.txt | 106 ++++++++++++++++++ packages/ui/tui/tests/tui.snapshot.ts | 80 +++++++++++++ packages/ui/tui/tests/tui.spec.ts | 4 +- 7 files changed, 250 insertions(+), 39 deletions(-) create mode 100644 packages/ui/tui/tests/snapshots/untrusted-controls.golden.txt diff --git a/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts b/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts index 2147dfb222..c55b3d355c 100644 --- a/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts +++ b/examples/tui-agent/tests/fixtures/tui-scripted-llm.ts @@ -2,7 +2,8 @@ import type { Context } from 'cordis' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' import { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' -const INITIAL_TEXT = 'I need one decision before I continue.' +const CONTROL_PROBE = '\u001b]2;MODEL_CONTROLLED\u0007\u001b[999CMODEL_CURSOR\u009b31mMODEL_C1' +const INITIAL_TEXT = `I need one decision before I continue. ${CONTROL_PROBE}` const FINAL_TEXT = 'Decision received. Scripted TUI run complete.' function textChunks(text: string): StreamChunk[] { diff --git a/examples/tui-agent/tests/tui-keyless-smoke.e2e.ts b/examples/tui-agent/tests/tui-keyless-smoke.e2e.ts index 26cee8aea2..f9b2ec1d43 100644 --- a/examples/tui-agent/tests/tui-keyless-smoke.e2e.ts +++ b/examples/tui-agent/tests/tui-keyless-smoke.e2e.ts @@ -153,6 +153,12 @@ describe('tui-agent keyless smoke (real Loader tree in a PTY)', () => { it('streams a response, answers a user-question dialog, completes the tool round-trip, and exits cleanly', async () => { const output = await runTuiLoaderSmoke({ config: scriptedConfigPath, scenario: 'conversation' }) expect(output).toContain('I need one decision before I continue.') + expect(output).toContain(String.raw`\x1b]2;MODEL_CONTROLLED\x07`) + expect(output).toContain(String.raw`\x1b[999CMODEL_CURSOR`) + expect(output).toContain(String.raw`\x9b31mMODEL_C1`) + expect(output).not.toContain('\u001B]2;MODEL_CONTROLLED\u0007') + expect(output).not.toContain('\u001B[999CMODEL_CURSOR') + expect(output).not.toContain('\u009B31mMODEL_C1') expect(output).toContain('How should the scripted run proceed?') expect(output).toContain('Safe') expect(output).toContain('Decision received. Scripted TUI run complete.') diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md index 865a20a469..cf4cc609ce 100644 --- a/packages/ui/tui/README.md +++ b/packages/ui/tui/README.md @@ -6,6 +6,8 @@ This package owns interactive terminal presentation and input only. It injects ` The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions as keyboard-driven overlays. Surface replacement events rebuild the transcript so compacted history does not reappear. +Before model output, session events, tool presenters, questions, configuration, or diagnostics reach pi-tui's ANSI-aware renderers or the terminal title, the TUI renders C0 and C1 controls other than line feeds as visible `\xNN` text. Those sources cannot add terminal control sequences; the TUI and pi-tui retain ownership of terminal rendering and styling. + While the agent is running, editor submissions call `agent.steer()`; otherwise they call `agent.send()`. Ctrl+C or Escape cancels a running turn. Ctrl+O expands tool cards, Ctrl+R toggles reasoning, Ctrl+L redraws, and Ctrl+D exits while idle. `/help`, `/clear`, `/cancel`, `/reasoning`, `/tools`, `/redraw`, and `/exit` provide the same actions without key chords. ## Config diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts index b9b74e7c9a..612f2f3099 100644 --- a/packages/ui/tui/src/index.ts +++ b/packages/ui/tui/src/index.ts @@ -179,6 +179,17 @@ function ansi(open: string, close: string, enabled: boolean): (text: string) => return enabled ? text => `\x1b[${open}m${text}\x1b[${close}m` : text => text } +const TERMINAL_CONTROL_PATTERN = /[\u0000-\u0009\u000b-\u001f\u007f-\u009f]/gu + +/** + * Escape external C0/C1 controls before pi-tui adds application-owned ANSI. + * Line feeds remain structural so transcript and tool output retain their layout. + */ +function displayText(text: string): string { + return text.replace(TERMINAL_CONTROL_PATTERN, control => + `\\x${control.charCodeAt(0).toString(16).padStart(2, '0')}`) +} + /** * Theme-agnostic palette built from the standard 16-color ANSI set plus SGR * attributes, which every terminal remaps to its active color scheme. Body @@ -281,11 +292,11 @@ class HeaderComponent implements Component { render(width: number): string[] { const usable = Math.max(1, width - 4) const title = `${this.palette.bold(this.palette.accent('DEEPSEEK'))} ${this.palette.bold('HARNESS')}` - const model = this.agent.options.model ?? 'model unset' - const detail = `${this.agent.id} • ${model} • ${this.agent.session.id}` + const model = displayText(this.agent.options.model ?? 'model unset') + const detail = `${displayText(this.agent.id)} • ${model} • ${displayText(this.agent.session.id)}` const top = this.palette.accent(`╭${'─'.repeat(Math.max(0, width - 2))}╮`) const bottom = this.palette.accent(`╰${'─'.repeat(Math.max(0, width - 2))}╯`) - const lines = [title, this.palette.muted(this.welcome), this.palette.dim(detail)] + const lines = [title, this.palette.muted(displayText(this.welcome)), this.palette.dim(detail)] .flatMap(line => wrapTextWithAnsi(line, usable)) .map((line) => { const clipped = truncateToWidth(line, usable, '') @@ -330,8 +341,8 @@ class GutterBox implements Component { class UserMessageComponent extends GutterBox { constructor(text: string, palette: Palette, mdTheme: MarkdownTheme, label = 'You') { super(value => palette.accent(value)) - this.addChild(new Text(palette.bold(palette.accent(label)), 0, 0)) - this.addChild(new Markdown(text, 0, 0, mdTheme, { color: value => palette.text(value) }, { + this.addChild(new Text(palette.bold(palette.accent(displayText(label))), 0, 0)) + this.addChild(new Markdown(displayText(text), 0, 0, mdTheme, { color: value => palette.text(value) }, { preserveOrderedListMarkers: true, preserveBackslashEscapes: true, })) @@ -341,8 +352,8 @@ class UserMessageComponent extends GutterBox { class AssistantMessageComponent extends Container { constructor(content: readonly ContentBlock[], showReasoning: boolean, palette: Palette, mdTheme: MarkdownTheme) { super() - const reasoning = textBlocks(content, 'reasoning').trim() - const text = textBlocks(content, 'text').trim() + const reasoning = displayText(textBlocks(content, 'reasoning').trim()) + const text = displayText(textBlocks(content, 'text').trim()) if (reasoning && showReasoning) { this.addChild(new Spacer(1)) this.addChild(new Text(palette.italic(palette.muted('Reasoning')), 1, 0)) @@ -422,19 +433,19 @@ function parseArguments(raw: string): ParsedArguments { } function pretty(value: unknown): string { - if (typeof value === 'string') return value + if (typeof value === 'string') return displayText(value) // The lib declaration narrows `unknown` to a string-returning overload, but // JSON.stringify returns undefined for runtime values such as symbols. const serialized = JSON.stringify(value, null, 2) as string | undefined - return serialized ?? String(value) + return displayText(serialized ?? String(value)) } function diffLines(diff: FileDiff, palette: Palette): string[] { - const lines = [palette.bold(diff.path)] + const lines = [palette.bold(displayText(diff.path))] if (diff.oldText !== null) { - for (const line of diff.oldText.split('\n')) lines.push(palette.removed(`- ${line}`)) + for (const line of displayText(diff.oldText).split('\n')) lines.push(palette.removed(`- ${line}`)) } - for (const line of diff.newText.split('\n')) lines.push(palette.added(`+ ${line}`)) + for (const line of displayText(diff.newText).split('\n')) lines.push(palette.added(`+ ${line}`)) return lines } @@ -460,10 +471,10 @@ class ToolCardComponent implements Component { const view = this.definition.presentCall(this.parsed.value) if (view !== undefined) return view } catch (error: unknown) { - return { card: 'generic', title: this.name, rawInput: `Presenter failed: ${String(error)}` } + return { card: 'generic', title: displayText(this.name), rawInput: `Presenter failed: ${String(error)}` } } } - return { card: 'generic', title: this.name, rawInput: this.parsed.value } + return { card: 'generic', title: displayText(this.name), rawInput: this.parsed.value } } updateResult(event: Extract['data']): void { @@ -492,7 +503,7 @@ class ToolCardComponent implements Component { const isError = this.result?.isError ?? false const glyph = this.result === undefined ? this.palette.warning('◌') : isError ? this.palette.error('✕') : this.palette.success('✓') const body = this.renderBody() - const title = truncateToWidth(`${glyph} ${this.title()}`, Math.max(1, width - 4), '') + const title = truncateToWidth(`${glyph} ${displayText(this.title())}`, Math.max(1, width - 4), '') const visibleBody = this.expanded || body.length <= this.maxOutputLines ? body : [...body.slice(0, this.maxOutputLines), this.palette.dim(`… ${body.length - this.maxOutputLines} more lines (Ctrl+O to expand)`)] @@ -514,17 +525,19 @@ class ToolCardComponent implements Component { if (view.card === 'terminal') { const pending = this.callView.card === 'terminal' ? this.callView : undefined const lines: string[] = [] - if (pending?.description) lines.push(this.palette.muted(pending.description)) - if (pending?.cwd) lines.push(this.palette.dim(pending.cwd)) + if (pending?.description) lines.push(this.palette.muted(displayText(pending.description))) + if (pending?.cwd) lines.push(this.palette.dim(displayText(pending.cwd))) if (this.resultView?.card === 'terminal') { - if (this.resultView.output) lines.push(...this.resultView.output.split('\n')) + if (this.resultView.output) lines.push(...displayText(this.resultView.output).split('\n')) if (this.resultView.exitCode !== undefined) lines.push(this.palette.dim(`[exit ${this.resultView.exitCode}]`)) - if (this.resultView.signal !== undefined) lines.push(this.palette.error(`[signal ${this.resultView.signal}]`)) + if (this.resultView.signal !== undefined) { + lines.push(this.palette.error(`[signal ${displayText(this.resultView.signal)}]`)) + } } else if (this.result === undefined) { // A pending terminal view is the call view itself; TerminalCallView requires a title. - lines.push(this.palette.code(`$ ${(pending as TerminalCallView).title}`)) + lines.push(this.palette.code(`$ ${displayText((pending as TerminalCallView).title)}`)) } else { - lines.push(...contentText(this.result.content).split('\n')) + lines.push(...displayText(contentText(this.result.content)).split('\n')) } return lines.filter(Boolean) } @@ -536,7 +549,7 @@ class ToolCardComponent implements Component { } const content = view.content ?? this.result?.content const lines: string[] = [] - if (content !== undefined) lines.push(...contentText(content).split('\n')) + if (content !== undefined) lines.push(...displayText(contentText(content)).split('\n')) const rawInput = this.result === undefined && this.callView.card === 'generic' ? this.callView.rawInput : undefined @@ -565,7 +578,8 @@ class TodoComponent implements Component { : todo.status === 'in_progress' ? this.palette.warning('●') : this.palette.dim('○') - const text = todo.status === 'completed' ? this.palette.muted(todo.content) : todo.content + const content = displayText(todo.content) + const text = todo.status === 'completed' ? this.palette.muted(content) : content lines.push(truncateToWidth(` ${prefix} ${text}`, width, '')) } return ['', ...lines] @@ -584,8 +598,8 @@ function formatCwd(cwd: string | undefined): string { const home = homedir() const rel = relative(resolve(home), resolve(cwd)) if (rel === '') return '~' - if (rel !== '..' && !rel.startsWith(`..${sep}`)) return `~${sep}${rel}` - return cwd + if (rel !== '..' && !rel.startsWith(`..${sep}`)) return displayText(`~${sep}${rel}`) + return displayText(cwd) } function sessionTokens(session: Session): { input: number; output: number } { @@ -702,7 +716,7 @@ class QuestionDialog implements Component, Focusable { render(width: number): string[] { this.input.focused = this.focused const innerWidth = Math.max(1, width - 4) - const title = this.question.header ?? 'Question' + const title = displayText(this.question.header ?? 'Question') const topLabel = ` ${title} ` const top = `╭${topLabel}${'─'.repeat(Math.max(0, width - visibleWidth(topLabel) - 2))}╮` const lines: string[] = [this.palette.accent(top)] @@ -710,7 +724,7 @@ class QuestionDialog implements Component, Focusable { const clipped = truncateToWidth(line, innerWidth, '') lines.push(`${this.palette.accent('│')} ${clipped}${' '.repeat(Math.max(0, innerWidth - visibleWidth(clipped)))} ${this.palette.accent('│')}`) } - for (const line of wrapTextWithAnsi(this.palette.bold(this.question.question), innerWidth)) push(line) + for (const line of wrapTextWithAnsi(this.palette.bold(displayText(this.question.question)), innerWidth)) push(line) push('') if (this.mode === 'custom') { for (const line of this.input.render(innerWidth)) push(line) @@ -729,8 +743,10 @@ class QuestionDialog implements Component, Focusable { const mark = this.question.multiSelect ? this.selected.has(index) ? this.palette.success('[x]') : '[ ]' : index === this.selectedIndex ? this.palette.accent('●') : this.palette.dim('○') - const description = option.description ? this.palette.muted(` — ${option.description}`) : '' - const line = `${cursor} ${mark} ${option.label}${description}` + const description = option.description + ? this.palette.muted(` — ${displayText(option.description)}`) + : '' + const line = `${cursor} ${mark} ${displayText(option.label)}${description}` push(index === this.selectedIndex ? this.palette.selected(line) : line) } if (options.length > this.maxVisible) push(this.palette.dim(`${this.selectedIndex + 1}/${options.length}`)) @@ -826,7 +842,7 @@ export function createTuiChat( ui.addChild(editor) ui.addChild(footer) ui.setFocus(editor) - runtime.terminal.setTitle(resolved.title) + runtime.terminal.setTitle(displayText(resolved.title)) const requestRender = (): void => { footer.invalidate() @@ -836,7 +852,7 @@ export function createTuiChat( const appendNotice = (message: string, kind: 'info' | 'warning' | 'error' = 'info'): void => { const color = kind === 'error' ? palette.error : kind === 'warning' ? palette.warning : palette.muted chat.addChild(new Spacer(1)) - chat.addChild(new Text(color(message), 1, 0)) + chat.addChild(new Text(color(displayText(message)), 1, 0)) requestRender() } @@ -876,7 +892,7 @@ export function createTuiChat( const renderEvent = (event: SessionEvent, options: { addHistory: boolean; renderChunks: boolean }): void => { switch (event.type) { case 'user/message': { - const text = contentText(event.data.content).trim() + const text = displayText(contentText(event.data.content).trim()) if (text) { chat.addChild(new Spacer(1)) chat.addChild(new UserMessageComponent(text, palette, mdTheme)) @@ -885,7 +901,7 @@ export function createTuiChat( break } case 'steering/message': { - const text = contentText(event.data.content).trim() + const text = displayText(contentText(event.data.content).trim()) if (text) { chat.addChild(new Spacer(1)) chat.addChild(new UserMessageComponent(text, palette, mdTheme, 'Steering')) @@ -893,11 +909,11 @@ export function createTuiChat( break } case 'context/message': { - const text = contentText(event.data.content).trim() + const text = displayText(contentText(event.data.content).trim()) if (text) { const source = event.data.source.kind === 'plugin' ? event.data.source.plugin : event.data.source.kind chat.addChild(new Spacer(1)) - chat.addChild(new Text(palette.dim(`Context · ${source}`), 1, 0)) + chat.addChild(new Text(palette.dim(`Context · ${displayText(source)}`), 1, 0)) chat.addChild(new Text(palette.muted(text), 1, 0)) } break @@ -1291,7 +1307,7 @@ export function mountTui(ctx: Context, config: Config, runtime: TuiRuntime): voi }, 'ui-tui') }, onFailed: (error) => { - runtime.terminal.write(`ui-tui: agent "${agentId}" failed to start: ${error.message}\n`) + runtime.terminal.write(displayText(`ui-tui: agent "${agentId}" failed to start: ${error.message}\n`)) runtime.exit(1) }, }) diff --git a/packages/ui/tui/tests/snapshots/untrusted-controls.golden.txt b/packages/ui/tui/tests/snapshots/untrusted-controls.golden.txt new file mode 100644 index 0000000000..1a64b277d5 --- /dev/null +++ b/packages/ui/tui/tests/snapshots/untrusted-controls.golden.txt @@ -0,0 +1,106 @@ +terminal 100x34 buffer=normal length=40 base=6 viewport=6 +lifecycle started=1 stopped=0 progress=inactive +title "Unsafe terminal title \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m" +cursor hidden column=100 viewportRow=33 bufferRow=39 +buffer +0| "╭──────────────────────────────────────────────────────────────────────────────────────────────────╮" + style 0-99 fg=bright-blue +1| "│ DEEPSEEK HARNESS │" + style 0-0 fg=bright-blue + style 2-9 fg=bright-blue bold + style 11-17 bold + style 99-99 fg=bright-blue +2| "│ Unsafe welcome \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m │" + style 0-0 fg=bright-blue + style 2-61 fg=bright-black + style 99-99 fg=bright-blue +3| "│ main • deepseek-v4-flash • main-session │" + style 0-0 fg=bright-blue + style 2-44 dim + style 99-99 fg=bright-blue +4| "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯" + style 0-99 fg=bright-blue +5| +6| "▌ " + style 0-0 fg=bright-blue +7| "▌ You " + style 0-0 fg=bright-blue + style 2-4 fg=bright-blue bold +8| "▌ Unsafe user \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 0-0 fg=bright-blue +9| "▌ " + style 0-0 fg=bright-blue +10| +11| " Reasoning " + style 1-9 fg=bright-black italic +12| " Unsafe reasoning \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 1-62 fg=bright-black italic +13| +14| " Assistant " + style 1-9 fg=bright-magenta bold +15| " Unsafe assistant \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " +16| +17| "▌ " + style 0-0 fg=green +18| "▌ ✓ Unsafe title \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 0-0 fg=green + style 2-2 fg=green bold + style 3-61 bold +19| "▌ Unsafe description \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 0-0 fg=green + style 2-65 fg=bright-black +20| "▌ /unsafe/\\x1b╭ Unsafe header \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m ─────────╮ " + style 0-0 fg=green + style 2-13 dim + style 14-85 fg=bright-blue +21| "▌ Unsafe outpu│ Unsafe question \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m │ " + style 0-0 fg=green + style 14-14 fg=bright-blue + style 16-76 bold + style 85-85 fg=bright-blue +22| "▌ [signal SIG\\│ │ " + style 0-0 fg=green + style 2-13 fg=red + style 14-14 fg=bright-blue + style 85-85 fg=bright-blue +23| "▌ │ › ● Unsafe option \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m — Un │ " + style 0-0 fg=green + style 14-14 fg=bright-blue + style 16-16 fg=bright-blue inverse + style 17-17 inverse + style 18-18 fg=bright-blue inverse + style 19-78 inverse + style 79-83 fg=bright-black inverse + style 85-85 fg=bright-blue +24| " │ ↑↓ navigate • Enter select • C custom • Esc cancel │ " + style 14-14 fg=bright-blue + style 16-65 dim + style 85-85 fg=bright-blue +25| " Context · uns╰──────────────────────────────────────────────────────────────────────╯ " + style 1-13 dim + style 14-85 fg=bright-blue +26| " Unsafe context \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 1-60 fg=bright-black +27| +28| " Prompt blocked: Unsafe policy \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 1-75 fg=yellow +29| +30| " Unsafe turn error \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 1-63 fg=red +31| +32| " Unsafe live error \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m " + style 1-63 fg=red +33| +34| "Plan" + style 0-3 fg=bright-blue bold +35| " ● Unsafe todo \\x1b]2;snapshot-controlled\\x07\\x09\\x7f\\x9b31m" + style 2-2 fg=yellow +36| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +37| " " + style 1-1 inverse +38| "────────────────────────────────────────────────────────────────────────────────────────────────────" + style 0-99 dim +39| "/workspace/project ↑0 ↓0 idle reasoning:on tools:compact" + style 0-24 dim + style 67-99 dim diff --git a/packages/ui/tui/tests/tui.snapshot.ts b/packages/ui/tui/tests/tui.snapshot.ts index 0967e7f64c..e0016184fd 100644 --- a/packages/ui/tui/tests/tui.snapshot.ts +++ b/packages/ui/tui/tests/tui.snapshot.ts @@ -29,6 +29,7 @@ const CHECKPOINTS = [ 'cordis-tools-pending', 'advanced-cards-collapsed', 'advanced-cards-expanded', + 'untrusted-controls', 'question-dialog', 'question-dialog-validation', 'surface-before-compaction', @@ -188,6 +189,9 @@ const ADVANCED_CARD_TOOLS: Record = { })), } +const CONTROL_PROBE = '\u001b]2;snapshot-controlled\u0007\t\u007f\u009b31m' +const DISPLAYED_CONTROL_PROBE = String.raw`\x1b]2;snapshot-controlled\x07\x09\x7f\x9b31m` + describe('TUI terminal-state snapshots', () => { it('pins an in-flight reasoning and Markdown stream', async () => { const harness = await setupSnapshot() @@ -298,6 +302,82 @@ describe('TUI terminal-state snapshots', () => { await disposeSnapshot(harness) }) + it('renders terminal controls as inert text across transcripts, tools, dialogs, diagnostics, and title', async () => { + const tools = { + unsafe: visualTool( + 'unsafe', + () => ({ + card: 'terminal', + title: `Unsafe title ${CONTROL_PROBE}`, + description: `Unsafe description ${CONTROL_PROBE}`, + cwd: `/unsafe/${CONTROL_PROBE}`, + }), + () => ({ + card: 'terminal', + output: `Unsafe output ${CONTROL_PROBE}`, + signal: `SIG${CONTROL_PROBE}`, + }), + ), + } + const harness = await setupSnapshot({ + tools, + config: { + welcome: `Unsafe welcome ${CONTROL_PROBE}`, + title: `Unsafe terminal title ${CONTROL_PROBE}`, + }, + beforeMount(session) { + appendUser(session, `Unsafe user ${CONTROL_PROBE}`) + appendAssistant(session, [ + { type: 'reasoning', text: `Unsafe reasoning ${CONTROL_PROBE}` }, + { type: 'text', text: `Unsafe assistant ${CONTROL_PROBE}` }, + ]) + appendToolCalls(session, [{ id: 'unsafe-1', name: 'unsafe', arguments: { value: CONTROL_PROBE } }]) + appendToolResult(session, 'unsafe-1', [{ type: 'text', text: `Unsafe fallback ${CONTROL_PROBE}` }]) + session.append('todo/write', { + todos: [{ content: `Unsafe todo ${CONTROL_PROBE}`, status: 'in_progress' }], + }) + session.append('context/message', { + content: [{ type: 'text', text: `Unsafe context ${CONTROL_PROBE}` }], + source: { kind: 'plugin', plugin: `unsafe-${CONTROL_PROBE}` }, + }, { surfaceOp: 'append' }) + session.append('prompt/blocked', { + content: [{ type: 'text', text: 'blocked' }], + source: { kind: 'user' }, + reason: `Unsafe policy ${CONTROL_PROBE}`, + }) + session.append('turn/end', { + turn: 7, + reason: { kind: 'error', step: 2, message: `Unsafe turn error ${CONTROL_PROBE}` }, + }) + }, + }, { columns: 100, rows: 34 }) + expect(harness.terminal.title).toContain(DISPLAYED_CONTROL_PROBE) + expect(harness.terminal.title).not.toContain('\u001b') + expect(harness.terminal.title).not.toContain('\u009b') + + const controller = new AbortController() + const beforeQuestion = harness.terminal.frames + const answer = harness.ctx.userInteraction.ask({ + questions: [{ + id: 'unsafe-question', + header: `Unsafe header ${CONTROL_PROBE}`, + question: `Unsafe question ${CONTROL_PROBE}`, + options: [{ label: `Unsafe option ${CONTROL_PROBE}`, description: `Unsafe detail ${CONTROL_PROBE}` }], + }], + signal: controller.signal, + }) + const rejected = expect(answer).rejects.toMatchObject({ code: 'ASK_ABORTED' }) + await harness.terminal.waitForFrame(beforeQuestion) + await renderAfter(harness, () => { + harness.ctx.emit('agent/error', harness.agent, 8, 3, new Error(`Unsafe live error ${CONTROL_PROBE}`)) + }) + await checkpoint('untrusted-controls', harness.terminal, { includeScrollback: true }) + + controller.abort() + await rejected + await disposeSnapshot(harness) + }) + it('pins a constrained multi-select question and its validation state', async () => { const harness = await setupSnapshot({ config: { diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index 5fc11cbe40..94a2447d5f 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -856,8 +856,8 @@ describe('terminal mounting', () => { ctx.agents.reportStartFailure(AgentId('other'), new Error('other failed')) expect(terminal.output).toBe('') expect(exit).not.toHaveBeenCalled() - ctx.agents.reportStartFailure(AgentId('main'), new Error('resume failed')) - expect(terminal.output).toBe('ui-tui: agent "main" failed to start: resume failed\n') + ctx.agents.reportStartFailure(AgentId('main'), new Error('resume \u001b]2;failure-controlled\u0007')) + expect(terminal.output).toBe('ui-tui: agent "main" failed to start: resume \\x1b]2;failure-controlled\\x07\n') expect(exit).toHaveBeenCalledWith(1) const session = ctx.sessions.create(SessionId('must-not-start')) From e8ea0c3b7e021789aca0aaa4201998b6a1958bd3 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 10:51:20 +0800 Subject: [PATCH 201/323] test(tui): make cwd coverage location-independent formatCwd has distinct branches for the home directory itself, a descendant of home, an unset cwd, and a path outside home. The descendant branch was exercised only indirectly because the test harness defaulted to process.cwd(), so the per-file coverage gate changed with the checkout location and failed in detached worktrees under /private/tmp even though every behavior assertion passed. Derive the home-root case from homedir() and add an explicit synthetic child with platform-aware path joins. Keep the unset and outside-home cases unchanged. The suite now drives every formatting branch regardless of where the repository is checked out, and the expected child form follows the host path separator on macOS, Linux, and Windows. --- packages/ui/tui/tests/tui.spec.ts | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/packages/ui/tui/tests/tui.spec.ts b/packages/ui/tui/tests/tui.spec.ts index 94a2447d5f..96f03647be 100644 --- a/packages/ui/tui/tests/tui.spec.ts +++ b/packages/ui/tui/tests/tui.spec.ts @@ -1,3 +1,5 @@ +import { homedir } from 'node:os' +import { join } from 'node:path' import { describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import type { Terminal } from '@earendil-works/pi-tui' @@ -341,8 +343,9 @@ describe('pi-tui chat lifecycle and transcript', () => { }) it('formats large token totals and cwd variants', async () => { + const home = homedir() const homeResult = await setup({ - cwd: process.env.HOME ?? process.cwd(), + cwd: home, beforeMount(session) { appendAssistant(session, [{ type: 'text', text: 'home' }], { inputTokens: 25_000, outputTokens: 10_000 }) }, @@ -350,6 +353,10 @@ describe('pi-tui chat lifecycle and transcript', () => { expect(homeResult.terminal.output).toContain('~ ↑25k ↓10k') await dispose(homeResult) + const childResult = await setup({ cwd: join(home, 'projects', 'dsh-tui') }) + expect(childResult.terminal.output).toContain(join('~', 'projects', 'dsh-tui')) + await dispose(childResult) + const unsetResult = await setup({ cwd: null }) expect(unsetResult.terminal.output).toContain('cwd unset') await dispose(unsetResult) From 89416002736122864b0eb1530350ad78ef090b26 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 10:59:23 +0800 Subject: [PATCH 202/323] docs: expand simplification RFC implementation plans --- .../2026-07-19-make-jsonrpc-directional.i18n.yaml | 4 ++-- .../simplification/2026-07-19-make-jsonrpc-directional.md | 8 ++++++++ .../2026-07-19-make-jsonrpc-directional.zh.md | 8 ++++++++ .../2026-07-19-use-one-session-surface-manager.i18n.yaml | 4 ++-- .../2026-07-19-use-one-session-surface-manager.md | 8 ++++++++ .../2026-07-19-use-one-session-surface-manager.zh.md | 8 ++++++++ 6 files changed, 36 insertions(+), 4 deletions(-) diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml index b515d611f5..e04aed96a6 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-make-jsonrpc-directional.md: 4531cb251c4d12c9f2d700c9297bdee87e284779 -2026-07-19-make-jsonrpc-directional.zh.md: fb9bd06a9817357112b1eba2f41130ce2368d0b9 +2026-07-19-make-jsonrpc-directional.md: 2a9579c53c111887e9d93cf02cc832304a496795 +2026-07-19-make-jsonrpc-directional.zh.md: 4f3793f1b4de3b4f69c4219c10fe5b3b360c8692 diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md index 4531cb251c..2a9579c53c 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.md @@ -18,6 +18,14 @@ Specialize each endpoint to its actual role. The TypeScript transport will retai Return the settled outcome directly from `session/prompt` as `{ status, reason }` after `agent.whenIdle()`. Delete `session.finished`, the constant acceptance response, and the Python post-response completion loop. `session.event` and subagent notifications still stream before the response, and durable session events remain the source for final-response reconstruction. +## Implementation plan + +1. In `packages/ui/jsonrpc/src/server.ts`, replace `SessionPromptResult.accepted` with `status: 'ok' | 'error' | 'aborted'` and the captured `TurnEndReason`. `HarnessSdkServer.prompt()` will return `completed` as `ok`, `aborted` as `aborted`, and every other current or merge-extensible reason as `error`; reaching idle without a `turn/end` remains an invariant error. Remove only `session.finished`, leaving `session.event`, `subagent.started`, and `subagent.finished` unchanged. +2. In `packages/ui/jsonrpc/src/transport.ts`, replace `JsonRpcTransportPeer` with a server-side notification surface and retain `onRequest()`, `notify()`, `start()`, `flush()`, and `close()`. Remove generated request IDs, the pending-response map, outbound `request()`, inbound response and notification dispatch, and close-time pending-request rejection. Incoming response- and notification-shaped frames will be ignored, while request result, method-not-found, and handler-error responses retain their current behavior and remain ordered after notifications emitted by the awaited handler. +3. In `python/sdk/src/deepseek_harness/client.py`, `models.py`, and `__init__.py`, remove `IncomingRequest`, `_requests`, `notify()`, `next_request()`, `respond()`, and `respond_error()`. Add a public validated `SessionPromptResponse` carrying status and reason, return it from `session_prompt()`, and keep an explicit reader guard that ignores unexpected server-request frames instead of allowing them to match a response waiter. +4. In `python/sdk/src/deepseek_harness/api.py`, build `TurnResult.status` and a new `TurnResult.reason` from `SessionPromptResponse`, then delete the `session.finished` branch and second completion loop. Keep the subscription open during the request and preserve `_request_raw()`'s final notification drain so the last `turn/end` event and any subagent notification written before the response are collected before `Session.run()` reconstructs the final assistant message. +5. Replace the symmetric transport-pair cases in `packages/ui/jsonrpc/tests/transport.spec.ts` with raw client-input/server-output coverage, and update `server.spec.ts`, `plugin-apply.spec.ts`, and `built-scope-carrier.e2e.ts` for direct outcomes, ordering, overlap, shutdown, and the narrowed fake. Update `python/sdk/tests/test_client.py` for response-based settlement, unexpected-request-frame handling, callback and concurrency behavior, and the removed public helpers. Update the JSON-RPC and bilingual Python SDK READMEs, export JSDoc and declarations, `scripts/smoke-python-runtime.py`, and the Python single-executable snapshot. + ## Alternatives considered **Keep a generic symmetric JSON-RPC peer for future methods.** Server-initiated requests may eventually support interactive permissions, but no typed method or production consumer exists. The pre-release protocol can add the smallest required direction when that feature is designed instead of carrying an unexercised peer today. diff --git a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md index fb9bd06a98..4f3793f1b4 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md +++ b/docs/rfc/proposed/simplification/2026-07-19-make-jsonrpc-directional.zh.md @@ -18,6 +18,14 @@ JSON-RPC 桥接层把两个端点都建模为对称的对等端，但实际协 在 `agent.whenIdle()` 完成后，由 `session/prompt` 直接返回 `{ status, reason }` 作为轮次结果。删除 `session.finished`、常量接纳响应以及 Python 中响应后的完成等待循环。`session.event` 与 subagent 通知仍在响应前流式发出，持久会话事件仍是最终响应重建的真源。 +## 实施计划 + +1. 在 `packages/ui/jsonrpc/src/server.ts` 中，用 `status: 'ok' | 'error' | 'aborted'` 和捕获的 `TurnEndReason` 替换 `SessionPromptResult.accepted`。`HarnessSdkServer.prompt()` 把 `completed` 映射为 `ok`，把 `aborted` 映射为 `aborted`，把其他当前或可合并扩展的原因映射为 `error`；进入空闲状态却没有 `turn/end` 仍视为不变量错误。只删除 `session.finished`，保持 `session.event`、`subagent.started` 和 `subagent.finished` 不变。 +2. 在 `packages/ui/jsonrpc/src/transport.ts` 中，用服务端通知接口替换 `JsonRpcTransportPeer`，并保留 `onRequest()`、`notify()`、`start()`、`flush()` 和 `close()`。删除生成的请求 ID、待处理响应表、出站 `request()`、入站响应与通知分发，以及关闭时对待处理请求的拒绝逻辑。入站响应结构和通知结构将被忽略；请求结果、方法不存在与处理器错误响应保持原有行为，并继续排在被等待处理器发出的通知之后。 +3. 在 `python/sdk/src/deepseek_harness/client.py`、`models.py` 和 `__init__.py` 中，删除 `IncomingRequest`、`_requests`、`notify()`、`next_request()`、`respond()` 和 `respond_error()`。新增公开且经过校验的 `SessionPromptResponse` 来携带状态与原因，由 `session_prompt()` 返回该对象，并保留明确的读取保护：忽略意外的服务端请求帧，避免它们命中响应等待器。 +4. 在 `python/sdk/src/deepseek_harness/api.py` 中，根据 `SessionPromptResponse` 构造 `TurnResult.status` 和新增的 `TurnResult.reason`，再删除 `session.finished` 分支与第二个完成循环。请求期间保持订阅打开，并保留 `_request_raw()` 最后的通知排空步骤，确保写在响应前的最后一条 `turn/end` 事件与任何 subagent 通知，都会在 `Session.run()` 重建最终助手消息之前被收集。 +5. 用原始客户端输入与服务端输出覆盖替换 `packages/ui/jsonrpc/tests/transport.spec.ts` 中的对称传输对用例，并更新 `server.spec.ts`、`plugin-apply.spec.ts` 和 `built-scope-carrier.e2e.ts`，覆盖直接结果、顺序、重叠、关闭和收窄后的伪实现。更新 `python/sdk/tests/test_client.py`，覆盖基于响应的结束流程、意外请求帧处理、回调与并发行为，以及已删除的公开辅助方法。同步更新 JSON-RPC README、双语 Python SDK README、导出 JSDoc 与声明、`scripts/smoke-python-runtime.py` 和 Python 单可执行文件快照。 + ## 备选方案 **为未来方法保留通用的对称 JSON-RPC 对等端。** 服务端发起的请求将来可能用于交互式权限，但当前没有类型化方法或生产消费方。该功能完成设计后，预发布协议可以增加所需的最小方向，无需提前保留未使用的对等端能力。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml index adee0c347d..185d7af4ac 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-use-one-session-surface-manager.md: f351c05cf5cb5d408aeb22c8c3e6ac5c575fc24a -2026-07-19-use-one-session-surface-manager.zh.md: 20c1f04f7b4197549f23145aa2c6015cd44f38cc +2026-07-19-use-one-session-surface-manager.md: 0e4fa14b21f5054e1ace425712506c5c060f2251 +2026-07-19-use-one-session-surface-manager.zh.md: 26126310eefaf56aa45efc428a54e65f0cf35947 diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md index f351c05cf5..0e4fa14b21 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md @@ -16,6 +16,14 @@ Keep one `SurfaceManager` per `Session`. Seed and append acceptance continue to Expose only the readonly surface contract from `Session.surface`; candidate validation remains owned by `Session`. Retain `foldSurface()` as the detached full-log replay function used by offline validation and reconstruction. +## Implementation plan + +1. In `packages/core/session/src/surface.ts`, export a structural `SessionSurface` contract containing only readonly `nodes` and `replaceGeneration`, and make `SurfaceManager` implement it. Re-export that type from `packages/core/session/src/index.ts` so `Session.surface` no longer exposes `validateNext()` through its declaration. +2. In `Session`, replace `surfaceValidator` and lazy `_surface` with one eagerly constructed `surfaceManager`. Route seed and append validation through that manager and return it from `get surface(): SessionSurface`; `deriveMessages()` will read the same nodes and generation. `validateNext()` may synchronize already committed log entries, but it must only plan the uncommitted candidate. The candidate reaches manager state after `log.push()` and the next delta synchronization, so rejection by surface validation or pre-commit `internal/dispatch` cannot leave phantom state. +3. Keep `foldSurface()` and the transition functions in `surface.ts` unchanged. Compile and exercise the direct consumers in `packages/compact/compact/src/tool-pairing.ts`, `packages/compact/compact-basic/src/region.ts`, and `packages/context/workspace-context/src/state.ts`; they continue to consume only nodes and replacement generation. +4. Extend `packages/core/session/tests/surface.spec.ts` to read the public view before an invalid candidate, prove that nodes and generation remain at the accepted prefix after rejection, append a later valid event, and compare every resulting prefix with `foldSurface()`. Add an `internal/dispatch` veto case and a type-level `SessionSurface` assertion in `session.spec.ts`, while retaining the seeded replay, delta-growth, replacement, generation, and derived-cache cases. +5. Run the request-reconstruction, compaction tool-pairing, compaction range, and workspace-context regression suites that consume the surface. In the implementation PR, update `packages/core/session/README.md`, `docs/core-data-structures/session.md`, the implemented session-surface RFC and its Chinese counterpart, the translation record, `scripts/type-equiv.manifest.json`, and the generated RFC index before moving this RFC pair to `implemented/`. + ## Alternatives considered **Keep acceptance and projection state separate.** Separate instances appear to isolate public reads from validation, but ordinary callers already receive borrowed surface state and cannot mutate it through the declared readonly contract. A cast that mutates the returned node array already corrupts derived history; duplicating the manager is not a sound runtime trust boundary. diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md index 20c1f04f7b..26126310ee 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md +++ b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md @@ -16,6 +16,14 @@ Status: proposed `Session.surface` 只公开只读表层契约，候选事件校验仍由 `Session` 负责。保留 `foldSurface()`，用于离线校验与重建时执行分离的完整日志回放。 +## 实施计划 + +1. 在 `packages/core/session/src/surface.ts` 中，导出结构化的 `SessionSurface` 契约，只包含只读的 `nodes` 与 `replaceGeneration`，并让 `SurfaceManager` 实现该契约。从 `packages/core/session/src/index.ts` 重新导出这个类型，使 `Session.surface` 的声明不再暴露 `validateNext()`。 +2. 在 `Session` 中，用一个主动创建的 `surfaceManager` 替换 `surfaceValidator` 与延迟创建的 `_surface`。种子事件与追加事件都通过该管理器校验，`get surface(): SessionSurface` 返回同一个对象，`deriveMessages()` 也读取同一份节点与代数。`validateNext()` 可以同步已提交的日志事件，但对尚未提交的候选事件只能制定变更计划。候选事件在 `log.push()` 之后、下一次增量同步时才进入管理器状态，因此表层校验拒绝或提交前 `internal/dispatch` 否决都不会留下虚假状态。 +3. 保持 `foldSurface()` 与 `surface.ts` 中的状态转换函数不变。编译并验证 `packages/compact/compact/src/tool-pairing.ts`、`packages/compact/compact-basic/src/region.ts` 和 `packages/context/workspace-context/src/state.ts` 中的直接消费方；它们仍然只读取节点与替换代数。 +4. 扩展 `packages/core/session/tests/surface.spec.ts`：先读取公共视图，再提交无效候选事件，证明拒绝后节点与代数仍停留在已接纳前缀；随后追加有效事件，并把每个结果前缀与 `foldSurface()` 比较。在 `session.spec.ts` 中新增 `internal/dispatch` 否决用例与类型层面的 `SessionSurface` 断言，同时保留种子回放、增量增长、替换、代数和派生缓存用例。 +5. 运行消费表层的请求重建、压缩工具配对、压缩范围与工作区上下文回归套件。在实现 PR 中，先更新 `packages/core/session/README.md`、`docs/core-data-structures/session.md`、已实现会话表层 RFC 及其中文对应文件、翻译记录、`scripts/type-equiv.manifest.json` 和生成的 RFC 索引，再把本 RFC 双语文件移入 `implemented/`。 + ## 备选方案 **继续分离接纳状态与投影视图。** 两个独立实例看似能够隔离公共读取和校验，但普通调用方目前取得的就是借用的表层状态，无法通过声明的只读契约修改它。通过类型断言修改返回的节点数组，本就会破坏派生历史；复制管理器并不能构成可靠的运行时信任边界。 From bca74015130ed89295d8d83f33979c491a637854 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 11:12:26 +0800 Subject: [PATCH 203/323] docs: retain rejected compaction RFC --- docs/rfc/INDEX.md | 1 + ...19-fold-compaction-package-split.i18n.yaml | 6 +++ ...026-07-19-fold-compaction-package-split.md | 37 +++++++++++++++++++ ...-07-19-fold-compaction-package-split.zh.md | 37 +++++++++++++++++++ 4 files changed, 81 insertions(+) create mode 100644 docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml create mode 100644 docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md create mode 100644 docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 4dc9b229ff..ec88f76c2d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -233,6 +233,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune the unimplemented subagent seam vocabulary](rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md) | 2026-07-04 | | [Collapse workflows to the exercised foreground core](rejected/simplification/2026-07-12-collapse-workflow-to-foreground-core.md) | 2026-07-12 | | [Prune unused skill registry surface](rejected/simplification/2026-07-12-prune-unused-skill-registry-surface.md) | 2026-07-12 | +| [Fold the single compaction backend into its service package](rejected/simplification/2026-07-19-fold-compaction-package-split.md) | 2026-07-19 | ### Architecture diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml new file mode 100644 index 0000000000..d2a15cc2c2 --- /dev/null +++ b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-19-fold-compaction-package-split.md: 7c7a2da85beb956f8d6c24f813fc33aa350b5c0e +2026-07-19-fold-compaction-package-split.zh.md: 37d75671d57226742608a525ea711b34780e65c6 diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md new file mode 100644 index 0000000000..7c7a2da85b --- /dev/null +++ b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.md @@ -0,0 +1,37 @@ +# RFC: Fold the single compaction backend into its service package + +Status: rejected — More compaction backends are planned, so the interface and basic implementation packages remain separate. + +English | [中文](2026-07-19-fold-compaction-package-split.zh.md) + +## Problem + +Compaction is split between `@deepseek-ai/dsh-compact`, which owns an abstract two-method service and shared types, and `@deepseek-ai/dsh-compact-basic`, which owns the only complete implementation. Shipped configurations load only the basic package, and no production package independently consumes the interface package except that implementation. + +The split adds a package manifest, README, project boundary, dependency edge, abstract forwarding class, generated catalog entries, and composition wiring without demonstrating backend substitution. The [capability-seam decision](../../implemented/architecture/2026-06-13-capability-seams.md) requires a real interface, implementation, and consumer rather than a preemptive split; the [compaction decision](../../implemented/feature/2026-06-18-compaction-capability-seam.md) records that its independent consumer was deferred. + +## Proposal + +Move the basic implementation into `@deepseek-ai/dsh-compact` and remove `@deepseek-ai/dsh-compact-basic`. Keep `ctx.compact`, `CompactionResult`, the shared transcript and tool-pairing helpers, the existing configuration, and the concrete compaction algorithm in one package. + +Preserve `summarize()` as a protected customization hook. A deployment-specific summarizer can subclass or intercept the existing LLM call without requiring a second capability package. Reintroduce an interface package only when a second complete backend and an independent consumer need substitution. + +Amend the implemented compaction decision and the [recallable-compaction proposal](../../proposed/feature/2026-07-06-recallable-compaction.md) if this proposal is accepted so package ownership has one durable description. + +## Alternatives considered + +**Keep the split because a remote or recall backend may arrive.** A possible future implementation does not justify the current package boundary. Recall adds a consumer of compaction results, not necessarily another implementation, and a remote summarizer can use the protected hook. + +**Move the implementation package name onto the interface package.** Keeping `compact-basic` as the surviving name would make the product service appear to be one optional backend. `compact` is the stable service identity already used by `ctx.compact` and is the clearer single-package owner. + +## Acceptance criteria + +- `@deepseek-ai/dsh-compact-basic` and its workspace/package metadata are removed. +- `@deepseek-ai/dsh-compact` owns the current configuration, plugin class, algorithm, types, events, and shared helpers. +- Existing deployments can load the surviving package with equivalent configuration and model-visible behavior. +- Automatic and manual compaction preserve cancellation, locking, token accounting, tool pairing, durable events, provenance, retry convergence, and transcript rendering. +- Loader composition, unit, runaway-turn, cancellation, snapshot, and real-model compaction tests pass; generated catalogs and module graphs are current. + +## Risks + +This is an intentional pre-release package-name contraction. Embedders loading `@deepseek-ai/dsh-compact-basic` must switch packages, and future backend substitution would require extracting a boundary again. The cost is acceptable only while one complete implementation exists; acceptance should be revisited if a second backend lands first. diff --git a/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md new file mode 100644 index 0000000000..37d75671d5 --- /dev/null +++ b/docs/rfc/rejected/simplification/2026-07-19-fold-compaction-package-split.zh.md @@ -0,0 +1,37 @@ +# RFC: 将唯一的压缩后端并入服务包 + +Status: rejected — 计划增加更多压缩后端，因此接口包与 basic 实现包继续分离。 + +[English](2026-07-19-fold-compaction-package-split.md) | 中文 + +## 问题 + +压缩（compaction）目前拆分在两个包中：`@deepseek-ai/dsh-compact` 拥有一个含两个方法的抽象服务和共享类型，`@deepseek-ai/dsh-compact-basic` 拥有唯一的完整实现。交付配置只加载 basic 包，除了该实现外，没有生产包独立消费接口包。 + +该拆分增加了一份包（package）manifest（元数据清单）、README、项目边界、依赖边、抽象转发类、生成目录项和组合接线，却没有体现后端替换需求。[能力服务边界决策](../../implemented/architecture/2026-06-13-capability-seams.md)要求接口、实现和消费方都必须真实存在，而不能预先拆分；[压缩决策](../../implemented/feature/2026-06-18-compaction-capability-seam.md)也记录了独立消费方仍被推迟。 + +## 提案 + +把 basic 实现移入 `@deepseek-ai/dsh-compact`，并删除 `@deepseek-ai/dsh-compact-basic`。`ctx.compact`、`CompactionResult`、共享 transcript（文本记录）和工具配对辅助方法、现有配置以及具体压缩算法都由一个包负责。 + +保留 `summarize()` 作为受保护的自定义钩子。部署专用的摘要器可以通过继承或拦截现有 LLM（大语言模型）调用完成定制，无需第二个能力包。只有在第二个完整后端与独立消费方确实需要替换实现时，才重新提取接口包。 + +如果本提案获准，应同步修订已实现的压缩决策与[可回忆压缩提案](../../proposed/feature/2026-07-06-recallable-compaction.md)，使包所有权只有一处持久说明。 + +## 备选方案 + +**为可能出现的远程或回忆后端保留拆分。** 一种可能的未来实现不足以支撑当前包边界。回忆功能会增加压缩结果的消费方，但不一定增加另一种实现；远程摘要器也可以使用受保护钩子。 + +**让接口包并入实现包名。** 如果保留 `compact-basic` 作为最终名称，产品服务会看起来像一个可选后端。`compact` 已经是 `ctx.compact` 使用的稳定服务标识，更适合作为单包所有者。 + +## 验收标准 + +- 删除 `@deepseek-ai/dsh-compact-basic` 及其工作区和包元数据。 +- `@deepseek-ai/dsh-compact` 拥有当前配置、插件类、算法、类型、事件和共享辅助方法。 +- 现有部署可以使用等效配置加载保留的包，模型可见行为不变。 +- 自动压缩和手动压缩保留取消、锁、token 用量、工具配对、持久事件、来源、重试收敛和 transcript 渲染行为。 +- Loader 组合、单元、失控轮次、取消、快照和真实模型压缩测试全部通过；生成目录与模块图保持最新。 + +## 风险 + +这是一项有意实施的预发布包名收缩。加载 `@deepseek-ai/dsh-compact-basic` 的嵌入方必须切换包，未来的后端替换也需要重新提取边界。只有在仍然只有一个完整实现时，这项代价才可接受；如果第二个后端先行落地，应重新评估是否接纳本提案。 From 765dfb217414295a81e0609fa704ba64316e52ee Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 11:36:07 +0800 Subject: [PATCH 204/323] refactor(session): use one surface manager --- docs/cordis-catalog/events.md | 8 +-- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/session.md | 13 ++++- docs/event-producer-consumer.md | 8 +-- docs/rfc/INDEX.md | 2 +- .../2026-06-18-session-surface.md | 4 +- ...-use-one-session-surface-manager.i18n.yaml | 4 +- ...6-07-19-use-one-session-surface-manager.md | 37 ++++++++++++++ ...7-19-use-one-session-surface-manager.zh.md | 37 ++++++++++++++ ...6-07-19-use-one-session-surface-manager.md | 43 ---------------- ...7-19-use-one-session-surface-manager.zh.md | 43 ---------------- .../compact-basic/tests/compact-basic.spec.ts | 2 +- packages/core/session/README.md | 3 +- packages/core/session/src/index.ts | 32 +++++------- packages/core/session/src/surface.ts | 10 +++- packages/core/session/tests/session.spec.ts | 51 ++++++++++++++++++- packages/core/session/tests/surface.spec.ts | 15 +++++- scripts/type-equiv.manifest.json | 1 + website/zh-CN/api/harness/events.md | 8 +-- website/zh-CN/api/harness/sessions.md | 18 +++---- 20 files changed, 201 insertions(+), 140 deletions(-) rename docs/rfc/{proposed => implemented}/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml (61%) create mode 100644 docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.md create mode 100644 docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 9e74c728ad..1fc8f99af8 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -257,7 +257,7 @@ Creation announcement during session publication. A synchronous throw vetoes and 'session/created'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:46`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/src/index.ts) ### `session/disposed` — emit @@ -267,7 +267,7 @@ Emitted once when an announced session leaves the store, including publication r 'session/disposed'(this: Scoped, session: Session): void ``` -Source: [`packages/core/session/src/index.ts:56`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/src/index.ts) ### `session/event` — emit @@ -279,7 +279,7 @@ Post-commit, fire-and-forget append feed. The listener snapshot resolves before Types: [SessionEvent](../core-data-structures/core.md) -Source: [`packages/core/session/src/index.ts:68`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/src/index.ts) ### `session/flush` — parallel @@ -289,7 +289,7 @@ Awaited parallel durability checkpoint: every listener runs and the caller await 'session/flush'(this: Scoped, session: Session): Promise | void ``` -Source: [`packages/core/session/src/index.ts:78`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/src/index.ts) ## `subagent/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 3b854a4312..dd637444f0 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -224,7 +224,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:585`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:577`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 0e882bae33..b0aa7d4fc5 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -194,9 +194,20 @@ Required for `SurfaceEventType` events — every message-producing event must de The same provenance distinction applies here: only `assistant/message` may carry a present empty `sourceEventSeqs`; omission does not assert that its source stream was empty. +### `SessionSurface` — the live readonly surface projection + +`Session.surface` returns the session's stable `SessionSurface` view. The same incremental manager validates append candidates before commit and advances this projection from committed events; callers can observe membership and replacement generation but cannot invoke validation. + +```ts type-equiv +export interface SessionSurface { + readonly nodes: readonly number[] + readonly replaceGeneration: number +} +``` + ### `SurfaceFoldReplacement` and `SurfaceFoldResult` — a complete surface replay -`foldSurface(events)` returns detached current event sequences together with the actual sequences shadowed by each declared replacement range. `SurfaceManager` uses the same transitions for its incremental cache without retaining replacement history. Its `replaceGeneration` increments for each replacement so incremental consumers can distinguish pure tail growth from a rewrite. +`foldSurface(events)` returns detached current event sequences together with the actual sequences shadowed by each declared replacement range. The live manager uses the same transitions without retaining replacement history. Its `replaceGeneration` increments for each committed replacement so incremental consumers can distinguish pure tail growth from a rewrite. ```ts type-equiv export interface SurfaceFoldReplacement { diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 655be6ecab..eaf56ee579 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -26,10 +26,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:53`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:40`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | -| `session/created` | `emit` | [`packages/core/session/src/index.ts:46`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | -| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | -| `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) | -| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | +| `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) | +| `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:112`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:86`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index ec88f76c2d..48774d96d7 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -23,7 +23,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Make JSON-RPC completion and transport directional](proposed/simplification/2026-07-19-make-jsonrpc-directional.md) | 2026-07-19 | | [Retire the standalone subagent mock package](proposed/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | -| [Use one surface manager per session](proposed/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | ### Architecture @@ -117,6 +116,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Drop unconsumed skill provider events](implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | | [Simplify session-log representation](implemented/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 | +| [Use one surface manager per session](implemented/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | ### Architecture diff --git a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md index 7c6c5b00d0..d639fe2917 100644 --- a/docs/rfc/implemented/architecture/2026-06-18-session-surface.md +++ b/docs/rfc/implemented/architecture/2026-06-18-session-surface.md @@ -31,7 +31,7 @@ export type SurfaceOp = ### SurfaceManager: delta-based, not full rebuild -A `SurfaceManager` class (private to `Session`) maintains one ordered `number[]` of event seqs. It tracks `_lastProcessedSeq` and processes only the new events since the last access rather than rescanning the entire log. Because the log is append-only, prior events never change; a seeded log is simply the initial suffix folded on first access. Replace locates its inclusive endpoints by array position and splices the replacement seq into that range; no link objects or seq-to-node map duplicate the order. +A `Session` owns one `SurfaceManager` that maintains an ordered `number[]` of event seqs. The manager validates each seed or append candidate without applying it before commit, then processes only committed events since its previous synchronization rather than rescanning the entire log. `Session.surface` exposes the same manager through the readonly `SessionSurface` contract, so acceptance, derived history, compaction, and workspace context share one incremental state. Replace locates its inclusive endpoints by array position and splices the replacement seq into that range; no second manager, link objects, or seq-to-node map duplicates the order. Delta processing is O(1) when no new events and O(new events) when new events arrive. @@ -60,7 +60,7 @@ Every surface-eligible event must carry `surfaceOp` or it would disappear from d ## Consequences -- **`packages/core/session`**: `surface.ts` (`SurfaceManager`) maintains one ordered seq array; `SurfaceOp`/`SurfaceIntent` and the top-level session-event fields record how entries join it. `append()` requires a `SurfaceIntent` for surface events, `deriveMessages()` walks the surface as the sole derivation path, and `repair.ts` emits surface-aware closers. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants). +- **`packages/core/session`**: `surface.ts` (`SurfaceManager`) maintains one ordered seq array for candidate acceptance and live projection; `SessionSurface` is its readonly public view. `SurfaceOp`/`SurfaceIntent` and the top-level session-event fields record how entries join it. `append()` requires a `SurfaceIntent` for surface events, `deriveMessages()` walks the surface as the sole derivation path, and `repair.ts` emits surface-aware closers. The seed constructor rejects a surface-eligible seed event missing its `surfaceOp` marker (see § Invariants). - **`packages/core/agent-loop`**: All surface-capable appends pass surface opts. Chunk seqs are collected for `assistant/message` provenance; `tool/call` seqs are captured for `tool/result` provenance. - **`packages/session-persistence/session-persistence-sqlite`**: Two new nullable TEXT columns (`source_event_seqs`, `surface_op`) on the `events` table; `SCHEMA_VERSION` bumped (bump-and-reject, no migration). - **`packages/support/invariants`**: Surface-related validation rules. diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml b/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml similarity index 61% rename from docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml rename to docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml index 185d7af4ac..55a113d22b 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml +++ b/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-use-one-session-surface-manager.md: 0e4fa14b21f5054e1ace425712506c5c060f2251 -2026-07-19-use-one-session-surface-manager.zh.md: 26126310eefaf56aa45efc428a54e65f0cf35947 +2026-07-19-use-one-session-surface-manager.md: 0c0fd70717ff4b49e8817e88592d0781d9ccbd09 +2026-07-19-use-one-session-surface-manager.zh.md: 6d11c9bb475b0ee5a568f96678d0251f1160dda3 diff --git a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.md b/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.md new file mode 100644 index 0000000000..0c0fd70717 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.md @@ -0,0 +1,37 @@ +# RFC: Use one surface manager per session + +Status: implemented + +English | [中文](2026-07-19-use-one-session-surface-manager.zh.md) + +## Problem + +`Session` maintained two `SurfaceManager` instances over the same append-only event log. One validated seed and append candidates, while a second lazy instance independently folded committed events for `session.surface`, derived messages, compaction, and workspace context. Once the public surface had been read, every later event advanced duplicate node and replacement-generation state without creating a separate authority or failure boundary. + +## Decision + +Each `Session` owns one eagerly constructed `SurfaceManager`. Seed and append acceptance call `validateNext()` on that manager before committing an event, and `session.surface` returns the same object through this readonly contract: + +```ts +export interface SessionSurface { + readonly nodes: readonly number[] + readonly replaceGeneration: number +} +``` + +Candidate validation remains atomic. `validateNext()` may synchronize committed log entries, but it only plans the uncommitted candidate. The candidate enters manager state after `log.push()` and the next delta synchronization, so surface validation failures and pre-commit `internal/dispatch` vetoes leave no phantom node or replacement generation. + +`foldSurface()` remains the detached full-log replay function for offline validation and reconstruction. It uses the same transitions and agrees with the live manager for every committed prefix without sharing mutable state. + +## Alternatives considered + +**Keep acceptance and projection state separate.** Separate instances appeared to isolate public reads from validation, but callers already receive borrowed surface state and the declared readonly contract prevents ordinary mutation. Duplicating the manager was not a runtime trust boundary. + +**Recompute the public surface from the full log on every access.** This removed duplicate cached state but gave up incremental derivation and made repeated request construction scale with complete session history. + +## Consequences + +- Acceptance, `session.surface`, derived messages, compaction, and workspace context observe one incremental state. +- `Session.surface` exposes no validation method, while its object identity and borrowed readonly node array remain stable. +- A hostile cast can still corrupt borrowed state; JavaScript callers that deliberately bypass the readonly contract remain outside the supported same-process boundary. +- Surface, seed, dispatch-veto, request-reconstruction, compaction, and workspace-context tests exercise the shared manager and detached replay paths. diff --git a/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md b/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md new file mode 100644 index 0000000000..6d11c9bb47 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-07-19-use-one-session-surface-manager.zh.md @@ -0,0 +1,37 @@ +# RFC: 每个会话只使用一个表层管理器 + +Status: implemented + +[English](2026-07-19-use-one-session-surface-manager.md) | 中文 + +## 问题 + +`Session` 曾针对同一份仅追加事件日志维护两个 `SurfaceManager` 实例。一个实例负责校验种子事件和追加候选事件，另一个延迟创建的实例则独立折叠已提交事件，供 `session.surface`、派生消息、压缩（compaction）和工作区上下文使用。一旦读取公共表层，之后的每个事件都会推进两份重复的节点状态与替换代数状态，却没有形成独立真源或失败边界。 + +## 决策 + +每个 `Session` 主动创建并只持有一个 `SurfaceManager`。种子事件与追加事件的接纳流程在提交事件之前调用该管理器的 `validateNext()`，`session.surface` 则通过以下只读契约返回同一个对象： + +```ts +export interface SessionSurface { + readonly nodes: readonly number[] + readonly replaceGeneration: number +} +``` + +候选事件校验仍保持原子性。`validateNext()` 可以同步已提交的日志事件，但对尚未提交的候选事件只制定变更计划。候选事件在 `log.push()` 之后、下一次增量同步时才进入管理器状态，因此表层校验失败或提交前 `internal/dispatch` 否决都不会留下虚假节点或替换代数。 + +`foldSurface()` 仍是离线校验与重建使用的分离式完整日志回放函数。它使用相同的状态转换，并且对每个已提交前缀都与活跃管理器一致，但不共享可变状态。 + +## 备选方案 + +**继续分离接纳状态与投影视图。** 两个独立实例看似能够隔离公共读取和校验，但调用方取得的本来就是借用的表层状态，声明的只读契约会阻止普通修改。复制管理器并不能构成运行时信任边界。 + +**每次读取都根据完整日志重新计算公共表层。** 该方案能消除重复缓存状态，但会放弃增量派生，使每次请求构造都随完整会话历史增长。 + +## 影响 + +- 接纳流程、`session.surface`、派生消息、压缩和工作区上下文观察同一份增量状态。 +- `Session.surface` 不暴露校验方法，同时保持对象标识和借用的只读节点数组稳定。 +- 恶意类型断言仍可破坏借用状态；刻意绕过只读契约的 JavaScript 调用方不属于受支持的同进程边界。 +- 表层、种子、调度否决、请求重建、压缩和工作区上下文测试覆盖共享管理器与分离回放路径。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md deleted file mode 100644 index 0e4fa14b21..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.md +++ /dev/null @@ -1,43 +0,0 @@ -# RFC: Use one surface manager per session - -Status: proposed - -English | [中文](2026-07-19-use-one-session-surface-manager.zh.md) - -## Problem - -`Session` maintains two `SurfaceManager` instances over the same append-only event log. `surfaceValidator` eagerly validates seed and append candidates, while the lazy `_surface` independently folds committed events for `session.surface`, derived messages, compaction, and workspace context. Once the public surface is read, every later event advances duplicate node and replacement-generation state. - -The [session surface decision](../../implemented/architecture/2026-06-18-session-surface.md) calls for one ordered surface and one representation to validate. The second manager does not create an independent authority or protect a different failure boundary; it repeats the canonical fold and gives the two views a state-drift opportunity. - -## Proposal - -Keep one `SurfaceManager` per `Session`. Seed and append acceptance continue to call `validateNext()` before committing an event, and the public surface view reads `nodes` and `replaceGeneration` from that same manager. - -Expose only the readonly surface contract from `Session.surface`; candidate validation remains owned by `Session`. Retain `foldSurface()` as the detached full-log replay function used by offline validation and reconstruction. - -## Implementation plan - -1. In `packages/core/session/src/surface.ts`, export a structural `SessionSurface` contract containing only readonly `nodes` and `replaceGeneration`, and make `SurfaceManager` implement it. Re-export that type from `packages/core/session/src/index.ts` so `Session.surface` no longer exposes `validateNext()` through its declaration. -2. In `Session`, replace `surfaceValidator` and lazy `_surface` with one eagerly constructed `surfaceManager`. Route seed and append validation through that manager and return it from `get surface(): SessionSurface`; `deriveMessages()` will read the same nodes and generation. `validateNext()` may synchronize already committed log entries, but it must only plan the uncommitted candidate. The candidate reaches manager state after `log.push()` and the next delta synchronization, so rejection by surface validation or pre-commit `internal/dispatch` cannot leave phantom state. -3. Keep `foldSurface()` and the transition functions in `surface.ts` unchanged. Compile and exercise the direct consumers in `packages/compact/compact/src/tool-pairing.ts`, `packages/compact/compact-basic/src/region.ts`, and `packages/context/workspace-context/src/state.ts`; they continue to consume only nodes and replacement generation. -4. Extend `packages/core/session/tests/surface.spec.ts` to read the public view before an invalid candidate, prove that nodes and generation remain at the accepted prefix after rejection, append a later valid event, and compare every resulting prefix with `foldSurface()`. Add an `internal/dispatch` veto case and a type-level `SessionSurface` assertion in `session.spec.ts`, while retaining the seeded replay, delta-growth, replacement, generation, and derived-cache cases. -5. Run the request-reconstruction, compaction tool-pairing, compaction range, and workspace-context regression suites that consume the surface. In the implementation PR, update `packages/core/session/README.md`, `docs/core-data-structures/session.md`, the implemented session-surface RFC and its Chinese counterpart, the translation record, `scripts/type-equiv.manifest.json`, and the generated RFC index before moving this RFC pair to `implemented/`. - -## Alternatives considered - -**Keep acceptance and projection state separate.** Separate instances appear to isolate public reads from validation, but ordinary callers already receive borrowed surface state and cannot mutate it through the declared readonly contract. A cast that mutates the returned node array already corrupts derived history; duplicating the manager is not a sound runtime trust boundary. - -**Recompute the public surface from the full log on every access.** This removes cached duplicate state but gives up incremental derivation and makes repeated request construction scale with complete session history. - -## Acceptance criteria - -- A live `Session` owns exactly one incremental `SurfaceManager`. -- Seed and append candidates are validated before publication with no partial surface mutation on rejection. -- `session.surface`, derived messages, compaction, and workspace context observe the same nodes and replacement generation as the acceptance path. -- `foldSurface()` remains available for detached replay and agrees with the live manager for every accepted prefix. -- Session surface, seed, request reconstruction, compaction tool-pairing, and workspace-context tests pass. - -## Risks - -Sharing one manager makes the readonly borrowed-state contract more important because a hostile cast could corrupt both validation and projection state. The implementation should return a narrowed view and keep mutation methods inaccessible through `Session.surface`; JavaScript callers that deliberately bypass the type contract remain outside the supported same-process boundary. diff --git a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md b/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md deleted file mode 100644 index 26126310ee..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-use-one-session-surface-manager.zh.md +++ /dev/null @@ -1,43 +0,0 @@ -# RFC: 每个会话只使用一个表层管理器 - -Status: proposed - -[English](2026-07-19-use-one-session-surface-manager.md) | 中文 - -## 问题 - -`Session` 针对同一份仅追加事件日志维护两个 `SurfaceManager` 实例。`surfaceValidator` 主动校验种子事件与追加候选事件，延迟创建的 `_surface` 则独立折叠已提交事件，供 `session.surface`、派生消息、压缩（compaction）和工作区上下文使用。一旦读取公共表层，之后的每个事件都会推进两份重复的节点状态与替换代数状态。 - -[会话表层决策](../../implemented/architecture/2026-06-18-session-surface.md)要求系统只保留一个有序表层，并使用一种表示完成校验。第二个管理器既不形成独立真源，也不保护不同的失败边界；它只会重复规范折叠，并使两个视图可能出现状态偏差。 - -## 提案 - -每个 `Session` 只保留一个 `SurfaceManager`。种子事件与追加事件的接纳流程仍在提交事件之前调用 `validateNext()`，公共表层视图则从同一个管理器读取 `nodes` 与 `replaceGeneration`。 - -`Session.surface` 只公开只读表层契约，候选事件校验仍由 `Session` 负责。保留 `foldSurface()`，用于离线校验与重建时执行分离的完整日志回放。 - -## 实施计划 - -1. 在 `packages/core/session/src/surface.ts` 中，导出结构化的 `SessionSurface` 契约，只包含只读的 `nodes` 与 `replaceGeneration`，并让 `SurfaceManager` 实现该契约。从 `packages/core/session/src/index.ts` 重新导出这个类型，使 `Session.surface` 的声明不再暴露 `validateNext()`。 -2. 在 `Session` 中，用一个主动创建的 `surfaceManager` 替换 `surfaceValidator` 与延迟创建的 `_surface`。种子事件与追加事件都通过该管理器校验，`get surface(): SessionSurface` 返回同一个对象，`deriveMessages()` 也读取同一份节点与代数。`validateNext()` 可以同步已提交的日志事件，但对尚未提交的候选事件只能制定变更计划。候选事件在 `log.push()` 之后、下一次增量同步时才进入管理器状态，因此表层校验拒绝或提交前 `internal/dispatch` 否决都不会留下虚假状态。 -3. 保持 `foldSurface()` 与 `surface.ts` 中的状态转换函数不变。编译并验证 `packages/compact/compact/src/tool-pairing.ts`、`packages/compact/compact-basic/src/region.ts` 和 `packages/context/workspace-context/src/state.ts` 中的直接消费方；它们仍然只读取节点与替换代数。 -4. 扩展 `packages/core/session/tests/surface.spec.ts`：先读取公共视图，再提交无效候选事件，证明拒绝后节点与代数仍停留在已接纳前缀；随后追加有效事件，并把每个结果前缀与 `foldSurface()` 比较。在 `session.spec.ts` 中新增 `internal/dispatch` 否决用例与类型层面的 `SessionSurface` 断言，同时保留种子回放、增量增长、替换、代数和派生缓存用例。 -5. 运行消费表层的请求重建、压缩工具配对、压缩范围与工作区上下文回归套件。在实现 PR 中，先更新 `packages/core/session/README.md`、`docs/core-data-structures/session.md`、已实现会话表层 RFC 及其中文对应文件、翻译记录、`scripts/type-equiv.manifest.json` 和生成的 RFC 索引，再把本 RFC 双语文件移入 `implemented/`。 - -## 备选方案 - -**继续分离接纳状态与投影视图。** 两个独立实例看似能够隔离公共读取和校验，但普通调用方目前取得的就是借用的表层状态，无法通过声明的只读契约修改它。通过类型断言修改返回的节点数组，本就会破坏派生历史；复制管理器并不能构成可靠的运行时信任边界。 - -**每次读取都根据完整日志重新计算公共表层。** 该方案不再缓存重复状态，但会放弃增量派生，使每次请求构造都随完整会话历史增长。 - -## 验收标准 - -- 每个活跃 `Session` 只拥有一个增量 `SurfaceManager`。 -- 种子事件与追加候选事件都在发布前完成校验，拒绝事件时不会留下只修改一半的表层状态。 -- `session.surface`、派生消息、压缩和工作区上下文观察到的节点与替换代数，和接纳路径使用的状态完全一致。 -- `foldSurface()` 仍可用于分离回放，并且对任意已接纳前缀都与活跃管理器一致。 -- 会话表层、种子、请求重建、压缩工具配对和工作区上下文测试全部通过。 - -## 风险 - -共享一个管理器会提高只读借用状态契约的重要性，因为恶意类型断言可能同时破坏校验状态和投影视图。实现应返回收窄后的视图，避免通过 `Session.surface` 暴露修改方法；刻意绕过类型契约的 JavaScript 调用方不属于受支持的同进程边界。 diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index caaac783b6..01ce91a4e9 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -353,7 +353,7 @@ describe('compaction region transaction', () => { it('lands a framed, replayable checkpoint with exact pricing provenance', async () => { const compact = service() const session = conversation(3) - const before = session.surface.nodes + const before = [...session.surface.nodes] const result = await compact.compactRegion( before[0]!, before[3]!, diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 46b6ecb703..ba4e8ea94a 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -35,7 +35,7 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. - `session.append(type, data, opts?)` snapshots and freezes durable data and surface metadata, validates marker shape, provenance, and complete replacement coverage, commits synchronously, then notifies observers with independent failure containment. Reentrant attached-session appends reject, and runtime checks cover widened unions and loaded logs. - `session.deriveMessages()` incrementally projects each new surface entry once and returns a fresh array over shared frozen messages. Assistant projections preserve provider/model provenance and adapter-private replay state. A surface rewrite rebuilds the projection; there is no raw-log fallback. - `session.deriveEventMessage(event)` is the canonical per-event projection used by reconstruction and invariants. -- `session.surface` lazily folds only new `surfaceOp` markers; `replaceGeneration` changes on every rewrite. +- `session.surface` exposes the readonly `SessionSurface` view owned by the session's single incremental surface manager; `replaceGeneration` changes on every committed rewrite. - `session.events` is a cached frozen snapshot invalidated by append; accepted events remain deeply frozen. - `session.seq`, `session.id` — current sequence and readonly typed identity. - `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`. @@ -48,6 +48,7 @@ Durable values need one accepted representation, not a check followed by a secon - `SurfaceOp` — how an event entered the ordered surface: `'append'` (normal tail append) or `{ op: 'replace', start, end }` (replace entries from `start` through `end` inclusive — both must be valid surface seqs; `start === end` replaces one entry). Used by compaction to shadow old events without deleting them. - `SurfaceIntent` — `{ surfaceOp: SurfaceOp; sourceEventSeqs?: number[] }`, the required third parameter to `session.append()` for surface-eligible types. +- `SessionSurface` — the readonly live `nodes` and `replaceGeneration` projection exposed by `session.surface`; candidate validation remains private to `Session`. - `foldSurface(events)` — replay the canonical surface contract into detached current event sequences and actual replacement ranges. The same pass rejects non-contiguous seqs, misplaced or malformed metadata, empty or duplicate provenance, non-earlier sources, invalid positional ranges, and replacements that fail to cite every shadowed surface entry; `SurfaceManager` shares the atomic transition while retaining only its incremental sequence cache. - `isSurfaceEvent(event)` / `isSurfaceEligibleType(type)` — the first narrows a `SessionEvent` to a fully formed surface event; the second detects a surface-eligible event missing its marker when validating a seed or loaded log. diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index ef84a6bfbc..b8b76ec2ed 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -16,13 +16,14 @@ import { SESSION_FORMAT_VERSION, SessionId } from './types.ts' import type { ContextEnvelope, CreateSessionOptions, EpochHeader, SessionEvent, SessionEventMap, SessionEventType, SessionHeader, SurfaceIntent, SurfaceEventType } from './types.ts' import { snapshotJsonValue } from './json.ts' import { SurfaceManager } from './surface.ts' +import type { SessionSurface } from './surface.ts' import { foldRequestHeader } from './request-header.ts' export * from './types.ts' export { isJsonValue, snapshotJsonValue } from './json.ts' export type { JsonValue } from './json.ts' export { interruptedTurnClosers } from './repair.ts' -export type { SurfaceFoldReplacement, SurfaceFoldResult } from './surface.ts' +export type { SessionSurface, SurfaceFoldReplacement, SurfaceFoldResult } from './surface.ts' export { foldSurface, isSurfaceEvent, isSurfaceEligibleType } from './surface.ts' export { canonicalHeader, foldRequestHeader, headerEquals } from './request-header.ts' @@ -251,22 +252,12 @@ export function renderContextContent( */ export class Session { private log: SessionEvent[] = [] - /** Incremental acceptance state, kept separate from the public lazy view. */ - private readonly surfaceValidator = new SurfaceManager(this.log) - - /** - * Derived surface — a cached order of message-producing event sequences. - * Lazily rebuilt from `surfaceOp` markers in the log; processes only new - * events (delta) on each access — the log is append-only, so prior events - * never change. - * Undefined until first accessed (including after fork/seed). - */ - private _surface: SurfaceManager | undefined + /** Single incremental owner of surface acceptance and projection state. */ + private readonly surfaceManager = new SurfaceManager(this.log) /** The ordered surface over this session's event log. */ - get surface(): SurfaceManager { - if (!this._surface) this._surface = new SurfaceManager(this.log) - return this._surface + get surface(): SessionSurface { + return this.surfaceManager } /** @@ -309,7 +300,7 @@ export class Session { // live append and a full-log fold. The candidate is planned before it // enters `log`, so a failure cannot partially mutate the surface. try { - this.surfaceValidator.validateNext(snapshot) + this.surfaceManager.validateNext(snapshot) } catch (error: unknown) { throw new Error(`invalid seed event at index ${index}: ${error instanceof Error ? error.message : 'invalid surface metadata'}`) } @@ -402,7 +393,7 @@ export class Session { data: dataSnapshot, ...(surfaceMetadataSnapshot as { surfaceOp?: unknown; sourceEventSeqs?: unknown }), } as unknown as SessionEvent) - this.surfaceValidator.validateNext(event as SessionEvent) + this.surfaceManager.validateNext(event as SessionEvent) if (entry !== undefined) entry.appending = true try { @@ -468,7 +459,7 @@ export class Session { * * CACHED: each surface node is projected exactly once, when first seen — a * call costs O(new nodes), and a surface rewrite (a `replace`; - * {@link SurfaceManager.replaceGeneration}) rebuilds. The returned array is + * {@link SessionSurface.replaceGeneration}) rebuilds. The returned array is * a fresh snapshot per call (later appends never grow an array a caller * already holds); the `Message` objects in it are SHARED and **deep-frozen**. * Their content reuses the already frozen durable event data, so the cache @@ -476,8 +467,9 @@ export class Session { * @returns a fresh array of the shared, frozen derived history. */ deriveMessages(): Message[] { - const nodes = this.surface.nodes - const generation = this.surface.replaceGeneration + const surface = this.surface + const nodes = surface.nodes + const generation = surface.replaceGeneration if (generation !== this.derivedGeneration) { this.derived = [] this.derivedNodes = 0 diff --git a/packages/core/session/src/surface.ts b/packages/core/session/src/surface.ts index d4f43bc303..cf03ae685d 100644 --- a/packages/core/session/src/surface.ts +++ b/packages/core/session/src/surface.ts @@ -55,6 +55,14 @@ export interface SurfaceFoldResult { replacements: SurfaceFoldReplacement[] } +/** Readonly live projection of the message-producing session events. */ +export interface SessionSurface { + /** Current surface event sequences in model-visible order. */ + readonly nodes: readonly number[] + /** Monotonic count of committed positional replacements. */ + readonly replaceGeneration: number +} + /** Mutable state shared by complete and incremental folds. */ interface SurfaceFoldState { nodes: number[] @@ -244,7 +252,7 @@ export function foldSurface(events: readonly SessionEvent[]): SurfaceFoldResult } /** Incremental ordered surface view and append-boundary validator. */ -export class SurfaceManager { +export class SurfaceManager implements SessionSurface { /** Shared transition state; replacement history is not retained. */ private _state = createFoldState() /** Last processed seq; -1 folds a seeded log on first access. */ diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index 16a74283be..3b15157bde 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -1,10 +1,18 @@ -import { describe, expect, it, vi } from 'vitest' +import { describe, expect, expectTypeOf, it, vi } from 'vitest' import { Context } from 'cordis' import { CallId } from '@deepseek-ai/dsh-llm' import SessionStore, { SESSION_FORMAT_VERSION, Session, SessionEvent, SessionId } from '@deepseek-ai/dsh-session' -import type { CreateSessionOptions, SessionEventType, SessionHeader, TodoItem } from '@deepseek-ai/dsh-session' +import type { CreateSessionOptions, SessionEventType, SessionHeader, SessionSurface, TodoItem } from '@deepseek-ai/dsh-session' describe('Session', () => { + it('exposes one stable readonly surface view', () => { + const session = new Session(SessionId('surface-view')) + const surface = session.surface + + expectTypeOf(surface).toEqualTypeOf() + expect(surface).toBe(session.surface) + }) + it('derives message history from the event log', () => { const session = new Session(SessionId('s1')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -1031,6 +1039,45 @@ describe('SessionStore', () => { expect(observed).toEqual([appended]) }) + it('does not publish a surface transition rejected by internal dispatch', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const session = ctx.sessions.create(SessionId('surface-dispatch-veto')) + session.append('user/message', { + content: [{ type: 'text', text: 'source' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + const surface = session.surface + let reject = true + ctx.on('internal/dispatch', (_mode, name) => { + if (name === 'session/event' && reject) { + reject = false + throw new Error('reject surface candidate') + } + }) + + expect(() => session.append('assistant/message', { + provenance: { provider: 'mock', model: 'mock' }, + turn: 1, + step: 1, + content: [{ type: 'text', text: 'replacement' }], + }, { + surfaceOp: { op: 'replace', start: 0, end: 0 }, + sourceEventSeqs: [0], + })).toThrow('reject surface candidate') + + expect(session.events).toHaveLength(1) + expect(surface.nodes).toEqual([0]) + expect(surface.replaceGeneration).toBe(0) + + session.append('user/message', { + content: [{ type: 'text', text: 'next' }], + source: { kind: 'user' }, + }, { surfaceOp: 'append' }) + expect(surface.nodes).toEqual([0, 1]) + expect(surface.replaceGeneration).toBe(0) + }) + it('resolves session/event dispatch before commit so instrumentation failure cannot hide a logged event', async () => { const ctx = new Context() await ctx.plugin(SessionStore) diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index fe222f8f2f..d239533476 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -142,6 +142,11 @@ describe('SurfaceManager', () => { it('leaves incremental state unchanged when candidate validation fails', () => { const s = new Session(SessionId('atomic-validation')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) + const surface = s.surface + const nodes = surface.nodes + + expect(nodes).toEqual(foldSurface(s.events).nodes) + expect(surface.replaceGeneration).toBe(0) expect(() => s.append( 'assistant/message', @@ -150,8 +155,16 @@ describe('SurfaceManager', () => { )).toThrow(/missing 0/) expect(s.events).toHaveLength(1) + expect(s.surface).toBe(surface) + expect(surface.nodes).toEqual([0]) + expect(surface.replaceGeneration).toBe(0) + expect(surface.nodes).toEqual(foldSurface(s.events).nodes) + s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - expect(s.surface.nodes).toEqual([0, 1]) + expect(surface.nodes).toBe(nodes) + expect(surface.nodes).toEqual([0, 1]) + expect(surface.replaceGeneration).toBe(0) + expect(surface.nodes).toEqual(foldSurface(s.events).nodes) }) it('foldSurface rejects a surface-eligible event without its mandatory marker', () => { diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index c16245f7cf..cfa345ebdc 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -47,6 +47,7 @@ { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceEventType", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceOp", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceIntent", "source": "packages/core/session/src/types.ts" }, + { "doc": "docs/core-data-structures/session.md", "symbol": "SessionSurface", "source": "packages/core/session/src/surface.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceFoldReplacement", "source": "packages/core/session/src/surface.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceFoldResult", "source": "packages/core/session/src/surface.ts" }, diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index 976629fedb..8d494739ba 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -324,7 +324,7 @@ Creation announcement during session publication. A synchronous throw vetoes and - `session` — the session just entered and announced. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L46) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L47) ### session/disposed @@ -338,7 +338,7 @@ Emitted once when an announced session leaves the store, including publication r - `session` — the session that is no longer live in the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L56) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L57) ### session/event @@ -353,7 +353,7 @@ Post-commit, fire-and-forget append feed. The listener snapshot resolves before - `session` — the session whose log grew. - `event` — the appended event, exactly as recorded. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L68) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L69) ### session/flush @@ -367,7 +367,7 @@ Awaited parallel durability checkpoint: every listener runs and the caller await - `session` — the session whose buffered events must reach durable storage. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L78) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L79) ## subagent/* diff --git a/website/zh-CN/api/harness/sessions.md b/website/zh-CN/api/harness/sessions.md index e39006dd88..712852fc49 100644 --- a/website/zh-CN/api/harness/sessions.md +++ b/website/zh-CN/api/harness/sessions.md @@ -7,7 +7,7 @@ In-memory session store (`ctx.sessions`). Persistence is intentionally not implemented here — persistence plugins subscribe to `session/event` and flush on `session/flush` / dispose. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L585) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L577) ### ctx.sessions.create(id?, options?) @@ -23,7 +23,7 @@ For an agent whose session must be torn down IN ORDER with its loop (so the loop **Returns** the live session, already entered and announced. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L614) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L606) ### ctx.sessions.prepare(id?, options?) @@ -38,7 +38,7 @@ Build a session WITHOUT entering it into the store — validate the id/cwd and c **Returns** the constructed session, NOT yet in the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L643) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L635) ### ctx.sessions.enter(session) @@ -53,7 +53,7 @@ Re-checks the id for a duplicate: `prepare` and `enter` are public cross-package **Returns** the detach disposer (publication hooks + store removal). When called from a synchronous `session/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L687) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L679) ### ctx.sessions.announce(session) @@ -65,7 +65,7 @@ Emit `session/created` exactly once for an entered session (with the carrier ent - `session` — the entered session to announce to listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L742) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L734) ### ctx.sessions.flush(session) @@ -79,7 +79,7 @@ Dispatch the awaited `session/flush` durability checkpoint for `session`, with t **Returns** resolves when every flush listener has settled; after all settle, rejects with the first registered listener failure if any listener failed. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L794) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L786) ### ctx.sessions.get(id) @@ -93,7 +93,7 @@ Look up a live session. **Returns** the session, or undefined when no live session has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L826) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L818) ### ctx.sessions.list() @@ -105,7 +105,7 @@ All live sessions, in creation order. **Returns** a fresh array; mutating it does not affect the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L834) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L826) ### ctx.sessions.fork(source, boundary?, childSessionId?) @@ -121,4 +121,4 @@ Create a live child session from a turn-enclosed prefix of a live source. `bound **Returns** The created live child session. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L851) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L843) From 85fc58943e34a1d207cde9e2343ba80b9b5afb72 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 11:37:41 +0800 Subject: [PATCH 205/323] docs(session-persistence): tighten SQLite permission prose --- docs/config-catalog.md | 11 ++++++----- .../session-persistence-sqlite/README.md | 4 +++- .../session-persistence-sqlite/src/index.ts | 16 +++++++++------- .../tests/sqlite.spec.ts | 4 ++-- 4 files changed, 20 insertions(+), 15 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a442b5a197..6069263b8e 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -656,10 +656,11 @@ Requires: `sessions` export interface Config { /** * Filesystem path to the SQLite database file. The special value `:memory:` - * opens an in-process database (tests). Missing directories and the database - * are created with owner-only permissions; existing path modes are preserved. - * Parent directories writable by another principal are outside the backend's - * database-integrity boundary. + * opens an in-process database (tests). On filesystems with POSIX modes, + * missing directories and databases are created owner-only; existing path + * modes are preserved. Filesystem setup errors other than an existing database + * fail initialization. The backend does not protect integrity when another + * principal can replace the database entry in its parent directory. */ path: string /** @@ -682,7 +683,7 @@ export interface Config { export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' ``` -Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:53`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) +Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:54`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) ## `@deepseek-ai/dsh-session-query` diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index 17713dda8f..602bd4e33f 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -10,7 +10,9 @@ A SQLite durable session-persistence backend — a second `SessionPersistence` i Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, type, time, data, source_event_seqs, surface_op)` — `data` is the event payload as JSON text, so the row shape is the event verbatim (including `assistant/chunk`, keeping `seq` contiguous). The two `TEXT` columns `source_event_seqs` and `surface_op` are nullable; they store the event's optional surface-metadata fields (see [session surface](../../../docs/rfc/implemented/architecture/2026-06-18-session-surface.md)). Out-of-log metadata (`SessionHeader`) lives in a `sessions` row. A `sessions` row is written only by the first `append` — its existence is the lazy-materialization signal (`list` reports exactly the sessions that have a row), so no separate column is needed. -The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). On filesystems with POSIX modes, missing directories are created as `0700` and a missing database is exclusively created as `0600` before SQLite opens it, causing new WAL sidecars to inherit owner-only access. Existing directories, database files, and sidecars keep their modes; ordinary filesystem access errors still fail initialization. This default prevents incidental exposure through the process umask; it does not protect database integrity when another principal can modify entries in an existing parent directory. `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. +The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. + +On filesystems with POSIX modes, the backend creates missing directories as `0700` and exclusively creates a missing database as `0600` before SQLite opens it. New WAL sidecars receive the database's owner-only mode. Existing directories, database files, and sidecars keep their modes; filesystem setup errors other than an existing database fail initialization. These defaults prevent incidental exposure through the process umask, but do not protect database integrity when another principal can replace the database entry in its parent directory. ## Contract semantics over rows diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts index 4203f38a87..3515309f9a 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/index.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts @@ -36,9 +36,10 @@ function surfaceBindings(event: SessionEvent): [string | null, string | null] { } /** - * Create a missing database owner-only while preserving an existing file's - * mode. `DatabaseSync` cannot adopt this handle, so a parent directory writable - * by another principal is outside the backend's database-integrity boundary. + * Exclusively create a missing database file with owner-only permissions. + * Existing files retain their modes, and errors other than `EEXIST` propagate. + * `DatabaseSync` reopens by path, so this does not protect integrity when + * another principal can replace the database entry in its parent directory. */ async function createDatabaseFile(path: string): Promise { try { @@ -53,10 +54,11 @@ async function createDatabaseFile(path: string): Promise { export interface Config { /** * Filesystem path to the SQLite database file. The special value `:memory:` - * opens an in-process database (tests). Missing directories and the database - * are created with owner-only permissions; existing path modes are preserved. - * Parent directories writable by another principal are outside the backend's - * database-integrity boundary. + * opens an in-process database (tests). On filesystems with POSIX modes, + * missing directories and databases are created owner-only; existing path + * modes are preserved. Filesystem setup errors other than an existing database + * fail initialization. The backend does not protect integrity when another + * principal can replace the database entry in its parent directory. */ path: string /** diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index a07bcb7913..4a6b141e04 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -390,7 +390,7 @@ describe('SessionPersistenceSqlite: durability and crash semantics', () => { }) describe('SessionPersistenceSqlite: edge cases', () => { - it('creates a new database and WAL sidecars owner-only without changing an existing directory mode', async () => { + it('creates a new database and WAL sidecars with owner-only modes without changing its parent mode', async () => { if (process.platform === 'win32') return const path = await freshDbPath() const dir = dirname(path) @@ -421,7 +421,7 @@ describe('SessionPersistenceSqlite: edge cases', () => { await fiber.dispose() }) - it('surfaces database pre-creation errors independently of process privileges', async () => { + it('surfaces an invalid database path during pre-creation', async () => { const path = await freshDbPath() const b = await backend(`${path}\0`) From 176973cb7b618a82eec4d24f7497352ea5da4acc Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 11:51:22 +0800 Subject: [PATCH 206/323] docs(session-persistence): clarify SQLite permission limits --- docs/config-catalog.md | 7 ++++--- .../session-persistence-sqlite/README.md | 2 +- .../session-persistence-sqlite/src/index.ts | 10 ++++++---- 3 files changed, 11 insertions(+), 8 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 6069263b8e..05fa3eab67 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -659,8 +659,9 @@ export interface Config { * opens an in-process database (tests). On filesystems with POSIX modes, * missing directories and databases are created owner-only; existing path * modes are preserved. Filesystem setup errors other than an existing database - * fail initialization. The backend does not protect integrity when another - * principal can replace the database entry in its parent directory. + * fail initialization. The backend does not protect confidentiality or + * integrity when another principal can replace the database entry in its + * parent directory. */ path: string /** @@ -683,7 +684,7 @@ export interface Config { export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' ``` -Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:54`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) +Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:55`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) ## `@deepseek-ai/dsh-session-query` diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index 602bd4e33f..e9066d3748 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -12,7 +12,7 @@ Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. -On filesystems with POSIX modes, the backend creates missing directories as `0700` and exclusively creates a missing database as `0600` before SQLite opens it. New WAL sidecars receive the database's owner-only mode. Existing directories, database files, and sidecars keep their modes; filesystem setup errors other than an existing database fail initialization. These defaults prevent incidental exposure through the process umask, but do not protect database integrity when another principal can replace the database entry in its parent directory. +On filesystems with POSIX modes, the backend requests mode `0700` for missing directories and exclusively creates a missing database with mode `0600` before SQLite opens it; the process umask may further restrict both. New WAL sidecars receive the database's resulting owner-only mode. Existing directories, database files, and sidecars keep their modes; filesystem setup errors other than an existing database fail initialization. These defaults prevent incidental exposure through a permissive process umask, but do not protect database confidentiality or integrity when another principal can replace the database entry in its parent directory. ## Contract semantics over rows diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts index 3515309f9a..4661b41309 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/index.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts @@ -38,8 +38,9 @@ function surfaceBindings(event: SessionEvent): [string | null, string | null] { /** * Exclusively create a missing database file with owner-only permissions. * Existing files retain their modes, and errors other than `EEXIST` propagate. - * `DatabaseSync` reopens by path, so this does not protect integrity when - * another principal can replace the database entry in its parent directory. + * `DatabaseSync` reopens by path, so this does not protect confidentiality or + * integrity when another principal can replace the database entry in its parent + * directory. */ async function createDatabaseFile(path: string): Promise { try { @@ -57,8 +58,9 @@ export interface Config { * opens an in-process database (tests). On filesystems with POSIX modes, * missing directories and databases are created owner-only; existing path * modes are preserved. Filesystem setup errors other than an existing database - * fail initialization. The backend does not protect integrity when another - * principal can replace the database entry in its parent directory. + * fail initialization. The backend does not protect confidentiality or + * integrity when another principal can replace the database entry in its + * parent directory. */ path: string /** From 4dda5b953b5cb3b2de24e964c6f9da6a8c9e1911 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 11:54:37 +0800 Subject: [PATCH 207/323] refactor(subagent): retire standalone mock package --- docs/capability-seams.md | 4 +- docs/config-catalog.md | 35 ----- docs/module-graph.md | 6 - docs/rfc/INDEX.md | 2 +- .../2026-06-21-subagent-capability-seam.md | 5 +- ...-19-retire-subagent-mock-package.i18n.yaml | 4 +- ...2026-07-19-retire-subagent-mock-package.md | 34 +++++ ...6-07-19-retire-subagent-mock-package.zh.md | 34 +++++ ...2026-07-19-retire-subagent-mock-package.md | 35 ----- ...6-07-19-retire-subagent-mock-package.zh.md | 35 ----- ...prune-unimplemented-subagent-vocabulary.md | 6 +- packages/subagent/README.md | 2 +- packages/subagent/tool-subagent/package.json | 1 - .../tests/scripted-provider.spec.ts | 98 ++++++++++++++ .../tool-subagent/tests/scripted-provider.ts | 104 ++++++++++++++ .../tool-subagent/tests/tool-subagent.spec.ts | 31 +++-- packages/support/README.md | 3 +- packages/support/subagent-mock/README.md | 29 ---- packages/support/subagent-mock/package.json | 42 ------ packages/support/subagent-mock/src/index.ts | 127 ------------------ .../subagent-mock/tests/subagent-mock.spec.ts | 122 ----------------- packages/support/subagent-mock/tsconfig.json | 30 ----- pnpm-lock.yaml | 28 ---- scripts/gen-doc-graphs.ts | 2 +- scripts/gen-tool-catalog.ts | 18 ++- .../verify-package-readme-model-experience.ts | 1 - tsconfig.build.json | 1 - tsconfig.json | 1 - 28 files changed, 311 insertions(+), 529 deletions(-) rename docs/rfc/{proposed => implemented}/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml (62%) create mode 100644 docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.md create mode 100644 docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md delete mode 100644 docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md create mode 100644 packages/subagent/tool-subagent/tests/scripted-provider.spec.ts create mode 100644 packages/subagent/tool-subagent/tests/scripted-provider.ts delete mode 100644 packages/support/subagent-mock/README.md delete mode 100644 packages/support/subagent-mock/package.json delete mode 100644 packages/support/subagent-mock/src/index.ts delete mode 100644 packages/support/subagent-mock/tests/subagent-mock.spec.ts delete mode 100644 packages/support/subagent-mock/tsconfig.json diff --git a/docs/capability-seams.md b/docs/capability-seams.md index 1aafbb2817..03239998b8 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -77,7 +77,6 @@ flowchart LR pkg_subagent_spawn["subagent-spawn"] pkg_subagent_fork["subagent-fork"] pkg_subagent_acp["subagent-acp"] - pkg_subagent_mock["subagent-mock"] pkg_tasks["tasks"] svc_tasks["ctx.tasks
Background task registry"] pkg_tool_tasks["tool-tasks"] @@ -129,7 +128,6 @@ flowchart LR pkg_subagent --> svc_subagents pkg_subagent_acp --> svc_subagents pkg_subagent_fork --> svc_subagents - pkg_subagent_mock --> svc_subagents pkg_subagent_spawn --> svc_subagents pkg_system_prompt --> svc_systemPrompt pkg_tasks --> svc_tasks @@ -224,7 +222,7 @@ flowchart LR | `ctx.codeRuntime` | `seam` | [`code-runtime`](../packages/code-runtime/code-runtime) | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | [`tools`](../packages/core/tools) | - | Runs one model-written program against host-provided async bindings; backends differ by substrate and language (the tool registry consumes it for Code Mode). | | `ctx.fs` | `seam` | [`fs`](../packages/fs/fs) | [`fs-local`](../packages/fs/fs-local) | [`tool-fs`](../packages/fs/tool-fs) | [`fs-policy`](../packages/fs/fs-policy) | tool-fs executes read/write/edit through ctx.fs; fs-policy contributes observed-state checks through the fs/* event gate. | | `ctx.compact` | `seam` | [`compact`](../packages/compact/compact) | [`compact-basic`](../packages/compact/compact-basic) | [`compact-basic`](../packages/compact/compact-basic) | - | The basic backend currently consumes the pre-step event directly; a model-facing compact tool remains deferred. | -| `ctx.subagents` | `seam` | [`subagent`](../packages/subagent/subagent) | [`subagent-spawn`](../packages/subagent/subagent-spawn), [`subagent-fork`](../packages/subagent/subagent-fork), [`subagent-acp`](../packages/subagent/subagent-acp), [`subagent-mock`](../packages/support/subagent-mock) | [`tool-subagent`](../packages/subagent/tool-subagent) | - | Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name. | +| `ctx.subagents` | `seam` | [`subagent`](../packages/subagent/subagent) | [`subagent-spawn`](../packages/subagent/subagent-spawn), [`subagent-fork`](../packages/subagent/subagent-fork), [`subagent-acp`](../packages/subagent/subagent-acp) | [`tool-subagent`](../packages/subagent/tool-subagent) | - | Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name. | | `ctx.tasks` | `core` | [`tasks`](../packages/tasks/tasks) | - | [`tool-bash`](../packages/bash/tool-bash), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-tasks`](../packages/tasks/tool-tasks) | - | Producers (tool-bash background commands, tool-subagent background delegations) register running work; tool-tasks is the model-facing control surface that reads, lists, and kills it. | | `ctx.web` | `seam` | [`web`](../packages/web/web) | [`web-search-exa`](../packages/web/web-search-exa), [`web-search-perplexity`](../packages/web/web-search-perplexity), [`web-search-deepseek`](../packages/web/web-search-deepseek), [`web-fetch-local`](../packages/web/web-fetch-local) | [`tool-web`](../packages/web/tool-web) | - | Search and fetch providers register into one ctx.web seam; tool-web owns the stable model-facing names. | | `ctx.spillStore` | `seam` | [`spill`](../packages/spill/spill) | [`spill-local`](../packages/spill/spill-local) | [`spill-policy`](../packages/spill/spill-policy) | - | The backend saves oversized tool text and returns a model-facing locator plus retrieval hint; spill-policy is the tools/post-execute consumer that decides when to spill. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 30c448ba03..69704c2aa2 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -890,41 +890,6 @@ export interface Config { Source: [`packages/subagent/subagent-fork/src/index.ts:25`](../packages/subagent/subagent-fork/src/index.ts) -## `@deepseek-ai/dsh-subagent-mock` - -Requires: `subagents` - -```ts config-catalog -/** Config for the mock provider; all optional with test-friendly defaults. */ -export interface Config { - /** Registry name to register under. */ - name: string - /** The text the scripted child "returns" as its final answer. */ - reply?: string - /** The stop reason the run settles with. */ - stopReason?: SubagentStopReason - /** Which start-time capabilities to advertise (default: all `true`). */ - capabilities?: Partial - /** - * The conversation-history descriptor to declare - * ({@link SubagentProvider.inheritsParentContext}); default `false` (fresh - * conversation). Set `true` to exercise seeded/fork wording in consumer - * tests. This flag says nothing about tool, service, scope, or authority - * inheritance. - */ - inheritsParentContext?: boolean - /** - * Structured value surfaced when a request carries an `outputSchema` and the - * `outputSchema` capability is on (default: `{ reply }`). - */ - structured?: unknown -} -``` - -Depends on: [`SubagentCapabilities`](../packages/subagent/subagent/src/index.ts) · [`SubagentStopReason`](../packages/subagent/subagent/src/index.ts) - -Source: [`packages/support/subagent-mock/src/index.ts:87`](../packages/support/subagent-mock/src/index.ts) - ## `@deepseek-ai/dsh-subagent-spawn` Requires: `subagents` diff --git a/docs/module-graph.md b/docs/module-graph.md index f49092f99d..afd4004673 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -100,7 +100,6 @@ flowchart TD pkg_invariants["invariants"] pkg_llm_replay["llm-replay"] pkg_loader_smoke["loader-smoke"] - pkg_subagent_mock["subagent-mock"] end subgraph group_ui["packages/ui"] pkg_acp["acp"] @@ -368,10 +367,6 @@ flowchart TD pkg_hooks_claude --> pkg_session_persistence pkg_hooks_claude --> pkg_subagent pkg_hooks_claude --> pkg_tools - pkg_subagent_mock --> pkg_agent - pkg_subagent_mock --> pkg_llm - pkg_subagent_mock --> pkg_session - pkg_subagent_mock --> pkg_subagent pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek @@ -513,7 +508,6 @@ flowchart TD | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`home`](../packages/util/home), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index ec88f76c2d..25f7637361 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -22,7 +22,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; |---|---| | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Make JSON-RPC completion and transport directional](proposed/simplification/2026-07-19-make-jsonrpc-directional.md) | 2026-07-19 | -| [Retire the standalone subagent mock package](proposed/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | | [Use one surface manager per session](proposed/simplification/2026-07-19-use-one-session-surface-manager.md) | 2026-07-19 | ### Architecture @@ -117,6 +116,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Drop unconsumed skill provider events](implemented/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](implemented/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | | [Simplify session-log representation](implemented/simplification/2026-07-12-simplify-session-log-representation.md) | 2026-07-12 | +| [Retire the standalone subagent mock package](implemented/simplification/2026-07-19-retire-subagent-mock-package.md) | 2026-07-19 | ### Architecture diff --git a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md index 11824bcf63..3f44940848 100644 --- a/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md @@ -2,7 +2,7 @@ Status: implemented -> The full seam is shipped: the `dsh-subagent` interface, the `dsh-subagent-mock` test backend, and the `dsh-tool-subagent` consumer; the two in-process backends (`dsh-subagent-spawn`, `dsh-subagent-fork`); the nested-agent snapshot infrastructure ([per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md)); and the out-of-process `dsh-subagent-acp` backend ([its RFC](2026-06-22-acp-subagent-backend.md)). +> The full seam is shipped: the `dsh-subagent` interface and `dsh-tool-subagent` consumer; the two in-process backends (`dsh-subagent-spawn`, `dsh-subagent-fork`); the nested-agent snapshot infrastructure ([per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md)); and the out-of-process `dsh-subagent-acp` backend ([its RFC](2026-06-22-acp-subagent-backend.md)). ## Problem @@ -32,7 +32,6 @@ A new package group `packages/subagent/`: | `@deepseek-ai/dsh-subagent-spawn` | implementation: a fresh in-process child via `ctx.agents.create` | | `@deepseek-ai/dsh-subagent-fork` | implementation: an in-process child seeded with a snapshot of the parent's log | | `@deepseek-ai/dsh-subagent-acp` | implementation: an ACP client driving a configured child process | -| `@deepseek-ai/dsh-subagent-mock` | support: a scripted provider for testing the seam through the real load path | | `@deepseek-ai/dsh-tool-subagent` | consumer: the model-facing `subagent` tool over `ctx.subagents` | ### The primitive: async `start → SubagentRun` @@ -62,7 +61,7 @@ Each subagent runs in its **own `Session`** (own id, `parentSession` lineage), p ## Testing -The seam is tested through the real Cordis Loader/export path, which catches the export-shape failure described in [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md). Registry tests cover reload safety, duplicate names, and start-time capability rejection; nested-agent scenarios replay keylessly through [per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md); in-process backends also have real-loop unit tests and a with-key e2e. +Registry and tool tests replace only the nondeterministic child boundary with a package-local scripted provider while exercising the real `SubagentService`, lifecycle, task integration, and model-facing tool. Provider and consumer export shapes retain their Loader regression coverage for the failure described in [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md). Registry tests cover reload safety, duplicate names, and start-time capability rejection; nested-agent scenarios replay keylessly through [per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md); in-process backends also have real-loop unit tests and a with-key e2e. ## Consequences diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml b/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml similarity index 62% rename from docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml rename to docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml index 37c3c8b508..b86d9405e0 100644 --- a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml +++ b/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-19-retire-subagent-mock-package.md: 2731d35448cbc4dc9db4c92579c35202a53eefdd -2026-07-19-retire-subagent-mock-package.zh.md: 919c56502227157465277cc07c23fb7096763684 +2026-07-19-retire-subagent-mock-package.md: 47174d22eaf27c5a5509280793dd50d70c542d00 +2026-07-19-retire-subagent-mock-package.zh.md: bfad78e1912f9d5153196df3fea2494c88436a91 diff --git a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.md b/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.md new file mode 100644 index 0000000000..47174d22ea --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.md @@ -0,0 +1,34 @@ +# RFC: Retire the standalone subagent mock package + +Status: implemented + +English | [中文](2026-07-19-retire-subagent-mock-package.zh.md) + +## Problem + +`@deepseek-ai/dsh-subagent-mock` was a configurable test double packaged as a workspace plugin. Its only external consumers were the `tool-subagent` unit suite and the tool-catalog generator; no runtime package, example, snapshot configuration, or real provider loaded it. + +That narrow fixture carried a manifest, exports, peer and development dependencies, project references, package README obligations, Loader composition tests, module-graph membership, and documentation exceptions. The tool-catalog generator mounted it only to make production consumers register their schemas and never executed a child. + +## Decision + +The standalone package is deleted. Its scripted child behavior now lives in `packages/subagent/tool-subagent/tests/scripted-provider.ts`, where tests mount the real `SubagentService`, provider registry, tool implementation, and task runtime while replacing only the nondeterministic child boundary. + +The local fixture retains deterministic replies, structured results, stop reasons, cancellation before and after publication, conversation-inheritance descriptors, and effect-scoped disposal. Package-specific Schemastery and Loader-export tests disappear because the fixture is no longer a deployable plugin. + +The tool-catalog generator registers a minimal local `SubagentProvider` descriptor before mounting `ToolSubagent` or the workflow engine. The descriptor cannot start a child; it exists only to satisfy production load-time dependencies while harvesting schemas from the real consumers. + +Workspace project references, package dependencies, lockfile entries, graph metadata, support-package prose, config-catalog entries, and README gate exceptions no longer name the retired package. + +## Alternatives considered + +**Keep a reusable mock package for future tests.** Reuse never materialized outside one test file and one generator. A future second behavioral consumer can extract a shared fixture after its contract is known; pre-packaging it made test infrastructure look like a supported backend. + +**Generate subagent schemas without mounting production consumers.** Hand-constructing or importing schemas would weaken the catalog check that the real registry and tool composition expose the documented shape. A minimal provider descriptor preserves that check without carrying executable fake-backend behavior. + +## Consequences + +- The workspace has one fewer deployable package and no test-only node in the capability or module graphs. +- `tool-subagent` tests retain foreground, background-task, lifecycle, cancellation, reply, stop-reason, and structured-result coverage through production services. +- Tool-catalog output remains generated from production registrations and is byte-for-byte unchanged. +- Runtime and example packages gain no dependency on test fixtures. diff --git a/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md b/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md new file mode 100644 index 0000000000..bfad78e191 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-07-19-retire-subagent-mock-package.zh.md @@ -0,0 +1,34 @@ +# RFC: 撤销独立的 subagent mock 包 + +Status: implemented + +[English](2026-07-19-retire-subagent-mock-package.md) | 中文 + +## 问题 + +`@deepseek-ai/dsh-subagent-mock` 曾是一个以工作区插件形式发布的可配置测试替身。它仅有两个外部消费方：`tool-subagent` 单元测试和工具目录生成器；运行时包、示例、快照配置和真实提供方都不会加载它。 + +这个用途狭窄的 fixture（测试前置数据）需要维护 manifest（元数据清单）、导出、对等依赖（peer dependency）与开发依赖、项目引用、包（package）README 契约、Loader 组合测试、模块图成员关系以及文档例外。工具目录生成器挂载它，只是为了让生产消费方注册 schema，并不会执行子 agent。 + +## 决策 + +删除独立包。脚本化子 agent 行为现位于 `packages/subagent/tool-subagent/tests/scripted-provider.ts`；测试挂载真实的 `SubagentService`、提供方注册表、工具实现和任务运行时，只替换具有不确定性的子 agent 边界。 + +本地 fixture 保留确定性回复、结构化结果、停止原因、发布前后的取消、对话继承描述和作用域化的 dispose（资源释放）覆盖。由于 fixture 不再是可部署插件，删除包专用的 Schemastery 与 Loader 导出测试。 + +工具目录生成器在挂载 `ToolSubagent` 或工作流引擎之前，注册一个最小本地 `SubagentProvider` 描述。该描述无法启动子 agent；它只用于满足生产消费方的加载时依赖，同时从真实消费方提取 schema。 + +工作区项目引用、包依赖、锁文件条目、图元数据、支持包说明、配置目录条目和 README 门禁例外不再提及已撤销的包。 + +## 备选方案 + +**为未来测试保留可复用 mock 包。** 除一个测试文件和一个生成器外，复用需求始终没有出现。未来产生第二个行为消费方时，可以在共享契约明确后再提取 fixture；提前将其打包会使测试基础设施看起来像受支持的后端。 + +**不挂载生产消费方，直接生成 subagent schema。** 手工构造或直接导入 schema，会削弱目录门禁对真实注册表与工具组合是否公开文档结构的校验。最小提供方描述能保留该校验，而无需携带可执行的虚假后端行为。 + +## 影响 + +- 工作区减少一个可部署包，能力图与模块图也不再包含测试专用节点。 +- `tool-subagent` 测试继续通过生产服务覆盖前台、后台任务、生命周期、取消、回复、停止原因和结构化结果。 +- 工具目录输出仍根据生产注册生成，并保持字节级一致。 +- 运行时包与示例包都不会依赖测试 fixture。 diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md deleted file mode 100644 index 2731d35448..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.md +++ /dev/null @@ -1,35 +0,0 @@ -# RFC: Retire the standalone subagent mock package - -Status: proposed - -English | [中文](2026-07-19-retire-subagent-mock-package.zh.md) - -## Problem - -`@deepseek-ai/dsh-subagent-mock` is a configurable test double packaged as a workspace plugin. Its only external consumers are the `tool-subagent` unit suite and the tool-catalog generator. No runtime package, example, snapshot configuration, or real provider loads it. - -That narrow fixture carries a manifest, exports, peer and development dependencies, project references, package README obligations, Loader composition tests, module-graph membership, and documentation-gate exceptions. The tool-catalog generator mounts it only to make the real subagent tool register its schema; it never executes a child. - -## Proposal - -Delete `packages/support/subagent-mock`. Move the scripted provider behavior actually used by `tool-subagent` into a package-local test fixture while continuing to exercise the real `SubagentService`, provider registry, and tool implementation. - -Have the tool-catalog generator register the minimal provider descriptor required before mounting `ToolSubagent`. Remove the package references, manifest dependency, graph node, README allowlists, and mock-specific Loader tests. - -## Alternatives considered - -**Keep a reusable mock package for future tests.** Reuse has not materialized outside one test file and one generator. A future second consumer can extract a fixture once its shared contract is known; packaging all configurable reply, cancellation, result, and Loader behavior today makes test infrastructure look like a supported backend. - -**Generate the subagent schema without mounting the real tool.** Hand-constructing or importing the schema would weaken the catalog's check that the production registry and tool composition expose the documented shape. The generator should keep mounting the real service and tool with only the child boundary replaced. - -## Acceptance criteria - -- `packages/support/subagent-mock` and every workspace, graph, dependency, and documentation entry for it are removed. -- `tool-subagent` tests retain every scripted reply, structured-result, cancellation, foreground/background, and task-integration case they currently exercise through the real service and tool. -- Tool-catalog generation mounts the production subagent registry and tool with a minimal local provider and produces a byte-identical catalog. -- No runtime or example package gains a dependency on test-only fixtures. -- Focused subagent tests, catalog and graph generation, module-graph verification, build, hygiene, and the full pre-push suite pass. - -## Risks - -Relocating the fixture could accidentally replace too much production composition with a stub. The local fixture must implement only the nondeterministic child boundary; capability checks, lifecycle, task handling, and tool output remain under production code. Mock Loader and HMR coverage can disappear because no deployed composition consumes the package afterward. diff --git a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md b/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md deleted file mode 100644 index 919c565022..0000000000 --- a/docs/rfc/proposed/simplification/2026-07-19-retire-subagent-mock-package.zh.md +++ /dev/null @@ -1,35 +0,0 @@ -# RFC: 撤销独立的 subagent mock 包 - -Status: proposed - -[English](2026-07-19-retire-subagent-mock-package.md) | 中文 - -## 问题 - -`@deepseek-ai/dsh-subagent-mock` 是一个以工作区插件形式发布的可配置测试替身。它仅有两个外部消费方：`tool-subagent` 单元测试和工具目录生成器。运行时包、示例、快照配置和真实提供方都不会加载它。 - -这个用途狭窄的 fixture（测试前置数据）需要维护 manifest（元数据清单）、导出、对等依赖（peer dependency）与开发依赖、项目引用、包（package）README 契约、Loader 组合测试、模块图成员关系以及文档门禁例外。工具目录生成器挂载它，只是为了让真实 subagent 工具注册 schema；生成器从不执行子 agent。 - -## 提案 - -删除 `packages/support/subagent-mock`。把 `tool-subagent` 实际使用的脚本化提供方行为移入该包的本地测试 fixture，同时继续测试真实的 `SubagentService`、提供方注册表和工具实现。 - -工具目录生成器在挂载 `ToolSubagent` 前，只注册所需的最小提供方描述。删除该包的项目引用、manifest 依赖、图节点、README 允许列表和 mock 专用 Loader 测试。 - -## 备选方案 - -**为未来测试保留可复用 mock 包。** 除一个测试文件和一个生成器外，复用需求并未出现。未来产生第二个消费方时，可以在共享契约明确后再提取 fixture；当前把所有可配置回复、取消、结果与 Loader 行为打包，会使测试基础设施看起来像受支持的后端。 - -**不挂载真实工具，直接生成 subagent schema。** 手工构造或直接导入 schema，会削弱目录生成器对生产注册表与工具组合是否公开文档结构的校验。生成器应继续挂载真实服务与工具，只替换不确定的子 agent 边界。 - -## 验收标准 - -- 删除 `packages/support/subagent-mock`，并移除其全部工作区、图、依赖和文档条目。 -- `tool-subagent` 测试保留当前通过真实服务与工具覆盖的全部脚本化回复、结构化结果、取消、前台与后台运行以及任务集成用例。 -- 工具目录生成器使用最小本地提供方挂载生产 subagent 注册表与工具，并生成字节级一致的目录。 -- 运行时包与示例包都不会新增对测试专用 fixture 的依赖。 -- 聚焦 subagent 测试、目录与图生成、模块图校验、构建、hygiene 和完整 pre-push 门禁全部通过。 - -## 风险 - -迁移 fixture 时，可能会误将过多生产组合替换成测试替身。本地 fixture 只能实现不确定的 subagent 边界；能力检查、生命周期、任务处理与工具输出仍由生产代码负责。由于之后不再有部署组合消费该包，可以删除 mock 的 Loader 与 HMR 覆盖。 diff --git a/docs/rfc/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md b/docs/rfc/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md index 4c52d0b1a4..266a1d911d 100644 --- a/docs/rfc/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md +++ b/docs/rfc/rejected/simplification/2026-07-04-prune-unimplemented-subagent-vocabulary.md @@ -1,19 +1,19 @@ # RFC: Prune the unimplemented subagent seam vocabulary -Status: rejected — the deferred capability vocabulary (`outputSchema`/`structured`, `toolFilter`, `sendMessage`/`resume`) is intentionally reserved surface: the seam advertises the full intended contract ahead of its implementations by design, so providers and consumers grow into a stable shape rather than re-negotiating it per capability. The consumer-evidence analysis below stands as the record of what is currently unimplemented. +Status: rejected — the deferred capability vocabulary (`outputSchema`/`structured`, `toolFilter`, `sendMessage`/`resume`) is intentionally reserved surface: the seam advertises the full intended contract ahead of its implementations by design, so providers and consumers grow into a stable shape rather than re-negotiating it per capability. The consumer-evidence analysis below records the decision-time state. ## Problem The [subagent seam](../../implemented/feature/2026-06-21-subagent-capability-seam.md) shipped a two-tier capability design: start-time capability flags checked by the service, and optional runtime methods on `SubagentRun`. Three start-time features and both optional runtime methods have zero implementations and zero callers: -- **`outputSchema`/`structured` and `toolFilter`** (`SubagentCapabilities`, `SubagentStartRequest`, `SubagentResult` in `packages/subagent/subagent/src/types.ts`): every real provider declares `outputSchema: false, toolFilter: false` (`packages/subagent/subagent-spawn/src/index.ts`, `packages/subagent/subagent-fork/src/index.ts`, `packages/subagent/subagent-acp/src/index.ts`); the sole production `ctx.subagents.start` caller (`packages/subagent/tool-subagent/src/index.ts`) builds `{ prompt, parent, signal?, agentOptions? }` and structurally cannot set either; `structured` is produced only by the test mock (`packages/support/subagent-mock`) for its own spec. The service's capability check carries two assert rows whose only exercisers are the rejection tests. +- **`outputSchema`/`structured` and `toolFilter`** (`SubagentCapabilities`, `SubagentStartRequest`, `SubagentResult` in `packages/subagent/subagent/src/types.ts`): at the decision point, every real provider declared `outputSchema: false, toolFilter: false` (`packages/subagent/subagent-spawn/src/index.ts`, `packages/subagent/subagent-fork/src/index.ts`, `packages/subagent/subagent-acp/src/index.ts`); the sole production `ctx.subagents.start` caller (`packages/subagent/tool-subagent/src/index.ts`) built `{ prompt, parent, signal?, agentOptions? }` and structurally could not set either; `structured` appeared only in the scripted test fixture. The service's capability check carried two assert rows whose only exercisers were the rejection tests. - **`SubagentRun.sendMessage` / `SubagentRun.resume`** (same file): implemented by NO provider — not even the mock; the spawn spec asserts their *absence*. The only reason `dsh-subagent` depends on `dsh-tools` at all is `outputSchema`'s `SchemaSpec` type. Three subsequent subagent workstreams (per-session snapshot replay, the fork seed boundary, the ACP backend) landed around this surface without growing a single consumer. ## Proposal -Remove `outputSchema`/`structured`, `toolFilter`, `sendMessage`, and `resume` from the seam; shrink `SubagentCapabilities` to `{ depthLimit }`; drop the two capability-assert rows, the all-false flags on the three providers, the mock's structured branch and its `capabilities`/`structured` config knobs, and the tests that exist to pin the removed surface (the two rejection rows, the spawn absence test, the mock structured specs). Drop the `dsh-tools` peer/dev dependency from `packages/subagent/subagent/package.json`. Update the [subagent.md](../../../core-data-structures/subagent.md) pastes and the type-equiv manifest, and the README rows in `packages/subagent/subagent`, `packages/subagent/subagent-spawn`, `packages/subagent/subagent-fork`, and `packages/support/subagent-mock`. The implementing PR amends the seam RFC's capability catalog per [implemented/AGENTS.md](../../implemented/AGENTS.md). +Remove `outputSchema`/`structured`, `toolFilter`, `sendMessage`, and `resume` from the seam; shrink `SubagentCapabilities` to `{ depthLimit }`; drop the two capability-assert rows, the all-false flags on the three providers, the scripted fixture's structured branch and capability knobs, and the tests that exist to pin the removed surface. Drop the `dsh-tools` peer/dev dependency from `packages/subagent/subagent/package.json`. Update the [subagent.md](../../../core-data-structures/subagent.md) pastes and the type-equiv manifest, plus the affected provider READMEs. The implementing PR amends the seam RFC's capability catalog per [implemented/AGENTS.md](../../implemented/AGENTS.md). **Keep** `depthLimit`/`maxDepth` and capability checks. The in-process backend enforces the limit, although the shipping tool does not yet set it. Recursion is a known seam risk, so the appropriate follow-up is to supply a tool default rather than delete working enforcement. diff --git a/packages/subagent/README.md b/packages/subagent/README.md index 62de4ffb08..9935233e85 100644 --- a/packages/subagent/README.md +++ b/packages/subagent/README.md @@ -12,6 +12,6 @@ The subagent seam: an agent delegating work to a child agent. Like the [bash](.. | `subagent-acp/` | Out-of-process backend: a child agent in a spawned subprocess, driven over ACP | (registers on `ctx.subagents`) | | `tool-subagent/` | Model-facing `subagent` delegation tool over `ctx.subagents` | (registers on `ctx.tools`) | -The interface lives at `subagent/subagent/`. The in-process `subagent-spawn` / `subagent-fork` backends share the `subagent-inprocess` driver (a library with no provider of its own — both depend on it, neither on the other), the out-of-process `subagent-acp` backend builds on the `subagent-subprocess` library (the credential env scrub, the dispose ladder, isolated config dirs) and ships alongside them here; the test-only `dsh-subagent-mock` (in [support](../support/README.md)) is separate. All **product** packages except the mock. +The interface lives at `subagent/subagent/`. The in-process `subagent-spawn` / `subagent-fork` backends share the `subagent-inprocess` driver (a library with no provider of its own — both depend on it, neither on the other), and the out-of-process `subagent-acp` backend builds on the `subagent-subprocess` library (the credential env scrub, the dispose ladder, isolated config dirs). Tests replace only the child boundary with package-local fixtures. The proposal and design rationale: [docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md](../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md). diff --git a/packages/subagent/tool-subagent/package.json b/packages/subagent/tool-subagent/package.json index c52f5a74dc..e2d4378743 100644 --- a/packages/subagent/tool-subagent/package.json +++ b/packages/subagent/tool-subagent/package.json @@ -37,7 +37,6 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", - "@deepseek-ai/dsh-subagent-mock": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tasks": "workspace:^", "@deepseek-ai/dsh-tool-tasks": "workspace:^", diff --git a/packages/subagent/tool-subagent/tests/scripted-provider.spec.ts b/packages/subagent/tool-subagent/tests/scripted-provider.spec.ts new file mode 100644 index 0000000000..7365348410 --- /dev/null +++ b/packages/subagent/tool-subagent/tests/scripted-provider.spec.ts @@ -0,0 +1,98 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { type Agent } from '@deepseek-ai/dsh-agent' +import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' +import { SessionId } from '@deepseek-ai/dsh-session' +import * as scripted from './scripted-provider.ts' + +/** A minimal parent; the scripted provider only reads its id. */ +function fakeParent(id = 'parent-1'): Agent { + return { id: SessionId(id) } as unknown as Agent +} + +function baseRequest(over: Partial = {}): SubagentStartRequest { + return { + prompt: [{ type: 'text', text: 'task' }], + parent: fakeParent(), + signal: new AbortController().signal, + ...over, + } +} + +async function mount(config: Partial = {}): Promise { + const ctx = new Context() + await ctx.plugin(SubagentService) + await scripted.mountScriptedProvider(ctx, { name: 'mock', ...config }) + return ctx +} + +describe('scripted subagent provider fixture', () => { + it('registers through the real service and returns the scripted reply', async () => { + const ctx = await mount({ reply: 'hello from fixture' }) + expect(ctx.subagents.list()).toEqual(['mock']) + + const run = await ctx.subagents.start('mock', baseRequest()) + await expect(run.result).resolves.toEqual({ + output: [{ type: 'text', text: 'hello from fixture' }], + structured: undefined, + stopReason: 'completed', + }) + await run.dispose() + }) + + it('registers under a configurable name', async () => { + const ctx = await mount({ name: 'spawn' }) + expect(ctx.subagents.list()).toEqual(['spawn']) + }) + + it('returns configured and default structured results', async () => { + const configured = await mount({ reply: 'r', structured: { answer: 42 } }) + const schema = { type: 'object' as const, properties: { answer: { type: 'number' as const } } } + const configuredRun = await configured.subagents.start('mock', baseRequest({ outputSchema: schema })) + await expect(configuredRun.result).resolves.toMatchObject({ structured: { answer: 42 } }) + + const fallback = await mount({ reply: 'fallback reply' }) + const fallbackRun = await fallback.subagents.start('mock', baseRequest({ outputSchema: schema })) + await expect(fallbackRun.result).resolves.toMatchObject({ structured: { reply: 'fallback reply' } }) + }) + + it('omits structured output when no schema is requested', async () => { + const ctx = await mount({ capabilities: { outputSchema: false } }) + const run = await ctx.subagents.start('mock', baseRequest()) + expect(await run.result).not.toHaveProperty('structured') + }) + + it('honors configured and cancellation stop reasons', async () => { + const refused = await mount({ stopReason: 'refusal' }) + const refusedRun = await refused.subagents.start('mock', baseRequest()) + await expect(refusedRun.result).resolves.toMatchObject({ stopReason: 'refusal' }) + + const cancelled = await mount() + const controller = new AbortController() + const cancelledRun = await cancelled.subagents.start('mock', baseRequest({ signal: controller.signal })) + controller.abort() + await expect(cancelledRun.result).resolves.toMatchObject({ stopReason: 'aborted' }) + }) + + it('rejects cancellation before or during asynchronous publication', async () => { + const ctx = await mount() + const alreadyAborted = new AbortController() + alreadyAborted.abort() + await expect(ctx.subagents.start('mock', baseRequest({ signal: alreadyAborted.signal }))) + .rejects.toThrow('scripted subagent start aborted before publication') + + const handoff = new AbortController() + const pending = ctx.subagents.start('mock', baseRequest({ signal: handoff.signal })) + handoff.abort() + await expect(pending).rejects.toThrow('scripted subagent start aborted before publication') + }) + + it('unregisters with its owning fixture fiber', async () => { + const ctx = new Context() + await ctx.plugin(SubagentService) + const fiber = await scripted.mountScriptedProvider(ctx, { name: 'mock' }) + expect(ctx.subagents.list()).toEqual(['mock']) + await fiber.dispose() + expect(ctx.subagents.list()).toEqual([]) + }) +}) diff --git a/packages/subagent/tool-subagent/tests/scripted-provider.ts b/packages/subagent/tool-subagent/tests/scripted-provider.ts new file mode 100644 index 0000000000..01c0769cf8 --- /dev/null +++ b/packages/subagent/tool-subagent/tests/scripted-provider.ts @@ -0,0 +1,104 @@ +/** Package-local scripted child boundary for deterministic tool-subagent tests. */ + +import type { Context } from 'cordis' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' +import type { + SubagentCapabilities, + SubagentProvider, + SubagentResult, + SubagentRun, + SubagentStartRequest, + SubagentStopReason, +} from '@deepseek-ai/dsh-subagent' + +const DEFAULT_CAPABILITIES: SubagentCapabilities = { + outputSchema: true, + depthLimit: true, + toolFilter: true, + persona: true, +} + +/** Options for one scripted provider fixture. */ +export interface Config { + /** Registry name to register under. */ + name: string + /** Final text returned by the scripted child. */ + reply?: string + /** Terminal result reason. */ + stopReason?: SubagentStopReason + /** Start-time features advertised by the provider. */ + capabilities?: Partial + /** Whether tool descriptions say the child inherits completed turns. */ + inheritsParentContext?: boolean + /** Structured value returned when the request asks for one. */ + structured?: unknown +} + +/** Scripted provider whose result aborts if its signal or disposer wins first. */ +class ScriptedSubagentProvider implements SubagentProvider { + readonly capabilities: SubagentCapabilities + readonly inheritsParentContext: boolean + + constructor( + readonly name: string, + private readonly config: Config, + ) { + this.capabilities = { ...DEFAULT_CAPABILITIES, ...config.capabilities } + this.inheritsParentContext = config.inheritsParentContext ?? false + } + + async start(request: SubagentStartRequest): Promise { + if (request.signal.aborted) throw new Error('scripted subagent start aborted before publication') + const reply = this.config.reply ?? 'scripted subagent reply' + const output: ContentBlock[] = [{ type: 'text', text: reply }] + const wantsStructured = request.outputSchema !== undefined && this.capabilities.outputSchema + const stopReason = this.config.stopReason ?? 'completed' + const state = { cancelled: false } + const onAbort = (): void => { state.cancelled = true } + request.signal.addEventListener('abort', onAbort, { once: true }) + await Promise.resolve() + if (state.cancelled) { + request.signal.removeEventListener('abort', onAbort) + throw new Error('scripted subagent start aborted before publication') + } + + const resultFor = (): SubagentResult => ({ + output, + ...wantsStructured ? { structured: this.config.structured ?? { reply } } : {}, + stopReason: state.cancelled ? 'aborted' : stopReason, + }) + const result = new Promise((resolve) => { + setTimeout(() => { resolve(resultFor()) }, 0) + }).finally(() => { + request.signal.removeEventListener('abort', onAbort) + }) + + return { + id: SessionId(`scripted-subagent:${this.name}:${request.parent.id}`), + localAgent: undefined, + result, + dispose(): Promise { + state.cancelled = true + request.signal.removeEventListener('abort', onAbort) + return Promise.resolve() + }, + } + } +} + +/** + * Mount one scripted provider through an effect-scoped local plugin. + * @param ctx - context carrying the real subagent registry. + * @param config - scripted provider identity and outcome. + * @returns the fixture plugin's disposable fiber. + */ +export function mountScriptedProvider(ctx: Context, config: Config) { + return ctx.plugin({ + name: 'scripted-subagent-provider', + inject: ['subagents'], + apply(pluginCtx: Context): void { + pluginCtx.subagents.registerProvider(new ScriptedSubagentProvider(config.name, config)) + }, + }) +} diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 3bd42ae299..d88367ced5 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -9,18 +9,17 @@ import AgentRegistry from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' import TaskService from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' -import * as mock from '@deepseek-ai/dsh-subagent-mock' +import * as mock from './scripted-provider.ts' import * as tool from '../src/index.ts' import { runOutcome, settleRun } from '../src/index.ts' import { SessionId } from '@deepseek-ai/dsh-session' /** * Drives the REAL plugin body: mounts `dsh-tool-subagent` on a real - * `ToolRegistry` + `SubagentService`, with the real `dsh-subagent-mock` as the - * backend, and invokes the registered `subagent` tool through - * `ctx.tools.execute`. The mock is the genuine collaborator (we mock only the - * "child agent", the expensive/non-deterministic boundary) — everything - * downstream of the tool is the shipping code path. + * `ToolRegistry` + `SubagentService`, with a package-local scripted child + * boundary, and invokes the registered `subagent` tool through + * `ctx.tools.execute`. Everything downstream of the child boundary is the + * shipping code path. */ /** A minimal parent Agent — the tool reads `agent.id` for `parent`. */ @@ -33,7 +32,7 @@ async function setup(toolConfig: tool.Config, mockConfig: Partial = await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(SubagentService) - await ctx.plugin(mock, { name: 'mock', ...mockConfig }) + await mock.mountScriptedProvider(ctx, { name: 'mock', ...mockConfig }) await ctx.plugin(tool, toolConfig) return ctx } @@ -131,8 +130,8 @@ describe('dsh-tool-subagent', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(SubagentService) - await ctx.plugin(mock, { name: 'spawn', reply: 'from spawn' }) - await ctx.plugin(mock, { name: 'acp', reply: 'from acp' }) + await mock.mountScriptedProvider(ctx, { name: 'spawn', reply: 'from spawn' }) + await mock.mountScriptedProvider(ctx, { name: 'acp', reply: 'from acp' }) await ctx.plugin(tool, { provider: 'spawn', toolName: 'subagent' }) await ctx.plugin(tool, { provider: 'acp', toolName: 'subagent_acp' }) @@ -249,7 +248,7 @@ describe('dsh-tool-subagent', () => { tool.apply(ctx, { provider: 'mock' }) expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(false) // Backend arrives (as a delayed sibling fiber would): the tool appears. - await ctx.plugin(mock, { name: 'mock', reply: 'late but fine' }) + await mock.mountScriptedProvider(ctx, { name: 'mock', reply: 'late but fine' }) expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(true) const result = await callSubagent(ctx, { description: 'd', prompt: 'p' }) expect(text(result)).toBe('late but fine') @@ -260,7 +259,7 @@ describe('dsh-tool-subagent', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(SubagentService) - const backend = await ctx.plugin(mock, { name: 'mock' }) // fresh conversation (descriptor: false) + const backend = await mock.mountScriptedProvider(ctx, { name: 'mock' }) // fresh conversation (descriptor: false) await ctx.plugin(tool, { provider: 'mock' }) expect(ctx.tools.schemas().find(s => s.name === 'subagent')!.description).toContain('does not see this conversation') @@ -270,7 +269,7 @@ describe('dsh-tool-subagent', () => { // Backend reloads with a DIFFERENT conversation-history descriptor: the wording is re-derived // from the fresh provider, not served stale from the first mount. - await ctx.plugin(mock, { name: 'mock', inheritsParentContext: true }) + await mock.mountScriptedProvider(ctx, { name: 'mock', inheritsParentContext: true }) expect(ctx.tools.schemas().find(s => s.name === 'subagent')!.description).toContain('inherits this conversation') }) @@ -281,7 +280,7 @@ describe('dsh-tool-subagent', () => { await ctx.plugin(SubagentService) // Arm 1: a mounted tool dies with its plugin fiber; the provider survives. - await ctx.plugin(mock, { name: 'mock' }) + await mock.mountScriptedProvider(ctx, { name: 'mock' }) const mounted = await ctx.plugin(tool, { provider: 'mock' }) expect(ctx.tools.schemas().some(s => s.name === 'subagent')).toBe(true) await mounted.dispose() @@ -293,7 +292,7 @@ describe('dsh-tool-subagent', () => { // live plugin owns (the zombie mount). const waiting = await ctx.plugin(tool, { provider: 'later', toolName: 'subagent_later' }) await waiting.dispose() - await ctx.plugin(mock, { name: 'later' }) + await mock.mountScriptedProvider(ctx, { name: 'later' }) expect(ctx.tools.schemas().some(s => s.name === 'subagent_later')).toBe(false) }) @@ -302,11 +301,11 @@ describe('dsh-tool-subagent', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(SubagentService) - await ctx.plugin(mock, { name: 'mock' }) + await mock.mountScriptedProvider(ctx, { name: 'mock' }) await ctx.plugin(tool, { provider: 'mock' }) // An unrelated provider registering (added-event with another name) and // unregistering (removed-event with another name) must not touch the tool. - const other = await ctx.plugin(mock, { name: 'other', inheritsParentContext: true }) + const other = await mock.mountScriptedProvider(ctx, { name: 'other', inheritsParentContext: true }) expect(ctx.tools.schemas().filter(s => s.name === 'subagent')).toHaveLength(1) expect(ctx.tools.schemas().find(s => s.name === 'subagent')!.description).toContain('does not see this conversation') await other.dispose() diff --git a/packages/support/README.md b/packages/support/README.md index 0d991f07cf..433d6b3cdb 100644 --- a/packages/support/README.md +++ b/packages/support/README.md @@ -9,6 +9,5 @@ Packages that exist to serve development, testing, and the examples rather than | `invariants/` | Runtime event-contract assertions for development diagnostics | (listens on `session/*`, `agent/*`) | | `loader-smoke/` | Shared real-Loader subprocess harness for keyless example smokes | (library — imported by example e2e suites) | | `llm-replay/` | Record/replay adapter: short-circuits `llm/stream` from a recorded session JSONL (keyless snapshot tests) | (listens on `llm/stream`) | -| `subagent-mock/` | Scripted `SubagentProvider` for deterministic seam/tool tests | (registers on `ctx.subagents`) | -`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-spine-demo` bundle mounts it unconditionally. `agent-loop-testkit` centralizes the mandatory service spine for hand-built AgentLoop tests without owning their loop or scenario. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the ACP subprocess/client boundary plus the snapshot harness, normalizers, and suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. `subagent-mock` exercises the real `ctx.subagents` load path without a model or child agent. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. +`invariants` is development support but has no environment guard: it runs wherever registered, and the default `dsh-agent-spine-demo` bundle mounts it unconditionally. `agent-loop-testkit` centralizes the mandatory service spine for hand-built AgentLoop tests without owning their loop or scenario. `llm-replay` backs the demos and the snapshot test tier under the per-file coverage gate. `acp-snapshot` carries the ACP subprocess/client boundary plus the snapshot harness, normalizers, and suite machinery, while `loader-smoke` owns the parallel stdio/Loader process boundary used by keyless example e2e suites. A package graduates OUT of `support/` into a product group only when it gains documented product consumers. diff --git a/packages/support/subagent-mock/README.md b/packages/support/subagent-mock/README.md deleted file mode 100644 index a879433b67..0000000000 --- a/packages/support/subagent-mock/README.md +++ /dev/null @@ -1,29 +0,0 @@ -# @deepseek-ai/dsh-subagent-mock - -A scripted `SubagentProvider` for testing the [subagent seam](../../subagent/subagent/README.md) without a model or a real child agent — the subagent analog of [`dsh-llm-replay`](../llm-replay/README.md). - -It lets a test drive `ctx.subagents` and the model-facing `dsh-tool-subagent` through the real Cordis loader/export path, exercising provider registration, async start, start-time capability validation, required-signal cancellation, `result`, `dispose`, and structured output deterministically and keylessly. - -## Usage - -Load it as a plugin (functional shape: `name`/`inject`/`Config`/`apply`, no default). Config (all optional): - -| Key | Default | Meaning | -|---|---|---| -| `name` | `mock` | Registry name to register the provider under. | -| `reply` | `mock subagent reply` | The scripted child's final answer text. | -| `stopReason` | `completed` | The stop reason `result` settles with. | -| `capabilities` | all `true` | Which start-time capabilities (`outputSchema`, `depthLimit`, `toolFilter`, and `persona`) the provider advertises. | -| `inheritsParentContext` | `false` | Conversation-history descriptor: `false` means fresh, while `true` exercises seeded/fork wording. It says nothing about tool, service, scope, or authority inheritance. | -| `structured` | `{ reply }` | Structured value surfaced when a request carries an `outputSchema` and the capability is on. | - -Aborting the required request signal or disposing before `result` settles flips the stop reason to `aborted`, so both holder-facing cancellation paths are observable. - -## Model Experience - -Indirectly, through `dsh-tool-subagent`, which renders this test provider's configured reply or stop-reason error into the parent test history. - -## Known Limitations and Deferred Work - -- **Scripted provider only** — it does not run a model, create a child agent, or exercise real prompt/tool-loop behavior. -- **One synthetic outcome per run** — it models no multi-turn, streaming, steering, resume, or subprocess transport behavior. diff --git a/packages/support/subagent-mock/package.json b/packages/support/subagent-mock/package.json deleted file mode 100644 index c9d0982f55..0000000000 --- a/packages/support/subagent-mock/package.json +++ /dev/null @@ -1,42 +0,0 @@ -{ - "name": "@deepseek-ai/dsh-subagent-mock", - "description": "Scripted subagent provider for testing the subagent seam (keyless, deterministic)", - "version": "0.0.1", - "private": true, - "type": "module", - "main": "lib/index.js", - "types": "lib/types/index.d.ts", - "exports": { - ".": { - "types": "./lib/types/index.d.ts", - "default": "./lib/index.js" - }, - "./src/*": "./src/*", - "./package.json": "./package.json" - }, - "files": [ - "lib/index.js", - "lib/types/**/*.d.ts", - "lib/types/**/*.d.ts.map", - "src" - ], - "license": "BSD-3-Clause", - "peerDependencies": { - "@deepseek-ai/dsh-agent": "^0.0.1", - "@deepseek-ai/dsh-llm": "^0.0.1", - "@deepseek-ai/dsh-session": "^0.0.1", - "@deepseek-ai/dsh-subagent": "^0.0.1", - "cordis": "^4.0.0-rc.7" - }, - "dependencies": { - "schemastery": "^3.18.0" - }, - "devDependencies": { - "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-llm": "workspace:^", - "@deepseek-ai/dsh-session": "workspace:^", - "@deepseek-ai/dsh-subagent": "workspace:^", - "@cordisjs/plugin-loader": "^1.0.0-rc.5", - "cordis": "^4.0.0-rc.7" - } -} diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts deleted file mode 100644 index 4ea30d166a..0000000000 --- a/packages/support/subagent-mock/src/index.ts +++ /dev/null @@ -1,127 +0,0 @@ -/** - * Scripted, model-free subagent provider for deterministic coverage of registration, - * capability checks, lifecycle, the model-facing tool, and structured results through the real - * loader path. It is a named-export functional plugin; no default export. - * @module @deepseek-ai/dsh-subagent-mock - */ - -import type { Context } from 'cordis' -import z from 'schemastery' -import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import { SessionId } from '@deepseek-ai/dsh-session' -import type { - SubagentCapabilities, - SubagentProvider, - SubagentResult, - SubagentRun, - SubagentStartRequest, - SubagentStopReason, -} from '@deepseek-ai/dsh-subagent' - -const STOP_REASONS = ['completed', 'aborted', 'error', 'max-tokens', 'refusal'] as const - -const DEFAULT_CAPS: SubagentCapabilities = { outputSchema: true, depthLimit: true, toolFilter: true, persona: true } - -/** Scripted provider whose configured result aborts if disposed or signalled first. */ -class MockSubagentProvider implements SubagentProvider { - readonly capabilities: SubagentCapabilities - readonly inheritsParentContext: boolean - - constructor( - readonly name: string, - private readonly config: Config, - ) { - this.capabilities = { ...DEFAULT_CAPS, ...config.capabilities } - this.inheritsParentContext = config.inheritsParentContext ?? false - } - - async start(request: SubagentStartRequest): Promise { - if (request.signal.aborted) throw new Error('mock subagent start aborted before publication') - const reply = this.config.reply ?? 'mock subagent reply' - const output: ContentBlock[] = [{ type: 'text', text: reply }] - const wantsStructured = request.outputSchema !== undefined && this.capabilities.outputSchema - const baseStop: SubagentStopReason = this.config.stopReason ?? 'completed' - const flags = { cancelled: false } - const onAbort = (): void => { flags.cancelled = true } - request.signal.addEventListener('abort', onAbort, { once: true }) - // Make publication genuinely asynchronous so a same-turn abort is still - // a provider-owned startup failure rather than a returned live run. - await Promise.resolve() - if (flags.cancelled) { - request.signal.removeEventListener('abort', onAbort) - throw new Error('mock subagent start aborted before publication') - } - - // A deterministic child id derived from the parent — no clock/random (both - // banned in deterministic paths here, and unnecessary for a scripted run). - const id = SessionId(`mock-subagent:${this.name}:${request.parent.id}`) - - const resultFor = (): SubagentResult => ({ - output, - ...wantsStructured ? { structured: this.config.structured ?? { reply } } : {}, - stopReason: flags.cancelled ? 'aborted' : baseStop, - }) - - const result = new Promise((resolve) => { - setTimeout(() => { resolve(resultFor()) }, 0) - }).finally(() => { - request.signal.removeEventListener('abort', onAbort) - }) - return { - id, - localAgent: undefined, - result, - dispose(): Promise { - flags.cancelled = true - request.signal.removeEventListener('abort', onAbort) - return Promise.resolve() - }, - } - } -} - -export const name = 'subagent-mock' -export const inject = ['subagents'] - -/** Config for the mock provider; all optional with test-friendly defaults. */ -export interface Config { - /** Registry name to register under. */ - name: string - /** The text the scripted child "returns" as its final answer. */ - reply?: string - /** The stop reason the run settles with. */ - stopReason?: SubagentStopReason - /** Which start-time capabilities to advertise (default: all `true`). */ - capabilities?: Partial - /** - * The conversation-history descriptor to declare - * ({@link SubagentProvider.inheritsParentContext}); default `false` (fresh - * conversation). Set `true` to exercise seeded/fork wording in consumer - * tests. This flag says nothing about tool, service, scope, or authority - * inheritance. - */ - inheritsParentContext?: boolean - /** - * Structured value surfaced when a request carries an `outputSchema` and the - * `outputSchema` capability is on (default: `{ reply }`). - */ - structured?: unknown -} - -export const Config: z = z.object({ - name: z.string().default('mock'), - reply: z.string(), - stopReason: z.union(STOP_REASONS), - capabilities: z.object({ - outputSchema: z.boolean(), - depthLimit: z.boolean(), - toolFilter: z.boolean(), - persona: z.boolean(), - }), - inheritsParentContext: z.boolean(), - structured: z.any(), -}) - -export function apply(ctx: Context, config: Config): void { - ctx.subagents.registerProvider(new MockSubagentProvider(config.name, config)) -} diff --git a/packages/support/subagent-mock/tests/subagent-mock.spec.ts b/packages/support/subagent-mock/tests/subagent-mock.spec.ts deleted file mode 100644 index aec0fd7db1..0000000000 --- a/packages/support/subagent-mock/tests/subagent-mock.spec.ts +++ /dev/null @@ -1,122 +0,0 @@ -import { describe, expect, it } from 'vitest' -import { Context } from 'cordis' -import Loader from '@cordisjs/plugin-loader' -import { type Agent } from '@deepseek-ai/dsh-agent' - -import SubagentService, { type SubagentStartRequest } from '@deepseek-ai/dsh-subagent' -import * as mock from '../src/index.ts' -import { SessionId } from '@deepseek-ai/dsh-session' - -/** A minimal parent — the mock provider only reads `parent.id`. */ -function fakeParent(id = 'parent-1'): Agent { - return { id: SessionId(id) } as unknown as Agent -} - -function baseRequest(over: Partial = {}): SubagentStartRequest { - return { prompt: [{ type: 'text', text: 'task' }], parent: fakeParent(), signal: new AbortController().signal, ...over } -} - -async function mount(config: Partial = {}): Promise { - const ctx = new Context() - await ctx.plugin(SubagentService) - await ctx.plugin(mock, { name: 'mock', ...config }) - return ctx -} - -describe('dsh-subagent-mock', () => { - it('registers a provider on ctx.subagents and returns the scripted reply', async () => { - const ctx = await mount({ reply: 'hello from mock' }) - expect(ctx.subagents.list()).toEqual(['mock']) - - const run = await ctx.subagents.start('mock', baseRequest()) - await expect(run.result).resolves.toEqual({ - output: [{ type: 'text', text: 'hello from mock' }], - structured: undefined, - stopReason: 'completed', - }) - await run.dispose() - }) - - it('registers under a configurable name', async () => { - const ctx = await mount({ name: 'spawn' }) - expect(ctx.subagents.list()).toEqual(['spawn']) - }) - - it('surfaces a structured result when the request carries an outputSchema', async () => { - const ctx = await mount({ reply: 'r', structured: { answer: 42 } }) - const run = await ctx.subagents.start('mock', baseRequest({ outputSchema: { type: 'object', properties: { answer: { type: 'number' } } } })) - await expect(run.result).resolves.toMatchObject({ structured: { answer: 42 } }) - }) - - it('defaults structured output to { reply } when outputSchema is requested but no structured value is configured', async () => { - const ctx = await mount({ reply: 'fallback reply' }) - const run = await ctx.subagents.start('mock', baseRequest({ outputSchema: { type: 'object', properties: { answer: { type: 'number' } } } })) - await expect(run.result).resolves.toMatchObject({ structured: { reply: 'fallback reply' } }) - }) - - it('omits structured output when outputSchema capability is off', async () => { - const ctx = await mount({ capabilities: { outputSchema: false } }) - // The service rejects an outputSchema request against a no-cap provider, so - // the structured path is only reachable when the cap is on; with it off and - // no schema requested, the result has no structured field. - const run = await ctx.subagents.start('mock', baseRequest()) - const result = await run.result - expect(result).not.toHaveProperty('structured') - }) - - it('honors a configured stop reason', async () => { - const ctx = await mount({ stopReason: 'refusal' }) - const run = await ctx.subagents.start('mock', baseRequest()) - await expect(run.result).resolves.toMatchObject({ stopReason: 'refusal' }) - }) - - it('flips the stop reason to aborted when the signal fires before the result settles', async () => { - const ctx = await mount() - const controller = new AbortController() - const run = await ctx.subagents.start('mock', baseRequest({ signal: controller.signal })) - controller.abort() - await expect(run.result).resolves.toMatchObject({ stopReason: 'aborted' }) - }) - - it('rejects an already-aborted request before starting publication', async () => { - const ctx = await mount() - const controller = new AbortController() - controller.abort() - - await expect(ctx.subagents.start('mock', baseRequest({ signal: controller.signal }))) - .rejects.toThrow('mock subagent start aborted before publication') - }) - - it('rejects when cancellation wins the asynchronous publication handoff', async () => { - const ctx = await mount() - const controller = new AbortController() - const pending = ctx.subagents.start('mock', baseRequest({ signal: controller.signal })) - - controller.abort() - - await expect(pending).rejects.toThrow('mock subagent start aborted before publication') - }) - - it('unregisters the provider when the owning fiber is disposed (HMR safety)', async () => { - const ctx = new Context() - await ctx.plugin(SubagentService) - const fiber = await ctx.plugin(mock, { name: 'mock' }) - expect(ctx.subagents.list()).toEqual(['mock']) - await fiber.dispose() - expect(ctx.subagents.list()).toEqual([]) - }) - - it('has the namespace-plugin export shape (no stray default) so the Loader keeps name/inject/Config/apply', () => { - // A default export would make Loader unwrap only that value and drop `inject`. - expect('default' in mock).toBe(false) - expect(mock.name).toBe('subagent-mock') - expect(mock.inject).toEqual(['subagents']) - - const loader = Object.create(Loader.prototype) as Loader - const unwrapped = loader.unwrapExports(mock) as Record - expect(unwrapped).toBe(mock) - expect(unwrapped.name).toBe('subagent-mock') - expect(unwrapped.inject).toEqual(['subagents']) - expect(typeof unwrapped.apply).toBe('function') - }) -}) diff --git a/packages/support/subagent-mock/tsconfig.json b/packages/support/subagent-mock/tsconfig.json deleted file mode 100644 index ccc9fa45ed..0000000000 --- a/packages/support/subagent-mock/tsconfig.json +++ /dev/null @@ -1,30 +0,0 @@ -{ - "extends": "../../../tsconfig.base.json", - "compilerOptions": { - "rootDir": "src", - "outDir": "lib/types" - }, - "include": [ - "src" - ], - "references": [ - { - "path": "../../../vendor/cosmokit" - }, - { - "path": "../../../vendor/cordis" - }, - { - "path": "../../../vendor/schemastery" - }, - { - "path": "../../core/agent" - }, - { - "path": "../../llm/llm" - }, - { - "path": "../../subagent/subagent" - } - ] -} diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 47d998fedc..f67e60bd8f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1640,9 +1640,6 @@ importers: '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../subagent - '@deepseek-ai/dsh-subagent-mock': - specifier: workspace:^ - version: link:../../support/subagent-mock '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt @@ -1751,31 +1748,6 @@ importers: specifier: ^4.0.0-rc.6 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) - packages/support/subagent-mock: - dependencies: - schemastery: - specifier: ^3.18.0 - version: 3.18.0 - devDependencies: - '@cordisjs/plugin-loader': - specifier: ^1.0.0-rc.5 - version: 1.0.0-rc.5(cordis@4.0.0-rc.7)(node-addon-require-builtin@0.1.0) - '@deepseek-ai/dsh-agent': - specifier: workspace:^ - version: link:../../core/agent - '@deepseek-ai/dsh-llm': - specifier: workspace:^ - version: link:../../llm/llm - '@deepseek-ai/dsh-session': - specifier: workspace:^ - version: link:../../core/session - '@deepseek-ai/dsh-subagent': - specifier: workspace:^ - version: link:../../subagent/subagent - cordis: - specifier: ^4.0.0-rc.7 - version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) - packages/tasks/tasks: devDependencies: '@deepseek-ai/dsh-agent': diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index f6aaa6c2d9..5a4178bd56 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -245,7 +245,7 @@ const SERVICE_ROLES: ServiceRole[] = [ pkg: 'subagent', title: 'Subagent provider registry', mode: 'seam', - implementations: ['subagent-spawn', 'subagent-fork', 'subagent-acp', 'subagent-mock'], + implementations: ['subagent-spawn', 'subagent-fork', 'subagent-acp'], consumers: ['tool-subagent'], note: 'Providers implement transports; tool-subagent exposes one configured provider as a model-facing tool name.', }, diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index f178f70e9f..ca69768227 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -19,7 +19,7 @@ import WebService from '@deepseek-ai/dsh-web' import * as WebSearchExa from '@deepseek-ai/dsh-web-search-exa' import * as WebFetchLocal from '@deepseek-ai/dsh-web-fetch-local' import SubagentService from '@deepseek-ai/dsh-subagent' -import * as SubagentMock from '@deepseek-ai/dsh-subagent-mock' +import type { SubagentProvider } from '@deepseek-ai/dsh-subagent' import SkillService from '@deepseek-ai/dsh-skill' import * as SkillLocal from '@deepseek-ai/dsh-skill-local' import TaskService from '@deepseek-ai/dsh-tasks' @@ -39,6 +39,17 @@ import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' const root = resolve(import.meta.dirname, '..') const OUT = 'docs/tool-catalog.md' +/** Register the descriptor needed to mount schema-producing consumers. */ +function registerCatalogSubagentProvider(ctx: Context, name: string): void { + const provider: SubagentProvider = { + name, + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: () => Promise.reject(new Error('tool-catalog provider cannot start a child')), + } + ctx.subagents.registerProvider(provider) +} + /** * Tool package plus its hand-maintained boot recipe. The caller mounts the * prompt and registry; each recipe supplies only package-specific seams and @@ -191,8 +202,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ shippedNames: ['subagent', 'subagent_fork'], async mount(ctx) { await ctx.plugin(SubagentService) - // Register a scripted provider under the name the tool delegates to. - await ctx.plugin(SubagentMock, { name: 'mock' }) + registerCatalogSubagentProvider(ctx, 'mock') await ctx.plugin(ToolSubagent, { provider: 'mock' }) }, note: @@ -234,7 +244,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ // subagent provider to satisfy it. The schema does not depend on which // provider backs the engine. await ctx.plugin(SubagentService) - await ctx.plugin(SubagentMock, { name: 'mock' }) + registerCatalogSubagentProvider(ctx, 'mock') await ctx.plugin(VmWorkflowEngine, { provider: 'mock' }) await ctx.plugin(ToolWorkflow) }, diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 75fb2b75ad..35cd2dae1b 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -65,7 +65,6 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/support/invariants': { kind: 'none', reason: 'The observer validates requests but never rewrites their context.' }, 'packages/support/loader-smoke': { kind: 'none', reason: 'The test harness observes child-process streams without changing live requests.' }, 'packages/support/llm-replay': { kind: 'none', reason: 'The keyless adapter invokes no provider model.' }, - 'packages/support/subagent-mock': { kind: 'indirect', reason: 'Only dsh-tool-subagent renders its configured test outcome.' }, 'packages/tasks/tasks': { kind: 'indirect', reason: 'Producer and control-surface plugins own all model rendering over the task registry.' }, 'packages/examples/acp-demo': { kind: 'indirect', reason: 'The app bundle delegates request composition to dsh-agent-spine-demo and dsh-acp.' }, 'packages/ui/app-boot': { kind: 'indirect', reason: 'Only the loaded plugin tree contributes model context.' }, diff --git a/tsconfig.build.json b/tsconfig.build.json index dd13e018c3..6f18011715 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -77,7 +77,6 @@ { "path": "./packages/support/acp-snapshot" }, { "path": "./packages/support/loader-smoke" }, { "path": "./packages/subagent/subagent" }, - { "path": "./packages/support/subagent-mock" }, { "path": "./packages/subagent/tool-subagent" }, { "path": "./packages/subagent/subagent-inprocess" }, { "path": "./packages/subagent/subagent-subprocess" }, diff --git a/tsconfig.json b/tsconfig.json index 22451dc10f..d0b5692cf0 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -88,7 +88,6 @@ { "path": "./packages/support/acp-snapshot" }, { "path": "./packages/support/loader-smoke" }, { "path": "./packages/subagent/subagent" }, - { "path": "./packages/support/subagent-mock" }, { "path": "./packages/subagent/tool-subagent" }, { "path": "./packages/subagent/subagent-inprocess" }, { "path": "./packages/subagent/subagent-subprocess" }, From 9912918a48438fade5a9b373df55682e2c9a31fb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 11:58:55 +0800 Subject: [PATCH 208/323] docs: tighten agent execution contracts --- docs/architecture.md | 2 +- docs/core-data-structures/core.md | 2 +- ...26-07-15-agent-execution-context.i18n.yaml | 4 +- .../2026-07-15-agent-execution-context.md | 48 +++++------------ .../2026-07-15-agent-execution-context.zh.md | 54 ++++++------------- packages/README.md | 2 +- packages/core/README.md | 2 +- packages/core/agent-execution/README.md | 4 +- packages/core/agent-execution/package.json | 2 +- packages/core/agent-execution/src/types.ts | 2 +- packages/core/agent-loop/README.md | 4 +- .../verify-package-readme-model-experience.ts | 2 +- 12 files changed, 41 insertions(+), 87 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 56e7fee812..2f47722ba7 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -121,7 +121,7 @@ Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, re ### Agent Execution Context -`AgentLoop` wraps each concrete driver in process-local `ctx.agentExecution`; child creation and setup stay outside its boundary, and explicit identities remain authoritative. See the [package contract](../packages/core/agent-execution/README.md) and [decision](rfc/implemented/architecture/2026-07-15-agent-execution-context.md). +`AgentLoop` establishes process-local `ctx.agentExecution` around each driver; the [decision](rfc/implemented/architecture/2026-07-15-agent-execution-context.md) owns boundary and explicit-identity rules. ## State diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 74dfa1ce78..1e802f3630 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -415,7 +415,7 @@ The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, che ## Agent execution context -`AgentExecution` is the process-local ambient frame established around a concrete driver's lifetime. It holds the exact Agent rather than duplicating Session or step state; ambient presence is neither liveness proof nor authorization. +`AgentExecution` is the process-local ambient frame established around a concrete driver's lifetime. It holds the exact Agent object rather than duplicating Session or step state; ambient presence is neither liveness proof nor authorization. Source: [`packages/core/agent-execution/src/types.ts`](../../packages/core/agent-execution/src/types.ts) diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml index 8131a9fa8e..371884096a 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-execution-context.md: a8d1338a6fc277c3adcd1ed835a54dd0b667ce4b -2026-07-15-agent-execution-context.zh.md: 4cf78ce2c6ecba15eb7ae90479f877ce4e07cfe1 +2026-07-15-agent-execution-context.md: 2ea88cddf7a686713157c77ce1d7520082a9da28 +2026-07-15-agent-execution-context.zh.md: 1c4e0ba9c3fa787dfa816eff4c5d04cff5c2f7b1 diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md index a8d1338a6f..2ea88cddf7 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md @@ -8,63 +8,41 @@ English | [中文](2026-07-15-agent-execution-context.zh.md) The harness has two useful but different notions of context. A Cordis `Context` selects services, registration ownership, and lifetime; `agent.ctx` is the flat registration scope owned by one live Agent. Agent and Session identity instead describe the subject of an asynchronous operation. Changing a root `ctx.agent` to mean “whichever Agent is running” would conflate those meanings and fail when one process drives Agents concurrently. -Deep process-local infrastructure still needs a trusted initiating Agent. Capability transports, tracing helpers, loggers, and gateway clients may sit below the explicit loop, tool, and request parameters. Threading `agent` through every private helper adds plumbing, while a process-global mutable slot is incorrect across `await`. Model-visible arguments are also unsuitable because a model must not choose a trusted Session or routing header. This is mandatory control infrastructure rather than optional model-visible context enrichment. +Deep process-local infrastructure sometimes needs a trusted initiating Agent below explicit loop, tool, and request parameters—for example, a host-aware transport, tracing helper, logger, or gateway client. Requiring every private helper to forward `agent` adds repetition, while a process-global mutable slot is incorrect across `await`. Model-visible arguments are unsuitable because a model must not choose a trusted Session or routing header. The carrier is mandatory control infrastructure rather than optional model-visible context. ## Decision -`@deepseek-ai/dsh-agent-execution` provides the mandatory `ctx.agentExecution` service using Node `AsyncLocalStorage`. The frame contains only the exact live Agent: +`@deepseek-ai/dsh-agent-execution` provides the mandatory `ctx.agentExecution` service using Node `AsyncLocalStorage`. The named `AgentExecution` frame contains only the exact Agent object; the [core-data catalog](../../../core-data-structures/core.md#agent-execution-context) owns the literal frame and service types. -```text -export interface AgentExecution { - readonly agent: Agent -} +`current()` reads optionally, `require()` throws `no agent execution context is active`, and `run()` preserves the operation's exact synchronous value or Promise. `run(undefined, operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `execution.agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. -export interface AgentExecutionService { - current(): AgentExecution | undefined - require(): AgentExecution - run(execution: AgentExecution | undefined, operation: () => T): T -} -``` +`AgentLoop` injects the service and wraps each concrete driver's complete `runLoop` lifetime in `agentExecution.run({ agent }, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. -`current()` is optional, `require()` throws `no agent execution context is active`, and `run()` preserves the operation's exact synchronous value or Promise. `run(undefined, operation)` establishes a real clearing boundary for work that must not inherit an Agent. A comparable implementation observed an uncleared ambient value crossing scheduled work into a later turn; the explicit undefined boundary prevents that class of leak. Session remains derived as `execution.agent.session`; turn, step, tool call, signal, model, cwd, sandbox, and authorization stay with their existing owners. - -`AgentLoop` injects the service and wraps each concrete driver's complete `runLoop` lifetime in `agentExecution.run({ agent }, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. - -Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, cwd selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. +Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. The provider uses an ordered composite effect. Teardown first rejects new boundaries, then removes the service and awaits injected dependents such as AgentLoop, then waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. `current()` and `require()` remain usable through a retained in-flight service reference while that drain runs; after disposal, retained calls throw `agent execution service is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting is required in addition to Cordis dependency ordering. -Asynchronous resources created inside `run()` inherit its store even when the returned operation does not await them. Agent-owned foreground work may inherit `{ agent }` but keeps the explicit cancellation and disposal contract of its execution seam. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)` and own an explicit stop. Queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation. +`run()` does not own detached work: provider drain tracks only the Promise returned by `operation`. Asynchronous resources created inside the boundary inherit its store until they settle or ALS is disabled, so their owning seam must stop unreturned work explicitly. Agent-owned foreground work returns its lifetime and keeps its cancellation contract. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)`; queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation. A host-aware transport may derive a deployment-owned header such as `X-Harness-Session-Id` from `ctx.agentExecution.require().agent.session.id`; the header is absent from model-visible schema and arguments. No production MCP or Web transport adopts such a header in this decision. A test-double transport proves the trusted boundary without assigning host routing policy to an existing provider-neutral seam. This decision extends the [Agent registration-scope contract](2026-07-08-agent-scope-contexts.md) and its [runtime design](2026-07-12-agent-scope-runtime-design.md); it does not change their static `agent.ctx` meaning. -## Reference model - -| Claude Code | Harness design | -|---|---| -| AppState store | Cordis deployment services and their owned live state | -| QueryEngine | Agent driver plus loop-owned runtime state | -| ToolUseContext | Explicit Agent, tool, and request parameters at capability seams | -| AgentContext ALS | Narrow `AgentExecution` carrier | -| Transcript | Event-sourced `Session` and persistence backends | - ## Verification -Service tests pin optional and required reads, synchronous and awaited propagation, overlapping and nested boundaries, explicit clearing, restoration after throw or rejection, exact return identity, drain ordering, and disposed-reference errors. AgentLoop integration tests run overlapping real drivers, nested parent/child creation, agentless direct tool execution, cancellation during provider/root teardown, service restart, and a captured Agent after disposal. Detached-work coverage prevents context leakage without changing existing explicit cancellation contracts. +Service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, missing-provider activation, service restart, and provider/root teardown. Composition, module-graph, build, and runtime-closure checks keep the provider wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses. -The test-double capability transport derives `X-Harness-Session-Id` internally and asserts that neither its tool schema nor logged arguments contains an identity field. Composition tests and generated catalogs keep the provider present in the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses; a missing provider leaves AgentLoop inactive. Documentation checks keep the repository layout in `AGENTS.md`, the package table in `packages/core/README.md`, and the group description in `packages/README.md` aligned with the mandatory provider. +Only a test-double host-aware transport consumes ambient identity; it derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by `operation`; that work remains subject to its owner's explicit stop contract. ## Alternatives considered -**Pass Agent through every function.** Public, worker, process, persistence, and wire boundaries continue to do this, but requiring every process-local private helper to carry Agent adds plumbing without improving trust. ALS is confined to the asynchronous chain inside those explicit boundaries. +**Pass Agent through every function.** Public, worker, process, persistence, and wire boundaries continue to do this, but requiring every process-local private helper to carry Agent adds repetitive forwarding without improving trust. ALS is confined to the asynchronous chain inside those explicit boundaries. **Make `ctx.agent` dynamic.** `ctx.agent` already means the static Agent associated with an Agent-scoped Cordis context. Changing the root meaning would mix registration and execution scopes and make concurrent behavior surprising. -**Store a complete mutable runtime frame.** Agent, Session, inbox, cancellation, turn, step, tool execution, and persistence already have authoritative owners. Duplicating them would create stale snapshots and another lifecycle. The wrapper leaves room for a separately justified stale-safe label without flattening the store to a bare Agent. +**Store a complete mutable runtime frame.** Agent, Session, inbox, cancellation, turn, step, tool execution, and persistence already have authoritative owners. Duplicating them would create stale snapshots and another lifecycle. A named frame makes the execution-context boundary explicit without duplicating owner state. -**Include a step `AbortSignal`, cwd, sandbox, or authorization.** Their lifetimes and authority do not match the driver boundary, and their existing seams already pass them explicitly. Adding a control capability requires a separate decision and nested lifecycle contract. +**Include a step `AbortSignal`, `cwd`, sandbox, or authorization.** Their lifetimes and authority do not match the driver boundary, and their existing seams already pass them explicitly. Adding a control capability requires a separate decision and nested lifecycle contract. **Use a process-global `currentAgent`.** Concurrent Agents and subagents overwrite one another across awaited continuations, so a mutable global is correct only under a serialization guarantee the harness does not make. @@ -76,8 +54,8 @@ The test-double capability transport derives `X-Harness-Session-Id` internally a Deep infrastructure gains one trusted process-local initiating Agent without widening existing tool and capability requests. Concurrent and nested drivers isolate automatically, AgentLoop stays inactive when the provider is absent, and HMR/root disposal reaches quiescence before ALS is disabled. -The dependency is implicit in function signatures and carries a live capability object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries. +The dependency is implicit in function signatures and carries a capability-bearing Agent object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries. The teardown design deliberately accepts Node's [Stability 1 (Experimental)](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) `AsyncLocalStorage.disable()` dependency. Node requires `disable()` before an ALS instance can be garbage-collected, which matters when HMR replaces provider-owned instances; the service state guard prevents a later `run()` from re-entering the instance after disposal. -The frame deliberately omits turn, step, signal, cwd, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control. +The frame deliberately omits turn, step, `signal`, `cwd`, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md index 4cf78ce2c6..1c4e0ba9c3 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md @@ -8,65 +8,43 @@ Status: implemented Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期；`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」，就会混淆这两种含义，并在单进程并发驱动多个 Agent 时失效。 -进程内深层基础设施仍需要可信的发起 Agent。能力传输层、追踪辅助函数、日志器和网关客户端可能位于显式 loop、工具及请求参数的下层。在每个私有辅助函数中传递 `agent` 会增加管道代码，而进程级可变槽会在 `await` 之间发生并发错误。模型可见参数同样不合适，因为模型不能选择可信的会话或路由请求头。它是必载控制基础设施，而不是模型可见的可选上下文增强。 +进程内深层基础设施有时需要在显式传递的循环、工具及请求参数之下获取可信的发起 Agent，例如宿主感知传输层、追踪辅助函数、日志器或网关客户端。要求每个私有辅助函数都转发 `agent` 会造成重复，而进程级可变槽会在跨 `await` 时发生并发错误。模型可见参数也不适用，因为模型不得选择可信的会话或路由请求头。该载体属于必需的控制基础设施，而非模型可见的可选上下文。 ## 决策 -`@deepseek-ai/dsh-agent-execution` 使用 Node `AsyncLocalStorage` 提供必载的 `ctx.agentExecution` 服务。该帧只包含准确的存活 Agent： +`@deepseek-ai/dsh-agent-execution` 使用 Node `AsyncLocalStorage` 提供必需的 `ctx.agentExecution` 服务。命名的 `AgentExecution` 帧仅包含同一个 Agent 对象；[核心数据目录](../../../core-data-structures/core.md#agent-execution-context)是帧与服务字面类型定义的真源。 -```text -export interface AgentExecution { - readonly agent: Agent -} +`current()` 用于可选读取，`require()` 抛出 `no agent execution context is active`，`run()` 保留操作返回的同步值或 Promise 本身。`run(undefined, operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `execution.agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 -export interface AgentExecutionService { - current(): AgentExecution | undefined - require(): AgentExecution - run(execution: AgentExecution | undefined, operation: () => T): T -} -``` +`AgentLoop` 注入该服务，并用 `agentExecution.run({ agent }, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 -`current()` 执行可选读取，`require()` 抛出 `no agent execution context is active`，`run()` 保留操作返回的准确同步值或 Promise。`run(undefined, operation)` 会建立真实的清空边界，供不得继承 Agent 的工作使用。一个同类实现曾观察到未清空的隐式值穿过已调度工作泄漏进后续轮次；显式 undefined 边界可以防止这类泄漏。会话仍通过 `execution.agent.session` 推导；轮次、步骤、工具调用、signal、模型、cwd、沙箱和授权继续由现有归属方管理。 - -`AgentLoop` 注入该服务，并用 `agentExecution.run({ agent }, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 - -隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、cwd 选择、取消、worker/进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 +隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 提供方使用有序复合 effect。teardown 会先拒绝新边界，再移除服务并等待 AgentLoop 等注入方排空，随后等待活动的返回 Promise 边界，最后调用 `AsyncLocalStorage.disable()`。排空期间，进行中代码可通过保留的服务引用继续调用 `current()` 和 `require()`；dispose 后，保留引用会抛出 `agent execution service is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown，因此除 Cordis 依赖顺序外还必须统计活动边界。 -在 `run()` 内创建的异步资源会继承其存储，即使返回的操作没有等待它们。Agent 所拥有的前台工作可以继承 `{ agent }`，但仍使用其执行 seam 的显式取消和 dispose 契约。无关的定时器、队列和部署基础设施在 `run(undefined, operation)` 下启动，并拥有显式停止操作。队列、worker、进程和协议边界必须序列化身份，不能期待 ALS 传播。 +`run()` 不负责管理脱离返回链的工作：提供方排空只跟踪 `operation` 返回的 Promise。边界内创建的异步资源会继承其存储，直到自身结束或 ALS 被禁用；所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所有前台工作会把完整生命周期纳入返回值，并保留显式取消契约。无关的定时器、队列和部署基础设施在 `run(undefined, operation)` 下启动；队列、worker、进程和协议边界必须序列化身份，不能期待 ALS 传播。 宿主感知的传输层可以从 `ctx.agentExecution.require().agent.session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头；模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界，而不会把宿主路由策略分配给现有的提供方无关 seam。 本决策扩展 [Agent 注册作用域契约](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md)，不会改变其中 `agent.ctx` 的静态含义。 -## 参考模型 - -| Claude Code | Harness 中的设计 | -|---|---| -| AppState store | Cordis 部署服务及其拥有的实时状态 | -| QueryEngine | Agent 驱动及 loop 所拥有的运行时状态 | -| ToolUseContext | 能力边界上的显式 Agent、工具和请求参数 | -| AgentContext ALS | 窄粒度 `AgentExecution` 载体 | -| Transcript | 事件溯源 `Session` 与持久化后端 | - ## 验证 -服务测试锁定可选与必需读取、同步与跨 `await` 传播、并发与嵌套边界、显式清空、throw 或 rejection 后的恢复、准确返回值身份、排空顺序及已 dispose 引用错误。AgentLoop 集成测试覆盖重叠的真实驱动、嵌套父子创建、无 Agent 的直接工具执行、提供方或根 Context teardown 期间的取消、服务重启，以及 Agent dispose 后保留的引用。针对脱离主调用链的异步工作的测试会防止上下文泄漏，同时不改变现有显式取消契约。 +服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、缺少提供方时的激活行为、服务重启，以及提供方或根 Context 的销毁流程。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 都装载提供方。 -测试替身能力传输层在内部推导 `X-Harness-Session-Id`，并断言工具 schema 与记录的参数都不包含身份字段。组合测试和生成目录确保默认 bundle、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 都装载提供方；缺少提供方时 AgentLoop 保持未激活。文档检查确保 `AGENTS.md` 中的仓库布局、`packages/core/README.md` 中的包表，以及 `packages/README.md` 中的分组说明都与该必载提供方保持一致。 +只有测试替身形式的宿主感知传输层消费隐式身份；它在内部推导 `X-Harness-Session-Id`，并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空 `operation` 返回的 Promise 之外的异步工作；这类工作仍由所属方的显式停止契约管理。 ## 考虑过的替代方案 -**在每个函数中传递 Agent。** 公开、worker、进程、持久化和协议边界继续显式传递，但要求每个进程内私有辅助函数都携带 Agent 只会增加管道代码，不会提高可信度。ALS 仅限于这些显式边界内部的异步调用链。 +**在每个函数中传递 Agent。** 公开、worker、进程、持久化和协议边界继续显式传递，但要求每个进程内私有辅助函数都携带 Agent 只会造成重复转发，不会提高可信度。ALS 仅限于这些显式边界内部的异步调用链。 **让 `ctx.agent` 变成动态值。** `ctx.agent` 已经表示与 Agent 作用域 Cordis 上下文静态关联的 Agent。改变根上下文的含义会混合注册作用域与执行作用域，并让并发行为变得意外。 -**保存完整的可变运行时帧。** Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。重复保存会产生陈旧快照和另一套生命周期。包装对象为另行论证的陈旧安全标签保留扩展空间，而不会把存储简化成裸 Agent。 +**保存完整的可变运行时帧。** Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。重复保存会产生陈旧快照和另一套生命周期。命名帧能够明确标识执行上下文边界，而不重复保存归属方状态。 -**包含步骤级 `AbortSignal`、cwd、沙箱或授权。** 它们的生命周期与权限不匹配驱动边界，而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。 +**包含步骤级 `AbortSignal`、`cwd`、沙箱或授权。** 它们的生命周期及权限范围与驱动边界不一致，而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。 -**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步 continuation 间相互覆盖，因此可变全局值只在 Harness 不具备的串行保证下才正确。 +**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步延续执行之间相互覆盖，因此可变全局值只在 Harness 不具备的串行保证下才正确。 **从模型可见参数推导身份。** 不能信任模型或用户输入来选择会话、租户或沙箱路由。 @@ -74,10 +52,10 @@ export interface AgentExecutionService { ## 后果 -深层基础设施可以获得一个可信的进程内发起 Agent，而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离，缺少提供方时 AgentLoop 保持未激活，HMR 或根 Context dispose 会在禁用 ALS 前达到静止状态。 +深层基础设施可以获得一个可信的进程内发起 Agent，而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离，缺少提供方时 AgentLoop 保持未激活，HMR 或根 Context dispose 会在禁用 ALS 前完成排空。 -该依赖不会出现在函数签名中，并且携带一个存活能力对象。消费方必须将其限制在横切基础设施中，把隐式存在视为既不证明存活、也不授予权限，并保留显式取消和归属检查。ALS 还有常驻传播成本，也无法跨越 worker、进程、HTTP 或持久化队列边界。 +该依赖不会出现在函数签名中，并且携带一个具有控制能力的 Agent 对象。消费方必须将其限制在横切基础设施中，把隐式存在视为既不证明存活、也不授予权限，并保留显式取消和归属检查。ALS 还有常驻传播成本，也无法跨越 worker、进程、HTTP 或持久化队列边界。 -该 teardown 设计有意接受 Node [Stability 1（实验性）](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) 的 `AsyncLocalStorage.disable()` 依赖。Node 要求在 ALS 实例可被垃圾回收前调用 `disable()`，这对 HMR 替换提供方所拥有的实例尤为重要；服务状态守卫会阻止 dispose 后通过后续 `run()` 重新进入该实例。 +该销毁设计有意依赖 Node 的 [Stability 1（实验性）](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) API `AsyncLocalStorage.disable()`。Node 要求在 ALS 实例可被垃圾回收前调用 `disable()`，这对 HMR 替换提供方所拥有的实例尤为重要；服务状态守卫会阻止 dispose 后通过后续 `run()` 重新进入该实例。 -该帧有意省略轮次、步骤、signal、cwd、沙箱和授权。若真实消费方无法使用现有显式字段，必须另行论证扩展；陈旧字段最多只能误标遥测数据，绝不能授予控制权。 +该帧有意省略轮次、步骤、`signal`、`cwd`、沙箱和授权。若真实消费方无法使用现有显式字段，必须另行论证扩展；陈旧字段最多只能误标遥测数据，绝不能授予控制权。 diff --git a/packages/README.md b/packages/README.md index 380a786d16..7e01fe30fe 100644 --- a/packages/README.md +++ b/packages/README.md @@ -8,7 +8,7 @@ Packages live at `packages///`; groups are containers, while names r | Group | Role | Release expectation | |---|---|---| -| [`core/`](core/README.md) | Product API spine: session, system-prompt, tools, agent, agent-execution, and the concrete loop | Product — stable surface | +| [`core/`](core/README.md) | Product API spine, including agent execution and the concrete loop | Product — stable surface | | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface | | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface | | [`code-runtime/`](code-runtime/README.md) | Code-execution capability family: the abstract runtime seam for model-written programs + a worker-thread backend | Product — stable surface | diff --git a/packages/core/README.md b/packages/core/README.md index 6736e29af2..3c0ad38819 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -14,6 +14,6 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. -`agent-execution` is mandatory control infrastructure shared by concrete loops and deep process-local consumers. `agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop; other plugins depend on the `agent` vocabulary and execution service, never on `agent-loop` directly, so the loop stays swappable. +`agent-execution` is mandatory control infrastructure for concrete loops and deep process-local consumers. `agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop. Extension plugins depend on `agent` and, when they need ambient identity, `agent-execution`; they never depend on `agent-loop` directly, so the loop stays swappable. The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + agent-execution + invariants + the local [skill family](../skill/README.md) + `tool-bash` + workspace-context + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door. diff --git a/packages/core/agent-execution/README.md b/packages/core/agent-execution/README.md index a389699863..8c01f0b3c4 100644 --- a/packages/core/agent-execution/README.md +++ b/packages/core/agent-execution/README.md @@ -8,13 +8,13 @@ Process-local ambient Agent identity for asynchronous work initiated by a concre - `require()` returns the inherited execution or throws `no agent execution context is active`. - `run(execution, operation)` returns the exact synchronous value or Promise from `operation`. Passing `undefined` establishes a real boundary that hides an inherited Agent. -The store contains only `{ readonly agent: Agent }`. A Session is available through `agent.session`; turn, step, signal, cwd, sandbox, authorization, and other capability state remain with their explicit owners. Ambient presence identifies the initiator but does not prove that the Agent is live or that an operation is authorized. +The store contains only `{ readonly agent: Agent }`. The `Session` remains available through `agent.session`; turn, step, `signal`, `cwd`, sandbox, authorization, and other capability state remain with their explicit owners. Ambient presence identifies the initiator but does not prove that the Agent is live or that an operation is authorized. ## Lifetime and detached work Provider teardown rejects new `run()` boundaries, removes the service so injected dependents drain, waits for returned Promise boundaries, then disables its `AsyncLocalStorage`. In-flight code retaining the service can call `current()` and `require()` while it drains; after disposal, all three methods throw `agent execution service is disposed`. -Async resources created inside `run()` inherit its Agent even when the operation does not await them. Agent-owned foreground work may inherit the boundary but keeps using the explicit cancellation and disposal contract of its execution seam. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)` and own an explicit stop. Queue, worker, process, and wire boundaries serialize any identity they need instead of relying on ALS propagation. +Async resources created inside `run()` inherit its Agent even if `operation` returns before they settle, but provider teardown waits only for the Promise returned by `operation`. The owning seam must stop unreturned work explicitly. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)` and own an explicit stop; queue, worker, process, and wire boundaries serialize any identity they need instead of relying on ALS propagation. ## Known Limitations and Deferred Work diff --git a/packages/core/agent-execution/package.json b/packages/core/agent-execution/package.json index e5ebbbf5f3..7c2c527d3d 100644 --- a/packages/core/agent-execution/package.json +++ b/packages/core/agent-execution/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-agent-execution", - "description": "Agent-scoped asynchronous execution context for the DeepSeek Harness", + "description": "Process-local ambient Agent context for asynchronous driver work", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/core/agent-execution/src/types.ts b/packages/core/agent-execution/src/types.ts index ccafb4840a..94b144785b 100644 --- a/packages/core/agent-execution/src/types.ts +++ b/packages/core/agent-execution/src/types.ts @@ -6,7 +6,7 @@ import type { Agent } from '@deepseek-ai/dsh-agent' -/** The exact live Agent associated with one asynchronous execution chain. */ +/** The exact Agent associated with one asynchronous execution chain. */ export interface AgentExecution { readonly agent: Agent } diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 2acda4ab52..f45411923c 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -50,9 +50,7 @@ The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publicati ### Loop lifecycle (`loop.ts`) -The driver owns one agent for its lifetime and runs inside `ctx.agentExecution.run({ agent }, ...)`, so process-local asynchronous continuations can recover the initiating Agent. Creation, persistence load, and unpublished setup stay outside the child boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [execution-context package](../agent-execution/README.md) owns propagation and detached-work rules. - -The loop records turn, step, request, stream, and tool boundaries in the session log; live extension events coordinate policy around those durable facts. The [architecture turn flow](../../../docs/architecture.md#turn-flow) and generated [event catalog](../../../docs/cordis-catalog/events.md) are the authoritative sequence and signatures. +The driver owns one agent for its lifetime and runs inside `ctx.agentExecution.run({ agent }, ...)`, so process-local asynchronous continuations can recover the initiating Agent. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [execution-context package](../agent-execution/README.md) owns propagation, teardown, and detached-work rules. Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index fc2347566d..407758afc7 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -28,7 +28,7 @@ interface SentenceContract { * so an absent section cannot be mistaken for forgotten documentation. */ const NO_MODEL_EXPERIENCE_SECTION: Readonly> = { - 'packages/core/agent-execution': 'The package is model-agnostic ambient control infrastructure; model-facing consumers own any resulting request surface.', + 'packages/core/agent-execution': 'The package adds no model-visible text or schema; consumers own any use in model requests.', 'packages/core/scope': 'The package is a model-agnostic registration and lifecycle primitive; model-facing consumers own any context selection.', 'packages/util/brand': 'The package is a type-only primitive erased at compile time.', 'packages/util/paths': 'The package only resolves harness-owned host paths; model-facing consumers own any rendered use.', From dd9f8947357e23556a83b10593a33cc5dd3e631f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:01:43 +0800 Subject: [PATCH 209/323] test(agent-loop): wire execution context into session-id harness --- packages/core/agent-loop/tests/config-session-id.spec.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 7badab97c1..8710ee5629 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -32,6 +32,7 @@ async function makeCoreContext(): Promise { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + await ctx.plugin(AgentExecutionProvider) return ctx } From 548bbe7ae898383ababa3a849905b0642dc966e7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:05:59 +0800 Subject: [PATCH 210/323] docs(tui): record dedicated terminal front-door decision Record the July 17 package split as an implemented bilingual feature RFC. The decision explains why TUI and stdio have separate terminal contracts, why concrete front-door selection belongs to composition, and how the TUI preserves existing session, tool-presentation, and lifecycle ownership. Link the deterministic dark, light, and animated demos from the RFC so the assets have an in-repository owner. Cross-link the feature and testing decisions from the package README, then regenerate the RFC index and bilingual consistency record. --- docs/rfc/INDEX.md | 1 + ...cated-full-screen-tui-front-door.i18n.yaml | 6 ++ ...17-dedicated-full-screen-tui-front-door.md | 58 +++++++++++++++++++ ...dedicated-full-screen-tui-front-door.zh.md | 58 +++++++++++++++++++ packages/ui/tui/README.md | 2 + 5 files changed, 125 insertions(+) create mode 100644 docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml create mode 100644 docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md create mode 100644 docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 2a262fca6e..9daf5de83b 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -89,6 +89,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Session query relationship tracing](implemented/feature/2026-07-13-session-query-tracing.md) | 2026-07-13 | | [Optional time-context plugin](implemented/feature/2026-07-14-time-context-plugin.md) | 2026-07-14 | | [Durable per-step time context](implemented/feature/2026-07-16-durable-per-step-time-context.md) | 2026-07-16 | +| [Dedicated full-screen TUI front door](implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md) | 2026-07-17 | ### Simplification diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml new file mode 100644 index 0000000000..e7770a2753 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-17-dedicated-full-screen-tui-front-door.md: dd4d7350a61b0f19fcc87658e4c0f9d8bbf2e998 +2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 45e0926f87e1b73c378c195a46a6d40d13a69bfa diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md new file mode 100644 index 0000000000..dd4d7350a6 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md @@ -0,0 +1,58 @@ +# RFC: Dedicated full-screen TUI front door + +Status: implemented + +English | [中文](2026-07-17-dedicated-full-screen-tui-front-door.zh.md) + +## Problem + +The line-oriented `@deepseek-ai/dsh-stdio` front door works in pipes and ordinary terminals, but a full-screen coding interface must own raw input, differential screen drawing, cursor state, overlays, and terminal restoration. Combining those contracts in one UI plugin couples the pipe-safe path to a TTY-only lifecycle and makes it unclear which terminal behavior a composition selects. + +The interactive channel must remain a Cordis plugin over the same agent, session, tool, and user-interaction services as every other front door. It needs to resume durable history, follow compaction replacements, display tool-owned presentation, and restore the terminal on startup failure and disposal. A standalone chat application or a second agent composition would duplicate behavior outside the plugin graph. + +## Decision + +DeepSeek Harness ships [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) as a dedicated Cordis plugin. It owns terminal input and presentation only; agent lifecycle, session persistence, tool execution, and the model-facing question tool remain separate composition entries. The plugin requires both stdin and stdout to be TTYs and fails instead of silently changing to line-oriented behavior. + +The app layer selects a concrete terminal front door before mounting it. `@deepseek-ai/dsh-stdio-demo` can resolve `auto` from the two process streams, while the `coding-agent` and `tui-agent` leaves explicitly select readline and TUI respectively. The TUI leaf reuses the coding agent's backend and tool composition through an asserted include patch, so the three runnable agent leaves remain symmetric without duplicating deployment choices. + +The selected front door receives the exact generated or resumed `SessionId` used by the pre-created agent. It mounts before the agent composition, waits for the matching root agent, and enters full-screen mode only after that agent exists. A matching `agent-loop/config-start-failed` event is therefore reported before screen takeover and exits with status 1. + +### Session projection and interaction + +The TUI rebuilds the transcript from the active `session.surface` and reprojects it whenever an event carries a `surfaceOp`, so resumed and compacted history matches the model-visible conversation. It renders Markdown text and reasoning, token totals, the latest `todo/write` plan, and tool cards produced through each tool definition's `presentCall` and `presentResult` methods. Pending chunks and tool calls update the same components that completed events settle. + +Editor input calls `agent.send()` while idle and `agent.steer()` while a turn is running. Cancellation, reasoning visibility, tool-card expansion, redraw, transcript clearing, and exit are terminal-only controls. The plugin registers the shared `userInteraction` provider and presents questions as queued keyboard overlays; agent behavior and answer logging remain owned by their existing services. + +### Terminal ownership + +Before model output, session data, tool presentation, questions, configuration, or diagnostics reach pi-tui or the terminal title, `displayText()` renders C0 and C1 controls other than line feeds as visible hexadecimal escapes. Only the TUI and pi-tui create ANSI control sequences. + +The built-in palette uses standard 16-color ANSI foregrounds and SGR attributes, keeps body text and backgrounds at terminal defaults, and uses reverse video for selection. Host terminals therefore remap the interface for light and dark themes without a TUI-specific theme setting; `color: false` removes styling. + +### Shipped interface + +The deterministic scripted demo shows prompt submission, streamed model output, and the ANSI palette under dark and light terminal themes without a network dependency. + +![Scripted TUI interaction](../../../assets/tui/jokes-dynamic.gif) + +| Dark terminal | Light terminal | +| --- | --- | +| ![TUI on a dark terminal](../../../assets/tui/jokes-dark.png) | ![TUI on a light terminal](../../../assets/tui/jokes-light.png) | + +## Verification + +The implemented [TUI terminal-state snapshot RFC](../testing/2026-07-18-tui-terminal-state-snapshots.md) owns the four-layer verification contract: direct behavior tests, transient semantic terminal snapshots, recorded JSONL journeys through production tools, and Loader/PTY smoke tests. The package README owns configuration, commands, model-visible effects, and current limitations. + +## Alternatives considered + +- **Keep readline and full-screen modes inside `@deepseek-ai/dsh-stdio`** — rejected because line-oriented output and differential TTY rendering have different dependencies, input rules, logging ownership, and teardown obligations. Separate packages keep the pipe-safe contract small and explicit. +- **Let the TUI plugin silently downgrade when either stream is not a TTY** — rejected because a fallback hides deployment mistakes and changes interaction semantics. The app bundle may select a front door with `auto`; an explicitly mounted TUI fails loud. +- **Keep TUI wiring and tests under the readline `coding-agent` leaf** — rejected because one leaf would represent two distinct front doors and break symmetry with `acp-agent`. A dedicated `tui-agent` leaf owns TUI overlays and tests while reusing the coding agent's backend composition. + +## Consequences + +- Interactive terminal work gains a stateful Markdown, card, plan, and question interface without changing the line-oriented protocol used by pipes and automation. +- The TUI carries a pi-tui dependency and a strict TTY requirement; non-TTY deployments select `@deepseek-ai/dsh-stdio` at composition time. +- Session projection makes resume and compaction consistent with the durable conversation, but one configured session owns the transcript and editor. +- Tool packages extend terminal cards through their existing presentation methods without adding tool-specific branches to the TUI. diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md new file mode 100644 index 0000000000..45e0926f87 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md @@ -0,0 +1,58 @@ +# RFC: 独立的全屏 TUI 入口 + +Status: implemented + +[English](2026-07-17-dedicated-full-screen-tui-front-door.md) | 中文 + +## 问题 + +逐行输出的 `@deepseek-ai/dsh-stdio` 入口适用于管道和普通终端，但全屏编码界面必须负责原始输入、差分绘制、光标状态、浮层和终端恢复。把这两类契约合并到一个 UI 插件中，会迫使管道安全路径依赖仅适用于 TTY 的生命周期，也使组合无法明确表达所选终端行为。 + +交互通道必须继续作为 Cordis 插件，使用与其他入口相同的 agent（智能体）、会话、工具和用户交互服务。它需要恢复持久历史、跟随压缩替换、显示工具自有的呈现内容，并在启动失败和资源释放时恢复终端。独立聊天应用或第二套 agent 组合会在插件图之外重复实现这些行为。 + +## 决策 + +DeepSeek Harness 将 [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 作为独立的 Cordis 插件交付。该插件只负责终端输入与呈现；agent 生命周期、会话持久化、工具执行以及模型可见的提问工具仍由不同组合项负责。插件要求 stdin 和 stdout 均为 TTY；条件不满足时会失败，不会静默切换为逐行输出。 + +应用组合层在挂载前选择具体的终端入口。`@deepseek-ai/dsh-stdio-demo` 可以根据两个进程流通过 `auto` 作出选择，`coding-agent` 和 `tui-agent` 叶节点则分别明确选择 readline 与 TUI。TUI 叶节点通过带断言的 include patch 复用 coding agent 的后端和工具组合，使三个可运行的 agent 叶节点保持对称，同时避免重复部署选项。 + +所选入口接收预创建 agent 使用的同一个新建或恢复 `SessionId`。入口先于 agent 组合挂载，等待相符的根 agent 出现，然后才进入全屏模式。因此，相符的 `agent-loop/config-start-failed` 事件会在接管屏幕前报告，并以状态码 1 退出。 + +### 会话投影与交互 + +TUI 从活跃的 `session.surface` 重建 transcript（文本记录），并在事件携带 `surfaceOp` 时重新投影，因此恢复或压缩后的历史与模型可见会话保持一致。TUI 渲染 Markdown 文本与推理、token 用量、最新 `todo/write` 计划，以及各工具定义通过 `presentCall` 和 `presentResult` 方法生成的工具卡片。进行中的分片与工具调用会更新同一组组件，随后由完成事件收束状态。 + +agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调用 `agent.steer()`。取消、推理显隐、工具卡片展开、重绘、清空 transcript 和退出都只是终端控制。插件注册共享的 `userInteraction` 提供方，以排队的键盘浮层呈现问题；agent 行为和答案日志仍由既有服务负责。 + +### 终端所有权 + +在模型输出、会话数据、工具呈现、问题、配置或诊断信息进入 pi-tui 或终端标题前，`displayText()` 会把换行之外的 C0 和 C1 控制字符显示为十六进制转义文本。只有 TUI 和 pi-tui 可以生成 ANSI 控制序列。 + +内置配色仅使用标准 16 色 ANSI 前景色和 SGR 属性，正文文字和背景沿用终端默认值，选中项使用反显。因此，宿主终端可以直接按浅色或深色主题重映射界面，无需 TUI 专用主题设置；`color: false` 会移除样式。 + +### 已交付界面 + +确定性的脚本化演示无需网络即可展示提示词提交、流式模型输出，以及 ANSI 配色在深色和浅色终端主题下的效果。 + +![脚本化 TUI 交互](../../../assets/tui/jokes-dynamic.gif) + +| 深色终端 | 浅色终端 | +| --- | --- | +| ![深色终端中的 TUI](../../../assets/tui/jokes-dark.png) | ![浅色终端中的 TUI](../../../assets/tui/jokes-light.png) | + +## 验证 + +已实现的 [TUI 终端状态快照 RFC](../testing/2026-07-18-tui-terminal-state-snapshots.md) 规定四层验证契约：直接行为测试、瞬态语义终端快照、通过生产工具执行的已录制 JSONL 流程，以及 Loader/PTY 冒烟测试。包（package）README 负责记录配置、命令、模型可见效果和当前限制。 + +## 曾考虑的替代方案 + +- **把 readline 与全屏模式都保留在 `@deepseek-ai/dsh-stdio` 中**：不予采纳，因为逐行输出和差分 TTY 渲染具有不同的依赖、输入规则、日志所有权和资源清理义务。拆分为独立包可以让管道安全契约保持精简、明确。 +- **当任一进程流不是 TTY 时，让 TUI 插件静默降级**：不予采纳，因为回退会掩盖部署错误并改变交互语义。应用包可以通过 `auto` 选择入口；明确挂载的 TUI 会快速失败。 +- **把 TUI 接线与测试保留在 readline `coding-agent` 叶节点下**：不予采纳，因为一个叶节点会代表两个不同入口，也会破坏它与 `acp-agent` 的对称性。独立的 `tui-agent` 叶节点负责 TUI 浮层和测试，同时复用 coding agent 的后端组合。 + +## 后果 + +- 交互式终端获得带状态的 Markdown、卡片、计划和提问界面，同时不会改变管道与自动化使用的逐行协议。 +- TUI 会引入 pi-tui 依赖并严格要求 TTY；非 TTY 部署在组合时选择 `@deepseek-ai/dsh-stdio`。 +- 会话投影使恢复和压缩与持久会话保持一致，但只有一个已配置会话拥有 transcript 和编辑器。 +- 工具包通过既有呈现方法扩展终端卡片，无需在 TUI 中增加工具专用分支。 diff --git a/packages/ui/tui/README.md b/packages/ui/tui/README.md index ff1f536754..ce7e9ac2fc 100644 --- a/packages/ui/tui/README.md +++ b/packages/ui/tui/README.md @@ -2,6 +2,8 @@ The interactive terminal front door for DeepSeek Harness agents, built on [`@earendil-works/pi-tui`](https://www.npmjs.com/package/@earendil-works/pi-tui). It requires stdin and stdout TTYs; scripts and Loader pipes should compose [`@deepseek-ai/dsh-stdio`](../stdio/README.md) instead. +The implemented [TUI feature RFC](../../../docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md) owns the front-door decision and shipped interface; the [terminal-state snapshot RFC](../../../docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md) owns its verification strategy. + This package owns interactive terminal presentation and input only. It injects `agents`, `tools`, and `userInteraction`, then drives an agent created or resumed by app or developer code. Agent lifecycle, persistence, and the model-facing [`ask_user_question`](../tool-ask-user/README.md) tool remain separate composition entries. The TUI rebuilds resumed history from the active session surface, renders Markdown responses and reasoning, applies each tool's `presentCall` / `presentResult` intent to terminal, diff, or generic cards, keeps the latest `todo/write` plan above the editor, and presents `ctx.userInteraction` questions as keyboard-driven overlays. Surface replacement events rebuild the transcript so compacted history does not reappear. From ddd3370477fbf420364c9369da4c88c10c0c9786 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:12:16 +0800 Subject: [PATCH 211/323] test(session-persistence): pin rollback journal permissions --- .../session-persistence-sqlite/README.md | 2 +- .../tests/sqlite.spec.ts | 16 ++++++++++++++++ 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index e9066d3748..11fef96dad 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -12,7 +12,7 @@ Each `SessionEvent` maps 1:1 onto a row in an `events` table `(session_id, seq, The repository's Node range supports unflagged `node:sqlite`. The database enables foreign keys and uses the configured journal mode (`wal` by default; use a rollback mode where WAL shared-memory files are unsuitable). `PRAGMA user_version` stores the table-layout version; databases with any other version are rejected because this unreleased format has no migrations. -On filesystems with POSIX modes, the backend requests mode `0700` for missing directories and exclusively creates a missing database with mode `0600` before SQLite opens it; the process umask may further restrict both. New WAL sidecars receive the database's resulting owner-only mode. Existing directories, database files, and sidecars keep their modes; filesystem setup errors other than an existing database fail initialization. These defaults prevent incidental exposure through a permissive process umask, but do not protect database confidentiality or integrity when another principal can replace the database entry in its parent directory. +On filesystems with POSIX modes, the backend requests mode `0700` for missing directories and exclusively creates a missing database with mode `0600` before SQLite opens it; the process umask may further restrict both. New WAL, shared-memory, and persistent rollback-journal sidecars receive the database's resulting owner-only mode. Existing directories, database files, and sidecars keep their modes; filesystem setup errors other than an existing database fail initialization. These defaults prevent incidental exposure through a permissive process umask, but do not protect database confidentiality or integrity when another principal can replace the database entry in its parent directory. ## Contract semantics over rows diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index 4a6b141e04..f26edfa54d 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -406,6 +406,22 @@ describe('SessionPersistenceSqlite: edge cases', () => { await b.dispose() }) + it('creates a persistent rollback journal with owner-only mode', async () => { + if (process.platform === 'win32') return + const path = await freshDbPath() + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(SessionPersistenceSqlite, { path, journalMode: 'persist' }) + const m = meta('persist-permissions') + + await ctx.sessionPersistence.create(m) + await ctx.sessionPersistence.append(m.id, oneTurnLog()) + + expect((await stat(path)).mode & 0o777).toBe(0o600) + expect((await stat(`${path}-journal`)).mode & 0o777).toBe(0o600) + await fiber.dispose() + }) + it('preserves the mode of an existing database file', async () => { if (process.platform === 'win32') return const path = await freshDbPath() From 86d97845dc7a3be558a5b494be667b039b72d9b7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:14:37 +0800 Subject: [PATCH 212/323] docs(agent): remove stale pre-step contracts --- packages/core/agent-loop/src/tool-calls.ts | 3 ++- packages/core/agent/README.md | 1 - 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index 57bfb081b4..13105d3082 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -106,7 +106,8 @@ function parseArguments(raw: string): unknown { * before start; an exclusive reclassification waits for the current pool to * drain and remains for the caller's next barrier. Results and contexts commit * in model order. Abort stops starts, drains and commits started calls, accepts - * their contexts into the owning batch, and throws. + * their contexts into the owning batch, records results for skipped calls, and + * returns an aborted outcome. */ async function runGroup( ctx: Context, diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 8d1870795d..5979b2bb08 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -77,4 +77,3 @@ The handle every plugin programs against: - **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface RFC](../../../docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). - **`HookContext` carries exactly one `MessageSource`** — contributions from several plugins merged onto one tool call collapse under one source; mixed provenance is unrepresentable. - **`SessionStartSource` reserves `'clear'`/`'compact'` with no emitter yet** — only `'startup'`/`'resume'` occur until the driving subsystems land (`TODO(compaction)`). -- **`agent/pre-step`'s `fullSystemPrompt`/`sessionPrefix` parameters are a flagged smell** — compaction is their only consumer; a lazy prompt provider or a compaction-specific pressure seam is the marked revisit. From 5dcf6095cb191d1f13fbc8ebe3d5df570d4d3b2e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:25:40 +0800 Subject: [PATCH 213/323] docs: include JSDoc in type-equiv blocks --- docs/AGENTS.md | 2 +- docs/core-data-structures/approval.md | 24 +++ docs/core-data-structures/bash.md | 113 +++++------ docs/core-data-structures/code-runtime.md | 36 ++++ docs/core-data-structures/compaction.md | 1 + docs/core-data-structures/core.md | 161 ++++++++------- docs/core-data-structures/filesystem.md | 99 +++++++++ docs/core-data-structures/llm-streaming.md | 29 +++ docs/core-data-structures/persistence.md | 34 ++-- docs/core-data-structures/sandbox.md | 40 +++- docs/core-data-structures/scope.md | 10 + docs/core-data-structures/session-query.md | 64 +++++- docs/core-data-structures/session.md | 191 ++++++++++++------ docs/core-data-structures/skills.md | 45 ++++- docs/core-data-structures/spill.md | 27 +++ docs/core-data-structures/subagent.md | 139 +++++++++++++ docs/core-data-structures/system-prompt.md | 20 ++ docs/core-data-structures/tasks.md | 16 ++ docs/core-data-structures/token-meter.md | 2 + docs/core-data-structures/tools.md | 105 +++++++++- docs/core-data-structures/user-interaction.md | 7 + docs/core-data-structures/web.md | 51 ++++- docs/core-data-structures/workflow.md | 50 +++++ docs/development.i18n.yaml | 4 +- docs/development.md | 4 +- docs/development.zh.md | 4 +- ...2026-06-20-core-data-structures-catalog.md | 10 +- scripts/type-equiv.manifest.json | 2 +- scripts/verify-type-equiv.ts | 60 ++++-- 29 files changed, 1068 insertions(+), 282 deletions(-) diff --git a/docs/AGENTS.md b/docs/AGENTS.md index 0c305e87c8..dc06018c16 100644 --- a/docs/AGENTS.md +++ b/docs/AGENTS.md @@ -27,7 +27,7 @@ Placement: bugs → postmortems; rationale → RFCs; procedures → cookbooks; t - **Document current state, not change history.** Avoid "previously/now/no longer", PRs, commits, and stack positions in durable prose; name the live mechanism. Put change stories in commits, PRs, RFCs, or postmortems. - **Write an RFC in the same PR for decisions a maintainer may reasonably revisit.** Mechanical or self-evident changes need none ([when to write one](rfc/README.md)). - **One physical line per paragraph** (`verify-md-wrap`): use editor soft-wrap. Code blocks, tables, and list structure keep their formatting; code comments stay under the linter's column limit. -- **Fenced `ts` blocks must compile** (`doc-typecheck`); a pasted type definition is fenced ` ```ts type-equiv ` and registered in the manifest so it cannot drift ([mechanics](development.md#documenting-types-verbatim-ts-type-equiv)). +- **Fenced `ts` blocks must compile** (`doc-typecheck`); a pasted type declaration and its original JSDoc are fenced ` ```ts type-equiv ` and registered in the manifest so neither can drift ([mechanics](development.md#documenting-types-verbatim-ts-type-equiv)). - **The [core-data-structures catalog](core-data-structures/core.md) updates in the same change** that reshapes a documented type. `verify-type-equiv` catches drifted pastes, not never-documented new types ([what counts as core](core-data-structures/core.md#what-counts-as-core)). - **Bilingual pairs update together**: editing either side obligates the counterpart and a re-record in the same change ([i18n contract](i18n/README.md)). - **Comments and JSDoc state complete contracts, not reasoning transcripts.** Preserve behavior, conditions, timing, modality, exceptions, consequences, and non-obvious orientation; delete implementation narration, test walkthroughs, review analysis, and code restatement. Keep the local contract and link to its owning rationale. Use [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for required coverage, decision rules, and examples. diff --git a/docs/core-data-structures/approval.md b/docs/core-data-structures/approval.md index e8820ccfeb..8634415a62 100644 --- a/docs/core-data-structures/approval.md +++ b/docs/core-data-structures/approval.md @@ -9,12 +9,20 @@ Source: [`packages/ui/user-approval/src/index.ts`](../../packages/ui/user-approv Every request receives a fresh `ApprovalRequestId`. The brand pairs the `approval/asked` and `approval/decided` audit events without making approval ids interchangeable with tool-call or agent/session ids. ```ts type-equiv +/** + * Pairs one `approval/asked` audit event with its `approval/decided`. + * Service-issued (one fresh id per {@link ApprovalService.request} call). + */ type ApprovalRequestId = Branded<'ApprovalRequestId'> ``` `ApprovalOutcome` is closed and fail-closed. `allowed-once` grants only the asked-about action; callers deny on `rejected`, `cancelled`, and `unavailable`. A missing, non-owning, throwing, or non-conforming answerer becomes `unavailable` rather than opening the gate. ```ts type-equiv +/** + * Closed approval outcomes: a one-shot grant, explicit rejection, withdrawn + * request, or unavailable answerer. Callers fail closed on `unavailable`. + */ type ApprovalOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable' ``` @@ -23,6 +31,18 @@ type ApprovalOutcome = 'allowed-once' | 'rejected' | 'cancelled' | 'unavailable' `ApprovalPolicy` determines what happens before interactive answerers run. `ask` delegates to the composed answerer chain, whose no-answer default is `unavailable`; `never` deterministically returns `rejected` without dispatching any answerer. The effective value is the last `approval/policy` event in the session log, falling back to the service config. `setApprovalPolicy(session, policy)` is the single write path, so replay reconstructs the override. ```ts type-equiv +/** + * A session's approval policy — what happens to an {@link ApprovalService} + * ask BEFORE any interactive answerer sees it: + * + * - `'ask'` (the default) — delegate to the composed answerers; with none + * composed the chain falls through to the fail-closed `'unavailable'` + * (exactly today's behavior). + * - `'never'` — never prompt anyone: every ask resolves `'rejected'` + * deterministically. The strict headless stance (CI, unattended runs) and + * the only policy value stated in the system prompt — unlike `'ask'`, its + * outcome is knowable without asking, so stating it cannot overclaim. + */ type ApprovalPolicy = 'ask' | 'never' ``` @@ -33,6 +53,10 @@ The prompt section states the deterministic `never` behavior and records either `ApprovalRequest` identifies the agent and tool action closely enough to route and audit the question. It deliberately omits tool arguments: an answerer attaches the prompt to the already-streamed tool call through `callId` instead of rendering a second copy that could drift. ```ts type-equiv +/** + * Readonly same-process permission question. `callId` links to an already + * presented tool call, so arguments are not duplicated here. + */ interface ApprovalRequest { /** * The agent on whose behalf the question is asked. Routes the question (a diff --git a/docs/core-data-structures/bash.md b/docs/core-data-structures/bash.md index c61c24add6..060d249eb7 100644 --- a/docs/core-data-structures/bash.md +++ b/docs/core-data-structures/bash.md @@ -9,10 +9,12 @@ Source: [`packages/bash/bash/src/types.ts`](../../packages/bash/bash/src/types.t `DSH_*` variables are Harness-owned child-process facts. The model-facing bash tool collects them through `ctx.bashEnv` and passes them through `BashExecRequest.dshEnv`; executors remove inherited `DSH_*` names before merging the current snapshot. ```ts type-equiv +/** One environment key inside the managed {@link DSH_ENV_PREFIX} namespace. */ type DshEnvironmentKey = `${typeof DSH_ENV_PREFIX}${string}` ``` ```ts type-equiv +/** Trusted DeepSeek Harness variables for one bash execution. */ type DshEnvironment = Readonly> ``` @@ -21,6 +23,12 @@ type DshEnvironment = Readonly> The seam separates the **model-/plugin-facing request** (optional `workdir`/`timeoutMs`/`stdoutMaxBytes`, filled from config or request policy) from the **fully-resolved spec** the executor acts on (those fields required). The tool layer calls `ctx.bash.resolve(request)` between them — this is the repo's "explicit > implicit at package seams" rule made concrete: the reader of a `BashExecSpec` never wonders where the working directory or output budget came from. ```ts type-equiv +/** + * A caller's execution REQUEST: `workdir` and `timeoutMs` are optional and + * filled by {@link BashExecutor.resolve} from the implementation's config. + * This is the model-/plugin-facing shape; pass it to `resolve()` to obtain a + * fully-resolved {@link BashExecSpec}. + */ interface BashExecRequest { command: string /** Working directory override (default: implementation-configured). */ @@ -59,24 +67,17 @@ interface BashExecRequest { * reject non-`DSH_*` names supplied through this managed channel. */ dshEnv?: DshEnvironment | undefined - /** - * Explicit per-call sandbox-policy input, overriding the executor's - * configured default mode for THIS call. Never a silent default: a - * consumer sets it only from an explicit policy source — an - * `'allowed-once'` grant a human just issued through `ctx.approval` (the - * escalation flow in the sandbox RFC § Escalation, which outranks), or the - * session's standing override folded from its own `bash/sandbox-mode` - * events (the sandbox RFC § Per-session mode switching — the user's recorded per-session - * choice). A sandboxing executor confines THIS call under the given mode; - * a non-sandboxing executor carries the field and confines nothing (the - * tool layer stamps neither escalation nor overrides without a sandboxing - * executor — see {@link BashExecutor.sandboxMode}). - */ + /** Explicit per-call sandbox mode override. */ sandboxMode?: SandboxMode | undefined } ``` ```ts type-equiv +/** + * A resolved execution spec. {@link BashExecutor.resolve} fills and caps the + * required fields; {@link BashExecutor.start} ignores `timeoutMs` because + * background processes have no executor timeout. + */ interface BashExecSpec { command: string workdir: string @@ -88,31 +89,18 @@ interface BashExecSpec { stdoutMaxBytes: number /** Abort signal — implementations kill the command when it fires. */ signal?: AbortSignal | undefined - /** - * Bytes to write to the command's stdin (then close it), carried through - * verbatim from {@link BashExecRequest.stdin}. It has no config default, so - * a missing value means "no stdin" and remains an ordinary optional. - */ + /** Bytes to write to stdin before closing it; absent means no stdin. */ stdin?: string | undefined /** - * Extra environment entries, carried through verbatim from - * {@link BashExecRequest.env} and merged by the implementation AFTER its - * credential scrub (an explicit entry wins even when its name matches the - * scrub pattern). OPTIONAL on the spec for the same reason as `stdin` — no - * config default, absent means "no extra env". + * Ordinary environment entries carried through from + * {@link BashExecRequest.env}. `DSH_*` remains reserved for {@link dshEnv}. + * OPTIONAL on the spec for the same reason as `stdin`: absent means no + * ordinary extra environment. */ env?: Record | undefined /** Managed `DSH_*` snapshot; implementations reject ordinary names. */ dshEnv?: DshEnvironment | undefined - /** - * The sandbox mode this call executes under, required-but-nullable so every - * resolved spec states its policy. A sandboxing executor's `resolve()` stamps - * the effective mode (the request's explicit override, else its configured - * default) so `run()`/`start()` read the spec, never the config; - * a non-sandboxing executor carries the request value through verbatim and - * ignores it (`undefined` under such an executor means what its README says: - * unconfined execution). - */ + /** Resolved sandbox mode; ignored by executors that do not confine. */ sandboxMode: SandboxMode | undefined } ``` @@ -126,24 +114,31 @@ interface BashExecSpec { The outcome of one completed (or killed) foreground run. Orthogonal outcomes are reported **independently** — a process can both time out AND exit 0 because it trapped the signal — so `timedOut`, `aborted`, `signal`, and `exitCode` are each their own field; a caller never reads a cut-short run as a clean success. ```ts type-equiv +/** The outcome of one completed (or killed) foreground run. */ interface BashRunResult { /** Exit code; null when the process died from a signal. */ exitCode: number | null /** Terminating signal (e.g. 'SIGTERM'); null on normal exit. */ signal: NodeJS.Signals | null - /** True when the executor's own timeout killed the command. */ + /** + * True when the executor's own timeout was the FIRST cause to cut the command + * short. Mutually exclusive with {@link aborted}: one fused deadline drives + * both the timeout and the caller's cancellation, so a timeout and an abort + * racing before process close report the single first-abort cause, not both + * (see the [timeout-library RFC](../../../../docs/rfc/implemented/architecture/2026-07-06-timeout-deadline-library.md)). + */ timedOut: boolean - /** True when the caller's AbortSignal killed the command. */ + /** + * True when the caller's `AbortSignal` was the FIRST cause to kill the command + * (and it was not the executor's own timeout). Mutually exclusive with + * {@link timedOut} — see there for the first-cause classification. + */ aborted: boolean /** The effective timeout applied to this run (after defaulting/capping). */ timeoutMs: number stdout: CollectedOutput stderr: CollectedOutput - /** - * Sandbox facts, present iff a sandboxing executor ran the command — an - * unsandboxed executor (e.g. `dsh-bash-local`) never sets it. See - * {@link BashSandboxInfo} for the `denied` classification semantics. - */ + /** Sandbox execution facts, absent for an unsandboxed executor. */ sandbox?: BashSandboxInfo } ``` @@ -151,6 +146,7 @@ interface BashRunResult { Each stream is a `CollectedOutput` — the (possibly truncated) text plus recovery info. When truncated, `text` is the **tail** and the complete stream spills to a private file: ```ts type-equiv +/** One captured stream: the (possibly truncated) text plus recovery info. */ interface CollectedOutput { /** Collected text — the TAIL of the stream when truncated. */ text: string @@ -168,36 +164,19 @@ A sandbox-consuming executor exposes its configured fallback through `BashExecut A sandboxed run reports its mode, conservative denial classification, and enforcement completeness. `runnerFailed` marks a sandbox runner failure before the command ran; foreground execution throws `SANDBOX_UNAVAILABLE`, while a settled background process has only its facts channel. ```ts type-equiv +/** + * Sandbox facts for one run, present iff a sandboxing executor handled it. + * Facts are reported independently of process exit status so callers can + * distinguish command failures from policy denials and runner failures. + */ interface BashSandboxInfo { /** The mode the command actually ran under. */ mode: SandboxMode - /** - * True when the executor classifies this run's failure as the sandbox - * denying a file operation. The classification is CONSERVATIVE (a failed - * exit whose stderr carries a filesystem-permission signature) and reads - * the COLLECTED stderr — the bounded in-memory tail per - * {@link CollectedOutput} semantics, so a signature that survives only in a - * spill file is missed toward `denied: false`. A plain command failure - * keeps `denied: false` even under a sandboxed mode. - */ + /** Whether the sandbox denied a file operation. */ denied: boolean - /** - * How completely the runner enforced `mode`'s file effects — see - * {@link SandboxEnforcement}. Absent exactly when `mode` is - * `danger-full-access`: nothing is confined, so there is no enforcement to - * report. - */ + /** How completely the selected runner enforced the requested mode. */ enforcement?: SandboxEnforcement - /** - * True when the executor classifies this failure as the SANDBOX RUNNER - * itself failing (missing binary, refused profile, fail-closed refusal - * before exec) — the command NEVER RAN; this is a sandbox failure, not a - * task failure, and it outranks `denied` (a runner's own error text can - * contain denial words). Only ever stamped on settled BACKGROUND tasks: a - * foreground run surfaces the same condition as the thrown - * `SANDBOX_UNAVAILABLE` error instead (the foreground path has an error - * channel; a settled task's facts are its only channel). - */ + /** Whether the sandbox runner failed before the command could run. */ runnerFailed?: boolean } ``` @@ -209,6 +188,11 @@ One more piece completes the vocabulary: the `SANDBOX_UNAVAILABLE` error code (o `start()` returns a handle with no id or owner. `dsh-tool-bash` adapts it into `ctx.tasks.start()` hooks; the generic runtime then owns task identity and lifecycle. `done` resolves when the process closes and never rejects, reads remain valid after settlement, and sandbox facts are stamped before `done` resolves. ```ts type-equiv +/** + * A background process handle returned by {@link BashExecutor.start}. It is the + * only access path; buffered output remains readable after exit. Executor + * disposal kills running processes and awaits {@link done}. + */ interface BashProcess { /** Process lifecycle state (settled exactly once). */ status: BashProcessStatus @@ -237,6 +221,7 @@ interface BashProcess { `readOutput()` returns the incremental delta and spill recovery facts: ```ts type-equiv +/** One incremental {@link BashProcess.readOutput} read. */ interface BashProcessRead { /** Output produced since the previous read (stderr in a marked section). */ delta: string diff --git a/docs/core-data-structures/code-runtime.md b/docs/core-data-structures/code-runtime.md index 9237a3cce9..cea69180af 100644 --- a/docs/core-data-structures/code-runtime.md +++ b/docs/core-data-structures/code-runtime.md @@ -9,6 +9,12 @@ Source: [`packages/code-runtime/code-runtime/src/types.ts`](../../packages/code- A `CodeRunRequest` carries **everything the runtime acts on** — per the "explicit > implicit at package seams" rule, defaulting (time budgets, output caps) is the implementation's validated config, never a hidden `??` inside `run()`: ```ts type-equiv +/** + * One run: the program source plus everything the runtime acts on. Per the + * explicit-over-implicit convention, defaulting (time budgets, output caps) + * is the implementation's validated config — a request carries no optional + * tuning knobs for a hidden `??` to fill in. + */ interface CodeRunRequest { /** * The program source, in the runtime's {@link ../index.ts | language}. It @@ -31,6 +37,11 @@ interface CodeRunRequest { The result reports an error as a **field**, never a rejection of `run()` — reporting a failed program is the caller's job, not an exception path (mirroring `BashExecutor.run`'s resolve-on-failure contract): ```ts type-equiv +/** + * The outcome of one run. An error is a FIELD on a resolved result, never a + * rejection of `run()` — reporting a failed program is the caller's job, not + * an exception path. + */ interface CodeRunResult { /** * The program's completion value (its top-level `return`), when it ran to @@ -51,6 +62,13 @@ interface CodeRunResult { Each `CodeBindingNamespace` becomes one global object of async callables inside the program (the Code Mode consumer passes one: `tools`). Arguments and resolutions must be structured-cloneable — a runtime may bridge calls across a serialization boundary — and a runtime treats binding names as hostile input (`__proto__` is an ordinary own property, never a prototype collision): ```ts type-equiv +/** + * A named group of {@link CodeBindingFunction}s the runtime exposes to the + * program as one global object (e.g. `tools`). Function names are arbitrary + * strings — a runtime must treat names like `__proto__` or `constructor` as + * ordinary own properties (null-prototype construction), never as prototype + * collisions. + */ interface CodeBindingNamespace { /** The global identifier the program sees (must be a valid JS identifier). */ global: string @@ -60,6 +78,14 @@ interface CodeBindingNamespace { ``` ```ts type-equiv +/** + * One host-side function exposed to the program as an async callable. The + * runtime bridges calls to it (possibly across a serialization boundary), so + * `args` and the resolution value MUST be structured-cloneable; a runtime + * rejects a non-cloneable value with a descriptive error rather than + * corrupting the run. A rejection of this function surfaces inside the + * program as a rejection of the corresponding call. + */ type CodeBindingFunction = (args: unknown) => Promise ``` @@ -70,6 +96,16 @@ Logs are plain strings in emission order. The runtime captures the program's con Failure kinds are **orthogonal outcomes reported independently** (per [defensive-patterns](../defensive-patterns.md)): a budget expiry is not an exception, an abort is not a timeout, and a substrate death (e.g. OOM) is neither: ```ts type-equiv +/** + * Why a run failed. The kinds are orthogonal outcomes reported independently + * (per docs/defensive-patterns.md): a budget expiry is not an exception, an + * abort is not a timeout, and a substrate death is neither. + * + * - `'exception'` — the program threw or failed to parse/transform. + * - `'timeout'` — an implementation-owned budget expired; the message says which. + * - `'abort'` — {@link CodeRunRequest.signal} fired. + * - `'worker-exit'` — the execution substrate died without settling (e.g. OOM). + */ interface CodeRunFailure { /** The failure class (see the interface doc for each kind's meaning). */ kind: 'exception' | 'timeout' | 'abort' | 'worker-exit' diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 11f895b2a8..ccc212a895 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -23,6 +23,7 @@ These variants are merged inside a `declare module '@deepseek-ai/dsh-session'` b What a successful compaction returns to its caller: the bookkeeping-event seqs, raw summary, shadowed range and seqs, and estimated token count. ```ts type-equiv +/** Result of a successful compaction operation. */ interface CompactionResult { /** The seq of the appended `compact/start` event. */ startSeq: number diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index dbf635922d..dfb59b3ac6 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -36,7 +36,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t | [spill.md](spill.md) | the spill storage seam: `SaveTextSpill`, `SpillOwner`/`SpillSource`, `SpillRef`, the branded `SpillLocator` | | [workflow.md](workflow.md) | the workflow seam: `WorkflowStartRequest`, `WorkflowMeta`, `WorkflowRun`/`Result`, the `workflow/*` event payloads, `WorkflowError` fatality | -> Type definitions on this page are pasted **verbatim** from source and drift-checked by `pnpm run verify-type-equiv` (see [development.md](../development.md#documenting-types-verbatim-ts-type-equiv)). Inline JSDoc is omitted for readability; follow the source link for the full contracts. +> Type declarations and their JSDoc on this page are pasted **verbatim** from source and drift-checked by `pnpm run verify-type-equiv` (see [development.md](../development.md#documenting-types-verbatim-ts-type-equiv)). FIXME(catalog-verbs): the drift gate covers only the nouns (the pasted type shapes); every method surface on these pages is hand-written prose. core-data-structures should probably also generate the *verbs* — the public methods of the cataloged classes — so a signature change cannot silently outdate the catalog. @@ -83,6 +83,7 @@ The `Branded` primitive lives in its own type-only package, [dsh-brand](../.. Source: [`packages/util/brand/src/index.ts`](../../packages/util/brand/src/index.ts) ```ts type-equiv +/** A string carrying a compile-time-only brand `B`. */ type Branded = string & { readonly [BRAND]: B } ``` @@ -95,6 +96,10 @@ A conversation is `Message`s; a message is an array of typed **content blocks**. Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) ```ts type-equiv +/** + * Merge-extensible content blocks keyed by `type`. New core blocks must land + * with adapter, UI, and compaction support. + */ interface ContentBlockMap { 'text': TextBlock 'reasoning': ReasoningBlock @@ -108,6 +113,7 @@ The block interfaces (full fields in source): `TextBlock` (`text`), `ReasoningBl A `Message` is a role plus blocks. Loop-derived assistant messages carry their durable provider/model identity and optional adapter-private replay metadata: ```ts type-equiv +/** Provider ownership and adapter-private replay data for an assistant message. */ interface AssistantProvenance { /** Provider route that produced the message. */ provider: string @@ -123,6 +129,10 @@ interface AssistantProvenance { ``` ```ts type-equiv +/** + * A single message in a conversation history. Loop-derived assistant messages + * always carry provenance; callers may omit it on hand-built foreign history. + */ interface Message { role: 'system' | 'user' | 'assistant' content: ContentBlock[] @@ -134,6 +144,10 @@ interface Message { Where a message came from is itself a merge-extensible sum type: ```ts type-equiv +/** + * Where a message (or injected content) came from. + * Merge-extensible sum type — plugins add their own `kind`s. + */ interface MessageSourceMap { user: { kind: 'user' } plugin: { kind: 'plugin'; plugin: string } @@ -155,6 +169,7 @@ Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) Provider and model discovery uses small provider-neutral descriptors. A model catalog is advisory: routing still keys on a registered provider, and an adapter may accept unlisted model ids. ```ts type-equiv +/** Display metadata for one registered provider route. */ interface LlmProviderInfo { /** Provider route key used by {@link GenerateOptions.provider}. */ id: string @@ -164,6 +179,7 @@ interface LlmProviderInfo { ``` ```ts type-equiv +/** One adapter-discovered model; catalog membership is advisory, not request validation. */ interface LlmModelInfo { /** Provider route that owns this model entry. */ provider: string @@ -177,6 +193,7 @@ interface LlmModelInfo { ``` ```ts type-equiv +/** A single model request, fully assembled. */ interface GenerateOptions { /** Registered provider route selecting the adapter instance. */ provider: string @@ -212,6 +229,10 @@ interface GenerateOptions { Why a model response stopped is a merge-extensible reason: ```ts type-equiv +/** + * Why a model response stopped. + * Merge-extensible so adapters can surface provider-specific reasons. + */ interface FinishReasonMap { 'stop': { kind: 'stop' } 'tool-calls': { kind: 'tool-calls' } @@ -226,6 +247,13 @@ interface FinishReasonMap { `GenerateOptions.tools` carries `ToolSchema` — the JSON-schema description of a tool, as sent to the model. It is declared in dsh-llm (not dsh-tools) precisely because it is part of the request the loop assembles every step: ```ts type-equiv +/** + * JSON-schema description of a tool, as sent to the model. + * + * Declared here (not in dsh-tools) because it is part of {@link GenerateOptions}; + * dsh-tools' ToolDefinition and dsh-system-prompt's PromptAssembly both import + * it from this package. + */ interface ToolSchema { name: string description: string @@ -247,6 +275,11 @@ On the wire, a loop-built request reads in this order: the `system` slot (the re FIXME(call-config-shape): revisit the exact definition of this type — which fields are genuinely epoch-level for cache purposes (`model` certainly; the sampling scalars sit here out of caution), and where provider-specific extras (reasoning options, extra body params) belong when an adapter needs them. ```ts type-equiv +/** + * Provider + model + sampling scalars of one conversation's requests. Every field maps + * 1:1 onto the same-named `GenerateOptions` field; the loop builds requests + * from the logged header rather than accepting these per call. + */ interface LlmCallConfig { provider: string model: string @@ -263,6 +296,19 @@ A `Session` is an **append-only log** of typed `SessionEvent`s — the single so Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts) ```ts type-equiv +/** + * One immutable entry in the session log. + * + * A proper discriminated union over `type` (not independent `type`/`data` + * unions), so `switch (event.type)` narrows `event.data` without casts. + * + * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: + * they only exist on {@link SurfaceEventType} variants (`user/message`, + * `assistant/message`, `tool/result`, `context/message`, `steering/message`). + * Non-surface events (boundary markers, chunks, usage, errors) never carry + * surface metadata — the compiler enforces this at `Session.append()` + * call sites. + */ type SessionEvent = { [K in SessionEventType]: { type: K @@ -275,7 +321,9 @@ type SessionEvent = { /** * Seq numbers of events that are provenance sources of this event * (e.g. the `assistant/chunk` seqs that built an `assistant/message`, - * or the surface nodes shadowed by a compaction replace node). + * or the surface nodes shadowed by a compaction replace node). An + * `assistant/message` may carry a present empty array for a known empty + * provider stream; omission means unrecorded provenance. */ sourceEventSeqs?: number[] /** How this event entered the surface; absent for non-surface events. */ @@ -295,35 +343,29 @@ Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types `InjectOptions` extends ordinary message attribution with context-only framing and durable model-hidden JSON metadata: ```ts type-equiv +/** Options specific to durable synthetic context injection. */ interface InjectOptions extends SendOptions { + /** Keep the canonical context tag, or send caller-owned framing verbatim. */ envelope?: ContextEnvelope + /** Opaque JSON state retained in the session event but hidden from the model. */ meta?: JsonValue } ``` ```ts type-equiv +/** Public agent handle; its concrete implementation is internal to `@deepseek-ai/dsh-agent-loop`. */ interface Agent { + /** The single identity shared with {@link session}. */ readonly id: SessionId readonly options: AgentOptions readonly session: Session readonly status: AgentStatus - - /** - * The agent's scope context (`@deepseek-ai/dsh-scope`, key = this agent): - * registrations through it — tools, prompt sections/variables, listeners, - * restrictions — are visible to this agent only and unwind when it is - * disposed; `agent.ctx.on('agent/…')` listeners fire only for this agent. - */ + /** Agent-scoped context; its contributions are agent-local, unwind on disposal, and reject registration afterward. */ readonly ctx: Context /** - * Queue a user message. Starts a turn when idle; otherwise waits for the next - * turn. Content and the resolved source are accepted as one detached, - * deeply-frozen lossless-JSON record before notification or enqueue, so - * caller or `agent/queued` listener in-place mutation cannot change later - * log/model input. Throws synchronously when either value is not losslessly - * JSON-serializable; `agent/prompt-submit` may still return an explicit - * replacement. + * Queue detached, frozen lossless-JSON input; starts a turn when idle. + * Invalid input throws synchronously before notification or enqueue. */ send(content: ContentBlock[], options?: SendOptions): void @@ -335,77 +377,25 @@ interface Agent { steer(content: ContentBlock[], options?: SendOptions): void /** - * Inject in-session context (file-change notices, skill content, cron - * notifications, …): appends a `context/message` session event the next model - * request sees at its chronological position, rendered as synthetic context - * rather than a user prompt. The default uses the canonical context tag; - * `options.envelope: 'raw'` preserves caller-owned framing. Does not run the - * model. - * - * In an open turn, inject appends at the current log position except while - * the current tool-call batch executes: accepted context waits FIFO until the - * batch settles, then appends after every recorded result and before turn - * close even when execution is interrupted. - * - * Turn-enclosure (the turn-enclosure RFC): an inject while a turn is open joins that turn; - * an inject while idle wraps its `context/message` in a one-shot `injection` - * turn (`turn/start` → `context/message` → `turn/end`) and checkpoints it for - * durability, so every event stays inside a turn and a persistence backend - * never loses a between-turn notice. The idle checkpoint is fire-and-forget - * (inject is synchronous): a failing flush is reported via `agent/error` - * (step `0`) and the logger, never thrown into the caller. - * - * Live-adapter review has validated the canonical tagged-envelope rendering - * against current DeepSeek behavior; provider-specific mismatches belong in - * that adapter, not in the canonical session vocabulary. + * Append detached model-facing context without running the model. An open-turn + * injection joins at the current log position unless the current tool batch is + * executing; then it waits FIFO until that batch settles and drains before turn + * close even when interrupted. Idle injection uses a one-shot turn and durability + * checkpoint. Disposal awaits idle checkpoints; flush failures report through `agent/error`. */ inject(content: ContentBlock[], options?: InjectOptions): void /** - * Cancel ALL pending work for the agent. `cancel()`: - * - * - clears the queued FIFO (un-started prompts never run) and the steering - * FIFO (steering for the cancelled turn is dropped, not re-enqueued); - * - aborts the in-flight step if one is running (the turn ends `aborted`); - * - drops a turn that is about to start (a `cancel()` landing in the - * pre-step window — after a `send()` queued but before the loop flips to - * `running`, or after `running` is emitted but before the first step) so - * that queued prompt does not run and cannot be batched into the cancelled - * turn. - * - * After `cancel()`, `whenIdle()` resolves on the post-cancel quiescent state. - * `cancel()` on an idle agent with nothing queued or running is a safe no-op - * — it does NOT arm anything that would drop a later legitimate prompt. + * Clear queued and steering work, including work waiting to start, and abort + * the active step. The supplied reason is preserved across pre-step and active + * cancellation windows, and `whenIdle()` resolves after cancellation reaches + * quiescence. Idle cancellation is a no-op and does not arm a later cancel. */ cancel(reason?: string): void - /** - * Resolve once the agent has reached quiescence after settling out of - * `running`, or immediately if it is already idle with no queued work. A - * non-owner's quiescence-observation hook: a consumer that does NOT own the - * agent's lifecycle awaits this to proceed only after queued/running work has - * fully stopped, rather than returning while the driver is still streaming or - * about to start a queued turn — without itself tearing the agent down. (A - * lifecycle OWNER does not need it: `AgentHandle.dispose()` already awaits the - * loop-exit promise directly as part of stopping and unregistering. So this is - * for a non-owning observer — e.g. a test awaiting a turn to settle, or a - * monitor — that wants the settle signal but must not dispose the agent.) - * - * "Quiescence", not merely "status changed": a disposed agent emits - * `agent/status('disposed')` from inside its disposer, BEFORE the driver loop - * has unwound — so `whenIdle()` resolving on `disposed` must wait for the loop - * to actually exit (the implementation chains the loop-exit promise), not just - * observe the status flip. A mid-step disposal that never reaches `idle` still - * unblocks the await this way. - */ + /** Resolve at idle quiescence; disposal waits for driver exit rather than only the status transition. */ whenIdle(): Promise - // Subagent delegation is realized on top of this interface by the - // `@deepseek-ai/dsh-subagent` seam, not by a method here: a backend creates - // the child through `ctx.agents.create` (fork seeds the child Session with a - // balanced prefix of the parent's log via `CreateAgentOptions.seed`; spawn - // starts fresh) and drives it as an ordinary Agent handle, so steer() and - // event subscription work uniformly. See docs/core-data-structures/subagent.md. } ``` @@ -420,10 +410,13 @@ Each `agent/*` interception waterfall returns a small, seam-specific typed union Source: [`packages/core/agent/src/types.ts`](../../packages/core/agent/src/types.ts) ```ts type-equiv +/** Model-facing context injected by a listener; `source` prevents plugin text from being labeled as user input. */ interface HookContext { content: ContentBlock[] source: MessageSource + /** Keep the canonical context tag, or use caller-owned framing verbatim. */ envelope?: ContextEnvelope + /** Opaque JSON state retained in the session event but hidden from the model. */ meta?: JsonValue } ``` @@ -431,6 +424,11 @@ interface HookContext { `agent/prompt-submit` returns a `PromptDecision` (allow a drained queued message — optionally rewriting its `content` or attaching `additionalContexts` — or block it; a batch whose every prompt is blocked opens a zero-step turn that ends `rejected`): ```ts type-equiv +/** + * Prompt interception result. `allow.content` replaces the prompt and each + * `additionalContexts` entry becomes a separate context message. `block` records a + * durable `prompt/blocked`; an all-blocked batch ends a zero-step rejected turn. + */ type PromptDecision = | { kind: 'allow'; content?: ContentBlock[]; additionalContexts?: HookContext[] } | { kind: 'block'; reason: string } @@ -439,6 +437,7 @@ type PromptDecision = `agent/turn-continuation` returns a `ContinuationDecision` (the loop's default is `continue` when the step had tool calls or steering was injected, else `stop`; a `continue` `reason` is recorded as next-step steering in the same turn and therefore carries no context envelope or metadata — the typed `/goal` pattern): ```ts type-equiv +/** Turn continuation override; a continue reason is recorded as next-step steering in the same turn. */ type ContinuationDecision = | { action: 'stop' } | { action: 'continue'; reason?: { content: ContentBlock[]; source: MessageSource } } @@ -447,12 +446,18 @@ type ContinuationDecision = `agent/turn-stop` returns the stop-only `ContinuationStop` subset or `undefined`. The loop calls this serial checkpoint after folding the ordinary decision, its reason, and pending steering; a stop is terminal and discards pending steering. ```ts type-equiv +/** + * The terminal subset of {@link ContinuationDecision}. A listener on + * `agent/turn-stop` returns this to make the already-composed continuation + * outcome terminal; `undefined` abstains. + */ type ContinuationStop = Extract ``` `agent/session-start` carries a `SessionStartSource` (why the session lifecycle began; a bridge keys its SessionStart matcher on it): ```ts type-equiv +/** Why a session lifecycle began; seeded creates are `startup`, while persisted loads are `resume`. */ type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact' ``` diff --git a/docs/core-data-structures/filesystem.md b/docs/core-data-structures/filesystem.md index 6438b1ba03..f29258857e 100644 --- a/docs/core-data-structures/filesystem.md +++ b/docs/core-data-structures/filesystem.md @@ -11,8 +11,17 @@ Provider source: [`packages/fs/fs/src/types.ts`](../../packages/fs/fs/src/types. Every operation resolves a user-supplied path to an opaque backend target first. Consumers may display `displayPath`, but must not parse `targetKey` (a branded opaque id) or assume it is a local absolute path. ```ts type-equiv +/** + * A path resolved by a backend into a stable identity. `resolve()` produces + * this; every other operation takes it. + */ interface FsTarget { + /** Opaque key for stale guards and target lookup. */ targetKey: FsTargetKey + /** + * Path for model/UI-facing output. May be a local absolute path, + * workspace-relative path, or remote URI depending on the backend. + */ displayPath: string } ``` @@ -20,19 +29,40 @@ interface FsTarget { The backend owns file-version tokens — the freshness token a write/edit guards against. The policy plugin stores them for stale checks; consumers do not interpret them. Both ids are branded opaque strings. ```ts type-equiv +/** + * Opaque key for stale guards and target lookup. The local backend uses a + * realpath-like string; a remote backend might use a workspace URI or file id. + * Consumers MUST NOT parse it or assume it is a local absolute path. + */ type FsTargetKey = Branded<'FsTargetKey'> ``` ```ts type-equiv +/** + * Opaque file-version token — the freshness token a write/edit guards against. + * The local backend derives it from high-resolution stat identity and freshness + * fields; a remote backend might use a revision id. The policy layer records it + * for stale checks; consumers may display related metadata but MUST NOT + * interpret this token. + */ type FsVersion = Branded<'FsVersion'> ``` `stat` returns metadata (never content), or `undefined` when the target is absent. `type` lets the tool reject directories/special files before reading, and `size` lets it choose `readText` vs `streamText` without probing by failure. ```ts type-equiv +/** + * Metadata about a target — what {@link FileSystem.stat} returns. Lets the + * policy layer reject directories/special files before reading and choose + * `readText` vs `streamText` from `size` without probing by failure. `version` + * is the freshness token. `undefined` from `stat` means the target is absent. + */ interface FsInfo { + /** Opaque freshness token of the target right now. */ version: FsVersion + /** Whether the target is a regular file, a directory, or something else. */ type: 'file' | 'directory' | 'other' + /** Byte size of a regular file, when the backend can report it. */ size?: number } ``` @@ -40,9 +70,18 @@ interface FsInfo { `lstat` is the path-level no-follow metadata primitive. It takes a path instead of an `FsTarget` because `resolve` intentionally follows symlinks to produce stable identity; consumers that need trust-boundary checks can call `lstat` first and reject `symlink` before resolving. ```ts type-equiv +/** + * Metadata about a path without following the final path component when it is a + * symbolic link. Unlike {@link FsInfo}, this path-level probe can report + * `symlink` so consumers with trust-boundary rules can reject repository-owned + * links before resolving a target. + */ interface FsPathInfo { + /** Opaque freshness token of the path entry right now. */ version: FsVersion + /** Whether the path entry is a regular file, directory, symlink, or other. */ type: 'file' | 'directory' | 'symlink' | 'other' + /** Byte size of the path entry, when the backend can report it. */ size?: number } ``` @@ -50,11 +89,20 @@ interface FsPathInfo { `listDir` returns direct child entries in stable name order. Each entry carries the child basename, type, resolved target, and cheap metadata when the backend can report it. It must not read file contents, so `size` is only for regular files and `version` is metadata-derived. Broken or disappeared children may be returned as `other` without metadata; permission or backend I/O failures while listing or resolving child metadata fail the whole listing with `FS_PERMISSION_DENIED` or `FS_IO_ERROR`. ```ts type-equiv +/** + * One direct child returned by {@link FileSystem.listDir}. Listing returns + * metadata and resolved targets only; it must not read file contents. + */ interface FsDirEntry { + /** Basename of the child inside the listed directory. */ name: string + /** Whether the child is a regular file, a directory, or something else. */ type: 'file' | 'directory' | 'other' + /** Resolved child target for follow-up operations. */ target: FsTarget + /** Opaque freshness token when the backend can report metadata cheaply. */ version?: FsVersion + /** Byte size of a regular file, when the backend can report it. */ size?: number } ``` @@ -64,16 +112,33 @@ interface FsDirEntry { Both `writeText` and `editText` take their version guard OPTIONALLY: omit it for an unconditional (bare-provider) mutation, supply it to guard. `writeText`'s guard is an `FsWriteIntent` — `createIfAbsent` creates a missing target and rejects an existing one with `FS_NOT_OBSERVED`; `replaceIfVersion` replaces only when the target exists at the observed version, else `FS_STALE_VERSION`. Omitting `expected` unconditionally creates-or-overwrites. The union itself carries only the two guarded intents; "no guard" is expressed by omission, so write and edit share one symmetric `expected?` shape. ```ts type-equiv +/** + * Guarded write intent. `createIfAbsent` rejects an existing target with + * `FS_NOT_OBSERVED`; `replaceIfVersion` rejects absence or mismatch with + * `FS_STALE_VERSION`. Omitting the intent from `writeText` means unconditional + * create-or-overwrite, not a third union arm. + */ type FsWriteIntent = | { kind: 'createIfAbsent' } | { kind: 'replaceIfVersion'; version: FsVersion } ``` ```ts type-equiv +/** Outcome of a full-file write. */ interface FsWriteOutcome { + /** Whether the write created a new file or replaced an existing one. */ operation: 'create' | 'update' + /** Opaque version of the file after the write. */ version: FsVersion + /** + * The file's content BEFORE the write, or `null` when the file did not exist + * (a create) or was undiffable (binary/non-UTF-8). LF-normalized storage text + * (the diff basis), never a diff — a consumer computes the result-time + * contextual diff from `before`/`after` when `before` is present, else falls + * back to a whole-file diff. + */ before: string | null + /** The file's content AFTER the write, LF-normalized to share `before`'s diff basis. */ after: string } ``` @@ -81,17 +146,29 @@ interface FsWriteOutcome { `editText` is a provider-level mutation, not a `read` plus `write` composed elsewhere. When guarded it verifies the expected version BEFORE literal matching (so a stale edit reports `FS_STALE_VERSION`, not a match failure against newer content); unguarded it edits the current content. Either way it applies the replacement and writes atomically — keeping matching, line-ending handling, the stale check, and atomic replacement inside one mutation critical section — and a missing target reports `FS_STALE_VERSION` on both paths. ```ts type-equiv +/** A literal-replacement edit request. */ interface FsEditRequest { + /** Literal non-empty text to replace. Must match exactly (after line-ending normalization). */ oldString: string + /** Literal replacement text. An empty string deletes the matched text. */ newString: string + /** Replace every match instead of requiring exactly one. */ replaceAll: boolean } ``` ```ts type-equiv +/** Outcome of a literal edit. */ interface FsEditOutcome { + /** Opaque version of the file after the edit. */ version: FsVersion + /** + * The file's content BEFORE the edit. Raw storage text (LF-normalized by the + * backend), never a diff — a consumer computes the result-time contextual diff + * (the applied hunk with context) from `before`/`after`. + */ before: string + /** The file's content AFTER the edit. */ after: string } ``` @@ -107,8 +184,20 @@ interface FsEditOutcome { The policy plugin needs just enough execution context to derive the observed-state owner by narrowing the opaque `object` actor the `fs/*` events carry. `ToolExecution` satisfies this shape, so `dsh-tool-fs` passes its execution object through as the actor without making `dsh-fs-policy` import the tool, agent, or session packages. ```ts type-equiv +/** + * Minimal structural view of a tool execution the policy plugin needs to derive + * an observed-state owner. `@deepseek-ai/dsh-tools`' `ToolExecution` satisfies + * this shape, so the tool passes its `exec` straight through as the opaque + * `object` actor on the `fs/*` events; this plugin narrows that actor to this + * shape without importing `dsh-tools`, `dsh-agent`, or `dsh-session`. + * + * The owner is `agent.session` when present. It is treated as an opaque object + * identity (a `WeakMap` key); this package never reads any of its fields. + */ interface FsPolicyExec { + /** The agent on whose behalf the call runs, when there is one. */ agent?: { + /** The session that owns observed-file state, used as an opaque key. */ session?: object } } @@ -119,10 +208,15 @@ interface FsPolicyExec { A text read is bounded by line window, byte cap, and backend limits. The outcome the model-facing `read` tool renders is purely presentational; there is no `full`/`partial` view — authorization is freshness-based (the tool emits `fs/observed` with the stat's version directly), so any windowed read can authorize a later write/edit when the file is unchanged. Read windowing and this outcome shape live in `dsh-tool-fs` (the executor that owns the read), not in the policy plugin. ```ts type-equiv +/** Outcome of a bounded text read — what {@link formatReadOutput} renders. */ interface FileReadOutcome { + /** 1-based first line requested. */ offset: number + /** Returned lines, already numbered. */ lines: FileTextLine[] + /** Total line count in the file, unless `truncatedByBytes` stopped scanning early. */ totalLines: number + /** Whether selected output hit the byte cap before EOF or the requested limit. */ truncatedByBytes?: true } ``` @@ -136,6 +230,11 @@ Observed state is a `WeakMap>` held inside th Filesystem failures use stable `FsErrorCode` strings carried by `FsError` (`HarnessError`). The tool registry preserves `{ name, code }` on error results, so retry, permission, and UI layers can branch without parsing text. ```ts type-equiv +/** + * Stable, machine-routable codes for filesystem failures. Carried on + * {@link FsError}; the tool registry surfaces `{ name, code }` on `isError` + * results so retry/permission/UI layers can branch without parsing messages. + */ type FsErrorCode = | 'FS_NOT_FOUND' | 'FS_NOT_DIRECTORY' diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index f9489a6d7f..0ef9ae02f7 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -9,6 +9,13 @@ Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) A streaming response interleaves several typed blocks (text, reasoning, multiple tool calls). `index` ties each delta to its block; `block-end` carries the fully-assembled `ContentBlock` so consumers don't have to re-assemble deltas themselves. It is a **closed** discriminated union — a `switch` over `type` ends with `assertNever`, so adding a variant breaks compilation at every consumer that must handle it. ```ts type-equiv +/** + * Raw streaming protocol emitted by adapters. + * Block indexes correlate interleaved deltas, and `block-end` carries the + * assembled block. Adapters emit usage before the terminal finish and nothing + * afterward; tool arguments remain raw JSON strings. Failures either throw or + * end with `error`/`aborted`, and consumers must handle both paths. + */ type StreamChunk = | { type: 'block-start'; index: number; blockType: ContentBlockType } | { type: 'text-delta'; index: number; text: string } @@ -41,9 +48,19 @@ This contract was pinned down by two deliberately independent implementations: ` The static public application identity every adapter sends to providers ([`packages/llm/llm/src/attribution.ts`](../../packages/llm/llm/src/attribution.ts)). `attributionHeaders(identity?)` maps it to the standard `User-Agent` header only; OpenRouter-specific app attribution headers are intentionally not supported by this contract. The default `APP_IDENTITY` sources its version from the package manifest; every field is a public product fact - no secrets, paths, session ids, or per-user identifiers, and nothing per-request may influence the values. Rationale: [Mandatory `User-Agent` attribution](../rfc/implemented/architecture/2026-06-21-mandatory-app-attribution-headers.md). ```ts type-equiv +/** + * Static public application identity sent to LLM providers. + * + * Every field is a public product fact, safe on every request: no secrets, + * local paths, session ids, prompt text, or per-user identifiers belong here, + * and nothing per-request may influence the values. + */ interface AppIdentity { + /** `User-Agent` product token (lowercase, hyphenated). */ product: string + /** Product version; sourced from package metadata, never hand-copied. */ version: string + /** Public home URL of the app, used as the `User-Agent` comment. */ url: string } ``` @@ -53,6 +70,14 @@ interface AppIdentity { Per-call token accounting. Counts are **disjoint**: `inputTokens` is uncached input only; cached input is reported separately, and billed input is the sum of the three. Adapters whose providers fold cache hits into a single prompt total (DeepSeek's `prompt_tokens`) subtract them back out. ```ts type-equiv +/** + * Token accounting for one model call (cache fields are optional). + * + * Counts are DISJOINT: `inputTokens` is uncached input only; cached input is + * reported separately as `cacheReadTokens`/`cacheWriteTokens` (billed input = + * sum of the three). Adapters whose providers fold cache hits into a total + * prompt count (DeepSeek's `prompt_tokens`) subtract them out. + */ interface TokenUsage { inputTokens: number outputTokens: number @@ -73,6 +98,10 @@ interface TokenUsage { `ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`: ```ts type-equiv +/** + * Merge-extensible content blocks keyed by `type`. New core blocks must land + * with adapter, UI, and compaction support. + */ interface ContentBlockMap { 'text': TextBlock 'reasoning': ReasoningBlock diff --git a/docs/core-data-structures/persistence.md b/docs/core-data-structures/persistence.md index c1e02ae743..72ebcc5852 100644 --- a/docs/core-data-structures/persistence.md +++ b/docs/core-data-structures/persistence.md @@ -17,6 +17,11 @@ A backend that reloads a log crashed mid-turn finds an open `turn/start` with no `SessionPersistence.locate(meta)` synchronously resolves a backend-owned independent artifact without reading, creating, or flushing it. JSONL returns its absolute target path; SQLite returns `undefined` because sessions share one database. A returned path can therefore name a file that does not yet exist or lacks the current unflushed turn; it is a location hint, not authorization or a freshness guarantee. ```ts type-equiv +/** + * A backend-resolved, per-session local artifact location. The path is an + * absolute target path and can name an artifact that has not materialized yet. + * Consumers must treat it as a location hint, never as an authorization token. + */ interface SessionLocation { /** Backend-specific artifact kind, for example `jsonl`. */ readonly kind: string @@ -32,6 +37,9 @@ Per-session metadata travels **separately** from the event log: format version, Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/types.ts) ```ts type-equiv +/** + * Immutable validated storage metadata, kept outside the conversation event log. + */ interface SessionHeader { /** * On-disk format version, stamped from {@link SESSION_FORMAT_VERSION} when the @@ -48,13 +56,8 @@ interface SessionHeader { /** The session this one was forked from (seed lineage), if any. */ readonly parentSession?: SessionId /** - * How many leading events were INHERITED via a seed rather than produced by - * this session — the seed boundary. Set when a fork seeds a child with a - * prefix of the parent's log (= the seeded prefix length); absent/0 means the - * session produced all its own events. Persisted so a reload reconstructs the - * boundary instead of re-deriving it from the full stored log, and so a replay - * harness can skip the inherited prefix when deriving the child's OWN script - * (the seeded events are the parent's, not this child's model calls). + * How many leading events were inherited through a seed. Persisting this + * boundary lets resume and replay distinguish parent history from child work. */ readonly seedLength?: number } @@ -65,20 +68,17 @@ interface SessionHeader { Creating a `Session` through the store takes a `seed` (replay/fork an existing event log) and `meta` (the storage-level fields the store folds into a `SessionHeader`). The store fills in `version`/`id` and defaults `createdAt`; the caller supplies the validated absolute `cwd`, the `parentSession` lineage, the `seedLength` seed boundary, and — only when reconstructing a persisted session — the original `createdAt` to preserve it. ```ts type-equiv +/** + * Options for creating a {@link Session} via the store. `seed` replays/forks + * an existing event log; `meta` carries the caller-supplied storage fields the + * store folds into a {@link SessionHeader}. + */ interface CreateSessionOptions { /** Events to seed the new session with (replay/fork). */ readonly seed?: readonly SessionEvent[] /** - * Creation metadata. The store fills in `version`/`id` and defaults - * `createdAt` to now; the caller supplies the storage-level fields (validated - * absolute `cwd`, `parentSession` lineage, the seed boundary `seedLength`, and - * — when reconstructing a persisted session — the original `createdAt` to - * preserve it). - * - * `seedLength` is EXPLICIT, not inferred from `seed.length`: a reconstruction - * (resume/load) seeds the WHOLE stored log, so its `seed.length` is the full - * length, not the original boundary — the caller must pass the persisted - * boundary back. A fresh fork passes its actual seeded-prefix length. + * Storage metadata read once before publication. `seedLength` is explicit + * because a resumed seed contains the full stored log, not only its inherited prefix. */ readonly meta?: { readonly cwd?: string diff --git a/docs/core-data-structures/sandbox.md b/docs/core-data-structures/sandbox.md index 6b7b212373..5b20febc3e 100644 --- a/docs/core-data-structures/sandbox.md +++ b/docs/core-data-structures/sandbox.md @@ -9,18 +9,30 @@ Source: [`packages/sandbox/sandbox/src/index.ts`](../../packages/sandbox/sandbox `SandboxMode` governs filesystem effects only. `read-only` denies writes except the required `/dev/null` sink; `workspace-write` permits writes under the workspace root and the backend's promised temp area; `danger-full-access` bypasses confinement. Network and process visibility are outside this vocabulary. ```ts type-equiv +/** + * File-effect policy for confined processes. `read-only` permits only required + * sinks such as `/dev/null`; `workspace-write` also permits the workspace and a + * backend-defined temp area; `danger-full-access` bypasses confinement. Network + * and process visibility are outside this vocabulary. + */ type SandboxMode = 'read-only' | 'workspace-write' | 'danger-full-access' ``` Only the first two modes can be sent to a provider. A `danger-full-access` consumer spawns its original argv and does not call `ctx.sandbox`. ```ts type-equiv +/** A confining (non-`danger-full-access`) mode — the modes a {@link SandboxPolicy} can carry. */ type ConfinedSandboxMode = Exclude ``` Enforcement is a reported fact. `full` means the backend governs every file effect promised by the mode; `partial` means an active backend or older kernel ABI governs only a subset, so consumers that require the absolute promise must reject or surface that distinction. ```ts type-equiv +/** + * Enforcement completeness for this host. `partial` means an active backend or + * older kernel ABI cannot govern every promised file effect; callers requiring + * an absolute boundary must not treat it as `full`. + */ type SandboxEnforcement = 'full' | 'partial' ``` @@ -29,6 +41,15 @@ type SandboxEnforcement = 'full' | 'partial' The policy is fully resolved and carried per call. This permits concurrent consumers and one-shot escalated retries to ask the same provider for different boundaries without mutating provider state. ```ts type-equiv +/** + * What one confined execution is allowed to touch — carried PER CALL, not + * fixed on the provider: two consumers may confine under different policies + * at the same instant (bash under `read-only` while a confined child agent + * needs its state directory writable), and an approved escalated retry is a + * new call with a wider policy. Defaulting/resolution is the consumer's + * explicit step (its config owns the fallback chain); the provider treats + * the policy as fully specified. + */ interface SandboxPolicy { /** The file-effect mode this execution runs under. */ mode: ConfinedSandboxMode @@ -42,6 +63,11 @@ interface SandboxPolicy { `ConfinedArgv` is what the consumer spawns. Besides the replacement argv, it carries the backend's enforcement fact and two orthogonal stderr dialects. `denialSignatures` identify the confined command being blocked while the sandbox works correctly. `runnerFailureSignatures` identify the sandbox runner refusing or failing before it executes the command; consumers check these first and surface a sandbox infrastructure failure, never an ordinary task failure. ```ts type-equiv +/** + * A {@link SandboxProvider.confine} result: the argv to spawn in place of + * the caller's own, plus the enforcement completeness the selected backend + * achieves for it. + */ interface ConfinedArgv { /** The wrapped argv (runner, profile, separator, then the caller's argv). */ argv: string[] @@ -57,17 +83,9 @@ interface ConfinedArgv { */ denialSignatures: readonly string[] /** - * How the RUNNER ITSELF failing identifies itself: case-insensitive stderr - * substrings produced when the sandbox binary is missing, refuses its - * profile, or fails closed before exec'ing the command (`bwrap: `, - * `landlock-run: `, `sandbox-exec: ` — each covers both the runner's own - * error prefix and the shell's runner-not-found message). ORTHOGONAL to - * {@link denialSignatures}: a denial is the confined COMMAND being blocked - * (the sandbox working as designed); a runner failure means the command - * NEVER RAN and must surface as a sandbox failure, not a task failure — - * consumers check these signatures FIRST (a runner's own error text may - * contain denial words, e.g. an unopenable grant root reporting - * `Permission denied`). + * Case-insensitive signatures for runner failure before command execution. + * Consumers check these before denial signatures: runner failure means the + * command never ran, while denial means confinement worked and blocked it. */ runnerFailureSignatures: readonly string[] } diff --git a/docs/core-data-structures/scope.md b/docs/core-data-structures/scope.md index 66d5f40de9..d79f464b3e 100644 --- a/docs/core-data-structures/scope.md +++ b/docs/core-data-structures/scope.md @@ -9,12 +9,18 @@ Source: [`packages/core/scope/src/index.ts`](../../packages/core/scope/src/index `ScopeKey` is an opaque object identity. The shipped loop uses the live `Agent` object as its own key, but the primitive never inspects the object. ```ts type-equiv +/** An opaque, identity-compared scope key. */ type ScopeKey = object ``` `Scoped` is the compile-time brand on the opaque routing receiver returned by `scopeTarget(base, key)`. Scope-filtered event declarations require this carrier as their `this` type, while the real event subject remains an explicit argument. ```ts type-equiv +/** + * A routing-only event receiver built by {@link scopeTarget}. The type + * parameter records the subject type for dispatch checking; the carrier does + * not expose the subject's properties. Event payloads carry the real subject. + */ type Scoped = object & { readonly [ScopedBrand]: T } ``` @@ -23,9 +29,13 @@ type Scoped = object & { readonly [ScopedBrand]: T } `Scope` pairs the tagged registration context with two teardown surfaces. `rawDispose` preserves the exact Cordis disposer identity needed by an ordered composite effect; `dispose()` is the public shared quiescence boundary for direct and racing callers. ```ts type-equiv +/** A minted registration scope and its quiescent disposal boundaries. */ interface Scope { + /** Context through which scope-owned registrations are made. */ ctx: Context + /** Exact Cordis disposer, used when nesting this scope in an ordered composite effect. */ rawDispose: () => Promise | void + /** Dispose every scope-owned registration; racing calls await the same completion. */ dispose(): Promise } ``` diff --git a/docs/core-data-structures/session-query.md b/docs/core-data-structures/session-query.md index 86d2259f7f..4652358162 100644 --- a/docs/core-data-structures/session-query.md +++ b/docs/core-data-structures/session-query.md @@ -9,23 +9,34 @@ Source: [`packages/session-query/session-query/src/types.ts`](../../packages/ses `SessionRecord` is returned by the cross-corpus list. It exposes source availability independently from the cloned live-preferred header. `SessionEventRecord` is a lightweight raw-log projection; classification uses the same `foldSurface()` transitions as model-history derivation. ```ts type-equiv -export type SessionEventSurface = 'current' | 'shadowed' | 'log-only' +/** Whether an event is current model context, replaced context, or raw-log-only. */ +type SessionEventSurface = 'current' | 'shadowed' | 'log-only' ``` ```ts type-equiv -export interface SessionRecord { +/** Lightweight identity and source availability for one logical session. */ +interface SessionRecord { + /** Cloned session header selected from the live-preferred corpus. */ header: SessionHeader + /** Whether the id currently exists in `ctx.sessions`. */ live: boolean + /** Whether the active persistence backend currently materializes the id. */ persisted: boolean } ``` ```ts type-equiv -export interface SessionEventRecord { +/** Lightweight metadata for one event within a logical session. */ +interface SessionEventRecord { + /** Session that owns the event. */ sessionId: SessionId + /** Monotonic event seq within the session. */ seq: number + /** Discriminant of the session event. */ type: SessionEventType + /** Event timestamp in Unix epoch milliseconds. */ time: number + /** Event placement in the folded session surface. */ surface: SessionEventSurface } ``` @@ -35,24 +46,35 @@ export interface SessionEventRecord { `SessionLineageTrace` carries known parents in immediate-to-outward order and a forest of recursively nested direct descendants. The completeness discriminant makes a known root and a missing parent mutually exclusive. ```ts type-equiv -export interface SessionLineageNode { +/** Recursive descendant node in a session-lineage trace. */ +interface SessionLineageNode { + /** Detached logical-corpus record for this descendant. */ session: SessionRecord + /** Direct children, each carrying its own recursive descendants. */ descendants: SessionLineageNode[] } ``` ```ts type-equiv -export type SessionLineageTrace = { +/** Known ancestry and descendants for one logical session. */ +type SessionLineageTrace = { + /** Detached record for the session that was traced. */ target: SessionRecord + /** Known parents from the immediate parent outward. */ ancestors: SessionRecord[] + /** Complete known descendant trees rooted at the target's direct children. */ descendants: SessionLineageNode[] } & ( | { + /** The complete parent chain is present in the logical corpus. */ complete: true + /** Detached record at the top of the complete lineage. */ root: SessionRecord } | { + /** The parent chain leaves the visible logical corpus. */ complete: false + /** First parent id that is not present in the logical corpus. */ unresolvedParentId: SessionId } ) @@ -63,20 +85,31 @@ export type SessionLineageTrace = { The request addresses one raw seq and optional neighboring counts. The result carries a `SessionHeader` rather than availability flags so a known live target can remain independent of persistence health. ```ts type-equiv -export interface SessionEventReadRequest { +/** Request for one event plus raw neighboring log context. */ +interface SessionEventReadRequest { + /** Session that owns the target event. */ sessionId: SessionId + /** Target event seq. */ seq: number + /** Number of preceding raw events to include. */ before?: number + /** Number of following raw events to include. */ after?: number } ``` ```ts type-equiv -export interface SessionEventWindow { +/** Full target event and a bounded raw-log window. */ +interface SessionEventWindow { + /** Cloned header for the live-preferred source read. */ session: SessionHeader + /** Full cloned target event. */ target: SessionEvent + /** Full cloned events from `startSeq` through `endSeq`. */ events: SessionEvent[] + /** First seq included in `events`. */ startSeq: number + /** Last seq included in `events`. */ endSeq: number } ``` @@ -86,19 +119,29 @@ export interface SessionEventWindow { Event traces distinguish positional surface replacement from logged provenance. Every seq list contains direct links except `replacementChain`, which follows immediate replacers from the target to the final positional replacement. ```ts type-equiv -export interface SessionEventTraceRequest { +/** Request for direct surface and provenance relationships around one event. */ +interface SessionEventTraceRequest { + /** Session that owns the target event. */ sessionId: SessionId + /** Target event seq. */ seq: number } ``` ```ts type-equiv -export interface SessionEventTrace { +/** Direct surface and provenance relationships for one event. */ +interface SessionEventTrace { + /** Lightweight target record. */ target: SessionEventRecord + /** Immediate positional replacement event, when the target was shadowed. */ replacedBy?: number + /** Positional replacers from the immediate replacement to the final replacement. */ replacementChain: number[] + /** Surface nodes directly removed when the target itself performed a replacement. */ replacedEventSeqs: number[] + /** Direct logged provenance sources in their recorded order. */ sourceEventSeqs: number[] + /** Later events that directly name the target as a provenance source, in log order. */ derivedEventSeqs: number[] } ``` @@ -108,7 +151,8 @@ export interface SessionEventTrace { The closed code union distinguishes request validation, missing targets, malformed surface logs, optional-backend failure, and contradictory source metadata. ```ts type-equiv -export type SessionQueryErrorCode = +/** Stable machine-routable failure taxonomy for exact session reads and traces. */ +type SessionQueryErrorCode = | 'SESSION_QUERY_EVENT_NOT_FOUND' | 'SESSION_QUERY_INVALID_CONFIG' | 'SESSION_QUERY_INVALID_LINEAGE' diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index b0aa7d4fc5..3d3fca045a 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -9,6 +9,7 @@ Source: [`packages/core/session/src/types.ts`](../../packages/core/session/src/t `ContextEnvelope` selects the standard tagged projection or preserves a producer-owned complete frame. The latter changes framing only; the event remains a user-role `context/message` in chronological history. ```ts type-equiv +/** Canonical context-tag framing, or caller-owned framing rendered verbatim. */ type ContextEnvelope = 'context' | 'raw' ``` @@ -17,30 +18,43 @@ type ContextEnvelope = 'context' | 'raw' The append-only event types. Merge-extensible: a plugin declares extra event types via declaration merging — e.g. the [compaction seam](compaction.md) adds `compact/start` / `compact/summary` / `compact/end`, and `@deepseek-ai/dsh-hook-protocol` adds log-only `hook/invoked` / `hook/result` provenance for a hook bridge. Like `compact/*`, these are NOT `SurfaceEventType`s (no `surfaceOp`). The generated [persistence log event catalog](../persistence-catalog.md) enumerates every member — core and merged — with its payload, surface badge, and declaration site. ```ts type-equiv +/** + * The merge-extensible, append-only source of truth for an agent interaction. + * Message history is derived from this log. Every event is lossless JSON and + * sequence numbers stay contiguous, including raw chunks, so persistence can + * store the canonical log verbatim. + */ interface SessionEventMap { + /** + * Opens turn `turn`. `trigger` records what started it — a drained message + * batch or an idle-time injection. The turn is the durability/replay + * boundary: every event sits between a `turn/start` and its matching + * `turn/end` (the turn-enclosure invariant). + */ 'turn/start': { turn: number; trigger: TurnTrigger } + /** + * Closes turn `turn` with the {@link TurnEndReason} that ended it. The loop + * fires the awaited `session/flush` checkpoint at every turn end, so the turn + * boundary is also the durable-commit boundary. + */ 'turn/end': { turn: number; reason: TurnEndReason } + /** Opens step `step` of turn `turn` — one model call plus the tool executions it requested. */ 'step/start': { turn: number; step: number } + /** Closes step `step` of turn `turn`. */ 'step/end': { turn: number; step: number } /** A user-visible prompt (queued message drained at turn start). */ 'user/message': { content: ContentBlock[]; source: MessageSource } /** - * A queued prompt an `agent/prompt-submit` listener VETOED — the durable - * record of a blocked prompt and why. Appended in place of the `user/message` - * the prompt would have become, so the block survives replay even in a MIXED - * batch where another queued prompt is allowed (there the turn does not end - * `rejected`, so the boundary reason alone would not preserve it). `content` - * is the original prompt the listener rejected; `reason` is the veto text - * ({@link PromptDecision} `block.reason`). NOT a {@link SurfaceEventType}: a - * blocked prompt produces no LLM message and never reaches `deriveMessages()`. + * Durable record of a prompt veto and its reason. It is log-only: the blocked + * prompt never enters the model-visible surface, including in a mixed batch. */ 'prompt/blocked': { content: ContentBlock[]; source: MessageSource; reason: string } /** * In-session context injection (file-change notices, subdir AGENTS.md, * skill content, cron notifications, …). Rendered into the derived history * as synthetic context — NOT a user prompt. `envelope: 'raw'` lets a caller - * supply its own complete framing; `meta` is persisted JSON hidden from the - * model. + * own the complete model-facing frame; `meta` is durable JSON state omitted + * from the model projection. */ 'context/message': { content: ContentBlock[] @@ -57,34 +71,29 @@ interface SessionEventMap { * usage record). `usage` is absent when the adapter reported none. */ 'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } + /** + * The model requested one tool invocation: `name` with the raw `arguments` + * JSON string exactly as the model produced it (unparsed). `callId` pairs the + * call with its `tool/result`. + */ 'tool/call': { turn: number; step: number; callId: CallId; name: string; arguments: string } + /** + * A completed tool call's model-facing result, plus an optional tool-private + * `meta` presentation payload. `meta` is opaque to the core (`unknown` — the + * producing tool owns its shape and reads it back in `presentResult`) but MUST + * be JSON-serializable: `Session.append` runtime-validates all event data with + * `isJsonValue`, so a non-serializable `meta` is rejected at the source, and the + * durable log reproduces the identical card on replay. Absent unless the tool + * attaches one (e.g. `dsh-tool-fs` carries its result-time contextual diff here). + */ 'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string }; meta?: unknown } /** Steering content injected between steps of a running turn. */ 'steering/message': { turn: number; content: ContentBlock[]; source: MessageSource } - /** - * The agent's whole todo list, carried as a full snapshot and replaced - * wholesale on each write — the current list is the most recent `todo/write` - * (last-write-wins on replay, no fold). Appended by an owning agent via - * `session.append('todo/write', { todos })`. - * - * NOT a {@link SurfaceEventType}: it produces no LLM message and never reaches - * `deriveMessages()`, so it carries no `surfaceOp` and stays off the surface — - * it is durable, replayable UI state, distinct from the conversation history. - * It is a `SessionEventMap` member riding the existing `session/event` emit, - * not a first-class Cordis `interface Events` notification, so it has no - * cordis-catalog row. - */ + /** Whole-list snapshot; latest write wins on replay. Log-only UI state; never derived history. */ 'todo/write': { todos: TodoItem[] } /** - * Full snapshot of the {@link EpochHeader} the NEXT request is built under, - * with the {@link RequestHeaderReason} it was recorded whole. Appended by - * the loop inside the step, before dispatch, on a loop instance's first - * request-building step (`'initial'`/`'resume'`) or when a later request's - * header changes (`'change'`); always records what the request actually - * used, post-`agent/request`. Reconstruction reads the latest snapshot. NOT a - * {@link SurfaceEventType}: it produces no LLM message — it is the request - * envelope, logged so every request is a pure function of the session log - * (the reconstructability RFC). + * Full header for the next request, appended inside its step before dispatch. + * It is log-only; the latest snapshot reconstructs the request header. */ 'request/header': { header: EpochHeader; reason: RequestHeaderReason } } @@ -95,8 +104,21 @@ interface SessionEventMap { The unit of the `todo/write` event's whole-list snapshot. Deliberately minimal — a `content` line and a three-state `status` (no id, priority, or `activeForm`): the list is replaced wholesale on every write, so entries need no stable identity, and the status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally requires). See the [todo_write RFC](../rfc/implemented/feature/2026-06-29-todo-write-tool.md). ```ts type-equiv -export interface TodoItem { +/** + * One entry in an agent's todo list — the unit of the `todo/write` + * {@link SessionEventMap} event's whole-list snapshot. + * + * Deliberately minimal: a human-readable `content` line and a three-state + * `status`. No id, priority, or `activeForm` — the list is replaced wholesale + * on every write (last-write-wins), so entries need no stable identity, and the + * status triple is exactly the ACP `PlanEntryStatus`, so a UI bridge can map a + * todo list onto an ACP `plan` 1:1 (synthesizing the priority ACP additionally + * requires). + */ +interface TodoItem { + /** What this task is — a short imperative line shown in the UI. */ content: string + /** Lifecycle state. `in_progress` marks the single task being worked now. */ status: 'pending' | 'in_progress' | 'completed' } ``` @@ -106,8 +128,13 @@ export interface TodoItem { The request envelope — the `EpochHeader` (call config + rendered system prompt + assembled tool schemas + the session prefix) — is logged session state, so every conversation request is a pure function of the log (the reconstructability RFC). A full `request/header` snapshot with reason `'initial'` or `'resume'` records each loop-instance boundary; a later changed request records another full snapshot with reason `'change'`. `foldRequestHeader(events)` reconstructs the header by selecting the latest snapshot. The event is not a `SurfaceEventType`: it produces no LLM message. ```ts type-equiv -export interface EpochHeader { - /** The conversation's call configuration (provider + model + sampling scalars). */ +/** + * Logged request state outside derived history: call config, system prompt, + * tools, and prefix. The latest full `request/header` snapshot reconstructs it; + * canonical empty optional fields are absent. + */ +interface EpochHeader { + /** The conversation's call configuration (provider, model, and sampling scalars). */ config: LlmCallConfig /** Rendered system prompt text; absent for a system-less request. */ system?: string @@ -131,6 +158,19 @@ Canonical form: an empty system prompt, an empty tool list, and an empty session A proper discriminated union over `type` (not independent `type`/`data` unions), so `switch (event.type)` narrows `event.data` without casts. `seq` is the monotonic position in the log (`seq = log.length`); `time` is epoch ms. ```ts type-equiv +/** + * One immutable entry in the session log. + * + * A proper discriminated union over `type` (not independent `type`/`data` + * unions), so `switch (event.type)` narrows `event.data` without casts. + * + * The {@link sourceEventSeqs} and {@link surfaceOp} fields are conditional: + * they only exist on {@link SurfaceEventType} variants (`user/message`, + * `assistant/message`, `tool/result`, `context/message`, `steering/message`). + * Non-surface events (boundary markers, chunks, usage, errors) never carry + * surface metadata — the compiler enforces this at `Session.append()` + * call sites. + */ type SessionEvent = { [K in SessionEventType]: { type: K @@ -143,7 +183,9 @@ type SessionEvent = { /** * Seq numbers of events that are provenance sources of this event * (e.g. the `assistant/chunk` seqs that built an `assistant/message`, - * or the surface nodes shadowed by a compaction replace node). + * or the surface nodes shadowed by a compaction replace node). An + * `assistant/message` may carry a present empty array for a known empty + * provider stream; omission means unrecorded provenance. */ sourceEventSeqs?: number[] /** How this event entered the surface; absent for non-surface events. */ @@ -163,7 +205,12 @@ The five message-producing types (`SurfaceEventType` — `user/message`, `assist ### `SurfaceEventType` — the message-producing subset of event types ```ts type-equiv -export type SurfaceEventType = +/** + * The subset of {@link SessionEventType} values whose events produce LLM + * messages and are eligible to appear on the ordered surface. Only these + * event types may carry {@link SurfaceOp} and {@link SessionEvent.sourceEventSeqs}. + */ +type SurfaceEventType = | 'user/message' | 'assistant/message' | 'tool/result' @@ -174,7 +221,19 @@ export type SurfaceEventType = ### `SurfaceOp` — how an event entered the surface ```ts type-equiv -export type SurfaceOp = +/** + * How a session event entered the ordered surface. Only valid on + * {@link SurfaceEventType} events. + * + * - `'append'`: added to the tail — normal path for user/assistant/tool/context + * messages. + * - `{ op: 'replace', start, end }`: replaces surface nodes from `start` + * (inclusive) through `end` (inclusive) with this node. Both must exist as + * surface nodes in the current surface. `start === end` replaces a single + * node. The node's {@link SessionEvent.sourceEventSeqs} must include every + * shadowed surface node. Used by compaction and possible other manipulations. + */ +type SurfaceOp = | 'append' | { op: 'replace'; start: number; end: number } ``` @@ -184,8 +243,18 @@ export type SurfaceOp = ### `SurfaceIntent` — the parameter to `session.append()` ```ts type-equiv -export interface SurfaceIntent { +/** + * Surface placement and provenance for {@link Session.append}. Required on + * message-producing events and forbidden on log-only events. + */ +interface SurfaceIntent { surfaceOp: SurfaceOp + /** + * Complete known provenance source set. `assistant/message` may use a + * present empty array for a known empty provider stream; omission means its + * provenance was not recorded. Other surface events require a non-empty set + * when this field is present. + */ sourceEventSeqs?: number[] } ``` @@ -199,8 +268,11 @@ The same provenance distinction applies here: only `assistant/message` may carry `Session.surface` returns the session's stable `SessionSurface` view. The same incremental manager validates append candidates before commit and advances this projection from committed events; callers can observe membership and replacement generation but cannot invoke validation. ```ts type-equiv -export interface SessionSurface { +/** Readonly live projection of the message-producing session events. */ +interface SessionSurface { + /** Current surface event sequences in model-visible order. */ readonly nodes: readonly number[] + /** Monotonic count of committed positional replacements. */ readonly replaceGeneration: number } ``` @@ -210,17 +282,25 @@ export interface SessionSurface { `foldSurface(events)` returns detached current event sequences together with the actual sequences shadowed by each declared replacement range. The live manager uses the same transitions without retaining replacement history. Its `replaceGeneration` increments for each committed replacement so incremental consumers can distinguish pure tail growth from a rewrite. ```ts type-equiv -export interface SurfaceFoldReplacement { +/** One replacement operation observed while folding a session surface. */ +interface SurfaceFoldReplacement { + /** Seq of the event that replaced the prior surface range. */ seq: number + /** Declared inclusive start seq of the replaced surface range. */ start: number + /** Declared inclusive end seq of the replaced surface range. */ end: number + /** Actual surface entries removed by the operation, in surface order. */ shadowedSeqs: number[] } ``` ```ts type-equiv -export interface SurfaceFoldResult { +/** Complete result of replaying the surface operations in a session log. */ +interface SurfaceFoldResult { + /** Current surface event sequences in model-visible order. */ nodes: number[] + /** Replacement operations in event order. */ replacements: SurfaceFoldReplacement[] } ``` @@ -248,6 +328,10 @@ An explicit `boundary` lets callers fork from a previous completed turn even if ## What started a turn: `TurnTriggerMap` ```ts type-equiv +/** + * What started a turn. + * Merge-extensible sum type (same pattern as MessageSourceMap). + */ interface TurnTriggerMap { message: { kind: 'message'; source: MessageSource } /** @@ -265,6 +349,9 @@ interface TurnTriggerMap { ## Why a turn ended: `TurnEndReasonMap` ```ts type-equiv +/** + * Why a turn ended. Merge-extensible sum type. + */ interface TurnEndReasonMap { completed: { kind: 'completed' } aborted: { kind: 'aborted'; reason?: string } @@ -276,26 +363,16 @@ interface TurnEndReasonMap { */ error: { kind: 'error'; step: number; message: string; code?: string } disposed: { kind: 'disposed' } + /** At least one step reached its output-token ceiling, even if a plugin continued the turn. */ 'max-tokens': { kind: 'max-tokens' } /** - * The turn's entire prompt batch was BLOCKED before any step ran — every - * drained queued message was vetoed by an `agent/prompt-submit` listener (a - * hook). The turn still opened (so the boundary stays balanced and the block - * is a durable in-turn fact), but ran zero steps. `reason` carries the block - * message from the vetoing decision. Distinct from `aborted` (a user-driven - * cancel) and `error` (a failure): the prompt was rejected by policy, not - * interrupted or broken. A UI renders it as "prompt blocked by hook". + * Policy blocked every prompt before the first step. The zero-step turn still + * records a balanced durable boundary and the veto reason. */ rejected: { kind: 'rejected'; reason: string } /** - * The turn never ended on its own: the process crashed mid-turn and a - * persistence backend later closed the orphaned (open) turn on reload so the - * log stays balanced. SYNTHESIZED by the backend's crash-recovery repair — no - * loop ever emits this. Its events are real (they were durably appended before - * the crash) and are PRESERVED, not discarded: a single turn can be huge in a - * long-horizon task (many steps, large tool output), so truncating it would - * lose real work. The marker records that the turn was cut short, not that the - * model completed it. See the session-persistence RFC. + * A persistence backend closed a crash-orphaned turn on reload. The loop never + * emits this marker, and the events recorded before the crash remain intact. */ interrupted: { kind: 'interrupted' } } diff --git a/docs/core-data-structures/skills.md b/docs/core-data-structures/skills.md index 93189ba2cb..daccb38550 100644 --- a/docs/core-data-structures/skills.md +++ b/docs/core-data-structures/skills.md @@ -11,9 +11,25 @@ Source: [`packages/skill/skill/src/index.ts`](../../packages/skill/skill/src/ind Duplicate names resolve by rank, provider order, then local order; summaries sort by name. A rejected `list()` is logged and skipped without caching the degraded catalog, while malformed candidates fail fast. ```ts type-equiv +/** Provider interface for one source of skills, such as local directories or a remote registry. */ interface SkillProvider { + /** Unique provider name in the `ctx.skills` registry. */ readonly name: string + /** + * List available skill candidates for the current lookup context. Provider + * plugins register synchronously during `apply()`; remote initialization, + * authentication, and discovery are awaited inside this method. Implementations + * should settle promptly when `options.signal` aborts. + * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work. + * @returns provider candidates with precedence ranks and opaque locators. + */ readonly list: (options: SkillLookupOptions) => Promise + /** + * Load a complete skill body for a previously listed candidate. + * @param candidate - the winning candidate originally returned by this provider. + * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work. + * @returns the full skill body, or `undefined` if it is no longer loadable. + */ readonly get: (candidate: SkillCandidate, options: SkillLookupOptions) => Promise } ``` @@ -37,6 +53,7 @@ The project root is the nearest ancestor containing `.git`; without one, the cur Skill names are kebab-case (`^[a-z0-9]+(?:-[a-z0-9]+)*$`). The local provider accepts directory bundles (`/SKILL.md`) and flat Markdown files (`.md`). Nested recursive `**/SKILL.md` discovery is intentionally outside v1. ```ts type-equiv +/** Origin bucket for a skill contribution. The value is prompt-visible metadata, not precedence by itself. */ type SkillSource = 'project-dsh' | 'project-agents' | 'runtime' | 'user-dsh' | 'user-agents' | 'custom' | (string & {}) ``` @@ -45,13 +62,21 @@ type SkillSource = 'project-dsh' | 'project-agents' | 'runtime' | 'user-dsh' | ' `SkillSummary` is the registry's model-invocable summary shape. Consumers choose which fields to render; the session catalog uses only `name` and `description`, never the body or absolute file path. `disableModelInvocation` hides a skill from model listings while allowing trusted code to load it by name. ```ts type-equiv +/** Model-visible skill metadata returned by `ctx.skills.list()` and rendered into request guidance. */ interface SkillSummary { + /** Kebab-case identifier used with the `skill` tool. */ readonly name: string + /** Short routing description shown to the model. */ readonly description: string + /** Optional extra routing guidance shown to the model. */ readonly whenToUse?: string + /** Whether the skill is hidden from model listings while remaining loadable by trusted callers. */ readonly disableModelInvocation?: boolean + /** Discovery source that produced this winning skill. */ readonly source: SkillSource + /** Provider that owns this skill body. */ readonly provider: string + /** Provider-specific base for relative resources. */ readonly resourceBase?: SkillResourceBase } ``` @@ -59,10 +84,15 @@ interface SkillSummary { `SkillCandidate` is the provider-to-registry shape. `locator` is opaque provider state; the registry only stores it and gives it back to the winning provider's `get()`. ```ts type-equiv +/** Provider catalog entry used by the registry to merge and later load skills. */ interface SkillCandidate extends SkillSummary { + /** Lower ranks win duplicate skill names before provider registration order is considered. */ readonly rank: number + /** Opaque provider-owned handle passed back to `provider.get()`. */ readonly locator: unknown + /** Absolute file path when the provider has one. */ readonly path?: string + /** Parsed optional metadata object from provider-specific skill frontmatter. */ readonly metadata?: Readonly> } ``` @@ -70,6 +100,7 @@ interface SkillCandidate extends SkillSummary { `SkillDefinition` is the complete parsed result returned by `ctx.skills.get()` and used by the `skill` tool. `resourceBase` tells the tool how to render relative-resource guidance for local, URL, or provider-managed skills. ```ts type-equiv +/** Optional provider-specific base used by loaded skill bodies to resolve relative resources. */ type SkillResourceBase = | { readonly kind: 'directory'; readonly path: string } | { readonly kind: 'url'; readonly url: string } @@ -77,9 +108,13 @@ type SkillResourceBase = ``` ```ts type-equiv +/** Complete parsed skill definition, including the body loaded by `ctx.skills.get()`. */ interface SkillDefinition extends SkillSummary { + /** Markdown instruction body after any provider-specific metadata removal. */ readonly content: string + /** Absolute file path when the skill came from disk. */ readonly path?: string + /** Parsed optional metadata object from frontmatter. */ readonly metadata?: Readonly> } ``` @@ -87,9 +122,8 @@ interface SkillDefinition extends SkillSummary { Runtime skills use the same complete shape and participate in the same first-wins collection order. The returned disposer removes the contribution and invalidates discovery caches. ```ts type-equiv -type SkillRegistration = Omit & { - readonly provider?: string -} +/** Runtime skill contribution accepted by `ctx.skills.register()`. */ +type SkillRegistration = Omit & { readonly provider?: string } ``` ## Lookup and configuration @@ -97,8 +131,11 @@ type SkillRegistration = Omit & { Skill lookup is cwd-sensitive because providers may expose workspace-local skills, and its optional signal cancels provider work for the caller. Providers receive the same readonly options object used for cache identity and loading. Cancellation is checked before and after catalog selection, including cache hits, and races both discovery and full-definition loading. If no git root is found, the local provider treats the supplied cwd itself as the project root. ```ts type-equiv +/** Caller context used for cwd-sensitive and abortable provider work. */ interface SkillLookupOptions { + /** Workspace selector for the current lookup. */ readonly cwd?: string | undefined + /** Abort discovery or loading work for the current caller. */ readonly signal?: AbortSignal | undefined } ``` @@ -106,7 +143,9 @@ interface SkillLookupOptions { The registry owns only its discovery-cache bound. The local provider owns filesystem roots (`dshHome`, `agentsHome`, and `customSkillDirs`). The consumer owns its catalog description bound. ```ts type-equiv +/** Skill registry configuration. */ interface Config { + /** Maximum number of completed cwd/provider catalogs kept in memory. */ readonly collectCacheMaxEntries?: number } ``` diff --git a/docs/core-data-structures/spill.md b/docs/core-data-structures/spill.md index 4e8ced8258..d046874b0e 100644 --- a/docs/core-data-structures/spill.md +++ b/docs/core-data-structures/spill.md @@ -9,15 +9,28 @@ Source: [`packages/spill/spill/src/types.ts`](../../packages/spill/spill/src/typ `saveText` is the whole seam: persist `content` verbatim, return an opaque locator, a backend-supplied retrieval hint, and the exact byte count. The request carries the save-time storage namespace (`owner`), WHERE it came from (`source`, descriptive provenance for naming and inspection — not access control), and a `suggestedName` the backend may use as a naming hint (it is not a path). ```ts type-equiv +/** One request to persist text to a spill artifact. */ interface SaveTextSpill { owner: SpillOwner source: SpillSource + /** + * A caller-suggested base name (e.g. `web_fetch.txt`). The backend sanitizes + * it to a single safe path segment before use — it is a hint, never a path. + */ suggestedName: string + /** The full text to persist (UTF-8). */ content: string } ``` ```ts type-equiv +/** + * Save-time storage namespace for a spilled artifact. The session id lets a + * backend group storage under the producing session, but the returned + * {@link SpillLocator} is the model-facing handle. Forked sessions inherit + * locators already present in the seeded log; those artifacts are not copied or + * re-owned, and spills produced after the fork use the child session id. + */ interface SpillOwner { sessionId: SessionId } @@ -26,9 +39,17 @@ interface SpillOwner { `SpillOwner.sessionId` is the save-time storage namespace. Forked sessions inherit existing spill locators from the seeded log; those artifacts are not copied or re-owned, and spills produced after the fork use the child session id. A retention-period cleanup may expire old locators with other old session artifacts; the spill seam does not define a per-session cleanup policy. ```ts type-equiv +/** + * Provenance of one spilled artifact — recorded by the backend for a readable + * filename and inspection. Not interpreted for access control; purely + * descriptive. + */ interface SpillSource { + /** The tool whose result was spilled (e.g. `web_fetch`). */ toolName: string + /** The model-issued call id the result belongs to. */ callId: CallId + /** A short human label for the artifact (e.g. `result`). */ label: string } ``` @@ -36,6 +57,7 @@ interface SpillSource { ## The result ```ts type-equiv +/** A saved spill artifact: its locator, byte length, and backend-specific retrieval guidance. */ interface SpillRef { locator: SpillLocator bytes: number @@ -46,6 +68,11 @@ interface SpillRef { `SpillLocator` is a [branded](core.md#branded-ids) model-facing handle returned by the backend. The local backend renders it as a filesystem path; a remote or database backend can render a URI, key, or command token. Consumers treat it as opaque and render it with `retrievalHint` instead of assuming `read` is always the right retrieval mechanism. ```ts type-equiv +/** + * Opaque model-facing handle for one spilled artifact. A local backend may use a + * filesystem path; a remote or database backend may use a URI or key. Consumers + * render it with {@link SpillRef.retrievalHint}, but do not parse it. + */ type SpillLocator = Branded<'SpillLocator'> ``` diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 815438f215..d279f26a9d 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -11,10 +11,22 @@ Source: [`packages/subagent/subagent/src/types.ts`](../../packages/subagent/suba A provider advertises its **start-time** features on a static descriptor the service checks BEFORE a run exists; a request that needs one the provider lacks is rejected loud (`SubagentError('UNSUPPORTED_CAPABILITY')`), never accepted-then-ignored. **Runtime** features (steering, resume) are instead optional methods on [`SubagentRun`](#a-live-run-subagentrun) — the method's presence IS the capability, and TS narrowing is the discovery mechanism. ```ts type-equiv +/** + * Which START-TIME features a provider supports. Checked by the service before delegating to + * {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks + * is rejected with a typed error rather than accepted-then-ignored (the "fail loud, no silent + * degradation" rule). These static flags cover features needed before a run exists; runtime + * capabilities such as steering and resume are optional {@link SubagentRun} methods whose presence + * is the capability. + */ interface SubagentCapabilities { + /** Honor {@link SubagentStartRequest.outputSchema} (structured final output). */ readonly outputSchema: boolean + /** Enforce {@link SubagentStartRequest.maxDepth} (recursion cap). */ readonly depthLimit: boolean + /** Enforce {@link SubagentStartRequest.toolFilter} (child tool scoping). */ readonly toolFilter: boolean + /** Honor {@link SubagentStartRequest.persona} (a per-child persona). */ readonly persona: boolean } ``` @@ -24,14 +36,60 @@ interface SubagentCapabilities { The tool layer builds this request from the model input and its own config; the service validates it against the named provider before `start`. Required `parent` supplies the session cwd, lineage, and delegation depth. Optional output schema, depth, tool filter, and persona require matching capability flags. Unsupported schemas fail at start; in-process backends scope filters and personas to child creation and implement the supported object-rooted schema with a forced capture tool. ```ts type-equiv +/** + * What a caller asks for when starting a subagent. The tool layer builds this + * from the model's `{ description, prompt }` plus its own config; the service + * validates {@link SubagentCapabilities} against the named provider, then + * passes it to {@link SubagentProvider.start}. + */ interface SubagentStartRequest { + /** The task/prompt for the child agent (a user message in the child session). */ readonly prompt: ContentBlock[] + /** + * The spawning ("parent") agent — the one whose tool call started this + * subagent. REQUIRED: in-process backends read `parent.session.header` for + * the working directory, the `parentSession` lineage to stamp on the child, + * and the parent's delegation depth. Out-of-process backends (ACP) ignore it. + */ readonly parent: Agent + /** + * Cancellation signal from the spawning context (the tool's `exec.signal`). + * This is the canonical cancellation channel both before and after startup: + * a provider rejects `start()` after cleaning partial resources when it + * fires before publication, and cancels a published child when it fires + * afterward. + */ readonly signal: AbortSignal + /** Per-child agent options (model and plugin-defined extension fields). */ readonly agentOptions?: AgentOptions + /** + * Object-rooted JSON Schema within `assertSupportedOutputSchema`'s enforced subset. Start rejects + * unsupported schemas or providers without the capability. Data must be plain host-realm JSON; + * a successful child returns the matching value as {@link SubagentResult.structured}. + */ readonly outputSchema?: StructuredOutputSchema + /** + * Optional absolute delegation-depth cap for the child being started: its + * computed depth must be less than or equal to this non-negative safe + * integer. Requires {@link SubagentCapabilities.depthLimit}; rejected at + * start otherwise. + */ readonly maxDepth?: number + /** + * Optional child tool scoping. Requires {@link SubagentCapabilities.toolFilter}; + * rejected at start otherwise. In-process backends apply it as a scoped + * `tools.restrict()` in the child's creation window: the named tools vanish + * from the child's prompt AND refuse to execute (one visibility), with loud + * unknown-name validation. + */ readonly toolFilter?: ToolRestriction + /** + * Optional per-child persona. Requires {@link SubagentCapabilities.persona}; + * rejected at start otherwise. In-process backends register it as a scoped + * `deployment:persona` section on the child, SHADOWING the deployment's + * persona for this child alone — same template semantics as the deployment + * persona (strict `{{…}}` interpolation against the registered variables). + */ readonly persona?: string } ``` @@ -43,9 +101,21 @@ interface SubagentStartRequest { The outcome of a run, resolved by `SubagentRun.result`. `structured` is present only after a requested `outputSchema` was successfully satisfied; requesting a schema does not guarantee it, and a provider may return `stopReason: 'error'` when the child fails or finishes without a valid capture. A non-`completed` `stopReason` means `output` may be partial — the consumer maps it to an `isError` tool result rather than reporting partial output as success. ```ts type-equiv +/** + * The terminal outcome of a subagent run, resolved by {@link SubagentRun.result}. + */ interface SubagentResult { + /** The child's final assistant output (the last assistant message's content). */ readonly output: ContentBlock[] + /** + * The structured result after a requested `outputSchema` was successfully + * satisfied. Requesting a schema does not guarantee presence: a provider can + * end with `stopReason: 'error'` when the child fails or finishes without a + * valid capture. Shape is validated against the request schema by the + * provider; `unknown` here because the seam is schema-agnostic. + */ readonly structured?: unknown + /** Why the run ended. A non-`completed` reason means `output` may be partial. */ readonly stopReason: SubagentStopReason } ``` @@ -53,11 +123,22 @@ interface SubagentResult { `SubagentStopReason` is a [merge-extensible derived union](core.md#the-map--derived-union-pattern) — a backend may add variants, so consumers branch on the known cases and treat an unknown terminal reason as a failure: ```ts type-equiv +/** + * Why a subagent run ended. Merge-extensible (a backend may add variants); + * consumers branch on the known cases and fall through `default`. The known + * cases mirror the harness turn-end vocabulary so the tool layer can map a + * non-`completed` result to an `isError` tool result. + */ interface SubagentStopReasonMap { + /** The child finished its turn normally. */ completed: 'completed' + /** The run was cancelled by its request signal or by disposal. */ aborted: 'aborted' + /** The child failed (model error, transport error). */ error: 'error' + /** The child hit its token ceiling before finishing. */ 'max-tokens': 'max-tokens' + /** The child declined the task. */ refusal: 'refusal' } ``` @@ -67,12 +148,47 @@ interface SubagentStopReasonMap { `SubagentRun` is the consumer-owned handle for a ready child. Consumers await `result` and always dispose the run to reach quiescence. Child failures resolve with a non-completed stop reason; only unrepresentable infrastructure faults reject. Optional `sendMessage` and `resume` methods advertise their runtime capabilities by presence. ```ts type-equiv +/** + * Child handle returned only after readiness. Consumers await {@link result} and must always + * {@link dispose} to cancel remaining work and reach quiescence. Optional methods are runtime + * capability discovery; narrow their presence before calling. + */ interface SubagentRun { + /** + * Parent-scoped run id. For a local run, this MUST equal the published child + * session id, whose `parentSession` records `request.parent.session.id`; a + * remote provider mints an id unique in the parent namespace. + */ readonly id: SessionId + /** + * The exact published in-process child, or `undefined` for a remote run. + * When present, its id is {@link id}; the provider retains no ownership + * implication beyond the run's ordinary {@link dispose} contract. + */ readonly localAgent: Agent | undefined + /** + * Resolves with the child's terminal {@link SubagentResult} when the run + * settles. Does NOT reject on a child-level failure — a model/transport + * failure resolves with `stopReason: 'error'` so the consumer maps it to an + * `isError` tool result. Rejects only on an infrastructure fault the seam + * cannot represent as a stop reason. + */ readonly result: Promise + /** + * Cancel remaining work, reach child quiescence, and release the run's + * resources (in-process: dispose the owned agent and remove its session; + * ACP: kill and reap the subprocess). Idempotent. + */ dispose(): Promise + /** + * OPTIONAL (steering capability): send additional content to the running + * child between steps. Present only on providers that support live steering. + */ sendMessage?(content: ContentBlock[]): void + /** + * OPTIONAL (resume capability): send a follow-up task to a settled child, + * continuing its session, and return a fresh run for the continuation. + */ resume?(content: ContentBlock[]): Promise } ``` @@ -84,10 +200,33 @@ A local run MUST publish an ordinary child agent/session before `start()` fulfil Each provider is a named child-agent transport, and multiple providers may coexist. The service validates requested start-time capabilities before `start()`. `inheritsParentContext` describes only conversation seeding (`fork`: true; `spawn` and `acp`: false), allowing consumers to generate accurate model-facing wording without implying inherited tools, services, or authority. ```ts type-equiv +/** + * A subagent backend: one transport for running a child agent (in-process + * spawn/fork, ACP to another process, …). Implementations register under a + * unique name via {@link SubagentService.registerProvider}; multiple providers + * coexist in one context (unlike the single-implementation bash seam). The + * Providers are trusted same-process implementations; callers treat their + * descriptors and returned values as borrowed immutable data. + */ interface SubagentProvider { + /** Unique registry name (e.g. `spawn`, `fork`, `acp`). */ readonly name: string + /** The start-time features this provider supports (see {@link SubagentCapabilities}). */ readonly capabilities: SubagentCapabilities + /** + * Whether the child sees the parent's completed-turn prefix. This is descriptive, not a + * service-validated start capability: the model-facing tool derives truthful wording from it. + * It says nothing about tool registration, injected services, or authority inheritance. + */ readonly inheritsParentContext: boolean + /** + * Establish a child and return its handle only after publication. The + * service has already validated that every requested start-time capability + * is supported, so an implementation may assume e.g. `request.maxDepth` is + * honorable when present. If setup fails or `request.signal` aborts before + * fulfillment, the provider owns and cleans all partial resources before this + * promise rejects. Ownership transfers to the caller only on fulfillment. + */ start(request: SubagentStartRequest): Promise } ``` diff --git a/docs/core-data-structures/system-prompt.md b/docs/core-data-structures/system-prompt.md index 4b6f1e6625..04c86aabe6 100644 --- a/docs/core-data-structures/system-prompt.md +++ b/docs/core-data-structures/system-prompt.md @@ -9,7 +9,12 @@ Source: [`packages/core/system-prompt/src/index.ts`](../../packages/core/system- `AssembleContext` identifies the scope layer one assembly resolves. It is merge-extensible: `dsh-agent` adds the optional live `agent` field, and `assembleContextFor(agent)` sets that field and `scope` together. ```ts type-equiv +/** Merge-extensible context for one prompt assembly. */ interface AssembleContext { + /** + * Scope whose providers and waterfall listeners participate. When absent, + * only global providers and subject-less listeners participate. + */ scope?: ScopeKey } ``` @@ -19,8 +24,11 @@ interface AssembleContext { `ToolProviderResult.schemas` is the model-visible set for the current assembly. `knownNames` is the provider's pre-restriction name universe used to distinguish a configured-name typo from a known tool that is deliberately hidden in this scope. ```ts type-equiv +/** Tool schemas visible in one assembly and their pre-restriction name set. */ interface ToolProviderResult { + /** The schemas this provider contributes to THIS assembly. */ readonly schemas: readonly ToolSchema[] + /** The pre-restriction name universe for config validation (defaults to `schemas`' names). */ readonly knownNames?: readonly string[] } ``` @@ -30,9 +38,21 @@ interface ToolProviderResult { `PromptSection` is a readonly same-process registration contract. Its text may be static or resolved from the current assembly context. ```ts type-equiv +/** One contributed section of the system prompt (registry input). */ interface PromptSection { + /** Unique name — a duplicate registration throws (see {@link SystemPrompt.section}). */ readonly name: string + /** + * Sections are concatenated in ascending order. Convention: `-100` is the + * harness identity, `0` the deployment persona, tool guidance uses 100–199; + * other negative orders also render before the persona. + */ readonly order: number + /** + * Static text or a provider evaluated at each assembly with that assembly's + * {@link AssembleContext}. The text may reference `{{variable}}`s — they are + * interpolated later, by {@link renderPrompt}. + */ readonly text: string | ((context: AssembleContext) => string) } ``` diff --git a/docs/core-data-structures/tasks.md b/docs/core-data-structures/tasks.md index 0482912af7..ebe2062a84 100644 --- a/docs/core-data-structures/tasks.md +++ b/docs/core-data-structures/tasks.md @@ -7,6 +7,10 @@ Types shared by long-running producers, `ctx.tasks`, and task control surfaces. `TaskId` is a [branded id](core.md#branded-ids) generated as `-N`. Access control relies on owner authorization, not id secrecy. `TaskKind` derives from a merge-extensible map; the registry treats kinds as opaque id namespaces. ```ts type-equiv +/** + * Producer-defined task kinds. Plugins extend this map by declaration merging; + * the registry treats every value as an opaque id namespace. + */ interface TaskKindMap { bash: 'bash' subagent: 'subagent' @@ -20,6 +24,11 @@ interface TaskKindMap { `TaskStart` declares identity and a starter. The runtime finishes preflight before calling `run()` and commits without a later failable step. Producers own execution resources; the runtime owns identity, access, and lifecycle state. ```ts type-equiv +/** + * Producer declaration passed to {@link TaskService.start}. The runtime + * preflights access and cleanup before invoking {@link run}; the producer owns + * execution resources while the runtime owns identity and lifecycle state. + */ interface TaskStart { /** Producer kind — also the id prefix (`bash`, `subagent`, …). */ kind: TaskKind @@ -44,6 +53,7 @@ interface TaskStart { `TaskHooks.done` is the quiescence boundary. Optional `readOutput` distinguishes consuming stream tasks from final-output-only tasks. ```ts type-equiv +/** Hooks through which the runtime controls and observes producer work. */ interface TaskHooks { /** * Request termination. Must be synchronous, idempotent, and eventually settle @@ -67,6 +77,7 @@ interface TaskHooks { ``` ```ts type-equiv +/** Terminal result supplied by a producer through {@link TaskHooks.done}. */ interface TaskOutcome { /** How the task ended: finished (`completed`), cancelled (`killed`), or broke (`failed`). */ status: 'completed' | 'killed' | 'failed' @@ -82,6 +93,10 @@ interface TaskOutcome { Snapshots are fresh read-only projections. `ownerSession` carries the shared `SessionId` used for authorization; completion listeners separately receive the exact owner object used for lifecycle cleanup. `reported` suppresses a completion notice after another surface has delivered or committed to deliver the terminal state. ```ts type-equiv +/** + * A read-only projection of one task, safe to hand to listeners and tools — + * a fresh object per call, never live registry state. + */ interface TaskSnapshot { /** The registry-issued id (`-N`). */ id: TaskId @@ -112,6 +127,7 @@ interface TaskSnapshot { ``` ```ts type-equiv +/** Output and post-read state returned by {@link TaskService.read}. */ interface TaskRead { /** * Stream kinds: the consuming delta since the previous read. Final-output diff --git a/docs/core-data-structures/token-meter.md b/docs/core-data-structures/token-meter.md index e082ea08a9..880ec79d7d 100644 --- a/docs/core-data-structures/token-meter.md +++ b/docs/core-data-structures/token-meter.md @@ -7,6 +7,7 @@ Source: [`packages/llm/token-meter/src/types.ts`](../../packages/llm/token-meter ## `TokenMeasurement` ```ts type-equiv +/** Detached immutable request-pressure and surface snapshot at one consumed log revision. */ interface TokenMeasurement { /** Number of durable events consumed; equal to the next unread event seq. */ readonly logRevision: number @@ -28,6 +29,7 @@ interface TokenMeasurement { ## `TokenSurfaceNode` ```ts type-equiv +/** One token-priced node in the current ordered session surface. */ interface TokenSurfaceNode { /** Durable sequence number of the surface event. */ readonly seq: number diff --git a/docs/core-data-structures/tools.md b/docs/core-data-structures/tools.md index edb20586bc..7cc0910d90 100644 --- a/docs/core-data-structures/tools.md +++ b/docs/core-data-structures/tools.md @@ -9,6 +9,7 @@ Source: [`packages/core/tools/src/index.ts`](../../packages/core/tools/src/index A `ToolSchema` (the model-facing fields) plus the `execute` function, host-only scheduler metadata, and optional UI presenters. The registry holds these; the loop dispatches calls through them. The registry's `schemas()` builds the model-facing `ToolSchema[]` by an explicit allowlist — `execute`/`timeoutMs`/`isConcurrencySafe`/`presentCall`/`presentResult` must never leak into a model request. ```ts type-equiv +/** A registered tool: its schema plus the execution function. */ interface ToolDefinition extends ToolSchema { execute(args: unknown, exec: ToolRunContext): Promise /** @@ -26,7 +27,9 @@ interface ToolDefinition extends ToolSchema { * * Opted-in executions must not mutate parent-owned state. Shared state must * tolerate concurrent dispatch; recorder races are permitted only when they - * commute or fail closed. See the parallel-tool-call RFC for the full contract. + * commute or fail closed. See the + * [parallel-tool-call RFC](../../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md) + * for the full contract. * @param args - parsed arguments; `defineTool` validates before calling. * @returns Whether this call may join a parallel group. */ @@ -61,6 +64,7 @@ Plugin authors write per-property specs with a boolean `required: true`, and a t Source: [`packages/core/tools/src/schema.ts`](../../packages/core/tools/src/schema.ts) ```ts type-equiv +/** One schema-spec property entry. */ interface SchemaProp { type: SchemaType /** Per-property required flag (NOT the JSON Schema top-level required array). */ @@ -69,7 +73,10 @@ interface SchemaProp { description?: string /** Enum of allowed values (strings only). */ enum?: string[] - /** Default value. */ + /** + * Model-visible JSON Schema default annotation. Validation does not apply it; + * dynamic tool mounts may supply it even though first-party definitions do not. + */ default?: unknown /** Nested properties for type: 'object'. */ properties?: SchemaSpec @@ -79,12 +86,29 @@ interface SchemaProp { ``` ```ts type-equiv +/** + * The author-facing parameter schema: a shallow map of property name to + * {@link SchemaProp}. Required-ness is a per-property boolean (`required: + * true`), not a separate array. + */ type SchemaSpec = Record ``` `SchemaType` is the primitive union `'string' | 'number' | 'boolean' | 'object' | 'array'`. `InferArgs` maps a `SchemaSpec` to the TS argument type — `required: true` props become required keys, everything else genuinely optional: ```ts type-equiv +/** + * Infer the TS argument type for a complete {@link SchemaSpec}. + * + * Properties marked `required: true` are required keys; all others are + * genuinely optional keys (`?`), so callers may omit them entirely. + * + * Example: + * ```ts + * type Args = InferArgs<{ path: { type: 'string'; required: true }; limit: { type: 'number' } }> + * // → { path: string; limit?: number } + * ``` + */ type InferArgs = Simplify< & { [K in RequiredKeys]: InferPropValue } & { [K in Exclude>]?: InferPropValue } @@ -100,8 +124,14 @@ Registration is a trusted same-process contract. The registry borrows the typed `ToolRestriction` applies only to the live deployment-global tool layer. The registry compiles readonly names into private sets, intersects multiple restrictions, then overlays scope-local tools. A deny-only filter admits later unlisted globals, while an allow-list excludes them. ```ts type-equiv +/** + * Per-scope filter over global tools. Restrictions intersect and do not affect + * scoped registrations or the reserved Code Mode transport. + */ interface ToolRestriction { + /** Global tool names that stay visible; everything else is removed. */ readonly allow?: readonly string[] + /** Global tool names removed from visibility. */ readonly deny?: readonly string[] } ``` @@ -111,14 +141,20 @@ interface ToolRestriction { `ctx.tools.execute()` accepts a caller-owned `ToolExecutionInput`, materializes its parsed JSON arguments once into a pipeline-owned `ToolExecution`, and runs that call through `tools/pre-execute` (the reorderable allow/deny/ask waterfall) → registered monotonic guards → `tools/execute` (around-dispatch wrappers) → `tools/post-execute` (inspect/replace the result) → `tools/result` (the immutable authoritative outcome). The outcome is a `ToolExecutionResult`. ```ts type-equiv +/** Opaque call identity that permits correlation without exposing mutable execution state. */ type ToolExecutionToken = symbol & { readonly [toolExecutionTokenBrand]: true } ``` ```ts type-equiv +/** + * Caller-supplied description of one tool call. {@link ToolRegistry.execute} + * adds the registry-owned token to form a pipeline {@link ToolExecution}; + * callers do not choose that token. + */ interface ToolExecutionInput { readonly callId: CallId readonly name: string - /** Parsed JSON arguments (unknown — tools validate their own input). */ + /** Losslessly JSON-serializable parsed arguments (tools validate their own schema). */ readonly arguments: unknown /** The agent on whose behalf the call runs (set by the agent loop). */ readonly agent?: Agent @@ -135,6 +171,12 @@ interface ToolExecutionInput { A tool body receives the runtime extension. `deferContext()` is the composite-tool channel: it records nested-dispatch context without injecting inside the still-open outer call. ```ts type-equiv +/** + * Runtime context handed to a tool implementation after the registry has + * accepted a {@link ToolExecution}. A composite tool uses + * {@link deferContext} to ferry context produced by nested dispatches back to + * the outer result; the loop appends it only after the outer `tool/result`. + */ interface ToolRunContext extends ToolExecution { /** * Defer one nested-dispatch context until this tool's final result reaches @@ -148,12 +190,23 @@ interface ToolRunContext extends ToolExecution { The agent loop asks the registry for each pending call's execution mode and uses it to form exclusive barriers and rolling-pool parallel runs: ```ts type-equiv +/** + * Scheduling mode for one pending call. `parallel` may overlap with siblings; + * `exclusive` runs alone and forms an ordering barrier. + */ type ToolExecutionMode = | { kind: 'parallel' } | { kind: 'exclusive' } ``` ```ts type-equiv +/** + * One pending tool call inside the registry pipeline. Parsed arguments cross + * one lossless-JSON materialization boundary before policy and are deep-frozen; + * call identity and the registry-assigned {@link token} are readonly. An + * around-dispatch wrapper may set, replace, or remove `signal`. The registry + * freezes the complete object before `tools/result` observers run. + */ interface ToolExecution extends ToolExecutionInput { /** Registry-assigned identity shared with nested calls only as their opaque `parent` token. */ readonly token: ToolExecutionToken @@ -165,10 +218,19 @@ interface ToolExecution extends ToolExecutionInput { A `ToolGuard` is scope-aware final pre-dispatch policy. Its shape deliberately has no allow result: `undefined` preserves the waterfall decision, while a returned reason can only reduce permission, so a later listener cannot undo it. ```ts type-equiv +/** + * A monotonic execution guard evaluated after every `tools/pre-execute` + * listener and before the tool body. Returning a reason denies the call; + * returning `undefined` leaves it unchanged. Because guards have no allow + * result, listener ordering cannot turn a denial back into permission. + * @param execution - the identity-protected call after extensible pre-execute policy completed. + * @returns a final denial reason, or `undefined` to leave the call allowed. + */ type ToolGuard = (execution: Readonly) => string | undefined ``` ```ts type-equiv +/** The outcome of one tool call. */ interface ToolExecutionResult { content: ContentBlock[] isError: boolean @@ -179,14 +241,8 @@ interface ToolExecutionResult { */ error?: ToolErrorInfo /** - * Extra model-facing contexts deferred by a composite tool or attached by - * `tools/post-execute` listeners for the NEXT request. They are not part of - * this call's `content`: the loop accepts them into the active-batch FIFO and - * appends them after every recorded `tool/result` when the batch settles, even - * when execution is interrupted. The array preserves each context's source, - * envelope, metadata, and production order. An accepted outer call keeps - * deferred contexts before decision contexts; a block retains only contexts - * supplied by the blocking decision. + * Model-facing context for the next request, separate from this tool result. The loop + * accepts it into the active-batch FIFO, then appends after recorded results even if interrupted. */ additionalContexts?: HookContext[] /** @@ -206,6 +262,12 @@ The registry materializes and freezes the final accepted result immediately befo Each interception waterfall returns a typed **Decision** (the idiom shared with the `agent/*` seams). `tools/pre-execute` listeners receive `(exec, next)` and return a `PreToolDecision`; `tools/execute` wrappers return a `ToolExecutionResult`; `tools/post-execute` listeners receive `(exec, result, next)` and return a `PostToolDecision`: ```ts type-equiv +/** + * Pre-dispatch decision. `allow` runs the call; `deny` materializes an error; + * `ask` runs only after an approval service returns `allowed-once` and otherwise + * denies. Input rewriting is excluded because arguments are already logged and + * presented. + */ type PreToolDecision = | { kind: 'allow' } | { kind: 'deny'; reason: string } @@ -213,6 +275,10 @@ type PreToolDecision = ``` ```ts type-equiv +/** + * Post-dispatch decision: accept or replace content, attach context for the next + * request, or block by turning corrective feedback into an error result. + */ type PostToolDecision = | { kind: 'accept'; content?: ContentBlock[]; additionalContexts?: HookContext[] } | { kind: 'block'; feedback: ContentBlock[]; additionalContexts?: HookContext[] } @@ -227,25 +293,41 @@ Post-policy may replace content; a block becomes an `isError` result containing The vocabulary a caller uses to demand a machine-readable result from a subagent (`SubagentStartRequest.outputSchema`, [subagent.md](subagent.md#the-start-request)) or a workflow `agent()` call. It is deliberately NOT full JSON Schema: the schema travels verbatim to the model as a forced tool's `parameters`, and the produced value is validated client-side by `validateStructuredValue` — so every accepted keyword must be one the validator actually enforces, and `assertSupportedOutputSchema` rejects anything else loud (`OutputSchemaError`, listing every violation). Both walkers reason over own enumerable properties only (JSON carries nothing else) and reject non-plain objects (`Date`, `Map`) that would serialize lossily. ```ts type-equiv +/** The scalar values `enum`/`const` may carry (finite numbers only). */ type StructuredScalar = string | number | boolean | null ``` ```ts type-equiv +/** The `type` keywords the subset accepts. */ type StructuredSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null' ``` ```ts type-equiv +/** + * One node of the structured-output schema subset. Recursive via `properties` + * and `items`; see the module doc for the exact keyword semantics. + */ interface StructuredSchemaNode { type: StructuredSchemaType + /** Nested property schemas (`type: 'object'` only). */ properties?: Record + /** Required property names; each must appear in `properties`. */ required?: string[] + /** `false` rejects undeclared keys; absent/`true` allows them (JSON Schema default). */ additionalProperties?: boolean + /** Item schema (`type: 'array'` only); absent ⇒ any JSON items. */ items?: StructuredSchemaNode + /** Allowed values (scalar types only). */ enum?: StructuredScalar[] + /** The single allowed value (scalar types only). */ const?: StructuredScalar + /** Annotation, ignored for validation. */ description?: string + /** Annotation, ignored for validation. */ title?: string + /** Annotation, ignored for validation (must still be JSON data). */ default?: unknown + /** Annotation, ignored for validation (must still be JSON data). */ examples?: unknown } ``` @@ -253,6 +335,7 @@ interface StructuredSchemaNode { A schema is an object-rooted node (`enum`/`const` are scalar-only; `description`/`title`/`default`/`examples` are annotations, allowed and ignored but still required to be JSON data — they ride the wire): ```ts type-equiv +/** A structured-output schema: an OBJECT-rooted {@link StructuredSchemaNode}. */ type StructuredOutputSchema = StructuredSchemaNode & { type: 'object' } ``` diff --git a/docs/core-data-structures/user-interaction.md b/docs/core-data-structures/user-interaction.md index 4edc415039..bab8e8d37b 100644 --- a/docs/core-data-structures/user-interaction.md +++ b/docs/core-data-structures/user-interaction.md @@ -9,6 +9,7 @@ Source: [`packages/ui/user-interaction/src/index.ts`](../../packages/ui/user-int `AskUserQuestionOption` is the selectable-choice shape. `label` is the user-facing option text and also the model-facing selected value; `description` is optional UI help text. ```ts type-equiv +/** One selectable answer offered to the user. */ interface AskUserQuestionOption { /** User-facing label. */ label: string @@ -22,6 +23,7 @@ interface AskUserQuestionOption { `AskUserQuestionItem` is one question in a request. The model supplies a stable `id`, which is echoed back with the answer so batched questions remain routable. ```ts type-equiv +/** One question in an ask_user_question request. */ interface AskUserQuestionItem { /** Stable model-provided question id, echoed in the answer. */ id: string @@ -41,6 +43,7 @@ interface AskUserQuestionItem { `AskUserQuestionRequest` is the cross-package request. `questions` is an array so a UI can present related prompts in one flow while preserving a stable id per answer. ```ts type-equiv +/** Request for a human answer. */ interface AskUserQuestionRequest { /** Questions to display. */ questions: AskUserQuestionItem[] @@ -56,6 +59,7 @@ interface AskUserQuestionRequest { Providers return one answer per answered question id. `selected` contains selected option labels, and `custom` carries a free-form "Other" answer when the user typed one. When `custom` is present, `selected` is empty; custom text is an answer override, not a supplement to selected choices. ```ts type-equiv +/** Answer to one question. */ interface AskUserQuestionAnswerItem { /** The answered question id. */ id: string @@ -67,6 +71,7 @@ interface AskUserQuestionAnswerItem { ``` ```ts type-equiv +/** The human's answer. */ interface AskUserQuestionAnswer { /** Structured answers keyed by question id. */ answers: AskUserQuestionAnswerItem[] @@ -78,6 +83,7 @@ interface AskUserQuestionAnswer { Only one provider may be active in a context. Provider registration is effect-bound so HMR/disposal removes the active UI. ```ts type-equiv +/** UI-side provider for user questions. */ interface UserInteractionProvider { ask(request: AskUserQuestionRequest): Promise } @@ -88,6 +94,7 @@ interface UserInteractionProvider { `UserInteractionError` extends `HarnessError`, so `ctx.tools.execute()` preserves `{ name, code }` for model-facing tool failures such as `EMPTY_QUESTIONS`, `NO_PROVIDER`, `ASK_ABORTED`, or ACP-side cancellation. ```ts type-equiv +/** Stable error taxonomy for user-interaction failures. */ class UserInteractionError extends HarnessError { constructor(message: string, code: string, options?: ErrorOptions) { super(message, code, options) diff --git a/docs/core-data-structures/web.md b/docs/core-data-structures/web.md index 9d79cd96c8..af14f54466 100644 --- a/docs/core-data-structures/web.md +++ b/docs/core-data-structures/web.md @@ -13,20 +13,37 @@ Search and fetch share no request schema and no business logic, but they are del The model-facing tool argument is just a `query`; `maxResults` is a consumer-owned bound (`dsh-tool-web`'s `searchMaxResults` config, default `8`) passed through the seam and enforced on the way back — if a provider over-returns, the seam truncates `sources[]` and sets `truncated`. ```ts type-equiv +/** + * What one search-capable backend can return. The model-facing argument is just + * a query; `maxResults` is a `dsh-tool-web`-layer bound passed through unchanged + * and enforced on the way back by the seam (see {@link WebSearchResult}). + */ interface WebSearchRequest { readonly query: string /** * Upper bound on returned sources; the seam truncates to it. Omitted = no - * bound. `dsh-tool-web` always sets it. + * bound. `dsh-tool-web` always sets it. A provider whose API supports a + * result-count control (Exa's `numResults`) should apply it at the request + * layer as a cost/latency optimization; the seam enforces the bound + * regardless. */ readonly maxResults?: number } ``` ```ts type-equiv +/** + * Normalized search outcome. `content` is optional provider-generated answer + * text or summary (Exa returns none; Perplexity returns a generated answer). + * `sources[]` is the portable citation surface. `truncated` is set by the seam + * when it cut `sources[]` down to `maxResults`. + */ interface WebSearchResult { + /** Optional provider-generated answer text, search context, or summary. */ readonly content?: string + /** Citeable sources, already truncated to the request's `maxResults`. */ readonly sources: readonly WebSearchSource[] + /** True when the seam dropped sources to honor `maxResults`. */ readonly truncated: boolean } ``` @@ -34,10 +51,17 @@ interface WebSearchResult { `content` is optional provider-generated answer text (Exa and DeepSeek return none; Perplexity returns a generated answer). `sources[]` is the portable citation surface. A source always has a `url`; `title`/`snippet`/`publishedAt` are optional because not every provider returns them — Perplexity citations may be URL-only, and forcing adapters to invent the rest would make the seam lie. `dsh-tool-web` renders `title ?? hostname(url)`. ```ts type-equiv +/** + * One citeable source. A source always has a URL; `title`, `snippet`, and + * `publishedAt` are optional because not every provider returns them — forcing + * adapters to invent them would make the seam lie (Perplexity citations may be + * URL-only). `dsh-tool-web` renders `title ?? hostname(url)` for display. + */ interface WebSearchSource { readonly url: string readonly title?: string readonly snippet?: string + /** Publication/crawl timestamp as a provider-supplied ISO-8601 string. */ readonly publishedAt?: string } ``` @@ -45,6 +69,12 @@ interface WebSearchSource { ## Fetch request and result ```ts type-equiv +/** + * What one fetch-capable backend is asked to retrieve. The request deliberately + * omits timeout, format, prompt, and extraction controls: cancellation is a + * direct execution argument, while presentation and higher-level LLM concerns + * belong outside safe retrieval. + */ interface WebFetchRequest { readonly url: string } @@ -53,10 +83,20 @@ interface WebFetchRequest { HTTP status is part of the fetched resource state, not automatically a failure: a successful network fetch of a `404`/`500` returns a `WebFetchResult` with the status code and a bounded decoded body. `url` is the final URL after allowed redirects. `WebError` is reserved for failures to safely retrieve or represent the resource. ```ts type-equiv +/** + * Normalized fetch outcome. A successful network fetch of a non-2xx response is + * a result, not an error: the status code is part of the fetched resource + * state. {@link WebError} is reserved for failures to safely retrieve or + * represent the resource. + */ interface WebFetchResult { + /** The final URL after allowed redirects (the request URL is in the request). */ readonly url: string + /** HTTP status code of the fetched response. */ readonly statusCode: number + /** Decoded body, classified by content kind. */ readonly body: WebFetchBody + /** True when the provider capped the decoded body. */ readonly truncated: boolean } ``` @@ -64,6 +104,15 @@ interface WebFetchResult { `WebFetchBody` is a **closed** discriminated union owned by `dsh-web` (not a merge-extensible map): the provider decodes the kind and `dsh-tool-web` renders it, so a new kind is a coordinated change across known packages, not a plugin extension. Consumers `switch` on `kind` ending in `default: assertNever(...)`, so adding a kind breaks compilation at every consumer until handled. Each arm stays its own object literal even where fields coincide today, leaving room for arm-specific fields later (a future `pdf` body's `pageCount`). ```ts type-equiv +/** + * The decoded body of a fetched resource. A CLOSED discriminated union owned by + * `dsh-web`: the provider decodes the kind and `dsh-tool-web` renders it, so a + * new kind is a coordinated change across known packages, not a plugin + * extension. Consumers `switch` on `kind` ending in `default: assertNever(...)` + * so adding a kind breaks compilation at every consumer until handled. Each arm + * stays its own object literal even where fields coincide today, leaving room + * for arm-specific fields later (a `pdf` body's `pageCount`). + */ type WebFetchBody = | { readonly kind: 'html'; readonly content: string } | { readonly kind: 'text'; readonly content: string } diff --git a/docs/core-data-structures/workflow.md b/docs/core-data-structures/workflow.md index 4354105e70..40b17a3112 100644 --- a/docs/core-data-structures/workflow.md +++ b/docs/core-data-structures/workflow.md @@ -11,11 +11,24 @@ Source: [`packages/workflow/workflow/src/types.ts`](../../packages/workflow/work What a caller asks for when starting a run. The tool layer builds this from the model's `{ script, meta, args }` call plus the calling agent; `meta` and `args` are plain JSON DATA (the engine shape-validates `meta` and rejects loud BEFORE anything runs — no script text is ever evaluated to obtain it). `parent` is REQUIRED — every child the script spawns is attributed to it (cwd, lineage, and depth flow through the [subagent seam](subagent.md)). ```ts type-equiv +/** + * What a caller asks for when starting a workflow run. `meta` and `args` are + * plain JSON DATA by the seam contract (the tool builds both from the model's + * schema-validated call; the engine validates `meta`'s shape and rejects loud + * before anything runs) — an engine never evaluates script text to obtain + * them. `parent` is REQUIRED — every `agent()` the script spawns is + * attributed to it (cwd, lineage, depth flow through the subagent seam). + */ interface WorkflowStartRequest { + /** The plain-JS script body (top-level await allowed; ends with `return `). */ script: string + /** The workflow's identity block, as plain JSON data (shape-validated by the engine). */ meta: WorkflowMeta + /** Optional input exposed verbatim to the script as the `args` global. */ args?: unknown + /** The agent on whose behalf the run executes (parent of every child). */ parent: Agent + /** Cancels the run when aborted (the tool's `exec.signal`). */ signal?: AbortSignal } ``` @@ -25,10 +38,21 @@ interface WorkflowStartRequest { The identity block carried as data on the start request (the tool's `meta` parameter; the field vocabulary matches the Claude Code dynamic-workflows meta block). `phases` is progress vocabulary only: `phase()` calls match titles for observers; no execution structure is implied. ```ts type-equiv +/** + * The script's identity block, provided as plain JSON data alongside the + * script body (the model-facing tool carries it as its `meta` parameter) and + * validated by the engine before the body runs. `name`/`description` are + * required; the rest is optional annotation. The field vocabulary matches the + * Claude Code dynamic-workflows meta block. + */ interface WorkflowMeta { + /** Short kebab-case workflow name (display + persistence key). */ name: string + /** One-line description of what the workflow does. */ description: string + /** Optional guidance on when this workflow applies (shown in listings). */ whenToUse?: string + /** Optional phase declarations matched by `phase()` calls. */ phases?: WorkflowPhase[] } ``` @@ -38,10 +62,27 @@ interface WorkflowMeta { The outcome of one run, resolved by `WorkflowRun.result`. `value` is the script's materialized return value — plain host-realm JSON data (`null` when the script returned nothing) — meaningful only for `completed`. `stopReason` is a CLOSED union (engine-owned; consumers may exhaust it): `completed` | `cancelled` | `error`. A non-`completed` reason carries the failure in `error`, and the consumer maps it to an `isError` tool result rather than reporting partial output as success. ```ts type-equiv +/** + * The outcome of one run, resolved by {@link WorkflowRun.result}. `value` is + * the script's materialized return value (plain host-realm JSON data; `null` + * when the script returned `undefined`) — meaningful only for `completed`. + * A non-`completed` reason carries the failure in `error`; the consumer maps + * it to an `isError` tool result rather than reporting partial output. + */ interface WorkflowResult { + /** The script's return value (host JSON data; `null` for no return). */ value: unknown + /** Why the run settled. */ stopReason: WorkflowStopReason + /** The failure message (present iff `stopReason` is not `completed`). */ error?: string + /** + * How many `agent()` calls the run accepted over its whole lifetime. On a + * graceful settlement this is the script-side count (calls still queued for + * a concurrency slot included); on a termination path (grace force-settle, + * worker death) it degrades to the host-observed count — calls queued + * inside a terminated script are unknowable then. + */ agentsStarted: number } ``` @@ -51,11 +92,20 @@ interface WorkflowResult { The handle the consumer holds while a script executes. The consumer awaits `result`, may `cancel` mid-flight, and MUST `dispose` on every path. `result` does NOT reject — a script failure resolves with `stopReason: 'error'` — and once the run is cancelled it SETTLES within the engine's bounded grace even if the script itself never settles (the engine force-settles `cancelled`; the worker-thread engine then terminates the script's worker), so a consumer awaiting `result` is never wedged past a cancellation. `dispose()` = cancel + that bounded settle + child quiescence; it never hangs on a stuck script. ```ts type-equiv +/** + * Holder-owned live workflow. `result` never rejects and settles within the + * engine's cancellation grace; failures resolve through `stopReason`. Consumers + * may cancel and must call idempotent `dispose()` on every path to await bounded + * script settlement and child quiescence. + */ interface WorkflowRun { readonly id: WorkflowRunId + /** The validated meta block (available before the body runs). */ readonly meta: WorkflowMeta readonly result: Promise + /** Cancel the run: children abort, pending hooks reject, the script dies at its next await (or is force-settled at the grace). */ cancel(reason?: string): void + /** Cancel + bounded-grace settle; safe to call on every path (idempotent). */ dispose(): Promise } ``` diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index 494eb09922..30da04eb96 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: b3c338f03f548b4de4b676850732731323d611f1 -development.zh.md: 20f5c585dd378a7b0a3bd6b0af8ebf7dc5e0fd3c +development.md: 4efb0a1fafb9a8dc34fdbabf3dbf9baa3281929c +development.zh.md: 010b0d48a9597b578e938fd7900c4f7e5949a481 diff --git a/docs/development.md b/docs/development.md index b3c338f03f..4efb0a1faf 100644 --- a/docs/development.md +++ b/docs/development.md @@ -133,13 +133,13 @@ Pick the tag that matches the urgency so anyone scanning the code can tell a rel ## Documenting types verbatim (`ts type-equiv`) -The [core data structures](core-data-structures/core.md) docs paste real type definitions so a reader sees the exact shape. To keep a paste from drifting when source changes, fence it as ` ```ts type-equiv ` (instead of ` ```ts `) and register it in `scripts/type-equiv.manifest.json` with the source file and symbol it mirrors: +The [core data structures](core-data-structures/core.md) docs paste real type declarations together with their original JSDoc so a reader sees the exact shape and source contract. To keep a paste from drifting when source changes, fence it as ` ```ts type-equiv ` (instead of ` ```ts `) and register it in `scripts/type-equiv.manifest.json` with the source file and symbol it mirrors: ```json { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" } ``` -`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration from source via the TypeScript parser and asserts the block matches it (whitespace- and comment-insensitive, so a doc block may show a clean definition and the prose can carry the semantics). It also enforces a 1:1 correspondence: every `ts type-equiv` block has exactly one manifest entry and vice-versa, so a block can't go silently unchecked and a stale entry can't linger. `doc-typecheck` skips `ts type-equiv` blocks (they aren't standalone-compilable) and excludes them from its opt-out ratio. When you change a documented type, the gate fails until you update the paste; when you add or remove a block, update the manifest in the same change. +`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration and attached JSDoc from source via the TypeScript parser and asserts the block matches both. Comparison ignores whitespace and non-JSDoc comments but requires every original JSDoc comment, including member documentation, so readers see the source contract beside the exact shape. The gate also enforces a 1:1 correspondence: every `ts type-equiv` block has exactly one manifest entry and vice-versa, so a block can't go silently unchecked and a stale entry can't linger. `doc-typecheck` skips `ts type-equiv` blocks (they aren't standalone-compilable) and excludes them from its opt-out ratio. When you change a documented declaration or its JSDoc, the gate fails until you update the paste; when you add or remove a block, update the manifest in the same change. ## Architecture context diff --git a/docs/development.zh.md b/docs/development.zh.md index 20f5c585dd..010b0d48a9 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -133,13 +133,13 @@ pnpm run demo:acp ## 逐字记录类型（`ts type-equiv`） -[核心数据结构](core-data-structures/core.md)文档粘贴真实的类型定义，让读者看到确切的形状。为防止粘贴内容在源码变化时漂移，请将其围栏为 ` ```ts type-equiv `（而不是 ` ```ts `），并在 `scripts/type-equiv.manifest.json` 中登记它镜像的源文件和符号： +[核心数据结构](core-data-structures/core.md)文档会把真实类型声明及其原始 JSDoc 一并粘贴，让读者看到确切形状和源码契约。为防止粘贴内容在源码变化时漂移，请将其围栏为 ` ```ts type-equiv `（而不是 ` ```ts `），并在 `scripts/type-equiv.manifest.json` 中登记它镜像的源文件和符号： ```json { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" } ``` -`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明，并断言文档块与之一致（对空白和注释不敏感，因此文档块可以展示干净的定义，语义由行文承载）。它还强制 1:1 对应：每个 `ts type-equiv` 块恰好有一条 manifest 条目，反之亦然；因此不会有块被静默漏检，也不会有陈旧条目滞留。`doc-typecheck` 跳过 `ts type-equiv` 块（它们不能独立编译），并将其排除在 opt-out 比例之外。当你改动一个被记录的类型时，门禁会失败直到你更新粘贴内容；当你增删一个块时，请在同一个变更里更新 manifest。 +`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明及其附带的 JSDoc，并断言代码块同时匹配两者。比对会忽略空白和非 JSDoc 注释，但要求保留每条原始 JSDoc（包括成员文档），让读者同时看到源码契约和确切形状。该门禁还强制 1:1 对应：每个 `ts type-equiv` 块恰好有一条 manifest 条目，反之亦然；因此不会有块被静默漏检，也不会有陈旧条目滞留。`doc-typecheck` 跳过 `ts type-equiv` 块（它们不能独立编译），并将其排除在 opt-out 比例之外。当你改动一个已记录的类型声明或其 JSDoc 时，门禁会失败直到你更新粘贴内容；当你增删一个块时，请在同一个变更里更新 manifest。 ## 架构上下文 diff --git a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md b/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md index aaac6fbd3c..bf70879c71 100644 --- a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md +++ b/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md @@ -10,7 +10,7 @@ So the work had two intertwined questions: **what belongs in such a catalog** (t ## Decision -A new `docs/core-data-structures/` folder catalogs the vocabulary, with a new `verify-type-equiv` doc-sync gate that keeps every pasted type definition byte-identical to its source. +A new `docs/core-data-structures/` folder catalogs the vocabulary, with a new `verify-type-equiv` doc-sync gate that keeps every pasted type declaration and its JSDoc synchronized with source. ### What counts as "core" — the spine-vs-seam line @@ -27,10 +27,10 @@ The rule that settled the remaining cases: ***the type you write, hold, or recei ### The `ts type-equiv` mechanism — literal AND drift-proof -The durability requirement was specific: the doc should show the **literal** current type definition (so a reader sees the real shape, not a paraphrase) **and** be mechanically guaranteed to match source. The repo already compiles fenced ` ```ts ` blocks (`doc-typecheck`), but a real typechecked block needs import noise and proves only *assignability*, not *byte-equality* — a renamed field with the same type would pass. So: +The durability requirement was specific: the doc shows the **literal** current type declaration and original JSDoc (so a reader sees the real shape and source contract, not a paraphrase) **and** is mechanically guaranteed to match source. The repo already compiles fenced ` ```ts ` blocks (`doc-typecheck`), but a real typechecked block needs import noise and proves only *assignability* — a renamed field or changed JSDoc can pass. So: -- Type definitions are pasted verbatim into a dedicated ` ```ts type-equiv ` fence. `doc-typecheck` recognizes the fence and skips it (a bare definition is not standalone-compilable), and **excludes it from the opt-out ratio** — it is a separately-checked category, not an unchecked sketch. -- A new `scripts/verify-type-equiv.ts` extracts each block via the TypeScript parser and asserts a **verbatim source match** against the declared symbol — chosen over a compiled `_Check` assertion precisely because byte-equality, not assignability, is the property we want. +- Type declarations and their JSDoc are pasted verbatim into a dedicated ` ```ts type-equiv ` fence. `doc-typecheck` recognizes the fence and skips it (a bare definition is not standalone-compilable), and **excludes it from the opt-out ratio** — it is a separately-checked category, not an unchecked sketch. +- A new `scripts/verify-type-equiv.ts` extracts each block via the TypeScript parser and asserts that its declaration structure and every JSDoc comment match the declared symbol, ignoring only formatting whitespace and non-JSDoc comments. This is chosen over a compiled `_Check` assertion because source names and documentation identity, not assignability, are the properties the catalog preserves. - Provenance lives in a central `scripts/type-equiv.manifest.json` (`{ doc, symbol, source }` entries), **not** in directive comments in the prose. The script enforces a **1:1 correspondence**: every type-equiv block has exactly one manifest entry and vice versa, so a block can never be silently unchecked and an entry can never rot. - Wired into `doc-sync`, so it runs in the same lefthook pre-push and CI paths as the other doc gates. @@ -41,7 +41,7 @@ The durability requirement was specific: the doc should show the **literal** cur ## Alternatives considered - **A flat dump of all cross-package vocabulary** — the `BashExecRequest` test case killed it: if seam vocabulary is "core", the catalog helps no one; the tiered spine-vs-seam structure won. -- **A compiled `_Check` assignability assertion** instead of the verbatim source match — rejected because byte-equality, not assignability, is the property we want: a renamed field with the same type would pass assignability. +- **A compiled `_Check` assignability assertion** instead of the source match — rejected because assignability does not preserve names or JSDoc: a renamed field with the same type or a changed contract comment would pass. - **Provenance as directive comments in the prose** — rejected for the central manifest, whose enforced 1:1 correspondence means a block can never be silently unchecked and an entry can never rot. ## Verification lesson diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index cfa345ebdc..566bdade7b 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -1,5 +1,5 @@ { - "comment": "Maps each ` ```ts type-equiv ` block (by doc + declared symbol) to the source symbol it must match verbatim. verify-type-equiv.ts enforces a 1:1 correspondence: every type-equiv block has exactly one entry here, and every entry resolves to exactly one block. Add an entry when you add a type-equiv block; remove it when you remove the block.", + "comment": "Maps each ` ```ts type-equiv ` block (by doc + declared symbol) to the source declaration and original JSDoc it must match. verify-type-equiv.ts enforces a 1:1 correspondence: every type-equiv block has exactly one entry here, and every entry resolves to exactly one block. Add an entry when you add a type-equiv block; remove it when you remove the block.", "entries": [ { "doc": "docs/core-data-structures/core.md", "symbol": "Branded", "source": "packages/util/brand/src/index.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, diff --git a/scripts/verify-type-equiv.ts b/scripts/verify-type-equiv.ts index 08278a6a8f..585796206c 100644 --- a/scripts/verify-type-equiv.ts +++ b/scripts/verify-type-equiv.ts @@ -1,7 +1,8 @@ /** * Verify every `ts type-equiv` block against the source symbol named by the * manifest. Blocks and entries have a one-to-one relationship; comparison - * ignores comments and whitespace but preserves declaration structure. + * ignores whitespace and non-JSDoc comments but preserves declaration + * structure and every original JSDoc comment. */ import { globSync, readFileSync, existsSync } from 'node:fs' @@ -34,12 +35,8 @@ interface EquivBlock { code: string } -/** - * Remove comments and normalize whitespace so prose-only edits do not drift - * structural copies. This is intentionally not a general tokenizer: repo type - * declarations do not contain comment delimiters inside string literals. - */ -function normalize(code: string): string { +/** Normalize declaration structure independently of comments and whitespace. */ +function normalizeStructure(code: string): string { return code .replace(/\/\*[\s\S]*?\*\//g, '') .replace(/(^|[^:])\/\/.*$/gm, '$1') @@ -47,6 +44,15 @@ function normalize(code: string): string { .trim() } +/** + * Extract normalized JSDoc comments in source order. Type declarations in this + * repository do not contain comment delimiters inside string literals. + */ +function normalizeJSDoc(code: string): string[] { + return [...code.matchAll(/\/\*\*[\s\S]*?\*\//g)] + .map(match => match[0].replace(/\s+/g, ' ').trim()) +} + /** Strip source-only export modifiers. */ function stripExport(code: string): string { return code.replace(/^export\s+(default\s+)?/, '') @@ -54,8 +60,14 @@ function stripExport(code: string): string { /** Parse the declared symbol name from a type-equiv block body. */ function blockSymbol(code: string): string | null { - const m = /(?:export\s+(?:default\s+)?)?(?:abstract\s+)?(?:interface|type|class|enum)\s+([A-Za-z0-9_]+)/.exec(code) - return m?.[1] ?? null + const sf = ts.createSourceFile('type-equiv.ts', code, ts.ScriptTarget.Latest, /* setParentNodes */ false, ts.ScriptKind.TS) + for (const stmt of sf.statements) { + const named = + ts.isInterfaceDeclaration(stmt) || ts.isTypeAliasDeclaration(stmt) + || ts.isClassDeclaration(stmt) || ts.isEnumDeclaration(stmt) + if (named && stmt.name) return stmt.name.text + } + return null } /** Extract every ` ```ts type-equiv ` block from one Markdown file. */ @@ -88,11 +100,12 @@ function extractEquivBlocks(docRel: string): EquivBlock[] { return blocks } -/** The declaration text of `symbol` in `sourceRel`, with `export` stripped, or +/** + * The declaration text of `symbol` in `sourceRel`, with `export` stripped, or * null when the symbol is not declared there. Uses the TS parser so it spans * interfaces, type aliases (including mapped/generic ones), classes, and enums - * uniformly, and excludes the leading JSDoc (getStart skips leading trivia) - * while keeping inline member comments. */ + * uniformly while including declaration and member JSDoc. + */ function sourceDeclaration(sourceRel: string, symbol: string): string | null { const abs = resolve(root, sourceRel) const text = readFileSync(abs, 'utf8') @@ -102,7 +115,13 @@ function sourceDeclaration(sourceRel: string, symbol: string): string | null { ts.isInterfaceDeclaration(stmt) || ts.isTypeAliasDeclaration(stmt) || ts.isClassDeclaration(stmt) || ts.isEnumDeclaration(stmt) if (named && stmt.name?.text === symbol) { - return stripExport(stmt.getText(sf)) + const declarationStart = stmt.getStart(sf) + const jsDoc = ts.getJSDocCommentsAndTags(stmt) + .filter(ts.isJSDoc) + .map(doc => text.slice(doc.pos, doc.end)) + .join('\n') + const declaration = stripExport(text.slice(declarationStart, stmt.getEnd())) + return jsDoc === '' ? declaration : `${jsDoc}\n${declaration}` } } return null @@ -178,11 +197,18 @@ for (const e of entries) { errors.push(`symbol ${e.symbol} not found in ${e.source} (manifest entry for ${e.doc})`) continue } - if (normalize(decl) !== normalize(stripExport(b.code))) { + const doc = stripExport(b.code) + const sourceStructure = normalizeStructure(decl) + const docStructure = normalizeStructure(doc) + const sourceJSDoc = normalizeJSDoc(decl) + const docJSDoc = normalizeJSDoc(doc) + if (sourceStructure !== docStructure || JSON.stringify(sourceJSDoc) !== JSON.stringify(docJSDoc)) { errors.push( `DRIFT: ${e.doc}:${b.line} — type-equiv block for ${e.symbol} does not match ${e.source}.\n` - + ` source: ${normalize(decl)}\n` - + ` doc: ${normalize(stripExport(b.code))}`, + + ` source structure: ${sourceStructure}\n` + + ` doc structure: ${docStructure}\n` + + ` source JSDoc: ${JSON.stringify(sourceJSDoc)}\n` + + ` doc JSDoc: ${JSON.stringify(docJSDoc)}`, ) continue } @@ -190,7 +216,7 @@ for (const e of entries) { } if (errors.length === 0) { - console.log(`verify-type-equiv: ${verified} type-equiv block(s) match source (1:1 with manifest).`) + console.log(`verify-type-equiv: ${verified} type-equiv block(s) match source structure and JSDoc (1:1 with manifest).`) process.exit(0) } From 7538cef967b745d9817b9502363699d494d6d069 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:35:43 +0800 Subject: [PATCH 214/323] docs(agent): describe cancelled post-step checkpoint --- docs/cordis-catalog/events.md | 12 ++++++------ docs/core-data-structures/core.md | 2 +- docs/event-producer-consumer.md | 10 +++++----- packages/cordis/tool-cordis/src/api-catalog.ts | 2 +- packages/core/agent/src/types.ts | 9 +++++---- website/zh-CN/api/harness/events.md | 16 ++++++++-------- 6 files changed, 26 insertions(+), 25 deletions(-) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index f7fe327f80..1dd62f0b76 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -47,11 +47,11 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:310`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:311`](../../packages/core/agent/src/types.ts) ### `agent/post-step` — serial -Awaited serial checkpoint after the response, tool results, injected context, and steering are durable but before `step/end`. +Awaited serial checkpoint after the response, real or synthetic tool results, injected context, and steering are durable but before `step/end`. A cancelled tool batch reaches this checkpoint with an aborted signal. ```ts cordis-catalog 'agent/post-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void @@ -59,7 +59,7 @@ Awaited serial checkpoint after the response, tool results, injected context, an Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:263`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:264`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -119,7 +119,7 @@ Recover a model-request failure after its failed step has closed. `retry` opens Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:277`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:278`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -179,7 +179,7 @@ Override whether the turn continues. The default continues after tool calls or s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:287`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:288`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -191,7 +191,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:297`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:298`](../../packages/core/agent/src/types.ts) ## `agent-loop/*` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index c50134550d..15fd4f2942 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -456,7 +456,7 @@ It returns a `RequestErrorDecision`; `retry` opens a new numbered step after the type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } ``` -`agent/post-step` is the awaited successful-step checkpoint after assistant output, tool results, buffered context, and steering are durable. Its signature is `(agent, turn, step, signal)`; replayable facts remain in the session log rather than a transient payload. +`agent/post-step` is awaited after assistant output, real or synthetic tool results, buffered context, and steering are durable but before `step/end`. A cancelled tool batch reaches it with an aborted signal after draining; its signature is `(agent, turn, step, signal)`, and replayable facts remain in the session log rather than a transient payload. `agent/turn-stop` returns the stop-only `ContinuationStop` subset or `undefined`. The loop calls this serial checkpoint after folding the ordinary decision, its reason, and pending steering; a stop is terminal and discards pending steering. diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 2e39b77563..abba29627b 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -10,19 +10,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:362`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | | `agent/created` | `emit` | [`packages/core/agent/src/types.ts:147`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | | `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:156`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:310`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:263`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:311`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/post-step` | `serial` | [`packages/core/agent/src/types.ts:264`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic) | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:204`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`time-context`](../packages/context/time-context), [`user-approval`](../packages/ui/user-approval) | | `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:214`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | | `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:175`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:226`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) | -| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:277`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic) | +| `agent/request-error` | `waterfall` | [`packages/core/agent/src/types.ts:278`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`compact-basic`](../packages/compact/compact-basic) | | `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:241`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill), [`workspace-context`](../packages/context/workspace-context) | | `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:188`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`stdio`](../packages/ui/stdio) | | `agent/status` | `emit` | [`packages/core/agent/src/types.ts:165`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`stdio`](../packages/ui/stdio) | | `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:252`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:287`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:297`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:288`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:298`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:61`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 116366b910..6555aed2a4 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -323,7 +323,7 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'agent/post-step', mode: 'serial', signature: '\'agent/post-step\'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void', - summary: 'Awaited serial checkpoint after the response, tool results, injected context, and steering are durable but before `step/end`.', + summary: 'Awaited serial checkpoint after the response, real or synthetic tool results, injected context, and steering are durable but before `step/end`.', }, { name: 'agent/pre-step', diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 0c79c822f2..702861f407 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -251,11 +251,12 @@ declare module 'cordis' { */ 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise /** - * Awaited serial checkpoint after the response, tool results, injected - * context, and steering are durable but before `step/end`. - * @param agent - the agent that completed the step. + * Awaited serial checkpoint after the response, real or synthetic tool + * results, injected context, and steering are durable but before `step/end`. + * A cancelled tool batch reaches this checkpoint with an aborted signal. + * @param agent - the agent whose step is settling. * @param turn - the open turn number. - * @param step - the completed step number. + * @param step - the open step number. * @param signal - the turn abort signal. * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. * @mode serial diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index 0a7bb0a5f6..bc2a9e7e4b 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -49,7 +49,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w - `step` — the step at which the failure surfaced. - `error` — the failure, verbatim. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L310) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L311) ### agent/post-step @@ -59,14 +59,14 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w 'agent/post-step'(this: Scoped, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise | void ``` -Awaited serial checkpoint after the response, tool results, injected context, and steering are durable but before `step/end`. +Awaited serial checkpoint after the response, real or synthetic tool results, injected context, and steering are durable but before `step/end`. A cancelled tool batch reaches this checkpoint with an aborted signal. -- `agent` — the agent that completed the step. +- `agent` — the agent whose step is settling. - `turn` — the open turn number. -- `step` — the completed step number. +- `step` — the open step number. - `signal` — the turn abort signal. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L263) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L264) ### agent/pre-step @@ -151,7 +151,7 @@ Recover a model-request failure after its failed step has closed. `retry` opens - `retryAttempt` — zero-based number of prior recovery retries. - `signal` — the turn abort signal. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L277) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L278) ### agent/session-prefix @@ -230,7 +230,7 @@ Override whether the turn continues. The default continues after tool calls or s - `turn` — the turn being continued or stopped. - `defaultDecision` — what the loop would do absent an override. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L287) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L288) ### agent/turn-stop @@ -245,7 +245,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a - `agent` — the agent whose composed continuation outcome may be stopped. - `turn` — the turn at its terminal-stop checkpoint. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L297) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L298) ## agent-loop/* From 85ae6848875f96c3199367ccf33454a46a3e39a9 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:40:56 +0800 Subject: [PATCH 215/323] docs: sync type-equivalent JSDoc --- docs/core-data-structures/compaction.md | 3 ++- docs/core-data-structures/core.md | 2 ++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index eae8d2e727..f6cdfd5b8b 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -54,7 +54,8 @@ interface CompactionResult { Automatic callers state why policy is running; implementations may treat confirmed overflow more aggressively than ordinary pressure. ```ts type-equiv -export type CompactionTrigger = 'pressure' | 'context-overflow' +/** Why automatic policy is asking a backend to consider compaction. */ +type CompactionTrigger = 'pressure' | 'context-overflow' ``` `CompactService` exposes `compactIfNeeded(agent, trigger, signal)` for automatic `pressure` or `context-overflow` policy, returning `null` when no safe work exists, and `compactRegion(...)` for an explicit inclusive surface range. Implementations must forward the supplied signal to summarization. The seam owns no pricing API: the singleton [`ctx.tokenMeter`](token-meter.md) directly owns estimation and replay, while `dsh-compact-basic` owns retention, event sequencing, routed summarization calls, and their configuration. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 4d32b7796f..0eaede9345 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -446,12 +446,14 @@ type ContinuationDecision = `agent/request-error` receives the original `RequestError`, whose optional provider-neutral `code` supports stable routing without message parsing: ```ts type-equiv +/** Model-request failure with an optional machine-routable provider code. */ type RequestError = Error & { code?: string } ``` It returns a `RequestErrorDecision`; `retry` opens a new numbered step after the recovery listener's durable mutation, while `fail` preserves that error: ```ts type-equiv +/** Failed-request recovery decision; `retry` opens another numbered step while listeners delegate by calling `next()`. */ type RequestErrorDecision = { action: 'fail' } | { action: 'retry' } ``` From aa21c0b83f882397511b86217d4a09028d92c4be Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 12:41:38 +0800 Subject: [PATCH 216/323] docs(tui): remove demo image assets Remove the animated, dark, and light terminal captures and their bilingual RFC section. The implemented RFC retains the durable front-door decision and verification contract without carrying binary demo artifacts that need visual maintenance. Tighten the package README ownership wording and refresh the bilingual consistency record so no repository link or prose claim refers to the removed files. --- docs/assets/tui/jokes-dark.png | Bin 66598 -> 0 bytes docs/assets/tui/jokes-dynamic.gif | Bin 78162 -> 0 bytes docs/assets/tui/jokes-light.png | Bin 70844 -> 0 bytes ...dicated-full-screen-tui-front-door.i18n.yaml | 4 ++-- ...7-17-dedicated-full-screen-tui-front-door.md | 10 ---------- ...7-dedicated-full-screen-tui-front-door.zh.md | 10 ---------- packages/ui/tui/README.md | 2 +- 7 files changed, 3 insertions(+), 23 deletions(-) delete mode 100644 docs/assets/tui/jokes-dark.png delete mode 100644 docs/assets/tui/jokes-dynamic.gif delete mode 100644 docs/assets/tui/jokes-light.png diff --git a/docs/assets/tui/jokes-dark.png b/docs/assets/tui/jokes-dark.png deleted file mode 100644 index 876ea9c24c9422e76aa839bdead1edd6cb6df22f..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 66598 zcmbTdWmFtZ)V7NR3GM^}!3j=q2rgl8cMXGkaEIXT?(Xgm3Blc6g1ft)e#rZN-#Y93 zJN;wUn(msKu3cTb?tSgu!E!PnWCVN!2nYydaWN4E2#9yzAt0c};h}&ta*ol}5D;h( z;v#}d&S^(0Fz%SfL~v)NwAcp{lGN7;4FaL9EXxZ4haaGKP<-#_VW9&oIK!&-{;Z_q zG?LQGWuI7`GB!sUTE^1IIeY0|yq_D|w;R*Wczr%)NNEWufI@#e-utu&h`b#NNKrv= zhrtKpf7b@S2#~%VF?v7$wITll5&YIhEC3SYtx+@*H2J?qc(7vs8ZrO>>nN;1Kmr@_ ztqaD_Y~F(xub9M4izNSb9#blGdG|_M;5q!+h-nI&;H&+z3JNN+^Yin|1L>qh z&1@yWWoKB^?mzR2^DPYze>-7{Y(8VOC&cW3?dA z_DfOJhl~jq_6@7cBh^s>y%}Tdolqn&uHiaX^FaL2XjazxYdr>5u?3XX9fxe<{nKIy*=it+Jf-vkIb{444KsHk=zpD{z{{50+f~mX zM3tESj5p&IyUEn9-1J zEzSri-NM85ce=P3HQXf{!U+o6>&YuEO^sE&*0jyUK$b>k6D-gAd3%U~-u`9U9$DJI zq~vs!>inE6`{Kx<&hxBjZg#jyRUO>=`gK}* z_`!#jHXH3vKeLT;JayV_@mBKrDM%mq^^A^xyv|Z&mz2Z`mOQM0Lfg_)Q>Lj`h)AY{ z7!r{!Kw-Z`lbjru(noB@)nHs7?!iDx;eo_yLGc0`JxIsa2wN-To zlkI`v%;DiOHd?PSFVPv!(7ohCT5IRB&*q{i=Odkw_EslgYPCq*5AKdfXl!i z%47uBy`b_cc->6Q+Qc9g6u>#{!tG@i%D7O@k9Q4bOE2BkWU7p+&ziMb@SyZVjywI4 zk~pjZHgwZs)5Wig$`KJ+!n+lel#~>%z(<){L!C#TjFHg}DiNQQbhNgYw=^|s)S}a# zfsxhA-uj=oI0>zEL6NH(fubBrCGi=kJTu-Ty`XUQj{SEXF;d33fjk^WmZ{_G1Ns)oLyg{a=JXJso8FIRxLFkkO3YG=YD;LTTuA4Hm zm4`N)m=Ag8{+PK~^E=?OxvHwJCKoW9Y0#FJpBT^wO{Ax#k)ol?b9E=>PwGwDHNh1( z=9@M{7r{rlve6qSGyM#K5HEG%iu~3G0r>YKE$V>*2Sx6H9IoT>$TeFUNG|K{zRaJ>kzY^%{;rQX1)SDUQzIq3 zI{OWM#YpoYyFpr{ewnp1ay~KJ`HDej%7i68MXY&Z7MkqU~77fP+Y+(2*^ z{$XKZgi8%z7G#32!@aXOnJ8`^-RV_J+^-Alj$P!^^yNK>JGXlaLp|l|5td6QYw^Q| zN8JOit}UG}%$-F|O~d8XPKO0_wR3IChZ`H<>REL3i7CYe<8f@&*XGq#hpSSSpHA(z zIRZ1#CSMaTMbF}O|%kPSU&s-)5J(sk%XRcbQ zrmo(}=ZYjmNl$+~2MX`X+`}Wp3x<3^{gl&`CMHmCHpNa$X4f}MpFamh67Kaq>&c&g zn+W*>&-C!}Q}4Ao`ugq2@bDw@hoFoWSJy?2MYYA@uwl1ba(d4^<8io6KBP#2yxpB0 z?>mv65U0b5sovR>hndpd(F`VL<}R(c>oRy@Vc}sy!O%9b!#O7xH1r55nahN7G^ZXB z5Cw&VOgqJAinSKc_GS7FrM2w|U%2!0_d0xh-qJobwY9>GS_1AE%Vo{J`n*W&26yJy z+FA;+id|M~UCV(;Uf8LBt>%xHwFV4VQM*n-%bk%Z9?%|A1cX!+blKLqqI;q)q_jyf zF+LDAz^nj^D!kbKNud}C!|Ng_s0iu3jg2!02S=Ym+98h@G;DGPrn-|3b6VVi26w+rE9+bgFLJcT3Zxii^FDb1>viSiP=0iXO^DF z(HTjYiJqQ!P}l0H4j_C$AdatJ4=#G-t{OqK9T}JxUpB5jHnre$SjA*yG??9=8m`t< zW@k@iE8_O>T^voN#CPK2V1Xrq2o73Vzc4-D()@h9J+XW_l=vNI=`{2Z;Gb_ef1D~tRXne-u{V^+AZn8htvBX-22U4Lk-?Bd=!7Z@2LkzN&a$(A zkZkiAU713purRQ&XCm)j`7<=S`m%Mt3CO9CA-l)f@(NyrgBd%~#>h%?sTM4Z91C+k z_d5Y%(wr2fV9l6}KNOC0leLTcA4)$7%oL)AEZrlNz{#DP3OaW*bOsziz9Y>U{L&a_ z@M$AYFXm1SCJ%QjQ$us9Xpd1$INI4%|0{)hjKVm_7qrLIVW=6EUd2$WP`O_c22IqvlSXRZAMvioCqHYL=ojj82lyv3K65;(M=AQ~wU z=yTIIJ9{2?H1FH6FeDF;=X?Ga;-Ozf#n`ymrF*FG-@?MerxX;KAQlIclVf5-iSq^!QiSVV`Z@;V^{_*(xC;p}}&fpu4-9qd-Pc z(Zn}*LKpnCC%=O(uH1Pm7u5N5mD}u}pPH&EcZpNJ*wE^}4+hNYwL-}FeQWrnnZ7ie4qw{hpOMFWeyqZ1S7JK={HRTA2{ zVYKs%X}qBj#o|-nyGw6RS9)f}#p1MB)LqRHuw&Db42+CUv^qU)#V}sF4~RpPQZ)}f zkwSus9E(gaihUpzq;<3!Kl5Gx5GtwpU@EJH04vAlYBI4->puw2<0XOlAkec1vuk_7 zutOCZ4d_aJ2=AaG9+U3>wt)Wb?#V$7Nl6yUuMfTT=6ghrk2nepzJcwo+mqk6+|gpw z_-vklEobl{RME|0s|Z-CWRiX-fs?7xNJz-|tQMT$tEAFI#>0bs7uQEIO3y_kIN!|yh zTwDXwbyjQMzF>VYnsAOmg;qyUq=KTt(a|xt@HE!Jm$KTQ?KgwoV4P#r@W z_h*^H;d1rgAVsZaTfF!@%fN`8ganu7W*xqmL)w$I_RoN8UZBAuQ{Ey$X7f6nD0KR? zjgx@hYk-60?%evMEA(^}*|yxqoIt};xR+bMtxKHP&YWLVHW6AITI0Fts~B8F0FDun zl^y%D^ig`ftSpQ+k>R=8u|7$LtIlifc!`6)oV+vMkDa4MHk~Isr<1rni}uCF;`=7$ z11ziw#p!B2H1F-n^7Y<2^cLJ=!ztQw8P^3n+|4mMbn0~}#hBUU`Ssy){YQU|%J=`v z0&q6_vwclu$wn@AAL_Z9xyl#oET<|wJUw3u!o6@LgYCq_BKfPV8Ece%1CeowjO5Uh zCIE#WowzrhUm9$>^7Q266`IYnp&C_#y>>muPF`PC)c$bOlj-JoBCwM;oFN1gRI2_p zH~(%wy-G7k6bb1{v%!+KXqhwwLq;Q?)zBr_d+ohjy`zB5ke8y}yps;U|t7^QjE%)ArR9TV`B zP9)G6z{kgDd$bczN=ztll#!`Ni7~_ps;FQ9H(*F=8jYop>W~(Fkf2^t2#J~-937>8 zcB`bq)7EYu4vU#H(!W=ht-7)wTu#9@umG2omipeQs|SgRTzT~jFRs6ohYs>HehyZ$ z`k8kir#bQ;T-kz*`47mjWw$|y%Mp?lcMSS`&It<2sNm&xEK$9|-3KD(A`PXLu)Jd1 zx(iB45s?{8$H#)V-;_S}F;Nlv?9%^(GzM`nVp2qJ5$*(HX;X->618vl-dn^SWY$dM zPk#`ffssr07W})CV5vUnUk^(APW%g@+XZOw$j(WS|3%=;6j0;^k#9fU+g3;>$6)zi z*b@SYG4+o^TrrpYz$gaek&FJ%ccD@>xm=y*-~aALN2um!5fmPIfXrK$R~SVCCb`r~ zk;(PG{|MBT0va^=cC?ZUlZui^(!X;`-1A&)O4m$K1Z>Kg=S*w=b2kSw;{V2l-u_+5 zpQ~s1e~A?pYE%;6KbnykbMZY8@Bag*B%sK3bpPETBNGJ)>i-$Y|Djfc2vN=+gl|@8 zzZyhvPZE6VkTj;)^{3LX6z1EN8NQkK$`UYQVXps-@+wk%7MM8y&vpY!OadF%4sSQB zWUkEhT@Uu34a9aj0doocGl182r=XlNvshclKf+?xT;fmP*8T6x{{?JeLO+$N-(gi& zzD-mPu8@ttF9Da){|DBYsF>{)I(ejrJ8k~Tj6+9_uxL` zc*Uou5sxE6k%ZwlIQc6x2)IhrT_eK{KbC&sXQW`(x+u)(kW*4~{o-Ir=y1)9qXvLC zDmtnaU15-Fxtg5n9F;y6@CR@Iv$37-pAb>ekn!6tna%h&@IQ>VbknS?%iK5h*Jf=8 zGqX_bc^T7ryANA1iL)zbFXpI~8#QKM{xhpQ{rY&5^4jU#!8Fr=v@H6bq0djT6yp-? zTjGTWR&iP9;eU^|S#y7A;hEL(KI6D#iHa7uu%JLkOO5Ic7tL6KOO>_LBfq+tDubsk zaQ_)`&tI`vAfTG@ZSwvv&`j2_L5<1IFOLu;d}CaD-@bo0qWG`VcVY|F!S`J1Zwz%J zl$e`dJS#Eo3Zr%R`OLqoZJCs>=WP~s(7xT@L$$l->B*P(6Dw;GN@^04#ct$mlx^J| zZM}2xVndc@*$tq8mGN{&%}y-Vheo!v?0MO@nP@hp7G+0SoIHF$u&rg;&_}Sf#R{C5 zoN}^Sr3T>PgGSID?f3ZfZ!#JoE*_|C4)xt0t6#sys2dv_`h!G*gndd& z%?WeAR!8dR=H#3e1_rifbaBr|gP_XxF z+A_zD(VlrJO2VF(-gA!PP{;A(Cak`>o6A@q2jj^-SYmNgj14*5yVIiP=I*wyGlKqU zV{)xi)e*-T`PBop#f#`eT=H4dX6u@Z1Cf@JT$PaloFU|77@jri2To!>h7N~Pl{>p< zqL_tne5Q-xWR|@T{GMHT1F_>a&x_ZP&yS(GPuI7)@HyQl8yg!R=PFS@eno;DZb3dg z{4gsnBVn~#mTbWF`XDJOIW*SSXt~sI>6xqx?$GZG<8|5SJ|q*BN@bUp)s;O;j!(w^ zfJQ8)Uu8IyK;j%bW_VYnhbzqZk76>y`>~k$XnYHBC&>h>CNU0tH`(8Z33o0XFt?`h zjKjgD_u4i#?te6<_&oSn*ef#lXk18XOd-xJ9~9&|dXG%l(XI>PAWc4F2_$7q7lfNs znMsCeaySYFVghdd%qV+uGWWzfREt%a1@7X$ooiJqpQp0Nvy1hHQz<0Fs-;e#PQ4gN~{zg8j83Y zO*lC_D@tttyvTMB%5=Xt&-M+BAmBDLG~C|ZE##cloGKs{R01pXL$RU0jA_(aO^K?i z;u5a3I!ca-fk3GZmOYU??c{UU9TP=Xtymf)$Ixx!n63Nrb9h zqpb*1?Hdp z92#ienz3Lyu&XjQBqJ_0D5Xl!R8#A0IBK0_dsUBE==G>m1OW~0+gKn?JHbNyML<## z(KM%uyYcx6ANj)<0VaVMy0(;*hJ-DnJP<0;fE#HF0s@MPDkGUJU^9VgGIsWp`H5Uy zhBVN$U+~dlt=kDIzr{++^60nGbfBch#Tr#j=sg7V%+zsWMRVO#1BjMg{2PXcje z{ytCYb~Za5mF5@j&N;o)!DXl8Yu+-y-wwgf^l$q}La;i+#_AU`!7-l6X$lU`@OZrb z^Z0yrR$DkmDquEI+hCUH3xquFRO&|-D1JX1S5@!C-UM0d>WX~`HGDB z==2nKgO|^HVxIQa_gMuaeVqVk;qS`p6{f^bQ9pS!YjKYo9L*`p63|whTKuy%%R%)p z==BL%wE)0*rK*)VWC9Oi@8mB5u9y*#6zjqFSX~ zYoWvAaZbmr{z|Ls&!3(MU{*s2gMuEe_E`)MQXL%~3knLno|>}_Lvh52%5~}wzeeYomnW5%Q1zrv#bQxJRkS5RFi=&hx*nFR zWBj?VGo`Aqs00>5AB^0XQyG>iY$CA!Ul? z_Ls9|`JO#0lPx4k(~CqjVXyVqNPcEPt#;49oKAE9bgwoGrhXFIcGzFUMn}K+ zW}L^&Lg6IUK3SUR{_fI6B62a~5TEhFupAy$}ZEfuxPY<+&rmhD^ z3$@K$F=#^r3-3=m8Fa$ZFusB}!9;vfd8u@C!*8jtoWu#lWWfuUZRNJ^lg&`0p~uqV z($4DBh^Mh|>#N{SGPj&xKQlQ78Qr*B%~taXnm^9^^i(5($AC=3cIXUjjkWI1*x z|4~lri7zkR^6d%K4sLOu9c3&!)~r1xSW(Z0tD@aoP{dIACL$7s&xAq9Vmv~?V<7hZ zd)CI6eZ2k0+tbs@e96w2=g#|`k1nr(OY^$lR=qHG9GVr9K0dhi$~^yK+YQgl`|SDr zaJ@gZYhzJX9Uaa22i;)01Y4QcO}>>roS!|>%m0e?rb=~088u+{#osAJrN(05 zbsRsVbKJg^-!%s$G(6>36w{wpRuog8R+d**f>G9uQE;%a_U70)>>PzTf$hk{;H6MG zxyP&0jGI$6Mr4wM?eh3JMNYh9^0QMWx0}q9-Q&%%&lN`m5;9T`pTB<$IGN3k68wQY zde!ap`E~f=JKh-1oKjY9?nk_PDkc(nZS9rW-riroAg1mgPdiUnVwVlDac}~D4h}C% zg+*Acb+ntTlm3sZ&MPoCA;n5$k*kg&(c*#1A?@-rJG@&(bqx1WMK-6N#yB_-RdIBs z+$m;4wN;4md;Qo;*?VGjf|rcv)OE78y*==FxVP8T+&#_a+$L&Ztq7mbq)y$nFN1Yr+CT~mlo%BYY5vt+TPjG zX|`4W=Y|$c6H@<07^DxKa$4NXVt_Tj!aBTV7;|vFy_4ew7>hN~i46X4ii(TX3nPd%7J-6+e{})X5fN73U>oY~ESB?<q1fB!ju?n?Oikxp&3GnkH2ilUvbV!MElnGkfnoYGR2klz3tsKHC52<%X90) z!^8XYb98j4e96+C?Wz9X*%<*XqDs@bl8FphxZ)Z!FW!R5c>5nFS37hpERYgtXeB2% zEEZazN5@M`OF8UsYpUu*GZArRhIVtLE)y(?c!P=*`-(DZ5qE-MLL*}0vU3%m1CV*I zu90G5Fc`ErV`I~mqwB|~raHY&BiuI_ke4kik0J@Vsc=#P0z^yM2~Pu7Lc-jMl`<+a zK5h7oN7+GoOCKK-l98SSKi9L?P~ch}RCV^Ab%96d&jX!u8t zshJr;C%GR(X-8=QxzPuq_QU2$c~+!O<5E4QChi2 zJlj7pBf(7n@MlAMTj3`kG`PMS!j_%w?G4%Cpd%sz|sjQud>w{7q zC3ACbM9ET62IA4K8TI_+>F9Fr#IhxYrkr4`BFw4U^JJ0YAk{TiMN~ zIa$b{%f(S;GqbW1z+T<3zyjvvYVGaoYhk|<@FTkcr6nX$nQG;vhoH2D&_p2%+cm2X zH9&^@j>AgJ%GTG{F$oNe?eLbu1TZ_xf{g188cZpxIuwl^w4?xo(A6rm^xb^h>5wM~t zNJ1hewH0@V^oFCcs%)346eGwVZ5tm?oFPh>@Q))k1D!}XMx(rpRYS-(p(cMlg?v4! z8UyG)>HwUtEiKZi^&&(pETI)Et^nVU(dr^^QQ{_%Ptw+4$j{ zMjo!>{BnQoT>Zoh_#7}%pNW}CQpz-T+^MU-zyBn*_;0lU(N`VXpn)6beEzPgKvXiM zYvfkP)9`X)PoMIYF1Me2|9rprceJN4TrYxc;u{W&*ajLeUCR*iMPMGQ}#_5 zb=sWQA7(;*$YWf3hL%n*@)7qOf7o|8aU5M0=kAFr4lge&@YSC^#f_mrZVzQA zVO>D{(IwQ^*N-$Rsi+{2x7nE2Gc5sG&X?x;Uu2DhC(b{g={ZMcJX=^CML}0b!=k=g zJY!1#a&tPhce6Ey(U=dS9nIvX*P)1yLR)JRudOwf4GIngBz<`*2eG$zK~-TQ(ZvU` ziRC6o@hBc*5(w&u!#PGo?1J+A`tz|Fm*yB^v{<1GxRJf0{=h)gW9-B>)l5N?ep10~ z3wjGn3MYc+T0^n~IF~90ZC&)h;PCL#(NWPYG)%%^{*Ntg1>~PexX6^=Z_svshNmYb z`bNww(ox!^cCpm!c!LtDug?&W_U(4$qpD<>e^#S#Uxm}@GM~pmQc6n6K3Ub1`6hn# zWAF745HObQZjs88Qc(7ut~O&6{vOfb=Hv`rAd$7^_k(-9Jr;1Pkp+{zQuYT1tqUf9 z5?RL0voVU6v%envmdzu!toH?r&z4h9k0T})LlWu7_ca-dM7Z@^^yI9aP-tS?UH}6W zc4LB+aO0TOxZi~*GWsKZxGG6)Z3IiuaMJ=s4PK#|kk&E0vI7-~v9aOUzxN>+8FhPt zIV>0H82O3fo12>U!2QkM!aC;TS?l$siE+m(!S8LHvBh@`<)fkglPM(;xO4&~`UYjd zMoMC76VhFp8Wt{n{^^!ef>sqcZ!K^{RnuQto^PVSqiJHmPN(Lom#bkBH$<)Mn*Tl*+m_pFY()6U~ zcgH7K0eiobyl$^p=$)MyU4lzglZ_=R2txb=d^L4H;|Y0GirNS_x_eVyaW^K&XXGp7 zni3mbxRg$?J-JxLVXPMDb8=$&^DmOhp}=C@PDuQX!PzdI7M!4nywIymb6o4SjtHKl zhJ=QK0vv>=;eAY@`0ukSv+Q$~;!yl~RcQ9=>I*yxR@;H7q|3Z*UmZ`-F$o<`b&{Of zvfycb_TbMAfNf-EA{stfAdj=G+>(s~v8=c>m+Y15=3KuTdZ`_dG94X)@;2xNkr4X> z5HTqF`pS?BBVDe+i8B-u<|s7A`|uLcAwCKuf-QpbAiGOjX(=ge{t)<1T2YWs-44~# z^_Pm8;MAm)>@+wePvs{?kR}{95@bwGd+L7yn!4+6DDv}+>&b8))^3=6WzmgHu1OTu zE}*0&|Jg8FKu0D*j_G1Y+eW@Rr7k`kbKRMdDz1JW;o`Cfg8E{@cQ`BzBR3S8dkY5` zA0Q#@A8(MQaEIkSBjt&f2dO zvRKyd;qUQjx7joc>muY#PR65|6#~gJo(|aJU}F!?L7fDw2>skrT2od9;Xadfox&@F z&1v6DpyOskhMScqb%TciVn9&fwdDi-VZ^VDiC@F`SC0R7IhANgtPX^9`C;Yx8!=1^bgaBk+AQ8pay ziJnIiVpf7!A~kQ&BijJv69)>x-F>|@FU1yfihM2uh4RsnR#fCXJt27(r?JP{Clk@|*n@8CFnA%UApUxv3aYih^R0vnBUaROqnG&G+H4Kd%TZ zPQrJ(#^C@S2=wQxDBiy5d{aO`K%>>mZdV&PTkTxdur(uOe^b#x`g)R0dSR75)jFEo z=`&6x_*G(t>c0TMw*5P*slX8TSIWVGfu24_0o}D!o$bh;^x)^IwYrgt;FHc>k-5^JTi2BYaN0u zqPR3T*q~gBA_QY#Xvj5ZZDMH{D)6mbqB*p!Z5h~5Mz23QJ3s90;{gtz&1!O3#1*ll zrXG#)2@%0ey|Kb&>Td!CrSs(u8yT5CFK_$Oq=1l&EWV!@RPY6^M3vnSkq)Y(8{~6` z$64esDh6yE)NosR>GGBWqeTr3wSJ6EQIX})pr*CFVhj2>mnTk)DUteO&ABp{Qb!8D z`ubXsgHS@To^a%RA5)P`krGp6uH0{Y)*pY=_&OkqoF_|(V3_K+k2eEN2G=^pgT=F7 zl9H3Tzs~frPfpVDr;J1uobt3k$+ZOpI1Cc%lnwWrkT*%`YN)Fp0lLuX-$RHe; zOj4S;(A%Wb*glkclaQ7RuI20Re!9c_TsxM=LxbXVzR^6Y zt!p|bcwzt7&yVw-SInfx(evVo3E-BV&;i-{&n?>*kF*BlmSFWvGSE$<)l{|Np(E!E zArY=7>5|+cpqS}3ot*P;A?yQJIu^!9gwrsXWq>E$YHKaeVJQMWOl-Mkvmcz5%V(aSkNE*T#HNFqw;W-YLk+bHBT)=&S-0+h<~j@LKP(Xi1e zl{EWqJ*&*I+RW63LLz+%YQ6Q+kILxI^_EFlmywZ?5ko^HmV1A`i1vzpXc9fS$6>tK z=RZ>xVFYfF!O1xdu}>(0%bbmkjZnKC5;`zYioMM!2BYt2(PA_?D54(b+0$m{84JC~;BFyC4Mj%`u@U>$CWAD__k zAxoe>CSCE58^_SgfJi;Ua^I`ai(DBo?;+i4buPU0%w#xywO9Dl4~bmS@Mv){X=w+0 z`^l*(Zm(0vZ@n~^C=>=cQI@|noLwbka`=Pp#-wrkKlKwa-G=E!M`cp4=q`Aum z_X82e$SMFZ@{95}Aj|emi-9sdB^=MTAV7oQ-*f!NCtU1&bn$mlGF(_#V7q21TU~t- z6Q-c-&g69y3U`A4kGmk|0O`v&WVO8(@UpxDsQD+o*#mAzgU+**!QV}h3aRlCl>k_UoHx^yA*Sai@D6Mipqw|y1Vh!{^EA|1!MYwNq|6G zL4SX5FN~0%fsD7E6h^sTy^TPp3}1O{!1UM8mqzQAQLhw`9U#N)>@Kga?C)dG!^5SY z@b5L$Gz!QIv9Mlt(Sv~9u*1_+tqRawX=wyDBtSC4_Heemtt}>UbZUC~?Ci{9zDm#5 zwq~PnZ>=gjHLwt*CrGkW${7MAITITbYisR9jS4tD?%mtl+m8v4Ho^MXM5#KIQft3| zPi%EwTwEgN^{7?q@G@GT0;mT_tx<@UDHcXVR?5ojMQ>Q|92_3Hxwrs`Kw4aUpnUk) z1qfSFP*93&7hXLY43aG@ET7#yuCK1;RVX~`Ao9HpBSJ%Iok#~8U=sA6{La-E7V=fq z<%KyKy?tQ;_LzS*kjw}yNON;@2Z!rriPgk;fZ1pL%`%^R@#y~?A&-ND19J}(!iL~5 z*4GEDiFCg^KLi=PP(P^i>&qFAFJe++&NV)UbF4EGszz8??8)GIap~vVXmTKyPF9*` zC3V&D5tTvZZlVV=`dJzS{oQn2*+;MkLr++(gOii96}mu?>>p60wd&r49U~;D&-MNL z_ar3ot@-c5Q9*DZZtm6)ETtKvb6e+XGpt23H4WBxwKW;D^<^g6GU+!sC|~)X@AQ4@ znionON*T0ULjp2P8o#b_Ah_QSBC1WQ49|GBTp)mOa&MW*#2ik&)qUD>AZN zop!g@*4A8R0v_kTFHXC52%Vz}q9Yr~GKxcncNUtwtlMs9x7I_m?~GV=~3~ z!s|ZxpmA_C3i`rzUPv%92?#Z|1oZBVq;{PKMiQ{qsMqcQc|j2tC1K&s-tfafAXz#x zfXC{LhJU`&;*sgZ6PkE+Ff%kahwHsjo!eJc@L4va>BozZhM9(3?cdRKZd5{c z3m~6`xGiWiV^{K73F3m?#HFvVuUxHTa%!m7cq{`N4ppPY`90skL~dX}%R`qxBA|RJ zJDKn#-M+v6o}R{9-#?sctnBm>kdUYe4lb7C6;szIosXb0=y`$vQ$>$fKMQQFUoA}J z#Lxlw4$hk;cBO~uCs{WJiRE0rXiYn&@2Tg zi;^8d#32sP{GubL_@{Y(ufHg5nZVfCxXwW)ohLZ*htb5yinOjQKL^KWIy#G?9r_E* zKZ>jFn8;-IM{AwBo*T7_g)*bp>8ER`){}YSGBP)-?T<>CnDmL+N)8&sYA_!^9=14) zTwGo<>b78E5%~440SR6JWQdP=K0g8hOhI<>Ip@xKi^E|}W**cJpN7|;-c$&LmdA0^ z)8(2CJkDnVHZ=za2f3n=lQT2ITe%wuw3^(lzkT6CSKMxnnq4*np2+GTH0rI&3kw4k zOE_JCWtoeynUDm7WBTitpc*+c@-={a=PETnXEKgbxVgIGfBXo%#+1(Kxp7sjD8#0w zsY#Zj*cMV;lVKe$kMFU)oPU7#TCVztK4N6} zmAybh3JOY>)0K~}wm3W{JZUl8QXVfh3M-@=BbD6bA47)j;e<>Be(bG*4p>M37p>{)a^oTVosT62|=K_w;q>UgB2rq=Z1 zcNghC>f9$@TM-)tY2OrAx5umv)s5^)`rbu0mTF z`y$if-r8SRR?dtA0YAP!Cvpnz6 zEt(uM^7QUO_XF{no|7LhPyQ%`U*{JWauyaFJh-ox>r62RF|Q?RM5R+n1%zlsKLzW> zS63q)en8m%oxx`EH;Y?Ouc883(%lcoeUmc$`Wm^4mXP1|2&j+&ub(b85=EollmX6@ z>?0jYm^OyZH+!YHJRa*6QSJ^a?I~O6yvZdYzw4Cq8zg99VW}V2B{N`ev97=9mHL?9 zdx-cW;!(pa11VqH-EMc>uMNL3e1^6|3|;>dxJl*B!lt3|>M5>ASgG9}u!X8%7SgHn zvQ%RT21(dn>?;;>+aK*sW_f=QN=iyW!DIe_Nk>Q3W`DkMvJ#Vd(_1~-J-=0k_0nB4 zfUB%7Ei7MWG9mOZ)eEE6%0F9)8(UpMYiFTV*7g#lWI<+Qir%QHruKa;I5=YAtdEGZ ziMrGjAoaX#2VICgC?gEqZfQO}w?rC9&CM<=ZuWh+EPM#?XJdoILi!9WEVN&$&if~F zxAZ9}C~^!V866%!C+hw5&DC#rm9bo`laZ48r7oV9tXSG>U2lIpdkv(aUF{B(1}wRh zxBpV97j^r+bEj=Ionz-C$&T*i9~IanOY83r7PikT%+E#VKOU(6`sMk!u}9A;a77f! zmpyiaRi2Y&)pM!Y^I13$rMTnu-R?B{N;bCtO<;I^eVfixI2Ym5GHo1ZFy)nC`Ft5>KN<2*7woiN9+8Wsl^ci_}PTs+zja%abgf|5d%F+|#B zM$Rpol-u>Hs0|ed<1m7LzRjf;oPBqZKeS;m5iWqsjRNJ|T@4HS3MmC*6C<^;McFeCo9}yMhzwlLQz`Ul+>5gSnBh>zdlJ8 zm6y}2kIbv3xtw2I2vM&SN@DAHH`6ZRm}~=~i&0+TT;(bA!GNbX7Aega_B!C*F&>$K zQq_tlqWdxiW@TvOK-uj*gcwJeH$l!XF3_rOP$S zv?B3)x@!ySQA%N3KqZmetM9FR5du3~FmtZMOqm zmsJmQ(wi9=T)n^%QQcUtWkYww7>}d{E9RMKtQ+veeDZp|ZmdziyL(7VnQaH$Ujn`6 zJJV0FpLKgKA9PlAlBRR~5ow)C)nWY1Om5*PxsS(9<{O5cqYHHK8^VFo<)vN#E)492s(P0CN!8fA+Ko(Y(G6eySQ-AYCu&$gm*_VM%@b|A+e)(?Ty#mB4U%;S8}YW>IDxzZ`R{1$lJ0f5Hnk8c8A1^Vdebo?2cOikd}M+F46ra0AM=sxJ{H zAAcvjzO>3g0&z=?p03w5_E$=olpsYUuO1D;3nz*<)4GqhIm#qW>J4Xjr)ynQG4=Q(Vh~;#nuC9XvGJ#*u zXN4?;fn7BtX)@BB!rdOkDBBvl?#j%vvLm{Emh|pkNR24L--34yy}|tMBT9MiBYIn$ zNs{MZ>}(w?Y=8QFn_!O7>WR3g$ylu@~cCibMD?Q**G(e;#X5Hs1!!XwcU zuzkFt7fk7sV?rbcpM9EdV$!(xxxy!*bC0Ez23)$s{sx7nW-CxBb~W)QuuwL=VssOE zQbDo$zB^Tix%Bq0ccFH!(O7c$gd~#7(cT0wdwi~UML=!PX~*m8A2`%;VywzsVPVWe z<+CrlC|d+6r67^H=F2!3ot2V zL}Jm)^%m4*!JU5H?`UZyd)_-9Ouxr|0o+2P)k@4QkNZ~t^W!ag0vXI*ZyZO*>xrA7 zE&Z%|-r|oO$VYUIB_DfLg|z8zaUg|t#qn}q*wh)?ZRClcgv4lde&0A9C#x*S8U zsHm7ne7HUhtbHjqHJ!AT6CMu6(CM@yH1fNSkF2rT6g43Hc+b%l@#Xtp0aiyFSQ09# zqV6)AcXvlqV>({XYy?sgenCE0wh~fL4MHSA=H7M$@Y?tsramm_Ev_|vs9TcO9(eqE zJ`oWpQ0xYN?(S{!{zhXNmZ#tO^}0l|vF_952OD}e`)YQfRyv7J{{9W(K@Gv(mFW6& z%1_<0H#zq%A*)O@ct)(P3e%M6|Do=!qpIxQcV86&1(62nmIi4grBS*Ylx`%XLqNK_ zyFt376cH^bL;uZhJHZJp}OmH;|FQZq@Luc4v7ukR0G5iy6Yp=MH!=c`4Ece!+Q;Z?JR);=jm zmtgJgPs)g?Y#wE_jk`ov=sT4eLMq@GX!UZ-H^wBMgIVBmErq}nJi+_YO|Eo`jTk|m~QI`%a*s2qx7*iYqk zslZ_PRqt}iuppDllaP`!UoU0Wy>4EDWVO&(Zr`t-@#!mr$6+cjD6IrWzwX8s3$pR- z<5s)f+FwUathM`22CnyVJ8TD=KN@fL+l{@R_N-OoYujuF2X6a zm}P{_T57Fcue3X{65#p)z1Sgb0rZ>u6FJ2AY=NmZ|JR$3A|Zu)>Py1h&k8~1yyA0~ zMeMXT(}mtC^I2q~SZg*zPfTSJ&KPx}#i2!PF!gvOZx&Pht%g5b4zb1c7j5Hr}#w z>4ecdzgGl>SK;fEI&pI}l~#*${{xxt?ujSD#QI&G?TL|O@A}$WdUZ&< zxxGDB;^9bfx-SYW>QXB#;(7K{SDQ~b4k#J8XRbMvi8I5KR>XClfj$92ljppSDCIT~ z1OfH9db{lvq9u>jn-DE-huBncd9+Z<5}F#HJGx-UmlToYJ|hHT?jZ(-qSv*sG(~b2 zv(=c{N?LnSaY=dCj6Px?izWa9hl6MZAvv|kHD7bxhdg!>ER)oPBX&v)t zp9Q&=x|FL!v=eD=U*cO7U?Mw>e36f9i^QtF^zk50Ub%`T6Dx zunOp6U8c>!v3y>7!r|bcC=I#YRyxE^OvD`+IFHKd!6&8^V>Xj8F~mG?N!8<}gJCDy zFf-Rr4wvmO5c8!^FNiq}I>kzyUmzY{mDOS&hlcM^Fd zM5(;zj!53TIo8}h#EwxLElYgCEN9eSmTfZX!Qx&>Tlpf#4>~x4s3UVS2zu(Y(yEh@@$ly9kVVrMfwi)SLiW+1K? z6_wJ`TKyx`4YMe(pn!&s4)U-!-~hLgTORPyY}+>TaIS8YHNT)Zgx-s)s)LS>92o}1 zBNr~D5bVXD-y{cOdFYCyD*n`{Em=D@8%gr`S^V=W7Je20kI)v$#pF0T6Mj_0nAuS( zf`mUYT8Xg#piwE8CF=hX*n--te%IM<*4yv~L* zn-Ml3A;cGHK9R#Jv=O}mXUl18=t~AqPOVQ@-`p#czO^-sZREnY0S$1m2;;v*fajk) zkve--_SqJ-J=x?~g@J@3G9-vx;`f29qN2Y~yXAPciNdylW5p4i02zCc&)GKa3w8C4 z>h|9+7%3%_jZM|TzR#^J@3jURJL2#ps~k3C`6i=zB;^lFe_*mr_V@NCerkKW8fsgX zUxs)b$8WQQ!T|Wp8h9i`y<1ngW%* zfU~7Ieh%1I#ZRNUIz#a|4t{&y1O04otPcIc*qqydEd)eQQ?cKFa31+AqKB#z6%i5k z^ zs)Sn>3&Ns@gw>c&(`jGCro{L({#has8uD#Jq?NyEK)3KY-5kg$7|xN1Yg%`!jBW1w z3KR@u6xL`oa-CC>oWbh2c-WPkFKxcnajki3(-jJn{y~YK{37U_>?imi%&|>ljI^`N zEi5#%!<0LZ{8jA_!{ws*HVEN6u8iZP$VP==+Ul17WxJPRbV} zz4dE@x}sy7E2MQ@@+W16+e$`(ByRS~_Bz{bgcZyz$l|A&{;c8sqeDYmCu`O|s-Iak z5Od^62QGUN-n}^^=9Y7{iTb?!A*Hvo73A4Mbe}geECzMQykib(4M&tC+;u7 zbW`x~RwH~GrKnb4u97*7fS2a27mDk_TzQtuAR&lqppy^2|3$(lfouJ2QVEb%X2{t)d_Eay}tD$C0HU#6$$S~Ze5rLMJ! zAyW))#9AU5#Nd?UW63nrGibkxF&gWg11Xsk!Qe-si_eYRAe2h3FNMaAouFl=UmzD6Ch!ieve>Bom&%z#G8d zll|gUM9M!XY>?qR7-`Iao}Qjul7<=4oOq3bl#EQGPf$i@aiRmRJ10+Nv^|BCf}+~4 z%=7DuV-lK{6)06xSl1^V9ey63Mp1-DZ;Lp||Iz~bz6lp(p2=?H7>0aq!pj8 z`Tes$yTNxwliX~73xy~xT&rm__r-`yU^t2JOkO)|vXVD5z&Hr-GRl3FePGJ!WMaac z##iO0LsPChBaKl@pg?|CRWs1r8{&$gri+0&`@&Y>ldOUejFLKE>|<+buy?EtxyFN) z>+Vdz)0Bcc&-c>OH}*OrQ5LEIuU+^gpfJlR2jcHGuC zY}Nal9?73*u+=x(SrzxxmfsPiUz*AnX$y7x_m9;Ft1XcAc27J`L$qbV?>)W(FkB-2 zuOJU|m3cNAK*CH)Na$}Aq;P$V;-xQOErGvNP3n!|aw<WI)~ zx8gAk5+P7;t1ot2+mc##Z@O}?aiuW(n~IU8`0R5c7Z+?@UCyl;9`2?=b}Un4O-cG& zjJ1tuCWOEF=ww)<zMHzf#K#4A8KY7M#09+eV+0#S zy?GGn3A8MDy*HW7{zkR6Z`6d7xozyAM$eiWL15)M@*n}^KL|x&vUMM*CC^`OpgF{lCEOhfgO#$t2@n5FOKQ(O=i+DRpZS0#l@q@zP)W4)G zsdI^Az&~if|2wyZ)n}7@eYpv77rXmG(%Dhv?^hDMi&Ty8(S+D;rqi{5)9I*k#eXFB z{-(kF^;0$Ay8EV^X8U|j_#FllBOM=dcjWA(c5o9lHaGS2M16zY&id)jrTQ^%|Irnd zrfm_!!GGG}Vh?{PFfvy^pbGUYZg6KtCZP4JmJD)IqwxVca@Q5 z?l?s-lp}KgVk28-;!Y7y%Is4&|S#TNQd|c37{IkiS37k6UkD63Z&iIGlA-`p->5a3S%4--ZS>Im$Q#AQ+j{URFVo-{sF};p4%(Wb;NdyfJE~ z%tS7a%YX2QXy=d5e51u8T>{OUk}xFFCW!f1HBZ_;iHL}^X3Vw^6qG0k{d+6ob=Z3( zNIgI9j*Epzl*Ot%CY3psy% z?Zd1?AOZs5M~tztRVqZ)Hu6^eDnlXCx>}uVz2gC!#LsL_>(5Mie`9UJie8B&o*(OA zFeTh&@?S9!K9xiLA{fKTYB_#+TYbXMG57}8={Q=JSGA}9H3MwjG+-M9-jB1g?y64b zi0}iR6!_W7G29$GTIe5Q=9h14IcX#Zk@K8oukIS zPou+^d(!K)kI0Ar1qmGo-_?=TOd0xH<$sHzknO)M$v*J^`jY2$w7$tgnTrldcnHWu zL+2_iXtimTixu|{cXuf-I(ruuv>j`blT+Z3alGP6QY|5!%&hP3RtJ$RW@?JNe(!SJ z4VQZGFDHx+4^Nj_3*||t{Fu@2i)RYLdMMO=G8R?G52YG=8#6QacyAQRz*5Y%GL)Mv z_q@viYv^wv{EXIA?!zva7RGET07YSriNm zJBBqL;E*&5QZ81nGS1Nb2^w(rTT=r0QZ&_dN{+YtwP9(TB#*0G4z@8o4j6i;-g9v& ze_isZvA|<-?u(I#lQ?T}I3&Db)PXh}^#Kvf^>V+~LZjMbv1Yy?iV`)W>2{$36Nia` z&l2DbK(hoJnx<%K>m3mxN6^OA@pk>;cU-0n|Gj?S*07+3yh73}ppSuw=i_IRiQxF> zS$3K`6sHc`mcne3L>?B`UE$t)}^T%A|ex>+^{=(K98O5K#@#;$ z)3mA$tIGq*rylwX6ede_DDCw=)3t#v?MoUChXhwwSEjzaG&kRa_qH49cm|oAzsG79 z1Q`q_Q|AL!o`mA^n%)i&w9u)(b2`z7c%mx0p7&3Rg%Jr&>qgwc+`+~yxIHwnnN7Ms zv|XxlV|=bXn1|9MVPn%t0#jSr1Qog~jU{z7iRhmrs;KumZq!8DkPXZETqLXwLE|n@ zA$Uxqr|6VY!ZOyU8OrH{z-Ymg0_x?=HOR9&C+I&?N3;w0P(UwtuHLOEKc9+`5t+ad z($0g$FR1X#thR)@fI1>9Q@zHtx`G+oKYdxU;@Jb3*@k^@dgL*zK&6G z?~PZ?%uKcFY%rykrII*Q^u3JnIe>h*z}S-R(i>Y`2rn%&_`63`M1<=-cU@gW_wD8G z;^F8Z9~%q6!66puv_O4B@PKy*Lu?EzvL*)^S=pgdMC=Xy%@;k0rmgJ(t8aq`2L`6A zT~uszC-W0gqUI4Q-+6uatx3|ZwR&1_Dnemqv z_sH4ImDQCbc8hx3O@?w{(fNKC$wQAs|I`0hC=I(q0yFanlcc65T|HSA=`evkw6XcnR-3)}@;vEO3`Hyq+{O5@-_ZMG2F2gt z{C{_kOX7^0UET@ljRPQsCi{Ne+?kJT`E-pd5vmi&zd12i!VKE%i!HWfV z9j+%9Mw8@I(O)d-=*S7z7TBkA)VrdCO~h-H-Ts6nS4ynPd*5eFwrHXl^3;BRDgc}L zJzw)fomJ2LJi*hBU*)SmdK@oP9Lm`UcE@KMtPZ&k8(9p`-du|%s3jC@R0)<*ibt7% z=YUA0>EwWx)nL3QpI9h?h$8jt0&`ok_dpb)L+{^a>*-i>v4xFqV+H5l^M6jwAi0xaSVmI(W$e?EEVvE&v?r9b%{7b)L>J8 zm6xAihlfH(Rn=Hue{FNu&nZKIZonDR6LV#}b@XK&7*NJ)V;Qv3u(ACvxR@~oV~8Do z&>`XWZ}E{@9B>#f(L7)zkebo%vKS5c4@aa|q}Nz2h8|R6576IQsKKTsvs>O>wQyL8 z8e`ZnVZ6i<5)!%w4$nn2?tzr|erG{RNqCVY@z8Nv6$ljmH6cp28uqf9z>>q!l7Jol zd*|ne;`8~0(3ACEK)HYq!xy#5o$Cdr^iPwBsIPYd+B~dMxZHNC-Vg*Jl9k;45rT*C zsg!7<(nbabkfjT1{y-s^eLWlz8>`$qK|kCg_np5(>D3E`$bThdVIwx3ceW&GgdXu- z-V#MdMXmD!h91Qj6;rjBIh^)NnmN=wwT-6#gDn5o@e4h89pNJA?6phzkvhl>I4k zCEbM}KXr(hbZ5>?III@bYwS$)^~d(!SFU3hzl`*Q@4?*)`1sMWwz^tMTwGWTkff*h zFUr?+-wO$OqeYERjANy~7N*l}E+UpelL_4B#_R|sWU=Ttvz%`L+(wwv>B?rROQ)Cl zXeZeQ?%M7FGBWu5C0BXB4s_qYkohD!_n{~K2NAF9)o!Lono279d}v2UWJ4X$TK`fi z3RAI}KhV(7OpJ~z?Ah*a^fPGHZ{ch)>NGd@$*rKHecd4_c-8(Y@IEU`? zsXcAyes$o|816IcvGw~%MTef_gW!-)Bgzh1t0Lg)Mz^fw>1xsgs}XNwtr=*Q3Hl#p z>mL-pDz2=oU}I&Im}D)#us;|v0KV0nP8vG8-(E2#cYiCe8APW5Elu;ECR(H2R+1OU zN7!jPjrQm2Yw)6Bxc3`l1;COG1ku@>L3W57^lnwAkx{+z7w}yLh6QswtvsLkGrE|% z0HiV2b)TM~fB=9IUfy2?erg@Pp01{!s?`-Dy|FZ+2`x);)3zH`W|Nk{PviluMwRRL zC1Lzr0V>O1ZY1gL)OJuzk+gfsxC~ym`(pc6N5ah_m>x zg^M(UjVsj*Q1^V#ZZ)lG(>4f^&3J|qRC74we!esAwRTV;MdLen zJoq~L_YjGYoG%q^w4|b9^v)Z@&QO9b$d^A}US4IUI_~%5XWOH&+n8=|CPznCH?L3U z=H|fmeL6bG-`k0nHB`rc{{|m_Z*7nKvHXm%Vbq6vsTM&Y5t|th7UxKzDr(q~9T2tA zpXO)Cs{Q6I#XA4xXJDLk>b%(Jgn*|^cGS&=R-|z%6aLznBHC2PI|M^W@~m1HqS}l*B}4qYHe2 z93A)6#oTX6jD~|)*sUa^pRYg>p7Bcy*YUV8xEVH%2de8J!9>5%b6lu&0nFdkf9(NxQ_b4ySvi_ zDgqOn%qNSktNcaE&bE4vw6whw7Bj47SabuH$E87#Fwtf{-Sr(Mt?Z-C0)+={oqFBt z6JW}(u?ox9g1>HKc|4TmOM;Bi`a`N=x$K2r|9?bO8f)XZ!o$ml4KDV_gIzhCB~C?U z)Lp*uR7zR<58>r$(EGeNIR^?o=>eFTdt0)HGu1^Dgh75H zke$U}?peYfE-trw$$LgE%ZeZP`n$WgS8{?dsi(eq{JaF-kxR3+-CgWcPA)zM0ON{I z&5JWqHpCKaMn4@*o} zKG*Bs9l)W1GMP0d72QEfm~y`H~3LR zVl;)L=4H4Ut2jAyru?fxI2&qrb-Mn8P4XfQ(tGP~>@8Sq2wtZ(7)gC>)Ct(E`+FQl z9sl+JTRrN3MRon(KWOHENh35ycp$=csVZZyY_NV9x!-#CACZTyn#+4l_i$kdAm`__ z^J})-_#W)`=2X;?Q6EFF9GXQ$5f zYMa#_Yc=aF`eyeqxK)CzlR{lp=^Dn*HemSze8^J0`ol(t+w{leL>AL_!bcZn?E*yTqZl zn^4RK8H>n4-4C~@1c?{sOG~K{Dc0u)K7&{-0jWANYPx!cep@f*i9+re$heU{W|yio zhw_$}oQ}xC_Rdal>aX5k8-tbCvoF@#wO^aHR-8|9UEuO|i^Iatau9`F||8i_-ugI@*H zOBTm@T*%~cxDHYNF2)fgzSeY4t|{Da_pP6CKH(#_C(G3P{%--BjgLI(9<7V0iDegz zNa^Gt{a{nHNd|1IRer=sCeG4Ukx6l*Q&|x2c$ckJ{oO#oY!u?(M!~`RVx%@$6`H`= zGj`}#P*6~Oty>z@l(a%u&$=6OX*(I#a((~K&hGUN*~KB}G-6xY)jpqYDn|<*uFb9; zz~Nt^$_r_P{RBP6s-I?+mKS_${wM;x&iD+##yj!{7O&-Iwa6QESacsYvQiqgp2fO1 z*5&8tuTR~)$t}y5{i~B@&J@P-K}xdD;IhZg$k!rJw1@@PHfNr@U8GJ2ItafN!&(GL z`q0dk)~o2wE!)fC{=H;#JM){1tBpfx)?@Q;``Y=O1(_?PKPVs&io<7IuI?NQ5#C%i zX9Jg3_wMHhPLO5Dfmh};JM530+2a^ZCGk0&XwMFd6Uw_uyAWmD_Xfrz$^CK}A zs;vwuB1ZCCi;~}aqy&IKXF)8SI6dCS1Kf)0uU8xWIV<}g2$C+^xks4O7@cTID5M*+ z_a~8|JHs~VoIUMUaQ-sMLN{A&5x~;cp*voArMFlSGwUIsnv+#LJJWJHQD;Oa`BUi? zztfPPxaybY_}-Ezk09P}Rd#DI*@kadoAUEj|J@dB1&deVtZY>~)4$SJuW~@p$+898 z32&Z08(Dp5l4;7p&@9ZvlQ)m84*zZU^_dA--3MtcsrxT|O_ThGGlq@3J1L06V$jcU z26olw?(=6_vjIqAeR~m+3;`C-Rk-92ihZ~^coQ*~CM&~ehp592OmWo>aW60xz;GjR zqLK8XV%ondyxhJr-l2f$@+={kp5g>H1Ox)h^G4;t8Sh3Ed0ql#w7@yi1aTqD)RIs?2nRP z&Aq?6*{l@Zyw=^M*RPh9UJ?^jFs z*!G2G7dBNE5?!dAXFNM3k9TRz}RhSX-b%+jwMTqrRd-yMUgJ zLn+L5LXC$LzZ8?Apo3pq?Xj6ULVNb^K3pS@ok*LE=p-qI$d&y-?A6}RmWgI3h8sJ9 z=5)0h5w=Th^S-Yh6QGH;n?0;ycj?wFBa`d)(2g3QT-a)0kFxQB0S`A{>%O*I~m+$X z$3J71`V9v6-=}`2QP}@vuo`aS_|?Wvk4mdJlrlJeMv?-aXP?D4L`1?~iES=*)!5FY+r_*dnWDmez8?5|=C7)!uuhr)6L^*e+>jk6Btnsx<^U)+$L%0_t6M8(x&$LdcW%mT`rRm--oI78fE0>UH~WSM?*L0ULjl2I_woVS({Ck zqBk(Ti(QVplzqvR>G8eA6+=<{Cx&+5 zc<|%))MIM(UEkyjll6%3vCl>A6nb&hyvt>}kHhW6J}4sq33*lFnu?I{z^dt7`H;^I zEeb6|sPpw!zy>pJ=S-qHkh8v7TTfTjCGY-8-gyrT3%^+BvU#-JR?k&$tUyx(Yo?C{ z)?nSYTV**pIc;r1uA{&JC%T6!mBR(Yjcpb|9u^ihRh*OI zgNZsRcV0sU_K8S~d0=tNIGGjHP{9-7HSBxCtJTzg)xJTm{xiz=E4UZ^gM(J1H6gld z#DxPJ&@Ts?(S-8yDy70HQi-f;Rr=*S)v_uo4{p~d zAQ=J#V?MW=;2;SYTU#|Ljk2#_()irKV5Wr@5B?nufU#bytf{WHj%_u>d|dB^#TVMT zezqM}Qc230n|*4PD1<;lKtQ6p3mEMX@_ns!x2t>o#CY(V`6AH1KZUPo2(y(228i6=t1);gm8F37x zib+gv&Hy+!1EL#c@04Se#X^ac_8vN-sUZ+Z2+T7kvY(TUIvbCo1X1II=M^>XrOU-( zbyXQYx8WY>%E4~mvj8#6!{TnYQidOr)8SEP#-v z*QojcugiW&`5wPL{N$N%FCL<|KBPQLET&)Z@ndZBLq67SY0h@jskZQZQX0eBeB&~@ z2(TOLF^Q4&mizUnWMZGMTka1U+*~gEZ(I$XMeAil`a^z|1K~^poAG)(FRe$bfZ3s` z=Kxz*#(XP1SE{_Pi>%sW7VCakY+4;;I@%Yi03tn%@2aeQ4zxXit*SGGK*iaF3ALO{ zsZ9RyU|XQ<0+XG@Vby(z(Q>zzT$`6ixe!OEK?4n#z)aNCO_JY3$Ht~)AAWA)-90#o z48u85F)07BDa7E*AhvE$&kN$*A+!HU}Yyl8Trwq0h)LMX-DnF~TyH2Zx-gcRwE1)-m z5Tp6vfd}A^+HZyisx|WIwpVSB4vA|1chMXfy{JGf9}Am^(cYh4LWG){TGb80r&RJL;%sk*$N>Q|lV{31?csJ+RBFFHhO_=13Yt?1?0U|iM~cd@!UjCDk8ShE{VCN8 zp#B0w16sE?wHoYW{L$ACf}p2#6<{4L&yS7S^~TZ*LK<&&zW#W+f@8PlQ&nAU=86Ss zA6>AsehMLtuJ@(lrqvKqs66}GOP?Ru+tX83U5VMi%QH7z?}mSRXuHl7#Aw*h<#aNJ z%s=p$2)2=D#_a(Vhhdf>Y(`kRFF}CHGmv`kGFxSmHZ;VV?h31F_AU6v_D;eH`O0_;=rF#)CL8eX> zQD6GgD-;{(vuD}Azkhfxu9PHVXLlAamjzuoa{x_6FfYq5I!M+jW}Z<|wg$`VtfIR> zVF4o>+Z1{=Dg(#?srL|UuQUBW$ct`aan&*BP$75}ZlJp%%Y;qaHVbziWe64N%swh` z+GTlD_skwoakpk24z?y+(xNIy@e~$RtFBZq+dA9ZLD_qBar~#w7FYuG>6L$~PYXKt z`Y~?~q=~Is0lj{Irdp#}*QqWDz|;K!z%)WA{;oqG49uvq^r4w9*Mn!K>{Tgwg@AB! zasfTrEzOllV^C~PSLAeFqe9T%uE?PZzedDLA53I3!-VhZ9!TIZLGx9kZMw7C->JU7 zzRnU00ac(PJUl$z?+K5Z0HJ|oHru@`Yj$?_r%#`X`ie3!F%=qtFYlOb;pMUz5ozUc zp;A$Pm-yPpAwJP}LuFsuF8QxM4=o7@!66HDmD}FFe%0uaM&5AV@35G;9x_73RM2CI zXr+?|YELWRDu|yfP{<=|CHqlmi3qq5lBVrl5r6s-RdgSKyk3|(kROqyT&z8=@+n*!EjB8uSoiAxEU0f*jDLkPpkQdJE~Ra zQ)j+tY!B)W41!knmleE+JKLe9KcN47F;{0xDV5A>1?6eSb9^~M3j_JH^ZtDXB$@8r`HN$7^6JVh2b1x_xAIe$gIG$foJp`b~(Nw;o zTTaV&uo$JB^?7+Nm3937y}oa*8cJK}nG8IUO@MHbiJO^g_F4Ym14M9|9vM6Ad%pj> zWv8Q~uag|_emR{QDjO<`_;UQ0OphjW5!X8~@H)fG@j(by$sUXCMc##*t6MnHFQ-+* z07Eka#6mZ}3q)-CL?*YJ1FZ(kTe3f1=yx2Jb0|b>TBuY)Vq%?T++RRlags_!;ehOb z5izw=x?~q^fk-ZdPp|`awQAwjH$jC~>5qvrwEO-2{Yu*k%(%P`C07k%A{*fO(ZRm2 zHy!T*m8(v@<40=~DM_gz77mU>X;oEiZS8SGxz)ll9jYvIdQB~@kl+wOAwdaqZgN6E z_F&MiS3SmkG_XCS{dbtVmwH`ROa4=|aZY``A-Mg~+OUX-h}t~t!A^dQlP4z7MyJ2} z;&`|zoH*l@5H6q!ve*Zgms?BP^?|M@6PGg_0wN-)&DLegABQew&U}B0)?H;X4&VV) z6z_8)O4I%x+^f40FaGP?p6B;JIk*3}(Ng~(3*HIp1jLw#UgarKB_Fji3W2?d9yo1o zx3;#PKZgUX4L~6<9A44!Nt^&!WF$O}Exaw-i{#VsIN%^sWbctVbteSDSXl}g6MEBt z-yNP*k}S3?8Iff%DqvU5wa{430aUMPu=`Ak1-~mcQ$P4!?_8h1ztTI^u9~i1+6Uv$ z3~YDFx2s`-)fuUFAUkumHO%=Lfh_~U?@wTnl1puA>0+#f1|$w(w`46CkIRGnw_xQZ zV942!`hSx|y*&VB#{TfYp-MUIcdNv6kGtb(qcqx!y{UrH`tx0IaGJ|hD#D^yf5Fzj zxVSi28Ub)#x`UukZnrn4HcbV#db9cZYT4BE^mJR2O*}T!?5R`gV#uh%hC0>i{=RoB zD-$~^%}b=_rKP1O4~ZuGALc(S@zt`ZxcKfC)fmdsH zxH9iUwQ2%9iUFX&Ol9c7XE=k1GBz4+JvgI-Z5bK9k7#26v#|I-*XdwrC<@#IC7~q% z>Qq-(2d;JZ@me97)MKB(uo5CpW7pQEBrXO*K_xJKU}JrKdTNH|!h9(G>4Ff$4?r5x za#ZdJ#`Qjw%Ww`31~kD5CiVimD%m2Qq-t>qDLigNbJZz}<@LP_`(m7n3^{XpUXU!$b@zqEh?LNjn{W@{~wEwOmk`>7XQZ~F%bxSu;yyWVV58XCq7 zl+xJP*n>V~DR5$R2IGEvaK8%A5b7`D5WqBDdq*`^0Zf5SE_$M2IGn~y*p)_zY|93` z_Q1}sYH9+vy?m{Q_x4Fs)d~h}bu1G$)qlR?TjLCtn?Y|lDTsliq0%4-H5z8toXUnW% z3_ZiXTK<}=1IMN33Y3LFiiwL5FMFphbGlp-WzpZfPij# z#A1t6A;5WPG`MRez*5X&Z4S6z-aB-4e}0ou2&?qA&taZuR}Q14RQ34u&gsqWIVxFu z7+>0Z^vaHFmo<9;(aA|nOq?PLItF5k#hn@1hSxK(9L(D^eh29IavMncMa73Zo^8pU z0Xzv>4`_gH^u+W^#L>NMaMMswP;f7vU*mYIcMuN&D=Z}?WxY)gap3+~Ec)7K2&Ipg z_}vrU@kHtFI)Sh|cxOt$}w%%x&;wsN#*!Mf{4J=D!7^yhpA3+bv zhu<0AfW}4ZfcXx4FD9Ow9UTkCXnGiZ`rR0*)AEx~uj<&wE5BM>|4}92vQw=#WV=wK zi!UuDGCc%^P2kVcDg~IET>*=vpz>DMs8q60**t4 zU*ELT#nNecSp=%UGSbo69{K|1;4^}%I^76R&$JF6pHT*~LK8o=Ztsy7vpzHF*2UBS zLr1{dRPJMO4(xAp`G*fl z`s6cQTk(K}C`u{ zj!wHi+v#*8;5Y#EYCsB9<&KJm8IAG^JmNrE$#7_5VGyG1?^Ac()Nlz>SPbliid|je zEkIb()cmO*lKCI6qDg|8=f>VaQ{=CMi{e?(EHK`QaXEh|TW$k@$WQ`a-yGAC?C#Vi zmv*Ref6K+q?iCdSpZmz#NAW*(pDMrh7-p1YgtG4fHO|aXo8!XT9Ee_g(5qFONkLe1 zPIAey@$s@BAaWLSd3p5JW4E~W-F`H!KV}FcVZG#p*RZeSN|(;&WR~E|=2MpZLCh z=9dO@;ujxk*IRmHCnjrkTHKN5=MLr@f-r%5OCkUc-zye)A9a5M5Xg&lfrA(8fK`+i zr(!25Y5IxAne>SZsJ1PnifL6!NDZf|oGM+f=5H@D)iYssjm`CW02RWH`+x9^TGtDh zW9iuf9^oQjr{PcX|6c5z6x&OEXT9?4UE|R&f3j(FWD?W?04ne*5T?dURrp%GZxs$-ylYq z0-jwtY&9!u5*%Bd!(~ZQ((F)%5af%j%)2`_@8roj&$PNTxSz`F?su4Genuq>3s zbnFJnBV7^<$q6|d$V>B>s4b438uBQn6;YU}$I@v$HLU z!!mZORG0oaMT52hviH$r)nFuIq8B5Jhld9_7m5h6^;m(e5h88x)fMOU zqbG9_h<44l)+6PB(jXRwe|?>oHdAB9ZP1fcX*j^j`c7Ek$>IVKfN3^XHg_G)dtwA& z;4|VzmiScRwKNqMT ziNq^eXL`edL?6++t%$6$qc=}B34qWTXsy(jV|BKl>FWCT6r*)7tF#- zeEw+g!;v4Zut;newG|ppSkJ>KD8y^1N>A`dYKvgBJQ*DJbd* z3Bjy`e_)_sEzgg5_H+7VPJY`9^X-o@4EayJDT*IdoG*f3gl)}K?}B2A!NDmSGdfUC zI+^o$8J_5K1a#`CvwM{?wp3HDrI}@5n&b7WXc>gfZJ1}z*0R#;;n++9qi$a4h40|- z=pO-xnLkm+alP((&s_4H=RJIWNdl?xYsY}myR%i9Ay0*Ksvq#Es9Fu;HE$Cw#c%Bn z=A6LEd&|m9uM#{-w*ksBD~P%R44b*WWkZX@avA;ac3aF-NKFSm{Ka9I0|d$$6AH1! z!Vj))!+Oe~9ZrHIWq;Af*he z499l@`$$=6E58LPJ2^Q4$o}W{LB5B(@kt$x7I)s8v;9dxHC;DXQ_5$JekD!PmFG?4 z8482|VJRU2t$Lg55RN=B6b=@KYIct1HF3}0OgTE^8td9}zUH=;j1QOSxAyOKKX4BF zfP|1a^7m^VdX6uL%+wF0McMo^=F0=id5YsZF(NlRfNwyM7K4=JwKg0!HrRH)?sPuC zIGDX1;64n-;T6p%4-T@mZ(+Fk295_*ZM2gmH16sJdXF7CnSKd(QUrjyU*|O*N(b}d zz_2cO4l_f2;~(}hSJdjjM@=Z)8IdJ+6pH@Cu@h$$_?|6!$yH>RvI#`fE=PGVD}UF0 z;B{*ProJE#fF7)z%Q0QdAX7J7(Z%Ocb%*;<%{BcmhjhQU0~b)f>ZKPQZ2n?JqfSCuy$a;rZ4C%lyh z^J!oFI7fyS>($?2ifN#a@&TQ68W-SVwnin|UJZRoKCdmS`oQ%pXKqf3^LxH>ffjPF=Ek@I7@wf1J6Y7K{yDF=t7{9`3olZ* z`EIVr6eThW*)6Zo4};vbe*B!wAI_p-4h+Z3f1* z1^k_f2v)Y0l~qV8=11#%EF#JzMS#^*uMZ@euU8A0&`*Fh`21NmoKZuN^?C0+77fBD zpH|Av!XN~MAOwo}9b8=L0cn2dodQrYV*8W8*SWX_rTtuy%;B2;M|zR90Lci~@4%>iWJ!$VLMX~Z$8-aRr+&`+ zEg46zg^Pp3<}$FyTzV=u_n}C+L{dVEfW?xI6hFIcs5OcC8cD#}Vm!+a*&0oYPhZ}q zB3(0uE3!y`)BQoHqV+TA3bo#zEXIW;y>q|&@$&ZK0P=H^x7#>|J7}Z;PXB#4K?<`$ zpvioFJ{%$z9SV)%VQN#L2guNV-t8)K1LAYMmqJZl(bp$(#qtecfK_5dx!g7sP|Zu) zOH`_>w`Ot>PdtI^*$MF8{J>PpIO&viqf#2!kCg&2aBf$}ew=2jhll*mXYtDPNaT+qF{;c8+n(qmeIx2XPJ4UY4kjvjd3i#%q^AK3 zcss+H?UBY}8)#HI6xYz#mG@q^pYJ6ISNOJSF|Qmn;`rfO2{o4cC1hDkHwQ?b&vxN+ z>pfLMmH$b znsfz_;l^a)hoA4}aOReSJOSXU1II^YcO6OK&9acDVLOwJP&{4uOJqL( zWuT6imsj4J;je%^QWefk-d{Jrw^Z~0px#MYe&4Pbe*EE621tc_?zdGY+nd?}=tbRX zTXv8?b1PI>RC$);?&aZe$eTj^KUl!8l>i+7%<8!b^-oK^8di;V6Wi*00@Y;~W#Qjj z7jJ8mGnAYD7RkZ-4L>^!fUO$@=Hlne!V``Hx8XlQyMXvro^RtBfK7m~{p1XJ-WdoO zMQR$Y^RCM}xL>2;&9!=(I3akj8WkxI85+KKfpfgX%LvE+ll`>P(PI`S8zvX%^=T)J zTZVOT21xTiQmx+{g(y)FK2+ECK9j2C0UOBq>FJek$0vP#{SL*bU%F>=l_0tqjJ5Zb z*AhVjA7wN5@+rWfun38Uc^$_$l`TIjfRbjF+<4}&e`Wk%0&cdG%SP}dyevA3Vp($N z7BowAe#{tOxG#DWC%XdK`f?S|V5&$&#y_N4;DzbaMA0dMLEDaKzSw4}vc_uf&ZV8gaSq*i4 z*^v1VaK{Lc=#)}XQ5`)nGP9u4X}0Dn;&0>YxSD6Q*-NVNFf6yE!m_?4893RK)c>9L z)gI$BUt(ZPV|E~l^s~6V*NL_6?AD_(Pb6QMU=OCfmF&==R}E;-sH%Ev&C4BG6I%`@mTaA`u+#z)M+EN5bp6}(ljc&c`>)K$-GS!TdeKV)~jE`N0W9lv5q z4&v<k=9bq5eV+|_xE?0|CN{)Wq@D?a%!8N%3Kf?d$)ld8@bSvD&Ts3 zIp^>P0fLv4bMxzxA8_K;KmMv|wDLP3glMVBR=H#JB~V-d_82I6h;>*l#@Yw;J9PeH zU&SMjfirEbudL;%h`MhVUrQBO`b0iDa`Wa8$J$E)EYqCjKPtbr zAs1jbm!x*~oZ68gZ{ED=X6r7~d9VHrm3S&15Ws5zS?e`R5!heM7Pxn(zuBPK>xk+t z2gl=z@3>u0M*B=+xd-R9l0v8_~SnT)*>$y5$mTU~Lfnz6gkuYfCMK@Krf( z4m#e#h+n>;&pI!aN!o9Yj#1ntbKgnt(OoMS9eG_{Rl?!E`wQvo=uqxg(Qo47KkRKHu!q1hf)=y42_^;~T({64(~uo%LO5LKaT{s>jsBOAqGO zd~&iNG|zshwY9Q9nE4xUIm0Qiu&-sn5}us7-_E} z50rmk0U>=7X4-LWW^bP*jv` zE`iN}K^AY=iNp~J(&QnIpF7ugYM z-YyS-Njg`R_2eXBl1tnp^x0;9x=-8YcNtk3xu=xFhQ8W~iGVTR0kfH##u?a}OxlbJSdw>z+x0DTla%LSAR0$i!xxaBpKwCgz4yb4#eeAFSmu}nG;p|SCro}R$Hg;4} zk`4g({R}I7+BxtESI@r;^q519O_s$-+4t=rF|!xWNc%+f}OH zh;>s2kny!Y(gd--I)~`2YCt_{fpLI8&~-R0oM$m5>%t23`$$Ak2ssYFvthDXy7>`& z|NFMxA*T@mvsQI^f5i1-leVDc`SyZt0eLT)!qY3Z{%cw*b4((ta~1fu3zyqTNnhL? zZUh1u+dpiD!L}j5?3Xc^(GEJ?y9&VEf&GCETRu}`8@-U^C9e~*fSj43g0KqLZChj> zO&05#+UiM+O?LG)ibFNNj7n|Qg8?EnpuS`DwX7P>&yl?9;IS=zFkC^A!0 zid0euU&_ebevAJmCo3x+Q*KE%%lJK;sggdnZb~kbk6RHaA2e{b%gf6F$Lu$Yf996s z#j!ghUbt_KzRr|++)#Y85;2MfsQ=ewj5_CzebBw-9)XYv{)d2Zt7fU}1xROH0bf&9MTIB&mTv)IVH@^C zc$o(a2$9e}UT?$3qe~qAWi?h*qhvG9H%&-L6pI|m12rRv`Bo=Gk6J*UMe@JlF7#T* ziuIWu&IAee%!k`tHWXc*E$4#*n}fam&kEK2nIv{O-tZNg!>%h*6!y> z{{-K0zzr!tr-uA=3*LZ3qY2*RD_g+z@1Or(@pVOrHCEk2<=6=@zq<{kJZo^W(lF8U znU2NYp&@=V?SY9E>kd5ik=RroAh-1yA>oe&kDmVr3$`i*g8sN|=N;Ek+CC?UtNp^X z4uEv-&DYp~voL=!1t8V0BwBwRg&2T%QNM$O%wsCzH=oPO(tU~%Lf&M8pPpA;0I_99 zp_Prz&B^f)okE(RGXkfj6SP?eFt%!2gobZ@`xb~0D8HGYi=s+M{8!@yn9X*Tz4_)o zk>9YBO|2#%Ne(3ul0j7gF6{ZyfAJEHuKOAY9eV#~g0vyaAUahX(_nec;Oo)XPk{C@ z`j7TGt&coTNL|j)#RVjrF2Pvqx>miHdVPFnW;MI-e=#6VQ6Qv_$?w|>J9z#5p4@X0 z4@3An!`(tJXC@~46w5#Kn-Q*L+_nkR1allaH~nF&;<7C?c81jD;H)H%vSPA}%jB)64TMxJIdUzJGUrAX%B91$jnl zN?=-%A8hwU^tYtcfF0U`)V$hkP6LRLQ$GLcH7WMJI?vozNa0il=Z%3z?^y_7$c?O& zhm?7q?eJy&V@o238s8c#I9MzFT8S0~m36b(f&W88rl^^nhxC%LTYq$NI`rOeiBE`p zPDy;zQLLTJV@DJ-MgL^dzBMagy0AjKf**c!&^!&pN^YzyHv$;}hqtUFwhZ%M>1~4< zzc1FG$&|N9a+mL@4AufIVdFkbx8>7oybE!`5pD}r z+WCeRBN0ZnTG0=d73v$HfO${`OAL)pEr1VNZ0GCS6h} zOU!VqI2k#)xpnH8UW7sH0O3>EttX7y6eCk{T#cX7QcjH3Zn<+I^$Ca1SEuPEE}+CN zs)j^}8#|&~`Sh4%nV1>z^e!sfL*EeP(ZVXT`{RC8qSui2*je$vu@53KOa-JT1rTS1 znR!dy9QLSRfZ+q%(%_X@i$^KB;hV;DL~HBXf815JWQ2yVa-)qu#;N}H#@ZSH4;7My z_mo$uIg3TEPY8U*%OEgCk*o3keozov46b|LYHcl@43XI};M=Wv!vk|aH#nzQ7~zaj z#0@GhU1-S5$@?H2+@|bmrtX0Csb~X~+xToCQo(wghVFT>)txhb$ETg?X^= z05wtUbK($mJHE*3`dX<@Jr?AZi(aM6kFc77j$tKJQ*f$YJ~Ctk1=xwCQw|_N1v~5% zg!s4sx604#tPDW0%=gS}0WUNOkA3J1D=SNGT5BX}r3)%mD6L@{lLQ#36|80x3|_Sn7hPepPPpUfv(f=Mi6Z zsz10XhgH@n;o8Z+J#MIoFa_;c$A?{%AwqYoBS`)S3sASkcE`t;a|7EK-WeX)l*;~P zqcRD21$>2%k56!YY-sR9@A1@f zyLq1@nmu>S`-oWj^dFjC1q9c82Tpd}Ruvwbvwh?R<1R7iv7k&#iAjl14zhQdZ}!&Q zg)Fr_tUmBVA?Y5tg8v0nIqMGO#%*u5`TY7yi#&x73oCklQM+b9U%T;qPh2_Ue#ie} z_};I9cjjQwdq1vJxfk!{*J!&h+D5usI$GejEdyEJKs5&Xn5(THPE>6$0e?5E-amZa zXUvQ&aq}Ppii`qI&FkE-q&mK=4Z(Pp-+1gVE(F@!6V_9m z0c!t1WlBv^PR0iSifd?)?*5+S)64R%Ua$)8P43N=H5~;{!$pP-{qpXlo9KP?rU`m) zK_?mH1xnr$o)pFXsQB?5N^g@$KWCUWQ0sBAX$%->e#bnFQz}70(U)G@w`kF7Xz|{C zjL@(~XQAss*CmDoc02xAG2XbPVq>6>i=g1+aGqrLVGF0=1FDv>=XdBL03oJ>5Z}9h zd8%9ERa2I}57Nh@Dx4f$-VO2O$+iAi?7aI0+_0$v?h-g>XLAmagKJDQ=2=(%LZe%I z)I)eNZw-UO1G-NjBK3OqV(L~ZC#5(7PW|T_#Lkt@-(*0vcr?tAy87zj*7^DWrkhY( z2m}Q=xsd(tFAm8Mw3rpWVC@dXqX-U=q)hqRcEp2?Cz1WYuoDPzTKHVIL$}7jLV_hC z?eL{zrm%}WA|J*jzi6oaz6Z0rzt?sli_qlxd#@Ia4(7`<1a)c6%lgtIUCw#soQq{m zZdBXDXw>R|O8sZVkHG7|11@bJ{Mf-)arO1FgyW&^=0=J63Z4X9xO2;+v3(9rd_b$t z(o4i3C`cyzb-x^m?f1SzEcIC$UW}*GSe};oYSggFZ_%s>@IDC@c2z{o)!2vNrM$wm zo!8pcM%2DzAwNvYiJ}_R*{%1ULeyFGzpH_HY(1Tg`hK9kOHBVdl(!rLL2hONu4>>g zLilp?&*6$_2mKtIT5*6@x|4~P)4#8W&q-_05n>&Sj)RCr@1mDUs8J?U|EqInqnjFi z*LUZ4pp$L^pt%8bSIQII?zw+At!+&GU4~AqD$%n2p9&V)dW-+p%fN0_PV>||*J9}V z!9Ot*ipPvz)HYjRFF`TMjG+&e-zSYG1(T+(su`eYc*i;kO zFM>YXi!@fa+(>Mky|~J#^=kl(`Q4k(Bw7e&uan)h)L8QQ57DEo41~xRF9>6iKO;n1 zM+&7^I<*tE+kW}8-o5n44e`D!SLIw1c}P>DY#e%4C&2(^d9Ev5Y`EiG-cv)<0>IhnBI zU$H@cE)e$aa-bd+8~dY5_~NaAfUcq8Cvl=dn%95mzMl(_M^U5!8vtPrkAGGPTbetc z$H8YG{^esw5VsA_FI(luU1fc<1KRLPw3~Gbn*O)@K;tg_yxZeD`c`fqBQ&~6EGA0K zs`a_Oz~@;%-pCUTi`nF{RTc%GQxg{?F+s{EL5BT z%Ar%>wlwcqvEp~(OG!D?bMdLJBam(=QfWR92 zB8$eeJ+%i?Tpp2Yw~X41DtCy}c4BG-L%P7+uH=>Q*bO zJTTzYMRm$s_xs*i(H{S9L3>C_=jG%W6{-!j4Gi4!s=LB&y9I*pRFo5)<~=U{etAy* zNRbg{E#1@8jh#tN#ZE;nBqsNi(I(NTCqM?lHe{sxxcLFFkmY2Sy#3gNx4_>C3Ehv1 zeNHC`QqGaf#?3DkN9CU37XmjJ?{fd8PoB>kpZ9tBx$y!uU)$P%U)ssTNre}~Ot_wk zqKmv=wrPHTditL#qN|l(3=ZUzh18yD`}6w{DFuZ%#k27qRnavn0TH{)Y5;4p=r(Y2 za9E$E%q&0r_6Cd*J|Tafc>}oiAW3K^1l&}8l7il6wqtqnQ`Z%EEEE;^5Tn%s;Rp@ZecYeSIG@y}mwqaTKclrPdgS;;Xo; z1-+G9{y5ynDu-_Jv6)S#j-F4`G?n21Sc{vz&*IY5$0#OT2J);MMqg;t-{2hC-|}_n$3nWrON6? zMn*5wIv(d>5}D0qy?S_h%ytaclkr)eG;15;a9Iz&cBZno0%IBbW9R?+i*4_K{Z)YlpNmtXiq z6iiEqYGV>PZw1WrYILus#hTgL7JCtO<58JBX*4yxv5TXJ_G{sgiS-J7v$nd)#~>1Y zpZT%`6(Al^q)Q7*>X~X_g8p{zPo5U!-i=NQ?EL*uH`Hzi&E@*e#G@zwj{LNzzP|iQ zXIhx#284FJdNYAO#c-y^M)L<-H{-kL*2zJQ-LnJ7F6AvJIh=;5SCnszK6_{f04pIX zsX~{>!EI|)eCVBFQ+0Or#kU73JfkBc4DK@qfMO$gfX;Ep5txJqwKt%s$=*S3)0aT- z|2ZZ98`Om6+TEvk->D5Lzx@2etB&f}omm!tIio#8l9ZIo_DHq%zoRKe$fWea$2*Qs zpX8pS>!NM$W8hOTtH}X%XIg2Rl29)e<6pIU=<7Uk({RQFl%SNoY z*Uk@{E`&6v#;gB~M{XlQ5TT0?yUk=CjOP*PtJhJ}5U&+~sAvmaWUG}j&Y!M=IDp8$ zRdks_Gly-rl1s*~H(mhLQ4`s$?MG)}amk$ejex`|Ai)5}pfE}vgMvpd5?}NbGQ<%@ z=cR3vyjCu1RV^IwRg@{nDW5Y2Tj_HSTgx9!!IkJN4A3fRvRR&Kat$IiJCE#?1HQId zQ8RDk{D^K8mO;HFq$Pd){P8EM2SM62+fmcVp_t&1lH!t8NKt7&@aY{BNu418M;C$I zXD^onww>0yOAGGss`6^BMz@k_=l+BWtsE!QuI~}1NT136r>5#C?+@B$8bTo)5&G&^ z6oup0Stg{hR#&x<%d@?ZUIyWnKcl0S^Y`An<${&Qq;7dcLffp9ij|H|QtmqD^Si$J ze!X4$#U>P`YLQM~4n|!^?cR-1{Evu;_;kV7UiA~BL7YuTYoBB_%gV)W5@rRwU0!^S zFKmawjsJ%%TyIl7=tDiU%y59$XB*!5@hYByMy4W^cO?*Eb!e`Sn#mrLb3?wYV#+z1 zWAE$cV&Z zlX>KE!s+k#_t|&Wn68iIn|#)KDTKV2mFAkvoO@2Yh{Xb;U%wGyX2w~mjZAZaSC|HY zZoN)X(~-WptG+T=5^J;gd+->1sr*`046J)TR5cD$i+yu8>&1zSge@F&tlX2;r3`JN zK1|&XK3%l$s?F`FJw?e|ki#qxmk)_CgyT9}4FKJHY!l@AC#kpWLCC+<9ZuNi8N)$# z?#rPbS=)O}ib;Zx=15e3p7Ru|O6vA1U0!8!DcnANv325BjAz(#p8uy!=ZJd^^c9%< zviHe*t#D;TB_$*jc(Ixxh=Gg*{*F@p9ve*zPVPc!X>^}0xY7!Y{QSbcLftE_!Ai*k zGQng++>pC`&bD^8gHjH%kJTm%I3~u|HH;^UVl8vSNQAai&lfwM5RMT$uxeHqs>M~> z9ZpH~+$E?n1B!-Y2vXcBrk6+!{D7dS$c*2?K(&l{Q^gT-}$I! z4F0`RKKv2D$ao9}=_es3L3WeHFD8A_7&ERNz*y8aa*Ox^z7`kDS_e@Ko#ZHNwNsv| zW}Sr2(~yqHW&@(IScnFH(`9EGldWQ?o(qM9cXWLuo7yDjjW*{p`n$7Qpe7t@xkgC%>V?KkuS?4R{lPWu?uN7U}7df|JJS zG}?qb9#-iBh|yLiZ#I)A>;800vvWKv=yVnEz3d0M1FQ8)u z4{KT)VqpFHCF@6EUUN5uK!5dTJt>3volI9e#3p{ggPVjzZfI!4f$|tD+UEE>V^17# z)c-pn8L_3`rkql8eC&oN(-aa`Q$+FI=Pt}yl&)OrfkhtBK$ z6MdR7cJ^iuT`vxn0F`!z7?VT^xAR@FrOivD{-g2q<;dV;ygWZt6OOEw`}}}G5Rx+5br85P^;wl>kqA61n_v5b#k5Sadzn@E2wIX=NMfiU_)wL(`s>}hY& z+t`J9_0PKl;|va2&0G>#x#!u{d%3nSC5>!g{$q)RUtE>JMlw=_O@S8S*OxEv{l4sC zW%Uw`D~eq6S`5ZBT8&1lP48!%?OxG2nHuLofj!7MJ$0JyJ^kkCl9l)~lE>86$ruvP9% zrS*!DK;>=^zybRZj&tmkYxi@XTP&lQ%mi+@^;iDD2LP_D{RgA zlk=3g@Kqm35mzpRu3HzG9pSW${YYc`zf)R3Cxt%MEzg$rP+ooj2tNVcj=_UVw3#?v zVM8~Fu*k8%p%f-#feANzX$l(oorP0~m>V096pBfjMLa;k+Ry>ti?WmMs@UC-)4a-x z@1&!I_?-5te@P?s!47}UE-EHQ&BC&`5+PhPF!IEQ-C4s;0WX`H55Wc^;okh8450Ov z>ijLuvKy379KqvO-ADlPrTmUQY&+33-ah2Sr zsc_p5^9*b5@@+ub=oFF)Y-4~bLC~-5L8gqg^{ul{nK{?+qI+Oqprb=vI48a?9&{{k z{^pN+K0Vv3;~|ZXXukR!k#%v!+hRqNNprIJzUTyR)H{liJmyu#XoWH6&aviQLhtu6 zuZZ47THjZ072R(>CwUq9KqYN|fpsHlUY|Ao&Jz)bmP+h5iLch;ygN8q%Pa_S`i`GIS`#>qSPg-yQ3$!ptNMX zWaz^OwQu&4U{r$|?2QfOZIf_bACGQFKlscUqi{bbyi9)obYwYBv3bOEnOF=4S9k9w zkmzL~N<&Y|XR1GB6IiAOY zgM$aa#!}%)%#aeKuAR(AqE!v?n7N#4Ee#qQ2L}b5%!^lleY>I!A;$wByjN<(kBNQ| z`5h(Zht8?}%o`x#l)HYuz?n8g??7K|P;WiKbaMqGHuSPWcjER0>ZakJ15g|Vu7ej0 z%C)vHYB+Wl)Y)ig)F6YDTp;Jvswz){QLo{d=UIPZM3g!QsGZI6+7L*OocZ)|OgN53 zwNolUhLCBZR9`@MGG@(jJ9qv0!b>Yx>C4Wb%D&XCx90SlTzBS)?uEHn?L<3F`XE~m zS!^m-8K%uq-V@$}<-S|HRafqLmal>B8VGKs)okLJwN-8mtGwi)lXjuWW=1z(tQB4q z5`gyW*UoVV#XLD(6%P9?#!JRY7jS6VdSCqhVvFwp65IudmLuRCqU84}aM|J*61?gM z-^jttcp(_0xg1qA;6@>J2eh7Q5C+0h^O3lnZ1@+8Bzwh2}blbT^VYAU(Zf0UqjNjDlP21;$ z2hm)+a)v9H8{MUzu(y2Snw%(PaW<&m2nvQx=JmD?p65=y-Xf*!Wp&4T#`u_$*x}AE zmYlIWRvU`&Bm%5p?tXOfVK;FlaXmFyKYO#o_2Gt=au zFX%eZAEay+HWuCD$mOc=K^{FSYepo%^YrI}C_QOZ^Fm=IQZ4&Mq5;8WEoatwa*3Si z&Ri-TwYX|F8Y}Dju(Pd+UD$!JtiF?lp=mUprZg_Ry@1zqT#+Kwo$Ld@7=ox z!~mD`Z-+_^VT-6>FMdj&%~qLMJE0ID?57-td>);sF5)!HkQm}H@Ao)b?a5E~vR;^V zO;epJUu3#Dhj4+gssx4=a8#supMjNpGD*7W;z$-4xP&0rC^|}CLFaWjXQW9-aP#Te z#{qbqyMvTe`Ed~i$)!?!seXIqM?Rm60}zG)g48$oww}J0X+jSQl)=tso6!g+-O}BT z5U|RI&i-=p=azm_$j$JE-e@H-3}{ZihX>owl`a6c9EH!p-M7xG00{*ZNefJDFq2;* z+0hh;z%Y_9a)Gn!FZWYPjX``i3Fk-0t~2sQpA}r^!Nf5OJPLlTA~go!$T_xbSVcGj zsc?o(ojp*FpB*3THhuiDzB^rSI{rN>(3@H^%zC0oebLABG}iNY!)6fJgYy)V^L~K1 za(Be2I02nviqeHKYnk4t3ET(mx>IY1O~hD^+Ast3MKALE@nwN`1jYGjBO7?nK*kR! zpWY~lqISh4VK@iQ$}PR^@yu*2OtdOXHyaEIk5ATaf=mVcPn1mhQc$Jk{z03*-i66v!E~FF4iX-=0iUA(Z|md`ZEmB zZ|oDXs(d_}`w6sT=z|1y#HjCC{YGyLi|Q|>rGm|Zhj5n78E6+sSmw>-HmXHyb zgxm6Y0@dwTOdW{NGsLMoD2V*C;9eII5~ADW5p_IE0y-xyrn`<;d$PC9+jh#>463IO z3QRg=*qV=``4;LFDL3%G0;LS6-6FF?TGJEaK~NR&>^RGDqxAAL-D|rL$XM~ncwdgN ztNao0JeqTlX`w!o**!9h6G7+Ll}`nk=A43n5a?QOEIux-kn>spM!GM;^QRm?XoEo4 zEO&%lA+PMwOqo9m!K{-hM^MxcI{9Y(Ba}mW0P{v{|%66S|Jrek*9*@F>d>&$LEZgY0j6Q z<7TACjd(@PW)H7Gul5ks3h{r^8WV6w5im8(W2>`-#Iq`g74Tp8PB0ZcQn~4t*;X&o zssJ={u1x%5l|^0P(RzO(G)ek+uBNe3Y9tG)S%y3w62T^9<^;yjbuseUc*Q)qLT%_| zFB}MoPbGgmeGLM^)96*3M!+$VD&SVoQ-D*fny*k<$ad{l_(_+5$xr(U1(BcPRB6)S zPl1SNRs9yzF1#=u!Q=TVEUNysi4T(!)~d4lH_s+z%bEmz{(Q&z@*Y@UMo~b0M3d|S znvV$+VTY5+6Hv{m_xM=<6l+5RLCScw5}ocJw)SG}$kB$cBp(b6gSw+@K*E;BTh~+laceX;7DkapjXy3k{KyliiR5iW zAy;R#1gwl{<0cI_6A5o&S&rSP%|AUqX9ZlX!5FjfZ-ANGYE&1+K-Al-A1ieHF1rP8 znMmcb#pdyx;k)XkMUN^!Zar(#H~lAbNI{!S>v#Ofk%wXF&B3 z1itcHNzw{KI&X`5jSOKGn?z&wVz5q)wT*dhZ!AHuI+a5rFsqxUs_hmp+N-uI2gj>@I597+Oa7cQZ}L<~Amw>|wvcNX1RW*Xkr!u<4Y=e_lN z?rN^ANIxrZ{7yLJPPeG!%B=Ol3z4afE|Y(&dbM0X7Br=vP85HLz@%II#3q-f=>K7U zf;z2_HD3A`w8(9LF}Do*kNSvp>GpKR%A~p0DCQnNo`nNnyuR0_oNg48sGzkxRhf)871!Qi^ z5(-&|aXE~<(oCBNHhmZ73!;m<3X}dx!e!41M4g8#oo0hE^|mt{ zjH*KOR_4?DwD4*t)4I|HPBfSw*ZNO~?mzmui!XiCY+iGGq~9=m**#ZnU2?I9INO_m zT6pAOtO3ua8UfVd0)4(XB|)q6a?2o;RK%d;^0Obh=1|9IB)UV$>+Hk_e_|jrTL~&L zkdW}a<2gyt)?)TmF`Iew2^cK|Z<^{qcM2`u{6#AOuYli9Nt-y9O|=DLzFsk09`!h> zVMnbQw*e9vzs2Z$w9%Iz&fhhif%G^@knE(FB4xMz#i2yka~Vb&2m;2QVG}au3||5a z#n0ks&bpxlHaSzcH&TSR3x^k(F|}XkoSwXR3mTXX(dTfwM%;K-Lu;k7mKQ1XBa?PI zOtEFK%gY&yH1^%*_1>_^;m4_jU5aFy$D0gS3i!`?l@hu4s)hz)e+g#KliTO2*BR)$ zN)#RI?nTeQ`&m6DAJt%!8;-|8^=p7(_x=5S9-qoT_MjVQmOM2V%s{}wcsb^1Qe&-7 z;A=MWHQ*Ag+6|qi1irGKqrcu$w_pDbrS=(3hyb-5aOjQdTTShv$^0l$XY-+v0?~Bu ztE816e)M2^gc51D6d!)P!Kw8GneNqCW%|T-m+Pz~Cz5|Syuk=||L3`8UE|Nm`&IDf zwKF>i`fy_i7BqRV%+eP~S}Fvuw`zz^kmSG^o>2z26 z6VDpH#Nj|AB*7?3n9Hp5tD8(rw`G~QYHko*o=Z`Tv5d)Gq8%#@xH|%FyMH|&Zv_w= zstMC)zCQc%%uY+R$<93xk2DWmWKfe-DccdAg!Y7c=~G&8`C}iy$WJG>SJGN z&h4wW=s8E!#G+dvD9pO(sgA(%JZ-mDvH>vB`7~xf1nC-pQQ2Q+S)g~QGGVPgRjNH# zt1qD6oo>j4x;rno<^Evn1W^JP_S@f1+?S9vusojk&eZm;m(}w9%{T=F#BKm*sR2UJ zLV`Fxxzh?{Ved}5UnQ=b)rG;0rbX;^S=0kp-x~Y5*>ZQ9ogD`SuQ9Qw+f_IN&o8Io zkmMT>MyLCU)XdvMhegx*t>5LAB(XIoVuX`Rl8 z58rg2CMlhl8++5Gl{hPx@K2E4D%H48K?gdwtr%-&EUb0AX&w|Hbs%-B8mE14QkOJ25VWWCcys|Zq@bezgNNno0#>@uK)J7 z87y1P$~kYN`5-OGWH=}^I*76&b;&`_i+W~LDl5zG{7Heq8_dVc%gZ1Zit}Z*jpJCS z{5proY+bKU`j^sd{~)}iW6k1=jtUB{WkP&QRo9o#$Qc})p{@FXiY-?Nf!ynjZ5Z&Z zW(Q7nevOVjd7em$8XKAvA_k)ZX9#mU9ZB!C`5;+i+ai31DZZD(9nFGpoI2! zq+mh`T^LG?+wIuow?vFSD~zzUT(sSB9Lt42$$=`z<6WPIT;rAK&TQ3et?9Vxzh&yU z|8i$)CQa7L+g(7t9eQ)!s9m*=WnODnM}eU}Vp@xBS~e|XC&@P6|KhD=SnUG3Y>>*8 z)2l^&*5}cmdf+01fU@#QDFqLYglO)3Hp7OLtn0QM@YqT@elN;B913%0&QoJG_+^=s z(vnaBVPzGbJeU9iqJba4VkA&|7S`hclnma;$~C};Ymy6|{iwLUzPoM$vM1C6)T+$G zTFw{e8Wq#y26Piximotm$hgd1cDO;;lMNI`+$pl};ntlicjkrud+q;YJ?Ps5rgJjt zZ`L0ZsAc)~>L3MdGZiySOSRmk$gMIa4a+yZ7160vA|C654zTNO)DW|_Ee}M&WA7Bq zHhku#DBs*`k+q);+aJgTKX#wX#uxQ)QP*ExFOVaEWk{DiE_Ht^i(X21v9@H-)4wC+ z##7>z&6zD-IORE+Z!XxmQaR|zFlFh6EXIWK2Ol?mJX{6~64c3*t3DY+PrzA4M$CEp zGbOjJR_*RgtT#yzyU#L0tKd-RFihHFC?!?EVsMg0my(2A?McfqF}W}1po)uYqkxsK z+wP`v*CiTlCr#H#yy&cna~Y?cRq=9fAH3ALk)U%-m4cvdwsCu(C%vd{KLZliUrRiZ zB4pa3Nw;gJw%%VGGG*wODNKi?USY)+11!vKH&I zy9q?=D4iRIkxWdiDVOTa7{=X1_Y&Q^1J8lq=~=RlDS6yuP#t4B7#X08Lf@-pMQ+E} zrJbS{QU&bJwV-~f;3@%U$8@tKKH9l2Zy*hJx)s9!0<50%_%${B6uG`I9m2l3o^xQ_ zfld`1_R!Umt}&?rpb$Ccf?fE_MDDcC+4zt ze_|S1blh(x(%9YI7g#nvVW+@pGbwjtXtbYSrd^eXfuQjDeMZ(Xywsi&uW51c-MAh1 zsu>GJaj8Tkc?S7^S~=A;95Y-L^n_d>B_}-7?&p9#13b3Xl4WV(@dOEKcWrQ#(4Mn* z+Rr4iQRXby3r$FX2#jiizbhe=7y)PISE6|=0i!40%bE(X=a%h zDh+=Cie-?#S7%%W@RtsYP1Ya$K!0S~)Gor2O}{cna){zS1|As6;82aiqDYmEqT@Mc z129s=zhZk)2-rI)0X0YvHtz(}`-DnR>8Bwd@%QJ51p*ewlTG&a>+zPAlKXhp&Z|A% z3lS(XLC1G?d6RZ?AOGpi_}O}B*p;zzYxQbS?qFfgcO+I;r+iX^g9^L5 z#d(cF$}{q8VP7w%ge}m!ZYAEXnT;NfRtH=$iD*pWK{R3_O=8n?i95yDm?f6EyHG#QvD|E^p zViA_7=;lL`!tShOX=z!z3i1A6R*D?0O82{P0`ePk#r~w4o+bx*^{@On>g3i)eE8MN z85%qaUakF7uk+KLTQCOf&Etp4opLYK2{sj*XA}3v+~#W^Z- z1e`sR^g5%Kf{h~}ki?iKWCQa+*>C>>MuYGU+wl3P1Y_!{PzoL^%D)2AB zedA+>(C?H>tQJ_W4!SZ17ZTK?OnQaZIx>t@L;>^l$i3~R;rC?d1ItuKlE-e>mheSi z_XXGZhM%rnd`au+khA(%tX#4EQ;MF{R!6Yo=ckclIbxCKJ1ND-6$M~Wog%fuuCDMs zz>Y>Bgj~L|pa$LW=X&9gp*W#AY_{g<8r`Yzv(K$yb^QuJ87Qv`d#=9UR&2bax6d7E zmx`S~-1`sJr$X}vrU*C5S|A4*0O?gP(cxlt*22s1PF~?OxL&j!hInvYtXc7@;o!5WKu6W;t6@kdFJec(awD}m(NK$ribcjzl0N8#j zcuO;qBfT=W&tn=pw)`jD%Vx9On5`LAi7a$bOzGQH&IbIF#?rSJ$_1H5!a2H)3U*y$ zow1DSlj%C#J3n_OgF{2rc#S7j!W$ESSN8(!w}~PZ7VDw)Y*bXOH9O<%#2Tz6*WRZ9 z3^e!4)vM=lrERiD)XZ|0wH%2IZCSs2C-mJq2)BByuK!#Qod33qb#TxVJYs87H0pJ& zGqilQ4->JSF6W_xnKeQfjE%fm z1%#QE^>)7uoO%lG5G~7Vz?6-DS;(^^tw|h*8LVD*iAKlW7uH)qDCi6s_?}LHa|zWE zZ@Zu7hpOn>7)mClBz9kjd;aL~Oma_XKcJ5T49FcB_%GH3Hz0r<2qWRzo@ktE3&8F_ zzo1+5iT-2Q_tE)vJB8Qg@z&VY>AuCF=UJk~t3453ZqK7t;4p!k-eR%Cp_A`ge{H1o z{iJjE55(P>PX9En8SP6v2og#87NhxlgoQKwvaZih#|RgiB_o0;{j{9Hj_z?7KrB?& zwZJ}#VFT?9qjb0yjaTqr61%BaXA|$TJR)`AvK=1Qizu}zVVs$jdA$vcNcl`AsG7`c zciK6Ao~{VWGLK@v`(YtGZ+1=1ek?wX`uFAvgpU0t$3OkPRIw}b?-uaU=8?}qrU?}~ z(Ot@mewC6!$b9x>tLQ_2I=#|^=kBNJ_ZvKxfP}qqs3P80+G&j3k>DcWqs%qt%F}rq z^LTpQQ>k7^a<^=2VteH(i^o=fPl0oOShD>=Bvm#@@Zf3ewM zF_C(kt3RISMuKgTGnT|0f&xa9e%g$o@v=nNyXyr3cPOFdh4sK}jWyzAdqx#^7f1>c zMKG6|ZuvLa20vGjq!LtE^0Po=nAWPve&N#f$K;Ck`^JG}Zb^Rhu(gz>6j*$#?bi2Q zd56lBGTRzzcA{H4-v}}{`2+}nr)&A5=2bc&y;6qbQk#JL-pTsXr=ihp$D0uPz^3Ct zEFg+ML;;}u86XX|&Vlq#N07Gu{T+v2f<*jwSVXMVX2<5#EWhO1+NF~Y1tdA~P5h@|aC}To-fXv1JKnVa!CODi_C?9fpB@5f#lR7G2C)`2S5RBn`Nd3dM}ky9DV^i+kLRJ zdD_5voYyT=*ZQuVvlsfc4GS9cy=ts)QlrVFoF4|q%~lP#@+785p{iK6c-}Rr_r@{J zK{faB$OS%heV8iNXn!}$exK&JBk$d16rbukW{}W0m=X^T4%X$9`EIIN@8s~gwt)u4 zm5ucHi4xs9=`q@E>dldXvrv~1B9>WztX6BQI_r(x`3qIUkh=LA&pH3m)q1MF5xqdC zkm9lV1rs-?@cZ$T!u=NyM^pG~ft{vgaMmKtFKP3i-(hY`ZAh6|rl~^R^X&=f4nX@Y zzfUaQ%6KMwF4 z9M-&Tg8UnqkYE|#w{uep6Maha{`Oa$!&8to@*}j#LpGZBQS{3nH#$#2h_HiVn(bfi zPkr}tUZ$G8f6pp{g@YBU_+61-;p$SDe1_nlF7iPWQqSPBbNC1u0*V|wAD>V1+ zf%vD7FQp?NNauJyy}q80bZx9RyE_U@1qR-yT>n>l-x(Cew|y%jpa`M}5(O1d1Q~wh z42q;7N|rEyl7}P=Ig0|4Gf2*ogXA0}=QKkGksODd(>rtj_xItwx^?T__u+lIRa7xG z-90_s)90MM*Is)qY|NJ(CKT1d{4c)$1PlE0^!~ROYB^!nAT(Z~Ut1f}9SzaP9M}}p zeEZ+sh5xJ1{nt0}Umtpha~QMEkz-E&X@t$|f4k@Z`jCJ9bJ_H`GXhfTP0&YgcdGcw zXYM;Q8*~K^7q_il$L^==Cn;IkvYw?wk1^e+;K#uH9#cGiy|JZY5;}DZ(1=^m&{hu? zzwz;^$`=aUpQyl{RSNAdNqG`Oi-U{P{-X6oBJF+h)s+?aX;ah5$&;8KsyjX#Mc~K4 z{Iyynh`sjgVe%oM$9yuU!mr=SR3(-?m9Jg{zvd>hq6Q<(1-`C%(|H&3;_rv*Ke<5S z``@3o?x-GVpF$)O*evTrz438w-4c_Od{JuvX zXE@?$l=ArEB&F#If}j8SS*_DPXpY>jdkvg;z|`jqRIMFm-KTcCfU*6ClxWs;nm7Oo zHmu}CIBiWn-^A%X1=fAwe#DAcC7lj{@UYxuh#iE50KlX;p611_3e#50zh~GJ)e}qS z%jdSXXLv|Q!ubB(&-&fp%7w0{UO0CtuZ@I}bkMfe)>Y2VIIehp>k@-58}u~aLPf-L z3h#qW-TP0fi*gRzc+MnFjVi7l~XRfiDl@A9F>R&5TRYB zT6M}1TQXc}Wh_fsxIiae z0-P04lj00WhD#4tZ}HDpPIR z%K%6U3@W#?&0);~M2F_)W}mI#90=u#oYXfD{b4E{h6mJj8)s8_K(ZFSHd*lg=SM88 zE8lyMllb&~7Tmvp>at3nq7Wzj!E|-0t}ENdL5_0V1Xv}!yzvu7Xj5^6_*J4`>C~An zJV%^@s1H3tb92KQ&6e<`kWs>^{`(O;}rfl@D~M5^LP+1J-p8dx++#A=gSJ%khKOO4$BoFI{Cw7tW$b;p>lTY)K& zab!>6FpVh(7z{}q>V;L~yyY~HSar-H+ixXei4)5}y{mn?8Zo7o$Ue zT{V--7N3woYsIuUAoh#MJpAKJ8^=t+?OG*4!nNB%Bw{{O(zYWdlnzps={nPhbwLji z5iT##5NY6!Y0gkj4O*sj>gvasua zVF3X9sLIp*l`)e)nSf++-7x%fth)w)JigxE$^3Ro8+Y#BJqKRUeIeoX5T!*>i&RM9 zy&6mQ;9IV{n%r1!jYF9MeoVpB$D{(wL7(_pYVEduD9r~8NINBeE!pS{Ytf9??*|Nt z-aA1X>m;fc`4~I%e7>%~IYfB-dgsV0J8fhWx(zNRL72LZx2KBsxH&l&Ks$KD z*&ee4)RFPMiV+wLN`|$$#oz(!jpaC>!}GjJY0`^cbPWcl#oO0c=9bQPyHJ9^JAtMsimIYT>bH^ zR?53(uxwZ;UCT_AY}cO`P7s6wXQ*7IcN80f6-7p0DwqUiqePJa5(f-1+N21nmkx*D zVttvi_ZR!pnaly`0BR9zjq{Ln!B1l+KbJmSo^iod#y*W86|(p}+F(NSCGxa_2F2Vm zsI#FKNzUaWCaZ~(C1#Inm|GmtJvS3T1#y^lGB#-s^d$lowWpk@exHu^kdn$CAy_$a zIUikr^0hsB8puRDb}~-OTkgtGA_bNF(o28O+yshtz`jhYrWO7=`vbDxC8YS322w;Z zM=2Aqu}E0edM~6NbOQR_#ia$AM7yk7`cwYr67>sAC!7VN>(&AT(63Vwo#7MFVt`Sh z>dzNV&E;(CjZd1E2HCjTkdAx|C^jbj>K_U!WPt4+q#D?m6H##^6LhnsfMIulTD}T2 zZcXd97E?&M88}nxusu=AvCdh0>;2V$Ho2oKRhkJu@5w{QG1jK;Qu?esHesmuY{g9cQHXkm_ zsgMg2B@)O)!3m8>mq2=yIN6B+T1mO8%2VnLle-T)RLhB+cG?THN&dzHuq2brenhXK z^0Mwl2dj8`c;>!diL%`us+Ui!!T*WmK6I6+?qyVE0j^3f-xr6j6Onf0VgqG_O)UvN zdVW)dB*E0ackhYKn15UJOD6D`8^<*=MY%fd#|4l=lrr>EJuI&W57V5*jpduoj;)>a zXwVWtRFV=BXE-Ngc@8o1Qv2z^I!C*~R)f%6CI+IOr&j+P0EvNaCx6()@yV(k|I9bk zyWAy(L|&hL1#^&QBgAAYAWi_Z9Po2&APdYOr*m(K)`5l)zbYJ=udz9)n!ITj_U!WP zSUG44c>mQLu2*Y60p!JQgARRBSgoCEsU8r94~)!y_tOi$D#oGOpG|H)Se$zEuL6;^ z2$~6m!Pxcj6s-?Zqh{~SlcMSkSnhl-!;#dmaIog0GGjKKku5gA-Hr|WDBb7gu)H~Q z303b=H83ekDhfq&$g1sS&n9jCtZ$ur8pe-J4*p1 zM4YK5GMRnZis`+l-uQXP7}B+U*jp?BVP0U=c3uV)z50{}v}Pm)LELO)@CCnTTMB=COdaws>A{DY&oB^3O5> z$%Neo$%qQkZ2Y0xdAv5&fsm+PNZr*RcPT3$>(*Z>s>+j`My=uCle~JLlESSzkyjxm z+Z)AgF~w+w{pDtq;^79*ZT#;0PHalF_h{H#Wq-Y0Fg|D@0$wVJ^#s?>T4#JKXGP72UDD7uLiZA=N|$Wrf+KRaEWtWNqpDX=|}<=iAH1rB3X0M^thw0q@txug!N2Jf_- zdRvGpL0Q91CQeO#6f{N?2SuDDh&8x60rjGEOL9U($NhWQTmb+Px*lm&1|>A5fdszO zf=cSg*I@Nly`QOeHBov!t!%wB_q0?-Yii-W5}u6P^<*b#9nULhbUU|qa7m?xco?7F zq5~a;v(~PclfhH?DPU6Cw%M2X>TI_Gk0(tdr&-JIOzcoo9n03BGY(Fm%zmj+l5zIc zmePb83JsyD4f5;QO-L74|=fT=YO+{slPSJ0GdzBdWT$Z?=9s~C% zM{5a&K1S8F+_o&&y)IC8XgRI}cxh^77gBf^+~YtX!*xs@chezx0umKXbg#jdDZ#L`c2Pchgu|NR&4fyNWBYFwCDQc(bj;zXKJ zbbmCndQt8}=LH`^KS(AxT`siDxevadoST6%1Uj(cIu&aTU+Z6m*f3} zRTrSi@NchX8dz{EnPW)va&ckdAg&!501V3L6`)F}U@x>aHFajI|F&7sZ8dKXIa?g5nCm%G`4u6k2&8ZO})MeJb*qH9V0j+P$-D^xZ%ycF}(+aL) zN{mi9N++$m50^)#n6_=Pctsd=8(jIcT#n1Oyyf8mR5{U{ekDuh(C-5zxqPeNiyCgX z9GTl5G96h`MKv-NaQ3^;x89L67zkT9CDZxzN*h4glFWVDT>v{#8DAB`+wPnX^p z%Knu!Q|oc^2d^|}2|*0vyWwk(6Zh0~=<%-r)@)g5St+yo>C#HF1=$fG?)CCz$tT-H zE<5cnjWl_8j|Nh_Rpm4T9Dyo?XGTeT!Y9k+T=~B?(|O?IOFu(Y08{7CsR-noEa$)q zW_hsr3(%Oh5hL@sKFz{a1)aApi=BU1;wvwJs!4x*f&3*wbMro|{?*ekQ2vBxOGZh8 z*qXz~NaZq-$4VGMrqYl%BE^vN!(p>Hk#9W>afMErap_&{bizYD8BLaO1TSU$*qIvL z#&dg~(?YI_xL_5S!if5qZvY-zA>u__-b7bbIQ zzwU+7Sm_ipZ20lm*fb5!x&~!lhq8FABv#w3;J>pxIraWJZfVF_E6!~(Z88pg4-{h{ z@h~8XLb~S)%lP(86}8bK89blOZn zpqF8$R-LW%j0>bBXOnqFe8R&ydre=6+B@3ZdPkb1XnSRb>uP0(I+wD0K0|Zk#Ws)W zPKC~=5z8VdV_V4_lIibpk=;!qY6T@fwhTd2g7%|VHmh?_VUwV?H{OhmM}m&!SepBSIc1vo>KZ4i2vA{k8;;#m+Ex!@|3v zNls_6V$59@Ma30XQ%2)^g7T=?{T6x1#z9${+t_ubMQPkyUm{v2^};$z4)=;Cq=iKF zV&SfS9EVHr!mqfRqTaLs$*A-gyX^vMJ5lL5E|7%Eo{k&P>10a>wr*FBxUrPm5Z6rqo^~ z07^6<>d1PUA1J}I&nBO1#O5S4dJJB^`TSY><90*6A?l4vVM6k?UD2EAx~{f>?PvYs z+EdDTR0A_QtJfe)bWu@>#3itJ``aN>>9c@aoCWXvh4)<$v0F~rTac2PIM%y=!8M`{ z$pP*x_==-^LK=&~+&Wl*avDYY7#38o3A#*WV>x1R@+$fi@8{Voe$ER9RC)CDTAJ+G zpQ&1x5Q%lt-rCJwo0p0brY5=;-<*ECZwikT&qOs@AUo9x87J!LB zpCz?`y?NW7E=YrcAMcC(!0zu|qoym4e)i_t`4mrL_l2~{UM`IbbbN)*^ipn&K8?Tl zff~w|@N{;y(+s8*nk-I+fr5+LQ==oi^VcjKmjxQ766y1lROV+v} z$(jz8h{1+Xj=STk%oSeY1WSIb2%!B;B0{rn=+2mD8!xWY4=bpg~tY=L4heIh?c0QHcwIz zxwd;p?KxvD@h0E$wv~{)&008W-%yR;{m63yw$L%X8-GegE~Rd1=xHFV`Vtg(k}pOV zD;z2X?DjGioR(^Vwa`lIh1Ck5hv7;;41jU$lH#Ojm;Gmm7M(PTF@JhvNW^%(u>zoc z_6Z~+Q_)iMAZf;MkE8wher$i*@!YCz0uWz;9m;EL3>7_mzfmoF+j6>UETQOXjbg-@ z{Ag+&r2J0mmuF0IZZe_`m-afcwg+=~K0qm`vu>vI^d-XBFYTr;XwUJ!<;w`$zr+Id zbm^MF+GxvX=%Zg{qw?ajEg^!Njz(R@cG8cp<}Qgihw>a)-DY|@FO`GZ0%O@(U^Vn> zxe|fYU=6uPiU>v@fh5m_F22&Fa8os-;Ktk2MyH5^!~CD;Ahe4M$T`emXPZBZ_j#yY zAH3`;)(VC&=Of*6I2WM>-!oYUKEqBGEtl2I2=*v!>xx4cl;uQB&fH>bErdN zSmmXhhevaiwZ2qh3IgNXt+#I%OJ{NAsc(eWm5O>t9a$(FeB^!wu!Z5T6=K-D)<1s& zT42kgN0V#$G9-R$-vy36t1?P!+`pXpY%Mpf}Q4 z%^jds%?x&2v8^BMa-|+X_>ivy~USkafOQ1P)Sn&LUoirS(;BG~A73+mt0ciVd%+8bX?F$;KKB?q_&2F_OzR|9 z#k{HzJ^)&`X6t?Ruezg{Q8#jd;navxU!)os9X=uCAIAL)zJXMVjPd>JF9dK;xU8;R zvcRT;LM$-iDpZ{jF$w+Pf%5y{ajgK*U(S*u(dx)cni~izSNUJXB8{ob`k*5Z<;kst zP7x}5HwFbICQN%o8G&x~)ZLa*XY_c=hnAh4d~tu0J9qA=`dRfCY2+CJoLTk2Y+D5{ zTW-6mIma%3l=AMGop-=}(Oth>{vc7_0TrDbta{@CAaFirBAUm(Ej0eq&G%75k!~aC zwLC!UyENHGjfGSzoSrH9w&-xY8qmp4fvk;+eF%{8)JWZpel8b(0HOgaiY0Ug zm+AD|W&?oOlZ+cT*dMpG-6fNbewE5wsvOgw`t4~_++bJ{wl|LW~)${&C3kjbl( zr&g|c2-l4I6%MO4{{mCl?Wy`33oyFKDPU2_es}#DJE4Q6eBtaGv_68QI_!l4aBx58 z%~euPi%^r4?#OlyqU4vrFv*O6V&kD26eX=nm-~DPY0;~fhs!lm4COnKX;(!)dVs{G z60@Q3xN?2Zb)%2xu}6))iWkHAU6{W*=?A!@a-snL!`}Wm0FK|IWz%N)0+5`t?ZGz- z$@~)}57*P55($Q~XxXd&=@#NJ?a+dNrdiuDn1lD%TL4Hg5mgVxn!W*HRx5S;4RT$e zqh|JrYi(=Vh-e0YU3tXAn=uo`?!YWg1Mow${S^#<6ixu6NpjO}7%>|E(a^7&NELE; zwvLN6$l_bvNAy5TWm28fWSK>JNgl8{t7$5?8OT{F?YW=u1}Bp5@uu~wwj*KB`L^<~ zBii(V*wv9=-uNp6$s!@jF{8Or73X)(54Q5^--#Q!LD6?HSE&>M$<|J0Brwgffgvi zC@dA^5?K`cwujW*Ex%-P)GD{kB-YA`Siq6-iN`0ajIce6+g2;k$}6+EU`qSqtO`mJ z1wS(SkwCc`$M|+|KqatY`Ti*(eYuC~2tA{J<)hwOjR1niIRN6KJy$(IMkqK-iMr9B zF)NjsBn!J0wYKs~U?ax_w)O{H4%bnw@(75ehC{mh-frYM9-&G|+$ld<6s3CMj9OMv z-pd?SiX)zPu|@Y$dW8`AeVB#j>;1k$Yua!rsS{&CHz3yyW*$WuGmrpM%CKoe+3^i7 zmFbY{e4sOEc`&u&*z>WV?K_;Z6)N(F^9x0~ie3PDb4kTY1_h7`^NHbNLN)Cqk>Ae# z5_0W8Omr z{||)mln$fUB``(ntsl`#JiE!PmY?mYpq`mtGUho2vUW<)i25^qE92>Z1DabjjfFl7q24 z3wcZpvo6ONV&BeiW)CGNhgCyRK!|#lC&jaMgJ52=)LkWng;9@EAC6=|^R9GAtw5Q> z*IFQYqBvVa#fhub0&A-=pV-6r)c_Ig7X=X2>y7PYUf_=gcq}MZEe`C zqpGAV09pH1_-%b$_ItKzT3=Mp1Lj()URSb+t{-}aaDO=9+xxnvvo$Z^P)0~8Sfx{6 z+k4oXD9}N@X;*03YuZtOw+^*-HIQf3E}koDB!)#@yI%HalpY?0R zpG}u^BfK25N+CR-U1Mp6Fl$fCUx>0B%Gp142sw)c%$LrqL-yg8wo#^4+%z{y$my4efPAHN+M z3II7pht4YFWaX8bVVkHZ^9v($!bUMJsjzoraTOv% z`ZWA0r+Z845ksd16O@WwfKjo((7~sZ94bv|t0XcA=#oW0OgScHj;`9~^d&<;B-y-Z zDB*;FRT*py^(O1~In$AHN@RFi%zwS38Q<90c$$*3KRP*Uj%K>UaoFVP3FLEK5IQe; zkVqRR^%|#+egLSb2QHpCJzHqkCFA*Qqkt1!!Z=iom7(?K&6`|SjPy4hT6J4?I3(o z+Z{ zgqXClgVQp=Qq}29JA!HQRI0=Gn(K&0`3|X^Vbiyaw+QBbzm-$!=ozWY_;n%Cm^%xW zoLOs|E7z}A+U}9vx`{{mAm#zp*{KE#t*&qeAei7VUK^+Gghn5QQuV!sCJhJf{ZZvd zD;=lGk5z>_u_~k;x|m!flydCQM$ll>lVW-B)~mDKX>>kZ&mq#Hs{oZ5`LmWH(=f5g zK|MW9i=Uy^J7wcSSo7>dM>9Fx^g8CI*G7-Ea3R`9=N zviv8ElYdPg`9Ih`{|PbUzlZ*Nn$drMoc}&e{~dJypJs`G#y`fG>GK8&_1|Q=qMP(0 zKCzhhF5;aikbnKZbL{@U1}kiORu6|qn2#K$+HRqc_#ejPN1{-2Y7CWfht`-Vfc(wB zVO2(x+>)wWqXPRjHOl+n{QDFBd4gy&EMkWN41@7xpytv2e_lv*B#u;F7UtciMk(pH z0Mptd>3v>x)z1S(5Td@mWX!<9YQHk_PTbmBh(D@5&yYWOwO6pq>pvif$ zVukCcFg<@hIS?X%#%#(Ua(7oxOV5WU)7+~Oel7invQSL-XrJhRj(faAbUV<`PkO?k zkjP8PE&yhWTuMnH!2QRO*q=XBd`yE-ZcskZ6^&y4y{{7YM6h; zY3lfb+bfA z8`xA(u{SE-E1iAJm}lX}w8S7MKerq5W?+zq!K)8==7QLC-6#b*; z7v`%D?}39~OEb{ZpWsR9`OFOl#)I(k#M7={?&-|Hf$ zrjC0`&ly_Di}_|!spI2$;L!lCc!gpx|KNsv4+hwCxiq>32|TG;kBReY%wAWQ7j+3M zhwH=7U+*203sJm;K2vpBxYWjMyS7>5`$8B9`lJ5=fWM@sW& zZ=qmA)7F9nA@ymdpc*vV13y~sO^xXTx(ClO$6Q;w^O($aN}d0tGqd zN$Tt{eFB@G)bH+}worA}+FsUQw)Zs-p(p*rU4s3w7%&?XcVw0cKbbya$k^($yLR22 zxgD-hHgw07>zBUeC$E(dLflBOo2OPYYgBU9Uq7jMC5XTCvJkOJbX%3l^pJN+am%uQ z`^PTvovdZXsiNVXF`ep3^z8P_i5!}B5B`cj_w73RB|wr!j&;u7pn5B{W6 zP6-ejvAy3_^?)rrEbV7nMyymPh8*lj*XL{Ix}t9z8UBZ^rSJA|BfUgT1zZMSZJRyf zTO8P9M>l#>*StQ}Qr_0!#4!No91vE>ptsBR;P<_kA4tIt!|_z^w3Bl3>+NEag*Y|3 z8lvoerzCU~727j&DbExorpJ+%^Ie!{ZQ6#X@^a(+t)#m!#JWXyI21`pD=i(a^D*!Y zY`rmCmDz&jUir+42y2*-LagQp6;DOS0G;K!`2uXc;K^(}Pg5d&e9G@?K+of4tFKSL z@O;`b=GiplA0H0SdCV&iSxmFds9zaWTUL a`$p*P1=7cj$ra$88&Gk1u|iQjum1%LHms5W diff --git a/docs/assets/tui/jokes-dynamic.gif b/docs/assets/tui/jokes-dynamic.gif deleted file mode 100644 index f0036572e8a2eeb0721d6929cafe404e0f6099ad..0000000000000000000000000000000000000000 GIT binary patch literal 0 HcmV?d00001 literal 78162 zcmWhzWn2?p7v9DOBR7ze9NkDW(vgl1i4lW=qDYB|N~s%c!~h9tkp@R2-HuWO6jU06 zk`@6`N%#KW`|*6Zzx#Xcea=1SdCnCxQ>3OB4m<(+3;6$HV1hwe;LLDt7$-lRTkrx8 z;sUQQkAV0^AxSP_X+B{YeuNaasGOjvtcsY7h@^t3q_U2roS>Alw3LRJ^d$iqH3?Z2 zaRn`2MJYi=Eg401Sw$^nMFSN@aXBT;i^@{M%DUppdY;Ov3aUD?Y6hBWW&vs%qUuH} z>IORM63QBS+8UM@HKoOnCi+^o>e_~qdRCfxXhS_mq`rxkzM08o7ipA@HtNb112;V* z3kxGpITJ@K6R*prb_S+as4MoiSFX#WT@2CIwrHOgGgA}utGyOzC(8gOD~~HyF3Q$8 zjCGKwwItfc)y&4}t&O?4t+R^VHGX?}OM5r0eW;D2m#xz^J14BSQ@FpAq`I@;y0e`< z#`88tY71k3!{w2NYoLScH32sTq}%O7x2s6^U}x+te{2lK<2uIEpXTYTgS+R7yLsCy z!QI>6<9f*5>q&Y(5x5%x4{oI5Zr%&KnReOtk+*LU>el1y{&yq&GkpRg9tGqY29a(B z-6I4&^SvE*GdSEo_(62=bK{T%{}6mYNL1Y2(u8~E==&*m9y|;Qdt?@#{v^EWUSxDy zRGsCcoXkg!4<09kKPE-s*7-L$f?=RPhZwQ9mixeCS~N;XH2}wlxxhI z9L|yx%|@nWKNriUH_nwHL#~FMbqL>P9Me*Q(^ps$agZIlNi>{$}mOX07~(x<8fmEg$QT zZZ&+WYG|EmJgsf+nr;3k(W3jiMIoSdp`op(vHg`~hh9+Ux7%HdEnR*8x)p&w zfc*c-@qd~CpfmskDu8Y%>WhJ1kaZt!C?1G|i<#%6UzQ9d@~ZlM9)4N+CIw+c7BFip zd;3)SYL)xj#`4i@rE4SkW=$3Eo+0mUeSX{YV!RL)!z5_lO!-iXekzL{X|DYA!nV}> zxp_;~R5hl_@5@L_^-Mi(fGlXyS~J(=`>6^$+FHBN7Q8a@+@h`SOIO&htuLc(_1|9M z>6nEq+Z&b!;xEW~jJ3a9d6Oz;QDE88_t!EInVdq9lzEmN-YY7G5{b39^;JJ z_dQ*Ie=ZIr(u8e#yN`cue5&>w@9jDLySFl0X!EM~{PgJ8_P6m@ul|FQUV0G^=JqWL z7j<6*favyC0rVH-a^m4p-mhWD1+IJ-xxkg!eqWfoKC7#U^-v>gn2KS|)B`a6cEj2b*pW2$re9v%jy7fI1bK{~n zh(`^50d&DvW-aG>)~&T%--^n$ynxnC$t-q+(kBRW_pSBkVQZD^1yO%C*9-9)30TW3 z^nM$~@sd>=B}p1v8>K=Xdmlj@hJKsnIX9{{EAsDe$&i>^udlu+%ktZ*q*PRGRVmzm z%RyiBnkKtl(>(3BT^nRxl}>kWd273#N-ww5Fc{GeNR#Pv-Dw=t*xqTHkR%(JgE{$r zw9MY9{?YpRWMj*0=APVc`)ZbdP)Bir!)C`$>-KKfUd0x`eEPNj&z_^T>PrQkdE))O z00#LzDp*biWG=y3v)9j}xzi9QfpA}DGzsoAVVA;FNK#`;D+%0)Cj_#_e38oQ0qK>_ zx)he0{DaYW(hJIkpe{f;>DXAkmdNu;w9cE zI*%Inep>f3azz~WGSbPC_eaEK00zgCi0Iw$*wXCX(;SCxQTn8mZbL(|w(W<1a(`l2 z&xk!X?U#Q8n%TdZFSo(I?1X85ni$WKQe*uf8j)OT0$5P*FtQv5_C!ACjmTzfu=0(m z-zcJK?8koC^fHVMBQe|q#2rhZ;1!X^#ftFDSE1g4YeoRB0N>(6yW!9aqJ2MThGF7j zIiitOD7=uR2>qu`149I-2*@|5>)1}2_-lKDV?8^;in_#A5?071>#PGd{t$zmj5&p; z#(pL3N5?6Bk+jF-8+#17q{fV;GJKiT$o;@eNlROjp>LSZ>mR?0970G94|B1mibD=3 zc;Gormwcu9SXf-u)DBspl0W#9)tn(Rlf4&OFI~93@#V}q*Zf$78d?#*BKHwzI;5vh}h-{tRd|(lD zR)7VqWIA4%QC_V2oXhiN0%PUN5UJ}_K{HhJQ6IH1WwBD$BMspFanh%~`ZG}x0E9vh zLw__a5=ZDY9=q<9E12N5$59{#dEaU*b`HX_WWbdCE3+Px%GWjB`?vg%OYU9OCKE|; zhhoRV29*MZ7R4P8T}nK+z{{c^#5(gDyr^2Nv{5dzrOBil#)nFqNy&*OkclM%+6al1 zBGi*7rJQUmGCJbuxxie9xO$|QJ!7Y9v%N2c(;UDO9r!|zx}sJ2N9m=m z1Tet=t=44cy=SUE3cFCIn6Jro{_o23WjdXT|FAb3-c&c?NFK$4o1MBiIYie75fj@^ z8}(z&m2*MafQ98Jov+kay>QD4Pn@CmLRs_HUWrB_zfl>8S@3$1{Jr_JV|sQmd|S_5LqoH_1D^u%6 zX${WF*#l6{rEv#-S5Aauuiemb!2N#P!u0OiQU9We$UntJJ@`-MA_pW#1UnwRQ1u}? z{2lShh0ZUG`%7H1ruf*N++h>NqcQ00CG<&`$UCMw8dSg)@k_U_n86Uv<=Z>GYFr$5 zWiU8UB8td9@~0OCi%9++@SSlghw(F8X5w>I5V6Z#>-5V@%JWD+Zkg2qMxb3$U6YvK zEnP?c(#Z*;DS%j6ME6MoH&rX?7Z!EnE$6bLE)Dg46|t=^>?Z8ea&Jnq%)_>sK~}YOtE#BQ$h#ba*}_( z`|tUXzz>3gaCqvSs{v8dyW$6OzWMltmq%ZZX}cruyyXf|}Bd2#gkiO{Fw z?y+E=(+y{rWaUb4bMbYNCcla@UOV67jRt&{;{3z>?xE2=;SUgW@Pn%LjtxPr&TkBl zi^VVe+Y6`Dy#h`N>)$S_Nlxh=;C#jY+T!0q&UjR>bUpj1|G!^FFugWpA^UjZze9@6 z!v=H;`={!EzZ+7{D>0ARXGZ`1X&--B>U*1gVf)`-Donp1%#-~aGwo>DrZ+3zhJ8hj zc07^tC_U#g`?>|~WOiIXiE@d3+n;v22zy0)lpyu*;2G^qZ26IKcgnv%U7p8VanRFm zHnfu!{eLj6)PH}+Y5z|Ds{?rPAS51)!PAG~p*eV_cKjJZ3A~4g^Ab3a1WpWrJB+}a zL*Q#C2+R_MjtB_eXi;ReI3`*$ELu7zTDCn}el}Y1C|Zd(MgxCw#QL?z2F%6=9mNLo#)Tl`YGCn>hp4=XvG#mefb`+oLOCaUI<9HLY!V+?F67t#;@@ErdkqJ<{gaRbF3`4F6 zBU5t7J{$O|S#sSGxq&ya5t%3iB{PVSn{yI7+Y`HI6MNBdt-kQ~qr^c>((ACK;hZE5 z-Xw@}(#TQL1aI<3Wb&KgBszA$dvx-Ad-CVm}ws_*yF56;n^{{*|=Ld9tk-FmzL` zx4ts3&E;9oabCsovmlxL)`Yy?guH=-{MQ%rYdi8gb91S4d2iq5b>(JG$>h8be_kG* zAECv>mYQfv3(vU7o{4fHKvA$gTh=K!+s<*p&Rf>K# zN4E-p$P}G37SfIjfK`QH*&+tMLWp@Gb5+rw+@gOMi@CImVIu{s5rr(~MHjV;F3cD6 z%9fm&l>knP`N<_hekIV661J@p0omfS$`TRTQYofVHSJO)xm1g(NSCQ}6IV>%S)wst zVscV)g|C#Ss?==06uMQme_U!MTW+ycYQ^9lg z%%X3gV33K7pp%N=&S*mvj1`r*l2Bo$6{@${kD>mu?n4A5z$Gh zIH_tNr&DATSIi2yfmQ2fguYa^m-E%VooRXFVGMl+bbQq2*j zMt!bo%(Zs9Dy4}pu|>94-mI3_7pRB_Ein=xi=efLIw%St8eF&L`hpKvCz4vn9uII! z1>Z9Vd>^S(Os(4y7>@l^>St9YQShqg_7G+QWam`=T` z=@3o_rZ%ZBK*4Y}-BT8BeEm4J=>ZC$&D^Zd+%2weYmJU@ZWi{H?dU{@aVLEwShK1neiG z+tZ)*HFKNyUJC~r;;B>T5Zv{+s14TDgUIjsvOxakRsB$+LcGL^Dg&tHhsz)-eRP`#$LsSDgG~^-3v(6{~H8t%mC#j6r61y%d^(;@o z>KmvKYTG+N-zgOa3GU|l42w{D&7TkOjD+2W6aFgo94}{^Ag&Zx2uw> z`={-ilqZ^X{Mpo4nm5gx7g0@zd(2x~?FO`GO(^E!tkEXuUZ?sgiTl2Fe)YYrV{;z$Lo!B{u{Z^0QGH< z)hP>Amx(aONrPz6^ctervfVx~ed%SV46tLM zXZ)Sp&nDR0C(bQe6n1L3rKxTH>Yj+^;_IDEQFfkj^Mb;v1LoZ5CXk@;g}>lUJ+ z`}w!WTMK2-&+Pk+N(+RQ$QV92-Cx;Qn;5#F0735ygD2;UcSgRIV%lSw*#QOZ9LPm@ z?~*`4EXQsFr^lNJ)@Z)3OOlV4-Hw)?^DejPE(^C;OAD>26p;FuY6s_+`ybZ4)n3v4 zx?+Kzsyt~FEm$cTnbCi=iY|zeeV-sNG+`{%Wcnx?UIad}0;r)tNfbKFlW2wp#KmEt z7k@OQ2+R&3ic?28hk?EYG1u6DX8+dIEW4VS7LDFl>3@k9$3Yq3gy4og8w$OfM@$5K zO_D+v8%%$Z1_j3{MMH2<8QW;vCITCPfh`CewfOO*CI-T_A)Et>XIt0oS$#IUs{3Qv zb~ie_cO4Ez+lE2agJWU}qTgSKGFubK?>C-!M0+DX^6>&=7uVpvo7`c71{;7XwrK5! zjiR7WC3Oj91v3?ji+1`1eR>9ODi9V1Fasq5-vc^<5SKhK4xdp!aYPr^Q81 zG(_B%4w&)-Z2JTI3;+AkPlwc>-T;OuiAJTx^&>w>elG#yNEZv=fZEdC1Tes8_%@n{ zg5+%i0|4v?-{t@Jp;tVeO@p<K{HB2Q{~4hy^h4Kpr4KM{xTr?TtEa`1*C(o)h@MW=X6RIbJu zkWefMYP@~6f{0)i5hcpX3pQD2C{Fj9FTy6>uH3rZb!yA8#-%0b`~1|lbA#8=6A8EJ z9hc@?Q+3bHFEP5c-lvF$x!<3dYi~B z{ZLuk*3wL_XwCtzUo60cY2OT|8_=vdY3WgT=&^d!G5@QCH3%)q>w zYJAhFiWmZt$zngC#>_(ADztf7rHm5e$jp8Bb?38!lorNbby?~%&aRu zn&IBWVWGgdc%U~EWeh+IHfdAgpzLjBQRUFRWB~0si`MEyCA!EkB_rb?i7Mg95!mH^m z$9N~I|Cvp*H@-ht?Ha0V>U*50jOTmR`LfFL3i%^pmgUYO66DvwA|jCz(1-^09|mfJ zI2ISNVa#M`{DYY8ezlM8s$?SbNe`Y9qGj=``%BI8z<-L!ufA{0?a$jhW@q0$aNrFV ztnL2x$0mK5kJHzTPzB}= zF^geSsX|@fv+#iz_}(Fm>To$d0g+!)U1(L+ttWmpP1COOK5Z5AF4Ph(H~g*Y-&?L# z#;OOR9+gT&4SnerZ}+ijZlv!!*X0CQRQd7%dJ2~q@-oZ)Dr;5eJHew=Om)eGfsr)- z=53c4mZz=#KCwnAEotvL`YPLrUZKcN%lMRac#Cv!RfB-~_sM&~cjZ5J_F3EyzU&x9E-BH~8`+fN?{~-gcDn`Ft=Q8v`;N`y&k-J@g|3&V-+0u^k z>g)C2@f{VaQK}xq=>n6wS5HB6ADg0KY}fhQ@L&$g3i)5{j{EnIIi;cMnQ|L_Kyivu zDxNc4Q)yi%7y$$+;>z&Pt2OTV^3pcWrja1`CAc~o08XOTf)yJG4Yv|F5Q{H$8B=|s z$|DN`+1h2{)#5bQCoDwHi*14mvTBHV=4ag9MpQgl`l$`aC0p%z=?xJ3WE#i)WxQjW zv6?fU`ay%M`{*#m;=DAOJ{7>EyjvM~qdeFuA@%DA|81oG44Ln~48L;~ac;;Qs zCy3ies2?JZS;EoAlJ;qGeBVSZuIqOd!CbeR*iWmX0R_Mj1P?la@NpGyt>L3Qnwy@% z)Ib38ZGs|{CN7?EXG)pNi0%^%%y+Y;7@#KRA4I79Nuh048o{v+;rTIjN)ix7lk6s9 ze1ie5yf>7!<&)TlJ^b3-$Kmyb%(#%NIE20rl)Nh1Qz=EwoRdMP26p3VD~ zJKMz7n9mN0h7NpsL(u>Ru$mlnSQPlE%7nCBRw-myWpAaPUzt8wF24T-&9sQ8Xme3S zCH!69MNAvTa@O9>%`)>*6KlE$36%S2z>36~4Em6mWDo{d`^hyR>LP2RYju1mJvRq* zI+WxSa82+OL#wXjYV;Pl1^66c-(GhKqfLPdoRnpr?k};vD&+$m7SVsSzOSHNLKS#O~a1?h-7C<7}17{G$K&Qf}?)gLjc0hZW8}uZL>y56F2mrfHVn(gKL-clBI3 zL&-tI1|OQGe>0k%c_k?d6#FNe#heNVWmAeSHth$9=`QJuhk@zPApkzzzJ4+R$Q6|Z z7tDu?upANCgUP9Msi+}2>kEtp4WH7GIOr=2fPH*~8OPpDS^h8(3sVP35aZ~?CG-|3 z1iV&Br7g0@$)X0Dqe)j?Qtfz@KJZ zqD5rWsmH!)w%lC>3sC5X`5&7gnCl(9Vgrs#Px#~eFnxBeQ1*oecN9-21#iI8Xs9Ilmvau`s+Wnm&mY8~X# z3wxmVwzpVbtlEoem0M_jB7IFSOY6OTCc&qxQ;AR1pZ!qiZL8sVKc4x^X~Qy$`V~1& zd);deLs`FX<$gpxb%?r&}f9(Ppl|9!Xc$p8B{ z+QUIP?)^AN-9E%^_>i2jGQ)(A;cqnez-O~QMs`8)e_TGYlB z&y!Ct9{pCitG83#570%^5E$u4A0ADF+w(pH$6@bkqM)65v34vlvEmt+M!_=h-NNp37kDLLK3c>~_YfX@# zlO!8Nf-{CB7YV`rYB@H#Jd>lw`xF^Ng;?|IVKIbC3YB?P!bb;e9R@MoOQypRosYmc zH%38(AxATrc~RedQU6K|p!!rb-PSaF#PLswQetz@~fTz$W8b^q|Qk$uw#Zoj+(^2D6+r#==!RbcjcE1I=P2 z6AC2xs+t`&#sp6KHjLCeq6=FPml#z0I03nuaV4hxwN)7tJ(Z;C+ebf1vKIq9z0l)4 zOf-O#{`-I}bUM14gnXC{S?&OgjIMyFB#O}h?Yc3v`hr2FuZFlBfTK&NWU<9<%p{pP znc26`fWo9lf%psf(KNa%MwKCPcJO8X9jG2~Id|lE!peVuliLp^@$;9;F5#-r;CnG~69xA4U|a zG(%28N`~J&D)9M7e;JFK!RP%$ zz-n@EVp}x@>>z*!O^}|SQnM!^vs4or`of*3?Zd|L`b{PYrOEgFO_qO+l}wPd;D-5Q zrVZ^a54Oqux|Ue5FT{#S0g$eu!p1BU9JFVl*285? z=3ykz;+tCLeo$)ryEC(LalAz$%N2nH^GWvd$TqcNaMsQkUCg^Z0 zIcDUNIHO6T0q7`3L=9?~jTIsxnsCqoAx$c!(CAFK}ryK7&8((f@BsvH*UF-$%=5 zAp=&@zZ*Ep?d58l{rxNzuo~|1S9g#jjyvoj{vCD}uk}9-Nl#Fp`o}mbHw$Tfni+gz zUY7hV$-zl3!|wA{Q`LBbFwM(DPtZOoj;Bo)qfgB@-n!^yG9LkPPtopCnl$71z=3h( z!*NHkcD{iaX9^_f?YI%{ttFKt7#{7s01Yiw%f4zC!#j~Ao>10pXL)td2xGS6-h%AG zyQ{}zxkfYtTOY}E$yg#e9URS{!NO|BV~!@WBBo0jO)VWq%&zGuW?a0Z6VG}?XK(8$ zS~InhVXpImL`xKKM$5%dPRa@fJNYWur zWhU?0v7N%h^TNnH;T$`)?@Y27h&Arh4F?xloJ%&zB{$H)zh=%Sv7y4p^^Y__dBgtU z2a?gmyzpKwjB3g#0ifq4@=qz-sY8pumpjU}1P>;(CA)Pv8c+Rdwi$k^7)CT`S37qd zsN}M#)-ylDjie#$3O@i%!@vU6g&06BoQ>=jn6z?yBhB=cOTUh3x2_+AC@dbDQhHrv&GZ- zWL9lf)`S@H!qkGWG{8ueqfMT%LLPr}Dn=yUQFPK>OD`U@XbDDq)l%{(B#n4{7)xPY zO!cWtGbv23B|nACkLkLN2N)FYH|N$~Y3p%m-Iy!1njQeLQ?3szONk@0-51Rb6&{0)O0!?vGK3B`=@}wy| z>Z**!100O8YTDUJYyG8` z#1Cq}D8_%F9tzWHs-HDP^SwdIE9I1LF*(;jVd~hX&PqmHj{t5}cJZYat_qF2=;1Qn ztgVM2m|u6Gp9NSA(B)frzb;>FX~5M!_4+BG(H_9#PJt*>0Lp*?)Td^(Crp$;wr&#e z^B~@Y;M>&$n6^w8Gr4OA2JRJbmi{Wv9)Jkk`KI>unA)g@ipIv!f$7uT!&0}Edfoe2& z(mTg$i0rKI%n{yFDVi&c?oJsi2RcT60J0;FSG4U)o^Gsy8xe>c?c~Lb3Uxq{Gj>75Q4=)zECx71JAX6KDGEK#j8lblp;gLZ?QpwU>=r=vRXyhXck zEM9Snq!}1|?UbPS5aJQ^vv@TNTDyCM0bcI06{~3e$2MT|2`Pqa*?_j03|!+PHYakb zvle2U`1KsWx6os6$3SXTqc8$lxjQhtZ*r) zZAU#u6K;-Y>L+(DG!)IR$6h;Vq;$!Lw3}XKc?7hhK?azl){W}`cNMgeb>@5Ew1ceW zgQkWMf-2JVRwI|~uPQV^TXRWOIDun?35u=-9|2%0NOtRIday*+_5)&gNVO93PJ}Kg z1Rx<>c7^A~Ri?xHB7_F!kjnxG%d!V%+94h02V3)7T`PC(9^b>H{C+ETZ&~Fx?@~Y| zdU2@}Yt3u#Lc529{rOe$d#UkvTS!`ao~k3y{TsLM-+X-ESoHpq%Kb6JKMhbi6a4+a zZ})?K-mkg?;l!x={Zw#pzJL4jgHW3X_txurE$i=OXNCN2^YMHTQU4(F)n7{LpU)8w zHpma&J$n!Z3nK`J`OZ98SpK`;_~$@0EcSL-T=qR$OuYheoY_5v3HvxKX*?`hvp)Vs zZ9>W=Qel0vaCrKqoRs7F5(W|YgZ1e8OkqZiB8J?b;f1vD z#${jx^!E?@@WX5jNI83bGpegCs=_9!qCWCE{Or9{)H_<#*sGJb zu!qA8Q4N>RYuiqO@sU&6XCE2Pr#;W-ESymdCMSMT*Y~*^f$&O2?T*5V3xg*kI`61K8sr>Bk4c zj}PnVgOIe}&W{ftJU)!09o(k<=AoTt(+*xdK4_!;Wr+6!F*vQ52IJaeKphtya%{Z@ zVqh>82TY)7Up!cut!87Q#FU6IVp?sVD0v$#eks~m>!XBm4ySWP+3~?O%Y0Rz8>@34 zZdfO1lIXu6Cw=YG-~=Jd8T*^26?(=04#U&83@Zg|t5&PjtDWmTnaQk)E!%T1g%a%L zpG_+)RCdY3DgJ*IzjjCbJ@~Qx_tGLYnqfwPowlg7JOJWW4ca+UUKvcVfY${atE`RX zY2Mx4IadAeOjn*N2A-&GO;$NK1^qZt-v6vCr4tb225JwY2n}7OB1_$ zoW-A7X&;Mc*iAnWPfz|WEs^Eo*CCOOJ)q5aWv0n&O62t?)vY`Dbp@U0H1!iSG;-pmX;(ULAE@kMOh!i&mKJo&F5NSCFMIb_P7+UF&dXOPox zmE}7{$W#;s$;wt{N62ng7U#KERaAD4_`RsF)Ap}!cx3Kh(`sHNSJCJ`eV{x0pa41Xe98m@4{7i z@(|BWf&JG4p6>f^5OGQS!?5hnF9)PA(cD$uidA^B14;fQmINKjnTao|uR`*+X zQ-A%TZs@RxcD8=Ip=b@I8pIrt^C=elP}MWjlmu>X^eu*qB{ynXp zGWY8|>aqUGCXBZ?bH&rC_hf(c^5gKGL|Vf6&Am^rF4N90-K2TTuk)NA*W>AR5dnZ% z$+PfSJTwXc7CX8KVQRRDS8Uib>aX#rS|XU#m5~Ob&9ph7L^0X8IBaRcS!8MRxUL6M)$xXHB;?+E1Qg&u|~Q}jKg)Q zZD{?&^R$f8=Ib(c;pUbe92td44l}f{feJuG>LsxM?5Bchl?or$Z2c7prE({APqqs; zdem+xy}WOka2|5&?c}`b)oDvF#j7{pm#wLioUHt1Rr3ZvOHNWdEN+Yb%KM@wrS?JQ zowv%<=bv?@hT7@Hk)1CK{**nR*>xC=JZLJsQ}W_6o$Q1vFtmtXPdbZ zQGp@vHBjOrQIVxfaGE2bCUePHp=>J~OkD&#C^qo;8}0VxYkA!R)?JTNa=zw9^owXN zk_SG~Ws+q^@fn9D5I5oS$v6v{GC^XKwN3osw8m9W!Lx<3&#pM4TEp0XVA%++znZhP zX5O)Qd|`fms-01i*huj~7bO;^b6<e6<^x8QETv9d%0v5!}iNKSI0%MOwPx!(gZ1 z{my#v+%Q%Rkd((ua^^hbt=urNl?^~=&AW7=j2azuTX&h`0*b|!d+5T>LClrzXwERI z1<=pVOXTh{!-G2jDY74!bMy}=zX+IX0-WjNC}Pb&qQ?BE=c?;m9Le3Qr5m33YO;7W`@VG@0Q$xxZQ_5lA(&`Tj04ITv@X8JUE3~ z;=9gHXj~cikf?Qk9^R;nlbL-3h>`}cn)HRCdwnf+;ekB#i-h<0WB@{;=kfH3OYD^1 zCT!#Lgh0)_PbNWoK+99cOLw&{+-cp*etPZ|^QwP1vm>-ZQ}C0UTm;+wzP4U|_v|xQ z%xkqZ6)vRmj^<^Zg2KpQh0i{d9D*7rp6F? zl)rXj&e?OUgTz$irLz=~urq*3z5@Gn66J+r`v1*0)nn zL#Waf;O5LzK^>28N8+Yj6SN$>U-IB|g}8xVx-gNQq1a2n$q0gQ&X=u)^7|FSBIF!4 zCs^lyllDDqe-O@(x^rw$3X}Xx9gn{LD3Ln%{$Y6k0?n)Y@zFry@rbV}zE$xthIs9~ zWV*$sb8T%k$&0GZldG@a0yF0^FK2fglT> zY#Kt~0Je54c3247=^;*kk$VGVUY?CD&wj%WxGMtieESriHvgc97u+BWG+xgA0+E>> zlBw{<)`*VD;1p^=bcYbnS|OPlp*zO~7)KABS>~GKRH{#oV#cxz2Wo+xr%c4z1Dfo4 zy?^y0!Sk&k&^X5dI3sVrAa|DUATov^7Glvn9*C75cB=43bQ3!bK-3ab+cLarRq7Ec z>aoWI^!3CBf5WOdMembb?}-4V=X9orV#B?x&r5GFad90kUs7BJ?uY=pm#?WW`Ywq! zrSW<3_6aymU$TG3TSia>@WlQwq0=u?sLRwSS=HrB@tYcwE15E>SYmMHQ9N?Wv+}}G zr(c_8N*{^?&&o`^uN&4CG}adU)?8h1ute6{~Sr zA0=;zs~oYH^SGQ$Fj#jVjCmIC>k`E=Zyj??)MmetDE>C#8q@o70U?lq{Q~`>7aIq4 z=B0yjv?y@GBQ+ua^6QVGWA>1TD^jWWaAmwC2jD2dT{4vR&7|Ms#xz7{dFY0@=U*T< z(4k;XqEJy6*iw7r;Lg;8OpHQQH2n=j{)`;I_g=u>HG$V_imu$48+krlFL>3&fRn5A zXFwVFx~@|}hfgL(vh3B4ql?%6E};D&2te}$s)Hyn~0ADE3l_TUddmH#%esB`rk;x^yn z`RP#JB9d7{de)fW%a?@+-<5up&chY3(a7$L5T!Yai(Ze=<32K*B1k&H&AmgSr#B^d zf#lDh9Hou!mt{CfxE7SR5L~qlQR(Sf+Pfu@j@&^Za~^v>cPd{f2KXpAWd7%6GA%BR zycGw^-@L2ghIxM-Um$V4D(C)QDnje}P z65~37)F(FzDW0@j36oxI6VR}3IW;dx`eu2SuhI) zwe}^S%|KiKMbS zsng@{+OB?n+;T?Kpvr$JVE5LGpzJ1Bnp3j|cOPU6%R5)4%P8-+e3E9nzk7KqA}nJ4B}e=*-nV`_NPJeu7|jn^ zw|ui(9o4 zvN(^>H5U~j839A07C(F%l2|9u!WD#NnVvD@UYeHhh?*I<@?Kdp*(NV6(ffM&ZH@Hw zf6}isXx)&Vz42Y7S~2PQ;;tx5SP(YK@NZ8^Ak%EwxiHXI@g}Cm*)Q<>hYhSP!L^6E9GfYqOJ9+XAe;C$d*`a-}%W_9geTq&{vT z>PvwKJmz)c9@qCwLi*{IvKI=rH#MBM{#_Gpdnsd2pli;cXe_~m0@RDgkSRg$A!V zxBB?MZjhz|fCahc&Zf%3O^&_M>`Ciegl4o?FAn zKMxUtuUqu0uLfl;^r3uQrlYj+^Da&b)TsyO_i%xLJKiOpJU4N$*15hZID#kO?N5w$ ztpW#a{Xwqcx~M-%T?5BZc5Qp==v=szk+*coWWBujr%9%pD77iwKN55axR>ivJBPKQ zh^-7saj$z5TBFDsxa~~0?IC)Eh@qeQRD$7Oc3iZOJXpm;$Z2&ZS1@3X)Z)UexHoxy z+tEh{wQe>mH~e&9S|ptD{vGc7Lv{H|VoP#pe$Pe6=G{%tM9{MXHtd_w+ceLV`@Hhp z_`7ad$6vBI=)$7&gu~XC!q%I7<}`o)Q-6~c8vXt61$Xfqr>^TCM6wl%u{<{=)iO!h zdp-i1`rm%hv}Wj0?H2U;;ZL%>d8BrVMLe!+PVI9B@T|+*w3ZUKUoQrwEW6)o<;wGgyWpirbxK`OYr zltOT~Qi{7v$madNz4v#{^|?5=>tg-ZTJwyonR))h_W5*be)orq@b-I_HGHLa!FxIV z`VdPQ9D#XpD-kw@E>s3z{qXWxoHxP~b=52RmrG$rW3x3;! zKkff-aZ|SDvRS-7y;Ib(j3ztP0uOrCyynln9tBePVS1te+pa!4FdBrmur-mLS0~3) z(6eZ|#D5ZC=O-a7B2iS?mbXt`7SkZ)D#(`#7)??FI-^R8BrH(=pNp~!$&25gLs;VF z@^skW@k)TR0@Atj%;6}}ZN&$%KpKUt64t=)G5FapRJ5iDz9X(3U=2=#%Tz%NM@i#; zn(b`#auOYj(I*ml^w+jtAA?45HO?d*^V-QOc2^ERr*Vqnb;-(_QxjjTp+~2)hzXZ@ zKK~ZFruKxG2G*ty-WyL2sZNAc7hO!JvQ)Q0kh5A-w|!F&SA5$xX}ghN>7D0)B8(LCkNBUNzdeCsj{VK zE3p)xq~}_(WcAYX!&stz>4l|W=#2E@zBGmR&2o^`5<$q^we%{WWtlZ(o+@OGUgnQz z$im~6b+K=&8ZA_t(rf0pmUBaye{L-&4l?VZEr)(G8_Bmju`-+ax0_iqTa_XI%4D`% zW&YO5>j!$o5pQTdH{uu(+JL;> zQjs|^2;F+#x~tiG>K3|f9eUt^IFAY42}B&DS}*cLchhjERl--bt*c_K*S(0ew$_^| z9HnHR(GnWF-@1T7;6Pwt7>JNo$PZ>IA4Pmm#OnfPr4UE;Q2(bNg|*TfMsc5$3kn;R zC{Da|p_kgSsu_=8*68{l*$}1(I!^xdr?OYilk`73xukN?{D6$36%L@@R8Qs8YVg`h zcYK!p?2~?V01fVyez|eI&*>G7v*9=Cw*tWdnYQBqo!%PnYg$*6de6OeX-%y+(# zGn#@-7qj*VLOPKkdJn7agt0+WpS?At7?NImTwF=-FG5UWApbl z;@-P+^}gq~3l*o^ygwpDLs^0YPPdWqthidKz{}&!soLQM?8Wr?<@q^|we9y&qiZXG zR0`G(rnzxyTO%@obwD|D(eh}9o!xdK;dyi?+2f{zY7%LtlrG8_y5tHN1*w#7TGJr@ zI%+m!iXI$;OB03ifXzul4^!|BMIXF(_FE-OloVw@N5)NDU*8{N$^q_@-0wvXkb$WK zPpaore}#Pw8tCKcW=d0|Z#{YQaCyKa?YD@sR9d~zLT=iS1Y6{f629H}v|*XXPAW-p zEK@p0{u9WHQ<~H?eMIRwGF?iJIWK)w6{5S{tYWD>HmWX-72;LV(WV~Pej$DONNXjH zdP3hcSoopdv#5+oBbPN5{U>e<8B=CY2Qu``qnI-dBT)-Kr)@Gg&!)37gK1}ta)jf? z9Lk$BM;%K#GUr^GCw!i|bu-s$xPRfKTkxtCGFb3gm`GjlUCX2E_uFiyGiTiW{dOtj z+5FTJ4h6}CEr*fH(6@zCm}OaBQoGXsiER!v{1g8)B5zLXaDQr`|YJ?^J+2Me$sWwYw~>*O9OXyoD73wexmxj&5w>o zvzuillhCbCdlm6>k71|0l`O~kQ!fwWZt<{sj?0HBS4P)&OG!C<8S52{ zZmIi2Is0$U_ZZ#daAdg$Q3Sk99%1Afxrae?ZcMNJS(9^*ytpcvJl%MQb3I>)?lXDW zBFOW+ER}hgPmMJ+@=gs5+?aiI%#-uZ)a@&o&)q^pcsJ&Q4T62KUf4W8y9h4#i$59b zr)RjeJhva0>m{s$SDWQA=Y9lft?vWpe)PIu?{!Z}Kg#v=@wqu^=4D-9oCsyT+DDSG z-d=5gUA(<9?lQ;S;xfz?PmY%WQ;@cMglH6DIwg*Jx(&jQ38N5#fjJG^Z#6OD_ln8! zg{S4H@1d2UC(F?1U2>G~VF>t>RH)XpJW)0#ivMd8Q6BY^dyAS#zOEHANu|!mGw2vO zH8fe2p~3`gB=%WQI(d7SJg3ZvluG0u>Zk0AkIX#y^}GJik`^iQgz)RCDWnax8TRb@ zjU+lo5;IIpD}AdPdE>D|#I$Cp{1r2jwdb^BS*Z$k0?hSlcK1iKhdFG7N(fb) z^mUS_x;`>j*S`?=8Ow16+lx(zslR?VlDiJJmYC>Q^r@jr*pK9*Srgabo*a9x+GQ{E zrcNV-Xe1x^*HRV|j|`{PjV4emBc^H4q!tAyaSaQ0KX0pl!>1;JtW7w1V`&%-p zu?^>(@PNL)b1@SQH~)3-FP}-Ld`S6>P@s&{o3r#nMVB$%Mx*MC$>0haE@$z_b0Rg9 zHONjE*T5R%#l6AW)(l3MFm97!N`thX>Ibi1e43ZTpQ`t<-g7Lvp5Ju+((ucc72}k% z@KAoLF`&`4t|LeJAoJXMU9obhC$QqQ;z#p7)-GsGa&GsiqVbfOJNPt533qx%XN80C zb%LcVB59`E@R9D}G`;5dy<_dp^qnS zR?6OdVrFPi$MgMIjJ?dQ{@mN(q@Ob}QK|mwtL<-nqbb}~d2LU%iFfmM z!`bYVAH=8XT*BGvdSbel%=vr93qw26>#E`C8mkiN-5&k9S#-Bg4OgR!tMTOA($JG! za&CK%&Uf={Lg)4Nd3!V!ISVyDzNBf4`#QtdF{d@PpAQ!l{PuIEuq@V|z$6KIy4>dk z%3^2WMdff_CNH9xi*yc|LvFqKKhHb-deVM+B(e6dvXX1}Dc-WDzLiquQoekn+j7KE zJ-@~q?mu`==lZVE`Jbq$){ysYYc%iCk~A0NaMU7OAzd(1S@|l)xy1|paA6btDqwu( z`dCdScgsB@V3OvicLjUjwt4>YcsI+ps<&8#z4A4rzs0AsdSMqwpc6R1E$G`Y+`H#% zud#S~EB7T-U?X_{={#hZw}nn7K2rInnXL69?&0ELYDCcAg$cibSIT-HIrrC!CK--h z^p|qE-mN1ltws{21|E`OHwp5u9$V*~x?W#Td}9nOPFW24SQ|WXseRS9f4ljEKx!up zVKTMqd)gg(Z_hJ7Xzh9JdA?|QU_LpvS0(gn!VP;`f(zU=7!;fyzCC|M8?qCae*=`c z-F}sSyH=Tx9rq1As1FVKGmNlFqCjlSCF9aJLvgvoI3avMw+4U!V?~4kd?E(Eu;V?` z(D_>lY_Ghft-?LvYkq{mSiVupfA^=$c zQG7&f{|G)+5t;K5Gb-WdU?3hk>AS~m(hPc1s%6uQ6>x=;%G z2rc@U6#9e_`ecfGX4_>m^!tX zdQ+HwjW7*UFpp_5Po*%=jW91!u&ipatf#PSkFe}hupVo%o~N*0kFeq>;2>={K`NYB zfcYW+5{Wh&T`C*nC>tx~eRl2pT&edTkKX5{WEa$C7fmImNX3a!av-%ilv6pLk8)^G za_VSv8l-a4jk0f+b6RUZuupyPYV?5{C6}i*m+yC0bIJ$)l-v>8+%c)#38UP}ln-M@ zxt5+j%o%-{Px+`w`%!7?qoUUjC(0lF(0*K-`nYlQaVzDMrNc+x1fKjFeKJh>bWHo{ z)N793)F(5PJgeF~>#023qdYG$PeYG*lFw6luSa=tlzcA*cvqkB5s&eaQ}I*j@b7x? zl{oXWQVFo@2yh+qF#hQ0rV}G;mCGTR=2tUo<97EMZKnL_n-@U+is~c+Qx(v4Hr~ z1M$){i7#UkjH6s2y#F$~p8m(^;s?|LUIAc${}^3_P$sd1{QsxX#demX;&Hz{f#N?# zmzH&RJRPCPPKo-$qsSOltL?s{rDUX)kP^ju+lq2L=+Kt3|E|*v*@v~XM<<& z8lySXY9$qMJ9|8xV2=!vqf!?P&|Uo?MCLWVT?#6UV1pDca#Zn@wfOFP!7gg$m|6l0 zDXsMCXbQy|rxRBsZD3&*L1QqRuj3lYok;hk2_ZvSI+>saC)K=1gVU`6J&En`Wt4fV zt2Haz{FjU`$l#mF(=pM?{6Dk%squk^1s#k*SW2-jtDS|hh~HN$o~1WScAvp-P6MqD zOq(ZOQk(^sRc1$o6uv*f6{UPMe;QHgELkjn_+o4o|JoGCmDjAh0eW>jhwwN;OwQI% zqGg)J&Y`4ZD*_auSlA>QbMbPUBvL?ykD0-`ul%s>zvSF|X9yj+Cl(IDey zevCP%-AqejdM;ey$L~A}1gqGv6(B6{9k!(TwD0jZ455a%Was@8sD8X;$r{kn4_rgHbMPku>*C(r+@>eD= z*}b)NB~sE2w3H&rx%L%RkuuaPEAzo@aSkw2By=i6iBU=mr~tcxJyht>b;J;fRh8MO zbn3ryvCLiW7?vV`kuXxdT=Nt7?vK>xNo64Le?lw$F0?ZKC$zZ#-=THKzd^s{cPG#h zQWpO=|0ZX}^h`FUj)oB_!*stQeBf=fnDF@N##(0zJ>kZsGH1!}sF-taj2r2Mbi*RpC5= zmy1~Uiz23$plvUDl7<1676Srizs?wqsdl?q|CYG}w}r-#tHoxjLH7~KV60FhHfGpV zFlfPoN$B6u0#~HOM}FG3ZEPZ@Ye)6$9tXpc>{}SQ!|B9Sva(04O=Y-6-#ThebTmy0+NlX6`FnOwi`>$M?6yvs zx}FK%MC!@DK3VHDMiy)$^JF0Oy3Y~U8)Kvn_9fkYG8ekCZ3r`ION=D&wn!rmrsx2p z!P3)E2R;z!{^NkD7BxhiVSnfun6v3F0&zlP$?^E&-Y`O}7%hbZ^d{{YLJ})zDT+@c zYhr}IsfCfk9;}uqlHEkSKpdw`ph1;=$F@&b{PFl)`} z*dUvnA_Fxo{u|uo@FOgVCFU`9S$0+@8R`Vfhh1(K1-8)Mn?%rX>zE;y`3>)bpQ)-A zmq-zw4aJNL_hTS8O{*9`d_6qJoRk%+0v0UhblCmHK6@Mu%JOTnrVNo`oDgk=zKPXvln0)fo? zCll9#$C$>VyTRe-w;Bua5zxe$vGu)Pg!TT#spP;0>tF~C4?T71{t^=&uFB$tzotQJ z;Pgd?uwiAs^rwbfJ%JjHe12<}rVb9wc0N5G^mgKIK4Z5PY)neF$<^bGuofcU`Wu&m zY6v9&tJ~g?mkfkzFdZ2$4BJ+QD81g3y2xm23;Hv(dy_KKHPp-`4aJsNOX*4 zhcdb?_`*kW5mTAlp@tP$>*^I}&kQ}TQggm8eSWnWx_`B4BnL504<-8>f4_ZmM9u@t zjV*)w6}L6vH>aWe30&aA$SV>{810qRc!r$N^s1&H*82er4k_(q- zrB9JntnQBlaMc|MlB=_o7>?p!ZLpJ(@`a!1{dWPd|EB=B0hNF}(E9)BIsd=vmT7-l z|Nqu4#n}`8w{EHYzWl#*OWcQLrCdg$PvD3LbdqSt9 z{6-wEwAXsWyZBe=N1T(UqtEerdrK$-s|4`FX~t6T`=!f}Q-WZwJKfTWcF}Kb<=kBR z^0ZbDwIL224>Hl3PLCwAGo+3l^l-=z*`@i9Zu!8cz>g5m5FLLiT(=y}7TpJre*E3f z)N^>^A~{i^yKFW2dZn)@TzH^v5v`y^2S<^)FZ&=!>A(3QKj6|a>8%LiW}#~M7I!|XW^3z8ty~UlQc0S(P zy+NL9C!QgHd}8~0AN648-*`o8XLu*vl)vYYU9RW6#Pn^vQ3G6U zmX%gqZGElXyV|bm<+_u!QRzi6z~6HO zX+pVS9|+e~dLY)C2O!4bm%}$VJOQD(R}|v`Psm=$M^IyHBLf}PXqc5ltG2;d7Ea>ei_XkW!4Rr z@c8!sGQ(f@>FQr-`*)UxEJHF+L*vPkJ|&UYK_7EqB3NKm>EPH1A{24F*gsg^7q~2w zRolQn+7Xf>rVe@<_5|T?;%ZmULwO!WWJ_NKhbbkX_DTL+77}#0tN}%3rhblTjYSk` z&;dL5(o2ddblfHl4Ef#%hR1XrVOAa+?n55Vw*{V$S0uDwSl z@egTm@tCV&y@L`YfM0zc={`DA8g%hYqm1+DeRI6Mg;xM=-jNXR;o-XfmKJ%gx&s3N zO*{+z7Ur|2B?a9yO881HzLaB7i5c0kY@hIKwW_hu36Y-(x-3`BQ%e zDb41|DVl$||8X$#s*PRR#ahNR{+&ZYwd;ywgYcKx@2MmjU)G-3YVH|jg{#^YDn9NJ zZ6yEmUWd?n2g%yQr^FZ{KtAxfi1m*0r{s#21<;y1?I(PJIZjFGx!i`F=2 zAIuheJvkIz`DE<6>lZq);GV)8c|Lep>8Y1kY=VqKwE?`(Wkn~9b9L@Re5b^$tzW zqlLXMVTF^>Z!|d*?MlCK9u7W4#dp6xd#%+o$s#Zm7_0ICSp0_kFJ%Eh*Y8{-Wbbh{ zUN_5)>>ltUOdaim<(jAJGuvIO78dq3dnZ6S?ek=^_htQ&-nJsksQxBH-B^`S@VCGdlKACw{EQeIlb3VPuVL|RxE_oL?N9uZ8yg2Im<*r0n^#m zhJ*~}7rBYl%0=IBsslYJg`2e^(0kx9>c@Lj4 z1C4#(DftZ_x#WG99$6U7))!nrf|bQ{u=2B>2uaHz$HDyIrL1XOLQ1PP=lC|1_JUoM zhT*Gr*Gd6}>u#vk05yCK;M)ko&WM4d0OD0$DL;OB{Xoy`Z2tOOq3h;XFY76 z4<>N_`l?FP3hs~9jJEd!;^FuSh$qN@!})Q5&@EX)w<_{&d~J3Wz(EW|;*L^-!-S^v z2n>OQ7vyTf?4(&fkE=tgq94#)P!Yh15L4vbnW7&0%+oaCSQG*H8xfWd%r-?HP{%GU zs(*xvnLfeC9zY-JMCclN7)3&*fSWt;clN%X@Nmq)aC9oZ-lBkD+sty#qdhLjz3PBi zO)_vAGqlQSh9CCig8TyG1eOKWPB=gd$gcrF8~`mXCVSdO{)2$}2;&qsNuI;)SxW0n zwHaevN`TX}AIE`1zo`IDQQl!lfFXw5a~V|$)s}n)_~G}Mu8n-ZDvU%}7K3bo| zulLQ*4xF8cgZmPP`)*b7H}ky~nbzU#7u>gc^EoDIRx8lnibvZ)c||NU;*{rycFIm! z)JBR))P^-jwKeG;v)}<^6xaATcK^o8ChC2Y(mIX_O1MF*@*d%Ppl|>!|Bq>9a zg`=Ywu5_qr_9eI`~U+<`}E_7p_?awz}_fQ!&6m0UKyJP?SGMXSh_PZIenp`)LD1F~vTOJIzCM}bZn z*jcM8ULyk!70Ne^s9Vp-C6+4~^Z)@WPgg(Rhw_2X9#ID=RVhJ)FFQmp?xYmb}(JQbvps}_zr8ekJ zx175d!dMq+T$jdQ7oAfV|LVSYLtWB!U3yp@TCzU<6+gZ z3nd#2DH@6c8_Kq+Kjt)iooi6|)=IIM+0E-GpIm9+hk!H*TH`Y@WW;EgPHX=b9IaVaJVfI$^3i-plLqs(-h7duK$FfalU#ghRc$BkMdN9Y z0DA!>*txd*;rM`DQYJVJH5$*)n|caODhQ`}f+n3>Zi7F8m%`d+mhoj%K$-3&-7q4G z11e?|w9}oW$^wL-ASie5RD)5!gc1GXBS9ZfWnzc`gT&=%C}M=52~F}?svQR-Do5cr z0f-r!0Of7OfS^u2SclOK<2ahs15H}K+yU4j87gRB(d!x4?1?;}`T%RczNWGOwEaT2 zBeZ%ba!I=nsH}6_e;rWWV`|5{Y4yz|O{(gSPGn@>A)&@Cw+rWz{*rwmi0OC;Xrmeg zJ}D@LpozgZRPszjh%j(gZo8l+pgannunLg&q#cKD&%yxHnap^X+lzzxewr`_qez!ByLN!7|dZZ^Reii!E}T;_aMFz0G<#h0ovws+l3Fv zZ3lnjmVd99V7^)c0EvXD1^rEc>@aE|dl1ozZ5|XgJi0v8*91UV;`M8G$fmR_0H`nL zFrVg!XAXve%_D%DO8kYP z_IDGegAhL4+xELfst+&dSL;r{>N=Gj8&+59lj91)1Yft~=MUc4~- z+9L!(krxKkl;cnNwlQ1xo3`pVdYhL13zWJhZ?2=9w(;p4qr1_$`y8%-ESb;jqAIA8 z#`x0<>IrYt85-)r-FXbD@po_PJzTfdTj7-Es@DxDg9Z#q0>HTAfQk*@R6lV30zKa; zy`;+TlL5fh$wHAH}$W-(8A@|L+Kbm#is|o6aECYSge4_1@*uwmb~;ikUUjwN^JT$8ES`sEir zEwo{8xDjf$7ACXKu1qaML`_DRqWUcr5$4-0Z4!P(UcN{z{c?`5ZgXg269F_uwuhC- z?3B8qkNF5VGzr5SwisOBl|3s}_>eo8y=1MoUGj;zH2a;(NM3UGX45TM3(rTeQ^9@P zoxX~l&ZIxxq<_;3%9gu#5ELak5(bJRAKi%l{^X%PN-8;VrABQPEt;(_lc^Rw(kh(Y z+kCr6L{2Tl2cFEPp8ZUHFhEVgOG`XgB{y~abjX4`gtH#qM;vjOA3X>?;?6&M z)Oz$}>4*n+#K(FpfI}P$nIDUU9*gB4OSB$KEgj3?j%8U-NfWgnL`7dlkFA*O=L}qk} z`7~DUt41lOR+e`H=2-*~oV#>c(hjOX0jQRVIuxkw3oe)dAiTyP;R1Yji_@>J5HeYa zyDTIOSA2!D0MEO5J8D1-$iaLCAU6vzV{3uEES@erRiFO?2?Xl90}TrBDOBoaZAd!a-)gv4(GW@j-;Tp|Ei$r*Iqy-t;B8A zwPEq+7qRMc*(ZL@7#f+NuZC>=RVXrHH`%*YHKAOxN+1_1p`!_#xY>)Y%nC$9YJcN*mhKYq8Ys9b#>smaH#979Y zGmR0FPH@Bj!6L&5T|etXdtrM>D=5obm$Fhj_|P*ojf3Qf4@li{db|*}ayDj(_fvdc zJ<$9y(5t1P1^s?DxNuh@Z>UT&#hlU!Q(+bk&6aWN&)afI`@Eou0VNgzXTHF&Hxc7E zbif|viYdf}^$C(o&pLOOCq*^|BFW20_!UTIs5|%L1=YG93m_}9k|Ieni{$aS@NSe7 zk4CizzYrfuy1^fHVOE+%@jH^qu@^u3(Gp$-e~1Vl{)8c;h|)IN1Sw6>LVTUno@xTW zgpSpO#&kVj{Pv6OP3*Q10|R%63I*!9!mdk2m|O{ z&HF0(?=~iqZXdp?-vUpb*1t7-LpvJF6~9-qeIf2EZo-+`E|M*ddTEzI`qJ;db#Q}E9}eVZCuH2)hIc6j zcjna4>`~8CsS~`o80LI;-FOer`;C$W7jnqSclI`N^4zuQcrwtf<@${AJE*$~FWN=t zB7LeeCb%CaZL|6c6RZ6G=N|yO!_O~ZyYbw}c8)8*!tKv#SwyLvM58gp+O4SaS$IU4 zGSW%P^mGDu@4L1)srCkp*FD8OO%5Q@b6I%~Iyo80&g<;Bq<^S1xqg4J6xl`}4VhL1ShfxNJ1~)gr$7qX zCo7+v_?P1oxA3!IRYKS@#W2r3ju$m+cz5U?UKt-(6nDFL;@5E(m4YTb3Ch&e;=j`- z{W1EtpIvGLZAs0nW9dqw4HDu~{!!vZ7)t;iPrrtdz;I~1r>+>7x;yH?$uUa${cf7f z{0N&D8n8c3Nmkngpp}Nep}O`NaM9OmKS`>k`a z2PLS3Y--ns!8h2xXLA;Q<`RxZuRR~J7Y4Tt!N?dt$Hm8gO81W}4LEp+*bOjf`lnZE zCy(0bNe_QGx()dGl?0Co)7?IM%o%OEW67)oz!6+j^G9P}S|O-XavyfRF8`Kj%lKvN zt*rj{_wkALH1ab&u|AbwY+YWNUeEg1r-Jz~AbZOM4N5>5D7J&L=&z6QGQPoo>6TOl z(YYp;Kf8bDGckM7Mcw7v4VL_0-EwZt)wlWD^dQ=xX_eE>|9|V2+qQ0j3)f~BJq9hu zC2qmHf#x^=3|g<(+(NO}<^Tf2HqZn2Fw!6kFqdIFv7LJa^Nj^m*|4LN1}N|($dcFq z)JYf86D_!7X(J0_fKOJ%Nbamqx*2wH;2*|`=30?d(sw_#`xaw+W5qB$-NQb47;Tzp zNpF79BRj;OZ_KOuX_Jo7lG*2ErB^m5oq{YUx~iJeUC zJ&gOFVD7@8gCf@zCVA*M`#fkv3HNd|>f=%2V;4)Sx&nrx2d8D7T29)Ypox!W-okYs zw)FA?CaRRGziMH(^yeDJfAUmU==^@AeH}2~W_S8E&Xm-$QDUmR$NOt`v$HkwdUAB} z^jn&Xi=B1g(<`vy$0RP4rSc zf8B}NB$We#?8gVcNdFGq$?QnFctRatSD zc|IWpyf3hu&PrF{0u+<3KU8aoL#0 zHmhq{%E&glQ#-qY97|9Kcaz-xT-nDQ)rn)$yf^ZEBuIWHq`(uTpcGO_ z4JmAb#ECc~MT3xHiAeEWq{LUGWK-wLeW2eV5v4`snh}X~P#nU&RG2MHIje#r;LeN7 zAqKFFWJT1*zm+Xc1X)Bj;E^H~6#O5eXb$fEk_9ju0x=AYGB-%UfN-t`F3LL=VZJjs z9BA4W-cx{Q%2!C^7v&tT_%b)v$S=~LAJ4Q-pL`rQV&YeEhvgtUeah>K`5iK-n1-jSrz zhLPGY74@m}$d|!d7>M?Aq?#XnP8YS7A4D3a@_GcMZ3r=BfIcxCP&3RD@&ilzLA1o^ z>y4uH{34UY0A=X|v7ZJE>Qp%om7#r+y6Lgj;}NQU5Gfcl`*Ng#Aq1ft+h`J|rt%Af z0;=ZMBwE}Ry34g8T^bN?@Lz} z@iLeJt){g>7=05XvK&bc9r*BMVDKli`oZ(I6Y74BD66i_?KI{r^E<|w7^JBAQ8&3qD(l2#_)Hgy-xe`) zLMUZ8tPEp@K2_biiQ%^BR@96IX%5wYeeV1ce0K9YwjYf7`Jsmd%~BH1D%{=8J+!Je zgr|y{&jppmju>QV#i9E1@ScCug+5x2OqHWKo@3VVcoztvDOn&Hk^ILn&U>gv95!oPI|K$3%YqFiG?&#MZ3KQVv(+iFiQB# zw27$YzkNve5!2k4+I@Q3^syiHluhA83NIm1)e}y?CloEgrWcVP#v!eRGaKJ^19u0l zZ;VazNS?r^4dBxeT9ay;lXCRX`jWY)8Omj16S~zj-fv#MSu;$|pms0UHFb|OY8%X8 z9spSY+@7eK7DR?E>zPkLESO_I?C9ZMVPpE3r^EHg-MXU4s|cgYP`xFpre&zmHlV_( zKKtvwx0;JA9eAbyva}P$w4d5JqY$u|k~$n}iY88?hC(q>%zBFh>9Kpv&`6S{n{kbL zfYPI~C_M{Qx0q5q2PFP4k@p0Zw^>)u65Nqn3u<&&J#I0S`0uY?sKgd~V^PReV`I$!!ejZOonA3$E$`EC6Pz z*OW83qoB*r%og)g`;>Z?HQ-?>HYm@ZbLuUoQOvd*UD;naR|xcDqffu6YEE09C|WY> z2ind76zu~`l#+I0jV{3PzsE&3Vm)0=-BP_arT@iLJOMC%N$etKo+a0b7LH+wX z1XK#mgg)@zx?#dZz0^oQQ+jtc)#ncQWRvhtcS>X$z^7jLenH(TU70tjKRuz>-f>mb zbvhPmw7b~F`fTn6&okdgG`Hc+eNsdoZk8Wesm}3FV)=|*S zXqTlhzs)e%WIHU%=wR=Tkp=a-f(_j9$?evB?CQE!!pV{-)KOQ9hoAyQGeWmD&M1)! zpqjAlsOj?yy9Dds;3t?czgq%J+XS|MuKW6ZeP~tMJX5pV*>2cszNx#4k9J|kLCoSd zj<{x`QN2%~*ZS-4K~bgg5NhY1Ww5~1fyRNW#L)QNjG-z;M2B7+IsMQ(n<+s=&#NYn zo5>Zxf}*##b_q*t;7`5CUE}^cv^az;avmki`&n-N`LONC(V3D#I<)*>H_6h0QJGra zgfl&Q;q3GfySIP{>DJvYXxuiuJ4o~_Zn@8y?Yx4|*F@#tPH>!We(dQ-L)F@CTnzJ& z9@^fL)7_Ll_C;QW^Vj}Ix8SH3=KdA^%ehvsrbwQg+YHl8+B*~Fn54fuSq{C3jHne? zN4YOnuSMG$z4kHmP@bI$+7nryg|YyNrunjyv$HrJr}|jVfYV8$7YPvup;G zyj%?oO|mBaPQECYMcNKrhP9bLBXCkpPK-J~(e9rBp|8RU0xazv977+omw_{Gr(AE{ zqpE$)^}Qcic+dP+lOe+_+?+9ga*q3XiS3ShWghEPayNQVy7Oz3d%{R9h;y)D1^^4# zBB;0+%s{Vdt^h#q;6YW~Ra$5CzIO?g>ofR`|B?BRdaE8hHj2OwCMx5k41>`b)VxVu zaVjU?Ot$LNfJhTd)Z5ti8b+g`kTK=p9HRtdCO3A!i1B_s>6ZgM+WMo+s?r<1`1%HU zEUISh=NWcNV819MSl-}LP}X~>Vbd{D8{VzM?fURw%xlzUDRelLFbNEO!a;v?&9z07 zB;MdeV^d`r#UsTCr~c}Y5?^6}q;9z+K)z+6Oz_%#bdi#tLL8xTBUnh>(<;;;@kj^{ znO>m*dDTpr_Rv~Ror1T`0z7tqwD@je^}Coh38~4KbR(~4uQj{%8XPP}s$(BbS6TI@ zK7DoeWcH`i)aNw?qE9TQ8hl#~2W}Ldp-`{5%X5XP=vxy}dp&(=9n&!1Z9!trToUdH4Z zl7yhsnKTkc0Zj0@v+1-}J^mH#SQWZwkxMW3~d}^YxZ8QNZ%qbYk@hVlH zTM|(qSkz{}DlescHlzS%JiU|hO!zS^XgE!u66FTd24{7dLu$F_~dq=hlEnA^vItF)rWf{045Nw33;M*GYZ zUUPo?`r?%}!v3y2$HL7Pp7;z6SAbr+nMJIPNutU1$FJ^boLVr1o9?^qIV6C)Bd1Ha z({6mjdhZhE9x)Kg;fT_D{nLn4*K3-Sk9)ifa${L=4Hh z^h3k;Gq{!Dr>!U!- zz*u*csEGv}lSM5IHBIvOTI0YUhL?`(9XOC^kAj;v4}R7pnAHEUXS@2d>J!PB$NU2F z+h>naVYS5qT2y4rW3L}d|GPo&-d`@~=&Q@xtx$P6^U0^3rz@*B(f#zfrs{GR#JZ*Y z<)3?oS>%i_+72`ikDuy(=7<%7B8YWMCxu+Xtay?1b$7VC2(fO-tMKG{{Q1fo|jilF)#lhP5 zY+@qYo}&O2-4weB*n6{Y`O@)RgzH^l`2Zf12|TEKPdLla1~hLpfTF z6-%vthd-7A>bhVM{bIUe=b0z6b(D=aT<+_X>js{cu;z)33fPypfEzZ4n`^&~=PAXo z>$KEav;H=8;5d12)A3S@O!e|5;EhxjGe-s{v}2XXrS-FjR7^5U$R@FdmU#m z8uOFtquW{*; zlA7ej$W~qo**kY+@@&M4&N^+xNp9ik$@|PVrjcGpg)sk1D}=r=bYyDWnZSD*FLmko zcbv<4tw7h5{CgElybnJG^DzE{8J9Mon2ycZ#omF7pX2BBg3_346Xf~?Ol?d^*Cxif z2w09HvC|`^6yTbV(RePwxNAn%G51i9&Q)~0 z@%puu{{uVuwdM_7(-SBmirqfVM$?Go4EIc1PWTd&E7mf7n2HQOcF2hz;3@rCGa|kt zV4y>NKAsObdaxjW#da2kw4dQ5p1UE6C{6057^Hl>VR!;^ecOxM{;gr}yEhQsfG;`W zZZpI3$HYNbl8cMK-x~;RnAZh=q2BS;1ZsRxn2gkQ7DKlwQ-`K|15OeW>pFXS1X-t&pI-6>2E7WsEm zJ~Ht!wF;$dLA=~rdu_H^=O5sw;UVa>s(j|f{ogZx*xxbc5@dueC)d)7x#iuxHc zVy@N1C#iI$a{Sc<9n+MuzESrwXTh(l@^5q=_{`Lh>*%8iLIq+Cp^bO-^L7*MYw?%U z4pcg_k%DL2Md{D|b>%606K2$E1i3TWOxgxm>&ETA%6lb#(YsF}R!(#4g{$gJi1xh? z#B+Gif9LS9OHT@3&^Y?qI}s+vIq^eA=d29GgM7y?81hPNV-|H1Ke;(}2K`-`W4{{2 zcg5n?-kj0|uH$EA;c}T`m-!!dw30-ie@Q}FkqnVP`fuv?cl~4La7WW0Qh#J_5S_5v zB$)K58V1$=a5GIEO8TQ47Cx}?>K-Q1Z)7@wG@JiE&D1A(Z`z9WG&k#M{t>A&TKY^z zkgTxg1O;`-T{oOq+IE)+S^woc39hnCyQhu`=?LK$hu zaY&QYq!gtHJKKgtJ3WaN?fq!8o!<-NbHDA1MQfXX3^$8K0jp0 z6Un?mrm_!|?Hy7t=q0|#`Ok~<}2hip(D4qX=GUoL(_d(N zdhC-FIw&X@t{e_ZP62wL#Mo*=NpJL$NC_1nO;Nz|s|}$3COK&YZU&9Bg^C*)^RVs# z%WD`RI&3Zv$vtQD){8!hCzYDo34tofYCfn^m)SzJ@RO{H4AlqDk~0?gKB?pC#5e)v zw!iU3@m?A9$z@L@hQEyYAJ^tlmpiFx%}-_>*Olm$JDUy9&$b-bSH+dPKGj;7C(Iu= zG>w)&e>uFce0JQ}MP1<@skOL%<8RY|PK9Us@Zy%#-)3A~h4*`{r5_f5TkxY5zKz36 zyZ(P$SE(!g`n8r1vi`Ph>s0#B4KE+J{B7Ths|@_6wQ@H9x8r2AGWhTC%GKH5PNf+n zkXaEx3J(LwH|6+V)nGH&@m-KRLSf{J;qVUdeOGA;9-!s}?s9*fm*1c2pF zpjMQuCqS6B2Lrm=3sX6?11y+71@9?IZ&$}Ks^R+)-__>G4#Z?*M-j;2y;yKEc?320 zO+$f!M7op&JXM&Eh>b{c{RKUjaVCcja7jKn(1bY8aoh1Zl*ZG!F3d5LFr4#YKknPl zGF4pR4H?}-BuX0=}0OUw2;i?%o6!z`|B8V6u{s zn|OCXm_{fpz_EwTnAg1tR+pnv0=(Ix|F^z2C(A>v^o^RWG=>M@w?+ zv-PaE1stTdL>^U-ipgzf)}DPUUfa)Kal90c})YSj zC$C-4MpF}UrmuD{FN_+f=Bcj8d5R21@O+$V+Y(+m9X4q9TKdcWEwJwaE)tey&i{3^ zU=d)(ZjkU2jtK6ep;I|iau05JxJ5dl_JAr@Z-;?-h^|7JAWv};A#$f^(rj1l=$!U< z=ykj;y{>1}T9aoH(}@wDB?BqsTj9^l>{cT=ya|1=5d%pUi2AKQ{ zTW|ElbKYut>PkR{FhE2{k&Fd-;-cMM<|_l5V$Xim!U|1e}ILllfx`}qv5e< zWRQ?K27en}s1_(Ad86-T0Np!?NwpN-_Rjd6_dmLhfRm~Lh+EdC4H*7C9wkl6 zn0&@R>3!LMLKhM2+(@U<6!wBkvY*sZ)RyXRo~SDB=|g62yitVa2H+bf6_|%+oF4Vl z%t6Wwb%{_Sdb4xlMG3%|ZJ@X%B0}*zAa}uQgp()Fnj)+wA|xd2&Z_PO*efh>lHn6! znj8Knwzk*8DB(Ps9DYw^Ut&JK!)W$JvN&N)-ba`7y2zTxcyoB?@Hkvf1XjZN$H|_t z^TLhoK{^@H1SELQ!Peb790UjkU-PV)2)8MTOc2L9e!BNdN&5GvXmBFz97pNr&f~^> z3%qq3zahK2p=f*(IIA94VIHOPiF+UTYD&l}%;Pa;`{l%a*sdY~Y#aPyHg1JE{t_8g zd+olVhwLRS_#OsUv`417?tk?crcpv^ItQa6@$w{#d9RB3?Swf{dtPQ9Rq7POlgS`| z0{aDkr6)$y9VZxsYQmtg6ZDRb2d?)CWcCC<6xczaZz~pr617zbaFDov=}vp%WZMl@ zzG}b_su&AwZ8!B3!6`5>k0$<;GRQ*^f`06vdS89eOJq(IGp>Oq6mlmMgoP9 zfMFw=A>&lC{6HcY|FI@htP$Q(r&-Pra?@AvHww6l&Z6O>$%eDz?`L;0I2veVf$aG@ z9=b5hi4xU#fpYYSu>&K~Vq4}@is~apucuuzh9$uHbC_b{c-e;r8HN24kq$`|Utk6( z&AvR~p)q}4(R!oJparqMkAT}hgT9$a`MA`^-#c@%>41ZOyaP) z>}~V`N~B>Hb}K#MqF30m`WlGWK`&2qNe!_1O_*1aJE`amSw5v^Ef0?cBbln9)r5bc znSE)V==MYe6mZL+MwH>P!Sr?4S;;4oLyYs}2|4t7h1YWtzC6TGNTP26X{hLWHw<|r zh9FdAZMbbotsW9!G|1<;?hgbj@<*_Tf6r@f%%h^nH_F0LP{dShdtH+%$*+z! zUiTzlWBTkEn?+y>moYG-G5}PQI70LRdg?+X;ij=49jW(8qD`ZyyOW?o;pmBsWaqcn z*8rX5qK$SS=&A!NIc@cg()d@lH8+x>7Rg~Pr3DJWrY_iH1G<*?Op9axVYTQt@-X zV)v|K??&Z;ROOLH<*|R|Nmk`qOXbCU<<(gwfTfC5x(Z}jMHWy6WqCT)R7JH=MRQ&S zXQ`%>u4W*<#sSsLZ>n#!RYq%|Icmis8-_-E6)(9-r2%gsnvDAu4 z*NR%!iW35AC5iF7)>@eb;ty3wmO4f0I%Uf`)qpznH+7n=b=nJcy61KJEcJ%c^~RR< zrU6V-e)Sdsl@D9%ZTKs#1K{53aH2qL_y#w+)u8I$pcV?C*=u+~Xcx#P|1Gw)$2$8T#!MpnG z>0UGI9>*|0{GURsYS^>;uR`RfZPU}}9A0Zo7KS4MK&d@4)v5=?(-r>^BEUf+w3+OG z5n{XI{~|uEUqf5$bakOv_f#Eyl$!0HiU4` zt+o;}4-!q{pgN+N@IQm)w%zTVAO0<++bZ*FgIRxeAGXqwX@ikMaIh_yj0z%#^a0!c zn_j;I=z-fo<=o+Sgu02t?8aq4Zf&rn6&#M}baszs66ywM`*2tF+`Z_zUDo}Sl}*aM zS3?{A#S$(x@=30({SRXU8Nm+Zvj+>*Z`K7s5h+vEtcc0*v7z(}tvC^N8SC=@Ug2#r9r42_J8mBGmYBVqv1+jAH~k27b>vg*VAjZhZT0XAR7h!hfRhJf!XG0G1f9 zy%pO0@tmWMl_ff0K#z?rGI4U)4(jhZQd|o6N0os0W{x>#5tlu2I|^FmuT-p`Pe?Z_ zxxsNPsu6&4X=}hU>RFnuSpsqv;?ZJEg(J-;t1g7-BH(0kxUSNcd6w}9ZB0OuFTi}V zNTeW?del~7^ttRb#2vb+&Eh#a_hz*7p4-?<*(p&SKyV_>wZthQSLmItRx2tH-t}?Z z0)O8{Qv^;wb$N|ihS!P8nE6U6*wGUjme$l($x|U6< z825#OqmN8s*c||ZQjNL=!kw+*1%YINd7~(U<#~@~c-0(OVP*buz)1j(k%8l5Cyam1 z|1KVY)8I@2z^ok7Q0nq~y3=ID*Uom(Kd`6BYEfTlc<^outu6FchhDYJS8n~b2_3jh z#l~#;oSZv}ZZOHL-3W{XNaqISo@mm!`pTHQe50Zp=m9O(+RPkALpe%cn31^ zGlTt6R`9k``Kaxhy^uRem6qU)AiSFeZ<@zOzPCUQxK^6`)iG${TReRw>oB|WPU+aZ zlu!e~9UQ3-BnObFBEC88Y{l^d`7ZZ4VVvXL@1GXYXO## zg=+%7I#>d-v`Jskh_S;CIQ0(T9fyH=hrvPL=En}jkdqO%0SRU0K^3^_k(ujyI50q0)z?v|G~_8tmluOO@AQD z%cc20F8J!l=l8dj6+#FA$l#77 zr4-#mg6NIi706h;_Y|O9sqTst{B?VZRQIRh6~R(RxKGqd3?9nApCo4XnPaG7!LC85aD7u zAJ-6F<=rIG8ZB;ep>55uE}5Z`_N-LRQLYrl6j708hWotY5;2EwZ%em%jG-IK4#p~% z1C1&aV!ozm5|Hh^!V`+rvPXg)?B#bR#WC8Vbz0wsy!&(_Q$-78&Z}!Q4DYC<>KW;< zF{+vvnbaB!x5j#pnLhQI88Bh`Tt9xRICbAd^I4tATnFlNy{;*S@tVnf7ug2dmf%;Y||em(D%QfzAJ-ak{lr1SL8Yx74ipN0|NZ}pnX zR^QWn=P`<#Ov`FB)J!%(1TjhLhyby<6+8OZO)KciKneTkPHQm--$*wCVj7^%uO-UP7i+mX=l9Be#94k1opy+OJ{qQx z`Cj(>>ZmwI<0>29F?F2n8T*%-&BSd#F4cL)#Vp`pC}->RC_HDkaU&(9V$Q-cWX|kZ zHs2)Y`4)eJ*~{`*j={etRRn$3x3u~L_xdz`FMZ8W>#y<}Q(1ZQyTpyKe_GfqNI0G0 zcy#f*`tE!7+4`N4H@_#C>`F7AT18?m8ooa+;_qt;%vu*Xi~ z>3*h-&gF6(TxaUzjNfy209mgf(z_BoJiIvb*Qc)ab?3YyK5z}dH#my*??fe`ExlGq z-b8e|yb|%%^0MWrotC@2l@tIAe9IehZIGL%5-sv3^N>zWNoum}wI;(G;q+I^o3}*# z6dkfp1qgq&^X*EV*aCTYULEW7g>xI*Eo^aPG{*Fw(B-tcI9$FP957Tgimr3KMfa4v z{^2Bj))r`4PVdY8w?UOJJ4ZGi*!9UV_u(>is2pXlM~|X^h&b)Lex*(QWW zdiP6)?$mc(zjecP$&Dv=?W+35$j(%pYiTWC3$t(T-#1Z=uIx;!)MA~UVR+;X*}4lwWKF|Cey z?CQXFZcZ3bHLXc0CXS&5JREsqTKi_x^(hlKsbiRFU4D6=lgc^ORI+&e0E$f1)N+2h zK)k+6%+2LdtHqbB*A0dBzg#^67N(C)8$18Fxm#OWO>OzswKA5wr)w>)-C$}O%n^K% zz+(M_bFO7Z_U=oi9jgfuiMk=`-_G5o^LYRC`njOz{`Cu1$FJww@k_e_{iVx?oJws2 zh=Gx2Abr2le`8iJxBm7pzN-oo)3!am zVcx@R>K@5)VNHpVtm}1G5VN|lXNm;&-P`Jmb#UEqb}#G`e_b8-Qf7mF+`M0sMkF?b zYJ+o%a58XDw@{-I-B=f%+|j1 zDR&EUvHE5)*Sh6H9KLh0g;?T0$wA2xRdjSh1w!|PeHE{e;jM|Qw8;~LT<*wBN>>1% zmmkn3i#io3L`r6mBwqi=5XHFN#U-zRqA}G^8srK1QuYeXZl#3Q{(6qD2@Msjs-olD z?pY)d%)9y3ZIgltEFATIz1FdLF&>p5k{0z(jy%hI@5>Y!Xz!eKe@b@8$e?LuG*E)Q z@U%!ZnR_&T;eu8b2f0TJo0WM{jzBs0S($=s>9o!If>lu6?VgRC@6CFW29$m;xJiWk zVilYK9x<%4-@$fGpYjDgqV=|@TX4R861j=*KV9${N?>_Au98W+^0ss}njf*}Q?eQ7 zU8@8P@!J@Xux*oWBwPDWSsR7s8}H^bRJ5wh126FFBYfJg#3{`XJOHwZ_KcBx&}+*3(c1db)Cssx{L1-2OyVlM)SU2{ z3xW2Zsa-}?M9S7L(1dE^7dYwXly2FCLNb{{=_}2{Yp6Ld868QFAt;jDv3ul(w)vc0 zkJ{CG^MVXyx)Jhzz5ME-kulRfhr{1`VNZIZJXqHLWHO(DB^5Bo^x>GPCbSb!_XIF9 zB{TM>Go(xI*KkZwv#sPJ^z}BlET~q^b0JL}x5yrO$ z4ufvM$#1NJgb`p0QLKcYtU(6QFQv=G54=M>9)2GAU+TNs719LwRTw5A8Md|{pS=?$ zA%w;-D-3xxGcrf1Y)hdJk;3lH4Bh{U`+JoL5baZe&H%kQr`||tRdHYORyXi!sP&lSu z8mrj_#<~NnyTTi%TG34?C8(5hD@r~O)P4@!ypMHfRkOC0O#jrRhYQy(0eN3QWbkb& z8PX0TYP8c0q*cvYQng;~dhH@_U7{XU zG>|6=O5Z?whIMjIgUuJQq_}VnAuP(MbzmACH=UTbGoXf-#Pefcr^Ysm_LsY2Ur&dp zw@LXps$rZSr2SN%i`6ECeAUiV*D)|34e@Is(%;u9RCM~4BJD7}aQSPv*Ohj(HSlW56FZfiqpzwXFFw1qjC3>p=6E@gNk<%byx zQqmyA7U~>0%1um#bIMMJ?Dc;DYQ|K_CJlg6MA6YK10lG!2tO%4lOZ#wmIz#vLY~(9 z)|Qlu{s^M}9q0)eXp@LDvPM9q;;`&0&|ZFQgMi*1gQCh37PT=Rk|#%Uw>7$M#D#La ze|z#C^^~z}JM|@mSGIY)s8yi7NAo8+R|f7irBN{hMig%dqly}*8s%q{l)Y=J!IqSV z`5fUy{Hu(HWDGNj4tcm}1b7)uj2N_k9Sf-%iO36!4jUT#8Rev7LiE4=yeJF(j{VXZ zqd$Y_y-{GelgihMwB8Tu8G$b@=R)u(c|>?!nsKUj_expsEXeYMN#|>A-83$> zh#1l^Kgn~-C~;gk&^%nLUYGn*D&iJi@B$d7Zv|JuvdLmwWU)cqmg!o6_Q&HLvY=`s z3*A41M7`Z8gH4+;tT$PpgfE9>FpTYv$ox zchpQF`De_KI3DHjM;lkC5KZ4=FV;p)F4ZYLb6Pvw?24Un(`b8)ECkQ_e>NCQ>_iI< zd2f>cELU7FA6Txp=2u>dp9VT(42(uwQ+8|&a%3Dp;|)vAl={ZQRx17sbMiAY%svZm z6Y=-7yOqNM7jA6^OL(JAwMxdQWJb;YdL8n5i81eG#xC3=@7cz@8X6Zy%fTZGd5aG8 z_P6Bht<~2#XB#2|+AZ?Pi3(VV#sMn1G_5n>$A%^-7h8g^Mk`!&_yp~XJJq|;RBb7P67a37P*Oh!&iIW7 z6&vij#9!2!Y>GXsvnb@2}E*`06yOzjm7zjk%lAGLF?pA89Yu?voRtcpD} zUU%Ew0s%-(b`Y8wj)58;s`;SHiUkT#TXJmme7q zWe7q^!_?At8teNWhxxVsEdEhZ=UjG$%-Wom>6m*I`*?=UBnB$kXBl3uGAKS9j^0zt z)_PEMtl1PcS#Baj6FU-ua4tOA#Qb`eT4%F-%XQPJP4O~PuPdBkEv)0pC^1J1?`rXE ztL4L$saNY3Yfi`GrL8oiTUeJ7A?zeLtoErT4Efwq=m2}72&UBUX%BAya1P1vempvbc~5Uv!eBibBUzuj7^j3X ze@#yIa!*wS8+;x{xLE=aaPOfE38%VwAi;aU_174XfNlIlN|!h@_bIg07)PzIDT7Bv zsA5q8;T*`p=Y{5U8Csu%pBW0FDVf7CDIPFo4K5VPXux{2wES@HG!0=dFOYnc%tAPi z#L9LHi(7JdvUB&+;N~^jB{^tGAZe?sn_iHcvmg|x<_?A&IFC-)2Z4m)3X9jG%w9~Z zn1@n#VNwdcwII7LGbCg}L!2{hqC)7`T+pw%ZPa+cyCq-l`h6PNhw9W8QO`&Ach#Az zv`;=g&nr2UPS`RNLVvoHa&A1g>m`pi3#G#^22ZcTCm=Ntcl6}ijiZ9k6jYmy4K%wP)l@%l5p3>bR+)5YgkN3X3Zp>xI^ra|!sdMt`Xc{gh# zu-lNCyn%r9`zFSOi(1nwr3U5C#jQDJ3k53rVJC{|4i|e20emWcQSoRJ_O;Q{R~kW> zVhGfl|LPL6ugRpy2O_w^!`*Q`SW3$2b#CGHP|B7qtDnqC1)t+-)Uj6GNPALd#%pr^ ze-grgQB3L#P1{}EnrZAW54g=yPsZ~k^aQo5IC)g*m^hz&^g%e`K-_R-`3>(+#!*UK zH&o7GMKhHwJ(@)Yl#1cSR{b^tsQM>*5V(|F`Jbp#-5SN2AHmz6FwgkI2f;6%tC z&6LZt^)L^`Y%N506H!efsL(8Krl0nzdB5|0nm1Sl$w}gr@ci`blGU4MEBATmwb7xJ zP(fis2SRK+ob+1#FA@yf>$1U|LQnMGN~hDjTbq*jow)n*1?UN# zMBw` z%%tu6K?2RW?I%n5JI7qnNc>MO9M@$DCPs?kic3}g%sfR;zL`T*PyTnw6wK@9QQ?3Xml-$xMIoo!K6+R7npD4^` za}1+0{*I25r36ctDX#B*{1Hid>j92~z2Na~QTyyEtj(7;%efModuP9w!OV64GeYIo zEIol6^#Q4LgmEx;y!^z7h8}t8qS18D+wxhe0*SI0-Y)_2w^&kDl$-*lWi3%eYzW_c&3@Ay`V(EGa0;<8u2_tEX?N|Pk9vxF{ETB@q$q{j#2B#CrK zf01nQiwUdDFNqE5yvVT|t^{R|r=)u7J{cbwp4@d&Ncj1lZ~6}GOfNs~Z%Tp~x->Xr zmwau#)wr+w%&wXAw8B|VBf%t5_|gjbn~!qBKNp$BF65PCFHqtvPbk9?*F9q6^uM(H z;fh7Bx5XyP{bf$QJYJ}XTRz$R<|b&dluS3Jm`*=Xal%1!&RZ04dcxj`;(-T`I3Qxr zBR8my6ZD9AQ_>H!fj4|xg9jj_m#Cy|RboRrYcEWRBL{T8ADN@$KqHh5q`6u{;NW4l zKk|B6jyYhjzf=SPGci_#Gmqk?L9Pg|)y2cJYA824;%*=QOJyv!_iY{p3>>9>H`PuK zgVTKCd3`_{PJcZxah*Dyl#w2sT<^#R3X=2ARP=X96rym9UC1I+P<;GWoKE=#@B>O@ zk0UJ?kcbKRVRAud*mwWkg!?LR76=s2S|o{;C%|*5DH|1Dt&KTuDCP4K8`6eEAPy@1 zOm=1`fp${y1SRzkb54C~Vx+yfJEbEFKZI>df(+6m2fTW_VW87VL`fE>!d4PY+w@*? zMr$7OSXgw;nl2EGSZ8Z>f=kZo#*=%%`=OH@R9Bd+1-|v>x>H#5_HTrA%p}LA3Vi#{ zcf>5{nka0NaId9^iU}B{D4%>kClqaXR~}$|z(A&{*AaWSVP{j$^T|-O#ZdvXiH>nr zHPpdzSi^JTGerq1jyEG#w*WzM+llnHtnHd^J$E8=*xwp68GE1}A|B}!PR+H7WI7U1 zC*4jZryH>g0qsPt`~5J=6W7ZGrbL_MK7JWHCZ*p6)Xn>|GC>)Co{4s?Qk2<+QFduaK|cVf^@}NQ z94W)*Q;hsmIZUNWSWakm3t{oVPERpnbk^B!*cV1V=yX}y1 z@iBfTJU;pl?oF?${jjP8BmIJsc~_9oe*vWYl1#yM#&uIaWmV2lEFnF}L`41$ z;LSTytuSSd=H%}6FE=y3D(!a)6v+1xxFLjl@{qLs`WNFb`{XO1-YE7e$}|Lv zaHs%<37o;>iE!g)NONL#7&_d!c{ei5?vACz5o_T z;Q|Lykw8SWpt}4x_-&oW#x8P1mMCW-2cHK+xh7@ipD#h9zmfvrh^OkGNF={AEV^=nhqOZS9DwF*?1C4 z&AjZ$I+a8s8p>sPww?J-P3MQ-TIGaqd!br&t|IP>&u?%>{u+E%{GnISG*kE zu{l4R>!N9>iq!dO&vK6cPjP#c80tR%f{Smcd$04$+46iIKi1IDIQr{(!1=-|O=DBP z&aUU1^TlmlVhd$-*SGb2X)nI9?VHYT|Aq7Ald;B*zoWl{&(Bu?u%<4E?jD-uVil^_ z)WbBk7qOxOv|LqCf+7KEIDm|0@I>{h8tQW`Y#o~K_xY|pRTlSGxHO^qm%Q@W0hU#9 zljhFp>O6|t!#J7)aeD|}Mf(K%)r$AVxFlHs?KGAZ$@)l2llY{bK5SrdO<#UUa9hF0 zkHP*cgtqxJ`S(@e#orBcNC5tJ0c?x=D>YGW--Gmcmh*r8MzE#-GAhXZu>@#Kf3sDk zHy8R9Z1MF(E+FvF+kBgk-O}Gpfqu`*R5j1hwIDiDfQt#oi~-6>WS--s&&A z&J%cq`}+y`t(|Lgtw>J2q@jC`H(VYCEfAwK=mBfa3bO&3pMT-qmPPD;aIL_SuDa-x zWkiDEx>B&vnRwilQmmNgb zXhHy1amS6&&$7Hv6DYIJzFxI<^Z6kS8>)?3al_zAI@^Llpa)aH`g_M71=dI*PsTh- z!DAYEeGgYfj}^O{(JzAU%c^00cXjhhoUgUte}r z_{l2G$RxFpkmq$LwwZL1o@5TW6Z9z@<3LO&=ij^t1x)8d4s1if`W~PGHm+~1xKMMc z9x87HZ)Sz=-g|1=ndfx#4Ulp$m;z$qDEYVU=`^DFmb+jF{s9rQY?}27H{P zet7`pVhX83o4%QZ4ei0~415heNI*i!%bGi+9(OX=qk$v=_WhoL>$mmsC<5-@Y#!ww zBsl{f27+JPU*k>WypviJ4g188z8?5P>;++@3$=4KOFa#L-jtu}X6}%NqsONn-9YMS>DVzUh15 zNM5=gK;EEVt11B`Qs{`!=^xzjV_*v6j7$UNr7^x2g(5wmoPM+^V!J*5zR8J*lb5^d z07H#5f^8Z|DBUMY%;Hd7&e-Fe7d{9{qf>heJXaIx{y+Uh~fgajw;&AM#+PPQyL3)bxmu%Xk*WUrKHxPeC zja2U12o)o^7DHH=1)xjivCM2Ex zg{M#d&bQ)dhW9dEg)~1h)3qAYe{^|n4T^xzU?s_P&zVAqJh;ytwsI&%(~^;|28ch6 zU;6+9A#<+=We$xpA0;KYi3Pv?kU?)24z%NDAigIb<&!6g^yqsakMd}x@~gkV<~Te- z8%ga&*M6N!qZ9$4T50sB=omycn<4D<0UXYkZ@4eT5GG5K6*Ts$m}qPk;jp(%sWZ=V zRGVQ85CZ~^Mg53Oq|m2I5iklUI7DP|Mcx5*X;eUEbr_T`UZHHw;F3j3GR7Xn?)l3e zMZE%JH%`w>cV%I3dT&BjP;!$Wn9mcODO30%?=tb3{G9K9@%bvk&?3LfOGeFO)RP0;MQlh@;Y{TSXk z%!^!#WN7urtq#6>-r{F}mUmYJ&@;tG{+YEa4DN1^Lf_V6P}4GRjOMclwcv1eyY72_ z2D@~I??FD8`c;Z1R=z&tkG|tsVlSP0t9a!Url|B0B~j@{aUV8a^_5!(gwky=_Gl9I zG%c=1M1s!=RWLt9HviL70z8O6Oo1rRAjiRkS;q>v?J`XZ1!B6plg-oI-HpehPa?mhzzIxjMj+Pyc`FsiS*QZjJA5 zm(sk*5+nA`(-pxWxX9+7VTGjenZB`F@pa8`a5G2hU6rPTu1sRP+%A-|Tis)V4h-rt zmfyUF)@t(phUV}06XwyP6a04r2CM z$U2TQb@UeFxXA~rIUWb|(C04v&^&8<60P!#yZJkLi9??3GK>KkEnZbEcN-~IrtUFV z)=FGLs*RXievtZBR}`QKBn9ES83*19{lH&OT*#o8>M2QLRy zs*dpYp22>D)7&+H3@0P|5X@BtimiWJ;^@1TOg)#Zk(l$8$eB+oz-7KSO&6E`w2f z2b@o7psB8QfBIO&;fb2+(`$c+>gEH`k;BQXufT|5Imk<+2p_G8r!6E;lVyg$1|zj2 z@DEn-muU0E?9mX8mbt#s&TQw@je&WYv4HN;*{#uJD`$uh#6xv#_hM|1b^JhP{9i>W zaQq~D{H$&KVsZTHVjRGRBbCJwi&tbpIA{)zq8+z?QA~4*gR@Q0$xbj>Ph1O{V9uGi z(LTYtG{Js3fnb{?KDOevp5zIdc=9yJ>pVj#1+hKCL;{47 z9>VZQDABju`VoEm$m0L;?Q^RCeEXNo^8fgDII}+h&qVa?m$a$?E0z2&S#DoK|LfcF zQW_o~geokNu(+37XT2g*V^^n1Z+Y{dMN?eI0CY}c;~&`~taG-Hym3GsbNLomVIz+N!9>+ zcPLpdK*|=JCJUzxDP}-Q)W!$_@$`|{+ZJFJlX6`!?U9*Wn;4(RhRGojU-H?y0 z_4$@eJUng`Qk1jwkG11=K$}15Dk0e7|7Gp&yWcx@e+j~a<=_j!WJ_1S(DCkW{lI;~ z|3%w*y*1Uo4K{=XLQ6suq=w!RqzKXi2}KCK_g6@B3M6-5zvN5ZXk|TkLPgM9R?hTRGzA(7}zXO;z z%{ka>KVS^}l|JaJKkVZELCtH}NINrXWPbXK&mPzU;Pc_Y6-FE44zFNYOV||)+!eb+ z0ReAp0;#hv3g$OY?Na637|)n?90FLkHNUha|MXW*I7GfqDKM+YvIxqO5Alkw9{ z#Vn{5DKWhO_%3}7iP$zCoBrN$m{~Jp{#3tE9v+I^Nbq2LCx=X+?B~{eu1beP+~9TB zC_l8|XWDn-?n=_><=2bwp=&=dD}Z|W6L;!$(C9UY6hL~WX1Xr?Pm?F37N2yQX|^7ph#KVONPOzAgJika8_mHYeKQJ@d;iAAmmHr1MxZ89DS+cQ1nK zfzB*e0(B<|RjypP3M#qcZRR}si!|Y%KEcN{eMnP6FXdJQv`$1WM#S>mafL$*dAOp? zUE~#RuYUkX=K!?#_DP@Lgj+xR-{D^B^Ln-{iQxe5{wyY|cQTDkAn95JDo~Q5u?@(9f*!jLjseA@<_2L`kQ?#V&>v0cJ)T?dqdM(Q{1FFqM}MmxHUn)5Tf# z6!!2MF{?nbnb4d;vSfYU17wEmIB0pZP=*F{3d@_|{thF(zDakr1MDwG(=9iPw z+jwN1&xgn<^E9O?tapaSuOsg`z+hm7EqIwctLyyvV&kho%9N;zX3p>M~-bp+1{=oFq;#1@<-WwA}riRcT$F z1j?NDIxGYY?QXRgS*xz5-+STrc=lCH#??7q_M}I!H(kF1RDs(uWXPjMtPuiYrA_dU zi;9`m&11&@3UoK&d9E~!lk5*^z8n8d<>f?g6g4 z-a>BS1M0FQKnjiDeibr?A}qgga5FAAR(Y#TtYp;rc~RX z+}-WuijDet->U$Z_DGC|PV4CfYILa)AdZ%tiNIg9+;j)T)% zNW3hgyFs&6nOy=BVqg)+UgiOo!|F2oS;X_MdQj=Lj&#rddkG?vKO|9>{52eAgq<(BC|KHj|ZM+Ry=mKot?-u&BGL(MOinRi#c z1y7C)k#tsB%bSKmELX|8;#T)k35!DfeMUwGR@sQ~RiV2VFBUb`A|5xfi{D=E)4pLP zT~f_16%YJaS@hEkf00o}!jZ%F{c!FY@5rfiGTA)k;)BY3-&n7=eQwL&9%3G?DOmUQ zd5CxAnK+8a0>J%F@53YqLGBk1s6K-(R^#T=$Gvh)x39SV%6_=+EOzPDH(*GH@xxDN+0lfsY>n8#RLbyvw6I%l zET-oVAa6;H?&&K(=8as_i~rVF9U6grJg|;L8(8|J9BEHL`s? z7X7%XKt)9yE%mwAKRdUACwkrFy3=T(OKv4R@|)F-z_UKWM2RW!s@46E6QSR2%C^d+ z)t&FyR+sFQ3559T_VP^PZ`xLx9Rymmx7fWBzF!?YdDUR)&ZpNM5qXYURnD=O?Q$O| z*WU*Fy2RcYY5Azq5Li%UdX;CA+9Q1~KS=+Z57(1%Td<8>)#jjPC}<5>1YHL4)+`i$eJ!S@fU+qGmv=`~!4z@{1| z6?v27*@20bVsugOJJ{C3zj zyY$-jRcW}?-T6(P!?(AI<@U*U7j}TTZS#|X;SZf%3cp+``eM3+w|(dOO%?lr=2#~5 z)23yum+u?ajPGjcmp$Ia9o81IP%PP7K11(5jKsTcU2nWHPFL}&US=&Q$#Khhp9kCe zT4l#pNz)e0uJ-;>noMM&@#5t;YVL=lgW8y#{>7=G2Mw1JuEi+IdLDk{>Xa||nvwis zkvH){&z8z|wz`Jv55|B_sf3!;y5M>Eta9(GS2aQAtzN3v)!*#Bsx-IDw}K|#erKE! z9@u{T1;Fc2zp)mU;BMlfC2^SBK&*dqmFcru#_dL017%d7%T=9z?)Pam7jqW})?}H~ z#*(J|pJb*|cub~paefi^YUaMC1WZ49Bi{5xVk^k(@MaI^{r!v&cRl#2W1VDX9=D9_9q-azehf2o+>S0J9ZDg{_fqt>lfI0tu5~==g;Zo z!34|s)u}t`{V$?+iw0f3%$|Olr)tf}Iq~wY*YRjBJ@k_)d*0@v8Llz*Oe_Rz+3yr< zuR1X2ca;0v^oLj7&Ef5uSD}heuMfY+zRw$Ksw_zVZrIOTUvsl5ORLt=S;L{6>v}}4 zNru-J@WBXwU2Qs5cHHOO{-mCHBx$>Kzci(F;asoGOEKoiERo1{Y{Bd2{x9a9#Gc<0 zFT6cS8#9-$p|x5}cTx4tP?%cS@tp31%SqwVhlSn+3$}}Y?QW#*9416htKK?Td>7)K zCgS?ixc6GsniD2@^ZfK_!rwBP!p(?q?nbp*SZe`h7|ir|F4_0p#lE)Nit&GcVwu~9 z?R92=<^l(A1==1^m4m{|8%wn&so#6u7fr9f|NOIe%VSel^=|Kq|Mu^F_nE#o$1q_X zNn^pEv1u2sd}CMtJMh*2pqD-xcCGO5ibU-1!PuDn3ip#u|Jc9t)R?1Q_tU+K*puzp z*yFG6)W2V2sV8TW4>OX64++d?WJS_}Fi21}9T-FM4rM#2b4HfCLRSzV55tA#vokbK10@)70gjXlISk<(q5g z+R_z>APJ#KJQ&h>G>IFn$Dr8(=^~wVqXnCEC7Jbj^7X{4I|MoOWNbPlBlLWX^n4sT zBvz5KvM4ZfB5#=CQ5BWPj$6JPP9WlSMSoXo;pY8B@UFrK1zG8Qg4RNs{O zY~^CNiE_7zPq%4=z6qh*I9K0XR^Pdr&I#0QdyKZ_(|6y}cj4%<5$&-X=ypXLxZCtt zDfc);^f(a=EPQ&rKs}yKJ%O6tzPSd0ng-Wad#=r)LyrxD_j|&cx*{Mw;nm%tX+4qo z24NFDLAkxbQQaX?y*CMlQGC78UA*eHwn%00d-*|Jx1G_T~!BH7gVo+4-r6cB|DeS{<0 zOV8Qaumt)SPYp>l>2Cp~dnxMc`5O27O4I-b+y#}*efeEEKnEIr%2TdUJZI6=-Gw>8*LXHA2-uUp+#rWtp!D*el zLo?;yo;H}Ynm5eHXjTb+F#zEXD2gqjd0U+{QD*#x&_BJ;(As2@c9zsW>Z_!fP*ZTG zeYq(!d=SfZlOjm~cQfX>14jG5liHFg|0cEZt!ZcD9n+KNxUq?x6--Jqvw8Y?^I`;z zE8LhLPP83~*Ehn{ZW%BC2AILYt_ZLhnb7Po+zTh#kHmj&;?hD8ZJW9ABp_grAa^C+ za3tOy4u1Wc{-xttRU5RehC7>SFj|h-dsyH@%^+k@4F=NspQ<)O;NPk?@gZN*IafU9 zXykuYwT)O=R4hOz^oo_1me@G_5#A6Bwj#yHoq?{D;S?mm?1)Bb33Oi}4h+8cPgUE< z%5sE(@}H`9z4=-0R}#!XH7l~@P0tk-1J8?EAZoIN(k(<(*r@-js!e#OhQoO9DvtEW zu7AW7;h+Aes*M}RV`%}LM0Ggtf2!KtoR)0*Pf!S={SiTfC7tIP;Zjms?5+h|CFRok zz1UrAM&bbHdNR-fL~^8|a?p~uL^Qbxk^l<{b;1xHkI75Yi?orC%=%|)^9qh`6Y$g` zFu6WbrSuE&4;8FWy0ci&3t7Fsf-`5CwDbjNlCAbgv=-5zWp%p~8ykF5T&)XXj%I?x z)e^6U(}zq7)nsAntwe;zzN-Q5*p621Cu?nw>$qltu;c1TXhbwPQY`7GG8^@3+X!PZ z&P-Q>(VkZ?2!c?K1Zj!P?$d733qWt%+0pqidD{@ zZA=nz4yfv0^=z>O;9&{(n2sW%umf~L_#Ku-4dM_=(*AXXyH%016&wQkf^jusB|8w8 z3s}#J*%$w5YlDs_h?}?FkCHx5KeK8jxbTZJ%C67bAGyAkn!`xW>B1rBZh9t*nXbZ} zU;6fq`7Um>Eo|8)4-!A0o+LV9t*Cq5!)JIsdBWVa2!wB*ZJi{xaYBx}X33_u;y1nM z@fepQz!rBBW997G)B7L1{_Nd>K>)IZNz$D%M#Vt3qfEAgr(-FmAd-n$J>1p8X1x^( z83Ets_YvP_aV7bfe(^E4n`kckm#wGpGo8{~A``|}>$_tj_ zMr?c1MxK%hZ7RTb6Q5&A!=1Q6>z+yb=Il;Nzpjy+;cFK>#dq&0QRl45e3JN=`HPK! zpKB3QmFu99JY=6QxrJ|m*MRrhLh{S}Wtv*=1{w?LDe%*L)^+Tf!_&3U*AFjgC$Gu@ z_PUqMGHh>gGEzmFk5)Bnp8id@Y4rJ$ChxDsGYD2^2Ap3<+{P7K;I zv`4ae3@sW6czEAj>?|Ve$<6-(GiF2mElJ?@(6Ng@MhOBQANiA<0By`D?vgjkm+y^mg+0<7P| zL9fP`x_XSAarK=Xv@Y`i)r6q3$yApqV&b$*P3zN!j4x+x?M)xt0AZ;rV`X_e5GD8U z(d(cx^up$I!g6>2o2}W3bk`r>w~WWF5g zx(;pOgz$NsX(}OAq^V4;(8y*=_%j^FBiOTYeWSrVK{gY(}CkvHNhcc-=8>2*RK2CtJR ztAF zF`t3;4w;b<()APQtkX!m(Dauj)h}ni3o{50tGbARBbt^;aP(;+EX%X`9E3Lg%7&_Y zJMoDVcHN$6<^`jt~(Fx`eQytEHbB1Y55_lL+0*NU`#rUY<-~Vn%!$6LGLJ8`1SZZ#>KaPZ2O3YD`}$3bADo{gnM(7j(K4Y_jD(} z@S&ybgCmQ?fjUeQ!*!Fu3MVB$t3L%{+#V~|Q|`{ak*?Ilkc8PT@uZR9c$rb(IErZ- zY4T%C@O07lxRJZ>UB5a+o1pyqh0g6)^mw&)t@iE?cU?$&>Kj#?`A{g+s`S%!mr2vI z`GYvM-!xx_`|6TtkG?(Hx}(4F4dbyVzy-Ea10Cnv@}5hAWiq?ee5c~ic2fF2te-f! zegU$+KQva6G~P?ZBckGP(T_5j@ryfmYm;7X<=Z-Jzdt!>l>d_Nf;osXDXd{deL$?=rqwBdCKm7QzId0Rf{rY<~Ex715KY4OLg;QJ3@aV z#^$>*M3ttdkdoLW%vRBX%QBW6I+JV=-A@(C&`?gzqAJQ+Iy&vxdE$p4(A7&+`woM( zJr6$3ZP`mSE2kF3Drg(WdV^ID|H^KD;P-Wj?n+C2*R%k1ISJDO%|k!Weum_3i9k;l zZ>CQg$BNn+OW&C6XK8_+R1v=}b~3eiD5y#8X4L{^LK(}-s6pL2iVjj%_l;R;${k-1M(2hsaBd!L+A&xK6Y%P+baN>Et8hcm7@fqtd4CYQt(;gE`N$_N& z%JVrb0WxbP>V3yw*D$@gR%)OA0xhFbZe1y^9ukUmpzyh}!yX7Yz;(|O3A|P}>X&WF zu?7n+%|)DXNXt4#3(;q(p6J?dy7BV(lhR%ng=W7Ao%j=lQE48bU1K@D6OqpnW%?Wo zXs_s>D6qo_Q6PNtWY6I4PWLS*n>J5fAnotAI287RVtu;@HW*iEV{?27jSWbCM$cfB ze3<%#lj)C&VG74pO+CXt2)L-l%~~xonI8btgss|AHJHH!&aiMJc|x zM4PL*u2{=rE_ZPGzt!zV*IQuW2LSn3NtSqS2j*w}sfsb*M(8<+6-*MZj`lNS!ROR| z=wMy$h<0)u{8|h$YH>n5hDLeakn1?0s)qT!y2kgCeC}aX7+#91)a9o0P1wao-1l&d zm-jFsFW1oNnaS;}4uzNU0T+dp;t8i;a|6vxR~O&X3)tbVmtVD|xB}H7#jm`IbAR;k z^6<0fpEGZ58n~=GpC!*?-GmQnsXu>Jt|j6xo5wlo*SyTzIVJU;EvrFIUf^Xbo*`zS zejF`l&d-$h)b){D27t$D7l&`BNU;KMf3R|Ue8;4zom@iNkl1SI*Vfp6_4WBxG_Om! zi8I6bJL4F8v2?5MYl+F(Wq)529UI=*b6V2ixu&~`54`0^zQ1o9YUxHn_WxD`8QduB z+K193;M2*H$<3~88F(1j4_Nhk@H;j6@G1f>VW>|eMNtImp1xG)3kV`t(1Z0tu#l$BecPlRUavhjX`}5(*IM0)_m?lX?jQ_WoK*~>( zr@F)p{9sWr~5uB*j>~>nuu$yO{H)Xc4lt{AFIa4Q?25v4R7%nizSx2X>-*x;t0j<30Gi}xV+upD$MvR zqWb>O?XkwE4N7`)zaU0h%^RH3O%h02=@I;teDs-B!^6-b5i+^Vns2kN$!?K)I4Fna@Bm?G5u>Dzt-2{E)h*?L~8t5A6P`Sd=2a6-+Z%**TbODnfVF6c!spX2GP5E1sN z+W=h>)%{dU>bo!GW>#rlFVOk)Uq1iU=BIk~7rvWzlqWGA(k@sPiPv4Xe?d30o-2py zP54$Qs;V8|@F9Brv1~Yw3iM0N-@KEd?HX|q|BPBd)!us7`g?DEyvqH0=*`(T)QJNb z3wZmxr__tKpC*GX+oC!k=x&Wa6FGE-5N_{G?eE8kEGTGdFA@1mt^}&xlB7JQak9HN zq@e)uNz?cqrDwr=KpAIJeRS+C81sjvt1uRDx`$FfT5U87nBE#^(mtSEf`@VN#KW}5 z5r}(g&CF%J8p3T>ncBbB^%jvIIhDPVCCUQ^0<5gA`r7SGj}L1JLjS?~841GL?lE6S z($&A89dz9x#}A9x*HX@~et0un>SzvS?C*0ga;Jcb9|d$A4nL-Y?)&945~-I2?lw&YZq_t^xqMIl$i)Jn{Sne+tkYwI zgac0qf6Oy!Z{$5xYuB&H{3rA6VsNnf3}MGb7R%5+*-r@8Ip~^9MdovNnrruPqkt`g zyL%6j^FK@NbnXdN$uYWm?E^heO|QGm6T+ntCv|)W^nvsc)z934bDnd#bfYLgI`>anz3*04hL$nd?Bfzn|us#;O#rI{(^Yj02TXMgrD zcO4H8On&rv`G)cN%8-r&B|ND%>X5p9xQOeeqtOnV8K)!mF?Q|f@C6zcY8^}72I!dj zD$_U6CQq2?xCl9CrmixAM0M?WSM!kfs}EG)7wx<=Z%i7ywf5qq$-%*#cft&Q@9MsF zDza|BR1`gG>Ok{_I*{?BH~n7zpY}Ie7007Dd&h0Bh?n44R#VRS4#=e}x6v<&xQE>ES->4<;I-HyBv z3QsEnNf_zYA1}G(2NW#3eY&u;U5h%laL|V9CBMz97vx2fzo_ZMe>-h+;Klo+c-D z{L#&lePou%hXHIZJm{8#mfb-Ciyfm^;uvB6^6x z`mh+UkYel7uUoRmT-EKl_KzH?z7D zugom0%{T_TJ+O2?d_6s7GrTK_8 zJV2D`sZpAO!NU~!@^??{H!5c`g>XSESj<)fVlUKh zcf%?VzBch_Ny;dN!_ZRNq3K>=pO`cky?v!G^Ap8c&ooA|*d2MG83N8R*n^So8kLMKBc6uG@&*21J$vL6a~DV)%l*$VUd#vpl!c!JY?u zeJfJ97CrK@9+C48W-i2|r}Gg{4Aw9I&~sGhLYJ*^+k@r1F9O5`uLkq+`Pw*tngBgFHQ!5ylZpVO(~<$8?Ua-yd+^+^4B zm!CHr;%soCt9mxNYgYbvJ^(5ElpczcE96A{e0fc7$%PQ+&tKO92zroOwWha$_qk1Q z|A)`783U3i42v8_GzxS7$_I_JWcsusG~)>XD5Hy;DtfGWQ;9&wBMo60tI1-~YH4NPsQkM`1POA%hs?NOTX>gub>$P44Z^Hk1?OQd zUSNBUZB;b;{&@EIi(2obhV~DLlKPaq-`EQfENd&D_hjA3yk%_kCzQC<*?6;E4I^KjeuTf=`B{+=F^J|!`A zkm3{IH~>h91RG1o3911kAnGyu&)nhCNwiPEJRxSW-{g1=$-b}FpLJciyk1fhnt z2Y&nz^}xbi8q+}jdn+=R7*+TOilr5BaLYP)SV(~v)Ak^s7Plbxy<-maq^I0i3q@-(5o~1Tt%u}O6#n9 ziLAD2@K2Vk_7GN`Jh*`o;Exj5!7aF@B$qXr!D9tJy~dR)3||-tqWcj|+W?#<39%l+ z2)d%Ix`{WF&N)`Xk4F6L5I#N`B_5^I)`v$Nc4j@Tlq2hpy zim{-2n3|1s#JY=`TC`!FAe}E;rW(BT9z38)_sqejr8&bmK{FRq%_a$`pIi(Ipf}~r zC`1H*1JTJL1qMlk3Z+3u`IvvCJi;+?D!BF>o!u6xAM!$Jdf?#hFj0z4FP2boBXMR` zf&E8%40rlWggh;)1#C10+K>Xfm!#dE#J&WuA;k)`XJkWo7bNKS5#T3DQDcUHUvR#} zdPdN$4l9( z7k4~k2Lk%ijZHW@1}F&v#^mk_Zqx(ikBBn6P=^tgPd4Wn!bGp=0YY}68n>g?kc{Lv z_drWhMK7gy>S-n}(eEf|_DTpg?xoyR$pJP%K+ETLcC&!(Y53nl)=g(F9Ls{e5LdPk z`A{^&Dh~7`ea}#|qzG!i3@CjGUk%8!I`k@VZ^8y(|W4VU5-} z*gQOx;3b*VAsvzpzl;?AK5`?U3K!zN1*grHxclhSb8IkO%f@9L=}E9_+XRvf{EMJ_B{x+JC#5297N zZ_N$5EC@oVo*-3Eb|EK@_dp{Na_X=P&!LJluo!iC9Yj9MQ+dBw3EZgAXU(&n4b!-S zI`Lp>v4G{)=W>zJf-P>B#sS&bxD0i%GnZ{7cBAw%3hUoHQepHmL@|(`!Vny`~-5?J3XCyBSuiA!- z+Ejq`P+0U00S_LFWhRPLhlT56J<}W*wB+seLBW^gU2E zvE~Z3R$^!X4w8gEU9{Z5F>Ta`(l@+7S{o7?p@bavh7DCnG3{SUmY-hXf%@58DsCSE zLjQreS318{DmmDNf-Jb1Z>x{f&?e{tynJfD8%O`KfRZ2j@`OdjEJZ^jioxv}zl;G# zcd`J4sK*zdsZB>vjREqvqoP#cp_fy_)^t^#(StmS+?_N)r1LE!g(fzz?aT0os65X- z*mo2FWTUN24N^YdI7hDVVD2kaH?ldx0m$}%Hfts_m!@&HFxj44&lw}Sr$bXFrS8iD zLNa2JfM+Pc=nv@K-!YU=4O5lbH@LF~vT?nK3B+&eWO~uwTVkMkbu$cUHJzFK;18?E)Q49*~_Jvr)v2at?3t;jc^S&Dn63*n%r|C_W_y}8k*Z`_;0MfkHW~v`I0ZbE_1bGY@y_;w!Vc(IA42WnV z{)N+XxC|&>J|aqyV5krp6=MvDe`X-#U7=$lJMq=uvgs1Gi;H6;t|#LCz5OC+y$X5x zp~MTA>1HFH(1!$#*D8*6b>6Q*xYtP{%%_foUqQ@=_4=}+Z**qRpdUJ1MRo3LkHR(J z2w5&+yuOpNCx5QV@{N~9({-;ycCrIk+c`OdL1 zFQ@rBhsRFQ8v#z$t%RH?WUX$PKEMm^LJz7EiA$VMbcR1=< z$g*xB*{&9QC_T3*V6{5xg2&3jZ%T1lMb=22aCLU1x5s-Pkta5g4A<*nKM{SNthDH150C7c*d;05}G#(cF$Vnfmc zh3A|xzeZlmG!BQMOh6Ehrwq-w8DBtZ8hjL)jGT z0UnjRogC0<1lWKSVXeQc=^N%~S!Y4*b|%W>;Pwkm!Sl4#A2UEthr6#PHY8i9xOwjb zJHj(KmjC>E&HQ~SeizO@x}}~UjpKidn8+6|VB33=!I}k%_OKfhiexKB%Y}>^JRgMx zI~zYS3BmZf&O6pjTIn)}!D)lD3WXHl(qzV-yA70Ox3C*DS55nKyY=5j$C}=PU>n-# z3|y!50e0uS!1TV{QzB3EWkEO};~pRDjakVTGp|HE?}pQ)!ZnxcA*@`bI?{BhH=@K1 z+_Kt$Qyw5L3yZ}1rZb=CVf+UMR+mm&7f`78$NMjdlU^5oRrpsk$sobga4=2_j_w{> zpm+a+aNh^VRDI0rJzR$T3UD1?QMa6O2z^202)ju&ZC~_XHL6{uRkR%R0BP~O|IRZ) zmT=uTdv&}I0MGXYr_;8N!wiu3jxAsz3LAqRZr@dsPH<#q%Z&=?`jyu{>NK8gbc?j@ z^U0knO#%x6W-l5_VAx$+<2XvJ=O*Bn&$%z5V8xZ{_$|M=Q7}y=Rw#q?VqEhCHY3ca z{3YPx)OMtzZ`**JE4-(HlCIb;NWNU_Nq%9-`SUn zYL~L;LB(;k$eiQfu%8x+z!_NA{MQrYck}_*#i&^GdVP=yz*my1q$lLI7JF5~ih4f- zSt7)GZ{;`N>Qm;y#6c~I2%O>z_Y(_-UaDcx(Xz&`clsw3maz)LLD3-N55I6B|K|q& zG{@6n?Lp)>Gz`NbDEQaH8=n{GuZAnO^@wwY#zdXp2@w78bH)mQ_U#0y54hcpJs*pM z)GOP>HiSVsxipLM=Ug|Aw-7?XV|%fITb%{^49@ z0Y0RLE=fX^gPZ_6i@V<|42p@^2l|FQylxABEV4hpBQpw+M~<@M(?E)r)o;(%Lqxe5 zMJs=0m8TDXc>Dn6aV%e*vax$ZiYf~S_`_dvU#EJ6&VNYWqYEEQyxt28+xrSIA1USV z3@v0TrEZizQ#xC9?92a5;KhPoZ6f2``fGjvUcgI6ov1ebSA6^6``YZM z9rw)C{lWP516hyygU3P(cVByc?oAV87cGVfKJ9y?a{bHP%%1;9v3}M zgj1D&8j0rEgk2GT67lnjWP8;GW9h1<>^`Zwi7*rSTLam`^l*zx06iv!p)!R}QtAST zFLc~g(Q;f!VpuKoYR#oZ*>qazN`(>=WFZFx&kZfD1W-}mMc09-xa__x9%A1Pu@Uug zFm37bafHeOV0k6y`Si3ac1JFc5y2)+N}3#}4zTq7(lytm3o1=O$OO3P9;<3afDG358Y4 zgCV1cp>P)UPKY+Q1SEWr%g|0p3`$c%r?_6Ni(O8?Bph!2@PwXb3#KSK@ue_xp%g@@ zqk)*)f5OAGB1YOrWtfXQl2NKB{(qKIKWOd^b_ah;x8?*{dsXrc*WLmzp6|eXXzAGc z^78WUJ`zJ2Tm0@wPh*Ng3aqr_9F?=Hh<3RRkN7lOB+w-B_VPN8(H>!R{KZ~}S-JV*?k1ABnXC=r{9E6#i{WS60ZECke!Q>>9eMipbcp~E z{}E~S*5(DHx5h&RW4xU#S;!&j0*b;CKKL?8z(ztviLHy~YBd-C`N;Y!zcZ7mp)1DX zVwV#&O@z{<2Xx{baKJ9s^uW1N6h=%1RcXfZVmzK5viuHQD{A{l1aczKA*t^>CKRX! zYCx-NDY_2(-a783f!;t7;6Jg?Fh&$ic^BUot3=Q)>ay%EDn&sW+%m=kZ@wjAFv<{~ zVQf@h@+C|2u~}r!SW@jds&A6q&%m5KCjniyFYwu9c{c_j5gr(gaxXFPk>uM2`W5Bg zaA10}!HB@2)hZd>SeJS`lc-X{4JeUI@9;PVls?bT?GALj`@h}n`HCt&l`Z?ByBO=4T{hE>Jx zm3-7k2|5`PE>|kgTPU@qE0J3dcE590uA;drcDnX)aSA|HCL1^7dmkhiPQJt`Y#W!x zo-A=pUm6uk)8vLo$xCHmmJUdIo2OC}So2WZ{ZD3^*ebj%Or~5QfK}z2E|yV9lC44A z9z<5D2~t7pBmTgsXwI;b@G@&Q#Xqd+F&7JyFK+4NeC&yBeL*Luh&JAK%JaF5PED$L zX8ObTMf-P~*E_66Y;nZ^CU~iZKsyJ^muX3~Ze&41a4>t214b-#A>+eC|8ON0L4}ffi2&?xj;+br@%JTParJ?PuoX^;@f& z0gvrpPJi}b;&d<(Qy3S1q&2}VH?r+FamHA^59|~ zdt~qk9|IfHq>Sk8K2w7i=KTZo7e!vSuc?HyWFNW5sX@zWuTi$TK(v=MJc2;#fWIC% z9EXD%)+}_qa5@;wTguV#M+~wak%fDJd_8!5fqaN4VpYtU88}17s@g=dfXCSYZP_2F z<)|ycVjfzm^lFwA9Xv zT_@RWBoT2zGLa##(Yg9{{z>-4l-W1zvVt%1%2Jtio~|(8`*LG;vIK&y5_)>|I%erf{x=u? z)&qqA`wAE1eMd%M)Z_z>0B!|(wXlAE%C*OhcSMEe-@b#bogH_SnUX)=whhi6CfKNi zVWe8ju4S-Y1Q&djxcX-(66#n~<+8c_?YYlK43K->^P7b*4SWlP>Ku#M4Dx@6Y8lD{ zRni35L+<1_4ZM$BG9iV0y}NjFdW%Hwwi_=IwZsyO?UHc&k?J3{!cWDL4c&g`R79=G z#oiw9ciVgNHR`Jt_4Y`j+kUA;^f%MkI};Ud2UY&jo37M5)4guL8Y`l=Lt^jFeRVs0 z_mvvG6P?)^19Cs=pho{l*Lk!gK|SjCKXuF2InJaoiUn9g4*m*9r+UO*oVsLE^Sk3D zFW`gp@*$G~(d)D;M@N<7uJgxtFKYQN`p@bo?Z0~^ryH|^3P*{Ie}C)5Y>a9_#WJN536-)B@R>yVc16wQB6WkaFp zm31!-2+2gHDYtoEuq^GqkpAZ*P^T2e5>1RAFW?) z;HunXY}0O$Z(z`BATQe$u&;koseg5~tBKU5Hehg5wkxN8gz+jNv1@VT=r2x~~(`;;SK1E)ZuM11eEe&zI2aNieuO zryqLeG|co8C&-aa^CCC;bkr3=ILeWMV9uI^R+iq5U?-?l+Nv&CQ8j-f8&K<2Sy%y2m0*l^h>BgYm%J(|(|qMFtk$Cek;d&jphDBDpcv7sG|jgYSuS#txem|nk++hEE60x z!zuf=XrfIgdCV(#_*n$wI}U?};9eN$ifD+9YdWdlX2?fO-$!h!^M;-8&tz0$4_ zYaiR4de>APf7bSM)y5Ii6QVN+YxcI!CR@6XiScYc~aTfq7G&9-9`*tyNsxo+F}-N|f|uQTb{Y+JXpPoA?+ z_?vPQSexv)}0cTHhog@0ki*KIk{ zZP|5U_5K2dxIlTeu-xrNnOs<0b6bse+pVG7v0d0Ob=wGW+t+gc;k)=Pa&eP?@#lT_ z{b!3`iHqCai#wCC|zIzIudLp1+LIPgG@?Ij^UZQ4RVs2jI;*M+p(bO}us8S;nyPSAL%ecaHW)`(o zB>}OZyy-NiqpG?*+IxFUR2l6QS`SceV~X7OjS`h9%x4ynv3RO29Gnv1 zbLB6iky(=Ana^N!rW}dX*ZW|;Gtpzgu9a&Jrw~-_ntfhNr?rpTgLK16@Q9Ibc{5I* za^`3F4kP>uDFi37cXk{eT!J^Lh4|lmbES4QP&?UdVRaBo>x%HMg7~HseQ`cb2{MCN z!q@JfnMIT}s~Nu@>{+@5&sa&cSNo4yL}Tu!$@{K)x)R`PkQRB9(L_FANG;&eKW35o znOQ{rM=i<|*Bt`gJNj?62o!K9AdKxFwJ7+S*gtBKno=AIm^}nC{4ceLn5s^&bs!oh z<PIRaUc zfYv{+KIoCDK1Y-=N)p5p>=EDr?i?q;w|}J~d^&~Dp%C{lrr;l`$Rfy+%n){(s7fKg zMglT^1vJ-knKf@z_i()u2VegmjotNE)A7T{{lPX^2#ii~bfM@Avcd(DumW_L33) z-Sile{)_LwcE?O6a3D^FKGygmA^9<9>VJcxtvC!YgC$<+i0yxZB5?KN)huOCa+@N^ z3=?nMzSY?4sfUSWgl(4GONutdf4Nt1R{@qP9HVtq!;J8dsa(Ajz}4`S8MiYvx^G;{ z9W6XQUw{2xUi7S^@)~M)zklqT|7$7EJ=UalE3g%^{p(N0?ZU>l&p;%f1r}eb?$}OA z$jzf|9Rzgu(0%eEK^U>3g}%Hz?Oh(?scj2dxQx37K^>3rjkKAN3LJFJIdwF4_|Miz zVM%`>uu6nvt?0k2=Z5e0D5zz+ggY7ow&uz=!`MmD7*NZ-I8~eYrYtX+qd03D(6boN zs;>{9bNe%_d5^rUm55!7zO0EbLiXL@u#2@uWspnAbNCTZkF=tC2><)`+A~4O z{R^!A&t2ha-!D-h(;4P~um6!c8W{p*N2K)o_pKdbK$T$QU+ZY9V99F-W~v8qihEfX zz=(@jRsTd^L5McO?LSh7`)aDmibBPzB=Ucx4)=X(GBwr0)_XTZM8oNLqo2Rvq+Kl|$X(wZ3+m(O=)eTkq!iZprxm}f6+w4tVGP}& zk<;;?%GWdyB=l{JnR}2K5}!`zW{+fXy#w~M-na1E2RQvFCwlr7d|&M-&IDs@6+-;8 zQXLvp)J^FX4fcM=XgmTkz6Qdf!d^!2Oponl{0T(u9^gVlG1>omix1@bkD@E%+b%+% z-Ud)rx~6^w>tXiMMM1$v!IAw}n%^CIs}|nv1HW9)jjIGSk*P0T4%iVj*FwM@zvDRR zwFJ`H8SHZW`hniz17pEU-+qIDvP>^C+Uts2yGq{CLK^Muio!y*WtGXLYkl}CN#C10V*~kh)EP@h)foo%P{E~fR~N#AYAu?ul^K=4 z+DX!qRM*-&t}iFv(luztS8Q_GmkG~)I5w{6`y>|>Sr=Sc##YD4hQEf^Ju+J%B8AIu z`?njs9^8jQ>pFV@u0S5D1=ZXYt4Tg40mZSfR@3GM&CHcwrg4iK8JUvAn~PHkNZH*H zJ{lT}PeNI)P0=!#pK$2SOa~&cyNu=EX^Oxh%-iyLsH1cRq}(=_#GkHMfZ<^C$7ycUKx- zA%IK`t{1G`Psgw;r&SqVTpx(~O&d3=3-r+$vy$pVX9;JUKL3UCx`>@sy*)*wj7+#P z`Bha%kez@kd_&G0>jrN0dCJ4vp@K6k0!#9PxfZY8KKI|JqeTWm z##OyzoL)+_9MJ(|KMdXa2a?>%z7(#1B3Y@?~isk)LVs^|F5P{A?Rp#+#LyQ$v# zPXC6_Kl@rE&HItRAL_HzPM&P%zU}jTckAEx@cYa{@oi;3xMc52CdUxtaEXx#2DcnZ zW&Kp^BlgSBUw0w}tQxVSpJ>|f@M4F;R^HPpLFxW`tI*1p#4Rd4&Qsz8~hm&o=1~&89=-d-&*)eO2=4nop_T?p_CPE_uq}WC)0-6Fj=T}1Nmn~nq zvcKu(olO%TAyG>l?IeAf5h{>!jl<`dr(5vG#Z$X!>R&HKC$%rr$D4q7oO5|WB2FKF z$Y_hE)WE1X*E3tbKk#MO{dsgjq20(8BPT2}Tjx(=Pf|pq>Uci#hzh1zu9REx1|oBW z8)32Y{pu6CE1JE}(wPLjcmtdDu0AX&;$`u?S*x@%7nOyospOBVaW}eE=`YHf(W23tY=(Vo;%oE?)_r1*mX#)YgXmRemE$7DzG?D1A#=rMLRPyl6J3P>xERN0W~rYeQx- z@{ZvVyo%>9D1#qBAJ^QQ`pQ|k5X0Q*RempB7;pdG$W zRAqP0r9$@Ogi=%IuUmfqhIHviZmJ0ks~2akE2riCkgJ$G6SU#xdA#&wFIP|~({&V*wcXRIhN*`cmfha>@u_o@IXo37r|E%FhfmL1J@0|D zwjeaX9}wD=uUlJO90#aPmU!TQo-w5kjcJmKtD+s)1w=gc&XB}R#PA@+Bbcc~`!j<4 zZ*QQgUQ-@+^4E=MyoyG<-TfHdbizU)kE&ieC%y8t;sub(E6W_c@6Gv7!PUp?j;(fQ zr+TJLJRfA8GhC42j^aZX<=K;j9F4L&&kg9&r$Nnye8X;Y&)Eey0mzQDS8zK#?+t}V zld$Uq20#X(<=?T%eL<&c#Nv`ibgNFmYv;BFhC1%fpItG0f^RC3hE7wv|Ak0}7YvPj~$+)g5hy(O_rh;;rs+W!-vMFhldWTIQraCA#>} zUmw(8OU+YF24rYXbK2%|YqB2F1Z&m%n(gNx<!_BQoVvC#!5ZsbIGqYI{&ZQ z=S~XehsE~^G`McngWawP)6q>7^^dQcyp=WI2<^R0n>npkcDU%|9~-~_{V8a`Mv{NQ z&q}%8M*LpCxPJKb+H&ZV%b~m05Dv<*ncczV6-jJtXfjoRS!iqP_FQ}5?;peA55Ob8 zpKp}z`WdN4E}a~7phjy^5$9jk{1iw90pUwq0^-HSMKaFE=rb~-^XGf-{^nNSAG!F; z{MK!lCHlyEaOU>kzFA0qzm2`>L&|f0<6A>Yq>;P8jXfj3D+=oiu?TJ966@i8zQ^tr z^q6kU`IdZIphdnA0=xO~(3k?6KDwx8!|qa$C`=GG!EdAtOridpfduB=Za#M|#OCks zy;t?w-|LSvP}o>`W}+>!ssfw5vuTz zT#sxu=w-j7L7JhXrR<7L)nFC|+Nj_-rbdo?HEreC_=f&S#tT)H# z1ZoeR7gU!>%P7@J!_BRxQEjp9W~$>hb+w}{J_OCV&4gVOd3`KZnDRKm?G<8mW<#~> zh;6NE7<^~&^_yO?OB%!?V8hgnL(GKf$$w?<}4yN5DC+li@syFgH>eR(-oIikx`+)zHySec;dFwZP$(!$#3U`itL+gdl&rXoK9$lh~bH6gLa?lv$x zEI?fjQ=WeV#B+H%aY#sBb|P;mB4~cekWZz41i_mrgU((}?5noyzt^=lbKX8$zC0~| zqy}Cne*YM#Mgr!+Eu(z2q_6Z;YRYlVjZztduKrWKpnsnK;#t4s=~nYJ?N`39XQn(c z%a#Lm+m}Q1XQU4`WeIr$SG{Ng@>&0$?TzY4o$pUt`<)-mJg7TAoDcnb{%;{c>f&f6 z+wbCdy`t{oWUKA(#VM&@ihQ;|?MFU8TB{>poPBzyCJ4BK1ZeSe0~qRKauppYv`SDE z3ZpR)0|yYhVh@a$gav*m21&X1fIUgESA&ocCA2!-V+2lsX%R}@-V1u_kCiBMfSE$x z!{3f#Wjc9i9=gA0`!$+y{WB6l_Hyq<`ljJU<(9-A=V*;XZ4lO$$dh^Ea#q4LrPv4INWuEYEsHLp`;{+!1dPkV)jf3otzDU? zQD>#Xlp<*L-LbR;CVnLI8?-j0W~7%rUlwyz`eZrYm=*oRmEZCX+V0nQcH+vaR6M(Zwq$MefI+!z z_TXnX<-Od|C*^V#y2GA#_wr^wmn*al4*Q1fy;!(Xq1dncWkzHze_gynd3x}RWXbh{ z?I#sCJC2Po+;IR95^{SFN~VwCbt#hmR)KoAWL(Y^#7}uk*n&!VoGU z6h|CEQnyn5uZL-&_df5nDKz>PVeF}LdB-{!II^sMIe(Ns4*&=7fV`J34^OqWl8C&dQ;`*DWaBALzAz}o>yCM zdm6msuzKw@S?=a4Y$Y}{)|6yPaIySt+d-U4d7D{@d6{JDoHvQZO;rUM{x<(RYu+u( zToWzeZN54*)2_f$;TkEf%J|#5jmoOwM%OD>k0Hy!u;8ZHmmB(~dDG+Cu66#mwp^%f z(>jRqHTByy1|m4CO7h*H=6k~u8e2nmV@|%dHhlL%KNOp5-)wDZi}dtXnoFw>2`Psi zZw5xc7-h+XctciD%Ys&|CEe^CsWtfZK&0>e7uCiePAr--hb6p{Rpt%@ zLYjYeiR-Y!ZI`uOI&y z_Ri;w<1ulWz_4lCbx!k>_uhXROYJ|eEgULc9^d+u@7Zlk^3IGtraCABzVN(o3mL=F zHbrVhKF|se`TFv4bFDqE2L&CGukopF{jFE`#PxG$-qtploa%bW1S$^>JpQBcmTTMI zR%QIV;ZXc^_Ka8fT>dxhq1LH?(|-T|H4gvHbGj#1^GocEZ%ICxy<=ck>0cR^$Ss&5KTs+JbyZOYs4D;pT z+kk?9`D+pn9u0d)q8LmVa&&~;#{H`H4Hddlt6Yea;fX;N#*sP3QZFUiz68Iz-<5O! ze%Q=TrM|(_f-Q`<>(`b)2eq-^x1ADHW@~7JiA`PGn33@Ls;H2fy{^9xZ@TsTf7Cuv zA;(>vzrcmZ!{Kj#atKg>(hMlIyK8v}HwLcBSurx)#3@}7>E=Vfd=B?^;15I(8k(u5 z|Hs+pe|T#vxRFwH{s$7W5UEKE04}qxP->%X)kKSx-LfwBfju~G&@Kq@_?NixOcdD{ zjX<@n2$o2Xf?3iG!1h+U0P`C#P5;m&Gfu_8yacW2qccKjH2F&4nxFZ76i4sp>_4J za#n@>ddl2-&CmT%Z4$I>L8b+h{6-PsB>j{?0s(h`sU%og4E1w!_-lMbzCV9x548IM z=nMM#r8zHWl1e~w-=Cq%Cs9=7B-P9$%?UqUIijOANi9o@Cl^2Yy#ACVoC?}WqAa1# zkAV}rq4_8->NIE`50wQQYCHiU*9~<-!Pu1$e&p_Cf;6>NKza=c_LD7TLRc;V1*;=L zk;inb(odh0sHFH1m#q@>4iygu!G{qClVAxZ30HQgN}Mu@qc_PhU?PgEXP2(iJ(2>X zqJIo~F8%b$I-U#wk}9$ESn5~=xKlVPNaP7+Iza2ubKOAzMmmks6o7Gfp1L3?dFL6G z62cUK5^PKtNlft#0LUFd{|+eS0@8S(sg{obna8ki!u0$e8NyXE(3tcF1!CncM}3m6KIJu=#|GaHYn>l~sE9u*ynAWn5*=ifvaF%%b7kHI_9L==jMjDnU? zFTQ~RWvB&?U(LZD-%*$^&8F+mIi zVL8IlQpB;IKvozY-+fa}22|qml923$2_`v*|LAOWVS#!u%JlLDk(aUr;K!U;mZXxU zeh85St*V6A2V!+M3XVly>NLIzoGqlqg72Te9IM$ybD*M%5XzmJ9z8_kqn!9kYAVmD zMO-D&vEnedqI<1$w+c?xm=HLtNAw3=@yFIw!awZNan6>wVoJsnQ-8q9okS5E{|a6c zfTtD|>_lT1b~(lR;+vaMm3mm9W5Xmm%eUmR$8CIlOlOM+kV6e#C`vEtvLa9wWQT?$ zG8!Q)h7g-;q}*wIdnc=<9(JV|L4HtL=1^*dEBi%F0O5HBh>>59=#*+29d)k}rIi(7 zji50-csi8Z6GSmn9IjCg!QtgJ3ZNmy1Vwzxd}St(^tbHXuQbTParHp#38F4ECx zB^EFLq6Cahyh9n|nis3S+zK6wy8Lg<9meZABVwx?4york)d8!iGzWI1gHGwLhx34A zDsS4>5E0L49YNvl*c=svKwcxKNfx;~Gc)h9O2f|d%f_lBiiQj%g%Q`iqN$N}YnymN z44l&p(9-?-^(OJDO6SM$&fL=u@TV5=!;&U=gom>9ZCInCB0@_Hp#!g=B&R3UJ7-w3 z*8%rBR>r%?q%KCD_6?z^v=gF2QW;ZwZFG1On1ax&j7S&b;LJ!8c51~3Lg+9Fc5L;h zD!7F7X5s?NZM~FwzIOLxD8C8*$^!1_c{#M+I5$n`oqjyIzQeDk1<&(ZI!6d-!^PU3 zFezFlFwk2iwATkDJqX7<>_hg#p4@I@$%pc|4MM}XSlI$i>G<7P9IOvkO&e2P00@RdIL?7> ztc9gv9ap3wK3goT=VM&2;oPss+S;N!6+clrf{e)~6ACmGE+=%j{LFq8kk92*&F4tF z0ltm&agNKM)6x~h`gSsjLa{Ol)bQj=L*nfdm_Qyw3leiEqDUlV0_pJ{N$*_YZK9ur z2`2Ds=RmN-BzwxF-tZ*j)zNwV_Nki#zApd@1=G}{QRhPAEc!4X67XQ7OI&e+RrFK8 z86h_Ytc-du8X@lSZS30jc>0DRU;~9(vfzt$7{CJeJP(m&j|dKrfTSg<+k6`0?>*fR zY>B8&+ksv)?4{{}`iUb(IOfR3Gf%c>gm|gOIB?gx6XRc9b5d!i$4E_Z4XE&zbtRR} z-b5seBXl4G@%r>Q&OX=1cuvGTu`SV&yxX*AJudVbq5UZOZUJ{oOseaktTdwj#;56< zuc>c$jri!7ES~m{Tu!q11CGj?DO=(bc*>CCy@(q4{hJ-6>fVZm#ABVTt}xaYwunU$ zZgO@b(6LcuaRIzo09F~4u1~~Srvyn1sOMe2v77{(68dj^a-uY72@Dr?;ISp@oh60JW~%h%iPPte-qZal zi0z8-8fjr9afusOB&CQ&8WlZ~ZHjG7L?%{p71Ec`P+a5^$JtP-)t3awxQcKVxxR?U z25=xUS6N`dE51UBg^RZr8Ipy&SbCtRD%D5lbVdHZMu>~;Y25E@`A)cSAJ3!jTnsBo z43J~sKdIyD_aK=ltOqPyP5-;HPdh?wb%P5V7zW6eMC9H^Y&^(jm7KqB5B1tA%sZP> z{W6X({bAAlgTj{2_6|Tm5_kHf^v=D23GJBru?V6sv_Vnk zd`eaX5FYgcIFV(TdJ5=0#P&a!27n;4^OirYoI4|`tX?)2$!%3h67>d2rzN%hF8V86 zw|DRFzuWX#kpPw%DvPv#GucDb*l(=Du!A>C%7gCZfY`k zHnIJa`%j4xOs+mtyge})1^i4wNUo>kjG-R;Q9V)HTcUcxN=fh>IecFYys}U#@*>H@ z0mOpgc=4x|vz{W;1l}>yNF#*^Orj3<>TTVw1WUrC>obpzHfk>rdL#R>r!Z|qpMu_L z>-`oW7ET}+1EihzvYXbO|GzKPe zAU&%!!7V+*-@%l%$~vEF^XN>EX|uQ?v)t{%Z;A&;YcNeym29?$<@8KcPdmS^X{t=j zE4=vH{A-eDF;A&m&y3+zhG%8 zJdYvDfT7(PM)USIE}L2;wUvKLG034ZrdVfXNumsn7IvsoT;rTxHj?E ztIxEy=Yy=bkTz=O_hOktY@CwiLvDe#%;?5xoK`dMJirnTChlhwi@!Nayw+shM<98y z&i3COrf{_>S#NHS&@g`0y5(b}CnKHG3ee2nWwvoiX^;8*Se8B(HauWSM-iDgeBCZC zb*f}2jin#Sz|1Rs@*uFLbq*lEY8!Lx+RH~sp@MQX4Y z$8Pz7KPK^axqNI=Gw$h{KOiJ4oVb^zD-g==a#P&!C}6AvYmqB!T2DM*HGK{9s_i&D z@v48%67JpjN#WGHdBQ5(r*$sm)TezpE8Lg(yYhb*?<{asgEcbfzZ!@2_x&u}(DUFK=j_Ok zS+BP9komyr$j~3*|IR}fVp*dwOUXAbFe}fjqaOWw5qj}xy)-*2Y_q2AB5bQ^Ix756 z$G?mJXdJ4?Q=e{-Blah(qazRJLdlUw%h}OUC%@asQD^_vI4*bKsZ3&k{06OGs{#v2<{e9BJnA z;W*c2>v^YkCZ->xYclzc{XuLQ*UH85FJu=H39CKaOVWuQvIIJ>^}?(!#AAIfPG*&X z9u}gBmlcSYIZ#o9+lk)Q(3^K)h^>e>Al(|x#25AjuPyH>o@5e1U`jpEuKU;!=MzE4 z9ayfT&`3&r{hPqHrr3WK*7!8Ru8dddNJCw4JieI|!pm8uj>gp+WC!Jf9d!`u0cNqm zugZi<@ja%rV;O`97Y&6$JrmD{TY28A3_uZG6}{cem#+jw+1b$!o9Wqa`Q4-&j`SV+ z0@7-{mt}Pysk?AwJinh`1}P;geYRGf$RT#F+9n+vdf%ORKFhUs!=8QEIio2d-NkLI z_t?mHR|el4WUpwO_zB(DRJapYA-kRUNmKM$s-DG~sz&0Ms4p2g#Is^KdfguL@}}%> zK`x?Vn>tb4&BbSvYtmp(qlBpa{1F2>l^a9)>5t`JUVUw^%BS~5?}YK?I~Md&B4Jkj4~$feo}PsXo^3ACM9L<(kQembjg!QM4CWoaytm-BRChfTej zrER*iU2R_{I`$#tph5oSno*>vzIzs98=++lHKq4y=%l43F2&1ZP|r5dX`)5*eCgiH zJl&pqSx>RSE}o&uce_~Rn=&P8{5~dr`xSQB(mDLcLPG!BlUAmJ{O>}B!*KIe^;V@~ ztvbu^UiNym3Qw>veZBpXEmwNKwlaQn_v)B4!RA@veooc;)4cd@FWO$V8?m8P6#k`$ zhk_s{$rx) zOMJc7ptwCkCHo@-ccbO|u%&($g|??)kBIF#dpM)b$W>R7=iz5R>He~nL=<|*{F`67 z*T*`@Y$W+YV*ZYw?ATl-;6Yzt$`&D|g-A&=xw)A#_^(t^IgQaYmDGxgaV)-SwT zzw;L&F4#u@zN{;g-=54g2;$eL2-2MJFo8D+c`RL%TvEH|>V|Z?Fd8nu718t63 zk8N+2rmg$IOS36MhfY569w;;C+^I;GgSPj#emjdXOd0)Z!cfm|>dv)KE`Mx(=4!n? zT8k;bOgeIi7<@DOXVd3xdZ7@~bCa~Ju(dG!)Var6e+4AQobdj8^IK@4exh;1(#VhE zZhFaUG9%NA(2<%pr(Il(2|l$FRi->!czuUEi<%>( zw@B7kVZ!FUF8V)VJ|z?FY}|06Scx-&?cdX3npvVncAF+N5oD!+&6Z`6h!5{yUfQCz zKe)B8hlNTrM;%&9C+~`*8(rU7X-8S!{hpp2>Po%wfmr^Z0^te^#hGU^HKEEsBJBPN z=QD&;Ad;hYk$Jwc+#c}*LQo9>NT)A@cSxvMF>2JzVqjC~zKQ?3Y#~UFDV`jWsnxS9 z3KwG#lb?D0_$n2%SP7Yfeh*5KE43vZ2m1r} zYa}JXfT>9$J>q}z-ob^k80s-5;+xwokUlx?cfUl71av29Ot&>$WQ8}g?Kabp9^NQG z;J+yLz9{+wMXH6I0vg`?ROX9-OP*7;0^!exd%2=lpC&$uW%V4{%r9Wcio>qQ(+ zDOU`v{zFp^P*sAQ#C&s0ii3<1=pOq{$;2SMe(-c!s$w8f@~vQw9pH>nK;gU6)g+1W zi;kR2luAc9P#15NsU}N869!Af3mAqHK2lI$%oQeCqvnu~Y<|r$Y|RbaRTAO}%zs(D zrD9g1NS8oGVar;e68`<|2QYlQT_sthvb;1E;#{+WC#zVDx44GxET9h;+SL*|E(+4j z70crs$xs$>ewpvHm=ZlAGS{sFG;w(ziFCl#{KK~*_1Xun>2Ni$V)Xd&XX=XzaTCQ~ zjfK@xz6qSQfDfAgHos%39JBp;5Q`3-=G~Wl|1;77^!Q5}WK`_0>KT`8*LMsTMz3z#h&a7j0+4YmM@U*>I&U``!eXOiY(QVvjTOcFlA3HwEc92 zzjr0!vCJ?f2Z(hRk%g&Om6-f3#LSW-2b`I*2f7sPAORL%)YP2&Tgnr8ESN-U_ahm^ zRuMr0A|k$zB@XDy9n6bXtkt9ZL=>08{#TH6Uq@bEQ(gWWH7zZG?3SFI9Od88aD2ih zrlx!Q`v<%G!QFaQ@%8cXtZ$iM-GlR^WA(`_H+Bo{vM>e)M!$XQXJce!Vq%(`nZYtQ zRm$=wdwIdboLp00W#wlYCQ@!vDH)ly@%dP}K?=mVMw*5+ge%MG7>3*HGxN_Mh!CfX zXlQ8%21F}1c5_P##$LL^wOIJQeQR4a0nFcymH&H3^*mZC&?fqnHkr9&ZTL#wuXqNL zEF9^~zOJs;(&FeNLIm`sUk6QWEWV1Sy!ZfFTZBMju1je5weBYENDgVx^m)S}A0qEJ zChnf)<<8z&vXftW=k#%Q7JY+jjCD40~LWJc^B4|{82 zfz!ma=zYWgx)51fS`u=)A&Jei5p;{%=@*&!@t4|t|Fyg8GFklX20%xR%ZOqp@*;f# zlqDAHe(I0BQ1Ki5iw)U#Jc}s|iRyOOfq5m+G!RkZ> zwY9Ocd}|%vFDMJ=oP&ZIc4lW!CF-&&;j{0E1Ul+Y77_`a#MfL`QkT~=uqduRefKg` z@3|m&tl%grQ8`hpIE@u)9v~*og&uQAcw=~UG$xZhGQx{kCIJIe1I*C2n`rPzgOUb; zB9n!sLNX+m2mdvzk25hu#>Nl!eH#lf#U(9zgna$A8#tzlgM(uhbh`APR%B^qodx)j zNbzc72}!9xlt_{wiio&pWOu@2!2f4?g~U``S)cv9O2k5QBZV+&Bp=}a?22|iVq&SA z{5M@Q0fJo7H?KcJJ^(!n>+LFbXkAN^_J+*rrTgYocK9=|rV6IDG;56HHYtQH7Zrb= zDWV@a&>y9KaJ0)o=-DO;`Q~QMbDK1LkiO7{enwi@T-BzbvdQ{ds+j?HL^=-AQ%%oJ z85Sq$?IqNP*R#SjUx9~L6DahxJcXmN{oyA8@K;12#_6WLps)@v3hT zyPR3^#-G=VSznMILk`&biI|l2Ow~rW{16ewo@PgzO4z|-C0q$IKvXk@>zZBP;nLJQkk*IvR~=qbCN`OQb==SK=)nf35u(u7Ne5klTOyttf(o~4 zTBkXvp#=b;* zMV$#JHYFt^H99>iiIxG)5)Gn_>&X~*Y`;El2r#DCVu*2(P}NA9pupcnHjE_p2d1}f zO*M!tQ9wb7D%;D38JUs&doc)ViAm!cgyzT`v2o$y{d*zWRkj02+|(R*Hv5(53GP(D zJ69+flY)Nv^G1vcQ+0I$ZL09f4*i-dCJyg&Owe*N>`W@?rwqBV!f_$9dIRRdoWM0n z;X77HFzijMLw1F_c06TE;*V}%KWJK&Jit@e(nvVs@*TJ@>NJuQ38sjdbfNa z(5*CeLV)9oYz;HKXAO%{V1g(1Eyy>tSOM9MhRQ9fs}D>3_2P}q&RL{mLAcyYOi!vg zF6@I4I&s1v)FgAvI~tm%J}Cie5UQNqKer9->yHep9A}rS06ohMQsaLGJ2mVfqtSku2D+)?!c-`vp zdTO%9Y+eKXa3)Kd_MH`G+~b_Z4^4H=$x6?o1D#UITwFXNqm}s6m2Wf`$c!WW)8xo-cOWpIc_K<7JtCu5maeB&yKLii zbD)le$wj@+Nl!_G>3IL275p%A@&Xc0`y(~UuOLp&`EbICkTV?g-y~BU18*&UGOpJ*!HZT}36AY0)ns0*i^pN+BIr|H7<>c_u z{4ld|N*;L1Nhm}|ecV~gDNA9?T))aF6G1`_;Yr~R*XRl&y`PS!Gd!B@Qd0w;^QMcg zjRPVmD%w&?_cx1>wPS<+j&i`R9?G~k{nr!BFf<=6vTy~0WV;(EMirBlEi9CP*x53Niu zAdvN~%BmAFv-uX#+WKy}-E}G>YBnpoy%|kA^EXKJhRJoQUBwOXs4(`}#|1_3ZJcr3 zU(8YyGMH{E6QMH5mcME8ikQ?uk}DLIBK^eWDeTF8%lA{b@&)MCb*7>2iy^x<<0@5XIq?RBTcfkBZeDi(Q3O z)M{BX|CbG!x2zAP0c^r=)0SBG)@roe1@^-|jHfTBg&ZA;XY}^k}ghmT9KWQ!1trStPTSt3WZpB-j(VStVg{AIs2%wQb)^%374r`=B#S|ZEW+$%9V)^GfPi|P%sa~UaJho+<^6njZ!PpYl=Pd+Cw z0C2EaBI9NXIU~mQ9S^bNCt76A-;%c#6O$FqEiae8rn6843flwz^ih!E;ovF+PG(w- z7)kBRKWC0pUXuVriB@A$cxh?qcotTB?RvMq07w?->F9WD9;)3*ch5iAON7Tb2YDMXGJdLCK2jd7uP2vDfO@tJO@-LGcn|VAjrz-i0#HkQJQCry! z-X@9)5+S+ay5FUThdc7?>RL$?`&EzWVI5k~b`c9Fr4YzuuqRq^&VoQ_Uf6MIF>|H1 zT7zYBvOSuwtgDvxK6ZNA{*G!~V@j-?*al$npy1)JX5N5Ob{mH)>D4k_;}&Yita-1&4h~G5XGhSipPh9NKE`QRSk`lY&9#ML6I7PSMo(dZG;Py zaB%UOeoc7$i*Xtg;ktyT&Q)608~z`QiHV{*!_$0UlM(R$G>N+W3_)na0e-;em@I9u zd%cE43X8W0hUlr9+#k^tl&MF12f4^;&-*I!?NJlNc&&xuAH_^fO^uYpi-P2=w0Yv< zXlaKFcOVB&Of~lY7e|^?3+dWTi;FP#&&xAznsLm|q6>FqS|c2c_4uX`h;tR_agnFe zz`DZ8x^u6vO{q*kAZNQgFU!ktBlpOcfGed~dtFwRXGocFn%SV~9UGqxf=<#BFgqGp zOE698Jgv&911@eW+>NDI{5hv9Z?C4P2dMXSBXY)Eok=)17hnJ}n10r7B}7f&!OdM> ztqBnwoYh$m?B{g4#T6FmdgoxO+AiJE6*z@wB`-s>$N0CCP=HZJ(n9aCiRHGkSZJof zASE7({dwieP4v_ZX8wD-s>wB{xn~mw%=+f$r_3Brdo}FHri%=0Y#G&o4=_-F=%ely zMasg+p#WyDi)viuThJjf#U0BAh69L5aac^%HQU>o@QWI4u?YB0?9Qb*D9WaLM0<>g zOy2w&X#Ut>YCNx~6*@iB$PxxK<5)@n#YSj=le+r$W(?lpb2b%uR}l zPcQcmCL2kdh(cFBbuzelLd@=FdZv4e8Hv;bS}oNgFFF9*mL2Lhy!(1&w^2#er?pC> z;Vy;~7?jpG?_(fd-|a4$4K5t)MZ&*1ow*k*^nS6&50Z~Vq)dK1-ySqQH40OfuD2-&HoK!{Vp8ip}K`4RdHsopFLP_R=!qd(^mkquDm49JDe* z#0%qGoF>iGL+)HZYoyw{YYQ1754YN(fsq1v&bh1Ce&qTA*MH$tim(u%%U-in2gGw; zTkB9w7uT!Wjb`*TUeDQ>rV+_d$}lJmW}L@Uh>&u;k$%ACveUHw0W<~{Tl7EI7BWa6 zPhFJ}D6Hx~%b^1X6{uTO7k#}&ebz29R=?!_s`$fh+1WvKKemGUUKf6zl-=+U zj&4f$9CrF*Tv3V3$f$hb`)aAd%;nY7*Wd3w>wAy`H8IO}qzyPFbtU=Xag>a=RQaw< zw^=z1;R;H%L_XLa@E-0&CmVKkJS!rb*gW~{i5r?c2m<7git`%gQO-G8cPhq*S5%Dp z@EsK#CP>+iBn!uKnkoD`43jPnaBNC&lzz_%mh;g&4;PNdDI{{DIBznpKlXWezi(A~ zJUi1k!Z$^S0@pFbM-rp9@S_)qfHadAdrz-X)!LZ51w$@8Z0w*qAtXdBg4o#9@`{R* z2aOD7D*6gOFprWaznrP*z|bR@OkLSluBxq#SV3*y@jdyPxP&+=>gCYUZFT?iH~)@c z>i&_Df)SOcR+UAjx3|JTU~q}Lx;g+eh$TX5nn()O(73exKKahPQMN}fk z3lGPKMIqHyU2gH&8;mfTGa>AGL*;hS0SV_wanfj-$07H|rxIyG4u?b##x}|~gfso4 zA?V}2eR5?40thd-fbzGZ(W)-mb}PlMU!7n>!G6}SZ`XzCzI0PvZv`pUi(l&{UI=ud zxXTzszBFeNL`NuZm9$d_{6Mnat55}7tFe)C!A6Ju`0B_L-^g<&Cr*6!AUjaTa{G_V zP^1AI{9z;@i|Q^m{vyXcg_lj*E&9?y7F7(}2M=Nc{IRtW7=`gdiF!Y?XBkIE^8ELw zLE~+VC|8ehr0-HoOhkC3!+(#>MA|a9p5e+k;HR@7c+k5Z=L%r%n%G*qW@hA1M z7@22aqum}U!vE&1DB)fxKS3Ea{cld@e_l9ASmeSMJTfHayJ)l?^zl!lc-Q}^tr-#W zY{K#k)gCzDS*L;7q)1@Y%i=N#B>$HKw)UkRvBvYwU>sF=}il8))Z$>G4lLQc5w2 z0x196$HH{%7`|kT1kU=wAK9KnFJmZb00i-+^hm1Kf94B>{O1ny@+Ps6>5IVDf4s$ z7-glJyQ=-p5x>%+ksi`DPD!U_WW%M7h*9~>IIb|kOWQo%sVbbCpwUrYlvONN`TiSx zNXOU8KqqGmIkCJ^*1v4kCNGaxZ-v>H0*x+a>SS5a6lt(41BDKCvp)d41F_x2@uQOU z3(L4Dx9f(eBSRlqB1XZzEDKERob8Gl8a+j+I{mSQ>aD5nLE-hmPvEzQR|&<*Z~l$* zZ#d@wJpLGi9f{Tc?5dal4R~^zotj{sLqcWOb&b~utEl2x(T-|f8;-<^s5r^ldM!Q@ zyA^XJu$#?`vGCP_j&1k4dF^V>$$Ak)zbfft7gG_D@Ob3923Ke4#dTqGB&x_3NNcZ8 zMK`f@2ZsOCQD(Bad&{$5}q`dibpGo+*?-5&p@uTI8{2`k0BUnNn5WH1*-R!LL1uF+fJX&;XYg#y(TVil<@a85~Vb^l!aQA#-3K<%^|7U}EeV4p5j zno{#jy|@U?4EPeSj0@5_Ffng8EI|FYHQxTrw0p`itZjJEZ;cp=ogjr!X5+}wE#ju> zM}}g92WuB3Qj*)%%3nE+YuTUto^-;d-P$8YQ$cV4$dS8`L8WTFQVY$E>FB5px68-c z2~>yC?_7$XPOcVlw7TcZ7kzMd2s|&d8r&tV*>-fUXZ|9LYAFWkGZ%;xk%A_3zbdR zxUg>vmtpTmbOt*1zDZCo$RqtR%La05!ZGIbE2J#Y%iQ|5r9GxjR72u|EGzbF_QO$h zSq4EWSV3|HdjQ3%BqoI(?B34K_~_RyCyd8mzDl3J8_2;r%2KGSHZbU`z1m=C-|Xmv z9?6dVK98(G-l7JyWTi5K{rN!a2-h7FQvg=KEZ|EYb>O4lQ zMaWW0V#B*zzQ%2}+rD%??oKdWvQ!{*U1-eMC!IbpFl6{|kKu|L0c+J5ay=od)`nU| zMXjJd$H^yMr$3jO(U3l*TR1U^;d}>0>1w$NJ{nF_^#1VZ?n)YW|YJ(e|-ysa_j$P@;X=!tZ51XBXst z7Fx~0a(HyhuQQgR(q6tqnc-po)S34V{r4?gP%68N(N(}P&2Vrvp9Wib{4o{=hS&rK zs8szlBt4xN-PV+fUyy8RKG+_)9gYQB3Aze z`?`~iDZkj3!E}GSSX`KQR!8azt|kqcBO?s;pHM#@hFMdbJ!PKY=60Ay zR{+XZ0G(h%6{7ea(H-iKlW_CQvBm3nvm71 zx;zkybFUO`URG1dD2;*_Q_~jG7(U4oyQZk7Emqj{-~21%ufZLBrES=i%Nv1BW*qNHJEE*)h0(Mqsmo~3QpvunCPtcYRx&U5;kyZ+ z&c156EvL2lP7h6yW|ArcDZ}FBwSs&M*;5~h?(YH9jWUyJGjoJKe}BJ zWq+IXrDnQ(Sv*FUZyVg9sn?C6aQ`h&%h;T>kVyxHyL?S?t;YU*2wte}X34#bxE0TIV}4rddZcV{ zVCgs79S^P$?U9tKxPfTQgi4xb-IuQ8nY$NLzql&9Q z1;}%0@gOg@Z5K#Gw0!=h@xsH>;~IX`Y^1O^mgf+}>*S_H&ULeCw=m@va!<}nLRD%= zSEz?BF&?2(El=)s8RtcV)0mY#Z@L(f z^eEajJhA5WSrRJBsbq75 zYhyhvwOI4wij#=VE*E_H5ldUc5}%o5=@BRH?e(22);sWU`}r@uCw}h3nL4 z)t~VBcN+~I^L*2_@w21!sIDwtUwVgVou2^l<}GEFH!jaD@L9qR=B0ThBV1xstwhQK z8?vuOPFub-Dd}{pkS_2+)v~vSSM>6Kw^&uRdrvn>Aww-owny;ytUux4;@Ww1f4yQ4 zC;l*+nc=>ixG{Jh8X>c#6U$y*$#A?{W-o5GpL9-)?J?o*dAs+{+?a`L98lJTsoVgd{zt1wpT)4%_CFNaBUFr0#>Ao`+8=T`==d`r6_;wq3aBCrj-MmY} z-xHLb&Uji}TCi!4{ukk$WXzo893Ev5))sXhYjn~;obEYDXR*X=5pmVnQminzk3CnZ zE$g!mJ$eXDBNeZaoRuhXtJ-S}jQ>2$;p5}O9KUoq<2Sj;JGcLg=;)7fw!V<$+jFAD z8SoeDmt}a*`5=dMi+d!^(bFkKr)v$qJXLg4{3$&u^m~IS>(i5B$Qpk&GsZ{4hXCTs zfAH?zkN^ukpA(1`o+~hrQDQ1wufn$gwL?g*c0ZmYX`Wr&8usK%Euou#Kg;Pi zX0yI!QUX#UrU9@M8R-Xp<=_FZ!4u%S^D`;20n;;XQeqL8`#0|;aX#Vh?ST@Cq+#K# zsSLnElzh4E{^xBn(Z4H42aPgqI=^d;kqk-6W4y7L{$|YNR8682HhF%x9wWK^88Xu4 zr9)DKg1bPpY6<)`DH1X=R*d}lkSDUL;G-*Ocd?3GAq{``fc{1=ADqOfz_RyIjZst( zrtprEYh?t{r)$9$t2GH}>6%)GgPAgqE(8$1scRFg{=RBO?OG$A%N zo!yO`{i4bboD?#J%)4!WTJ7ZUNn^{d;&`zQgjH@Vsrh&BJY9>kzR7h{+ELo7!s;lQ z&9vjuTM=kBy$^>X@knF|liD``jdYpnm^k}-ihu{Ws6}3|;-Maz26z(x1Z~wvao&7a=zv+5KL?*j%EbtF3j4iCOUmM5|+b1u`h2=~0 zeK#{bwFp^l@}4}e1+84~CyY2a7g0%;hlZzBW6CmHr<+_zJ-1ieuDd$FuBEVtE}8oI z2`^ozo2)gN#sEP{!9&A?`8fE?6@;`@RP5PG=l+_{4-fDaORug;e2sRtV97XiqVbj4 zUU^-0_0|xTR?b>eib@j>%Tb*sF>pm{s-^~EiB+1qZS(J#*wm(tH6QAty~~4HV%EZU zPT!~m-7cGsSG)sicMh6nKTWo$q%&LOkZHrxmW>#Xh0Tq*220RQ?xtE$*^$FjG@h{2 zL{*SOBC8drkl<3C*<`7h2dG4-57I9d0i(nBd2F^?f~vmII^D%$JiK>$Akl7i>6`8@ zv>roaNh4}Z|HZ%I1br(P;0NA2;pe`MVp)(o+dUEPBTGz4T0ZsqX<@+L=+&^uLImc= z&i=&i>dAL3&ErJkE6l~n$ePUHnpqbIZjzuUXW2Xn3ejYff*dOP=!iR5bpD7)u{{ln zkKgvWb0|}q`bCoK4w}k$xku>kp*-b`EKhi9<$R&qDms=_dcw1lkKDp3$@A(hXM6_( z-Tks>2(MRLAja0lf-8N}Iy@eKVh&_h=B$>h>Z|)lhT5GWetk^C!%~H%B%cUA5}*1W zCq+eFGHhYQb%ml_?9tNFaImHm);dnD!aUxpE=`a$T^6H$S;VUF!z~%0-gdKzHkrlw z?%Q?(P73&)sfpB+b~_D#B1_q_z&^psb+zUEMvR$lz~2i!t<^bA?+c{}XYe>0QESI# zff9#%=VtkHmwH`li#zma(JT7kcw19+Tl~V@@_1Z%V}nCa5?#k zPnGPlYT6jGNYtqj6_X;O!GCIyrao%SZDnA*W3#EDkqk?#`TBBi zudX7aWJU!ScHonLUrKR%|+1@xMQ+%jyXr`N^Ew(>RGxXNo44lX4*LRZddh zT{meJnI7xr%YjZ#(Jp;R22iv3=)Ca@@hV@$CBj;( zwSBCu9d4gJ%1zX)?^4oQp`h?*CQ-m*)!cFXoYwFHmL;e0hLKc6{D!uGQO~;xgL3qh z*8Fz4Dn!Lqg82rT6@`KZ#o}g%8DrVCauhdX?o!L4UaUT}Y$(LsQAoJ&)IR44MZjv$WB}M|8Z{HqFCo};{Op~$iaU7|& z?J9JPXYch3W%}wzs6J%>{zgtUZ7FPWgXKuG?FGyC&Nm6?%n&--Z%%_ijI69pwnG`) zK{%MdE_^~aCJu?)^Qjw>P#2^SPPPKUi@ znKX6jb0e8-C~`u}sAh}w?T1@@ApejN^diAASyf_L#;4^SIn;!C@wUwqodaaCSIWE- zVH}>bIayqEpDg7@y}kh~)EbJ?c5(50g|5w>;pY^~k>Sq%tKRl!#%M@<+37_SX-0JR zG=wcfY9|~%?FW1UanG;XFAkjEm{w;@ymo)1%ggD~hSk;e2LE_AY*~}6-Fvu!6rDhG zcDA_*qTj-UgN_5bF<=L4i=MTbcWh*;xbPOP)XFW7=28BQufd&0LpbtWO}Yjx5-U|M zH8ri&SbwoXU(&&`a-SLxALhDt1#TDXdZD4AY3~XJI+CHnR~Vq+vnpf!m|xn0>?p87 zKA;h`7czjOvi?+)Y{RMy@0VeTqqCcV8vNj*LS7Z?eSTT|u#OcBCr5YfSLNCV@7;dlM-Y|{PmJxxK+Z7q)4Tx=m?!%s*^rU4Ogy*P1va!z}Q z1_M+FqW3NvlS<1P;>#;wJfT<7O(le|?OF!`kRw;4jhd13oMNTo2DOF#gfHgCWi#9) z-a0vMW$OX5Y93Jy9$^anID-Fi0QU=K5LjLE*2RK7S3_A3RzADZ*1_-pZEg?miV%0 z+-ouvg*=_`Y|QqDrQhz36D!TNrm7WaYg3(_l0Rv_+uL1S8oCK;XoRdG0h7J6;RfdD zsVLbZ?#|KCl(1EnMy7_2>vcZh6n%u{s5QNr?L_G*MKso$(WP}xa`DL98hvpJ>;sgw zd7hT8K0Q14I&TQSc`IVEW}k}m*cEW`or!U=>AdhE@2A1f4vBQshzTe-v-*1oc4+`xP_m3Q1@r{ zR*qac6~?@^g8xs!>j0Cu6#inXb|(Y#5uQYh8-^B_DTK2}+C1Ugeq%<*dS#1%izs4y zCakJ?NezvAQ$>p@;AP?1X2FD{A&bSj>*0lAvOTHORZ_h1#Hmp}a8fvBQUXG@+VEPP z*|dXY%ZBZ9;_+H;)>77HRIFAOJKzhWAHAeKjf`3-MLCYu*yoDR?E;(j160Hf`ZYCn z%bHsFBlX#G9*zOn39+)e9E{XTJY<=NuM9D*md|ozE7dk#&s^ZfQk=$M!4y$QdrD4@ z*61GI2Ym4W>-i4o@)BXg!!hrBBDQLhhNmM9wmiI^pU?N8*103Nwq+T}{Y01RT=`xl zEFd&zgW6o;%z&XsGKP286li%?gKp!?TLF_FdqA+lvpg2t=xr$e9^!1B0*ya+&OAor z)Yx!$A_YA)^~@yZIeOeFRq?Tp2|k#;D7(q{LXT^Cu82(z|pj+mwXNofETleNC6gVE9ZG3e5S9ZOKXg$!fLf zdR^DI;rMZVyzikjI7C8z>ieGXb&dV`SrI8Wx5Cef!x#pCg!_op_RVLTzH}^20l`Fb z%NB+x=Aww;jg-NDh3j`u4TD939Zy1g(S-1__1_j7CcZ-tjsx;te{7BpmMmccE#Sa|JayM|$IdDvf36r~V{GqZ!LG`lRn3Uo;)y!i#-3M2Zdq&W#M#<<) zrzt)BP$8rV*`0sWe*eW{bLAEiz>Pb37ehSfZgQR9UuTnv=JZ`5J!Vw0yjj#WIKDYY zG5hr(@od))zA0e@ynZokb1C*F@+`Y^jBE8AiA#~Ki#8cXwj@VCi@(O z%%(YmwjTv*=UU&zJ z$go*(-)uIJ6wy>SSg!a^>MfgYZkfm!qp`iVy8J|Ri1ta>=M9o(0Lrd1>k>cnlc%ZI z;=bAx&^`z`IW>G+ErReOJ5$ zJY62J(Oacjpxz4GP*%EM4;SSSf}4w1^N5e>r*b5YU1+1sruY1809v3K< zmb8A96GdL~c7RKF>M?iwIQO<^(=dJ1r3fB;4d{&n{n~uLx7V(yHmpuf*%2DSTS3HA zNcnug7q#m?^Rdv%Rv8SU*mBS4sCB7dh1sx(z5Q&@OZTpn0}f|ZmhB{~vT7?1Q= zQ)9n};{Nzfn$OP>8zM@rUvIF{2P;qm`rjeg%_YEr5{R=jFtN=&t|qW=NjUWe0cUa! zLf6RHQ1QZ+CKvz~NBEN%T0bvmO0^cp^R45YHhXA&oy3XLbqh+YX4A~)C*xHl1Gok9 zE$&#BRm)_-Y;a@3Q4S#JVz5u|j;ASDFyhvs&*Er!KD9{=CnVcJY`^O6$r)!TD3bX%Q!IDfEo^$d6p_j`U-^n$(FyFsX~ zP>;<^;;FTdoOo!wh5ny)DLO%GYE*{DNyZ71{LS{Y3iXUlzkX-!ATs*b>WnO_wz&M> zaL!4&?tSFHq%Li$!M}zR$8q3m)Z=obC$ve8lG@to&9ge+ZnACO&1F9cIXRps-DOzb z)P9GXd08$_qq}+Ih$BZ{Uf$Fa85ucAg_@I+l7&U8P3!pK;h{ig?^BT6(@G`Gb_--O zxWnC}Rc1AL%C^Ag35D%vsixL_J(NOR!HW3ek9!|rX{^zH*$0f8=;-Lg`NsbK0vCGL zJ{kK=oNVEt=h`X`W;DyF&XBdR>BrquEOkZ*;`uqU3H8Fl!Wp+|=We2^`qIPi;KwI= zOJrJ_>mD6OWlAQd5JyEly=uGH2h>HTwKB}Nh@7Cl-;VDuRloyhCVR{TW%cf3rKN|# zR_us~sMl=}nzevY^5nSAkHXE#;UIT`uL>Bof}Nct1J>b9Oj3zw1EucU{Sovwp^BL7 zQ!wCGx~Wi1%e9^gNhs%-Us_mrQc>?~vODt6%k!(L0rH{@($G zT{&?~lPfaatF1p;s+*nhK%`wM5h9=FRW8lKJV9UcFeI}~_4)cs%MH!OP*0yU=OgTM zp~{9$;8i2k5eP)+E=MS`x^9@E)S39m#lamb(%{0{HeuT`n%Z0F{hC<(CN9M{s+Ud~I zc)3)28~0mJiIna0``{TQZr-VB z{e>Fyp=}5=V{%LkjHCS{5+&2v088KPj<=O{BvJ4|22vAaTkK{yZYMm|nnb@D9g7xo z0{7pin!>yw_(27p41hQKe5j8V<5W=9sN&nU-hOMBUd2c-Ox3pp0?s(tX4kPWJO3!l zE^*i&etY`>hZAy5#I9#<&aHb`h`GP&b#pQili|+ngD_#~36OQPSgVI6KVWQ$Oga#8 zEXhb1vcg)Xk(`q9HozCU;5FYrZ*ueDYRAOwa(91S)<--nC`gR+`qRAE?);q2XwDNJ zSGj?qvDf$e*EBRGQ^uoHWS9F*a*VN7^XNqL6=E^K#l^)rE^GNOtAGBq!Fb7iTuWWu zr%OEh+lE*_H~dfghlipoQ0S$4t%;erep*_Z{oUc)#U@v)@>>5`!OY!4sS;elch~I) zPRH{DHC9%j{Ta~A#6%jir$gEz%jM-Ii3rb1wdGvT&>Rqjs5>^maV{){ClrB-l%M?g z%2ES$caD>l&a-R#D4nh4?s8AeM>-uGnUK(Ml0v`R!tH+Xri?c3$y6#)%=5Yon=q;{qX)x5L2vM zu4+O!#R|{*WDvY@GDj!n`9)DoX_-Mg!yjQ0_&!l0kTC%a5-Wx^a6ij|1A^IQGJxQw zS=RA6bVStS*}52WSSfE{+jqg=UGh^?Ba%`ulby>4A$t~M6^zEkR>yHKHdv0V-MHT{ zkiiNM1}6Som$$=`q6OhczQ;lFC7GF#iHRl-5~}2jZvZ=TjK7hpr3k=l7i}xGrld`3 z{VN;!m$`&huxlx3fBJ9{Oqzj|Ne{|ca@w`xj(cBJDe6>8T|&yMv8bO=?!3K&hq5~- zA@L~VXJlkF0fjW-TmcQXrZjk*CYin;!oF5;ILLljDXo0J2UtNxM5d<$lpky_=GnV> zg89*l)-m{(OiZm-+dK|9>dYCHBIDx9L>d~E9^Y5^uO5CB-jU>6_Zc6z0o=_mE?yk2 z`iXBXe^$rhZTAixmgLB9b#=^Ze$sp{+)ae7N+c=@0RbV55PW_eO+ClI7gc#863Uz~ zS>WVkl~I75Wb*&(0wfe(EwlUFT}O?5F5=1oIBAXB`3QC*pzpfvAHMbU*p+raPS*n0 zRDnuxVTBc9Vq$gG)w%XvgOk7izJqq>uk(8!oB!xOz`78U>~#< zxHXKbRIKF+6!Uot`Kgyw!_z@fs5!E8u^RMm6%yzI;%Sp%M#KP1d^Y(I`!h`Thg})# zVWxDRwL4`f`;RJk@?XSXnVE?bC=he}fE~?PUFZG{otfj6@00EA!~t63u|JEnnvER3 zHES$3mxlqG9 z`E0VBh!KmJ+fZw@yajJe;2|`Q6BQdPNy1J?7yfYh)%|-)QqtKDy2v`dt+~W0CT*;= z{+`l85YO^-8my)puI0P+0+Xm>dJesX1}7n4Zqg|?DrzHK>%K9?i_LoVI}1~ud}&e9 zURDkzolfhhjPUizu%uK`U1{d9zsKJXqne?n^BoB}BwVMk6nLkQM?k6V!(~^XfV+4q+7(LRUw; z0!~FmIfmy(YDsDs5u}hEG0vTiEPZB|lK7D~*`xy3(?zO+Iy;JJkzU!P!H%QbmbQq9 zFn?>pJNXGI24TNPr2o6Vv8hOqfB*led&{sW-?m>AML5}el5RitU z29Q<}5RmR1y1Q#YLAtxUhVC3gO*SSp^i7cf(|5TC zb+vNj%IUsXuVB2Zu#|zZ!K$(nTDsS%l}wEEOV0{-f8_mE8z{?pEMSEY6lqx(aBEF^ z;7(SQ{G`?Gn3IE}$P-?tr^jEB9|Gf*_K~}&9kg}>=6Cv+LqRUD=OVFBGf%U6*D zztRk;f?UQ0Qo`IkAhlCdTJF8HuWhpSAK#}4D%vP6Yg-c6|(v|a@S*Jbxk=o zZ{RjMWN&Pz-h8~$Y$~?w1-r;59fAMFj`0N9eU1zXZ@0%ecIm$42HQao>MAzAWmlHD z9&iLmZ3d(H{FNk5B^yKFjlH(GbAj4zc~}uOCI__A5kZ+9@={FeHYiN(EwAg+@h-fA zQGXR<2(OR*7Wri)+oim%uMc~!de>^cHe`$0ofXFG2tgJBf6Y&UAZptm2%SsI6Yi-X zwXtX@wZMJM&W?@+F=dymJAnHKl~w$kd#%zX+LmdUZPcuWH*1N1!f ziw=p$CByAYeo#g13dq=X0MSrMX(@podm-BnE&UAb?@yeN%K`Pn^&|eYS?M$VTP^s_ zjrU7_yVQpJ0SH9O50bZuOH{7fEx&HSPN^eI@oI^sH*aR0mR%?lv+lZIf=s%`ebqJH zcUQ(3{);W3t6&#v({XRgzYexH6dtae-CqqEwCX`D9#^>xw>1@O$ck#4|9&FkfquMI zXv^;4aFnypZt?pugu24@>Lopz)6P)XlOHNFk+Ao(gsT39HPDOr+Bm}5~ zEf3eo{fB`mJO?Tb=>^YP&_8VtlSCeWI%Et``yod&m5(RNcx`tFHkHP%0z^?c-oiq! zaVeV^cQ2ko?qOR$n-x#NerDPZlvVb837pnXo*##HQ!93bhw(eS5+Ku}!n~XNe6}Vv zOW@3XdK{+Ya9B#X6Nm40+v3=t#1;Wzc{5bg4fLP{9_JIeHy&<^WnZhpU@Hr$%V&4V z6vSiXNPyarx#4~MDZ-zPOeUeHH%`3tc=9NQ_Tr7pl134Z^QZ%oeo2v1*L7t53lui& zJKQOgt4rTC+}bT6?;m0!Ys#LotHGY5e+Fb+_T_2XkB-AcXMg=ly+T#T!&j&Z%EjZ3 zBNK4pw(h!D$9{RbQTky}sW&^*!F%_eLSAV1w8BhmczoMxF`_WID0q)V;PS`nS6a-V z8XcCMm8-A9yR0j8iRLZnI12(;h~NiF_7%y;adftw9p;h&_EL zhW9Aj^rPo#X93aBl{WI!`kX3{_fLZ|>Vo7qJvlz9DJJ7HU!~uq4JE){T7LTVt4K== zS*Gd7f$>NBRFWw8W3@}cNhI3-w7Hmfo@C;kW2E4dS{6M<k_e7!TCO{1TjmGMPbC=R+g06{F= zY^wR&i>v%tXw0jeaarjtH$`u5vxKqq4oflo6!JaYo0|L1crUJ&9C>{fB>0zH&Y_ zRoJ&cg}bIIqSejK%}Y~Q#qt7inL2I(UAZ)Ui6Q=hpyul9Hq|~GdM&*-FwZQ2jO~ii z<#9eg>2D(A^Aui3<-|uL*AbU}W-1ld={Jl+=Btoqvr-~-Xo_uJ;0>Qm@5qjPnr;YE zDc(Z1MVkb4N-vS-V?qX2pWE*uKUHBaZ`Zl6~tDdh0jne!9_eo%2>t zhyvtu#_o?LIZ7IF3^A?N(&Pk7Pa*#FI{}%YP;^u6(-MuMzdHI)D1v%Y)UD^`;*TVFR4=m$K6qqxPw8>(S8! zKrI}_uuhv^tOUU}ES2C+=u$7;8n2EC4#u8+xu>T_(PaOA=xu7#4E>e_8Aq-CO%!zKp?qaZVoX>7PISpg0M7<)$+Ey7kn~AL+DPeMDZ= znag_Rs#GlG_d{kIMKa~^oqN&fDIO#$;?H7o z2eWgHKXyo~2w2EvTc-;XB^D-p@=!X^v_Ea*3JNVKH8^s5y218_T1h8*w7EHPjDwOf z5hwIGqZ)l;lx?6p+>)Ay^>E{K771EXDIuRL?tztKdnc!%(LpZH&F!Bz9tacOsBJov zi0DBoycMe(=a{&SqcwKkVmCzv@i@Y+UVD!&`0L$EjDdOTAfm1i!5H4&FK*Xx6VxPf zyqfsf=gMPC$F+gbykX7wgd|J)YO^k@fxy?_Mk?4bRm`+!Hb;`VuK9dKw>CBvB*cVR zu`-uu}_>3dDJF5f2R{8c@8Fhy$Da9sCU*o61*BrssxVArvuA|_O zo1jeF7+c6$6sfVP8NYSImS$K}Wl1Ofvt$QemdRN}-MK6thNU`+ zw>gvRkx$TTXt?aW$MtS6LbI-pTSX_wY_6?&=BhKoREIN)JSW8j0(o6>9}<-#v$m}! z?gCK>%^WWwN6r0d*RrLSiApJUDJZO~8u*D$Z;4Q~JgdA;2+xn*d?r+n;s~Qyr?O9A zfj?@LG1G@KU_hk`CYR~dg*p&u$Ps{%^Sl>7FGo=F&I34tgAG5`?0OaGf?wK-sX`gd zd@A*>a(U?)9I%{lF&BxXo|522yfKz(uIv!$5`0uB+cmJ zD|O-GW$!e1l}-2Pnv$fp-!(h1Z7f#>2TbYUb={CE%3~@)Z`k-)rse?q1*Q zJ*4gbIqSZtl+|^DL%0#~&0V**aN1d!JB+*LebBGKL1{xJ%tCV5Hxo zhtEqbEvQ&>C z5~M}l>Eq4py~{6CY|hqXiI5i<3PrwZ+COvi*_ag$dTXWGEo?f9P6$16r!V4S-p4`>Rc>NNGztc8AT>!fLr8fp{c2* zQ@14PIQ~J;VQ?k|Pi6}^Rr0=c zEG#SlU~Vqn)>01v;Rc8M7D2DO`<~Xc##<{8B-C~1i%@Sods%6z=OsHm*W1eE1cupS zc?qc@QwFrMv-4a9$Ms!!ThL5U(4$&2KW62%wKc_(_=Il$FA-63ASNm=KR>^?I2*K8 zw3x)_^NF=v&-Pa|M*tpK8%aIu&m1Mu(<77XZ5UpZ#BEFHyVjd9bI`PIcVTgqC2RI% zbD8=XLW$Pc*dRGET#RLILUCJJBRAKanA0XZBA^Sgh#Nv^uF8kmGc?RrqIu%l$59v?;JLEllF@F#LhNHXqc4WwYf7D-MLIr&i@H(5HZJ_H*Xe9jIFFxAZ#A& z)H?=s^UU){K>C6AXg~j+WUnw0g1{!B6GN{ z_U~pbbk&l`L^%#3Ay0nXkdI95lvFgzoK%zdniT`mHrRHSRxMF4PqJ2r9Dl)jpiBe& zEAgTJ!Ty=Of6ACt(|(r$(Wzp2d7`*Lbn}~$Ce>~efJ?vNb#E|2azsZ*L!}hL%PnJq z$JC;sU)*L7D=RC3aBAkHUflHljw(Rws!=!Y4`FEiUY4lixTsWhW<|~&#AJDFZ+P!! zak{y(+sDkdD7pNQ*cxNvwQ(K3n1oA<*Y&P=g;+cIEb)N@0Q7>}#_sd+RUAgx_eNy^ z5kq&ISB+@;hsL!N)R?|@6P?%XxW(8g`R5l1J8zrxCT3lAd^2GhXcRuoKW>(j0$4Zc&he1Z%W%B~+>?(ZHxC*}|-R3mX50b7K|wQEt3egQ?s zS0%odF{Xs}wzeer!msNZav#AiA7UTThTFN{Kz?sMPi2Yl$2``-h!Qw&X99cK?qK0V z<)nriw#|cO8lB-y=mM>w`JBwy{gcP1gU@h#uS$-YcJ>K|Fh4|&aN8X+o~_{HZ*6GU zI=azrA2d25w_Q$A1~&%lP1Scd9LjD76zPraXT1t11-+2Rn{)N1oQ|d{qs4*i^3gOj z4!tyQhSo%Cnn6I`wIcd9Aa6)xCbMK+PZ0EEL&LSl{cT=^=H66687_kvD|k~MU9Bgp z0*U?9J`Fk_(GA_ldU#gnm@xeXuUc6+T-(*tlYjm-%yLKTXMdz{ z?CNcK$7gM<)(8oiNAhpwOFGHuv0eyDHY9=o0X4Cw( zKY^IT#xx_Fp|Fq|r<9iLp|I*zib_QU5vG8bx{(jIR9jYBL)TBuUWwR{RL+c zjdIoch6NFm{*G+teyVrX&W!XgRBNk&2Q z*SZKU3bqJsksFQu4Mw4@N0QDQtDqtK@NZ%KdNO@OhYBJM16HqTfOPr$C2vZ98rPh#SX&ZS(T zA@C(U@MlmjL>@4h2t;yG~Q0|aTeHpXK2 zZK9$|WVSoeY?|6!X$4d&{5cU(mw=I2t8AC%U`JO|jVQ+VGHuMJ`d2awKV0c*90XU# zq9P*|=s)+}yD$+w&y|vrW;e(84$JDWKRRUW>BS>Z)XO_i15mZJd39Gy|hYM#)`R1%Qc|;!hh6 zmjff~(}z_rV%6}h@2-AD^x(pO5UW?nBP>|exh3hLH^YnRY|;E!k?N9wvVrLXm|K+Q z^I_@ZcVhH@n1HR>&tku#bwjSBTW_k~lsbIMyn^V*e20n}Pw2hM+73GY;>9&oZS4Fh z(_=1oOxO_$?dhSvO-LPu35E^+6l@AOK?j{&ctpgqn;%@W=rIY4Ri0G4k~f(gopTi8 zIlN$K(Q==tkJf`utam7i*fcv~a+7HEjR^~Wn!#fw^Sjwp_^P8xiul|Sxg$AczvV?o z18%P5L?7tj9Z%+6{p35z_^?KWo=#t_m{KFppfjkis^-iH1;GsYmL@4_h~tvH1&m-6 zM`VWZx&R5kV@z^aM4Y|<<)tgW7MY_6!@P58)Ve3Zq+3}aI|qIE*Mo#Y6gwb0-lx;^lP6E>g;tX|6^(~9$W;J; zYhklj+5GKT34KoSyT>2J5emx3$1nf+rQ_v4hGUdaq0j%giC=pEV`@SX%+g{%Vj^J6 zqR37!zVXuWwClz_Tv058uIMbDL{ z*a;u{O8U?~Vbnyv^4QA1wlpAzw^-0HB|FVa%PH5VG{Awq`tyy%BURb2q91TI?h$+u zZDB>sg#I6e;8UOd9@pLr$Y3YS&UXU;EDW63Bf0@D8pRp7q^|gyYpMP>z4Mg#;fZ|sJ zsqo(ugfjPHB>A5c^52{p^gI9LF?@dXue3-M!h8QDL7=eS|0iGKf9@3j?>^9=$y{i* zf9Cui_M>0f}aLS8%9AXpyU;c+_xz|r2OlKNBK$YlkwLejq<=BLPonP0QBnR_nzAQH-~QfdtsJ>{YL=;RDH&Oc$WDeCd7?ApVDcml*Ryyy(6e~5m| z?7Us^FEGORaJ?&??j`-VTg28iikJ~b2~H{{)ns*?($Ix|HK82_s;@)M_|+?*p$&SOL~V$&0!gW|uYjy~iW!aUj^cO@fq=+U2<1*(@p*ybgICo5oTxn}5c8N6Uu9(mWvI}2 zHQ3z~^`53YRgsCORO2^wJnicMS&%B+R=o62212Mar6AF`sB^bZnyG*I-28gR$Fjk& zB%hop;si5`l{Cj&$mU$(*`y0M7kX$(CbqscrZ*)oM{wr0b_ z@zF`_2%~>QrIk^u*{{FR&L}D_3~Ul)r{kG1!u`PVe63E{o*{7zrQ|T_M{R0ks&M0Y zE7!+ZSuKdq^Y;rpJ`7eVUH%SKo!=ENgD9+-(Ek+)9Qn}TpL^kR4{`TPE-e-i6RKZih_waw?|OI%-^X zI~Y>kEP2BTLmtR9ddXN_MSD5h&%!)eyL);fU4oR9hXEy(9-Jjhw1F^l#RKLr^}^XV zRvjsI5XUZ(i~cA}*R$=Z22JI)6Z+S$^=d6<7lf{7w#JR}f&k+9i`;-MOJ0%lZW2uh z1qF@l^KKPleD0Y)Uvponq4bfG7Ka08+BYxbRY`W(Y4PY5Xe2WhJH*6%0i0p5h>L+u z7PVKLoiB2Iba?2rI|oZjYH1K7jVY?ynlZgv!9k2>8TC_j-_X+04SsC?+T4tlP$e$j zZpM1(D?2URLdH@|0t_0x)9J~gY|N5A*qknh>=w(z4j1_%HLW84}&G?iWQvw#zK=sUnpr9YGVFD0q>&~kf6@+a> z!&L*1^WN&(Dhob~@lp-02nO3|XE*muCmkJs_1?eVm{D-5a$Rts`p7A@?f1u_thm+EMK5R2YXQc>a3{0c0< zP2*Mzb=i%asY39&tCZrqw*`^RW!O=CX(?2)(rE_XU(jwpH^&l@e&|3#l0+r&dO>`@#(f9SxoXh_%G4pt zmME?+^Zd>Std1ik<(aW@WLz{fXCsqG~otA)h{4T6ww?kq~+rB31%gEH`Ov%?QWh}+;sUP7;ncfNV^Jjp4ry})y^R->ArT$ z4`1wl|K4HEbNbEKkB5iL^Nj~)(|!BiqqTzw(`4SDXwt^g3O^gyi$rb*e)er#>xb2- zv&18AHiw`77DgkVx{1tfp*e#C@WwBVjX{<8jsx8@%|D1MJ}idcULU(*x$)57y(zcr z*3TbjVOCX8=m57n?G2ab;r5k{m)TgwAWoncHYRqe5O{!)wtedtK0bhXsM&N`_KrJZ zk0ZwqCKK>1GnqBn+#ShH+V606b*(6UtD8tSkN=Fg|E%emt=G^94v??qvb!&hObWHM z(W^Ymutg;75!g&tIgETK*NIGnh$|jkF3UG@ykU)f=NXv#ARDSYl6 zR~fXR2gY1oPR@krL7wCS2n5!fBuj`wZ`OC~zMI-YLwBUy1et|->9SayFX(&e$t*u2 z9BER&T~rBWs`meit&1G=@YvL-Iz|HQ95ckqz(8&~Au37M|Nh0zwDUGF1o1jr!J?zb z0N~{t9Q$c=+vmVY%vK~2GqCa8V$oXvmICQKlB*nuJEO=6_b^kN_qeW=pfqG(Kxiz_ z$<<~&b4cy)&;TSxI?~(9nq@D z%#208_P4s0LhOIsTX^OzWWX$J=8r$KTFCAJrT*P?O37x3_obOKPGNIIOhP z4#u5pojoTWoD?oEsra+p`bf*#T9cKDcj;i%l9Pb> zGTxGKDWbnI^@IIoh2)RR7P!R;x|`dy2(o%m#zY1-WV+B%zRvr{G2i)fUcF#8{YN!@X0!r}GJuaLe^% zzB-E``zer)!P(#eaY1I8nkdjyh-g&@4VTpxobY!2w3=z)V`1^{I<6>CV~V%CPT;f= z_JZ-cQ9phO*MTmW2`G!}Zp@2^yz;3owSkd>APz>l*XH9@s!g8oZ~3x^L?cEaJfiRV z`hp|LBgsYpDEFHC6`l{jM;C|DM1khhBKd^q-ah@B$mnRf;k<;}Te#p{fI_M`z2dy(v@qi^4-O=+UcfEQ$D zS$@aADq1Z!gPk)(_c&3Ltip0QoNRckFKeb&@t!DimsI7}%=&~sThzl)Ow5P9y~dS& zIs39c=T}$jLD}`SW02vx)h^X7*JDI8n$=yNJP{;^-|3Cp`2-zi#Enj^$**yk!{j4J z$i++?3v&33I^=e#oJ&nD`lv~hGR)F{pl9UU)*BWBo*_22prDEUp$aQ&*`Udr$V-J- zYr9f0tV`9eg+Xs)_J)QGZ>1<#*%RNHo?-wdxG(AK+-}3>c&gk;Ibn?H8%^r-AM#r9 z33P2-vPAXWO})$?Lh!1|V$1j<^h5h|#0LjE47_QA$y(1?*bR*wU+aIgzL>Xw|0&rP zR6jAGQsPo{_4GyWDG#^C-4Nj6K{s#2bf@qAT4g(R=dp_=$7uD_9 zI~?rnkLMIC9voj9EUN3fSMJY~)cc@jq_@kB7Oj>c>MurQT|zo&`n5W)*OWdeycx%R z@kGpk*tohTt7mT>hlmCG*pc^BN3cRmvaYrzF++SJ54RAGH$FjzdyS9XMa4{F9>=WQ z5#c}+C)~5Ei|C!z4A|{}sEs!0DG+e2D=8}4EqJF$J{9Z6$;1i+flj94UO-l7iz7Rj zoZ7@OHg@+2yX{iVcOlQPCQKYBCoqe zFVYK%9%D4jn8X2*TyM9kbn3R_l9TP27x>lde~jmfxQSg33z8cwc6QRa-vY_T++5?k2 zau5@U*z;5CuH2-FI>(3cOxAaqTsQi?Xdm&p%`G2KK8!S;a$c~leoZ3!3OA|`B$v1y zp98k_^^i(J^={fvf9X7Sn>LevGct5EzpHYC{N{p4oa#3`#2g;grt=2eV|E7ztHJVL zsNlc?MMu)^sQg&?di<(9t`AddDZM=mPnUC?5e1Z@@dNwc@x99Xu`8cip_iCP_*P(W zSkFqjd7t9%#F2YnK4^af$|K;+x?4CAk*!!^4yuNFgq=^=7$V&qhm^a@XuR?F?~Kn# z9H$+wpYp0AL~MH#m9Q+Z(;NL+Bn9Eshrx%D{>!9%u7`_>{kaMG53=&}>s@B&=NWZ) zkxwUa4Cy~g0CP>u)&5Qs&*@dA>vcA)=jLPIBhLYwZi3?J8poB`GZ1-HX*rEvDIHah z?B_IkNl=Qr<~;979`lPygpFKHGY2+lmefeEpI%>{DpjYar5iTgoQfCKd(@AW zn>6;{-<&UwXUIla0k}gkiy`1;F*0geO&K_#p zqUF$NI+f?PeKh^Sdn;D4C7RJFy#U8l2EMUMK_D8$(FusBX77A0a;~l13%$?Ch}HRLZXgr^$YomnbVM zdlSYXp1SD%+*~G&mzJ5CnTfC57hWh_{wb1$fu1o9OC2F!o_5u_C187(78V^Izq^7+ z=?vBdEmgj{O(Jgf*Jy_Z|J}fvBR79YptOYZLG0(v$8u zaDN>ei;gD~0{7@==O6PsTTjA@avn`f|Bi$k%m=JU%tx;ZWO&R~nm)}n?0qS{jKut=Nw0< z(r$4PR}H7*!o6527JQXd3h8I$qE(oDJ~*5{VKYY3U1omcMXSw!9~I-p)Sc><;8`RE z1&rNhY$cz0-Qt`_bU$8GGj_b_+Wza)7mz<6mvc2pwN$!`md_FC;@#IWWvLyX^78M# zilTa0rB+)02d`Q$v=YJjb67A5>VJ$_iB$aUDo|{Oh#!UymBrQL_QQm_x+4B|nxMqN z3+MQIjQ=%IBR~iri!-d{hq+#9(=dFq`1{uTzVK3%&Ni7VPqKTWe_v4udink@R`uTj z$^W}i&i_E$>AhE+l;V*q*{o}?4UODz|2|_VDN>bvFO6FzS&b-Na-U>%-E|^JzGOd( zb7uM1zl)vpzFf_gb_(gq!e&rEh}9MA*>b#@ZfJl?_V1m@CgtIYn6yjt60C0!1)|@W z|NMJK1W(jFP%|_HG^=P<70n^`xv7p(ccX$~8`W`igPh|Pp1Kt_l8QwcIiGXW(%dE8 z1^t7`H~;1$p){c7*?h+H$o_VtHS#2zk1pth*>Q{FVQ9Fpbn+*H_8GdtA%lX=0ByO^ zJdGat#zu^}ThT8AZRq@^>L<8Difdlh9i_{1C8=cv+NGJ`Ak*X-+Fh}@=eSSZLSz{fCD;tT zQ#Jgo6Z$mbTRP<;6`=1)D5{?mX$Cq(NIxtyF5i47U%adXmkvC7#j9tQx){ffV#%$S zz0B*e`Tc}>@iJu2;I~9%8ATO9eSxum5kJTe4m^)laQjfdbRK-cjR#MKM zF6RBK-fRR1QEt84dye`;Nvm5;PMM+PXwulobR*h$&tI`^xT%_se@^dbi-LG`iBeCi z8p9>pzVGyzh*!+A;Y6Ain&R6N0YPtQSud)+sx0MqsFxj2dMEZ`Xqe@`{g!B}fGRT?jr~6vdmcr`eR>c|zq9+}pK! zH~gJ>0#;-+VOiTiY9@ht=FY;(3y2Ksg1oou^<)ZSBWQ_De{FVBM-KI2W&H+JKS$mG zzm@G~`e8LrPhbCI3whpil|gS*p9&o-+}l!p#s(^Vhx-UQUv#dylj<9{M@E)`5O^{y z6Fs(#s?UY2&zy>KW-{5I7qEFY4Squvs|uR9{@JeeUYqC+{wgm{+|pj@ug95%W^@n_ z==0w1nf?@*`BIpFfdZ7AwLByI`i#dM3M^&#cK-1_h@tx-hFuS%2w3dyv~sHBDYzSc z_?016lD=^aNze)OgDdIX zJ*G!ZIU6{Ahw`)}Kyat1yfUSoZ9?;}Kwkw})%IrYGn8;?p2@m6ZhtJsiT2PZ-qOcE zMA0bLHNUZDg1xGqOb&aL|H+YhjJmd!{kC2C}*eSh}-^%bg%Hr^X37Sumlaux~1|J58b2QuT`m8xx60 z*j0-J=6mCl?TVAQ-T5u#wf0Y@skAD!-ha)aQ;|X~-w zrIdkSPD>=kMQB_Zx{F_=&8Ya727PyXk)xB@Dg!CYsL(Lnq%~o8gMR;-*8JiD?AgCC z_SU^qM}G-*72h2y!>+j!8&UfVo4B$;4I2YTW?UmPCXNaawUAxasrScV2>`nBbbZ1p0YzdY(GNRn32(2dIdV9$H#Ae3%o4JDf#s4Ogab0S`=6mJ`%^qiAq1f#wOv-xh?s1 zjrHhJ%?-dedprBA6`FQaDcX$;m;G=E-xyq(ZIa>Q)>^kG5A55T(zN4b$(w_=c!nfX z$=$tq-jc(1R(U>QAVp8tbHG}^368{WZKD|}Ugxk}Lk44?Vh$@wt;0^V*~-fsZw&v; z76J*Tji};4ht}2Kzc*Ccf*ht+l!x>@e8%jicjo#0$=bGt(a>*}L!?^Ve(Cpru=)Qx z9zP(&^=ai?G$fzh8YBdp%6WxMe~EeRHs|&D_@W`?x%u1LTc&I4nTbVNBF-oL1e+R~ znj8>>T=7gpL**8S*Slpn(dj8Z9|0N~T42o0SfxXIw>odSkx{PE8pfWvr6mm&l|J0b z=pe0lt8O%P5WzhDE4OQrA52k-Iopw6b4Mt&1m~tm={$@4P*GkjD<@U!bZr8Fmo^}> zv$UjWzz1YbcE4VY=Ws$@0*CqW22Hu6qhk)RlmAz2zh!4-qtGh)3FX|Rz- z7Q@BO{f>+4a^^HW`M<;0zr`fP$9p0W2f(ruM9T7xhsJbhM6=psuW?579ruVCLT_GB zf4*%hfE!^9F=)fNHaO^iaPXk0$kB|hT|RLUiA16SK+j_n<4-taZq0^^H`9A`KVPip z+-pJ#wtLC5lR4&Ktg%1tB1vXA$Z;-|lzp}?A};s4we1LyS~D>Ala|mD+xSs`Wm60+ z;)J9m3ITE-k$Ly(Pu*2X>0*x-rE(q;yuO&1ZyGPDcCb;{gMm~^EqE|-#Mt700DV0C zq*^$Q;JL=tWxGC|`9`JXs7|F*OT1$lroDFcj$RFdW-~`Q`xLAQYaXSax5!>RaXOt5 zEvm1m_?Fg-K-AcWh}PCQ??`yHG*7ttf;#|=gR972_c*XNadIk*f6Z`n<9DbyGCwud zH92_zkUpVbJzOC`LO)=qdD?Bi zSV+snl!UyfrjbwD8qYQbzNy_AcuWKZ&+wS_%we|;L&95gcKhE8GYvEQ-`DYZfFTZt zlwXdSyWr2tD;T9ZPh13jnxu!xm-`$Hk#bn<37e|aK@@&T{q>82rVb1i4S7rk`_zss zi;JV9kfp{WAh^ET3Q%mpxV=0w++_QxaI1Iir+m=^5`i7N9iatwyCdYKu~;PS!Gwdg zNHDvZchx3Z-2<1e&N;QI(fO+4x0W(>kn(fx6#ZgV2CwvB1mZdH_qK-+x8kJPuT=F~ zf?-7MOz}5GTJT?UbEgA0){!o;EFMy@FBJXBN3pziR<%4*aXvm=g)(YRr-w~rU1#%+ zMlj&F%r!z*R8*j2BiNw7e=D0Z{~%-gO01=#aono@&<1%)HrbRem!$RM_#zId8?WlN z#RFmx)-AqR1k4vF<+Wsr+tA@@Ka-Q$aaiE{S7NBm?PBVu# zQVeP7WkKtDHL>xB9*ELHU6{9Cw{IH0IWY^oRdMM7w z#6n7l@g!TM7{UN3y}M-ht}8w+)(mb>QhB{A(mmRogm)Lj4d)~fcMT7XrDZDk`O@J3 z*(pjkiC@AwU9Qsh)*NO%FoIXO@1l|o&EuH#uFhp;Wv#BP4DC2Hk`hJT*1RI3V0zQ~ zyKV6P`fI&Lk8v2R+^_xZ7le;a)1pVq^m=r)jjIWID<$Cu;h~6r*Q2qh~g^fy2`PJt&R5Em_qCFte_1Wci|^! zTz?4Tk89qmI>`+?k<0FL@TXPmv(Dl5jnPJ3OW8CEvEIyfmHoN}?mEZa zjwG&=t=d6)Dw^zx361<|OaSu$C$wS~EyBPIL^#m;XXNKIXb1800Ul37Nk@3y3$O?) z`6Xix4)AsDFKV>lTA+M`8>^m{JAe!>%iGIgoPIa|_cOhYat`Kn5itod(q8L5mnpgl z(eCoVH2g($=CGE{=rmhJ?CL)lea1kW{pd6Do*o^w)<6cQ?(`*!R+K}JoD?qmi3R^< zm}%UjpdZh%oFdo$umcyWLt|NG=ANE+1R|q{vK+gk^2bgPgFb-|92_P|%C62b+lG*r ziQGk2--l8?5=7i?`P{ehd?dY!bjlaD`hjAXvczoB$iT#+*)cY@gk&Qwu1&0M#6YX6 zDyz*3B(l2uOcFe6s;JYDlghE?t!2A8#N*w<#B{c`*@hn&i4O&q zF&s6XM<3b;5!b2j+A8btIb6DV73wtsoZ06%aE;zo*OsyHW7s3-Ir}&&M{S`hh>izh zpCyDL84&GhY&%yQB02+a|3f#V*oNu3Iayf@*P;FCO7<}ujDgdR4sq&`F1CwlcQ+*e z?r#UDkFXUvX?dHmf(Pkw0M#F4a^J;v)zWeWG$}|Y^{5S8`2JiGth}w%ih1uxI^ZDb zGxad7dsZ>t0h(hszDGKq6dEd#sr{OCK_-FQZl#1A=c_RP_0_bIpA#_=(FoMeB!lU( zt?C{8fxMwDKOcRMgVAO$=WPP)P_PvIn=$Y)?}9`{mW1_RBZVk@vD1Pva3*nU)}9tv z7nmIaI%A6bFKM9SZ}f|cN%o+Y^8-ao7fB#SSSereljU<>c@B4+s zyN@2N0ozKBKxQiX@t$lktgH+jH27C5g#3bOz;9orJ95w)bCl;<_2;CjfFeMJ=&k#G z{DEhTI`+&9o)#8UQTgMXHnVhZ8vjET$ei^>L@1N;1?a$?hC%s!kJ@~;4h{e2>I${_ z6)Ds81x^-kl*YaG$=1Q6x@XqHP^guh+-qgJfAIC@crOkC7b5&;WL^vVrGcdCu>pIu zcYs7AlcWr=3RC1d40l1cLIjzRxVT#@nZV#Xf!i*AX%X{3Ge`bIa0oH{RBfRUmrrc; zZ27aP(Q|WfQ#X1fj5P-m@DrH!yCw3wePJa=V!zlO%cKwuQQ;@$P1ze<&hAUBmr%Bz zs|yqkrVg4lUs>y&xI!nPrgyphOD@p6GJ?FC;a82?6@UWw2As3Cx%n@ZQ;kG!w`7x5 zk8bDrR0=*fXlh{!Eo5aPH}W0GoBrdRXg?gq;~03EW#NYmlwW7hQIA>DXmrx|Q8})A zoC0Amd&&W9nSAACWnW3luv8|ZDqY1XFwprjM2--4AKl#z9cmZo-!gejpYk0qH5-A8 z@tHoaky8gBBH>W`v`)G402cMIQQvhtqrj!wh0KeV7q-`UE&R#=F?Vs+!z!jl^`oAq zQ0~?f&ih)Qm~#VFZ0eEVmRfJO$7y|9;DSutyWpX_WPKNjb+uh4QV*5fi`^qU{{^2{ zU%^fI;F+I3Oos2pN$t=Q`UEHsH9OndBFGrjhXdzsDn6zjmWzNe{M*y+B^v_9-Jx2K zrbakNF%p^J6KLvnh{hQyPbDhe>Uq5rqT>wQ;HJIqFx-q?4coX1Cu?o5(^cmYp@ZjV z=lmC^Tm6R1Px+%b^u*nauBQZQ*EMLZSxrVtsJbV@ul?Av=8g|>17Ul5t48DvhJd6^ zNy)UMIBSZ& zM|s`wen7+us28o0u_#IYEue(?7dv;XA$^-wX*D^Y#^+GM%GYvo1sE7^$(l|N_dQ#R z;klIOpE^=J?E@7{-~G7?QcwSq1&=}r0;!&8ZYlpi$pRZ;VPQidp;S1W&{8@fIx#V?Fx}Y5x=_Jk zn~HQdAn&(hYH(elgp^cYcXzg};^Ktj5)0Ma+0MZ`0#1J8+oWspIG{eOZCc$8Z( zTp|_>hY}0^mRo>8Ol)tzxZnqvgQ6k}XpcGJ?i@C=oefsFxM5xe8oC-9l=DYGj0JLr z@)AC-?_LA7Sge$bsJ5akuN#3Z4=}aGeOmo58B73u# zN5{v!ZIYYqyC|OmRfbV=Yrb)PD$hZFozZ*f;3=Tg!+SO4czqA z!b!0c@228hF7RJZf)o%CqqW!>k=;{I#m}GG|1(TPTqg1GX4|B&9w?B?_s>%o7ok-S z#aV@QJ#lBM9|lCw^H`$DUT)4bIyjFfd&`Uh7-v4S{U><~jZDG;i^qrEN$pWW)~L(p zBRZ9Jbth0qtAawrF6!*MQVpRx*WRY-GnAjxq6xXtRr>T=o)sw`sD&AivW6-uEB_1& z@|O?Yi+c={@X}38YG?qX6^vWSx)E-XxkLd^|FllX==D2#{c3;&g9$ixjE(uaR0DJe zi-h;X(D|URuW!@!#o4^&n0)fPwwW23PxRc^T2*GJh{5Gnfol%a-K(vb{x|z_v8;A8 z-&4Kg=p|%jiP;QX0r~+#vO2oDhR%Y$OxC0&ymO9~_|fAmoE){awLRD^>tJ3eK3+ZD z`$e8kcTgI1^UObw45@BSylQd9UZN&51szFN+02Yi?MI(8ruoQ`kzc6D)>fM5goH!Y zM4Vp%af^XNR$W#R%j%NocI`T1dNL(TKwuI<6TB*RKk(D>UezoZ8?p+sbk=df<)Ik5r0!)4AN!$)M zz$xikSC=k^ebTUaJ@?xV0;wEj`g+=y)+#Vu)aZI`0`?sspY_Aql`p4vW*Dhmbyz=+ zdx+-a)8hLmBXj>c=6`@uF<)Qwrx~7(oqV&SxPUL(ZCHFzu#ITLigLztW&~+f7$&ufZ5E#KIE&Xs)f4Fs{ytce{a_Ge=$R1gDsJ-)K z#{!J@a6Q==_1LPKg;pnMFEXeXlks?R^RwhCwxE-F9e;_+q~hc!`E`vEGE=hwKHAdm z+=n%!a$*w6q}xh8_W9*Sc1A|+SP_@W@f(QEa0igXaX9tt0~xX%^5R#^V^1n(orZ0f zS)_qPY`Ia8aBbG6Sv)S!!UN$_ahyK|}{Ql$GcBQJ7iNz%7T}`wcOFhNNLhftwBoh5ZI+{Tg48~8UKCPi442+y~c~g-R=R?KHuKy zuOh-5s0K^lSgf_G7uwXFYtZ-wM-C1fJ$9FjH**Y3rO}|C%()F9&bJ)sIWDDv>O6_b z5o$K?OO^p)c>XpxUFckqMMM}DxF_0Jx*pTjS*pTjyF=E_b&;NPe*LA&K*TehC&GS8A`^ES3IgaCf zBm=$#!oc`K=JxXAT{f5BGi|n$Rba05KH9x2^c^LmKa_A2;7hCm4h zd$sCMabLyaYq0ZbVQq59&ODbX8L(5X?Oj9qZ`f7@kCpuXfG99;NeTR9hKDFEC^*Ee z8me39iLarlC3FDG&@)fPKlOhA)Qg09=h~32Aoo2fNmYh$$jz-f0N(3@uEY5&ZIs%T zRFDLQe-?D(<(8KJZ0On$CvX4+03?o7-y;F*F$=I-{(I(IQQNw@COY;&wJVg#dwUM= z9dPT`?Tge8!i!ujvpNriA4vWlEb9VGJq9VqtO>-8=SnCPii4d!?zA&)MW~ucVpU5z zS`WzNhs(=fW@VL69``YX2R_UhP*|a5psEkMcZ+TdEVSFi*g3@FL;aw&-fhKTPkw&x zJ>!Lod{JW>%j(hzil0h3z{8u1IX_vXPNaoM0;2(?vZa$bU&~MbXpps3-rD(8 z-)zyjLrz}hw(c;v({!0{VQU6X93+5Ut182t@W(8VJ%|%#BM_Ox)b!?fK|6lWhCizb z39q!wHQq*sGp?TmgvvFyBpF?$xGLtne{NW1p}slU$M((pr;f)@*crAjKN04)sqJ}I zs#61V3;PzrBx%KK^s_F$=*`qEG`sc4c%@Jdp}UC-%(wCqMhOXv$~zTc@LlLlZ|O8} z2gQk3cpd^Wb5@+lQNIL?QtN72QO@EPi0qyeTX&yrv)#5<_0teVei>fYgYbv!Pst}= znxITGnOdMxS65dsA4r*+QB4pX#~8(bFWUUJ(RuC4mD&H?OV0%OQYoWbT3Ac(W3tgo zYR{klInTc6+#4?b3GrsY(39%qZU(u-`od(AxN9LaImsJFNJ&hN(DI=Yh|+b})ZAX& z>VNW>me2D8pdu6+*J!N&>mFKc$Qq}{azSO8#�%^@#dq}3j{IDaY(s{Y&2k(r-F zXmk6+n(U*35?t)t-$tKwer}`@=O(vLM0a!l4dCZlURp9uwO;{fEUh%(v@7UIraO0T z-M($mjS!ToYjTBaNY}99q!TtJ=PoRRt#`Z^Xn1qo+8&&exuhv_a6gJ!>SrEsKo>?74Eu|I+2Kghc=}tkv`}JcxSDNv>#XYYTsU z%x4OFBIdYu*m-Ghd400R?{L_~EzOBtD0K5706CRe&DmcYSCtFyUaOjE4*C0jBJSsR zOMZa!y7q)_S1+lsX!xjmc}+8Hw3pJ;mb*M5e}In{Px_1kWTkX*jyZ<8mG->BgB?FQp;O zm)$o@6xEcZU|l9%tCSTe7j%+1I;QU?SG-XA$G|=vNZRxzjj26fJ?FJG8(mVd@mvBv%G zEpDpR3aBV!5HowZuzsG$Xls`51v_qcKb6IYu(v=)nAb(%pQF|&*Cyo*a;+LCi{cPYOo5#TDBADYEKo z9Cz2aATl!*R2QTQxHuzJmhN+_IRXEwV$WdSQisKx%@m&<$s}0@=LIm?jKcn0!Kny4 zx=^llfEU3aS_b?M`v{AnFLLVtyjd(KdJ>IADn%B$pqh6xyq2zZEG+e#0}=xVLCSUh zGaB*d3G`pLME>JV=^iyDYNt`gLx(r~Dcj2wSFWXDcce}m2FnD~X+J5c)dH_|JinE& z_i{#gqNkQ-VmHo`8?4(UPr-bpYPrlKnb@D_O-W3pI$V7RUKUXvg!7LMD?{6Csf(X!>;L}=sv8=r1u3Yi zrkyUNf%kF`vl_Z8WgP+8jzb6M?nQ_w~Hk<(y|Sva)*pH(m1~X;no4 zYdW#H?Q!?skEkdWZ(iP#96;qy>Pme73?NO{j}MlqQxTmyKbCq_b#$}ABn^TEyxKhl zmL`S1>jY?(o5_?AbklcH!Lcel(tt_}Sk%@sO@0sd_7!!c+R0z#8XNgKzSGns=YQ#N zAe^J7>>eF8I9t(WJ~5e@&S_}Xbz+X}oetaxp)VHjND}u3Lm&;eaq7p@rYOGSa`JSA z6s=}A7kJ_=9-wYgpciCcQHj3(_r95_vwnsys+Q5;U&|ewkcp&Y5gE%Idb}j6+Pj~R z@5zIRaO1A?pTY5q=zhegDCx2>R%sqqc)Y%crBR3=Fg)U@(E6!DEBNUQo3L;&iB#;h zH@0V!ey38zqjcMc^w&$Nl8Q_4fcAnhY)ste$E_<9svPb&Bg_6Yy>IJEcy+r;ee)D2 z1nm(~j@fLJig^~dq^@H|L?1tzF5BaGgOS@hTzPJ)u;KF8A~GY-J8xnX zA^f-5i>U7TDIsqeNYgMR&SHsPxE-QcCCIh3(IJw2eRVS1S&1Nwz`YR|<+$UVP;T~utTB>UPi2uoRS_r$bya|5rMajd)eb0@cV9IXiw8@)-G zPX_!F&im6dEiL*2rc@YP+k(pYulo9{P|1tW>~=S4OQgIHIpfxE0<2tb?{DKbHx2s> zv$7sf7-(H@D_~<|^BR4js~dnh{>iRhNi`}W;v#=Mob2;KGD#sLJ3HI%G5?_X4mQ2C z2`HoR-6?){DCu}y(M~5ecGTbh*TY|hq#cnQgO{(a8l2P@aK7moy5IPqW2E6LDD`-z zs;n5zG*Hdy*7v22Au1}?)P_^c4PwkjcztE{$=P?sIR!EuROuiTc1IHoM(HXm(Le!m zb#t01JF4A_M;*NCXz#jl+cNPPQMRFxMcqTSQa`c?Sd}%tJhzO7ouv#89_>uvTRC6& zzO}f_B$>QBqMXsr(z5U=kt#MD&eG+vfn2wk-3(cTr=AyP_!wl%5$ ze5qG(5ek>|9s|stYfb;Mp~I6#pYro+VyBhuxD6&<|623sLRA?o3qSUKb7^^EY&-gk zR#w`#ov{>LEWpps!D-s_5p(ChQH2W&2Xn;yXuiCz93L6wmpijGJ-t(Wusb3F{_;=z z#ICSYy0b_=|DwIvmu{eN2gX4FeGTH^B5^V(cAZ(42?+Br+?uG`xWTm!*4t)LV_s;v zLL<={^GRuRe97B>!N4Y=0;2~{F`Jp$6p2)#qQC5wo%x)z9tH-!zkX<{lz($sY2!!H z4nKd-qvx6gZP5FUY%w6p6yq?RYr;|spka0{)Y7D0Qp^R^=z&9|p!LKe2!*+9RGN7R zm@m4Cc^lY|RpS6k@fmZ#)iC8bRXXBZhbIIz}sW9!+*}6gfdFWu77_UEk z8T<|t-ggcRpu!&(M=-wf@)S%DC(1vG`$ZJ_*D&~*13Suu0ou(lVbmyZ-9dNy{47h_ z&R_Z=oZkcNtxA$hekkeEML!37AZ+q! z^SwX#0{jhNf02Cl%*U8)U|e(YUG1xR=cz$Rueh~*#Z#w_Ql;&QN_TjMSqz*eWPM1; zvO~wrVyM6oAj&~YMxcA07H|@%#XU7UO-<+b30qHWH@Xl~La2SaVSoWyKyhZ>?98H~ zCl4Nk8@q@_+bLFAFbRW383*{Z5niQk<@M~j3G2&-cEZc#JRF!6|Q12)&< zxaaRW7Q(sp{i!*0V;%@O5}uc*6~+JoOf&rJg1(@ev; zgFx=ITL!;J(XKJc@W0yxHq6>Uam{86CNFl5X{*<%dAB)rnh zf_*x76I@w?FAiS@G|%OOWZG%L_xNk=>M8DNMoCjs>v8+8bjG%`NZ-hlS?~KY~mc#{c{zR z(W|QypX*)}#-DqUHQf}|IIzDy=(}BXj1<^St(o2^yJmpgAfEqlhpA7y z#A7A2HU(h!WXG}}BhH&P)iE;y2wEspKj=EQ_Gllh=b9WlSI`CX%sU%kT%wTuD zr97tZE_a)L8sK`dqyY%(1`i6%xMCb5Mi#QG+?GZ_rfe!4KNaIRa~mRT5@X=?ETpL954TMJe2AZ&r5hrk8HpV1zl!e!YpN) z2<^Wv_i7YF;YZBFIE>MX9^d2wTK*b+ zb0?jATixO#4xz?N?WCPkKF_C|?WX^QTzuGOHuyvE_ee|5t8{;5(?MrvqeHBp4Y?ER z=>FW}V0r}QK+(hMZ02A)Nv`hhYHn`M!)EPS3Ub__jQY{Ba!PIS zjprQ1SQnJRlPdZ<4u@^P}W z0qLj@NyAB6jNnJxe)9s(Ah!e#?O&K2@dSC17)6pbb z*qf(M21@4{yb{ou|bdK8=0sU!93B_e)y+wJCxFiI)Kpm@o zee*s$`fF+FE|`yYxDK>sf$A}L7g4}TTp$RuQwnM2QhtvK>Jw(mU2;)e0l5;1L0j;| z86j(XJU2I|6{#6DS!I&ZEc)P?p1gt5PV#GQcTPxJ!t!9gkSgQ2QcOl{?p5~~grP@) z*IZDL!CUk=@0*sNP1kX!2ewy%V$BovzvWqQjnVra&GeQz7ueS)H@EeweE4uR{l|m@ z3tjdJbxs=ZMymrZ11c)d$YiqcwzKq6-v#YPdjV*kJ>CxgEB)1sTv^7Nr>@=2C=;DI z*5QlCn^-8oD_XxvQFC`#vISYS_QaQSp?UY%!}2)NG>ExbLAQ6=N6wZ>10)0&)bKl-r-4XJj@0*Ot2>w2h^ZMcsAeKSzc+ z-f+#uTsw||+y)(oux~mH3@d@gKhDJ@eI(;*e6E@C3NwTw z^5np~F>fNF`qK4f#)&HJ9kCvys*1V1*tjmE+c_Q~A$t(oqM#5cw>92TOn3aC^sj8r zT3z)uFbGz;F?)`t_pdI89VdW|yQ|dZ+p2QJPu<#u{Y2nM(e<2hpxD5*RRJ~t&Wx~GF0sg+4iZ+%LjOjzm#w8lhzO>l9Q1I2L}VJ|2=w|jb;7# z+&DmmoP#6EN{fn$%iobAC>SM^5)w4?vx3@E-O0bC6 zx*mBXvAwKncD=@5Hph8x*;O=7C7!>}0p#C~u{y{SR7v_wdvy@M2=(8vsOR0joVUI} zFOoQ-prxfJnPab{&;Rj06~I!Mlf_L*`4kKyj`id6IQ32>x#_UI=V_&r z3aA+HyD;DgR*ybCVM_27ym?D0EmK(hu5`PbM0K@2-zhCPd(|~hYj5sQ3V%5G*(U8K zD7c%dlGy>0#Xpx*CpN-koOpHTO7huTcFhj3%S|K&dCdJOf zBnB~phP;=TxVN0&7k|Dp8)UXw`n&@)C;YNVd9Afb<G)ALT?XMae(V5QAXoElFBd)w7n$GN!FRLPy>2b*WN55xREf(oXd$-i8A2>qN- zSal@B>%DI74|)!qXV?*7P6=viw+eoJH^}T-Pa;-CN;t2fvAoV&$$hhe0`wp;7}?U$ zu=;_L45-+LgNmrkMsRcnWStpLO?{7<=rsu0GhSXg!S}TQrhI|==D~f7)88iViiJfV zyDiUd!S6Yn`a$3GgBX=QF1@ zG)?Blzo{~!qERAp|BKb#cD#ihGCMn)Bnl(NW$P*`S{V(CmPmO`wzf*Yb<(fF!6+yI zk-{XPd{^+{L#Odj2_SWMsfIEE{z6O5r%jz4F!BEt*Nw0q?L94T{u<@GK|8^(vNABi z{Fe#`)@l2gIRLo*tHW){MB%`>+-tWXy;*J1*b zyzW5UVp!)+6jPT6G$WwGRrFGO?d6sW!tQ^eM4=gEg*Gj8em_W6rJ%UY8f*zXb<7e& z|Hz9Dg_;4)nfWeS$3W3EnYpEd!~q3LT4E_FA=9riG_>mn6U|eqW+uI{sZxKk1^6q= zrFn!H(g^!%h0mu$Vg30P8$VExQ(%fkT=~CF|4MIe2Trez0|2;KuBYuU-w$;WSPt1gzOfNr|Qq#s}3`mkY^10YetcqvM;dpy@CRjx|0m01iXQ0EpjPnl=G* z@md0q6`W20X>g(k$UXD#7X(4|Ku`FLiyb8s@0+@VUgb;*ciG;+HK`A?O)AN=k$2n) zm-r@=r&m{7af=)otX(O3HN&>(FJFm8PYZ4B#9i!yY^Yi_a$rA;ZGfspiCF1w&YE(pe{bIOG zC92PGXp4#3NA_rWq?J#X8z$G-0K)qFi$k$Z;e+%V$TZfHHrXq1x0-^Do2~;4>40Q0 z=v|bNkwvO8GXW5L+!c-%o}Tw?Kq?h>TD{}V0C*^B7%adc%5W5U4`V(CWt#0fVDa(k4f%2%84#bif{Yz4ZSkg z$w>auz1E;dLB=rf3kfY!eXRX&v&g+y3a1IlOBuxe`K*J3RSCXvx{6(t$(6E*B> zht8d>T4m5mzRx7C$Rx4bDFJM*uDIn@JZy6_{5JohaqY<~Evai)$+PtmgYKq#aA zSViyRO<&-+eXNow%OY#ngAOt9A=;XjJPwfyy_*mpL(jOS@K#@ctyRl>X=MdvKOBeu zpP_>3x}4VC%!k!f0LNogk_z)?pBQ;5=Egx~=BbjX4N zpNumXeZ8ICO+`&j!7zaYHJMcepeb}M)aB1Es{88H{}XgDU~wkrvjg{1C_wW#YTT5y zJ7y3D+$J}9Q*%l>$X+ZC`_|R_8D1eg~;WAFB-H#2Hc2CG#vx3 z`6@WjTE>e!V>=w{%-9((Fp9P%{DMZe>&SHKTsiu`DGKV7iq(UwdID6ROtv`LknC=dw z8^ri{dtRC#&k)G&V;7S24m;j&hPp8HN@tgZZXmnb55H&Eu69#dA1L~}NPh8`n10x5 zJH9_MHs0s`Ow0f=kx^A}qSoNk^=HsaZWy<~80R`}yP7ompD3i~~Ti2Iw- z*&x-=aZiI(JisCprli!S`k#QDhUBD%m8zK>ozpH8?|fY&hmokO1%RVvagBprojLpc zKWB#%BNLQa-}^{*R(#YEc*LI&%FOkIM`*(m(g9jI-Vekm4;b+v7hacI^p?sh?MvI4 z+%`E3{)IwNcaNQ|zB9=0+n}VtbF%V5THc*&m=5_Udc0zt=Wt^2l~C>DYBiy6xz$Q@ z4 z4xj4`0nnu0-lp>b2|1$n!yz4=(i&jDTZ~lysW>;Kg96!)%I6nHZ_5*UV)sElO5c6) zmHTa7e(N;5DA12$sj?^*JRSX3=2EXnYc*YIH|07`@o1uBz@-zdQfjjF6@&n$^gu_S z^Qm3ueeMf{GfKN+M+R*riLeu;{=CHs*zxeN2` z4n`9|Iz=3;uXIz{eZPF+QZH0gG!FG5^q!u|0`q~tsbD`3yt8S*V#Jx+ZZ9l z6U}+#YaB^Q{LmE)hF$@{Ec0Cips->FEjI>jFf?9?y3?INIM_Nu0`JkJ_|n>?sg)OV zw3+MYzW}eOm-pyL;z26TMJZ{0f)Xgry}{d|X)b4RB@6zV3Q`VFj?Rwco9h;K?{l51 zPg~6IvLVI@8I%$D8gzdAj?(e>?69`Ky_nWt6gx_R1w<12p?7#9<*x|MYU`;l%Fr)T zB6TClKvvBxD(J?+s^_;!=H)9)%yX2~=`(Kig!d(q0O*K0Aq?)hZx$WMg1sfA5sVw4Jl3u`XGP)+Qpx*Cm!v2q^) zzfO$gOh<-$$?|Z1b2saMiHq^M%tEYT)N2cHBmkEvH}*EKT(?g)z+;wTX?MMoAE=Z? zV7xsG^s9<9Dl&}5b%0AOElk7bmi|3i`BIS*bJZE81QOw#pCU819BcG>OQ;gapGy`vIt!Ii`>7^h#N^%ws(emE5eUPooOo9 zK_(5EgsY$+nv9`cl@68W8s|Id(NIaG8&3lVacb)CF8J_Y@LzmS07Y_2JjR-Ih=5KSY8b5FX_ zqPjU;Dv*XXh1@K#<|AHIYa63t@;ES%GfxH_aZ+KpAxRokvhpFJ7iHzI!EV=_6QYZB zzhio{+o*bVP1gPUaZuohoGUn{s9; zk2RioZCKuo0`U7k7^2-kO^1!4p_f1*~^M;<{9Jn_v;ptLOUEF`AVLGUL4q&eC{0{P>%#Es-x0BsL)xv_$Gw@ z0n)G1t5@FevDq-m1Ucw=mjE^48Hgo7_~1g>TX<5qrpGU)a$Ub3rk(^2wk+{h1^h}J zda-hn0@-#PUt+fckT!e*BGkuP@a>NFvHBZ9Wfl6!bHlO$`?eHoCxp#ntvioTDxEq% zBc+lhLu#b0-@S8M>sta_0%Nq7ZGD#Q9kE{TcXHp`R?=>n4=7c0f9YNB4dNatzMaJ+ z<|rrfTvIX~*le37ExsdcWhvZ&s}p5sh;aJ;+~mZg(gxGgr&-MQ9z6Sq!FgW_Iyl$4 zFEQ7=8Dt<=aU00u5(Bi>&Apf%a0E2eXZNr_l>ebQYWcim&iYUzI5O@bM1G6KrzJvz z*@KSb2@FKYkB zcjco~$LGpZ*<4v7e%x|1V0Wph_BT1ZNs*Iv_Lk8$(@6x)ZozErx%#;Bz^E0pcf0|F zGj>A8yelPUl2I3+`*ZFN;XKK8u;B+kpvz#ge0kD;xDt8>wq!TV=)m7RQ8Vw!<;5GGy?2guCMKRQnZ=R zgV8_O2*nwGe0k4m1jHFT1gf+C=2VB1%cHG=b2tpOA_3R}6a#Qp_FR@b}``odTi=el*vb$NmWW-&w3 zsUGASoD&RqZW|H`s1b9YO-5#0IW?afozd&R`_1}TOMpZP%tURJnHMu#{FLihok2GB zFyvITxqwznMZiMD`8gK<*E$~SOe4V!ow2txs&wm$?7|Xy~MS0 zR$qxqHi|l8%C{oaSnLvW zA<#Bl;>|Fn7d1Rw;L&h0?ms>^v>07kZgW4^Twq}&N88S>t;x``la$YYKxy~O(NV8; z5XiVwZ#)sK-2JN)%d$#gsUjma;*ywOb^5Txe$uE9=wZcu_ETEFIFWtyK2meCy6gv* zg5TjeG*DU4ZcNp0OiHK7-MCUz);6<}6qQd(jaP2hEu3o39-jjKC+i{GN|#YS2?<}F zziwe}sd`n05yd_idGSY_;vyolZ+a01s1(_Ll)zse98YOL6;MMzNmDMBfRvWPVVq6j zF576n`S7>fOm8~A%?ivxF~xa3I6g_bU!&4dQS?}o1v8-W?b)yf(b$9Tptus`T5DZ zDE0)|F`Apc*Ob@PAq#3+XxR#>Zl7+Cyr`Y zZiJH=@zgad(Bfn=_?-8o;sGP}33p~bX5y8oo0a^+twg?E9NKoA5d%(s;vU;0U**GH zeru}fqomr)i(QqC>+VlZG)9#_S^@rPmsTPExqQOe1N)pT+DFMx%T1Hk zVgeT%_w=61xhr z?~i9MK%Tx42MSg9&cN^o&n&UMhBNH18o#8yly>S8SxC@xG8Wu8N?yX7xn)(EyV1P$ znE32vLHs^Wf<-rbph^-t*ET8y^&`i=Ase+KUJ=bae-o}L=CLWoN&?{L_SMyv} zvmg9r5$daJU_xN6^4Zcp^?|}CD>S@eyXADgNASJT)0+KgQHKsTX+$s;MIDOt|9bamh?*aFdP+n=&#Y4`Tb-lskPizQwG*C$YnnTrEPLS20*TN){ z$jHs_6pY8i2#M}47Un)0Yl%oKF^Rg+30-fC;)FV)8Hz1>A8yp_cy{v~=A|J~^g7w6 zIo6)&Ppl5q7YebJPfDbkZ8;`lZj1juhEj*h_H5`_BRaIVE4ba(M^5_M?cittW@~6wg18Mv$6)*W6sEq^YRP6}xw`Y%eQ|>(D2uaF*2icr_LeFuV5sgK6`8C$?(z54SW)*sufpA zj^bA9kdK@Y66e|4{ok8=u_t zS1~7Rq7&)EYT_iJoo^lGg<;}3IWwey<@R z{$W--96J8ZeICPf_rp*uv4n`!o30pCu13c2ec)WJF+W4&pQFt|P4pi)k{`^@)JtFK zKX-u7QhUnlLl+f2vb&uhvJ;6E;d)SPSozE27opz6iX38=F?T^CTLE`dK8(Tr_*F7k zJ2HrRy)@b!y?4Pza+ZI0-m-X32TmxzdYwJ+copY<-@Wke5h1b8sfzno5tZF=V}JL_WW`p5&p|ngcg5u=n1F@nLc$WjPiPTT6b{gncF#?~7&Acw|x%xUNf9wfF5boF1(if_k znzG6d#dw7>QE|TR3DvA~5|15>NTFa6Xb|r|dBzNLG0GuSc~$a#=c`KW&{KF=GN(XY zNE2o*w-P^%&5KR& z1JHC7b$4<&brdUmqP=EhIH}3X_sTIpJA2LANW#mH7tWYVD=M~Sa_I}@Ky|4k&zm=5 zNhir1`i4nTa17LkAy0KrPpkPQe)#39 zXS(Rm9}@Cjr+)raB8z*;w0|JJKAQ^+m8bhVLLwrfKg^STj{O$Uw;4t&jL#%+?Eb4? zLKyzOMK8-|2--gD!gpK)GjCV}vO>Ic*mj z!M0~xCE&lOw{BsEPYQ2($#Bjt2_Ovz?xHK8W7{1<}!I7C4WogrJL#)V%%-_XddP*WdD4gnBAr-m}AnL?bC5N@jttONfga+p{cnR zJn!J(Kn>=jU1+11_(D#{b`rC5#B>>S2MW2bPc-?hDI5JbbHk#$a7_-P3=y5oc*1-V zvSAB3b85isEtq_7%y)PDSY~XA34H|Wu^iuiC!HaaiVO`+Y+vYB# zWOy&@`T*O^YFpQ{!-#}jC0^@a-`y*TrREz+&|SVW2{cZ$B7L1P^XQ{xaaVTv4XGdd zW0YH`^l=U{>4w^EFHNl;R65P&86(;XgBwTiBi@H7#W}^21hmtu23^pi@QI{P3sApZ({Let$O9T$p}k5&)jT?vpZMSkm?m!oWzY z;PuV(=Cb?UPX<>fKkPNej~l|L8@}18Nu25-F~i2rna#)efTP;qzB}_g{JbWI9U>RW zsSl>c@n}_FNzasa913M`{@(YnA!&8LWtye^&Z|q_1AF0@ckRQvG5o)pnZIEZWP@Vx z4&EHh!cW%2&fSM|lra1Q-hn}t}B&AW;J`94OgJ(QGPg3tb`{w{MqL+5${m6p0o zw?HM0t@5bj{W8T^Wpjx#t3m$ww)qYths~Z;Hxxd@OiH^QQu)mMr?AJEy^LHWr^fN8 zqYcdLbP&HR*Yn08ni_1o(fqX)Q1I?ntJdwZp_A&Rhk^`fXYRMtmdr!))KgUxgU(6O z9qia!3)%Dqal}F0c2tJP`vE??A35m`va^`IEc##vw~f*9oghj1(0hX`r`~<}FSp)R zIxqMfb?UCtzCgVgNE#!oY(#TG^@`s7raT3-6`HQg<>XlBieBUHbF6RWi3_!NmB=T4fH6%b;gX{cVR|Ip| zBW@($sK{Z{GQY;OB@d1?d&@&hq}g;9rN~Xy!`e^2Oz^`-8A`mEPu=^(KvTsi&!xr% zcAY2L+J|$)sr_ahp;N-S>5Oe0o&iQ=>G7?`v|9 zN`FB~@DGW{(r(VQ^GNEJE-opK{4(XZbe*v)j|JyeCx4Zlh;^yPbP5Xw-Q= zEb*xxPg@LE`euCs6!xlQX*yBVWGGHxWvr~GQl=_?XQA8vz-qtU|Jspv|2zVNuo!qQ zz~$^|mdk7noXMx2YqBLU3BWO!-0;a^@R_6P4C!#L+Vu~+CtubV(JVHnh{sxsux3s6bb!i>xb`U%HaazGUsdxeE$2s)?6wrpF$24(KJT#5OtaC z&gNP@k(~PUxcv{V7{-Ii(Lptnvaa>OL_!VTlELUMIC9EY?{GIinh4Bex=cb_?TxXt z>pWt493Rxj;<2aAbsfG>71tWyf3!>g)Omk`J&N53juYTp=zyQh!Lu?RVRuNU=bRZ` z9Xb=Si=D$z-ZKeCB7_Imb1j>`X<3pFW$)5P+`VnfpPv}z9~&o-x3+&-!5(vx46ojd zv!bjbGz{e!E@-@YR(o#!kh0EC{1~v@sM?m35LkqmyG%c~W@U{~ALsFXlPM3l1km6`AC8eFidh z^?p;8R(7Y2o25xqWSIDVa2|6U#-jDt9EVOBW`8-}uG((2kIGgIZyOrjTQ0s679$@@ zm%qe*e{j=dJ3}CPDIWtpUGP<-6UcFIUR#@1ZL}S!V6$01_1fA);fd-zq7!Z_B<~~h z?s()dAn&O=VZ-S9(}o5?;q4A$hIZ~l1=WJJ2QH@T{QEt&!2YY2#`ir_v1D`g1F*J8HpFOKBo`v5=~!{<;m{BjoBnG9lxe#T!%dh^ zBJ$IuWdymE5?CIOLsM7Lb zDz}FV#}7<5kbJJLRf(l`%L9eECrBFYJP3c7Y|_W1Rxox}ew9M6A2v(^Ht1?G72YF~ zIn3s1iC9}!^cADJd|jla`${L{E2Mszj;mIgUGQCzdB2#`%!mc3eGS&CQ{Q{H^J8+P z{E}=4-QeKs{nZ_v3l0P+gVfu$ zB#GiUjLWE#t0YI*;49F3U>i_XN1^OGK^8%`rMwd?eTzxZ8qv`<(kAZqC179fTolyOd&*~x

`QjiYv*g&RT8Ek@ZuaA`(gaqwh^Tr-R8XH`#GO7voRsn@Z z`TlVxQpX27S0l3Bs@HS|Ykah94|)T{<>Fd1TKflFPT)MpM#w5xxX*TEe>%~=I<<_H z_|($s&#{?=%?MH|#}eCl9kE`q@}NEfR3TJs*hMw4KMr#GXceV;2v=cH{&mTvuZS-+# zrpM8Vfm6WV`ZyAYTXOTxNPNR%K2|z94Dcr7CX_2>#9SdiiS%X_h*-j?P!3#;nEyCk zE=>0u>8R+_*e5s~ZBPG7(bdfsWk;eZ5(O^g=f z;FEAAdwXlx&YqC_Kx%RPz61oJ>GAxOr{mAd@KpBqR;{EBm_6R($Tm(BWtWJ;lQx{Y z#dAxhqvH!ty=Q+`t*_=RnKY^NsalUt^Ey8WHIE#h8Zr=Y%X_AY$hJb-PUK9bH7Ze& zjX?+E@{KbYa=3+=l_1M2JffmjUDX#qU2gH!ci3~^UEE?2bGzi7>4Q_+b?0559dV5K zjLG!gCbBZ!#gLkez(Ewfur9WD*g0%mI)mmlZOe(vKd)QxT7x;F)ZA*YpwN!LM zQ-do`C_g&$@}&=ko-*(wyzw}5Kv*!X*j6qpV;MH*uuzqb}T%a%OJ}g z$%uYmt)*+;4!)1nb;ChZ=s`1|Z$R(>x2-zTuAAp*%zR9?%qqt!pCV1aEKe<2#K1^K ziek~^K+Zzf>(p1RW6ld-5{9n4L`j#jqMunCg2Jbkm0i9s%&z?_V;(~A3pM$(tLF^1 zDNyevCO3DzM=!#{(V+l~e3uE*@u(JzPK0SR8Wfj2v^Ck8?MTpyQ* zfo`Zi@|!CzKJsA_-Mn@BCXkzeH?`|@pFB-N&xW?<(fki zo;n5+srKHp8~2UAu5@ao%Gb%C`m-hk6*!aNDkAhePv`M`GYuK%c*6EcWP|xpLm0{Z z)4Pj&?vy{KD8EBaw9{j@-I(bIeRAywC?}n^e~Jp$5h88m;Qx zH}?4E#RDi9hWwvAY8g9|!IxthA!qhQ9h+o-zir5Noa#Q?4F<8d+XNL$>(MfTqou_6gYo(sT$)Lv0cZ#F0 zuqgXy)w`W&gg^4}Y(CMlQC|>iQ-2A{Q822mkHxdhyF`VXr30l9R?1pdzC*)ROe5ep zU8->Ik$~u!kx<@wuqrm@kvyzeps6`pk)3GO(%+tDQHqD+l^tUOJHYIkTQ20%(9)GC z>W|O4-LmGuL9PGG#xJgB@Bl%Vn%8A@1uK@Kxs7u_zhVeELcmX;L+G%stmq}jM2fbb z#R1ow0pMSpkYjYqDrJ7pExp&|s^;{>ep;M%d)6FH=& z5S@)L1f7>%%=8^~p+Dpq32Wa8lSJK-MTNjS?C-h3*!9^{BjpXLqC#svsha;JH6?^z zs0V9+ve*5{Z@PS~$~0A@{&3$Zn$sxN$|b(sJFn22Z&Jm)q`0ET?FsUz)!bBVfyKcbril5cYm87RG1R6)R$npAaDry(gB(C9%wu zy6|=|Pe9aod53=zvCK3mvJ)6Z~!K#2WP?_p1E= zY45G0+Iqi#&l;sjOY!1uf#Oiy2~gZMIF#a0+zLTj3T?6A?hXlVL4&rqTX85Jw73Mg zhtKDJ*UYSS*Q~iSb7%hft;HWnNS@?8=bY!+d%s_M?*Y_o?LGki$HL+k-sKHYpS~{W zdJ@#Kb-L8{_0;~A*WoHOSKw@^ju@zypcQ)Vzj!^hb&*|puC{K-Sw9+vyX(3T=kEA( zl)tImzdy0Q_8NI3QSz1J`e<6%!7(8@`4or*=jZ7&`HdkqmVmNZDoHm-9ACBfpjT$) z_1ojwhH%U93KWs|#>4BUXk>=(eq@fOGx8>zfIa~J1SrC+Up)V=u;HZPDaFa3gOQw@ zI978N4&&-Vy{RzaHHzH>Ere`}$>g}PTvBCT_!FK&fBB_Zf!o&L2#`;KS}T@XPJS6g z(>_LsMeD?IraB5{xGS7buf~~PQ!hGx0`0FXfZ`a+q<^tpS&?;B) zq2%l>Q`OSruYl!KPiids>0o$~8hP8(MFZB>-o0F~@1X|#N}2nk=kl6R8qxeTf8TAp zFji+_5}428mG~5JZTc=D8<}-rfO*<7n8?e25b7~2k*Q=f@4#RmPps%4DDLJKCfLBS z16;Ih6#X+$E_BINqemC=7?sk3M`ry^lsY@x_r%EPyx!$Pg&|F=$fgMB7Vm9Dcdf*t z(VZasv+F9|xQfBUaU{$up@#VTv-y!MqXfuabpa9Mi#Im>D0*u25dzh$m3Z8u>fL-e z3VI-{G#5yna~}8zvbH-AtonnWOLdot8Jni*Hhm)l0yFO+;6N`@m~xa6Iy)0H$Kr+S z0>ycD<8i3O)*Ak%pLGY#V9;WcNlHyzyW9>_}<3&;(A62irJ&^ z8wuf&iyV)%%%9CJEzf6cCKpjl-?Qp9$^2lx{>tDie@3&^SCE}aaQ9}iKEswGpQ_vE zw6z=btNC`2A{;dZ*;?a2;oDKQFI?01vTnIqR8AEsDex~2`cBRZvss_8n@pnm%K|Ru zYOl|>IMOlp7X~8uC3eD|dtzkMRc-?cK8EJJ)FpAK&=ZtV^mT({Ry)Qnuhz9v8II*j zmkdd+XH&7!hMj(6|04QgY^bGZ;G{y<_lup{Z3;{oPxQC6KPrFw)5f)C!4Q|MfVJbC z%hA(I2tc+O2+xUrShe22*F)(Aa$IQ7EO3wG&;e_w0-;&>#_$1X5Uyacn3}+U#7kLf z(30hx^Ub@$sb|#XhGw&Hr-ftfAd1#w%yPAVV{aA){+sq4wSeVI0QguJGxIKEK^V@y4N$A`&#D`Z@Wi*d(ydhm4RqOrRM<-`OIuA1}|F(k~HU?6Lx@!|RU(m;< zruy)ivGJO+0RV14^|ub~v6*Bc#3$M?H=o^tXTRNynJTeUv*T^j^kGqyf-c8U zC_?)86nS#sY(*lMeZI#?qhqt}&1m2DE%shkNE7*LeBi7+MQ}`%Xwe*mg)2_B-r}p? zf;vnA)owHUcMsUeyD9Id=vgRSQ7=^aT)<|pa~^|BPk9+*IX3KGHvVk@vw%zatho2V zToaACP;cVOND6^bm*catDPy0TpHs-|n*zB9xoT^@m+1`EwkP`BV`J-^i=%nPv)0`1 zVc(w8Q` zj6cswcTe>@hIW2pmaledi)X^YfG<=AE(w{ID+0^!J2K@o?Hlth)x63A4X#CI@m*FXwr&lVxpHr^!#x*$0E+Br>CU95@^aMn;aNtf% z0wi%XW?()Y*>YZLZBtIEJw|6Qt`8W5_iKKw2*@xt@fEc>bkpv2&mI42>OWJus|;L5 z8k}B`D-RFBT@RUhsy&!C^A_dgFJmu@qiqAD5>lP&CRQh^OaH5}Vf>uedItM|P--%D zanmIsq^p0Q7T#YX?EG3~cVOLaLTui$RI8$i*%a8IgTv>Acg{eP8SO92f>Wv1Dm-gKUUPq)T+e+ayp~Yzl{Hb5c1`hk1ys$}OEQHxer+P{mRxpQ4J z%3ImXh6R`+Xs}k97%IY9KluUi1d-_a@j{5wn!3aEdk>G;cCDJAB0|f~ZcdqXrVU3= z#S~Lo872yoCUd=8N563_OAoZMv&9jhzu-|{Hs<5KcsqR4`|xa0)VBYVg{;s~O;5`+ zGKYvbmz+=|hFWqx+{Jxms)LLJq?7bUxyrg(7j*Y`J!GTwH%S67cV({W*9PQcq@&+3 z?1s~_iBHzo&SMv(*;S}l^`@7ghSDNpzv(s#|BK3v)j;#*ug1%GmjcJfXmd*<1hAil zYEZ+aeaCYO@(umxYrdG^HqbRAUTcc<;?u@>B^an%zzp-URS1kCJX-godKR6G;ANQT zOqbQ~8IQNZo*F`3h!ivTNrk87%zvVr6PLX=o$wA4Ic{=1$`7{kP74{? z7mY2G>{+T!eUcIZM39kyd6GNHBFRKpJH~Ww&PS(J`7_vn@1#RDPlVRLAm79U#K<2D|%LZj+jv?4O;Sg;PvK zI6e0t$(CM#Y@7hn2d`Z<1(@UbH}+b&Zwq=gZfcP%{YEir$isiGJGwMtuElia7ej_u zo6i+`F@wu-biT=Aw!^3~h4AY1R>j};9Cx;OqFO!&kc5sv{=S7nq@w-7c%ZqpaQ<7@ z6*eTqtlDbl@yu%ODvkfmM5-QSYpbB4*4jav{C`6x)ZCLZG55b|d~codg&@(W*&(sp z%8QcpN#EbRix+2hNX(oIJFT+?-wi6NVw0tdGYSsR?VBcSk%8hry`=)k%flm>I^6Wi zy<@7@2yW@#$jPM%D2-#c@S&Ui8btc1naia1R%FiOtKu-||haYpfWdeb?#jaW6|vzj{lwyef4Ym^fO%?h@$@H{eSgpvv2m z3L?8RT9hgHc`{b^UoOQW3}~{iQ_zQsL%Y!VE6>}G?P`VQmh%j+7KQ)t3y(JL_=OF1 zgr_y!4{zdpU`NixYkzm@sVWEZF#l4we`-KA?vHO`^x4qk1!I3xf~+Z`j@nPKb`{j`iGHV=~}2JiKvJhl5!Uc{49()y77P zYsahaArV`IVPP3EdGvhEXxo(`XD%`O{iy0cLD|PvsqQdSk(ph+qh-se{<7vQk4k`T zki8*#R6|ZJ>LIe@C}AE`hIsWK^rA7_c1px$RX2$%?{KZ}@<*}oo_FDNUbyk)MwKl^ zsTwlX_qMbd#@zHSq0F*dv*3?*$fKv9hMB4U1u-Q0{(2m5R&>Zh!Hgz+2V(QNx#lO5 zv8;OS=w@i^77*@+6}&#?{Py?n-$u_a5*G0IO-(jHPyl2{uF{sqbQ8sZfa~`w4mw_5 zchw!Fi-jTtWXnbH9gn6S-Al0}OJy0eQZa0kQ~J<#d@>_8uuC42pW0U9)c1I32inWZ zs{};ui~fo+4yhMZ*j8jEG(AvXdn|+vKp}&JM=I456_7JHC6i%cWRxg#w43+pV2p5| z>PUIg*|dzyn2H(-XzGa_`CzC6a2!Jz+<(a=+GGHuv&dGqmJ}W?#rLGVyIQ!)?COp( z+Zd#DRMinUTWK}f7)o|qUR`Y^Lwvdkt1c8#-|~sc4m;*YBGm7r9mi7o`{f1s#D#QX z&jx^!TA>Tq6F9d=c-K!;1uZ|Di~T0*76ghDPH5b0FD)x3lqB*wYvrQ??nUa^1{yV6 z8jZaP2bUNh>6M9{&Cg!^-0+PsHLP;Do~y@MxLqQwG8wrSsXdJwdGi3zMxc-H(l6oY z3TS=v*nN}s3I;CKtyRkP41Z`9PF@S~8$n109Rh^LYoP}RRxE0nt+6)Tm_E0zfB#6+ z0M^jnR?9K3{Y-Ji${TmcP8LI>#b3nMy;S`FJ*H7`D@1pPTBP#+p8^>xE46?B6ASns z!x{7m&VbA8;WHX*1Eom|6V@&l2NWN`=eamscTT)DH*5>QkSt)Jqmz-AUh9cTp_2=^ z`(rPpJEalOYS0RHjpmV$d?asZE#KL>YP+~+`EVo3mEw@bTF{oXY<-6vbtb`e--HW8Tt%#$LC1_-?K~gD^$q?jHPqMz1799ew=I zmsdfl|2bp-cYvCB*VA_uT~MkF9*g7^S%wuAV%A8Io41eT2V|2Mux4r2IDXXUt>OtW7qzZN~cUfCqY1}Pr%7pKZ9tTZuMGC#gOai=@H_k z0xA567$PPl6cXip^{UtTCNR*jo|2D_a|D5|uIBk?D6HtZ@@O@36=_`I$h-4D_=$jX zr04M<#|Eo7vwHTqsOLOTegbGH1a13&FvtGk_qMvDatc&_%5rT0I`&y8*La|<6YX33EwVwHoUWFmj0ngX%>kfdUYE(1{ZvetHJPq3+wcV49G+g$ z_;N4FK0J>RBq`>T23nS}bDIGEZ-LXYB;;(*pxmj#d3n0heLK|)C%mPS70`iQ)gL-yL5%(LgGVL~{Psx#MDcv7+!r9HH&K#@~pY*O}*tu%oBv%L!jvaQ(J2hGsHgj#lf%UNWbKiEi4Q+R_GUdZb@t2PTBU{V+@C=iW^JfKKq$Y|l;N>j z2>Ko6A`Ns{q2TAb>8(_Q1~O|E4!f6>f(?cOq!q)C#>uADyL()`Kj%Vcf)wNDAya9< zJ-8lg)OeK1Sz)))8a}fI=KeolrxjY6A z(U0I@Wb?a5xo9WAE*1HW)LrFP=y>}9s zg{DkAl>q~f*ZCqu8*;YGqEUBHxd!LS(}u&DV>zq_%LXxhZJ#Y@I=ieqE$NrG;0qQ9 zuK8c8$r`n8Me%IyQuqabR%FAefyx@`zrrba9CR1wbY^RJ)r|A)#2goz01dNg9mdkX zRcX;zE3Ft`({Ks{K)Kzy8o0*K5JXM$)>7L$00=?ujJ^S4>SFkwhan^hCO+yV<-)cT zC|}C&0A6R=Pjotx<c3 z6EggQX7~WyMvVhdx1P+K}cG)&u&a#jViPDc;^Is3aGAE z0EmDCL1;1Cj|#RS#?^IAdcR?{lTsAgh(T!_5{`*dhso-SW@6N|ZlmRO7OiXu36tT* zpHOzYNjj%nKof#&49;IFgp+HR)uVa=N(hsk?;uxMNhwv-sx97rRwX@*#R!%gZ{}FT z{tJt+p!3%r91Ji~m3ctB0k44xokW_TW_B)%o>5}@5K_2)O{M7C-XJ1{!_C+xr(h_V zkR~IN!^F75U;i1|X(Q_XnAKpg2-a@tD81sN^t`7igA1jL!!^`Yv-wQ_^o)@Zp+jA1 zoS>-xjgKw4F2ZyLd5!62Ny3=eVlef++LefFSGci*);Y_WRrl#pbSe+8$It>03}B#_ z=E*nuavi4U`r&MkO)opJ)TEK8Ki~p~l%bPh(_633Iv9Hls8Y|@(v)OCKuxA7Dfy?8 zm}RPD*6B}Y50{0)wm!RYQ{qLGLI=>H3NRHfxY^-6JXOOA#4MYd7B|eiJE@xU)&NX1 z8JaB}VlB8XwblwynYQEQHw`BgU$G4rt)VvD{0?)5*`NM4xO3>YIJ;ie^3Pt}9z^A6 zGaCA8E7k-|8qpqzZUlZdMT1FqRxyHD4woI5$z(TM2E7@g-_>fP$IEW`JNy8Pq4> zn>d7=U3pBE&I2eaPrJIG_wlB>HqUolih4TVxxwf)me?yE2dx&DHEh>)cJ$tNlbs7Z zDzR+h7YFm=L7crNwT_EXv9ZNyNy3(ky#k+$BOB`G^0T;EFeB#eO@T=qW|53BfYuHe z)K0T3Zo_Y`PWM~Tm5SOAjT`wsy`Kf53uiPUpHAY~MEMkwin&-ZD83N7dt1{Vk#@J3 zbqy|DWA02hB4omC0V5r~dQ_%0z`GHwDtBx@fA+9u!j@54MIOw{eX>A)^PDScnwukLN=JvAF0V?{$D1FI2!+IQ2_FU3S7TxmC%b+o> znDXxr_MqWLNT0aoNDX?$Le{Ahm-As$+SHXU-|ttA8IOrs^tI>_wUR%>YPhP_NtpDd zq%EUfOFzcDny3DlUv)W_Zn9+$5P&Enm%qK*cJ7lH?A)8V+9%QzRK!UG$$ScOa+_nf zjleu4yWa2|AnK1uwadWnEBOO0&!`>1QejU@LjecZcaj4@2`cybQ}`U+QzbT<9=zoi zA|OsJ`140wo{P(@CweUlQ|o7WrGz#)(R(|SY2L@P6)VW%9P{8mmpa?eiQYc+C+G^8 zc+1h_h2t*I+&57}<{`-Z6m+wLGqJQi(JUnxt?({L7XXB38;o@9S{#u&R>(h(xMkfH z+iA^`xZE!RYXM&KXH=2GPTd2a&upEt>W@K#QW0R>Ff~@ye%MFKYvxD15Y%^$3Q1Y; zZPBK-^UDR}?iN10!eck8Z8ui+g^9p!5uiYly51MsU)0@VBNH>{jD6o%3G<22GwsgA5y$nDT!wZ^f=9IkYAqK!3IVO_LH@kB;a= z-kK=@8X;+HDF10v@u?QVp9X!3GCH&=6FVK%vQZ0-dT`y!ZltW$2R~G1D*&o)e+lPw zkO!i??{3A8##egx-R_^ED>DR*Sn@-6ONE7vXU3<#7$YU?@mnImE8mSHF3k*q3ME1S z&^KkHYd`+ToOBd+a$**s1rBs}X-*u1=GC+2m_cvW@|e&2-{_E^%^UzvvJ&Kr!wCXyIe@LDdI3-k!o&tKm8(Z@YT>(^}L>Tl17v zJ=bAD+Pp8gbvX=b!=mi722L0C1a$6?V^fZExm56`I?DmuZ)IzaWkS;fO2bN?w@BQ1DcfP} zaH!U+Ns|)tiGfWu*9-7+Vt^ZtTLxRG^0yn2B8HCow6jO3?H=Wm0N6s zJ4}2wO)OG?pGTJQd|d`@KkJDKxmjdr?nl^iYbYvsJfK_q(mP74)Xr(f=`-y|bppxF z&xJu+{H_};7c4ACm~#faU|N4MUIC@Uc($(DJU6eVpzCS%!ckb)t%I81+9f42ALf%MZN+d4NmdIvfW zpCZj$6n=lcKf~+PCXjGH8bv}nQJM$MxoVu7*oON7nq9q1DOktE#!>?)8a`&#k33Dr zY6RV>7@m7O6| z3e(dwVA_|>^Ckc#v}QLq$Jj2hHRF^Geck)EOPdww2f9aAcG@1k>GCe{oh?n)=)ah+ zZ9lO3qYC<4*f64nL&@#%q0wL_u|y4UBp_=)H?;Omnl0yn0Ol?q^;ql{H*t2N=g24S zjp-UYL^f?nNkI5O3c|zMAHM8wn9_XfzHXhtU`feuBG`fie0DY9Z?wf4!diJ8v$1najntW6tmXR80)P3Ih2qNxZI2_{vu>OlaXJc_}DT{OK-f=l!{iyOq*9@R7 zoxO3hGseW9fPA@Cnu8T*BlCFQ3QP-D6zipBYXr>8ZO`1D#%4e}Ys5y-{I^`kVq&w$ zu6K!@L4rz4xtk=a%wNb}9?QHC_#Z z0$&R|@M)x5IFH?Eo%E67E|XWKjt@)W6WdW2MPRMx^cj+^ul<?gAB$s#M#>jvSFzPK>Xqsf1OQ9@<0%X#aD z=vB@3Kd0%~VAloK;Y!FCzyLn(*Nhl2sgv?$J-zM?CE?J1Gy2+0)p>V@cftUcocHHb z4PH{clCC9R@(ZpiGXhkbTEQ2um}66a!WzMO%DHU2N*D1AWbA=S1MJP?1$X)i#yDAGXxvX%Sx-C5`uZsBvr<>eEI6?m>vG#^wxl=OaxmR)>WY{Femt6C`y2K$ zSy*}OY$w8(liZ>C+m)L<$Av49VfUU7}>zZiTF@&$7;tF)t_+c;=|t#Om4zCN)o~_rLECkSAc$bu9a$KFDsZ{ z4Q`MbFAAF=;%-Oy8(F3JpBG{V*-OlON{sJV)jor1m-!hjQmF~K*NAy~Gz}CF@Bihm z*P}3ojUT(aR>P@iQlEQ|0xqyp8e(^L{^PmqhaJ$Ta#)M~=tl-{$a*N?6T~qt3wxNB zg>p**^{MRRqVN{{BaE`tNzql7O)B>P~^$+M=4Lo*!PgGazFUVPVe{<|NP+#d+ zFO#mwmiE}2v41u>Q_p?g_3#%oB{4O623?td+IpBR9m>q1Eoyv1->mIyxquD%6%uGIRTm{gD`=n^0E7JcS82XNFtJlderEhx&XH#%0&y3DqP>5;a+ z47lDtXxZN{A$l0hQYY%OTIico&%75J&#F1e0Xf?r+Sn#Vki+u_5=)+ub$wA1ie*Lx z_=OdEl#tublo@Qi{yFNMB^`IT;rx_ha;zUn519d?+?VFKx4P!ET>LflD%%GDWHsFq zv-wG;zP{RqmdZJ;dWIM_02fgsRh#sPot3xK_?`J)qi@P{N7$rhJD%MjOTcwGJ1=F_ zQJD`-d+AoJ4cj~kt`lg6u6_@;98AtR8PA@y|E*gUzyEp-X;=yUJ{H!}GG zQ<1TDuGYR0TI}5s@C-aG4|iasq8%tUJH9I9{8Clq$9))4F{2Kome?)MQuVk;DZ`eN zRB7r_AtZpzI#=#ob>l`}*aHwZh#CI|k8v_TAUzMlp^QHcgqSCq1)Tv#g?&JL1}!Z; zfeR>4g)3qJnUwZ%-8%jbiwW_@(VpUosr4@gU;F~lk$&4R#(__LzZ3(ZtAWewz@9O; zX7~`uO~7+E87V{Kn@iT85r_mxwmcRvbE9Tkfrx8cHa(pC8FQZ)f^LqBWTd|#HkOQe zaTu)iH=;#@KG*r{WhgOQiEf^wa)zKR>8GC|Yt5P<%iUBd44d`s)kq1-FDPRTS-tE- z_8Kf^Jlsnlw6Di)IUq=Wurhvvc0V35W3Xn?inIwOH}~n?OCr#R77}Yf#4RdLe*w8X zHCD+yw$FDrnsbQ!HbvCE3etRrLC=2y9FT^xyg>=wgQ>0(${zisQtgS1!+s#rR&;;- zpcq|PueJ^HXkR5}(Sh$6?_ODShEoe;ZzNG(Chl9XfSC~3z9O-ud3V^p$cKyGi3Fn= zsT0MAz*`Qr&l~V{d%@=EGKFI*mf3-6m@bUo8OI}DW$CR4)PMZpevd6^)@3gn4j=F;lOYXG z%Q$D%H8eFg`qLbZN0TMS2J-*1(&7JR$~wg}0=gyfRoliX(4$owv57}<%$p}%9PA)R ziOz)m!p;UJu6bP69hzFdNJQA$4C}hUltONwh8;Wlr$XEfOzcE)w2hv(L{OS}Ocr?* zDpZl(qZIih*X(6G^H(=K(}CzLlfX$yiaas4i@wDhy3Aj zwWSjiI<`Z&G=ef$hB|A>$KRjZ;(-9aQ~x}{w}lstpn_v`I)QAo7vT4}tR@fb&h?8* zobk`*e7nlN`U=DJ<9biFCxee74md?Pnz>(dGW9eCeO$_Xb=paq;h(S7-9hkr%Sik5 z47~m~HQWfNVtGZt1wv*kUetABC^?I|%nqUJODt^9Rq- zp-AS?xGTWl}PMNqC!z2q>4Wg@A;HEM+ygZk8m*SBInF z``TCGurQCV=H*5_zc3V(1HG~}98GISKp0a!Tl2+K_T4pE^_Ll+G%blD*}9z9_3V^e zp(y6VbF3mc#;^aM@Ps@qUFVVv{$yt@y_sNL3KC~fx4 zXO&x{S1LWw;8%8l@pbu3$gra7bS3lgbiZInX~|)=dQKOIUIQBN=${C;oYwbRTeRra zVe($Z#>jR_eSelTxC1>bM1Lxv)`vhKU$Chnd$~JYZ8ndGGQVpG>k&u7v zfJxeE{+j|oG%Qp!yk*y|`;7!mr<{5{V{PYZ%n@M*B`J&ISa?&nWCkz9(IA+~1|0=C z#WhIOM3*YGB#1VF23Qi|_lbKGAeX_i4}~cQwFs;fvL0acXCNge6Csv^x#r|4%>}|6>H@|DVz#|Mji^tBbe%*9`yH z4FA7Z3h00J)fC-xkBNE7LM!%P*i7l08hwnqqT3sir+15~j#Z@+N47h0Oq=;TxShU@}A<|6h#dsai^^frG z=L>LnJrW*Cy8fp|6MCXPNMwY}@)i5tQ>Ryd7h!Hf&;EEu-hHk$y6?)2`oUevrzP}r z;qUmLmAORjeGL-QyU*U+&|h7~eYbP>u=Nj4B;~$=OJh=SoBQ1hHw1I9$s-OJvZ?6; z{yAEI8~n$-BW)%wA$gQ0cjJja+n^de&sd8zeGMYQ0bW>YiY}oEara4ocaA|od3T82 z73~D>#voS3#8iAL8qt+>LJnHDe_tze+TX8Z$#S z?;HPF#=RTh2D|+chsyQ45&ZuBQ>LhYF9n9Vhub1zJlP$;1gWVsMn*V+&ae0Gt-i2~ zjIK%f#`7-mJC6YS$X;PcPaF#`@5J3dKU2P>rw3|KC0xwl8gN~`4YJ! zksRa5n08HJU`UL})H!6AbH?X0d)P|S|&lk3EKBq-piZ@ zZktnFO;4wS%@uh+OqS_6uO8h0XVwNoI=(;qsEg2OlUwR6pO-CFg&l!@vcG%Kmb1g< zawS3M+5onjg6_^D9OM)g|D6HVnE2#c`@V1UjkN{2f@qJZ0pV(_WRo$MX&Q(~F#D$F zmHm<%_m|w*@f=xIN~79xmpF21#aLV;(A{x&LwRU-H?zJ9BOFyid()zm$$1*sdav;p zsQW~&OHSGzl8YZps3}Ng`ZLsJv~?#N5qVJ4IkSigO1h* zXku7?y)?dC3nFc7n0lD7unJVt1^nLME_4Q-Z@vhU0e`|j#;tGt>%PTNJpG_+>H^ev zFj)?XJO=&bb(oi;b{xn%H-4cW619U+kb|dKu0lgql|tqTscIN_rK2@8$-M9E#Fwtw zIXPw@T((kS5#F##EH=b7XNPcnf+LxX7JV$Q9Tgk1HV;T6-OJ(fLbB>R^hR962@egQAUeRED zV^<;Mb~}IMwqGdwM%z?fAq0dD_Mnj3sB2${uzC{LS8vDIEZbc))s3w(Clpm&CUx{IhkJ^S;0@$*2q^;9y!!y)v=L&I7V=@=P%HQb2CnPQQTI#%a>-Mj(KEVJy9uQ@2Ut;UYAkdUdPGtBWF=1kt% z-XqY|tB+x^$iOkq=w+hS-=@*cL8sU+RI;L?s4Xy*v1W{Exi<}gBNHEt8i>Cx$5-F% zeDaQ#*36A)jgmIaIMdZUEvFQ|aw;Va!v``*|${LJQ$ zJG{PR*^$YgMJ=C3e(M&Fn!_9v1f2}B$s7*FlDK(lTI*>1e#>NiB>9!TgUOgH)jQ-# zI54QwvJ;dBw=1*#q>(x+YMG46>zGPVM$A+=fNR#*ypNceOPu{9gGOxM7`dbw9qp1O z-TsRn{Sn6P5f5V{d6~qwJ>73J2cPJwT-FA5D$3M3{h+uT_CSYJy(|iU?Qs4rPQQz_ z`3rnm*)2|0>(rH|-^aIP>GQG@@*CJQJJn$k+D@C#LR>!Szl$BSmy;3SB;b?b;u66g za@tnldeA|)ay)|LdmMm&5Y_yLte~JQ7ym{o*qj9Tj+YFfy-InLY>6&7A-Dx~-A-7N z4>qt-L&0x_u$8AOa+utdB^x6GkoceQqFos@oIKT9an<+mGPzsgOl{N$@oxAY2n9U& zK1-$o9LW1bb4TUm4%D;>mQlb8^hsiu=?5bGyFFx37XO&J9#b+)lZ%GjB9(e=Zi(NA2?=nkC+mzlWRU$6^g=P>d&XR^#w_cUEn1##+t z0+oP4`X~SemVv7{{?v=PQ7#B{-@nhxW<@;f{0mbBULSl4kUIePNiY-IGKD zn=qntVn{`nX|(8{!R{BqWKb#vnP2bL4!7mM7?{@eS(*dQup1&^=A=jg< z|3)~pX>TyQ@t+e#l|;oxEYzZ?qtUwUG|wC5MoIQ64TLW(d*8dTxNop4X4K{RD!H165P_%se@fXp@qRbt_i0K>=b*k2E~fx(?5unjPuU5hX>avA=4 zO=}3!SnWWCJ&~F8Iu^rl_|f&@DszsjtB8{h5zb>;QiA@68kcN~y^B^5J1#0?MY&Y|rv6=XL%!lgB= z0VQ1XZfw{!&V>=x5!k2zcd;aJudVW%hJU^ffzs|t0;5)Cbg}7j89pm87+;j zF| Date: Sun, 19 Jul 2026 12:52:34 +0800 Subject: [PATCH 217/323] docs: include JSDoc in cordis catalog blocks --- docs/cordis-catalog/events.md | 354 +++++++- docs/cordis-catalog/services.md | 849 +++++++++++++++++- .../2026-06-20-generated-cordis-catalog.md | 6 +- ...26-07-04-cordis-jsdoc-completeness-gate.md | 6 +- .../agent/tests/gen-cordis-catalog.spec.ts | 9 +- scripts/gen-cordis-api.ts | 4 +- scripts/gen-cordis-catalog.ts | 57 +- 7 files changed, 1259 insertions(+), 26 deletions(-) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 1fc8f99af8..12f877ad48 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -3,9 +3,9 @@ # Cordis Events Catalog -Every cordis event a plugin can listen to: exact signature, dispatch mode, and the declaration's JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. +Every cordis event a plugin can listen to: exact signature, dispatch mode, and original declaration JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. -This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them. +This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence and include the original source JSDoc immediately before each event or service method. doc-typecheck skips these bare declaration fragments; type names in a signature link to the page that documents them. The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary this repo owns, grouped by scope. The **inherited tier** at the end is the cordis-core + loader/hmr/timer event surface a plugin also sees — pinned vendor source, summarized tersely. @@ -18,6 +18,16 @@ Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `n A fully configured agent and live session were published. Setup is composition-only; `agent/session-start` is the first startup-driving seam. Synchronous listener failure vetoes publication, while returned-promise rejection is reported. Detach requested during dispatch waits until every creation listener has observed the stable entry. ```ts cordis-catalog +/** + * A fully configured agent and live session were published. Setup is + * composition-only; `agent/session-start` is the first startup-driving seam. + * Synchronous listener failure vetoes publication, while returned-promise + * rejection is reported. Detach requested during dispatch waits until every + * creation listener has observed the stable entry. + * @param agent - the newly registered agent with its live session and completed setup. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/created'(this: Scoped, agent: Agent): void ``` @@ -30,6 +40,14 @@ Source: [`packages/core/agent/src/types.ts:141`](../../packages/core/agent/src/t An agent left the registry; AgentLoop emits this after driver quiescence but before session detachment and scoped-registration unwind. Custom registry users own their driver-ordering contract. ```ts cordis-catalog +/** + * An agent left the registry; AgentLoop emits this after driver quiescence + * but before session detachment and scoped-registration unwind. Custom + * registry users own their driver-ordering contract. + * @param agent - the exact agent removed from the registry. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/disposed'(this: Scoped, agent: Agent): void ``` @@ -42,6 +60,16 @@ Source: [`packages/core/agent/src/types.ts:150`](../../packages/core/agent/src/t A step or turn errored. The loop reports a failure here (plus the logger) even when the error has no in-turn position for a session `error` event. ```ts cordis-catalog +/** + * A step or turn errored. The loop reports a failure here (plus the logger) + * even when the error has no in-turn position for a session `error` event. + * @param agent - the agent whose turn errored. + * @param turn - the turn in which the failure surfaced. + * @param step - the step at which the failure surfaced. + * @param error - the failure, verbatim. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/error'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void ``` @@ -54,6 +82,22 @@ Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/t Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step. The loop derives history once afterward, so compaction records and replacements are included without rewriting an assembled request. The prompt and prefix are the exact pressure inputs for that request, and `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog +/** + * Awaited serial checkpoint for session-surface mutation after prompt + * assembly and before `step/start`; appends land outside the pending step. + * The loop derives history once afterward, so compaction records and + * replacements are included without rewriting an assembled request. The + * prompt and prefix are the exact pressure inputs for that request, and + * `signal` cancels listener work. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param agent - the agent opening the step. + * @param turn - the open turn number. + * @param step - the pending step number. + * @param fullSystemPrompt - the assembled prompt. + * @param sessionPrefix - the frozen request prefix. + * @param signal - the turn abort signal. + * @mode serial + */ 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void ``` @@ -66,6 +110,15 @@ Source: [`packages/core/agent/src/types.ts:204`](../../packages/core/agent/src/t Allow, rewrite, or block one drained prompt before it becomes a user message. Call `next()` for the unchanged default. ```ts cordis-catalog +/** + * Allow, rewrite, or block one drained prompt before it becomes a user + * message. Call `next()` for the unchanged default. + * @param agent - the agent draining its inbox. + * @param content - the drained message's blocks, as queued. + * @param source - the message's resolved source. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/prompt-submit'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise ``` @@ -78,6 +131,15 @@ Source: [`packages/core/agent/src/types.ts:214`](../../packages/core/agent/src/t Detached, frozen content entered the agent's inbox. Source defaults have already been applied, so these are the exact values retained for the log. ```ts cordis-catalog +/** + * Detached, frozen content entered the agent's inbox. Source defaults have + * already been applied, so these are the exact values retained for the log. + * @param agent - the agent whose inbox received the message. + * @param content - the accepted content blocks retained by the inbox. + * @param info - the accepted source plus whether it entered as steering. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/queued'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void ``` @@ -90,6 +152,17 @@ Source: [`packages/core/agent/src/types.ts:169`](../../packages/core/agent/src/t Replace the frozen call configuration. Model-visible content must use logged channels; this seam cannot mutate messages. Injection here joins the next request because the current step boundary is already fixed. ```ts cordis-catalog +/** + * Replace the frozen call configuration. Model-visible content must use + * logged channels; this seam cannot mutate messages. Injection here joins + * the next request because the current step boundary is already fixed. + * @param agent - the agent making the model call. + * @param turn - the open turn number. + * @param step - the step whose request this is. + * @param config - the config the loop would use (frozen); return a replacement to switch. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/request'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise ``` @@ -102,6 +175,20 @@ Source: [`packages/core/agent/src/types.ts:226`](../../packages/core/agent/src/t Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request and pressure accounting sees the composed prefix. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog +/** + * Compose request-only messages placed before derived history. The frozen + * result is computed once per loop instance, logged on its anchoring request + * header, and reused so the provider prefix remains stable. Interrupted + * composition is discarded. Composition precedes the first `agent/pre-step` + * and request boundary, so listener appends join the current request and + * pressure accounting sees the composed prefix. Changing context belongs in + * history; contributors should prepend to `await next()` to preserve registration order. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param agent - the agent whose session prefix is being composed. + * @param prefix - the frozen seed; return an extended replacement. + * @param signal - aborts composition when the step is torn down. + * @mode waterfall + */ 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise ``` @@ -114,6 +201,16 @@ Source: [`packages/core/agent/src/types.ts:241`](../../packages/core/agent/src/t The session lifecycle began, once before the first turn. Use `agent.inject()` to seed model-facing context. This is a notification, not a veto; disposal requested by a lifecycle owner is rechecked before the driver starts. ```ts cordis-catalog +/** + * The session lifecycle began, once before the first turn. Use + * `agent.inject()` to seed model-facing context. This is a notification, not + * a veto; disposal requested by a lifecycle owner is rechecked before the + * driver starts. + * @param agent - the agent whose session lifecycle began. + * @param source - why the session started (fresh startup, resume, …). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/session-start'(this: Scoped, agent: Agent, source: SessionStartSource): void ``` @@ -126,6 +223,14 @@ Source: [`packages/core/agent/src/types.ts:182`](../../packages/core/agent/src/t Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does not enter `running` synchronously; drive lifecycle from this event. ```ts cordis-catalog +/** + * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does + * not enter `running` synchronously; drive lifecycle from this event. + * @param agent - the agent whose status flipped. + * @param status - the status just entered (the transition's destination). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/status'(this: Scoped, agent: Agent, status: AgentStatus): void ``` @@ -138,6 +243,16 @@ Source: [`packages/core/agent/src/types.ts:159`](../../packages/core/agent/src/t Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …). ```ts cordis-catalog +/** + * Waterfall: post-process the assembled assistant {@link Message} before + * tool dispatch (validation, content rewriting, …). + * @param agent - the agent that received the step's response. + * @param turn - the open turn number. + * @param step - the step that produced the message. + * @param message - the assistant message as assembled from the stream. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise ``` @@ -150,6 +265,15 @@ Source: [`packages/core/agent/src/types.ts:252`](../../packages/core/agent/src/t Override whether the turn continues. The default continues after tool calls or steering and stops otherwise; a continue reason becomes steering. ```ts cordis-catalog +/** + * Override whether the turn continues. The default continues after tool + * calls or steering and stops otherwise; a continue reason becomes steering. + * @param agent - the agent deciding whether to run another step. + * @param turn - the turn being continued or stopped. + * @param defaultDecision - what the loop would do absent an override. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/turn-continuation'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise ``` @@ -162,6 +286,15 @@ Source: [`packages/core/agent/src/types.ts:262`](../../packages/core/agent/src/t Monotonic terminal-stop checkpoint after continuation and steering are folded; a stop remains authoritative through turn close and flush: steering queued in that window is discarded, while ordinary sends survive. ```ts cordis-catalog +/** + * Monotonic terminal-stop checkpoint after continuation and steering are + * folded; a stop remains authoritative through turn close and flush: + * steering queued in that window is discarded, while ordinary sends survive. + * @param agent - the agent whose composed continuation outcome may be stopped. + * @param turn - the turn at its terminal-stop checkpoint. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode serial + */ 'agent/turn-stop'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined ``` @@ -176,6 +309,15 @@ Source: [`packages/core/agent/src/types.ts:272`](../../packages/core/agent/src/t A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt. ```ts cordis-catalog +/** + * A declarative agent entry failed before it could publish a live agent. + * Consumers that buffer work for the configured identity use this + * transient signal to reject that work instead of waiting forever. Normal + * factory teardown suppresses failures from the cancelled startup attempt. + * @param sessionId - exact shared agent/session identity that failed startup. + * @param error - persistence, setup, or publication failure. + * @mode emit + */ 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` @@ -188,6 +330,13 @@ Source: [`packages/core/agent-loop/src/index.ts:362`](../../packages/core/agent- Ask composed answerers for one decision. Return an outcome to claim the request or call `next()`; failure yields the fail-closed default. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog +/** + * Ask composed answerers for one decision. Return an outcome to claim the + * request or call `next()`; failure yields the fail-closed default. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param req - the pending decision (agent, tool identity, reason, signal). + * @mode waterfall + */ 'approval/request'(this: Scoped, req: ApprovalRequest, next: () => Promise): Promise ``` @@ -202,6 +351,13 @@ Source: [`packages/ui/user-approval/src/index.ts:31`](../../packages/ui/user-app Single-slot decision for the next FileSystem.editText. Calling `next()` yields an unconditional edit; the first returned guard wins. ```ts cordis-catalog +/** + * Single-slot decision for the next {@link FileSystem.editText}. Calling + * `next()` yields an unconditional edit; the first returned guard wins. + * @param target - the resolved target about to be edited. + * @param actor - the opaque tool-execution context the decider keys off. + * @mode waterfall + */ 'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined> ``` @@ -214,6 +370,14 @@ Source: [`packages/fs/fs/src/index.ts:61`](../../packages/fs/fs/src/index.ts) Record a successful observation. Listeners must be synchronous recorders: throws fail the tool call and returned promises are not awaited. ```ts cordis-catalog +/** + * Record a successful observation. Listeners must be synchronous recorders: + * throws fail the tool call and returned promises are not awaited. + * @param target - the target that was read/written/edited. + * @param version - the version the actor now holds as its observation. + * @param actor - the observing tool-execution context; undefined records nothing useful. + * @mode emit + */ 'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void ``` @@ -226,6 +390,14 @@ Source: [`packages/fs/fs/src/index.ts:70`](../../packages/fs/fs/src/index.ts) Single-slot decision for the next FileSystem.writeText. Calling `next()` yields the bare provider's unconditional write; the first listener that returns an intent owns the decision rather than composing with peers. ```ts cordis-catalog +/** + * Single-slot decision for the next {@link FileSystem.writeText}. Calling + * `next()` yields the bare provider's unconditional write; the first listener + * that returns an intent owns the decision rather than composing with peers. + * @param target - the resolved target about to be written. + * @param actor - the opaque tool-execution context the decider keys off. + * @mode waterfall + */ 'fs/write-intent'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise): Promise ``` @@ -240,6 +412,17 @@ Source: [`packages/fs/fs/src/index.ts:53`](../../packages/fs/fs/src/index.ts) Waterfall around every streaming model call (retry, replay, routing). Bound to the LlmService; call `next()` to reach the resolved adapter's stream, or yield your own chunks to short-circuit. ```ts cordis-catalog +/** + * Waterfall around every streaming model call (retry, replay, routing). + * Bound to the {@link LlmService}; call `next()` to reach the resolved + * adapter's stream, or yield your own chunks to short-circuit. + * @param options - the full request. A LOOP-built request arrives + * deep-frozen (mutation throws): its content is a pure function of the + * session log (the reconstructability RFC), so listeners read it, never + * rewrite it. A hand-built one-shot (compaction summarize) is the + * caller's own object and stays mutable here. + * @mode waterfall + */ 'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable): AsyncIterable ``` @@ -254,6 +437,17 @@ Source: [`packages/llm/llm/src/index.ts:40`](../../packages/llm/llm/src/index.ts Creation announcement during session publication. A synchronous throw vetoes and rolls back with a paired disposal; detach requested during dispatch is deferred. A returned-promise rejection is logged but cannot retroactively veto this synchronous boundary. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only sessions entered through that agent's context. ```ts cordis-catalog +/** + * Creation announcement during session publication. A synchronous throw vetoes and rolls + * back with a paired disposal; detach requested during dispatch is deferred. + * A returned-promise rejection is logged but cannot retroactively veto this + * synchronous boundary. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners + * receive only sessions entered through that agent's context. + * @param session - the session just entered and announced. + * @dshScopeScan unsupported + * @mode emit + */ 'session/created'(this: Scoped, session: Session): void ``` @@ -264,6 +458,15 @@ Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/sr Emitted once when an announced session leaves the store, including publication rollback, but never for an entry whose creation announcement did not begin. Listener failures are logged and contained. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope. ```ts cordis-catalog +/** + * Emitted once when an announced session leaves the store, including + * publication rollback, but never for an entry whose creation announcement + * did not begin. Listener failures are logged and contained. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope. + * @param session - the session that is no longer live in the store. + * @dshScopeScan unsupported + * @mode emit + */ 'session/disposed'(this: Scoped, session: Session): void ``` @@ -274,6 +477,17 @@ Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/sr Post-commit, fire-and-forget append feed. The listener snapshot resolves before the log push, but callbacks run after it; observer failures are logged and contained without making the committed append fail. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only events from sessions entered through that agent's context. ```ts cordis-catalog +/** + * Post-commit, fire-and-forget append feed. The listener snapshot resolves + * before the log push, but callbacks run after it; observer failures are + * logged and contained without making the committed append fail. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners + * receive only events from sessions entered through that agent's context. + * @param session - the session whose log grew. + * @param event - the appended event, exactly as recorded. + * @dshScopeScan unsupported + * @mode emit + */ 'session/event'(this: Scoped, session: Session, event: SessionEvent): void ``` @@ -286,6 +500,15 @@ Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/sr Awaited parallel durability checkpoint: every listener runs and the caller awaits all of them, with no waterfall veto. Dispatch through SessionStore.flush. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the session's owner scope. ```ts cordis-catalog +/** + * Awaited parallel durability checkpoint: every listener runs and the + * caller awaits all of them, with no waterfall veto. Dispatch through + * {@link SessionStore.flush}. Scope-filtered dispatch + * (`@deepseek-ai/dsh-scope`) reuses the session's owner scope. + * @param session - the session whose buffered events must reach durable storage. + * @dshScopeScan unsupported + * @mode parallel + */ 'session/flush'(this: Scoped, session: Session): Promise | void ``` @@ -298,6 +521,14 @@ Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/sr A ready child settled. Scope-filtered dispatch uses the same delegating parent carrier as `subagent/start`, so the lifecycle pair reaches the same scoped audience. ```ts cordis-catalog +/** + * A ready child settled. Scope-filtered dispatch uses the same delegating + * parent carrier as `subagent/start`, so the lifecycle pair reaches the + * same scoped audience. + * @param info - the run identity and terminal outcome. + * @dshScopeScan unsupported + * @mode emit + */ 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` @@ -308,6 +539,11 @@ Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/ A provider became resolvable in the registry. ```ts cordis-catalog +/** + * A provider became resolvable in the registry. + * @param provider - the registered provider. + * @mode emit + */ 'subagent/provider-added'(provider: SubagentProvider): void ``` @@ -318,6 +554,11 @@ Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/s A provider left the registry. Accepted runs remain holder-owned. ```ts cordis-catalog +/** + * A provider left the registry. Accepted runs remain holder-owned. + * @param name - the provider name that no longer resolves. + * @mode emit + */ 'subagent/provider-removed'(name: string): void ``` @@ -328,6 +569,16 @@ Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/s A provider established a ready child. For in-process providers, `ctx.agents.get(info.id)` resolves during this notification. Scope-filtered dispatch keys the carrier by the delegating parent, so a parent-scoped listener observes only its own delegations. Paired with `subagent/end`. ```ts cordis-catalog +/** + * A provider established a ready child. For in-process providers, + * `ctx.agents.get(info.id)` resolves during this notification. + * Scope-filtered dispatch keys the carrier by the delegating parent, so a + * parent-scoped listener observes only its own delegations. Paired with + * `subagent/end`. + * @param info - the provider and ready child identity. + * @dshScopeScan unsupported + * @mode emit + */ 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` @@ -340,6 +591,14 @@ Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/ Expert waterfall over the assembled sections, tools, and variables. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners receive only that scope's assemblies. The returned value is authoritative. ```ts cordis-catalog +/** + * Expert waterfall over the assembled sections, tools, and variables. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners + * receive only that scope's assemblies. The returned value is authoritative. + * @param assembly - the mutable assembly built from registered providers. + * @param context - the caller's per-assembly context. + * @mode waterfall + */ 'system-prompt/assemble'(this: Scoped, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise ``` @@ -350,6 +609,11 @@ Source: [`packages/core/system-prompt/src/index.ts:27`](../../packages/core/syst Emitted when any prompt provider changes. This registry notification is unfiltered because a global change affects every scope. ```ts cordis-catalog +/** + * Emitted when any prompt provider changes. This registry notification is + * unfiltered because a global change affects every scope. + * @mode emit + */ 'system-prompt/change'(): void ``` @@ -362,6 +626,15 @@ Source: [`packages/core/system-prompt/src/index.ts:33`](../../packages/core/syst A tool was registered or unregistered, or a scoped restriction changed (the available tool set changed — possibly for one scope only). An UNFILTERED registry-subject notification, deliberately not scope-filtered dispatch: a global change concerns every agent's next assembly, so a scoped listener subscribing here sees every change, not just its own scope's. ```ts cordis-catalog +/** + * A tool was registered or unregistered, or a scoped restriction changed + * (the available tool set changed — possibly for one scope only). An + * UNFILTERED registry-subject notification, deliberately not scope-filtered + * dispatch: a global change concerns every agent's next assembly, so a + * scoped listener subscribing here sees every change, not just its own + * scope's. + * @mode emit + */ 'tools/change'(): void ``` @@ -372,6 +645,14 @@ Source: [`packages/core/tools/src/index.ts:116`](../../packages/core/tools/src/i Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns a normalized result; wrappers may change only `exec.signal`, while call identity remains immutable. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. ```ts cordis-catalog +/** + * Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns + * a normalized result; wrappers may change only `exec.signal`, while call + * identity remains immutable. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal). + * @mode waterfall + */ 'tools/execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` @@ -384,6 +665,14 @@ Source: [`packages/core/tools/src/index.ts:89`](../../packages/core/tools/src/in Accept, replace, enrich, or block a normalized dispatch result. `next()` accepts it unchanged; thrown tools still reach this seam as errors. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. ```ts cordis-catalog +/** + * Accept, replace, enrich, or block a normalized dispatch result. `next()` + * accepts it unchanged; thrown tools still reach this seam as errors. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the call that just ran (name, parsed arguments, caller agent). + * @param result - the dispatch outcome a listener may accept, replace, or block. + * @mode waterfall + */ 'tools/post-execute'(this: Scoped, exec: ToolExecution, result: Readonly, next: () => Promise): Promise ``` @@ -396,6 +685,13 @@ Source: [`packages/core/tools/src/index.ts:98`](../../packages/core/tools/src/in Allow, deny, or ask before dispatch. `next()` delegates to allow; missing approval support turns `ask` into denial. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. ```ts cordis-catalog +/** + * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing + * approval support turns `ask` into denial. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the pending call (name, parsed arguments, caller agent). + * @mode waterfall + */ 'tools/pre-execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` @@ -408,6 +704,13 @@ Source: [`packages/core/tools/src/index.ts:80`](../../packages/core/tools/src/in Observe the frozen, lossless-JSON final outcome. Listener failures are contained. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`. ```ts cordis-catalog +/** + * Observe the frozen, lossless-JSON final outcome. Listener failures are contained. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`. + * @param exec - the execution object that traversed the pipeline. + * @param result - a deep-frozen snapshot of the final returned result. + * @mode emit + */ 'tools/result'(this: Scoped, exec: Readonly, result: Readonly): undefined ``` @@ -422,6 +725,16 @@ Source: [`packages/core/tools/src/index.ts:106`](../../packages/core/tools/src/i One `agent()` call settled (clean result, child failure, or run cancellation). Paired with Events['workflow/agent-start'] by `agent.seq`, exactly once per started call on every stop path — on an engine termination path (a worker killed past its grace) the end is engine-synthesized with outcome `'cancelled'`. ```ts cordis-catalog +/** + * One `agent()` call settled (clean result, child failure, or run + * cancellation). Paired with {@link Events['workflow/agent-start']} by + * `agent.seq`, exactly once per started call on every stop path — on an + * engine termination path (a worker killed past its grace) the end is + * engine-synthesized with outcome `'cancelled'`. + * @param info - the run's identity snapshot. + * @param agent - the call identity plus its outcome. + * @mode emit + */ 'workflow/agent-end'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): void ``` @@ -432,6 +745,15 @@ Source: [`packages/workflow/workflow/src/index.ts:81`](../../packages/workflow/w One `agent()` call established a ready child run. Paired with Events['workflow/agent-end'] by `agent.seq`. A call that never receives a ready run from the provider emits neither event in this pair. ```ts cordis-catalog +/** + * One `agent()` call established a ready child run. Paired with + * {@link Events['workflow/agent-end']} by `agent.seq`. A call that never + * receives a ready run from the provider emits neither + * event in this pair. + * @param info - the run's identity snapshot. + * @param agent - the call's sequence number, label, phase, and child id. + * @mode emit + */ 'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void ``` @@ -442,6 +764,15 @@ Source: [`packages/workflow/workflow/src/index.ts:70`](../../packages/workflow/w A workflow run settled (any stop reason). Fired when WorkflowRun.result resolves. Paired with Events['workflow/start']. ```ts cordis-catalog +/** + * A workflow run settled (any stop reason). Fired when + * {@link WorkflowRun.result} resolves. Paired with + * {@link Events['workflow/start']}. + * @param info - the run's identity snapshot. + * @param result - the outcome data (stop reason, error, agent count) — + * deliberately WITHOUT the result value (see {@link WorkflowResultInfo}). + * @mode emit + */ 'workflow/end'(info: WorkflowRunInfo, result: WorkflowResultInfo): void ``` @@ -452,6 +783,12 @@ Source: [`packages/workflow/workflow/src/index.ts:91`](../../packages/workflow/w The script emitted a narration line (a `log(message)` call). ```ts cordis-catalog +/** + * The script emitted a narration line (a `log(message)` call). + * @param info - the run's identity snapshot. + * @param message - the logged message, verbatim. + * @mode emit + */ 'workflow/log'(info: WorkflowRunInfo, message: string): void ``` @@ -462,6 +799,13 @@ Source: [`packages/workflow/workflow/src/index.ts:60`](../../packages/workflow/w The script entered a phase (a `phase(title)` call) — progress grouping for observers; no execution semantics. ```ts cordis-catalog +/** + * The script entered a phase (a `phase(title)` call) — progress grouping + * for observers; no execution semantics. + * @param info - the run's identity snapshot. + * @param title - the phase title, verbatim. + * @mode emit + */ 'workflow/phase'(info: WorkflowRunInfo, title: string): void ``` @@ -472,6 +816,12 @@ Source: [`packages/workflow/workflow/src/index.ts:53`](../../packages/workflow/w A workflow run started — the script's meta block validated, the body about to execute. Paired with Events['workflow/end']. ```ts cordis-catalog +/** + * A workflow run started — the script's meta block validated, the body + * about to execute. Paired with {@link Events['workflow/end']}. + * @param info - the run's identity snapshot (id + meta). + * @mode emit + */ 'workflow/start'(info: WorkflowRunInfo): void ``` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index dd637444f0..78ec4c82c0 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -3,9 +3,9 @@ # Cordis Services Catalog -Every `ctx.` service a plugin can call: the exact public interface plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against. +Every `ctx.` service a plugin can call: the exact public interface with original method JSDoc, plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against. -This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them. +This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence and include the original source JSDoc immediately before each event or service method. doc-typecheck skips these bare declaration fragments; type names in a signature link to the page that documents them. The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary this repo owns. The **inherited tier** at the end is the cordis-core + loader/hmr/timer `ctx` surface a plugin also sees — pinned vendor source, summarized tersely. @@ -14,8 +14,31 @@ The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary Concrete agent factory and driver service. ```ts cordis-catalog +/** + * Create an agent and session under one caller-supplied identity, owned by + * the accessing fiber. Constructor-driven config calls mint a fresh combined + * id before entering this boundary. + * @param id - shared agent/session identity. + * @param options - concrete loop options. + * @param meta - optional fresh-session workspace metadata. + * @returns the published running agent. + */ create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent + +/** + * Create an owned agent on a caller-supplied session id. + * @param ownerCtx - caller context that structurally owns the transaction. + * @param options - identities, session seed/metadata, loop options, setup, and cancellation. + * @returns the published handle. + */ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise + +/** + * Resume an owned agent from the configured persistence service. + * @param ownerCtx - caller context that owns load, setup, and the live lifecycle. + * @param options - persisted identity, loop options, setup, and cancellation. + * @returns the published handle. + */ async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` @@ -28,15 +51,115 @@ Source: [`packages/core/agent-loop/src/index.ts:407`](../../packages/core/agent- Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. ```ts cordis-catalog +/** + * Register the agent-creation factory (the loop calls this on construction, + * effect-scoped). A traced Cordis service is canonicalized to its concrete + * target; each create/resume call is then traced through that caller's + * context so ownership follows the caller without stacking proxy layers. + * Throws if a factory is already registered. Returns the disposer; on + * dispose the factory slot is cleared. + * @param factory - the loop-owned factory {@link create}/{@link resume} delegate to. + * @returns the disposer that clears the factory slot. The exact + * Cordis effect disposer (single-shot): composite (generator) effects may + * yield it directly — exact identity nests the teardown in order. + */ setFactory(factory: AgentFactory): () => void + +/** + * Create and publish a new agent through the registered factory. + * Distinct from {@link register} (which records an already-constructed + * agent): this constructs the agent and its session. Rejects if no factory is + * registered or creation/setup fails. The resolved {@link AgentHandle} lets + * the owner tear down exactly this agent. + * @param options - shared identity, session seed/metadata, and agent options. + * @returns the handle after setup, rollback-covered publication, and loop start complete. + */ async create(options: CreateAgentOptions): Promise + +/** + * Load a persisted session and resume an agent on it through the registered + * factory. Rejects if no factory is registered; the factory rejects if + * session persistence is not configured or persistence/setup fails. + * @param options - persisted identity, configuration, and optional setup. + * @returns the handle after setup, rollback-covered publication, and loop start complete. + */ async resume(options: ResumeAgentOptions): Promise + +/** + * Register a live agent. Throws if an agent with the same id is already + * registered. Emits `agent/created` on registration and `agent/disposed` + * when the calling fiber is disposed — both with the agent's scope carrier + * (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the + * emits are scope-filtered regardless of which context invoked `register` + * (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always + * requires passing the carrier). Returns the disposer. + * @param agent - the already-constructed agent to record in the store. + * @returns the EXACT Cordis effect disposer (single-shot; a repeat call + * returns undefined without awaiting an in-flight teardown). Exact + * identity is load-bearing: a composite (generator) effect that owns a + * teardown ORDER — the agent factory's lifecycle chain — must yield THIS + * function so Cordis nests the unregistration at that yield position; + * yielding a wrapper would leave it disposing as a concurrent sibling on + * owner unload, unregistering the agent (and emitting `agent/disposed`) + * while its final turn is still draining. + */ register(agent: Agent): () => void + +/** + * Insert an already-constructed agent without announcing it. This is the + * advanced ordered-lifecycle primitive used by the async agent factory: it + * first completes setup while the agent is unpublished, then assigns the + * returned detach closure into its pre-installed composite teardown before + * calling {@link announce}. Ordinary callers use {@link register}. + * @param agent - the prepared, unpublished agent. + * @param owner - live agent whose scoped context created this agent, or + * undefined for a top-level runtime root. This is runtime ownership, not + * the resumed session's durable parent lineage. + * @returns an idempotent closure that removes this exact entry and emits + * `agent/disposed` with listener failures contained. When called from a + * synchronous `agent/created` listener, removal and disposal wait until + * that creation dispatch unwinds. + */ enter(agent: Agent, owner: Agent | undefined): () => void + +/** + * Announce an agent previously inserted with {@link enter}. + * @param agent - the live inserted agent to announce. + * @throws if `agent` is not the exact live registry entry for its id, or its + * creation announcement already began (including a reentrant call from a + * creation listener). + */ announce(agent: Agent): void + +/** + * Look up a live agent. + * @param id - the shared agent/session id to look up. + * @returns the agent, or undefined when no live agent has that id. + */ get(id: SessionId): Agent | undefined + +/** + * Test whether a live agent was created through one exact parent agent's + * scoped context. Runtime ownership is independent of durable session + * lineage and remains unambiguous when unrelated providers reuse an id. + * @param id - the candidate child agent's shared agent/session id. + * @param owner - the expected runtime creator agent. + * @returns true only while the exact child entry is live under that owner. + */ isOwnedBy(id: SessionId, owner: Agent): boolean + +/** + * All live agents, in registration order. + * @returns a fresh array; mutating it does not affect the registry. + */ list(): Agent[] + +/** + * All live top-level agents in registration order. A top-level agent was + * created without an owning agent context; durable session lineage does not + * affect this runtime relation, so a resumed fork may still be a root. + * @returns a fresh array; mutating it does not affect the registry. + */ roots(): Agent[] ``` @@ -49,6 +172,24 @@ Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/i Approval service that applies session policy before answerers and logs every ask/outcome pair to the requesting session. It exposes deterministic policy changes to the model through prompt and pre-step notices. ```ts cordis-catalog +/** + * Ask the composed answerers to decide one readonly same-process request. + * The service borrows the request, agent, session, and live signal directly. + * The request requires an open turn because the audit pair must be enclosed + * by the durable log's commit/replay boundary; an idle ask rejects before + * appending anything. The answerer phase always produces an outcome: an + * aborted signal yields `'cancelled'`, a missing or throwing answerer yields + * `'unavailable'` (fail closed), and a rogue non-vocabulary return value is + * normalized to `'unavailable'`. A failure that prevents either audit append + * from committing still rejects because returning an unlogged decision would + * violate the pair. Session contains post-commit observer failures, so an + * authoritative append cannot reject the request or suppress its matching + * audit event. + * @param req - the pending decision (agent, tool identity, reason, signal). + * @returns the closed outcome; `'allowed-once'` is the only grant. + * @throws when no turn is open or either audit event fails before the session + * append commit point. + */ async request(req: ApprovalRequest): Promise ``` @@ -68,8 +209,27 @@ Implementations must honor these semantics: - Disposal kills all running background processes and awaits their exit. ```ts cordis-catalog +/** + * Apply implementation-owned defaults and caps to a request before execution. + * @param request - the caller's request; omitted fields get this + * implementation's defaults, capped fields are clamped. + * @returns the fully-specified spec to hand to {@link run}/{@link start}. + */ abstract resolve(request: BashExecRequest): BashExecSpec + +/** + * Run a command in the foreground; resolves when it finishes. + * @param spec - a resolved spec from {@link resolve}, never a raw request. + * @returns the outcome; nonzero exits, timeout kills, and abort kills + * resolve with a descriptive result rather than reject. + */ abstract run(spec: BashExecSpec): Promise + +/** + * Start a background process and return its handle immediately. + * @param spec - a resolved spec from {@link resolve}, never a raw request. + * @returns the live process handle (reads, kill, quiescence promise). + */ abstract start(spec: BashExecSpec): BashProcess ``` @@ -82,8 +242,25 @@ Source: [`packages/bash/bash/src/index.ts:49`](../../packages/bash/bash/src/inde Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. The namespace is rebuilt for every model bash call: ambient `DSH_*` values are discarded by the executor, then the registry's current snapshot is injected. Built-in shell facts remain owned by the registry itself while plugins can register additional, enumerable facts with effect-scoped disposal. ```ts cordis-catalog +/** + * Register one environment contributor. Names and keys are unique; built-in + * keys are reserved. Registration is disposed with the calling plugin fiber. + * @param contributor - declared key ownership and per-execution resolver. + * @returns the disposer that unregisters the contribution. + */ register(contributor: BashEnvContributor): () => void + +/** + * Build the trusted `DSH_*` snapshot for one bash tool execution. + * @param execution - the current tool execution. + * @returns an immutable environment overlay containing built-ins and current contributions. + */ collect(execution: ToolExecution): DshEnvironment + +/** + * Enumerate plugin-contributed variables without executing their resolvers. + * @returns declarations sorted by environment variable name. + */ list(): BashEnvVariableInfo[] ``` @@ -96,6 +273,15 @@ Source: [`packages/bash/tool-bash/src/index.ts:102`](../../packages/bash/tool-ba Registers one `ctx.codeRuntime` implementation. Program, budget, abort, and substrate failures resolve in CodeRunResult; only seam misuse rejects. Implementations bridge structured-cloneable bindings while treating programs as hostile peers, isolate runs from one another, and terminate and await in-flight runs during disposal. ```ts cordis-catalog +/** + * Execute one program against the request's bindings and capture what it + * emitted. See the class doc for the resolution contract (error is a result + * field; rejection means seam misuse only). + * @param request - the program, its bindings, and the abort signal; the + * request carries everything the runtime acts on, with no hidden defaults. + * @returns the run's outcome: completion value (when transferable), the + * ordered log capture, and the failure (if any). + */ abstract run(request: CodeRunRequest): Promise ``` @@ -108,7 +294,40 @@ Source: [`packages/code-runtime/code-runtime/src/index.ts:30`](../../packages/co Abstract compaction service. Implementations own trigger policy, retention, and summarization, and may consume a separate measurement service. A successful run replaces the selected surface span with one summary node and prevents concurrent compaction of the same session. Load one implementation per context as `ctx.compact`. ```ts cordis-catalog +/** + * Check token pressure and compact if the conversation is too large. + * Estimate the next request, including its session prefix, derived history, + * and system prompt. Above threshold, compact a head-anchored range ending at + * a balanced tool boundary and reconsolidate any prior automatic checkpoint. + * Return `null` when no compaction is needed or an open tail leaves no safe + * cutoff. A single oversized retained unit or prefix cannot be repaired here. + * + * @param agent - agent context owning the session surface and model options. + * @param fullSystemPrompt - assembled system prompt, counted toward the estimate. + * @param sessionPrefix - the instance's composed session prefix, counted toward the + * estimate. + * @param signal - cancellation signal; model-backed implementations must forward it. + * @returns the compaction result, or `null` if no compaction was needed. + */ abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise + +/** + * Forcibly compact a range of surface nodes into a single summary node. + * `start` and `end` name an inclusive span by surface position, not numeric seq + * order; replacements can make visible seqs non-monotonic. Both edges must be + * balanced so assistant tool calls remain paired with their results. A model- + * backed implementation forwards cancellation and rejects active, missing, + * reversed, or unbalanced ranges. The target session is `agent.session`. + * Use {@link toolPairingBalancedBefore} and {@link toolPairingBalancedAfter} + * for the edge checks. + * + * @param start - first surface seq, inclusive. + * @param end - last surface seq, inclusive. + * @param agent - context whose session is mutated and whose routing options guide summarization. + * @param signal - optional cancellation; model-backed implementations must forward it. + * @throws when compaction is active or the range is missing, reversed, or unbalanced. + * @returns the appended event seqs, summary, replaced range, and token accounting. + */ abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` @@ -121,13 +340,90 @@ Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/comp Abstract filesystem provider. Targets must preserve identity across aliases; reads expose regular UTF-8 text or typed errors, listings are stable and content-free, and mutations are atomic. Optional guards add stale protection without changing the unguarded provider contract. ```ts cordis-catalog +/** + * Resolve a model/plugin-supplied path into a stable {@link FsTarget}. May perform I/O (a + * remote/sandboxed backend may need a round-trip to map a path to a stable identity), hence + * async even though the local backend only normalizes + realpaths. + * + * @param path - the path to resolve; relative paths resolve against `opts.cwd`. + * @param opts - optional cwd override and cancellation signal. + * @returns the stable target; the same file yields the same `targetKey`. + */ abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise + +/** + * Return target metadata, or `undefined` when the target does not exist. + * @param target - the resolved target to stat. + * @param signal - aborts the metadata round-trip. + * @returns metadata only, never content; undefined for an absent target. + */ abstract stat(target: FsTarget, signal?: AbortSignal): Promise + +/** + * Return path metadata without following the final path component when it is a + * symbolic link. This is intentionally path-shaped, not target-shaped: + * {@link resolve} follows symlinks to produce the stable identity used by + * normal reads/writes, while `lstat` lets a consumer reject the path itself + * before that follow happens. + * + * `opts.cwd` follows {@link resolve}'s cwd rules. `undefined` means the path is + * absent. + * @param path - the path to inspect; relative paths resolve against `opts.cwd`. + * @param opts - `cwd` overrides the backend's default base for relative paths. + * @param signal - aborts the metadata round-trip. + * @returns metadata only, never content; undefined for an absent path. + */ abstract lstat(path: string, opts?: { cwd?: string }, signal?: AbortSignal): Promise + +/** + * Read the whole regular text file as a single decoded string. + * @param target - the resolved target to read. + * @param signal - aborts the read. + * @returns the full decoded UTF-8 content. + */ abstract readText(target: FsTarget, signal?: AbortSignal): Promise + +/** + * Stream the whole regular text file as decoded text chunks (same text + * semantics as {@link readText}, for large files). The backend owns + * cross-chunk UTF-8 decoding and binary rejection so the policy layer never + * touches raw bytes. + * @param target - the resolved target to read. + * @param signal - aborts the stream, including between chunks. + * @returns the chunk iterable, decoded and validated like {@link readText}. + */ abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> + +/** + * List direct children of a directory in stable name order. Returns resolved + * child targets plus cheap metadata only; never reads file contents. + * @param target - the resolved directory target. + * @param signal - aborts the listing. + * @returns one entry per direct child, in stable name order. + */ abstract listDir(target: FsTarget, signal?: AbortSignal): Promise + +/** + * Atomically create or replace UTF-8 text. `expected` guards intent and + * staleness; omission allows unconditional overwrite. + * @param target - the resolved target to write. + * @param content - the full new file content. + * @param expected - the write intent guarding the write; omit for unconditional. + * @param signal - aborts before the atomic rename takes effect. + * @returns the outcome, including the version the write produced. + */ abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise + +/** + * Atomically edit literal text. When supplied, the version guard is checked + * before matching so stale content reports `FS_STALE_VERSION`; omission edits + * the current content without a freshness precondition. + * @param target - the resolved target to edit. + * @param edit - the literal search/replace request. + * @param expected - the version guard; omit for an unconditional edit. + * @param signal - aborts before the atomic rename takes effect. + * @returns the outcome, including the version the edit produced. + */ abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise ``` @@ -140,9 +436,39 @@ Source: [`packages/fs/fs/src/index.ts:80`](../../packages/fs/fs/src/index.ts) The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. ```ts cordis-catalog +/** + * Register an adapter for the given provider routes. Throws `LlmError` with code + * `DUPLICATE_ADAPTER` if any provider already has an adapter (all-or-nothing). + * Disposed with the fiber. + * @param providers - every provider route this adapter should serve. + * @param adapter - the adapter that streams calls for those providers. + * @returns the disposer that unregisters all of them. + */ registerAdapter(providers: string[], adapter: LlmAdapter): () => void + +/** + * Describe provider routes with a registered adapter. + * @returns detached provider metadata in registration order. + */ listProviders(): LlmProviderInfo[] + +/** + * Discover models advertised by one registered provider. Catalog membership + * is advisory and never changes routing or request validation. + * @param provider - registered provider route to inspect. + * @returns detached model metadata in adapter-preferred order. + */ async listModels(provider: string): Promise + +/** + * Stream one model call as raw chunks (token-level deltas). Throws + * `LlmError` with code `NO_ADAPTER` if no adapter is registered for + * `options.provider`. Replay state is retained only when the same adapter + * instance owns its historical provider and the target provider. Dispatches + * through the `llm/stream` waterfall. + * @param options - the full request; `options.provider` selects the adapter. + * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. + */ stream(options: GenerateOptions): AsyncIterable ``` @@ -155,9 +481,38 @@ Source: [`packages/llm/llm/src/index.ts:94`](../../packages/llm/llm/src/index.ts Owns the deployment's permission presets and their write path. Requires a confining `ctx.bash` executor and `ctx.approval`; unmatched knob values are reported as CUSTOM_PRESET, not an error. ```ts cordis-catalog +/** + * Resolve the preset matching the effective knob values. A still-matching + * last selection wins shared-bundle ties; otherwise the first table match + * wins, or {@link CUSTOM_PRESET} when no entry matches. + * @param events - the session's events in log order. + * @returns the effective preset name, or `custom` when nothing matches. + */ current(events: readonly SessionEvent[]): string + +/** + * Resolve a preset's knob bundle. + * @param name - the preset name to resolve. + * @returns the configured bundle. + * @throws when `name` is not in the table. + */ resolve(name: string): PresetSpec + +/** + * Build the client option for a table entry or {@link CUSTOM_PRESET}. A + * missing label falls back to the table key. + * @param name - a table key, or `custom`. + * @returns the option a client renders. + * @throws when `name` is neither a table key nor `custom`. + */ optionOf(name: string): PresetOption + +/** + * Record a changed preset, then update each changed knob through its own + * setter. Selecting the effective preset again appends nothing. + * @param session - the session the switch belongs to. + * @param name - the preset to switch to; unknown names throw. + */ set(session: Session, name: string): void ``` @@ -170,6 +525,17 @@ Source: [`packages/ui/permission/src/index.ts:94`](../../packages/ui/permission/ Abstract process-sandbox service. confine must return enforcing argv or fail closed at wrap or runner-execution time; silent unconfined passthrough is forbidden. Functional probes arbitrate multi-runner chains and may be skipped for a sole candidate, whose own refusal remains the fail-closed end. ```ts cordis-catalog +/** + * Wrap `argv` so it executes confined under `policy` on this host; the + * caller spawns the returned argv in place of its own. + * @param argv - the exact argv the caller is about to spawn (program plus + * arguments), NOT a shell string — a shell-shaped consumer passes + * `['bash', '-c', command]`. + * @param policy - the file-effect policy this execution runs under, + * carried per call (see {@link SandboxPolicy}). + * @returns the argv to spawn instead, plus the enforcement completeness + * the selected backend achieves for it. + */ abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv ``` @@ -182,10 +548,49 @@ Source: [`packages/sandbox/sandbox/src/index.ts:111`](../../packages/sandbox/san Durable append-only session storage. Implementations preserve contiguous, losslessly JSON-serializable events; append resolves only after durability, and load balances a complete interrupted tail without rewriting committed events. ```ts cordis-catalog +/** + * Resolve this backend's independent local artifact for a session without + * reading, creating, flushing, or otherwise materializing it. Backends such + * as SQLite that do not own one artifact per session return `undefined`. + * @param meta - the immutable session header whose artifact is requested. + * @returns the backend-specific absolute location, when one exists. + */ abstract locate(meta: SessionHeader): SessionLocation | undefined + +/** + * Register a new session's metadata. A backend MAY defer the physical write + * until the first {@link append} (lazy materialization), in which case a + * created-but-never-appended session is absent from {@link list} + * — abandoned sessions leave nothing behind. + * @param meta - the immutable header (id, version, cwd, lineage) to record. + */ abstract create(meta: SessionHeader): Promise + +/** + * Durably persist a batch of events (called from the write-behind drain at + * the `session/flush` checkpoint). Honors the append-only and contiguous-seq + * contracts: the first event's `seq` MUST equal the stored next-seq (after + * `load` has durably closed any interrupted turn). Rejects non-JSON- + * serializable `event.data` with an error naming the offending event type. + * @param id - the session the batch belongs to. + * @param events - the contiguous batch to persist, in seq order. + */ abstract append(id: SessionId, events: readonly SessionEvent[]): Promise + +/** + * Load a header and balanced contiguous log. A complete interrupted final + * turn is preserved and durably closed with missing tool errors plus any open + * step and turn boundaries; only a torn final record is discarded. Unknown + * versions and corruption in the committed prefix reject. + * @param id - the persisted session to reload. + * @returns the header and a log ending on a balanced `turn/end`. + */ abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> + +/** + * Lightweight listing from metadata, without a full-log parse. + * @returns one header per materialized session. + */ abstract list(): Promise ``` @@ -198,10 +603,40 @@ Source: [`packages/session-persistence/session-persistence/src/index.ts:42`](../ Live-preferred logical-corpus exact-read and relationship-tracing service. ```ts cordis-catalog +/** + * List the complete logical corpus using live-preferred records. + * @returns deterministic newest-first cloned session records. + */ listSessions(): Promise + +/** + * List lightweight raw-log event records for one logical session. + * @param sessionId - live-preferred session id to read. + * @returns event records in ascending seq order. + */ async listEvents(sessionId: SessionId): Promise + +/** + * Trace known ancestry and descendants from one corpus observation. + * @param sessionId - logical session id to trace. + * @returns a complete lineage or an explicit unresolved parent boundary. + * @throws when corpus resolution fails, the target is absent, or its known ancestry cycles. + */ async traceSession(sessionId: SessionId): Promise + +/** + * Trace one event's direct positional and provenance relationships. + * @param request - target session id and event seq. + * @returns direct links plus the target's positional replacement chain. + * @throws when source resolution fails, the target is absent, or surface/provenance validation fails. + */ async traceEvent(request: SessionEventTraceRequest): Promise + +/** + * Read one full event plus a bounded raw-log context window. + * @param request - target session/seq and context sizes. + * @returns cloned target and neighboring events. + */ async readEvent(request: SessionEventReadRequest): Promise ``` @@ -214,13 +649,119 @@ In-memory session store (`ctx.sessions`). Persistence is intentionally not implemented here — persistence plugins subscribe to `session/event` and flush on `session/flush` / dispose. ```ts cordis-catalog +/** + * Create a session owned by the calling fiber: disposing that fiber stops + * event notification and removes the session from the store. `options.seed` + * populates the session with a copy of those events (replay/fork); + * `options.meta` attaches creation metadata (validated absolute `cwd`, + * `parentSession` lineage) as the immutable {@link SessionHeader} (the store + * fills `version`/`id`/`createdAt`). + * + * For an agent whose session must be torn down IN ORDER with its loop (so the + * loop's final flush is captured before the store attachment ends), do NOT use this + * — fold the session lifecycle into the agent's own effect via + * {@link prepare} + {@link enter} + {@link announce} (see + * `dsh-agent-loop`'s creation transaction). + * + * @param id - the session id; omitted, the store mints `session-`. + * @param options - seed events and/or creation metadata for the header. + * @returns the live session, already entered and announced. + * @throws if a session with `id` already exists, metadata is not a plain + * lossless-JSON record with valid scalar fields, or `meta.cwd` is a + * non-absolute path (storage backends key directories off it). + */ create(id?: SessionId, options?: CreateSessionOptions): Session + +/** + * Build a session WITHOUT entering it into the store — validate the id/cwd and + * construct the {@link Session} (with its immutable {@link SessionHeader}). + * Pairs with {@link enter} + {@link announce}: a caller that owns a composite + * `ctx.effect` (the agent factory) folds the session lifecycle into that ONE + * effect so a fiber unload tears the session + agent down as a single ORDERED + * chain rather than as racing sibling effects — which would remove the publication hooks + * before the loop's closing `session/flush`, dropping the closing events. + * + * @param id - the session id; omitted, the store mints `session-`. + * @param options - seed events and/or creation metadata for the header. + * @returns the constructed session, NOT yet in the store. + * @throws if a session with `id` already exists, metadata is not a plain + * lossless-JSON record with valid scalar fields, or `meta.cwd` is a + * non-absolute path. + */ prepare(id?: SessionId, options?: CreateSessionOptions): Session + +/** + * Enter a {@link prepare}d session into the store: install the module-private + * append publication hooks and add it to the store. Returns the DETACH + * disposer (hooks + store removal). Does NOT emit `session/created` — + * the caller yields this disposer inside its effect and THEN calls + * {@link announce}, so a throwing `session/created` listener rolls the attach + * back instead of leaking it. + * + * Re-checks the id for a duplicate: `prepare` and `enter` are public + * cross-package primitives and a caller may interleave arbitrary work (or + * another create) between them, so a stale prepared session must NOT overwrite + * a live store entry of the same id — its detach disposer would later delete + * the REAL session. The {@link create} convenience and the agent factory call + * the two back-to-back so they never trip this, but the public seam cannot + * assume that. + * + * @param session - a {@link prepare}d session not yet in the store. + * @returns the detach disposer (publication hooks + store removal). When called from + * a synchronous `session/created` listener, removal and disposal wait until + * that creation dispatch unwinds. + * @throws if a session with this id is already in the store. + */ enter(session: Session): () => void + +/** Emit `session/created` exactly once for an {@link enter}ed session (with + * the carrier {@link enter} captured). Separate from {@link enter} so the + * caller can yield the detach disposer first (rollback safety — see + * {@link enter}). + * @param session - the entered session to announce to listeners. + * @throws if the session is not live or its announcement already began, + * including a reentrant call from a creation listener. */ announce(session: Session): void + +/** + * Dispatch the awaited `session/flush` durability checkpoint for `session`, + * with the carrier captured at {@link enter}. THE flush entry point: the + * store owns the carrier, so callers (the loop's turn-end checkpoint, idle + * injection, teardown drains) must come through here rather than dispatch a + * raw `ctx.parallel('session/flush', …)` — one owner, one spelling, and the + * scoped-dispatch invariant can pin it. + * @param session - the session whose buffered events must reach durable storage. + * @returns resolves when every flush listener has settled; after all settle, + * rejects with the first registered listener failure if any listener failed. + */ async flush(session: Session): Promise + +/** + * Look up a live session. + * @param id - the session id to look up. + * @returns the session, or undefined when no live session has that id. + */ get(id: SessionId): Session | undefined + +/** + * All live sessions, in creation order. + * @returns a fresh array; mutating it does not affect the store. + */ list(): Session[] + +/** + * Create a live child session from a turn-enclosed prefix of a live source. + * `boundary` is an inclusive source event seq; omitted means the source's + * current last event. A non-empty selected slice must end at `turn/end`. + * + * @param source - Live source session object or id. + * @param boundary - Inclusive source event seq to fork through; omitted means + * the source's current last event, and omitted on an empty source forks an + * empty child. + * @param childSessionId - Optional child session id; omitted delegates to + * `SessionStore`'s id policy. + * @returns The created live child session. + */ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` @@ -231,9 +772,42 @@ Source: [`packages/core/session/src/index.ts:577`](../../packages/core/session/s Registry of skill providers. It merges provider catalogs with stable first-wins duplicate handling, exposes sorted model-visible summaries, and loads full skill bodies on demand. ```ts cordis-catalog +/** + * Register a borrowed same-process provider synchronously during plugin apply. Duplicate and + * reserved names throw; remote initialization belongs in `list()`. Fiber disposal unregisters + * the provider and invalidates catalog caches. + * @param provider - the provider to register by `provider.name`. + * @returns the exact Cordis effect disposer that unregisters this provider; + * composite effects may yield it directly to preserve teardown ordering. + */ registerProvider(provider: SkillProvider): () => void + +/** + * Register a borrowed readonly runtime skill. Project entries outrank runtime entries, which + * outrank user entries. Same-name runtime entries are first-wins; a duplicate logs a warning and + * receives a no-op disposer so it cannot remove the winner. + * @param skill - the complete skill definition to expose for discovery. + * @returns the exact Cordis effect disposer, preserving composite teardown order and invalidating caches. + */ register(skill: SkillRegistration): () => void + +/** + * List model-invocable skill summaries for a workspace. Lookup options and + * provider candidates are readonly same-process values borrowed throughout + * discovery. + * @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery. + * @returns sorted summaries, excluding skills disabled for model invocation. + */ async list(options: SkillLookupOptions = {}): Promise + +/** + * Load and validate the winning candidate, passing its opaque discovery locator back to the + * provider. Cancellation is rechecked after selection, including cache hits, and raced against + * loading so an uncooperative provider cannot hang the caller. + * @param name - kebab-case skill name. + * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work. + * @returns the full skill, including body content, or `undefined`. + */ async get(name: string, options: SkillLookupOptions = {}): Promise ``` @@ -250,6 +824,11 @@ Semantics every implementation must honor: - `saveText` REJECTS on a real storage failure (permissions, ENOSPC, backend unavailable); the caller decides how to degrade (the spill policy treats a rejection as best-effort and keeps the inline result). ```ts cordis-catalog +/** + * Persist `input.content` to a session-scoped spill artifact. + * @param input - the owner, provenance, suggested name, and full text to save. + * @returns the saved artifact's {@link SpillRef}; rejects on a storage failure. + */ abstract saveText(input: SaveTextSpill): Promise ``` @@ -260,9 +839,37 @@ Source: [`packages/spill/spill/src/index.ts:45`](../../packages/spill/spill/src/ Named provider registry and capability-checked start surface. ```ts cordis-catalog +/** + * Register a provider under its name. Registration is effect-scoped and HMR + * safe; removing a provider blocks new starts but does not revoke runs that + * were already returned to their holders. + * @param provider - the trusted provider implementation. + * @returns the exact Cordis effect disposer. + */ registerProvider(provider: SubagentProvider): () => void + +/** + * Look up a provider by name. + * @param name - the provider name. + * @returns the provider, or undefined when absent. + */ getProvider(name: string): SubagentProvider | undefined + +/** + * List registered provider names in insertion order. + * @returns the registered names. + */ list(): string[] + +/** + * Establish a ready child on the named provider. Capability and semantic + * checks run before delegation. Provider ownership lasts until its promise + * fulfills; a rejection therefore has no run for the caller to dispose and + * emits no run lifecycle events. + * @param name - the provider to use. + * @param request - child prompt, parent, signal, and optional capabilities. + * @returns the ready holder-owned run. + */ async start(name: string, request: SubagentStartRequest): Promise ``` @@ -273,9 +880,42 @@ Source: [`packages/subagent/subagent/src/index.ts:153`](../../packages/subagent/ Registry service for the prompt inputs assembled before each model step. ```ts cordis-catalog +/** + * Register an ordered prompt section in the calling context's scope. A scoped + * section shadows a global section with the same name; duplicates within one + * layer and non-finite orders throw. Registration and disposal emit + * `system-prompt/change`. + * @param section - the section to register. + * @returns the exact Cordis effect disposer. + */ section(section: PromptSection): () => void + +/** + * Register a tool-schema provider in the calling context's scope. Global and + * matching scoped providers both contribute; returning the reserved + * {@link TOOL_ORDER_REST} name makes assembly fail. + * @param provider - evaluated for each assembly with its context. + * @returns the exact Cordis effect disposer. + */ tools(provider: (context: AssembleContext) => ToolProviderResult): () => void + +/** + * Register a prompt variable in the calling context's scope. Scoped values + * shadow globals; invalid or duplicate names throw. A provider may return + * `undefined`, but rendering a section that references that value then fails. + * @param name - the `[a-z][a-z0-9_]*` reference name. + * @param provider - evaluated for each assembly. + * @returns the exact Cordis effect disposer. + */ variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void + +/** + * Assemble global and scoped providers, detach tool parameters, apply + * canonical ordering, then run the assembly waterfall. Scoped sections and + * variables shadow globals; the returned waterfall value is authoritative. + * @param context - the optional scope and plugin-defined assembly fields. + * @returns the authoritative post-waterfall assembly. + */ async assemble(context: AssembleContext = {}): Promise ``` @@ -286,13 +926,83 @@ Source: [`packages/core/system-prompt/src/index.ts:209`](../../packages/core/sys The `tasks` service: the runtime-global background task registry. See the module doc for the ownership, isolation, and lifecycle contracts. ```ts cordis-catalog +/** + * Preflight access, validation, and owner cleanup before starting and + * atomically registering work. A throwing starter leaves nothing registered; + * after it returns, registration cannot fail. Settlement records the outcome, + * notifies listeners, and releases waiters. + * @param spec - task identity, owner, and synchronous starter. + * @returns the registry-issued `-N` id. + */ start(spec: TaskStart): TaskId + +/** + * List caller-owned and unowned tasks in registration order without exposing + * another session's labels. + * @param caller - reading agent; a non-agent caller sees only unowned tasks. + * @returns fresh snapshots. + */ list(caller?: Agent): TaskSnapshot[] + +/** + * Return a non-consuming snapshot without changing its read cursor or notice + * state. Throws for an unknown or foreign task. + * @param id - task to look up. + * @param caller - reading agent checked against the owner. + * @returns a fresh snapshot. + */ get(id: TaskId, caller?: Agent): TaskSnapshot + +/** + * Read the next stream delta, or the idempotent final output after settlement. + * A terminal read marks the task reported. Throws for an unknown or foreign + * task. + * @param id - task to read. + * @param caller - reading agent checked against the owner. + * @returns output text and the post-read snapshot. + */ read(id: TaskId, caller?: Agent): TaskRead + +/** + * Request cancellation, then mark the task stopping and reported. A producer + * throw propagates without changing task state. Throws for an unknown or + * foreign task. + * @param id - task to cancel. + * @param caller - killing agent checked against the owner. + * @param reason - logged reason forwarded to the producer. + * @returns `requested` for live work, otherwise `already-finished`. + */ kill(id: TaskId, caller?: Agent, reason?: string): 'requested' | 'already-finished' + +/** + * Wait for settlement or timeout without cancelling the task. Caller abort + * rejects only while the task is live; after settlement it returns the + * terminal snapshot so a notice suppressed for this waiter is still delivered. + * Timed-out and aborted waits detach their resolvers. Throws for invalid, + * unknown, or foreign input. + * @param id - task to wait for. + * @param timeoutMs - positive finite wait bound in milliseconds. + * @param caller - waiting agent checked against the owner. + * @param signal - optional cancellation of the wait itself. + * @returns snapshot at settlement or timeout. + */ async wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSignal): Promise + +/** + * Register an effect-scoped completion listener. Each listener is contained; + * returned promises are observed but not awaited. No listener runs after + * service disposal. + * @param listener - receives each terminal snapshot and its exact owner. + * @returns disposer that unregisters the listener. + */ onTaskDone(listener: TaskDoneListener): () => void + +/** + * Attach an effect-scoped surface that can read and stop tasks. {@link start} + * refuses work while none is attached. + * @param name - diagnostic label; duplicate names remain independent. + * @returns disposer that detaches this surface. + */ attachSurface(name: string): () => void ``` @@ -305,7 +1015,29 @@ Source: [`packages/tasks/tasks/src/index.ts:76`](../../packages/tasks/tasks/src/ Replay owner for one service-wide estimator and isolated per-session folds. ```ts cordis-catalog +/** + * Measure current request pressure and surface through the durable tail. + * + * Provider usage is reused only when the latest successful call's canonical + * request envelope matches `requestHeader` and its total is no lower than + * that call's full heuristic anchor; otherwise the complete envelope and + * surface are heuristically repriced. + * + * `requestHeader` affects request pressure only; surface fields always + * describe the current session surface. Every call clones those positional + * nodes, so measurement is O(surface). + * + * @param session - session to replay through its current durable tail. + * @param requestHeader - optional effective request envelope replacing the latest logged header. + * @returns a detached deeply immutable pressure and surface measurement. + */ measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement + +/** + * Heuristically price one model-visible message. + * @param message - message to price without mutation. + * @returns content and role-framing tokens under the fixed service heuristic. + */ estimateMessage(message: Message): number ``` @@ -318,12 +1050,72 @@ Source: [`packages/llm/token-meter/src/index.ts:106`](../../packages/llm/token-m Tool registry and execution pipeline. Scoped registrations shadow globals; one visibility resolver feeds presentation, lookup, and dispatch. ```ts cordis-catalog +/** + * Register globally or in the calling agent scope. Scoped tools shadow + * globals; duplicates within one layer and the reserved `run_code` name fail. + * @param definition - the tool schema, execution, and optional presentation functions. + * @returns the exact disposer that unregisters the tool. + */ register(definition: ToolDefinition): () => void + +/** + * Restrict global tools for the calling agent scope. Empty filters, unknown + * names, scope-local names, and reserved transport names fail. Restrictions + * intersect; scoped registrations remain visible. + * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove). + * @returns the exact disposer that lifts this restriction. + */ restrict(filter: ToolRestriction): () => void + +/** + * Register a monotonic guard after the extensible `tools/pre-execute` + * waterfall. A plain-context guard applies globally; one registered through + * `agent.ctx` applies only to that agent. Any matching guard may deny by + * returning a reason, while no guard can force-allow a call another guard + * denied. The exact effect disposer is returned for ordered ownership and + * HMR cleanup. + * @param guard - synchronous check; a returned string denies the execution. + * @returns the exact disposer that unregisters the guard. + */ guard(guard: ToolGuard): () => void + +/** + * Look up a tool as one scope sees it (scoped + * shadows global; a restricted-away global reads as absent). Presenters pass + * the calling agent so the rendered card matches the definition that + * actually executed. + * @param name - the tool name as registered. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns the definition the scope resolves, or undefined when none is visible. + */ get(name: string, scope?: ScopeKey): ToolDefinition | undefined + +/** + * Project visible definitions onto the allowlisted model-facing schema fields, + * excluding execution and presentation callbacks. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns one deep-cloned schema per visible tool. + */ schemas(scope?: ScopeKey): ToolSchema[] + +/** + * Classify a pending call through the caller's visible tool definition. Only + * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or + * throwing classifiers are exclusive. + * @param exec - call name, parsed arguments, and optional agent scope. + * @returns the fail-closed scheduling mode. + */ executionMode(exec: ToolExecutionInput): ToolExecutionMode + +/** + * Execute through pre-policy, guards, around-dispatch, post-policy, and final + * notification. Tool and listener failures resolve as materialized error + * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is + * the same lossless, frozen snapshot final observers receive. + * @param exec - the typed same-process call input. The registry assigns its + * correlation token before policy begins. + * @returns the materialized final result. + */ async execute(exec: ToolExecutionInput): Promise ``` @@ -336,7 +1128,20 @@ Source: [`packages/core/tools/src/index.ts:438`](../../packages/core/tools/src/i `ctx.userInteraction`: one active UI provider plus an `ask()` surface. ```ts cordis-catalog +/** + * Register the UI provider. Only one provider may be active in a context. + * + * @param provider UI-side implementation that collects answers. + * @returns Disposer that unregisters this provider. + */ registerProvider(provider: UserInteractionProvider): () => void + +/** + * Ask the active UI provider and wait for the user's answer. + * + * @param request Questions, owner agent, and abort signal. + * @returns The answer chosen or typed by the human. + */ async ask(request: AskUserQuestionRequest): Promise ``` @@ -356,9 +1161,43 @@ Selection semantics (resolved at execution time, never order-dependent): - No id configured, no usable provider → `WEB_PROVIDER_UNAVAILABLE`. ```ts cordis-catalog +/** + * Register a search provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER` + * if its id is already registered for search. Returns a disposer; disposed + * with the calling fiber. + * @param provider - the provider; its `id` is the registry key. + * @returns the disposer that unregisters the provider. + */ registerSearchProvider(provider: WebSearchProvider): () => void + +/** + * Register a fetch provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER` + * if its id is already registered for fetch. Returns a disposer; disposed + * with the calling fiber. + * @param provider - the provider; its `id` is the registry key. + * @returns the disposer that unregisters the provider. + */ registerFetchProvider(provider: WebFetchProvider): () => void + +/** + * Run one search through the selected provider. Resolves the provider at call + * time with the selection rules above; throws {@link WebError} when the + * capability cannot run. The seam enforces `request.maxResults` on the result: + * if the provider over-returns, `sources[]` is truncated and `truncated` set. + * @param request - the query plus result-shaping options. + * @param signal - optional cancellation signal forwarded to the provider. + * @returns the provider's results, capped to `request.maxResults`. + */ async search(request: WebSearchRequest, signal?: AbortSignal): Promise + +/** + * Retrieve one URL through the selected provider. Resolves the provider at + * call time with the selection rules above; throws {@link WebError} when the + * capability cannot run. A non-2xx response is a result, not a throw. + * @param request - the URL plus retrieval options. + * @param signal - optional cancellation signal forwarded to the provider. + * @returns the retrieval outcome; non-2xx responses resolve descriptively. + */ async fetch(request: WebFetchRequest, signal?: AbortSignal): Promise ``` @@ -369,6 +1208,12 @@ Source: [`packages/web/web/src/index.ts:74`](../../packages/web/web/src/index.ts Workflow execution seam. Invalid requests throw before publication; a live run is holder-owned, its result never rejects, cancellation and disposal are bounded, and disposal waits for child cleanup within that bound. Lifecycle listener failures are contained, and `workflow/end` fires exactly once as the result settles. ```ts cordis-catalog +/** + * Parse and execute a workflow script. + * @param request - the script, its `args`, the parent agent, and an + * optional cancel signal. + * @returns the live run; its `result` resolves when the script settles. + */ abstract start(request: WorkflowStartRequest): WorkflowRun ``` diff --git a/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md b/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md index eafce4feae..c4c57d36d6 100644 --- a/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md +++ b/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md @@ -12,7 +12,7 @@ This is the wiring-axis complement to the [core-data-structures catalog](../../. Generate the catalog from source instead of hand-maintaining a table and verifying a subset. -`scripts/gen-cordis-catalog.ts` uses the TypeScript compiler API to emit separate event and service references from declarations and source JSDoc. Events include dispatch modes; services include public signatures. Deterministic `--write` and `--check` modes make both pages generated artifacts, with freshness enforced by `doc-sync`. +`scripts/gen-cordis-catalog.ts` uses the TypeScript compiler API to emit separate event and service references from declarations and source JSDoc. Events include dispatch modes and their original member JSDoc; services include public signatures with each method's original JSDoc. Deterministic `--write` and `--check` modes make both pages generated artifacts, with freshness enforced by `doc-sync`. Pure generation is correct here because the codebase is disciplined enough that the AST is the whole truth: every event/service name is a string literal that round-trips to a static declaration — there are no dynamically-named events and no runtime-only services. So a generated doc cannot be wrong, and it closes the undocumented-event gap structurally (generation enumerates source rather than checking a hand-written subset). @@ -21,7 +21,7 @@ Specific choices: - **`@mode` tag, cross-checked.** Each harness event's JSDoc carries an explicit `@mode emit|waterfall|parallel|serial` tag; the generator hard-errors on a missing tag. Where the signature shape is conclusive — a trailing `next: () => …` parameter is structurally a waterfall — it asserts the tag agrees and hard-errors on a contradiction. The emit/parallel/serial distinction is not structurally visible (`session/flush` returns `Promise | void` with no `next`, as does the ordered `agent/pre-step` checkpoint), so it is trusted from the tag. The authoring rule lives in [AGENTS.md](../../../../AGENTS.md). - **Tiered scope.** The harness tier (the 8 `@deepseek-ai/dsh-*` services + their events) is rendered in full from source. The inherited tier (cordis-core `ctx.on/emit/effect/provide/…` + the `internal/*` events + loader/hmr/timer) is pinned vendor source a plugin also sees; it is rendered tersely (name + one-line + source pointer) from a curated table in the generator, NOT walked from the vendor AST — the cordis-core `Context` mixes true ctx members with non-service fields (`root`, `baseUrl`, `logger`), and the vendor surface changes only on a deliberate vendor sync. - **Cross-links to the data-structure catalog.** A type name in a signature (`GenerateOptions`, `StreamChunk`, `ToolDefinition`, …) links to the core-data-structures page that documents it. The map is a small hand-curated const in the generator — NOT `type-equiv.manifest.json`, which documents the `…Map` symbols while signatures reference the derived union names, and lists a few symbols on two pages. -- **A dedicated fence.** Signature blocks use a ` ```ts cordis-catalog ` info string that `doc-typecheck` recognizes and skips (a bare signature fragment is not standalone-compilable), excluded from the opt-out ratio — the same treatment `type-equiv` blocks get. +- **A dedicated fence.** Signature blocks use a ` ```ts cordis-catalog ` info string and place the original event or public-method JSDoc immediately before its declaration. `doc-typecheck` recognizes and skips the bare fragments, excluding them from the opt-out ratio — the same treatment `type-equiv` blocks get. This **supersedes the event-taxonomy half** of [doc-sync enforcement](2026-06-11-doc-sync-enforcement.md): `verify-event-taxonomy` and its `docs/architecture.md` table are retired (the architecture.md heading stays, its body now points at the catalog; the Service-map role table stays as curated prose). doc-typecheck, verify-md-wrap, verify-md-links, and verify-type-equiv are unchanged. @@ -34,6 +34,6 @@ This **supersedes the event-taxonomy half** of [doc-sync enforcement](2026-06-11 ## Consequences - The catalog cannot drift: a source change that the committed file doesn't reflect fails `verify-cordis-catalog` in the pre-push hook and CI. A new event with no `@mode` tag, or a tag that contradicts its signature, fails the generator outright. -- Event prose now has a single home — the JSDoc at the declaration. Thin JSDoc yields a thin catalog entry, which pressures authors to document at the source (the generator is a forcing function for the AGENTS.md "every export has a semantic JSDoc" rule). +- Event and service-method contracts have a single home — the JSDoc at the declaration. The catalog repeats that original JSDoc inside its generated signature block and uses its description portion as entry prose, so thin source documentation yields a thin catalog entry. - The inherited tier is hand-summarized, so a vendor sync that adds/renames a cordis-core event or `ctx` member needs a matching edit to the curated table in `gen-cordis-catalog.ts`. This is the deliberate cost of not walking pinned vendor source; it changes rarely and is called out in the generator. - `verify-event-taxonomy.ts` is deleted and the `docs/architecture.md` event table is gone; anyone who linked to a specific table row now lands on the generated catalog instead. diff --git a/docs/rfc/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md b/docs/rfc/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md index 42ab306bb0..1c7e515c4f 100644 --- a/docs/rfc/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md +++ b/docs/rfc/implemented/process/2026-07-04-cordis-jsdoc-completeness-gate.md @@ -20,14 +20,14 @@ The contract: - **Explicitness the walk can check**: the gate is a pure-AST pass (no type checker), so a service method must annotate its return type (an inferred return cannot be classified) and surface parameters must be simple identifiers (a binding pattern has no name for `@param` to match). - **Violations aggregate** into one error listing every offender — a remediation pass sees the whole list at once. The previously fail-fast `@mode` checks moved into the same aggregated report, with their message texts unchanged. -The tags are **enforcement-only**: `parseJsDoc` now ends description prose at the first block tag (standard JSDoc semantics, which also stops multi-line tag descriptions from leaking into the catalog as prose), so `@param`/`@returns` never change the rendered catalog. +The generator keeps two views of the same source comment: `parseJsDoc` ends entry prose at the first block tag, while the `ts cordis-catalog` signature block includes the original JSDoc with `@param`, `@returns`, and `@mode` intact. Readers therefore see the complete source contract without block-tag text leaking into the surrounding prose. Negative-path tests in `packages/core/agent/tests/gen-cordis-catalog.spec.ts` drive `collectEvents`/`collectServices` against synthetic fixtures to prove each guard fires and that the exemptions hold. The authoring rule lives in the root [AGENTS.md](../../../../AGENTS.md) conventions bullet alongside the `@mode` rule. ## Alternatives considered - **An ESLint rule** — cannot see the scope's machine definition (which `interface Events` members and which `ctx.` classes are the cordis surface); the catalog generator computes exactly that mapping on every run, so the gate lives there. -- **Rendering the tags into the catalog** — restructuring the services section into per-method entries was considered and deliberately deferred: source JSDoc plus IDE hover is where method docs are consumed, and the catalog stays an index. +- **Expanding every method into a separate prose section** — rejected: the catalog stays skimmable by keeping one service section and one signature block, while the JSDoc attached to each declaration preserves the full method contract in place. - **An escape-hatch tag** — none exists; the surface is small and curated (12 services, 57 methods, 27 events at adoption), and the point is that the check cannot be waved off. ## Consequences @@ -36,4 +36,4 @@ Negative-path tests in `packages/core/agent/tests/gen-cordis-catalog.spec.ts` dr - The service surface must annotate return types explicitly and use identifier parameters. Neither constraint bound at adoption (every method already annotated; no destructured seam parameters existed); both are now load-bearing requirements a violating change will discover mechanically. - The general AGENTS.md JSDoc rule ("one-liners when one line suffices") acquires a stricter carve-out on this surface: a one-line summary still suffices only when the method has no parameters and a void result. - `@param` on `next` or `this` stays legal but unchecked — a deliberate asymmetry: the gate enforces the payload contract and refuses to demand boilerplate. -- The rendered catalog is unchanged by the tags (prose stops at the first block tag). If method-level rendering is wanted later, that is a catalog-design decision to take separately, not a gap in this gate. +- Each generated event or method fragment carries its original JSDoc, while the prose summary remains tag-free. Source edits therefore refresh both the readable index and the exact contract shown beside the signature. diff --git a/packages/core/agent/tests/gen-cordis-catalog.spec.ts b/packages/core/agent/tests/gen-cordis-catalog.spec.ts index 856ef899f7..24841c8c8e 100644 --- a/packages/core/agent/tests/gen-cordis-catalog.spec.ts +++ b/packages/core/agent/tests/gen-cordis-catalog.spec.ts @@ -6,7 +6,7 @@ import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' -import { collectEvents, collectServices } from '../../../../scripts/gen-cordis-catalog.ts' +import { collectEvents, collectServices, renderEvents, renderServices } from '../../../../scripts/gen-cordis-catalog.ts' /** Write a fixture package exposing one `interface Events` block and return the * scan root to hand `collectEvents`. */ @@ -58,6 +58,8 @@ describe('gen-cordis-catalog collectEvents', () => { )) expect(events).toHaveLength(1) expect(events[0]).toMatchObject({ name: 'fix/happened', scope: 'fix', mode: 'emit', doc: 'A thing happened.' }) + expect(events[0]?.jsDoc).toBe('/**\n * A thing happened.\n * @param id - which thing.\n * @mode emit\n */') + expect(renderEvents(events)).toContain("```ts cordis-catalog\n/**\n * A thing happened.\n * @param id - which thing.\n * @mode emit\n */\n'fix/happened'(id: string): void\n```") }) it('classifies a trailing-next signature as a waterfall', () => { @@ -158,6 +160,11 @@ export class FixService { expect(services).toHaveLength(1) expect(services[0]).toMatchObject({ key: 'fix', type: 'FixService', abstract: false, doc: 'Fixture service.' }) expect(services[0]?.methods).toHaveLength(3) + expect(services[0]?.methods[0]).toEqual({ + signature: 'run(id: string): string', + jsDoc: '/**\n * Do the thing.\n * @param id - which thing to do.\n * @returns the outcome of doing it.\n */', + }) + expect(renderServices(services)).toContain('```ts cordis-catalog\n/**\n * Do the thing.\n * @param id - which thing to do.\n * @returns the outcome of doing it.\n */\nrun(id: string): string\n\n/** Fire and forget (void needs no @returns). */\npoke(): void') }) it('hard-errors on a public method with no JSDoc at all', () => { diff --git a/scripts/gen-cordis-api.ts b/scripts/gen-cordis-api.ts index cc87c379e9..5d8a70fba4 100644 --- a/scripts/gen-cordis-api.ts +++ b/scripts/gen-cordis-api.ts @@ -80,7 +80,7 @@ function referencedTypes(seeds: string[], decls: Map): { name: s function render(): string { const services = collectServices() const events = collectEvents().sort((a, b) => a.name.localeCompare(b.name)) - const types = referencedTypes(services.flatMap(service => service.methods), collectTypeDecls()) + const types = referencedTypes(services.flatMap(service => service.methods.map(method => method.signature)), collectTypeDecls()) const lines: string[] = [ '/**', ' * Generated by scripts/gen-cordis-api.ts — do not edit by hand; run', @@ -145,7 +145,7 @@ function render(): string { lines.push(' methods: [],') } else { lines.push(' methods: [') - for (const method of service.methods) lines.push(` ${quote(method)},`) + for (const method of service.methods) lines.push(` ${quote(method.signature)},`) lines.push(' ],') } lines.push(' },') diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 66bc33851b..08f04947da 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -72,6 +72,8 @@ interface EventEntry { scope: string /** Full signature text (the method-signature member, JSDoc stripped). */ signature: string + /** Original declaration JSDoc, dedented from its containing interface. */ + jsDoc: string /** Dispatch mode from the `@mode` tag. */ mode: Mode /** Description prose (JSDoc minus the `@mode` tag), one line per paragraph. */ @@ -80,6 +82,14 @@ interface EventEntry { source: string } +/** One public service method and the source contract attached to it. */ +interface ServiceMethodEntry { + /** Public method signature (body stripped). */ + signature: string + /** Original method JSDoc, dedented from its containing class. */ + jsDoc: string +} + /** One harness service, extracted from an `interface Context` block. */ interface ServiceEntry { /** The `ctx.` name, e.g. `llm`. */ @@ -90,8 +100,8 @@ interface ServiceEntry { abstract: boolean /** Class-level JSDoc prose, one line per paragraph. */ doc: string - /** Public method signatures (bodies stripped), in source order. */ - methods: string[] + /** Public methods (bodies stripped), in source order. */ + methods: ServiceMethodEntry[] /** Source pointer of the class declaration. */ source: string } @@ -115,6 +125,22 @@ function memberSignature(member: ts.TypeElement | ts.ClassElement, sf: ts.Source return sig.replace(/\s*;?\s*$/, '').replace(/\s+/g, ' ').trim() } +/** + * Copy a node's original JSDoc while removing only the indentation imposed by + * its containing interface or class. + */ +function jsDocText(text: string, sf: ts.SourceFile, node: ts.Node): string { + const raw = rawJsDoc(text, node) + if (!raw) return '' + const start = text.lastIndexOf(raw, node.getStart(sf)) + const { line } = sf.getLineAndCharacterOfPosition(start) + const lineStart = sf.getPositionOfLineAndCharacter(line, 0) + const indent = text.slice(lineStart, start) + return raw.split('\n') + .map((lineText, index) => index > 0 && lineText.startsWith(indent) ? lineText.slice(indent.length) : lineText) + .join('\n') +} + /** Walk every harness `interface Events` block and extract its events, hard- * erroring (aggregated) on any JSDoc-completeness violation: a missing/ * contradicted `@mode`, missing description prose, or an undocumented payload @@ -155,7 +181,7 @@ export function collectEvents(scanRoot: string = root): EventEntry[] { const { params } = parseTags(raw) checkParams(where, 'event', member.parameters, params, sf, p => (ts.isIdentifier(p.name) && p.name.text === 'this') || (hasNext && p === last), violations) - if (mode) entries.push({ name, scope: name.split('/')[0] ?? name, signature, mode, doc, source: src }) + if (mode) entries.push({ name, scope: name.split('/')[0] ?? name, signature, jsDoc: jsDocText(text, sf, member), mode, doc, source: src }) } } reportViolations('gen-cordis-catalog', violations) @@ -180,7 +206,7 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { if (!body) continue // Resolve each ctx key to its service class (shared walk) and emit an entry. for (const { key, type, cls, abstract, doc: clsDoc } of serviceClasses(body, sf, rel, violations)) { - const methods: string[] = [] + const methods: ServiceMethodEntry[] = [] for (const member of cls.members) { if (!ts.isMethodDeclaration(member)) continue // Only instance methods callable through `ctx.` are surface; @@ -193,9 +219,9 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { if (nonPublic) continue const memberName = member.name.getText(sf) if (memberName.startsWith('[')) continue // computed/symbol members - methods.push(memberSignature(member, sf)) const where = `service method ctx.${key}.${memberName} (${pointer(rel, sf, member)})` const raw = rawJsDoc(text, member) + methods.push({ signature: memberSignature(member, sf), jsDoc: jsDocText(text, sf, member) }) if (!raw) { violations.push(`${where} has no JSDoc.`); continue } if (!parseJsDoc(raw).doc) violations.push(`${where} has no description prose above its block tags.`) const { params, returns } = parseTags(raw) @@ -275,7 +301,7 @@ function typeLinks(signature: string): string { function renderEvent(e: EventEntry): string[] { const out = [`### \`${e.name}\` — ${e.mode}`, ''] if (e.doc) out.push(e.doc, '') - out.push('```' + FENCE, e.signature, '```', '') + out.push('```' + FENCE, e.jsDoc, e.signature, '```', '') const links = typeLinks(e.signature) if (links) out.push(links, '') out.push(`Source: [\`${e.source}\`](../../${e.source.split(':')[0]})`, '') @@ -288,8 +314,13 @@ function renderService(s: ServiceEntry): string[] { const out = [`## \`ctx.${s.key}\` — \`${s.type}\`${kind}`, ''] if (s.doc) out.push(s.doc, '') if (s.methods.length) { - out.push('```' + FENCE, ...s.methods, '```', '') - const links = typeLinks(s.methods.join('\n')) + const declarations = s.methods.flatMap((method, index) => [ + ...(index > 0 ? [''] : []), + method.jsDoc, + method.signature, + ]) + out.push('```' + FENCE, ...declarations, '```', '') + const links = typeLinks(s.methods.map(method => method.signature).join('\n')) if (links) out.push(links, '') } out.push(`Source: [\`${s.source}\`](../../${s.source.split(':')[0]})`, '') @@ -304,15 +335,15 @@ const BANNER = [ ] /** The shared GENERATED + freshness-gate + fence notice paragraph. */ -const GATE_NOTICE = 'This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them.' +const GATE_NOTICE = 'This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence and include the original source JSDoc immediately before each event or service method. doc-typecheck skips these bare declaration fragments; type names in a signature link to the page that documents them.' /** Render the events catalog (pure, deterministic given sorted inputs). */ -function renderEvents(events: EventEntry[]): string { +export function renderEvents(events: EventEntry[]): string { const lines: string[] = [ ...BANNER, '# Cordis Events Catalog', '', - 'Every cordis event a plugin can listen to: exact signature, dispatch mode, and the declaration\'s JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around.', + 'Every cordis event a plugin can listen to: exact signature, dispatch mode, and original declaration JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around.', '', GATE_NOTICE, '', @@ -342,12 +373,12 @@ function renderEvents(events: EventEntry[]): string { } /** Render the services catalog (pure, deterministic given sorted inputs). */ -function renderServices(services: ServiceEntry[]): string { +export function renderServices(services: ServiceEntry[]): string { const lines: string[] = [ ...BANNER, '# Cordis Services Catalog', '', - 'Every `ctx.` service a plugin can call: the exact public interface plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against.', + 'Every `ctx.` service a plugin can call: the exact public interface with original method JSDoc, plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against.', '', GATE_NOTICE, '', From 954c2ad2b5a2c9cedae72b3e0aa6e4efacd2a106 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:03:15 +0800 Subject: [PATCH 218/323] docs(llm-pi-ai): track overflow classification gap --- packages/llm/llm-pi-ai/src/stream.ts | 3 +++ 1 file changed, 3 insertions(+) diff --git a/packages/llm/llm-pi-ai/src/stream.ts b/packages/llm/llm-pi-ai/src/stream.ts index c3aae46c44..f7a0d6ee7f 100644 --- a/packages/llm/llm-pi-ai/src/stream.ts +++ b/packages/llm/llm-pi-ai/src/stream.ts @@ -30,6 +30,9 @@ export function mapUsage(usage: PiUsage): TokenUsage { function classifyPiAiError(message: string): string { if (/\b(?:401|403)\b/.test(message)) return 'AUTH' if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' + // TODO: Classify the full message with pi-ai's isContextOverflow() and the + // resolved model's contextWindow so provider-specific and usage-based overflows + // reach automatic compaction. if (isContextWindowExceededError(message)) return CONTEXT_WINDOW_EXCEEDED_CODE if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' if (/\b5\d\d\b/.test(message)) return 'SERVER' From edaaa50fe375cf1a058367289d0bd553880af293 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:03:31 +0800 Subject: [PATCH 219/323] test(acp): snapshot cancelled queued tool calls --- examples/acp-agent/tests/acp.snapshot.ts | 1 + .../snapshots/cancel-tool-calls/input.json | 11 +++++++++ .../cancel-tool-calls/replay.override.json | 15 ++++++++++++ .../snapshots/cancel-tool-calls/session.jsonl | 20 ++++++++++++++++ .../cancel-tool-calls/stdout.golden.jsonl | 7 ++++++ packages/support/acp-snapshot/src/harness.ts | 24 ++++++++----------- .../tests/fixtures/fake-acp-agent.ts | 20 +++++++++++++++- .../acp-snapshot/tests/harness.spec.ts | 10 ++++++++ 8 files changed, 93 insertions(+), 15 deletions(-) create mode 100644 examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json create mode 100644 examples/acp-agent/tests/snapshots/cancel-tool-calls/replay.override.json create mode 100644 examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.golden.jsonl diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 124117afef..d60d8b9724 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -103,6 +103,7 @@ const SCENARIOS: Scenario[] = [ configPath: WORKSPACE_CONTEXT_CONFIG, }, { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true }, + { name: 'cancel-tool-calls', hasModelTurn: true, recorded: false, overridden: true }, { name: 'subagent-spawn', hasModelTurn: true, recorded: true }, { name: 'subagent-multi', hasModelTurn: true, recorded: true }, { name: 'subagent-fork', hasModelTurn: true, recorded: true }, diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json b/examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json new file mode 100644 index 0000000000..3610e1f436 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json @@ -0,0 +1,11 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { + "op": "promptAndCancel", + "text": "Run two shell commands: wait for cancellation, then write skipped.txt.", + "afterUpdate": "tool_call" + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/replay.override.json b/examples/acp-agent/tests/snapshots/cancel-tool-calls/replay.override.json new file mode 100644 index 0000000000..c0aa7730d7 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/replay.override.json @@ -0,0 +1,15 @@ +[ + { + "kind": "chunks", + "chunks": [ + { "type": "block-start", "index": 0, "blockType": "tool-call" }, + { "type": "tool-call-delta", "index": 0, "id": "call_wait", "name": "bash", "argumentsDelta": "{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" }, + { "type": "block-end", "index": 0, "block": { "type": "tool-call", "id": "call_wait", "name": "bash", "arguments": "{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}" } }, + { "type": "block-start", "index": 1, "blockType": "tool-call" }, + { "type": "tool-call-delta", "index": 1, "id": "call_skipped", "name": "bash", "argumentsDelta": "{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}" }, + { "type": "block-end", "index": 1, "block": { "type": "tool-call", "id": "call_skipped", "name": "bash", "arguments": "{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}" } }, + { "type": "usage", "usage": { "inputTokens": 10, "outputTokens": 10 } }, + { "type": "finish", "reason": { "kind": "tool-calls" } } + ] + } +] diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl b/examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl new file mode 100644 index 0000000000..e6d18515a6 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl @@ -0,0 +1,20 @@ +{"type":"session","version":0,"id":"{{sessionId}}","createdAt":0,"cwd":"{{cwd}}"} +{"type":"turn/start","seq":0,"time":1784437195072,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784437195072,"data":{"content":[{"type":"text","text":"Run two shell commands: wait for cancellation, then write skipped.txt."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784437195076,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784437195076,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_wait","name":"bash","argumentsDelta":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}} +{"type":"assistant/chunk","seq":6,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":8,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_skipped","name":"bash","argumentsDelta":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}} +{"type":"assistant/chunk","seq":9,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}}}} +{"type":"assistant/chunk","seq":10,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":10}}}} +{"type":"assistant/chunk","seq":11,"time":1784437195077,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":12,"time":1784437195078,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"},{"type":"tool-call","id":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":10}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"} +{"type":"tool/call","seq":13,"time":1784437195078,"data":{"turn":1,"step":1,"callId":"call_wait","name":"bash","arguments":"{\"command\":\"node -e \\\"setInterval(() => {}, 1000)\\\"\",\"description\":\"Wait until cancellation\"}"}} +{"type":"tool/result","seq":14,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_wait","content":[{"type":"text","text":"Error: command aborted"}],"isError":true},"sourceEventSeqs":[13],"surfaceOp":"append"} +{"type":"tool/call","seq":15,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_skipped","name":"bash","arguments":"{\"command\":\"printf skipped > skipped.txt\",\"description\":\"Write skipped marker\"}"}} +{"type":"tool/result","seq":16,"time":1784437195089,"data":{"turn":1,"step":1,"callId":"call_skipped","content":[{"type":"text","text":"Error: tool call skipped because the step was aborted before execution"}],"isError":true,"error":{"name":"AbortError","code":"ABORTED"}},"sourceEventSeqs":[15],"surfaceOp":"append"} +{"type":"step/end","seq":17,"time":1784437195090,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":18,"time":1784437195090,"data":{"turn":1,"reason":{"kind":"aborted","reason":"session/cancel"}}} diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.golden.jsonl new file mode 100644 index 0000000000..11178b9bc7 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/stdout.golden.jsonl @@ -0,0 +1,7 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_wait","title":"node -e \"setInterval(() => {}, 1000)\"","kind":"execute","status":"in_progress","rawInput":"node -e \"setInterval(() => {}, 1000)\"","content":[{"type":"content","content":{"type":"text","text":"Wait until cancellation"}}]}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_wait","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: command aborted\n```"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skipped","title":"printf skipped > skipped.txt","kind":"execute","status":"in_progress","rawInput":"printf skipped > skipped.txt","content":[{"type":"content","content":{"type":"text","text":"Write skipped marker"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skipped","status":"failed","content":[{"type":"content","content":{"type":"text","text":"```console\nError: tool call skipped because the step was aborted before execution\n```"}}]}}} diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index e3efca8da9..ca00056d93 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -37,11 +37,10 @@ export type { AgentUnderTest } from './launcher.ts' * (random) session id into a `{{sessionId}}` variable that later steps * reference, since a committed file cannot know the id in advance. * - * `promptAndCancel` sends a prompt WITHOUT awaiting its response, waits until - * the client observes the first streamed `agent_message_chunk` (so the emitted - * frames deterministically precede the cancellation), then cancels the turn — - * the only way to exercise a cancel deterministically (a plain `prompt` step - * awaits the response, which a cancel/hang scenario would block on forever). + * `promptAndCancel` starts a prompt without awaiting completion, waits until + * the client observes the selected update (`agent_message_chunk` by default), + * then cancels and awaits completion. This keeps update/cancel order + * deterministic for fixtures that a plain `prompt` cannot drive. */ export type InputStep = | { op: 'initialize'; terminalOutput?: boolean } @@ -49,7 +48,7 @@ export type InputStep = | { op: 'newSessionExpectError'; additionalDirectories?: string[] } | { op: 'prompt'; text: string } | { op: 'promptExpectError'; text: string } - | { op: 'promptAndCancel'; text: string } + | { op: 'promptAndCancel'; text: string; afterUpdate?: 'agent_message_chunk' | 'tool_call' } | { op: 'cancel' } | { op: 'setConfigOption'; configId: string; value: string } | { op: 'setConfigOptionExpectError'; configId: string; value: string } @@ -342,15 +341,12 @@ async function runStep( case 'promptAndCancel': { const sessionId = getSessionId() if (sessionId === undefined) throw new Error('snapshot-harness: promptAndCancel before newSession') - // Dispatch the prompt WITHOUT awaiting (a hang fixture never resolves on - // its own). To pin frame order deterministically, wait until the client - // has OBSERVED the hang's streamed agent_message_chunk before cancelling — - // so those update frames always precede the cancelled prompt response in - // the transcript (without this, the late chunk and the response race). - // Then cancel and await the prompt, which the bridge settles as - // `cancelled` once the abort propagates. + // Dispatch without awaiting because the fixture does not settle on its + // own. Waiting for the selected update pins it before cancellation and + // the cancelled prompt response in the transcript. const promptDone = client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] }) - await waitForUpdate(u => u.sessionUpdate === 'agent_message_chunk') + const afterUpdate = step.afterUpdate ?? 'agent_message_chunk' + await waitForUpdate(u => u.sessionUpdate === afterUpdate) await client.cancel({ sessionId }) await promptDone return diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index 5dd5524ed0..dd8ca9ce92 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -33,6 +33,8 @@ interface Behavior { rejectExtraDirs?: boolean /** How `session/prompt` settles: a clean response, a JSON-RPC error, or a hang until `session/cancel`. */ prompt?: 'respond' | 'error' | 'hang-until-cancel' + /** Emit a tool call instead of a message chunk before parking a cancellable prompt. */ + cancelAtToolCall?: boolean /** Before responding to a prompt, send a `session/request_permission` request and echo its outcome as a chunk. */ permissionProbe?: boolean /** Echo the `DSH_SNAPSHOT_*` env the harness set as a chunk (spec-side env-plumbing assertions). */ @@ -126,7 +128,23 @@ async function handlePrompt(id: number | string): Promise { params: { sessionId, update: { sessionUpdate: 'agent_thought_chunk', content: { type: 'text', text: 'mulling' } } }, }) } - chunk('thinking about it') + if (behavior.cancelAtToolCall === true) { + send({ + method: 'session/update', + params: { + sessionId, + update: { + sessionUpdate: 'tool_call', + toolCallId: 'call_fake_1', + title: 'fake tool', + kind: 'execute', + status: 'in_progress', + }, + }, + }) + } else { + chunk('thinking about it') + } if (behavior.echoEnv === true) { chunk(`env:${JSON.stringify({ mode: process.env.DSH_SNAPSHOT, diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index 2b9d6e032f..be03b27c78 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -334,6 +334,16 @@ describe('runScenario', () => { expect(result.rawStdout.indexOf('thinking about it')).toBeLessThan(result.rawStdout.indexOf('cancelled')) }) + it('promptAndCancel can wait for a tool call before cancelling', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({ prompt: 'hang-until-cancel', cancelAtToolCall: true }) + const result = await runScenario( + { steps: [...boot, { op: 'promptAndCancel', text: 'hang', afterUpdate: 'tool_call' }] }, + { agent: AGENT, mode: 'replay', fixtureFile }, + ) + expect(result.rawStdout).toContain('"sessionUpdate":"tool_call"') + expect(result.rawStdout.indexOf('"sessionUpdate":"tool_call"')).toBeLessThan(result.rawStdout.indexOf('cancelled')) + }) + it('promptExpectError swallows a model-error response as the expected outcome', { timeout: 20_000 }, async () => { const { fixtureFile } = await scenario({ prompt: 'error' }) const result = await runScenario( From d709a8a1a4aab517ffdf75059f681b6ad5cc8e91 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:09:16 +0800 Subject: [PATCH 220/323] test(acp): await cancelled tool updates --- .../snapshots/cancel-tool-calls/input.json | 3 ++- packages/support/acp-snapshot/src/harness.ts | 16 +++++++++++++--- .../tests/fixtures/fake-acp-agent.ts | 15 +++++++++++++++ .../support/acp-snapshot/tests/harness.spec.ts | 18 +++++++++++++++--- 4 files changed, 45 insertions(+), 7 deletions(-) diff --git a/examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json b/examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json index 3610e1f436..0f40e9d8b6 100644 --- a/examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json +++ b/examples/acp-agent/tests/snapshots/cancel-tool-calls/input.json @@ -5,7 +5,8 @@ { "op": "promptAndCancel", "text": "Run two shell commands: wait for cancellation, then write skipped.txt.", - "afterUpdate": "tool_call" + "afterUpdate": "tool_call", + "waitForToolCallUpdate": "call_skipped" } ] } diff --git a/packages/support/acp-snapshot/src/harness.ts b/packages/support/acp-snapshot/src/harness.ts index ca00056d93..542b6d6df3 100644 --- a/packages/support/acp-snapshot/src/harness.ts +++ b/packages/support/acp-snapshot/src/harness.ts @@ -39,8 +39,8 @@ export type { AgentUnderTest } from './launcher.ts' * * `promptAndCancel` starts a prompt without awaiting completion, waits until * the client observes the selected update (`agent_message_chunk` by default), - * then cancels and awaits completion. This keeps update/cancel order - * deterministic for fixtures that a plain `prompt` cannot drive. + * then cancels and awaits completion. A named `waitForToolCallUpdate` keeps the + * step open for a terminal tool update that may follow the prompt response. */ export type InputStep = | { op: 'initialize'; terminalOutput?: boolean } @@ -48,7 +48,12 @@ export type InputStep = | { op: 'newSessionExpectError'; additionalDirectories?: string[] } | { op: 'prompt'; text: string } | { op: 'promptExpectError'; text: string } - | { op: 'promptAndCancel'; text: string; afterUpdate?: 'agent_message_chunk' | 'tool_call' } + | { + op: 'promptAndCancel' + text: string + afterUpdate?: 'agent_message_chunk' | 'tool_call' + waitForToolCallUpdate?: string + } | { op: 'cancel' } | { op: 'setConfigOption'; configId: string; value: string } | { op: 'setConfigOptionExpectError'; configId: string; value: string } @@ -347,8 +352,13 @@ async function runStep( const promptDone = client.prompt({ sessionId, prompt: [{ type: 'text', text: step.text }] }) const afterUpdate = step.afterUpdate ?? 'agent_message_chunk' await waitForUpdate(u => u.sessionUpdate === afterUpdate) + // Arm this before cancellation so a fast tool drain cannot outrun the waiter. + const toolCallUpdateDone = step.waitForToolCallUpdate === undefined + ? undefined + : waitForUpdate(u => u.sessionUpdate === 'tool_call_update' && u.toolCallId === step.waitForToolCallUpdate) await client.cancel({ sessionId }) await promptDone + if (toolCallUpdateDone !== undefined) await toolCallUpdateDone return } case 'cancel': { diff --git a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts index dd8ca9ce92..43b5ee3fb3 100644 --- a/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts +++ b/packages/support/acp-snapshot/tests/fixtures/fake-acp-agent.ts @@ -35,6 +35,8 @@ interface Behavior { prompt?: 'respond' | 'error' | 'hang-until-cancel' /** Emit a tool call instead of a message chunk before parking a cancellable prompt. */ cancelAtToolCall?: boolean + /** Emit the parked tool call's terminal update after answering cancellation. */ + cancelToolCallUpdate?: boolean /** Before responding to a prompt, send a `session/request_permission` request and echo its outcome as a chunk. */ permissionProbe?: boolean /** Echo the `DSH_SNAPSHOT_*` env the harness set as a chunk (spec-side env-plumbing assertions). */ @@ -247,6 +249,19 @@ function handleFrame(frame: Record): void { const parked = parkedPromptId parkedPromptId = null respond(parked, { stopReason: 'cancelled' }) + if (behavior.cancelToolCallUpdate === true) { + send({ + method: 'session/update', + params: { + sessionId, + update: { + sessionUpdate: 'tool_call_update', + toolCallId: 'call_fake_1', + status: 'failed', + }, + }, + }) + } } return default: diff --git a/packages/support/acp-snapshot/tests/harness.spec.ts b/packages/support/acp-snapshot/tests/harness.spec.ts index be03b27c78..3d174b3c3e 100644 --- a/packages/support/acp-snapshot/tests/harness.spec.ts +++ b/packages/support/acp-snapshot/tests/harness.spec.ts @@ -334,14 +334,26 @@ describe('runScenario', () => { expect(result.rawStdout.indexOf('thinking about it')).toBeLessThan(result.rawStdout.indexOf('cancelled')) }) - it('promptAndCancel can wait for a tool call before cancelling', { timeout: 20_000 }, async () => { - const { fixtureFile } = await scenario({ prompt: 'hang-until-cancel', cancelAtToolCall: true }) + it('promptAndCancel can bracket cancellation with tool-call updates', { timeout: 20_000 }, async () => { + const { fixtureFile } = await scenario({ + prompt: 'hang-until-cancel', + cancelAtToolCall: true, + cancelToolCallUpdate: true, + }) const result = await runScenario( - { steps: [...boot, { op: 'promptAndCancel', text: 'hang', afterUpdate: 'tool_call' }] }, + { + steps: [...boot, { + op: 'promptAndCancel', + text: 'hang', + afterUpdate: 'tool_call', + waitForToolCallUpdate: 'call_fake_1', + }], + }, { agent: AGENT, mode: 'replay', fixtureFile }, ) expect(result.rawStdout).toContain('"sessionUpdate":"tool_call"') expect(result.rawStdout.indexOf('"sessionUpdate":"tool_call"')).toBeLessThan(result.rawStdout.indexOf('cancelled')) + expect(result.rawStdout.indexOf('cancelled')).toBeLessThan(result.rawStdout.indexOf('"sessionUpdate":"tool_call_update"')) }) it('promptExpectError swallows a model-error response as the expected outcome', { timeout: 20_000 }, async () => { From 2faeabb05a2ed90f4853d04162bbc3dc57c86164 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:13:14 +0800 Subject: [PATCH 221/323] refactor(examples): rename coding-agent leaf to repl-agent Name the runnable leaf for the line-oriented front door it owns, matching the existing tui-agent and acp-agent organization. Move the complete config, Code Mode overlay, tests, metadata, and generated composition graph together, then update every loader path and repository reference. Keep the shared model identity independent of its terminal front door by phrasing the persona as a coding-agent role rather than retaining the retired leaf name. Regenerate graph and tool catalogs and re-record each affected bilingual pair so derived documentation cannot point at the removed path. --- docs/cookbook/extension-cookbook.i18n.yaml | 4 +- docs/cookbook/extension-cookbook.md | 2 +- docs/cookbook/extension-cookbook.zh.md | 2 +- docs/development.i18n.yaml | 4 +- docs/development.md | 4 +- docs/development.zh.md | 4 +- docs/graph-atlas.md | 2 +- ...t-variables-and-tool-guidance-ownership.md | 6 +- .../2026-07-08-tool-output-spill-files.md | 2 +- .../2026-06-18-compaction-capability-seam.md | 2 +- ...6-07-09-bash-backed-grep-glob-discovery.md | 2 +- ...cated-full-screen-tui-front-door.i18n.yaml | 4 +- ...17-dedicated-full-screen-tui-front-door.md | 4 +- ...dedicated-full-screen-tui-front-door.zh.md | 4 +- .../2026-07-03-documentation-graph-atlas.md | 2 +- .../2026-07-04-fold-stdio-ui-helper.md | 2 +- ...-18-tui-terminal-state-snapshots.i18n.yaml | 4 +- ...2026-07-18-tui-terminal-state-snapshots.md | 2 +- ...6-07-18-tui-terminal-state-snapshots.zh.md | 2 +- docs/tool-catalog.md | 4 +- examples/README.md | 12 +-- examples/coding-agent/composition.md | 88 ------------------- examples/cordis-agent/README.md | 2 +- examples/echo-agent/README.md | 2 +- .../{coding-agent => repl-agent}/README.md | 4 +- .../code-mode.cordis.yml | 2 +- examples/repl-agent/composition.md | 88 +++++++++++++++++++ .../{coding-agent => repl-agent}/cordis.yml | 2 +- .../{coding-agent => repl-agent}/package.json | 2 +- .../tests/code-mode-keyless-smoke.e2e.ts | 0 .../tests/code-mode.e2e.ts | 2 +- .../tests/coding-task.e2e.ts | 0 .../tests/compaction.e2e.ts | 0 .../tests/full-loop.e2e.ts | 0 .../tests/harness.ts | 2 +- .../tests/keyless-smoke.e2e.ts | 8 +- .../tests/resume.e2e.ts | 0 .../tests/todo-write.e2e.ts | 0 examples/tui-agent/README.md | 4 +- examples/tui-agent/code-mode.cordis.yml | 6 +- examples/tui-agent/composition.md | 2 +- examples/tui-agent/cordis.yml | 6 +- package.json | 2 +- packages/examples/stdio-demo/src/bin.ts | 2 +- packages/examples/stdio-demo/src/index.ts | 2 +- packages/ui/tui/src/index.ts | 2 +- scripts/demo-code-mode.mjs | 2 +- scripts/gen-doc-graphs.ts | 20 ++--- scripts/gen-tool-catalog.ts | 2 +- website/zh-CN/guide/config.md | 4 +- website/zh-CN/guide/quickstart.md | 4 +- 51 files changed, 167 insertions(+), 167 deletions(-) delete mode 100644 examples/coding-agent/composition.md rename examples/{coding-agent => repl-agent}/README.md (95%) rename examples/{coding-agent => repl-agent}/code-mode.cordis.yml (93%) create mode 100644 examples/repl-agent/composition.md rename examples/{coding-agent => repl-agent}/cordis.yml (98%) rename examples/{coding-agent => repl-agent}/package.json (81%) rename examples/{coding-agent => repl-agent}/tests/code-mode-keyless-smoke.e2e.ts (100%) rename examples/{coding-agent => repl-agent}/tests/code-mode.e2e.ts (98%) rename examples/{coding-agent => repl-agent}/tests/coding-task.e2e.ts (100%) rename examples/{coding-agent => repl-agent}/tests/compaction.e2e.ts (100%) rename examples/{coding-agent => repl-agent}/tests/full-loop.e2e.ts (100%) rename examples/{coding-agent => repl-agent}/tests/harness.ts (98%) rename examples/{coding-agent => repl-agent}/tests/keyless-smoke.e2e.ts (81%) rename examples/{coding-agent => repl-agent}/tests/resume.e2e.ts (100%) rename examples/{coding-agent => repl-agent}/tests/todo-write.e2e.ts (100%) diff --git a/docs/cookbook/extension-cookbook.i18n.yaml b/docs/cookbook/extension-cookbook.i18n.yaml index 241ab178a4..3829d4eca7 100644 --- a/docs/cookbook/extension-cookbook.i18n.yaml +++ b/docs/cookbook/extension-cookbook.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -extension-cookbook.md: 1a1f0b200801a54f067faf9866b72ccadfdc62d3 -extension-cookbook.zh.md: 891a808b4ed87b1fd92d0b68c580895956f9ab8c +extension-cookbook.md: d271ceee208e276d97188a6ebbe91e1e90a4219f +extension-cookbook.zh.md: bdd2c5f0861aa55c6f0104764a34784e5e834d10 diff --git a/docs/cookbook/extension-cookbook.md b/docs/cookbook/extension-cookbook.md index 1a1f0b2008..d271ceee20 100644 --- a/docs/cookbook/extension-cookbook.md +++ b/docs/cookbook/extension-cookbook.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## Runnable wirings -Five runnable leaves load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool, `pnpm run demo:echo`), [`examples/coding-agent`](../../examples/coding-agent) (DeepSeek V4 + coding tools through a line-oriented readline REPL, `pnpm run demo:repl`), [`examples/tui-agent`](../../examples/tui-agent) (the same coding composition through full-screen pi-tui, `pnpm run demo:tui`), [`examples/cordis-agent`](../../examples/cordis-agent) (self-inspection and dynamic plugin mounting, `pnpm run demo:cordis`), and [`examples/acp-agent`](../../examples/acp-agent) (an ACP server over JSON-RPC stdio, `pnpm run demo:acp`). The terminal leaves load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP leaf loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine through [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo). +Five runnable leaves load their plugin trees from `cordis.yml`: [`examples/echo-agent`](../../examples/echo-agent) (mock model + echo tool, `pnpm run demo:echo`), [`examples/repl-agent`](../../examples/repl-agent) (DeepSeek V4 + coding tools through a line-oriented readline REPL, `pnpm run demo:repl`), [`examples/tui-agent`](../../examples/tui-agent) (the same coding composition through full-screen pi-tui, `pnpm run demo:tui`), [`examples/cordis-agent`](../../examples/cordis-agent) (self-inspection and dynamic plugin mounting, `pnpm run demo:cordis`), and [`examples/acp-agent`](../../examples/acp-agent) (an ACP server over JSON-RPC stdio, `pnpm run demo:acp`). The terminal leaves load [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo), the ACP leaf loads [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo), and both app packages share the spine through [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo). ## The feature → mechanism map diff --git a/docs/cookbook/extension-cookbook.zh.md b/docs/cookbook/extension-cookbook.zh.md index 891a808b4e..bdd2c5f086 100644 --- a/docs/cookbook/extension-cookbook.zh.md +++ b/docs/cookbook/extension-cookbook.zh.md @@ -87,7 +87,7 @@ export function apply(ctx: Context) { ## 可运行的组装示例 -五个可运行叶子从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具，`pnpm run demo:echo`）、[`examples/coding-agent`](../../examples/coding-agent)（DeepSeek V4 + coding 工具，通过面向行的 readline REPL 交互，`pnpm run demo:repl`）、[`examples/tui-agent`](../../examples/tui-agent)（通过全屏 pi-tui 复用相同的 coding 组装，`pnpm run demo:tui`）、[`examples/cordis-agent`](../../examples/cordis-agent)（自我检查和动态插件挂载，`pnpm run demo:cordis`）与 [`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露的 ACP 服务器，`pnpm run demo:acp`）。终端叶子加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 叶子加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) 共享主干。 +五个可运行叶子从 `cordis.yml` 加载各自的插件树：[`examples/echo-agent`](../../examples/echo-agent)（mock 模型 + echo 工具，`pnpm run demo:echo`）、[`examples/repl-agent`](../../examples/repl-agent)（DeepSeek V4 + coding 工具，通过面向行的 readline REPL 交互，`pnpm run demo:repl`）、[`examples/tui-agent`](../../examples/tui-agent)（通过全屏 pi-tui 复用相同的 coding 组装，`pnpm run demo:tui`）、[`examples/cordis-agent`](../../examples/cordis-agent)（自我检查和动态插件挂载，`pnpm run demo:cordis`）与 [`examples/acp-agent`](../../examples/acp-agent)（通过 JSON-RPC stdio 暴露的 ACP 服务器，`pnpm run demo:acp`）。终端叶子加载 [`@deepseek-ai/dsh-stdio-demo`](../../packages/examples/stdio-demo)，ACP 叶子加载 [`@deepseek-ai/dsh-acp-demo`](../../packages/examples/acp-demo)，两个 app 包通过 [`@deepseek-ai/dsh-agent-spine-demo`](../../packages/examples/agent-spine-demo) 共享主干。 ## 功能→机制映射 diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index e5b3feba33..692113eb2a 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: 37811f7215001fc371ac4943fe109dd5512ea8b0 -development.zh.md: 5036e3e75516fcaf063675fc9ab4e63c1fca851a +development.md: 452f4e82beaeacb23aa6bc3e7a60c0f2b1e2c95e +development.zh.md: 2285482726c43aa02d31c7d2094e2058de1d3863 diff --git a/docs/development.md b/docs/development.md index 37811f7215..452f4e82be 100644 --- a/docs/development.md +++ b/docs/development.md @@ -109,13 +109,13 @@ The echo demo does not need API credentials: pnpm run demo:echo ``` -The coding-agent REPL uses the line-oriented readline front door and needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`: +The repl-agent demo uses the line-oriented readline front door and needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`: ```sh pnpm run demo:repl ``` -The full-screen TUI reuses the coding-agent composition through the pi-tui front door and needs the same credentials: +The full-screen TUI reuses the repl-agent composition through the pi-tui front door and needs the same credentials: ```sh pnpm run demo:tui diff --git a/docs/development.zh.md b/docs/development.zh.md index 5036e3e755..2285482726 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -109,13 +109,13 @@ echo 演示不需要 API 凭证： pnpm run demo:echo ``` -coding-agent REPL 使用面向行的 readline 前端，并需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`： +repl-agent 示例使用面向行的 readline 前端，并需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`： ```sh pnpm run demo:repl ``` -全屏 TUI 通过 pi-tui 前端复用 coding-agent 组装，并需要相同的凭证： +全屏 TUI 通过 pi-tui 前端复用 repl-agent 组装，并需要相同的凭证： ```sh pnpm run demo:tui diff --git a/docs/graph-atlas.md b/docs/graph-atlas.md index 5220cfa81f..987d8ad7a5 100644 --- a/docs/graph-atlas.md +++ b/docs/graph-atlas.md @@ -13,7 +13,7 @@ The process decision behind this index is recorded in [the documentation graph R | [tool schema catalog and package map](tool-catalog.md) | `generated` | | [capability seams and core services](capability-seams.md) | `hybrid generated` | | [echo-agent app composition](../examples/echo-agent/composition.md) | `hybrid generated` | -| [coding-agent app composition](../examples/coding-agent/composition.md) | `hybrid generated` | +| [repl-agent app composition](../examples/repl-agent/composition.md) | `hybrid generated` | | [tui-agent app composition](../examples/tui-agent/composition.md) | `hybrid generated` | | [cordis-agent app composition](../examples/cordis-agent/composition.md) | `hybrid generated` | | [acp-agent app composition](../examples/acp-agent/composition.md) | `hybrid generated` | diff --git a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md index 854807c109..c154b2080b 100644 --- a/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md +++ b/docs/rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md @@ -8,9 +8,9 @@ The assembled system prompt had four defects, all of one family: facts the harne **The model could not know its own name.** `AgentOptions.model` drives every request, but no prompt text carried it — and nothing COULD carry it: sections in `dsh-system-prompt` were context-global while the model name is per-agent, and `assemble()` took no per-agent input at all. -**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the `systemPrompt` strings of `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml` — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand; both YAMLs carried a `FIXME(config-comments)` apologizing for a symptom of the split, and the stdio welcome banner hand-enumerated the tool set too. +**Tool guidance was hand-written prose in leaf YAML.** The bash/subagent/todo_write usage guidance lived in the `systemPrompt` strings of `examples/repl-agent/cordis.yml` and `examples/acp-agent/cordis.yml` — two drifting copies (the ACP one was already abridged) — while `dsh-tool-fs` and `dsh-tool-web` owned their guidance as `ctx.systemPrompt.section()` contributions. Loading or dropping a tool plugin meant editing every deployment's persona by hand; both YAMLs carried a `FIXME(config-comments)` apologizing for a symptom of the split, and the stdio welcome banner hand-enumerated the tool set too. -**The persona rendered after tool guidance.** The loop string-joined `agent.options.systemPrompt` AFTER the assembled sections, so the model read "Use the read tool…" before "You are coding-agent" — backwards relative to the identity-first convention (Claude Code, Codex) and a second composition path besides the section pipeline. +**The persona rendered after tool guidance.** The loop string-joined `agent.options.systemPrompt` AFTER the assembled sections, so the model read "Use the read tool…" before "You are a coding agent" — backwards relative to the identity-first convention (Claude Code, Codex) and a second composition path besides the section pipeline. **The fork tool's description was false.** `dsh-tool-subagent` hardcoded one description written for spawn semantics — "a separate agent that works in its own context … it does not see this conversation" — and the `subagent_fork` instance (whose child inherits the parent's completed turns) got the same words; the YAML prose corrected the lie out-of-band. Minor kin: `PromptSection.name` was documented "(diagnostics / dedup)" but duplicates were silently accepted. @@ -56,7 +56,7 @@ Per-tool semantics and selection guidance live in tool descriptions. Prompt sect ## Shipped invariants -- The coding-agent prompt renders identity, persona with the interpolated model, then fs/bash/web guidance through one assembly path. +- The repl-agent prompt renders identity, persona with the interpolated model, then fs/bash/web guidance through one assembly path. - Fork and fresh subagent descriptions reflect whether the provider inherits completed conversation turns; the tool appears, disappears, and is reworded with provider lifecycle changes. - Unknown, valueless, malformed, or unbalanced variable references name the section and throw; duplicate section, variable, and tool registrations also throw. - Snapshot replay is prompt-independent: it keys recorded chunk streams by turn and step without comparing the outgoing request. diff --git a/docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md b/docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md index 3a60c5c223..bbca065d87 100644 --- a/docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md +++ b/docs/rfc/implemented/architecture/2026-07-08-tool-output-spill-files.md @@ -162,7 +162,7 @@ Those cases can consume `ctx.spillStore` directly in later work. They are not pa - `dsh-spill-local` unit tests cover `saveText`, `encodeSegment` sanitization (separators/tilde/whole-segment dots/empty), the session-hash directory, owner-only permissions, distinct paths per save, the configured/private root, and a storage-failure rejection. - `dsh-spill-policy` unit tests drive real tools through `ctx.tools.execute`: disabled-mode no-op, oversized-text replacement, small/non-text passthrough, `read` skip, best-effort fallback (save failure / no backend / no owner), and downstream-composition (bounding a replaced result, preserving `additionalContexts`). - `dsh-tool-web` integration drives `web_fetch` through `ctx.tools.execute` with the real `spill-local` backend + policy, proving the model-facing text changes only by the deliberate spill notice while the spill file holds the full formatted result. -- The `coding-agent` example loads `spill-local` + `spill-policy`, so its keyless Loader smoke exercises the real load path (the namespace-plugin export shape + `inject`). +- The `repl-agent` example loads `spill-local` + `spill-policy`, so its keyless Loader smoke exercises the real load path (the namespace-plugin export shape + `inject`). ## Consequences diff --git a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md index 1986ad7624..f32355326f 100644 --- a/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md +++ b/docs/rfc/implemented/feature/2026-06-18-compaction-capability-seam.md @@ -115,7 +115,7 @@ Two failure paths, both documented: - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry. - **`dsh-compact`** owns `toolPairingBalancedBefore(session, seq)` and `toolPairingBalancedAfter(session, seq)`, the cached surface-edge checks that `compactRegion` and `compactIfNeeded` use to avoid splitting a tool-call/result pair. The cache validates current membership by seq and answers both edges from one per-cut balance sequence; stale or missing seqs and orphan results reject. `dsh-session` continues to own the surface `replace` operation, ordered event sequences, and rewrite generation. - **`dsh-invariants`** drops its `surface replace: start must be <= end` assertion: a head-anchored compaction lands a high-seq replacement entry at an older range's *position*, so `start > end` numerically is normal and valid (the range is positional, validated by the surface's `indexOf` checks that remain). The turn-enclosure invariant is reused unchanged. -- **Wiring**: `examples/coding-agent/cordis.yml` loads zero-config `dsh-token-meter` before `dsh-compact-basic`; the service-wide window and compact defaults make the pair usable without repeated numeric policy. +- **Wiring**: `examples/repl-agent/cordis.yml` loads zero-config `dsh-token-meter` before `dsh-compact-basic`; the service-wide window and compact defaults make the pair usable without repeated numeric policy. ## Testing diff --git a/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md b/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md index bc8a452c91..35f65c38f2 100644 --- a/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md +++ b/docs/rfc/implemented/feature/2026-07-09-bash-backed-grep-glob-discovery.md @@ -153,7 +153,7 @@ If the complete logical result fits under the inline cap, no formatted spill art - The tools execute through `ctx.bash.resolve(request)` → `ctx.bash.run(spec)`, forward `exec.signal`, never call `ctx.bash.start()`, and never expose a bash task id. The bash request workdir comes from `exec.agent?.session.header.cwd` when available; the resolved `spec.workdir` drives execution and relative-path display. - The tools request `stdoutMaxBytes: rawOutputMaxBytes` from the bash seam, parse only untruncated stdout within that cap, and treat over-cap or still-truncated raw output as a clear search failure; raw `rg` output is never exposed to the model. - Oversized complete formatted results are saved through `ctx.spillStore.saveText()` when available while inline results stay bounded; spill failure, a missing backend, or a missing owner preserves the inline result and reports the unsaved remainder — never an `isError`. -- The package README, the generated config catalog, and exported JSDoc document the Config fields and `SEARCH_*` codes; the coding-agent example ships the tools (the acp-agent tree waits on the snapshot re-record above); the fs group README records the co-located bash/filesystem deployment requirement. +- The package README, the generated config catalog, and exported JSDoc document the Config fields and `SEARCH_*` codes; the repl-agent example ships the tools (the acp-agent tree waits on the snapshot re-record above); the fs group README records the co-located bash/filesystem deployment requirement. ## Risks diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml index d57bf423f5..8618fd884f 100644 --- a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml +++ b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-17-dedicated-full-screen-tui-front-door.md: 5e66b85fa23ef394b88fd16880cf218ac5cc2202 -2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 4ccfde2d633115a41b24227ee78f7e4010bd70ee +2026-07-17-dedicated-full-screen-tui-front-door.md: c834594b3af1e1f348aec2cf67324d5123a1ed2d +2026-07-17-dedicated-full-screen-tui-front-door.zh.md: 8cb8eb6d2812e6ecf9d98d20c64da24c2943363c diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md index 5e66b85fa2..c834594b3a 100644 --- a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md +++ b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.md @@ -14,7 +14,7 @@ The interactive channel must remain a Cordis plugin over the same agent, session DeepSeek Harness ships [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) as a dedicated Cordis plugin. It owns terminal input and presentation only; agent lifecycle, session persistence, tool execution, and the model-facing question tool remain separate composition entries. The plugin requires both stdin and stdout to be TTYs and fails instead of silently changing to line-oriented behavior. -The app layer selects a concrete terminal front door before mounting it. `@deepseek-ai/dsh-stdio-demo` can resolve `auto` from the two process streams, while the `coding-agent` and `tui-agent` leaves explicitly select readline and TUI respectively. The TUI leaf reuses the coding agent's backend and tool composition through an asserted include patch, so the three runnable agent leaves remain symmetric without duplicating deployment choices. +The app layer selects a concrete terminal front door before mounting it. `@deepseek-ai/dsh-stdio-demo` can resolve `auto` from the two process streams, while the `repl-agent` and `tui-agent` leaves explicitly select readline and TUI respectively. The TUI leaf reuses the repl-agent backend and tool composition through an asserted include patch, so the three runnable agent leaves remain symmetric without duplicating deployment choices. The selected front door receives the exact generated or resumed `SessionId` used by the pre-created agent. It mounts before the agent composition, waits for the matching root agent, and enters full-screen mode only after that agent exists. A matching `agent-loop/config-start-failed` event is therefore reported before screen takeover and exits with status 1. @@ -38,7 +38,7 @@ The implemented [TUI terminal-state snapshot RFC](../testing/2026-07-18-tui-term - **Keep readline and full-screen modes inside `@deepseek-ai/dsh-stdio`** — rejected because line-oriented output and differential TTY rendering have different dependencies, input rules, logging ownership, and teardown obligations. Separate packages keep the pipe-safe contract small and explicit. - **Let the TUI plugin silently downgrade when either stream is not a TTY** — rejected because a fallback hides deployment mistakes and changes interaction semantics. The app bundle may select a front door with `auto`; an explicitly mounted TUI fails loud. -- **Keep TUI wiring and tests under the readline `coding-agent` leaf** — rejected because one leaf would represent two distinct front doors and break symmetry with `acp-agent`. A dedicated `tui-agent` leaf owns TUI overlays and tests while reusing the coding agent's backend composition. +- **Keep TUI wiring and tests under the readline `repl-agent` leaf** — rejected because one leaf would represent two distinct front doors and break symmetry with `acp-agent`. A dedicated `tui-agent` leaf owns TUI overlays and tests while reusing the repl-agent backend composition. ## Consequences diff --git a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md index 4ccfde2d63..8cb8eb6d28 100644 --- a/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md +++ b/docs/rfc/implemented/feature/2026-07-17-dedicated-full-screen-tui-front-door.zh.md @@ -14,7 +14,7 @@ Status: implemented DeepSeek Harness 将 [`@deepseek-ai/dsh-tui`](../../../../packages/ui/tui/README.md) 作为独立的 Cordis 插件交付。该插件只负责终端输入与呈现；agent 生命周期、会话持久化、工具执行以及模型可见的提问工具仍由不同组合项负责。插件要求 stdin 和 stdout 均为 TTY；条件不满足时会失败，不会静默切换为逐行输出。 -应用组合层在挂载前选择具体的终端入口。`@deepseek-ai/dsh-stdio-demo` 可以根据两个进程流通过 `auto` 作出选择，`coding-agent` 和 `tui-agent` 叶节点则分别明确选择 readline 与 TUI。TUI 叶节点通过带断言的 include patch 复用 coding agent 的后端和工具组合，使三个可运行的 agent 叶节点保持对称，同时避免重复部署选项。 +应用组合层在挂载前选择具体的终端入口。`@deepseek-ai/dsh-stdio-demo` 可以根据两个进程流通过 `auto` 作出选择，`repl-agent` 和 `tui-agent` 叶节点则分别明确选择 readline 与 TUI。TUI 叶节点通过带断言的 include patch 复用 repl-agent 的后端和工具组合，使三个可运行的 agent 叶节点保持对称，同时避免重复部署选项。 所选入口接收预创建 agent 使用的同一个新建或恢复 `SessionId`。入口先于 agent 组合挂载，等待相符的根 agent 出现，然后才进入全屏模式。因此，相符的 `agent-loop/config-start-failed` 事件会在接管屏幕前报告，并以状态码 1 退出。 @@ -38,7 +38,7 @@ agent 空闲时，编辑器输入调用 `agent.send()`；轮次运行中则调 - **把 readline 与全屏模式都保留在 `@deepseek-ai/dsh-stdio` 中**：不予采纳，因为逐行输出和差分 TTY 渲染具有不同的依赖、输入规则、日志所有权和资源清理义务。拆分为独立包可以让管道安全契约保持精简、明确。 - **当任一进程流不是 TTY 时，让 TUI 插件静默降级**：不予采纳，因为回退会掩盖部署错误并改变交互语义。应用包可以通过 `auto` 选择入口；明确挂载的 TUI 会快速失败。 -- **把 TUI 接线与测试保留在 readline `coding-agent` 叶节点下**：不予采纳，因为一个叶节点会代表两个不同入口，也会破坏它与 `acp-agent` 的对称性。独立的 `tui-agent` 叶节点负责 TUI 浮层和测试，同时复用 coding agent 的后端组合。 +- **把 TUI 接线与测试保留在 readline `repl-agent` 叶节点下**：不予采纳，因为一个叶节点会代表两个不同入口，也会破坏它与 `acp-agent` 的对称性。独立的 `tui-agent` 叶节点负责 TUI 浮层和测试，同时复用 repl-agent 的后端组合。 ## 后果 diff --git a/docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md b/docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md index a17973ea2e..4e3148ead6 100644 --- a/docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md +++ b/docs/rfc/implemented/process/2026-07-03-documentation-graph-atlas.md @@ -34,7 +34,7 @@ The first index links ten relationship surfaces. Package topology and tool-packa | [tool schema catalog and package map](../../../tool-catalog.md) | generated | boot-harvested tool schemas plus tool-package service/effect metadata | | [capability seams and core services](../../../capability-seams.md) | hybrid generated | Cordis service declarations plus a role manifest in `gen-doc-graphs.ts` | | [echo-agent app composition](../../../../examples/echo-agent/composition.md) | hybrid generated | `examples/echo-agent/cordis.yml` plugin list plus curated app/bundle expansion | -| [coding-agent app composition](../../../../examples/coding-agent/composition.md) | hybrid generated | `examples/coding-agent/cordis.yml` plugin list plus curated app/bundle expansion | +| [repl-agent app composition](../../../../examples/repl-agent/composition.md) | hybrid generated | `examples/repl-agent/cordis.yml` plugin list plus curated app/bundle expansion | | [acp-agent app composition](../../../../examples/acp-agent/composition.md) | hybrid generated | `examples/acp-agent/cordis.yml` plugin list plus curated app/bundle expansion | | [event producer/consumer matrix](../../../event-producer-consumer.md) | hybrid generated | Cordis event declarations, AST-scanned `ctx.on/emit/parallel/serial/waterfall` sites, and explicit dynamic dispatch overrides | | [agent turn and step lifecycle](../../../agent-lifecycle.md) | curated | architecture.md loop lifecycle, Cordis catalog links, and session event semantics | diff --git a/docs/rfc/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md b/docs/rfc/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md index d3775754b9..43f35ee770 100644 --- a/docs/rfc/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md +++ b/docs/rfc/implemented/simplification/2026-07-04-fold-stdio-ui-helper.md @@ -10,7 +10,7 @@ The boundary bought package metadata, workspace and tsconfig references, module- ## Decision -The helper lives in `@deepseek-ai/dsh-stdio` as the terminal-channel plugin (`packages/ui/stdio/src/index.ts`): `createStdioChat`, its `StdioRuntime` test seam, and its unit tests (`packages/ui/stdio/tests/stdio.spec.ts`, `readline.spec.ts`) moved with it, so EOF handling, rendering, disposal, and piped-vs-TTY behavior stay unit-covered under the per-file coverage gate without hijacking process globals. The module keeps the named `name`/`inject`/`Config`/`apply` export shape — the contract the app's `ctx.plugin(uiStdio, …)` mount consumes — and the keyless Loader-path smokes in `examples/echo-agent` and `examples/coding-agent` keep proving the composed tree boots through the real Loader (the stdio package's plugin-shape unit suite pins the explicit `unwrapExports` assertion, since a bundle without `inject` would boot past a stray default rather than crash). +The helper lives in `@deepseek-ai/dsh-stdio` as the terminal-channel plugin (`packages/ui/stdio/src/index.ts`): `createStdioChat`, its `StdioRuntime` test seam, and its unit tests (`packages/ui/stdio/tests/stdio.spec.ts`, `readline.spec.ts`) moved with it, so EOF handling, rendering, disposal, and piped-vs-TTY behavior stay unit-covered under the per-file coverage gate without hijacking process globals. The module keeps the named `name`/`inject`/`Config`/`apply` export shape — the contract the app's `ctx.plugin(uiStdio, …)` mount consumes — and the keyless Loader-path smokes in `examples/echo-agent` and `examples/repl-agent` keep proving the composed tree boots through the real Loader (the stdio package's plugin-shape unit suite pins the explicit `unwrapExports` assertion, since a bundle without `inject` would boot past a stray default rather than crash). The `packages/support/ui-stdio` package is gone: manifest, tsconfig references, module-graph rows, and README rows deleted; the doc comments that named the package (the example e2e module docs, `packages/README.md`, the support and todo READMEs, [the ui group README](../../../../packages/ui/README.md)) describe the in-package module. diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml index b68f7e7e78..f111c337dc 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-18-tui-terminal-state-snapshots.md: 280c2b4faec3bd5e14a24a5df7bc901ad31718cd -2026-07-18-tui-terminal-state-snapshots.zh.md: d1c609c6ce511bba1f498b72444af662b4444578 +2026-07-18-tui-terminal-state-snapshots.md: a1363a521372c11dab8b239cad87df5ff5ca8f22 +2026-07-18-tui-terminal-state-snapshots.zh.md: aa365ba1f2ba17e5bc5409dbdc3736cbc29fe26a diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md index 280c2b4fae..a1363a5213 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md @@ -21,7 +21,7 @@ TUI coverage has four complementary layers: 3. `examples/tui-agent/tests/tui.snapshot.ts` replays committed JSONL session logs through the production agent loop and real tools, then compares the resulting semantic terminal state. 4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` boots the real Loader composition in a PTY, drives a scripted conversation through streaming and `ask_user_question`, and verifies startup, input, exit, failure reporting, and terminal restoration. -The runnable TUI has its own `examples/tui-agent` leaf beside the readline `coding-agent` and `acp-agent` leaves. It reuses the coding agent's backend and tool composition through an asserted include patch while fixing the shared terminal app to `ui.mode: tui`; TUI snapshots and PTY tests live with that leaf. +The runnable TUI has its own `examples/tui-agent` leaf beside the readline `repl-agent` and `acp-agent` leaves. It reuses the repl-agent backend and tool composition through an asserted include patch while fixing the shared terminal app to `ui.mode: tui`; TUI snapshots and PTY tests live with that leaf. ### Recorded-session replay diff --git a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md index d1c609c6ce..aa365ba1f2 100644 --- a/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md +++ b/docs/rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.zh.md @@ -21,7 +21,7 @@ TUI 覆盖分为四个互补层次： 3. `examples/tui-agent/tests/tui.snapshot.ts` 通过生产 agent loop 和真实工具回放已提交的 JSONL 会话日志，再比较生成的语义终端状态。 4. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 在 PTY 中启动真实 Loader 组合，驱动一段经过流式输出和 `ask_user_question` 的脚本化会话，并验证启动、输入、退出、失败报告和终端恢复。 -可运行 TUI 在 `examples/tui-agent` 中拥有独立叶节点，与 readline `coding-agent` 和 `acp-agent` 叶节点并列。它通过带断言的 include patch 复用 coding agent 的后端与工具组合，只把共享终端应用固定为 `ui.mode: tui`；TUI 快照和 PTY 测试也归属这个叶节点。 +可运行 TUI 在 `examples/tui-agent` 中拥有独立叶节点，与 readline `repl-agent` 和 `acp-agent` 叶节点并列。它通过带断言的 include patch 复用 repl-agent 的后端与工具组合，只把共享终端应用固定为 `ui.mode: tui`；TUI 快照和 PTY 测试也归属这个叶节点。 ### 已录制会话回放 diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index f6a2e0625f..3dacb56902 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -22,7 +22,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after successful file operations`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. | | `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.bash`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are bash-backed discovery tools: they run fixed ripgrep commands through ctx.bash as ordinary foreground calls (never background tasks). Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | | `@deepseek-ai/dsh-tool-skill` | `skill` | `ctx.tools`, `ctx.skills` | `tool/call`, `tool/result` | - | - | -| `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. | +| `@deepseek-ai/dsh-tool-subagent` | `subagent` | `ctx.tools`, `ctx.subagents` | `tool/call`, `tool/result`, `child session events through the chosen provider` | `subagent`, `subagent_fork` | The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/repl-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. | | `@deepseek-ai/dsh-tool-tasks` | `task_kill`, `task_list`, `task_output` | `ctx.tools`, `ctx.tasks`, `ctx.systemPrompt` | `tool/call`, `tool/result`, `context/message via agent.inject() for background completion notices` | - | The kind-agnostic background-task control surface: a background bash command and a background subagent are read, listed, and killed through the same three tools. Loading the plugin attaches the control surface that arms producers' `ctx.tasks.start()`. | | `@deepseek-ai/dsh-tool-todo` | `todo_write` | `ctx.tools`, `owning Agent session` | `tool/call`, `todo/write`, `tool/result` | - | todo_write is session-owned state; UIs render the latest todo/write event as a checklist or ACP plan. | | `@deepseek-ai/dsh-tool-workflow` | `workflow` | `ctx.tools`, `ctx.workflows`, `ctx.systemPrompt`, `a calling Agent (exec.agent parents the script children)` | `tool/call`, `tool/result` | - | - | @@ -444,7 +444,7 @@ Delegate a self-contained task to a subagent (a separate agent that works in its Source: [`packages/subagent/tool-subagent/src/index.ts`](../packages/subagent/tool-subagent/src/index.ts) -The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. +The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/repl-agent/cordis.yml` and `examples/acp-agent/cordis.yml`. ## `@deepseek-ai/dsh-tool-tasks` diff --git a/examples/README.md b/examples/README.md index 03b798e164..17aa65bb8e 100644 --- a/examples/README.md +++ b/examples/README.md @@ -9,21 +9,21 @@ A mock model + echo tool on the stdio chat app — the all-mock skeleton. The le - A thin leaf `cordis.yml` loading the `@deepseek-ai/dsh-stdio-demo` app - Registering a mock `LlmAdapter` (streaming scripted responses) - Registering a tool via `ctx.tools.register()` -- "Swap the backend, keep the app" — the only difference from `coding-agent` is the adapter +- "Swap the backend, keep the app" — the only difference from `repl-agent` is the adapter Run with: `pnpm run demo:echo`. When prompted, type "echo " to trigger a tool call round-trip. -## coding-agent +## repl-agent -A coding-agent REPL: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the `@deepseek-ai/dsh-stdio-demo` app's readline front door. +A coding agent with DeepSeek V4, the `read`/`write`/`edit` filesystem tools, the bash tool suite, `subagent` delegation, and the `todo_write` task tracker on the `@deepseek-ai/dsh-stdio-demo` app's readline front door. -Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [coding-agent/README.md](coding-agent/README.md) for details. +Run with: `pnpm run demo:repl` (needs `DEEPSEEK_API_KEY` in the environment or a gitignored repo-root `.env`). See [repl-agent/README.md](repl-agent/README.md) for details. -Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](coding-agent/README.md#code-mode) for its composition and a sample task. +Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the ACP example. See the [Code Mode example](repl-agent/README.md#code-mode) for its composition and a sample task. ## tui-agent -The full-screen terminal sibling of `coding-agent`: it reuses the same coding backends and tools while forcing the shared terminal app to `dsh-tui`. It is the home of TUI PTY and snapshot scenarios. +The full-screen terminal sibling of `repl-agent`: it reuses the same coding backends and tools while forcing the shared terminal app to `dsh-tui`. It is the home of TUI PTY and snapshot scenarios. Run with: `pnpm run demo:tui` (needs `DEEPSEEK_API_KEY`). See [tui-agent/README.md](tui-agent/README.md) for controls and composition. diff --git a/examples/coding-agent/composition.md b/examples/coding-agent/composition.md deleted file mode 100644 index 2956291dc8..0000000000 --- a/examples/coding-agent/composition.md +++ /dev/null @@ -1,88 +0,0 @@ - - -# Coding Agent App Composition - -The coding-agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package. - -```mermaid -flowchart LR - cfg["examples/coding-agent
cordis.yml"] - plugin_coding_hmr["hmr
@cordisjs/plugin-hmr"] - cfg --> plugin_coding_hmr - plugin_coding_llm_deepseek["llm-deepseek
@deepseek-ai/dsh-llm-deepseek"] - cfg --> plugin_coding_llm_deepseek - plugin_coding_bash["bash
@deepseek-ai/dsh-bash-local"] - cfg --> plugin_coding_bash - plugin_coding_stdio_agent["stdio-agent
@deepseek-ai/dsh-stdio-demo"] - cfg --> plugin_coding_stdio_agent - plugin_coding_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] - plugin_coding_stdio_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] - plugin_coding_stdio_agent --> frontdoor_stdio["@deepseek-ai/dsh-stdio
pre-created main agent"] - bundle_agent_core --> spine_llm["ctx.llm"] - bundle_agent_core --> spine_sessions["ctx.sessions"] - bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] - bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] - plugin_coding_token_meter["token-meter
@deepseek-ai/dsh-token-meter"] - cfg --> plugin_coding_token_meter - plugin_coding_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] - cfg --> plugin_coding_compact_basic - plugin_coding_subagent["subagent
@deepseek-ai/dsh-subagent"] - cfg --> plugin_coding_subagent - plugin_coding_subagent_spawn["subagent-spawn
@deepseek-ai/dsh-subagent-spawn"] - cfg --> plugin_coding_subagent_spawn - plugin_coding_subagent_fork["subagent-fork
@deepseek-ai/dsh-subagent-fork"] - cfg --> plugin_coding_subagent_fork - plugin_coding_tool_subagent["tool-subagent
@deepseek-ai/dsh-tool-subagent"] - cfg --> plugin_coding_tool_subagent - plugin_coding_tool_subagent_fork["tool-subagent-fork
@deepseek-ai/dsh-tool-subagent"] - cfg --> plugin_coding_tool_subagent_fork - plugin_coding_workflow_workerthread["workflow-workerthread
@deepseek-ai/dsh-workflow-workerthread"] - cfg --> plugin_coding_workflow_workerthread - plugin_coding_tool_workflow["tool-workflow
@deepseek-ai/dsh-tool-workflow"] - cfg --> plugin_coding_tool_workflow - plugin_coding_tool_todo["tool-todo
@deepseek-ai/dsh-tool-todo"] - cfg --> plugin_coding_tool_todo - plugin_coding_fs_local["fs-local
@deepseek-ai/dsh-fs-local"] - cfg --> plugin_coding_fs_local - plugin_coding_fs_policy["fs-policy
@deepseek-ai/dsh-fs-policy"] - cfg --> plugin_coding_fs_policy - plugin_coding_tool_fs["tool-fs
@deepseek-ai/dsh-tool-fs"] - cfg --> plugin_coding_tool_fs - plugin_coding_tool_fs_search["tool-fs-search
@deepseek-ai/dsh-tool-fs-search"] - cfg --> plugin_coding_tool_fs_search - plugin_coding_timeout_policy["timeout-policy
@deepseek-ai/dsh-timeout-policy"] - cfg --> plugin_coding_timeout_policy - plugin_coding_spill_local["spill-local
@deepseek-ai/dsh-spill-local"] - cfg --> plugin_coding_spill_local - plugin_coding_spill_policy["spill-policy
@deepseek-ai/dsh-spill-policy"] - cfg --> plugin_coding_spill_policy -``` - -| Plugin id | Package / module | -| --- | --- | -| `hmr` | `@cordisjs/plugin-hmr` | -| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` | -| `bash` | `@deepseek-ai/dsh-bash-local` | -| `stdio-agent` | `@deepseek-ai/dsh-stdio-demo` | -| `token-meter` | `@deepseek-ai/dsh-token-meter` | -| `compact-basic` | `@deepseek-ai/dsh-compact-basic` | -| `subagent` | `@deepseek-ai/dsh-subagent` | -| `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | -| `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` | -| `tool-subagent` | `@deepseek-ai/dsh-tool-subagent` | -| `tool-subagent-fork` | `@deepseek-ai/dsh-tool-subagent` | -| `workflow-workerthread` | `@deepseek-ai/dsh-workflow-workerthread` | -| `tool-workflow` | `@deepseek-ai/dsh-tool-workflow` | -| `tool-todo` | `@deepseek-ai/dsh-tool-todo` | -| `fs-local` | `@deepseek-ai/dsh-fs-local` | -| `fs-policy` | `@deepseek-ai/dsh-fs-policy` | -| `tool-fs` | `@deepseek-ai/dsh-tool-fs` | -| `tool-fs-search` | `@deepseek-ai/dsh-tool-fs-search` | -| `timeout-policy` | `@deepseek-ai/dsh-timeout-policy` | -| `spill-local` | `@deepseek-ai/dsh-spill-local` | -| `spill-policy` | `@deepseek-ai/dsh-spill-policy` | - -Source config: [`examples/coding-agent/cordis.yml`](cordis.yml). - -Maintenance mode: hybrid: the leaf plugin list is parsed from its `cordis.yml`; app package expansion is curated from package source. diff --git a/examples/cordis-agent/README.md b/examples/cordis-agent/README.md index 1ddf8b1d3b..5900d6a0f0 100644 --- a/examples/cordis-agent/README.md +++ b/examples/cordis-agent/README.md @@ -1,6 +1,6 @@ # cordis-agent -The self-referential harness demo: the coding-agent spine (DeepSeek V4 + local bash on the stdio chat app) plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which hands the model three tools over the **live cordis runtime it is running inside** — inspect it, mount new plugins into it, and dispose them again. The `ctx.fs` and `ctx.web` services are mounted (provider-only, no model-facing file/web tools) so the plugins the agent writes have real capabilities to build on; Node built-ins are trapped in the sandbox and redirect to those services. The design (sandbox semantics, mount lifecycle, cross-mount composition, caveats) lives in [the toolset RFC](../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). +The self-referential harness demo: the coding spine (DeepSeek V4 + local bash on the stdio chat app) plus [`@deepseek-ai/dsh-tool-cordis`](../../packages/cordis/tool-cordis/README.md), which hands the model three tools over the **live cordis runtime it is running inside** — inspect it, mount new plugins into it, and dispose them again. The `ctx.fs` and `ctx.web` services are mounted (provider-only, no model-facing file/web tools) so the plugins the agent writes have real capabilities to build on; Node built-ins are trapped in the sandbox and redirect to those services. The design (sandbox semantics, mount lifecycle, cross-mount composition, caveats) lives in [the toolset RFC](../../docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). ## Run it diff --git a/examples/echo-agent/README.md b/examples/echo-agent/README.md index 183268f5da..f397cc633f 100644 --- a/examples/echo-agent/README.md +++ b/examples/echo-agent/README.md @@ -9,7 +9,7 @@ This example is just a leaf `cordis.yml`: it loads the [`@deepseek-ai/dsh-stdio- - `mock-llm.ts` — a mock `LlmAdapter` that streams scripted responses and calls the `echo` tool when the user types "echo ". Registered with `ctx.llm.registerAdapter(['mock-echo'], …)`. - `echo-tool.ts` — a tool registered via `ctx.tools.register(defineTool(…))` with typed `execute` args; echoes text back uppercased. -Swapping `mock-llm` for the real `llm-deepseek` adapter is all that separates this from `coding-agent` — the same app, a different backend. +Swapping `mock-llm` for the real `llm-deepseek` adapter is all that separates this from `repl-agent` — the same app, a different backend. ## Plugin files diff --git a/examples/coding-agent/README.md b/examples/repl-agent/README.md similarity index 95% rename from examples/coding-agent/README.md rename to examples/repl-agent/README.md index 40e8b7087f..2e559d129a 100644 --- a/examples/coding-agent/README.md +++ b/examples/repl-agent/README.md @@ -1,6 +1,6 @@ -# coding-agent +# repl-agent -The coding-agent REPL wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + readline chat + JSONL persistence, loaded from `cordis.yml`. The sibling [`tui-agent`](../tui-agent/README.md) fixes the same agent composition to the full-screen terminal front door. +The repl-agent wiring: DeepSeek V4 + the `read`/`write`/`edit` filesystem tools + the bash tool suite + subagent delegation + `todo_write` + readline chat + JSONL persistence, loaded from `cordis.yml`. The sibling [`tui-agent`](../tui-agent/README.md) fixes the same agent composition to the full-screen terminal front door. ## Run it diff --git a/examples/coding-agent/code-mode.cordis.yml b/examples/repl-agent/code-mode.cordis.yml similarity index 93% rename from examples/coding-agent/code-mode.cordis.yml rename to examples/repl-agent/code-mode.cordis.yml index b1f62829bc..8802b510ba 100644 --- a/examples/coding-agent/code-mode.cordis.yml +++ b/examples/repl-agent/code-mode.cordis.yml @@ -23,7 +23,7 @@ ui: mode: readline persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. + You are a coding agent powered by the {{model}} model. You work by writing TypeScript programs for run_code: batch related tool work into one program, loop and branch where it helps, and print diff --git a/examples/repl-agent/composition.md b/examples/repl-agent/composition.md new file mode 100644 index 0000000000..af3f810585 --- /dev/null +++ b/examples/repl-agent/composition.md @@ -0,0 +1,88 @@ + + +# REPL Agent App Composition + +The REPL agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package. + +```mermaid +flowchart LR + cfg["examples/repl-agent
cordis.yml"] + plugin_repl_hmr["hmr
@cordisjs/plugin-hmr"] + cfg --> plugin_repl_hmr + plugin_repl_llm_deepseek["llm-deepseek
@deepseek-ai/dsh-llm-deepseek"] + cfg --> plugin_repl_llm_deepseek + plugin_repl_bash["bash
@deepseek-ai/dsh-bash-local"] + cfg --> plugin_repl_bash + plugin_repl_stdio_agent["stdio-agent
@deepseek-ai/dsh-stdio-demo"] + cfg --> plugin_repl_stdio_agent + plugin_repl_stdio_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] + plugin_repl_stdio_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] + plugin_repl_stdio_agent --> frontdoor_stdio["@deepseek-ai/dsh-stdio
pre-created main agent"] + bundle_agent_core --> spine_llm["ctx.llm"] + bundle_agent_core --> spine_sessions["ctx.sessions"] + bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] + bundle_agent_core --> spine_loop["ctx.agents + ctx.agentLoop"] + plugin_repl_token_meter["token-meter
@deepseek-ai/dsh-token-meter"] + cfg --> plugin_repl_token_meter + plugin_repl_compact_basic["compact-basic
@deepseek-ai/dsh-compact-basic"] + cfg --> plugin_repl_compact_basic + plugin_repl_subagent["subagent
@deepseek-ai/dsh-subagent"] + cfg --> plugin_repl_subagent + plugin_repl_subagent_spawn["subagent-spawn
@deepseek-ai/dsh-subagent-spawn"] + cfg --> plugin_repl_subagent_spawn + plugin_repl_subagent_fork["subagent-fork
@deepseek-ai/dsh-subagent-fork"] + cfg --> plugin_repl_subagent_fork + plugin_repl_tool_subagent["tool-subagent
@deepseek-ai/dsh-tool-subagent"] + cfg --> plugin_repl_tool_subagent + plugin_repl_tool_subagent_fork["tool-subagent-fork
@deepseek-ai/dsh-tool-subagent"] + cfg --> plugin_repl_tool_subagent_fork + plugin_repl_workflow_workerthread["workflow-workerthread
@deepseek-ai/dsh-workflow-workerthread"] + cfg --> plugin_repl_workflow_workerthread + plugin_repl_tool_workflow["tool-workflow
@deepseek-ai/dsh-tool-workflow"] + cfg --> plugin_repl_tool_workflow + plugin_repl_tool_todo["tool-todo
@deepseek-ai/dsh-tool-todo"] + cfg --> plugin_repl_tool_todo + plugin_repl_fs_local["fs-local
@deepseek-ai/dsh-fs-local"] + cfg --> plugin_repl_fs_local + plugin_repl_fs_policy["fs-policy
@deepseek-ai/dsh-fs-policy"] + cfg --> plugin_repl_fs_policy + plugin_repl_tool_fs["tool-fs
@deepseek-ai/dsh-tool-fs"] + cfg --> plugin_repl_tool_fs + plugin_repl_tool_fs_search["tool-fs-search
@deepseek-ai/dsh-tool-fs-search"] + cfg --> plugin_repl_tool_fs_search + plugin_repl_timeout_policy["timeout-policy
@deepseek-ai/dsh-timeout-policy"] + cfg --> plugin_repl_timeout_policy + plugin_repl_spill_local["spill-local
@deepseek-ai/dsh-spill-local"] + cfg --> plugin_repl_spill_local + plugin_repl_spill_policy["spill-policy
@deepseek-ai/dsh-spill-policy"] + cfg --> plugin_repl_spill_policy +``` + +| Plugin id | Package / module | +| --- | --- | +| `hmr` | `@cordisjs/plugin-hmr` | +| `llm-deepseek` | `@deepseek-ai/dsh-llm-deepseek` | +| `bash` | `@deepseek-ai/dsh-bash-local` | +| `stdio-agent` | `@deepseek-ai/dsh-stdio-demo` | +| `token-meter` | `@deepseek-ai/dsh-token-meter` | +| `compact-basic` | `@deepseek-ai/dsh-compact-basic` | +| `subagent` | `@deepseek-ai/dsh-subagent` | +| `subagent-spawn` | `@deepseek-ai/dsh-subagent-spawn` | +| `subagent-fork` | `@deepseek-ai/dsh-subagent-fork` | +| `tool-subagent` | `@deepseek-ai/dsh-tool-subagent` | +| `tool-subagent-fork` | `@deepseek-ai/dsh-tool-subagent` | +| `workflow-workerthread` | `@deepseek-ai/dsh-workflow-workerthread` | +| `tool-workflow` | `@deepseek-ai/dsh-tool-workflow` | +| `tool-todo` | `@deepseek-ai/dsh-tool-todo` | +| `fs-local` | `@deepseek-ai/dsh-fs-local` | +| `fs-policy` | `@deepseek-ai/dsh-fs-policy` | +| `tool-fs` | `@deepseek-ai/dsh-tool-fs` | +| `tool-fs-search` | `@deepseek-ai/dsh-tool-fs-search` | +| `timeout-policy` | `@deepseek-ai/dsh-timeout-policy` | +| `spill-local` | `@deepseek-ai/dsh-spill-local` | +| `spill-policy` | `@deepseek-ai/dsh-spill-policy` | + +Source config: [`examples/repl-agent/cordis.yml`](cordis.yml). + +Maintenance mode: hybrid: the leaf plugin list is parsed from its `cordis.yml`; app package expansion is curated from package source. diff --git a/examples/coding-agent/cordis.yml b/examples/repl-agent/cordis.yml similarity index 98% rename from examples/coding-agent/cordis.yml rename to examples/repl-agent/cordis.yml index 497e2a80c8..00a6b4b9a6 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/repl-agent/cordis.yml @@ -42,7 +42,7 @@ # Keep the persona to identity and behavior; tool plugins own tool guidance. # The loop resolves {{model}} from this agent's configuration. persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. + You are a coding agent powered by the {{model}} model. Verify your work by running the code or tests. Keep answers brief and factual. diff --git a/examples/coding-agent/package.json b/examples/repl-agent/package.json similarity index 81% rename from examples/coding-agent/package.json rename to examples/repl-agent/package.json index b3594ff597..34c7db6918 100644 --- a/examples/coding-agent/package.json +++ b/examples/repl-agent/package.json @@ -1,5 +1,5 @@ { - "name": "coding-agent-example", + "name": "repl-agent-example", "private": true, "version": "0.0.1", "type": "module", diff --git a/examples/coding-agent/tests/code-mode-keyless-smoke.e2e.ts b/examples/repl-agent/tests/code-mode-keyless-smoke.e2e.ts similarity index 100% rename from examples/coding-agent/tests/code-mode-keyless-smoke.e2e.ts rename to examples/repl-agent/tests/code-mode-keyless-smoke.e2e.ts diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/repl-agent/tests/code-mode.e2e.ts similarity index 98% rename from examples/coding-agent/tests/code-mode.e2e.ts rename to examples/repl-agent/tests/code-mode.e2e.ts index aab4da376f..c7f5d48562 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/repl-agent/tests/code-mode.e2e.ts @@ -25,7 +25,7 @@ import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context' * each `tool/code-dispatch`. The keyless Loader smoke is in the sibling test. */ -const PERSONA = 'You are coding-agent. You work by writing TypeScript programs for run_code: ' +const PERSONA = 'You are a coding agent. You work by writing TypeScript programs for run_code: ' + 'batch related tool work into one program and print or return ONLY the findings that matter.' const WORKSPACE_PROBE = 'dragonfruit-8675309' diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/repl-agent/tests/coding-task.e2e.ts similarity index 100% rename from examples/coding-agent/tests/coding-task.e2e.ts rename to examples/repl-agent/tests/coding-task.e2e.ts diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/repl-agent/tests/compaction.e2e.ts similarity index 100% rename from examples/coding-agent/tests/compaction.e2e.ts rename to examples/repl-agent/tests/compaction.e2e.ts diff --git a/examples/coding-agent/tests/full-loop.e2e.ts b/examples/repl-agent/tests/full-loop.e2e.ts similarity index 100% rename from examples/coding-agent/tests/full-loop.e2e.ts rename to examples/repl-agent/tests/full-loop.e2e.ts diff --git a/examples/coding-agent/tests/harness.ts b/examples/repl-agent/tests/harness.ts similarity index 98% rename from examples/coding-agent/tests/harness.ts rename to examples/repl-agent/tests/harness.ts index 290ffcdf0b..eeba57fc61 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/repl-agent/tests/harness.ts @@ -14,7 +14,7 @@ import { BasicCompactService } from '@deepseek-ai/dsh-compact-basic' import type { BasicCompactConfig } from '@deepseek-ai/dsh-compact-basic' /** - * Shared harness for the coding-agent e2e suites: the full plugin stack + * Shared harness for the repl-agent e2e suites: the full plugin stack * with the real DeepSeek adapter and the real bash + todo_write tools. Lives * outside the *.e2e.ts pattern so importing it never re-registers another * file's tests. diff --git a/examples/coding-agent/tests/keyless-smoke.e2e.ts b/examples/repl-agent/tests/keyless-smoke.e2e.ts similarity index 81% rename from examples/coding-agent/tests/keyless-smoke.e2e.ts rename to examples/repl-agent/tests/keyless-smoke.e2e.ts index 831d0daf5c..62eb43f55a 100644 --- a/examples/coding-agent/tests/keyless-smoke.e2e.ts +++ b/examples/repl-agent/tests/keyless-smoke.e2e.ts @@ -3,7 +3,7 @@ import { describe, expect, it } from 'vitest' import { LOADER_SMOKE_TEST_TIMEOUT_MS, runLoaderSmoke } from '@deepseek-ai/dsh-loader-smoke' /** - * Keyless Loader-path smoke for examples/coding-agent: boot the real example + * Keyless Loader-path smoke for examples/repl-agent: boot the real example * through the stdio-agent bin and its `cordis.yml`, then close stdin without a * prompt and assert the banner. The dummy key satisfies adapter construction; * immediate EOF guarantees there is no model call. @@ -13,11 +13,11 @@ const binScript = fileURLToPath(new URL('../../../packages/examples/stdio-demo/s const configPath = fileURLToPath(new URL('../cordis.yml', import.meta.url)) const tsconfigPath = fileURLToPath(new URL('../../../tsconfig.json', import.meta.url)) -describe('coding-agent keyless smoke (real cordis.yml via the Loader)', () => { +describe('repl-agent keyless smoke (real cordis.yml via the Loader)', () => { it('boots the full plugin tree, prints its banner, and exits cleanly on EOF', async () => { const { stdout } = await runLoaderSmoke({ - label: 'coding-agent', - tempDirPrefix: 'coding-smoke-', + label: 'repl-agent', + tempDirPrefix: 'repl-smoke-', binScript, configPath, tsconfigPath, diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/repl-agent/tests/resume.e2e.ts similarity index 100% rename from examples/coding-agent/tests/resume.e2e.ts rename to examples/repl-agent/tests/resume.e2e.ts diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/repl-agent/tests/todo-write.e2e.ts similarity index 100% rename from examples/coding-agent/tests/todo-write.e2e.ts rename to examples/repl-agent/tests/todo-write.e2e.ts diff --git a/examples/tui-agent/README.md b/examples/tui-agent/README.md index ee5b610d53..b4074881fb 100644 --- a/examples/tui-agent/README.md +++ b/examples/tui-agent/README.md @@ -1,6 +1,6 @@ # tui-agent -The full-screen terminal counterpart to the [`coding-agent`](../coding-agent/README.md) readline REPL and [`acp-agent`](../acp-agent/README.md) server. It reuses the coding agent's backends and tool composition, then fixes the shared terminal app to the `dsh-tui` front door. +The full-screen terminal counterpart to the [`repl-agent`](../repl-agent/README.md) readline REPL and [`acp-agent`](../acp-agent/README.md) server. It reuses the coding agent's backends and tool composition, then fixes the shared terminal app to the `dsh-tui` front door. ## Run it @@ -16,7 +16,7 @@ Run `pnpm run demo:code-mode tui` for the sibling Code Mode overlay. ## Composition -[`cordis.yml`](cordis.yml) includes the readline coding-agent leaf so the LLM, bash, filesystem, compaction, subagent, workflow, todo, timeout, and spill choices have one owner. Its asserted patch replaces only the terminal app config and forces `ui.mode: tui`; [`code-mode.cordis.yml`](code-mode.cordis.yml) applies the same front-door patch to the coding agent's Code Mode overlay. +[`cordis.yml`](cordis.yml) includes the readline repl-agent leaf so the LLM, bash, filesystem, compaction, subagent, workflow, todo, timeout, and spill choices have one owner. Its asserted patch replaces only the terminal app config and forces `ui.mode: tui`; [`code-mode.cordis.yml`](code-mode.cordis.yml) applies the same front-door patch to the repl-agent Code Mode overlay. ## Snapshot tests diff --git a/examples/tui-agent/code-mode.cordis.yml b/examples/tui-agent/code-mode.cordis.yml index 7bb7932ba0..75d2cea38a 100644 --- a/examples/tui-agent/code-mode.cordis.yml +++ b/examples/tui-agent/code-mode.cordis.yml @@ -1,9 +1,9 @@ -# Code Mode keeps the TUI front door while reusing the coding-agent overlay's +# Code Mode keeps the TUI front door while reusing the repl-agent overlay's # worker runtime and one-tool registry composition. - id: base name: '@cordisjs/plugin-include' config: - path: ../coding-agent/code-mode.cordis.yml + path: ../repl-agent/code-mode.cordis.yml patches: - id: stdio-agent name: '@deepseek-ai/dsh-stdio-demo' @@ -23,7 +23,7 @@ showReasoning: true maxToolOutputLines: 12 persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. + You are a coding agent powered by the {{model}} model. You work by writing TypeScript programs for run_code: batch related tool work into one program, loop and branch where it helps, and print diff --git a/examples/tui-agent/composition.md b/examples/tui-agent/composition.md index 511f76d41e..94515c32c4 100644 --- a/examples/tui-agent/composition.md +++ b/examples/tui-agent/composition.md @@ -3,7 +3,7 @@ # TUI Agent App Composition -The TUI agent reuses the coding-agent backend and tool composition while fixing the shared terminal app to the full-screen dsh-tui front door. +The TUI agent reuses the repl-agent backend and tool composition while fixing the shared terminal app to the full-screen dsh-tui front door. ```mermaid flowchart LR diff --git a/examples/tui-agent/cordis.yml b/examples/tui-agent/cordis.yml index 0f329c38e2..515274b2a8 100644 --- a/examples/tui-agent/cordis.yml +++ b/examples/tui-agent/cordis.yml @@ -1,10 +1,10 @@ -# Full-screen TUI front door over the same coding-agent composition used by the +# Full-screen TUI front door over the same repl-agent composition used by the # readline REPL. The include keeps backends and optional tools aligned; the # patch owns only the terminal-specific app config. - id: base name: '@cordisjs/plugin-include' config: - path: ../coding-agent/cordis.yml + path: ../repl-agent/cordis.yml patches: - id: stdio-agent name: '@deepseek-ai/dsh-stdio-demo' @@ -22,7 +22,7 @@ showReasoning: true maxToolOutputLines: 12 persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. + You are a coding agent powered by the {{model}} model. Verify your work by running the code or tests. Keep answers brief and factual. diff --git a/package.json b/package.json index ca85fd32d2..19f6d15005 100644 --- a/package.json +++ b/package.json @@ -79,7 +79,7 @@ "doc-sync": "pnpm run doc-typecheck && pnpm run verify-cordis-catalog && pnpm run verify-cordis-api && pnpm run verify-export-jsdoc && pnpm run verify-tool-catalog && pnpm run verify-config-catalog && pnpm run verify-persistence-catalog && pnpm run verify-doc-graphs && pnpm run verify-scoped-events && pnpm run verify-website-api && pnpm run verify-md-wrap && pnpm run verify-md-links && pnpm run verify-doc-refs && pnpm run verify-package-paths && pnpm run verify-package-readme-model-experience && pnpm run verify-mermaid && pnpm run verify-rfc-classification && pnpm run verify-rfc-format && pnpm run verify-type-equiv && pnpm run verify-translation-prompt && pnpm run verify-translation-pairing && pnpm run verify-doc-budgets && pnpm run verify-package-readme-limitations && pnpm run verify-website-yaml", "hygiene": "pnpm run knip && pnpm run publint && pnpm run constraints && pnpm run verify-cordis-config && pnpm run verify-node-next-types && pnpm run verify-runtime-closure", "demo:echo": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/echo-agent/cordis.yml", - "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/coding-agent/cordis.yml", + "demo:repl": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/repl-agent/cordis.yml", "demo:tui": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/tui-agent/cordis.yml", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node --expose-internals --import tsx packages/examples/stdio-demo/src/bin.ts examples/cordis-agent/cordis.yml", diff --git a/packages/examples/stdio-demo/src/bin.ts b/packages/examples/stdio-demo/src/bin.ts index 278bb5faca..3d8a0c2a33 100644 --- a/packages/examples/stdio-demo/src/bin.ts +++ b/packages/examples/stdio-demo/src/bin.ts @@ -2,7 +2,7 @@ /** * Boot a stdio app from a leaf `cordis.yml`; usage is `dsh-stdio-demo [config]`, defaulting to the * cwd file. Shared `.env` loading, fail-loud Loader guards, and settled-tree boot live in - * dsh-app-boot. The echo and coding-agent demos invoke this bin with their own leaf configs. + * dsh-app-boot. The echo-agent and repl-agent demos invoke this bin with their own leaf configs. * @module @deepseek-ai/dsh-stdio-demo/bin */ diff --git a/packages/examples/stdio-demo/src/index.ts b/packages/examples/stdio-demo/src/index.ts index 69a0be1171..531c4a3d5e 100644 --- a/packages/examples/stdio-demo/src/index.ts +++ b/packages/examples/stdio-demo/src/index.ts @@ -174,7 +174,7 @@ export function composeTerminalApp(ctx: Context, config: Config, isTTY: boolean) /** Compose the configured terminal front door with the agent app. */ /* v8 ignore start -- production stream capability wiring; composeTerminalApp is unit-covered, - and the coding-agent PTY smoke covers the interactive process path */ + and the repl-agent PTY smoke covers the interactive process path */ export function apply(ctx: Context, config: Config): void { composeTerminalApp(ctx, config, process.stdin.isTTY && process.stdout.isTTY) } diff --git a/packages/ui/tui/src/index.ts b/packages/ui/tui/src/index.ts index 0906b7bc9f..1c3fc1315c 100644 --- a/packages/ui/tui/src/index.ts +++ b/packages/ui/tui/src/index.ts @@ -1342,7 +1342,7 @@ export function mountTui(ctx: Context, config: Config, runtime: TuiRuntime): voi /** Cordis entry point using the process terminal; explicit TUI composition requires a TTY pair. */ /* v8 ignore start -- production process wiring; fake-terminal tests cover mountTui/createTuiChat, - and the coding-agent PTY smoke covers the real entry */ + and the repl-agent PTY smoke covers the real entry */ export function apply(ctx: Context, config: Config): void { if (!process.stdin.isTTY || !process.stdout.isTTY) { throw new Error('ui-tui: both stdin and stdout must be TTYs; use @deepseek-ai/dsh-stdio for pipes') diff --git a/scripts/demo-code-mode.mjs b/scripts/demo-code-mode.mjs index 7a5e054cc0..43bff2d4ba 100644 --- a/scripts/demo-code-mode.mjs +++ b/scripts/demo-code-mode.mjs @@ -9,7 +9,7 @@ import { spawn } from 'node:child_process' // the overlay config (the stdio bin keeps --expose-internals for the cordis // Loader's HMR path). const UIS = new Map([ - ['repl', ['--expose-internals', '--import', 'tsx', 'packages/examples/stdio-demo/src/bin.ts', 'examples/coding-agent/code-mode.cordis.yml']], + ['repl', ['--expose-internals', '--import', 'tsx', 'packages/examples/stdio-demo/src/bin.ts', 'examples/repl-agent/code-mode.cordis.yml']], ['tui', ['--expose-internals', '--import', 'tsx', 'packages/examples/stdio-demo/src/bin.ts', 'examples/tui-agent/code-mode.cordis.yml']], ['acp', ['--import', 'tsx', 'packages/examples/acp-demo/src/bin.ts', '--config', 'examples/acp-agent/code-mode.cordis.yml']], ]) diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 7164e65a5c..7c698c0cb9 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -427,12 +427,12 @@ const APP_EXAMPLES = [ summary: 'The echo demo swaps in a local mock LLM and teaching echo tool, then loads the stdio app package for the shared spine and terminal front door.', }, { - id: 'coding', - rel: 'examples/coding-agent/composition.md', - title: 'Coding Agent App Composition', - label: 'examples/coding-agent', - config: 'examples/coding-agent/cordis.yml', - summary: 'The coding-agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', + id: 'repl', + rel: 'examples/repl-agent/composition.md', + title: 'REPL Agent App Composition', + label: 'examples/repl-agent', + config: 'examples/repl-agent/cordis.yml', + summary: 'The REPL agent demo adds the real DeepSeek adapter, filesystem tools, todo_write, compaction, and both subagent transports on top of the stdio app package.', }, { id: 'tui', @@ -440,7 +440,7 @@ const APP_EXAMPLES = [ title: 'TUI Agent App Composition', label: 'examples/tui-agent', config: 'examples/tui-agent/cordis.yml', - summary: 'The TUI agent reuses the coding-agent backend and tool composition while fixing the shared terminal app to the full-screen dsh-tui front door.', + summary: 'The TUI agent reuses the repl-agent backend and tool composition while fixing the shared terminal app to the full-screen dsh-tui front door.', }, { id: 'cordis', @@ -470,7 +470,7 @@ function renderAppExpansion(lines: string[], appNode: string, pluginName: string if (pluginName === '@deepseek-ai/dsh-stdio-demo') { const frontDoor = exampleId === 'tui' ? '@deepseek-ai/dsh-tui
pre-created main agent' - : exampleId === 'coding' + : exampleId === 'repl' ? '@deepseek-ai/dsh-stdio
pre-created main agent' : 'dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent' lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["${frontDoor}"]`) @@ -990,7 +990,7 @@ function renderIndex(docs: GraphDoc[]): string { const labels: Record = { 'docs/capability-seams.md': 'capability seams and core services', 'examples/echo-agent/composition.md': 'echo-agent app composition', - 'examples/coding-agent/composition.md': 'coding-agent app composition', + 'examples/repl-agent/composition.md': 'repl-agent app composition', 'examples/tui-agent/composition.md': 'tui-agent app composition', 'examples/cordis-agent/composition.md': 'cordis-agent app composition', 'examples/acp-agent/composition.md': 'acp-agent app composition', @@ -1002,7 +1002,7 @@ function renderIndex(docs: GraphDoc[]): string { const modes: Record = { 'docs/capability-seams.md': 'hybrid generated', 'examples/echo-agent/composition.md': 'hybrid generated', - 'examples/coding-agent/composition.md': 'hybrid generated', + 'examples/repl-agent/composition.md': 'hybrid generated', 'examples/tui-agent/composition.md': 'hybrid generated', 'examples/cordis-agent/composition.md': 'hybrid generated', 'examples/acp-agent/composition.md': 'hybrid generated', diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index ca69768227..8606d30895 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -206,7 +206,7 @@ const TOOL_PACKAGES: ToolPackage[] = [ await ctx.plugin(ToolSubagent, { provider: 'mock' }) }, note: - 'The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/coding-agent/cordis.yml` and `examples/acp-agent/cordis.yml`.', + 'The registered tool name is the load-time `toolName` config (default `subagent`); the schema above is that default. The shipped example agents load this package once per subagent backend, so the model additionally sees `subagent_fork` (bound to the fork backend) with an identical schema — see `examples/repl-agent/cordis.yml` and `examples/acp-agent/cordis.yml`.', }, { pkg: '@deepseek-ai/dsh-tool-tasks', diff --git a/website/zh-CN/guide/config.md b/website/zh-CN/guide/config.md index 07943288b8..35fb42185b 100644 --- a/website/zh-CN/guide/config.md +++ b/website/zh-CN/guide/config.md @@ -39,7 +39,7 @@ Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参 persistenceRoot: './.sessions' ``` -### coding-agent 的配置 +### repl-agent 的配置 真实场景——接入 DeepSeek API，带完整工具链： @@ -81,7 +81,7 @@ Harness 使用 `cordis.yml` 描述一个 Agent 加载哪些插件、以什么参 persistenceRoot: './.sessions' welcome: 'agent REPL ready. Give it a coding task.' persona: | - You are coding-agent, a coding assistant powered by the {{model}} model. + You are a coding agent powered by the {{model}} model. Verify your work by running the code or tests. Keep answers brief and factual. # Token 计量：统一定义模型能看到的 token 上限 diff --git a/website/zh-CN/guide/quickstart.md b/website/zh-CN/guide/quickstart.md index 76ff1fd3fe..27725fc6b9 100644 --- a/website/zh-CN/guide/quickstart.md +++ b/website/zh-CN/guide/quickstart.md @@ -69,7 +69,7 @@ echo-agent ready. Type a message ("echo " triggers the tool). DEEPSEEK_API_KEY=sk-your-key-here ``` -### 启动 coding-agent +### 启动 repl-agent ```sh pnpm run demo:repl @@ -90,7 +90,7 @@ agent REPL ready. Give it a coding task. ## 回头看 -echo-agent 和 coding-agent 用的是同一个应用框架(`@deepseek-ai/dsh-stdio-demo`)，区别只在 `cordis.yml`——换了哪些插件、填了什么配置。你以后定制自己的 Agent 也是同样的方式。 +echo-agent 和 repl-agent 用的是同一个应用框架(`@deepseek-ai/dsh-stdio-demo`)，区别只在 `cordis.yml`——换了哪些插件、填了什么配置。你以后定制自己的 Agent 也是同样的方式。 ## 下一步 From 40ad78ee0bdcddea49acd4adabe92da94c0e0280 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:13:36 +0800 Subject: [PATCH 222/323] docs: condense merged architecture contract --- docs/architecture.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 32df16a3cd..193dbf56bf 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -83,7 +83,7 @@ forever: snapshot the derived messages (the reconstruction boundary) 'step/start' agent/request (config only) -> log request/header -> llm/stream (frozen) - on final adapter failure or terminal in-band error/aborted finish: + on final adapter-path or terminal in-band failure: 'step/end' agent/request-error(original error, consecutive retry attempt, signal) retry in the next numbered step or preserve the original error @@ -108,15 +108,15 @@ forever: Each step assembles ordered prompt sections, tool schemas, and `{{name}}` variables; unknown or valueless references fail the turn. `dsh-system-prompt` owns the harness identity and default persona, which an agent scope may shadow. The loop supplies `model` and `cwd` ([prompt-ownership RFC](rfc/implemented/architecture/2026-07-05-prompt-variables-and-tool-guidance-ownership.md)). -Context accepted during tool execution—including async `agent.inject()` notices and post-tool `additionalContexts`—waits for settlement, then follows every recorded result. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering while the step signal remains open. Ordinary leftover steering becomes queued input. Terminal `agent/turn-stop` runs after continuation and steering folding, stays authoritative through turn close and flush, and discards later steering while preserving queued prompts. +Context accepted during tool execution—including async `agent.inject()` notices and post-tool `additionalContexts`—waits for settlement, then follows every recorded result. Steering drains before `agent/post-step`, which observes durable output, results, context, and steering before signal closure. Leftover steering becomes queued input. Terminal `agent/turn-stop` runs after continuation and steering folding, stays authoritative through turn close and flush, and discards later steering while preserving queued prompts. -`dsh-compact-basic` uses those checkpoints for routed-envelope pressure and canonical-overflow recovery; only a tool-balanced surface replacement authorizes retry ([RFC](rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)). +`dsh-compact-basic` handles pressure and canonical overflow at these checkpoints; retry requires a balanced surface replacement ([RFC](rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md)). ### Failure Boundaries -The turn is the containment boundary. Final adapter selection, dispatch, iteration, and terminal in-band failures close the step before `agent/request-error`; retry reconstructs a new numbered step, while the default preserves the provider error. Attempts reset after success. +The turn is the containment boundary. Final adapter-path and terminal in-band failures close the step before `agent/request-error`; retry starts a new numbered step, while the default preserves the provider error. Attempts reset on success. -Other plugin and step failures use `agent/error`. Cancellation and disposal beat recovery; undispatched model tool calls receive synthetic `tool/call` and `ABORTED` result pairs before turn closure. `cancel()` clears queues and aborts active work; disposal awaits quiescence before unregistering. +Other failures use `agent/error`. Cancellation and disposal beat recovery; undispatched model tool calls receive synthetic `tool/call` and `ABORTED` result pairs before turn closure. `cancel()` clears queues and aborts active work; disposal awaits quiescence before unregistering. Every session event is turn-enclosed. Reloading preserves an interrupted tail and closes it with a synthetic `interrupted` turn end. Failures after durable turn close report only through `agent/error` because no safe in-turn position remains. Each turn has one `TurnEndReason`; [TurnEndReasonMap](core-data-structures/session.md#why-a-turn-ended-turnendreasonmap) owns the variants. From 89987f0ad4615ef4b4f8db3854dc30c542dbe614 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:25:30 +0800 Subject: [PATCH 223/323] docs: align one-shot demo prose --- AGENTS.md | 4 +-- docs/config-catalog.md | 6 ++--- docs/testing.md | 2 +- examples/README.md | 2 +- examples/coding-agent/README.md | 9 +------ examples/headless-agent/README.md | 2 +- examples/headless-agent/composition.md | 4 +-- examples/headless-agent/cordis.yml | 1 - packages/examples/cli-demo/README.md | 16 ++++++------ packages/examples/cli-demo/src/cli.ts | 25 ++++++++----------- packages/examples/cli-demo/src/index.ts | 10 ++++---- .../session-persistence-jsonl/src/index.ts | 2 +- packages/support/llm-replay/README.md | 2 +- packages/support/loader-smoke/src/index.ts | 2 -- scripts/gen-doc-graphs.ts | 4 +-- 15 files changed, 38 insertions(+), 53 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index bb4d1973ce..efaa29bbac 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -28,7 +28,7 @@ packages/ @deepseek-ai/dsh- workspaces at packages/// hooks/ Claude Code / Codex hook bridges + shared wire-protocol library session-persistence/ persistence seam + JSONL/SQLite backends ui/ ACP/stdio/TUI/JSON-RPC bridges; boot, approval, interaction plugins - examples/ demo bundles (agent-spine + stdio/ACP/JSON-RPC bins) leaves load + examples/ demo bundles (agent-spine + stdio/CLI/ACP/JSON-RPC bins) leaves load support/ dev/test infrastructure packages util/ zero-dependency utilities python/ Python SDK and bundled runtime (see python/README.md) @@ -47,7 +47,7 @@ pnpm install # pnpm workspaces, node ^22.19 || >=24 pnpm run test # vitest unit tests pnpm run test:coverage # THE gating test run: per-file 100% coverage on packages/*/*/src pnpm run test:e2e # real-API tests; self-skip without DEEPSEEK_API_KEY -pnpm run test:snapshot # keyless ACP/headless replay vs goldens; filter: -t +pnpm run test:snapshot # keyless ACP/headless/TUI replay vs goldens; filter: -t pnpm run test:snapshot:record # re-record goldens (needs key) pnpm run typecheck pnpm run lint diff --git a/docs/config-catalog.md b/docs/config-catalog.md index bd68554d6a..adbd0eaf4a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -209,11 +209,11 @@ Source: [`packages/bash/bash-sandbox/src/index.ts:27`](../packages/bash/bash-san ## `@deepseek-ai/dsh-cli-demo` ```ts config-catalog -/** App config forwarded to the spine, pre-created agent, and JSONL backend. */ +/** App config forwarded to the spine, configured agent, and JSONL backend. */ export interface Config { - /** Provider route for the `main` agent. */ + /** Provider route for the configured agent. */ provider: string - /** Model name for the `main` agent; a matching adapter must be registered. */ + /** Model name for the configured agent; a matching adapter must be registered. */ model: string /** Deployment persona forwarded to the system-prompt plugin. */ persona?: string diff --git a/docs/testing.md b/docs/testing.md index 2fb0e5b2c1..cd3b1aa9e8 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -7,7 +7,7 @@ How this repo tests, tier by tier, and the rules that keep a green suite meaning - **Unit** (`pnpm run test`): vitest over `packages|examples/*/tests/**/*.spec.ts`, colocated with what they test. Every registry gets an HMR-safety test (dispose the contributing fiber, assert cleanup). Prefer edge cases, error paths, event ordering, concurrency races, and permanent contract regressions (see `packages/core/agent-loop/tests/contract-regressions.spec.ts`). - **Coverage gate** (`pnpm run test:coverage`): the gating run, per-file 100% on `packages/*/*/src`. An uncovered line is often dead code the gate is correctly flagging for deletion, not a missing test to bolt on. Line coverage is necessary, never sufficient — it proves lines ran, not that the feature works as shipped. - **Real-API e2e** (`pnpm run test:e2e`): with-key tests against live provider APIs — the DeepSeek model plus provider-specific smokes that gate on their own keys (`EXA_API_KEY`, `PERPLEXITY_API_KEY`, …); each suite self-skips without its key so keyless CI stays green ([real-API e2e RFC](rfc/implemented/testing/2026-06-19-real-api-e2e-ci.md)). -- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless goldens cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized stdout plus the re-persisted log ([ACP snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)); `examples/headless-agent` independently pins its `stream-json` event surface through the real one-shot subprocess. TUI completed journeys replay recorded primary/child JSONL through the real agent loop and tools before projecting ANSI into semantic terminal-state goldens; package-local snapshots retain transient renderer states, and a real PTY conversation covers the process boundary ([TUI snapshot RFC](rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when committed replay input remains correct; review every JSONL and golden diff. System-prompt/tool-schema content is pinned by ONE ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). +- **Snapshot** (`pnpm run test:snapshot`): transport-specific keyless goldens cover external presentation. ACP suites boot the real example subprocess, replay a recorded session, and diff normalized JSON-RPC plus the re-persisted log ([ACP snapshot RFC](rfc/implemented/testing/2026-06-19-acp-snapshot-tests.md)); the headless suite independently pins `stream-json` through its real one-shot subprocess. TUI completed journeys replay recorded primary/child JSONL through the real agent loop and tools before projecting ANSI into semantic terminal-state goldens; package-local snapshots retain transient renderer states, and a real PTY conversation covers the process boundary ([TUI snapshot RFC](rfc/implemented/testing/2026-07-18-tui-terminal-state-snapshots.md)). Use `pnpm run test:snapshot:record` when a model transcript must change and `pnpm run test:snapshot:refresh` when committed replay input remains correct; review every JSONL and golden diff. System-prompt/tool-schema content is pinned by one ACP scenario (`text-turn`) and tokenized in every other fixture, so a prompt or schema edit churns one committed line ([pinned-header RFC](rfc/implemented/testing/2026-07-06-pin-request-header-content-in-one-scenario.md)). ## The with-key policy: inference is cheap here diff --git a/examples/README.md b/examples/README.md index 7badb5599e..ef3abfdd85 100644 --- a/examples/README.md +++ b/examples/README.md @@ -25,7 +25,7 @@ Run the Code Mode overlay with `pnpm run demo:code-mode`, or pass `acp` for the A non-interactive agent demo that accepts one positional task, runs one complete model/tool turn on the `@deepseek-ai/dsh-cli-demo` app, persists a fresh session, prints `text`, `json`, or `stream-json`, and exits. -Run with: `pnpm run demo:headless -- "task"` (needs `DEEPSEEK_API_KEY`). See [headless-agent/README.md](headless-agent/README.md) for the wire contract, mutation and token risks, and the headless-owned snapshot suite. +Run with: `pnpm run demo:headless -- "task"` (needs `DEEPSEEK_API_KEY`). See [headless-agent/README.md](headless-agent/README.md) for the output contract, safety boundaries, and snapshot suite. ## tui-agent diff --git a/examples/coding-agent/README.md b/examples/coding-agent/README.md index 470872dedf..986608b3af 100644 --- a/examples/coding-agent/README.md +++ b/examples/coding-agent/README.md @@ -13,14 +13,6 @@ pnpm run demo:repl Type a coding task. The agent works through the `read`/`write`/`edit` filesystem tools for ordinary file operations and `bash` (+ the generic `task_output` / `task_list` / `task_kill` for background tasks) for shell commands, searches, and test runs, each in a fresh `bash -c` (the system prompt tells the model to pass `workdir` instead of `cd`). Both the fs tools and bash resolve relative paths against the session workspace. It can also delegate with `subagent`/`subagent_fork` and track multi-step work with `todo_write`. -``` -> fix the failing test in /path/to/project -[main turn 1] (reasoning…) - [tool call] bash({"command": "node --test", "workdir": "/path/to/project"}) -[tool result] … [exit code: 1] - … -``` - The REPL renders reasoning, tool calls/results, and the latest todo list as line-oriented output suitable for terminals and pipes. Use `pnpm run demo:tui` for the interactive Markdown/card interface. ### Resuming a prior session @@ -60,6 +52,7 @@ This example is a thin leaf `cordis.yml`: it picks the swappable backends, loads | `stdio-agent` (`@deepseek-ai/dsh-stdio-demo`) | the app bundle: the agent-spine demo + JSONL persistence + the configured terminal channel + a pre-created `main` agent. This leaf fixes `ui.mode` to `readline`; `tui-agent` owns the corresponding TUI leaf | | `subagent`, `subagent-spawn`, `subagent-fork` | the subagent provider registry plus the two in-process backends: a fresh child and a child seeded with the parent's completed-turn prefix | | `tool-subagent`, `tool-subagent-fork` | two model-facing `dsh-tool-subagent` loads, each bound to a different provider and exposed under a distinct tool name (`subagent`, `subagent_fork`) | +| `workflow-workerthread`, `tool-workflow` | the worker-thread workflow engine and its model-facing `workflow` tool, with child calls routed through the spawn backend | | `tool-todo` | the model-facing `todo_write` tool; writes the whole task list to the session log and renders as a persistent TUI plan or readline checklist | | `fs-local`, `fs-policy`, `tool-fs` | the filesystem stack: the local `ctx.fs` provider, the read-before-write/edit policy gate (on the `fs/*` event gate), and the model-facing `read`/`write`/`edit` tools. Relative paths resolve against the session workspace | diff --git a/examples/headless-agent/README.md b/examples/headless-agent/README.md index 5c21855afe..285263146f 100644 --- a/examples/headless-agent/README.md +++ b/examples/headless-agent/README.md @@ -13,7 +13,7 @@ pnpm run demo:headless --output-format json -- "summarize the implementation" pnpm run demo:headless --output-format stream-json -- "run the focused tests" ``` -Exactly one nonblank positional task is required; quote tasks containing spaces. There is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the parent `main` session's canonical task-turn events before that record. Child sessions surface only through parent tool events and results. +Exactly one nonblank positional task is required; quote tasks containing spaces. There is no `-p` flag. `text` prints the last text-bearing assistant message, `json` prints one DSH-native result record, and `stream-json` emits the top-level session's canonical task-turn events before that record. Child sessions surface only through parent tool events and results. Each invocation creates and persists a fresh session, runs all model and tool steps in one turn, flushes, disposes, and exits. This is non-interactive automation: there is no prompt, approval, resume, second turn, or stdin context. The configured tools can mutate the launch workspace, run commands, spawn child agents, and consume provider tokens. diff --git a/examples/headless-agent/composition.md b/examples/headless-agent/composition.md index 9a734fa2f0..9533af28d3 100644 --- a/examples/headless-agent/composition.md +++ b/examples/headless-agent/composition.md @@ -3,7 +3,7 @@ # Headless Agent App Composition -The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted main session. +The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted top-level session. ```mermaid flowchart LR @@ -16,7 +16,7 @@ flowchart LR cfg --> plugin_headless_cli_agent plugin_headless_cli_agent --> bundle_agent_core["@deepseek-ai/dsh-agent-spine-demo"] plugin_headless_cli_agent --> bundle_jsonl["@deepseek-ai/dsh-session-persistence-jsonl"] - plugin_headless_cli_agent --> frontdoor_cli["one-shot driver
format-pure stdout
pre-created main agent"] + plugin_headless_cli_agent --> frontdoor_cli["one-shot driver
format-pure stdout
fresh top-level agent"] bundle_agent_core --> spine_llm["ctx.llm"] bundle_agent_core --> spine_sessions["ctx.sessions"] bundle_agent_core --> spine_tools["ctx.tools + tool-bash"] diff --git a/examples/headless-agent/cordis.yml b/examples/headless-agent/cordis.yml index 11136eeb86..b119ccf0de 100644 --- a/examples/headless-agent/cordis.yml +++ b/examples/headless-agent/cordis.yml @@ -13,7 +13,6 @@ - deepseek-v4-pro - deepseek-v4-flash -# Local executor for the app bundle's bash tool. - id: bash name: '@deepseek-ai/dsh-bash-local' config: diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md index bbe867487f..5197e3bcd0 100644 --- a/packages/examples/cli-demo/README.md +++ b/packages/examples/cli-demo/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-cli-demo -Headless one-shot app and bin for running one agent task without a readline or editor client. The app composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and one fresh `main` agent; the bin submits one task, waits through all model and tool steps, emits the selected result, disposes to quiescence, and exits. +Headless one-shot app and bin for running one agent task without a readline or editor client. It composes [`@deepseek-ai/dsh-agent-spine-demo`](../agent-spine-demo/README.md), JSONL persistence, and exactly one fresh top-level agent. The bin submits the task, waits for its durable turn ending, renders the selected output, disposes to quiescence, and exits. The package mounts no console logger, readline UI, user-interaction service, or `ask_user_question` tool. Stdout is reserved for the selected output format; diagnostics use stderr. @@ -8,8 +8,8 @@ The package mounts no console logger, readline UI, user-interaction service, or | Key | Default | Routed to | |---|---|---| -| `provider` | required | the pre-created `main` agent's provider route | -| `model` | required | the pre-created `main` agent's model | +| `provider` | required | the configured agent's provider route | +| `model` | required | the configured agent's model | | `persona` | — | the deployment persona in `dsh-system-prompt` | | `toolOrder` | lexicographic | explicit model-facing tool order in `dsh-system-prompt` | | `tools` | `{ mode: 'native' }` | tool-registry presentation config through `dsh-agent-spine-demo` | @@ -17,8 +17,6 @@ The package mounts no console logger, readline UI, user-interaction service, or | `persistenceRoot` | `./.sessions` | JSONL session root | | `workspaceContext` | required | workspace-instruction byte budget, or `false` to disable loading | -Each process creates a new session whose workspace cwd is the launch directory. The app has no resume setting. - ## CLI contract ```sh @@ -39,7 +37,7 @@ Loader configs with bare package specifiers require `node --expose-internals` or - `text` writes the last assistant message containing text, followed by one newline. - `json` writes one DSH-native result record: `{ type: "result", success, sessionId, turn, result, reason, usage? }`. `usage` sums every model step in the task turn. -- `stream-json` writes each canonical event from the `main` session's task turn as `{ type: "session_event", sessionId, event }`, then the same result record. Child-agent activity appears only through the parent tool events and results. +- `stream-json` writes each canonical event from the top-level session's task turn as `{ type: "session_event", sessionId, event }`, then the same result record. Child-agent activity appears only through the parent tool events and results. Only `reason.kind === "completed"` exits successfully. Other durable turn endings still emit partial text or a result record, add a stderr diagnostic, and exit nonzero. Argument and boot failures leave stdout empty. SIGINT and SIGTERM cancel active work, await disposal, and exit 130 and 143 respectively. @@ -53,12 +51,12 @@ The headless-agent leaf supplies local bash, filesystem, skill, subagent, workfl ### One-shot task turn -**What the model sees**: The positional task becomes one user message. Through `dsh-agent-spine-demo`, the `main` agent also receives configured workspace instructions and persona, the skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn. +**What the model sees**: The positional task becomes one user message. Through `dsh-agent-spine-demo`, the top-level agent also receives configured workspace instructions and persona, the skill catalog, visible tool schemas, and retained tool results needed for later steps in the same turn. **Token effect**: The task, prompt sections, tool schemas, assistant output, and tool results consume tokens on each model step. JSON event streaming and final rendering add no model tokens; delegated child work has its own model usage and is not included in the parent result's `usage` total. ## Known Limitations and Deferred Work -- **One fresh main session per process** — there is no resume, second prompt, stdin context, or concurrent top-level session in this app. +- **One fresh top-level session per process** — its workspace cwd is the launch directory; there is no resume, second prompt, stdin context, or concurrent top-level session in this app. - **No interactive question or approval provider** — tools that require a human answer cannot complete unless a different leaf composes a non-interactive provider with explicit policy. -- **Streaming is main-session-only** — child sessions are not flattened into the stream, and aggregate usage covers only model steps recorded on the parent task turn. +- **Streaming is top-level-session-only** — child sessions are not flattened into the stream, and aggregate usage covers only model steps recorded on the parent task turn. diff --git a/packages/examples/cli-demo/src/cli.ts b/packages/examples/cli-demo/src/cli.ts index 7b5a907e43..1f19e3ddf5 100644 --- a/packages/examples/cli-demo/src/cli.ts +++ b/packages/examples/cli-demo/src/cli.ts @@ -1,6 +1,6 @@ /** - * Covered command parser and one-turn driver for `dsh-cli-demo`. The executable - * entry only installs process signal handlers and delegates here. + * Command parser and one-turn driver for `dsh-cli-demo`. The executable wrapper + * owns process signals; this module owns output, durability, and cleanup. * @module @deepseek-ai/dsh-cli-demo/cli */ @@ -44,9 +44,9 @@ export interface CliResult { export interface OneShotOptions { /** Exactly one nonblank user task. */ readonly task: string - /** Optional cancellation signal owned by the process wrapper. */ + /** Optional signal that cancels the selected agent. */ readonly signal?: AbortSignal - /** Synchronous observer for each canonical event in the selected task turn. */ + /** Synchronous task-turn observer; a throw cancels the agent and fails the run after flush. */ readonly onEvent?: (sessionId: string, event: SessionEvent) => void } @@ -91,12 +91,10 @@ class CliInterruptedError extends Error { } } -/** Convert an unknown thrown value to an Error without losing its text. */ function toError(error: unknown): Error { return error instanceof Error ? error : new Error(String(error)) } -/** Render the reason carried by an AbortSignal. */ function interruptionReason(signal: AbortSignal): string { return signal.reason === undefined ? 'interrupted' : String(signal.reason) } @@ -145,7 +143,6 @@ export function parseCliArgs(args: readonly string[]): CliCommand { } } -/** Add one model step's usage into a detached turn total. */ function addUsage(total: TokenUsage | undefined, step: TokenUsage): TokenUsage { const next: TokenUsage = { inputTokens: (total?.inputTokens ?? 0) + step.inputTokens, @@ -157,7 +154,6 @@ function addUsage(total: TokenUsage | undefined, step: TokenUsage): TokenUsage { return next } -/** Select the text blocks from an assistant message, or undefined when it has none. */ function assistantText(event: Extract): string | undefined { const blocks = event.data.content.filter(block => block.type === 'text') return blocks.length === 0 ? undefined : blocks.map(block => block.text).join('') @@ -189,8 +185,11 @@ async function waitForStartupIdle(agent: Agent, signal?: AbortSignal): Promise = z.object({ }) /** - * Compose the UI-less spine, a fresh `main` agent rooted at the process cwd, + * Compose the UI-less spine, a fresh top-level agent rooted at the process cwd, * and JSONL persistence. Swappable adapters, executors, and product tools stay * in the leaf `cordis.yml`. * @param ctx - app context that owns the composed child plugins. diff --git a/packages/session-persistence/session-persistence-jsonl/src/index.ts b/packages/session-persistence/session-persistence-jsonl/src/index.ts index 40a054ceb0..4e52cb0b9e 100644 --- a/packages/session-persistence/session-persistence-jsonl/src/index.ts +++ b/packages/session-persistence/session-persistence-jsonl/src/index.ts @@ -57,7 +57,7 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi private root: string private coordinator: PersistenceCoordinator - /** Runtime-only host-platform seam for directory-sync compatibility tests. */ + /** Runtime host platform used to decide whether directory sync is supported. */ readonly internals: { platform: NodeJS.Platform } = { platform: process.platform } constructor(ctx: Context, public config: Config) { diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index bd738e4641..b256ef9a59 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -2,7 +2,7 @@ A replay LLM plugin for keyless snapshot tests. It yields model streams reconstructed from a recorded **session JSONL** fixture, so a test can boot the real agent against a fixed model transcript with no API key. With `providers` configured it registers a replay-only adapter whose catalog is visible to clients such as ACP editors; without `providers` it installs the catch-all `llm/stream` waterfall used by tests that do not need discovery. -Its consumers are the ACP snapshot harness in `examples/acp-agent` and the `stream-json` snapshot in `examples/headless-agent`; each loads this plugin in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate). +Its consumers are the ACP snapshot harness in `examples/acp-agent` and the `stream-json` snapshot in `examples/headless-agent`; each loads this plugin in place of a real LLM adapter. Keeping derivation and replay here places that logic under the per-file 100% coverage gate on `packages/*/src`. ## How the fixture works diff --git a/packages/support/loader-smoke/src/index.ts b/packages/support/loader-smoke/src/index.ts index ca3396542e..36ab137f32 100644 --- a/packages/support/loader-smoke/src/index.ts +++ b/packages/support/loader-smoke/src/index.ts @@ -7,8 +7,6 @@ * zero-build dev path, resolving `@deepseek-ai/dsh-*` / `@cordisjs/*` through the tsconfig `paths` * map) or from built `lib/` under plain Node (resolving bare packages through real `exports`, as an * installed consumer does, while Node type-strips relative example-local TypeScript plugins). - * Consolidating that spawn glue here retires the copies in the ACP snapshot harness and the example - * e2e drivers (the `TODO(acp-test-harness)`). * * @module @deepseek-ai/dsh-loader-smoke */ diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 46e67b1056..4875160d81 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -448,7 +448,7 @@ const APP_EXAMPLES = [ title: 'Headless Agent App Composition', label: 'examples/headless-agent', config: 'examples/headless-agent/cordis.yml', - summary: 'The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted main session.', + summary: 'The headless demo combines the real DeepSeek adapter and coding capabilities with the one-shot app package, format-pure stdout, and one fresh persisted top-level session.', }, { id: 'cordis', @@ -483,7 +483,7 @@ function renderAppExpansion(lines: string[], appNode: string, pluginName: string : 'dsh-tui (TTY) / dsh-stdio (pipes)
pre-created main agent' lines.push(` ${appNode} --> ${nodeId('frontdoor', 'stdio')}["${frontDoor}"]`) } else if (pluginName === '@deepseek-ai/dsh-cli-demo') { - lines.push(` ${appNode} --> ${nodeId('frontdoor', 'cli')}["one-shot driver
format-pure stdout
pre-created main agent"]`) + lines.push(` ${appNode} --> ${nodeId('frontdoor', 'cli')}["one-shot driver
format-pure stdout
fresh top-level agent"]`) } else if (pluginName === '@deepseek-ai/dsh-acp-demo') { lines.push(` ${appNode} --> ${nodeId('frontdoor', 'acp')}["@deepseek-ai/dsh-acp
JSON-RPC stdio bridge
sessions created by client"]`) } From c23214be5602a4d66cb1d70baa4ddaa4dae965c8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:30:45 +0800 Subject: [PATCH 224/323] refactor(core): fold initiator scope into agents --- AGENTS.md | 2 +- docs/architecture.md | 7 +- docs/capability-seams.md | 9 +- docs/config-catalog.md | 7 +- docs/cordis-catalog/events.md | 356 ++++++- docs/cordis-catalog/services.md | 902 +++++++++++++++++- docs/core-data-structures/core.md | 44 +- docs/module-graph.md | 10 +- docs/rfc/INDEX.md | 2 +- .../2026-07-15-agent-execution-context.md | 61 -- .../2026-07-15-agent-execution-context.zh.md | 61 -- ...026-07-15-agent-initiator-scope.i18n.yaml} | 4 +- .../2026-07-15-agent-initiator-scope.md | 63 ++ .../2026-07-15-agent-initiator-scope.zh.md | 63 ++ examples/coding-agent/tests/code-mode.e2e.ts | 3 - .../context/workspace-context/package.json | 1 - .../tests/workspace-context.e2e.ts | 2 - .../tests/workspace-context.spec.ts | 2 - .../cordis/tool-cordis/src/api-catalog.ts | 19 +- packages/core/README.md | 7 +- packages/core/agent-execution/README.md | 23 - packages/core/agent-execution/package.json | 31 - packages/core/agent-execution/src/index.ts | 140 --- packages/core/agent-execution/src/types.ts | 12 - .../tests/agent-execution.spec.ts | 163 ---- packages/core/agent-execution/tsconfig.json | 21 - packages/core/agent-loop/README.md | 4 +- packages/core/agent-loop/package.json | 2 - packages/core/agent-loop/src/agent.ts | 2 +- packages/core/agent-loop/src/index.ts | 3 +- ...cution.spec.ts => agent-initiator.spec.ts} | 101 +- packages/core/agent-loop/tests/agent.spec.ts | 6 +- packages/core/agent-loop/tests/cancel.spec.ts | 4 - .../tests/config-session-id.spec.ts | 8 - .../tests/contract-regressions.spec.ts | 9 - .../agent-loop/tests/coverage-edges.spec.ts | 2 - .../agent-loop/tests/interception.spec.ts | 2 - packages/core/agent-loop/tests/loop.spec.ts | 4 - .../core/agent-loop/tests/properties.spec.ts | 2 - .../agent-loop/tests/request-cache.e2e.ts | 2 - .../tests/request-reconstruction.spec.ts | 2 - packages/core/agent-loop/tests/resume.spec.ts | 9 - .../agent-loop/tests/scope-lifecycle.spec.ts | 2 - .../core/agent-loop/tests/tool-calls.spec.ts | 3 - .../core/agent-loop/tests/tool-order.spec.ts | 2 - .../core/agent-loop/tests/turn-stop.spec.ts | 2 - packages/core/agent-loop/tsconfig.json | 3 - packages/core/agent/README.md | 17 +- packages/core/agent/package.json | 2 +- packages/core/agent/src/index.ts | 121 ++- .../core/agent/tests/agent-initiator.spec.ts | 163 ++++ .../agent/tests/gen-cordis-catalog.spec.ts | 27 +- packages/examples/agent-spine-demo/README.md | 3 +- .../examples/agent-spine-demo/package.json | 4 +- .../examples/agent-spine-demo/src/index.ts | 2 - .../examples/agent-spine-demo/tsconfig.json | 3 - .../sdk/helper/src/features/builtin/spine.ts | 4 - packages/support/agent-loop-testkit/README.md | 2 +- .../support/agent-loop-testkit/package.json | 2 - .../support/agent-loop-testkit/src/index.ts | 2 - .../support/agent-loop-testkit/tsconfig.json | 3 - .../workflow-workerthread/package.json | 1 - .../tests/workflow-workerthread.e2e.ts | 2 - pnpm-lock.yaml | 27 - python/sdk-runtime/package.json | 1 - scripts/cordis-walk.ts | 41 +- scripts/gen-cordis-api.ts | 4 +- scripts/gen-cordis-catalog.ts | 83 +- scripts/gen-doc-graphs.ts | 12 +- scripts/gen-website-api.ts | 27 +- scripts/type-equiv.manifest.json | 2 - .../verify-package-readme-model-experience.ts | 1 - tsconfig.build.json | 1 - tsconfig.json | 1 - website/.vitepress/config/api-sidebar.json | 4 - website/zh-CN/api/harness/agent-execution.md | 48 - website/zh-CN/api/harness/agent-loop.md | 8 +- website/zh-CN/api/harness/agents.md | 77 +- website/zh-CN/api/harness/events.md | 2 +- 79 files changed, 1883 insertions(+), 1003 deletions(-) delete mode 100644 docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md delete mode 100644 docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md rename docs/rfc/implemented/architecture/{2026-07-15-agent-execution-context.i18n.yaml => 2026-07-15-agent-initiator-scope.i18n.yaml} (64%) create mode 100644 docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md create mode 100644 docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md delete mode 100644 packages/core/agent-execution/README.md delete mode 100644 packages/core/agent-execution/package.json delete mode 100644 packages/core/agent-execution/src/index.ts delete mode 100644 packages/core/agent-execution/src/types.ts delete mode 100644 packages/core/agent-execution/tests/agent-execution.spec.ts delete mode 100644 packages/core/agent-execution/tsconfig.json rename packages/core/agent-loop/tests/{agent-execution.spec.ts => agent-initiator.spec.ts} (76%) create mode 100644 packages/core/agent/tests/agent-initiator.spec.ts delete mode 100644 website/zh-CN/api/harness/agent-execution.md diff --git a/AGENTS.md b/AGENTS.md index a0ef9c7539..38799b8e96 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -11,7 +11,7 @@ DeepSeek Harness SDK is a plugin-based agent harness on vendored Cordis: **every ``` vendor/ Vendored Cordis source — manifest + sync procedure in vendor/README.md packages/ @deepseek-ai/dsh- workspaces at packages/// - core/ product API spine: session, system-prompt, tools, agent, agent-execution, agent-loop + core/ product API spine: session, system-prompt, tools, agent, agent-loop prompt/ workspace instructions llm/ LLM seam + the DeepSeek adapters (hand-rolled + pi-ai design twin) bash/ bash executor seam + local impl + model-facing bash tools diff --git a/docs/architecture.md b/docs/architecture.md index 09cc43afeb..f791784e8e 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -16,8 +16,7 @@ A harness is one [Cordis](cordis-primer.md) context. Packages contribute service | `ctx.sessions` | `dsh-session` | in-memory event-sourced sessions | | `ctx.systemPrompt` | `dsh-system-prompt` | ordered prompt sections, tool schemas, and prompt variables | | `ctx.tools` | `dsh-tools` | tool registry and [execution pipeline](tool-execution-pipeline.md) | -| `ctx.agents` | `dsh-agent` | live agent registry, public `Agent` handle, `agent/*` events | -| `ctx.agentExecution` | `dsh-agent-execution` | process-local ambient Agent identity for asynchronous driver work | +| `ctx.agents` | `dsh-agent` | live agents, creation delegation, `agent/*` events, and process-local initiating Agent scope | | `ctx.agentLoop` | `dsh-agent-loop` | concrete `Agent` driver | ### Capability Services @@ -119,9 +118,9 @@ Every session event is turn-enclosed. Reloading preserves an interrupted tail an Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, receive only that agent's dispatches, and unwind with it; async effects such as background-task cleanup are awaited. `CreateAgentOptions.setup(agentCtx)` composes the scope before publication. Typed resolvers derive carrier checks from merged `Events` signatures and `scopeTarget` ([semantic-gates RFC](rfc/implemented/process/2026-07-14-typescript-program-backed-semantic-gates.md)). See the [agent-scope RFC](rfc/implemented/architecture/2026-07-08-agent-scope-contexts.md) and [subagent composition controls](rfc/implemented/feature/2026-07-12-subagent-persona-tool-filter-and-depth.md). -### Agent Execution Context +### Initiating Agent Scope -`AgentLoop` establishes process-local `ctx.agentExecution` around each driver; the [decision](rfc/implemented/architecture/2026-07-15-agent-execution-context.md) owns boundary and explicit-identity rules. +`AgentLoop` runs each process-local driver inside `ctx.agents.withInitiator()`; the [decision](rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns boundary and explicit-identity rules. ## State diff --git a/docs/capability-seams.md b/docs/capability-seams.md index feb31a358e..93c5335e61 100644 --- a/docs/capability-seams.md +++ b/docs/capability-seams.md @@ -48,9 +48,7 @@ flowchart LR pkg_skill["skill"] svc_skills["ctx.skills
Skill provider registry"] pkg_skill_local["skill-local"] - svc_agents["ctx.agents
Agent registry"] - pkg_agent_execution["agent-execution"] - svc_agentExecution["ctx.agentExecution
Agent execution context"] + svc_agents["ctx.agents
Agent service"] svc_agentLoop["ctx.agentLoop
Concrete loop driver"] pkg_agent_spine_demo["agent-spine-demo"] pkg_bash["bash"] @@ -99,7 +97,6 @@ flowchart LR pkg_acp --> svc_approval pkg_acp --> svc_userInteraction pkg_agent --> svc_agents - pkg_agent_execution --> svc_agentExecution pkg_agent_loop --> svc_agentLoop pkg_approval --> svc_approval pkg_bash --> svc_bash @@ -145,7 +142,6 @@ flowchart LR pkg_web_search_perplexity --> svc_web pkg_workflow --> svc_workflows pkg_workflow_workerthread --> svc_workflows - svc_agentExecution --> pkg_agent_loop svc_agentLoop --> pkg_agent_spine_demo svc_agents --> pkg_acp svc_agents --> pkg_agent_loop @@ -216,8 +212,7 @@ flowchart LR | `ctx.tools` | `core` | [`tools`](../packages/core/tools) | - | [`agent-loop`](../packages/core/agent-loop), [`tool-ask-user`](../packages/ui/tool-ask-user), [`tool-bash`](../packages/bash/tool-bash), [`tool-cordis`](../packages/cordis/tool-cordis), [`tool-fs`](../packages/fs/tool-fs), [`tool-skill`](../packages/skill/tool-skill), [`tool-subagent`](../packages/subagent/tool-subagent), [`tool-todo`](../packages/todo/tool-todo), [`tool-web`](../packages/web/tool-web), [`acp`](../packages/ui/acp) | - | Registers capabilities, owns Code Mode transport, and routes calls through pre-policy, monotonic guards, around dispatch, post-policy, and final-result observation. | | `ctx.userInteraction` | `seam` | [`user-interaction`](../packages/ui/user-interaction) | [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | [`tool-ask-user`](../packages/ui/tool-ask-user), [`stdio-demo`](../packages/examples/stdio-demo), [`acp`](../packages/ui/acp) | - | UI front doors provide the active human-answer provider; tool-ask-user pauses a tool call on the provider-neutral ask() promise. | | `ctx.skills` | `seam` | [`skill`](../packages/skill/skill) | [`skill-local`](../packages/skill/skill-local) | [`tool-skill`](../packages/skill/tool-skill) | - | Merges provider skill catalogs; tool-skill renders the session-prefix catalog and loads complete skill bodies. | -| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles and the create/resume factory seam. | -| `ctx.agentExecution` | `core` | [`agent-execution`](../packages/core/agent-execution) | - | [`agent-loop`](../packages/core/agent-loop) | - | Carries the exact initiating Agent across one process-local asynchronous driver chain; explicit identities remain authoritative at external boundaries. | +| `ctx.agents` | `core` | [`agent`](../packages/core/agent) | - | [`agent-loop`](../packages/core/agent-loop), [`acp`](../packages/ui/acp), [`subagent-inprocess`](../packages/subagent/subagent-inprocess), [`stdio-demo`](../packages/examples/stdio-demo), [`invariants`](../packages/support/invariants) | - | Owns live Agent handles, the create/resume factory seam, and process-local initiator propagation. | | `ctx.agentLoop` | `bundle` | [`agent-loop`](../packages/core/agent-loop) | - | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | - | The one concrete loop plugin; extension packages depend on dsh-agent events and services, not on this package. | | `ctx.bash` | `seam` | [`bash`](../packages/bash/bash) | [`bash-local`](../packages/bash/bash-local), [`bash-sandbox`](../packages/bash/bash-sandbox) | [`tool-bash`](../packages/bash/tool-bash), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | - | The model-facing bash tools and hook bridges consume this seam; sandboxed or remote executors replace bash-local without touching them. | | `ctx.bashEnv` | `core` | [`tool-bash`](../packages/bash/tool-bash) | - | - | - | Plugins declare effect-scoped DSH_* facts; tool-bash collects one trusted snapshot per execution and the executor rebuilds the namespace. | diff --git a/docs/config-catalog.md b/docs/config-catalog.md index ee6003c6f6..47c7ff90b7 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -75,7 +75,7 @@ Source: [`packages/examples/acp-demo/src/index.ts:33`](../packages/examples/acp- ## `@deepseek-ai/dsh-agent-loop` -Requires: `agents` · `agentExecution` · `sessions` · `llm` · `tools` · `systemPrompt` +Requires: `agents` · `sessions` · `llm` · `tools` · `systemPrompt` ```ts config-catalog /** Agent-loop plugin configuration. */ @@ -101,7 +101,7 @@ export interface Config { Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) -Source: [`packages/core/agent-loop/src/index.ts:370`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:369`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-agent-spine-demo` @@ -157,7 +157,7 @@ export interface SkillConfig { Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts) -Source: [`packages/examples/agent-spine-demo/src/index.ts:58`](../packages/examples/agent-spine-demo/src/index.ts) +Source: [`packages/examples/agent-spine-demo/src/index.ts:57`](../packages/examples/agent-spine-demo/src/index.ts) ## `@deepseek-ai/dsh-bash-local` @@ -1415,7 +1415,6 @@ Source: [`packages/context/workspace-context/src/config.ts:16`](../packages/cont These load from a `cordis.yml` entry with no `config:` block; they declare no config surface. - `@deepseek-ai/dsh-agent` ([`packages/core/agent/src/index.ts`](../packages/core/agent/src/index.ts)) -- `@deepseek-ai/dsh-agent-execution` ([`packages/core/agent-execution/src/index.ts`](../packages/core/agent-execution/src/index.ts)) - `@deepseek-ai/dsh-fs-policy` ([`packages/fs/fs-policy/src/index.ts`](../packages/fs/fs-policy/src/index.ts)) - `@deepseek-ai/dsh-invariants` — requires `sessions` ([`packages/support/invariants/src/index.ts`](../packages/support/invariants/src/index.ts)) - `@deepseek-ai/dsh-llm` ([`packages/llm/llm/src/index.ts`](../packages/llm/llm/src/index.ts)) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 4598390194..12f877ad48 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -3,9 +3,9 @@ # Cordis Events Catalog -Every cordis event a plugin can listen to: exact signature, dispatch mode, and the declaration's JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. +Every cordis event a plugin can listen to: exact signature, dispatch mode, and original declaration JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. -This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them. +This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence and include the original source JSDoc immediately before each event or service method. doc-typecheck skips these bare declaration fragments; type names in a signature link to the page that documents them. The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary this repo owns, grouped by scope. The **inherited tier** at the end is the cordis-core + loader/hmr/timer event surface a plugin also sees — pinned vendor source, summarized tersely. @@ -18,6 +18,16 @@ Dispatch modes: **emit** (fire-and-forget), **waterfall** (each listener gets `n A fully configured agent and live session were published. Setup is composition-only; `agent/session-start` is the first startup-driving seam. Synchronous listener failure vetoes publication, while returned-promise rejection is reported. Detach requested during dispatch waits until every creation listener has observed the stable entry. ```ts cordis-catalog +/** + * A fully configured agent and live session were published. Setup is + * composition-only; `agent/session-start` is the first startup-driving seam. + * Synchronous listener failure vetoes publication, while returned-promise + * rejection is reported. Detach requested during dispatch waits until every + * creation listener has observed the stable entry. + * @param agent - the newly registered agent with its live session and completed setup. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/created'(this: Scoped, agent: Agent): void ``` @@ -30,6 +40,14 @@ Source: [`packages/core/agent/src/types.ts:141`](../../packages/core/agent/src/t An agent left the registry; AgentLoop emits this after driver quiescence but before session detachment and scoped-registration unwind. Custom registry users own their driver-ordering contract. ```ts cordis-catalog +/** + * An agent left the registry; AgentLoop emits this after driver quiescence + * but before session detachment and scoped-registration unwind. Custom + * registry users own their driver-ordering contract. + * @param agent - the exact agent removed from the registry. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/disposed'(this: Scoped, agent: Agent): void ``` @@ -42,6 +60,16 @@ Source: [`packages/core/agent/src/types.ts:150`](../../packages/core/agent/src/t A step or turn errored. The loop reports a failure here (plus the logger) even when the error has no in-turn position for a session `error` event. ```ts cordis-catalog +/** + * A step or turn errored. The loop reports a failure here (plus the logger) + * even when the error has no in-turn position for a session `error` event. + * @param agent - the agent whose turn errored. + * @param turn - the turn in which the failure surfaced. + * @param step - the step at which the failure surfaced. + * @param error - the failure, verbatim. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/error'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void ``` @@ -54,6 +82,22 @@ Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/t Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step. The loop derives history once afterward, so compaction records and replacements are included without rewriting an assembled request. The prompt and prefix are the exact pressure inputs for that request, and `signal` cancels listener work. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog +/** + * Awaited serial checkpoint for session-surface mutation after prompt + * assembly and before `step/start`; appends land outside the pending step. + * The loop derives history once afterward, so compaction records and + * replacements are included without rewriting an assembled request. The + * prompt and prefix are the exact pressure inputs for that request, and + * `signal` cancels listener work. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param agent - the agent opening the step. + * @param turn - the open turn number. + * @param step - the pending step number. + * @param fullSystemPrompt - the assembled prompt. + * @param sessionPrefix - the frozen request prefix. + * @param signal - the turn abort signal. + * @mode serial + */ 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void ``` @@ -66,6 +110,15 @@ Source: [`packages/core/agent/src/types.ts:204`](../../packages/core/agent/src/t Allow, rewrite, or block one drained prompt before it becomes a user message. Call `next()` for the unchanged default. ```ts cordis-catalog +/** + * Allow, rewrite, or block one drained prompt before it becomes a user + * message. Call `next()` for the unchanged default. + * @param agent - the agent draining its inbox. + * @param content - the drained message's blocks, as queued. + * @param source - the message's resolved source. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/prompt-submit'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise ``` @@ -78,6 +131,15 @@ Source: [`packages/core/agent/src/types.ts:214`](../../packages/core/agent/src/t Detached, frozen content entered the agent's inbox. Source defaults have already been applied, so these are the exact values retained for the log. ```ts cordis-catalog +/** + * Detached, frozen content entered the agent's inbox. Source defaults have + * already been applied, so these are the exact values retained for the log. + * @param agent - the agent whose inbox received the message. + * @param content - the accepted content blocks retained by the inbox. + * @param info - the accepted source plus whether it entered as steering. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/queued'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void ``` @@ -90,6 +152,17 @@ Source: [`packages/core/agent/src/types.ts:169`](../../packages/core/agent/src/t Replace the frozen call configuration. Model-visible content must use logged channels; this seam cannot mutate messages. Injection here joins the next request because the current step boundary is already fixed. ```ts cordis-catalog +/** + * Replace the frozen call configuration. Model-visible content must use + * logged channels; this seam cannot mutate messages. Injection here joins + * the next request because the current step boundary is already fixed. + * @param agent - the agent making the model call. + * @param turn - the open turn number. + * @param step - the step whose request this is. + * @param config - the config the loop would use (frozen); return a replacement to switch. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/request'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise ``` @@ -102,6 +175,20 @@ Source: [`packages/core/agent/src/types.ts:226`](../../packages/core/agent/src/t Compose request-only messages placed before derived history. The frozen result is computed once per loop instance, logged on its anchoring request header, and reused so the provider prefix remains stable. Interrupted composition is discarded. Composition precedes the first `agent/pre-step` and request boundary, so listener appends join the current request and pressure accounting sees the composed prefix. Changing context belongs in history; contributors should prepend to `await next()` to preserve registration order. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog +/** + * Compose request-only messages placed before derived history. The frozen + * result is computed once per loop instance, logged on its anchoring request + * header, and reused so the provider prefix remains stable. Interrupted + * composition is discarded. Composition precedes the first `agent/pre-step` + * and request boundary, so listener appends join the current request and + * pressure accounting sees the composed prefix. Changing context belongs in + * history; contributors should prepend to `await next()` to preserve registration order. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param agent - the agent whose session prefix is being composed. + * @param prefix - the frozen seed; return an extended replacement. + * @param signal - aborts composition when the step is torn down. + * @mode waterfall + */ 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise ``` @@ -114,6 +201,16 @@ Source: [`packages/core/agent/src/types.ts:241`](../../packages/core/agent/src/t The session lifecycle began, once before the first turn. Use `agent.inject()` to seed model-facing context. This is a notification, not a veto; disposal requested by a lifecycle owner is rechecked before the driver starts. ```ts cordis-catalog +/** + * The session lifecycle began, once before the first turn. Use + * `agent.inject()` to seed model-facing context. This is a notification, not + * a veto; disposal requested by a lifecycle owner is rechecked before the + * driver starts. + * @param agent - the agent whose session lifecycle began. + * @param source - why the session started (fresh startup, resume, …). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/session-start'(this: Scoped, agent: Agent, source: SessionStartSource): void ``` @@ -126,6 +223,14 @@ Source: [`packages/core/agent/src/types.ts:182`](../../packages/core/agent/src/t Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does not enter `running` synchronously; drive lifecycle from this event. ```ts cordis-catalog +/** + * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does + * not enter `running` synchronously; drive lifecycle from this event. + * @param agent - the agent whose status flipped. + * @param status - the status just entered (the transition's destination). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/status'(this: Scoped, agent: Agent, status: AgentStatus): void ``` @@ -138,6 +243,16 @@ Source: [`packages/core/agent/src/types.ts:159`](../../packages/core/agent/src/t Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …). ```ts cordis-catalog +/** + * Waterfall: post-process the assembled assistant {@link Message} before + * tool dispatch (validation, content rewriting, …). + * @param agent - the agent that received the step's response. + * @param turn - the open turn number. + * @param step - the step that produced the message. + * @param message - the assistant message as assembled from the stream. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise ``` @@ -150,6 +265,15 @@ Source: [`packages/core/agent/src/types.ts:252`](../../packages/core/agent/src/t Override whether the turn continues. The default continues after tool calls or steering and stops otherwise; a continue reason becomes steering. ```ts cordis-catalog +/** + * Override whether the turn continues. The default continues after tool + * calls or steering and stops otherwise; a continue reason becomes steering. + * @param agent - the agent deciding whether to run another step. + * @param turn - the turn being continued or stopped. + * @param defaultDecision - what the loop would do absent an override. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/turn-continuation'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise ``` @@ -162,6 +286,15 @@ Source: [`packages/core/agent/src/types.ts:262`](../../packages/core/agent/src/t Monotonic terminal-stop checkpoint after continuation and steering are folded; a stop remains authoritative through turn close and flush: steering queued in that window is discarded, while ordinary sends survive. ```ts cordis-catalog +/** + * Monotonic terminal-stop checkpoint after continuation and steering are + * folded; a stop remains authoritative through turn close and flush: + * steering queued in that window is discarded, while ordinary sends survive. + * @param agent - the agent whose composed continuation outcome may be stopped. + * @param turn - the turn at its terminal-stop checkpoint. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode serial + */ 'agent/turn-stop'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined ``` @@ -176,10 +309,19 @@ Source: [`packages/core/agent/src/types.ts:272`](../../packages/core/agent/src/t A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt. ```ts cordis-catalog +/** + * A declarative agent entry failed before it could publish a live agent. + * Consumers that buffer work for the configured identity use this + * transient signal to reject that work instead of waiting forever. Normal + * factory teardown suppresses failures from the cancelled startup attempt. + * @param sessionId - exact shared agent/session identity that failed startup. + * @param error - persistence, setup, or publication failure. + * @mode emit + */ 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` -Source: [`packages/core/agent-loop/src/index.ts:363`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:362`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` @@ -188,6 +330,13 @@ Source: [`packages/core/agent-loop/src/index.ts:363`](../../packages/core/agent- Ask composed answerers for one decision. Return an outcome to claim the request or call `next()`; failure yields the fail-closed default. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. ```ts cordis-catalog +/** + * Ask composed answerers for one decision. Return an outcome to claim the + * request or call `next()`; failure yields the fail-closed default. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param req - the pending decision (agent, tool identity, reason, signal). + * @mode waterfall + */ 'approval/request'(this: Scoped, req: ApprovalRequest, next: () => Promise): Promise ``` @@ -202,6 +351,13 @@ Source: [`packages/ui/user-approval/src/index.ts:31`](../../packages/ui/user-app Single-slot decision for the next FileSystem.editText. Calling `next()` yields an unconditional edit; the first returned guard wins. ```ts cordis-catalog +/** + * Single-slot decision for the next {@link FileSystem.editText}. Calling + * `next()` yields an unconditional edit; the first returned guard wins. + * @param target - the resolved target about to be edited. + * @param actor - the opaque tool-execution context the decider keys off. + * @mode waterfall + */ 'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined> ``` @@ -214,6 +370,14 @@ Source: [`packages/fs/fs/src/index.ts:61`](../../packages/fs/fs/src/index.ts) Record a successful observation. Listeners must be synchronous recorders: throws fail the tool call and returned promises are not awaited. ```ts cordis-catalog +/** + * Record a successful observation. Listeners must be synchronous recorders: + * throws fail the tool call and returned promises are not awaited. + * @param target - the target that was read/written/edited. + * @param version - the version the actor now holds as its observation. + * @param actor - the observing tool-execution context; undefined records nothing useful. + * @mode emit + */ 'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void ``` @@ -226,6 +390,14 @@ Source: [`packages/fs/fs/src/index.ts:70`](../../packages/fs/fs/src/index.ts) Single-slot decision for the next FileSystem.writeText. Calling `next()` yields the bare provider's unconditional write; the first listener that returns an intent owns the decision rather than composing with peers. ```ts cordis-catalog +/** + * Single-slot decision for the next {@link FileSystem.writeText}. Calling + * `next()` yields the bare provider's unconditional write; the first listener + * that returns an intent owns the decision rather than composing with peers. + * @param target - the resolved target about to be written. + * @param actor - the opaque tool-execution context the decider keys off. + * @mode waterfall + */ 'fs/write-intent'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise): Promise ``` @@ -240,6 +412,17 @@ Source: [`packages/fs/fs/src/index.ts:53`](../../packages/fs/fs/src/index.ts) Waterfall around every streaming model call (retry, replay, routing). Bound to the LlmService; call `next()` to reach the resolved adapter's stream, or yield your own chunks to short-circuit. ```ts cordis-catalog +/** + * Waterfall around every streaming model call (retry, replay, routing). + * Bound to the {@link LlmService}; call `next()` to reach the resolved + * adapter's stream, or yield your own chunks to short-circuit. + * @param options - the full request. A LOOP-built request arrives + * deep-frozen (mutation throws): its content is a pure function of the + * session log (the reconstructability RFC), so listeners read it, never + * rewrite it. A hand-built one-shot (compaction summarize) is the + * caller's own object and stays mutable here. + * @mode waterfall + */ 'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable): AsyncIterable ``` @@ -254,6 +437,17 @@ Source: [`packages/llm/llm/src/index.ts:40`](../../packages/llm/llm/src/index.ts Creation announcement during session publication. A synchronous throw vetoes and rolls back with a paired disposal; detach requested during dispatch is deferred. A returned-promise rejection is logged but cannot retroactively veto this synchronous boundary. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only sessions entered through that agent's context. ```ts cordis-catalog +/** + * Creation announcement during session publication. A synchronous throw vetoes and rolls + * back with a paired disposal; detach requested during dispatch is deferred. + * A returned-promise rejection is logged but cannot retroactively veto this + * synchronous boundary. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners + * receive only sessions entered through that agent's context. + * @param session - the session just entered and announced. + * @dshScopeScan unsupported + * @mode emit + */ 'session/created'(this: Scoped, session: Session): void ``` @@ -264,6 +458,15 @@ Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/sr Emitted once when an announced session leaves the store, including publication rollback, but never for an entry whose creation announcement did not begin. Listener failures are logged and contained. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope. ```ts cordis-catalog +/** + * Emitted once when an announced session leaves the store, including + * publication rollback, but never for an entry whose creation announcement + * did not begin. Listener failures are logged and contained. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope. + * @param session - the session that is no longer live in the store. + * @dshScopeScan unsupported + * @mode emit + */ 'session/disposed'(this: Scoped, session: Session): void ``` @@ -274,6 +477,17 @@ Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/sr Post-commit, fire-and-forget append feed. The listener snapshot resolves before the log push, but callbacks run after it; observer failures are logged and contained without making the committed append fail. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only events from sessions entered through that agent's context. ```ts cordis-catalog +/** + * Post-commit, fire-and-forget append feed. The listener snapshot resolves + * before the log push, but callbacks run after it; observer failures are + * logged and contained without making the committed append fail. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners + * receive only events from sessions entered through that agent's context. + * @param session - the session whose log grew. + * @param event - the appended event, exactly as recorded. + * @dshScopeScan unsupported + * @mode emit + */ 'session/event'(this: Scoped, session: Session, event: SessionEvent): void ``` @@ -286,6 +500,15 @@ Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/sr Awaited parallel durability checkpoint: every listener runs and the caller awaits all of them, with no waterfall veto. Dispatch through SessionStore.flush. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the session's owner scope. ```ts cordis-catalog +/** + * Awaited parallel durability checkpoint: every listener runs and the + * caller awaits all of them, with no waterfall veto. Dispatch through + * {@link SessionStore.flush}. Scope-filtered dispatch + * (`@deepseek-ai/dsh-scope`) reuses the session's owner scope. + * @param session - the session whose buffered events must reach durable storage. + * @dshScopeScan unsupported + * @mode parallel + */ 'session/flush'(this: Scoped, session: Session): Promise | void ``` @@ -298,6 +521,14 @@ Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/sr A ready child settled. Scope-filtered dispatch uses the same delegating parent carrier as `subagent/start`, so the lifecycle pair reaches the same scoped audience. ```ts cordis-catalog +/** + * A ready child settled. Scope-filtered dispatch uses the same delegating + * parent carrier as `subagent/start`, so the lifecycle pair reaches the + * same scoped audience. + * @param info - the run identity and terminal outcome. + * @dshScopeScan unsupported + * @mode emit + */ 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` @@ -308,6 +539,11 @@ Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/ A provider became resolvable in the registry. ```ts cordis-catalog +/** + * A provider became resolvable in the registry. + * @param provider - the registered provider. + * @mode emit + */ 'subagent/provider-added'(provider: SubagentProvider): void ``` @@ -318,6 +554,11 @@ Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/s A provider left the registry. Accepted runs remain holder-owned. ```ts cordis-catalog +/** + * A provider left the registry. Accepted runs remain holder-owned. + * @param name - the provider name that no longer resolves. + * @mode emit + */ 'subagent/provider-removed'(name: string): void ``` @@ -328,6 +569,16 @@ Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/s A provider established a ready child. For in-process providers, `ctx.agents.get(info.id)` resolves during this notification. Scope-filtered dispatch keys the carrier by the delegating parent, so a parent-scoped listener observes only its own delegations. Paired with `subagent/end`. ```ts cordis-catalog +/** + * A provider established a ready child. For in-process providers, + * `ctx.agents.get(info.id)` resolves during this notification. + * Scope-filtered dispatch keys the carrier by the delegating parent, so a + * parent-scoped listener observes only its own delegations. Paired with + * `subagent/end`. + * @param info - the provider and ready child identity. + * @dshScopeScan unsupported + * @mode emit + */ 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` @@ -340,6 +591,14 @@ Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/ Expert waterfall over the assembled sections, tools, and variables. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners receive only that scope's assemblies. The returned value is authoritative. ```ts cordis-catalog +/** + * Expert waterfall over the assembled sections, tools, and variables. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners + * receive only that scope's assemblies. The returned value is authoritative. + * @param assembly - the mutable assembly built from registered providers. + * @param context - the caller's per-assembly context. + * @mode waterfall + */ 'system-prompt/assemble'(this: Scoped, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise ``` @@ -350,6 +609,11 @@ Source: [`packages/core/system-prompt/src/index.ts:27`](../../packages/core/syst Emitted when any prompt provider changes. This registry notification is unfiltered because a global change affects every scope. ```ts cordis-catalog +/** + * Emitted when any prompt provider changes. This registry notification is + * unfiltered because a global change affects every scope. + * @mode emit + */ 'system-prompt/change'(): void ``` @@ -362,6 +626,15 @@ Source: [`packages/core/system-prompt/src/index.ts:33`](../../packages/core/syst A tool was registered or unregistered, or a scoped restriction changed (the available tool set changed — possibly for one scope only). An UNFILTERED registry-subject notification, deliberately not scope-filtered dispatch: a global change concerns every agent's next assembly, so a scoped listener subscribing here sees every change, not just its own scope's. ```ts cordis-catalog +/** + * A tool was registered or unregistered, or a scoped restriction changed + * (the available tool set changed — possibly for one scope only). An + * UNFILTERED registry-subject notification, deliberately not scope-filtered + * dispatch: a global change concerns every agent's next assembly, so a + * scoped listener subscribing here sees every change, not just its own + * scope's. + * @mode emit + */ 'tools/change'(): void ``` @@ -372,6 +645,14 @@ Source: [`packages/core/tools/src/index.ts:116`](../../packages/core/tools/src/i Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns a normalized result; wrappers may change only `exec.signal`, while call identity remains immutable. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. ```ts cordis-catalog +/** + * Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns + * a normalized result; wrappers may change only `exec.signal`, while call + * identity remains immutable. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal). + * @mode waterfall + */ 'tools/execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` @@ -384,6 +665,14 @@ Source: [`packages/core/tools/src/index.ts:89`](../../packages/core/tools/src/in Accept, replace, enrich, or block a normalized dispatch result. `next()` accepts it unchanged; thrown tools still reach this seam as errors. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. ```ts cordis-catalog +/** + * Accept, replace, enrich, or block a normalized dispatch result. `next()` + * accepts it unchanged; thrown tools still reach this seam as errors. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the call that just ran (name, parsed arguments, caller agent). + * @param result - the dispatch outcome a listener may accept, replace, or block. + * @mode waterfall + */ 'tools/post-execute'(this: Scoped, exec: ToolExecution, result: Readonly, next: () => Promise): Promise ``` @@ -396,6 +685,13 @@ Source: [`packages/core/tools/src/index.ts:98`](../../packages/core/tools/src/in Allow, deny, or ask before dispatch. `next()` delegates to allow; missing approval support turns `ask` into denial. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. ```ts cordis-catalog +/** + * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing + * approval support turns `ask` into denial. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the pending call (name, parsed arguments, caller agent). + * @mode waterfall + */ 'tools/pre-execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` @@ -408,6 +704,13 @@ Source: [`packages/core/tools/src/index.ts:80`](../../packages/core/tools/src/in Observe the frozen, lossless-JSON final outcome. Listener failures are contained. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`. ```ts cordis-catalog +/** + * Observe the frozen, lossless-JSON final outcome. Listener failures are contained. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`. + * @param exec - the execution object that traversed the pipeline. + * @param result - a deep-frozen snapshot of the final returned result. + * @mode emit + */ 'tools/result'(this: Scoped, exec: Readonly, result: Readonly): undefined ``` @@ -422,6 +725,16 @@ Source: [`packages/core/tools/src/index.ts:106`](../../packages/core/tools/src/i One `agent()` call settled (clean result, child failure, or run cancellation). Paired with Events['workflow/agent-start'] by `agent.seq`, exactly once per started call on every stop path — on an engine termination path (a worker killed past its grace) the end is engine-synthesized with outcome `'cancelled'`. ```ts cordis-catalog +/** + * One `agent()` call settled (clean result, child failure, or run + * cancellation). Paired with {@link Events['workflow/agent-start']} by + * `agent.seq`, exactly once per started call on every stop path — on an + * engine termination path (a worker killed past its grace) the end is + * engine-synthesized with outcome `'cancelled'`. + * @param info - the run's identity snapshot. + * @param agent - the call identity plus its outcome. + * @mode emit + */ 'workflow/agent-end'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): void ``` @@ -432,6 +745,15 @@ Source: [`packages/workflow/workflow/src/index.ts:81`](../../packages/workflow/w One `agent()` call established a ready child run. Paired with Events['workflow/agent-end'] by `agent.seq`. A call that never receives a ready run from the provider emits neither event in this pair. ```ts cordis-catalog +/** + * One `agent()` call established a ready child run. Paired with + * {@link Events['workflow/agent-end']} by `agent.seq`. A call that never + * receives a ready run from the provider emits neither + * event in this pair. + * @param info - the run's identity snapshot. + * @param agent - the call's sequence number, label, phase, and child id. + * @mode emit + */ 'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void ``` @@ -442,6 +764,15 @@ Source: [`packages/workflow/workflow/src/index.ts:70`](../../packages/workflow/w A workflow run settled (any stop reason). Fired when WorkflowRun.result resolves. Paired with Events['workflow/start']. ```ts cordis-catalog +/** + * A workflow run settled (any stop reason). Fired when + * {@link WorkflowRun.result} resolves. Paired with + * {@link Events['workflow/start']}. + * @param info - the run's identity snapshot. + * @param result - the outcome data (stop reason, error, agent count) — + * deliberately WITHOUT the result value (see {@link WorkflowResultInfo}). + * @mode emit + */ 'workflow/end'(info: WorkflowRunInfo, result: WorkflowResultInfo): void ``` @@ -452,6 +783,12 @@ Source: [`packages/workflow/workflow/src/index.ts:91`](../../packages/workflow/w The script emitted a narration line (a `log(message)` call). ```ts cordis-catalog +/** + * The script emitted a narration line (a `log(message)` call). + * @param info - the run's identity snapshot. + * @param message - the logged message, verbatim. + * @mode emit + */ 'workflow/log'(info: WorkflowRunInfo, message: string): void ``` @@ -462,6 +799,13 @@ Source: [`packages/workflow/workflow/src/index.ts:60`](../../packages/workflow/w The script entered a phase (a `phase(title)` call) — progress grouping for observers; no execution semantics. ```ts cordis-catalog +/** + * The script entered a phase (a `phase(title)` call) — progress grouping + * for observers; no execution semantics. + * @param info - the run's identity snapshot. + * @param title - the phase title, verbatim. + * @mode emit + */ 'workflow/phase'(info: WorkflowRunInfo, title: string): void ``` @@ -472,6 +816,12 @@ Source: [`packages/workflow/workflow/src/index.ts:53`](../../packages/workflow/w A workflow run started — the script's meta block validated, the body about to execute. Paired with Events['workflow/end']. ```ts cordis-catalog +/** + * A workflow run started — the script's meta block validated, the body + * about to execute. Paired with {@link Events['workflow/end']}. + * @param info - the run's identity snapshot (id + meta). + * @mode emit + */ 'workflow/start'(info: WorkflowRunInfo): void ``` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 40bd029e41..22d4565830 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -3,66 +3,226 @@ # Cordis Services Catalog -Every `ctx.` service a plugin can call: the exact public interface plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against. +Every `ctx.` service a plugin can call: the exact public interface with original method JSDoc, plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against. -This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them. +This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence and include the original source JSDoc immediately before each event or service method. doc-typecheck skips these bare declaration fragments; type names in a signature link to the page that documents them. The **harness tier** below (the `@deepseek-ai/dsh-*` packages) is the vocabulary this repo owns. The **inherited tier** at the end is the cordis-core + loader/hmr/timer `ctx` surface a plugin also sees — pinned vendor source, summarized tersely. -## `ctx.agentExecution` — `AgentExecutionService` (abstract seam) - -Ambient Agent identity within one process-local asynchronous chain. - -```ts cordis-catalog -current(): AgentExecution | undefined -require(): AgentExecution -run(execution: AgentExecution | undefined, operation: () => T): T -``` - -Types: [AgentExecution](../core-data-structures/core.md) - -Source: [`packages/core/agent-execution/src/index.ts:18`](../../packages/core/agent-execution/src/index.ts) - ## `ctx.agentLoop` — `AgentLoop` Concrete agent factory and driver service. ```ts cordis-catalog +/** + * Create an agent and session under one caller-supplied identity, owned by + * the accessing fiber. Constructor-driven config calls mint a fresh combined + * id before entering this boundary. + * @param id - shared agent/session identity. + * @param options - concrete loop options. + * @param meta - optional fresh-session workspace metadata. + * @returns the published running agent. + */ create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent + +/** + * Create an owned agent on a caller-supplied session id. + * @param ownerCtx - caller context that structurally owns the transaction. + * @param options - identities, session seed/metadata, loop options, setup, and cancellation. + * @returns the published handle. + */ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise + +/** + * Resume an owned agent from the configured persistence service. + * @param ownerCtx - caller context that owns load, setup, and the live lifecycle. + * @param options - persisted identity, loop options, setup, and cancellation. + * @returns the published handle. + */ async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent-loop/src/index.ts:408`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:407`](../../packages/core/agent-loop/src/index.ts) ## `ctx.agents` — `AgentRegistry` -Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. +Agent service (`ctx.agents`): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. ```ts cordis-catalog +/** + * Read the Agent that initiated the inherited asynchronous driver chain. + * @returns the inherited Agent, or `undefined` outside a driver and inside an explicit clearing boundary. + * @throws when this service instance has been disposed. + */ +currentInitiator(): Agent | undefined + +/** + * Read the initiating Agent and fail when no driver boundary is active. + * @returns the inherited Agent. + * @throws when no initiator is active or this service instance has been disposed. + */ +requireInitiator(): Agent + +/** + * Run an operation with one exact Agent as its process-local initiator. The + * exact synchronous value or Promise returned by the operation is preserved. + * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization. + * @param operation - synchronous or asynchronous operation to invoke. + * @returns the exact value returned by `operation`. + * @throws when the initiator scope is closing/disposed, or when `operation` throws. + */ +withInitiator(agent: Agent, operation: () => T): T + +/** + * Run an operation inside a boundary that hides any inherited initiating + * Agent. The exact synchronous value or Promise is preserved. + * @param operation - synchronous or asynchronous operation to invoke without an initiator. + * @returns the exact value returned by `operation`. + * @throws when the initiator scope is closing/disposed, or when `operation` throws. + */ +withoutInitiator(operation: () => T): T + +/** + * Register the agent-creation factory (the loop calls this on construction, + * effect-scoped). A traced Cordis service is canonicalized to its concrete + * target; each create/resume call is then traced through that caller's + * context so ownership follows the caller without stacking proxy layers. + * Throws if a factory is already registered. Returns the disposer; on + * dispose the factory slot is cleared. + * @param factory - the loop-owned factory {@link create}/{@link resume} delegate to. + * @returns the disposer that clears the factory slot. The exact + * Cordis effect disposer (single-shot): composite (generator) effects may + * yield it directly — exact identity nests the teardown in order. + */ setFactory(factory: AgentFactory): () => void + +/** + * Create and publish a new agent through the registered factory. + * Distinct from {@link register} (which records an already-constructed + * agent): this constructs the agent and its session. Rejects if no factory is + * registered or creation/setup fails. The resolved {@link AgentHandle} lets + * the owner tear down exactly this agent. + * @param options - shared identity, session seed/metadata, and agent options. + * @returns the handle after setup, rollback-covered publication, and loop start complete. + */ async create(options: CreateAgentOptions): Promise + +/** + * Load a persisted session and resume an agent on it through the registered + * factory. Rejects if no factory is registered; the factory rejects if + * session persistence is not configured or persistence/setup fails. + * @param options - persisted identity, configuration, and optional setup. + * @returns the handle after setup, rollback-covered publication, and loop start complete. + */ async resume(options: ResumeAgentOptions): Promise + +/** + * Register a live agent. Throws if an agent with the same id is already + * registered. Emits `agent/created` on registration and `agent/disposed` + * when the calling fiber is disposed — both with the agent's scope carrier + * (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the + * emits are scope-filtered regardless of which context invoked `register` + * (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always + * requires passing the carrier). Returns the disposer. + * @param agent - the already-constructed agent to record in the store. + * @returns the EXACT Cordis effect disposer (single-shot; a repeat call + * returns undefined without awaiting an in-flight teardown). Exact + * identity is load-bearing: a composite (generator) effect that owns a + * teardown ORDER — the agent factory's lifecycle chain — must yield THIS + * function so Cordis nests the unregistration at that yield position; + * yielding a wrapper would leave it disposing as a concurrent sibling on + * owner unload, unregistering the agent (and emitting `agent/disposed`) + * while its final turn is still draining. + */ register(agent: Agent): () => void + +/** + * Insert an already-constructed agent without announcing it. This is the + * advanced ordered-lifecycle primitive used by the async agent factory: it + * first completes setup while the agent is unpublished, then assigns the + * returned detach closure into its pre-installed composite teardown before + * calling {@link announce}. Ordinary callers use {@link register}. + * @param agent - the prepared, unpublished agent. + * @param owner - live agent whose scoped context created this agent, or + * undefined for a top-level runtime root. This is runtime ownership, not + * the resumed session's durable parent lineage. + * @returns an idempotent closure that removes this exact entry and emits + * `agent/disposed` with listener failures contained. When called from a + * synchronous `agent/created` listener, removal and disposal wait until + * that creation dispatch unwinds. + */ enter(agent: Agent, owner: Agent | undefined): () => void + +/** + * Announce an agent previously inserted with {@link enter}. + * @param agent - the live inserted agent to announce. + * @throws if `agent` is not the exact live registry entry for its id, or its + * creation announcement already began (including a reentrant call from a + * creation listener). + */ announce(agent: Agent): void + +/** + * Look up a live agent. + * @param id - the shared agent/session id to look up. + * @returns the agent, or undefined when no live agent has that id. + */ get(id: SessionId): Agent | undefined + +/** + * Test whether a live agent was created through one exact parent agent's + * scoped context. Runtime ownership is independent of durable session + * lineage and remains unambiguous when unrelated providers reuse an id. + * @param id - the candidate child agent's shared agent/session id. + * @param owner - the expected runtime creator agent. + * @returns true only while the exact child entry is live under that owner. + */ isOwnedBy(id: SessionId, owner: Agent): boolean + +/** + * All live agents, in registration order. + * @returns a fresh array; mutating it does not affect the registry. + */ list(): Agent[] + +/** + * All live top-level agents in registration order. A top-level agent was + * created without an owning agent context; durable session lineage does not + * affect this runtime relation, so a resumed fork may still be a root. + * @returns a fresh array; mutating it does not affect the registry. + */ roots(): Agent[] ``` Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:204`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` Approval service that applies session policy before answerers and logs every ask/outcome pair to the requesting session. It exposes deterministic policy changes to the model through prompt and pre-step notices. ```ts cordis-catalog +/** + * Ask the composed answerers to decide one readonly same-process request. + * The service borrows the request, agent, session, and live signal directly. + * The request requires an open turn because the audit pair must be enclosed + * by the durable log's commit/replay boundary; an idle ask rejects before + * appending anything. The answerer phase always produces an outcome: an + * aborted signal yields `'cancelled'`, a missing or throwing answerer yields + * `'unavailable'` (fail closed), and a rogue non-vocabulary return value is + * normalized to `'unavailable'`. A failure that prevents either audit append + * from committing still rejects because returning an unlogged decision would + * violate the pair. Session contains post-commit observer failures, so an + * authoritative append cannot reject the request or suppress its matching + * audit event. + * @param req - the pending decision (agent, tool identity, reason, signal). + * @returns the closed outcome; `'allowed-once'` is the only grant. + * @throws when no turn is open or either audit event fails before the session + * append commit point. + */ async request(req: ApprovalRequest): Promise ``` @@ -82,8 +242,27 @@ Implementations must honor these semantics: - Disposal kills all running background processes and awaits their exit. ```ts cordis-catalog +/** + * Apply implementation-owned defaults and caps to a request before execution. + * @param request - the caller's request; omitted fields get this + * implementation's defaults, capped fields are clamped. + * @returns the fully-specified spec to hand to {@link run}/{@link start}. + */ abstract resolve(request: BashExecRequest): BashExecSpec + +/** + * Run a command in the foreground; resolves when it finishes. + * @param spec - a resolved spec from {@link resolve}, never a raw request. + * @returns the outcome; nonzero exits, timeout kills, and abort kills + * resolve with a descriptive result rather than reject. + */ abstract run(spec: BashExecSpec): Promise + +/** + * Start a background process and return its handle immediately. + * @param spec - a resolved spec from {@link resolve}, never a raw request. + * @returns the live process handle (reads, kill, quiescence promise). + */ abstract start(spec: BashExecSpec): BashProcess ``` @@ -96,8 +275,25 @@ Source: [`packages/bash/bash/src/index.ts:49`](../../packages/bash/bash/src/inde Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. The namespace is rebuilt for every model bash call: ambient `DSH_*` values are discarded by the executor, then the registry's current snapshot is injected. Built-in shell facts remain owned by the registry itself while plugins can register additional, enumerable facts with effect-scoped disposal. ```ts cordis-catalog +/** + * Register one environment contributor. Names and keys are unique; built-in + * keys are reserved. Registration is disposed with the calling plugin fiber. + * @param contributor - declared key ownership and per-execution resolver. + * @returns the disposer that unregisters the contribution. + */ register(contributor: BashEnvContributor): () => void + +/** + * Build the trusted `DSH_*` snapshot for one bash tool execution. + * @param execution - the current tool execution. + * @returns an immutable environment overlay containing built-ins and current contributions. + */ collect(execution: ToolExecution): DshEnvironment + +/** + * Enumerate plugin-contributed variables without executing their resolvers. + * @returns declarations sorted by environment variable name. + */ list(): BashEnvVariableInfo[] ``` @@ -110,6 +306,15 @@ Source: [`packages/bash/tool-bash/src/index.ts:102`](../../packages/bash/tool-ba Registers one `ctx.codeRuntime` implementation. Program, budget, abort, and substrate failures resolve in CodeRunResult; only seam misuse rejects. Implementations bridge structured-cloneable bindings while treating programs as hostile peers, isolate runs from one another, and terminate and await in-flight runs during disposal. ```ts cordis-catalog +/** + * Execute one program against the request's bindings and capture what it + * emitted. See the class doc for the resolution contract (error is a result + * field; rejection means seam misuse only). + * @param request - the program, its bindings, and the abort signal; the + * request carries everything the runtime acts on, with no hidden defaults. + * @returns the run's outcome: completion value (when transferable), the + * ordered log capture, and the failure (if any). + */ abstract run(request: CodeRunRequest): Promise ``` @@ -122,7 +327,40 @@ Source: [`packages/code-runtime/code-runtime/src/index.ts:30`](../../packages/co Abstract compaction service. Implementations own trigger policy, retention, and summarization, and may consume a separate measurement service. A successful run replaces the selected surface span with one summary node and prevents concurrent compaction of the same session. Load one implementation per context as `ctx.compact`. ```ts cordis-catalog +/** + * Check token pressure and compact if the conversation is too large. + * Estimate the next request, including its session prefix, derived history, + * and system prompt. Above threshold, compact a head-anchored range ending at + * a balanced tool boundary and reconsolidate any prior automatic checkpoint. + * Return `null` when no compaction is needed or an open tail leaves no safe + * cutoff. A single oversized retained unit or prefix cannot be repaired here. + * + * @param agent - agent context owning the session surface and model options. + * @param fullSystemPrompt - assembled system prompt, counted toward the estimate. + * @param sessionPrefix - the instance's composed session prefix, counted toward the + * estimate. + * @param signal - cancellation signal; model-backed implementations must forward it. + * @returns the compaction result, or `null` if no compaction was needed. + */ abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise + +/** + * Forcibly compact a range of surface nodes into a single summary node. + * `start` and `end` name an inclusive span by surface position, not numeric seq + * order; replacements can make visible seqs non-monotonic. Both edges must be + * balanced so assistant tool calls remain paired with their results. A model- + * backed implementation forwards cancellation and rejects active, missing, + * reversed, or unbalanced ranges. The target session is `agent.session`. + * Use {@link toolPairingBalancedBefore} and {@link toolPairingBalancedAfter} + * for the edge checks. + * + * @param start - first surface seq, inclusive. + * @param end - last surface seq, inclusive. + * @param agent - context whose session is mutated and whose routing options guide summarization. + * @param signal - optional cancellation; model-backed implementations must forward it. + * @throws when compaction is active or the range is missing, reversed, or unbalanced. + * @returns the appended event seqs, summary, replaced range, and token accounting. + */ abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` @@ -135,13 +373,90 @@ Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/comp Abstract filesystem provider. Targets must preserve identity across aliases; reads expose regular UTF-8 text or typed errors, listings are stable and content-free, and mutations are atomic. Optional guards add stale protection without changing the unguarded provider contract. ```ts cordis-catalog +/** + * Resolve a model/plugin-supplied path into a stable {@link FsTarget}. May perform I/O (a + * remote/sandboxed backend may need a round-trip to map a path to a stable identity), hence + * async even though the local backend only normalizes + realpaths. + * + * @param path - the path to resolve; relative paths resolve against `opts.cwd`. + * @param opts - optional cwd override and cancellation signal. + * @returns the stable target; the same file yields the same `targetKey`. + */ abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise + +/** + * Return target metadata, or `undefined` when the target does not exist. + * @param target - the resolved target to stat. + * @param signal - aborts the metadata round-trip. + * @returns metadata only, never content; undefined for an absent target. + */ abstract stat(target: FsTarget, signal?: AbortSignal): Promise + +/** + * Return path metadata without following the final path component when it is a + * symbolic link. This is intentionally path-shaped, not target-shaped: + * {@link resolve} follows symlinks to produce the stable identity used by + * normal reads/writes, while `lstat` lets a consumer reject the path itself + * before that follow happens. + * + * `opts.cwd` follows {@link resolve}'s cwd rules. `undefined` means the path is + * absent. + * @param path - the path to inspect; relative paths resolve against `opts.cwd`. + * @param opts - `cwd` overrides the backend's default base for relative paths. + * @param signal - aborts the metadata round-trip. + * @returns metadata only, never content; undefined for an absent path. + */ abstract lstat(path: string, opts?: { cwd?: string }, signal?: AbortSignal): Promise + +/** + * Read the whole regular text file as a single decoded string. + * @param target - the resolved target to read. + * @param signal - aborts the read. + * @returns the full decoded UTF-8 content. + */ abstract readText(target: FsTarget, signal?: AbortSignal): Promise + +/** + * Stream the whole regular text file as decoded text chunks (same text + * semantics as {@link readText}, for large files). The backend owns + * cross-chunk UTF-8 decoding and binary rejection so the policy layer never + * touches raw bytes. + * @param target - the resolved target to read. + * @param signal - aborts the stream, including between chunks. + * @returns the chunk iterable, decoded and validated like {@link readText}. + */ abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> + +/** + * List direct children of a directory in stable name order. Returns resolved + * child targets plus cheap metadata only; never reads file contents. + * @param target - the resolved directory target. + * @param signal - aborts the listing. + * @returns one entry per direct child, in stable name order. + */ abstract listDir(target: FsTarget, signal?: AbortSignal): Promise + +/** + * Atomically create or replace UTF-8 text. `expected` guards intent and + * staleness; omission allows unconditional overwrite. + * @param target - the resolved target to write. + * @param content - the full new file content. + * @param expected - the write intent guarding the write; omit for unconditional. + * @param signal - aborts before the atomic rename takes effect. + * @returns the outcome, including the version the write produced. + */ abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise + +/** + * Atomically edit literal text. When supplied, the version guard is checked + * before matching so stale content reports `FS_STALE_VERSION`; omission edits + * the current content without a freshness precondition. + * @param target - the resolved target to edit. + * @param edit - the literal search/replace request. + * @param expected - the version guard; omit for an unconditional edit. + * @param signal - aborts before the atomic rename takes effect. + * @returns the outcome, including the version the edit produced. + */ abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise ``` @@ -154,9 +469,39 @@ Source: [`packages/fs/fs/src/index.ts:80`](../../packages/fs/fs/src/index.ts) The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. ```ts cordis-catalog +/** + * Register an adapter for the given provider routes. Throws `LlmError` with code + * `DUPLICATE_ADAPTER` if any provider already has an adapter (all-or-nothing). + * Disposed with the fiber. + * @param providers - every provider route this adapter should serve. + * @param adapter - the adapter that streams calls for those providers. + * @returns the disposer that unregisters all of them. + */ registerAdapter(providers: string[], adapter: LlmAdapter): () => void + +/** + * Describe provider routes with a registered adapter. + * @returns detached provider metadata in registration order. + */ listProviders(): LlmProviderInfo[] + +/** + * Discover models advertised by one registered provider. Catalog membership + * is advisory and never changes routing or request validation. + * @param provider - registered provider route to inspect. + * @returns detached model metadata in adapter-preferred order. + */ async listModels(provider: string): Promise + +/** + * Stream one model call as raw chunks (token-level deltas). Throws + * `LlmError` with code `NO_ADAPTER` if no adapter is registered for + * `options.provider`. Replay state is retained only when the same adapter + * instance owns its historical provider and the target provider. Dispatches + * through the `llm/stream` waterfall. + * @param options - the full request; `options.provider` selects the adapter. + * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. + */ stream(options: GenerateOptions): AsyncIterable ``` @@ -169,9 +514,38 @@ Source: [`packages/llm/llm/src/index.ts:94`](../../packages/llm/llm/src/index.ts Owns the deployment's permission presets and their write path. Requires a confining `ctx.bash` executor and `ctx.approval`; unmatched knob values are reported as CUSTOM_PRESET, not an error. ```ts cordis-catalog +/** + * Resolve the preset matching the effective knob values. A still-matching + * last selection wins shared-bundle ties; otherwise the first table match + * wins, or {@link CUSTOM_PRESET} when no entry matches. + * @param events - the session's events in log order. + * @returns the effective preset name, or `custom` when nothing matches. + */ current(events: readonly SessionEvent[]): string + +/** + * Resolve a preset's knob bundle. + * @param name - the preset name to resolve. + * @returns the configured bundle. + * @throws when `name` is not in the table. + */ resolve(name: string): PresetSpec + +/** + * Build the client option for a table entry or {@link CUSTOM_PRESET}. A + * missing label falls back to the table key. + * @param name - a table key, or `custom`. + * @returns the option a client renders. + * @throws when `name` is neither a table key nor `custom`. + */ optionOf(name: string): PresetOption + +/** + * Record a changed preset, then update each changed knob through its own + * setter. Selecting the effective preset again appends nothing. + * @param session - the session the switch belongs to. + * @param name - the preset to switch to; unknown names throw. + */ set(session: Session, name: string): void ``` @@ -184,6 +558,17 @@ Source: [`packages/ui/permission/src/index.ts:94`](../../packages/ui/permission/ Abstract process-sandbox service. confine must return enforcing argv or fail closed at wrap or runner-execution time; silent unconfined passthrough is forbidden. Functional probes arbitrate multi-runner chains and may be skipped for a sole candidate, whose own refusal remains the fail-closed end. ```ts cordis-catalog +/** + * Wrap `argv` so it executes confined under `policy` on this host; the + * caller spawns the returned argv in place of its own. + * @param argv - the exact argv the caller is about to spawn (program plus + * arguments), NOT a shell string — a shell-shaped consumer passes + * `['bash', '-c', command]`. + * @param policy - the file-effect policy this execution runs under, + * carried per call (see {@link SandboxPolicy}). + * @returns the argv to spawn instead, plus the enforcement completeness + * the selected backend achieves for it. + */ abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv ``` @@ -196,10 +581,49 @@ Source: [`packages/sandbox/sandbox/src/index.ts:111`](../../packages/sandbox/san Durable append-only session storage. Implementations preserve contiguous, losslessly JSON-serializable events; append resolves only after durability, and load balances a complete interrupted tail without rewriting committed events. ```ts cordis-catalog +/** + * Resolve this backend's independent local artifact for a session without + * reading, creating, flushing, or otherwise materializing it. Backends such + * as SQLite that do not own one artifact per session return `undefined`. + * @param meta - the immutable session header whose artifact is requested. + * @returns the backend-specific absolute location, when one exists. + */ abstract locate(meta: SessionHeader): SessionLocation | undefined + +/** + * Register a new session's metadata. A backend MAY defer the physical write + * until the first {@link append} (lazy materialization), in which case a + * created-but-never-appended session is absent from {@link list} + * — abandoned sessions leave nothing behind. + * @param meta - the immutable header (id, version, cwd, lineage) to record. + */ abstract create(meta: SessionHeader): Promise + +/** + * Durably persist a batch of events (called from the write-behind drain at + * the `session/flush` checkpoint). Honors the append-only and contiguous-seq + * contracts: the first event's `seq` MUST equal the stored next-seq (after + * `load` has durably closed any interrupted turn). Rejects non-JSON- + * serializable `event.data` with an error naming the offending event type. + * @param id - the session the batch belongs to. + * @param events - the contiguous batch to persist, in seq order. + */ abstract append(id: SessionId, events: readonly SessionEvent[]): Promise + +/** + * Load a header and balanced contiguous log. A complete interrupted final + * turn is preserved and durably closed with missing tool errors plus any open + * step and turn boundaries; only a torn final record is discarded. Unknown + * versions and corruption in the committed prefix reject. + * @param id - the persisted session to reload. + * @returns the header and a log ending on a balanced `turn/end`. + */ abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> + +/** + * Lightweight listing from metadata, without a full-log parse. + * @returns one header per materialized session. + */ abstract list(): Promise ``` @@ -212,10 +636,40 @@ Source: [`packages/session-persistence/session-persistence/src/index.ts:42`](../ Live-preferred logical-corpus exact-read and relationship-tracing service. ```ts cordis-catalog +/** + * List the complete logical corpus using live-preferred records. + * @returns deterministic newest-first cloned session records. + */ listSessions(): Promise + +/** + * List lightweight raw-log event records for one logical session. + * @param sessionId - live-preferred session id to read. + * @returns event records in ascending seq order. + */ async listEvents(sessionId: SessionId): Promise + +/** + * Trace known ancestry and descendants from one corpus observation. + * @param sessionId - logical session id to trace. + * @returns a complete lineage or an explicit unresolved parent boundary. + * @throws when corpus resolution fails, the target is absent, or its known ancestry cycles. + */ async traceSession(sessionId: SessionId): Promise + +/** + * Trace one event's direct positional and provenance relationships. + * @param request - target session id and event seq. + * @returns direct links plus the target's positional replacement chain. + * @throws when source resolution fails, the target is absent, or surface/provenance validation fails. + */ async traceEvent(request: SessionEventTraceRequest): Promise + +/** + * Read one full event plus a bounded raw-log context window. + * @param request - target session/seq and context sizes. + * @returns cloned target and neighboring events. + */ async readEvent(request: SessionEventReadRequest): Promise ``` @@ -228,13 +682,119 @@ In-memory session store (`ctx.sessions`). Persistence is intentionally not implemented here — persistence plugins subscribe to `session/event` and flush on `session/flush` / dispose. ```ts cordis-catalog +/** + * Create a session owned by the calling fiber: disposing that fiber stops + * event notification and removes the session from the store. `options.seed` + * populates the session with a copy of those events (replay/fork); + * `options.meta` attaches creation metadata (validated absolute `cwd`, + * `parentSession` lineage) as the immutable {@link SessionHeader} (the store + * fills `version`/`id`/`createdAt`). + * + * For an agent whose session must be torn down IN ORDER with its loop (so the + * loop's final flush is captured before the store attachment ends), do NOT use this + * — fold the session lifecycle into the agent's own effect via + * {@link prepare} + {@link enter} + {@link announce} (see + * `dsh-agent-loop`'s creation transaction). + * + * @param id - the session id; omitted, the store mints `session-`. + * @param options - seed events and/or creation metadata for the header. + * @returns the live session, already entered and announced. + * @throws if a session with `id` already exists, metadata is not a plain + * lossless-JSON record with valid scalar fields, or `meta.cwd` is a + * non-absolute path (storage backends key directories off it). + */ create(id?: SessionId, options?: CreateSessionOptions): Session + +/** + * Build a session WITHOUT entering it into the store — validate the id/cwd and + * construct the {@link Session} (with its immutable {@link SessionHeader}). + * Pairs with {@link enter} + {@link announce}: a caller that owns a composite + * `ctx.effect` (the agent factory) folds the session lifecycle into that ONE + * effect so a fiber unload tears the session + agent down as a single ORDERED + * chain rather than as racing sibling effects — which would remove the publication hooks + * before the loop's closing `session/flush`, dropping the closing events. + * + * @param id - the session id; omitted, the store mints `session-`. + * @param options - seed events and/or creation metadata for the header. + * @returns the constructed session, NOT yet in the store. + * @throws if a session with `id` already exists, metadata is not a plain + * lossless-JSON record with valid scalar fields, or `meta.cwd` is a + * non-absolute path. + */ prepare(id?: SessionId, options?: CreateSessionOptions): Session + +/** + * Enter a {@link prepare}d session into the store: install the module-private + * append publication hooks and add it to the store. Returns the DETACH + * disposer (hooks + store removal). Does NOT emit `session/created` — + * the caller yields this disposer inside its effect and THEN calls + * {@link announce}, so a throwing `session/created` listener rolls the attach + * back instead of leaking it. + * + * Re-checks the id for a duplicate: `prepare` and `enter` are public + * cross-package primitives and a caller may interleave arbitrary work (or + * another create) between them, so a stale prepared session must NOT overwrite + * a live store entry of the same id — its detach disposer would later delete + * the REAL session. The {@link create} convenience and the agent factory call + * the two back-to-back so they never trip this, but the public seam cannot + * assume that. + * + * @param session - a {@link prepare}d session not yet in the store. + * @returns the detach disposer (publication hooks + store removal). When called from + * a synchronous `session/created` listener, removal and disposal wait until + * that creation dispatch unwinds. + * @throws if a session with this id is already in the store. + */ enter(session: Session): () => void + +/** Emit `session/created` exactly once for an {@link enter}ed session (with + * the carrier {@link enter} captured). Separate from {@link enter} so the + * caller can yield the detach disposer first (rollback safety — see + * {@link enter}). + * @param session - the entered session to announce to listeners. + * @throws if the session is not live or its announcement already began, + * including a reentrant call from a creation listener. */ announce(session: Session): void + +/** + * Dispatch the awaited `session/flush` durability checkpoint for `session`, + * with the carrier captured at {@link enter}. THE flush entry point: the + * store owns the carrier, so callers (the loop's turn-end checkpoint, idle + * injection, teardown drains) must come through here rather than dispatch a + * raw `ctx.parallel('session/flush', …)` — one owner, one spelling, and the + * scoped-dispatch invariant can pin it. + * @param session - the session whose buffered events must reach durable storage. + * @returns resolves when every flush listener has settled; after all settle, + * rejects with the first registered listener failure if any listener failed. + */ async flush(session: Session): Promise + +/** + * Look up a live session. + * @param id - the session id to look up. + * @returns the session, or undefined when no live session has that id. + */ get(id: SessionId): Session | undefined + +/** + * All live sessions, in creation order. + * @returns a fresh array; mutating it does not affect the store. + */ list(): Session[] + +/** + * Create a live child session from a turn-enclosed prefix of a live source. + * `boundary` is an inclusive source event seq; omitted means the source's + * current last event. A non-empty selected slice must end at `turn/end`. + * + * @param source - Live source session object or id. + * @param boundary - Inclusive source event seq to fork through; omitted means + * the source's current last event, and omitted on an empty source forks an + * empty child. + * @param childSessionId - Optional child session id; omitted delegates to + * `SessionStore`'s id policy. + * @returns The created live child session. + */ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` @@ -245,9 +805,42 @@ Source: [`packages/core/session/src/index.ts:577`](../../packages/core/session/s Registry of skill providers. It merges provider catalogs with stable first-wins duplicate handling, exposes sorted model-visible summaries, and loads full skill bodies on demand. ```ts cordis-catalog +/** + * Register a borrowed same-process provider synchronously during plugin apply. Duplicate and + * reserved names throw; remote initialization belongs in `list()`. Fiber disposal unregisters + * the provider and invalidates catalog caches. + * @param provider - the provider to register by `provider.name`. + * @returns the exact Cordis effect disposer that unregisters this provider; + * composite effects may yield it directly to preserve teardown ordering. + */ registerProvider(provider: SkillProvider): () => void + +/** + * Register a borrowed readonly runtime skill. Project entries outrank runtime entries, which + * outrank user entries. Same-name runtime entries are first-wins; a duplicate logs a warning and + * receives a no-op disposer so it cannot remove the winner. + * @param skill - the complete skill definition to expose for discovery. + * @returns the exact Cordis effect disposer, preserving composite teardown order and invalidating caches. + */ register(skill: SkillRegistration): () => void + +/** + * List model-invocable skill summaries for a workspace. Lookup options and + * provider candidates are readonly same-process values borrowed throughout + * discovery. + * @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery. + * @returns sorted summaries, excluding skills disabled for model invocation. + */ async list(options: SkillLookupOptions = {}): Promise + +/** + * Load and validate the winning candidate, passing its opaque discovery locator back to the + * provider. Cancellation is rechecked after selection, including cache hits, and raced against + * loading so an uncooperative provider cannot hang the caller. + * @param name - kebab-case skill name. + * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work. + * @returns the full skill, including body content, or `undefined`. + */ async get(name: string, options: SkillLookupOptions = {}): Promise ``` @@ -264,6 +857,11 @@ Semantics every implementation must honor: - `saveText` REJECTS on a real storage failure (permissions, ENOSPC, backend unavailable); the caller decides how to degrade (the spill policy treats a rejection as best-effort and keeps the inline result). ```ts cordis-catalog +/** + * Persist `input.content` to a session-scoped spill artifact. + * @param input - the owner, provenance, suggested name, and full text to save. + * @returns the saved artifact's {@link SpillRef}; rejects on a storage failure. + */ abstract saveText(input: SaveTextSpill): Promise ``` @@ -274,9 +872,37 @@ Source: [`packages/spill/spill/src/index.ts:45`](../../packages/spill/spill/src/ Named provider registry and capability-checked start surface. ```ts cordis-catalog +/** + * Register a provider under its name. Registration is effect-scoped and HMR + * safe; removing a provider blocks new starts but does not revoke runs that + * were already returned to their holders. + * @param provider - the trusted provider implementation. + * @returns the exact Cordis effect disposer. + */ registerProvider(provider: SubagentProvider): () => void + +/** + * Look up a provider by name. + * @param name - the provider name. + * @returns the provider, or undefined when absent. + */ getProvider(name: string): SubagentProvider | undefined + +/** + * List registered provider names in insertion order. + * @returns the registered names. + */ list(): string[] + +/** + * Establish a ready child on the named provider. Capability and semantic + * checks run before delegation. Provider ownership lasts until its promise + * fulfills; a rejection therefore has no run for the caller to dispose and + * emits no run lifecycle events. + * @param name - the provider to use. + * @param request - child prompt, parent, signal, and optional capabilities. + * @returns the ready holder-owned run. + */ async start(name: string, request: SubagentStartRequest): Promise ``` @@ -287,9 +913,42 @@ Source: [`packages/subagent/subagent/src/index.ts:153`](../../packages/subagent/ Registry service for the prompt inputs assembled before each model step. ```ts cordis-catalog +/** + * Register an ordered prompt section in the calling context's scope. A scoped + * section shadows a global section with the same name; duplicates within one + * layer and non-finite orders throw. Registration and disposal emit + * `system-prompt/change`. + * @param section - the section to register. + * @returns the exact Cordis effect disposer. + */ section(section: PromptSection): () => void + +/** + * Register a tool-schema provider in the calling context's scope. Global and + * matching scoped providers both contribute; returning the reserved + * {@link TOOL_ORDER_REST} name makes assembly fail. + * @param provider - evaluated for each assembly with its context. + * @returns the exact Cordis effect disposer. + */ tools(provider: (context: AssembleContext) => ToolProviderResult): () => void + +/** + * Register a prompt variable in the calling context's scope. Scoped values + * shadow globals; invalid or duplicate names throw. A provider may return + * `undefined`, but rendering a section that references that value then fails. + * @param name - the `[a-z][a-z0-9_]*` reference name. + * @param provider - evaluated for each assembly. + * @returns the exact Cordis effect disposer. + */ variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void + +/** + * Assemble global and scoped providers, detach tool parameters, apply + * canonical ordering, then run the assembly waterfall. Scoped sections and + * variables shadow globals; the returned waterfall value is authoritative. + * @param context - the optional scope and plugin-defined assembly fields. + * @returns the authoritative post-waterfall assembly. + */ async assemble(context: AssembleContext = {}): Promise ``` @@ -300,13 +959,83 @@ Source: [`packages/core/system-prompt/src/index.ts:209`](../../packages/core/sys The `tasks` service: the runtime-global background task registry. See the module doc for the ownership, isolation, and lifecycle contracts. ```ts cordis-catalog +/** + * Preflight access, validation, and owner cleanup before starting and + * atomically registering work. A throwing starter leaves nothing registered; + * after it returns, registration cannot fail. Settlement records the outcome, + * notifies listeners, and releases waiters. + * @param spec - task identity, owner, and synchronous starter. + * @returns the registry-issued `-N` id. + */ start(spec: TaskStart): TaskId + +/** + * List caller-owned and unowned tasks in registration order without exposing + * another session's labels. + * @param caller - reading agent; a non-agent caller sees only unowned tasks. + * @returns fresh snapshots. + */ list(caller?: Agent): TaskSnapshot[] + +/** + * Return a non-consuming snapshot without changing its read cursor or notice + * state. Throws for an unknown or foreign task. + * @param id - task to look up. + * @param caller - reading agent checked against the owner. + * @returns a fresh snapshot. + */ get(id: TaskId, caller?: Agent): TaskSnapshot + +/** + * Read the next stream delta, or the idempotent final output after settlement. + * A terminal read marks the task reported. Throws for an unknown or foreign + * task. + * @param id - task to read. + * @param caller - reading agent checked against the owner. + * @returns output text and the post-read snapshot. + */ read(id: TaskId, caller?: Agent): TaskRead + +/** + * Request cancellation, then mark the task stopping and reported. A producer + * throw propagates without changing task state. Throws for an unknown or + * foreign task. + * @param id - task to cancel. + * @param caller - killing agent checked against the owner. + * @param reason - logged reason forwarded to the producer. + * @returns `requested` for live work, otherwise `already-finished`. + */ kill(id: TaskId, caller?: Agent, reason?: string): 'requested' | 'already-finished' + +/** + * Wait for settlement or timeout without cancelling the task. Caller abort + * rejects only while the task is live; after settlement it returns the + * terminal snapshot so a notice suppressed for this waiter is still delivered. + * Timed-out and aborted waits detach their resolvers. Throws for invalid, + * unknown, or foreign input. + * @param id - task to wait for. + * @param timeoutMs - positive finite wait bound in milliseconds. + * @param caller - waiting agent checked against the owner. + * @param signal - optional cancellation of the wait itself. + * @returns snapshot at settlement or timeout. + */ async wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSignal): Promise + +/** + * Register an effect-scoped completion listener. Each listener is contained; + * returned promises are observed but not awaited. No listener runs after + * service disposal. + * @param listener - receives each terminal snapshot and its exact owner. + * @returns disposer that unregisters the listener. + */ onTaskDone(listener: TaskDoneListener): () => void + +/** + * Attach an effect-scoped surface that can read and stop tasks. {@link start} + * refuses work while none is attached. + * @param name - diagnostic label; duplicate names remain independent. + * @returns disposer that detaches this surface. + */ attachSurface(name: string): () => void ``` @@ -319,7 +1048,29 @@ Source: [`packages/tasks/tasks/src/index.ts:76`](../../packages/tasks/tasks/src/ Replay owner for one service-wide estimator and isolated per-session folds. ```ts cordis-catalog +/** + * Measure current request pressure and surface through the durable tail. + * + * Provider usage is reused only when the latest successful call's canonical + * request envelope matches `requestHeader` and its total is no lower than + * that call's full heuristic anchor; otherwise the complete envelope and + * surface are heuristically repriced. + * + * `requestHeader` affects request pressure only; surface fields always + * describe the current session surface. Every call clones those positional + * nodes, so measurement is O(surface). + * + * @param session - session to replay through its current durable tail. + * @param requestHeader - optional effective request envelope replacing the latest logged header. + * @returns a detached deeply immutable pressure and surface measurement. + */ measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement + +/** + * Heuristically price one model-visible message. + * @param message - message to price without mutation. + * @returns content and role-framing tokens under the fixed service heuristic. + */ estimateMessage(message: Message): number ``` @@ -332,12 +1083,72 @@ Source: [`packages/llm/token-meter/src/index.ts:106`](../../packages/llm/token-m Tool registry and execution pipeline. Scoped registrations shadow globals; one visibility resolver feeds presentation, lookup, and dispatch. ```ts cordis-catalog +/** + * Register globally or in the calling agent scope. Scoped tools shadow + * globals; duplicates within one layer and the reserved `run_code` name fail. + * @param definition - the tool schema, execution, and optional presentation functions. + * @returns the exact disposer that unregisters the tool. + */ register(definition: ToolDefinition): () => void + +/** + * Restrict global tools for the calling agent scope. Empty filters, unknown + * names, scope-local names, and reserved transport names fail. Restrictions + * intersect; scoped registrations remain visible. + * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove). + * @returns the exact disposer that lifts this restriction. + */ restrict(filter: ToolRestriction): () => void + +/** + * Register a monotonic guard after the extensible `tools/pre-execute` + * waterfall. A plain-context guard applies globally; one registered through + * `agent.ctx` applies only to that agent. Any matching guard may deny by + * returning a reason, while no guard can force-allow a call another guard + * denied. The exact effect disposer is returned for ordered ownership and + * HMR cleanup. + * @param guard - synchronous check; a returned string denies the execution. + * @returns the exact disposer that unregisters the guard. + */ guard(guard: ToolGuard): () => void + +/** + * Look up a tool as one scope sees it (scoped + * shadows global; a restricted-away global reads as absent). Presenters pass + * the calling agent so the rendered card matches the definition that + * actually executed. + * @param name - the tool name as registered. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns the definition the scope resolves, or undefined when none is visible. + */ get(name: string, scope?: ScopeKey): ToolDefinition | undefined + +/** + * Project visible definitions onto the allowlisted model-facing schema fields, + * excluding execution and presentation callbacks. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns one deep-cloned schema per visible tool. + */ schemas(scope?: ScopeKey): ToolSchema[] + +/** + * Classify a pending call through the caller's visible tool definition. Only + * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or + * throwing classifiers are exclusive. + * @param exec - call name, parsed arguments, and optional agent scope. + * @returns the fail-closed scheduling mode. + */ executionMode(exec: ToolExecutionInput): ToolExecutionMode + +/** + * Execute through pre-policy, guards, around-dispatch, post-policy, and final + * notification. Tool and listener failures resolve as materialized error + * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is + * the same lossless, frozen snapshot final observers receive. + * @param exec - the typed same-process call input. The registry assigns its + * correlation token before policy begins. + * @returns the materialized final result. + */ async execute(exec: ToolExecutionInput): Promise ``` @@ -350,7 +1161,20 @@ Source: [`packages/core/tools/src/index.ts:438`](../../packages/core/tools/src/i `ctx.userInteraction`: one active UI provider plus an `ask()` surface. ```ts cordis-catalog +/** + * Register the UI provider. Only one provider may be active in a context. + * + * @param provider UI-side implementation that collects answers. + * @returns Disposer that unregisters this provider. + */ registerProvider(provider: UserInteractionProvider): () => void + +/** + * Ask the active UI provider and wait for the user's answer. + * + * @param request Questions, owner agent, and abort signal. + * @returns The answer chosen or typed by the human. + */ async ask(request: AskUserQuestionRequest): Promise ``` @@ -370,9 +1194,43 @@ Selection semantics (resolved at execution time, never order-dependent): - No id configured, no usable provider → `WEB_PROVIDER_UNAVAILABLE`. ```ts cordis-catalog +/** + * Register a search provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER` + * if its id is already registered for search. Returns a disposer; disposed + * with the calling fiber. + * @param provider - the provider; its `id` is the registry key. + * @returns the disposer that unregisters the provider. + */ registerSearchProvider(provider: WebSearchProvider): () => void + +/** + * Register a fetch provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER` + * if its id is already registered for fetch. Returns a disposer; disposed + * with the calling fiber. + * @param provider - the provider; its `id` is the registry key. + * @returns the disposer that unregisters the provider. + */ registerFetchProvider(provider: WebFetchProvider): () => void + +/** + * Run one search through the selected provider. Resolves the provider at call + * time with the selection rules above; throws {@link WebError} when the + * capability cannot run. The seam enforces `request.maxResults` on the result: + * if the provider over-returns, `sources[]` is truncated and `truncated` set. + * @param request - the query plus result-shaping options. + * @param signal - optional cancellation signal forwarded to the provider. + * @returns the provider's results, capped to `request.maxResults`. + */ async search(request: WebSearchRequest, signal?: AbortSignal): Promise + +/** + * Retrieve one URL through the selected provider. Resolves the provider at + * call time with the selection rules above; throws {@link WebError} when the + * capability cannot run. A non-2xx response is a result, not a throw. + * @param request - the URL plus retrieval options. + * @param signal - optional cancellation signal forwarded to the provider. + * @returns the retrieval outcome; non-2xx responses resolve descriptively. + */ async fetch(request: WebFetchRequest, signal?: AbortSignal): Promise ``` @@ -383,6 +1241,12 @@ Source: [`packages/web/web/src/index.ts:74`](../../packages/web/web/src/index.ts Workflow execution seam. Invalid requests throw before publication; a live run is holder-owned, its result never rejects, cancellation and disposal are bounded, and disposal waits for child cleanup within that bound. Lifecycle listener failures are contained, and `workflow/end` fires exactly once as the result settles. ```ts cordis-catalog +/** + * Parse and execute a workflow script. + * @param request - the script, its `args`, the parent agent, and an + * optional cancel signal. + * @returns the live run; its `result` resolves when the script settles. + */ abstract start(request: WorkflowStartRequest): WorkflowRun ``` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 9efe04e63c..ac2440cd7c 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -403,49 +403,9 @@ interface Agent { The [event taxonomy](../architecture.md#event) owns the `agent/*` lifecycle, checkpoint, and waterfall contracts. Turn and step boundaries are durable session events rather than agent emits. -## Agent execution context +## Initiating Agent -`AgentExecution` is the process-local ambient frame established around a concrete driver's lifetime. It holds the exact Agent object rather than duplicating Session or step state; ambient presence is neither liveness proof nor authorization. - -Source: [`packages/core/agent-execution/src/types.ts`](../../packages/core/agent-execution/src/types.ts) - -```ts type-equiv -interface AgentExecution { - readonly agent: Agent -} -``` - -The mandatory service reads, requires, establishes, or explicitly clears that frame. `run()` preserves the operation's exact synchronous value or Promise. - -Source: [`packages/core/agent-execution/src/index.ts`](../../packages/core/agent-execution/src/index.ts) - -```ts type-equiv -interface AgentExecutionService { - /** - * Read the active execution without requiring one. - * @returns the inherited execution, or `undefined` outside/inside a cleared boundary. - * @throws when this service instance has been disposed. - */ - current(): AgentExecution | undefined - - /** - * Read the active execution and fail when no boundary is active. - * @returns the inherited execution. - * @throws when no execution is active or this service instance has been disposed. - */ - require(): AgentExecution - - /** - * Run an operation inside an execution boundary. Passing `undefined` clears - * an inherited execution; the exact synchronous value or Promise is returned. - * @param execution - execution to inherit, or `undefined` for a clearing boundary. - * @param operation - synchronous or asynchronous operation to invoke. - * @returns the exact value returned by `operation`. - * @throws when this service is closing/disposed, or when `operation` throws. - */ - run(execution: AgentExecution | undefined, operation: () => T): T -} -``` +The process-local initiator carried by `ctx.agents` is the exact `Agent` above, not a separate frame or copied identity. Ambient presence is neither liveness proof nor authorization; the [initiator-scope decision](../rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns its lifetime and boundary rules. ## Interception decisions diff --git a/docs/module-graph.md b/docs/module-graph.md index c65b31a6fc..edb6034216 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -22,7 +22,6 @@ flowchart TD end subgraph group_core["packages/core"] pkg_agent["agent"] - pkg_agent_execution["agent-execution"] pkg_agent_loop["agent-loop"] pkg_scope["scope"] pkg_session["session"] @@ -194,7 +193,6 @@ flowchart TD pkg_llm_replay --> pkg_session pkg_sandbox_local --> pkg_llm pkg_sandbox_local --> pkg_sandbox - pkg_agent_execution --> pkg_agent pkg_bash_local --> pkg_bash pkg_bash_local --> pkg_timeout pkg_compact_basic --> pkg_agent @@ -248,7 +246,6 @@ flowchart TD pkg_permission --> pkg_session pkg_permission --> pkg_user_approval pkg_agent_loop --> pkg_agent - pkg_agent_loop --> pkg_agent_execution pkg_agent_loop --> pkg_llm pkg_agent_loop --> pkg_scope pkg_agent_loop --> pkg_session @@ -311,7 +308,6 @@ flowchart TD pkg_hooks_codex --> pkg_session_persistence pkg_hooks_codex --> pkg_tools pkg_agent_loop_testkit --> pkg_agent - pkg_agent_loop_testkit --> pkg_agent_execution pkg_agent_loop_testkit --> pkg_llm pkg_agent_loop_testkit --> pkg_session pkg_agent_loop_testkit --> pkg_system_prompt @@ -390,7 +386,6 @@ flowchart TD pkg_tui --> pkg_tools pkg_tui --> pkg_user_interaction pkg_agent_spine_demo --> pkg_agent - pkg_agent_spine_demo --> pkg_agent_execution pkg_agent_spine_demo --> pkg_agent_loop pkg_agent_spine_demo --> pkg_home pkg_agent_spine_demo --> pkg_invariants @@ -481,7 +476,6 @@ flowchart TD | [`session-persistence`](../packages/session-persistence/session-persistence) | `session-persistence` | [`session`](../packages/core/session) | | [`llm-replay`](../packages/support/llm-replay) | `support` | [`llm`](../packages/llm/llm), [`session`](../packages/core/session) | | [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) | -| [`agent-execution`](../packages/core/agent-execution) | `core` | [`agent`](../packages/core/agent) | | [`bash-local`](../packages/bash/bash-local) | `bash` | [`bash`](../packages/bash/bash), [`timeout`](../packages/util/timeout) | | [`compact-basic`](../packages/compact/compact-basic) | `compact` | [`agent`](../packages/core/agent), [`compact`](../packages/compact/compact), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`token-meter`](../packages/llm/token-meter) | | [`spill-local`](../packages/spill/spill-local) | `spill` | [`spill`](../packages/spill/spill) | @@ -498,7 +492,7 @@ flowchart TD | [`tools`](../packages/core/tools) | `core` | [`agent`](../packages/core/agent), [`code-runtime`](../packages/code-runtime/code-runtime), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`user-approval`](../packages/ui/user-approval) | | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`sandbox`](../packages/sandbox/sandbox) | | [`permission`](../packages/ui/permission) | `ui` | [`bash`](../packages/bash/bash), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`user-approval`](../packages/ui/user-approval) | -| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`agent-execution`](../packages/core/agent-execution), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | +| [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`home`](../packages/util/home), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | @@ -510,7 +504,7 @@ flowchart TD | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | | [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools) | -| [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`agent-execution`](../packages/core/agent-execution), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | +| [`agent-loop-testkit`](../packages/support/agent-loop-testkit) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`workspace-context`](../packages/context/workspace-context) | `context` | [`agent`](../packages/core/agent), [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index 73d395af4b..16a5563532 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -163,7 +163,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | | [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 | -| [Agent execution context over AsyncLocalStorage](implemented/architecture/2026-07-15-agent-execution-context.md) | 2026-07-15 | +| [Initiating Agent scope over AsyncLocalStorage](implemented/architecture/2026-07-15-agent-initiator-scope.md) | 2026-07-15 | | [Advisory LLM catalogs and per-session ACP model selection](implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) | 2026-07-15 | | [Replay token meter service](implemented/architecture/2026-07-15-replay-token-meter-service.md) | 2026-07-15 | diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md deleted file mode 100644 index 2ea88cddf7..0000000000 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.md +++ /dev/null @@ -1,61 +0,0 @@ -# RFC: Agent execution context over AsyncLocalStorage - -Status: implemented - -English | [中文](2026-07-15-agent-execution-context.zh.md) - -## Problem - -The harness has two useful but different notions of context. A Cordis `Context` selects services, registration ownership, and lifetime; `agent.ctx` is the flat registration scope owned by one live Agent. Agent and Session identity instead describe the subject of an asynchronous operation. Changing a root `ctx.agent` to mean “whichever Agent is running” would conflate those meanings and fail when one process drives Agents concurrently. - -Deep process-local infrastructure sometimes needs a trusted initiating Agent below explicit loop, tool, and request parameters—for example, a host-aware transport, tracing helper, logger, or gateway client. Requiring every private helper to forward `agent` adds repetition, while a process-global mutable slot is incorrect across `await`. Model-visible arguments are unsuitable because a model must not choose a trusted Session or routing header. The carrier is mandatory control infrastructure rather than optional model-visible context. - -## Decision - -`@deepseek-ai/dsh-agent-execution` provides the mandatory `ctx.agentExecution` service using Node `AsyncLocalStorage`. The named `AgentExecution` frame contains only the exact Agent object; the [core-data catalog](../../../core-data-structures/core.md#agent-execution-context) owns the literal frame and service types. - -`current()` reads optionally, `require()` throws `no agent execution context is active`, and `run()` preserves the operation's exact synchronous value or Promise. `run(undefined, operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `execution.agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. - -`AgentLoop` injects the service and wraps each concrete driver's complete `runLoop` lifetime in `agentExecution.run({ agent }, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. - -Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. - -The provider uses an ordered composite effect. Teardown first rejects new boundaries, then removes the service and awaits injected dependents such as AgentLoop, then waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. `current()` and `require()` remain usable through a retained in-flight service reference while that drain runs; after disposal, retained calls throw `agent execution service is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting is required in addition to Cordis dependency ordering. - -`run()` does not own detached work: provider drain tracks only the Promise returned by `operation`. Asynchronous resources created inside the boundary inherit its store until they settle or ALS is disabled, so their owning seam must stop unreturned work explicitly. Agent-owned foreground work returns its lifetime and keeps its cancellation contract. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)`; queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation. - -A host-aware transport may derive a deployment-owned header such as `X-Harness-Session-Id` from `ctx.agentExecution.require().agent.session.id`; the header is absent from model-visible schema and arguments. No production MCP or Web transport adopts such a header in this decision. A test-double transport proves the trusted boundary without assigning host routing policy to an existing provider-neutral seam. - -This decision extends the [Agent registration-scope contract](2026-07-08-agent-scope-contexts.md) and its [runtime design](2026-07-12-agent-scope-runtime-design.md); it does not change their static `agent.ctx` meaning. - -## Verification - -Service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, missing-provider activation, service restart, and provider/root teardown. Composition, module-graph, build, and runtime-closure checks keep the provider wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses. - -Only a test-double host-aware transport consumes ambient identity; it derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by `operation`; that work remains subject to its owner's explicit stop contract. - -## Alternatives considered - -**Pass Agent through every function.** Public, worker, process, persistence, and wire boundaries continue to do this, but requiring every process-local private helper to carry Agent adds repetitive forwarding without improving trust. ALS is confined to the asynchronous chain inside those explicit boundaries. - -**Make `ctx.agent` dynamic.** `ctx.agent` already means the static Agent associated with an Agent-scoped Cordis context. Changing the root meaning would mix registration and execution scopes and make concurrent behavior surprising. - -**Store a complete mutable runtime frame.** Agent, Session, inbox, cancellation, turn, step, tool execution, and persistence already have authoritative owners. Duplicating them would create stale snapshots and another lifecycle. A named frame makes the execution-context boundary explicit without duplicating owner state. - -**Include a step `AbortSignal`, `cwd`, sandbox, or authorization.** Their lifetimes and authority do not match the driver boundary, and their existing seams already pass them explicitly. Adding a control capability requires a separate decision and nested lifecycle contract. - -**Use a process-global `currentAgent`.** Concurrent Agents and subagents overwrite one another across awaited continuations, so a mutable global is correct only under a serialization guarantee the harness does not make. - -**Derive identity from model-visible arguments.** Model or user input cannot be trusted to select Session, tenant, or sandbox routing. - -**Add routing identity to every capability seam.** That spreads hosting concerns through provider-neutral APIs. A host-aware implementation owns its transport header while public boundaries remain explicit. - -## Consequences - -Deep infrastructure gains one trusted process-local initiating Agent without widening existing tool and capability requests. Concurrent and nested drivers isolate automatically, AgentLoop stays inactive when the provider is absent, and HMR/root disposal reaches quiescence before ALS is disabled. - -The dependency is implicit in function signatures and carries a capability-bearing Agent object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries. - -The teardown design deliberately accepts Node's [Stability 1 (Experimental)](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) `AsyncLocalStorage.disable()` dependency. Node requires `disable()` before an ALS instance can be garbage-collected, which matters when HMR replaces provider-owned instances; the service state guard prevents a later `run()` from re-entering the instance after disposal. - -The frame deliberately omits turn, step, `signal`, `cwd`, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md deleted file mode 100644 index 1c4e0ba9c3..0000000000 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.zh.md +++ /dev/null @@ -1,61 +0,0 @@ -# RFC: 基于 AsyncLocalStorage 的 Agent 执行上下文 - -Status: implemented - -[English](2026-07-15-agent-execution-context.md) | 中文 - -## 问题 - -Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期；`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」，就会混淆这两种含义，并在单进程并发驱动多个 Agent 时失效。 - -进程内深层基础设施有时需要在显式传递的循环、工具及请求参数之下获取可信的发起 Agent，例如宿主感知传输层、追踪辅助函数、日志器或网关客户端。要求每个私有辅助函数都转发 `agent` 会造成重复，而进程级可变槽会在跨 `await` 时发生并发错误。模型可见参数也不适用，因为模型不得选择可信的会话或路由请求头。该载体属于必需的控制基础设施，而非模型可见的可选上下文。 - -## 决策 - -`@deepseek-ai/dsh-agent-execution` 使用 Node `AsyncLocalStorage` 提供必需的 `ctx.agentExecution` 服务。命名的 `AgentExecution` 帧仅包含同一个 Agent 对象；[核心数据目录](../../../core-data-structures/core.md#agent-execution-context)是帧与服务字面类型定义的真源。 - -`current()` 用于可选读取，`require()` 抛出 `no agent execution context is active`，`run()` 保留操作返回的同步值或 Promise 本身。`run(undefined, operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `execution.agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 - -`AgentLoop` 注入该服务，并用 `agentExecution.run({ agent }, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 - -隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 - -提供方使用有序复合 effect。teardown 会先拒绝新边界，再移除服务并等待 AgentLoop 等注入方排空，随后等待活动的返回 Promise 边界，最后调用 `AsyncLocalStorage.disable()`。排空期间，进行中代码可通过保留的服务引用继续调用 `current()` 和 `require()`；dispose 后，保留引用会抛出 `agent execution service is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown，因此除 Cordis 依赖顺序外还必须统计活动边界。 - -`run()` 不负责管理脱离返回链的工作：提供方排空只跟踪 `operation` 返回的 Promise。边界内创建的异步资源会继承其存储，直到自身结束或 ALS 被禁用；所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所有前台工作会把完整生命周期纳入返回值，并保留显式取消契约。无关的定时器、队列和部署基础设施在 `run(undefined, operation)` 下启动；队列、worker、进程和协议边界必须序列化身份，不能期待 ALS 传播。 - -宿主感知的传输层可以从 `ctx.agentExecution.require().agent.session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头；模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界，而不会把宿主路由策略分配给现有的提供方无关 seam。 - -本决策扩展 [Agent 注册作用域契约](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md)，不会改变其中 `agent.ctx` 的静态含义。 - -## 验证 - -服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、缺少提供方时的激活行为、服务重启，以及提供方或根 Context 的销毁流程。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 都装载提供方。 - -只有测试替身形式的宿主感知传输层消费隐式身份；它在内部推导 `X-Harness-Session-Id`，并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空 `operation` 返回的 Promise 之外的异步工作；这类工作仍由所属方的显式停止契约管理。 - -## 考虑过的替代方案 - -**在每个函数中传递 Agent。** 公开、worker、进程、持久化和协议边界继续显式传递，但要求每个进程内私有辅助函数都携带 Agent 只会造成重复转发，不会提高可信度。ALS 仅限于这些显式边界内部的异步调用链。 - -**让 `ctx.agent` 变成动态值。** `ctx.agent` 已经表示与 Agent 作用域 Cordis 上下文静态关联的 Agent。改变根上下文的含义会混合注册作用域与执行作用域，并让并发行为变得意外。 - -**保存完整的可变运行时帧。** Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。重复保存会产生陈旧快照和另一套生命周期。命名帧能够明确标识执行上下文边界，而不重复保存归属方状态。 - -**包含步骤级 `AbortSignal`、`cwd`、沙箱或授权。** 它们的生命周期及权限范围与驱动边界不一致，而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。 - -**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步延续执行之间相互覆盖，因此可变全局值只在 Harness 不具备的串行保证下才正确。 - -**从模型可见参数推导身份。** 不能信任模型或用户输入来选择会话、租户或沙箱路由。 - -**给每个能力 seam 增加路由身份。** 这会把宿主关注点扩散到提供方无关 API。宿主感知实现拥有其传输请求头，而公开边界继续显式传递身份。 - -## 后果 - -深层基础设施可以获得一个可信的进程内发起 Agent，而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离，缺少提供方时 AgentLoop 保持未激活，HMR 或根 Context dispose 会在禁用 ALS 前完成排空。 - -该依赖不会出现在函数签名中，并且携带一个具有控制能力的 Agent 对象。消费方必须将其限制在横切基础设施中，把隐式存在视为既不证明存活、也不授予权限，并保留显式取消和归属检查。ALS 还有常驻传播成本，也无法跨越 worker、进程、HTTP 或持久化队列边界。 - -该销毁设计有意依赖 Node 的 [Stability 1（实验性）](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) API `AsyncLocalStorage.disable()`。Node 要求在 ALS 实例可被垃圾回收前调用 `disable()`，这对 HMR 替换提供方所拥有的实例尤为重要；服务状态守卫会阻止 dispose 后通过后续 `run()` 重新进入该实例。 - -该帧有意省略轮次、步骤、`signal`、`cwd`、沙箱和授权。若真实消费方无法使用现有显式字段，必须另行论证扩展；陈旧字段最多只能误标遥测数据，绝不能授予控制权。 diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml similarity index 64% rename from docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml rename to docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml index 371884096a..9d9e11522f 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-execution-context.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-execution-context.md: 2ea88cddf7a686713157c77ce1d7520082a9da28 -2026-07-15-agent-execution-context.zh.md: 1c4e0ba9c3fa787dfa816eff4c5d04cff5c2f7b1 +2026-07-15-agent-initiator-scope.md: 480bb56f811567406e964ca94fca04fd3d4ace62 +2026-07-15-agent-initiator-scope.zh.md: 29ea3a47f42d607a4584b888ace232de124e7598 diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md new file mode 100644 index 0000000000..480bb56f81 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md @@ -0,0 +1,63 @@ +# RFC: Initiating Agent scope over AsyncLocalStorage + +Status: implemented + +English | [中文](2026-07-15-agent-initiator-scope.zh.md) + +## Problem + +The harness has two useful but different notions of context. A Cordis `Context` selects services, registration ownership, and lifetime; `agent.ctx` is the flat registration scope owned by one live Agent. Agent and Session identity instead describe the subject of an asynchronous operation. Changing a root `ctx.agent` to mean “whichever Agent is running” would conflate those meanings and fail when one process drives Agents concurrently. + +Deep process-local infrastructure sometimes needs a trusted initiating Agent below explicit loop, tool, and request parameters—for example, a host-aware transport, tracing helper, logger, or gateway client. Requiring every private helper to forward `agent` adds repetition, while a process-global mutable slot is incorrect across `await`. Model-visible arguments are unsuitable because a model must not choose a trusted Session or routing header. The carrier belongs to the Agent service rather than optional model-visible context. + +## Decision + +The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; the [core-data catalog](../../../core-data-structures/core.md#initiating-agent) identifies the carried type. + +`currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. + +`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. + +Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. + +`AgentRegistry` owns an ordered initiator lifecycle. Teardown first rejects new boundaries; removing `ctx.agents` then drains injected dependents such as AgentLoop, and the registry waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. `currentInitiator()` and `requireInitiator()` remain usable through a retained in-flight service reference while that drain runs; after disposal, initiator methods throw `agent initiator scope is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting remains necessary in addition to Cordis dependency ordering. + +Initiator scope does not own detached work: registry drain tracks only the Promise returned by `withInitiator()` or `withoutInitiator()`. Asynchronous resources created inside a boundary inherit its store until they settle or ALS is disabled, so their owning seam must stop unreturned work explicitly. Agent-owned foreground work returns its lifetime and keeps its cancellation contract. Unrelated timers, queues, and deployment infrastructure start under `withoutInitiator(operation)`; queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation. + +A host-aware transport may derive a deployment-owned header such as `X-Harness-Session-Id` from `ctx.agents.requireInitiator().session.id`; the header is absent from model-visible schema and arguments. No production MCP or Web transport adopts such a header in this decision. A test-double transport proves the trusted boundary without assigning host routing policy to an existing provider-neutral seam. + +This decision extends the [Agent registration-scope contract](2026-07-08-agent-scope-contexts.md) and its [runtime design](2026-07-12-agent-scope-runtime-design.md); it does not change their static `agent.ctx` meaning. + +## Verification + +Agent service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, AgentRegistry restart, and root teardown. Composition, module-graph, build, and runtime-closure checks keep `ctx.agents` wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses without another provider. + +Only a test-double host-aware transport consumes ambient identity; it derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by the boundary operation; that work remains subject to its owner's explicit stop contract. + +## Alternatives considered + +**Pass Agent through every function.** Public, worker, process, persistence, and wire boundaries continue to do this, but requiring every process-local private helper to carry Agent adds repetitive forwarding without improving trust. ALS is confined to the asynchronous chain inside those explicit boundaries. + +**Make `ctx.agent` dynamic.** `ctx.agent` already means the static Agent associated with an Agent-scoped Cordis context. Changing the root meaning would mix registration and execution scopes and make concurrent behavior surprising. + +**Add a separate `ctx.agentExecution` service.** The carrier has no independent backend, configuration, or identity type: it stores the same `Agent` that `ctx.agents` already owns, and AgentLoop already depends on that service. A second mandatory provider would add package, composition, lifecycle, generated-catalog, and test-harness wiring without separating a real capability. + +**Store a named or complete runtime frame.** A one-field `{ agent }` frame only wraps the value, while Agent, Session, inbox, cancellation, turn, step, tool execution, and persistence already have authoritative owners. Adding more fields would create stale snapshots and another lifecycle; carrying `Agent` directly keeps the boundary named by its methods without duplicating state. + +**Include a step `AbortSignal`, `cwd`, sandbox, or authorization.** Their lifetimes and authority do not match the driver boundary, and their existing seams already pass them explicitly. Adding a control capability requires a separate decision and nested lifecycle contract. + +**Use a process-global `currentAgent`.** Concurrent Agents and subagents overwrite one another across awaited continuations, so a mutable global is correct only under a serialization guarantee the harness does not make. + +**Derive identity from model-visible arguments.** Model or user input cannot be trusted to select Session, tenant, or sandbox routing. + +**Add routing identity to every capability seam.** That spreads hosting concerns through provider-neutral APIs. A host-aware implementation owns its transport header while public boundaries remain explicit. + +## Consequences + +Deep infrastructure gains one trusted process-local initiating Agent without widening existing tool and capability requests. Concurrent and nested drivers isolate automatically, AgentLoop gains no additional mandatory service, and HMR/root disposal reaches quiescence before ALS is disabled. + +The dependency is implicit in function signatures and carries a capability-bearing Agent object. Consumers must restrict it to cross-cutting infrastructure, treat ambient presence as neither liveness nor authorization, and retain explicit cancellation and ownership checks. ALS also has an always-on propagation cost and does not cross worker, process, HTTP, or durable queue boundaries. + +The teardown design deliberately accepts Node's [Stability 1 (Experimental)](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) `AsyncLocalStorage.disable()` dependency. Node requires `disable()` before an ALS instance can be garbage-collected, which matters when HMR replaces AgentRegistry-owned instances; the service state guard prevents a later boundary from re-entering the instance after disposal. + +The scope deliberately carries only the Agent, omitting turn, step, `signal`, `cwd`, sandbox, and authorization. A real consumer that cannot use existing explicit fields must justify any refinement separately; a stale copied field may at most mislabel telemetry, never grant control. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md new file mode 100644 index 0000000000..29ea3a47f4 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md @@ -0,0 +1,63 @@ +# RFC: 基于 AsyncLocalStorage 的发起 Agent 作用域 + +Status: implemented + +[English](2026-07-15-agent-initiator-scope.md) | 中文 + +## 问题 + +Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负责选择服务、注册归属和生命周期；`agent.ctx` 是一个存活 Agent 所拥有的扁平注册作用域。Agent 与会话身份描述的则是异步操作主体。若把根 `ctx.agent` 改成「当前正在运行的 Agent」，就会混淆这两种含义，并在单进程并发驱动多个 Agent 时失效。 + +进程内深层基础设施有时需要在显式传递的循环、工具及请求参数之下获取可信的发起 Agent，例如宿主感知传输层、追踪辅助函数、日志器或网关客户端。要求每个私有辅助函数都转发 `agent` 会造成重复，而进程级可变槽会在跨 `await` 时发生并发错误。模型可见参数也不适用，因为模型不得选择可信的会话或路由请求头。该载体归 Agent 服务所有，而非模型可见的可选上下文。 + +## 决策 + +必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`，不引入只有一个字段的帧；[核心数据目录](../../../core-data-structures/core.md#initiating-agent)标明了所携带的类型。 + +`currentInitiator()` 用于可选读取，`requireInitiator()` 抛出 `no initiating agent is active`，`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 + +`AgentLoop` 已经注入 `ctx.agents`，并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 + +隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 + +`AgentRegistry` 管理一个有序的发起方生命周期。teardown 会先拒绝新边界；移除 `ctx.agents` 后，AgentLoop 等注入方开始排空，注册表随后等待活动的返回 Promise 边界，最后调用 `AsyncLocalStorage.disable()`。排空期间，进行中代码可通过保留的服务引用继续调用 `currentInitiator()` 和 `requireInitiator()`；dispose 后，发起方方法会抛出 `agent initiator scope is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown，因此除 Cordis 依赖顺序外仍必须统计活动边界。 + +发起方作用域不负责管理脱离返回链的工作：注册表排空只跟踪 `withInitiator()` 或 `withoutInitiator()` 返回的 Promise。边界内创建的异步资源会继承其存储，直到自身结束或 ALS 被禁用；所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所有前台工作会把完整生命周期纳入返回值，并保留显式取消契约。无关的定时器、队列和部署基础设施在 `withoutInitiator(operation)` 下启动；队列、worker、进程和协议边界必须序列化身份，不能期待 ALS 传播。 + +宿主感知的传输层可以从 `ctx.agents.requireInitiator().session.id` 推导由部署方拥有的 `X-Harness-Session-Id` 等请求头；模型可见 schema 和参数中不包含该请求头。本决策不让现有生产 MCP 或 Web 传输层采用此请求头。测试替身传输层用于证明可信边界，而不会把宿主路由策略分配给现有的提供方无关 seam。 + +本决策扩展 [Agent 注册作用域契约](2026-07-08-agent-scope-contexts.md)及其[运行时设计](2026-07-12-agent-scope-runtime-design.md)，不会改变其中 `agent.ctx` 的静态含义。 + +## 验证 + +Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启及根 Context 销毁。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线，无需其他提供方。 + +只有测试替身形式的宿主感知传输层消费隐式身份；它在内部推导 `X-Harness-Session-Id`，并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空边界操作所返回 Promise 之外的异步工作；这类工作仍由所属方的显式停止契约管理。 + +## 考虑过的替代方案 + +**在每个函数中传递 Agent。** 公开、worker、进程、持久化和协议边界继续显式传递，但要求每个进程内私有辅助函数都携带 Agent 只会造成重复转发，不会提高可信度。ALS 仅限于这些显式边界内部的异步调用链。 + +**让 `ctx.agent` 变成动态值。** `ctx.agent` 已经表示与 Agent 作用域 Cordis 上下文静态关联的 Agent。改变根上下文的含义会混合注册作用域与执行作用域，并让并发行为变得意外。 + +**新增独立的 `ctx.agentExecution` 服务。** 该载体没有独立后端、配置或身份类型：它存储的是 `ctx.agents` 已经管理的同一个 `Agent`，而 AgentLoop 本就依赖该服务。第二个必需提供方会增加包、组合、生命周期、生成目录及测试 harness 接线，却没有拆出真实能力。 + +**保存命名帧或完整运行时帧。** 只有一个字段的 `{ agent }` 帧只是包装该值，而 Agent、会话、inbox、取消、轮次、步骤、工具执行和持久化已经有各自的真源。增加更多字段会产生陈旧快照和另一套生命周期；直接携带 `Agent`，由方法名标识边界，无需重复保存状态。 + +**包含步骤级 `AbortSignal`、`cwd`、沙箱或授权。** 它们的生命周期及权限范围与驱动边界不一致，而且现有 seam 已经显式传递这些值。新增控制能力需要独立决策和嵌套生命周期契约。 + +**使用进程级 `currentAgent`。** 并发 Agent 和 subagent 会在异步延续执行之间相互覆盖，因此可变全局值只在 Harness 不具备的串行保证下才正确。 + +**从模型可见参数推导身份。** 不能信任模型或用户输入来选择会话、租户或沙箱路由。 + +**给每个能力 seam 增加路由身份。** 这会把宿主关注点扩散到提供方无关 API。宿主感知实现拥有其传输请求头，而公开边界继续显式传递身份。 + +## 后果 + +深层基础设施可以获得一个可信的进程内发起 Agent，而无需加宽现有工具和能力请求。并发及嵌套驱动会自动隔离，AgentLoop 不增加新的必需服务，HMR 或根 Context dispose 会在禁用 ALS 前完成排空。 + +该依赖不会出现在函数签名中，并且携带一个具有控制能力的 Agent 对象。消费方必须将其限制在横切基础设施中，把隐式存在视为既不证明存活、也不授予权限，并保留显式取消和归属检查。ALS 还有常驻传播成本，也无法跨越 worker、进程、HTTP 或持久化队列边界。 + +该销毁设计有意依赖 Node 的 [Stability 1（实验性）](https://nodejs.org/api/async_context.html#asynclocalstoragedisable) API `AsyncLocalStorage.disable()`。Node 要求在 ALS 实例可被垃圾回收前调用 `disable()`，这对 HMR 替换 AgentRegistry 所拥有的实例尤为重要；服务状态守卫会阻止 dispose 后通过后续边界重新进入该实例。 + +该作用域有意只携带 Agent，省略轮次、步骤、`signal`、`cwd`、沙箱和授权。若真实消费方无法使用现有显式字段，必须另行论证扩展；陈旧字段最多只能误标遥测数据，绝不能授予控制权。 diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index e243270e29..a5e69b85ea 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -9,7 +9,6 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' @@ -49,7 +48,6 @@ async function codeModeHarness(cwd: string): Promise { await harness.plugin(SystemPrompt, { persona: PERSONA }) await harness.plugin(ToolRegistry, { mode: 'code' }) await harness.plugin(AgentRegistry) - await harness.plugin(AgentExecutionProvider) await harness.plugin(AgentLoop, { agents: [] }) await harness.plugin(LlmDeepSeek) await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 }) @@ -68,7 +66,6 @@ async function workspaceCodeModeHarness(): Promise { await harness.plugin(LocalFileSystem, { cwd: '/' }) await harness.plugin(ToolFs) await harness.plugin(WorkspaceContext, { maxBytes: 65536 }) - await harness.plugin(AgentExecutionProvider) await harness.plugin(AgentLoop, { agents: [] }) await harness.plugin(LlmDeepSeek, { models: [{ id: 'deepseek-v4-flash' }] }) await harness.plugin(WorkerCodeRuntime, {}) diff --git a/packages/context/workspace-context/package.json b/packages/context/workspace-context/package.json index b6ff240cf1..7f704c838a 100644 --- a/packages/context/workspace-context/package.json +++ b/packages/context/workspace-context/package.json @@ -36,7 +36,6 @@ "devDependencies": { "@cordisjs/plugin-loader": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-fs": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", diff --git a/packages/context/workspace-context/tests/workspace-context.e2e.ts b/packages/context/workspace-context/tests/workspace-context.e2e.ts index 3710f77547..0c11da8ed4 100644 --- a/packages/context/workspace-context/tests/workspace-context.e2e.ts +++ b/packages/context/workspace-context/tests/workspace-context.e2e.ts @@ -9,7 +9,6 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context' @@ -44,7 +43,6 @@ async function harness(): Promise<{ ctx: Context; agent: Agent }> { await ctx.plugin(LocalFileSystem, { cwd: '/' }) await ctx.plugin(ToolFs) await ctx.plugin(WorkspaceContext, { maxBytes: 65536 }) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LlmDeepSeek, { models: [{ id: 'deepseek-v4-flash' }] }) const handle = await ctx.agents.create({ diff --git a/packages/context/workspace-context/tests/workspace-context.spec.ts b/packages/context/workspace-context/tests/workspace-context.spec.ts index f161ac0bc9..2ff2067cf5 100644 --- a/packages/context/workspace-context/tests/workspace-context.spec.ts +++ b/packages/context/workspace-context/tests/workspace-context.spec.ts @@ -8,7 +8,6 @@ import * as workspaceContext from '@deepseek-ai/dsh-workspace-context' import LlmService, { CallId, type Message, type StreamChunk } from '@deepseek-ai/dsh-llm' import SessionStore, { Session, SessionId, SESSION_FORMAT_VERSION, type SessionEvent } from '@deepseek-ai/dsh-session' import AgentRegistry, { type Agent, type HookContext } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { FileSystem, FsTargetKey, FsVersion } from '@deepseek-ai/dsh-fs' import type { @@ -1587,7 +1586,6 @@ describe('dynamic nested workspace context injection', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(LocalFileSystem, { cwd: '/' }) await ctx.plugin(ToolFs) await ctx.plugin(workspaceContext, { dshHome: home, maxBytes: 65536 }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 4ff01c81ae..5d99506c8a 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -52,15 +52,6 @@ export interface TypeApiEntry { /** Every harness `ctx.` service, sorted by key. */ export const SERVICE_API: readonly ServiceApiEntry[] = [ - { - key: 'agentExecution', - summary: 'Ambient Agent identity within one process-local asynchronous chain.', - methods: [ - 'current(): AgentExecution | undefined', - 'require(): AgentExecution', - 'run(execution: AgentExecution | undefined, operation: () => T): T', - ], - }, { key: 'agentLoop', summary: 'Concrete agent factory and driver service.', @@ -72,8 +63,12 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ }, { key: 'agents', - summary: 'Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package.', + summary: 'Agent service (`ctx.agents`): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain.', methods: [ + 'currentInitiator(): Agent | undefined', + 'requireInitiator(): Agent', + 'withInitiator(agent: Agent, operation: () => T): T', + 'withoutInitiator(operation: () => T): T', 'setFactory(factory: AgentFactory): () => void', 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', @@ -552,10 +547,6 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'Agent', declaration: 'export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: InjectOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n}', }, - { - name: 'AgentExecution', - declaration: 'export interface AgentExecution {\n readonly agent: Agent;\n}', - }, { name: 'AgentFactory', declaration: 'export interface AgentFactory {\n createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise;\n resume(ownerCtx: Context, options: ResumeAgentOptions): Promise;\n}', diff --git a/packages/core/README.md b/packages/core/README.md index 3c0ad38819..fe98a78c22 100644 --- a/packages/core/README.md +++ b/packages/core/README.md @@ -8,12 +8,11 @@ The session log, system-prompt assembly, tool registry, agent vocabulary, and co | `session/` | Event-sourced session log + in-memory store | `ctx.sessions` | | `system-prompt/` | Prompt-section + tool-schema assembly registry | `ctx.systemPrompt` | | `tools/` | Scoped tool registry + pre-policy, guards, around-dispatch, post-policy, and final-result observation | `ctx.tools` | -| `agent/` | Agent interface, registry, `agent/*` event vocabulary | `ctx.agents` | -| `agent-execution/` | Process-local ambient Agent identity for asynchronous driver work | `ctx.agentExecution` | +| `agent/` | Agent interface, live registry, process-local initiator scope, `agent/*` event vocabulary | `ctx.agents` | | `agent-loop/` | Concrete plugin implementing the public `Agent` contract and owning the loop driver | `ctx.agentLoop` | `scope/` is the one non-service package here: a dependency-free library (`createScope`/`scopeOf`/`scopeTarget`) the registries and the loop build per-agent scoping on — it sits below `session/` and `system-prompt/` in the module graph precisely so they can consume it without a cycle. -`agent-execution` is mandatory control infrastructure for concrete loops and deep process-local consumers. `agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop. Extension plugins depend on `agent` and, when they need ambient identity, `agent-execution`; they never depend on `agent-loop` directly, so the loop stays swappable. +`agent-loop` is the one concrete implementation of the `agent` seam and lives here because it is the harness's default product loop. It runs each driver inside `ctx.agents.withInitiator()`. Extension plugins depend on `agent`, including when they need the initiating Agent, and never on `agent-loop` directly, so the loop stays swappable. -The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + agent-execution + invariants + the local [skill family](../skill/README.md) + `tool-bash` + workspace-context + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door. +The default composition that wires this spine into a runnable agent lives in [`examples/agent-spine-demo`](../examples/agent-spine-demo/README.md): one bundle plugin that loads the control spine plus selected default capabilities (`timer` + `llm` + sessions + system-prompt + tools + agents + invariants + the local [skill family](../skill/README.md) + `tool-bash` + workspace-context + `agent-loop`) and forwards `agent-loop`'s `agents` list as its own config. It sits in `examples/` — ready-to-run demo/reference bundles — not in `core/`: `core/` ships the swappable spine pieces, while a demo bundle picks one concrete composition of them and adds a front door. diff --git a/packages/core/agent-execution/README.md b/packages/core/agent-execution/README.md deleted file mode 100644 index 8c01f0b3c4..0000000000 --- a/packages/core/agent-execution/README.md +++ /dev/null @@ -1,23 +0,0 @@ -# dsh-agent-execution - -Process-local ambient Agent identity for asynchronous work initiated by a concrete agent driver. The default export, `AgentExecutionProvider`, installs the mandatory `ctx.agentExecution` service; [`dsh-agent-loop`](../agent-loop/README.md) establishes one boundary around each driver's complete lifetime. - -## Service: `AgentExecutionService` (ctx key: `agentExecution`) - -- `current()` returns the inherited `AgentExecution` or `undefined` outside a driver and inside an explicit clearing boundary. -- `require()` returns the inherited execution or throws `no agent execution context is active`. -- `run(execution, operation)` returns the exact synchronous value or Promise from `operation`. Passing `undefined` establishes a real boundary that hides an inherited Agent. - -The store contains only `{ readonly agent: Agent }`. The `Session` remains available through `agent.session`; turn, step, `signal`, `cwd`, sandbox, authorization, and other capability state remain with their explicit owners. Ambient presence identifies the initiator but does not prove that the Agent is live or that an operation is authorized. - -## Lifetime and detached work - -Provider teardown rejects new `run()` boundaries, removes the service so injected dependents drain, waits for returned Promise boundaries, then disables its `AsyncLocalStorage`. In-flight code retaining the service can call `current()` and `require()` while it drains; after disposal, all three methods throw `agent execution service is disposed`. - -Async resources created inside `run()` inherit its Agent even if `operation` returns before they settle, but provider teardown waits only for the Promise returned by `operation`. The owning seam must stop unreturned work explicitly. Unrelated timers, queues, and deployment infrastructure start under `run(undefined, operation)` and own an explicit stop; queue, worker, process, and wire boundaries serialize any identity they need instead of relying on ALS propagation. - -## Known Limitations and Deferred Work - -- **Process-local only** — ALS does not cross workers, child processes, HTTP, durable queues, or restarts; each boundary materializes a typed identity explicitly. -- **Agent identity only** — turn, step, signal, cwd, sandbox, and authorization stay outside the frame until a concrete cross-cutting consumer justifies a separate design. -- **Ambient references may outlive liveness** — consumers still check `agent.status`, their explicit signal, and the owning capability contract before lifecycle-sensitive work. diff --git a/packages/core/agent-execution/package.json b/packages/core/agent-execution/package.json deleted file mode 100644 index 7c2c527d3d..0000000000 --- a/packages/core/agent-execution/package.json +++ /dev/null @@ -1,31 +0,0 @@ -{ - "name": "@deepseek-ai/dsh-agent-execution", - "description": "Process-local ambient Agent context for asynchronous driver work", - "version": "0.0.1", - "private": true, - "type": "module", - "main": "lib/index.js", - "types": "lib/types/index.d.ts", - "exports": { - ".": { - "types": "./lib/types/index.d.ts", - "default": "./lib/index.js" - }, - "./package.json": "./package.json" - }, - "files": [ - "lib/index.js", - "lib/types/**/*.d.ts", - "lib/types/**/*.d.ts.map", - "src" - ], - "license": "BSD-3-Clause", - "peerDependencies": { - "@deepseek-ai/dsh-agent": "^0.0.1", - "cordis": "^4.0.0-rc.7" - }, - "devDependencies": { - "@deepseek-ai/dsh-agent": "workspace:^", - "cordis": "^4.0.0-rc.7" - } -} diff --git a/packages/core/agent-execution/src/index.ts b/packages/core/agent-execution/src/index.ts deleted file mode 100644 index cb2683dbaa..0000000000 --- a/packages/core/agent-execution/src/index.ts +++ /dev/null @@ -1,140 +0,0 @@ -/** - * Process-local Agent execution context backed by Node AsyncLocalStorage. - * - * @module @deepseek-ai/dsh-agent-execution - */ - -import type { Context } from 'cordis' -import { AsyncLocalStorage } from 'node:async_hooks' -import { isPromise } from 'node:util/types' -import type { AgentExecution } from './types.ts' - -export type { AgentExecution } from './types.ts' - -const NO_ACTIVE_EXECUTION = 'no agent execution context is active' -const DISPOSED_SERVICE = 'agent execution service is disposed' - -/** Ambient Agent identity within one process-local asynchronous chain. */ -export interface AgentExecutionService { - /** - * Read the active execution without requiring one. - * @returns the inherited execution, or `undefined` outside/inside a cleared boundary. - * @throws when this service instance has been disposed. - */ - current(): AgentExecution | undefined - - /** - * Read the active execution and fail when no boundary is active. - * @returns the inherited execution. - * @throws when no execution is active or this service instance has been disposed. - */ - require(): AgentExecution - - /** - * Run an operation inside an execution boundary. Passing `undefined` clears - * an inherited execution; the exact synchronous value or Promise is returned. - * @param execution - execution to inherit, or `undefined` for a clearing boundary. - * @param operation - synchronous or asynchronous operation to invoke. - * @returns the exact value returned by `operation`. - * @throws when this service is closing/disposed, or when `operation` throws. - */ - run(execution: AgentExecution | undefined, operation: () => T): T -} - -declare module 'cordis' { - interface Context { - agentExecution: AgentExecutionService - } -} - -/** One provider-owned ALS instance with quiescent shutdown. */ -class DefaultAgentExecutionService implements AgentExecutionService { - private readonly storage = new AsyncLocalStorage() - private state: 'active' | 'closing' | 'disposed' = 'active' - private activeRuns = 0 - private drainWaiter: PromiseWithResolvers | undefined - private disposalTask: Promise | undefined - - current(): AgentExecution | undefined { - this.assertReadable() - return this.storage.getStore() - } - - require(): AgentExecution { - const execution = this.current() - if (execution === undefined) throw new Error(NO_ACTIVE_EXECUTION) - return execution - } - - run(execution: AgentExecution | undefined, operation: () => T): T { - if (this.state !== 'active') throw new Error(DISPOSED_SERVICE) - this.activeRuns += 1 - let result: T - try { - result = this.storage.run(execution, operation) - } catch (error: unknown) { - this.releaseRun() - throw error - } - if (isPromise(result)) { - void result.then( - () => { this.releaseRun() }, - () => { this.releaseRun() }, - ) - } else { - this.releaseRun() - } - return result - } - - /** Reject new boundaries while existing continuations remain readable. */ - close(): void { - if (this.state === 'active') this.state = 'closing' - } - - /** Wait for every returned Promise boundary, then invalidate retained references. */ - dispose(): Promise { - return (this.disposalTask ??= (async () => { - this.close() - if (this.activeRuns !== 0) { - this.drainWaiter ??= Promise.withResolvers() - await this.drainWaiter.promise - } - this.state = 'disposed' - this.storage.disable() - })()) - } - - private assertReadable(): void { - if (this.state === 'disposed') throw new Error(DISPOSED_SERVICE) - } - - private releaseRun(): void { - this.activeRuns -= 1 - if (this.activeRuns !== 0) return - this.drainWaiter?.resolve() - this.drainWaiter = undefined - } -} - -/** Cordis provider for the mandatory `ctx.agentExecution` service. */ -export class AgentExecutionProvider { - private readonly service = new DefaultAgentExecutionService() - - /** - * Install one isolated execution service and its ordered lifecycle. - * @param ctx - provider-owning Cordis context. - */ - constructor(ctx: Context) { - const service = this.service - ctx.effect(function* () { - // First yielded, disposed last: invalidate ALS only after dependents and active runs drain. - yield () => service.dispose() - yield ctx.provide('agentExecution', service) - // Last yielded, disposed first: prevent a teardown race from opening another boundary. - yield () => { service.close() } - }, 'agentExecution.lifecycle()') - } -} - -export default AgentExecutionProvider diff --git a/packages/core/agent-execution/src/types.ts b/packages/core/agent-execution/src/types.ts deleted file mode 100644 index 94b144785b..0000000000 --- a/packages/core/agent-execution/src/types.ts +++ /dev/null @@ -1,12 +0,0 @@ -/** - * Public Agent execution-context types. - * - * @module @deepseek-ai/dsh-agent-execution/types - */ - -import type { Agent } from '@deepseek-ai/dsh-agent' - -/** The exact Agent associated with one asynchronous execution chain. */ -export interface AgentExecution { - readonly agent: Agent -} diff --git a/packages/core/agent-execution/tests/agent-execution.spec.ts b/packages/core/agent-execution/tests/agent-execution.spec.ts deleted file mode 100644 index b18d19e63d..0000000000 --- a/packages/core/agent-execution/tests/agent-execution.spec.ts +++ /dev/null @@ -1,163 +0,0 @@ -import { describe, expect, it } from 'vitest' -import { Context } from 'cordis' -import { runInNewContext } from 'node:vm' -import type { Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' -import type { AgentExecution, AgentExecutionService } from '@deepseek-ai/dsh-agent-execution' -import { SessionId } from '@deepseek-ai/dsh-session' - -function execution(id: string): AgentExecution { - return { agent: { id: SessionId(id) } as Agent } -} - -async function harness(): Promise<{ - ctx: Context - service: AgentExecutionService - dispose: () => Promise -}> { - const ctx = new Context() - const fiber = await ctx.plugin(AgentExecutionProvider) - return { - ctx, - service: ctx.agentExecution, - dispose: fiber.dispose, - } -} - -describe('AgentExecutionProvider', () => { - it('reports an absent boundary and requires an active execution', async () => { - const { service, dispose } = await harness() - expect(service.current()).toBeUndefined() - expect(() => service.require()).toThrow('no agent execution context is active') - await dispose() - }) - - it('preserves exact synchronous and Promise return identities across await', async () => { - const { service, dispose } = await harness() - const active = execution('identity') - const value = { result: true } - expect(service.run(active, () => { - expect(service.require()).toBe(active) - return value - })).toBe(value) - - const promise = service.run(active, async () => { - expect(service.require()).toBe(active) - await Promise.resolve() - expect(service.require()).toBe(active) - return value - }) - expect(service.run(active, () => promise)).toBe(promise) - await expect(promise).resolves.toBe(value) - expect(service.current()).toBeUndefined() - await dispose() - }) - - it('isolates overlapping executions', async () => { - const { service, dispose } = await harness() - const a = execution('a') - const b = execution('b') - const bothStarted = Promise.withResolvers() - const release = Promise.withResolvers() - let starts = 0 - const run = (active: AgentExecution): Promise => service.run(active, async () => { - expect(service.require()).toBe(active) - starts += 1 - if (starts === 2) bothStarted.resolve(true) - await release.promise - expect(service.require()).toBe(active) - }) - - const pending = [run(a), run(b)] - await bothStarted.promise - expect(service.current()).toBeUndefined() - release.resolve(true) - await Promise.all(pending) - await dispose() - }) - - it('restores nested and explicitly cleared boundaries', async () => { - const { service, dispose } = await harness() - const parent = execution('parent') - const child = execution('child') - - service.run(parent, () => { - expect(service.require()).toBe(parent) - service.run(child, () => { expect(service.require()).toBe(child) }) - expect(service.require()).toBe(parent) - service.run(undefined, () => { - expect(service.current()).toBeUndefined() - expect(() => service.require()).toThrow('no agent execution context is active') - }) - expect(service.require()).toBe(parent) - }) - expect(service.current()).toBeUndefined() - await dispose() - }) - - it('restores context after synchronous throws and rejected operations', async () => { - const { service, dispose } = await harness() - const parent = execution('parent') - const child = execution('child') - const syncError = new Error('sync failure') - const asyncError = new Error('async failure') - - service.run(parent, () => { - expect(() => service.run(child, () => { throw syncError })).toThrow(syncError) - expect(service.require()).toBe(parent) - }) - await expect(service.run(child, async () => { - await Promise.resolve() - throw asyncError - })).rejects.toBe(asyncError) - expect(service.current()).toBeUndefined() - await dispose() - }) - - it('stops new boundaries, drains active Promises, and invalidates retained references', async () => { - const { ctx, service, dispose } = await harness() - const active = execution('draining') - const release = Promise.withResolvers() - const pending = service.run(active, async () => { - await release.promise - expect(service.require()).toBe(active) - }) - let disposed = false - const disposal = dispose().then(() => { disposed = true }) - await Promise.resolve() - - expect(() => service.run(active, () => 1)).toThrow('agent execution service is disposed') - expect(disposed).toBe(false) - expect(ctx.get('agentExecution')).toBeUndefined() - release.resolve(true) - await pending - await disposal - expect(() => service.current()).toThrow('agent execution service is disposed') - expect(() => service.require()).toThrow('agent execution service is disposed') - }) - - it('drains cross-realm Promise boundaries before disposal', async () => { - const { service, dispose } = await harness() - const active = execution('cross-realm') - const release = Promise.withResolvers() - const operation = runInNewContext( - '(async () => { await release; inspect() })', - { - release: release.promise, - inspect: () => { expect(service.require()).toBe(active) }, - }, - ) as () => Promise - const pending = service.run(active, operation) - expect(pending).not.toBeInstanceOf(Promise) - - let disposed = false - const disposal = dispose().then(() => { disposed = true }) - await Promise.resolve() - expect(disposed).toBe(false) - - release.resolve(true) - await pending - await disposal - expect(disposed).toBe(true) - }) -}) diff --git a/packages/core/agent-execution/tsconfig.json b/packages/core/agent-execution/tsconfig.json deleted file mode 100644 index a06784e926..0000000000 --- a/packages/core/agent-execution/tsconfig.json +++ /dev/null @@ -1,21 +0,0 @@ -{ - "extends": "../../../tsconfig.base.json", - "compilerOptions": { - "rootDir": "src", - "outDir": "lib/types" - }, - "include": [ - "src" - ], - "references": [ - { - "path": "../../../vendor/cosmokit" - }, - { - "path": "../../../vendor/cordis" - }, - { - "path": "../../core/agent" - } - ] -} diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f45411923c..db5861f8c1 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -25,7 +25,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo ### Injected services -`agents`, `agentExecution`, `sessions`, `llm`, `tools`, `systemPrompt` — all six interface services. The loop cannot activate without `agentExecution`; the default bundle loads its provider before the loop. +`agents`, `sessions`, `llm`, `tools`, `systemPrompt` — all five interface services. ### Configuration (schemastery) @@ -50,7 +50,7 @@ The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publicati ### Loop lifecycle (`loop.ts`) -The driver owns one agent for its lifetime and runs inside `ctx.agentExecution.run({ agent }, ...)`, so process-local asynchronous continuations can recover the initiating Agent. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [execution-context package](../agent-execution/README.md) owns propagation, teardown, and detached-work rules. +The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`, so process-local asynchronous continuations can recover the initiating Agent. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules. Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. diff --git a/packages/core/agent-loop/package.json b/packages/core/agent-loop/package.json index 6a7fe2d937..7e2fb235a2 100644 --- a/packages/core/agent-loop/package.json +++ b/packages/core/agent-loop/package.json @@ -22,7 +22,6 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", - "@deepseek-ai/dsh-agent-execution": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -36,7 +35,6 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index 67c9160332..6ab02bfc13 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -387,7 +387,7 @@ export class ReactLoopAgent implements Agent { [startDriver](): void { if (this._status === 'disposed') return this.driverStarted = true - this.done = this.loopCtx.agentExecution.run({ agent: this }, () => runLoop(this.loopCtx, this, { + this.done = this.loopCtx.agents.withInitiator(this, () => runLoop(this.loopCtx, this, { inbox: this.#inbox, maxParallelToolCalls: this.maxParallelToolCalls, setStatus: (status) => { this.setStatus(status) }, diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 6a0d714ef3..2a77afc983 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -11,7 +11,6 @@ import z from 'schemastery' import { createScope } from '@deepseek-ai/dsh-scope' import type { Scope } from '@deepseek-ai/dsh-scope' import { agentEvents } from '@deepseek-ai/dsh-agent' -import type {} from '@deepseek-ai/dsh-agent-execution' import type { Agent, AgentFactory, @@ -406,7 +405,7 @@ function validateConfiguredAgents(agents: Config['agents']): void { /** Concrete agent factory and driver service. */ export class AgentLoop extends Service implements AgentFactory { - static inject = ['agents', 'agentExecution', 'sessions', 'llm', 'tools', 'systemPrompt'] + static inject = ['agents', 'sessions', 'llm', 'tools', 'systemPrompt'] /** Runtime schema for declarative agents. */ static Config = z.object({ diff --git a/packages/core/agent-loop/tests/agent-execution.spec.ts b/packages/core/agent-loop/tests/agent-initiator.spec.ts similarity index 76% rename from packages/core/agent-loop/tests/agent-execution.spec.ts rename to packages/core/agent-loop/tests/agent-initiator.spec.ts index ee6f2d94c7..7f0903fc00 100644 --- a/packages/core/agent-loop/tests/agent-execution.spec.ts +++ b/packages/core/agent-loop/tests/agent-initiator.spec.ts @@ -1,8 +1,6 @@ import { describe, expect, it } from 'vitest' -import { Context, FiberState, type Fiber } from 'cordis' +import { Context, type Fiber } from 'cordis' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' -import type { AgentExecutionService } from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import LlmService, { CallId, LlmAdapter } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' @@ -13,7 +11,7 @@ import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' interface Harness { ctx: Context - providerFiber: Fiber + agentsFiber: Fiber loopFiber: Fiber } @@ -23,11 +21,10 @@ async function harness(adapter: LlmAdapter): Promise { await ctx.plugin(SessionStore) await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - const providerFiber = await ctx.plugin(AgentExecutionProvider) + const agentsFiber = await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) - return { ctx, providerFiber, loopFiber } + return { ctx, agentsFiber, loopFiber } } function waitForIdle(ctx: Context, agent: Agent): Promise { @@ -56,12 +53,12 @@ class OverlapAdapter extends LlmAdapter { } async * stream(options: GenerateOptions): AsyncIterable { - const before = this.ctx.agentExecution.require().agent + const before = this.ctx.agents.requireInitiator() this.starts += 1 if (this.starts === 2) this.bothStarted.resolve(true) await this.bothStarted.promise await Promise.resolve() - const after = this.ctx.agentExecution.require().agent + const after = this.ctx.agents.requireInitiator() this.observations.push({ sessionId: options.sessionId, before, after }) yield* textResponse('done') } @@ -71,12 +68,12 @@ class OverlapAdapter extends LlmAdapter { class TestCapabilityTransport { readonly requests: { path: string; headers: Record }[] = [] - constructor(private readonly execution: AgentExecutionService) {} + constructor(private readonly agents: AgentRegistry) {} async request(path: string): Promise> { await Promise.resolve() const headers = { - 'X-Harness-Session-Id': this.execution.require().agent.session.id, + 'X-Harness-Session-Id': this.agents.requireInitiator().session.id, } this.requests.push({ path, headers }) return headers @@ -89,11 +86,11 @@ class ReloadAdapter extends LlmAdapter { firstAgentDuringAbort: Agent | undefined laterAgent: Agent | undefined calls = 0 - execution: AgentExecutionService | undefined + agents: AgentRegistry | undefined async * stream(options: GenerateOptions): AsyncIterable { - const execution = this.execution - if (execution === undefined) throw new Error('execution service missing') + const agents = this.agents + if (agents === undefined) throw new Error('agent service missing') this.calls += 1 if (this.calls === 1) { this.firstStarted.resolve(true) @@ -105,18 +102,18 @@ class ReloadAdapter extends LlmAdapter { }) } catch (error: unknown) { await Promise.resolve() - this.firstAgentDuringAbort = execution.require().agent + this.firstAgentDuringAbort = agents.requireInitiator() throw error } return } await Promise.resolve() - this.laterAgent = execution.require().agent + this.laterAgent = agents.requireInitiator() yield* textResponse('reloaded') } } -describe('AgentLoop execution context', () => { +describe('AgentLoop initiator scope', () => { it('keeps overlapping driver continuations bound to their exact Agents', async () => { const ctx = new Context() const adapter = new OverlapAdapter(ctx) @@ -125,7 +122,6 @@ describe('AgentLoop execution context', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) @@ -142,7 +138,7 @@ describe('AgentLoop execution context', () => { { sessionId: a.session.id, before: a, after: a }, { sessionId: b.session.id, before: b, after: b }, ])) - expect(ctx.agentExecution.current()).toBeUndefined() + expect(ctx.agents.currentInitiator()).toBeUndefined() await ctx.fiber.dispose() }) @@ -170,7 +166,7 @@ describe('AgentLoop execution context', () => { sessionId: SessionId('child-session'), agentOptions: { provider: 'mock', model: 'mock' }, setup: (agentCtx) => { - parentDuringSetup = ctx.agentExecution.require().agent + parentDuringSetup = ctx.agents.requireInitiator() explicitChild = agentCtx.agent agentCtx.tools.register(defineTool({ name: 'observe-child', @@ -178,7 +174,7 @@ describe('AgentLoop execution context', () => { parameters: {}, execute: async () => { await Promise.resolve() - childDuringDriver = ctx.agentExecution.require().agent + childDuringDriver = ctx.agents.requireInitiator() return [{ type: 'text', text: 'observed' }] }, })) @@ -187,7 +183,7 @@ describe('AgentLoop execution context', () => { child = handle.agent send(handle.agent, 'run child') await handle.agent.whenIdle() - parentAfterChild = ctx.agentExecution.require().agent + parentAfterChild = ctx.agents.requireInitiator() await handle.dispose() return [{ type: 'text', text: 'child completed' }] }, @@ -205,7 +201,7 @@ describe('AgentLoop execution context', () => { expect(explicitChild).toBe(child) expect(childDuringDriver).toBe(child) expect(parentAfterChild).toBe(parentHandle.agent) - expect(ctx.agentExecution.current()).toBeUndefined() + expect(ctx.agents.currentInitiator()).toBeUndefined() await parentHandle.dispose() await ctx.fiber.dispose() }) @@ -216,7 +212,7 @@ describe('AgentLoop execution context', () => { textResponse('done'), ]) const { ctx } = await harness(adapter) - const transport = new TestCapabilityTransport(ctx.agentExecution) + const transport = new TestCapabilityTransport(ctx.agents) let directAmbient: Agent | undefined let captured: Agent | undefined @@ -226,7 +222,7 @@ describe('AgentLoop execution context', () => { parameters: {}, execute: async () => { await Promise.resolve() - directAmbient = ctx.agentExecution.current()?.agent + directAmbient = ctx.agents.currentInitiator() return [{ type: 'text', text: 'ok' }] }, })) @@ -235,7 +231,7 @@ describe('AgentLoop execution context', () => { description: 'call the test capability transport', parameters: { path: { type: 'string' } }, execute: async (args) => { - captured = ctx.agentExecution.require().agent + captured = ctx.agents.requireInitiator() const path = (args as { path: string }).path const headers = await transport.request(path) return [{ type: 'text', text: JSON.stringify(headers) }] @@ -271,43 +267,15 @@ describe('AgentLoop execution context', () => { await handle.dispose() expect(captured?.status).toBe('disposed') - expect(ctx.agentExecution.current()).toBeUndefined() + expect(ctx.agents.currentInitiator()).toBeUndefined() await ctx.fiber.dispose() }) - it('keeps AgentLoop inactive until the mandatory provider appears', async () => { - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - const loopFiber = ctx.plugin(AgentLoop, { agents: [] }) - await Promise.resolve() - expect(loopFiber.state).toBe(FiberState.PENDING) - - await ctx.plugin(AgentExecutionProvider) - await loopFiber - expect(loopFiber.state).toBe(FiberState.ACTIVE) - await ctx.fiber.dispose() - }) - - it('drains the old driver before disabling ALS during provider restart', async () => { - const ctx = new Context() + it('drains the old driver before disabling ALS during agent-service restart', async () => { const adapter = new ReloadAdapter() - const { providerFiber, loopFiber } = await (async (): Promise => { - await ctx.plugin(LlmService) - await ctx.plugin(SessionStore) - await ctx.plugin(SystemPrompt) - await ctx.plugin(ToolRegistry) - await ctx.plugin(AgentRegistry) - const mountedProvider = await ctx.plugin(AgentExecutionProvider) - const mountedLoop = await ctx.plugin(AgentLoop, { agents: [] }) - ctx.llm.registerAdapter(['mock'], adapter) - return { ctx, providerFiber: mountedProvider, loopFiber: mountedLoop } - })() - const oldService = ctx.agentExecution - adapter.execution = oldService + const { ctx, agentsFiber, loopFiber } = await harness(adapter) + const oldService = ctx.agents + adapter.agents = oldService const oldHandle = await ctx.agents.create({ sessionId: SessionId('before-restart-session'), agentOptions: { provider: 'mock', model: 'mock' }, @@ -316,14 +284,14 @@ describe('AgentLoop execution context', () => { send(oldAgent, 'block') await adapter.firstStarted.promise - await providerFiber.restart() + await agentsFiber.restart() await loopFiber.await() expect(adapter.firstAgentDuringAbort?.id).toBe(oldAgent.id) expect(adapter.firstAgentDuringAbort?.session).toBe(oldAgent.session) expect(oldAgent.status).toBe('disposed') - expect(() => oldService.current()).toThrow('agent execution service is disposed') - expect(ctx.agentExecution).not.toBe(oldService) - adapter.execution = ctx.agentExecution + expect(() => oldService.currentInitiator()).toThrow('agent initiator scope is disposed') + expect(ctx.agents).not.toBe(oldService) + adapter.agents = ctx.agents const newHandle = await ctx.agents.create({ sessionId: SessionId('after-restart-session'), @@ -346,11 +314,10 @@ describe('AgentLoop execution context', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) - const service = ctx.agentExecution - adapter.execution = service + const service = ctx.agents + adapter.agents = service const handle = await ctx.agents.create({ sessionId: SessionId('root-dispose-session'), agentOptions: { provider: 'mock', model: 'mock' }, @@ -363,6 +330,6 @@ describe('AgentLoop execution context', () => { expect(adapter.firstAgentDuringAbort?.id).toBe(agent.id) expect(adapter.firstAgentDuringAbort?.session).toBe(agent.session) expect(agent.status).toBe('disposed') - expect(() => service.current()).toThrow('agent execution service is disposed') + expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed') }) }) diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 668190dd3d..d23b69efb7 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -5,7 +5,6 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop' import { bindReactLoopAgentContext, prepareReactLoopAgent, type ReactLoopAgent } from '../src/agent.ts' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -21,7 +20,6 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -56,7 +54,6 @@ function send(agent: Agent, text: string) { describe('Agent', () => { it('rejects access before context binding and a second driver for one session', async () => { const ctx = new Context() - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) const prepared = prepareReactLoopAgent( @@ -266,8 +263,8 @@ describe('Agent', () => { // test seam. Then call its disposer twice — the second call hits the // early-return branch. const ctx = new Context() - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(SessionStore) + await ctx.plugin(AgentRegistry) const session = ctx.sessions.create(SessionId('test')) const prepared = prepareReactLoopAgent( ctx, SessionId('bare'), { provider: 'mock', model: 'mock' }, session, DEFAULT_MAX_PARALLEL_TOOL_CALLS, @@ -386,7 +383,6 @@ describe('Agent', () => { // `done` (loop exit), not an eager resolve. A bare Agent + direct // internal driver disposer keeps the emit synchronous. const ctx = new Context() - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(LlmService) await ctx.plugin(SessionStore) await ctx.plugin(SystemPrompt) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index e65ffc42a6..2d32388171 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -14,7 +14,6 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -29,7 +28,6 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -200,7 +198,6 @@ describe('Agent.cancel()', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) @@ -325,7 +322,6 @@ describe('Agent.cancel()', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 8710ee5629..cadc176aea 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -10,7 +10,6 @@ import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -32,7 +31,6 @@ async function makeCoreContext(): Promise { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) return ctx } @@ -308,7 +306,6 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) const loopFiber = await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }], }) @@ -331,7 +328,6 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentExecutionProvider) await ctx1.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) @@ -351,7 +347,6 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('cfg'), provider: 'mock', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) @@ -376,7 +371,6 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentExecutionProvider) await ctx1.plugin(AgentLoop, { agents: [] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('first')])) @@ -393,7 +387,6 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -423,7 +416,6 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 891272a3c2..1875ce3757 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -5,7 +5,6 @@ import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent, type ContinuationDecision } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop' import { prepareReactLoopAgent } from '../src/agent.ts' import * as Invariants from '@deepseek-ai/dsh-invariants' @@ -24,7 +23,6 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -824,7 +822,6 @@ describe('turn numbering continues across seeded sessions', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) ctx2.llm.registerAdapter(['mock'], second) @@ -967,7 +964,6 @@ describe('turn and step boundary recovery', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1419,7 +1415,6 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1471,7 +1466,6 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1527,7 +1521,6 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1579,7 +1572,6 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) @@ -1629,7 +1621,6 @@ describe('disposal and cancellation during pre-step assembly', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(Invariants) ctx.llm.registerAdapter(['mock'], adapter) diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index d7971c81bc..38fdaedf57 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -6,7 +6,6 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -21,7 +20,6 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index d3c66af720..a715265a97 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -5,7 +5,6 @@ import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from ' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -25,7 +24,6 @@ async function harness(adapter: MockAdapter) { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 105156f70e..63fef89087 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -5,7 +5,6 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -20,7 +19,6 @@ async function harness(adapter: MockAdapter, persona = '') { await ctx.plugin(SystemPrompt, { persona }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx @@ -1029,7 +1027,6 @@ describe('agent loop', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock' }], }) @@ -1054,7 +1051,6 @@ describe('agent loop', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [{ id: SessionId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }], }) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 48c5d767c0..6f872cc423 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -18,7 +18,6 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' @@ -42,7 +41,6 @@ async function harness() { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], new EchoAdapter()) return ctx diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 31c4865c61..c82eccbf85 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -5,7 +5,6 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' @@ -43,7 +42,6 @@ async function loopHarness(): Promise { await created.plugin(SystemPrompt, { persona: SYSTEM }) await created.plugin(ToolRegistry) await created.plugin(AgentRegistry) - await created.plugin(AgentExecutionProvider) await created.plugin(AgentLoop, { agents: [] }) await created.plugin(LlmDeepSeek) created.tools.register(defineTool({ diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 20000e9057..6622092f47 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -13,7 +13,6 @@ import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-a import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -24,7 +23,6 @@ async function harness(adapter: MockAdapter, persona = 'stable base') { await ctx.plugin(SystemPrompt, { persona }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index bd00eb8bdd..74192dde90 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -11,7 +11,6 @@ import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -31,7 +30,6 @@ async function mountPersistentHarness(root: string, adapter: MockAdapter): Promi await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], adapter) @@ -139,7 +137,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -168,7 +165,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -383,7 +379,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) const loopFiber = await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SessionPersistenceJsonl, { root }) ctx.llm.registerAdapter(['mock'], new MockAdapter([textResponse('next')])) @@ -445,7 +440,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -499,7 +493,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -529,7 +522,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentExecutionProvider) await ctx2.plugin(AgentLoop, { agents: [] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], adapter2) @@ -560,7 +552,6 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) await expect(ctx.agents.resume({ resumeSessionId: SessionId('nope') })) diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index aba59c8a68..73ee48f7a6 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -8,7 +8,6 @@ import AgentRegistry, { agentEvents, assembleContextFor } from '@deepseek-ai/dsh import type { Agent } from '@deepseek-ai/dsh-agent' import { scopeOf } from '@deepseek-ai/dsh-scope' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -20,7 +19,6 @@ async function harnessWithLoop(adapter: MockAdapter = new MockAdapter([textRespo await ctx.plugin(SystemPrompt, { persona: 'You are the deployment.' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) const loopFiber = await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return { ctx, loopFiber } diff --git a/packages/core/agent-loop/tests/tool-calls.spec.ts b/packages/core/agent-loop/tests/tool-calls.spec.ts index c8794d49e9..84c2fb34eb 100644 --- a/packages/core/agent-loop/tests/tool-calls.spec.ts +++ b/packages/core/agent-loop/tests/tool-calls.spec.ts @@ -11,7 +11,6 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import LlmService from '@deepseek-ai/dsh-llm' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -22,7 +21,6 @@ async function harness(adapter: MockAdapter, maxParallelToolCalls?: number) { await ctx.plugin(SystemPrompt, { persona: '' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [], ...maxParallelToolCalls === undefined ? {} : { maxParallelToolCalls }, @@ -346,7 +344,6 @@ describe('tool-call scheduler: rolling pool honors maxParallelToolCalls', () => await ctx.plugin(SystemPrompt, { persona: '' }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [], maxParallelToolCalls: 1 }) ctx.llm.registerAdapter(['mock'], adapter) const gated = gatedParallelTool('p') diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index 3346591811..a4b5f82c4a 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -14,7 +14,6 @@ import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' @@ -25,7 +24,6 @@ async function harness(adapter: MockAdapter, toolOrder?: SystemPromptConfig['too await ctx.plugin(SystemPrompt, { persona: 'stable base', ...toolOrder !== undefined ? { toolOrder } : {} }) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index 9920cb1c29..8bbd26f2ac 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -5,7 +5,6 @@ import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-se import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent, type ContinuationStop } from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' @@ -18,7 +17,6 @@ async function harness(adapter: MockAdapter): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(Invariants) - await ctx.plugin(AgentExecutionProvider) await ctx.plugin(AgentLoop, { agents: [] }) ctx.llm.registerAdapter(['mock'], adapter) return ctx diff --git a/packages/core/agent-loop/tsconfig.json b/packages/core/agent-loop/tsconfig.json index 1e17efa41f..5d7cf98bb7 100644 --- a/packages/core/agent-loop/tsconfig.json +++ b/packages/core/agent-loop/tsconfig.json @@ -35,9 +35,6 @@ { "path": "../../core/agent" }, - { - "path": "../../core/agent-execution" - }, { "path": "../../core/scope" } diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 122e58f39d..23d9d998c6 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -1,10 +1,10 @@ # dsh-agent -Agent interface, registry, and `agent/*` event vocabulary. Every plugin (UI, hooks, orchestrators) programs against the `Agent` handle defined here — it has zero loop dependency, so the loop is swappable. +Agent interface, registry, process-local initiator scope, and `agent/*` event vocabulary. Every plugin (UI, hooks, orchestrators) programs against the `Agent` handle defined here — it has zero loop dependency, so the loop is swappable. ## Service: `AgentRegistry` (ctx key: `agents`) -Tracks live agents so UI, hook, and orchestrator plugins can find them without importing the concrete loop package. +Tracks live agents and carries the initiating Agent through asynchronous driver work without importing the concrete loop package. ### Public API @@ -17,6 +17,17 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. +#### Initiating Agent scope + +`AgentLoop` runs each concrete driver's complete lifetime inside an initiator boundary. Concurrent drivers remain isolated, a child driver shadows its parent, and the parent returns after the child settles. Creation, persistence load, and unpublished setup remain outside the child's boundary, so setup initiated by a parent inherits the parent while `agentCtx.agent` identifies the child explicitly. + +- `ctx.agents.currentInitiator(): Agent | undefined` — read the inherited initiator without requiring one. +- `ctx.agents.requireInitiator(): Agent` — read it or throw `no initiating agent is active`. +- `ctx.agents.withInitiator(agent, operation)` — run with one exact Agent and preserve the operation's exact synchronous value or Promise. +- `ctx.agents.withoutInitiator(operation)` — hide an inherited initiator for unrelated process-local work. + +The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. The [initiator-scope decision](../../../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract. + #### Factory seam (creation) Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-agent-loop`), registered via `setFactory`. This keeps creation on the `dsh-agent` interface so consumers (UI, the ACP bridge) program against `ctx.agents` without depending on the concrete loop package. The registry canonicalizes an already traced Service to its concrete target and re-traces each call through the caller's context; this avoids nested Cordis shadows while passing an explicit caller-bound `ownerCtx` to plain factories. @@ -72,6 +83,8 @@ The handle every plugin programs against: ## Known Limitations and Deferred Work +- **Initiator scope is process-local** — workers, child processes, HTTP, durable queues, and restarts materialize any required identity explicitly. +- **Ambient identity may outlive liveness** — consumers still check `agent.status`, cancellation, and the owning capability contract before lifecycle-sensitive work. - **Inter-agent channels beyond delegation** — shared state, streaming child output, and background/poll semantics remain outside the current synchronous `ctx.subagents` seam. - **`agent/session-start` cannot gate startup** — it remains a synchronous, veto-less notification; async composition that must finish before publication belongs in the factory's `setup(agentCtx)` transaction instead. - **No public step-only abort** — `cancel()` clears ALL pending work (queued + steering + in-flight); an abort that preserves queued prompts returns only with a named consumer ([stop-surface RFC](../../../docs/rfc/implemented/simplification/2026-06-20-public-agent-stop-surface.md)). diff --git a/packages/core/agent/package.json b/packages/core/agent/package.json index 72cd18942e..bcf75ea7ca 100644 --- a/packages/core/agent/package.json +++ b/packages/core/agent/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-agent", - "description": "Agent interface, registry, and event vocabulary for the DeepSeek Harness", + "description": "Agent interface, registry, initiator scope, and event vocabulary for the DeepSeek Harness", "version": "0.0.1", "private": true, "type": "module", diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 8a9ed68ab6..f2e774223d 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -1,11 +1,13 @@ /** - * Agent registry service. Tracks live agents so plugins can find them without - * depending on the concrete loop package. Agent creation belongs to the loop. + * Agent service: live registry, factory delegation, and process-local + * initiator scope. Concrete creation and driving belong to the loop. * * @module @deepseek-ai/dsh-agent */ import { Context, getTraceable, Service, symbols } from 'cordis' +import { AsyncLocalStorage } from 'node:async_hooks' +import { isPromise } from 'node:util/types' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session' @@ -173,6 +175,8 @@ export interface AgentFactory { /** Thrown when create/resume is called before an agent factory is registered. */ const NO_FACTORY_MESSAGE = 'no agent factory registered (load an agent-loop plugin)' +const NO_INITIATOR_MESSAGE = 'no initiating agent is active' +const DISPOSED_INITIATOR_MESSAGE = 'agent initiator scope is disposed' /** All mutable lifecycle state for one exact registry entry. */ interface AgentEntry { @@ -192,15 +196,19 @@ interface FactorySlot { } /** - * Agent registry (`ctx.agents`): tracks live agents so UI, hook, and - * orchestrator plugins can find them without depending on the concrete loop - * package. Agent *creation* is provided by whichever plugin implements the - * {@link AgentFactory} (`@deepseek-ai/dsh-agent-loop`), registered via - * {@link setFactory}. + * Agent service (`ctx.agents`): tracks live agents and carries the initiating + * Agent through one process-local asynchronous driver chain. Agent *creation* + * is provided by whichever plugin implements the {@link AgentFactory} + * (`@deepseek-ai/dsh-agent-loop`), registered via {@link setFactory}. */ export class AgentRegistry extends Service { private store = new Map() private factory: FactorySlot | undefined + private readonly initiators = new AsyncLocalStorage() + private initiatorState: 'active' | 'closing' | 'disposed' = 'active' + private activeInitiatorRuns = 0 + private initiatorDrain: PromiseWithResolvers | undefined + private initiatorDisposal: Promise | undefined constructor(ctx: Context) { super(ctx, 'agents') @@ -211,6 +219,54 @@ export class AgentRegistry extends Service { // accessor body never needs to resolve a scope itself. Effect-scoped: // unwinds with this service's fiber. ctx.accessor('agent', { get: () => undefined }) + ctx.effect(function* (this: AgentRegistry) { + yield () => this.disposeInitiators() + yield () => { this.closeInitiators() } + }.bind(this), 'agents.initiatorLifecycle()') + } + + /** + * Read the Agent that initiated the inherited asynchronous driver chain. + * @returns the inherited Agent, or `undefined` outside a driver and inside an explicit clearing boundary. + * @throws when this service instance has been disposed. + */ + currentInitiator(): Agent | undefined { + this.assertInitiatorsReadable() + return this.initiators.getStore() + } + + /** + * Read the initiating Agent and fail when no driver boundary is active. + * @returns the inherited Agent. + * @throws when no initiator is active or this service instance has been disposed. + */ + requireInitiator(): Agent { + const agent = this.currentInitiator() + if (agent === undefined) throw new Error(NO_INITIATOR_MESSAGE) + return agent + } + + /** + * Run an operation with one exact Agent as its process-local initiator. The + * exact synchronous value or Promise returned by the operation is preserved. + * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization. + * @param operation - synchronous or asynchronous operation to invoke. + * @returns the exact value returned by `operation`. + * @throws when the initiator scope is closing/disposed, or when `operation` throws. + */ + withInitiator(agent: Agent, operation: () => T): T { + return this.runWithInitiator(agent, operation) + } + + /** + * Run an operation inside a boundary that hides any inherited initiating + * Agent. The exact synchronous value or Promise is preserved. + * @param operation - synchronous or asynchronous operation to invoke without an initiator. + * @returns the exact value returned by `operation`. + * @throws when the initiator scope is closing/disposed, or when `operation` throws. + */ + withoutInitiator(operation: () => T): T { + return this.runWithInitiator(undefined, operation) } /** @@ -471,6 +527,57 @@ export class AgentRegistry extends Service { .filter(entry => entry.owner === undefined) .map(entry => entry.agent) } + + /** Reject new initiator boundaries while inherited continuations drain. */ + private closeInitiators(): void { + if (this.initiatorState === 'active') this.initiatorState = 'closing' + } + + /** Wait for returned-Promise boundaries, then invalidate retained references. */ + private disposeInitiators(): Promise { + return (this.initiatorDisposal ??= (async () => { + this.closeInitiators() + if (this.activeInitiatorRuns !== 0) { + this.initiatorDrain ??= Promise.withResolvers() + await this.initiatorDrain.promise + } + this.initiatorState = 'disposed' + this.initiators.disable() + })()) + } + + /** Establish one tracked initiator or clearing boundary. */ + private runWithInitiator(agent: Agent | undefined, operation: () => T): T { + if (this.initiatorState !== 'active') throw new Error(DISPOSED_INITIATOR_MESSAGE) + this.activeInitiatorRuns += 1 + let result: T + try { + result = this.initiators.run(agent, operation) + } catch (error: unknown) { + this.releaseInitiatorRun() + throw error + } + if (isPromise(result)) { + void result.then( + () => { this.releaseInitiatorRun() }, + () => { this.releaseInitiatorRun() }, + ) + } else { + this.releaseInitiatorRun() + } + return result + } + + private assertInitiatorsReadable(): void { + if (this.initiatorState === 'disposed') throw new Error(DISPOSED_INITIATOR_MESSAGE) + } + + private releaseInitiatorRun(): void { + this.activeInitiatorRuns -= 1 + if (this.activeInitiatorRuns !== 0) return + this.initiatorDrain?.resolve() + this.initiatorDrain = undefined + } } export default AgentRegistry diff --git a/packages/core/agent/tests/agent-initiator.spec.ts b/packages/core/agent/tests/agent-initiator.spec.ts new file mode 100644 index 0000000000..87a8387e07 --- /dev/null +++ b/packages/core/agent/tests/agent-initiator.spec.ts @@ -0,0 +1,163 @@ +import { describe, expect, it } from 'vitest' +import { Context } from 'cordis' +import { runInNewContext } from 'node:vm' +import AgentRegistry from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import { SessionId } from '@deepseek-ai/dsh-session' + +function agent(id: string): Agent { + return { id: SessionId(id) } as Agent +} + +async function harness(): Promise<{ + ctx: Context + service: AgentRegistry + dispose: () => Promise +}> { + const ctx = new Context() + const fiber = await ctx.plugin(AgentRegistry) + return { + ctx, + service: ctx.agents, + dispose: fiber.dispose, + } +} + +describe('AgentRegistry initiator scope', () => { + it('reports an absent initiator and requires an active boundary', async () => { + const { service, dispose } = await harness() + expect(service.currentInitiator()).toBeUndefined() + expect(() => service.requireInitiator()).toThrow('no initiating agent is active') + await dispose() + }) + + it('preserves exact synchronous and Promise return identities across await', async () => { + const { service, dispose } = await harness() + const initiator = agent('identity') + const value = { result: true } + expect(service.withInitiator(initiator, () => { + expect(service.requireInitiator()).toBe(initiator) + return value + })).toBe(value) + + const promise = service.withInitiator(initiator, async () => { + expect(service.requireInitiator()).toBe(initiator) + await Promise.resolve() + expect(service.requireInitiator()).toBe(initiator) + return value + }) + expect(service.withInitiator(initiator, () => promise)).toBe(promise) + await expect(promise).resolves.toBe(value) + expect(service.currentInitiator()).toBeUndefined() + await dispose() + }) + + it('isolates overlapping initiators', async () => { + const { service, dispose } = await harness() + const a = agent('a') + const b = agent('b') + const bothStarted = Promise.withResolvers() + const release = Promise.withResolvers() + let starts = 0 + const run = (initiator: Agent): Promise => service.withInitiator(initiator, async () => { + expect(service.requireInitiator()).toBe(initiator) + starts += 1 + if (starts === 2) bothStarted.resolve(true) + await release.promise + expect(service.requireInitiator()).toBe(initiator) + }) + + const pending = [run(a), run(b)] + await bothStarted.promise + expect(service.currentInitiator()).toBeUndefined() + release.resolve(true) + await Promise.all(pending) + await dispose() + }) + + it('restores nested and explicitly cleared boundaries', async () => { + const { service, dispose } = await harness() + const parent = agent('parent') + const child = agent('child') + + service.withInitiator(parent, () => { + expect(service.requireInitiator()).toBe(parent) + service.withInitiator(child, () => { expect(service.requireInitiator()).toBe(child) }) + expect(service.requireInitiator()).toBe(parent) + service.withoutInitiator(() => { + expect(service.currentInitiator()).toBeUndefined() + expect(() => service.requireInitiator()).toThrow('no initiating agent is active') + }) + expect(service.requireInitiator()).toBe(parent) + }) + expect(service.currentInitiator()).toBeUndefined() + await dispose() + }) + + it('restores the parent after synchronous throws and rejected operations', async () => { + const { service, dispose } = await harness() + const parent = agent('parent') + const child = agent('child') + const syncError = new Error('sync failure') + const asyncError = new Error('async failure') + + service.withInitiator(parent, () => { + expect(() => service.withInitiator(child, () => { throw syncError })).toThrow(syncError) + expect(service.requireInitiator()).toBe(parent) + }) + await expect(service.withInitiator(child, async () => { + await Promise.resolve() + throw asyncError + })).rejects.toBe(asyncError) + expect(service.currentInitiator()).toBeUndefined() + await dispose() + }) + + it('stops new boundaries, drains active Promises, and invalidates retained references', async () => { + const { ctx, service, dispose } = await harness() + const initiator = agent('draining') + const release = Promise.withResolvers() + const pending = service.withInitiator(initiator, async () => { + await release.promise + expect(service.requireInitiator()).toBe(initiator) + }) + let disposed = false + const disposal = dispose().then(() => { disposed = true }) + await Promise.resolve() + + expect(() => service.withInitiator(initiator, () => 1)).toThrow('agent initiator scope is disposed') + expect(() => service.withoutInitiator(() => 1)).toThrow('agent initiator scope is disposed') + expect(disposed).toBe(false) + expect(ctx.get('agents')).toBeUndefined() + release.resolve(true) + await pending + await disposal + expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed') + expect(() => service.requireInitiator()).toThrow('agent initiator scope is disposed') + }) + + it('drains cross-realm Promise boundaries before disposal', async () => { + const { service, dispose } = await harness() + const initiator = agent('cross-realm') + const release = Promise.withResolvers() + const operation = runInNewContext( + '(async () => { await release; inspect() })', + { + release: release.promise, + inspect: () => { expect(service.requireInitiator()).toBe(initiator) }, + }, + ) as () => Promise + const pending = service.withInitiator(initiator, operation) + expect(pending).not.toBeInstanceOf(Promise) + + let disposed = false + const disposal = dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) + + release.resolve(true) + await pending + await disposal + expect(disposed).toBe(true) + }) +}) diff --git a/packages/core/agent/tests/gen-cordis-catalog.spec.ts b/packages/core/agent/tests/gen-cordis-catalog.spec.ts index 53847b0e97..24841c8c8e 100644 --- a/packages/core/agent/tests/gen-cordis-catalog.spec.ts +++ b/packages/core/agent/tests/gen-cordis-catalog.spec.ts @@ -6,7 +6,7 @@ import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' import { afterEach, describe, expect, it } from 'vitest' -import { collectEvents, collectServices } from '../../../../scripts/gen-cordis-catalog.ts' +import { collectEvents, collectServices, renderEvents, renderServices } from '../../../../scripts/gen-cordis-catalog.ts' /** Write a fixture package exposing one `interface Events` block and return the * scan root to hand `collectEvents`. */ @@ -58,6 +58,8 @@ describe('gen-cordis-catalog collectEvents', () => { )) expect(events).toHaveLength(1) expect(events[0]).toMatchObject({ name: 'fix/happened', scope: 'fix', mode: 'emit', doc: 'A thing happened.' }) + expect(events[0]?.jsDoc).toBe('/**\n * A thing happened.\n * @param id - which thing.\n * @mode emit\n */') + expect(renderEvents(events)).toContain("```ts cordis-catalog\n/**\n * A thing happened.\n * @param id - which thing.\n * @mode emit\n */\n'fix/happened'(id: string): void\n```") }) it('classifies a trailing-next signature as a waterfall', () => { @@ -158,26 +160,11 @@ export class FixService { expect(services).toHaveLength(1) expect(services[0]).toMatchObject({ key: 'fix', type: 'FixService', abstract: false, doc: 'Fixture service.' }) expect(services[0]?.methods).toHaveLength(3) - }) - - it('extracts an interface service as an abstract seam', () => { - const services = collectServices(makeService(`/** Fixture service interface. */ -export interface FixService { - /** - * Do the thing. - * @param id - which thing to do. - * @returns the outcome of doing it. - */ - run(id: string): string -}`)) - expect(services).toHaveLength(1) - expect(services[0]).toMatchObject({ - key: 'fix', - type: 'FixService', - abstract: true, - doc: 'Fixture service interface.', + expect(services[0]?.methods[0]).toEqual({ + signature: 'run(id: string): string', + jsDoc: '/**\n * Do the thing.\n * @param id - which thing to do.\n * @returns the outcome of doing it.\n */', }) - expect(services[0]?.methods).toEqual(['run(id: string): string']) + expect(renderServices(services)).toContain('```ts cordis-catalog\n/**\n * Do the thing.\n * @param id - which thing to do.\n * @returns the outcome of doing it.\n */\nrun(id: string): string\n\n/** Fire and forget (void needs no @returns). */\npoke(): void') }) it('hard-errors on a public method with no JSDoc at all', () => { diff --git a/packages/examples/agent-spine-demo/README.md b/packages/examples/agent-spine-demo/README.md index 794df27760..409aef5ef2 100644 --- a/packages/examples/agent-spine-demo/README.md +++ b/packages/examples/agent-spine-demo/README.md @@ -16,8 +16,7 @@ Read this package for the whole plugin tree and its composition order. @deepseek-ai/dsh-tools registry + guarded pre/around/post/final-result pipeline @deepseek-ai/dsh-skill skill provider registry @deepseek-ai/dsh-skill-local local filesystem skill provider -@deepseek-ai/dsh-agent agent registry + agent/* event vocabulary -@deepseek-ai/dsh-agent-execution process-local ambient Agent execution context +@deepseek-ai/dsh-agent agent registry + initiator scope + agent/* events @deepseek-ai/dsh-tasks generic background-task registry @deepseek-ai/dsh-invariants dev-mode event-contract assertions @deepseek-ai/dsh-tool-bash the model-facing bash schema diff --git a/packages/examples/agent-spine-demo/package.json b/packages/examples/agent-spine-demo/package.json index 7d78b5eddb..772d6c059b 100644 --- a/packages/examples/agent-spine-demo/package.json +++ b/packages/examples/agent-spine-demo/package.json @@ -1,6 +1,6 @@ { "name": "@deepseek-ai/dsh-agent-spine-demo", - "description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + skills + agents + agent-execution + tasks + invariants + tool-bash + workspace-context + tool-skill + tool-tasks + agent-loop)", + "description": "The default executor-less/UI-less agent spine as one Cordis bundle plugin (timer + llm + sessions + system-prompt + tools + skills + agents + tasks + invariants + tool-bash + workspace-context + tool-skill + tool-tasks + agent-loop)", "version": "0.0.1", "private": true, "type": "module", @@ -24,7 +24,6 @@ "peerDependencies": { "@cordisjs/plugin-timer": "^1.1.2", "@deepseek-ai/dsh-agent": "^0.0.1", - "@deepseek-ai/dsh-agent-execution": "^0.0.1", "@deepseek-ai/dsh-agent-loop": "^0.0.1", "@deepseek-ai/dsh-invariants": "^0.0.1", "@deepseek-ai/dsh-home": "^0.0.1", @@ -44,7 +43,6 @@ "devDependencies": { "@cordisjs/plugin-timer": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", diff --git a/packages/examples/agent-spine-demo/src/index.ts b/packages/examples/agent-spine-demo/src/index.ts index 338c09b586..a4965ca457 100644 --- a/packages/examples/agent-spine-demo/src/index.ts +++ b/packages/examples/agent-spine-demo/src/index.ts @@ -18,7 +18,6 @@ import ToolRegistry, { type Config as ToolsConfig } from '@deepseek-ai/dsh-tools import SkillService, { type Config as SkillRegistryConfig } from '@deepseek-ai/dsh-skill' import * as SkillLocal from '@deepseek-ai/dsh-skill-local' import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import TaskService from '@deepseek-ai/dsh-tasks' import * as invariants from '@deepseek-ai/dsh-invariants' import * as toolBash from '@deepseek-ai/dsh-tool-bash' @@ -154,7 +153,6 @@ export function apply(ctx: Context, config: Config): void { ctx.plugin(SkillService, config.skills?.registry ?? {}) ctx.plugin(SkillLocal, Object.assign({}, config.skills?.local, { dshHome })) ctx.plugin(AgentRegistry) - ctx.plugin(AgentExecutionProvider) ctx.plugin(TaskService) ctx.plugin(invariants) ctx.plugin(toolBash, Object.assign({}, config.toolBash, { dshHome })) diff --git a/packages/examples/agent-spine-demo/tsconfig.json b/packages/examples/agent-spine-demo/tsconfig.json index d1e01cf84c..89cb2accd8 100644 --- a/packages/examples/agent-spine-demo/tsconfig.json +++ b/packages/examples/agent-spine-demo/tsconfig.json @@ -41,9 +41,6 @@ { "path": "../../core/agent" }, - { - "path": "../../core/agent-execution" - }, { "path": "../../context/workspace-context" }, diff --git a/packages/sdk/helper/src/features/builtin/spine.ts b/packages/sdk/helper/src/features/builtin/spine.ts index d2fb877ec4..caf066865e 100644 --- a/packages/sdk/helper/src/features/builtin/spine.ts +++ b/packages/sdk/helper/src/features/builtin/spine.ts @@ -36,10 +36,6 @@ class SpineOption extends FeatureOption { }, ['persona'], config => requiredString(config, 'persona')), ...npmCordisConfigEntry(ID, { id: 'tools', name: '@deepseek-ai/dsh-tools' }, []), ...npmCordisConfigEntry(ID, { id: 'agent', name: '@deepseek-ai/dsh-agent' }), - ...npmCordisConfigEntry(ID, { - id: 'agent-execution', - name: '@deepseek-ai/dsh-agent-execution', - }), ...npmCordisConfigEntry(ID, { id: 'invariants', name: '@deepseek-ai/dsh-invariants' }), ...npmCordisConfigEntry(ID, { id: 'agent-loop', diff --git a/packages/support/agent-loop-testkit/README.md b/packages/support/agent-loop-testkit/README.md index cad60b21a4..350a8643e1 100644 --- a/packages/support/agent-loop-testkit/README.md +++ b/packages/support/agent-loop-testkit/README.md @@ -1,6 +1,6 @@ # `@deepseek-ai/dsh-agent-loop-testkit` -Shared prerequisite mounting for tests that exercise the concrete `AgentLoop`. `mountAgentLoopTestDependencies(ctx, options?)` installs the LLM, session, system-prompt, tool, agent, and agent-execution services in dependency order, then returns before the loop is mounted. +Shared prerequisite mounting for tests that exercise the concrete `AgentLoop`. `mountAgentLoopTestDependencies(ctx, options?)` installs the LLM, session, system-prompt, tool, and agent services in dependency order, then returns before the loop is mounted. The caller registers adapters and optional plugins, mounts `AgentLoop` with the configuration under test, and disposes its own Context. System-prompt and tool-registry configuration can be forwarded through `options`; the helper does not provide test defaults beyond those owned by the services. A plugin-load failure rejects the helper call, while services activated earlier in the sequence remain owned by the caller's Context. diff --git a/packages/support/agent-loop-testkit/package.json b/packages/support/agent-loop-testkit/package.json index 712631ab29..423bd3e80d 100644 --- a/packages/support/agent-loop-testkit/package.json +++ b/packages/support/agent-loop-testkit/package.json @@ -23,7 +23,6 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", - "@deepseek-ai/dsh-agent-execution": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-system-prompt": "^0.0.1", @@ -32,7 +31,6 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/support/agent-loop-testkit/src/index.ts b/packages/support/agent-loop-testkit/src/index.ts index 32549dbc2d..c7b0cb7304 100644 --- a/packages/support/agent-loop-testkit/src/index.ts +++ b/packages/support/agent-loop-testkit/src/index.ts @@ -7,7 +7,6 @@ import type { Context } from 'cordis' import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -44,5 +43,4 @@ export async function mountAgentLoopTestDependencies( await ctx.plugin(SystemPrompt, options.systemPrompt ?? {}) await ctx.plugin(ToolRegistry, options.tools ?? {}) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentExecutionProvider) } diff --git a/packages/support/agent-loop-testkit/tsconfig.json b/packages/support/agent-loop-testkit/tsconfig.json index f8eddb5693..5e5b3c47f2 100644 --- a/packages/support/agent-loop-testkit/tsconfig.json +++ b/packages/support/agent-loop-testkit/tsconfig.json @@ -17,9 +17,6 @@ { "path": "../../core/agent" }, - { - "path": "../../core/agent-execution" - }, { "path": "../../llm/llm" }, diff --git a/packages/workflow/workflow-workerthread/package.json b/packages/workflow/workflow-workerthread/package.json index 7ccfbc3ebb..1cd6e07e17 100644 --- a/packages/workflow/workflow-workerthread/package.json +++ b/packages/workflow/workflow-workerthread/package.json @@ -41,7 +41,6 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", "@deepseek-ai/dsh-brand": "workspace:^", diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index cbde053d45..680b2e25c7 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -5,7 +5,6 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' -import AgentExecutionProvider from '@deepseek-ai/dsh-agent-execution' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import SubagentService from '@deepseek-ai/dsh-subagent' @@ -35,7 +34,6 @@ async function harness(): Promise { await built.plugin(SystemPrompt) await built.plugin(ToolRegistry) await built.plugin(AgentRegistry) - await built.plugin(AgentExecutionProvider) await built.plugin(AgentLoop, { agents: [] }) await built.plugin(LlmDeepSeek) await built.plugin(SubagentService) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index b54201c207..6c7e4a3d05 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -435,9 +435,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent - '@deepseek-ai/dsh-agent-execution': - specifier: workspace:^ - version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -533,15 +530,6 @@ importers: specifier: ^4.0.0-rc.7 version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) - packages/core/agent-execution: - devDependencies: - '@deepseek-ai/dsh-agent': - specifier: workspace:^ - version: link:../agent - cordis: - specifier: ^4.0.0-rc.7 - version: 4.0.0-rc.7(@cordisjs/plugin-include@1.0.4)(@cordisjs/plugin-loader@1.0.0-rc.5) - packages/core/agent-loop: dependencies: schemastery: @@ -551,9 +539,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../agent - '@deepseek-ai/dsh-agent-execution': - specifier: workspace:^ - version: link:../agent-execution '@deepseek-ai/dsh-invariants': specifier: workspace:^ version: link:../../support/invariants @@ -704,9 +689,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent - '@deepseek-ai/dsh-agent-execution': - specifier: workspace:^ - version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -1698,9 +1680,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent - '@deepseek-ai/dsh-agent-execution': - specifier: workspace:^ - version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -2353,9 +2332,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent - '@deepseek-ai/dsh-agent-execution': - specifier: workspace:^ - version: link:../../core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../core/agent-loop @@ -2413,9 +2389,6 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../packages/core/agent - '@deepseek-ai/dsh-agent-execution': - specifier: workspace:^ - version: link:../../packages/core/agent-execution '@deepseek-ai/dsh-agent-loop': specifier: workspace:^ version: link:../../packages/core/agent-loop diff --git a/python/sdk-runtime/package.json b/python/sdk-runtime/package.json index f2646835d6..2d3560ec5c 100644 --- a/python/sdk-runtime/package.json +++ b/python/sdk-runtime/package.json @@ -10,7 +10,6 @@ "@cordisjs/plugin-timer": "workspace:^", "@deepseek-ai/dsh-acp": "workspace:^", "@deepseek-ai/dsh-agent": "workspace:^", - "@deepseek-ai/dsh-agent-execution": "workspace:^", "@deepseek-ai/dsh-agent-spine-demo": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-app-boot": "workspace:^", diff --git a/scripts/cordis-walk.ts b/scripts/cordis-walk.ts index 617fd34bd5..44e87b2a21 100644 --- a/scripts/cordis-walk.ts +++ b/scripts/cordis-walk.ts @@ -2,7 +2,7 @@ * Shared AST walkers for the cordis documentation generators * (`gen-cordis-catalog.ts`, `gen-website-api.ts`): locating the cordis module * merge in a source file, enumerating its `interface Events` members, and - * resolving the `interface Context` service keys to their service declarations. + * resolving the `interface Context` service keys to their service classes. * One walk, two renderers — the catalog and the website page carry different * prose but must agree on WHAT exists. */ @@ -50,50 +50,45 @@ function contextKeyMap(body: ts.ModuleBlock, sf: ts.SourceFile): Map` service declaration resolved from a Context merge. */ -export interface ServiceDeclaration { +/** One `ctx.` service class resolved from a Context merge. */ +export interface ServiceClass { key: string type: string - declaration: ts.ClassDeclaration | ts.InterfaceDeclaration + cls: ts.ClassDeclaration abstract: boolean - /** Declaration-level JSDoc prose (empty string when missing — also reported). */ + /** Class-level JSDoc prose (empty string when missing — also reported). */ doc: string } /** - * Resolve each `ctx.` of a merge to the service class or interface declared in the + * Resolve each `ctx.` of a merge to the service class declared in the * same file. A key whose type is not a class here (a Pick-mixin member, e.g. - * timer helpers) is skipped. A declaration without JSDoc prose is reported into + * timer helpers) is skipped. A class without JSDoc prose is reported into * `violations` (named `where` by the caller's gate). * * @param body — the cordis module merge body. * @param sf — the source file containing the merge. * @param rel — repo-relative path of `sf`, for violation pointers. * @param violations — sink for JSDoc-completeness violations. - * @returns the resolved service declarations, in Context-declaration order. + * @returns the resolved service classes, in Context-declaration order. */ -export function serviceDeclarations( +export function serviceClasses( body: ts.ModuleBlock, sf: ts.SourceFile, rel: string, violations: string[], -): ServiceDeclaration[] { +): ServiceClass[] { const text = sf.getFullText() - const out: ServiceDeclaration[] = [] + const out: ServiceClass[] = [] for (const [key, type] of contextKeyMap(body, sf)) { - const declaration = sf.statements.find( - (s): s is ts.ClassDeclaration | ts.InterfaceDeclaration => - (ts.isClassDeclaration(s) || ts.isInterfaceDeclaration(s)) && s.name?.text === type, + const cls = sf.statements.find( + (s): s is ts.ClassDeclaration => ts.isClassDeclaration(s) && s.name?.text === type, ) - if (!declaration) continue // a Pick-mixin member, not a service declaration here - const abstract = ts.isInterfaceDeclaration(declaration) - || (declaration.modifiers?.some(m => m.kind === ts.SyntaxKind.AbstractKeyword) ?? false) - const doc = parseJsDoc(rawJsDoc(text, declaration)).doc - if (!doc) { - const kind = ts.isInterfaceDeclaration(declaration) ? 'interface' : 'class' - violations.push(`service ctx.${key} (${pointer(rel, sf, declaration)}): ${kind} ${type} has no JSDoc.`) - } - out.push({ key, type, declaration, abstract, doc }) + if (!cls) continue // a Pick-mixin member, not a class here + const abstract = cls.modifiers?.some(m => m.kind === ts.SyntaxKind.AbstractKeyword) ?? false + const doc = parseJsDoc(rawJsDoc(text, cls)).doc + if (!doc) violations.push(`service ctx.${key} (${pointer(rel, sf, cls)}): class ${type} has no JSDoc.`) + out.push({ key, type, cls, abstract, doc }) } return out } diff --git a/scripts/gen-cordis-api.ts b/scripts/gen-cordis-api.ts index cc87c379e9..5d8a70fba4 100644 --- a/scripts/gen-cordis-api.ts +++ b/scripts/gen-cordis-api.ts @@ -80,7 +80,7 @@ function referencedTypes(seeds: string[], decls: Map): { name: s function render(): string { const services = collectServices() const events = collectEvents().sort((a, b) => a.name.localeCompare(b.name)) - const types = referencedTypes(services.flatMap(service => service.methods), collectTypeDecls()) + const types = referencedTypes(services.flatMap(service => service.methods.map(method => method.signature)), collectTypeDecls()) const lines: string[] = [ '/**', ' * Generated by scripts/gen-cordis-api.ts — do not edit by hand; run', @@ -145,7 +145,7 @@ function render(): string { lines.push(' methods: [],') } else { lines.push(' methods: [') - for (const method of service.methods) lines.push(` ${quote(method)},`) + for (const method of service.methods) lines.push(` ${quote(method.signature)},`) lines.push(' ],') } lines.push(' },') diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 293215a174..08f04947da 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -9,7 +9,7 @@ import { globSync, readFileSync, writeFileSync } from 'node:fs' import { resolve, sep } from 'node:path' import ts from 'typescript' import { checkParams, checkReturns, parseJsDoc, parseTags, pointer, rawJsDoc, reportViolations, type Mode } from './jsdoc.ts' -import { cordisModuleBody, eventMembers, serviceDeclarations } from './cordis-walk.ts' +import { cordisModuleBody, eventMembers, serviceClasses } from './cordis-walk.ts' const root = resolve(import.meta.dirname, '..') const OUT_EVENTS = 'docs/cordis-catalog/events.md' @@ -27,8 +27,6 @@ const FENCE = 'ts cordis-catalog' // TODO(catalog-type-links): verify or generate link-map coverage. export const LINK_MAP: Record = { Agent: 'core.md', - AgentExecution: 'core.md', - AgentExecutionService: 'core.md', ContentBlock: 'core.md', Message: 'core.md', MessageSource: 'core.md', @@ -74,6 +72,8 @@ interface EventEntry { scope: string /** Full signature text (the method-signature member, JSDoc stripped). */ signature: string + /** Original declaration JSDoc, dedented from its containing interface. */ + jsDoc: string /** Dispatch mode from the `@mode` tag. */ mode: Mode /** Description prose (JSDoc minus the `@mode` tag), one line per paragraph. */ @@ -82,19 +82,27 @@ interface EventEntry { source: string } +/** One public service method and the source contract attached to it. */ +interface ServiceMethodEntry { + /** Public method signature (body stripped). */ + signature: string + /** Original method JSDoc, dedented from its containing class. */ + jsDoc: string +} + /** One harness service, extracted from an `interface Context` block. */ interface ServiceEntry { /** The `ctx.` name, e.g. `llm`. */ key: string /** The service class/interface name, e.g. `LlmService`. */ type: string - /** Whether the service declaration is abstract (a seam interface). */ + /** Whether the service class is abstract (a seam interface). */ abstract: boolean - /** Declaration-level JSDoc prose, one line per paragraph. */ + /** Class-level JSDoc prose, one line per paragraph. */ doc: string - /** Public method signatures (bodies stripped), in source order. */ - methods: string[] - /** Source pointer of the service declaration. */ + /** Public methods (bodies stripped), in source order. */ + methods: ServiceMethodEntry[] + /** Source pointer of the class declaration. */ source: string } @@ -117,6 +125,22 @@ function memberSignature(member: ts.TypeElement | ts.ClassElement, sf: ts.Source return sig.replace(/\s*;?\s*$/, '').replace(/\s+/g, ' ').trim() } +/** + * Copy a node's original JSDoc while removing only the indentation imposed by + * its containing interface or class. + */ +function jsDocText(text: string, sf: ts.SourceFile, node: ts.Node): string { + const raw = rawJsDoc(text, node) + if (!raw) return '' + const start = text.lastIndexOf(raw, node.getStart(sf)) + const { line } = sf.getLineAndCharacterOfPosition(start) + const lineStart = sf.getPositionOfLineAndCharacter(line, 0) + const indent = text.slice(lineStart, start) + return raw.split('\n') + .map((lineText, index) => index > 0 && lineText.startsWith(indent) ? lineText.slice(indent.length) : lineText) + .join('\n') +} + /** Walk every harness `interface Events` block and extract its events, hard- * erroring (aggregated) on any JSDoc-completeness violation: a missing/ * contradicted `@mode`, missing description prose, or an undocumented payload @@ -157,15 +181,15 @@ export function collectEvents(scanRoot: string = root): EventEntry[] { const { params } = parseTags(raw) checkParams(where, 'event', member.parameters, params, sf, p => (ts.isIdentifier(p.name) && p.name.text === 'this') || (hasNext && p === last), violations) - if (mode) entries.push({ name, scope: name.split('/')[0] ?? name, signature, mode, doc, source: src }) + if (mode) entries.push({ name, scope: name.split('/')[0] ?? name, signature, jsDoc: jsDocText(text, sf, member), mode, doc, source: src }) } } reportViolations('gen-cordis-catalog', violations) return entries } -/** Walk every harness `interface Context` block + its service declaration, hard- - * erroring (aggregated) on any JSDoc-completeness violation: a declaration or public +/** Walk every harness `interface Context` block + its service class, hard- + * erroring (aggregated) on any JSDoc-completeness violation: a class or public * method without JSDoc prose, an undocumented parameter, a stale `@param`, a * missing `@returns` on a non-void method, or an inferred (unannotated) return * type the pure-AST walk cannot classify. @@ -180,11 +204,11 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { const sf = ts.createSourceFile(abs, text, ts.ScriptTarget.Latest, true) const body = cordisModuleBody(sf) if (!body) continue - // Resolve each ctx key to its service declaration (shared walk) and emit an entry. - for (const { key, type, declaration, abstract, doc: declarationDoc } of serviceDeclarations(body, sf, rel, violations)) { - const methods: string[] = [] - for (const member of declaration.members) { - if (!ts.isMethodDeclaration(member) && !ts.isMethodSignature(member)) continue + // Resolve each ctx key to its service class (shared walk) and emit an entry. + for (const { key, type, cls, abstract, doc: clsDoc } of serviceClasses(body, sf, rel, violations)) { + const methods: ServiceMethodEntry[] = [] + for (const member of cls.members) { + if (!ts.isMethodDeclaration(member)) continue // Only instance methods callable through `ctx.` are surface; // private, protected, and static methods are not. const nonPublic = member.modifiers?.some(m => @@ -195,9 +219,9 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { if (nonPublic) continue const memberName = member.name.getText(sf) if (memberName.startsWith('[')) continue // computed/symbol members - methods.push(memberSignature(member, sf)) const where = `service method ctx.${key}.${memberName} (${pointer(rel, sf, member)})` const raw = rawJsDoc(text, member) + methods.push({ signature: memberSignature(member, sf), jsDoc: jsDocText(text, sf, member) }) if (!raw) { violations.push(`${where} has no JSDoc.`); continue } if (!parseJsDoc(raw).doc) violations.push(`${where} has no description prose above its block tags.`) const { params, returns } = parseTags(raw) @@ -212,9 +236,9 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { key, type, abstract, - doc: declarationDoc, + doc: clsDoc, methods, - source: pointer(rel, sf, declaration), + source: pointer(rel, sf, cls), }) } } @@ -277,7 +301,7 @@ function typeLinks(signature: string): string { function renderEvent(e: EventEntry): string[] { const out = [`### \`${e.name}\` — ${e.mode}`, ''] if (e.doc) out.push(e.doc, '') - out.push('```' + FENCE, e.signature, '```', '') + out.push('```' + FENCE, e.jsDoc, e.signature, '```', '') const links = typeLinks(e.signature) if (links) out.push(links, '') out.push(`Source: [\`${e.source}\`](../../${e.source.split(':')[0]})`, '') @@ -290,8 +314,13 @@ function renderService(s: ServiceEntry): string[] { const out = [`## \`ctx.${s.key}\` — \`${s.type}\`${kind}`, ''] if (s.doc) out.push(s.doc, '') if (s.methods.length) { - out.push('```' + FENCE, ...s.methods, '```', '') - const links = typeLinks(s.methods.join('\n')) + const declarations = s.methods.flatMap((method, index) => [ + ...(index > 0 ? [''] : []), + method.jsDoc, + method.signature, + ]) + out.push('```' + FENCE, ...declarations, '```', '') + const links = typeLinks(s.methods.map(method => method.signature).join('\n')) if (links) out.push(links, '') } out.push(`Source: [\`${s.source}\`](../../${s.source.split(':')[0]})`, '') @@ -306,15 +335,15 @@ const BANNER = [ ] /** The shared GENERATED + freshness-gate + fence notice paragraph. */ -const GATE_NOTICE = 'This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence (skipped by doc-typecheck, since a bare signature is not standalone-compilable). Type names in a signature link to the page that documents them.' +const GATE_NOTICE = 'This file is GENERATED from source (`scripts/gen-cordis-catalog.ts`) and verified fresh by `pnpm run verify-cordis-catalog` (part of `doc-sync`) — do not edit it by hand. Signature blocks use a `ts cordis-catalog` fence and include the original source JSDoc immediately before each event or service method. doc-typecheck skips these bare declaration fragments; type names in a signature link to the page that documents them.' /** Render the events catalog (pure, deterministic given sorted inputs). */ -function renderEvents(events: EventEntry[]): string { +export function renderEvents(events: EventEntry[]): string { const lines: string[] = [ ...BANNER, '# Cordis Events Catalog', '', - 'Every cordis event a plugin can listen to: exact signature, dispatch mode, and the declaration\'s JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around.', + 'Every cordis event a plugin can listen to: exact signature, dispatch mode, and original declaration JSDoc. This is one axis of the **wiring** reference a plugin author works against — the callable `ctx.` surface is the sibling [services catalog](services.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around.', '', GATE_NOTICE, '', @@ -344,12 +373,12 @@ function renderEvents(events: EventEntry[]): string { } /** Render the services catalog (pure, deterministic given sorted inputs). */ -function renderServices(services: ServiceEntry[]): string { +export function renderServices(services: ServiceEntry[]): string { const lines: string[] = [ ...BANNER, '# Cordis Services Catalog', '', - 'Every `ctx.` service a plugin can call: the exact public interface plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against.', + 'Every `ctx.` service a plugin can call: the exact public interface with original method JSDoc, plus the class JSDoc. This is one axis of the **wiring** reference a plugin author works against — the events a plugin listens to are the sibling [events catalog](events.md), and [core-data-structures/](../core-data-structures/core.md) catalogs the *data structures* these signatures move around. An abstract seam (e.g. `ctx.bash`) is implemented by a separate package; the interface is what consumers code against.', '', GATE_NOTICE, '', diff --git a/scripts/gen-doc-graphs.ts b/scripts/gen-doc-graphs.ts index 94836eaefd..19a124ccdf 100644 --- a/scripts/gen-doc-graphs.ts +++ b/scripts/gen-doc-graphs.ts @@ -156,18 +156,10 @@ const SERVICE_ROLES: ServiceRole[] = [ { key: 'agents', pkg: 'agent', - title: 'Agent registry', + title: 'Agent service', mode: 'core', consumers: ['agent-loop', 'acp', 'subagent-inprocess', 'stdio-demo', 'invariants'], - note: 'Owns live Agent handles and the create/resume factory seam.', - }, - { - key: 'agentExecution', - pkg: 'agent-execution', - title: 'Agent execution context', - mode: 'core', - consumers: ['agent-loop'], - note: 'Carries the exact initiating Agent across one process-local asynchronous driver chain; explicit identities remain authoritative at external boundaries.', + note: 'Owns live Agent handles, the create/resume factory seam, and process-local initiator propagation.', }, { key: 'agentLoop', diff --git a/scripts/gen-website-api.ts b/scripts/gen-website-api.ts index bae24c3f3d..0420ad2ff3 100644 --- a/scripts/gen-website-api.ts +++ b/scripts/gen-website-api.ts @@ -35,7 +35,7 @@ import { globSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs' import { dirname, resolve } from 'node:path' import ts from 'typescript' import { checkParams, checkReturns, parseJsDoc, parseTags, pointer, rawJsDoc, reportViolations, type Mode } from './jsdoc.ts' -import { cordisModuleBody, eventMembers, serviceDeclarations } from './cordis-walk.ts' +import { cordisModuleBody, eventMembers, serviceClasses } from './cordis-walk.ts' const root = resolve(import.meta.dirname, '..') @@ -197,18 +197,6 @@ function isPublicInstance(member: ts.ClassElement): boolean { return !member.name.getText().startsWith('_') } -type HarnessServiceMember = ts.MethodDeclaration | ts.MethodSignature | ts.PropertyDeclaration - | ts.PropertySignature | ts.GetAccessorDeclaration - -/** Whether a class/interface service member is renderable public API. */ -function isPublicServiceMember(member: HarnessServiceMember): boolean { - if (ts.isMethodSignature(member) || ts.isPropertySignature(member)) { - if (ts.isComputedPropertyName(member.name)) return false - return !member.name.getText().startsWith('_') - } - return isPublicInstance(member) -} - /** Whether a class member is renderable public STATIC API. */ function isPublicStatic(member: ts.ClassElement): boolean { const mods = ts.getCombinedModifierFlags(member) @@ -465,15 +453,14 @@ function collectHarnessServices(violations: string[]): HarnessService[] { // Manifest shape is repo-owned; `name` is the one field read here. const manifest = JSON.parse(readFileSync(pkgJson, 'utf8')) as { name: string } const pkg = manifest.name - for (const { key, type, declaration, abstract, doc: declarationDoc } of serviceDeclarations(body, sf, rel, violations)) { - const groups = new Map() - for (const member of declaration.members) { + for (const { key, type, cls, abstract, doc: clsDoc } of serviceClasses(body, sf, rel, violations)) { + const groups = new Map() + for (const member of cls.members) { // Public properties are API too: ctx.codeRuntime.language/isolation // are readonly descriptors consumers key presentation off. - const renderable = ts.isMethodDeclaration(member) || ts.isMethodSignature(member) - || ts.isPropertyDeclaration(member) || ts.isPropertySignature(member) || ts.isGetAccessorDeclaration(member) + const renderable = ts.isMethodDeclaration(member) || ts.isPropertyDeclaration(member) || ts.isGetAccessorDeclaration(member) if (!renderable) continue - if (!isPublicServiceMember(member)) continue + if (!isPublicInstance(member)) continue const name = member.name.getText(sf) const group = groups.get(name) ?? [] group.push(member) @@ -481,7 +468,7 @@ function collectHarnessServices(violations: string[]): HarnessService[] { } const members = [...groups.entries()].map(([name, group]) => memberDoc(`ctx.${key}.${name} (${rel})`, name, group, rel, violations)) - services.push({ key, type, abstract, doc: declarationDoc, members, source: pointer(rel, sf, declaration), pkg }) + services.push({ key, type, abstract, doc: clsDoc, members, source: pointer(rel, sf, cls), pkg }) } } return services.sort((a, b) => a.key.localeCompare(b.key)) diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index b6a92c55f6..566bdade7b 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -15,8 +15,6 @@ { "doc": "docs/core-data-structures/core.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "InjectOptions", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "Agent", "source": "packages/core/agent/src/types.ts" }, - { "doc": "docs/core-data-structures/core.md", "symbol": "AgentExecution", "source": "packages/core/agent-execution/src/types.ts" }, - { "doc": "docs/core-data-structures/core.md", "symbol": "AgentExecutionService", "source": "packages/core/agent-execution/src/index.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "HookContext", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "PromptDecision", "source": "packages/core/agent/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContinuationDecision", "source": "packages/core/agent/src/types.ts" }, diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index f42c346678..35cd2dae1b 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -28,7 +28,6 @@ interface SentenceContract { * so an absent section cannot be mistaken for forgotten documentation. */ const NO_MODEL_EXPERIENCE_SECTION: Readonly> = { - 'packages/core/agent-execution': 'The package adds no model-visible text or schema; consumers own any use in model requests.', 'packages/core/scope': 'The package is a model-agnostic registration and lifecycle primitive; model-facing consumers own any context selection.', 'packages/util/brand': 'The package is a type-only primitive erased at compile time.', 'packages/util/paths': 'The package only resolves harness-owned host paths; model-facing consumers own any rendered use.', diff --git a/tsconfig.build.json b/tsconfig.build.json index c631871672..31a42172e4 100644 --- a/tsconfig.build.json +++ b/tsconfig.build.json @@ -25,7 +25,6 @@ { "path": "./packages/session-query/session-query" }, { "path": "./packages/core/system-prompt" }, { "path": "./packages/core/agent" }, - { "path": "./packages/core/agent-execution" }, { "path": "./packages/context/time-context" }, { "path": "./packages/ui/user-interaction" }, { "path": "./packages/ui/user-approval" }, diff --git a/tsconfig.json b/tsconfig.json index 8c8a2531c8..9d1a299b1b 100644 --- a/tsconfig.json +++ b/tsconfig.json @@ -36,7 +36,6 @@ { "path": "./packages/session-query/session-query" }, { "path": "./packages/core/system-prompt" }, { "path": "./packages/core/agent" }, - { "path": "./packages/core/agent-execution" }, { "path": "./packages/context/time-context" }, { "path": "./packages/ui/user-interaction" }, { "path": "./packages/ui/user-approval" }, diff --git a/website/.vitepress/config/api-sidebar.json b/website/.vitepress/config/api-sidebar.json index c0774e23a4..3a2b11db3c 100644 --- a/website/.vitepress/config/api-sidebar.json +++ b/website/.vitepress/config/api-sidebar.json @@ -22,10 +22,6 @@ } ], "harness": [ - { - "text": "ctx.agentExecution", - "link": "/zh-CN/api/harness/agent-execution" - }, { "text": "ctx.agentLoop", "link": "/zh-CN/api/harness/agent-loop" diff --git a/website/zh-CN/api/harness/agent-execution.md b/website/zh-CN/api/harness/agent-execution.md deleted file mode 100644 index 2276d8ecbb..0000000000 --- a/website/zh-CN/api/harness/agent-execution.md +++ /dev/null @@ -1,48 +0,0 @@ - - -# ctx.agentExecution - -`AgentExecutionService` (abstract seam) — provided by `@deepseek-ai/dsh-agent-execution`. - -Ambient Agent identity within one process-local asynchronous chain. - -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-execution/src/index.ts#L18) - -### ctx.agentExecution.current() - -```ts website-api -current(): AgentExecution | undefined -``` - -Read the active execution without requiring one. - -**Returns** the inherited execution, or `undefined` outside/inside a cleared boundary. - -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-execution/src/index.ts#L24) - -### ctx.agentExecution.require() - -```ts website-api -require(): AgentExecution -``` - -Read the active execution and fail when no boundary is active. - -**Returns** the inherited execution. - -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-execution/src/index.ts#L31) - -### ctx.agentExecution.run(execution, operation) - -```ts website-api -run(execution: AgentExecution | undefined, operation: () => T): T -``` - -Run an operation inside an execution boundary. Passing `undefined` clears an inherited execution; the exact synchronous value or Promise is returned. - -- `execution` — execution to inherit, or `undefined` for a clearing boundary. -- `operation` — synchronous or asynchronous operation to invoke. - -**Returns** the exact value returned by `operation`. - -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-execution/src/index.ts#L41) diff --git a/website/zh-CN/api/harness/agent-loop.md b/website/zh-CN/api/harness/agent-loop.md index 79003deb84..6401898e24 100644 --- a/website/zh-CN/api/harness/agent-loop.md +++ b/website/zh-CN/api/harness/agent-loop.md @@ -6,7 +6,7 @@ Concrete agent factory and driver service. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L408) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L407) ### ctx.agentLoop.create(id, options?, meta?) @@ -22,7 +22,7 @@ Create an agent and session under one caller-supplied identity, owned by the acc **Returns** the published running agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L543) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L542) ### ctx.agentLoop.createAgent(ownerCtx, options) @@ -37,7 +37,7 @@ Create an owned agent on a caller-supplied session id. **Returns** the published handle. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L565) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L564) ### ctx.agentLoop.resume(ownerCtx, options) @@ -52,4 +52,4 @@ Resume an owned agent from the configured persistence service. **Returns** the published handle. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L597) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L596) diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index 8d6c84cc7a..328ea6097e 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -4,9 +4,62 @@ `AgentRegistry` — provided by `@deepseek-ai/dsh-agent`. -Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. +Agent service (`ctx.agents`): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L201) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L204) + +### ctx.agents.currentInitiator() + +```ts website-api +currentInitiator(): Agent | undefined +``` + +Read the Agent that initiated the inherited asynchronous driver chain. + +**Returns** the inherited Agent, or `undefined` outside a driver and inside an explicit clearing boundary. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L233) + +### ctx.agents.requireInitiator() + +```ts website-api +requireInitiator(): Agent +``` + +Read the initiating Agent and fail when no driver boundary is active. + +**Returns** the inherited Agent. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L243) + +### ctx.agents.withInitiator(agent, operation) + +```ts website-api +withInitiator(agent: Agent, operation: () => T): T +``` + +Run an operation with one exact Agent as its process-local initiator. The exact synchronous value or Promise returned by the operation is preserved. + +- `agent` — initiating Agent to inherit; presence is neither liveness proof nor authorization. +- `operation` — synchronous or asynchronous operation to invoke. + +**Returns** the exact value returned by `operation`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L257) + +### ctx.agents.withoutInitiator(operation) + +```ts website-api +withoutInitiator(operation: () => T): T +``` + +Run an operation inside a boundary that hides any inherited initiating Agent. The exact synchronous value or Promise is preserved. + +- `operation` — synchronous or asynchronous operation to invoke without an initiator. + +**Returns** the exact value returned by `operation`. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L268) ### ctx.agents.setFactory(factory) @@ -20,7 +73,7 @@ Register the agent-creation factory (the loop calls this on construction, effect **Returns** the disposer that clears the factory slot. The exact Cordis effect disposer (single-shot): composite (generator) effects may yield it directly — exact identity nests the teardown in order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L228) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L284) ### ctx.agents.create(options) @@ -34,7 +87,7 @@ Create and publish a new agent through the registered factory. Distinct from reg **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L261) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L317) ### ctx.agents.resume(options) @@ -48,7 +101,7 @@ Load a persisted session and resume an agent on it through the registered factor **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L280) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L336) ### ctx.agents.register(agent) @@ -62,7 +115,7 @@ Register a live agent. Throws if an agent with the same id is already registered **Returns** the EXACT Cordis effect disposer (single-shot; a repeat call returns undefined without awaiting an in-flight teardown). Exact identity is load-bearing: a composite (generator) effect that owns a teardown ORDER — the agent factory's lifecycle chain — must yield THIS function so Cordis nests the unregistration at that yield position; yielding a wrapper would leave it disposing as a concurrent sibling on owner unload, unregistering the agent (and emitting `agent/disposed`) while its final turn is still draining. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L306) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L362) ### ctx.agents.enter(agent, owner) @@ -77,7 +130,7 @@ Insert an already-constructed agent without announcing it. This is the advanced **Returns** an idempotent closure that removes this exact entry and emits `agent/disposed` with listener failures contained. When called from a synchronous `agent/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L330) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L386) ### ctx.agents.announce(agent) @@ -89,7 +142,7 @@ Announce an agent previously inserted with enter. - `agent` — the live inserted agent to announce. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L405) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L461) ### ctx.agents.get(id) @@ -103,7 +156,7 @@ Look up a live agent. **Returns** the agent, or undefined when no live agent has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L439) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L495) ### ctx.agents.isOwnedBy(id, owner) @@ -118,7 +171,7 @@ Test whether a live agent was created through one exact parent agent's scoped co **Returns** true only while the exact child entry is live under that owner. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L451) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L507) ### ctx.agents.list() @@ -130,7 +183,7 @@ All live agents, in registration order. **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L459) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L515) ### ctx.agents.roots() @@ -142,4 +195,4 @@ All live top-level agents in registration order. A top-level agent was created w **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L469) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L525) diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index 66bec18578..8d494739ba 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -228,7 +228,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers - `sessionId` — exact shared agent/session identity that failed startup. - `error` — persistence, setup, or publication failure. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L363) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L362) ## approval/* From f4a30da10df2e6b227d6213926982bb108cf65e7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:32:04 +0800 Subject: [PATCH 225/323] chore: align one-shot demo workspace metadata --- examples/package.json | 1 + knip.json | 1 + pnpm-lock.yaml | 3 +++ 3 files changed, 5 insertions(+) diff --git a/examples/package.json b/examples/package.json index 8d77731a05..76349b2ea4 100644 --- a/examples/package.json +++ b/examples/package.json @@ -10,6 +10,7 @@ "@deepseek-ai/dsh-acp-demo": "workspace:*", "@deepseek-ai/dsh-bash-local": "workspace:*", "@deepseek-ai/dsh-bash-sandbox": "workspace:*", + "@deepseek-ai/dsh-cli-demo": "workspace:*", "@deepseek-ai/dsh-code-runtime-worker": "workspace:*", "@deepseek-ai/dsh-compact-basic": "workspace:*", "@deepseek-ai/dsh-fs-local": "workspace:*", diff --git a/knip.json b/knip.json index 8dedeb2f4c..2c3465ab38 100644 --- a/knip.json +++ b/knip.json @@ -10,6 +10,7 @@ "examples": { "entry": [ "echo-agent/src/*.ts", + "headless-agent/tests/fixtures/cli-mock-llm.ts", "tui-agent/tests/fixtures/tui-scripted-llm.ts", "*/tests/**/*.e2e.ts", "*/tests/**/*.snapshot.ts" diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index c0b312a484..d7649345fc 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -107,6 +107,9 @@ importers: '@deepseek-ai/dsh-bash-sandbox': specifier: workspace:* version: link:../packages/bash/bash-sandbox + '@deepseek-ai/dsh-cli-demo': + specifier: workspace:* + version: link:../packages/examples/cli-demo '@deepseek-ai/dsh-code-runtime-worker': specifier: workspace:* version: link:../packages/code-runtime/code-runtime-worker From e0b5cadd2a97c56404ce4f23ef3070fb819ce9ee Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:37:11 +0800 Subject: [PATCH 226/323] chore(core): align merged initiator changes --- examples/repl-agent/tests/code-mode.e2e.ts | 1 + packages/README.md | 2 +- packages/core/agent-loop/tests/cancel.spec.ts | 1 + packages/core/agent-loop/tests/coverage-edges.spec.ts | 1 + packages/core/agent-loop/tests/interception.spec.ts | 1 + packages/core/agent-loop/tests/loop.spec.ts | 1 + packages/core/agent-loop/tests/properties.spec.ts | 1 + packages/core/agent-loop/tests/request-cache.e2e.ts | 1 + packages/core/agent-loop/tests/request-reconstruction.spec.ts | 1 + packages/core/agent-loop/tests/tool-order.spec.ts | 1 + packages/core/agent-loop/tests/turn-stop.spec.ts | 1 + .../workflow-workerthread/tests/workflow-workerthread.e2e.ts | 1 + 12 files changed, 12 insertions(+), 1 deletion(-) diff --git a/examples/repl-agent/tests/code-mode.e2e.ts b/examples/repl-agent/tests/code-mode.e2e.ts index e03dcc6b03..c7f5d48562 100644 --- a/examples/repl-agent/tests/code-mode.e2e.ts +++ b/examples/repl-agent/tests/code-mode.e2e.ts @@ -9,6 +9,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' diff --git a/packages/README.md b/packages/README.md index 7e01fe30fe..7ddda1d0a9 100644 --- a/packages/README.md +++ b/packages/README.md @@ -8,7 +8,7 @@ Packages live at `packages///`; groups are containers, while names r | Group | Role | Release expectation | |---|---|---| -| [`core/`](core/README.md) | Product API spine, including agent execution and the concrete loop | Product — stable surface | +| [`core/`](core/README.md) | Product API spine: sessions, prompts, tools, agent services, and the concrete loop | Product — stable surface | | [`llm/`](llm/README.md) | LLM capability family: the abstract service + provider adapters | Product — stable surface | | [`bash/`](bash/README.md) | Bash capability family: the executor seam, a local impl, and the model-facing tool | Product — stable surface | | [`code-runtime/`](code-runtime/README.md) | Code-execution capability family: the abstract runtime seam for model-written programs + a worker-thread backend | Product — stable surface | diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 2d32388171..92eb046788 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -14,6 +14,7 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 38fdaedf57..b324c02b6c 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -6,6 +6,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index a715265a97..ea8dcfd58a 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -5,6 +5,7 @@ import SessionStore, { SessionId, type SessionEvent, type TurnEndReason } from ' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent, type ContinuationDecision, type PromptDecision, type SessionStartSource } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 63fef89087..13a63f0f3c 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -5,6 +5,7 @@ import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, maxTokensResponse, textResponse, toolCallResponse } from './mock-adapter.ts' diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 6f872cc423..2becadcc40 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -18,6 +18,7 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import fc from 'fast-check' diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index c82eccbf85..9fc832fd0a 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -5,6 +5,7 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index 6622092f47..46cfe3eb56 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -13,6 +13,7 @@ import SessionStore, { Session, SessionId, foldRequestHeader } from '@deepseek-a import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index a4b5f82c4a..bf78208a42 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -14,6 +14,7 @@ import SystemPrompt, { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' import type { Config as SystemPromptConfig } from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { MockAdapter, textResponse } from './mock-adapter.ts' diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index 8bbd26f2ac..355e1e8e3d 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -5,6 +5,7 @@ import SessionStore, { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-se import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { type Agent, type ContinuationStop } from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as Invariants from '@deepseek-ai/dsh-invariants' import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts' diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 680b2e25c7..74d42f739b 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -5,6 +5,7 @@ import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' + import AgentLoop from '@deepseek-ai/dsh-agent-loop' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import SubagentService from '@deepseek-ai/dsh-subagent' From 692ef8e61f1ea34cc30e0736c48a951f3dcdb693 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:37:27 +0800 Subject: [PATCH 227/323] test: align headless replay with model routing --- examples/headless-agent/cordis.yml | 4 ++-- .../snapshots/advanced-toolchain/session.1.jsonl | 4 ++-- .../snapshots/advanced-toolchain/session.2.jsonl | 4 ++-- .../snapshots/advanced-toolchain/session.jsonl | 14 +++++++------- .../advanced-toolchain/stream-json.golden.jsonl | 14 +++++++------- 5 files changed, 20 insertions(+), 20 deletions(-) diff --git a/examples/headless-agent/cordis.yml b/examples/headless-agent/cordis.yml index b119ccf0de..7f48c529c4 100644 --- a/examples/headless-agent/cordis.yml +++ b/examples/headless-agent/cordis.yml @@ -10,8 +10,8 @@ apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL models: - - deepseek-v4-pro - - deepseek-v4-flash + - id: deepseek-v4-pro + - id: deepseek-v4-flash - id: bash name: '@deepseek-ai/dsh-bash-local' diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 95924ff6c6..b4e8cd6340 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,12 +2,12 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 5e4387ccb7..d8d2e59e6e 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,12 +2,12 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl index a1785105cd..e3849110ce 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,13 +2,13 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} {"type":"assistant/chunk","seq":7,"time":1783950000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"tool/call","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}} {"type":"tool/result","seq":11,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} {"type":"step/end","seq":12,"time":1783957884489,"data":{"turn":1,"step":1}} @@ -18,7 +18,7 @@ {"type":"assistant/chunk","seq":16,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} {"type":"assistant/chunk","seq":17,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":18,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} +{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} {"type":"tool/call","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}} {"type":"tool/code-dispatch","seq":21,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}} {"type":"tool/result","seq":22,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"} @@ -29,7 +29,7 @@ {"type":"assistant/chunk","seq":27,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":28,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":29,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} +{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} {"type":"tool/call","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}} {"type":"tool/result","seq":32,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783957884593,"data":{"turn":1,"step":3}} @@ -39,7 +39,7 @@ {"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}} {"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} +{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} {"type":"tool/call","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}} {"type":"tool/result","seq":42,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"} {"type":"step/end","seq":43,"time":1783957884718,"data":{"turn":1,"step":4}} @@ -49,7 +49,7 @@ {"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}} {"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} +{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} {"type":"tool/call","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}} {"type":"tool/result","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} {"type":"step/end","seq":53,"time":1783957884719,"data":{"turn":1,"step":5}} @@ -59,6 +59,6 @@ {"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_HEADLESS_OK"}}}} {"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} +{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} {"type":"step/end","seq":61,"time":1783957884721,"data":{"turn":1,"step":6}} {"type":"turn/end","seq":62,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl index 35aad5fc89..44577f1fe0 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/stream-json.golden.jsonl @@ -1,13 +1,13 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_HEADLESS_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":11,"time":0,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":12,"time":0,"data":{"turn":1,"step":1}}} @@ -17,7 +17,7 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":16,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":19,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":20,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/code-dispatch","seq":21,"time":0,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":22,"time":0,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[]}},"sourceEventSeqs":[20],"surfaceOp":"append"}} @@ -28,7 +28,7 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":27,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":30,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":30,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":31,"time":0,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":33,"time":0,"data":{"turn":1,"step":3}}} @@ -38,7 +38,7 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":37,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":38,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":39,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":40,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":41,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-headless-snapshot\",\"description\":\"exercise one workflow child through the headless agent\"}}"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":42,"time":0,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-headless-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":43,"time":0,"data":{"turn":1,"step":4}}} @@ -48,7 +48,7 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":47,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":48,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":49,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":50,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":50,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/call","seq":51,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"tool/result","seq":52,"time":0,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":53,"time":0,"data":{"turn":1,"step":5}}} @@ -58,7 +58,7 @@ {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":57,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_HEADLESS_OK"}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":58,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/chunk","seq":59,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}} -{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} +{"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"assistant/message","seq":60,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_HEADLESS_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"step/end","seq":61,"time":0,"data":{"turn":1,"step":6}}} {"type":"session_event","sessionId":"{{sessionId}}","event":{"type":"turn/end","seq":62,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}}} {"type":"result","success":true,"sessionId":"{{sessionId}}","turn":1,"result":"ADVANCED_HEADLESS_OK","reason":{"kind":"completed"},"usage":{"inputTokens":18,"outputTokens":18}} From 1fdcd5a77314717391462d377e6991622db4eb31 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 13:42:21 +0800 Subject: [PATCH 228/323] ci: run pi-ai OpenAI e2e through Azure --- .github/workflows/pi-ai-provider-e2e.yml | 20 ++++++++------- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 19 ++++++++++++++ .../llm/llm-pi-ai/tests/provider-apis.e2e.ts | 25 +++++++++++-------- 3 files changed, 45 insertions(+), 19 deletions(-) diff --git a/.github/workflows/pi-ai-provider-e2e.yml b/.github/workflows/pi-ai-provider-e2e.yml index 7a273c52f3..4be5f0c13a 100644 --- a/.github/workflows/pi-ai-provider-e2e.yml +++ b/.github/workflows/pi-ai-provider-e2e.yml @@ -1,12 +1,12 @@ -name: E2E (pi-ai OpenAI and Anthropic) +name: E2E (pi-ai Azure OpenAI and Anthropic) # This suite spends tokens against two external providers and is intentionally # opt-in. It has no push, pull_request, schedule, or workflow_call trigger. on: workflow_dispatch: inputs: - openai_model: - description: OpenAI model from pi-ai's installed catalog + azure_openai_model: + description: Azure OpenAI model from pi-ai's installed catalog required: true default: gpt-5.5 type: string @@ -22,7 +22,7 @@ permissions: jobs: e2e: runs-on: ubuntu-latest - name: OpenAI Responses + Anthropic Messages + name: Azure OpenAI Responses + Anthropic Messages timeout-minutes: 20 steps: - uses: actions/checkout@v6 @@ -52,12 +52,12 @@ jobs: # dispatched CI run must fail instead of reporting an all-skipped green. - name: Preflight (require provider API keys) env: - OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY_EXTERNAL }} + AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY_EXTERNAL }} ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }} run: | set -euo pipefail missing=0 - for name in OPENAI_API_KEY ANTHROPIC_API_KEY; do + for name in AZURE_OPENAI_API_KEY ANTHROPIC_API_KEY; do if [ -z "${!name:-}" ]; then echo "::error::${name} is empty. Configure the corresponding *_EXTERNAL repository secret." missing=1 @@ -65,11 +65,13 @@ jobs: done exit "$missing" - - name: E2E tests (real OpenAI and Anthropic APIs) + - name: E2E tests (real Azure OpenAI and Anthropic APIs) env: - OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY_EXTERNAL }} + AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY_EXTERNAL }} + AZURE_OPENAI_API_VERSION: v1 ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }} - DSH_PI_AI_OPENAI_MODEL: ${{ inputs.openai_model }} + DSH_PI_AI_AZURE_OPENAI_MODEL: ${{ inputs.azure_openai_model }} + DSH_PI_AI_AZURE_OPENAI_BASE_URL: https://openai-routerhub-resource.services.ai.azure.com/api/projects/openai/openai/ DSH_PI_AI_ANTHROPIC_MODEL: ${{ inputs.anthropic_model }} DSH_E2E_MAX_WORKERS: 2 run: >- diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 559c36bf27..3ebb23ee50 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -167,6 +167,25 @@ describe('PiAiAdapter provider routing', () => { expect(server.paths).toEqual(['/v1/responses']) }) + it('uses Azure OpenAI Responses with the configured project base path and API key', async () => { + vi.stubEnv('AZURE_OPENAI_API_VERSION', 'v1') + const server = await mockServer([{ status: 401, body: JSON.stringify({ error: { message: 'expected mock failure' } }) }]) + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmPiAi, { + providers: [{ + provider: 'azure-openai-responses', + apiKey: 'test-key', + baseURL: `${server.url}/api/projects/openai/openai/`, + maxRetries: 0, + }], + }) + const result = await assemble(ctx, { provider: 'azure-openai-responses', model: 'gpt-5.5', messages: [] }) + expect(result.finish.kind).toBe('error') + expect(server.paths).toEqual(['/api/projects/openai/openai/responses?api-version=v1']) + expect(server.headers[0]?.['api-key']).toBe('test-key') + }) + it.each([ [401, 'AUTH'], [400, 'INVALID_REQUEST'], diff --git a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts index 7fffba4618..1ed0959785 100644 --- a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts +++ b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts @@ -3,22 +3,26 @@ import { Context } from 'cordis' import LlmService, { CallId } from '@deepseek-ai/dsh-llm' import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import type { PiAiReplayState } from '@deepseek-ai/dsh-llm-pi-ai' +import type { PiAiReplayState } from '../src/replay.ts' import { assemble, type AssembledResult } from './assemble.ts' interface ProviderCase { - provider: 'openai' | 'anthropic' - api: 'openai-responses' | 'anthropic-messages' + provider: 'azure-openai-responses' | 'anthropic' + api: 'azure-openai-responses' | 'anthropic-messages' model: string apiKey?: string + baseURL?: string } +const azureOpenAIBaseURL = process.env.DSH_PI_AI_AZURE_OPENAI_BASE_URL ?? process.env.AZURE_OPENAI_BASE_URL + const providerCases: ProviderCase[] = [ { - provider: 'openai', - api: 'openai-responses', - model: process.env.DSH_PI_AI_OPENAI_MODEL ?? 'gpt-5.5', - ...process.env.OPENAI_API_KEY ? { apiKey: process.env.OPENAI_API_KEY } : {}, + provider: 'azure-openai-responses', + api: 'azure-openai-responses', + model: process.env.DSH_PI_AI_AZURE_OPENAI_MODEL ?? 'gpt-5.5', + ...process.env.AZURE_OPENAI_API_KEY ? { apiKey: process.env.AZURE_OPENAI_API_KEY } : {}, + ...azureOpenAIBaseURL ? { baseURL: azureOpenAIBaseURL } : {}, }, { provider: 'anthropic', @@ -38,6 +42,7 @@ async function harness(): Promise { providers: providerCases.map(profile => ({ provider: profile.provider, ...profile.apiKey === undefined ? {} : { apiKey: profile.apiKey }, + ...profile.baseURL === undefined ? {} : { baseURL: profile.baseURL }, })), }) return ctx @@ -90,7 +95,7 @@ for (const profile of providerCases) { provider: profile.provider, model: profile.model, messages: ask('Reply with exactly the word: pong'), - maxTokens: 64, + maxTokens: 1024, }) expect(result.finish.kind).toBe('stop') @@ -108,7 +113,7 @@ for (const profile of providerCases) { model: profile.model, messages: prompt, tools: [lookupTool], - maxTokens: 256, + maxTokens: 2048, }) expect(first.finish.kind).toBe('tool-calls') @@ -134,7 +139,7 @@ for (const profile of providerCases) { }, ], tools: [lookupTool], - maxTokens: 256, + maxTokens: 2048, }) expect(second.finish.kind).toBe('stop') From 51425dd61a481257a72f0351e7a564439e470be0 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 13:51:25 +0800 Subject: [PATCH 229/323] test(llm-pi-ai): surface provider e2e failures --- packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts index 1ed0959785..b830bfe08b 100644 --- a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts +++ b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts @@ -63,6 +63,13 @@ function textOf(result: AssembledResult): string { .join('') } +function expectFinish(result: AssembledResult, expected: 'stop' | 'tool-calls'): void { + if (result.finish.kind === 'error') { + throw new Error(`provider request failed (${result.finish.code ?? 'unknown'}): ${result.finish.message}`) + } + expect(result.finish.kind).toBe(expected) +} + function expectNativeReplay(result: AssembledResult, profile: ProviderCase): PiAiReplayState { const replayState = result.message.provenance?.replayState expect(replayState).toMatchObject({ @@ -98,7 +105,7 @@ for (const profile of providerCases) { maxTokens: 1024, }) - expect(result.finish.kind).toBe('stop') + expectFinish(result, 'stop') expect(textOf(result).toLowerCase()).toContain('pong') expect(result.usage?.inputTokens).toBeGreaterThan(0) expect(result.usage?.outputTokens).toBeGreaterThan(0) @@ -116,7 +123,7 @@ for (const profile of providerCases) { maxTokens: 2048, }) - expect(first.finish.kind).toBe('tool-calls') + expectFinish(first, 'tool-calls') const call = first.message.content.find(block => block.type === 'tool-call') expect(call).toBeDefined() expect(call!.name).toBe('lookup_code') @@ -142,7 +149,7 @@ for (const profile of providerCases) { maxTokens: 2048, }) - expect(second.finish.kind).toBe('stop') + expectFinish(second, 'stop') expect(textOf(second).toLowerCase()).toContain('ocean') expect(expectNativeReplay(second, profile).stopReason).toBe('stop') }) From 2ef9590f3323ebf7293b49d73394ca0fb28c2f09 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:51:41 +0800 Subject: [PATCH 230/323] test(loader-smoke): declare argv lib fixture --- packages/support/loader-smoke/tests/loader-smoke.spec.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/support/loader-smoke/tests/loader-smoke.spec.ts b/packages/support/loader-smoke/tests/loader-smoke.spec.ts index ec5d01db2b..e8f6554691 100644 --- a/packages/support/loader-smoke/tests/loader-smoke.spec.ts +++ b/packages/support/loader-smoke/tests/loader-smoke.spec.ts @@ -50,6 +50,7 @@ describe('runLoaderSmoke', () => { label: 'argv fixture', tempDirPrefix: 'loader-smoke-argv-', binScript: fixture('success'), + libBinScript: fixture('success'), configPath, binArgs: ['--config', configPath, '--output-format', 'json', 'task with spaces'], tsconfigPath, From 3ceccc87a0299f6ec88b44a5d267665424f1bdaa Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 13:59:05 +0800 Subject: [PATCH 231/323] docs: drift-check public class APIs --- docs/AGENTS.md | 2 +- docs/core-data-structures/core.md | 4 +- docs/core-data-structures/llm-streaming.md | 69 ++++++++++ docs/core-data-structures/session.md | 120 ++++++++++++++++++ docs/development.i18n.yaml | 4 +- docs/development.md | 4 +- docs/development.zh.md | 4 +- ...2026-06-20-core-data-structures-catalog.md | 6 +- scripts/doc-typecheck.ts | 1 + scripts/type-equiv.manifest.json | 5 +- scripts/verify-type-equiv.ts | 102 +++++++++++++-- 11 files changed, 296 insertions(+), 25 deletions(-) diff --git a/docs/AGENTS.md b/docs/AGENTS.md index dc06018c16..27db1d88d7 100644 --- a/docs/AGENTS.md +++ b/docs/AGENTS.md @@ -27,7 +27,7 @@ Placement: bugs → postmortems; rationale → RFCs; procedures → cookbooks; t - **Document current state, not change history.** Avoid "previously/now/no longer", PRs, commits, and stack positions in durable prose; name the live mechanism. Put change stories in commits, PRs, RFCs, or postmortems. - **Write an RFC in the same PR for decisions a maintainer may reasonably revisit.** Mechanical or self-evident changes need none ([when to write one](rfc/README.md)). - **One physical line per paragraph** (`verify-md-wrap`): use editor soft-wrap. Code blocks, tables, and list structure keep their formatting; code comments stay under the linter's column limit. -- **Fenced `ts` blocks must compile** (`doc-typecheck`); a pasted type declaration and its original JSDoc are fenced ` ```ts type-equiv ` and registered in the manifest so neither can drift ([mechanics](development.md#documenting-types-verbatim-ts-type-equiv)). +- **Fenced `ts` blocks must compile** (`doc-typecheck`); a pasted type declaration and its original JSDoc use ` ```ts type-equiv `, while a body-stripped public class declaration uses its `public-api` variant; register either in the manifest so neither can drift ([mechanics](development.md#documenting-types-verbatim-ts-type-equiv)). - **The [core-data-structures catalog](core-data-structures/core.md) updates in the same change** that reshapes a documented type. `verify-type-equiv` catches drifted pastes, not never-documented new types ([what counts as core](core-data-structures/core.md#what-counts-as-core)). - **Bilingual pairs update together**: editing either side obligates the counterpart and a re-record in the same change ([i18n contract](i18n/README.md)). - **Comments and JSDoc state complete contracts, not reasoning transcripts.** Preserve behavior, conditions, timing, modality, exceptions, consequences, and non-obvious orientation; delete implementation narration, test walkthroughs, review analysis, and code restatement. Keep the local contract and link to its owning rationale. Use [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for required coverage, decision rules, and examples. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index dfb59b3ac6..732b6d9599 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -36,9 +36,7 @@ Everything else is documented on a **sub-page**, not here. The rule that draws t | [spill.md](spill.md) | the spill storage seam: `SaveTextSpill`, `SpillOwner`/`SpillSource`, `SpillRef`, the branded `SpillLocator` | | [workflow.md](workflow.md) | the workflow seam: `WorkflowStartRequest`, `WorkflowMeta`, `WorkflowRun`/`Result`, the `workflow/*` event payloads, `WorkflowError` fatality | -> Type declarations and their JSDoc on this page are pasted **verbatim** from source and drift-checked by `pnpm run verify-type-equiv` (see [development.md](../development.md#documenting-types-verbatim-ts-type-equiv)). - -FIXME(catalog-verbs): the drift gate covers only the nouns (the pasted type shapes); every method surface on these pages is hand-written prose. core-data-structures should probably also generate the *verbs* — the public methods of the cataloged classes — so a signature change cannot silently outdate the catalog. +> Type declarations and their JSDoc on these pages are source-equivalent and drift-checked by `pnpm run verify-type-equiv` (see [development.md](../development.md#documenting-types-verbatim-ts-type-equiv)). Ordinary blocks preserve complete declarations; `public-api` blocks preserve body-stripped public class declarations. Cordis services use the generated [service catalog](../cordis-catalog/services.md). ## The `…Map → derived-union` pattern diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index 0ef9ae02f7..b27c21a69c 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -91,10 +91,79 @@ interface TokenUsage { `BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s, usage, finish reason, and replay state. The loop logs the raw chunks while feeding the same chunks through an assembler, then stores the assembled assistant content with its provider/model provenance. A consumer that needs the assembled result without re-implementing the fold uses this. +```ts type-equiv public-api +/** + * Incrementally assembles raw {@link StreamChunk}s into complete + * {@link ContentBlock}s and a final assistant {@link Message}. + * + * The agent loop feeds it while logging raw chunks for replay fidelity, then + * reads `blocks()` / `message()` / `usage` / `finish` once the stream ends. + * + * Tolerant of delta-only protocols (no block-start/end); deltas arriving for + * an index already closed by `block-end` are ignored (malformed stream) so a + * misbehaving adapter cannot grow memory or corrupt a completed block. + */ +declare class BlockAssembler { + /** + * Feed one chunk into the assembly state. + * @param chunk - the next raw chunk, in stream order. + */ + push(chunk: StreamChunk): void; + /** + * Assemble all blocks seen so far, in stream order. + * @returns one block per seen index; an open block assembles from its + * accumulated deltas (an unknown block type never closed by `block-end` throws). + */ + blocks(): ContentBlock[]; + /** Usage from the `usage` chunk; undefined until one arrives. */ + get usage(): TokenUsage | undefined; + /** Finish reason from the `finish` chunk; `{kind: 'stop'}` when the stream ended without one. */ + get finish(): FinishReason; + /** Adapter-private replay state from the terminal finish chunk, if any. */ + get replayState(): unknown; + /** + * The assembled assistant message. + * @returns an assistant-role message over `blocks()` (same open-block assembly rules). + */ + message(): Message; +} +``` + ## The seam `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerInfo()` and asynchronous `listModels()` methods feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). +```ts type-equiv public-api +/** + * Provider-wire adapter for the harness message and stream vocabulary. Register implementations + * with `ctx.llm.registerAdapter(providers, adapter)`. Every provider HTTP request must include + * `attributionHeaders()`; prove that at the wire or library header-hook boundary. The hand-rolled + * DeepSeek and pi-ai adapters intentionally exercise this contract through different internals. + */ +declare abstract class LlmAdapter { + /** + * Describe one provider route owned by this adapter. + * @param provider - a route passed to `registerAdapter()` for this instance. + * @returns detached display metadata whose id must equal `provider`. + */ + providerInfo(provider: string): LlmProviderInfo; + /** + * List models this adapter can currently advertise for one owned provider. + * The result is advisory: an adapter may accept unlisted model ids, and + * consumers must not turn absence into request rejection. + * @param _provider - one provider route owned by this adapter. + * @returns discoverable models in adapter-preferred order. + */ + listModels(_provider: string): Promise; + /** + * Stream one model call as raw chunks. The only required method. + * @param options - the fully-assembled request; implementations must honor `options.signal`. + * @returns the chunk stream, obeying the adapter contract documented on `StreamChunk`. + */ + abstract stream(options: GenerateOptions): AsyncIterable; +} +``` + `ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`: ```ts type-equiv diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 3d3fca045a..1ece65c1c3 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -305,6 +305,126 @@ interface SurfaceFoldResult { } ``` +## `Session` public API + +The body-stripped declaration keeps the plain class's public constructor, state accessors, append boundary, and history projections synchronized with source. Store operations remain in the generated [`ctx.sessions` service catalog](../cordis-catalog/services.md#ctxsessions--sessionstore). + +```ts type-equiv public-api +/** + * An event-sourced session: an append-only log of {@link SessionEvent}s. + * + * Plain class (not a Service) — create instances via `ctx.sessions.create()`. + * Seeding with an existing event log replays/forks a session. + */ +declare class Session { + /** The ordered surface over this session's event log. */ + get surface(): SessionSurface; + /** + * Detached, deep-frozen creation metadata (format version, cwd, lineage, + * seed boundary). Supplied by the store via `ctx.sessions.create()`. When a + * `Session` is constructed bare (tests, ad-hoc replay), a minimal header is + * synthesized (stamped with the current {@link SESSION_FORMAT_VERSION}) so + * `session.header` is always present. Kept out of the event log — it is a + * storage concern, not replayable conversation state. + */ + readonly header: SessionHeader; + /** The session identity, derived from its durable header's single copy. */ + get id(): SessionId; + constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader); + /** + * An immutable snapshot of the append-only event log. The snapshot is reused + * until the next append; a previously returned array does not grow later. + * Events and their nested data are deep-frozen at acceptance, so neither a + * cast nor ordinary JavaScript can rewrite durable history. + */ + get events(): readonly SessionEvent[]; + /** The next event's sequence number — always the log length (the `seq = log.length` contiguity contract). */ + get seq(): number; + /** + * Append one typed event to the log and synchronously notify observers via + * the store-owned, module-private publication hooks. The hot path never blocks + * on I/O — persistence plugins buffer asynchronously. Once the event enters + * the log, the append is committed: observer failures are logged and + * contained per listener, so they do not change the return value or prevent + * later listeners from observing the same accepted event. + * + * @param type - The event type (key of {@link SessionEventMap}). + * @param data - The event payload; must be JSON-serializable. + * @param opts - Surface metadata: `surfaceOp` controls how the event enters + * the ordered surface; `sourceEventSeqs` records provenance (the seq + * numbers of events this one derives from). REQUIRED for + * {@link SurfaceEventType} events (every message-producing event must + * declare how it joins the surface, the sole source of derived history) and + * rejected by the compiler for non-surface types like `turn/start` or + * `assistant/chunk`. + * @returns the logged event — its assigned `seq`/`time` plus the SNAPSHOT of + * `data` that entered the log, so reading `event.data` back sees the logged + * value, never the caller's still-mutable input. + * @throws if `data` or surface metadata is not losslessly JSON-serializable + * (BigInt, function, symbol, undefined, negative zero, non-finite number, + * circular reference, sparse array, or an exotic object such as + * Map/Set/Date/class instance), or when the candidate violates the + * canonical surface contract (marker shape and eligibility, unique + * earlier provenance, positional replacement validity, and complete + * shadowed-node coverage). One recursive pass reads, validates, and + * copies each nested value once, so a stateful getter cannot supply one value + * to validation and another to storage. The event log is the durable source + * of truth, so a bad event fails at the append site rather than later during + * a backend flush. A synchronous internal dispatch validation failure or an + * append reentered while this acceptance/publication boundary is open also + * rejects before the log changes. + */ + append( + type: T, + data: SessionEventMap[T], + ...opts: T extends SurfaceEventType ? [opts: SurfaceIntent] : [] + ): SessionEvent; + /** + * The {@link EpochHeader} in force after the log's last header event — the + * header the NEXT request will be compared against — or undefined before + * the first `request/header` snapshot. The live, incrementally-maintained + * form of `foldRequestHeader(session.events)`: each header event is folded + * once, when first seen, so a per-step read costs O(new events). + * @returns the folded header, or undefined when no header event exists yet. + */ + requestHeader(): EpochHeader | undefined; + /** + * Derive the LLM message history by walking the ordered sequences of + * message-producing events maintained by `surfaceOp` markers. The + * surface is the single source of derived history: every message-producing + * append records its `surfaceOp`, so a raw event with no marker (a chunk, a + * turn boundary) is correctly absent, and a compaction `replace` deletes the + * shadowed nodes from the derivation. The projection rules are + * {@link deriveEventMessage}, folded per node. + * + * CACHED: each surface node is projected exactly once, when first seen — a + * call costs O(new nodes), and a surface rewrite (a `replace`; + * {@link SessionSurface.replaceGeneration}) rebuilds. The returned array is + * a fresh snapshot per call (later appends never grow an array a caller + * already holds); the `Message` objects in it are SHARED and **deep-frozen**. + * Their content reuses the already frozen durable event data, so the cache + * needs no second deep clone and consumers still cannot mutate the log. + * @returns a fresh array of the shared, frozen derived history. + */ + deriveMessages(): Message[]; + /** + * Project a single event into the LLM message it derives to, or null when + * it produces none — a non-surface event (chunk, boundary, log-only record) + * or an empty-content assistant/message (which exists only to host usage). + * The per-node pure function {@link deriveMessages} folds over the surface; + * an external reconstructor (or the dev invariant) folds the same function + * over a log prefix's surface to rebuild the exact messages any request was + * built from (the reconstructability RFC). The returned message wrapper is + * fresh; its content reuses the logged event's already deep-frozen durable + * data, so changing the wrapper cannot rewrite the log and changing content + * throws. + * @param event - the event to project. + * @returns the derived message, or null when the event produces none. + */ + deriveEventMessage(event: SessionEvent): Message | null; +} +``` + ## Derived history: `deriveMessages()` and `deriveEventMessage()` `Session.deriveMessages()` projects the event log into the `Message[]` the model sees — cached (each surface node projected once, when first seen; a surface rewrite rebuilds) and frozen (a fresh array per call over shared, deep-frozen messages, so mutating logged history through a projection is unrepresentable). `deriveEventMessage(event)` is the per-node pure function the fold applies — public so external reconstructors and the dev invariant project a log prefix with exactly the same rules and cannot disagree with the cache. The projection rules: diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index e5b3feba33..e41578431b 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: 37811f7215001fc371ac4943fe109dd5512ea8b0 -development.zh.md: 5036e3e75516fcaf063675fc9ab4e63c1fca851a +development.md: 204b50d7733ba18aa6bac1ae714ad09972f3db25 +development.zh.md: 11a844fa6939aa0894d0657d207c5082f5406732 diff --git a/docs/development.md b/docs/development.md index 37811f7215..204b50d773 100644 --- a/docs/development.md +++ b/docs/development.md @@ -145,13 +145,13 @@ Pick the tag that matches the urgency so anyone scanning the code can tell a rel ## Documenting types verbatim (`ts type-equiv`) -The [core data structures](core-data-structures/core.md) docs paste real type declarations together with their original JSDoc so a reader sees the exact shape and source contract. To keep a paste from drifting when source changes, fence it as ` ```ts type-equiv ` (instead of ` ```ts `) and register it in `scripts/type-equiv.manifest.json` with the source file and symbol it mirrors: +The [core data structures](core-data-structures/core.md) docs paste source-equivalent declarations together with their original JSDoc so a reader sees the exact shape and source contract. To keep a paste from drifting when source changes, fence it as ` ```ts type-equiv ` (instead of ` ```ts `) and register it in `scripts/type-equiv.manifest.json` with the source file and symbol it mirrors: ```json { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" } ``` -`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration and attached JSDoc from source via the TypeScript parser and asserts the block matches both. Comparison ignores whitespace and non-JSDoc comments but requires every original JSDoc comment, including member documentation, so readers see the source contract beside the exact shape. The gate also enforces a 1:1 correspondence: every `ts type-equiv` block has exactly one manifest entry and vice-versa, so a block can't go silently unchecked and a stale entry can't linger. `doc-typecheck` skips `ts type-equiv` blocks (they aren't standalone-compilable) and excludes them from its opt-out ratio. When you change a documented declaration or its JSDoc, the gate fails until you update the paste; when you add or remove a block, update the manifest in the same change. +`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration and attached JSDoc from source via the TypeScript parser and asserts the block matches both. For a class whose implementation bodies do not belong in the catalog, use ` ```ts type-equiv public-api ` and set `"projection": "public-api"`; the checked projection retains the public fields, constructor, accessors, methods, and original class/member JSDoc while omitting bodies and private or protected members. Comparison ignores whitespace and non-JSDoc comments but requires every original JSDoc comment, including member documentation, so readers see the source contract beside the exact shape. The gate also enforces a 1:1 correspondence by document, symbol, and projection, so a block can't go silently unchecked and a stale entry can't linger. `doc-typecheck` skips both variants (they aren't standalone-compilable) and excludes them from its opt-out ratio. When you change a documented declaration or its JSDoc, the gate fails until you update the paste; when you add or remove a block, update the manifest in the same change. ## Architecture context diff --git a/docs/development.zh.md b/docs/development.zh.md index 5036e3e755..11a844fa69 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -145,13 +145,13 @@ pnpm run demo:acp ## 逐字记录类型（`ts type-equiv`） -[核心数据结构](core-data-structures/core.md)文档会把真实类型声明及其原始 JSDoc 一并粘贴，让读者看到确切形状和源码契约。为防止粘贴内容在源码变化时漂移，请将其围栏为 ` ```ts type-equiv `（而不是 ` ```ts `），并在 `scripts/type-equiv.manifest.json` 中登记它镜像的源文件和符号： +[核心数据结构](core-data-structures/core.md)文档会把与源码等价的声明及其原始 JSDoc 一并粘贴，让读者看到确切形状和源码契约。为防止粘贴内容在源码变化时漂移，请将其围栏为 ` ```ts type-equiv `（而不是 ` ```ts `），并在 `scripts/type-equiv.manifest.json` 中登记它镜像的源文件和符号： ```json { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" } ``` -`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明及其附带的 JSDoc，并断言代码块同时匹配两者。比对会忽略空白和非 JSDoc 注释，但要求保留每条原始 JSDoc（包括成员文档），让读者同时看到源码契约和确切形状。该门禁还强制 1:1 对应：每个 `ts type-equiv` 块恰好有一条 manifest 条目，反之亦然；因此不会有块被静默漏检，也不会有陈旧条目滞留。`doc-typecheck` 跳过 `ts type-equiv` 块（它们不能独立编译），并将其排除在 opt-out 比例之外。当你改动一个已记录的类型声明或其 JSDoc 时，门禁会失败直到你更新粘贴内容；当你增删一个块时，请在同一个变更里更新 manifest。 +`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明及其附带的 JSDoc，并断言代码块同时匹配两者。对于不应把实现体写进目录的类，请使用 ` ```ts type-equiv public-api ` 并设置 `"projection": "public-api"`；门禁检查的投影会保留公共字段、构造函数、访问器、方法以及类和成员的原始 JSDoc，同时省略实现体和私有或受保护成员。比对会忽略空白和非 JSDoc 注释，但要求保留每条原始 JSDoc（包括成员文档），让读者同时看到源码契约和确切形状。该门禁还按文档、符号和投影强制 1:1 对应，因此不会有块被静默漏检，也不会有陈旧条目滞留。`doc-typecheck` 跳过两种变体（它们不能独立编译），并将其排除在 opt-out 比例之外。当你改动一个已记录的类型声明或其 JSDoc 时，门禁会失败直到你更新粘贴内容；当你增删一个块时，请在同一个变更里更新 manifest。 ## 架构上下文 diff --git a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md b/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md index bf70879c71..974a19a621 100644 --- a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md +++ b/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md @@ -29,8 +29,8 @@ The rule that settled the remaining cases: ***the type you write, hold, or recei The durability requirement was specific: the doc shows the **literal** current type declaration and original JSDoc (so a reader sees the real shape and source contract, not a paraphrase) **and** is mechanically guaranteed to match source. The repo already compiles fenced ` ```ts ` blocks (`doc-typecheck`), but a real typechecked block needs import noise and proves only *assignability* — a renamed field or changed JSDoc can pass. So: -- Type declarations and their JSDoc are pasted verbatim into a dedicated ` ```ts type-equiv ` fence. `doc-typecheck` recognizes the fence and skips it (a bare definition is not standalone-compilable), and **excludes it from the opt-out ratio** — it is a separately-checked category, not an unchecked sketch. -- A new `scripts/verify-type-equiv.ts` extracts each block via the TypeScript parser and asserts that its declaration structure and every JSDoc comment match the declared symbol, ignoring only formatting whitespace and non-JSDoc comments. This is chosen over a compiled `_Check` assertion because source names and documentation identity, not assignability, are the properties the catalog preserves. +- Complete type declarations and their JSDoc are pasted verbatim into a dedicated ` ```ts type-equiv ` fence. A `public-api` variant carries the source-equivalent ambient projection for a class whose implementation bodies do not belong in the catalog. `doc-typecheck` recognizes both and skips them (the bare declarations are not standalone-compilable), and **excludes them from the opt-out ratio** — they are a separately-checked category, not unchecked sketches. +- A new `scripts/verify-type-equiv.ts` extracts each block via the TypeScript parser and asserts that its declaration structure and every JSDoc comment match the declared symbol, ignoring only formatting whitespace and non-JSDoc comments. Ordinary blocks retain the complete declaration. A `public-api` projection retains a class's public fields, constructor, accessors, and methods with their original JSDoc while removing implementation bodies and private or protected members. This is chosen over a compiled `_Check` assertion because source names and documentation identity, not assignability, are the properties the catalog preserves. - Provenance lives in a central `scripts/type-equiv.manifest.json` (`{ doc, symbol, source }` entries), **not** in directive comments in the prose. The script enforces a **1:1 correspondence**: every type-equiv block has exactly one manifest entry and vice versa, so a block can never be silently unchecked and an entry can never rot. - Wired into `doc-sync`, so it runs in the same lefthook pre-push and CI paths as the other doc gates. @@ -52,7 +52,7 @@ The spine-vs-seam rule was tested against `BashExecRequest`, tool schemas and de ## Consequences -- The vocabulary now has a single home that **cannot silently drift**: a field rename in source fails `verify-type-equiv` in the pre-push hook and CI until the paste is refreshed. +- The vocabulary now has a single home that **cannot silently drift**: a field or public class-member change in source fails `verify-type-equiv` in the pre-push hook and CI until the paste is refreshed. Cordis service methods remain owned by the generated services catalog rather than being duplicated here. - The spine-vs-seam line is a reusable scoping tool, not a one-off: the same "the thing you write/hold/receive is core; the machinery that types/renders/persists it is a detail" rule is what later scoped the events/services catalog's harness-vs-inherited tiering. - The `ts type-equiv` fence is a third doc-block category alongside ` ```ts ` (compiled) and ` ```ts ignore-check ` (sketch). A later sibling added a fourth, ` ```ts cordis-catalog ` (generated signature), reusing the same skip-and-exclude treatment. - Adding or reshaping a core type now carries a documentation obligation the author must honor (the gate cannot detect a missing *new* type), backstopped by the `dsh-code-review` checklist. diff --git a/scripts/doc-typecheck.ts b/scripts/doc-typecheck.ts index 7549ee982b..c4d6c04a35 100644 --- a/scripts/doc-typecheck.ts +++ b/scripts/doc-typecheck.ts @@ -33,6 +33,7 @@ const KIND_BY_INFO: Record = { 'ts': 'check', 'ts ignore-check': 'ignore', 'ts type-equiv': 'type-equiv', + 'ts type-equiv public-api': 'type-equiv', 'ts cordis-catalog': 'cordis-catalog', 'ts persistence-catalog': 'persistence-catalog', 'ts config-catalog': 'config-catalog', diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 566bdade7b..09888916d0 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -1,5 +1,5 @@ { - "comment": "Maps each ` ```ts type-equiv ` block (by doc + declared symbol) to the source declaration and original JSDoc it must match. verify-type-equiv.ts enforces a 1:1 correspondence: every type-equiv block has exactly one entry here, and every entry resolves to exactly one block. Add an entry when you add a type-equiv block; remove it when you remove the block.", + "comment": "Maps each ` ```ts type-equiv ` block (by doc + declared symbol + projection) to the source declaration and original JSDoc it must match. Omit projection for the complete declaration; use public-api with a ` ```ts type-equiv public-api ` block for a body-stripped public class declaration. verify-type-equiv.ts enforces a 1:1 correspondence: every type-equiv block has exactly one entry here, and every entry resolves to exactly one block. Add an entry when you add a type-equiv block; remove it when you remove the block.", "entries": [ { "doc": "docs/core-data-structures/core.md", "symbol": "Branded", "source": "packages/util/brand/src/index.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, @@ -33,6 +33,8 @@ { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "TokenUsage", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "AppIdentity", "source": "packages/llm/llm/src/attribution.ts" }, + { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "BlockAssembler", "source": "packages/llm/llm/src/assembler.ts", "projection": "public-api" }, + { "doc": "docs/core-data-structures/llm-streaming.md", "symbol": "LlmAdapter", "source": "packages/llm/llm/src/index.ts", "projection": "public-api" }, { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenMeasurement", "source": "packages/llm/token-meter/src/types.ts" }, { "doc": "docs/core-data-structures/token-meter.md", "symbol": "TokenSurfaceNode", "source": "packages/llm/token-meter/src/types.ts" }, @@ -50,6 +52,7 @@ { "doc": "docs/core-data-structures/session.md", "symbol": "SessionSurface", "source": "packages/core/session/src/surface.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceFoldReplacement", "source": "packages/core/session/src/surface.ts" }, { "doc": "docs/core-data-structures/session.md", "symbol": "SurfaceFoldResult", "source": "packages/core/session/src/surface.ts" }, + { "doc": "docs/core-data-structures/session.md", "symbol": "Session", "source": "packages/core/session/src/index.ts", "projection": "public-api" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "SessionHeader", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "CreateSessionOptions", "source": "packages/core/session/src/types.ts" }, diff --git a/scripts/verify-type-equiv.ts b/scripts/verify-type-equiv.ts index 585796206c..58affaffca 100644 --- a/scripts/verify-type-equiv.ts +++ b/scripts/verify-type-equiv.ts @@ -1,8 +1,10 @@ /** * Verify every `ts type-equiv` block against the source symbol named by the - * manifest. Blocks and entries have a one-to-one relationship; comparison - * ignores whitespace and non-JSDoc comments but preserves declaration - * structure and every original JSDoc comment. + * manifest. Ordinary entries preserve the complete declaration; `public-api` + * entries preserve a class's body-stripped public declaration. Blocks and + * entries have a one-to-one relationship; comparison ignores whitespace and + * non-JSDoc comments but preserves declaration structure and every original + * JSDoc comment. */ import { globSync, readFileSync, existsSync } from 'node:fs' @@ -22,6 +24,8 @@ interface ManifestEntry { symbol: string /** Source file (repo-relative) that exports the symbol. */ source: string + /** Complete declaration (default), or a body-stripped public class API. */ + projection?: 'public-api' } /** One extracted ` ```ts type-equiv ` block. */ @@ -31,6 +35,8 @@ interface EquivBlock { line: number /** Symbol name parsed from the block's declaration. */ symbol: string + /** Complete declaration (default), or a body-stripped public class API. */ + projection?: 'public-api' /** Block body (the pasted declaration). */ code: string } @@ -75,7 +81,7 @@ function extractEquivBlocks(docRel: string): EquivBlock[] { const text = readFileSync(resolve(root, docRel), 'utf8') const lines = text.split('\n') const blocks: EquivBlock[] = [] - let open: { line: number; body: string[] } | null = null + let open: { line: number; body: string[]; projection?: 'public-api' } | null = null for (let i = 0; i < lines.length; i++) { const raw = lines[i] ?? '' @@ -90,11 +96,19 @@ function extractEquivBlocks(docRel: string): EquivBlock[] { if (!symbol) { throw new Error(`verify-type-equiv: ${docRel}:${open.line} — type-equiv block has no parseable interface/type/class declaration`) } - blocks.push({ doc: docRel, line: open.line, symbol, code }) + blocks.push({ + doc: docRel, + line: open.line, + symbol, + code, + ...(open.projection === undefined ? {} : { projection: open.projection }), + }) open = null continue } - if ((fence[2] ?? '').trim() === 'ts type-equiv') open = { line: i + 1, body: [] } + const info = (fence[2] ?? '').trim() + if (info === 'ts type-equiv') open = { line: i + 1, body: [] } + if (info === 'ts type-equiv public-api') open = { line: i + 1, body: [], projection: 'public-api' } } if (open) throw new Error(`verify-type-equiv: ${docRel}:${open.line} — unterminated type-equiv block`) return blocks @@ -127,13 +141,77 @@ function sourceDeclaration(sourceRel: string, symbol: string): string | null { return null } +/** Leading source JSDoc attached to one declaration or member. */ +function sourceJSDoc(text: string, node: ts.Node): string { + return ts.getJSDocCommentsAndTags(node) + .filter(ts.isJSDoc) + .map(doc => text.slice(doc.pos, doc.end)) + .join('\n') +} + +/** Whether a class member is part of its public declaration. */ +function isPublicMember(member: ts.ClassElement): boolean { + if (ts.isClassStaticBlockDeclaration(member)) return false + const name = ts.getNameOfDeclaration(member) + if (name && ts.isPrivateIdentifier(name)) return false + const modifiers = ts.canHaveModifiers(member) ? ts.getModifiers(member) : undefined + return !(modifiers?.some(modifier => + modifier.kind === ts.SyntaxKind.PrivateKeyword + || modifier.kind === ts.SyntaxKind.ProtectedKeyword, + ) ?? false) +} + +/** Remove an implementation body while retaining the source signature. */ +function bodylessMember(text: string, sf: ts.SourceFile, member: ts.ClassElement): string { + const start = member.getStart(sf) + let end = member.end + if (ts.isConstructorDeclaration(member) || ts.isMethodDeclaration(member) + || ts.isGetAccessorDeclaration(member) || ts.isSetAccessorDeclaration(member)) { + if (member.body) end = member.body.getStart(sf) + } + if (ts.isPropertyDeclaration(member) && member.initializer) end = member.initializer.getStart(sf) + const signature = text.slice(start, end).trimEnd().replace(/;$/, '').replace(/=\s*$/, '').trimEnd() + return `${signature};` +} + +/** + * Render a class as an ambient declaration containing only its public fields, + * constructor, accessors, and methods. Implementation bodies and private or + * protected members are deliberately absent; original class/member JSDoc is + * retained so the projection is the source-owned public contract. + */ +function sourcePublicApi(sourceRel: string, symbol: string): string | null { + const abs = resolve(root, sourceRel) + const text = readFileSync(abs, 'utf8') + const sf = ts.createSourceFile(abs, text, ts.ScriptTarget.Latest, /* setParentNodes */ true) + for (const stmt of sf.statements) { + if (!ts.isClassDeclaration(stmt) || stmt.name?.text !== symbol) continue + const classDoc = sourceJSDoc(text, stmt) + const abstract = stmt.modifiers?.some(modifier => modifier.kind === ts.SyntaxKind.AbstractKeyword) ? 'abstract ' : '' + const typeParameters = stmt.typeParameters?.map(parameter => parameter.getText(sf)).join(', ') + const heritage = stmt.heritageClauses?.map(clause => clause.getText(sf)).join(' ') + const header = `declare ${abstract}class ${symbol}${typeParameters ? `<${typeParameters}>` : ''}${heritage ? ` ${heritage}` : ''} {` + const members = stmt.members + .filter(isPublicMember) + .map((member) => { + const jsDoc = sourceJSDoc(text, member) + const declaration = bodylessMember(text, sf, member) + return jsDoc === '' ? declaration : `${jsDoc}\n${declaration}` + }) + const declaration = [header, ...members.map(member => member.split('\n').map(line => ` ${line}`).join('\n')), '}'].join('\n') + return classDoc === '' ? declaration : `${classDoc}\n${declaration}` + } + return null +} + const manifestRaw = readFileSync(resolve(root, 'scripts/type-equiv.manifest.json'), 'utf8') const manifest = JSON.parse(manifestRaw) as { entries: ManifestEntry[] } const entries = manifest.entries -// Key a block/entry by doc + symbol (a symbol may be documented in more than one -// doc, but at most once per doc). -const keyOf = (x: { doc: string; symbol: string }): string => `${x.doc}::${x.symbol}` +// Key a block/entry by doc + symbol + projection. A symbol may be documented in +// more than one doc, and a doc may carry both complete and projected forms. +const keyOf = (x: { doc: string; symbol: string; projection?: 'public-api' }): string => + `${x.doc}::${x.symbol}::${x.projection ?? 'declaration'}` // Collect every type-equiv block across ALL docs in scope — not only the docs // the manifest names — so a block in an unmanifested doc is found and reported @@ -152,7 +230,7 @@ for (const d of [...new Set(entries.map(e => e.doc))]) { else if (!docSet.has(d)) errors.push(`manifest references ${d}, which is outside the scanned markdown scope (${MARKDOWN_GLOBS.join(', ')})`) } -// Duplicate-block guard: the same symbol twice in one doc is ambiguous. +// Duplicate-block guard: the same projected symbol twice in one doc is ambiguous. const blockByKey = new Map() for (const b of blocks) { const k = keyOf(b) @@ -192,7 +270,9 @@ let verified = 0 for (const e of entries) { const b = blockByKey.get(keyOf(e)) if (!b) continue // already reported as an orphan entry - const decl = sourceDeclaration(e.source, e.symbol) + const decl = e.projection === 'public-api' + ? sourcePublicApi(e.source, e.symbol) + : sourceDeclaration(e.source, e.symbol) if (decl === null) { errors.push(`symbol ${e.symbol} not found in ${e.source} (manifest entry for ${e.doc})`) continue From 39dea6107ea7ec00994142b078b04e12506dc7a9 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 14:06:18 +0800 Subject: [PATCH 232/323] fix(ci): target Azure Foundry OpenAI v1 route --- .github/workflows/pi-ai-provider-e2e.yml | 5 ++--- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 12 ++++++------ .../llm/llm-pi-ai/tests/provider-apis.e2e.ts | 19 +++++++++++-------- 3 files changed, 19 insertions(+), 17 deletions(-) diff --git a/.github/workflows/pi-ai-provider-e2e.yml b/.github/workflows/pi-ai-provider-e2e.yml index 4be5f0c13a..d198abf5b5 100644 --- a/.github/workflows/pi-ai-provider-e2e.yml +++ b/.github/workflows/pi-ai-provider-e2e.yml @@ -68,10 +68,9 @@ jobs: - name: E2E tests (real Azure OpenAI and Anthropic APIs) env: AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY_EXTERNAL }} - AZURE_OPENAI_API_VERSION: v1 ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY_EXTERNAL }} - DSH_PI_AI_AZURE_OPENAI_MODEL: ${{ inputs.azure_openai_model }} - DSH_PI_AI_AZURE_OPENAI_BASE_URL: https://openai-routerhub-resource.services.ai.azure.com/api/projects/openai/openai/ + DSH_PI_AI_OPENAI_MODEL: ${{ inputs.azure_openai_model }} + DSH_PI_AI_OPENAI_BASE_URL: https://openai-routerhub-resource.services.ai.azure.com/api/projects/openai/openai/v1 DSH_PI_AI_ANTHROPIC_MODEL: ${{ inputs.anthropic_model }} DSH_E2E_MAX_WORKERS: 2 run: >- diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 3ebb23ee50..26fbb392de 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -167,22 +167,22 @@ describe('PiAiAdapter provider routing', () => { expect(server.paths).toEqual(['/v1/responses']) }) - it('uses Azure OpenAI Responses with the configured project base path and API key', async () => { - vi.stubEnv('AZURE_OPENAI_API_VERSION', 'v1') + it('uses OpenAI Responses against an Azure project v1 path with its API key header', async () => { const server = await mockServer([{ status: 401, body: JSON.stringify({ error: { message: 'expected mock failure' } }) }]) const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmPiAi, { providers: [{ - provider: 'azure-openai-responses', + provider: 'openai', apiKey: 'test-key', - baseURL: `${server.url}/api/projects/openai/openai/`, + baseURL: `${server.url}/api/projects/openai/openai/v1`, + headers: { 'api-key': 'test-key' }, maxRetries: 0, }], }) - const result = await assemble(ctx, { provider: 'azure-openai-responses', model: 'gpt-5.5', messages: [] }) + const result = await assemble(ctx, { provider: 'openai', model: 'gpt-5.5', messages: [] }) expect(result.finish.kind).toBe('error') - expect(server.paths).toEqual(['/api/projects/openai/openai/responses?api-version=v1']) + expect(server.paths).toEqual(['/api/projects/openai/openai/v1/responses']) expect(server.headers[0]?.['api-key']).toBe('test-key') }) diff --git a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts index b830bfe08b..a2fcc2c143 100644 --- a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts +++ b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts @@ -7,22 +7,24 @@ import type { PiAiReplayState } from '../src/replay.ts' import { assemble, type AssembledResult } from './assemble.ts' interface ProviderCase { - provider: 'azure-openai-responses' | 'anthropic' - api: 'azure-openai-responses' | 'anthropic-messages' + provider: 'openai' | 'anthropic' + api: 'openai-responses' | 'anthropic-messages' model: string apiKey?: string baseURL?: string + headers?: Record } -const azureOpenAIBaseURL = process.env.DSH_PI_AI_AZURE_OPENAI_BASE_URL ?? process.env.AZURE_OPENAI_BASE_URL +const openAIBaseURL = process.env.DSH_PI_AI_OPENAI_BASE_URL +const azureOpenAIKey = process.env.AZURE_OPENAI_API_KEY const providerCases: ProviderCase[] = [ { - provider: 'azure-openai-responses', - api: 'azure-openai-responses', - model: process.env.DSH_PI_AI_AZURE_OPENAI_MODEL ?? 'gpt-5.5', - ...process.env.AZURE_OPENAI_API_KEY ? { apiKey: process.env.AZURE_OPENAI_API_KEY } : {}, - ...azureOpenAIBaseURL ? { baseURL: azureOpenAIBaseURL } : {}, + provider: 'openai', + api: 'openai-responses', + model: process.env.DSH_PI_AI_OPENAI_MODEL ?? 'gpt-5.5', + ...azureOpenAIKey ? { apiKey: azureOpenAIKey, headers: { 'api-key': azureOpenAIKey } } : {}, + ...openAIBaseURL ? { baseURL: openAIBaseURL } : {}, }, { provider: 'anthropic', @@ -43,6 +45,7 @@ async function harness(): Promise { provider: profile.provider, ...profile.apiKey === undefined ? {} : { apiKey: profile.apiKey }, ...profile.baseURL === undefined ? {} : { baseURL: profile.baseURL }, + ...profile.headers === undefined ? {} : { headers: profile.headers }, })), }) return ctx From f21ed1bfa05449045b6d1b425def6e1c44c90d5e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:06:47 +0800 Subject: [PATCH 233/323] refactor(core): use initiator in loop internals --- ...2026-07-15-agent-initiator-scope.i18n.yaml | 4 +-- .../2026-07-15-agent-initiator-scope.md | 6 ++-- .../2026-07-15-agent-initiator-scope.zh.md | 6 ++-- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/agent.ts | 2 +- packages/core/agent-loop/src/loop.ts | 28 ++++++++++--------- packages/core/agent-loop/src/tool-calls.ts | 9 ++---- 7 files changed, 28 insertions(+), 29 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml index 9d9e11522f..7c9a43da69 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-initiator-scope.md: 480bb56f811567406e964ca94fca04fd3d4ace62 -2026-07-15-agent-initiator-scope.zh.md: 29ea3a47f42d607a4584b888ace232de124e7598 +2026-07-15-agent-initiator-scope.md: 61aad24c13d66f206fed81ae6eb074666b23d0d2 +2026-07-15-agent-initiator-scope.zh.md: e420e3cd5fa4b2b2f868be11080c37f29b2ce313 diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md index 480bb56f81..61aad24c13 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md @@ -16,7 +16,7 @@ The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the in `currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. -`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. +`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Its package-private loop, turn, step, and tool-call helpers recover the exact Agent from `ctx.agents` instead of forwarding the concrete driver through their signatures. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. @@ -30,9 +30,9 @@ This decision extends the [Agent registration-scope contract](2026-07-08-agent-s ## Verification -Agent service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, AgentRegistry restart, and root teardown. Composition, module-graph, build, and runtime-closure checks keep `ctx.agents` wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses without another provider. +Agent service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, AgentRegistry restart, root teardown, and package-private loop and tool scheduling through the ambient lookup. Composition, module-graph, build, and runtime-closure checks keep `ctx.agents` wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses without another provider. -Only a test-double host-aware transport consumes ambient identity; it derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by the boundary operation; that work remains subject to its owner's explicit stop contract. +A test-double host-aware transport derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by the boundary operation; that work remains subject to its owner's explicit stop contract. ## Alternatives considered diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md index 29ea3a47f4..e420e3cd5f 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md @@ -16,7 +16,7 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 `currentInitiator()` 用于可选读取，`requireInitiator()` 抛出 `no initiating agent is active`，`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 -`AgentLoop` 已经注入 `ctx.agents`，并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 +`AgentLoop` 已经注入 `ctx.agents`，并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。其包内私有的循环、轮次、步骤和工具调用辅助函数从 `ctx.agents` 恢复同一个 Agent，无需在函数签名中转发具体驱动。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 @@ -30,9 +30,9 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 ## 验证 -Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启及根 Context 销毁。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线，无需其他提供方。 +Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启、根 Context 销毁，以及包内私有的循环和工具调度通过隐式查找完成。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线，无需其他提供方。 -只有测试替身形式的宿主感知传输层消费隐式身份；它在内部推导 `X-Harness-Session-Id`，并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空边界操作所返回 Promise 之外的异步工作；这类工作仍由所属方的显式停止契约管理。 +测试替身形式的宿主感知传输层在内部推导 `X-Harness-Session-Id`，并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空边界操作所返回 Promise 之外的异步工作；这类工作仍由所属方的显式停止契约管理。 ## 考虑过的替代方案 diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index db5861f8c1..f0030845c1 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -50,7 +50,7 @@ The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publicati ### Loop lifecycle (`loop.ts`) -The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`, so process-local asynchronous continuations can recover the initiating Agent. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules. +The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`, so package-private loop, turn, step, and tool-call helpers recover the exact Agent from `ctx.agents` instead of forwarding the concrete driver through their signatures. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules. Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index 6ab02bfc13..61b661c082 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -387,7 +387,7 @@ export class ReactLoopAgent implements Agent { [startDriver](): void { if (this._status === 'disposed') return this.driverStarted = true - this.done = this.loopCtx.agents.withInitiator(this, () => runLoop(this.loopCtx, this, { + this.done = this.loopCtx.agents.withInitiator(this, () => runLoop(this.loopCtx, { inbox: this.#inbox, maxParallelToolCalls: this.maxParallelToolCalls, setStatus: (status) => { this.setStatus(status) }, diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index a153eba7e4..56211fb2e0 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -19,7 +19,6 @@ import { renderPrompt } from '@deepseek-ai/dsh-system-prompt' import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt' import type {} from '@deepseek-ai/dsh-tools' import { executeToolCalls } from './tool-calls.ts' -import type { ReactLoopAgent } from './agent.ts' import type { Inbox } from './inbox.ts' /** An Error with an optional machine-readable code (e.g., from LlmError or a throwing plugin). */ @@ -96,11 +95,13 @@ export interface LoopHandle { /** * Drive queued batches as durable turns until disposal. Plugin failures end the * current turn without terminating the driver. - * @param ctx - the plugin context the loop reaches events (agent/…, session/flush) and services (systemPrompt, llm, tools) through. - * @param agent - the agent this invocation drives for its whole lifetime (its inbox, session, and options). + * @param ctx - the plugin context the loop reaches its initiating Agent, + * events (agent/…, session/flush), and services (systemPrompt, llm, tools) + * through. * @param handle - the bridge to the agent's mutable state: status/abort setters plus the disposal and cancel-marker reads. */ -export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopHandle): Promise { +export async function runLoop(ctx: Context, handle: LoopHandle): Promise { + const agent = ctx.agents.requireInitiator() // Per-instance prefix and request-header state; conversation history remains in the session log. const transmission = createTransmissionLog() @@ -138,7 +139,7 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH const turn = lastTurnNumber(session) + 1 let terminalStopped = false try { - terminalStopped = await runTurn(ctx, events, agent, handle, turn, transmission) + terminalStopped = await runTurn(ctx, events, handle, turn, transmission) } catch (error: unknown) { // Pre-turn failure has no durable boundary to close; report it without appending outside a turn. const err = toError(error) @@ -161,8 +162,9 @@ export async function runLoop(ctx: Context, agent: ReactLoopAgent, handle: LoopH } async function runTurn( - ctx: Context, events: AgentEventDispatch, agent: ReactLoopAgent, handle: LoopHandle, turn: number, transmission: TransmissionLog, + ctx: Context, events: AgentEventDispatch, handle: LoopHandle, turn: number, transmission: TransmissionLog, ): Promise { + const agent = ctx.agents.requireInitiator() const { session } = agent // Drain before opening the turn, but append only after `turn/start`. @@ -262,7 +264,7 @@ async function runTurn( // Steering from the previous round's continuation listeners joins before // the request. - drainSteering(agent, handle.inbox, turn) + drainSteering(session, handle.inbox, turn) // The step's AbortController exists BEFORE any async pre-step work so a // dispose() or cancel() — in a synchronous turn-start listener or an @@ -336,7 +338,7 @@ async function runTurn( let stepOutcome: { hadToolCalls: boolean; finish: FinishReason } | { error: Error } try { stepOutcome = await runStep( - ctx, events, agent, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) + ctx, events, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) } catch (error: unknown) { stepOutcome = { error: toError(error) } } finally { @@ -365,7 +367,7 @@ async function runTurn( if (stepReason) reason = stepReason // Steering that arrived during streaming/tool execution. - const steered = drainSteering(agent, handle.inbox, turn) + const steered = drainSteering(session, handle.inbox, turn) closeStep() @@ -455,10 +457,10 @@ async function runTurn( } /** Drain the steering queue into the session. Returns whether any arrived. */ -function drainSteering(agent: ReactLoopAgent, inbox: Inbox, turn: number): boolean { +function drainSteering(session: Session, inbox: Inbox, turn: number): boolean { const messages = inbox.drainSteering() for (const message of messages) { - agent.session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' }) + session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' }) } return messages.length > 0 } @@ -472,7 +474,6 @@ function drainSteering(agent: ReactLoopAgent, inbox: Inbox, turn: number): boole async function runStep( ctx: Context, events: AgentEventDispatch, - agent: ReactLoopAgent, handle: LoopHandle, turn: number, step: number, @@ -482,6 +483,7 @@ async function runStep( transmission: TransmissionLog, signal: AbortSignal, ): Promise<{ hadToolCalls: boolean; finish: FinishReason }> { + const agent = ctx.agents.requireInitiator() const { session, options } = agent // Seed the first request from agent options and later requests from the logged header; @@ -567,7 +569,7 @@ async function runStep( if (toolCalls.length === 0) return { hadToolCalls: false, finish: assembler.finish } return handle.withToolBatch(async (acceptContext) => { await executeToolCalls( - ctx, agent, turn, step, toolCalls, signal, handle.maxParallelToolCalls, acceptContext, + ctx, turn, step, toolCalls, signal, handle.maxParallelToolCalls, acceptContext, ) return { hadToolCalls: true, finish: assembler.finish } }) diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index 3f3581c70a..0b9f9ae26b 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -14,7 +14,6 @@ import { assertNever, type ToolCallBlock } from '@deepseek-ai/dsh-llm' import type { HookContext } from '@deepseek-ai/dsh-agent' import type { Session } from '@deepseek-ai/dsh-session' import { TOOL_REGISTRY_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools' -import type { ReactLoopAgent } from './agent.ts' /** One tool call after argument parsing, ready to schedule. */ interface PlannedCall { @@ -35,7 +34,6 @@ interface Slot { * accepting their context into the batch FIFO owned by the caller. * * @param ctx - loop context that owns the tool registry. - * @param agent - agent and session receiving the call lifecycle. * @param turn - current turn number. * @param step - current step number. * @param toolCalls - assistant calls in model order. @@ -45,7 +43,6 @@ interface Slot { */ export async function executeToolCalls( ctx: Context, - agent: ReactLoopAgent, turn: number, step: number, toolCalls: ToolCallBlock[], @@ -53,7 +50,7 @@ export async function executeToolCalls( maxParallel: number, acceptContext: (context: HookContext) => void, ): Promise { - const { session } = agent + const agent = ctx.agents.requireInitiator() // Inputs are distinct because tools/execute wrappers may replace `exec.signal`. const planned: PlannedCall[] = toolCalls.map(block => ({ @@ -74,7 +71,7 @@ export async function executeToolCalls( const first = planned[next]! const mode = ctx.tools.executionMode(first.exec).kind const group = mode === 'parallel' ? planned.slice(next) : [first] - next += await runGroup(ctx, session, turn, step, group, mode, signal, maxParallel, acceptContext) + next += await runGroup(ctx, turn, step, group, mode, signal, maxParallel, acceptContext) } } @@ -96,7 +93,6 @@ function parseArguments(raw: string): unknown { */ async function runGroup( ctx: Context, - session: Session, turn: number, step: number, group: PlannedCall[], @@ -105,6 +101,7 @@ async function runGroup( maxParallel: number, acceptContext: (context: HookContext) => void, ): Promise { + const { session } = ctx.agents.requireInitiator() /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) const slots: (Slot | undefined)[] = group.map(() => undefined) From fc478d675c8ce32bc838f2f56a60ac0e0cdc1511 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 14:10:47 +0800 Subject: [PATCH 234/323] fix(ci): suppress bearer auth for Azure API keys --- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 3 ++- packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts | 4 +++- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 26fbb392de..af791bd806 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -176,7 +176,7 @@ describe('PiAiAdapter provider routing', () => { provider: 'openai', apiKey: 'test-key', baseURL: `${server.url}/api/projects/openai/openai/v1`, - headers: { 'api-key': 'test-key' }, + headers: { 'api-key': 'test-key', Authorization: '' }, maxRetries: 0, }], }) @@ -184,6 +184,7 @@ describe('PiAiAdapter provider routing', () => { expect(result.finish.kind).toBe('error') expect(server.paths).toEqual(['/api/projects/openai/openai/v1/responses']) expect(server.headers[0]?.['api-key']).toBe('test-key') + expect(server.headers[0]?.authorization).toBe('') }) it.each([ diff --git a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts index a2fcc2c143..107c12d264 100644 --- a/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts +++ b/packages/llm/llm-pi-ai/tests/provider-apis.e2e.ts @@ -23,7 +23,9 @@ const providerCases: ProviderCase[] = [ provider: 'openai', api: 'openai-responses', model: process.env.DSH_PI_AI_OPENAI_MODEL ?? 'gpt-5.5', - ...azureOpenAIKey ? { apiKey: azureOpenAIKey, headers: { 'api-key': azureOpenAIKey } } : {}, + ...azureOpenAIKey + ? { apiKey: azureOpenAIKey, headers: { 'api-key': azureOpenAIKey, Authorization: '' } } + : {}, ...openAIBaseURL ? { baseURL: openAIBaseURL } : {}, }, { From 9163f6129947b4f908d785968fe3c9dbf963144c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:14:02 +0800 Subject: [PATCH 235/323] docs: include JSDoc in website API markers --- scripts/gen-website-api.ts | 58 ++- website/zh-CN/api/cordis/context.md | 100 +++++ website/zh-CN/api/cordis/events.md | 62 ++++ website/zh-CN/api/cordis/fiber.md | 86 +++++ website/zh-CN/api/cordis/registry.md | 28 ++ website/zh-CN/api/cordis/service.md | 8 + website/zh-CN/api/harness/agent-loop.md | 21 ++ website/zh-CN/api/harness/agents.md | 91 +++++ website/zh-CN/api/harness/approval.md | 18 + website/zh-CN/api/harness/bash-env.md | 15 + website/zh-CN/api/harness/bash.md | 22 ++ website/zh-CN/api/harness/code-runtime.md | 22 ++ website/zh-CN/api/harness/compact.md | 32 ++ website/zh-CN/api/harness/events.md | 350 ++++++++++++++++++ website/zh-CN/api/harness/fs.md | 70 ++++ website/zh-CN/api/harness/llm.md | 27 ++ website/zh-CN/api/harness/permission.md | 30 ++ website/zh-CN/api/harness/sandbox.md | 11 + .../zh-CN/api/harness/session-persistence.md | 35 ++ website/zh-CN/api/harness/session-query.md | 26 ++ website/zh-CN/api/harness/sessions.md | 99 +++++ website/zh-CN/api/harness/skills.md | 30 ++ website/zh-CN/api/harness/spill-store.md | 5 + website/zh-CN/api/harness/subagents.md | 25 ++ website/zh-CN/api/harness/system-prompt.md | 30 ++ website/zh-CN/api/harness/tasks.md | 63 ++++ website/zh-CN/api/harness/token-meter.md | 22 ++ website/zh-CN/api/harness/tools.md | 54 +++ website/zh-CN/api/harness/user-interaction.md | 12 + website/zh-CN/api/harness/web.md | 31 ++ website/zh-CN/api/harness/workflows.md | 6 + website/zh-CN/api/index.md | 2 +- 32 files changed, 1479 insertions(+), 12 deletions(-) diff --git a/scripts/gen-website-api.ts b/scripts/gen-website-api.ts index 0420ad2ff3..480c19779f 100644 --- a/scripts/gen-website-api.ts +++ b/scripts/gen-website-api.ts @@ -20,11 +20,12 @@ * cannot land undocumented without CI going red. Pages are English (the * planned zh translation flow arrives separately; see docs/i18n/README.md). * - * Signature fences use the ` ```ts website-api ` info string: doc-typecheck - * only processes its known info strings, so these bare (non-compilable) - * signature fragments are skipped there, while VitePress still highlights the - * `ts` token. The sidebar fragment `website/.vitepress/config/api-sidebar.json` - * is generated alongside so navigation can never drift from the page set. + * Signature fences use the ` ```ts website-api ` info string and retain the + * declaration's original source JSDoc. doc-typecheck only processes its known + * info strings, so these bare (non-compilable) fragments are skipped there, + * while VitePress still highlights the `ts` token. The sidebar fragment + * `website/.vitepress/config/api-sidebar.json` is generated alongside so + * navigation can never drift from the page set. * * `tsx scripts/gen-website-api.ts` → write pages + sidebar * `tsx scripts/gen-website-api.ts --check` → exit 1 if committed copies are @@ -64,6 +65,8 @@ interface MemberDoc { heading: string /** All overload signature lines (bodies stripped). */ signatures: string[] + /** Original source JSDoc, dedented only from its containing declaration. */ + jsDoc: string /** Description prose, one paragraph per line. */ doc: string /** Parameter name → `@param` text, in declaration order. */ @@ -166,6 +169,20 @@ function load(rel: string): { sf: ts.SourceFile; text: string } { // The module-merge walk (cordisModuleBody / eventMembers / serviceClasses) is // shared with gen-cordis-catalog.ts via cordis-walk.ts. +/** Original JSDoc with only the source container's indentation removed. */ +function sourceJSDoc(text: string, sf: ts.SourceFile, node: ts.Node): string { + const raw = rawJsDoc(text, node) + if (raw === '') return '' + const { line } = sf.getLineAndCharacterOfPosition(node.getStart(sf)) + const lineStart = sf.getPositionOfLineAndCharacter(line, 0) + const indent = text.slice(lineStart, node.getStart(sf)) + return raw.split('\n') + .map((sourceLine, index) => index > 0 && sourceLine.startsWith(indent) + ? sourceLine.slice(indent.length) + : sourceLine) + .join('\n') +} + /** Signature text of a member: full text minus body/initializer, whitespace * collapsed, trailing semicolon stripped. */ function signatureOf(member: ts.Node, sf: ts.SourceFile): string { @@ -219,7 +236,7 @@ function memberDoc( const first = group[0] if (!first) throw new Error(`gen-website-api: empty member group for ${name}`) // Doc from the first overload that carries JSDoc prose. - const rawDocs = group.map(m => rawJsDoc(text, m)) + const rawDocs = group.map(m => sourceJSDoc(text, sf, m)) const docIndex = rawDocs.findIndex(r => parseJsDoc(r).doc !== '') const raw = docIndex === -1 ? '' : (rawDocs[docIndex] ?? '') const doc = parseJsDoc(raw).doc @@ -255,6 +272,7 @@ function memberDoc( signatures: (ts.isMethodDeclaration(first) && funcLike.length > 1 ? funcLike.filter(m => ts.isMethodDeclaration(m) && !m.body) : group).map(m => signatureOf(m, sf)), + jsDoc: raw, doc, params, returns: returnsText, @@ -424,8 +442,13 @@ function declPaste(rel: string, symbol: string): { doc: string; code: string; so if (matches.length === 0) throw new Error(`gen-website-api: declaration ${symbol} not found in ${rel}`) const first = matches[0] if (!first) throw new Error(`gen-website-api: declaration ${symbol} not found in ${rel}`) - const doc = parseJsDoc(rawJsDoc(text, first)).doc - const code = matches.map(s => stripBodies(s, sf).replace(/^export\s+(default\s+)?/, '')).join('\n\n') + const firstJSDoc = sourceJSDoc(text, sf, first) + const doc = parseJsDoc(firstJSDoc).doc + const code = matches.map((statement) => { + const jsDoc = sourceJSDoc(text, sf, statement) + const declaration = stripBodies(statement, sf).replace(/^export\s+(default\s+)?/, '') + return jsDoc === '' ? declaration : `${jsDoc}\n${declaration}` + }).join('\n\n') return { doc, code, source: pointer(rel, sf, first) } } @@ -480,6 +503,8 @@ interface HarnessEvent { scope: string mode: Mode | null signature: string + /** Original source event JSDoc, dedented from its module/interface. */ + jsDoc: string doc: string params: { name: string; text: string }[] source: string @@ -494,7 +519,7 @@ function collectHarnessEvents(violations: string[]): HarnessEvent[] { const body = cordisModuleBody(sf) if (!body) continue for (const { name, member } of eventMembers(body, sf)) { - const raw = rawJsDoc(text, member) + const raw = sourceJSDoc(text, sf, member) const { doc, mode } = parseJsDoc(raw) if (!mode) violations.push(`event '${name}' (${pointer(rel, sf, member)}) is missing @mode.`) if (!doc) violations.push(`event '${name}' (${pointer(rel, sf, member)}) has no JSDoc prose.`) @@ -509,7 +534,7 @@ function collectHarnessEvents(violations: string[]): HarnessEvent[] { const tag = tags.get(pname) if (tag) params.push({ name: pname, text: tag }) } - events.push({ name, scope: name.split('/')[0] ?? name, mode, signature: signatureOf(member, sf), doc, params, source: pointer(rel, sf, member) }) + events.push({ name, scope: name.split('/')[0] ?? name, mode, signature: signatureOf(member, sf), jsDoc: raw, doc, params, source: pointer(rel, sf, member) }) } } return events.sort((a, b) => a.name.localeCompare(b.name)) @@ -548,6 +573,7 @@ function renderMember(prefix: string, m: MemberDoc): string[] { const call = m.heading === '' ? '' : m.heading lines.push(`### ${prefix}${m.name}${call}`, '') lines.push('```' + FENCE) + lines.push(m.jsDoc) for (const sig of m.signatures) lines.push(sig) lines.push('```', '') lines.push(...prose(m.doc), '') @@ -620,7 +646,7 @@ function renderEventsPage(events: HarnessEvent[]): string { for (const e of events.filter(ev => ev.scope === scope)) { lines.push(`### ${e.name}`, '') lines.push(`**Mode:** \`${e.mode ?? 'unknown'}\``, '') - lines.push('```' + FENCE, e.signature, '```', '') + lines.push('```' + FENCE, e.jsDoc, e.signature, '```', '') lines.push(...prose(e.doc), '') if (e.params.length > 0) { for (const p of e.params) lines.push(`- \`${p.name}\` — ${unlink(p.text)}`) @@ -653,6 +679,16 @@ export function generate(): Map { const events = collectHarnessEvents(violations) files.set(`${PAGES_DIR}/harness/events.md`, renderEventsPage(events)) + for (const [rel, content] of files) { + if (!rel.endsWith('.md')) continue + for (const match of content.matchAll(/^```ts website-api\n([\s\S]*?)\n```$/gm)) { + const body = match[1] ?? '' + if (!body.startsWith('/**')) { + violations.push(`${rel}: a ts website-api fence does not begin with original source JSDoc.`) + } + } + } + reportViolations('gen-website-api', violations) const sidebar = { diff --git a/website/zh-CN/api/cordis/context.md b/website/zh-CN/api/cordis/context.md index cc08f4e28a..0fbb2fcc70 100644 --- a/website/zh-CN/api/cordis/context.md +++ b/website/zh-CN/api/cordis/context.md @@ -12,6 +12,15 @@ A context is a proxy: normal property reads go through the service resolver, whi ### ctx.extend(meta?) ```ts website-api +/** + * Create a child context with extra metadata on top of the current scope. + * + * The child prototypally inherits every property of this context; own + * properties of `meta` shadow the inherited ones. The parent is not mutated. + * + * @param meta — own properties (including symbol keys) to define on the child. + * @returns a child context inheriting from this one. + */ extend(meta = {}): this ``` @@ -27,6 +36,18 @@ The child prototypally inherits every property of this context; own properties o ### ctx.isolate(name, label?) ```ts website-api +/** + * Create a child context with an independent service scope for `name`. + * + * Below the returned context, reads and writes of the service `name` + * resolve against the new label instead of the parent's, so a different + * implementation can be provided without affecting the parent scope. + * Passing the same `label` to two `isolate()` calls joins their scopes. + * + * @param name — the service name to isolate. + * @param label — scope label to join; defaults to a fresh unique symbol. + * @returns a child context whose `name` service resolves in the new scope. + */ isolate(name: string, label?: symbol) ``` @@ -43,6 +64,18 @@ Below the returned context, reads and writes of the service `name` resolve again ### ctx.intercept(name, config) ```ts website-api +/** + * Add service-specific intercept config for plugins started below this + * context. + * + * Plugins loaded under the returned context see `config` merged into the + * service's resolved config (ancestor entries first; see + * `Service[symbols.resolveConfig]`). The parent context is not affected. + * + * @param name — the service name whose config to intercept. + * @param config — the intercept config to merge for that service. + * @returns a child context carrying the additional intercept entry. + */ intercept(name: K, config: Context[K] extends { [symbols.config]: infer T } ? T : never): this intercept(name: string, config: any): this ``` @@ -60,6 +93,7 @@ Plugins loaded under the returned context see `config` merged into the service's ### ctx.root ```ts website-api +/** The root context of the application (every child context shares it). @experimental */ root: this ``` @@ -70,6 +104,7 @@ The root context of the application (every child context shares it). @experiment ### ctx.baseUrl ```ts website-api +/** Base URL used to resolve relative plugin/module specifiers, if the runtime sets one. */ baseUrl?: string ``` @@ -80,6 +115,7 @@ Base URL used to resolve relative plugin/module specifiers, if the runtime sets ### ctx.events ```ts website-api +/** The event bus. Its methods are also mixed onto `ctx` (`ctx.on`, `ctx.emit`, ...). */ events: EventsService ``` @@ -90,6 +126,7 @@ The event bus. Its methods are also mixed onto `ctx` (`ctx.on`, `ctx.emit`, ...) ### ctx.logger ```ts website-api +/** The logging service. Call `ctx.logger(name)` for a named logger. */ logger: LoggerService ``` @@ -100,6 +137,7 @@ The logging service. Call `ctx.logger(name)` for a named logger. ### ctx.reflect ```ts website-api +/** The reflection layer backing the context proxy (`ctx.get`, `ctx.provide`, ...). */ reflect: ReflectService ``` @@ -110,6 +148,7 @@ The reflection layer backing the context proxy (`ctx.get`, `ctx.provide`, ...). ### ctx.registry ```ts website-api +/** The plugin registry. Its methods are mixed onto `ctx` (`ctx.plugin`, `ctx.inject`). */ registry: RegistryService ``` @@ -122,6 +161,7 @@ The plugin registry. Its methods are mixed onto `ctx` (`ctx.plugin`, `ctx.inject ### Context.effect ```ts website-api +/** Symbol key under which a disposer exposes its {@link EffectMeta} diagnostics tree. */ static readonly effect: unique symbol ``` @@ -132,6 +172,7 @@ Symbol key under which a disposer exposes its EffectMeta diagnostics tree. ### Context.filter ```ts website-api +/** Symbol key for a context's listener filter, consulted on every event dispatch. */ static readonly filter: unique symbol ``` @@ -142,6 +183,7 @@ Symbol key for a context's listener filter, consulted on every event dispatch. ### Context.isolate ```ts website-api +/** Symbol key of the isolation map (see the `Context[symbols.isolate]` property). */ static readonly isolate: unique symbol ``` @@ -152,6 +194,7 @@ Symbol key of the isolation map (see the `Context[symbols.isolate]` property). ### Context.intercept ```ts website-api +/** Symbol key of the intercept map (see the `Context[symbols.intercept]` property). */ static readonly intercept: unique symbol ``` @@ -162,6 +205,15 @@ Symbol key of the intercept map (see the `Context[symbols.intercept]` property). ### Context.is(value) ```ts website-api +/** + * Returns true for Cordis context proxies and context prototypes. + * + * Works across realms and across multiple copies of cordis, because the + * brand is keyed by a global symbol rather than by `instanceof`. + * + * @param value — the value to test. + * @returns `true` if `value` is a Cordis context, narrowing its type. + */ static is(value: any): value is Context ``` @@ -179,6 +231,14 @@ Works across realms and across multiple copies of cordis, because the brand is k ### ctx.get(name, strict?) ```ts website-api +/** + * Read a service from the store without the inject requirement. + * + * @param name — the service name. + * @param strict — when `true` (default), only return implementations + * whose providing fiber is currently active. + * @returns the service value, or `undefined` when not (yet) provided. + */ get(name: K, strict?: boolean): undefined | this[K] get(name: string, strict?: boolean): any ``` @@ -195,6 +255,15 @@ Read a service from the store without the inject requirement. ### ctx.set(name, value) ```ts website-api +/** + * Overwrite a provided service's value. + * + * Only the fiber that provided the service may set it; setting an + * unprovided name throws. + * + * @param name — the service name. + * @param value — the new service value. + */ set(name: K, value: undefined | this[K]): void set(name: string, value: any): void ``` @@ -210,6 +279,18 @@ Only the fiber that provided the service may set it; setting an unprovided name ### ctx.provide(name, value) ```ts website-api +/** + * Register a service implementation owned by the current fiber. + * + * The service becomes visible to dependents in the same isolation scope + * once the fiber is active; it is unregistered (waking dependents) when + * the returned disposer runs or the fiber unloads. Throws if the name is + * already provided in this scope or declared as an accessor. + * + * @param name — the service name. + * @param value — the service value. + * @returns a disposer that unregisters the service. + */ provide(name: K, value: undefined | this[K]): () => void provide(name: string, value?: any): () => void ``` @@ -227,6 +308,15 @@ The service becomes visible to dependents in the same isolation scope once the f ### ctx.accessor(name, options) ```ts website-api +/** + * Define a computed context property backed by get/set hooks. + * + * The accessor is removed when the current fiber unloads. Throws if the + * name is already declared. + * + * @param name — the context property name. + * @param options — the `get` hook and optional `set` hook. + */ accessor(name: string, options: Omit): void ``` @@ -241,6 +331,16 @@ The accessor is removed when the current fiber unloads. Throws if the name is al ### ctx.mixin(name, mixins) ```ts website-api +/** + * Expose selected members of a service directly on `ctx`. + * + * Each mixed-in key becomes an accessor that forwards to the service + * (binding methods to it), so e.g. `ctx.on` forwards to `ctx.events.on`. + * Mixins are removed when the current fiber unloads. + * + * @param name — the context property holding the source service. + * @param mixins — keys to forward, or a source-key → ctx-key map. + */ mixin(name: K, mixins: (keyof this & keyof this[K])[] | Dict): void mixin(source: T, mixins: (keyof this & keyof T)[] | Dict): void ``` diff --git a/website/zh-CN/api/cordis/events.md b/website/zh-CN/api/cordis/events.md index b56f8096fe..77488b5d24 100644 --- a/website/zh-CN/api/cordis/events.md +++ b/website/zh-CN/api/cordis/events.md @@ -7,6 +7,13 @@ The event system mixed into every context. Harness-defined events are cataloged ### ctx.parallel(name, ...args) ```ts website-api +/** + * Dispatch an event, running all listeners concurrently. + * + * @param name — the event name. + * @param args — arguments passed to every listener. + * @returns a promise resolving once every listener has settled. + */ parallel(name: K, ...args: Parameters): Promise parallel(thisArg: NoInfer>, name: K, ...args: Parameters): Promise ``` @@ -23,6 +30,12 @@ Dispatch an event, running all listeners concurrently. ### ctx.emit(name, ...args) ```ts website-api +/** + * Dispatch an event synchronously, ignoring listener return values. + * + * @param name — the event name. + * @param args — arguments passed to every listener. + */ emit(name: K, ...args: Parameters): void emit(thisArg: NoInfer>, name: K, ...args: Parameters): void ``` @@ -37,6 +50,13 @@ Dispatch an event synchronously, ignoring listener return values. ### ctx.serial(name, ...args) ```ts website-api +/** + * Dispatch an event, awaiting listeners in order until one bails. + * + * @param name — the event name. + * @param args — arguments passed to each listener. + * @returns the first bail value (non-null, non-false, non-undefined), if any. + */ serial(name: K, ...args: Parameters): Promisify> serial(thisArg: NoInfer>, name: K, ...args: Parameters): Promisify> ``` @@ -53,6 +73,13 @@ Dispatch an event, awaiting listeners in order until one bails. ### ctx.bail(name, ...args) ```ts website-api +/** + * Dispatch an event, calling listeners in order until one bails. + * + * @param name — the event name. + * @param args — arguments passed to each listener. + * @returns the first bail value (non-null, non-false, non-undefined), if any. + */ bail(name: K, ...args: Parameters): ReturnType bail(thisArg: NoInfer>, name: K, ...args: Parameters): ReturnType ``` @@ -69,6 +96,16 @@ Dispatch an event, calling listeners in order until one bails. ### ctx.waterfall(name, ...args) ```ts website-api +/** + * Dispatch an event whose last argument is a `next` continuation. + * + * Each listener wraps the rest of the chain: calling `next()` invokes the + * next listener (finally the built-in behavior); not calling it vetoes. + * + * @param name — the event name. + * @param args — listener arguments; the final one is the innermost `next`. + * @returns the outermost listener's return value. + */ waterfall(name: K, ...args: Parameters): ReturnType waterfall(thisArg: NoInfer>, name: K, ...args: Parameters): ReturnType ``` @@ -86,6 +123,14 @@ Each listener wraps the rest of the chain: calling `next()` invokes the next lis ### ctx.on(name, listener, options?) ```ts website-api +/** + * Register an event listener owned by the current fiber. + * + * @param name — the event name to listen for. + * @param listener — called with the dispatch arguments. + * @param options — listener options; a boolean is shorthand for `prepend`. + * @returns a disposer removing the listener; `true` if it was still registered. + */ on(name: K, listener: Events[K], options?: boolean | EventOptions): () => boolean ``` @@ -102,6 +147,14 @@ Register an event listener owned by the current fiber. ### ctx.once(name, listener, options?) ```ts website-api +/** + * Same as `on()`, but the listener disposes itself after its first call. + * + * @param name — the event name to listen for. + * @param listener — called at most once with the dispatch arguments. + * @param options — listener options; a boolean is shorthand for `prepend`. + * @returns a disposer removing the listener; `true` if it was still registered. + */ once(name: K, listener: Events[K], options?: boolean | EventOptions): () => boolean ``` @@ -120,6 +173,7 @@ Same as `on()`, but the listener disposes itself after its first call. Options accepted by `ctx.on()` and `ctx.once()`. ```ts website-api +/** Options accepted by `ctx.on()` and `ctx.once()`. */ interface EventOptions { /** Add the listener before existing listeners for the same event. */ prepend?: boolean @@ -136,6 +190,14 @@ Event dispatch strategy used by the event service. `emit` runs synchronous listeners without awaiting them, `parallel` awaits all listeners together, `serial` awaits them in order until one bails, `bail` stops on the first synchronous bail value, and `waterfall` composes listeners around a final `next` callback. ```ts website-api +/** + * Event dispatch strategy used by the event service. + * + * `emit` runs synchronous listeners without awaiting them, `parallel` awaits + * all listeners together, `serial` awaits them in order until one bails, + * `bail` stops on the first synchronous bail value, and `waterfall` composes + * listeners around a final `next` callback. + */ type DispatchMode = 'emit' | 'parallel' | 'serial' | 'bail' | 'waterfall' ``` diff --git a/website/zh-CN/api/cordis/fiber.md b/website/zh-CN/api/cordis/fiber.md index db93a6d273..f79adbaf20 100644 --- a/website/zh-CN/api/cordis/fiber.md +++ b/website/zh-CN/api/cordis/fiber.md @@ -7,6 +7,19 @@ A fiber is one loaded plugin instance: its lifecycle state, validated config, an ### ctx.effect(execute, label?) ```ts website-api +/** + * Register a cleanup-aware effect on this fiber. + * + * `execute` runs immediately; the disposers it produces are collected and + * run (in reverse order) either when the returned disposer is called or + * when the fiber unloads, whichever comes first. Calling the disposer twice + * is a no-op. Throws `CordisError('INACTIVE_EFFECT')` if the fiber is + * already disposed, and `TypeError` if `execute` returns an invalid shape. + * + * @param execute — the effect body; see {@link Effect} for accepted shapes. + * @param label — effect label shown in `getEffects()` diagnostics. + * @returns a disposer that tears the effect down and settles once done. + */ effect(execute: () => SyncEffect, label?: string): Disposable> effect(execute: () => Effect, label?: string): AsyncDisposable> ``` @@ -24,6 +37,7 @@ Register a cleanup-aware effect on this fiber. ### ctx.fiber ```ts website-api +/** The fiber (plugin runtime instance) that owns this context. */ fiber: Fiber ``` @@ -41,6 +55,7 @@ A fiber tracks dependency state, validated config, lifecycle effects, and cleanu ### fiber.uid ```ts website-api +/** Unique id within the registry; 0 for the root fiber, `null` once disposed. */ public uid: number | null ``` @@ -51,6 +66,7 @@ Unique id within the registry; 0 for the root fiber, `null` once disposed. ### fiber.ctx ```ts website-api +/** The context this fiber's plugin runs in (extends the parent context). */ public readonly ctx: Context ``` @@ -61,6 +77,7 @@ The context this fiber's plugin runs in (extends the parent context). ### fiber.config ```ts website-api +/** The validated plugin config (updated by `update()`). */ public config: any ``` @@ -71,6 +88,7 @@ The validated plugin config (updated by `update()`). ### fiber.state ```ts website-api +/** Current lifecycle state; transitions emit `internal/status`. */ public state ``` @@ -81,6 +99,7 @@ Current lifecycle state; transitions emit `internal/status`. ### fiber.dispose ```ts website-api +/** Dispose this fiber: unload the plugin, then settle once cleanup finished. */ public readonly dispose: () => Promise ``` @@ -91,6 +110,7 @@ Dispose this fiber: unload the plugin, then settle once cleanup finished. ### fiber.store ```ts website-api +/** Snapshot of required service implementations while loaded; `undefined` otherwise. */ public store: Dict | undefined ``` @@ -101,6 +121,7 @@ Snapshot of required service implementations while loaded; `undefined` otherwise ### fiber.inertia ```ts website-api +/** The in-flight load/unload transition, if one is currently running. */ public inertia: Promise | undefined ``` @@ -111,6 +132,7 @@ The in-flight load/unload transition, if one is currently running. ### fiber.name ```ts website-api +/** The plugin's display name, inherited from the nearest named ancestor, else `'root'`. */ get name() ``` @@ -121,6 +143,12 @@ The plugin's display name, inherited from the nearest named ancestor, else `'roo ### fiber.assertActive() ```ts website-api +/** + * Throw if the fiber has already been disposed. + * + * @returns nothing when the fiber is still active. + * @throws {CordisError} `INACTIVE_EFFECT` when the fiber's uid has been cleared. + */ assertActive() ``` @@ -133,6 +161,19 @@ Throw if the fiber has already been disposed. ### fiber.effect(execute, label?) ```ts website-api +/** + * Register a cleanup-aware effect on this fiber. + * + * `execute` runs immediately; the disposers it produces are collected and + * run (in reverse order) either when the returned disposer is called or + * when the fiber unloads, whichever comes first. Calling the disposer twice + * is a no-op. Throws `CordisError('INACTIVE_EFFECT')` if the fiber is + * already disposed, and `TypeError` if `execute` returns an invalid shape. + * + * @param execute — the effect body; see {@link Effect} for accepted shapes. + * @param label — effect label shown in `getEffects()` diagnostics. + * @returns a disposer that tears the effect down and settles once done. + */ effect(execute: () => SyncEffect, label?: string): Disposable> effect(execute: () => Effect, label?: string): AsyncDisposable> ``` @@ -150,6 +191,11 @@ Register a cleanup-aware effect on this fiber. ### fiber.getEffects() ```ts website-api +/** + * Return metadata for currently registered effects. + * + * @returns one {@link EffectMeta} tree per labeled live effect. + */ getEffects() ``` @@ -162,6 +208,12 @@ Return metadata for currently registered effects. ### fiber.await() ```ts website-api +/** + * Wait for current lifecycle work and rethrow startup errors. + * + * @returns this fiber, once it has settled into a stable state. + * @throws the config-validation or plugin-startup error, if any. + */ async await() ``` @@ -174,6 +226,12 @@ Wait for current lifecycle work and rethrow startup errors. ### fiber.restart() ```ts website-api +/** + * Dispose and immediately reload this plugin with its current config. + * + * @returns a promise resolving once the reload settled. + * @throws {CordisError} `INACTIVE_EFFECT` when the fiber is already disposed. + */ async restart() ``` @@ -186,6 +244,17 @@ Dispose and immediately reload this plugin with its current config. ### fiber.update(config, noSave?) ```ts website-api +/** + * Validate and apply new config, then restart the plugin. + * + * Runs the `internal/update` waterfall first, so update hooks (and HMR) + * can veto or replace the restart. + * + * @param config — the new raw config; validated before anything restarts. + * @param noSave — hint for persistence hooks not to write the change back. + * @returns nothing; the restart runs behind the `internal/update` waterfall. + * @throws {ValidationError} when the new config fails validation. + */ update(config: any, noSave = false) ``` @@ -205,6 +274,13 @@ Effect body result accepted by `ctx.effect()` and plugin startup. Either a single disposer, a promise of one, or a (possibly async) iterable yielding several — generator effects register each yielded disposer as it is produced. ```ts website-api +/** + * Effect body result accepted by `ctx.effect()` and plugin startup. + * + * Either a single disposer, a promise of one, or a (possibly async) iterable + * yielding several — generator effects register each yielded disposer as it + * is produced. + */ type Effect = | SyncEffect | AsyncEffect @@ -218,6 +294,12 @@ Function returned by an effect to release resources during disposal. Disposers run in reverse registration order when the owning fiber unloads; they may be async, in which case unloading awaits them. ```ts website-api +/** + * Function returned by an effect to release resources during disposal. + * + * Disposers run in reverse registration order when the owning fiber unloads; + * they may be async, in which case unloading awaits them. + */ type Disposable = () => T ``` @@ -228,6 +310,7 @@ type Disposable = () => T Tree node used to expose nested effect labels for diagnostics. ```ts website-api +/** Tree node used to expose nested effect labels for diagnostics. */ interface EffectMeta { /** Human-readable effect label, e.g. `ctx.on("event")` or `ctx.provide("name")`. */ label: string @@ -243,6 +326,7 @@ interface EffectMeta { Framework error with a stable machine-readable code. ```ts website-api +/** Framework error with a stable machine-readable code. */ class CordisError extends Error { /** * @param code — the stable error code; also the default message. @@ -251,6 +335,7 @@ class CordisError extends Error { constructor(public code: CordisError.Code, message?: string) } +/** Cordis error code definitions. */ namespace CordisError { export type Code = keyof typeof Code @@ -267,6 +352,7 @@ namespace CordisError { Error raised when plugin configuration fails standard-schema validation. ```ts website-api +/** Error raised when plugin configuration fails standard-schema validation. */ class ValidationError extends TypeError { name = 'ValidationError' diff --git a/website/zh-CN/api/cordis/registry.md b/website/zh-CN/api/cordis/registry.md index 55f6d666e5..f91f5a72af 100644 --- a/website/zh-CN/api/cordis/registry.md +++ b/website/zh-CN/api/cordis/registry.md @@ -7,6 +7,16 @@ Plugin loading and dependency injection. ### ctx.inject(deps, callback) ```ts website-api +/** + * Run a callback once the requested services are available. + * + * Shorthand for `ctx.plugin({ inject, apply: callback })`: the callback + * is unloaded and re-run whenever a required service changes. + * + * @param deps — required services, as an array or a name → config map. + * @param callback — plugin body called with `(ctx, config)`. + * @returns the fiber; awaiting it settles once loading finished. + */ inject(deps: Inject, callback: Plugin.Function): Fiber & PromiseLike ``` @@ -23,6 +33,14 @@ Shorthand for `ctx.plugin({ inject, apply: callback })`: the callback is unloade ### ctx.plugin(plugin, ...args) ```ts website-api +/** + * Load a plugin in the current context. + * + * @param plugin — a function, class, or `{ apply }` object plugin. + * @param args — the plugin config, validated against its `Config` schema. + * @returns the fiber; awaiting it settles once loading finished + * (rejecting on config or startup errors). + */ plugin

(plugin: P, ...args: Spread>): Fiber & PromiseLike ``` @@ -40,11 +58,13 @@ Load a plugin in the current context. Supported plugin entrypoint shapes. ```ts website-api +/** Supported plugin entrypoint shapes. */ type Plugin = | Plugin.Function | Plugin.Constructor | Plugin.Object +/** Types associated with plugin entrypoints and runtime records. */ namespace Plugin { /** Shared metadata understood by the plugin registry and related tooling. */ export interface Base { @@ -104,8 +124,16 @@ Service dependency declaration accepted by plugins and the `@Inject` decorator. Array form requests services without intercept config. Object form maps each service name to optional intercept config for the plugin context. ```ts website-api +/** + * Service dependency declaration accepted by plugins and the `@Inject` + * decorator. + * + * Array form requests services without intercept config. Object form maps each + * service name to optional intercept config for the plugin context. + */ type Inject = (keyof M)[] | { [K in keyof M]?: M[K] } +/** Utilities for normalizing plugin dependency declarations. */ namespace Inject { /** * Convert array/object/class-inherited inject metadata into a plain map. diff --git a/website/zh-CN/api/cordis/service.md b/website/zh-CN/api/cordis/service.md index acd43163d6..13aa82a2ca 100644 --- a/website/zh-CN/api/cordis/service.md +++ b/website/zh-CN/api/cordis/service.md @@ -12,6 +12,7 @@ Subclasses call `super(ctx, name)` from their constructor. The service is regist ### service.name ```ts website-api +/** The service name this instance is registered under. */ public name!: string ``` @@ -24,6 +25,7 @@ The service name this instance is registered under. ### Service.init ```ts website-api +/** Symbol key of an instance method run after construction (class plugins). */ static readonly init: unique symbol ``` @@ -34,6 +36,7 @@ Symbol key of an instance method run after construction (class plugins). ### Service.check ```ts website-api +/** Symbol key of the availability predicate passed to `ctx.provide()`. */ static readonly check: unique symbol ``` @@ -44,6 +47,7 @@ Symbol key of the availability predicate passed to `ctx.provide()`. ### Service.config ```ts website-api +/** Symbol key of the phantom intercept-config type parameter. */ static readonly config: unique symbol ``` @@ -54,6 +58,7 @@ Symbol key of the phantom intercept-config type parameter. ### Service.invoke ```ts website-api +/** Symbol key of the call body making a service callable (e.g. `ctx.logger()`). */ static readonly invoke: unique symbol ``` @@ -64,6 +69,7 @@ Symbol key of the call body making a service callable (e.g. `ctx.logger()`). ### Service.extend ```ts website-api +/** Symbol key of the helper deriving an extended service instance. */ static readonly extend: unique symbol ``` @@ -74,6 +80,7 @@ Symbol key of the helper deriving an extended service instance. ### Service.tracker ```ts website-api +/** Symbol key of the tracker metadata used for context tracing. */ static readonly tracker: unique symbol ``` @@ -84,6 +91,7 @@ Symbol key of the tracker metadata used for context tracing. ### Service.resolveConfig ```ts website-api +/** Symbol key of the intercept-config resolution helper below. */ static readonly resolveConfig: unique symbol ``` diff --git a/website/zh-CN/api/harness/agent-loop.md b/website/zh-CN/api/harness/agent-loop.md index 6401898e24..9a43a1ba14 100644 --- a/website/zh-CN/api/harness/agent-loop.md +++ b/website/zh-CN/api/harness/agent-loop.md @@ -11,6 +11,15 @@ Concrete agent factory and driver service. ### ctx.agentLoop.create(id, options?, meta?) ```ts website-api +/** + * Create an agent and session under one caller-supplied identity, owned by + * the accessing fiber. Constructor-driven config calls mint a fresh combined + * id before entering this boundary. + * @param id - shared agent/session identity. + * @param options - concrete loop options. + * @param meta - optional fresh-session workspace metadata. + * @returns the published running agent. + */ create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent ``` @@ -27,6 +36,12 @@ Create an agent and session under one caller-supplied identity, owned by the acc ### ctx.agentLoop.createAgent(ownerCtx, options) ```ts website-api +/** + * Create an owned agent on a caller-supplied session id. + * @param ownerCtx - caller context that structurally owns the transaction. + * @param options - identities, session seed/metadata, loop options, setup, and cancellation. + * @returns the published handle. + */ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` @@ -42,6 +57,12 @@ Create an owned agent on a caller-supplied session id. ### ctx.agentLoop.resume(ownerCtx, options) ```ts website-api +/** + * Resume an owned agent from the configured persistence service. + * @param ownerCtx - caller context that owns load, setup, and the live lifecycle. + * @param options - persisted identity, loop options, setup, and cancellation. + * @returns the published handle. + */ async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise ``` diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index 8d6c84cc7a..f92f69bbeb 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -11,6 +11,18 @@ Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator ### ctx.agents.setFactory(factory) ```ts website-api +/** + * Register the agent-creation factory (the loop calls this on construction, + * effect-scoped). A traced Cordis service is canonicalized to its concrete + * target; each create/resume call is then traced through that caller's + * context so ownership follows the caller without stacking proxy layers. + * Throws if a factory is already registered. Returns the disposer; on + * dispose the factory slot is cleared. + * @param factory - the loop-owned factory {@link create}/{@link resume} delegate to. + * @returns the disposer that clears the factory slot. The exact + * Cordis effect disposer (single-shot): composite (generator) effects may + * yield it directly — exact identity nests the teardown in order. + */ setFactory(factory: AgentFactory): () => void ``` @@ -25,6 +37,15 @@ Register the agent-creation factory (the loop calls this on construction, effect ### ctx.agents.create(options) ```ts website-api +/** + * Create and publish a new agent through the registered factory. + * Distinct from {@link register} (which records an already-constructed + * agent): this constructs the agent and its session. Rejects if no factory is + * registered or creation/setup fails. The resolved {@link AgentHandle} lets + * the owner tear down exactly this agent. + * @param options - shared identity, session seed/metadata, and agent options. + * @returns the handle after setup, rollback-covered publication, and loop start complete. + */ async create(options: CreateAgentOptions): Promise ``` @@ -39,6 +60,13 @@ Create and publish a new agent through the registered factory. Distinct from reg ### ctx.agents.resume(options) ```ts website-api +/** + * Load a persisted session and resume an agent on it through the registered + * factory. Rejects if no factory is registered; the factory rejects if + * session persistence is not configured or persistence/setup fails. + * @param options - persisted identity, configuration, and optional setup. + * @returns the handle after setup, rollback-covered publication, and loop start complete. + */ async resume(options: ResumeAgentOptions): Promise ``` @@ -53,6 +81,24 @@ Load a persisted session and resume an agent on it through the registered factor ### ctx.agents.register(agent) ```ts website-api +/** + * Register a live agent. Throws if an agent with the same id is already + * registered. Emits `agent/created` on registration and `agent/disposed` + * when the calling fiber is disposed — both with the agent's scope carrier + * (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the + * emits are scope-filtered regardless of which context invoked `register` + * (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always + * requires passing the carrier). Returns the disposer. + * @param agent - the already-constructed agent to record in the store. + * @returns the EXACT Cordis effect disposer (single-shot; a repeat call + * returns undefined without awaiting an in-flight teardown). Exact + * identity is load-bearing: a composite (generator) effect that owns a + * teardown ORDER — the agent factory's lifecycle chain — must yield THIS + * function so Cordis nests the unregistration at that yield position; + * yielding a wrapper would leave it disposing as a concurrent sibling on + * owner unload, unregistering the agent (and emitting `agent/disposed`) + * while its final turn is still draining. + */ register(agent: Agent): () => void ``` @@ -67,6 +113,21 @@ Register a live agent. Throws if an agent with the same id is already registered ### ctx.agents.enter(agent, owner) ```ts website-api +/** + * Insert an already-constructed agent without announcing it. This is the + * advanced ordered-lifecycle primitive used by the async agent factory: it + * first completes setup while the agent is unpublished, then assigns the + * returned detach closure into its pre-installed composite teardown before + * calling {@link announce}. Ordinary callers use {@link register}. + * @param agent - the prepared, unpublished agent. + * @param owner - live agent whose scoped context created this agent, or + * undefined for a top-level runtime root. This is runtime ownership, not + * the resumed session's durable parent lineage. + * @returns an idempotent closure that removes this exact entry and emits + * `agent/disposed` with listener failures contained. When called from a + * synchronous `agent/created` listener, removal and disposal wait until + * that creation dispatch unwinds. + */ enter(agent: Agent, owner: Agent | undefined): () => void ``` @@ -82,6 +143,13 @@ Insert an already-constructed agent without announcing it. This is the advanced ### ctx.agents.announce(agent) ```ts website-api +/** + * Announce an agent previously inserted with {@link enter}. + * @param agent - the live inserted agent to announce. + * @throws if `agent` is not the exact live registry entry for its id, or its + * creation announcement already began (including a reentrant call from a + * creation listener). + */ announce(agent: Agent): void ``` @@ -94,6 +162,11 @@ Announce an agent previously inserted with enter. ### ctx.agents.get(id) ```ts website-api +/** + * Look up a live agent. + * @param id - the shared agent/session id to look up. + * @returns the agent, or undefined when no live agent has that id. + */ get(id: SessionId): Agent | undefined ``` @@ -108,6 +181,14 @@ Look up a live agent. ### ctx.agents.isOwnedBy(id, owner) ```ts website-api +/** + * Test whether a live agent was created through one exact parent agent's + * scoped context. Runtime ownership is independent of durable session + * lineage and remains unambiguous when unrelated providers reuse an id. + * @param id - the candidate child agent's shared agent/session id. + * @param owner - the expected runtime creator agent. + * @returns true only while the exact child entry is live under that owner. + */ isOwnedBy(id: SessionId, owner: Agent): boolean ``` @@ -123,6 +204,10 @@ Test whether a live agent was created through one exact parent agent's scoped co ### ctx.agents.list() ```ts website-api +/** + * All live agents, in registration order. + * @returns a fresh array; mutating it does not affect the registry. + */ list(): Agent[] ``` @@ -135,6 +220,12 @@ All live agents, in registration order. ### ctx.agents.roots() ```ts website-api +/** + * All live top-level agents in registration order. A top-level agent was + * created without an owning agent context; durable session lineage does not + * affect this runtime relation, so a resumed fork may still be a root. + * @returns a fresh array; mutating it does not affect the registry. + */ roots(): Agent[] ``` diff --git a/website/zh-CN/api/harness/approval.md b/website/zh-CN/api/harness/approval.md index fe3b090016..4aa2b8ad2d 100644 --- a/website/zh-CN/api/harness/approval.md +++ b/website/zh-CN/api/harness/approval.md @@ -11,6 +11,24 @@ Approval service that applies session policy before answerers and logs every ask ### ctx.approval.request(req) ```ts website-api +/** + * Ask the composed answerers to decide one readonly same-process request. + * The service borrows the request, agent, session, and live signal directly. + * The request requires an open turn because the audit pair must be enclosed + * by the durable log's commit/replay boundary; an idle ask rejects before + * appending anything. The answerer phase always produces an outcome: an + * aborted signal yields `'cancelled'`, a missing or throwing answerer yields + * `'unavailable'` (fail closed), and a rogue non-vocabulary return value is + * normalized to `'unavailable'`. A failure that prevents either audit append + * from committing still rejects because returning an unlogged decision would + * violate the pair. Session contains post-commit observer failures, so an + * authoritative append cannot reject the request or suppress its matching + * audit event. + * @param req - the pending decision (agent, tool identity, reason, signal). + * @returns the closed outcome; `'allowed-once'` is the only grant. + * @throws when no turn is open or either audit event fails before the session + * append commit point. + */ async request(req: ApprovalRequest): Promise ``` diff --git a/website/zh-CN/api/harness/bash-env.md b/website/zh-CN/api/harness/bash-env.md index f8baf32bac..906464080e 100644 --- a/website/zh-CN/api/harness/bash-env.md +++ b/website/zh-CN/api/harness/bash-env.md @@ -11,6 +11,12 @@ Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables. The names ### ctx.bashEnv.register(contributor) ```ts website-api +/** + * Register one environment contributor. Names and keys are unique; built-in + * keys are reserved. Registration is disposed with the calling plugin fiber. + * @param contributor - declared key ownership and per-execution resolver. + * @returns the disposer that unregisters the contribution. + */ register(contributor: BashEnvContributor): () => void ``` @@ -25,6 +31,11 @@ Register one environment contributor. Names and keys are unique; built-in keys a ### ctx.bashEnv.collect(execution) ```ts website-api +/** + * Build the trusted `DSH_*` snapshot for one bash tool execution. + * @param execution - the current tool execution. + * @returns an immutable environment overlay containing built-ins and current contributions. + */ collect(execution: ToolExecution): DshEnvironment ``` @@ -39,6 +50,10 @@ Build the trusted `DSH_*` snapshot for one bash tool execution. ### ctx.bashEnv.list() ```ts website-api +/** + * Enumerate plugin-contributed variables without executing their resolvers. + * @returns declarations sorted by environment variable name. + */ list(): BashEnvVariableInfo[] ``` diff --git a/website/zh-CN/api/harness/bash.md b/website/zh-CN/api/harness/bash.md index c3e4173763..f340697063 100644 --- a/website/zh-CN/api/harness/bash.md +++ b/website/zh-CN/api/harness/bash.md @@ -16,6 +16,11 @@ Implementations must honor these semantics: ### ctx.bash.sandboxMode ```ts website-api +/** + * The sandbox mode this executor applies by default, or `undefined` when it + * does not sandbox commands. + * @returns the configured default sandbox mode, when supported. + */ get sandboxMode(): SandboxMode | undefined ``` @@ -26,6 +31,12 @@ The sandbox mode this executor applies by default, or `undefined` when it does n ### ctx.bash.resolve(request) ```ts website-api +/** + * Apply implementation-owned defaults and caps to a request before execution. + * @param request - the caller's request; omitted fields get this + * implementation's defaults, capped fields are clamped. + * @returns the fully-specified spec to hand to {@link run}/{@link start}. + */ abstract resolve(request: BashExecRequest): BashExecSpec ``` @@ -40,6 +51,12 @@ Apply implementation-owned defaults and caps to a request before execution. ### ctx.bash.run(spec) ```ts website-api +/** + * Run a command in the foreground; resolves when it finishes. + * @param spec - a resolved spec from {@link resolve}, never a raw request. + * @returns the outcome; nonzero exits, timeout kills, and abort kills + * resolve with a descriptive result rather than reject. + */ abstract run(spec: BashExecSpec): Promise ``` @@ -54,6 +71,11 @@ Run a command in the foreground; resolves when it finishes. ### ctx.bash.start(spec) ```ts website-api +/** + * Start a background process and return its handle immediately. + * @param spec - a resolved spec from {@link resolve}, never a raw request. + * @returns the live process handle (reads, kill, quiescence promise). + */ abstract start(spec: BashExecSpec): BashProcess ``` diff --git a/website/zh-CN/api/harness/code-runtime.md b/website/zh-CN/api/harness/code-runtime.md index ee8300a9f0..fef72ce525 100644 --- a/website/zh-CN/api/harness/code-runtime.md +++ b/website/zh-CN/api/harness/code-runtime.md @@ -11,6 +11,13 @@ Registers one `ctx.codeRuntime` implementation. Program, budget, abort, and subs ### ctx.codeRuntime.language ```ts website-api +/** + * The source language {@link run} expects `program` to be written in, as a + * lowercase identifier. Informational, not gating — a consumer that + * generates language-specific presentation (typed SDK stubs, usage + * instructions) switches on it and fails loud on a language it cannot + * present. Well-known value: `'typescript'`. + */ abstract readonly language: string ``` @@ -21,6 +28,12 @@ The source language run expects `program` to be written in, as a lowercase ident ### ctx.codeRuntime.isolation ```ts website-api +/** + * The execution substrate, as a lowercase identifier. Informational, not + * gating — a descriptor so deployments and diagnostics can tell backends + * apart, not a security claim. Well-known values: `'worker-thread'`, + * `'process'`, `'container'`. + */ abstract readonly isolation: string ``` @@ -31,6 +44,15 @@ The execution substrate, as a lowercase identifier. Informational, not gating ### ctx.codeRuntime.run(request) ```ts website-api +/** + * Execute one program against the request's bindings and capture what it + * emitted. See the class doc for the resolution contract (error is a result + * field; rejection means seam misuse only). + * @param request - the program, its bindings, and the abort signal; the + * request carries everything the runtime acts on, with no hidden defaults. + * @returns the run's outcome: completion value (when transferable), the + * ordered log capture, and the failure (if any). + */ abstract run(request: CodeRunRequest): Promise ``` diff --git a/website/zh-CN/api/harness/compact.md b/website/zh-CN/api/harness/compact.md index 67f17cc941..e06188ee27 100644 --- a/website/zh-CN/api/harness/compact.md +++ b/website/zh-CN/api/harness/compact.md @@ -11,6 +11,21 @@ Abstract compaction service. Implementations own trigger policy, retention, and ### ctx.compact.compactIfNeeded(agent, fullSystemPrompt, sessionPrefix, signal) ```ts website-api +/** + * Check token pressure and compact if the conversation is too large. + * Estimate the next request, including its session prefix, derived history, + * and system prompt. Above threshold, compact a head-anchored range ending at + * a balanced tool boundary and reconsolidate any prior automatic checkpoint. + * Return `null` when no compaction is needed or an open tail leaves no safe + * cutoff. A single oversized retained unit or prefix cannot be repaired here. + * + * @param agent - agent context owning the session surface and model options. + * @param fullSystemPrompt - assembled system prompt, counted toward the estimate. + * @param sessionPrefix - the instance's composed session prefix, counted toward the + * estimate. + * @param signal - cancellation signal; model-backed implementations must forward it. + * @returns the compaction result, or `null` if no compaction was needed. + */ abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise ``` @@ -28,6 +43,23 @@ Check token pressure and compact if the conversation is too large. Estimate the ### ctx.compact.compactRegion(start, end, agent, signal?) ```ts website-api +/** + * Forcibly compact a range of surface nodes into a single summary node. + * `start` and `end` name an inclusive span by surface position, not numeric seq + * order; replacements can make visible seqs non-monotonic. Both edges must be + * balanced so assistant tool calls remain paired with their results. A model- + * backed implementation forwards cancellation and rejects active, missing, + * reversed, or unbalanced ranges. The target session is `agent.session`. + * Use {@link toolPairingBalancedBefore} and {@link toolPairingBalancedAfter} + * for the edge checks. + * + * @param start - first surface seq, inclusive. + * @param end - last surface seq, inclusive. + * @param agent - context whose session is mutated and whose routing options guide summarization. + * @param signal - optional cancellation; model-backed implementations must forward it. + * @throws when compaction is active or the range is missing, reversed, or unbalanced. + * @returns the appended event seqs, summary, replaced range, and token accounting. + */ abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index 8d494739ba..fcfa426a81 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -11,6 +11,16 @@ Every event the harness packages declare on the cordis event bus (40 total), gro **Mode:** `emit` ```ts website-api +/** + * A fully configured agent and live session were published. Setup is + * composition-only; `agent/session-start` is the first startup-driving seam. + * Synchronous listener failure vetoes publication, while returned-promise + * rejection is reported. Detach requested during dispatch waits until every + * creation listener has observed the stable entry. + * @param agent - the newly registered agent with its live session and completed setup. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/created'(this: Scoped, agent: Agent): void ``` @@ -25,6 +35,14 @@ A fully configured agent and live session were published. Setup is composition-o **Mode:** `emit` ```ts website-api +/** + * An agent left the registry; AgentLoop emits this after driver quiescence + * but before session detachment and scoped-registration unwind. Custom + * registry users own their driver-ordering contract. + * @param agent - the exact agent removed from the registry. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/disposed'(this: Scoped, agent: Agent): void ``` @@ -39,6 +57,16 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef **Mode:** `emit` ```ts website-api +/** + * A step or turn errored. The loop reports a failure here (plus the logger) + * even when the error has no in-turn position for a session `error` event. + * @param agent - the agent whose turn errored. + * @param turn - the turn in which the failure surfaced. + * @param step - the step at which the failure surfaced. + * @param error - the failure, verbatim. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/error'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void ``` @@ -56,6 +84,22 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w **Mode:** `serial` ```ts website-api +/** + * Awaited serial checkpoint for session-surface mutation after prompt + * assembly and before `step/start`; appends land outside the pending step. + * The loop derives history once afterward, so compaction records and + * replacements are included without rewriting an assembled request. The + * prompt and prefix are the exact pressure inputs for that request, and + * `signal` cancels listener work. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param agent - the agent opening the step. + * @param turn - the open turn number. + * @param step - the pending step number. + * @param fullSystemPrompt - the assembled prompt. + * @param sessionPrefix - the frozen request prefix. + * @param signal - the turn abort signal. + * @mode serial + */ 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void ``` @@ -75,6 +119,15 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and **Mode:** `waterfall` ```ts website-api +/** + * Allow, rewrite, or block one drained prompt before it becomes a user + * message. Call `next()` for the unchanged default. + * @param agent - the agent draining its inbox. + * @param content - the drained message's blocks, as queued. + * @param source - the message's resolved source. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/prompt-submit'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise ``` @@ -91,6 +144,15 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca **Mode:** `emit` ```ts website-api +/** + * Detached, frozen content entered the agent's inbox. Source defaults have + * already been applied, so these are the exact values retained for the log. + * @param agent - the agent whose inbox received the message. + * @param content - the accepted content blocks retained by the inbox. + * @param info - the accepted source plus whether it entered as steering. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/queued'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void ``` @@ -107,6 +169,17 @@ Detached, frozen content entered the agent's inbox. Source defaults have already **Mode:** `waterfall` ```ts website-api +/** + * Replace the frozen call configuration. Model-visible content must use + * logged channels; this seam cannot mutate messages. Injection here joins + * the next request because the current step boundary is already fixed. + * @param agent - the agent making the model call. + * @param turn - the open turn number. + * @param step - the step whose request this is. + * @param config - the config the loop would use (frozen); return a replacement to switch. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/request'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise ``` @@ -124,6 +197,20 @@ Replace the frozen call configuration. Model-visible content must use logged cha **Mode:** `waterfall` ```ts website-api +/** + * Compose request-only messages placed before derived history. The frozen + * result is computed once per loop instance, logged on its anchoring request + * header, and reused so the provider prefix remains stable. Interrupted + * composition is discarded. Composition precedes the first `agent/pre-step` + * and request boundary, so listener appends join the current request and + * pressure accounting sees the composed prefix. Changing context belongs in + * history; contributors should prepend to `await next()` to preserve registration order. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param agent - the agent whose session prefix is being composed. + * @param prefix - the frozen seed; return an extended replacement. + * @param signal - aborts composition when the step is torn down. + * @mode waterfall + */ 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise ``` @@ -140,6 +227,16 @@ Compose request-only messages placed before derived history. The frozen result i **Mode:** `emit` ```ts website-api +/** + * The session lifecycle began, once before the first turn. Use + * `agent.inject()` to seed model-facing context. This is a notification, not + * a veto; disposal requested by a lifecycle owner is rechecked before the + * driver starts. + * @param agent - the agent whose session lifecycle began. + * @param source - why the session started (fresh startup, resume, …). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/session-start'(this: Scoped, agent: Agent, source: SessionStartSource): void ``` @@ -155,6 +252,14 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to **Mode:** `emit` ```ts website-api +/** + * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does + * not enter `running` synchronously; drive lifecycle from this event. + * @param agent - the agent whose status flipped. + * @param status - the status just entered (the transition's destination). + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode emit + */ 'agent/status'(this: Scoped, agent: Agent, status: AgentStatus): void ``` @@ -170,6 +275,16 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no **Mode:** `waterfall` ```ts website-api +/** + * Waterfall: post-process the assembled assistant {@link Message} before + * tool dispatch (validation, content rewriting, …). + * @param agent - the agent that received the step's response. + * @param turn - the open turn number. + * @param step - the step that produced the message. + * @param message - the assistant message as assembled from the stream. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise ``` @@ -187,6 +302,15 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va **Mode:** `waterfall` ```ts website-api +/** + * Override whether the turn continues. The default continues after tool + * calls or steering and stops otherwise; a continue reason becomes steering. + * @param agent - the agent deciding whether to run another step. + * @param turn - the turn being continued or stopped. + * @param defaultDecision - what the loop would do absent an override. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode waterfall + */ 'agent/turn-continuation'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise ``` @@ -203,6 +327,15 @@ Override whether the turn continues. The default continues after tool calls or s **Mode:** `serial` ```ts website-api +/** + * Monotonic terminal-stop checkpoint after continuation and steering are + * folded; a stop remains authoritative through turn close and flush: + * steering queued in that window is discarded, while ordinary sends survive. + * @param agent - the agent whose composed continuation outcome may be stopped. + * @param turn - the turn at its terminal-stop checkpoint. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @mode serial + */ 'agent/turn-stop'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined ``` @@ -220,6 +353,15 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a **Mode:** `emit` ```ts website-api +/** + * A declarative agent entry failed before it could publish a live agent. + * Consumers that buffer work for the configured identity use this + * transient signal to reject that work instead of waiting forever. Normal + * factory teardown suppresses failures from the cancelled startup attempt. + * @param sessionId - exact shared agent/session identity that failed startup. + * @param error - persistence, setup, or publication failure. + * @mode emit + */ 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` @@ -237,6 +379,13 @@ A declarative agent entry failed before it could publish a live agent. Consumers **Mode:** `waterfall` ```ts website-api +/** + * Ask composed answerers for one decision. Return an outcome to claim the + * request or call `next()`; failure yields the fail-closed default. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. + * @param req - the pending decision (agent, tool identity, reason, signal). + * @mode waterfall + */ 'approval/request'(this: Scoped, req: ApprovalRequest, next: () => Promise): Promise ``` @@ -253,6 +402,13 @@ Ask composed answerers for one decision. Return an outcome to claim the request **Mode:** `waterfall` ```ts website-api +/** + * Single-slot decision for the next {@link FileSystem.editText}. Calling + * `next()` yields an unconditional edit; the first returned guard wins. + * @param target - the resolved target about to be edited. + * @param actor - the opaque tool-execution context the decider keys off. + * @mode waterfall + */ 'fs/edit-intent'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined> ``` @@ -268,6 +424,14 @@ Single-slot decision for the next FileSystem.editText. Calling `next()` yields a **Mode:** `emit` ```ts website-api +/** + * Record a successful observation. Listeners must be synchronous recorders: + * throws fail the tool call and returned promises are not awaited. + * @param target - the target that was read/written/edited. + * @param version - the version the actor now holds as its observation. + * @param actor - the observing tool-execution context; undefined records nothing useful. + * @mode emit + */ 'fs/observed'(target: FsTarget, version: FsVersion, actor: object | undefined): void ``` @@ -284,6 +448,14 @@ Record a successful observation. Listeners must be synchronous recorders: throws **Mode:** `waterfall` ```ts website-api +/** + * Single-slot decision for the next {@link FileSystem.writeText}. Calling + * `next()` yields the bare provider's unconditional write; the first listener + * that returns an intent owns the decision rather than composing with peers. + * @param target - the resolved target about to be written. + * @param actor - the opaque tool-execution context the decider keys off. + * @mode waterfall + */ 'fs/write-intent'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise): Promise ``` @@ -301,6 +473,17 @@ Single-slot decision for the next FileSystem.writeText. Calling `next()` yields **Mode:** `waterfall` ```ts website-api +/** + * Waterfall around every streaming model call (retry, replay, routing). + * Bound to the {@link LlmService}; call `next()` to reach the resolved + * adapter's stream, or yield your own chunks to short-circuit. + * @param options - the full request. A LOOP-built request arrives + * deep-frozen (mutation throws): its content is a pure function of the + * session log (the reconstructability RFC), so listeners read it, never + * rewrite it. A hand-built one-shot (compaction summarize) is the + * caller's own object and stays mutable here. + * @mode waterfall + */ 'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable): AsyncIterable ``` @@ -317,6 +500,17 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t **Mode:** `emit` ```ts website-api +/** + * Creation announcement during session publication. A synchronous throw vetoes and rolls + * back with a paired disposal; detach requested during dispatch is deferred. + * A returned-promise rejection is logged but cannot retroactively veto this + * synchronous boundary. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners + * receive only sessions entered through that agent's context. + * @param session - the session just entered and announced. + * @dshScopeScan unsupported + * @mode emit + */ 'session/created'(this: Scoped, session: Session): void ``` @@ -331,6 +525,15 @@ Creation announcement during session publication. A synchronous throw vetoes and **Mode:** `emit` ```ts website-api +/** + * Emitted once when an announced session leaves the store, including + * publication rollback, but never for an entry whose creation announcement + * did not begin. Listener failures are logged and contained. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope. + * @param session - the session that is no longer live in the store. + * @dshScopeScan unsupported + * @mode emit + */ 'session/disposed'(this: Scoped, session: Session): void ``` @@ -345,6 +548,17 @@ Emitted once when an announced session leaves the store, including publication r **Mode:** `emit` ```ts website-api +/** + * Post-commit, fire-and-forget append feed. The listener snapshot resolves + * before the log push, but callbacks run after it; observer failures are + * logged and contained without making the committed append fail. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners + * receive only events from sessions entered through that agent's context. + * @param session - the session whose log grew. + * @param event - the appended event, exactly as recorded. + * @dshScopeScan unsupported + * @mode emit + */ 'session/event'(this: Scoped, session: Session, event: SessionEvent): void ``` @@ -360,6 +574,15 @@ Post-commit, fire-and-forget append feed. The listener snapshot resolves before **Mode:** `parallel` ```ts website-api +/** + * Awaited parallel durability checkpoint: every listener runs and the + * caller awaits all of them, with no waterfall veto. Dispatch through + * {@link SessionStore.flush}. Scope-filtered dispatch + * (`@deepseek-ai/dsh-scope`) reuses the session's owner scope. + * @param session - the session whose buffered events must reach durable storage. + * @dshScopeScan unsupported + * @mode parallel + */ 'session/flush'(this: Scoped, session: Session): Promise | void ``` @@ -376,6 +599,14 @@ Awaited parallel durability checkpoint: every listener runs and the caller await **Mode:** `emit` ```ts website-api +/** + * A ready child settled. Scope-filtered dispatch uses the same delegating + * parent carrier as `subagent/start`, so the lifecycle pair reaches the + * same scoped audience. + * @param info - the run identity and terminal outcome. + * @dshScopeScan unsupported + * @mode emit + */ 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` @@ -390,6 +621,11 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c **Mode:** `emit` ```ts website-api +/** + * A provider became resolvable in the registry. + * @param provider - the registered provider. + * @mode emit + */ 'subagent/provider-added'(provider: SubagentProvider): void ``` @@ -404,6 +640,11 @@ A provider became resolvable in the registry. **Mode:** `emit` ```ts website-api +/** + * A provider left the registry. Accepted runs remain holder-owned. + * @param name - the provider name that no longer resolves. + * @mode emit + */ 'subagent/provider-removed'(name: string): void ``` @@ -418,6 +659,16 @@ A provider left the registry. Accepted runs remain holder-owned. **Mode:** `emit` ```ts website-api +/** + * A provider established a ready child. For in-process providers, + * `ctx.agents.get(info.id)` resolves during this notification. + * Scope-filtered dispatch keys the carrier by the delegating parent, so a + * parent-scoped listener observes only its own delegations. Paired with + * `subagent/end`. + * @param info - the provider and ready child identity. + * @dshScopeScan unsupported + * @mode emit + */ 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` @@ -434,6 +685,14 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( **Mode:** `waterfall` ```ts website-api +/** + * Expert waterfall over the assembled sections, tools, and variables. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners + * receive only that scope's assemblies. The returned value is authoritative. + * @param assembly - the mutable assembly built from registered providers. + * @param context - the caller's per-assembly context. + * @mode waterfall + */ 'system-prompt/assemble'(this: Scoped, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise ``` @@ -449,6 +708,11 @@ Expert waterfall over the assembled sections, tools, and variables. Scope-filter **Mode:** `emit` ```ts website-api +/** + * Emitted when any prompt provider changes. This registry notification is + * unfiltered because a global change affects every scope. + * @mode emit + */ 'system-prompt/change'(): void ``` @@ -463,6 +727,15 @@ Emitted when any prompt provider changes. This registry notification is unfilter **Mode:** `emit` ```ts website-api +/** + * A tool was registered or unregistered, or a scoped restriction changed + * (the available tool set changed — possibly for one scope only). An + * UNFILTERED registry-subject notification, deliberately not scope-filtered + * dispatch: a global change concerns every agent's next assembly, so a + * scoped listener subscribing here sees every change, not just its own + * scope's. + * @mode emit + */ 'tools/change'(): void ``` @@ -475,6 +748,14 @@ A tool was registered or unregistered, or a scoped restriction changed (the avai **Mode:** `waterfall` ```ts website-api +/** + * Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns + * a normalized result; wrappers may change only `exec.signal`, while call + * identity remains immutable. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal). + * @mode waterfall + */ 'tools/execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` @@ -489,6 +770,14 @@ Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns a nor **Mode:** `waterfall` ```ts website-api +/** + * Accept, replace, enrich, or block a normalized dispatch result. `next()` + * accepts it unchanged; thrown tools still reach this seam as errors. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the call that just ran (name, parsed arguments, caller agent). + * @param result - the dispatch outcome a listener may accept, replace, or block. + * @mode waterfall + */ 'tools/post-execute'(this: Scoped, exec: ToolExecution, result: Readonly, next: () => Promise): Promise ``` @@ -504,6 +793,13 @@ Accept, replace, enrich, or block a normalized dispatch result. `next()` accepts **Mode:** `waterfall` ```ts website-api +/** + * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing + * approval support turns `ask` into denial. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls. + * @param exec - the pending call (name, parsed arguments, caller agent). + * @mode waterfall + */ 'tools/pre-execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` @@ -518,6 +814,13 @@ Allow, deny, or ask before dispatch. `next()` delegates to allow; missing approv **Mode:** `emit` ```ts website-api +/** + * Observe the frozen, lossless-JSON final outcome. Listener failures are contained. + * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`. + * @param exec - the execution object that traversed the pipeline. + * @param result - a deep-frozen snapshot of the final returned result. + * @mode emit + */ 'tools/result'(this: Scoped, exec: Readonly, result: Readonly): undefined ``` @@ -535,6 +838,16 @@ Observe the frozen, lossless-JSON final outcome. Listener failures are contained **Mode:** `emit` ```ts website-api +/** + * One `agent()` call settled (clean result, child failure, or run + * cancellation). Paired with {@link Events['workflow/agent-start']} by + * `agent.seq`, exactly once per started call on every stop path — on an + * engine termination path (a worker killed past its grace) the end is + * engine-synthesized with outcome `'cancelled'`. + * @param info - the run's identity snapshot. + * @param agent - the call identity plus its outcome. + * @mode emit + */ 'workflow/agent-end'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): void ``` @@ -550,6 +863,15 @@ One `agent()` call settled (clean result, child failure, or run cancellation). P **Mode:** `emit` ```ts website-api +/** + * One `agent()` call established a ready child run. Paired with + * {@link Events['workflow/agent-end']} by `agent.seq`. A call that never + * receives a ready run from the provider emits neither + * event in this pair. + * @param info - the run's identity snapshot. + * @param agent - the call's sequence number, label, phase, and child id. + * @mode emit + */ 'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void ``` @@ -565,6 +887,15 @@ One `agent()` call established a ready child run. Paired with Events['workflow/a **Mode:** `emit` ```ts website-api +/** + * A workflow run settled (any stop reason). Fired when + * {@link WorkflowRun.result} resolves. Paired with + * {@link Events['workflow/start']}. + * @param info - the run's identity snapshot. + * @param result - the outcome data (stop reason, error, agent count) — + * deliberately WITHOUT the result value (see {@link WorkflowResultInfo}). + * @mode emit + */ 'workflow/end'(info: WorkflowRunInfo, result: WorkflowResultInfo): void ``` @@ -580,6 +911,12 @@ A workflow run settled (any stop reason). Fired when WorkflowRun.result resolves **Mode:** `emit` ```ts website-api +/** + * The script emitted a narration line (a `log(message)` call). + * @param info - the run's identity snapshot. + * @param message - the logged message, verbatim. + * @mode emit + */ 'workflow/log'(info: WorkflowRunInfo, message: string): void ``` @@ -595,6 +932,13 @@ The script emitted a narration line (a `log(message)` call). **Mode:** `emit` ```ts website-api +/** + * The script entered a phase (a `phase(title)` call) — progress grouping + * for observers; no execution semantics. + * @param info - the run's identity snapshot. + * @param title - the phase title, verbatim. + * @mode emit + */ 'workflow/phase'(info: WorkflowRunInfo, title: string): void ``` @@ -610,6 +954,12 @@ The script entered a phase (a `phase(title)` call) — progress grouping for obs **Mode:** `emit` ```ts website-api +/** + * A workflow run started — the script's meta block validated, the body + * about to execute. Paired with {@link Events['workflow/end']}. + * @param info - the run's identity snapshot (id + meta). + * @mode emit + */ 'workflow/start'(info: WorkflowRunInfo): void ``` diff --git a/website/zh-CN/api/harness/fs.md b/website/zh-CN/api/harness/fs.md index 1246bbd27f..aed69681f6 100644 --- a/website/zh-CN/api/harness/fs.md +++ b/website/zh-CN/api/harness/fs.md @@ -11,6 +11,15 @@ Abstract filesystem provider. Targets must preserve identity across aliases; rea ### ctx.fs.resolve(path, opts?) ```ts website-api +/** + * Resolve a model/plugin-supplied path into a stable {@link FsTarget}. May perform I/O (a + * remote/sandboxed backend may need a round-trip to map a path to a stable identity), hence + * async even though the local backend only normalizes + realpaths. + * + * @param path - the path to resolve; relative paths resolve against `opts.cwd`. + * @param opts - optional cwd override and cancellation signal. + * @returns the stable target; the same file yields the same `targetKey`. + */ abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise ``` @@ -26,6 +35,12 @@ Resolve a model/plugin-supplied path into a stable FsTarget. May perform I/O (a ### ctx.fs.stat(target, signal?) ```ts website-api +/** + * Return target metadata, or `undefined` when the target does not exist. + * @param target - the resolved target to stat. + * @param signal - aborts the metadata round-trip. + * @returns metadata only, never content; undefined for an absent target. + */ abstract stat(target: FsTarget, signal?: AbortSignal): Promise ``` @@ -41,6 +56,20 @@ Return target metadata, or `undefined` when the target does not exist. ### ctx.fs.lstat(path, opts?, signal?) ```ts website-api +/** + * Return path metadata without following the final path component when it is a + * symbolic link. This is intentionally path-shaped, not target-shaped: + * {@link resolve} follows symlinks to produce the stable identity used by + * normal reads/writes, while `lstat` lets a consumer reject the path itself + * before that follow happens. + * + * `opts.cwd` follows {@link resolve}'s cwd rules. `undefined` means the path is + * absent. + * @param path - the path to inspect; relative paths resolve against `opts.cwd`. + * @param opts - `cwd` overrides the backend's default base for relative paths. + * @param signal - aborts the metadata round-trip. + * @returns metadata only, never content; undefined for an absent path. + */ abstract lstat(path: string, opts?: { cwd?: string }, signal?: AbortSignal): Promise ``` @@ -58,6 +87,12 @@ Return path metadata without following the final path component when it is a sym ### ctx.fs.readText(target, signal?) ```ts website-api +/** + * Read the whole regular text file as a single decoded string. + * @param target - the resolved target to read. + * @param signal - aborts the read. + * @returns the full decoded UTF-8 content. + */ abstract readText(target: FsTarget, signal?: AbortSignal): Promise ``` @@ -73,6 +108,15 @@ Read the whole regular text file as a single decoded string. ### ctx.fs.streamText(target, signal?) ```ts website-api +/** + * Stream the whole regular text file as decoded text chunks (same text + * semantics as {@link readText}, for large files). The backend owns + * cross-chunk UTF-8 decoding and binary rejection so the policy layer never + * touches raw bytes. + * @param target - the resolved target to read. + * @param signal - aborts the stream, including between chunks. + * @returns the chunk iterable, decoded and validated like {@link readText}. + */ abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> ``` @@ -88,6 +132,13 @@ Stream the whole regular text file as decoded text chunks (same text semantics a ### ctx.fs.listDir(target, signal?) ```ts website-api +/** + * List direct children of a directory in stable name order. Returns resolved + * child targets plus cheap metadata only; never reads file contents. + * @param target - the resolved directory target. + * @param signal - aborts the listing. + * @returns one entry per direct child, in stable name order. + */ abstract listDir(target: FsTarget, signal?: AbortSignal): Promise ``` @@ -103,6 +154,15 @@ List direct children of a directory in stable name order. Returns resolved child ### ctx.fs.writeText(target, content, expected?, signal?) ```ts website-api +/** + * Atomically create or replace UTF-8 text. `expected` guards intent and + * staleness; omission allows unconditional overwrite. + * @param target - the resolved target to write. + * @param content - the full new file content. + * @param expected - the write intent guarding the write; omit for unconditional. + * @param signal - aborts before the atomic rename takes effect. + * @returns the outcome, including the version the write produced. + */ abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise ``` @@ -120,6 +180,16 @@ Atomically create or replace UTF-8 text. `expected` guards intent and staleness; ### ctx.fs.editText(target, edit, expected?, signal?) ```ts website-api +/** + * Atomically edit literal text. When supplied, the version guard is checked + * before matching so stale content reports `FS_STALE_VERSION`; omission edits + * the current content without a freshness precondition. + * @param target - the resolved target to edit. + * @param edit - the literal search/replace request. + * @param expected - the version guard; omit for an unconditional edit. + * @param signal - aborts before the atomic rename takes effect. + * @returns the outcome, including the version the edit produced. + */ abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise ``` diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md index a70d5bd478..f762857881 100644 --- a/website/zh-CN/api/harness/llm.md +++ b/website/zh-CN/api/harness/llm.md @@ -11,6 +11,14 @@ The abstract `llm` service: an adapter registry plus a streaming model-call surf ### ctx.llm.registerAdapter(providers, adapter) ```ts website-api +/** + * Register an adapter for the given provider routes. Throws `LlmError` with code + * `DUPLICATE_ADAPTER` if any provider already has an adapter (all-or-nothing). + * Disposed with the fiber. + * @param providers - every provider route this adapter should serve. + * @param adapter - the adapter that streams calls for those providers. + * @returns the disposer that unregisters all of them. + */ registerAdapter(providers: string[], adapter: LlmAdapter): () => void ``` @@ -26,6 +34,10 @@ Register an adapter for the given provider routes. Throws `LlmError` with code ` ### ctx.llm.listProviders() ```ts website-api +/** + * Describe provider routes with a registered adapter. + * @returns detached provider metadata in registration order. + */ listProviders(): LlmProviderInfo[] ``` @@ -38,6 +50,12 @@ Describe provider routes with a registered adapter. ### ctx.llm.listModels(provider) ```ts website-api +/** + * Discover models advertised by one registered provider. Catalog membership + * is advisory and never changes routing or request validation. + * @param provider - registered provider route to inspect. + * @returns detached model metadata in adapter-preferred order. + */ async listModels(provider: string): Promise ``` @@ -52,6 +70,15 @@ Discover models advertised by one registered provider. Catalog membership is adv ### ctx.llm.stream(options) ```ts website-api +/** + * Stream one model call as raw chunks (token-level deltas). Throws + * `LlmError` with code `NO_ADAPTER` if no adapter is registered for + * `options.provider`. Replay state is retained only when the same adapter + * instance owns its historical provider and the target provider. Dispatches + * through the `llm/stream` waterfall. + * @param options - the full request; `options.provider` selects the adapter. + * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. + */ stream(options: GenerateOptions): AsyncIterable ``` diff --git a/website/zh-CN/api/harness/permission.md b/website/zh-CN/api/harness/permission.md index fe05ef3a61..c9f99adbf1 100644 --- a/website/zh-CN/api/harness/permission.md +++ b/website/zh-CN/api/harness/permission.md @@ -11,6 +11,10 @@ Owns the deployment's permission presets and their write path. Requires a confin ### ctx.permission.names ```ts website-api +/** + * The advertised preset names, in the preset table's declaration order. + * @returns every switchable preset name. + */ get names(): readonly string[] ``` @@ -21,6 +25,13 @@ The advertised preset names, in the preset table's declaration order. ### ctx.permission.current(events) ```ts website-api +/** + * Resolve the preset matching the effective knob values. A still-matching + * last selection wins shared-bundle ties; otherwise the first table match + * wins, or {@link CUSTOM_PRESET} when no entry matches. + * @param events - the session's events in log order. + * @returns the effective preset name, or `custom` when nothing matches. + */ current(events: readonly SessionEvent[]): string ``` @@ -35,6 +46,12 @@ Resolve the preset matching the effective knob values. A still-matching last sel ### ctx.permission.resolve(name) ```ts website-api +/** + * Resolve a preset's knob bundle. + * @param name - the preset name to resolve. + * @returns the configured bundle. + * @throws when `name` is not in the table. + */ resolve(name: string): PresetSpec ``` @@ -49,6 +66,13 @@ Resolve a preset's knob bundle. ### ctx.permission.optionOf(name) ```ts website-api +/** + * Build the client option for a table entry or {@link CUSTOM_PRESET}. A + * missing label falls back to the table key. + * @param name - a table key, or `custom`. + * @returns the option a client renders. + * @throws when `name` is neither a table key nor `custom`. + */ optionOf(name: string): PresetOption ``` @@ -63,6 +87,12 @@ Build the client option for a table entry or CUSTOM_PRESET. A missing label fall ### ctx.permission.set(session, name) ```ts website-api +/** + * Record a changed preset, then update each changed knob through its own + * setter. Selecting the effective preset again appends nothing. + * @param session - the session the switch belongs to. + * @param name - the preset to switch to; unknown names throw. + */ set(session: Session, name: string): void ``` diff --git a/website/zh-CN/api/harness/sandbox.md b/website/zh-CN/api/harness/sandbox.md index bc5b1d38a5..45187e9d31 100644 --- a/website/zh-CN/api/harness/sandbox.md +++ b/website/zh-CN/api/harness/sandbox.md @@ -11,6 +11,17 @@ Abstract process-sandbox service. confine must return enforcing argv or fail clo ### ctx.sandbox.confine(argv, policy) ```ts website-api +/** + * Wrap `argv` so it executes confined under `policy` on this host; the + * caller spawns the returned argv in place of its own. + * @param argv - the exact argv the caller is about to spawn (program plus + * arguments), NOT a shell string — a shell-shaped consumer passes + * `['bash', '-c', command]`. + * @param policy - the file-effect policy this execution runs under, + * carried per call (see {@link SandboxPolicy}). + * @returns the argv to spawn instead, plus the enforcement completeness + * the selected backend achieves for it. + */ abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv ``` diff --git a/website/zh-CN/api/harness/session-persistence.md b/website/zh-CN/api/harness/session-persistence.md index e382a2f4a4..f200cb1801 100644 --- a/website/zh-CN/api/harness/session-persistence.md +++ b/website/zh-CN/api/harness/session-persistence.md @@ -11,6 +11,13 @@ Durable append-only session storage. Implementations preserve contiguous, lossle ### ctx.sessionPersistence.locate(meta) ```ts website-api +/** + * Resolve this backend's independent local artifact for a session without + * reading, creating, flushing, or otherwise materializing it. Backends such + * as SQLite that do not own one artifact per session return `undefined`. + * @param meta - the immutable session header whose artifact is requested. + * @returns the backend-specific absolute location, when one exists. + */ abstract locate(meta: SessionHeader): SessionLocation | undefined ``` @@ -25,6 +32,13 @@ Resolve this backend's independent local artifact for a session without reading, ### ctx.sessionPersistence.create(meta) ```ts website-api +/** + * Register a new session's metadata. A backend MAY defer the physical write + * until the first {@link append} (lazy materialization), in which case a + * created-but-never-appended session is absent from {@link list} + * — abandoned sessions leave nothing behind. + * @param meta - the immutable header (id, version, cwd, lineage) to record. + */ abstract create(meta: SessionHeader): Promise ``` @@ -37,6 +51,15 @@ Register a new session's metadata. A backend MAY defer the physical write until ### ctx.sessionPersistence.append(id, events) ```ts website-api +/** + * Durably persist a batch of events (called from the write-behind drain at + * the `session/flush` checkpoint). Honors the append-only and contiguous-seq + * contracts: the first event's `seq` MUST equal the stored next-seq (after + * `load` has durably closed any interrupted turn). Rejects non-JSON- + * serializable `event.data` with an error naming the offending event type. + * @param id - the session the batch belongs to. + * @param events - the contiguous batch to persist, in seq order. + */ abstract append(id: SessionId, events: readonly SessionEvent[]): Promise ``` @@ -50,6 +73,14 @@ Durably persist a batch of events (called from the write-behind drain at the `se ### ctx.sessionPersistence.load(id) ```ts website-api +/** + * Load a header and balanced contiguous log. A complete interrupted final + * turn is preserved and durably closed with missing tool errors plus any open + * step and turn boundaries; only a torn final record is discarded. Unknown + * versions and corruption in the committed prefix reject. + * @param id - the persisted session to reload. + * @returns the header and a log ending on a balanced `turn/end`. + */ abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> ``` @@ -64,6 +95,10 @@ Load a header and balanced contiguous log. A complete interrupted final turn is ### ctx.sessionPersistence.list() ```ts website-api +/** + * Lightweight listing from metadata, without a full-log parse. + * @returns one header per materialized session. + */ abstract list(): Promise ``` diff --git a/website/zh-CN/api/harness/session-query.md b/website/zh-CN/api/harness/session-query.md index f081950aa7..cc826c7af4 100644 --- a/website/zh-CN/api/harness/session-query.md +++ b/website/zh-CN/api/harness/session-query.md @@ -11,6 +11,10 @@ Live-preferred logical-corpus exact-read and relationship-tracing service. ### ctx.sessionQuery.listSessions() ```ts website-api +/** + * List the complete logical corpus using live-preferred records. + * @returns deterministic newest-first cloned session records. + */ listSessions(): Promise ``` @@ -23,6 +27,11 @@ List the complete logical corpus using live-preferred records. ### ctx.sessionQuery.listEvents(sessionId) ```ts website-api +/** + * List lightweight raw-log event records for one logical session. + * @param sessionId - live-preferred session id to read. + * @returns event records in ascending seq order. + */ async listEvents(sessionId: SessionId): Promise ``` @@ -37,6 +46,12 @@ List lightweight raw-log event records for one logical session. ### ctx.sessionQuery.traceSession(sessionId) ```ts website-api +/** + * Trace known ancestry and descendants from one corpus observation. + * @param sessionId - logical session id to trace. + * @returns a complete lineage or an explicit unresolved parent boundary. + * @throws when corpus resolution fails, the target is absent, or its known ancestry cycles. + */ async traceSession(sessionId: SessionId): Promise ``` @@ -51,6 +66,12 @@ Trace known ancestry and descendants from one corpus observation. ### ctx.sessionQuery.traceEvent(request) ```ts website-api +/** + * Trace one event's direct positional and provenance relationships. + * @param request - target session id and event seq. + * @returns direct links plus the target's positional replacement chain. + * @throws when source resolution fails, the target is absent, or surface/provenance validation fails. + */ async traceEvent(request: SessionEventTraceRequest): Promise ``` @@ -65,6 +86,11 @@ Trace one event's direct positional and provenance relationships. ### ctx.sessionQuery.readEvent(request) ```ts website-api +/** + * Read one full event plus a bounded raw-log context window. + * @param request - target session/seq and context sizes. + * @returns cloned target and neighboring events. + */ async readEvent(request: SessionEventReadRequest): Promise ``` diff --git a/website/zh-CN/api/harness/sessions.md b/website/zh-CN/api/harness/sessions.md index 712852fc49..f59001009d 100644 --- a/website/zh-CN/api/harness/sessions.md +++ b/website/zh-CN/api/harness/sessions.md @@ -12,6 +12,27 @@ Persistence is intentionally not implemented here — persistence plugins subscr ### ctx.sessions.create(id?, options?) ```ts website-api +/** + * Create a session owned by the calling fiber: disposing that fiber stops + * event notification and removes the session from the store. `options.seed` + * populates the session with a copy of those events (replay/fork); + * `options.meta` attaches creation metadata (validated absolute `cwd`, + * `parentSession` lineage) as the immutable {@link SessionHeader} (the store + * fills `version`/`id`/`createdAt`). + * + * For an agent whose session must be torn down IN ORDER with its loop (so the + * loop's final flush is captured before the store attachment ends), do NOT use this + * — fold the session lifecycle into the agent's own effect via + * {@link prepare} + {@link enter} + {@link announce} (see + * `dsh-agent-loop`'s creation transaction). + * + * @param id - the session id; omitted, the store mints `session-`. + * @param options - seed events and/or creation metadata for the header. + * @returns the live session, already entered and announced. + * @throws if a session with `id` already exists, metadata is not a plain + * lossless-JSON record with valid scalar fields, or `meta.cwd` is a + * non-absolute path (storage backends key directories off it). + */ create(id?: SessionId, options?: CreateSessionOptions): Session ``` @@ -28,6 +49,22 @@ For an agent whose session must be torn down IN ORDER with its loop (so the loop ### ctx.sessions.prepare(id?, options?) ```ts website-api +/** + * Build a session WITHOUT entering it into the store — validate the id/cwd and + * construct the {@link Session} (with its immutable {@link SessionHeader}). + * Pairs with {@link enter} + {@link announce}: a caller that owns a composite + * `ctx.effect` (the agent factory) folds the session lifecycle into that ONE + * effect so a fiber unload tears the session + agent down as a single ORDERED + * chain rather than as racing sibling effects — which would remove the publication hooks + * before the loop's closing `session/flush`, dropping the closing events. + * + * @param id - the session id; omitted, the store mints `session-`. + * @param options - seed events and/or creation metadata for the header. + * @returns the constructed session, NOT yet in the store. + * @throws if a session with `id` already exists, metadata is not a plain + * lossless-JSON record with valid scalar fields, or `meta.cwd` is a + * non-absolute path. + */ prepare(id?: SessionId, options?: CreateSessionOptions): Session ``` @@ -43,6 +80,28 @@ Build a session WITHOUT entering it into the store — validate the id/cwd and c ### ctx.sessions.enter(session) ```ts website-api +/** + * Enter a {@link prepare}d session into the store: install the module-private + * append publication hooks and add it to the store. Returns the DETACH + * disposer (hooks + store removal). Does NOT emit `session/created` — + * the caller yields this disposer inside its effect and THEN calls + * {@link announce}, so a throwing `session/created` listener rolls the attach + * back instead of leaking it. + * + * Re-checks the id for a duplicate: `prepare` and `enter` are public + * cross-package primitives and a caller may interleave arbitrary work (or + * another create) between them, so a stale prepared session must NOT overwrite + * a live store entry of the same id — its detach disposer would later delete + * the REAL session. The {@link create} convenience and the agent factory call + * the two back-to-back so they never trip this, but the public seam cannot + * assume that. + * + * @param session - a {@link prepare}d session not yet in the store. + * @returns the detach disposer (publication hooks + store removal). When called from + * a synchronous `session/created` listener, removal and disposal wait until + * that creation dispatch unwinds. + * @throws if a session with this id is already in the store. + */ enter(session: Session): () => void ``` @@ -58,6 +117,13 @@ Re-checks the id for a duplicate: `prepare` and `enter` are public cross-package ### ctx.sessions.announce(session) ```ts website-api +/** Emit `session/created` exactly once for an {@link enter}ed session (with + * the carrier {@link enter} captured). Separate from {@link enter} so the + * caller can yield the detach disposer first (rollback safety — see + * {@link enter}). + * @param session - the entered session to announce to listeners. + * @throws if the session is not live or its announcement already began, + * including a reentrant call from a creation listener. */ announce(session: Session): void ``` @@ -70,6 +136,17 @@ Emit `session/created` exactly once for an entered session (with the carrier ent ### ctx.sessions.flush(session) ```ts website-api +/** + * Dispatch the awaited `session/flush` durability checkpoint for `session`, + * with the carrier captured at {@link enter}. THE flush entry point: the + * store owns the carrier, so callers (the loop's turn-end checkpoint, idle + * injection, teardown drains) must come through here rather than dispatch a + * raw `ctx.parallel('session/flush', …)` — one owner, one spelling, and the + * scoped-dispatch invariant can pin it. + * @param session - the session whose buffered events must reach durable storage. + * @returns resolves when every flush listener has settled; after all settle, + * rejects with the first registered listener failure if any listener failed. + */ async flush(session: Session): Promise ``` @@ -84,6 +161,11 @@ Dispatch the awaited `session/flush` durability checkpoint for `session`, with t ### ctx.sessions.get(id) ```ts website-api +/** + * Look up a live session. + * @param id - the session id to look up. + * @returns the session, or undefined when no live session has that id. + */ get(id: SessionId): Session | undefined ``` @@ -98,6 +180,10 @@ Look up a live session. ### ctx.sessions.list() ```ts website-api +/** + * All live sessions, in creation order. + * @returns a fresh array; mutating it does not affect the store. + */ list(): Session[] ``` @@ -110,6 +196,19 @@ All live sessions, in creation order. ### ctx.sessions.fork(source, boundary?, childSessionId?) ```ts website-api +/** + * Create a live child session from a turn-enclosed prefix of a live source. + * `boundary` is an inclusive source event seq; omitted means the source's + * current last event. A non-empty selected slice must end at `turn/end`. + * + * @param source - Live source session object or id. + * @param boundary - Inclusive source event seq to fork through; omitted means + * the source's current last event, and omitted on an empty source forks an + * empty child. + * @param childSessionId - Optional child session id; omitted delegates to + * `SessionStore`'s id policy. + * @returns The created live child session. + */ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` diff --git a/website/zh-CN/api/harness/skills.md b/website/zh-CN/api/harness/skills.md index 32c4d1b825..31ab6cd1d9 100644 --- a/website/zh-CN/api/harness/skills.md +++ b/website/zh-CN/api/harness/skills.md @@ -11,6 +11,14 @@ Registry of skill providers. It merges provider catalogs with stable first-wins ### ctx.skills.registerProvider(provider) ```ts website-api +/** + * Register a borrowed same-process provider synchronously during plugin apply. Duplicate and + * reserved names throw; remote initialization belongs in `list()`. Fiber disposal unregisters + * the provider and invalidates catalog caches. + * @param provider - the provider to register by `provider.name`. + * @returns the exact Cordis effect disposer that unregisters this provider; + * composite effects may yield it directly to preserve teardown ordering. + */ registerProvider(provider: SkillProvider): () => void ``` @@ -25,6 +33,13 @@ Register a borrowed same-process provider synchronously during plugin apply. Dup ### ctx.skills.register(skill) ```ts website-api +/** + * Register a borrowed readonly runtime skill. Project entries outrank runtime entries, which + * outrank user entries. Same-name runtime entries are first-wins; a duplicate logs a warning and + * receives a no-op disposer so it cannot remove the winner. + * @param skill - the complete skill definition to expose for discovery. + * @returns the exact Cordis effect disposer, preserving composite teardown order and invalidating caches. + */ register(skill: SkillRegistration): () => void ``` @@ -39,6 +54,13 @@ Register a borrowed readonly runtime skill. Project entries outrank runtime entr ### ctx.skills.list(options?) ```ts website-api +/** + * List model-invocable skill summaries for a workspace. Lookup options and + * provider candidates are readonly same-process values borrowed throughout + * discovery. + * @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery. + * @returns sorted summaries, excluding skills disabled for model invocation. + */ async list(options: SkillLookupOptions = {}): Promise ``` @@ -53,6 +75,14 @@ List model-invocable skill summaries for a workspace. Lookup options and provide ### ctx.skills.get(name, options?) ```ts website-api +/** + * Load and validate the winning candidate, passing its opaque discovery locator back to the + * provider. Cancellation is rechecked after selection, including cache hits, and raced against + * loading so an uncooperative provider cannot hang the caller. + * @param name - kebab-case skill name. + * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work. + * @returns the full skill, including body content, or `undefined`. + */ async get(name: string, options: SkillLookupOptions = {}): Promise ``` diff --git a/website/zh-CN/api/harness/spill-store.md b/website/zh-CN/api/harness/spill-store.md index b7fd81c934..942e811c6b 100644 --- a/website/zh-CN/api/harness/spill-store.md +++ b/website/zh-CN/api/harness/spill-store.md @@ -15,6 +15,11 @@ Semantics every implementation must honor: ### ctx.spillStore.saveText(input) ```ts website-api +/** + * Persist `input.content` to a session-scoped spill artifact. + * @param input - the owner, provenance, suggested name, and full text to save. + * @returns the saved artifact's {@link SpillRef}; rejects on a storage failure. + */ abstract saveText(input: SaveTextSpill): Promise ``` diff --git a/website/zh-CN/api/harness/subagents.md b/website/zh-CN/api/harness/subagents.md index 52632e820d..de71a5effe 100644 --- a/website/zh-CN/api/harness/subagents.md +++ b/website/zh-CN/api/harness/subagents.md @@ -11,6 +11,13 @@ Named provider registry and capability-checked start surface. ### ctx.subagents.registerProvider(provider) ```ts website-api +/** + * Register a provider under its name. Registration is effect-scoped and HMR + * safe; removing a provider blocks new starts but does not revoke runs that + * were already returned to their holders. + * @param provider - the trusted provider implementation. + * @returns the exact Cordis effect disposer. + */ registerProvider(provider: SubagentProvider): () => void ``` @@ -25,6 +32,11 @@ Register a provider under its name. Registration is effect-scoped and HMR safe; ### ctx.subagents.getProvider(name) ```ts website-api +/** + * Look up a provider by name. + * @param name - the provider name. + * @returns the provider, or undefined when absent. + */ getProvider(name: string): SubagentProvider | undefined ``` @@ -39,6 +51,10 @@ Look up a provider by name. ### ctx.subagents.list() ```ts website-api +/** + * List registered provider names in insertion order. + * @returns the registered names. + */ list(): string[] ``` @@ -51,6 +67,15 @@ List registered provider names in insertion order. ### ctx.subagents.start(name, request) ```ts website-api +/** + * Establish a ready child on the named provider. Capability and semantic + * checks run before delegation. Provider ownership lasts until its promise + * fulfills; a rejection therefore has no run for the caller to dispose and + * emits no run lifecycle events. + * @param name - the provider to use. + * @param request - child prompt, parent, signal, and optional capabilities. + * @returns the ready holder-owned run. + */ async start(name: string, request: SubagentStartRequest): Promise ``` diff --git a/website/zh-CN/api/harness/system-prompt.md b/website/zh-CN/api/harness/system-prompt.md index 56537ac407..ac22619752 100644 --- a/website/zh-CN/api/harness/system-prompt.md +++ b/website/zh-CN/api/harness/system-prompt.md @@ -11,6 +11,14 @@ Registry service for the prompt inputs assembled before each model step. ### ctx.systemPrompt.section(section) ```ts website-api +/** + * Register an ordered prompt section in the calling context's scope. A scoped + * section shadows a global section with the same name; duplicates within one + * layer and non-finite orders throw. Registration and disposal emit + * `system-prompt/change`. + * @param section - the section to register. + * @returns the exact Cordis effect disposer. + */ section(section: PromptSection): () => void ``` @@ -25,6 +33,13 @@ Register an ordered prompt section in the calling context's scope. A scoped sect ### ctx.systemPrompt.tools(provider) ```ts website-api +/** + * Register a tool-schema provider in the calling context's scope. Global and + * matching scoped providers both contribute; returning the reserved + * {@link TOOL_ORDER_REST} name makes assembly fail. + * @param provider - evaluated for each assembly with its context. + * @returns the exact Cordis effect disposer. + */ tools(provider: (context: AssembleContext) => ToolProviderResult): () => void ``` @@ -39,6 +54,14 @@ Register a tool-schema provider in the calling context's scope. Global and match ### ctx.systemPrompt.variable(name, provider) ```ts website-api +/** + * Register a prompt variable in the calling context's scope. Scoped values + * shadow globals; invalid or duplicate names throw. A provider may return + * `undefined`, but rendering a section that references that value then fails. + * @param name - the `[a-z][a-z0-9_]*` reference name. + * @param provider - evaluated for each assembly. + * @returns the exact Cordis effect disposer. + */ variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void ``` @@ -54,6 +77,13 @@ Register a prompt variable in the calling context's scope. Scoped values shadow ### ctx.systemPrompt.assemble(context?) ```ts website-api +/** + * Assemble global and scoped providers, detach tool parameters, apply + * canonical ordering, then run the assembly waterfall. Scoped sections and + * variables shadow globals; the returned waterfall value is authoritative. + * @param context - the optional scope and plugin-defined assembly fields. + * @returns the authoritative post-waterfall assembly. + */ async assemble(context: AssembleContext = {}): Promise ``` diff --git a/website/zh-CN/api/harness/tasks.md b/website/zh-CN/api/harness/tasks.md index 5ec3061471..1a43639871 100644 --- a/website/zh-CN/api/harness/tasks.md +++ b/website/zh-CN/api/harness/tasks.md @@ -11,6 +11,14 @@ The `tasks` service: the runtime-global background task registry. See the module ### ctx.tasks.start(spec) ```ts website-api +/** + * Preflight access, validation, and owner cleanup before starting and + * atomically registering work. A throwing starter leaves nothing registered; + * after it returns, registration cannot fail. Settlement records the outcome, + * notifies listeners, and releases waiters. + * @param spec - task identity, owner, and synchronous starter. + * @returns the registry-issued `-N` id. + */ start(spec: TaskStart): TaskId ``` @@ -25,6 +33,12 @@ Preflight access, validation, and owner cleanup before starting and atomically r ### ctx.tasks.list(caller?) ```ts website-api +/** + * List caller-owned and unowned tasks in registration order without exposing + * another session's labels. + * @param caller - reading agent; a non-agent caller sees only unowned tasks. + * @returns fresh snapshots. + */ list(caller?: Agent): TaskSnapshot[] ``` @@ -39,6 +53,13 @@ List caller-owned and unowned tasks in registration order without exposing anoth ### ctx.tasks.get(id, caller?) ```ts website-api +/** + * Return a non-consuming snapshot without changing its read cursor or notice + * state. Throws for an unknown or foreign task. + * @param id - task to look up. + * @param caller - reading agent checked against the owner. + * @returns a fresh snapshot. + */ get(id: TaskId, caller?: Agent): TaskSnapshot ``` @@ -54,6 +75,14 @@ Return a non-consuming snapshot without changing its read cursor or notice state ### ctx.tasks.read(id, caller?) ```ts website-api +/** + * Read the next stream delta, or the idempotent final output after settlement. + * A terminal read marks the task reported. Throws for an unknown or foreign + * task. + * @param id - task to read. + * @param caller - reading agent checked against the owner. + * @returns output text and the post-read snapshot. + */ read(id: TaskId, caller?: Agent): TaskRead ``` @@ -69,6 +98,15 @@ Read the next stream delta, or the idempotent final output after settlement. A t ### ctx.tasks.kill(id, caller?, reason?) ```ts website-api +/** + * Request cancellation, then mark the task stopping and reported. A producer + * throw propagates without changing task state. Throws for an unknown or + * foreign task. + * @param id - task to cancel. + * @param caller - killing agent checked against the owner. + * @param reason - logged reason forwarded to the producer. + * @returns `requested` for live work, otherwise `already-finished`. + */ kill(id: TaskId, caller?: Agent, reason?: string): 'requested' | 'already-finished' ``` @@ -85,6 +123,18 @@ Request cancellation, then mark the task stopping and reported. A producer throw ### ctx.tasks.wait(id, timeoutMs, caller?, signal?) ```ts website-api +/** + * Wait for settlement or timeout without cancelling the task. Caller abort + * rejects only while the task is live; after settlement it returns the + * terminal snapshot so a notice suppressed for this waiter is still delivered. + * Timed-out and aborted waits detach their resolvers. Throws for invalid, + * unknown, or foreign input. + * @param id - task to wait for. + * @param timeoutMs - positive finite wait bound in milliseconds. + * @param caller - waiting agent checked against the owner. + * @param signal - optional cancellation of the wait itself. + * @returns snapshot at settlement or timeout. + */ async wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSignal): Promise ``` @@ -102,6 +152,13 @@ Wait for settlement or timeout without cancelling the task. Caller abort rejects ### ctx.tasks.onTaskDone(listener) ```ts website-api +/** + * Register an effect-scoped completion listener. Each listener is contained; + * returned promises are observed but not awaited. No listener runs after + * service disposal. + * @param listener - receives each terminal snapshot and its exact owner. + * @returns disposer that unregisters the listener. + */ onTaskDone(listener: TaskDoneListener): () => void ``` @@ -116,6 +173,12 @@ Register an effect-scoped completion listener. Each listener is contained; retur ### ctx.tasks.attachSurface(name) ```ts website-api +/** + * Attach an effect-scoped surface that can read and stop tasks. {@link start} + * refuses work while none is attached. + * @param name - diagnostic label; duplicate names remain independent. + * @returns disposer that detaches this surface. + */ attachSurface(name: string): () => void ``` diff --git a/website/zh-CN/api/harness/token-meter.md b/website/zh-CN/api/harness/token-meter.md index ab4dd8f684..30b83f79d4 100644 --- a/website/zh-CN/api/harness/token-meter.md +++ b/website/zh-CN/api/harness/token-meter.md @@ -11,6 +11,7 @@ Replay owner for one service-wide estimator and isolated per-session folds. ### ctx.tokenMeter.contextWindow ```ts website-api +/** Provider context-window capacity used by pressure consumers. */ readonly contextWindow: number ``` @@ -21,6 +22,22 @@ Provider context-window capacity used by pressure consumers. ### ctx.tokenMeter.measure(session, requestHeader?) ```ts website-api +/** + * Measure current request pressure and surface through the durable tail. + * + * Provider usage is reused only when the latest successful call's canonical + * request envelope matches `requestHeader` and its total is no lower than + * that call's full heuristic anchor; otherwise the complete envelope and + * surface are heuristically repriced. + * + * `requestHeader` affects request pressure only; surface fields always + * describe the current session surface. Every call clones those positional + * nodes, so measurement is O(surface). + * + * @param session - session to replay through its current durable tail. + * @param requestHeader - optional effective request envelope replacing the latest logged header. + * @returns a detached deeply immutable pressure and surface measurement. + */ measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement ``` @@ -38,6 +55,11 @@ Provider usage is reused only when the latest successful call's canonical reques ### ctx.tokenMeter.estimateMessage(message) ```ts website-api +/** + * Heuristically price one model-visible message. + * @param message - message to price without mutation. + * @returns content and role-framing tokens under the fixed service heuristic. + */ estimateMessage(message: Message): number ``` diff --git a/website/zh-CN/api/harness/tools.md b/website/zh-CN/api/harness/tools.md index 6ed4ce024d..eb416e8b75 100644 --- a/website/zh-CN/api/harness/tools.md +++ b/website/zh-CN/api/harness/tools.md @@ -11,6 +11,12 @@ Tool registry and execution pipeline. Scoped registrations shadow globals; one v ### ctx.tools.register(definition) ```ts website-api +/** + * Register globally or in the calling agent scope. Scoped tools shadow + * globals; duplicates within one layer and the reserved `run_code` name fail. + * @param definition - the tool schema, execution, and optional presentation functions. + * @returns the exact disposer that unregisters the tool. + */ register(definition: ToolDefinition): () => void ``` @@ -25,6 +31,13 @@ Register globally or in the calling agent scope. Scoped tools shadow globals; du ### ctx.tools.restrict(filter) ```ts website-api +/** + * Restrict global tools for the calling agent scope. Empty filters, unknown + * names, scope-local names, and reserved transport names fail. Restrictions + * intersect; scoped registrations remain visible. + * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove). + * @returns the exact disposer that lifts this restriction. + */ restrict(filter: ToolRestriction): () => void ``` @@ -39,6 +52,16 @@ Restrict global tools for the calling agent scope. Empty filters, unknown names, ### ctx.tools.guard(guard) ```ts website-api +/** + * Register a monotonic guard after the extensible `tools/pre-execute` + * waterfall. A plain-context guard applies globally; one registered through + * `agent.ctx` applies only to that agent. Any matching guard may deny by + * returning a reason, while no guard can force-allow a call another guard + * denied. The exact effect disposer is returned for ordered ownership and + * HMR cleanup. + * @param guard - synchronous check; a returned string denies the execution. + * @returns the exact disposer that unregisters the guard. + */ guard(guard: ToolGuard): () => void ``` @@ -53,6 +76,15 @@ Register a monotonic guard after the extensible `tools/pre-execute` waterfall. A ### ctx.tools.get(name, scope?) ```ts website-api +/** + * Look up a tool as one scope sees it (scoped + * shadows global; a restricted-away global reads as absent). Presenters pass + * the calling agent so the rendered card matches the definition that + * actually executed. + * @param name - the tool name as registered. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns the definition the scope resolves, or undefined when none is visible. + */ get(name: string, scope?: ScopeKey): ToolDefinition | undefined ``` @@ -68,6 +100,12 @@ Look up a tool as one scope sees it (scoped shadows global; a restricted-away gl ### ctx.tools.schemas(scope?) ```ts website-api +/** + * Project visible definitions onto the allowlisted model-facing schema fields, + * excluding execution and presentation callbacks. + * @param scope - the viewing scope (the agent); omitted = the global view. + * @returns one deep-cloned schema per visible tool. + */ schemas(scope?: ScopeKey): ToolSchema[] ``` @@ -82,6 +120,13 @@ Project visible definitions onto the allowlisted model-facing schema fields, exc ### ctx.tools.executionMode(exec) ```ts website-api +/** + * Classify a pending call through the caller's visible tool definition. Only + * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or + * throwing classifiers are exclusive. + * @param exec - call name, parsed arguments, and optional agent scope. + * @returns the fail-closed scheduling mode. + */ executionMode(exec: ToolExecutionInput): ToolExecutionMode ``` @@ -96,6 +141,15 @@ Classify a pending call through the caller's visible tool definition. Only an ex ### ctx.tools.execute(exec) ```ts website-api +/** + * Execute through pre-policy, guards, around-dispatch, post-policy, and final + * notification. Tool and listener failures resolve as materialized error + * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is + * the same lossless, frozen snapshot final observers receive. + * @param exec - the typed same-process call input. The registry assigns its + * correlation token before policy begins. + * @returns the materialized final result. + */ async execute(exec: ToolExecutionInput): Promise ``` diff --git a/website/zh-CN/api/harness/user-interaction.md b/website/zh-CN/api/harness/user-interaction.md index 09db0f6107..072087f8ca 100644 --- a/website/zh-CN/api/harness/user-interaction.md +++ b/website/zh-CN/api/harness/user-interaction.md @@ -11,6 +11,12 @@ ### ctx.userInteraction.registerProvider(provider) ```ts website-api +/** + * Register the UI provider. Only one provider may be active in a context. + * + * @param provider UI-side implementation that collects answers. + * @returns Disposer that unregisters this provider. + */ registerProvider(provider: UserInteractionProvider): () => void ``` @@ -25,6 +31,12 @@ Register the UI provider. Only one provider may be active in a context. ### ctx.userInteraction.ask(request) ```ts website-api +/** + * Ask the active UI provider and wait for the user's answer. + * + * @param request Questions, owner agent, and abort signal. + * @returns The answer chosen or typed by the human. + */ async ask(request: AskUserQuestionRequest): Promise ``` diff --git a/website/zh-CN/api/harness/web.md b/website/zh-CN/api/harness/web.md index ca23406caf..5827430261 100644 --- a/website/zh-CN/api/harness/web.md +++ b/website/zh-CN/api/harness/web.md @@ -18,6 +18,13 @@ Selection semantics (resolved at execution time, never order-dependent): ### ctx.web.registerSearchProvider(provider) ```ts website-api +/** + * Register a search provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER` + * if its id is already registered for search. Returns a disposer; disposed + * with the calling fiber. + * @param provider - the provider; its `id` is the registry key. + * @returns the disposer that unregisters the provider. + */ registerSearchProvider(provider: WebSearchProvider): () => void ``` @@ -32,6 +39,13 @@ Register a search provider. Throws WebError `WEB_DUPLICATE_PROVIDER` if its id i ### ctx.web.registerFetchProvider(provider) ```ts website-api +/** + * Register a fetch provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER` + * if its id is already registered for fetch. Returns a disposer; disposed + * with the calling fiber. + * @param provider - the provider; its `id` is the registry key. + * @returns the disposer that unregisters the provider. + */ registerFetchProvider(provider: WebFetchProvider): () => void ``` @@ -46,6 +60,15 @@ Register a fetch provider. Throws WebError `WEB_DUPLICATE_PROVIDER` if its id is ### ctx.web.search(request, signal?) ```ts website-api +/** + * Run one search through the selected provider. Resolves the provider at call + * time with the selection rules above; throws {@link WebError} when the + * capability cannot run. The seam enforces `request.maxResults` on the result: + * if the provider over-returns, `sources[]` is truncated and `truncated` set. + * @param request - the query plus result-shaping options. + * @param signal - optional cancellation signal forwarded to the provider. + * @returns the provider's results, capped to `request.maxResults`. + */ async search(request: WebSearchRequest, signal?: AbortSignal): Promise ``` @@ -61,6 +84,14 @@ Run one search through the selected provider. Resolves the provider at call time ### ctx.web.fetch(request, signal?) ```ts website-api +/** + * Retrieve one URL through the selected provider. Resolves the provider at + * call time with the selection rules above; throws {@link WebError} when the + * capability cannot run. A non-2xx response is a result, not a throw. + * @param request - the URL plus retrieval options. + * @param signal - optional cancellation signal forwarded to the provider. + * @returns the retrieval outcome; non-2xx responses resolve descriptively. + */ async fetch(request: WebFetchRequest, signal?: AbortSignal): Promise ``` diff --git a/website/zh-CN/api/harness/workflows.md b/website/zh-CN/api/harness/workflows.md index 5518f3e564..f34c3d8a6c 100644 --- a/website/zh-CN/api/harness/workflows.md +++ b/website/zh-CN/api/harness/workflows.md @@ -11,6 +11,12 @@ Workflow execution seam. Invalid requests throw before publication; a live run i ### ctx.workflows.start(request) ```ts website-api +/** + * Parse and execute a workflow script. + * @param request - the script, its `args`, the parent agent, and an + * optional cancel signal. + * @returns the live run; its `result` resolves when the script settles. + */ abstract start(request: WorkflowStartRequest): WorkflowRun ``` diff --git a/website/zh-CN/api/index.md b/website/zh-CN/api/index.md index 7e1812bd5f..4357fcbfe3 100644 --- a/website/zh-CN/api/index.md +++ b/website/zh-CN/api/index.md @@ -1,6 +1,6 @@ # API 参考 -本节是 DeepSeek Harness 的 API 参考。除本页外，`cordis/` 与 `harness/` 下的所有页面**由脚本从源码生成**（`pnpm run gen-website-api`，CI 校验新鲜度），签名与说明永远与代码一致；生成页目前为英文，中文版将随统一翻译流程提供。 +本节是 DeepSeek Harness 的 API 参考。除本页外，`cordis/` 与 `harness/` 下的所有页面**由脚本从源码生成**（`pnpm run gen-website-api`，CI 校验新鲜度）；签名代码块保留源码的原始 JSDoc，签名与说明永远与代码一致。生成页目前为英文，中文版将随统一翻译流程提供。 ## 框架 API From f66cde41d181cf2b6fcd80ee7426854889e8e655 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:16:07 +0800 Subject: [PATCH 236/323] docs(core): clarify initiator restoration timing --- .../2026-07-15-agent-initiator-scope.i18n.yaml | 4 ++-- .../architecture/2026-07-15-agent-initiator-scope.md | 2 +- .../architecture/2026-07-15-agent-initiator-scope.zh.md | 2 +- packages/core/agent-loop/tests/agent-initiator.spec.ts | 8 ++++---- packages/core/agent/README.md | 2 +- 5 files changed, 9 insertions(+), 9 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml index 9d9e11522f..696b119797 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-initiator-scope.md: 480bb56f811567406e964ca94fca04fd3d4ace62 -2026-07-15-agent-initiator-scope.zh.md: 29ea3a47f42d607a4584b888ace232de124e7598 +2026-07-15-agent-initiator-scope.md: 08c9eca50ed51925fec7c09eda7a82d0c61cb55b +2026-07-15-agent-initiator-scope.zh.md: 284d52126e02e44d512b88a5d64e35ba80552d9b diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md index 480bb56f81..08c9eca50e 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md @@ -16,7 +16,7 @@ The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the in `currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. -`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Concurrent drivers therefore receive independent stores, a child driver shadows its parent, and the parent store returns when the child boundary settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. +`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Concurrent drivers therefore receive independent stores. A child driver's continuations carry the child, while the caller resumes in its prior store as soon as `withInitiator()` returns; active-run tracking keeps the returned Promise in the teardown drain until it settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md index 29ea3a47f4..284d52126e 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md @@ -16,7 +16,7 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 `currentInitiator()` 用于可选读取，`requireInitiator()` 抛出 `no initiating agent is active`，`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 -`AgentLoop` 已经注入 `ctx.agents`，并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储，子驱动会遮蔽父驱动，子边界结束后父存储得到恢复。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 +`AgentLoop` 已经注入 `ctx.agents`，并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。因此，并发驱动使用彼此独立的存储。子驱动的异步延续携带子 Agent；`withInitiator()` 返回后，调用方立即恢复之前的存储，而活动运行计数仍持续跟踪返回的 Promise，直到其结束。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 diff --git a/packages/core/agent-loop/tests/agent-initiator.spec.ts b/packages/core/agent-loop/tests/agent-initiator.spec.ts index 7f0903fc00..8e9b951fa1 100644 --- a/packages/core/agent-loop/tests/agent-initiator.spec.ts +++ b/packages/core/agent-loop/tests/agent-initiator.spec.ts @@ -142,7 +142,7 @@ describe('AgentLoop initiator scope', () => { await ctx.fiber.dispose() }) - it('keeps child setup under the parent boundary, switches for the child driver, then restores the parent', async () => { + it('keeps child setup under the parent boundary and restores the parent while the child driver remains active', async () => { const adapter = new MockAdapter([ toolCallResponse('spawn', 'spawn-child', {}), toolCallResponse('observe', 'observe-child', {}), @@ -153,7 +153,7 @@ describe('AgentLoop initiator scope', () => { let parentDuringSetup: Agent | undefined let explicitChild: Agent | undefined let childDuringDriver: Agent | undefined - let parentAfterChild: Agent | undefined + let parentWhileChildDriverActive: Agent | undefined let child: Agent | undefined ctx.tools.register(defineTool({ @@ -181,9 +181,9 @@ describe('AgentLoop initiator scope', () => { }, }) child = handle.agent + parentWhileChildDriverActive = ctx.agents.requireInitiator() send(handle.agent, 'run child') await handle.agent.whenIdle() - parentAfterChild = ctx.agents.requireInitiator() await handle.dispose() return [{ type: 'text', text: 'child completed' }] }, @@ -200,7 +200,7 @@ describe('AgentLoop initiator scope', () => { expect(parentDuringSetup).toBe(parentHandle.agent) expect(explicitChild).toBe(child) expect(childDuringDriver).toBe(child) - expect(parentAfterChild).toBe(parentHandle.agent) + expect(parentWhileChildDriverActive).toBe(parentHandle.agent) expect(ctx.agents.currentInitiator()).toBeUndefined() await parentHandle.dispose() await ctx.fiber.dispose() diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 23d9d998c6..839907bf62 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -19,7 +19,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- #### Initiating Agent scope -`AgentLoop` runs each concrete driver's complete lifetime inside an initiator boundary. Concurrent drivers remain isolated, a child driver shadows its parent, and the parent returns after the child settles. Creation, persistence load, and unpublished setup remain outside the child's boundary, so setup initiated by a parent inherits the parent while `agentCtx.agent` identifies the child explicitly. +`AgentLoop` runs each concrete driver's complete lifetime inside an initiator boundary. Concurrent drivers remain isolated: a child driver's continuations carry the child, while the parent continuation regains the parent as soon as `withInitiator()` returns; drain tracking continues until the child driver's Promise settles. Creation, persistence load, and unpublished setup remain outside the child's boundary, so setup initiated by a parent inherits the parent while `agentCtx.agent` identifies the child explicitly. - `ctx.agents.currentInitiator(): Agent | undefined` — read the inherited initiator without requiring one. - `ctx.agents.requireInitiator(): Agent` — read it or throw `no initiating agent is active`. From 4791b40b269b19a3c40daae5ed412ebc5d1b6d42 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:18:13 +0800 Subject: [PATCH 237/323] fix(llm-pi-ai): classify usage-based context overflow Pass each resolved catalog model capacity into pi-ai stream conversion so the upstream full-message classifier can recognize provider-specific, silent, and length-stop overflow signals. Retain the harness text fallback for legacy provider wording and cover the catalog-resolution path with a mock-provider regression. --- packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm-pi-ai/src/adapter.ts | 2 +- packages/llm/llm-pi-ai/src/stream.ts | 34 +++++++++++++++----- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 26 ++++++++++++++- packages/llm/llm-pi-ai/tests/convert.spec.ts | 28 ++++++++++++++++ 5 files changed, 81 insertions(+), 11 deletions(-) diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index e2d56e28a5..1deae8f039 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -43,7 +43,7 @@ If a listener rewrites assembled assistant content, the loop drops replay state ## Vocabulary differences - pi-ai tool-call arguments are parsed objects; the harness stores raw JSON strings. The adapter parses input and re-stringifies output. -- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted'}` chunks, with recognized context overflow normalized to `CONTEXT_WINDOW_EXCEEDED`. +- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted'}` chunks. Provider-specific error text and usage signals evaluated against the resolved model's context window normalize overflow to `CONTEXT_WINDOW_EXCEEDED`. - pi-ai folds reasoning tokens into output usage; there is no separate reasoning count to map. - `GenerateOptions.stop` is rejected with `UNSUPPORTED_OPTION` because pi-ai's common streaming surface cannot guarantee it across providers. diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 26e28ecd1f..7f40c67da3 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -115,7 +115,7 @@ export class PiAiAdapter extends LlmAdapter { // Harness-owned and therefore win collisions. headers: requestHeaders(profile.headers), }) - yield* toStreamChunks(events) + yield* toStreamChunks(events, model.contextWindow) } finally { options.signal?.removeEventListener('abort', onCallerAbort) controller.abort('consumer stopped streaming') diff --git a/packages/llm/llm-pi-ai/src/stream.ts b/packages/llm/llm-pi-ai/src/stream.ts index f7a0d6ee7f..8bc41cded2 100644 --- a/packages/llm/llm-pi-ai/src/stream.ts +++ b/packages/llm/llm-pi-ai/src/stream.ts @@ -10,6 +10,7 @@ import { CallId, CONTEXT_WINDOW_EXCEEDED_CODE, isContextWindowExceededError, LlmError } from '@deepseek-ai/dsh-llm' import type { FinishReason, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm' +import { isContextOverflow } from '@earendil-works/pi-ai' import type { AssistantMessage, AssistantMessageEvent, Usage as PiUsage } from '@earendil-works/pi-ai' import { toPiReplayState } from './replay.ts' @@ -30,10 +31,6 @@ export function mapUsage(usage: PiUsage): TokenUsage { function classifyPiAiError(message: string): string { if (/\b(?:401|403)\b/.test(message)) return 'AUTH' if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' - // TODO: Classify the full message with pi-ai's isContextOverflow() and the - // resolved model's contextWindow so provider-specific and usage-based overflows - // reach automatic compaction. - if (isContextWindowExceededError(message)) return CONTEXT_WINDOW_EXCEEDED_CODE if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' if (/\b5\d\d\b/.test(message)) return 'SERVER' return 'PI_AI_ERROR' @@ -42,9 +39,22 @@ function classifyPiAiError(message: string): string { /** * Map a terminal pi-ai event to the harness finish reason. * @param message - the assistant message carried by the `done` or `error` event. + * @param contextWindow - resolved catalog capacity for usage-based overflow detection. * @returns the harness reason; `error` yields `{kind: 'error'}` with a code classified from the error text. */ -export function mapStopReason(message: AssistantMessage): FinishReason { +export function mapStopReason(message: AssistantMessage, contextWindow?: number): FinishReason { + const piAiOverflow = isContextOverflow(message, contextWindow) + const harnessOverflow = message.stopReason === 'error' + && message.errorMessage !== undefined + && isContextWindowExceededError(message.errorMessage) + if (piAiOverflow || harnessOverflow) { + return { + kind: 'error', + message: message.errorMessage ?? `pi-ai detected context overflow for model "${message.model}"`, + code: CONTEXT_WINDOW_EXCEEDED_CODE, + } + } + switch (message.stopReason) { case 'stop': return { kind: 'stop' } case 'length': return { kind: 'max-tokens' } @@ -62,10 +72,14 @@ export function mapStopReason(message: AssistantMessage): FinishReason { * mid-stream — failures arrive as `error` events, which become error/aborted * `finish` chunks (the harness protocol's other error-delivery style). * @param events - one assistant turn's pi-ai event stream. + * @param contextWindow - resolved catalog capacity for usage-based overflow detection. * @returns the harness chunks, ending with `usage` then `finish`; throws * `LlmError` (`STREAM_CLOSED`) if the source ends without a terminal event. */ -export async function* toStreamChunks(events: AsyncIterable): AsyncGenerator { +export async function* toStreamChunks( + events: AsyncIterable, + contextWindow?: number, +): AsyncGenerator { // pi-ai contentIndex ↔ our block index map 1:1 (both count blocks from 0 // in stream order), but we track ids per index for tool calls. const toolIds = new Map() @@ -128,13 +142,17 @@ export async function* toStreamChunks(events: AsyncIterable { const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) expect(result.finish).toMatchObject({ kind: 'error', code }) }) + + it('uses the resolved catalog context window for usage-based overflow detection', async () => { + const model = getModels('deepseek').find(candidate => candidate.id === 'deepseek-v4-flash') + if (model === undefined) throw new Error('deepseek-v4-flash missing from pi-ai test catalog') + const events = [ + '{"choices":[{"delta":{"role":"assistant","content":""},"index":0,"finish_reason":null}]}', + JSON.stringify({ + choices: [{ delta: {}, index: 0, finish_reason: 'stop' }], + usage: { prompt_tokens: model.contextWindow + 1, completion_tokens: 0 }, + }), + '[DONE]', + ] + const server = await mockServer([{ events }]) + const ctx = await harness(server.url) + + const result = await assemble(ctx, { model: model.id, messages: [] }) + + expect(result.finish).toEqual({ + kind: 'error', + message: `pi-ai detected context overflow for model "${model.id}"`, + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + }) }) describe('provider profile lifecycle', () => { diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 6c58f67bb7..a2f37ce511 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -537,6 +537,34 @@ describe('mapStopReason / mapUsage', () => { }))).toMatchObject({ kind: 'error', code: 'INVALID_REQUEST' }) }) + it('uses pi-ai provider-specific overflow classification without losing rate-limit exclusions', () => { + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'prompt is too long: 213462 tokens > 200000 maximum', + }))).toMatchObject({ kind: 'error', code: CONTEXT_WINDOW_EXCEEDED_CODE }) + expect(mapStopReason(assistant({ + stopReason: 'error', + errorMessage: 'ThrottlingException: Too many tokens, rate limit reached', + }))).toMatchObject({ kind: 'error', code: 'RATE_LIMIT' }) + }) + + it('uses the resolved context window for silent and length-stop overflows', () => { + const silent = assistant({ stopReason: 'stop', usage: usage(101, 0) }) + expect(mapStopReason(silent)).toEqual({ kind: 'stop' }) + expect(mapStopReason(silent, 100)).toEqual({ + kind: 'error', + message: 'pi-ai detected context overflow for model "deepseek-v4-flash"', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + + const truncated = assistant({ stopReason: 'length', usage: usage(80, 0, 19) }) + expect(mapStopReason(truncated)).toEqual({ kind: 'max-tokens' }) + expect(mapStopReason(truncated, 100)).toMatchObject({ + kind: 'error', + code: CONTEXT_WINDOW_EXCEEDED_CODE, + }) + }) + it('maps cache fields only when nonzero', () => { expect(mapUsage(usage(10, 5, 8, 2))).toEqual({ inputTokens: 10, From 7a9c2ef4738ce11b8c9bdde4ce65ea14bc022f61 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:20:27 +0800 Subject: [PATCH 238/323] docs(core): state loop initiator precondition --- packages/core/agent-loop/src/loop.ts | 5 ++++- packages/core/agent-loop/src/tool-calls.ts | 4 +++- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 56211fb2e0..4f2f768d89 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -94,11 +94,14 @@ export interface LoopHandle { /** * Drive queued batches as durable turns until disposal. Plugin failures end the - * current turn without terminating the driver. + * current turn without terminating the driver. The caller establishes the + * `ctx.agents.withInitiator()` boundary before entry; package-private helpers + * recover that exact Agent from the inherited store. * @param ctx - the plugin context the loop reaches its initiating Agent, * events (agent/…, session/flush), and services (systemPrompt, llm, tools) * through. * @param handle - the bridge to the agent's mutable state: status/abort setters plus the disposal and cancel-marker reads. + * @throws when no initiating Agent is active. */ export async function runLoop(ctx: Context, handle: LoopHandle): Promise { const agent = ctx.agents.requireInitiator() diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index 0b9f9ae26b..5bf41c4895 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -32,8 +32,10 @@ interface Slot { * Schedule one assistant step's tool calls by their live concurrency mode. * Started calls receive ordered results. Abort drains them and rethrows after * accepting their context into the batch FIFO owned by the caller. + * The committed step's AgentLoop driver boundary supplies the initiating Agent + * that becomes each explicit {@link ToolExecutionInput.agent}. * - * @param ctx - loop context that owns the tool registry. + * @param ctx - loop context that owns the tool registry and carries the initiating Agent. * @param turn - current turn number. * @param step - current step number. * @param toolCalls - assistant calls in model order. From e5721393969d581e3d7596544e99f94f4ee11798 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:23:59 +0800 Subject: [PATCH 239/323] docs: shorten public API fence marker --- docs/AGENTS.md | 2 +- docs/core-data-structures/llm-streaming.md | 4 +-- docs/core-data-structures/session.md | 2 +- docs/development.i18n.yaml | 4 +-- docs/development.md | 2 +- docs/development.zh.md | 2 +- ...2026-06-20-core-data-structures-catalog.md | 2 +- scripts/doc-typecheck.ts | 4 +-- scripts/type-equiv.manifest.json | 2 +- scripts/verify-type-equiv.ts | 27 ++++++++++--------- 10 files changed, 27 insertions(+), 24 deletions(-) diff --git a/docs/AGENTS.md b/docs/AGENTS.md index 27db1d88d7..f7635c659b 100644 --- a/docs/AGENTS.md +++ b/docs/AGENTS.md @@ -27,7 +27,7 @@ Placement: bugs → postmortems; rationale → RFCs; procedures → cookbooks; t - **Document current state, not change history.** Avoid "previously/now/no longer", PRs, commits, and stack positions in durable prose; name the live mechanism. Put change stories in commits, PRs, RFCs, or postmortems. - **Write an RFC in the same PR for decisions a maintainer may reasonably revisit.** Mechanical or self-evident changes need none ([when to write one](rfc/README.md)). - **One physical line per paragraph** (`verify-md-wrap`): use editor soft-wrap. Code blocks, tables, and list structure keep their formatting; code comments stay under the linter's column limit. -- **Fenced `ts` blocks must compile** (`doc-typecheck`); a pasted type declaration and its original JSDoc use ` ```ts type-equiv `, while a body-stripped public class declaration uses its `public-api` variant; register either in the manifest so neither can drift ([mechanics](development.md#documenting-types-verbatim-ts-type-equiv)). +- **Fenced `ts` blocks must compile** (`doc-typecheck`); a pasted type declaration and its original JSDoc use ` ```ts type-equiv `, while a body-stripped public class declaration uses ` ```ts public-api `; register either in the manifest so neither can drift ([mechanics](development.md#documenting-types-verbatim-ts-type-equiv)). - **The [core-data-structures catalog](core-data-structures/core.md) updates in the same change** that reshapes a documented type. `verify-type-equiv` catches drifted pastes, not never-documented new types ([what counts as core](core-data-structures/core.md#what-counts-as-core)). - **Bilingual pairs update together**: editing either side obligates the counterpart and a re-record in the same change ([i18n contract](i18n/README.md)). - **Comments and JSDoc state complete contracts, not reasoning transcripts.** Preserve behavior, conditions, timing, modality, exceptions, consequences, and non-obvious orientation; delete implementation narration, test walkthroughs, review analysis, and code restatement. Keep the local contract and link to its owning rationale. Use [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for required coverage, decision rules, and examples. diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index b27c21a69c..ce8c1bf074 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -91,7 +91,7 @@ interface TokenUsage { `BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s, usage, finish reason, and replay state. The loop logs the raw chunks while feeding the same chunks through an assembler, then stores the assembled assistant content with its provider/model provenance. A consumer that needs the assembled result without re-implementing the fold uses this. -```ts type-equiv public-api +```ts public-api /** * Incrementally assembles raw {@link StreamChunk}s into complete * {@link ContentBlock}s and a final assistant {@link Message}. @@ -133,7 +133,7 @@ declare class BlockAssembler { `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerInfo()` and asynchronous `listModels()` methods feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). -```ts type-equiv public-api +```ts public-api /** * Provider-wire adapter for the harness message and stream vocabulary. Register implementations * with `ctx.llm.registerAdapter(providers, adapter)`. Every provider HTTP request must include diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 1ece65c1c3..3668191fb2 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -309,7 +309,7 @@ interface SurfaceFoldResult { The body-stripped declaration keeps the plain class's public constructor, state accessors, append boundary, and history projections synchronized with source. Store operations remain in the generated [`ctx.sessions` service catalog](../cordis-catalog/services.md#ctxsessions--sessionstore). -```ts type-equiv public-api +```ts public-api /** * An event-sourced session: an append-only log of {@link SessionEvent}s. * diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index b0ce75ca4c..d7f82d7e92 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -development.md: 6938e922c7937f0e6ef6c6e611752827e6a06f82 -development.zh.md: dfb302f23a3f09ea97684b75fcfa7c7dc2e9ade5 +development.md: a3268164cd06fb8bf66f52391bc42c2dc3ca9396 +development.zh.md: f8f29c64aa6e49e3ed6d7ef12df2a4911c9182b0 diff --git a/docs/development.md b/docs/development.md index 6938e922c7..a3268164cd 100644 --- a/docs/development.md +++ b/docs/development.md @@ -151,7 +151,7 @@ The [core data structures](core-data-structures/core.md) docs paste source-equiv { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" } ``` -`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration and attached JSDoc from source via the TypeScript parser and asserts the block matches both. For a class whose implementation bodies do not belong in the catalog, use ` ```ts type-equiv public-api ` and set `"projection": "public-api"`; the checked projection retains the public fields, constructor, accessors, methods, and original class/member JSDoc while omitting bodies and private or protected members. Comparison ignores whitespace and non-JSDoc comments but requires every original JSDoc comment, including member documentation, so readers see the source contract beside the exact shape. The gate also enforces a 1:1 correspondence by document, symbol, and projection, so a block can't go silently unchecked and a stale entry can't linger. `doc-typecheck` skips both variants (they aren't standalone-compilable) and excludes them from its opt-out ratio. When you change a documented declaration or its JSDoc, the gate fails until you update the paste; when you add or remove a block, update the manifest in the same change. +`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration and attached JSDoc from source via the TypeScript parser and asserts the block matches both. For a class whose implementation bodies do not belong in the catalog, use ` ```ts public-api ` and set `"projection": "public-api"`; the checked projection retains the public fields, constructor, accessors, methods, and original class/member JSDoc while omitting bodies and private or protected members. Comparison ignores whitespace and non-JSDoc comments but requires every original JSDoc comment, including member documentation, so readers see the source contract beside the exact shape. The gate also enforces a 1:1 correspondence by document, symbol, and projection, so a block can't go silently unchecked and a stale entry can't linger. `doc-typecheck` skips both fence kinds (they aren't standalone-compilable) and excludes them from its opt-out ratio. When you change a documented declaration or its JSDoc, the gate fails until you update the paste; when you add or remove a block, update the manifest in the same change. ## Architecture context diff --git a/docs/development.zh.md b/docs/development.zh.md index dfb302f23a..f8f29c64aa 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -151,7 +151,7 @@ pnpm run demo:acp { "doc": "docs/core-data-structures/session.md", "symbol": "SessionEvent", "source": "packages/core/session/src/types.ts" } ``` -`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明及其附带的 JSDoc，并断言代码块同时匹配两者。对于不应把实现体写进目录的类，请使用 ` ```ts type-equiv public-api ` 并设置 `"projection": "public-api"`；门禁检查的投影会保留公共字段、构造函数、访问器、方法以及类和成员的原始 JSDoc，同时省略实现体和私有或受保护成员。比对会忽略空白和非 JSDoc 注释，但要求保留每条原始 JSDoc（包括成员文档），让读者同时看到源码契约和确切形状。该门禁还按文档、符号和投影强制 1:1 对应，因此不会有块被静默漏检，也不会有陈旧条目滞留。`doc-typecheck` 跳过两种变体（它们不能独立编译），并将其排除在 opt-out 比例之外。当你改动一个已记录的类型声明或其 JSDoc 时，门禁会失败直到你更新粘贴内容；当你增删一个块时，请在同一个变更里更新 manifest。 +`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明及其附带的 JSDoc，并断言代码块同时匹配两者。对于不应把实现体写进目录的类，请使用 ` ```ts public-api ` 并设置 `"projection": "public-api"`；门禁检查的投影会保留公共字段、构造函数、访问器、方法以及类和成员的原始 JSDoc，同时省略实现体和私有或受保护成员。比对会忽略空白和非 JSDoc 注释，但要求保留每条原始 JSDoc（包括成员文档），让读者同时看到源码契约和确切形状。该门禁还按文档、符号和投影强制 1:1 对应，因此不会有块被静默漏检，也不会有陈旧条目滞留。`doc-typecheck` 跳过两种围栏（它们不能独立编译），并将其排除在 opt-out 比例之外。当你改动一个已记录的类型声明或其 JSDoc 时，门禁会失败直到你更新粘贴内容；当你增删一个块时，请在同一个变更里更新 manifest。 ## 架构上下文 diff --git a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md b/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md index 974a19a621..47dc370d22 100644 --- a/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md +++ b/docs/rfc/implemented/process/2026-06-20-core-data-structures-catalog.md @@ -29,7 +29,7 @@ The rule that settled the remaining cases: ***the type you write, hold, or recei The durability requirement was specific: the doc shows the **literal** current type declaration and original JSDoc (so a reader sees the real shape and source contract, not a paraphrase) **and** is mechanically guaranteed to match source. The repo already compiles fenced ` ```ts ` blocks (`doc-typecheck`), but a real typechecked block needs import noise and proves only *assignability* — a renamed field or changed JSDoc can pass. So: -- Complete type declarations and their JSDoc are pasted verbatim into a dedicated ` ```ts type-equiv ` fence. A `public-api` variant carries the source-equivalent ambient projection for a class whose implementation bodies do not belong in the catalog. `doc-typecheck` recognizes both and skips them (the bare declarations are not standalone-compilable), and **excludes them from the opt-out ratio** — they are a separately-checked category, not unchecked sketches. +- Complete type declarations and their JSDoc are pasted verbatim into a dedicated ` ```ts type-equiv ` fence. A concise ` ```ts public-api ` fence carries the source-equivalent ambient projection for a class whose implementation bodies do not belong in the catalog. `doc-typecheck` recognizes both and skips them (the bare declarations are not standalone-compilable), and **excludes them from the opt-out ratio** — they are a separately-checked category, not unchecked sketches. - A new `scripts/verify-type-equiv.ts` extracts each block via the TypeScript parser and asserts that its declaration structure and every JSDoc comment match the declared symbol, ignoring only formatting whitespace and non-JSDoc comments. Ordinary blocks retain the complete declaration. A `public-api` projection retains a class's public fields, constructor, accessors, and methods with their original JSDoc while removing implementation bodies and private or protected members. This is chosen over a compiled `_Check` assertion because source names and documentation identity, not assignability, are the properties the catalog preserves. - Provenance lives in a central `scripts/type-equiv.manifest.json` (`{ doc, symbol, source }` entries), **not** in directive comments in the prose. The script enforces a **1:1 correspondence**: every type-equiv block has exactly one manifest entry and vice versa, so a block can never be silently unchecked and an entry can never rot. - Wired into `doc-sync`, so it runs in the same lefthook pre-push and CI paths as the other doc gates. diff --git a/scripts/doc-typecheck.ts b/scripts/doc-typecheck.ts index c4d6c04a35..34af82b48b 100644 --- a/scripts/doc-typecheck.ts +++ b/scripts/doc-typecheck.ts @@ -1,6 +1,6 @@ /** * Typecheck Markdown `ts` fences against the workspace API. `ignore-check` fences are reported as - * opt-outs; generated catalog fragments and `type-equiv` blocks are skipped here because their + * opt-outs; generated catalog fragments and source-equivalence blocks are skipped here because their * owning gates verify them. A build-coordinated mode consumes existing declarations without emit. */ @@ -33,7 +33,7 @@ const KIND_BY_INFO: Record = { 'ts': 'check', 'ts ignore-check': 'ignore', 'ts type-equiv': 'type-equiv', - 'ts type-equiv public-api': 'type-equiv', + 'ts public-api': 'type-equiv', 'ts cordis-catalog': 'cordis-catalog', 'ts persistence-catalog': 'persistence-catalog', 'ts config-catalog': 'config-catalog', diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 09888916d0..831c45e610 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -1,5 +1,5 @@ { - "comment": "Maps each ` ```ts type-equiv ` block (by doc + declared symbol + projection) to the source declaration and original JSDoc it must match. Omit projection for the complete declaration; use public-api with a ` ```ts type-equiv public-api ` block for a body-stripped public class declaration. verify-type-equiv.ts enforces a 1:1 correspondence: every type-equiv block has exactly one entry here, and every entry resolves to exactly one block. Add an entry when you add a type-equiv block; remove it when you remove the block.", + "comment": "Maps each ` ```ts type-equiv ` or ` ```ts public-api ` block (by doc + declared symbol + projection) to the source declaration and original JSDoc it must match. Omit projection for the complete declaration; use public-api with a ` ```ts public-api ` block for a body-stripped public class declaration. verify-type-equiv.ts enforces a 1:1 correspondence: every source-equivalence block has exactly one entry here, and every entry resolves to exactly one block. Add an entry when you add a source-equivalence block; remove it when you remove the block.", "entries": [ { "doc": "docs/core-data-structures/core.md", "symbol": "Branded", "source": "packages/util/brand/src/index.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, diff --git a/scripts/verify-type-equiv.ts b/scripts/verify-type-equiv.ts index 58affaffca..d703536f17 100644 --- a/scripts/verify-type-equiv.ts +++ b/scripts/verify-type-equiv.ts @@ -1,10 +1,10 @@ /** - * Verify every `ts type-equiv` block against the source symbol named by the - * manifest. Ordinary entries preserve the complete declaration; `public-api` - * entries preserve a class's body-stripped public declaration. Blocks and - * entries have a one-to-one relationship; comparison ignores whitespace and - * non-JSDoc comments but preserves declaration structure and every original - * JSDoc comment. + * Verify every `ts type-equiv` and `ts public-api` block against the source + * symbol named by the manifest. Ordinary entries preserve the complete + * declaration; `public-api` entries preserve a class's body-stripped public + * declaration. Blocks and entries have a one-to-one relationship; comparison + * ignores whitespace and non-JSDoc comments but preserves declaration + * structure and every original JSDoc comment. */ import { globSync, readFileSync, existsSync } from 'node:fs' @@ -16,9 +16,9 @@ const root = resolve(import.meta.dirname, '..') /** Scan doc-typecheck's full Markdown scope so unmanifested blocks also fail. */ const MARKDOWN_GLOBS = ['README.md', 'docs/**/*.md', 'packages/*/*.md', 'packages/*/*/*.md', 'website/zh-CN/**/*.md'] -/** One manifest entry: a documented type-equiv block and its source symbol. */ +/** One manifest entry: a source-equivalence block and its source symbol. */ interface ManifestEntry { - /** Doc file (repo-relative) containing the ` ```ts type-equiv ` block. */ + /** Doc file (repo-relative) containing the source-equivalence block. */ doc: string /** The declared symbol the block must match (e.g. `SessionEvent`). */ symbol: string @@ -28,7 +28,7 @@ interface ManifestEntry { projection?: 'public-api' } -/** One extracted ` ```ts type-equiv ` block. */ +/** One extracted ` ```ts type-equiv ` or ` ```ts public-api ` block. */ interface EquivBlock { doc: string /** 1-based line of the opening fence (for diagnostics). */ @@ -64,7 +64,7 @@ function stripExport(code: string): string { return code.replace(/^export\s+(default\s+)?/, '') } -/** Parse the declared symbol name from a type-equiv block body. */ +/** Parse the declared symbol name from a source-equivalence block body. */ function blockSymbol(code: string): string | null { const sf = ts.createSourceFile('type-equiv.ts', code, ts.ScriptTarget.Latest, /* setParentNodes */ false, ts.ScriptKind.TS) for (const stmt of sf.statements) { @@ -76,7 +76,7 @@ function blockSymbol(code: string): string | null { return null } -/** Extract every ` ```ts type-equiv ` block from one Markdown file. */ +/** Extract every source-equivalence block from one Markdown file. */ function extractEquivBlocks(docRel: string): EquivBlock[] { const text = readFileSync(resolve(root, docRel), 'utf8') const lines = text.split('\n') @@ -107,8 +107,11 @@ function extractEquivBlocks(docRel: string): EquivBlock[] { continue } const info = (fence[2] ?? '').trim() + if (info === 'ts type-equiv public-api') { + throw new Error(`verify-type-equiv: ${docRel}:${i + 1} — use the concise \`ts public-api\` fence`) + } if (info === 'ts type-equiv') open = { line: i + 1, body: [] } - if (info === 'ts type-equiv public-api') open = { line: i + 1, body: [], projection: 'public-api' } + if (info === 'ts public-api') open = { line: i + 1, body: [], projection: 'public-api' } } if (open) throw new Error(`verify-type-equiv: ${docRel}:${open.line} — unterminated type-equiv block`) return blocks From ae419fb692322bdb48facc1394807ad25e8b1e3c Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:27:10 +0800 Subject: [PATCH 240/323] fix(cli-demo): interrupt Loader boot on signals Race Loader startup with the process abort signal so SIGINT and SIGTERM can settle the one-shot CLI even when initialization has not returned a Context. If boot settles after cancellation, dispose the late context asynchronously instead of recreating the wait. Contain late boot rejection and report a late disposal failure on stderr. Cover prompt interruption, late context disposal, late boot rejection, and cleanup failure with focused CLI regressions. --- packages/examples/cli-demo/src/cli.ts | 55 +++++++++++++- packages/examples/cli-demo/tests/cli.spec.ts | 77 ++++++++++++++++++++ 2 files changed, 130 insertions(+), 2 deletions(-) diff --git a/packages/examples/cli-demo/src/cli.ts b/packages/examples/cli-demo/src/cli.ts index 1f19e3ddf5..63c08ae39f 100644 --- a/packages/examples/cli-demo/src/cli.ts +++ b/packages/examples/cli-demo/src/cli.ts @@ -294,6 +294,53 @@ function renderResult(outputFormat: OutputFormat, result: CliResult): string { return outputFormat === 'text' ? `${result.result}\n` : `${JSON.stringify(result)}\n` } +/** + * Race Loader boot with cancellation without abandoning a context that becomes + * available after the caller has been released. Waiting for that late context + * would recreate the signal hang, so its disposal and diagnostics run detached. + */ +async function bootInterruptibly( + start: () => Promise, + signal: AbortSignal | undefined, + disposeLateContext: (ctx: Context) => Promise, + reportLateDisposalFailure: (error: unknown) => void, +): Promise { + if (signal === undefined) return await start() + if (signal.aborted) throw new CliInterruptedError(interruptionReason(signal)) + + let onAbort!: () => void + const interruptedBoot = new Promise((_resolve, reject) => { + onAbort = (): void => { + reject(new CliInterruptedError(interruptionReason(signal))) + } + signal.addEventListener('abort', onAbort, { once: true }) + /* v8 ignore next -- closes registration against a non-standard synchronously mutating signal */ + if (signal.aborted) onAbort() + }) + const booting = Promise.resolve().then(start) + try { + return await Promise.race([booting, interruptedBoot]) + } catch (error: unknown) { + // The awaited race permits the signal to change after the preflight check. + // eslint-disable-next-line @typescript-eslint/no-unnecessary-condition + if (signal.aborted) { + void booting.then( + async (lateContext) => { + try { + await disposeLateContext(lateContext) + } catch (error: unknown) { + reportLateDisposalFailure(error) + } + }, + () => {}, + ) + } + throw error + } finally { + signal.removeEventListener('abort', onAbort) + } +} + /** * Render a non-completed turn reason for stderr. * @param reason - durable turn ending to describe. @@ -349,8 +396,12 @@ export async function executeCli(args: readonly string[], runtime: CliRuntime = let diagnostic: string | undefined try { loadEnvironment(CLI_NAME, cwd, line => writeStderr(line)) - ctx = await bootContext(CLI_NAME, resolveConfigPath(command.configPath, undefined, cwd)) - if (runtime.signal?.aborted === true) throw new CliInterruptedError(interruptionReason(runtime.signal)) + ctx = await bootInterruptibly( + () => bootContext(CLI_NAME, resolveConfigPath(command.configPath, undefined, cwd)), + runtime.signal, + disposeContext, + error => writeStderr(`${CLI_NAME}: dispose after interrupted boot failed: ${toError(error).message}\n`), + ) const result = await runOneShot(ctx, { task: command.task, ...runtime.signal === undefined ? {} : { signal: runtime.signal }, diff --git a/packages/examples/cli-demo/tests/cli.spec.ts b/packages/examples/cli-demo/tests/cli.spec.ts index 4daaea7e03..fcdf8a3004 100644 --- a/packages/examples/cli-demo/tests/cli.spec.ts +++ b/packages/examples/cli-demo/tests/cli.spec.ts @@ -199,6 +199,83 @@ describe('runOneShot and executeCli', () => { expect(stderr).toContain('boot exploded') }) + it('interrupts Loader boot and contains every late boot outcome', async () => { + const abort = new AbortController() + const lateContext = new Context() + liveContexts.push(lateContext) + const boot = Promise.withResolvers() + const disposed = Promise.withResolvers() + let disposeCalls = 0 + let stderr = '' + const running = executeCli(['task'], { + signal: abort.signal, + boot: () => boot.promise, + loadEnv: () => {}, + writeStdout: () => {}, + writeStderr: (chunk) => { stderr += chunk }, + dispose: async (ctx) => { + disposeCalls += 1 + await ctx.fiber.dispose() + disposed.resolve(undefined) + }, + }) + abort.abort('received SIGTERM') + await expect(running).resolves.toBe(1) + expect(stderr).toContain('received SIGTERM') + expect(disposeCalls).toBe(0) + boot.resolve(lateContext) + await disposed.promise + expect(disposeCalls).toBe(1) + + const rejectedBoot = Promise.withResolvers() + const rejectedAbort = new AbortController() + const rejected = executeCli(['task'], { + signal: rejectedAbort.signal, + boot: () => rejectedBoot.promise, + loadEnv: () => {}, + writeStdout: () => {}, + writeStderr: () => {}, + }) + rejectedAbort.abort('stop rejected boot') + await expect(rejected).resolves.toBe(1) + rejectedBoot.reject(new Error('late boot rejection')) + await Promise.resolve() + + let ordinaryBootStderr = '' + const ordinaryBootFailure = await executeCli(['task'], { + signal: new AbortController().signal, + boot: async () => { throw new Error('ordinary boot failure') }, + loadEnv: () => {}, + writeStdout: () => {}, + writeStderr: (chunk) => { ordinaryBootStderr += chunk }, + }) + expect(ordinaryBootFailure).toBe(1) + expect(ordinaryBootStderr).toContain('ordinary boot failure') + + const failedCleanupBoot = Promise.withResolvers() + const failedCleanupAbort = new AbortController() + const cleanupFailure = Promise.withResolvers() + const failedCleanupContext = new Context() + liveContexts.push(failedCleanupContext) + const failedCleanup = executeCli(['task'], { + signal: failedCleanupAbort.signal, + boot: () => failedCleanupBoot.promise, + loadEnv: () => {}, + writeStdout: () => {}, + writeStderr: (chunk) => { + if (chunk.includes('dispose after interrupted boot failed: late cleanup')) cleanupFailure.resolve(undefined) + }, + dispose: async (ctx) => { + await ctx.fiber.dispose() + throw new Error('late cleanup') + }, + }) + failedCleanupAbort.abort('stop failed cleanup boot') + await expect(failedCleanup).resolves.toBe(1) + failedCleanupBoot.resolve(failedCleanupContext) + await cleanupFailure.promise + }) + it('renders text, flushes a persisted fresh session, and disposes the context', async () => { const { ctx, agent, persistenceRoot } = await harness([textResponse('final answer')]) const output = await invoke(ctx, ['task']) From 62fc876318dd6b06b1e70e6a769a2194b13747be Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:39:49 +0800 Subject: [PATCH 241/323] feat: inspect exact Cordis API JSDoc --- ...6-07-08-self-referential-cordis-toolset.md | 8 +- docs/tool-catalog.md | 6 +- .../system-prompt.golden.md | 4 +- .../tool-schemas.golden.json | 6 +- packages/cordis/tool-cordis/README.md | 6 +- .../cordis/tool-cordis/src/api-catalog.ts | 535 ++++++++++++++---- packages/cordis/tool-cordis/src/index.ts | 18 +- packages/cordis/tool-cordis/src/inspect.ts | 71 ++- packages/cordis/tool-cordis/src/present.ts | 5 +- .../cordis/tool-cordis/tests/inspect.spec.ts | 57 +- .../cordis/tool-cordis/tests/present.spec.ts | 8 + .../tool-cordis/tests/tool-cordis.spec.ts | 3 +- scripts/gen-cordis-api.ts | 35 +- 13 files changed, 616 insertions(+), 146 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md b/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md index 4d592af42b..94d11ee931 100644 --- a/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md +++ b/docs/rfc/implemented/feature/2026-07-08-self-referential-cordis-toolset.md @@ -18,11 +18,11 @@ The vm isolates accidental global pollution, and the context façade hides frame | Tool | Contract | |---|---| -| `cordis_inspect` | Read-only report over the live runtime, one Markdown section per `what` value (omit `what` for all sections). Never mutates. | +| `cordis_inspect` | Read-only report over the live runtime, one Markdown section per `what` value (omit `what` for all sections). An exact `name` with `what: "api"` or `what: "events"` narrows to one source-documented target. Never mutates. | | `cordis_mount` | Evaluates `code` (the body of an async JavaScript function) in a `node:vm` sandbox; the code must `return` a cordis plugin, which is mounted as a child of the `cordis-dynamic` group fiber and tracked under a fresh id (`dyn-1`, `dyn-2`, …). | | `cordis_unmount` | Disposes one dynamic mount by id and returns only after disposal reaches quiescence — every registration the plugin made is unwound, not merely requested to stop. | -`cordis_inspect` sections: `services` (every provided ctx service and the owning fiber, non-active owners flagged), `plugins` (a flat list of every loaded plugin with its lifecycle state, from `ctx.registry` — what capabilities are loaded, deliberately not the tree shape), `tools` (what the model can call), `dynamic` (the mount table: id, name, state, provided services, awaited services), `api` (live service signatures + the type shapes they reference, from the generated catalog), and `events` (harness events with dispatch mode and signature). The model-facing tool descriptions carry the operational rules the model needs at call time; [the generated tool catalog](../../../tool-catalog.md) is their exhaustive rendering. +`cordis_inspect` sections: `services` (every provided ctx service and the owning fiber, non-active owners flagged), `plugins` (a flat list of every loaded plugin with its lifecycle state, from `ctx.registry` — what capabilities are loaded, deliberately not the tree shape), `tools` (what the model can call), `dynamic` (the mount table: id, name, state, provided services, awaited services), `api` (live service signatures + the type shapes they reference, from the generated catalog), and `events` (harness events with dispatch mode and signature). Broad `api` and `events` reports omit full JSDoc to stay compact; an exact `name` returns one service or event with its original method/declaration JSDoc. A name is invalid with other sections, unknown targets fail, and an API target must be live. The model-facing tool descriptions carry the operational rules the model needs at call time; [the generated tool catalog](../../../tool-catalog.md) is their exhaustive rendering. ### Sandbox semantics @@ -44,9 +44,9 @@ Mounts relate to each other through ordinary cordis service semantics, with thei ### The generated API catalog -`cordis_inspect` serves API and event data from a generated catalog rather than a duplicated table. The generator reuses the Cordis catalog AST scan and emits service summaries, signatures, event modes, referenced type declarations, and the inherited context surface. Ambiguous type names are omitted and oversized declarations are marked as truncated. +`cordis_inspect` serves API and event data from a generated catalog rather than a duplicated table. The generator reuses the Cordis catalog AST scan and emits service summaries, signatures, original service-method and event JSDoc, event modes, referenced type declarations, and the inherited context surface. Ambiguous type names are omitted and oversized declarations are marked as truncated. -Freshness is gated like every generated artifact: `pnpm run verify-cordis-api` (in `doc-sync`) regenerates in memory and fails on any diff, so a JSDoc edit that changes a public signature cannot ship without regenerating the catalog the model reads. At runtime the inspect tool intersects the catalog with the live runtime rather than dumping it: live catalogued services render summary + signatures, live services without a catalog entry (mount-provided ones) render name + owning fiber, catalogued services with no live provider are listed tersely, and the referenced type shapes follow. +Freshness is gated like every generated artifact: `pnpm run verify-cordis-api` (in `doc-sync`) regenerates in memory and fails on any diff, so a JSDoc or public-signature edit cannot ship without regenerating the catalog the model reads. At runtime the inspect tool intersects the catalog with the live runtime rather than dumping it: broad reports render live catalogued services as summary + signatures, live services without a catalog entry (mount-provided ones) as name + owning fiber, catalogued services with no live provider tersely, and then the referenced type shapes. Exact-name reports render one live service or event with the original JSDoc immediately before each signature; keeping that detail opt-in avoids charging its token cost on exploratory listings. ### Configuration, rendering, and observability diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 3dacb56902..dfb97deef3 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -169,7 +169,7 @@ The bash tool is the model-facing consumer of the bash executor seam. A `run_in_ ### `cordis_inspect` -Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. +Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:"api"` or `what:"events"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. ```json { @@ -186,6 +186,10 @@ Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: "api", "events" ] + }, + "name": { + "type": "string", + "description": "Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"." } } } diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index fb5b48c70c..b8acef973c 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -44,10 +44,12 @@ declare const tools: { /** Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access. */ justification?: string; }): Promise; - /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. */ + /** Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:"api"` or `what:"events"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc. */ cordis_inspect(args: { /** Limit the report to one section. Omit for all sections. */ what?: "services" | "plugins" | "tools" | "dynamic" | "api" | "events"; + /** Exact service key or event name whose original JSDoc to include; valid only with what:"api" or what:"events". */ + name?: string; }): Promise; /** Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:"api" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:"events"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:"api" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime. */ cordis_mount(args: { diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json index 57e78b6345..978819fa1f 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/tool-schemas.golden.json @@ -47,7 +47,7 @@ }, { "name": "cordis_inspect", - "description": "Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.", + "description": "Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections. With `what:\"api\"` or `what:\"events\"`, pass an exact `name` to narrow to one service/event and include its original source JSDoc.", "parameters": { "type": "object", "properties": { @@ -62,6 +62,10 @@ "api", "events" ] + }, + "name": { + "type": "string", + "description": "Exact service key or event name whose original JSDoc to include; valid only with what:\"api\" or what:\"events\"." } } } diff --git a/packages/cordis/tool-cordis/README.md b/packages/cordis/tool-cordis/README.md index fdc4e51e6b..c43e2fcc4d 100644 --- a/packages/cordis/tool-cordis/README.md +++ b/packages/cordis/tool-cordis/README.md @@ -4,7 +4,7 @@ The self-referential cordis toolset: three model-facing tools over the live runt ## What it does -- `cordis_inspect` — read-only report over the runtime: services, the loaded-plugin list, registered tools, the dynamic-mount table, and the catalog-backed `api` / `events` references. +- `cordis_inspect` — read-only report over the runtime: services, the loaded-plugin list, registered tools, the dynamic-mount table, and the catalog-backed `api` / `events` references. An exact `name` with `what: "api"` or `what: "events"` narrows the report and adds the original source JSDoc. - `cordis_mount` — evaluates model-written JavaScript (the body of an async function) in a `node:vm` sandbox; the code must `return` a cordis plugin, which is mounted under the `cordis-dynamic` group fiber and tracked as `dyn-`. - `cordis_unmount` — disposes one mount by id, returning only after quiescence. @@ -22,7 +22,7 @@ The sandbox isolates globals but is not a security boundary. Node globals are ab ## The generated API catalog -`src/api-catalog.ts` is generated by `scripts/gen-cordis-api.ts` from the same AST walk as [docs/cordis-catalog](../../../docs/cordis-catalog/services.md) and freshness-gated by `pnpm run verify-cordis-api` (in `doc-sync`) — never edit it by hand. `cordis_inspect` intersects it with the live service store at call time. +`src/api-catalog.ts` is generated by `scripts/gen-cordis-api.ts` from the same AST walk as [docs/cordis-catalog](../../../docs/cordis-catalog/services.md) and freshness-gated by `pnpm run verify-cordis-api` (in `doc-sync`) — never edit it by hand. `cordis_inspect` intersects it with the live service store at call time. Broad `api` / `events` reports render summaries and signatures only; an exact `name` opts into the retained method/event JSDoc, and unknown or non-running service targets fail loud. ## Rendering @@ -42,7 +42,7 @@ Namespace plugin: named exports `name` / `inject` / `Config` / `apply`, no defau ### Tool-call history and results -**What the model sees**: Inspect joins selected sections exactly as `##

` then a newline and the data-dependent body, with one blank line between sections. Mount returns `mounted (plugin "", state: )`, optionally inserting ` — waiting for service(s): (activates when provided)` before the closing parenthesis. Unmount returns `unmounted (plugin "")`; an unknown id becomes `Error: no dynamic plugin with id "" (list mounts with cordis_inspect what:"dynamic")`. The submitted mount program remains in the assistant tool-call history. +**What the model sees**: Inspect joins selected sections exactly as `##
` then a newline and the data-dependent body, with one blank line between sections. Its broad API/event reports omit JSDoc; `name` with `what: "api"` or `what: "events"` returns one exact target with its original JSDoc. Mount returns `mounted (plugin "", state: )`, optionally inserting ` — waiting for service(s): (activates when provided)` before the closing parenthesis. Unmount returns `unmounted (plugin "")`; an unknown id becomes `Error: no dynamic plugin with id "" (list mounts with cordis_inspect what:"dynamic")`. The submitted mount program remains in the assistant tool-call history. **Token effect**: Inspect output and mount code are data-dependent and resent until compaction; lifecycle acknowledgements are small. diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 7a02519b02..b274e357bf 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -4,22 +4,30 @@ * `pnpm run verify-cordis-api` in doc-sync). * * The machine-readable cordis API catalog `cordis_inspect` serves to the - * model: harness services (summary + public method signatures), harness - * events (mode + signature), and the inherited `ctx` surface. Produced by + * model: harness services (summary + public method signatures/JSDoc), + * harness events (mode + signature/JSDoc), and the inherited `ctx` surface. Produced by * the same AST walk as docs/cordis-catalog, so this data and the rendered * docs cannot diverge. * * @module @deepseek-ai/dsh-tool-cordis/api-catalog */ -/** One harness `ctx.` service: its one-line summary and public method signatures. */ +/** One public service method and its source-owned contract. */ +export interface ServiceApiMethod { + /** Public method signature with its body stripped. */ + signature: string + /** Original method JSDoc, with only container indentation removed. */ + jsDoc: string +} + +/** One harness `ctx.` service: its one-line summary and public methods. */ export interface ServiceApiEntry { /** The `ctx.` name, e.g. `tools`. */ key: string /** First sentence of the service class JSDoc. */ summary: string - /** Public method signatures, bodies stripped, in source order. */ - methods: readonly string[] + /** Public methods, bodies stripped, in source order. */ + methods: readonly ServiceApiMethod[] } /** One harness event: its dispatch mode, exact signature, and one-line summary. */ @@ -30,6 +38,8 @@ export interface EventApiEntry { mode: string /** The exact listener signature, whitespace-normalized. */ signature: string + /** Original event JSDoc, with only container indentation removed. */ + jsDoc: string /** First sentence of the event JSDoc. */ summary: string } @@ -56,239 +66,524 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'agentLoop', summary: 'Concrete agent factory and driver service.', methods: [ - 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent', - 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', - 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', + { + signature: 'create(id: SessionId, options: AgentOptions = {}, meta: Pick = {}): Agent', + jsDoc: '/**\n * Create an agent and session under one caller-supplied identity, owned by\n * the accessing fiber. Constructor-driven config calls mint a fresh combined\n * id before entering this boundary.\n * @param id - shared agent/session identity.\n * @param options - concrete loop options.\n * @param meta - optional fresh-session workspace metadata.\n * @returns the published running agent.\n */', + }, + { + signature: 'async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise', + jsDoc: '/**\n * Create an owned agent on a caller-supplied session id.\n * @param ownerCtx - caller context that structurally owns the transaction.\n * @param options - identities, session seed/metadata, loop options, setup, and cancellation.\n * @returns the published handle.\n */', + }, + { + signature: 'async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise', + jsDoc: '/**\n * Resume an owned agent from the configured persistence service.\n * @param ownerCtx - caller context that owns load, setup, and the live lifecycle.\n * @param options - persisted identity, loop options, setup, and cancellation.\n * @returns the published handle.\n */', + }, ], }, { key: 'agents', summary: 'Agent registry (`ctx.agents`): tracks live agents so UI, hook, and orchestrator plugins can find them without depending on the concrete loop package.', methods: [ - 'setFactory(factory: AgentFactory): () => void', - 'async create(options: CreateAgentOptions): Promise', - 'async resume(options: ResumeAgentOptions): Promise', - 'register(agent: Agent): () => void', - 'enter(agent: Agent, owner: Agent | undefined): () => void', - 'announce(agent: Agent): void', - 'get(id: SessionId): Agent | undefined', - 'isOwnedBy(id: SessionId, owner: Agent): boolean', - 'list(): Agent[]', - 'roots(): Agent[]', + { + signature: 'setFactory(factory: AgentFactory): () => void', + jsDoc: '/**\n * Register the agent-creation factory (the loop calls this on construction,\n * effect-scoped). A traced Cordis service is canonicalized to its concrete\n * target; each create/resume call is then traced through that caller\'s\n * context so ownership follows the caller without stacking proxy layers.\n * Throws if a factory is already registered. Returns the disposer; on\n * dispose the factory slot is cleared.\n * @param factory - the loop-owned factory {@link create}/{@link resume} delegate to.\n * @returns the disposer that clears the factory slot. The exact\n * Cordis effect disposer (single-shot): composite (generator) effects may\n * yield it directly — exact identity nests the teardown in order.\n */', + }, + { + signature: 'async create(options: CreateAgentOptions): Promise', + jsDoc: '/**\n * Create and publish a new agent through the registered factory.\n * Distinct from {@link register} (which records an already-constructed\n * agent): this constructs the agent and its session. Rejects if no factory is\n * registered or creation/setup fails. The resolved {@link AgentHandle} lets\n * the owner tear down exactly this agent.\n * @param options - shared identity, session seed/metadata, and agent options.\n * @returns the handle after setup, rollback-covered publication, and loop start complete.\n */', + }, + { + signature: 'async resume(options: ResumeAgentOptions): Promise', + jsDoc: '/**\n * Load a persisted session and resume an agent on it through the registered\n * factory. Rejects if no factory is registered; the factory rejects if\n * session persistence is not configured or persistence/setup fails.\n * @param options - persisted identity, configuration, and optional setup.\n * @returns the handle after setup, rollback-covered publication, and loop start complete.\n */', + }, + { + signature: 'register(agent: Agent): () => void', + jsDoc: '/**\n * Register a live agent. Throws if an agent with the same id is already\n * registered. Emits `agent/created` on registration and `agent/disposed`\n * when the calling fiber is disposed — both with the agent\'s scope carrier\n * (`scopeTarget(agent, agent)`): the subject is the agent in hand, so the\n * emits are scope-filtered regardless of which context invoked `register`\n * (calling through `agent.ctx` scopes EFFECTS; dispatch scoping always\n * requires passing the carrier). Returns the disposer.\n * @param agent - the already-constructed agent to record in the store.\n * @returns the EXACT Cordis effect disposer (single-shot; a repeat call\n * returns undefined without awaiting an in-flight teardown). Exact\n * identity is load-bearing: a composite (generator) effect that owns a\n * teardown ORDER — the agent factory\'s lifecycle chain — must yield THIS\n * function so Cordis nests the unregistration at that yield position;\n * yielding a wrapper would leave it disposing as a concurrent sibling on\n * owner unload, unregistering the agent (and emitting `agent/disposed`)\n * while its final turn is still draining.\n */', + }, + { + signature: 'enter(agent: Agent, owner: Agent | undefined): () => void', + jsDoc: '/**\n * Insert an already-constructed agent without announcing it. This is the\n * advanced ordered-lifecycle primitive used by the async agent factory: it\n * first completes setup while the agent is unpublished, then assigns the\n * returned detach closure into its pre-installed composite teardown before\n * calling {@link announce}. Ordinary callers use {@link register}.\n * @param agent - the prepared, unpublished agent.\n * @param owner - live agent whose scoped context created this agent, or\n * undefined for a top-level runtime root. This is runtime ownership, not\n * the resumed session\'s durable parent lineage.\n * @returns an idempotent closure that removes this exact entry and emits\n * `agent/disposed` with listener failures contained. When called from a\n * synchronous `agent/created` listener, removal and disposal wait until\n * that creation dispatch unwinds.\n */', + }, + { + signature: 'announce(agent: Agent): void', + jsDoc: '/**\n * Announce an agent previously inserted with {@link enter}.\n * @param agent - the live inserted agent to announce.\n * @throws if `agent` is not the exact live registry entry for its id, or its\n * creation announcement already began (including a reentrant call from a\n * creation listener).\n */', + }, + { + signature: 'get(id: SessionId): Agent | undefined', + jsDoc: '/**\n * Look up a live agent.\n * @param id - the shared agent/session id to look up.\n * @returns the agent, or undefined when no live agent has that id.\n */', + }, + { + signature: 'isOwnedBy(id: SessionId, owner: Agent): boolean', + jsDoc: '/**\n * Test whether a live agent was created through one exact parent agent\'s\n * scoped context. Runtime ownership is independent of durable session\n * lineage and remains unambiguous when unrelated providers reuse an id.\n * @param id - the candidate child agent\'s shared agent/session id.\n * @param owner - the expected runtime creator agent.\n * @returns true only while the exact child entry is live under that owner.\n */', + }, + { + signature: 'list(): Agent[]', + jsDoc: '/**\n * All live agents, in registration order.\n * @returns a fresh array; mutating it does not affect the registry.\n */', + }, + { + signature: 'roots(): Agent[]', + jsDoc: '/**\n * All live top-level agents in registration order. A top-level agent was\n * created without an owning agent context; durable session lineage does not\n * affect this runtime relation, so a resumed fork may still be a root.\n * @returns a fresh array; mutating it does not affect the registry.\n */', + }, ], }, { key: 'approval', summary: 'Approval service that applies session policy before answerers and logs every ask/outcome pair to the requesting session.', methods: [ - 'async request(req: ApprovalRequest): Promise', + { + signature: 'async request(req: ApprovalRequest): Promise', + jsDoc: '/**\n * Ask the composed answerers to decide one readonly same-process request.\n * The service borrows the request, agent, session, and live signal directly.\n * The request requires an open turn because the audit pair must be enclosed\n * by the durable log\'s commit/replay boundary; an idle ask rejects before\n * appending anything. The answerer phase always produces an outcome: an\n * aborted signal yields `\'cancelled\'`, a missing or throwing answerer yields\n * `\'unavailable\'` (fail closed), and a rogue non-vocabulary return value is\n * normalized to `\'unavailable\'`. A failure that prevents either audit append\n * from committing still rejects because returning an unlogged decision would\n * violate the pair. Session contains post-commit observer failures, so an\n * authoritative append cannot reject the request or suppress its matching\n * audit event.\n * @param req - the pending decision (agent, tool identity, reason, signal).\n * @returns the closed outcome; `\'allowed-once\'` is the only grant.\n * @throws when no turn is open or either audit event fails before the session\n * append commit point.\n */', + }, ], }, { key: 'bash', summary: 'Abstract bash execution service.', methods: [ - 'abstract resolve(request: BashExecRequest): BashExecSpec', - 'abstract run(spec: BashExecSpec): Promise', - 'abstract start(spec: BashExecSpec): BashProcess', + { + signature: 'abstract resolve(request: BashExecRequest): BashExecSpec', + jsDoc: '/**\n * Apply implementation-owned defaults and caps to a request before execution.\n * @param request - the caller\'s request; omitted fields get this\n * implementation\'s defaults, capped fields are clamped.\n * @returns the fully-specified spec to hand to {@link run}/{@link start}.\n */', + }, + { + signature: 'abstract run(spec: BashExecSpec): Promise', + jsDoc: '/**\n * Run a command in the foreground; resolves when it finishes.\n * @param spec - a resolved spec from {@link resolve}, never a raw request.\n * @returns the outcome; nonzero exits, timeout kills, and abort kills\n * resolve with a descriptive result rather than reject.\n */', + }, + { + signature: 'abstract start(spec: BashExecSpec): BashProcess', + jsDoc: '/**\n * Start a background process and return its handle immediately.\n * @param spec - a resolved spec from {@link resolve}, never a raw request.\n * @returns the live process handle (reads, kill, quiescence promise).\n */', + }, ], }, { key: 'bashEnv', summary: 'Registry (`ctx.bashEnv`) for trusted, per-execution `DSH_*` variables.', methods: [ - 'register(contributor: BashEnvContributor): () => void', - 'collect(execution: ToolExecution): DshEnvironment', - 'list(): BashEnvVariableInfo[]', + { + signature: 'register(contributor: BashEnvContributor): () => void', + jsDoc: '/**\n * Register one environment contributor. Names and keys are unique; built-in\n * keys are reserved. Registration is disposed with the calling plugin fiber.\n * @param contributor - declared key ownership and per-execution resolver.\n * @returns the disposer that unregisters the contribution.\n */', + }, + { + signature: 'collect(execution: ToolExecution): DshEnvironment', + jsDoc: '/**\n * Build the trusted `DSH_*` snapshot for one bash tool execution.\n * @param execution - the current tool execution.\n * @returns an immutable environment overlay containing built-ins and current contributions.\n */', + }, + { + signature: 'list(): BashEnvVariableInfo[]', + jsDoc: '/**\n * Enumerate plugin-contributed variables without executing their resolvers.\n * @returns declarations sorted by environment variable name.\n */', + }, ], }, { key: 'codeRuntime', summary: 'Registers one `ctx.codeRuntime` implementation.', methods: [ - 'abstract run(request: CodeRunRequest): Promise', + { + signature: 'abstract run(request: CodeRunRequest): Promise', + jsDoc: '/**\n * Execute one program against the request\'s bindings and capture what it\n * emitted. See the class doc for the resolution contract (error is a result\n * field; rejection means seam misuse only).\n * @param request - the program, its bindings, and the abort signal; the\n * request carries everything the runtime acts on, with no hidden defaults.\n * @returns the run\'s outcome: completion value (when transferable), the\n * ordered log capture, and the failure (if any).\n */', + }, ], }, { key: 'compact', summary: 'Abstract compaction service.', methods: [ - 'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise', - 'abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', + { + signature: 'abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal, ): Promise', + jsDoc: '/**\n * Check token pressure and compact if the conversation is too large.\n * Estimate the next request, including its session prefix, derived history,\n * and system prompt. Above threshold, compact a head-anchored range ending at\n * a balanced tool boundary and reconsolidate any prior automatic checkpoint.\n * Return `null` when no compaction is needed or an open tail leaves no safe\n * cutoff. A single oversized retained unit or prefix cannot be repaired here.\n *\n * @param agent - agent context owning the session surface and model options.\n * @param fullSystemPrompt - assembled system prompt, counted toward the estimate.\n * @param sessionPrefix - the instance\'s composed session prefix, counted toward the\n * estimate.\n * @param signal - cancellation signal; model-backed implementations must forward it.\n * @returns the compaction result, or `null` if no compaction was needed.\n */', + }, + { + signature: 'abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise', + jsDoc: '/**\n * Forcibly compact a range of surface nodes into a single summary node.\n * `start` and `end` name an inclusive span by surface position, not numeric seq\n * order; replacements can make visible seqs non-monotonic. Both edges must be\n * balanced so assistant tool calls remain paired with their results. A model-\n * backed implementation forwards cancellation and rejects active, missing,\n * reversed, or unbalanced ranges. The target session is `agent.session`.\n * Use {@link toolPairingBalancedBefore} and {@link toolPairingBalancedAfter}\n * for the edge checks.\n *\n * @param start - first surface seq, inclusive.\n * @param end - last surface seq, inclusive.\n * @param agent - context whose session is mutated and whose routing options guide summarization.\n * @param signal - optional cancellation; model-backed implementations must forward it.\n * @throws when compaction is active or the range is missing, reversed, or unbalanced.\n * @returns the appended event seqs, summary, replaced range, and token accounting.\n */', + }, ], }, { key: 'fs', summary: 'Abstract filesystem provider.', methods: [ - 'abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise', - 'abstract stat(target: FsTarget, signal?: AbortSignal): Promise', - 'abstract lstat(path: string, opts?: { cwd?: string }, signal?: AbortSignal): Promise', - 'abstract readText(target: FsTarget, signal?: AbortSignal): Promise', - 'abstract streamText(target: FsTarget, signal?: AbortSignal): Promise>', - 'abstract listDir(target: FsTarget, signal?: AbortSignal): Promise', - 'abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise', - 'abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise', + { + signature: 'abstract resolve(path: string, opts?: { cwd?: string; signal?: AbortSignal }): Promise', + jsDoc: '/**\n * Resolve a model/plugin-supplied path into a stable {@link FsTarget}. May perform I/O (a\n * remote/sandboxed backend may need a round-trip to map a path to a stable identity), hence\n * async even though the local backend only normalizes + realpaths.\n *\n * @param path - the path to resolve; relative paths resolve against `opts.cwd`.\n * @param opts - optional cwd override and cancellation signal.\n * @returns the stable target; the same file yields the same `targetKey`.\n */', + }, + { + signature: 'abstract stat(target: FsTarget, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Return target metadata, or `undefined` when the target does not exist.\n * @param target - the resolved target to stat.\n * @param signal - aborts the metadata round-trip.\n * @returns metadata only, never content; undefined for an absent target.\n */', + }, + { + signature: 'abstract lstat(path: string, opts?: { cwd?: string }, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Return path metadata without following the final path component when it is a\n * symbolic link. This is intentionally path-shaped, not target-shaped:\n * {@link resolve} follows symlinks to produce the stable identity used by\n * normal reads/writes, while `lstat` lets a consumer reject the path itself\n * before that follow happens.\n *\n * `opts.cwd` follows {@link resolve}\'s cwd rules. `undefined` means the path is\n * absent.\n * @param path - the path to inspect; relative paths resolve against `opts.cwd`.\n * @param opts - `cwd` overrides the backend\'s default base for relative paths.\n * @param signal - aborts the metadata round-trip.\n * @returns metadata only, never content; undefined for an absent path.\n */', + }, + { + signature: 'abstract readText(target: FsTarget, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Read the whole regular text file as a single decoded string.\n * @param target - the resolved target to read.\n * @param signal - aborts the read.\n * @returns the full decoded UTF-8 content.\n */', + }, + { + signature: 'abstract streamText(target: FsTarget, signal?: AbortSignal): Promise>', + jsDoc: '/**\n * Stream the whole regular text file as decoded text chunks (same text\n * semantics as {@link readText}, for large files). The backend owns\n * cross-chunk UTF-8 decoding and binary rejection so the policy layer never\n * touches raw bytes.\n * @param target - the resolved target to read.\n * @param signal - aborts the stream, including between chunks.\n * @returns the chunk iterable, decoded and validated like {@link readText}.\n */', + }, + { + signature: 'abstract listDir(target: FsTarget, signal?: AbortSignal): Promise', + jsDoc: '/**\n * List direct children of a directory in stable name order. Returns resolved\n * child targets plus cheap metadata only; never reads file contents.\n * @param target - the resolved directory target.\n * @param signal - aborts the listing.\n * @returns one entry per direct child, in stable name order.\n */', + }, + { + signature: 'abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Atomically create or replace UTF-8 text. `expected` guards intent and\n * staleness; omission allows unconditional overwrite.\n * @param target - the resolved target to write.\n * @param content - the full new file content.\n * @param expected - the write intent guarding the write; omit for unconditional.\n * @param signal - aborts before the atomic rename takes effect.\n * @returns the outcome, including the version the write produced.\n */', + }, + { + signature: 'abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Atomically edit literal text. When supplied, the version guard is checked\n * before matching so stale content reports `FS_STALE_VERSION`; omission edits\n * the current content without a freshness precondition.\n * @param target - the resolved target to edit.\n * @param edit - the literal search/replace request.\n * @param expected - the version guard; omit for an unconditional edit.\n * @param signal - aborts before the atomic rename takes effect.\n * @returns the outcome, including the version the edit produced.\n */', + }, ], }, { key: 'llm', summary: 'The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.', methods: [ - 'registerAdapter(providers: string[], adapter: LlmAdapter): () => void', - 'listProviders(): LlmProviderInfo[]', - 'async listModels(provider: string): Promise', - 'stream(options: GenerateOptions): AsyncIterable', + { + signature: 'registerAdapter(providers: string[], adapter: LlmAdapter): () => void', + jsDoc: '/**\n * Register an adapter for the given provider routes. Throws `LlmError` with code\n * `DUPLICATE_ADAPTER` if any provider already has an adapter (all-or-nothing).\n * Disposed with the fiber.\n * @param providers - every provider route this adapter should serve.\n * @param adapter - the adapter that streams calls for those providers.\n * @returns the disposer that unregisters all of them.\n */', + }, + { + signature: 'listProviders(): LlmProviderInfo[]', + jsDoc: '/**\n * Describe provider routes with a registered adapter.\n * @returns detached provider metadata in registration order.\n */', + }, + { + signature: 'async listModels(provider: string): Promise', + jsDoc: '/**\n * Discover models advertised by one registered provider. Catalog membership\n * is advisory and never changes routing or request validation.\n * @param provider - registered provider route to inspect.\n * @returns detached model metadata in adapter-preferred order.\n */', + }, + { + signature: 'stream(options: GenerateOptions): AsyncIterable', + jsDoc: '/**\n * Stream one model call as raw chunks (token-level deltas). Throws\n * `LlmError` with code `NO_ADAPTER` if no adapter is registered for\n * `options.provider`. Replay state is retained only when the same adapter\n * instance owns its historical provider and the target provider. Dispatches\n * through the `llm/stream` waterfall.\n * @param options - the full request; `options.provider` selects the adapter.\n * @returns the chunk stream, possibly wrapped by `llm/stream` listeners.\n */', + }, ], }, { key: 'permission', summary: 'Owns the deployment\'s permission presets and their write path.', methods: [ - 'current(events: readonly SessionEvent[]): string', - 'resolve(name: string): PresetSpec', - 'optionOf(name: string): PresetOption', - 'set(session: Session, name: string): void', + { + signature: 'current(events: readonly SessionEvent[]): string', + jsDoc: '/**\n * Resolve the preset matching the effective knob values. A still-matching\n * last selection wins shared-bundle ties; otherwise the first table match\n * wins, or {@link CUSTOM_PRESET} when no entry matches.\n * @param events - the session\'s events in log order.\n * @returns the effective preset name, or `custom` when nothing matches.\n */', + }, + { + signature: 'resolve(name: string): PresetSpec', + jsDoc: '/**\n * Resolve a preset\'s knob bundle.\n * @param name - the preset name to resolve.\n * @returns the configured bundle.\n * @throws when `name` is not in the table.\n */', + }, + { + signature: 'optionOf(name: string): PresetOption', + jsDoc: '/**\n * Build the client option for a table entry or {@link CUSTOM_PRESET}. A\n * missing label falls back to the table key.\n * @param name - a table key, or `custom`.\n * @returns the option a client renders.\n * @throws when `name` is neither a table key nor `custom`.\n */', + }, + { + signature: 'set(session: Session, name: string): void', + jsDoc: '/**\n * Record a changed preset, then update each changed knob through its own\n * setter. Selecting the effective preset again appends nothing.\n * @param session - the session the switch belongs to.\n * @param name - the preset to switch to; unknown names throw.\n */', + }, ], }, { key: 'sandbox', summary: 'Abstract process-sandbox service.', methods: [ - 'abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv', + { + signature: 'abstract confine(argv: readonly string[], policy: SandboxPolicy): ConfinedArgv', + jsDoc: '/**\n * Wrap `argv` so it executes confined under `policy` on this host; the\n * caller spawns the returned argv in place of its own.\n * @param argv - the exact argv the caller is about to spawn (program plus\n * arguments), NOT a shell string — a shell-shaped consumer passes\n * `[\'bash\', \'-c\', command]`.\n * @param policy - the file-effect policy this execution runs under,\n * carried per call (see {@link SandboxPolicy}).\n * @returns the argv to spawn instead, plus the enforcement completeness\n * the selected backend achieves for it.\n */', + }, ], }, { key: 'sessionPersistence', summary: 'Durable append-only session storage.', methods: [ - 'abstract locate(meta: SessionHeader): SessionLocation | undefined', - 'abstract create(meta: SessionHeader): Promise', - 'abstract append(id: SessionId, events: readonly SessionEvent[]): Promise', - 'abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>', - 'abstract list(): Promise', + { + signature: 'abstract locate(meta: SessionHeader): SessionLocation | undefined', + jsDoc: '/**\n * Resolve this backend\'s independent local artifact for a session without\n * reading, creating, flushing, or otherwise materializing it. Backends such\n * as SQLite that do not own one artifact per session return `undefined`.\n * @param meta - the immutable session header whose artifact is requested.\n * @returns the backend-specific absolute location, when one exists.\n */', + }, + { + signature: 'abstract create(meta: SessionHeader): Promise', + jsDoc: '/**\n * Register a new session\'s metadata. A backend MAY defer the physical write\n * until the first {@link append} (lazy materialization), in which case a\n * created-but-never-appended session is absent from {@link list}\n * — abandoned sessions leave nothing behind.\n * @param meta - the immutable header (id, version, cwd, lineage) to record.\n */', + }, + { + signature: 'abstract append(id: SessionId, events: readonly SessionEvent[]): Promise', + jsDoc: '/**\n * Durably persist a batch of events (called from the write-behind drain at\n * the `session/flush` checkpoint). Honors the append-only and contiguous-seq\n * contracts: the first event\'s `seq` MUST equal the stored next-seq (after\n * `load` has durably closed any interrupted turn). Rejects non-JSON-\n * serializable `event.data` with an error naming the offending event type.\n * @param id - the session the batch belongs to.\n * @param events - the contiguous batch to persist, in seq order.\n */', + }, + { + signature: 'abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>', + jsDoc: '/**\n * Load a header and balanced contiguous log. A complete interrupted final\n * turn is preserved and durably closed with missing tool errors plus any open\n * step and turn boundaries; only a torn final record is discarded. Unknown\n * versions and corruption in the committed prefix reject.\n * @param id - the persisted session to reload.\n * @returns the header and a log ending on a balanced `turn/end`.\n */', + }, + { + signature: 'abstract list(): Promise', + jsDoc: '/**\n * Lightweight listing from metadata, without a full-log parse.\n * @returns one header per materialized session.\n */', + }, ], }, { key: 'sessionQuery', summary: 'Live-preferred logical-corpus exact-read and relationship-tracing service.', methods: [ - 'listSessions(): Promise', - 'async listEvents(sessionId: SessionId): Promise', - 'async traceSession(sessionId: SessionId): Promise', - 'async traceEvent(request: SessionEventTraceRequest): Promise', - 'async readEvent(request: SessionEventReadRequest): Promise', + { + signature: 'listSessions(): Promise', + jsDoc: '/**\n * List the complete logical corpus using live-preferred records.\n * @returns deterministic newest-first cloned session records.\n */', + }, + { + signature: 'async listEvents(sessionId: SessionId): Promise', + jsDoc: '/**\n * List lightweight raw-log event records for one logical session.\n * @param sessionId - live-preferred session id to read.\n * @returns event records in ascending seq order.\n */', + }, + { + signature: 'async traceSession(sessionId: SessionId): Promise', + jsDoc: '/**\n * Trace known ancestry and descendants from one corpus observation.\n * @param sessionId - logical session id to trace.\n * @returns a complete lineage or an explicit unresolved parent boundary.\n * @throws when corpus resolution fails, the target is absent, or its known ancestry cycles.\n */', + }, + { + signature: 'async traceEvent(request: SessionEventTraceRequest): Promise', + jsDoc: '/**\n * Trace one event\'s direct positional and provenance relationships.\n * @param request - target session id and event seq.\n * @returns direct links plus the target\'s positional replacement chain.\n * @throws when source resolution fails, the target is absent, or surface/provenance validation fails.\n */', + }, + { + signature: 'async readEvent(request: SessionEventReadRequest): Promise', + jsDoc: '/**\n * Read one full event plus a bounded raw-log context window.\n * @param request - target session/seq and context sizes.\n * @returns cloned target and neighboring events.\n */', + }, ], }, { key: 'sessions', summary: 'In-memory session store (`ctx.sessions`).', methods: [ - 'create(id?: SessionId, options?: CreateSessionOptions): Session', - 'prepare(id?: SessionId, options?: CreateSessionOptions): Session', - 'enter(session: Session): () => void', - 'announce(session: Session): void', - 'async flush(session: Session): Promise', - 'get(id: SessionId): Session | undefined', - 'list(): Session[]', - 'fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session', + { + signature: 'create(id?: SessionId, options?: CreateSessionOptions): Session', + jsDoc: '/**\n * Create a session owned by the calling fiber: disposing that fiber stops\n * event notification and removes the session from the store. `options.seed`\n * populates the session with a copy of those events (replay/fork);\n * `options.meta` attaches creation metadata (validated absolute `cwd`,\n * `parentSession` lineage) as the immutable {@link SessionHeader} (the store\n * fills `version`/`id`/`createdAt`).\n *\n * For an agent whose session must be torn down IN ORDER with its loop (so the\n * loop\'s final flush is captured before the store attachment ends), do NOT use this\n * — fold the session lifecycle into the agent\'s own effect via\n * {@link prepare} + {@link enter} + {@link announce} (see\n * `dsh-agent-loop`\'s creation transaction).\n *\n * @param id - the session id; omitted, the store mints `session-`.\n * @param options - seed events and/or creation metadata for the header.\n * @returns the live session, already entered and announced.\n * @throws if a session with `id` already exists, metadata is not a plain\n * lossless-JSON record with valid scalar fields, or `meta.cwd` is a\n * non-absolute path (storage backends key directories off it).\n */', + }, + { + signature: 'prepare(id?: SessionId, options?: CreateSessionOptions): Session', + jsDoc: '/**\n * Build a session WITHOUT entering it into the store — validate the id/cwd and\n * construct the {@link Session} (with its immutable {@link SessionHeader}).\n * Pairs with {@link enter} + {@link announce}: a caller that owns a composite\n * `ctx.effect` (the agent factory) folds the session lifecycle into that ONE\n * effect so a fiber unload tears the session + agent down as a single ORDERED\n * chain rather than as racing sibling effects — which would remove the publication hooks\n * before the loop\'s closing `session/flush`, dropping the closing events.\n *\n * @param id - the session id; omitted, the store mints `session-`.\n * @param options - seed events and/or creation metadata for the header.\n * @returns the constructed session, NOT yet in the store.\n * @throws if a session with `id` already exists, metadata is not a plain\n * lossless-JSON record with valid scalar fields, or `meta.cwd` is a\n * non-absolute path.\n */', + }, + { + signature: 'enter(session: Session): () => void', + jsDoc: '/**\n * Enter a {@link prepare}d session into the store: install the module-private\n * append publication hooks and add it to the store. Returns the DETACH\n * disposer (hooks + store removal). Does NOT emit `session/created` —\n * the caller yields this disposer inside its effect and THEN calls\n * {@link announce}, so a throwing `session/created` listener rolls the attach\n * back instead of leaking it.\n *\n * Re-checks the id for a duplicate: `prepare` and `enter` are public\n * cross-package primitives and a caller may interleave arbitrary work (or\n * another create) between them, so a stale prepared session must NOT overwrite\n * a live store entry of the same id — its detach disposer would later delete\n * the REAL session. The {@link create} convenience and the agent factory call\n * the two back-to-back so they never trip this, but the public seam cannot\n * assume that.\n *\n * @param session - a {@link prepare}d session not yet in the store.\n * @returns the detach disposer (publication hooks + store removal). When called from\n * a synchronous `session/created` listener, removal and disposal wait until\n * that creation dispatch unwinds.\n * @throws if a session with this id is already in the store.\n */', + }, + { + signature: 'announce(session: Session): void', + jsDoc: '/** Emit `session/created` exactly once for an {@link enter}ed session (with\n * the carrier {@link enter} captured). Separate from {@link enter} so the\n * caller can yield the detach disposer first (rollback safety — see\n * {@link enter}).\n * @param session - the entered session to announce to listeners.\n * @throws if the session is not live or its announcement already began,\n * including a reentrant call from a creation listener. */', + }, + { + signature: 'async flush(session: Session): Promise', + jsDoc: '/**\n * Dispatch the awaited `session/flush` durability checkpoint for `session`,\n * with the carrier captured at {@link enter}. THE flush entry point: the\n * store owns the carrier, so callers (the loop\'s turn-end checkpoint, idle\n * injection, teardown drains) must come through here rather than dispatch a\n * raw `ctx.parallel(\'session/flush\', …)` — one owner, one spelling, and the\n * scoped-dispatch invariant can pin it.\n * @param session - the session whose buffered events must reach durable storage.\n * @returns resolves when every flush listener has settled; after all settle,\n * rejects with the first registered listener failure if any listener failed.\n */', + }, + { + signature: 'get(id: SessionId): Session | undefined', + jsDoc: '/**\n * Look up a live session.\n * @param id - the session id to look up.\n * @returns the session, or undefined when no live session has that id.\n */', + }, + { + signature: 'list(): Session[]', + jsDoc: '/**\n * All live sessions, in creation order.\n * @returns a fresh array; mutating it does not affect the store.\n */', + }, + { + signature: 'fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session', + jsDoc: '/**\n * Create a live child session from a turn-enclosed prefix of a live source.\n * `boundary` is an inclusive source event seq; omitted means the source\'s\n * current last event. A non-empty selected slice must end at `turn/end`.\n *\n * @param source - Live source session object or id.\n * @param boundary - Inclusive source event seq to fork through; omitted means\n * the source\'s current last event, and omitted on an empty source forks an\n * empty child.\n * @param childSessionId - Optional child session id; omitted delegates to\n * `SessionStore`\'s id policy.\n * @returns The created live child session.\n */', + }, ], }, { key: 'skills', summary: 'Registry of skill providers.', methods: [ - 'registerProvider(provider: SkillProvider): () => void', - 'register(skill: SkillRegistration): () => void', - 'async list(options: SkillLookupOptions = {}): Promise', - 'async get(name: string, options: SkillLookupOptions = {}): Promise', + { + signature: 'registerProvider(provider: SkillProvider): () => void', + jsDoc: '/**\n * Register a borrowed same-process provider synchronously during plugin apply. Duplicate and\n * reserved names throw; remote initialization belongs in `list()`. Fiber disposal unregisters\n * the provider and invalidates catalog caches.\n * @param provider - the provider to register by `provider.name`.\n * @returns the exact Cordis effect disposer that unregisters this provider;\n * composite effects may yield it directly to preserve teardown ordering.\n */', + }, + { + signature: 'register(skill: SkillRegistration): () => void', + jsDoc: '/**\n * Register a borrowed readonly runtime skill. Project entries outrank runtime entries, which\n * outrank user entries. Same-name runtime entries are first-wins; a duplicate logs a warning and\n * receives a no-op disposer so it cannot remove the winner.\n * @param skill - the complete skill definition to expose for discovery.\n * @returns the exact Cordis effect disposer, preserving composite teardown order and invalidating caches.\n */', + }, + { + signature: 'async list(options: SkillLookupOptions = {}): Promise', + jsDoc: '/**\n * List model-invocable skill summaries for a workspace. Lookup options and\n * provider candidates are readonly same-process values borrowed throughout\n * discovery.\n * @param options - lookup options; `cwd` selects project roots and `signal` cancels discovery.\n * @returns sorted summaries, excluding skills disabled for model invocation.\n */', + }, + { + signature: 'async get(name: string, options: SkillLookupOptions = {}): Promise', + jsDoc: '/**\n * Load and validate the winning candidate, passing its opaque discovery locator back to the\n * provider. Cancellation is rechecked after selection, including cache hits, and raced against\n * loading so an uncooperative provider cannot hang the caller.\n * @param name - kebab-case skill name.\n * @param options - lookup options; `cwd` selects workspace-sensitive skills and `signal` cancels work.\n * @returns the full skill, including body content, or `undefined`.\n */', + }, ], }, { key: 'spillStore', summary: 'Abstract spill storage service.', methods: [ - 'abstract saveText(input: SaveTextSpill): Promise', + { + signature: 'abstract saveText(input: SaveTextSpill): Promise', + jsDoc: '/**\n * Persist `input.content` to a session-scoped spill artifact.\n * @param input - the owner, provenance, suggested name, and full text to save.\n * @returns the saved artifact\'s {@link SpillRef}; rejects on a storage failure.\n */', + }, ], }, { key: 'subagents', summary: 'Named provider registry and capability-checked start surface.', methods: [ - 'registerProvider(provider: SubagentProvider): () => void', - 'getProvider(name: string): SubagentProvider | undefined', - 'list(): string[]', - 'async start(name: string, request: SubagentStartRequest): Promise', + { + signature: 'registerProvider(provider: SubagentProvider): () => void', + jsDoc: '/**\n * Register a provider under its name. Registration is effect-scoped and HMR\n * safe; removing a provider blocks new starts but does not revoke runs that\n * were already returned to their holders.\n * @param provider - the trusted provider implementation.\n * @returns the exact Cordis effect disposer.\n */', + }, + { + signature: 'getProvider(name: string): SubagentProvider | undefined', + jsDoc: '/**\n * Look up a provider by name.\n * @param name - the provider name.\n * @returns the provider, or undefined when absent.\n */', + }, + { + signature: 'list(): string[]', + jsDoc: '/**\n * List registered provider names in insertion order.\n * @returns the registered names.\n */', + }, + { + signature: 'async start(name: string, request: SubagentStartRequest): Promise', + jsDoc: '/**\n * Establish a ready child on the named provider. Capability and semantic\n * checks run before delegation. Provider ownership lasts until its promise\n * fulfills; a rejection therefore has no run for the caller to dispose and\n * emits no run lifecycle events.\n * @param name - the provider to use.\n * @param request - child prompt, parent, signal, and optional capabilities.\n * @returns the ready holder-owned run.\n */', + }, ], }, { key: 'systemPrompt', summary: 'Registry service for the prompt inputs assembled before each model step.', methods: [ - 'section(section: PromptSection): () => void', - 'tools(provider: (context: AssembleContext) => ToolProviderResult): () => void', - 'variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void', - 'async assemble(context: AssembleContext = {}): Promise', + { + signature: 'section(section: PromptSection): () => void', + jsDoc: '/**\n * Register an ordered prompt section in the calling context\'s scope. A scoped\n * section shadows a global section with the same name; duplicates within one\n * layer and non-finite orders throw. Registration and disposal emit\n * `system-prompt/change`.\n * @param section - the section to register.\n * @returns the exact Cordis effect disposer.\n */', + }, + { + signature: 'tools(provider: (context: AssembleContext) => ToolProviderResult): () => void', + jsDoc: '/**\n * Register a tool-schema provider in the calling context\'s scope. Global and\n * matching scoped providers both contribute; returning the reserved\n * {@link TOOL_ORDER_REST} name makes assembly fail.\n * @param provider - evaluated for each assembly with its context.\n * @returns the exact Cordis effect disposer.\n */', + }, + { + signature: 'variable(name: string, provider: (context: AssembleContext) => string | undefined): () => void', + jsDoc: '/**\n * Register a prompt variable in the calling context\'s scope. Scoped values\n * shadow globals; invalid or duplicate names throw. A provider may return\n * `undefined`, but rendering a section that references that value then fails.\n * @param name - the `[a-z][a-z0-9_]*` reference name.\n * @param provider - evaluated for each assembly.\n * @returns the exact Cordis effect disposer.\n */', + }, + { + signature: 'async assemble(context: AssembleContext = {}): Promise', + jsDoc: '/**\n * Assemble global and scoped providers, detach tool parameters, apply\n * canonical ordering, then run the assembly waterfall. Scoped sections and\n * variables shadow globals; the returned waterfall value is authoritative.\n * @param context - the optional scope and plugin-defined assembly fields.\n * @returns the authoritative post-waterfall assembly.\n */', + }, ], }, { key: 'tasks', summary: 'The `tasks` service: the runtime-global background task registry.', methods: [ - 'start(spec: TaskStart): TaskId', - 'list(caller?: Agent): TaskSnapshot[]', - 'get(id: TaskId, caller?: Agent): TaskSnapshot', - 'read(id: TaskId, caller?: Agent): TaskRead', - 'kill(id: TaskId, caller?: Agent, reason?: string): \'requested\' | \'already-finished\'', - 'async wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSignal): Promise', - 'onTaskDone(listener: TaskDoneListener): () => void', - 'attachSurface(name: string): () => void', + { + signature: 'start(spec: TaskStart): TaskId', + jsDoc: '/**\n * Preflight access, validation, and owner cleanup before starting and\n * atomically registering work. A throwing starter leaves nothing registered;\n * after it returns, registration cannot fail. Settlement records the outcome,\n * notifies listeners, and releases waiters.\n * @param spec - task identity, owner, and synchronous starter.\n * @returns the registry-issued `-N` id.\n */', + }, + { + signature: 'list(caller?: Agent): TaskSnapshot[]', + jsDoc: '/**\n * List caller-owned and unowned tasks in registration order without exposing\n * another session\'s labels.\n * @param caller - reading agent; a non-agent caller sees only unowned tasks.\n * @returns fresh snapshots.\n */', + }, + { + signature: 'get(id: TaskId, caller?: Agent): TaskSnapshot', + jsDoc: '/**\n * Return a non-consuming snapshot without changing its read cursor or notice\n * state. Throws for an unknown or foreign task.\n * @param id - task to look up.\n * @param caller - reading agent checked against the owner.\n * @returns a fresh snapshot.\n */', + }, + { + signature: 'read(id: TaskId, caller?: Agent): TaskRead', + jsDoc: '/**\n * Read the next stream delta, or the idempotent final output after settlement.\n * A terminal read marks the task reported. Throws for an unknown or foreign\n * task.\n * @param id - task to read.\n * @param caller - reading agent checked against the owner.\n * @returns output text and the post-read snapshot.\n */', + }, + { + signature: 'kill(id: TaskId, caller?: Agent, reason?: string): \'requested\' | \'already-finished\'', + jsDoc: '/**\n * Request cancellation, then mark the task stopping and reported. A producer\n * throw propagates without changing task state. Throws for an unknown or\n * foreign task.\n * @param id - task to cancel.\n * @param caller - killing agent checked against the owner.\n * @param reason - logged reason forwarded to the producer.\n * @returns `requested` for live work, otherwise `already-finished`.\n */', + }, + { + signature: 'async wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Wait for settlement or timeout without cancelling the task. Caller abort\n * rejects only while the task is live; after settlement it returns the\n * terminal snapshot so a notice suppressed for this waiter is still delivered.\n * Timed-out and aborted waits detach their resolvers. Throws for invalid,\n * unknown, or foreign input.\n * @param id - task to wait for.\n * @param timeoutMs - positive finite wait bound in milliseconds.\n * @param caller - waiting agent checked against the owner.\n * @param signal - optional cancellation of the wait itself.\n * @returns snapshot at settlement or timeout.\n */', + }, + { + signature: 'onTaskDone(listener: TaskDoneListener): () => void', + jsDoc: '/**\n * Register an effect-scoped completion listener. Each listener is contained;\n * returned promises are observed but not awaited. No listener runs after\n * service disposal.\n * @param listener - receives each terminal snapshot and its exact owner.\n * @returns disposer that unregisters the listener.\n */', + }, + { + signature: 'attachSurface(name: string): () => void', + jsDoc: '/**\n * Attach an effect-scoped surface that can read and stop tasks. {@link start}\n * refuses work while none is attached.\n * @param name - diagnostic label; duplicate names remain independent.\n * @returns disposer that detaches this surface.\n */', + }, ], }, { key: 'tokenMeter', summary: 'Replay owner for one service-wide estimator and isolated per-session folds.', methods: [ - 'measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement', - 'estimateMessage(message: Message): number', + { + signature: 'measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement', + jsDoc: '/**\n * Measure current request pressure and surface through the durable tail.\n *\n * Provider usage is reused only when the latest successful call\'s canonical\n * request envelope matches `requestHeader` and its total is no lower than\n * that call\'s full heuristic anchor; otherwise the complete envelope and\n * surface are heuristically repriced.\n *\n * `requestHeader` affects request pressure only; surface fields always\n * describe the current session surface. Every call clones those positional\n * nodes, so measurement is O(surface).\n *\n * @param session - session to replay through its current durable tail.\n * @param requestHeader - optional effective request envelope replacing the latest logged header.\n * @returns a detached deeply immutable pressure and surface measurement.\n */', + }, + { + signature: 'estimateMessage(message: Message): number', + jsDoc: '/**\n * Heuristically price one model-visible message.\n * @param message - message to price without mutation.\n * @returns content and role-framing tokens under the fixed service heuristic.\n */', + }, ], }, { key: 'tools', summary: 'Tool registry and execution pipeline.', methods: [ - 'register(definition: ToolDefinition): () => void', - 'restrict(filter: ToolRestriction): () => void', - 'guard(guard: ToolGuard): () => void', - 'get(name: string, scope?: ScopeKey): ToolDefinition | undefined', - 'schemas(scope?: ScopeKey): ToolSchema[]', - 'executionMode(exec: ToolExecutionInput): ToolExecutionMode', - 'async execute(exec: ToolExecutionInput): Promise', + { + signature: 'register(definition: ToolDefinition): () => void', + jsDoc: '/**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - the tool schema, execution, and optional presentation functions.\n * @returns the exact disposer that unregisters the tool.\n */', + }, + { + signature: 'restrict(filter: ToolRestriction): () => void', + jsDoc: '/**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */', + }, + { + signature: 'guard(guard: ToolGuard): () => void', + jsDoc: '/**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */', + }, + { + signature: 'get(name: string, scope?: ScopeKey): ToolDefinition | undefined', + jsDoc: '/**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */', + }, + { + signature: 'schemas(scope?: ScopeKey): ToolSchema[]', + jsDoc: '/**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */', + }, + { + signature: 'executionMode(exec: ToolExecutionInput): ToolExecutionMode', + jsDoc: '/**\n * Classify a pending call through the caller\'s visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */', + }, + { + signature: 'async execute(exec: ToolExecutionInput): Promise', + jsDoc: '/**\n * Execute through pre-policy, guards, around-dispatch, post-policy, and final\n * notification. Tool and listener failures resolve as materialized error\n * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is\n * the same lossless, frozen snapshot final observers receive.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */', + }, ], }, { key: 'userInteraction', summary: '`ctx.userInteraction`: one active UI provider plus an `ask()` surface.', methods: [ - 'registerProvider(provider: UserInteractionProvider): () => void', - 'async ask(request: AskUserQuestionRequest): Promise', + { + signature: 'registerProvider(provider: UserInteractionProvider): () => void', + jsDoc: '/**\n * Register the UI provider. Only one provider may be active in a context.\n *\n * @param provider UI-side implementation that collects answers.\n * @returns Disposer that unregisters this provider.\n */', + }, + { + signature: 'async ask(request: AskUserQuestionRequest): Promise', + jsDoc: '/**\n * Ask the active UI provider and wait for the user\'s answer.\n *\n * @param request Questions, owner agent, and abort signal.\n * @returns The answer chosen or typed by the human.\n */', + }, ], }, { key: 'web', summary: 'The web access service.', methods: [ - 'registerSearchProvider(provider: WebSearchProvider): () => void', - 'registerFetchProvider(provider: WebFetchProvider): () => void', - 'async search(request: WebSearchRequest, signal?: AbortSignal): Promise', - 'async fetch(request: WebFetchRequest, signal?: AbortSignal): Promise', + { + signature: 'registerSearchProvider(provider: WebSearchProvider): () => void', + jsDoc: '/**\n * Register a search provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER`\n * if its id is already registered for search. Returns a disposer; disposed\n * with the calling fiber.\n * @param provider - the provider; its `id` is the registry key.\n * @returns the disposer that unregisters the provider.\n */', + }, + { + signature: 'registerFetchProvider(provider: WebFetchProvider): () => void', + jsDoc: '/**\n * Register a fetch provider. Throws {@link WebError} `WEB_DUPLICATE_PROVIDER`\n * if its id is already registered for fetch. Returns a disposer; disposed\n * with the calling fiber.\n * @param provider - the provider; its `id` is the registry key.\n * @returns the disposer that unregisters the provider.\n */', + }, + { + signature: 'async search(request: WebSearchRequest, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Run one search through the selected provider. Resolves the provider at call\n * time with the selection rules above; throws {@link WebError} when the\n * capability cannot run. The seam enforces `request.maxResults` on the result:\n * if the provider over-returns, `sources[]` is truncated and `truncated` set.\n * @param request - the query plus result-shaping options.\n * @param signal - optional cancellation signal forwarded to the provider.\n * @returns the provider\'s results, capped to `request.maxResults`.\n */', + }, + { + signature: 'async fetch(request: WebFetchRequest, signal?: AbortSignal): Promise', + jsDoc: '/**\n * Retrieve one URL through the selected provider. Resolves the provider at\n * call time with the selection rules above; throws {@link WebError} when the\n * capability cannot run. A non-2xx response is a result, not a throw.\n * @param request - the URL plus retrieval options.\n * @param signal - optional cancellation signal forwarded to the provider.\n * @returns the retrieval outcome; non-2xx responses resolve descriptively.\n */', + }, ], }, { key: 'workflows', summary: 'Workflow execution seam.', methods: [ - 'abstract start(request: WorkflowStartRequest): WorkflowRun', + { + signature: 'abstract start(request: WorkflowStartRequest): WorkflowRun', + jsDoc: '/**\n * Parse and execute a workflow script.\n * @param request - the script, its `args`, the parent agent, and an\n * optional cancel signal.\n * @returns the live run; its `result` resolves when the script settles.\n */', + }, ], }, ] @@ -299,240 +594,280 @@ export const EVENT_API: readonly EventApiEntry[] = [ name: 'agent-loop/config-start-failed', mode: 'emit', signature: '\'agent-loop/config-start-failed\'(sessionId: SessionId, error: unknown): void', + jsDoc: '/**\n * A declarative agent entry failed before it could publish a live agent.\n * Consumers that buffer work for the configured identity use this\n * transient signal to reject that work instead of waiting forever. Normal\n * factory teardown suppresses failures from the cancelled startup attempt.\n * @param sessionId - exact shared agent/session identity that failed startup.\n * @param error - persistence, setup, or publication failure.\n * @mode emit\n */', summary: 'A declarative agent entry failed before it could publish a live agent.', }, { name: 'agent/created', mode: 'emit', signature: '\'agent/created\'(this: Scoped, agent: Agent): void', + jsDoc: '/**\n * A fully configured agent and live session were published. Setup is\n * composition-only; `agent/session-start` is the first startup-driving seam.\n * Synchronous listener failure vetoes publication, while returned-promise\n * rejection is reported. Detach requested during dispatch waits until every\n * creation listener has observed the stable entry.\n * @param agent - the newly registered agent with its live session and completed setup.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'A fully configured agent and live session were published.', }, { name: 'agent/disposed', mode: 'emit', signature: '\'agent/disposed\'(this: Scoped, agent: Agent): void', + jsDoc: '/**\n * An agent left the registry; AgentLoop emits this after driver quiescence\n * but before session detachment and scoped-registration unwind. Custom\n * registry users own their driver-ordering contract.\n * @param agent - the exact agent removed from the registry.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'An agent left the registry; AgentLoop emits this after driver quiescence but before session detachment and scoped-registration unwind.', }, { name: 'agent/error', mode: 'emit', signature: '\'agent/error\'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void', + jsDoc: '/**\n * A step or turn errored. The loop reports a failure here (plus the logger)\n * even when the error has no in-turn position for a session `error` event.\n * @param agent - the agent whose turn errored.\n * @param turn - the turn in which the failure surfaced.\n * @param step - the step at which the failure surfaced.\n * @param error - the failure, verbatim.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'A step or turn errored.', }, { name: 'agent/pre-step', mode: 'serial', signature: '\'agent/pre-step\'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void', + jsDoc: '/**\n * Awaited serial checkpoint for session-surface mutation after prompt\n * assembly and before `step/start`; appends land outside the pending step.\n * The loop derives history once afterward, so compaction records and\n * replacements are included without rewriting an assembled request. The\n * prompt and prefix are the exact pressure inputs for that request, and\n * `signal` cancels listener work.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @param agent - the agent opening the step.\n * @param turn - the open turn number.\n * @param step - the pending step number.\n * @param fullSystemPrompt - the assembled prompt.\n * @param sessionPrefix - the frozen request prefix.\n * @param signal - the turn abort signal.\n * @mode serial\n */', summary: 'Awaited serial checkpoint for session-surface mutation after prompt assembly and before `step/start`; appends land outside the pending step.', }, { name: 'agent/prompt-submit', mode: 'waterfall', signature: '\'agent/prompt-submit\'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise', + jsDoc: '/**\n * Allow, rewrite, or block one drained prompt before it becomes a user\n * message. Call `next()` for the unchanged default.\n * @param agent - the agent draining its inbox.\n * @param content - the drained message\'s blocks, as queued.\n * @param source - the message\'s resolved source.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode waterfall\n */', summary: 'Allow, rewrite, or block one drained prompt before it becomes a user message.', }, { name: 'agent/queued', mode: 'emit', signature: '\'agent/queued\'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void', + jsDoc: '/**\n * Detached, frozen content entered the agent\'s inbox. Source defaults have\n * already been applied, so these are the exact values retained for the log.\n * @param agent - the agent whose inbox received the message.\n * @param content - the accepted content blocks retained by the inbox.\n * @param info - the accepted source plus whether it entered as steering.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'Detached, frozen content entered the agent\'s inbox.', }, { name: 'agent/request', mode: 'waterfall', signature: '\'agent/request\'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise', + jsDoc: '/**\n * Replace the frozen call configuration. Model-visible content must use\n * logged channels; this seam cannot mutate messages. Injection here joins\n * the next request because the current step boundary is already fixed.\n * @param agent - the agent making the model call.\n * @param turn - the open turn number.\n * @param step - the step whose request this is.\n * @param config - the config the loop would use (frozen); return a replacement to switch.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode waterfall\n */', summary: 'Replace the frozen call configuration.', }, { name: 'agent/session-prefix', mode: 'waterfall', signature: '\'agent/session-prefix\'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise', + jsDoc: '/**\n * Compose request-only messages placed before derived history. The frozen\n * result is computed once per loop instance, logged on its anchoring request\n * header, and reused so the provider prefix remains stable. Interrupted\n * composition is discarded. Composition precedes the first `agent/pre-step`\n * and request boundary, so listener appends join the current request and\n * pressure accounting sees the composed prefix. Changing context belongs in\n * history; contributors should prepend to `await next()` to preserve registration order.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @param agent - the agent whose session prefix is being composed.\n * @param prefix - the frozen seed; return an extended replacement.\n * @param signal - aborts composition when the step is torn down.\n * @mode waterfall\n */', summary: 'Compose request-only messages placed before derived history.', }, { name: 'agent/session-start', mode: 'emit', signature: '\'agent/session-start\'(this: Scoped, agent: Agent, source: SessionStartSource): void', + jsDoc: '/**\n * The session lifecycle began, once before the first turn. Use\n * `agent.inject()` to seed model-facing context. This is a notification, not\n * a veto; disposal requested by a lifecycle owner is rechecked before the\n * driver starts.\n * @param agent - the agent whose session lifecycle began.\n * @param source - why the session started (fresh startup, resume, …).\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'The session lifecycle began, once before the first turn.', }, { name: 'agent/status', mode: 'emit', signature: '\'agent/status\'(this: Scoped, agent: Agent, status: AgentStatus): void', + jsDoc: '/**\n * Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does\n * not enter `running` synchronously; drive lifecycle from this event.\n * @param agent - the agent whose status flipped.\n * @param status - the status just entered (the transition\'s destination).\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode emit\n */', summary: 'Agent status changed (`idle` ⇄ `running`, or → `disposed`).', }, { name: 'agent/step-result', mode: 'waterfall', signature: '\'agent/step-result\'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise', + jsDoc: '/**\n * Waterfall: post-process the assembled assistant {@link Message} before\n * tool dispatch (validation, content rewriting, …).\n * @param agent - the agent that received the step\'s response.\n * @param turn - the open turn number.\n * @param step - the step that produced the message.\n * @param message - the assistant message as assembled from the stream.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode waterfall\n */', summary: 'Waterfall: post-process the assembled assistant Message before tool dispatch (validation, content rewriting, …).', }, { name: 'agent/turn-continuation', mode: 'waterfall', signature: '\'agent/turn-continuation\'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise', + jsDoc: '/**\n * Override whether the turn continues. The default continues after tool\n * calls or steering and stops otherwise; a continue reason becomes steering.\n * @param agent - the agent deciding whether to run another step.\n * @param turn - the turn being continued or stopped.\n * @param defaultDecision - what the loop would do absent an override.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode waterfall\n */', summary: 'Override whether the turn continues.', }, { name: 'agent/turn-stop', mode: 'serial', signature: '\'agent/turn-stop\'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined', + jsDoc: '/**\n * Monotonic terminal-stop checkpoint after continuation and steering are\n * folded; a stop remains authoritative through turn close and flush:\n * steering queued in that window is discarded, while ordinary sends survive.\n * @param agent - the agent whose composed continuation outcome may be stopped.\n * @param turn - the turn at its terminal-stop checkpoint.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @mode serial\n */', summary: 'Monotonic terminal-stop checkpoint after continuation and steering are folded; a stop remains authoritative through turn close and flush: steering queued in that window is discarded, while ordinary sends survive.', }, { name: 'approval/request', mode: 'waterfall', signature: '\'approval/request\'(this: Scoped, req: ApprovalRequest, next: () => Promise): Promise', + jsDoc: '/**\n * Ask composed answerers for one decision. Return an outcome to claim the\n * request or call `next()`; failure yields the fail-closed default.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.\n * @param req - the pending decision (agent, tool identity, reason, signal).\n * @mode waterfall\n */', summary: 'Ask composed answerers for one decision.', }, { name: 'fs/edit-intent', mode: 'waterfall', signature: '\'fs/edit-intent\'(target: FsTarget, actor: object | undefined, next: () => { version: FsVersion } | undefined | Promise<{ version: FsVersion } | undefined>): Promise<{ version: FsVersion } | undefined>', + jsDoc: '/**\n * Single-slot decision for the next {@link FileSystem.editText}. Calling\n * `next()` yields an unconditional edit; the first returned guard wins.\n * @param target - the resolved target about to be edited.\n * @param actor - the opaque tool-execution context the decider keys off.\n * @mode waterfall\n */', summary: 'Single-slot decision for the next FileSystem.editText.', }, { name: 'fs/observed', mode: 'emit', signature: '\'fs/observed\'(target: FsTarget, version: FsVersion, actor: object | undefined): void', + jsDoc: '/**\n * Record a successful observation. Listeners must be synchronous recorders:\n * throws fail the tool call and returned promises are not awaited.\n * @param target - the target that was read/written/edited.\n * @param version - the version the actor now holds as its observation.\n * @param actor - the observing tool-execution context; undefined records nothing useful.\n * @mode emit\n */', summary: 'Record a successful observation.', }, { name: 'fs/write-intent', mode: 'waterfall', signature: '\'fs/write-intent\'(target: FsTarget, actor: object | undefined, next: () => FsWriteIntent | undefined | Promise): Promise', + jsDoc: '/**\n * Single-slot decision for the next {@link FileSystem.writeText}. Calling\n * `next()` yields the bare provider\'s unconditional write; the first listener\n * that returns an intent owns the decision rather than composing with peers.\n * @param target - the resolved target about to be written.\n * @param actor - the opaque tool-execution context the decider keys off.\n * @mode waterfall\n */', summary: 'Single-slot decision for the next FileSystem.writeText.', }, { name: 'llm/stream', mode: 'waterfall', signature: '\'llm/stream\'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable): AsyncIterable', + jsDoc: '/**\n * Waterfall around every streaming model call (retry, replay, routing).\n * Bound to the {@link LlmService}; call `next()` to reach the resolved\n * adapter\'s stream, or yield your own chunks to short-circuit.\n * @param options - the full request. A LOOP-built request arrives\n * deep-frozen (mutation throws): its content is a pure function of the\n * session log (the reconstructability RFC), so listeners read it, never\n * rewrite it. A hand-built one-shot (compaction summarize) is the\n * caller\'s own object and stays mutable here.\n * @mode waterfall\n */', summary: 'Waterfall around every streaming model call (retry, replay, routing).', }, { name: 'session/created', mode: 'emit', signature: '\'session/created\'(this: Scoped, session: Session): void', + jsDoc: '/**\n * Creation announcement during session publication. A synchronous throw vetoes and rolls\n * back with a paired disposal; detach requested during dispatch is deferred.\n * A returned-promise rejection is logged but cannot retroactively veto this\n * synchronous boundary.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners\n * receive only sessions entered through that agent\'s context.\n * @param session - the session just entered and announced.\n * @dshScopeScan unsupported\n * @mode emit\n */', summary: 'Creation announcement during session publication.', }, { name: 'session/disposed', mode: 'emit', signature: '\'session/disposed\'(this: Scoped, session: Session): void', + jsDoc: '/**\n * Emitted once when an announced session leaves the store, including\n * publication rollback, but never for an entry whose creation announcement\n * did not begin. Listener failures are logged and contained.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope.\n * @param session - the session that is no longer live in the store.\n * @dshScopeScan unsupported\n * @mode emit\n */', summary: 'Emitted once when an announced session leaves the store, including publication rollback, but never for an entry whose creation announcement did not begin.', }, { name: 'session/event', mode: 'emit', signature: '\'session/event\'(this: Scoped, session: Session, event: SessionEvent): void', + jsDoc: '/**\n * Post-commit, fire-and-forget append feed. The listener snapshot resolves\n * before the log push, but callbacks run after it; observer failures are\n * logged and contained without making the committed append fail.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners\n * receive only events from sessions entered through that agent\'s context.\n * @param session - the session whose log grew.\n * @param event - the appended event, exactly as recorded.\n * @dshScopeScan unsupported\n * @mode emit\n */', summary: 'Post-commit, fire-and-forget append feed.', }, { name: 'session/flush', mode: 'parallel', signature: '\'session/flush\'(this: Scoped, session: Session): Promise | void', + jsDoc: '/**\n * Awaited parallel durability checkpoint: every listener runs and the\n * caller awaits all of them, with no waterfall veto. Dispatch through\n * {@link SessionStore.flush}. Scope-filtered dispatch\n * (`@deepseek-ai/dsh-scope`) reuses the session\'s owner scope.\n * @param session - the session whose buffered events must reach durable storage.\n * @dshScopeScan unsupported\n * @mode parallel\n */', summary: 'Awaited parallel durability checkpoint: every listener runs and the caller awaits all of them, with no waterfall veto.', }, { name: 'subagent/end', mode: 'emit', signature: '\'subagent/end\'(this: Scoped, info: SubagentRunEndInfo): void', + jsDoc: '/**\n * A ready child settled. Scope-filtered dispatch uses the same delegating\n * parent carrier as `subagent/start`, so the lifecycle pair reaches the\n * same scoped audience.\n * @param info - the run identity and terminal outcome.\n * @dshScopeScan unsupported\n * @mode emit\n */', summary: 'A ready child settled.', }, { name: 'subagent/provider-added', mode: 'emit', signature: '\'subagent/provider-added\'(provider: SubagentProvider): void', + jsDoc: '/**\n * A provider became resolvable in the registry.\n * @param provider - the registered provider.\n * @mode emit\n */', summary: 'A provider became resolvable in the registry.', }, { name: 'subagent/provider-removed', mode: 'emit', signature: '\'subagent/provider-removed\'(name: string): void', + jsDoc: '/**\n * A provider left the registry. Accepted runs remain holder-owned.\n * @param name - the provider name that no longer resolves.\n * @mode emit\n */', summary: 'A provider left the registry.', }, { name: 'subagent/start', mode: 'emit', signature: '\'subagent/start\'(this: Scoped, info: SubagentRunInfo): void', + jsDoc: '/**\n * A provider established a ready child. For in-process providers,\n * `ctx.agents.get(info.id)` resolves during this notification.\n * Scope-filtered dispatch keys the carrier by the delegating parent, so a\n * parent-scoped listener observes only its own delegations. Paired with\n * `subagent/end`.\n * @param info - the provider and ready child identity.\n * @dshScopeScan unsupported\n * @mode emit\n */', summary: 'A provider established a ready child.', }, { name: 'system-prompt/assemble', mode: 'waterfall', signature: '\'system-prompt/assemble\'(this: Scoped, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise', + jsDoc: '/**\n * Expert waterfall over the assembled sections, tools, and variables.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners\n * receive only that scope\'s assemblies. The returned value is authoritative.\n * @param assembly - the mutable assembly built from registered providers.\n * @param context - the caller\'s per-assembly context.\n * @mode waterfall\n */', summary: 'Expert waterfall over the assembled sections, tools, and variables.', }, { name: 'system-prompt/change', mode: 'emit', signature: '\'system-prompt/change\'(): void', + jsDoc: '/**\n * Emitted when any prompt provider changes. This registry notification is\n * unfiltered because a global change affects every scope.\n * @mode emit\n */', summary: 'Emitted when any prompt provider changes.', }, { name: 'tools/change', mode: 'emit', signature: '\'tools/change\'(): void', + jsDoc: '/**\n * A tool was registered or unregistered, or a scoped restriction changed\n * (the available tool set changed — possibly for one scope only). An\n * UNFILTERED registry-subject notification, deliberately not scope-filtered\n * dispatch: a global change concerns every agent\'s next assembly, so a\n * scoped listener subscribing here sees every change, not just its own\n * scope\'s.\n * @mode emit\n */', summary: 'A tool was registered or unregistered, or a scoped restriction changed (the available tool set changed — possibly for one scope only).', }, { name: 'tools/execute', mode: 'waterfall', signature: '\'tools/execute\'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise', + jsDoc: '/**\n * Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns\n * a normalized result; wrappers may change only `exec.signal`, while call\n * identity remains immutable.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent\'s calls.\n * @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal).\n * @mode waterfall\n */', summary: 'Around-dispatch waterfall for timeout, retry, or metrics.', }, { name: 'tools/post-execute', mode: 'waterfall', signature: '\'tools/post-execute\'(this: Scoped, exec: ToolExecution, result: Readonly, next: () => Promise): Promise', + jsDoc: '/**\n * Accept, replace, enrich, or block a normalized dispatch result. `next()`\n * accepts it unchanged; thrown tools still reach this seam as errors.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent\'s calls.\n * @param exec - the call that just ran (name, parsed arguments, caller agent).\n * @param result - the dispatch outcome a listener may accept, replace, or block.\n * @mode waterfall\n */', summary: 'Accept, replace, enrich, or block a normalized dispatch result.', }, { name: 'tools/pre-execute', mode: 'waterfall', signature: '\'tools/pre-execute\'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise', + jsDoc: '/**\n * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing\n * approval support turns `ask` into denial.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent\'s calls.\n * @param exec - the pending call (name, parsed arguments, caller agent).\n * @mode waterfall\n */', summary: 'Allow, deny, or ask before dispatch.', }, { name: 'tools/result', mode: 'emit', signature: '\'tools/result\'(this: Scoped, exec: Readonly, result: Readonly): undefined', + jsDoc: '/**\n * Observe the frozen, lossless-JSON final outcome. Listener failures are contained.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): keyed by `exec.agent`.\n * @param exec - the execution object that traversed the pipeline.\n * @param result - a deep-frozen snapshot of the final returned result.\n * @mode emit\n */', summary: 'Observe the frozen, lossless-JSON final outcome.', }, { name: 'workflow/agent-end', mode: 'emit', signature: '\'workflow/agent-end\'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): void', + jsDoc: '/**\n * One `agent()` call settled (clean result, child failure, or run\n * cancellation). Paired with {@link Events[\'workflow/agent-start\']} by\n * `agent.seq`, exactly once per started call on every stop path — on an\n * engine termination path (a worker killed past its grace) the end is\n * engine-synthesized with outcome `\'cancelled\'`.\n * @param info - the run\'s identity snapshot.\n * @param agent - the call identity plus its outcome.\n * @mode emit\n */', summary: 'One `agent()` call settled (clean result, child failure, or run cancellation).', }, { name: 'workflow/agent-start', mode: 'emit', signature: '\'workflow/agent-start\'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void', + jsDoc: '/**\n * One `agent()` call established a ready child run. Paired with\n * {@link Events[\'workflow/agent-end\']} by `agent.seq`. A call that never\n * receives a ready run from the provider emits neither\n * event in this pair.\n * @param info - the run\'s identity snapshot.\n * @param agent - the call\'s sequence number, label, phase, and child id.\n * @mode emit\n */', summary: 'One `agent()` call established a ready child run.', }, { name: 'workflow/end', mode: 'emit', signature: '\'workflow/end\'(info: WorkflowRunInfo, result: WorkflowResultInfo): void', + jsDoc: '/**\n * A workflow run settled (any stop reason). Fired when\n * {@link WorkflowRun.result} resolves. Paired with\n * {@link Events[\'workflow/start\']}.\n * @param info - the run\'s identity snapshot.\n * @param result - the outcome data (stop reason, error, agent count) —\n * deliberately WITHOUT the result value (see {@link WorkflowResultInfo}).\n * @mode emit\n */', summary: 'A workflow run settled (any stop reason).', }, { name: 'workflow/log', mode: 'emit', signature: '\'workflow/log\'(info: WorkflowRunInfo, message: string): void', + jsDoc: '/**\n * The script emitted a narration line (a `log(message)` call).\n * @param info - the run\'s identity snapshot.\n * @param message - the logged message, verbatim.\n * @mode emit\n */', summary: 'The script emitted a narration line (a `log(message)` call).', }, { name: 'workflow/phase', mode: 'emit', signature: '\'workflow/phase\'(info: WorkflowRunInfo, title: string): void', + jsDoc: '/**\n * The script entered a phase (a `phase(title)` call) — progress grouping\n * for observers; no execution semantics.\n * @param info - the run\'s identity snapshot.\n * @param title - the phase title, verbatim.\n * @mode emit\n */', summary: 'The script entered a phase (a `phase(title)` call) — progress grouping for observers; no execution semantics.', }, { name: 'workflow/start', mode: 'emit', signature: '\'workflow/start\'(info: WorkflowRunInfo): void', + jsDoc: '/**\n * A workflow run started — the script\'s meta block validated, the body\n * about to execute. Paired with {@link Events[\'workflow/end\']}.\n * @param info - the run\'s identity snapshot (id + meta).\n * @mode emit\n */', summary: 'A workflow run started — the script\'s meta block validated, the body about to execute.', }, ] diff --git a/packages/cordis/tool-cordis/src/index.ts b/packages/cordis/tool-cordis/src/index.ts index 321546c8c3..fd15d75624 100644 --- a/packages/cordis/tool-cordis/src/index.ts +++ b/packages/cordis/tool-cordis/src/index.ts @@ -12,9 +12,9 @@ import z from 'schemastery' import { defineTool } from '@deepseek-ai/dsh-tools' import { STATE_LABELS } from './fiber-state.ts' import { isPlugin, pluginName } from './guard.ts' +import { EVENT_API, INHERITED_CTX_API, SERVICE_API, TYPE_API } from './api-catalog.ts' import { describeApi, describeDynamic, describeEvents, describePlugins, describeServices, describeTools } from './inspect.ts' -import { missingServices, mountDynamic } from './mount.ts' -import type { DynamicMount } from './mount.ts' +import { missingServices, mountDynamic, type DynamicMount } from './mount.ts' import { presentInspectCall, presentMountCall, presentUnmountCall } from './present.ts' import { createSandbox, evaluateMountCode } from './sandbox.ts' @@ -63,15 +63,23 @@ export function apply(ctx: Context, config: Config): void { + '`dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), ' + '`api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), ' + '`events` (every harness event with its dispatch mode and exact signature — pick listener targets here). ' - + 'Omit `what` to get all six sections.', + + 'Omit `what` to get all six sections. With `what:"api"` or `what:"events"`, pass an exact `name` ' + + 'to narrow to one service/event and include its original source JSDoc.', parameters: { what: { type: 'string', enum: ['services', 'plugins', 'tools', 'dynamic', 'api', 'events'], description: 'Limit the report to one section. Omit for all sections.', }, + name: { + type: 'string', + description: 'Exact service key or event name whose original JSDoc to include; valid only with what:"api" or what:"events".', + }, }, execute(args, exec): Promise<{ type: 'text'; text: string }[]> { + if (args.name !== undefined && args.what !== 'api' && args.what !== 'events') { + throw new Error('name is valid only with what:"api" or what:"events"') + } const sections: [heading: string, body: () => string[]][] = [ ['services', () => describeServices(ctx)], ['plugins', () => describePlugins(ctx)], @@ -79,8 +87,8 @@ export function apply(ctx: Context, config: Config): void { // globals absent — "what you can call", not the global registry. ['tools', () => describeTools(ctx, exec.agent)], ['dynamic', () => describeDynamic(ctx, mounts)], - ['api', () => describeApi(ctx)], - ['events', () => describeEvents()], + ['api', () => describeApi(ctx, SERVICE_API, INHERITED_CTX_API, TYPE_API, args.name)], + ['events', () => describeEvents(EVENT_API, args.name)], ] const selected = sections.filter(([heading]) => args.what === undefined || args.what === heading) const text = selected diff --git a/packages/cordis/tool-cordis/src/inspect.ts b/packages/cordis/tool-cordis/src/inspect.ts index b483b13712..7196f370ce 100644 --- a/packages/cordis/tool-cordis/src/inspect.ts +++ b/packages/cordis/tool-cordis/src/inspect.ts @@ -1,7 +1,8 @@ /** * Read-only renderers over the live runtime for `cordis_inspect`: the service list, the flat * plugin list, the registered tools, the dynamic-mount table (with per-mount provides/waits), - * and the catalog-backed `api` / `events` sections. + * and the catalog-backed `api` / `events` sections. Exact-name lookups add the + * original source JSDoc without inflating the default reports. * @module @deepseek-ai/dsh-tool-cordis/inspect */ @@ -126,6 +127,18 @@ function typeClosure(seeds: string[], types: readonly TypeApiEntry[]): TypeApiEn return [...included.values()].sort((a, b) => a.name.localeCompare(b.name)) } +/** Render one catalogued service, optionally including source-owned method JSDoc. */ +function serviceLines(entry: ServiceApiEntry, detailed: boolean): string[] { + const lines = [`- ${entry.key} — ${entry.summary}`] + for (const method of entry.methods) { + if (detailed) { + for (const docLine of method.jsDoc.split('\n')) lines.push(` ${docLine}`) + } + lines.push(` ${method.signature}`) + } + return lines +} + /** * Render the generated catalog against the live runtime: live catalogued services with methods, * uncatalogued live services with owners, absent loadable services, referenced type shapes, and @@ -134,6 +147,7 @@ function typeClosure(seeds: string[], types: readonly TypeApiEntry[]): TypeApiEn * @param api - generated service entries, replaceable in tests. * @param inherited - inherited `ctx` entries, replaceable in tests. * @param types - public type shapes, replaceable in tests. + * @param name - exact live service key whose methods should include original JSDoc; omitted for the compact catalog. * @returns the section lines. */ export function describeApi( @@ -141,25 +155,33 @@ export function describeApi( api: readonly ServiceApiEntry[] = SERVICE_API, inherited: readonly InheritedApiEntry[] = INHERITED_CTX_API, types: readonly TypeApiEntry[] = TYPE_API, + name?: string, ): string[] { const live = new Map() for (const impl of liveImpls(ctx)) live.set(impl.name, impl.fiber.name) const lines: string[] = [] const liveMethodTexts: string[] = [] - for (const entry of api) { - if (!live.has(entry.key)) continue - lines.push(`- ${entry.key} — ${entry.summary}`) + let selected = api.filter(entry => live.has(entry.key)) + if (name !== undefined) { + const entry = api.find(candidate => candidate.key === name) + if (!entry) throw new Error(`no catalogued service named "${name}"`) + if (!live.has(name)) throw new Error(`catalogued service "${name}" is not running`) + selected = [entry] + } + for (const entry of selected) { + lines.push(...serviceLines(entry, name !== undefined)) for (const method of entry.methods) { - lines.push(` ${method}`) - liveMethodTexts.push(method) + liveMethodTexts.push(method.signature) } } - const catalogued = new Set(api.map(entry => entry.key)) - for (const [name, fiber] of [...live].sort(([a], [b]) => a.localeCompare(b))) { - if (!catalogued.has(name)) lines.push(`- ${name} (provided by ${fiber}, no catalog entry)`) + if (name === undefined) { + const catalogued = new Set(api.map(entry => entry.key)) + for (const [liveName, fiber] of [...live].sort(([a], [b]) => a.localeCompare(b))) { + if (!catalogued.has(liveName)) lines.push(`- ${liveName} (provided by ${fiber}, no catalog entry)`) + } + const notRunning = api.filter(entry => !live.has(entry.key)).map(entry => entry.key) + if (notRunning.length > 0) lines.push(`not running (loadable services with no live provider): ${notRunning.join(', ')}`) } - const notRunning = api.filter(entry => !live.has(entry.key)).map(entry => entry.key) - if (notRunning.length > 0) lines.push(`not running (loadable services with no live provider): ${notRunning.join(', ')}`) const shapes = typeClosure(liveMethodTexts, types) if (shapes.length > 0) { lines.push('type shapes (referenced by the signatures above — read these before assuming a field is a string):') @@ -167,8 +189,10 @@ export function describeApi( for (const declLine of shape.declaration.split('\n')) lines.push(` ${declLine}`) } } - lines.push('inherited ctx API:') - for (const entry of inherited) lines.push(`- ${entry.name} — ${entry.summary}`) + if (name === undefined) { + lines.push('inherited ctx API:') + for (const entry of inherited) lines.push(`- ${entry.name} — ${entry.summary}`) + } return lines } @@ -176,13 +200,24 @@ export function describeApi( * The `events` section: every harness event with its dispatch mode, one-line * summary, and exact signature, closed by the waterfall caution. * @param events - the event catalog (the generated one by default; injectable for tests). + * @param name - exact event name whose signature should include original JSDoc; omitted for the compact catalog. * @returns the section lines. */ -export function describeEvents(events: readonly EventApiEntry[] = EVENT_API): string[] { - const lines = events.flatMap(event => [ - `- ${event.name} [${event.mode}] — ${event.summary}`, - ` ${event.signature}`, - ]) +export function describeEvents(events: readonly EventApiEntry[] = EVENT_API, name?: string): string[] { + let selected = events + if (name !== undefined) { + const event = events.find(candidate => candidate.name === name) + if (!event) throw new Error(`no catalogued event named "${name}"`) + selected = [event] + } + const lines = selected.flatMap((event) => { + const entry = [`- ${event.name} [${event.mode}] — ${event.summary}`] + if (name !== undefined) { + for (const docLine of event.jsDoc.split('\n')) entry.push(` ${docLine}`) + } + entry.push(` ${event.signature}`) + return entry + }) lines.push('waterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() vetoes the chain.') return lines } diff --git a/packages/cordis/tool-cordis/src/present.ts b/packages/cordis/tool-cordis/src/present.ts index 614b070193..e13570cf43 100644 --- a/packages/cordis/tool-cordis/src/present.ts +++ b/packages/cordis/tool-cordis/src/present.ts @@ -15,11 +15,12 @@ import type { GenericCallView } from '@deepseek-ai/dsh-tools' * @param args - the validated call arguments. * @returns the generic card the ACP bridge renders. */ -export function presentInspectCall(args: { what?: string }): GenericCallView { +export function presentInspectCall(args: { what?: string; name?: string }): GenericCallView { + const target = args.name === undefined ? args.what : `${args.what}: ${args.name}` return { card: 'generic', kind: 'read', - title: args.what === undefined ? 'Inspect cordis runtime' : `Inspect cordis runtime: ${args.what}`, + title: target === undefined ? 'Inspect cordis runtime' : `Inspect cordis runtime: ${target}`, } } diff --git a/packages/cordis/tool-cordis/tests/inspect.spec.ts b/packages/cordis/tool-cordis/tests/inspect.spec.ts index 1a8c39467a..4d986d4f3e 100644 --- a/packages/cordis/tool-cordis/tests/inspect.spec.ts +++ b/packages/cordis/tool-cordis/tests/inspect.spec.ts @@ -64,6 +64,24 @@ describe('cordis_inspect', () => { // The inherited ctx surface closes the section. expect(report).toContain('inherited ctx API:') expect(report).toContain('- ctx.effect — ') + // The broad report stays compact; exact-name lookup owns full JSDoc. + expect(report).not.toContain('/**') + expect(report).not.toContain('@param definition') + }) + + it('adds original method JSDoc only for an exact live api name', async () => { + const ctx = await setup() + const report = text(await call(ctx, 'cordis_inspect', { what: 'api', name: 'tools' })) + expect(report).toContain('## api') + expect(report).toContain('- tools — Tool registry and execution pipeline.') + expect(report).toContain('/**') + expect(report).toContain('Register globally or in the calling agent scope.') + expect(report).toContain('@param definition - the tool schema') + expect(report).toContain('@returns the exact disposer') + expect(report).toContain('register(definition: ToolDefinition)') + expect(report).toContain('type shapes (referenced by the signatures above') + expect(report).not.toContain('not running (loadable services') + expect(report).not.toContain('inherited ctx API:') }) it('renders the events section with mode badges, signatures, and the waterfall caution', async () => { @@ -73,6 +91,39 @@ describe('cordis_inspect', () => { expect(report).toContain('- tools/pre-execute [waterfall]') expect(report).toMatch(/'agent\/status'\(/) expect(report).toContain('returning without next() vetoes the chain') + expect(report).not.toContain('/**') + expect(report).not.toContain('@mode waterfall') + }) + + it('adds original event JSDoc only for an exact event name', async () => { + const ctx = await setup() + const report = text(await call(ctx, 'cordis_inspect', { what: 'events', name: 'tools/pre-execute' })) + expect(report).toContain('## events') + expect(report).toContain('- tools/pre-execute [waterfall]') + expect(report).toContain('/**') + expect(report).toContain('Allow, deny, or ask before dispatch.') + expect(report).toContain('@param exec - the pending call') + expect(report).toContain('@mode waterfall') + expect(report).not.toContain('- tools/change [emit]') + }) + + it('fails loud for incompatible, unknown, and non-running names', async () => { + const ctx = await setup() + const incompatible = await call(ctx, 'cordis_inspect', { what: 'tools', name: 'tools' }) + expect(incompatible.isError).toBe(true) + expect(text(incompatible)).toContain('name is valid only with what:"api" or what:"events"') + + const unknownService = await call(ctx, 'cordis_inspect', { what: 'api', name: 'not-a-service' }) + expect(unknownService.isError).toBe(true) + expect(text(unknownService)).toContain('no catalogued service named "not-a-service"') + + const nonRunning = await call(ctx, 'cordis_inspect', { what: 'api', name: 'bash' }) + expect(nonRunning.isError).toBe(true) + expect(text(nonRunning)).toContain('catalogued service "bash" is not running') + + const unknownEvent = await call(ctx, 'cordis_inspect', { what: 'events', name: 'not/an-event' }) + expect(unknownEvent.isError).toBe(true) + expect(text(unknownEvent)).toContain('no catalogued event named "not/an-event"') }) }) @@ -102,7 +153,11 @@ describe('inspect renderers (direct)', () => { it('describeApi omits the not-running line and type shapes when nothing applies', async () => { const ctx = await setup() - const lines = describeApi(ctx, [{ key: 'tools', summary: 'The registry.', methods: ['register(x): void'] }], [], []) + const lines = describeApi(ctx, [{ + key: 'tools', + summary: 'The registry.', + methods: [{ signature: 'register(x): void', jsDoc: '/** Register x. */' }], + }], [], []) expect(lines[0]).toBe('- tools — The registry.') expect(lines[1]).toBe(' register(x): void') expect(lines.join('\n')).not.toContain('not running') diff --git a/packages/cordis/tool-cordis/tests/present.spec.ts b/packages/cordis/tool-cordis/tests/present.spec.ts index d8f380439f..ed45fd1518 100644 --- a/packages/cordis/tool-cordis/tests/present.spec.ts +++ b/packages/cordis/tool-cordis/tests/present.spec.ts @@ -11,6 +11,11 @@ describe('presenters', () => { it('cordis_inspect renders a generic read card titled with the section', () => { expect(presentInspectCall({})).toEqual({ card: 'generic', kind: 'read', title: 'Inspect cordis runtime' }) expect(presentInspectCall({ what: 'api' })).toEqual({ card: 'generic', kind: 'read', title: 'Inspect cordis runtime: api' }) + expect(presentInspectCall({ what: 'events', name: 'tools/change' })).toEqual({ + card: 'generic', + kind: 'read', + title: 'Inspect cordis runtime: events: tools/change', + }) }) it('cordis_mount renders a generic execute card carrying the code as raw input', () => { @@ -33,6 +38,9 @@ describe('presenters', () => { kind: 'read', title: 'Inspect cordis runtime: tools', }) + expect(ctx.tools.get('cordis_inspect')!.presentCall!({ what: 'api', name: 'tools' })).toMatchObject({ + title: 'Inspect cordis runtime: api: tools', + }) expect(ctx.tools.get('cordis_mount')!.presentCall!({ code: 'return 1' })).toMatchObject({ kind: 'execute' }) expect(ctx.tools.get('cordis_unmount')!.presentCall!({ id: 'dyn-2' })).toMatchObject({ title: 'Unmount dyn-2' }) // Soft validation: presenter args that fail the schema render as no card, never a throw. diff --git a/packages/cordis/tool-cordis/tests/tool-cordis.spec.ts b/packages/cordis/tool-cordis/tests/tool-cordis.spec.ts index 8953b5da94..d305a92883 100644 --- a/packages/cordis/tool-cordis/tests/tool-cordis.spec.ts +++ b/packages/cordis/tool-cordis/tests/tool-cordis.spec.ts @@ -32,8 +32,9 @@ describe('tool registration', () => { const names = ctx.tools.schemas().map(schema => schema.name) expect(names).toEqual(expect.arrayContaining(['cordis_inspect', 'cordis_mount', 'cordis_unmount'])) const inspect = ctx.tools.schemas().find(schema => schema.name === 'cordis_inspect')! - const props = (inspect.parameters as { properties: Record }).properties + const props = (inspect.parameters as { properties: Record }).properties expect(props.what?.enum).toEqual(['services', 'plugins', 'tools', 'dynamic', 'api', 'events']) + expect(props.name?.type).toBe('string') }) }) diff --git a/scripts/gen-cordis-api.ts b/scripts/gen-cordis-api.ts index 5d8a70fba4..7c61b9395d 100644 --- a/scripts/gen-cordis-api.ts +++ b/scripts/gen-cordis-api.ts @@ -1,8 +1,9 @@ /** * Generate the model-facing Cordis API data module from the same event/service - * collector as the documentation catalogs. It emits first-sentence docs, raw - * signatures, transitive public type shapes, and inherited context entries, - * without source pointers; output is deterministic and `--check` verifies it. + * collector as the documentation catalogs. It emits original declaration + * JSDoc, first-sentence summaries, raw signatures, transitive public type + * shapes, and inherited context entries, without source pointers; output is + * deterministic and `--check` verifies it. */ import { globSync, readFileSync, writeFileSync } from 'node:fs' @@ -88,22 +89,30 @@ function render(): string { ' * `pnpm run verify-cordis-api` in doc-sync).', ' *', ' * The machine-readable cordis API catalog `cordis_inspect` serves to the', - ' * model: harness services (summary + public method signatures), harness', - ' * events (mode + signature), and the inherited `ctx` surface. Produced by', + ' * model: harness services (summary + public method signatures/JSDoc),', + ' * harness events (mode + signature/JSDoc), and the inherited `ctx` surface. Produced by', ' * the same AST walk as docs/cordis-catalog, so this data and the rendered', ' * docs cannot diverge.', ' *', ' * @module @deepseek-ai/dsh-tool-cordis/api-catalog', ' */', '', - '/** One harness `ctx.` service: its one-line summary and public method signatures. */', + '/** One public service method and its source-owned contract. */', + 'export interface ServiceApiMethod {', + ' /** Public method signature with its body stripped. */', + ' signature: string', + ' /** Original method JSDoc, with only container indentation removed. */', + ' jsDoc: string', + '}', + '', + '/** One harness `ctx.` service: its one-line summary and public methods. */', 'export interface ServiceApiEntry {', ' /** The `ctx.` name, e.g. `tools`. */', ' key: string', ' /** First sentence of the service class JSDoc. */', ' summary: string', - ' /** Public method signatures, bodies stripped, in source order. */', - ' methods: readonly string[]', + ' /** Public methods, bodies stripped, in source order. */', + ' methods: readonly ServiceApiMethod[]', '}', '', '/** One harness event: its dispatch mode, exact signature, and one-line summary. */', @@ -114,6 +123,8 @@ function render(): string { ' mode: string', ' /** The exact listener signature, whitespace-normalized. */', ' signature: string', + ' /** Original event JSDoc, with only container indentation removed. */', + ' jsDoc: string', ' /** First sentence of the event JSDoc. */', ' summary: string', '}', @@ -145,7 +156,12 @@ function render(): string { lines.push(' methods: [],') } else { lines.push(' methods: [') - for (const method of service.methods) lines.push(` ${quote(method.signature)},`) + for (const method of service.methods) { + lines.push(' {') + lines.push(` signature: ${quote(method.signature)},`) + lines.push(` jsDoc: ${quote(method.jsDoc)},`) + lines.push(' },') + } lines.push(' ],') } lines.push(' },') @@ -161,6 +177,7 @@ function render(): string { lines.push(` name: ${quote(event.name)},`) lines.push(` mode: ${quote(event.mode)},`) lines.push(` signature: ${quote(event.signature)},`) + lines.push(` jsDoc: ${quote(event.jsDoc)},`) lines.push(` summary: ${quote(firstSentence(event.doc))},`) lines.push(' },') } From ba693f0355f378b289e536436f774aa914cbd721 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:30:39 +0800 Subject: [PATCH 242/323] fix(cli-demo): forward the complete spine config Align the one-shot app with the shared agent-spine contract that landed on master after this branch began. Expose maxParallelToolCalls, dshHome, toolBash, and toolTasks through the Loader schema and route them with pickSpineConfig(). This restores deployment control over tool-call concurrency, the shared Harness home, background bash, and task_output wait bounds instead of silently retaining owner defaults. Exercise all four fields through the composed runtime, document the package-level contract, and regenerate the config catalog from the owning interface. --- docs/config-catalog.md | 8 ++++ packages/examples/cli-demo/README.md | 4 ++ packages/examples/cli-demo/src/index.ts | 27 +++++++---- .../examples/cli-demo/tests/cli-demo.spec.ts | 48 +++++++++++++++++-- 4 files changed, 76 insertions(+), 11 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index fb099937e8..ed8597832a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -215,16 +215,24 @@ export interface Config { provider: string /** Model name for the configured agent; a matching adapter must be registered. */ model: string + /** Bundled agent-loop concurrency cap; `1` is serial and omission uses its default. */ + maxParallelToolCalls?: number /** Deployment persona forwarded to the system-prompt plugin. */ persona?: string /** Explicit model-facing tool order forwarded to the system-prompt plugin. */ toolOrder?: string[] /** Tool-registry presentation config forwarded through agent-spine-demo. */ tools?: ToolsConfig + /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */ + dshHome?: string /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string /** Skill registry, local-provider, and model-facing consumer config. */ skills?: agentCore.SkillConfig + /** Model-facing bash tool config forwarded through agent-spine-demo. */ + toolBash?: NonNullable + /** Generic background-task control-tool config forwarded through agent-spine-demo. */ + toolTasks?: NonNullable /** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */ workspaceContext: agentCore.Config['workspaceContext'] } diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md index 5197e3bcd0..c938f6c583 100644 --- a/packages/examples/cli-demo/README.md +++ b/packages/examples/cli-demo/README.md @@ -10,10 +10,14 @@ The package mounts no console logger, readline UI, user-interaction service, or |---|---|---| | `provider` | required | the configured agent's provider route | | `model` | required | the configured agent's model | +| `maxParallelToolCalls` | agent-loop default | positive-integer concurrent tool-call cap; `1` is serial | | `persona` | — | the deployment persona in `dsh-system-prompt` | | `toolOrder` | lexicographic | explicit model-facing tool order in `dsh-system-prompt` | | `tools` | `{ mode: 'native' }` | tool-registry presentation config through `dsh-agent-spine-demo` | +| `dshHome` | `$DSH_HOME` or `~/.dsh` | Harness home exposed to model bash and used by local skill discovery | | `skills` | owner defaults | skill registry, local provider, and model-facing skill tool | +| `toolBash` | owner defaults | model-facing bash config, including this producer's background opt-in | +| `toolTasks` | owner defaults | generic `task_output` wait bounds | | `persistenceRoot` | `./.sessions` | JSONL session root | | `workspaceContext` | required | workspace-instruction byte budget, or `false` to disable loading | diff --git a/packages/examples/cli-demo/src/index.ts b/packages/examples/cli-demo/src/index.ts index e58bcdad06..1308209681 100644 --- a/packages/examples/cli-demo/src/index.ts +++ b/packages/examples/cli-demo/src/index.ts @@ -24,31 +24,47 @@ export interface Config { provider: string /** Model name for the configured agent; a matching adapter must be registered. */ model: string + /** Bundled agent-loop concurrency cap; `1` is serial and omission uses its default. */ + maxParallelToolCalls?: number /** Deployment persona forwarded to the system-prompt plugin. */ persona?: string /** Explicit model-facing tool order forwarded to the system-prompt plugin. */ toolOrder?: string[] /** Tool-registry presentation config forwarded through agent-spine-demo. */ tools?: ToolsConfig + /** DeepSeek Harness home directory exposed to bash and used for local skill discovery. */ + dshHome?: string /** Directory the JSONL session backend writes under. Defaults to `./.sessions`. */ persistenceRoot?: string /** Skill registry, local-provider, and model-facing consumer config. */ skills?: agentCore.SkillConfig + /** Model-facing bash tool config forwarded through agent-spine-demo. */ + toolBash?: NonNullable + /** Generic background-task control-tool config forwarded through agent-spine-demo. */ + toolTasks?: NonNullable /** Controls automatic AGENTS.md/CLAUDE.md loading; configure a byte budget or set `false`. */ workspaceContext: agentCore.Config['workspaceContext'] } +// Each front door keeps a complete Loader schema so its deployment contract is +// readable without a cross-package config facade. +/* jscpd:ignore-start */ export const Config: z = z.object({ provider: z.string().required(), model: z.string().required(), + maxParallelToolCalls: z.number().step(1).min(1), persistenceRoot: z.string().default(DEFAULT_PERSISTENCE_ROOT), persona: z.string(), + dshHome: z.string(), skills: agentCore.SkillConfigSchema, // Absent means lexicographic order; schemastery's native array default is []. toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, + toolBash: agentCore.ToolBashConfigSchema, + toolTasks: agentCore.ToolTasksConfigSchema, workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(), }) +/* jscpd:ignore-end */ /** * Compose the UI-less spine, a fresh top-level agent rooted at the process cwd, @@ -58,14 +74,9 @@ export const Config: z = z.object({ * @param config - validated app configuration. */ export function apply(ctx: Context, config: Config): void { - const spineConfig: agentCore.Config = { + ctx.plugin(agentCore, { + ...agentCore.pickSpineConfig(config), agents: [{ id: SessionId('main'), provider: config.provider, model: config.model, cwd: process.cwd() }], - workspaceContext: config.workspaceContext, - } - if (config.persona !== undefined) spineConfig.persona = config.persona - if (config.toolOrder !== undefined) spineConfig.toolOrder = config.toolOrder - if (config.tools !== undefined) spineConfig.tools = config.tools - if (config.skills !== undefined) spineConfig.skills = config.skills - ctx.plugin(agentCore, spineConfig) + }) ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? DEFAULT_PERSISTENCE_ROOT }) } diff --git a/packages/examples/cli-demo/tests/cli-demo.spec.ts b/packages/examples/cli-demo/tests/cli-demo.spec.ts index 52433abe81..343d6184d7 100644 --- a/packages/examples/cli-demo/tests/cli-demo.spec.ts +++ b/packages/examples/cli-demo/tests/cli-demo.spec.ts @@ -4,9 +4,10 @@ import { join } from 'node:path' import { Context } from 'cordis' import Loader from '@cordisjs/plugin-loader' import { agentEvents, type Agent } from '@deepseek-ai/dsh-agent' -import type { Message } from '@deepseek-ai/dsh-llm' +import { CallId, type Message } from '@deepseek-ai/dsh-llm' import { TOOL_ORDER_REST } from '@deepseek-ai/dsh-system-prompt' -import { afterEach, describe, expect, it } from 'vitest' +import type { ToolExecution } from '@deepseek-ai/dsh-tools' +import { afterEach, describe, expect, it, vi } from 'vitest' import * as cliDemo from '../src/index.ts' const contexts: Context[] = [] @@ -19,8 +20,9 @@ async function skillConfig(catalogDescriptionMaxLength?: number): Promise { +async function mount(config: cliDemo.Config, withBash = false): Promise { const ctx = new Context() + if (withBash) ctx.provide('bash', { sandboxMode: undefined }) contexts.push(ctx) await ctx.plugin(cliDemo, config) await new Promise(resolve => setTimeout(resolve, 80)) @@ -104,6 +106,46 @@ describe('dsh-cli-demo app composition', () => { ]) }) + it('forwards the complete shared spine configuration', async () => { + const dshHome = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-home-')) + const agentsHome = await mkdtemp(join(tmpdir(), 'dsh-cli-demo-agents-')) + const ctx = await mount({ + provider: 'mock', + model: 'mock', + maxParallelToolCalls: 3, + dshHome, + skills: { local: { agentsHome } }, + toolBash: { enableRunInBackground: false }, + toolTasks: { waitTimeoutMs: 7, maxWaitTimeoutMs: 11 }, + workspaceContext: false, + }, true) + + expect(ctx.get('agentLoop')?.config.maxParallelToolCalls).toBe(3) + const execution: ToolExecution = { + token: Symbol('cli-demo-dsh-home-test') as ToolExecution['token'], + callId: CallId('cli-demo-dsh-home'), + name: 'bash', + arguments: { command: 'true' }, + } + expect(ctx.bashEnv.collect(execution)).toMatchObject({ DSH_HOME: dshHome }) + const bash = ctx.tools.schemas().find(tool => tool.name === 'bash') + expect(Object.keys((bash!.parameters as { properties: Record }).properties)) + .not.toContain('run_in_background') + + const id = ctx.tasks.start({ + kind: 'bash', + label: 'config forwarding probe', + run: () => ({ cancel: () => {}, done: Promise.resolve({ status: 'completed' }) }), + }) + const wait = vi.spyOn(ctx.tasks, 'wait') + await ctx.tools.execute({ + callId: CallId('cli-demo-task-config'), + name: 'task_output', + arguments: { task_id: id, wait: true }, + }) + expect(wait).toHaveBeenCalledWith(id, 7, undefined, undefined) + }) + it('exposes the Loader-safe namespace plugin shape and schema', () => { expect(cliDemo.name).toBe('cli-demo') expect(cliDemo.Config).toBeDefined() From 1698f0baa6226a945bc1c459a2a320e389f2cec2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:31:33 +0800 Subject: [PATCH 243/323] fix(cli-demo): preserve disposal diagnostics Report context-disposal failure as an independent outcome even when argument, boot, task, or output handling has already produced a primary diagnostic. Keep the primary error first, append the cleanup error, and retain the nonzero exit status so operators can see both the initiating failure and the possibility that teardown or persistence did not complete. Add a regression that combines an invalid app composition with a failing disposer and asserts both ordered stderr lines. --- packages/examples/cli-demo/src/cli.ts | 5 +++-- packages/examples/cli-demo/tests/cli.spec.ts | 12 ++++++++++++ 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/packages/examples/cli-demo/src/cli.ts b/packages/examples/cli-demo/src/cli.ts index 63c08ae39f..3a8fecc7a8 100644 --- a/packages/examples/cli-demo/src/cli.ts +++ b/packages/examples/cli-demo/src/cli.ts @@ -361,7 +361,8 @@ export function formatTurnFailure(reason: TurnEndReason): string { /** * Execute one CLI invocation. Argument and boot failures never write stdout; - * every booted context is disposed before this promise resolves. + * context disposal is awaited before return, and its failure does not replace + * an earlier diagnostic. * @param args - arguments after the executable name. * @param runtime - optional injected process boundaries for tests and embedding. * @returns the ordinary process exit code; the thin bin overrides it for Unix signals. @@ -421,7 +422,7 @@ export async function executeCli(args: readonly string[], runtime: CliRuntime = try { await disposeContext(ctx) } catch (error: unknown) { - diagnostic ??= `${CLI_NAME}: dispose failed: ${toError(error).message}\n` + diagnostic = `${diagnostic ?? ''}${CLI_NAME}: dispose failed: ${toError(error).message}\n` exitCode = 1 } } diff --git a/packages/examples/cli-demo/tests/cli.spec.ts b/packages/examples/cli-demo/tests/cli.spec.ts index fcdf8a3004..8c41236829 100644 --- a/packages/examples/cli-demo/tests/cli.spec.ts +++ b/packages/examples/cli-demo/tests/cli.spec.ts @@ -398,6 +398,18 @@ describe('runOneShot and executeCli', () => { expect(disposalOutput.stderr).toContain('dispose exploded') }) + it('reports disposal failure alongside an earlier run failure', async () => { + const ctx = new Context() + liveContexts.push(ctx) + const output = await invoke(ctx, ['task'], { failDispose: true }) + expect(output).toEqual({ + code: 1, + stdout: '', + stderr: 'dsh-cli-demo: config must create exactly one top-level agent, found 0\n' + + 'dsh-cli-demo: dispose failed: dispose exploded\n', + }) + }) + it('cancels startup work and queued work before the correlated turn begins', async () => { const startup = await harness(['hang']) let started!: () => void From 306dd2b1fef2d1df141b6acf268ee4a0da3af598 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:32:41 +0800 Subject: [PATCH 244/323] fix(cli-demo): make failure rendering total Contain arbitrary plugin and runtime failures even when a thrown Proxy traps instanceof checks or its string coercion throws. Fall back to a stable diagnostic instead of letting executeCli reject outside its exit-code contract. Route abort reasons through the same total renderer so cancellation cannot escape containment through an exotic reason value. Add a focused regression that exercises both hostile inspection paths and verifies stdout remains empty, stderr remains labelled, and the CLI resolves with exit code 1. --- packages/examples/cli-demo/src/cli.ts | 19 ++++++++++++++++-- packages/examples/cli-demo/tests/cli.spec.ts | 21 ++++++++++++++++++++ 2 files changed, 38 insertions(+), 2 deletions(-) diff --git a/packages/examples/cli-demo/src/cli.ts b/packages/examples/cli-demo/src/cli.ts index 3a8fecc7a8..68c9598e6c 100644 --- a/packages/examples/cli-demo/src/cli.ts +++ b/packages/examples/cli-demo/src/cli.ts @@ -91,12 +91,27 @@ class CliInterruptedError extends Error { } } +/** Render an arbitrary value without trusting its type traps or string coercion. */ +function renderUnknown(value: unknown): string { + try { + return String(value) + } catch { + return '[unrenderable thrown value]' + } +} + +/** Normalize an arbitrary thrown value without letting inspection escape containment. */ function toError(error: unknown): Error { - return error instanceof Error ? error : new Error(String(error)) + try { + if (error instanceof Error) return error + } catch { + // A hostile proxy may throw during instanceof; use the total renderer below. + } + return new Error(renderUnknown(error)) } function interruptionReason(signal: AbortSignal): string { - return signal.reason === undefined ? 'interrupted' : String(signal.reason) + return signal.reason === undefined ? 'interrupted' : renderUnknown(signal.reason) } /** diff --git a/packages/examples/cli-demo/tests/cli.spec.ts b/packages/examples/cli-demo/tests/cli.spec.ts index 8c41236829..fe61a42304 100644 --- a/packages/examples/cli-demo/tests/cli.spec.ts +++ b/packages/examples/cli-demo/tests/cli.spec.ts @@ -199,6 +199,27 @@ describe('runOneShot and executeCli', () => { expect(stderr).toContain('boot exploded') }) + it('contains a thrown value whose inspection and coercion both fail', async () => { + const hostile = new Proxy({}, { + getPrototypeOf: () => { throw new Error('prototype trap escaped') }, + get: (target, key, receiver) => { + if (key === Symbol.toPrimitive) throw new Error('coercion escaped') + return Reflect.get(target, key, receiver) as unknown + }, + }) + let stdout = '' + let stderr = '' + const code = await executeCli(['task'], { + boot: async () => { throw hostile }, + loadEnv: () => {}, + writeStdout: (chunk) => { stdout += chunk }, + writeStderr: (chunk) => { stderr += chunk }, + }) + expect(code).toBe(1) + expect(stdout).toBe('') + expect(stderr).toBe('dsh-cli-demo: [unrenderable thrown value]\n') + }) + it('interrupts Loader boot and contains every late boot outcome', async () => { const abort = new AbortController() const lateContext = new Context() From 3956118c18badbacf0eec7e434e57a95c0335185 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 14:53:39 +0800 Subject: [PATCH 245/323] fix(dsbench): adapt evaluation config to master runtime --- docs/config-catalog.md | 2 +- examples/dsbench-coding-agent/cordis.yml | 3 --- examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts | 2 +- examples/package.json | 3 +++ packages/ui/jsonrpc/src/index.ts | 4 +++- pnpm-lock.yaml | 9 +++++++++ 6 files changed, 17 insertions(+), 6 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 5fe8ffe568..542728293c 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -159,7 +159,7 @@ export interface SkillConfig { Depends on: [`AgentLoopConfig`](#deepseek-aidsh-agent-loop) · [`SkillLocal`](../packages/skill/skill-local/src/index.ts) · [`SkillRegistryConfig`](#deepseek-aidsh-skill) · [`SystemPromptConfig`](#deepseek-aidsh-system-prompt) · [`toolBash`](../packages/bash/tool-bash/src/index.ts) · [`ToolsConfig`](#deepseek-aidsh-tools) · [`toolSkill`](../packages/skill/tool-skill/src/index.ts) · [`toolTasks`](../packages/tasks/tool-tasks/src/index.ts) · [`workspaceContext`](../packages/context/workspace-context/src/index.ts) -Source: [`packages/examples/agent-spine-demo/src/index.ts:57`](../packages/examples/agent-spine-demo/src/index.ts) +Source: [`packages/examples/agent-spine-demo/src/index.ts:59`](../packages/examples/agent-spine-demo/src/index.ts) ## `@deepseek-ai/dsh-bash-local` diff --git a/examples/dsbench-coding-agent/cordis.yml b/examples/dsbench-coding-agent/cordis.yml index 67e1604b07..4d970c8b47 100644 --- a/examples/dsbench-coding-agent/cordis.yml +++ b/examples/dsbench-coding-agent/cordis.yml @@ -11,9 +11,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash - - deepseek-v4-pro - id: bash name: '@deepseek-ai/dsh-bash-local' diff --git a/examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts b/examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts index 9bbc07a829..f5e2d7b938 100644 --- a/examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts +++ b/examples/dsbench-coding-agent/tests/keyless-smoke.e2e.ts @@ -97,7 +97,7 @@ describe('dsbench-coding-agent keyless smoke', () => { jsonrpc: '2.0', id: 1, method: 'initialize', - params: { cwd: root, model: 'deepseek-v4-pro' }, + params: { cwd: root, provider: 'deepseek', model: 'deepseek-v4-pro' }, })}\n`) const initialized = await waitForLine(lines, value => value.id === 1, () => stderr) expect(initialized).toMatchObject({ diff --git a/examples/package.json b/examples/package.json index 8d77731a05..01faf631ba 100644 --- a/examples/package.json +++ b/examples/package.json @@ -8,6 +8,7 @@ "@cordisjs/plugin-hmr": "workspace:*", "@cordisjs/plugin-include": "workspace:*", "@deepseek-ai/dsh-acp-demo": "workspace:*", + "@deepseek-ai/dsh-agent-spine-demo": "workspace:*", "@deepseek-ai/dsh-bash-local": "workspace:*", "@deepseek-ai/dsh-bash-sandbox": "workspace:*", "@deepseek-ai/dsh-code-runtime-worker": "workspace:*", @@ -16,12 +17,14 @@ "@deepseek-ai/dsh-fs-policy": "workspace:*", "@deepseek-ai/dsh-hooks-claude": "workspace:*", "@deepseek-ai/dsh-hooks-codex": "workspace:*", + "@deepseek-ai/dsh-jsonrpc": "workspace:*", "@deepseek-ai/dsh-llm": "workspace:*", "@deepseek-ai/dsh-llm-deepseek": "workspace:*", "@deepseek-ai/dsh-llm-replay": "workspace:*", "@deepseek-ai/dsh-permission": "workspace:*", "@deepseek-ai/dsh-repeat-tool-guard": "workspace:*", "@deepseek-ai/dsh-sandbox-local": "workspace:*", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:*", "@deepseek-ai/dsh-spill-local": "workspace:*", "@deepseek-ai/dsh-spill-policy": "workspace:*", "@deepseek-ai/dsh-stdio-demo": "workspace:*", diff --git a/packages/ui/jsonrpc/src/index.ts b/packages/ui/jsonrpc/src/index.ts index fe782c934f..099ef6008f 100644 --- a/packages/ui/jsonrpc/src/index.ts +++ b/packages/ui/jsonrpc/src/index.ts @@ -45,6 +45,8 @@ export const Config: Schema = Schema.object({ * owns root-context disposal for EOF and signals. */ export function apply(ctx: Context, config: JsonRpcConfig): void { + // Cordis applies the schema default before invoking the plugin. + const resolvedConfig = config as JsonRpcConfig & { maxTokensAsSuccess: boolean } // The later transport callback must dispose this plugin's fiber, not its ambient context. const fiber = ctx.fiber /* v8 ignore next -- production stdio wiring; tests always inject the runtime seams */ @@ -56,7 +58,7 @@ export function apply(ctx: Context, config: JsonRpcConfig): void { const transport = new JsonRpcLineTransport(input, output) const server = new HarnessSdkServer(ctx, transport, { - maxTokensAsSuccess: config.maxTokensAsSuccess ?? false, + maxTokensAsSuccess: resolvedConfig.maxTokensAsSuccess, }) // Share one exit task and attempt flush and disposal independently before exiting. diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6c7e4a3d05..b363f3e88a 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -101,6 +101,9 @@ importers: '@deepseek-ai/dsh-acp-demo': specifier: workspace:* version: link:../packages/examples/acp-demo + '@deepseek-ai/dsh-agent-spine-demo': + specifier: workspace:* + version: link:../packages/examples/agent-spine-demo '@deepseek-ai/dsh-bash-local': specifier: workspace:* version: link:../packages/bash/bash-local @@ -125,6 +128,9 @@ importers: '@deepseek-ai/dsh-hooks-codex': specifier: workspace:* version: link:../packages/hooks/hooks-codex + '@deepseek-ai/dsh-jsonrpc': + specifier: workspace:* + version: link:../packages/ui/jsonrpc '@deepseek-ai/dsh-llm': specifier: workspace:* version: link:../packages/llm/llm @@ -143,6 +149,9 @@ importers: '@deepseek-ai/dsh-sandbox-local': specifier: workspace:* version: link:../packages/sandbox/sandbox-local + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:* + version: link:../packages/session-persistence/session-persistence-jsonl '@deepseek-ai/dsh-spill-local': specifier: workspace:* version: link:../packages/spill/spill-local From 350d1b268830d76def9fd8dae53759d1953bb098 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 14:57:52 +0800 Subject: [PATCH 246/323] docs: verify Cordis signature type links --- docs/config-catalog.md | 4 +- docs/cordis-catalog/events.md | 68 ++++-- docs/cordis-catalog/services.md | 42 ++-- .../2026-06-20-generated-cordis-catalog.md | 6 +- .../agent/tests/gen-cordis-catalog.spec.ts | 36 +++- scripts/gen-cordis-catalog.ts | 198 ++++++++++++++++-- 6 files changed, 294 insertions(+), 60 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index f77334b442..9aa0d48dc6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -99,7 +99,7 @@ export interface Config { } ``` -Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts) +Depends on: [`AgentOptions`](core-data-structures/core.md) · [`SessionId`](core-data-structures/core.md) Source: [`packages/core/agent-loop/src/index.ts:369`](../packages/core/agent-loop/src/index.ts) @@ -1108,7 +1108,7 @@ export interface Config { } ``` -Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) +Depends on: [`AgentOptions`](core-data-structures/core.md) Source: [`packages/subagent/tool-subagent/src/index.ts:23`](../packages/subagent/tool-subagent/src/index.ts) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 12f877ad48..f522790fd0 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -31,7 +31,7 @@ A fully configured agent and live session were published. Setup is composition-o 'agent/created'(this: Scoped, agent: Agent): void ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:141`](../../packages/core/agent/src/types.ts) @@ -51,7 +51,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef 'agent/disposed'(this: Scoped, agent: Agent): void ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:150`](../../packages/core/agent/src/types.ts) @@ -73,7 +73,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w 'agent/error'(this: Scoped, agent: Agent, turn: number, step: number, error: Error): void ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:285`](../../packages/core/agent/src/types.ts) @@ -101,7 +101,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and 'agent/pre-step'(this: Scoped, agent: Agent, turn: number, step: number, fullSystemPrompt: string, sessionPrefix: readonly Message[], signal: AbortSignal): Promise | void ``` -Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:204`](../../packages/core/agent/src/types.ts) @@ -122,7 +122,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca 'agent/prompt-submit'(this: Scoped, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise): Promise ``` -Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) · [PromptDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:214`](../../packages/core/agent/src/types.ts) @@ -143,7 +143,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already 'agent/queued'(this: Scoped, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void ``` -Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:169`](../../packages/core/agent/src/types.ts) @@ -166,7 +166,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha 'agent/request'(this: Scoped, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise): Promise ``` -Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:226`](../../packages/core/agent/src/types.ts) @@ -192,7 +192,7 @@ Compose request-only messages placed before derived history. The frozen result i 'agent/session-prefix'(this: Scoped, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise): Promise ``` -Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:241`](../../packages/core/agent/src/types.ts) @@ -214,7 +214,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to 'agent/session-start'(this: Scoped, agent: Agent, source: SessionStartSource): void ``` -Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SessionStartSource](../core-data-structures/core.md) Source: [`packages/core/agent/src/types.ts:182`](../../packages/core/agent/src/types.ts) @@ -234,7 +234,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no 'agent/status'(this: Scoped, agent: Agent, status: AgentStatus): void ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [AgentStatus](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:159`](../../packages/core/agent/src/types.ts) @@ -256,7 +256,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va 'agent/step-result'(this: Scoped, agent: Agent, turn: number, step: number, message: Message, next: () => Promise): Promise ``` -Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:252`](../../packages/core/agent/src/types.ts) @@ -277,7 +277,7 @@ Override whether the turn continues. The default continues after tool calls or s 'agent/turn-continuation'(this: Scoped, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise): Promise ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [ContinuationDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:262`](../../packages/core/agent/src/types.ts) @@ -298,7 +298,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a 'agent/turn-stop'(this: Scoped, agent: Agent, turn: number): ContinuationStop | undefined ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [ContinuationStop](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/core/agent/src/types.ts:272`](../../packages/core/agent/src/types.ts) @@ -321,6 +321,8 @@ A declarative agent entry failed before it could publish a live agent. Consumers 'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void ``` +Types: [SessionId](../core-data-structures/core.md) + Source: [`packages/core/agent-loop/src/index.ts:362`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` @@ -340,7 +342,7 @@ Ask composed answerers for one decision. Return an outcome to claim the request 'approval/request'(this: Scoped, req: ApprovalRequest, next: () => Promise): Promise ``` -Types: [ApprovalOutcome](../core-data-structures/approval.md) · [ApprovalRequest](../core-data-structures/approval.md) +Types: [ApprovalOutcome](../core-data-structures/approval.md) · [ApprovalRequest](../core-data-structures/approval.md) · [ApprovalService](../core-data-structures/approval.md) · [Scoped](../core-data-structures/scope.md) Source: [`packages/ui/user-approval/src/index.ts:31`](../../packages/ui/user-approval/src/index.ts) @@ -426,7 +428,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t 'llm/stream'(this: LlmService, options: GenerateOptions, next: () => AsyncIterable): AsyncIterable ``` -Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) +Types: [GenerateOptions](../core-data-structures/core.md) · [LlmService](../core-data-structures/llm-streaming.md) · [StreamChunk](../core-data-structures/llm-streaming.md) Source: [`packages/llm/llm/src/index.ts:40`](../../packages/llm/llm/src/index.ts) @@ -451,6 +453,8 @@ Creation announcement during session publication. A synchronous throw vetoes and 'session/created'(this: Scoped, session: Session): void ``` +Types: [Scoped](../core-data-structures/scope.md) · [Session](../core-data-structures/session.md) + Source: [`packages/core/session/src/index.ts:47`](../../packages/core/session/src/index.ts) ### `session/disposed` — emit @@ -470,6 +474,8 @@ Emitted once when an announced session leaves the store, including publication r 'session/disposed'(this: Scoped, session: Session): void ``` +Types: [Scoped](../core-data-structures/scope.md) · [Session](../core-data-structures/session.md) + Source: [`packages/core/session/src/index.ts:57`](../../packages/core/session/src/index.ts) ### `session/event` — emit @@ -491,7 +497,7 @@ Post-commit, fire-and-forget append feed. The listener snapshot resolves before 'session/event'(this: Scoped, session: Session, event: SessionEvent): void ``` -Types: [SessionEvent](../core-data-structures/core.md) +Types: [Scoped](../core-data-structures/scope.md) · [Session](../core-data-structures/session.md) · [SessionEvent](../core-data-structures/core.md) Source: [`packages/core/session/src/index.ts:69`](../../packages/core/session/src/index.ts) @@ -512,6 +518,8 @@ Awaited parallel durability checkpoint: every listener runs and the caller await 'session/flush'(this: Scoped, session: Session): Promise | void ``` +Types: [Scoped](../core-data-structures/scope.md) · [Session](../core-data-structures/session.md) + Source: [`packages/core/session/src/index.ts:79`](../../packages/core/session/src/index.ts) ## `subagent/*` @@ -532,6 +540,8 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` +Types: [Scoped](../core-data-structures/scope.md) · [SubagentService](../core-data-structures/subagent.md) + Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -547,6 +557,8 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` +Types: [SubagentProvider](../core-data-structures/subagent.md) + Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -582,6 +594,8 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` +Types: [Scoped](../core-data-structures/scope.md) · [SubagentService](../core-data-structures/subagent.md) + Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` @@ -602,6 +616,8 @@ Expert waterfall over the assembled sections, tools, and variables. Scope-filter 'system-prompt/assemble'(this: Scoped, assembly: PromptAssembly, context: AssembleContext, next: () => Promise): Promise ``` +Types: [AssembleContext](../core-data-structures/system-prompt.md) · [Scoped](../core-data-structures/scope.md) · [SystemPrompt](../core-data-structures/system-prompt.md) + Source: [`packages/core/system-prompt/src/index.ts:27`](../../packages/core/system-prompt/src/index.ts) ### `system-prompt/change` — emit @@ -656,7 +672,7 @@ Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns a nor 'tools/execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` -Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) +Types: [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md) Source: [`packages/core/tools/src/index.ts:89`](../../packages/core/tools/src/index.ts) @@ -676,7 +692,7 @@ Accept, replace, enrich, or block a normalized dispatch result. `next()` accepts 'tools/post-execute'(this: Scoped, exec: ToolExecution, result: Readonly, next: () => Promise): Promise ``` -Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) +Types: [PostToolDecision](../core-data-structures/tools.md) · [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md) Source: [`packages/core/tools/src/index.ts:98`](../../packages/core/tools/src/index.ts) @@ -695,7 +711,7 @@ Allow, deny, or ask before dispatch. `next()` delegates to allow; missing approv 'tools/pre-execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise ``` -Types: [ToolExecution](../core-data-structures/tools.md) +Types: [PreToolDecision](../core-data-structures/tools.md) · [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md) Source: [`packages/core/tools/src/index.ts:80`](../../packages/core/tools/src/index.ts) @@ -714,7 +730,7 @@ Observe the frozen, lossless-JSON final outcome. Listener failures are contained 'tools/result'(this: Scoped, exec: Readonly, result: Readonly): undefined ``` -Types: [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) +Types: [Scoped](../core-data-structures/scope.md) · [ToolExecution](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolRegistry](../core-data-structures/tools.md) Source: [`packages/core/tools/src/index.ts:106`](../../packages/core/tools/src/index.ts) @@ -738,6 +754,8 @@ One `agent()` call settled (clean result, child failure, or run cancellation). P 'workflow/agent-end'(info: WorkflowRunInfo, agent: WorkflowAgentEndInfo): void ``` +Types: [WorkflowRunInfo](../core-data-structures/workflow.md) + Source: [`packages/workflow/workflow/src/index.ts:81`](../../packages/workflow/workflow/src/index.ts) ### `workflow/agent-start` — emit @@ -757,6 +775,8 @@ One `agent()` call established a ready child run. Paired with Events['workflow/a 'workflow/agent-start'(info: WorkflowRunInfo, agent: WorkflowAgentInfo): void ``` +Types: [WorkflowRunInfo](../core-data-structures/workflow.md) + Source: [`packages/workflow/workflow/src/index.ts:70`](../../packages/workflow/workflow/src/index.ts) ### `workflow/end` — emit @@ -776,6 +796,8 @@ A workflow run settled (any stop reason). Fired when WorkflowRun.result resolves 'workflow/end'(info: WorkflowRunInfo, result: WorkflowResultInfo): void ``` +Types: [WorkflowRunInfo](../core-data-structures/workflow.md) + Source: [`packages/workflow/workflow/src/index.ts:91`](../../packages/workflow/workflow/src/index.ts) ### `workflow/log` — emit @@ -792,6 +814,8 @@ The script emitted a narration line (a `log(message)` call). 'workflow/log'(info: WorkflowRunInfo, message: string): void ``` +Types: [WorkflowRunInfo](../core-data-structures/workflow.md) + Source: [`packages/workflow/workflow/src/index.ts:60`](../../packages/workflow/workflow/src/index.ts) ### `workflow/phase` — emit @@ -809,6 +833,8 @@ The script entered a phase (a `phase(title)` call) — progress grouping for obs 'workflow/phase'(info: WorkflowRunInfo, title: string): void ``` +Types: [WorkflowRunInfo](../core-data-structures/workflow.md) + Source: [`packages/workflow/workflow/src/index.ts:53`](../../packages/workflow/workflow/src/index.ts) ### `workflow/start` — emit @@ -825,6 +851,8 @@ A workflow run started — the script's meta block validated, the body about to 'workflow/start'(info: WorkflowRunInfo): void ``` +Types: [WorkflowRunInfo](../core-data-structures/workflow.md) + Source: [`packages/workflow/workflow/src/index.ts:45`](../../packages/workflow/workflow/src/index.ts) ## Inherited events (cordis core + loader/hmr/timer) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 78ec4c82c0..02207c52dd 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -42,7 +42,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [AgentOptions](../core-data-structures/core.md) · [SessionHeader](../core-data-structures/persistence.md) · [SessionId](../core-data-structures/core.md) Source: [`packages/core/agent-loop/src/index.ts:407`](../../packages/core/agent-loop/src/index.ts) @@ -163,7 +163,7 @@ list(): Agent[] roots(): Agent[] ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [SessionId](../core-data-structures/core.md) Source: [`packages/core/agent/src/index.ts:201`](../../packages/core/agent/src/index.ts) @@ -233,7 +233,7 @@ abstract run(spec: BashExecSpec): Promise abstract start(spec: BashExecSpec): BashProcess ``` -Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md) +Types: [BashExecRequest](../core-data-structures/bash.md) · [BashExecSpec](../core-data-structures/bash.md) · [BashProcess](../core-data-structures/bash.md) · [BashRunResult](../core-data-structures/bash.md) Source: [`packages/bash/bash/src/index.ts:49`](../../packages/bash/bash/src/index.ts) @@ -264,7 +264,7 @@ collect(execution: ToolExecution): DshEnvironment list(): BashEnvVariableInfo[] ``` -Types: [ToolExecution](../core-data-structures/tools.md) +Types: [DshEnvironment](../core-data-structures/bash.md) · [ToolExecution](../core-data-structures/tools.md) Source: [`packages/bash/tool-bash/src/index.ts:102`](../../packages/bash/tool-bash/src/index.ts) @@ -331,7 +331,7 @@ abstract compactIfNeeded( agent: CompactAgentContext, fullSystemPrompt: string, abstract compactRegion( start: number, end: number, agent: CompactAgentContext, signal?: AbortSignal, ): Promise ``` -Types: [Message](../core-data-structures/core.md) +Types: [CompactionResult](../core-data-structures/compaction.md) · [Message](../core-data-structures/core.md) Source: [`packages/compact/compact/src/index.ts:38`](../../packages/compact/compact/src/index.ts) @@ -427,7 +427,7 @@ abstract writeText(target: FsTarget, content: string, expected?: FsWriteIntent, abstract editText(target: FsTarget, edit: FsEditRequest, expected?: { version: FsVersion }, signal?: AbortSignal): Promise ``` -Types: [FsEditOutcome](../core-data-structures/filesystem.md) · [FsEditRequest](../core-data-structures/filesystem.md) · [FsInfo](../core-data-structures/filesystem.md) · [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md) · [FsWriteOutcome](../core-data-structures/filesystem.md) +Types: [FsDirEntry](../core-data-structures/filesystem.md) · [FsEditOutcome](../core-data-structures/filesystem.md) · [FsEditRequest](../core-data-structures/filesystem.md) · [FsInfo](../core-data-structures/filesystem.md) · [FsPathInfo](../core-data-structures/filesystem.md) · [FsTarget](../core-data-structures/filesystem.md) · [FsVersion](../core-data-structures/filesystem.md) · [FsWriteIntent](../core-data-structures/filesystem.md) · [FsWriteOutcome](../core-data-structures/filesystem.md) Source: [`packages/fs/fs/src/index.ts:80`](../../packages/fs/fs/src/index.ts) @@ -472,7 +472,7 @@ async listModels(provider: string): Promise stream(options: GenerateOptions): AsyncIterable ``` -Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) +Types: [GenerateOptions](../core-data-structures/core.md) · [LlmAdapter](../core-data-structures/llm-streaming.md) · [LlmModelInfo](../core-data-structures/core.md) · [LlmProviderInfo](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) Source: [`packages/llm/llm/src/index.ts:94`](../../packages/llm/llm/src/index.ts) @@ -516,7 +516,7 @@ optionOf(name: string): PresetOption set(session: Session, name: string): void ``` -Types: [SessionEvent](../core-data-structures/core.md) +Types: [Session](../core-data-structures/session.md) · [SessionEvent](../core-data-structures/core.md) Source: [`packages/ui/permission/src/index.ts:94`](../../packages/ui/permission/src/index.ts) @@ -594,7 +594,7 @@ abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEven abstract list(): Promise ``` -Types: [SessionEvent](../core-data-structures/core.md) +Types: [SessionEvent](../core-data-structures/core.md) · [SessionHeader](../core-data-structures/persistence.md) · [SessionId](../core-data-structures/core.md) · [SessionLocation](../core-data-structures/persistence.md) Source: [`packages/session-persistence/session-persistence/src/index.ts:42`](../../packages/session-persistence/session-persistence/src/index.ts) @@ -640,6 +640,8 @@ async traceEvent(request: SessionEventTraceRequest): Promise async readEvent(request: SessionEventReadRequest): Promise ``` +Types: [SessionEventReadRequest](../core-data-structures/session-query.md) · [SessionEventRecord](../core-data-structures/session-query.md) · [SessionEventTrace](../core-data-structures/session-query.md) · [SessionEventTraceRequest](../core-data-structures/session-query.md) · [SessionEventWindow](../core-data-structures/session-query.md) · [SessionId](../core-data-structures/core.md) · [SessionLineageTrace](../core-data-structures/session-query.md) · [SessionRecord](../core-data-structures/session-query.md) + Source: [`packages/session-query/session-query/src/index.ts:38`](../../packages/session-query/session-query/src/index.ts) ## `ctx.sessions` — `SessionStore` @@ -765,6 +767,8 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` +Types: [CreateSessionOptions](../core-data-structures/persistence.md) · [Session](../core-data-structures/session.md) · [SessionId](../core-data-structures/core.md) + Source: [`packages/core/session/src/index.ts:577`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` @@ -811,6 +815,8 @@ async list(options: SkillLookupOptions = {}): Promise async get(name: string, options: SkillLookupOptions = {}): Promise ``` +Types: [SkillDefinition](../core-data-structures/skills.md) · [SkillLookupOptions](../core-data-structures/skills.md) · [SkillProvider](../core-data-structures/skills.md) · [SkillRegistration](../core-data-structures/skills.md) · [SkillSummary](../core-data-structures/skills.md) + Source: [`packages/skill/skill/src/index.ts:141`](../../packages/skill/skill/src/index.ts) ## `ctx.spillStore` — `SpillStore` (abstract seam) @@ -832,6 +838,8 @@ Semantics every implementation must honor: abstract saveText(input: SaveTextSpill): Promise ``` +Types: [SaveTextSpill](../core-data-structures/spill.md) · [SpillRef](../core-data-structures/spill.md) + Source: [`packages/spill/spill/src/index.ts:45`](../../packages/spill/spill/src/index.ts) ## `ctx.subagents` — `SubagentService` @@ -873,6 +881,8 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` +Types: [SubagentProvider](../core-data-structures/subagent.md) · [SubagentRun](../core-data-structures/subagent.md) · [SubagentStartRequest](../core-data-structures/subagent.md) + Source: [`packages/subagent/subagent/src/index.ts:153`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` @@ -919,6 +929,8 @@ variable(name: string, provider: (context: AssembleContext) => string | undefine async assemble(context: AssembleContext = {}): Promise ``` +Types: [AssembleContext](../core-data-structures/system-prompt.md) · [PromptSection](../core-data-structures/system-prompt.md) · [ToolProviderResult](../core-data-structures/system-prompt.md) + Source: [`packages/core/system-prompt/src/index.ts:209`](../../packages/core/system-prompt/src/index.ts) ## `ctx.tasks` — `TaskService` @@ -1006,7 +1018,7 @@ onTaskDone(listener: TaskDoneListener): () => void attachSurface(name: string): () => void ``` -Types: [Agent](../core-data-structures/core.md) +Types: [Agent](../core-data-structures/core.md) · [TaskDoneListener](../core-data-structures/tasks.md) · [TaskId](../core-data-structures/tasks.md) · [TaskRead](../core-data-structures/tasks.md) · [TaskSnapshot](../core-data-structures/tasks.md) · [TaskStart](../core-data-structures/tasks.md) Source: [`packages/tasks/tasks/src/index.ts:76`](../../packages/tasks/tasks/src/index.ts) @@ -1041,7 +1053,7 @@ measure(session: Session, requestHeader?: EpochHeader): TokenMeasurement estimateMessage(message: Message): number ``` -Types: [Message](../core-data-structures/core.md) +Types: [EpochHeader](../core-data-structures/session.md) · [Message](../core-data-structures/core.md) · [Session](../core-data-structures/session.md) · [TokenMeasurement](../core-data-structures/token-meter.md) Source: [`packages/llm/token-meter/src/index.ts:106`](../../packages/llm/token-meter/src/index.ts) @@ -1119,7 +1131,7 @@ executionMode(exec: ToolExecutionInput): ToolExecutionMode async execute(exec: ToolExecutionInput): Promise ``` -Types: [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) +Types: [ScopeKey](../core-data-structures/scope.md) · [ToolDefinition](../core-data-structures/tools.md) · [ToolExecutionInput](../core-data-structures/tools.md) · [ToolExecutionMode](../core-data-structures/tools.md) · [ToolExecutionResult](../core-data-structures/tools.md) · [ToolGuard](../core-data-structures/tools.md) · [ToolRestriction](../core-data-structures/tools.md) · [ToolSchema](../core-data-structures/tools.md) Source: [`packages/core/tools/src/index.ts:438`](../../packages/core/tools/src/index.ts) @@ -1145,6 +1157,8 @@ registerProvider(provider: UserInteractionProvider): () => void async ask(request: AskUserQuestionRequest): Promise ``` +Types: [AskUserQuestionAnswer](../core-data-structures/user-interaction.md) · [AskUserQuestionRequest](../core-data-structures/user-interaction.md) · [UserInteractionProvider](../core-data-structures/user-interaction.md) + Source: [`packages/ui/user-interaction/src/index.ts:82`](../../packages/ui/user-interaction/src/index.ts) ## `ctx.web` — `WebService` @@ -1201,6 +1215,8 @@ async search(request: WebSearchRequest, signal?: AbortSignal): Promise ``` +Types: [WebFetchProvider](../core-data-structures/web.md) · [WebFetchRequest](../core-data-structures/web.md) · [WebFetchResult](../core-data-structures/web.md) · [WebSearchProvider](../core-data-structures/web.md) · [WebSearchRequest](../core-data-structures/web.md) · [WebSearchResult](../core-data-structures/web.md) + Source: [`packages/web/web/src/index.ts:74`](../../packages/web/web/src/index.ts) ## `ctx.workflows` — `WorkflowService` (abstract seam) @@ -1217,6 +1233,8 @@ Workflow execution seam. Invalid requests throw before publication; a live run i abstract start(request: WorkflowStartRequest): WorkflowRun ``` +Types: [WorkflowRun](../core-data-structures/workflow.md) · [WorkflowStartRequest](../core-data-structures/workflow.md) + Source: [`packages/workflow/workflow/src/index.ts:159`](../../packages/workflow/workflow/src/index.ts) ## Inherited `ctx` members (cordis core + loader/hmr/timer) diff --git a/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md b/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md index c4c57d36d6..879f8de701 100644 --- a/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md +++ b/docs/rfc/implemented/process/2026-06-20-generated-cordis-catalog.md @@ -20,7 +20,7 @@ Specific choices: - **`@mode` tag, cross-checked.** Each harness event's JSDoc carries an explicit `@mode emit|waterfall|parallel|serial` tag; the generator hard-errors on a missing tag. Where the signature shape is conclusive — a trailing `next: () => …` parameter is structurally a waterfall — it asserts the tag agrees and hard-errors on a contradiction. The emit/parallel/serial distinction is not structurally visible (`session/flush` returns `Promise | void` with no `next`, as does the ordered `agent/pre-step` checkpoint), so it is trusted from the tag. The authoring rule lives in [AGENTS.md](../../../../AGENTS.md). - **Tiered scope.** The harness tier (the 8 `@deepseek-ai/dsh-*` services + their events) is rendered in full from source. The inherited tier (cordis-core `ctx.on/emit/effect/provide/…` + the `internal/*` events + loader/hmr/timer) is pinned vendor source a plugin also sees; it is rendered tersely (name + one-line + source pointer) from a curated table in the generator, NOT walked from the vendor AST — the cordis-core `Context` mixes true ctx members with non-service fields (`root`, `baseUrl`, `logger`), and the vendor surface changes only on a deliberate vendor sync. -- **Cross-links to the data-structure catalog.** A type name in a signature (`GenerateOptions`, `StreamChunk`, `ToolDefinition`, …) links to the core-data-structures page that documents it. The map is a small hand-curated const in the generator — NOT `type-equiv.manifest.json`, which documents the `…Map` symbols while signatures reference the derived union names, and lists a few symbols on two pages. +- **Cross-links to the data-structure catalog.** Every repository-owned type name in a signature (`GenerateOptions`, `StreamChunk`, `ToolDefinition`, …) links to its primary core-data-structures page through a curated map. The AST walk is fail-closed: each parameter, generic constraint/default, and return-type reference must be mapped, be the signature's own type parameter, be a named TypeScript/Cordis foundation type, or carry a named exception with its non-catalog documentation owner. Violations aggregate with source pointers and name the appropriate owning lists. The map does NOT reuse `type-equiv.manifest.json`, which documents `…Map` symbols while signatures reference derived union names and lists some symbols on multiple pages. - **A dedicated fence.** Signature blocks use a ` ```ts cordis-catalog ` info string and place the original event or public-method JSDoc immediately before its declaration. `doc-typecheck` recognizes and skips the bare fragments, excluding them from the opt-out ratio — the same treatment `type-equiv` blocks get. This **supersedes the event-taxonomy half** of [doc-sync enforcement](2026-06-11-doc-sync-enforcement.md): `verify-event-taxonomy` and its `docs/architecture.md` table are retired (the architecture.md heading stays, its body now points at the catalog; the Service-map role table stays as curated prose). doc-typecheck, verify-md-wrap, verify-md-links, and verify-type-equiv are unchanged. @@ -29,11 +29,11 @@ This **supersedes the event-taxonomy half** of [doc-sync enforcement](2026-06-11 - **Verify-don't-generate, as the retired taxonomy check did** — reversed *for this surface only*: the data here is mechanically complete, so generation is strictly stronger (full signatures, cannot drift, catches undocumented events) than a name-set check of a hand-maintained table. - **Walking the vendor AST for the inherited tier** — rejected for the curated table: the cordis-core `Context` mixes true ctx members with non-service fields, and the pinned vendor surface changes only on a deliberate sync. -- **Reusing `type-equiv.manifest.json` as the signature cross-link map** — rejected for a small hand-curated const: the manifest documents the `…Map` symbols while signatures reference the derived union names, and it lists a few symbols on two pages. +- **Reusing `type-equiv.manifest.json` as the signature cross-link map** — rejected for a complete curated const plus fail-closed coverage: the manifest documents `…Map` symbols while signatures reference derived union names, and it lists some symbols on multiple pages. The explicit map makes each rendered destination and each non-catalog exception a reviewable decision. ## Consequences -- The catalog cannot drift: a source change that the committed file doesn't reflect fails `verify-cordis-catalog` in the pre-push hook and CI. A new event with no `@mode` tag, or a tag that contradicts its signature, fails the generator outright. +- The catalog cannot drift: a source change that the committed file doesn't reflect fails `verify-cordis-catalog` in the pre-push hook and CI. A new event with no `@mode` tag, a tag that contradicts its signature, or an unclassified signature type fails the generator outright. - Event and service-method contracts have a single home — the JSDoc at the declaration. The catalog repeats that original JSDoc inside its generated signature block and uses its description portion as entry prose, so thin source documentation yields a thin catalog entry. - The inherited tier is hand-summarized, so a vendor sync that adds/renames a cordis-core event or `ctx` member needs a matching edit to the curated table in `gen-cordis-catalog.ts`. This is the deliberate cost of not walking pinned vendor source; it changes rarely and is called out in the generator. - `verify-event-taxonomy.ts` is deleted and the `docs/architecture.md` event table is gone; anyone who linked to a specific table row now lands on the generated catalog instead. diff --git a/packages/core/agent/tests/gen-cordis-catalog.spec.ts b/packages/core/agent/tests/gen-cordis-catalog.spec.ts index 24841c8c8e..23c558bd95 100644 --- a/packages/core/agent/tests/gen-cordis-catalog.spec.ts +++ b/packages/core/agent/tests/gen-cordis-catalog.spec.ts @@ -1,5 +1,6 @@ /** - * Negative-path tests for the cordis catalog generator (`scripts/gen-cordis-catalog.ts`). + * Contract and negative-path tests for the cordis catalog generator + * (`scripts/gen-cordis-catalog.ts`). */ import { mkdtempSync, mkdirSync, rmSync, writeFileSync } from 'node:fs' @@ -76,6 +77,33 @@ describe('gen-cordis-catalog collectEvents', () => { expect(events[0]?.mode).toBe('parallel') }) + it('accepts linked, foundation, generic-parameter, and explicitly exempt signature types', () => { + const events = collectEvents(make( + ' /**\n * Carry linked and foundation types.\n * @param value - the linked value.\n * @param preset - deployment metadata outside the core catalog.\n * @param signal - cancellation.\n * @mode parallel\n */\n \'fix/typed\'(value: Readonly, preset: PresetSpec, signal: AbortSignal): Promise', + )) + expect(events).toHaveLength(1) + expect(renderEvents(events)).toContain('Types: [SessionEvent](../core-data-structures/core.md)') + expect(renderEvents(events)).not.toContain('[PresetSpec]') + }) + + it('aggregates every unclassified signature type with its source and remediation', () => { + const expected = new RegExp([ + '2 signature type-link coverage violation\\(s\\)', + 'fix/one', + 'packages/group/fix/src/index.ts', + 'MissingOne', + 'fix/two', + 'packages/group/fix/src/index.ts', + 'missingTwo', + 'Add it to LINK_MAP', + 'FOUNDATION_TYPE_NAMES', + 'TYPE_LINK_EXEMPTIONS', + ].join('[\\s\\S]*')) + expect(() => collectEvents(make( + ' /**\n * First.\n * @param value - first value.\n * @mode emit\n */\n \'fix/one\'(value: MissingOne): void\n /**\n * Second.\n * @param value - second value.\n * @mode emit\n */\n \'fix/two\'(value: missingTwo): void', + ))).toThrow(expected) + }) + it('hard-errors when an event is missing its @mode tag', () => { expect(() => collectEvents(make( ' /** No mode here. */\n \'fix/untagged\'(): void', @@ -167,6 +195,12 @@ export class FixService { expect(renderServices(services)).toContain('```ts cordis-catalog\n/**\n * Do the thing.\n * @param id - which thing to do.\n * @returns the outcome of doing it.\n */\nrun(id: string): string\n\n/** Fire and forget (void needs no @returns). */\npoke(): void') }) + it('hard-errors on an unclassified service-method signature type', () => { + expect(() => collectServices(makeService( + '/** Fixture service. */\nexport class FixService {\n /**\n * Use an unknown value.\n * @param value - the value.\n */\n run(value: MissingServiceType): void {}\n}', + ))).toThrow(/service method ctx\.fix\.run .* references unclassified type 'MissingServiceType'/) + }) + it('hard-errors on a public method with no JSDoc at all', () => { expect(() => collectServices(makeService( '/** Fixture service. */\nexport class FixService {\n run(id: string): string { return id }\n}', diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 08f04947da..5176c8e330 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -1,8 +1,8 @@ /** * Generate the Cordis event and service catalogs from static declarations. - * The walk enforces event modes plus JSDoc parameter/return completeness; - * inherited Cordis services come from the curated table below. `--check` - * verifies both committed artifacts. + * The walk enforces event modes, JSDoc parameter/return completeness, and + * signature type-link coverage; inherited Cordis services come from the + * curated table below. `--check` verifies both committed artifacts. */ import { globSync, readFileSync, writeFileSync } from 'node:fs' @@ -20,48 +20,196 @@ const OUT_SERVICES = 'docs/cordis-catalog/services.md' const FENCE = 'ts cordis-catalog' /** - * One primary core-data-structures page per signature type, shared by the - * Cordis and config catalogs; union names intentionally do not reuse the - * type-equivalence manifest's map-symbol entries. + * One primary core-data-structures page per project type used by a generated + * signature. This stays curated because union names intentionally do not + * reuse the type-equivalence manifest's map-symbol entries and some symbols + * appear on more than one page. */ -// TODO(catalog-type-links): verify or generate link-map coverage. export const LINK_MAP: Record = { Agent: 'core.md', + AgentOptions: 'core.md', + AgentStatus: 'core.md', ContentBlock: 'core.md', - Message: 'core.md', - MessageSource: 'core.md', + ContinuationDecision: 'core.md', + ContinuationStop: 'core.md', GenerateOptions: 'core.md', LlmCallConfig: 'core.md', + LlmModelInfo: 'core.md', + LlmProviderInfo: 'core.md', + Message: 'core.md', + MessageSource: 'core.md', + PromptDecision: 'core.md', SessionEvent: 'core.md', + SessionId: 'core.md', SessionStartSource: 'core.md', - StreamChunk: 'llm-streaming.md', - TurnEndReason: 'session.md', - ToolDefinition: 'tools.md', - ToolExecution: 'tools.md', - ToolExecutionMode: 'tools.md', - ToolExecutionInput: 'tools.md', - ToolExecutionResult: 'tools.md', - ToolExecutionToken: 'tools.md', ApprovalOutcome: 'approval.md', ApprovalPolicy: 'approval.md', ApprovalRequest: 'approval.md', + ApprovalService: 'approval.md', BashExecRequest: 'bash.md', BashExecSpec: 'bash.md', + BashProcess: 'bash.md', BashRunResult: 'bash.md', - ConfinedArgv: 'sandbox.md', - SandboxMode: 'sandbox.md', - SandboxPolicy: 'sandbox.md', + DshEnvironment: 'bash.md', CodeRunRequest: 'code-runtime.md', CodeRunResult: 'code-runtime.md', + CompactionResult: 'compaction.md', + FileReadOutcome: 'filesystem.md', + FsDirEntry: 'filesystem.md', FsEditOutcome: 'filesystem.md', FsEditRequest: 'filesystem.md', FsInfo: 'filesystem.md', + FsPathInfo: 'filesystem.md', + FsPolicyExec: 'filesystem.md', FsTarget: 'filesystem.md', FsVersion: 'filesystem.md', FsWriteIntent: 'filesystem.md', FsWriteOutcome: 'filesystem.md', - FsPolicyExec: 'filesystem.md', - FileReadOutcome: 'filesystem.md', + LlmAdapter: 'llm-streaming.md', + LlmService: 'llm-streaming.md', + StreamChunk: 'llm-streaming.md', + CreateSessionOptions: 'persistence.md', + SessionHeader: 'persistence.md', + SessionLocation: 'persistence.md', + ConfinedArgv: 'sandbox.md', + SandboxMode: 'sandbox.md', + SandboxPolicy: 'sandbox.md', + ScopeKey: 'scope.md', + Scoped: 'scope.md', + EpochHeader: 'session.md', + Session: 'session.md', + TurnEndReason: 'session.md', + SessionEventReadRequest: 'session-query.md', + SessionEventRecord: 'session-query.md', + SessionEventTrace: 'session-query.md', + SessionEventTraceRequest: 'session-query.md', + SessionEventWindow: 'session-query.md', + SessionLineageTrace: 'session-query.md', + SessionRecord: 'session-query.md', + SkillDefinition: 'skills.md', + SkillLookupOptions: 'skills.md', + SkillProvider: 'skills.md', + SkillRegistration: 'skills.md', + SkillSummary: 'skills.md', + SaveTextSpill: 'spill.md', + SpillRef: 'spill.md', + SubagentProvider: 'subagent.md', + SubagentRun: 'subagent.md', + SubagentService: 'subagent.md', + SubagentStartRequest: 'subagent.md', + AssembleContext: 'system-prompt.md', + PromptSection: 'system-prompt.md', + SystemPrompt: 'system-prompt.md', + ToolProviderResult: 'system-prompt.md', + TaskDoneListener: 'tasks.md', + TaskId: 'tasks.md', + TaskRead: 'tasks.md', + TaskSnapshot: 'tasks.md', + TaskStart: 'tasks.md', + TokenMeasurement: 'token-meter.md', + PostToolDecision: 'tools.md', + PreToolDecision: 'tools.md', + ToolDefinition: 'tools.md', + ToolExecution: 'tools.md', + ToolExecutionInput: 'tools.md', + ToolExecutionMode: 'tools.md', + ToolExecutionResult: 'tools.md', + ToolExecutionToken: 'tools.md', + ToolGuard: 'tools.md', + ToolRegistry: 'tools.md', + ToolRestriction: 'tools.md', + ToolSchema: 'tools.md', + AskUserQuestionAnswer: 'user-interaction.md', + AskUserQuestionRequest: 'user-interaction.md', + UserInteractionProvider: 'user-interaction.md', + WebFetchProvider: 'web.md', + WebFetchRequest: 'web.md', + WebFetchResult: 'web.md', + WebSearchProvider: 'web.md', + WebSearchRequest: 'web.md', + WebSearchResult: 'web.md', + WorkflowRun: 'workflow.md', + WorkflowRunInfo: 'workflow.md', + WorkflowStartRequest: 'workflow.md', +} + +/** TypeScript lib and pinned framework types that have no repository-owned data page. */ +const FOUNDATION_TYPE_NAMES = new Set([ + 'AbortSignal', + 'AsyncIterable', + 'Context', + 'Error', + 'Pick', + 'Promise', + 'Readonly', +]) + +/** Project types deliberately documented outside the core-data catalog. */ +const TYPE_LINK_EXEMPTIONS: Readonly> = { + AgentFactory: 'agent creation seam is owned by packages/core/agent/README.md', + AgentHandle: 'agent ownership handle is owned by packages/core/agent/README.md', + BashEnvContributor: 'service-local extension type is owned by packages/bash/tool-bash/src/index.ts', + BashEnvVariableInfo: 'service-local metadata type is owned by packages/bash/tool-bash/src/index.ts', + CompactAgentContext: 'compaction service input is owned by packages/compact/compact/src/index.ts', + CreateAgentOptions: 'agent creation contract is owned by packages/core/agent/README.md', + PresetOption: 'deployment menu metadata is owned by packages/ui/permission/README.md', + PresetSpec: 'deployment preset composition is owned by packages/ui/permission/README.md', + PromptAssembly: 'assembly result is owned by packages/core/system-prompt/README.md', + ResumeAgentOptions: 'agent resume contract is owned by packages/core/agent/README.md', + SessionForkSource: 'service-local fork input is owned by packages/core/session/src/index.ts', + SubagentRunEndInfo: 'event-local snapshot is owned by packages/subagent/subagent/src/index.ts', + SubagentRunInfo: 'event-local snapshot is owned by packages/subagent/subagent/src/index.ts', + WorkflowAgentEndInfo: 'event-local snapshot is owned by packages/workflow/workflow/src/index.ts', + WorkflowAgentInfo: 'event-local snapshot is owned by packages/workflow/workflow/src/index.ts', + WorkflowResultInfo: 'event-local snapshot is owned by packages/workflow/workflow/src/index.ts', +} + +/** Collect named references from parameter, generic-constraint/default, and return types. */ +function signatureTypeNames(member: ts.MethodSignature | ts.MethodDeclaration, sf: ts.SourceFile): string[] { + const declared = new Set(member.typeParameters?.map(parameter => parameter.name.text) ?? []) + const referenced = new Set() + const visit = (node: ts.Node): void => { + if (ts.isTypeReferenceNode(node)) referenced.add(node.typeName.getText(sf)) + if (ts.isTypeQueryNode(node)) referenced.add(node.exprName.getText(sf)) + ts.forEachChild(node, visit) + } + for (const parameter of member.typeParameters ?? []) { + if (parameter.constraint) visit(parameter.constraint) + if (parameter.default) visit(parameter.default) + } + for (const parameter of member.parameters) { + if (parameter.type) visit(parameter.type) + } + if (member.type) visit(member.type) + return [...referenced].filter(name => !declared.has(name)).sort() +} + +/** Append fail-closed signature type-link violations with actionable ownership choices. */ +function checkTypeLinks( + where: string, + member: ts.MethodSignature | ts.MethodDeclaration, + sf: ts.SourceFile, + violations: string[], +): void { + for (const name of signatureTypeNames(member, sf)) { + if (Object.hasOwn(LINK_MAP, name) + || FOUNDATION_TYPE_NAMES.has(name) + || Object.hasOwn(TYPE_LINK_EXEMPTIONS, name)) continue + violations.push( + `${where} references unclassified type '${name}'. Add it to LINK_MAP with its core-data-structures page, ` + + 'to FOUNDATION_TYPE_NAMES if TypeScript or Cordis owns it, or to TYPE_LINK_EXEMPTIONS with ' + + 'the non-catalog documentation owner.', + ) + } +} + +/** Throw one aggregated diagnostic for every unclassified signature type. */ +function reportTypeLinkViolations(gate: string, violations: string[]): void { + if (violations.length === 0) return + throw new Error( + `${gate}: ${violations.length} signature type-link coverage violation(s):\n` + + violations.map(violation => ` ${violation}`).join('\n'), + ) } /** One harness event, extracted from an `interface Events` block. */ @@ -148,6 +296,7 @@ function jsDocText(text: string, sf: ts.SourceFile, node: ts.Node): string { export function collectEvents(scanRoot: string = root): EventEntry[] { const entries: EventEntry[] = [] const violations: string[] = [] + const typeLinkViolations: string[] = [] for (const rel of globSync('packages/*/*/src/*.ts', { cwd: scanRoot }).map(s => s.split(sep).join('/')).sort()) { const abs = resolve(scanRoot, rel) const text = readFileSync(abs, 'utf8') @@ -161,6 +310,7 @@ export function collectEvents(scanRoot: string = root): EventEntry[] { const { doc, mode } = parseJsDoc(raw) const src = pointer(rel, sf, member) const where = `event '${name}' (${src})` + checkTypeLinks(where, member, sf, typeLinkViolations) if (!mode) { violations.push(`${where} is missing an @mode tag. Add '@mode emit|waterfall|parallel|serial' to its JSDoc (see AGENTS.md).`) } @@ -185,6 +335,7 @@ export function collectEvents(scanRoot: string = root): EventEntry[] { } } reportViolations('gen-cordis-catalog', violations) + reportTypeLinkViolations('gen-cordis-catalog', typeLinkViolations) return entries } @@ -197,6 +348,7 @@ export function collectEvents(scanRoot: string = root): EventEntry[] { export function collectServices(scanRoot: string = root): ServiceEntry[] { const entries: ServiceEntry[] = [] const violations: string[] = [] + const typeLinkViolations: string[] = [] for (const rel of globSync('packages/*/*/src/index.ts', { cwd: scanRoot }).map(s => s.split(sep).join('/')).sort()) { const abs = resolve(scanRoot, rel) const text = readFileSync(abs, 'utf8') @@ -220,6 +372,7 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { const memberName = member.name.getText(sf) if (memberName.startsWith('[')) continue // computed/symbol members const where = `service method ctx.${key}.${memberName} (${pointer(rel, sf, member)})` + checkTypeLinks(where, member, sf, typeLinkViolations) const raw = rawJsDoc(text, member) methods.push({ signature: memberSignature(member, sf), jsDoc: jsDocText(text, sf, member) }) if (!raw) { violations.push(`${where} has no JSDoc.`); continue } @@ -243,6 +396,7 @@ export function collectServices(scanRoot: string = root): ServiceEntry[] { } } reportViolations('gen-cordis-catalog', violations) + reportTypeLinkViolations('gen-cordis-catalog', typeLinkViolations) return entries.sort((a, b) => a.key.localeCompare(b.key)) } From 98e224e45e04308b99751eae4bc227df1c2ba763 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 15:02:11 +0800 Subject: [PATCH 247/323] refactor(agent): exhaust recovery and compaction decisions Dispatch RequestErrorDecision and CompactionTrigger through explicit discriminant switches. End each closed union with assertNever so new variants fail compilation instead of silently inheriting fail or pressure behavior. This preserves the current retry, fail, pressure, and overflow semantics while aligning the new recovery seams with the repository closed-union contract. --- packages/compact/compact-basic/src/index.ts | 19 +++++++++++++------ packages/core/agent-loop/src/loop.ts | 16 +++++++++++----- 2 files changed, 24 insertions(+), 11 deletions(-) diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index b77ebebc76..5d325d57ba 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -9,7 +9,7 @@ import z from 'schemastery' import { CompactService } from '@deepseek-ai/dsh-compact' import type { CompactionResult, CompactionTrigger } from '@deepseek-ai/dsh-compact' import type { Session } from '@deepseek-ai/dsh-session' -import { CONTEXT_WINDOW_EXCEEDED_CODE } from '@deepseek-ai/dsh-llm' +import { CONTEXT_WINDOW_EXCEEDED_CODE, assertNever } from '@deepseek-ai/dsh-llm' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' import { resolveConfig } from './config.ts' @@ -152,11 +152,18 @@ export class BasicCompactService extends CompactService { const model = routedModel(agent.session) if (model === undefined) return null const meter = this.ctx.tokenMeter - if (trigger === 'context-overflow') { - const measurement = meter.measure(agent.session) - const range = selectCompactableRange(agent.session, measurement, 0) - if (range === null) return null - return this.compactRegion(range.start, range.end, agent, signal) + switch (trigger) { + case 'context-overflow': { + const measurement = meter.measure(agent.session) + const range = selectCompactableRange(agent.session, measurement, 0) + if (range === null) return null + return this.compactRegion(range.start, range.end, agent, signal) + } + case 'pressure': + break + /* v8 ignore next -- closed-union exhaustiveness guard */ + default: + assertNever(trigger, 'compaction trigger') } const threshold = Math.floor(meter.contextWindow * this.config.thresholdRatio) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 54cbbc6bdd..08c1ab9412 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -8,7 +8,7 @@ import type { Context } from 'cordis' import type { ContentBlock, FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' import { isDeepStrictEqual } from 'node:util' -import { BlockAssembler, HarnessError, deepFreeze, isLlmAdapterFailure } from '@deepseek-ai/dsh-llm' +import { BlockAssembler, HarnessError, assertNever, deepFreeze, isLlmAdapterFailure } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision, RequestError, RequestErrorDecision } from '@deepseek-ai/dsh-agent' import { canonicalHeader } from '@deepseek-ai/dsh-session' @@ -392,11 +392,17 @@ async function runTurn( : { kind: 'aborted', reason: String(abort.signal.reason) } break } - if (recoveryDecision.action === 'retry') { - requestRetryAttempt += 1 - continue + switch (recoveryDecision.action) { + case 'retry': + requestRetryAttempt += 1 + continue + case 'fail': + failTurn(stepOutcome.requestError) + break + /* v8 ignore next -- closed-union exhaustiveness guard */ + default: + assertNever(recoveryDecision, 'agent request-error decision') } - failTurn(stepOutcome.requestError) break } From 8eb9beb31909ae83639c9b5c5df1664c996be0b5 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 15:03:15 +0800 Subject: [PATCH 248/323] docs(rfc): correct recovery translation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use the repository-mandated 回放 terminology for replayable pressure and replace the literal cancellation-owned rendering with idiomatic Chinese that preserves boundedness, cancellation authority, and monotonic retry behavior. The corresponding English clauses remain accurate. Re-record the English and Chinese pair after checking the corrected text against the implemented recovery contract. --- ...r-call-compaction-pressure-and-overflow-recovery.i18n.yaml | 2 +- ...after-call-compaction-pressure-and-overflow-recovery.zh.md | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index 9f3f9fcebf..aa45a7ccb2 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -3,4 +3,4 @@ # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write 2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: abc374d98fed8cac039f10d930fec332515c846e -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 5f6661c9fdc905048aaec56d9b0831a9a5a4548e +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: ef13c64fc4c728e5b4fe9718ae8ef8b8ef9ecdd9 diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index 5f6661c9fd..ef13c64fc4 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -8,7 +8,7 @@ Status: implemented `agent/pre-step` 运行在最终请求路由之前，也早于 assistant 输出、工具结果、缓冲上下文与 steering 的产生。即使它接收已装配提示词与会话前缀，压力视图仍是临时的，因为 `agent/request` 还可以改变路由或调用配置，工具 schema 也没有与这些输入一同冻结。增加字段无法让调用前状态描述已完成调用，还会把通用 seam 与压缩耦合。 -成功调用也不是唯一的压力信号。提供方可能在返回 usage 之前就因上下文窗口超限拒绝请求，一些成功调用也不提供 usage。因此，系统需要可重放的调用后压力，以及一条狭窄的失败恢复路径；当压缩无法证明取得有效进展时，必须保留原始提供方错误。 +成功调用也不是唯一的压力信号。提供方可能在返回 usage 之前就因上下文窗口超限拒绝请求，一些成功调用也不提供 usage。因此，系统需要可回放的调用后压力，以及一条狭窄的失败恢复路径；当压缩无法证明取得有效进展时，必须保留原始提供方错误。 ## 决策 @@ -54,7 +54,7 @@ Status: implemented ## 后果 -Post-step 压力描述已完成的路由请求，包括持久工具结果与仅请求前缀字段。当成功 usage 锚点不存在时，规范化溢出提供兜底路径。恢复有上限、受取消所有，并保持单调：只有模型可见的表层 generation 变化后才重试。 +Post-step 压力描述已完成的路由请求，包括持久工具结果与仅请求前缀字段。当成功 usage 锚点不存在时，规范化溢出提供兜底路径。恢复有明确上限、以取消为准，并保持单调：只有模型可见的表层 generation 变化后才重试。 代价是成功 step 增加一个串行检查点，并需要适配器持续维护溢出分类。提供方措辞与启发式字符密度仍是维护风险。表层压缩依然无法修复仅信封本身就超出窗口的情况，也不能拆分单个不可分割的超大消息或工具单元。 From 761796347482382699baa71f36b9c8705c75fc01 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 15:04:51 +0800 Subject: [PATCH 249/323] docs(llm-pi-ai): describe usage overflow mapping Document every context-window path returned by mapStopReason: recognized provider error wording, successful stop usage beyond the resolved window, and zero-output length stops that fill the window. This keeps the public return contract aligned with usage-based overflow classification without duplicating the provider-specific detection table owned by pi-ai. --- packages/llm/llm-pi-ai/src/stream.ts | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/packages/llm/llm-pi-ai/src/stream.ts b/packages/llm/llm-pi-ai/src/stream.ts index 8bc41cded2..c1a85addf0 100644 --- a/packages/llm/llm-pi-ai/src/stream.ts +++ b/packages/llm/llm-pi-ai/src/stream.ts @@ -40,7 +40,9 @@ function classifyPiAiError(message: string): string { * Map a terminal pi-ai event to the harness finish reason. * @param message - the assistant message carried by the `done` or `error` event. * @param contextWindow - resolved catalog capacity for usage-based overflow detection. - * @returns the harness reason; `error` yields `{kind: 'error'}` with a code classified from the error text. + * @returns the mapped harness reason. Recognized error text, `stop` usage above + * `contextWindow`, and zero-output `length` usage that fills the window map + * to `CONTEXT_WINDOW_EXCEEDED`. */ export function mapStopReason(message: AssistantMessage, contextWindow?: number): FinishReason { const piAiOverflow = isContextOverflow(message, contextWindow) From ee1a44793acc670ef99797a7ef2c16f60d5cf2bf Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 15:12:18 +0800 Subject: [PATCH 250/323] fix(core): make initiator teardown reentrant-safe --- docs/cordis-catalog/services.md | 6 +- docs/event-producer-consumer.md | 1 + ...2026-07-15-agent-initiator-scope.i18n.yaml | 4 +- .../2026-07-15-agent-initiator-scope.md | 6 +- .../2026-07-15-agent-initiator-scope.zh.md | 6 +- packages/core/agent/README.md | 2 +- packages/core/agent/src/index.ts | 70 ++++++++++-- .../core/agent/tests/agent-initiator.spec.ts | 102 ++++++++++++++++++ website/zh-CN/api/harness/agents.md | 34 +++--- 9 files changed, 195 insertions(+), 36 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 22d4565830..30ca04ba79 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -68,6 +68,8 @@ requireInitiator(): Agent /** * Run an operation with one exact Agent as its process-local initiator. The * exact synchronous value or Promise returned by the operation is preserved. + * If its inherited async chain starts an owning-fiber unload, the nested + * boundary lineage is excluded from the drain so teardown cannot wait on itself. * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization. * @param operation - synchronous or asynchronous operation to invoke. * @returns the exact value returned by `operation`. @@ -78,6 +80,8 @@ withInitiator(agent: Agent, operation: () => T): T /** * Run an operation inside a boundary that hides any inherited initiating * Agent. The exact synchronous value or Promise is preserved. + * If its inherited async chain starts an owning-fiber unload, the nested + * boundary lineage is excluded from the drain so teardown cannot wait on itself. * @param operation - synchronous or asynchronous operation to invoke without an initiator. * @returns the exact value returned by `operation`. * @throws when the initiator scope is closing/disposed, or when `operation` throws. @@ -198,7 +202,7 @@ roots(): Agent[] Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:204`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:211`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index abea24e3a5..40048b2e7c 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -53,5 +53,6 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event string | Dispatchers | Listeners | | --- | --- | --- | | `internal/dispatch` | - | [`invariants`](../packages/support/invariants) | +| `internal/status` | - | [`agent`](../packages/core/agent) | Maintenance mode: generated: Cordis event declarations and producer/listener edges are resolved from the repository TypeScript Program. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml index 696b119797..9e2a50bd57 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-initiator-scope.md: 08c9eca50ed51925fec7c09eda7a82d0c61cb55b -2026-07-15-agent-initiator-scope.zh.md: 284d52126e02e44d512b88a5d64e35ba80552d9b +2026-07-15-agent-initiator-scope.md: b3c9be0be1dea29568dfcdeb0578e643734486e8 +2026-07-15-agent-initiator-scope.zh.md: 55494977b8ade0d380fa21b25171bce65a46a9fb diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md index 08c9eca50e..b3c9be0be1 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md @@ -12,7 +12,7 @@ Deep process-local infrastructure sometimes needs a trusted initiating Agent bel ## Decision -The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; the [core-data catalog](../../../core-data-structures/core.md#initiating-agent) identifies the carried type. +The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the initiating Agent. It stores the exact `Agent` directly rather than introducing a one-field frame; a separate private run token records nested boundary lineage only for teardown bookkeeping and carries no identity. The [core-data catalog](../../../core-data-structures/core.md#initiating-agent) identifies the carried type. `currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. @@ -20,7 +20,7 @@ The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the in Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. -`AgentRegistry` owns an ordered initiator lifecycle. Teardown first rejects new boundaries; removing `ctx.agents` then drains injected dependents such as AgentLoop, and the registry waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. `currentInitiator()` and `requireInitiator()` remain usable through a retained in-flight service reference while that drain runs; after disposal, initiator methods throw `agent initiator scope is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting remains necessary in addition to Cordis dependency ordering. +`AgentRegistry` owns an ordered initiator lifecycle. Teardown first rejects new boundaries; removing `ctx.agents` then drains injected dependents such as AgentLoop, and the registry waits for active returned-Promise boundaries before calling `AsyncLocalStorage.disable()`. If a boundary's inherited async chain starts an owning Cordis fiber's unload, the private run-token lineage releases that nested boundary chain from the drain, which prevents teardown from waiting on itself while unrelated boundaries still drain. `currentInitiator()` and `requireInitiator()` remain usable through a retained in-flight service reference while the ordinary drain runs; after disposal, initiator methods throw `agent initiator scope is disposed`. Root Context disposal may start sibling fiber teardown concurrently, so active-boundary counting remains necessary in addition to Cordis dependency ordering. Initiator scope does not own detached work: registry drain tracks only the Promise returned by `withInitiator()` or `withoutInitiator()`. Asynchronous resources created inside a boundary inherit its store until they settle or ALS is disabled, so their owning seam must stop unreturned work explicitly. Agent-owned foreground work returns its lifetime and keeps its cancellation contract. Unrelated timers, queues, and deployment infrastructure start under `withoutInitiator(operation)`; queue, worker, process, and wire boundaries serialize identity rather than expecting ALS propagation. @@ -30,7 +30,7 @@ This decision extends the [Agent registration-scope contract](2026-07-08-agent-s ## Verification -Agent service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, overlapping, nested, and cleared boundaries, restoration after throws or rejection, drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, AgentRegistry restart, and root teardown. Composition, module-graph, build, and runtime-closure checks keep `ctx.agents` wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses without another provider. +Agent service tests pin optional and required reads, exact synchronous and cross-realm Promise identity, intrinsic Promise settlement observation, overlapping, nested, and cleared boundaries, restoration after throws or rejection, ordinary and reentrant drain ordering, and retained-reference errors. AgentLoop integration pins concurrent and nested drivers, agentless calls, AgentRegistry restart, and root teardown. Composition, module-graph, build, and runtime-closure checks keep `ctx.agents` wired through the default bundle, SDK spine, Python runtime closure, and direct AgentLoop harnesses without another provider. Only a test-double host-aware transport consumes ambient identity; it derives `X-Harness-Session-Id` internally and verifies that tool schema and logged arguments contain no identity field. The service deliberately does not drain async work omitted from the Promise returned by the boundary operation; that work remains subject to its owner's explicit stop contract. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md index 284d52126e..55494977b8 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md @@ -12,7 +12,7 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 ## 决策 -必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`，不引入只有一个字段的帧；[核心数据目录](../../../core-data-structures/core.md#initiating-agent)标明了所携带的类型。 +必需的 `ctx.agents` 服务使用 Node `AsyncLocalStorage` 携带发起 Agent。它直接存储同一个 `Agent`，不引入只有一个字段的帧；另一个私有运行标记只记录嵌套边界的谱系，供 teardown 记账使用，不携带身份。[核心数据目录](../../../core-data-structures/core.md#initiating-agent)标明了所携带的类型。 `currentInitiator()` 用于可选读取，`requireInitiator()` 抛出 `no initiating agent is active`，`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 @@ -20,7 +20,7 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 -`AgentRegistry` 管理一个有序的发起方生命周期。teardown 会先拒绝新边界；移除 `ctx.agents` 后，AgentLoop 等注入方开始排空，注册表随后等待活动的返回 Promise 边界，最后调用 `AsyncLocalStorage.disable()`。排空期间，进行中代码可通过保留的服务引用继续调用 `currentInitiator()` 和 `requireInitiator()`；dispose 后，发起方方法会抛出 `agent initiator scope is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown，因此除 Cordis 依赖顺序外仍必须统计活动边界。 +`AgentRegistry` 管理一个有序的发起方生命周期。teardown 会先拒绝新边界；移除 `ctx.agents` 后，AgentLoop 等注入方开始排空，注册表随后等待活动的返回 Promise 边界，最后调用 `AsyncLocalStorage.disable()`。如果某个边界继承的异步调用链启动所属 Cordis fiber 的卸载，私有运行标记谱系会从排空范围中释放该嵌套边界链，从而避免 teardown 等待自身完成，同时继续排空无关边界。在普通排空期间，进行中代码可通过保留的服务引用继续调用 `currentInitiator()` 和 `requireInitiator()`；dispose 后，发起方方法会抛出 `agent initiator scope is disposed`。根 Context dispose 可能并发启动同级 fiber 的 teardown，因此除 Cordis 依赖顺序外仍必须统计活动边界。 发起方作用域不负责管理脱离返回链的工作：注册表排空只跟踪 `withInitiator()` 或 `withoutInitiator()` 返回的 Promise。边界内创建的异步资源会继承其存储，直到自身结束或 ALS 被禁用；所属 seam 必须显式停止未纳入返回 Promise 的工作。Agent 所有前台工作会把完整生命周期纳入返回值，并保留显式取消契约。无关的定时器、队列和部署基础设施在 `withoutInitiator(operation)` 下启动；队列、worker、进程和协议边界必须序列化身份，不能期待 ALS 传播。 @@ -30,7 +30,7 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 ## 验证 -Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启及根 Context 销毁。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线，无需其他提供方。 +Agent 服务测试锁定可选与必需读取、同步值和跨 realm Promise 的引用身份、内建 Promise 结束状态观察、并发、嵌套及清空边界、同步抛错或 Promise 拒绝后的恢复、普通与重入排空顺序及保留引用的错误。AgentLoop 集成测试锁定并发与嵌套驱动、无 Agent 调用、AgentRegistry 重启及根 Context 销毁。组合、模块图、构建及运行时闭包检查确保默认组合包、SDK 主干、Python 运行时闭包及直接 AgentLoop harness 通过 `ctx.agents` 完成接线，无需其他提供方。 只有测试替身形式的宿主感知传输层消费隐式身份；它在内部推导 `X-Harness-Session-Id`，并验证工具 schema 与记录参数都不包含身份字段。服务有意不排空边界操作所返回 Promise 之外的异步工作；这类工作仍由所属方的显式停止契约管理。 diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 839907bf62..3cf8bbb6ad 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -26,7 +26,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.withInitiator(agent, operation)` — run with one exact Agent and preserve the operation's exact synchronous value or Promise. - `ctx.agents.withoutInitiator(operation)` — hide an inherited initiator for unrelated process-local work. -The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. The [initiator-scope decision](../../../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract. +The scope carries the `Agent` itself and is process-local. Ambient presence is neither liveness proof nor authorization; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. Teardown rejects new boundaries, lets injected dependents and returned-Promise boundaries drain, then disables the underlying `AsyncLocalStorage`; unreturned work remains owned by the subsystem that detached it. If a boundary's inherited async chain starts an owning Cordis fiber's unload, that nested boundary chain is released from the drain so the unload cannot wait on itself; its continuations observe the disposed service after teardown. The [initiator-scope decision](../../../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns the detailed boundary and teardown contract. #### Factory seam (creation) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index f2e774223d..24087011b7 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -5,7 +5,8 @@ * @module @deepseek-ai/dsh-agent */ -import { Context, getTraceable, Service, symbols } from 'cordis' +import { Context, FiberState, getTraceable, Service, symbols } from 'cordis' +import type { Fiber } from 'cordis' import { AsyncLocalStorage } from 'node:async_hooks' import { isPromise } from 'node:util/types' import { scopeTarget } from '@deepseek-ai/dsh-scope' @@ -190,6 +191,12 @@ interface AgentEntry { detachRequested: boolean } +/** One tracked boundary plus its inherited nesting chain. */ +interface InitiatorRun { + active: boolean + readonly parent: InitiatorRun | undefined +} + /** Plain holder prevents Cordis from tracing the factory field before the caller context is known. */ interface FactorySlot { readonly target: AgentFactory @@ -205,6 +212,7 @@ export class AgentRegistry extends Service { private store = new Map() private factory: FactorySlot | undefined private readonly initiators = new AsyncLocalStorage() + private readonly initiatorRuns = new AsyncLocalStorage() private initiatorState: 'active' | 'closing' | 'disposed' = 'active' private activeInitiatorRuns = 0 private initiatorDrain: PromiseWithResolvers | undefined @@ -219,6 +227,11 @@ export class AgentRegistry extends Service { // accessor body never needs to resolve a scope itself. Effect-scoped: // unwinds with this service's fiber. ctx.accessor('agent', { get: () => undefined }) + ctx.on('internal/status', (fiber) => { + if (fiber.state === FiberState.UNLOADING && this.hasLifecycleAncestor(fiber)) { + this.closeInitiators() + } + }) ctx.effect(function* (this: AgentRegistry) { yield () => this.disposeInitiators() yield () => { this.closeInitiators() } @@ -249,6 +262,8 @@ export class AgentRegistry extends Service { /** * Run an operation with one exact Agent as its process-local initiator. The * exact synchronous value or Promise returned by the operation is preserved. + * If its inherited async chain starts an owning-fiber unload, the nested + * boundary lineage is excluded from the drain so teardown cannot wait on itself. * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization. * @param operation - synchronous or asynchronous operation to invoke. * @returns the exact value returned by `operation`. @@ -261,6 +276,8 @@ export class AgentRegistry extends Service { /** * Run an operation inside a boundary that hides any inherited initiating * Agent. The exact synchronous value or Promise is preserved. + * If its inherited async chain starts an owning-fiber unload, the nested + * boundary lineage is excluded from the drain so teardown cannot wait on itself. * @param operation - synchronous or asynchronous operation to invoke without an initiator. * @returns the exact value returned by `operation`. * @throws when the initiator scope is closing/disposed, or when `operation` throws. @@ -537,42 +554,77 @@ export class AgentRegistry extends Service { private disposeInitiators(): Promise { return (this.initiatorDisposal ??= (async () => { this.closeInitiators() + this.releaseReentrantInitiatorRuns() if (this.activeInitiatorRuns !== 0) { this.initiatorDrain ??= Promise.withResolvers() await this.initiatorDrain.promise } this.initiatorState = 'disposed' this.initiators.disable() + this.initiatorRuns.disable() })()) } /** Establish one tracked initiator or clearing boundary. */ private runWithInitiator(agent: Agent | undefined, operation: () => T): T { if (this.initiatorState !== 'active') throw new Error(DISPOSED_INITIATOR_MESSAGE) + const run: InitiatorRun = { + active: true, + parent: this.initiatorRuns.getStore(), + } this.activeInitiatorRuns += 1 let result: T try { - result = this.initiators.run(agent, operation) + result = this.initiatorRuns.run(run, () => this.initiators.run(agent, operation)) } catch (error: unknown) { - this.releaseInitiatorRun() + this.releaseInitiatorRun(run) throw error } if (isPromise(result)) { - void result.then( - () => { this.releaseInitiatorRun() }, - () => { this.releaseInitiatorRun() }, - ) + try { + void Promise.prototype.then.call( + result, + () => { this.releaseInitiatorRun(run) }, + () => { this.releaseInitiatorRun(run) }, + ) + } catch { + // A branded Promise may expose a failing @@species. Observer setup did + // not attach, so preserve the exact return without leaking the run. + this.releaseInitiatorRun(run) + } } else { - this.releaseInitiatorRun() + this.releaseInitiatorRun(run) } return result } + /** Whether one unloading fiber owns this service's lifecycle. */ + private hasLifecycleAncestor(candidate: Fiber): boolean { + let fiber = this.ctx.fiber + while (true) { + if (fiber === candidate) return true + const parent = fiber.parent.fiber + if (parent === fiber) return false + fiber = parent + } + } + private assertInitiatorsReadable(): void { if (this.initiatorState === 'disposed') throw new Error(DISPOSED_INITIATOR_MESSAGE) } - private releaseInitiatorRun(): void { + /** Exclude the boundary chain that initiated this teardown from its own drain. */ + private releaseReentrantInitiatorRuns(): void { + let run = this.initiatorRuns.getStore() + while (run !== undefined) { + this.releaseInitiatorRun(run) + run = run.parent + } + } + + private releaseInitiatorRun(run: InitiatorRun): void { + if (!run.active) return + run.active = false this.activeInitiatorRuns -= 1 if (this.activeInitiatorRuns !== 0) return this.initiatorDrain?.resolve() diff --git a/packages/core/agent/tests/agent-initiator.spec.ts b/packages/core/agent/tests/agent-initiator.spec.ts index 87a8387e07..7e0b70d13c 100644 --- a/packages/core/agent/tests/agent-initiator.spec.ts +++ b/packages/core/agent/tests/agent-initiator.spec.ts @@ -23,6 +23,17 @@ async function harness(): Promise<{ } } +/** Fail a lifecycle regression promptly instead of waiting for Vitest's suite timeout. */ +async function promptly(task: Promise): Promise { + const timeout = Promise.withResolvers() + const timer = setTimeout(() => { timeout.reject(new Error('initiator teardown did not settle promptly')) }, 1000) + try { + return await Promise.race([task, timeout.promise]) + } finally { + clearTimeout(timer) + } +} + describe('AgentRegistry initiator scope', () => { it('reports an absent initiator and requires an active boundary', async () => { const { service, dispose } = await harness() @@ -52,6 +63,44 @@ describe('AgentRegistry initiator scope', () => { await dispose() }) + it('tracks a branded Promise without calling its overridable then property', async () => { + const { service, dispose } = await harness() + const initiator = agent('overridden-then') + const release = Promise.withResolvers() + void Object.defineProperty(release.promise, 'then', { + value: () => { throw new Error('overridden then called') }, + }) + + const pending = service.withInitiator(initiator, () => release.promise) + expect(pending).toBe(release.promise) + + let disposed = false + const disposal = dispose().then(() => { disposed = true }) + await Promise.resolve() + expect(disposed).toBe(false) + + release.resolve(true) + await new Promise((resolve, reject) => { + void Promise.prototype.then.call(pending, resolve, reject) + }) + await disposal + expect(disposed).toBe(true) + }) + + it('preserves a settled branded Promise when its species blocks observer construction', async () => { + const { service, dispose } = await harness() + const initiator = agent('invalid-species') + const promise = Promise.resolve() + const constructor = {} + Object.defineProperty(constructor, Symbol.species, { + get: () => { throw new Error('invalid species') }, + }) + void Object.defineProperty(promise, 'constructor', { value: constructor }) + + expect(service.withInitiator(initiator, () => promise)).toBe(promise) + await dispose() + }) + it('isolates overlapping initiators', async () => { const { service, dispose } = await harness() const a = agent('a') @@ -160,4 +209,57 @@ describe('AgentRegistry initiator scope', () => { await disposal expect(disposed).toBe(true) }) + + it('does not self-deadlock when a boundary returns service disposal', async () => { + const { service, dispose } = await harness() + const initiator = agent('service-disposer') + + const returned = service.withInitiator(initiator, dispose) + await promptly(returned) + + expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed') + }) + + it('does not self-deadlock when nested boundaries return ancestor disposal', async () => { + const { ctx, service } = await harness() + const parent = agent('parent-disposer') + const child = agent('child-disposer') + let disposal: Promise | undefined + + const returned = service.withInitiator(parent, () => service.withInitiator(child, () => { + disposal = ctx.fiber.dispose() + return disposal + })) + expect(returned).toBe(disposal) + + await promptly(returned) + expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed') + }) + + it('excludes an asynchronous teardown initiator while draining unrelated boundaries', async () => { + const { ctx, service } = await harness() + const initiator = agent('async-disposer') + const unrelated = agent('unrelated') + const release = Promise.withResolvers() + const pending = service.withInitiator(unrelated, async () => { + await release.promise + expect(service.requireInitiator()).toBe(unrelated) + }) + + const returned = service.withInitiator(initiator, async () => { + await Promise.resolve() + await ctx.fiber.dispose() + }) + let disposed = false + void returned.then(() => { disposed = true }) + await Promise.resolve() + await Promise.resolve() + expect(disposed).toBe(false) + + release.resolve(true) + await pending + await promptly(returned) + + expect(() => service.currentInitiator()).toThrow('agent initiator scope is disposed') + }) }) diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index 328ea6097e..e2d94a84f4 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -6,7 +6,7 @@ Agent service (`ctx.agents`): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L204) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L211) ### ctx.agents.currentInitiator() @@ -18,7 +18,7 @@ Read the Agent that initiated the inherited asynchronous driver chain. **Returns** the inherited Agent, or `undefined` outside a driver and inside an explicit clearing boundary. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L233) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L246) ### ctx.agents.requireInitiator() @@ -30,7 +30,7 @@ Read the initiating Agent and fail when no driver boundary is active. **Returns** the inherited Agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L243) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L256) ### ctx.agents.withInitiator(agent, operation) @@ -38,14 +38,14 @@ Read the initiating Agent and fail when no driver boundary is active. withInitiator(agent: Agent, operation: () => T): T ``` -Run an operation with one exact Agent as its process-local initiator. The exact synchronous value or Promise returned by the operation is preserved. +Run an operation with one exact Agent as its process-local initiator. The exact synchronous value or Promise returned by the operation is preserved. If its inherited async chain starts an owning-fiber unload, the nested boundary lineage is excluded from the drain so teardown cannot wait on itself. - `agent` — initiating Agent to inherit; presence is neither liveness proof nor authorization. - `operation` — synchronous or asynchronous operation to invoke. **Returns** the exact value returned by `operation`. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L257) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L272) ### ctx.agents.withoutInitiator(operation) @@ -53,13 +53,13 @@ Run an operation with one exact Agent as its process-local initiator. The exact withoutInitiator(operation: () => T): T ``` -Run an operation inside a boundary that hides any inherited initiating Agent. The exact synchronous value or Promise is preserved. +Run an operation inside a boundary that hides any inherited initiating Agent. The exact synchronous value or Promise is preserved. If its inherited async chain starts an owning-fiber unload, the nested boundary lineage is excluded from the drain so teardown cannot wait on itself. - `operation` — synchronous or asynchronous operation to invoke without an initiator. **Returns** the exact value returned by `operation`. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L268) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L285) ### ctx.agents.setFactory(factory) @@ -73,7 +73,7 @@ Register the agent-creation factory (the loop calls this on construction, effect **Returns** the disposer that clears the factory slot. The exact Cordis effect disposer (single-shot): composite (generator) effects may yield it directly — exact identity nests the teardown in order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L284) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L301) ### ctx.agents.create(options) @@ -87,7 +87,7 @@ Create and publish a new agent through the registered factory. Distinct from reg **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L317) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L334) ### ctx.agents.resume(options) @@ -101,7 +101,7 @@ Load a persisted session and resume an agent on it through the registered factor **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L336) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L353) ### ctx.agents.register(agent) @@ -115,7 +115,7 @@ Register a live agent. Throws if an agent with the same id is already registered **Returns** the EXACT Cordis effect disposer (single-shot; a repeat call returns undefined without awaiting an in-flight teardown). Exact identity is load-bearing: a composite (generator) effect that owns a teardown ORDER — the agent factory's lifecycle chain — must yield THIS function so Cordis nests the unregistration at that yield position; yielding a wrapper would leave it disposing as a concurrent sibling on owner unload, unregistering the agent (and emitting `agent/disposed`) while its final turn is still draining. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L362) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L379) ### ctx.agents.enter(agent, owner) @@ -130,7 +130,7 @@ Insert an already-constructed agent without announcing it. This is the advanced **Returns** an idempotent closure that removes this exact entry and emits `agent/disposed` with listener failures contained. When called from a synchronous `agent/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L386) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L403) ### ctx.agents.announce(agent) @@ -142,7 +142,7 @@ Announce an agent previously inserted with enter. - `agent` — the live inserted agent to announce. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L461) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L478) ### ctx.agents.get(id) @@ -156,7 +156,7 @@ Look up a live agent. **Returns** the agent, or undefined when no live agent has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L495) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L512) ### ctx.agents.isOwnedBy(id, owner) @@ -171,7 +171,7 @@ Test whether a live agent was created through one exact parent agent's scoped co **Returns** true only while the exact child entry is live under that owner. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L507) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L524) ### ctx.agents.list() @@ -183,7 +183,7 @@ All live agents, in registration order. **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L515) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L532) ### ctx.agents.roots() @@ -195,4 +195,4 @@ All live top-level agents in registration order. A top-level agent was created w **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L525) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L542) From bf93605f8cffea1c977c8957873f5085557b0504 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 15:12:29 +0800 Subject: [PATCH 251/323] docs: keep architecture within its budget Condense the app-bundle sentence after combining the current-master CLI wiring with the recovery architecture changes. The text still identifies the TUI, line-oriented, headless, and ACP front doors and their output contracts. This restores the enforced architecture.md word ceiling without raising the budget or relocating an architecture-level seam fact. --- docs/architecture.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/architecture.md b/docs/architecture.md index 415d3b2aee..f65a901315 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -156,7 +156,7 @@ Some seams bend the template deliberately: LLM combines interface and consumer b ### Bundles And Apps -`dsh-agent-spine-demo` bundles the default spine ([README](../packages/examples/agent-spine-demo/README.md)). `dsh-stdio-demo` adds a terminal front door that selects `dsh-tui` for interactive terminals and line-oriented `dsh-stdio` for pipes; `dsh-cli-demo` runs one persisted headless turn with format-pure stdout; and `dsh-acp-demo` adds stdout-pure ACP over JSON-RPC ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` boots external `cordis.yml`; the Python SDK supplies its default only without an explicit config channel and drives `dsh-jsonrpc` over line-delimited JSON-RPC ([Python SDK](../python/README.md)). Deployments remain thin leaves with swappable backends and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). +`dsh-agent-spine-demo` bundles the default spine ([README](../packages/examples/agent-spine-demo/README.md)). `dsh-stdio-demo` selects `dsh-tui` for interactive terminals and line-oriented `dsh-stdio` for pipes; `dsh-cli-demo` runs one persisted headless turn with format-pure stdout; `dsh-acp-demo` adds stdout-pure ACP over JSON-RPC ([ui/](../packages/ui/README.md)). `dsh-jsonrpc-agent` boots external `cordis.yml`; the Python SDK supplies its default only without an explicit config channel and drives `dsh-jsonrpc` over line-delimited JSON-RPC ([Python SDK](../python/README.md)). Deployments remain thin leaves with swappable backends and optional product tools ([examples/](../examples/AGENTS.md), [runnable wirings](cookbook/extension-cookbook.md#runnable-wirings), [graph atlas](graph-atlas.md)). ### Where New Behavior Goes From e1a4a2963d2105056a5e85da2a7c47232f5095f6 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 15:34:08 +0800 Subject: [PATCH 252/323] docs(core): document initiator API scenarios --- docs/cordis-catalog/services.md | 28 +++++++--- packages/core/agent/src/index.ts | 30 ++++++++--- website/zh-CN/api/harness/agents.md | 82 ++++++++++++++++++++++------- 3 files changed, 107 insertions(+), 33 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 30ca04ba79..84f38ec859 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -50,16 +50,25 @@ Source: [`packages/core/agent-loop/src/index.ts:407`](../../packages/core/agent- Agent service (`ctx.agents`): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. +Initiator methods provide same-process causal attribution only. Ambient presence is neither liveness proof nor authorization; subjects and owners remain explicit, as does identity at worker, process, persistence, and wire boundaries. Returned Promise boundaries drain during teardown, except a nested lineage that starts an owning-fiber unload is excluded from its own drain. + ```ts cordis-catalog /** * Read the Agent that initiated the inherited asynchronous driver chain. - * @returns the inherited Agent, or `undefined` outside a driver and inside an explicit clearing boundary. + * Use this optional form for logging, tracing, metrics, or host attribution + * that also supports agentless calls. When a parent creates a child, setup + * reports the causal parent while `agentCtx.agent` identifies the child. + * @returns the inherited Agent, or `undefined` outside an initiator boundary + * and inside an explicit clearing boundary. * @throws when this service instance has been disposed. */ currentInitiator(): Agent | undefined /** - * Read the initiating Agent and fail when no driver boundary is active. + * Read the initiating Agent and fail when no initiator boundary is active. + * Use this for private helpers contractually below a driver, or for a + * deployment-owned outbound request whose contract forbids agentless calls. + * Generic or direct-call seams use optional lookup or explicit request fields. * @returns the inherited Agent. * @throws when no initiator is active or this service instance has been disposed. */ @@ -68,8 +77,11 @@ requireInitiator(): Agent /** * Run an operation with one exact Agent as its process-local initiator. The * exact synchronous value or Promise returned by the operation is preserved. - * If its inherited async chain starts an owning-fiber unload, the nested - * boundary lineage is excluded from the drain so teardown cannot wait on itself. + * Custom drivers and test harnesses wrap their complete returned foreground + * lifetime. + * A queue or wire receiver may establish this boundary only after validating + * explicit identity and resolving the exact live Agent; this method does neither. + * Detached work remains owned by the subsystem that starts it. * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization. * @param operation - synchronous or asynchronous operation to invoke. * @returns the exact value returned by `operation`. @@ -80,8 +92,10 @@ withInitiator(agent: Agent, operation: () => T): T /** * Run an operation inside a boundary that hides any inherited initiating * Agent. The exact synchronous value or Promise is preserved. - * If its inherited async chain starts an owning-fiber unload, the nested - * boundary lineage is excluded from the drain so teardown cannot wait on itself. + * Use this while creating lazy shared timers, queue pumps, pool maintenance, + * watchers, or exporters so they do not inherit the first Agent that happens + * to initialize them. It clears only initiator attribution, not explicit + * fields, and does not own or drain detached resources. * @param operation - synchronous or asynchronous operation to invoke without an initiator. * @returns the exact value returned by `operation`. * @throws when the initiator scope is closing/disposed, or when `operation` throws. @@ -202,7 +216,7 @@ roots(): Agent[] Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:211`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:217`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 24087011b7..75f00daebb 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -207,6 +207,12 @@ interface FactorySlot { * Agent through one process-local asynchronous driver chain. Agent *creation* * is provided by whichever plugin implements the {@link AgentFactory} * (`@deepseek-ai/dsh-agent-loop`), registered via {@link setFactory}. + * + * Initiator methods provide same-process causal attribution only. Ambient + * presence is neither liveness proof nor authorization; subjects and owners + * remain explicit, as does identity at worker, process, persistence, and wire + * boundaries. Returned Promise boundaries drain during teardown, except a + * nested lineage that starts an owning-fiber unload is excluded from its own drain. */ export class AgentRegistry extends Service { private store = new Map() @@ -240,7 +246,11 @@ export class AgentRegistry extends Service { /** * Read the Agent that initiated the inherited asynchronous driver chain. - * @returns the inherited Agent, or `undefined` outside a driver and inside an explicit clearing boundary. + * Use this optional form for logging, tracing, metrics, or host attribution + * that also supports agentless calls. When a parent creates a child, setup + * reports the causal parent while `agentCtx.agent` identifies the child. + * @returns the inherited Agent, or `undefined` outside an initiator boundary + * and inside an explicit clearing boundary. * @throws when this service instance has been disposed. */ currentInitiator(): Agent | undefined { @@ -249,7 +259,10 @@ export class AgentRegistry extends Service { } /** - * Read the initiating Agent and fail when no driver boundary is active. + * Read the initiating Agent and fail when no initiator boundary is active. + * Use this for private helpers contractually below a driver, or for a + * deployment-owned outbound request whose contract forbids agentless calls. + * Generic or direct-call seams use optional lookup or explicit request fields. * @returns the inherited Agent. * @throws when no initiator is active or this service instance has been disposed. */ @@ -262,8 +275,11 @@ export class AgentRegistry extends Service { /** * Run an operation with one exact Agent as its process-local initiator. The * exact synchronous value or Promise returned by the operation is preserved. - * If its inherited async chain starts an owning-fiber unload, the nested - * boundary lineage is excluded from the drain so teardown cannot wait on itself. + * Custom drivers and test harnesses wrap their complete returned foreground + * lifetime. + * A queue or wire receiver may establish this boundary only after validating + * explicit identity and resolving the exact live Agent; this method does neither. + * Detached work remains owned by the subsystem that starts it. * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization. * @param operation - synchronous or asynchronous operation to invoke. * @returns the exact value returned by `operation`. @@ -276,8 +292,10 @@ export class AgentRegistry extends Service { /** * Run an operation inside a boundary that hides any inherited initiating * Agent. The exact synchronous value or Promise is preserved. - * If its inherited async chain starts an owning-fiber unload, the nested - * boundary lineage is excluded from the drain so teardown cannot wait on itself. + * Use this while creating lazy shared timers, queue pumps, pool maintenance, + * watchers, or exporters so they do not inherit the first Agent that happens + * to initialize them. It clears only initiator attribution, not explicit + * fields, and does not own or drain detached resources. * @param operation - synchronous or asynchronous operation to invoke without an initiator. * @returns the exact value returned by `operation`. * @throws when the initiator scope is closing/disposed, or when `operation` throws. diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index 923bd2748b..bba6a7a5d4 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -5,61 +5,103 @@ `AgentRegistry` — provided by `@deepseek-ai/dsh-agent`. Agent service (`ctx.agents`): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. +Initiator methods provide same-process causal attribution only. Ambient presence is neither liveness proof nor authorization; subjects and owners remain explicit, as does identity at worker, process, persistence, and wire boundaries. Returned Promise boundaries drain during teardown, except a nested lineage that starts an owning-fiber unload is excluded from its own drain. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L211) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L217) ### ctx.agents.currentInitiator() ```ts website-api +/** + * Read the Agent that initiated the inherited asynchronous driver chain. + * Use this optional form for logging, tracing, metrics, or host attribution + * that also supports agentless calls. When a parent creates a child, setup + * reports the causal parent while `agentCtx.agent` identifies the child. + * @returns the inherited Agent, or `undefined` outside an initiator boundary + * and inside an explicit clearing boundary. + * @throws when this service instance has been disposed. + */ currentInitiator(): Agent | undefined ``` -Read the Agent that initiated the inherited asynchronous driver chain. +Read the Agent that initiated the inherited asynchronous driver chain. Use this optional form for logging, tracing, metrics, or host attribution that also supports agentless calls. When a parent creates a child, setup reports the causal parent while `agentCtx.agent` identifies the child. -**Returns** the inherited Agent, or `undefined` outside a driver and inside an explicit clearing boundary. +**Returns** the inherited Agent, or `undefined` outside an initiator boundary and inside an explicit clearing boundary. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L246) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L256) ### ctx.agents.requireInitiator() ```ts website-api +/** + * Read the initiating Agent and fail when no initiator boundary is active. + * Use this for private helpers contractually below a driver, or for a + * deployment-owned outbound request whose contract forbids agentless calls. + * Generic or direct-call seams use optional lookup or explicit request fields. + * @returns the inherited Agent. + * @throws when no initiator is active or this service instance has been disposed. + */ requireInitiator(): Agent ``` -Read the initiating Agent and fail when no driver boundary is active. +Read the initiating Agent and fail when no initiator boundary is active. Use this for private helpers contractually below a driver, or for a deployment-owned outbound request whose contract forbids agentless calls. Generic or direct-call seams use optional lookup or explicit request fields. **Returns** the inherited Agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L256) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L269) ### ctx.agents.withInitiator(agent, operation) ```ts website-api +/** + * Run an operation with one exact Agent as its process-local initiator. The + * exact synchronous value or Promise returned by the operation is preserved. + * Custom drivers and test harnesses wrap their complete returned foreground + * lifetime. + * A queue or wire receiver may establish this boundary only after validating + * explicit identity and resolving the exact live Agent; this method does neither. + * Detached work remains owned by the subsystem that starts it. + * @param agent - initiating Agent to inherit; presence is neither liveness proof nor authorization. + * @param operation - synchronous or asynchronous operation to invoke. + * @returns the exact value returned by `operation`. + * @throws when the initiator scope is closing/disposed, or when `operation` throws. + */ withInitiator(agent: Agent, operation: () => T): T ``` -Run an operation with one exact Agent as its process-local initiator. The exact synchronous value or Promise returned by the operation is preserved. If its inherited async chain starts an owning-fiber unload, the nested boundary lineage is excluded from the drain so teardown cannot wait on itself. +Run an operation with one exact Agent as its process-local initiator. The exact synchronous value or Promise returned by the operation is preserved. Custom drivers and test harnesses wrap their complete returned foreground lifetime. A queue or wire receiver may establish this boundary only after validating explicit identity and resolving the exact live Agent; this method does neither. Detached work remains owned by the subsystem that starts it. - `agent` — initiating Agent to inherit; presence is neither liveness proof nor authorization. - `operation` — synchronous or asynchronous operation to invoke. **Returns** the exact value returned by `operation`. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L272) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L288) ### ctx.agents.withoutInitiator(operation) ```ts website-api +/** + * Run an operation inside a boundary that hides any inherited initiating + * Agent. The exact synchronous value or Promise is preserved. + * Use this while creating lazy shared timers, queue pumps, pool maintenance, + * watchers, or exporters so they do not inherit the first Agent that happens + * to initialize them. It clears only initiator attribution, not explicit + * fields, and does not own or drain detached resources. + * @param operation - synchronous or asynchronous operation to invoke without an initiator. + * @returns the exact value returned by `operation`. + * @throws when the initiator scope is closing/disposed, or when `operation` throws. + */ withoutInitiator(operation: () => T): T ``` -Run an operation inside a boundary that hides any inherited initiating Agent. The exact synchronous value or Promise is preserved. If its inherited async chain starts an owning-fiber unload, the nested boundary lineage is excluded from the drain so teardown cannot wait on itself. +Run an operation inside a boundary that hides any inherited initiating Agent. The exact synchronous value or Promise is preserved. Use this while creating lazy shared timers, queue pumps, pool maintenance, watchers, or exporters so they do not inherit the first Agent that happens to initialize them. It clears only initiator attribution, not explicit fields, and does not own or drain detached resources. - `operation` — synchronous or asynchronous operation to invoke without an initiator. **Returns** the exact value returned by `operation`. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L285) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L303) ### ctx.agents.setFactory(factory) @@ -85,7 +127,7 @@ Register the agent-creation factory (the loop calls this on construction, effect **Returns** the disposer that clears the factory slot. The exact Cordis effect disposer (single-shot): composite (generator) effects may yield it directly — exact identity nests the teardown in order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L301) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L319) ### ctx.agents.create(options) @@ -108,7 +150,7 @@ Create and publish a new agent through the registered factory. Distinct from reg **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L334) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L352) ### ctx.agents.resume(options) @@ -129,7 +171,7 @@ Load a persisted session and resume an agent on it through the registered factor **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L353) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L371) ### ctx.agents.register(agent) @@ -161,7 +203,7 @@ Register a live agent. Throws if an agent with the same id is already registered **Returns** the EXACT Cordis effect disposer (single-shot; a repeat call returns undefined without awaiting an in-flight teardown). Exact identity is load-bearing: a composite (generator) effect that owns a teardown ORDER — the agent factory's lifecycle chain — must yield THIS function so Cordis nests the unregistration at that yield position; yielding a wrapper would leave it disposing as a concurrent sibling on owner unload, unregistering the agent (and emitting `agent/disposed`) while its final turn is still draining. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L379) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L397) ### ctx.agents.enter(agent, owner) @@ -191,7 +233,7 @@ Insert an already-constructed agent without announcing it. This is the advanced **Returns** an idempotent closure that removes this exact entry and emits `agent/disposed` with listener failures contained. When called from a synchronous `agent/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L403) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L421) ### ctx.agents.announce(agent) @@ -210,7 +252,7 @@ Announce an agent previously inserted with enter. - `agent` — the live inserted agent to announce. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L478) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L496) ### ctx.agents.get(id) @@ -229,7 +271,7 @@ Look up a live agent. **Returns** the agent, or undefined when no live agent has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L512) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L530) ### ctx.agents.isOwnedBy(id, owner) @@ -252,7 +294,7 @@ Test whether a live agent was created through one exact parent agent's scoped co **Returns** true only while the exact child entry is live under that owner. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L524) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L542) ### ctx.agents.list() @@ -268,7 +310,7 @@ All live agents, in registration order. **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L532) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L550) ### ctx.agents.roots() @@ -286,4 +328,4 @@ All live top-level agents in registration order. A top-level agent was created w **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L542) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L560) From d2672460fed59aecc8ddcfd7325589d3afb7a8b6 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 15:36:48 +0800 Subject: [PATCH 253/323] fix(cli-demo): accept disabled task controls --- packages/examples/cli-demo/src/index.ts | 2 +- packages/examples/cli-demo/tests/cli-demo.spec.ts | 15 +++++++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) diff --git a/packages/examples/cli-demo/src/index.ts b/packages/examples/cli-demo/src/index.ts index 1308209681..e5c77af9ed 100644 --- a/packages/examples/cli-demo/src/index.ts +++ b/packages/examples/cli-demo/src/index.ts @@ -61,7 +61,7 @@ export const Config: z = z.object({ toolOrder: z.array(z.string()).default(undefined as unknown as string[]), tools: ToolRegistry.Config, toolBash: agentCore.ToolBashConfigSchema, - toolTasks: agentCore.ToolTasksConfigSchema, + toolTasks: z.union([z.const(false), agentCore.ToolTasksConfigSchema]), workspaceContext: z.union([z.const(false), workspaceContext.Config]).required(), }) /* jscpd:ignore-end */ diff --git a/packages/examples/cli-demo/tests/cli-demo.spec.ts b/packages/examples/cli-demo/tests/cli-demo.spec.ts index 343d6184d7..2111ff6aa8 100644 --- a/packages/examples/cli-demo/tests/cli-demo.spec.ts +++ b/packages/examples/cli-demo/tests/cli-demo.spec.ts @@ -146,6 +146,21 @@ describe('dsh-cli-demo app composition', () => { expect(wait).toHaveBeenCalledWith(id, 7, undefined, undefined) }) + it('accepts false to keep task services without model-facing task controls', async () => { + const ctx = await mount({ + provider: 'mock', + model: 'mock', + skills: { enabled: false }, + toolTasks: false, + workspaceContext: false, + }) + + expect(ctx.get('tasks')).toBeDefined() + expect(ctx.get('tools')?.get('task_output')).toBeUndefined() + expect(ctx.get('tools')?.get('task_list')).toBeUndefined() + expect(ctx.get('tools')?.get('task_kill')).toBeUndefined() + }) + it('exposes the Loader-safe namespace plugin shape and schema', () => { expect(cliDemo.name).toBe('cli-demo') expect(cliDemo.Config).toBeDefined() From ee6b9d081a254279a21452e3f0aa76b3ea907a63 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 16:14:58 +0800 Subject: [PATCH 254/323] fix(llm): scope adapter failures to model calls Replace the process-wide adapter-failure WeakSet with a per-call scope bound to the exact AsyncIterable returned by LlmService.stream(). Give every call a unique wrapper so waterfall middleware can reuse an iterable without sharing provenance. Move agent-loop recovery classification to the model-stream boundary. Only the final adapter behind that exact call can become an agent/request-error; nested llm/stream calls remain ordinary outer middleware failures while preserving the original Error. Cover nested calls, reused middleware iterables, and end-to-end agent-loop recovery. Update the package and RFC contracts, bilingual pairing record, and generated API and catalog references. --- docs/cordis-catalog/events.md | 2 +- docs/cordis-catalog/services.md | 7 +- docs/event-producer-consumer.md | 2 +- ...n-pressure-and-overflow-recovery.i18n.yaml | 4 +- ...mpaction-pressure-and-overflow-recovery.md | 2 +- ...ction-pressure-and-overflow-recovery.zh.md | 2 +- packages/core/agent-loop/src/loop.ts | 24 ++-- .../agent-loop/tests/request-recovery.spec.ts | 36 +++++ packages/llm/llm/README.md | 2 +- packages/llm/llm/src/adapter-failure.ts | 49 +++++-- packages/llm/llm/src/index.ts | 21 ++- packages/llm/llm/tests/service.spec.ts | 124 ++++++++++++++++-- website/zh-CN/api/harness/events.md | 2 +- website/zh-CN/api/harness/llm.md | 12 +- 14 files changed, 233 insertions(+), 56 deletions(-) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 1acfb39a3d..20a92bffb8 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -471,7 +471,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:42`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:43`](../../packages/llm/llm/src/index.ts) ## `session/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 60b6fcbd4e..d07d0c2164 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -461,8 +461,9 @@ async listModels(provider: string): Promise * `options.provider`. Replay state is retained only when the same adapter * instance owns its historical provider and the target provider. Final * adapter selection, dispatch, and iteration failures retain their original - * Error identity and are tagged for narrow agent-loop request recovery; - * middleware failures remain untagged. + * Error identity and are tagged in a call-local scope for narrow agent-loop + * request recovery; middleware and nested-call failures remain untagged for + * the outer call. * @param options - the full request; `options.provider` selects the adapter. * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. */ @@ -471,7 +472,7 @@ stream(options: GenerateOptions): AsyncIterable Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:96`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:97`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index b10fd76897..5b5a899b44 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -27,7 +27,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:61`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:70`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:53`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | -| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:42`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | +| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:43`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:47`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`tui`](../packages/ui/tui), [`workspace-context`](../packages/context/workspace-context) | diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml index aa45a7ccb2..c54a0b344d 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: abc374d98fed8cac039f10d930fec332515c846e -2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: ef13c64fc4c728e5b4fe9718ae8ef8b8ef9ecdd9 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md: d88d7aaea8ccec30b10bfeb17f1312cfe87a0ce7 +2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md: 42e6114304de9c8022ef8f1341035858c0c7d9ec diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md index abc374d98f..d88d7aaea8 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.md @@ -22,7 +22,7 @@ The loop fires awaited serial `agent/post-step(agent, turn, step, signal)` after ### Request recovery is limited to the final model boundary -`RequestError`, `RequestErrorDecision`, and the `agent/request-error` waterfall represent failures after the final adapter has been selected. Private `WeakSet` tagging preserves the original thrown error identity across dispatch, iterator construction, and iteration. Terminal in-band `error` or `aborted` finishes enter the same path. Prompt assembly, request middleware, request logging, result processing, tools, post-step listeners, and cleanup remain ordinary failures. +`RequestError`, `RequestErrorDecision`, and the `agent/request-error` waterfall represent failures after the final adapter has been selected. Each returned stream handle owns a private failure set that preserves the original thrown error identity across dispatch, iterator construction, and iteration without leaking nested-call provenance into an outer call. Terminal in-band `error` or `aborted` finishes enter the same path. Prompt assembly, request middleware, request logging, result processing, tools, post-step listeners, and cleanup remain ordinary failures. The failed step closes before recovery runs. A retry opens the next numbered step and rebuilds the request from the durable log; consecutive recovery attempts reset only after a successful provider request. Both DeepSeek adapters normalize recognized provider context-limit failures to `CONTEXT_WINDOW_EXCEEDED`. diff --git a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md index ef13c64fc4..42e6114304 100644 --- a/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-10-after-call-compaction-pressure-and-overflow-recovery.zh.md @@ -22,7 +22,7 @@ Status: implemented ### 请求恢复只覆盖最终模型边界 -`RequestError`、`RequestErrorDecision` 与 `agent/request-error` waterfall 表示最终适配器已经选定之后的失败。私有 `WeakSet` 标记在分发、异步迭代器构造与迭代过程中保留原始抛出错误的身份。终止性的带内 `error` 或 `aborted` finish 进入同一路径。提示词装配、请求中间件、请求日志、结果处理、工具、post-step 监听器与清理仍属于普通失败。 +`RequestError`、`RequestErrorDecision` 与 `agent/request-error` waterfall 表示最终适配器已经选定之后的失败。每个返回的流句柄都绑定一个私有失败集合；该集合在分发、异步迭代器构造与迭代过程中保留原始抛出错误的身份，同时防止把嵌套调用的错误来源误归到外层调用。终止性的带内 `error` 或 `aborted` finish 进入同一路径。提示词装配、请求中间件、请求日志、结果处理、工具、post-step 监听器与清理仍属于普通失败。 恢复运行前，失败 step 已经关闭。重试会打开下一个编号 step，并从持久日志重建请求；连续恢复尝试计数只在提供方请求成功后重置。两个 DeepSeek 适配器都把识别出的提供方上下文限制错误规范化为 `CONTEXT_WINDOW_EXCEEDED`。 diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 08c1ab9412..3d34026df0 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -27,7 +27,7 @@ function toError(error: unknown): RequestError { return error instanceof Error ? error : new HarnessError(String(error), 'UNKNOWN', { cause: error }) } -/** Distinguishes a terminal failure finish from failures in later step processing. */ +/** Distinguishes final model-request failures from failures in later step processing. */ class TerminalModelRequestFailure extends Error { constructor(readonly requestError: RequestError) { super(requestError.message, { cause: requestError }) @@ -347,9 +347,7 @@ async function runTurn( stepOutcome = await runStep( ctx, events, agent, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal) } catch (error: unknown) { - if (isLlmAdapterFailure(error)) { - stepOutcome = { requestError: error } - } else if (error instanceof TerminalModelRequestFailure) { + if (error instanceof TerminalModelRequestFailure) { stepOutcome = { requestError: error.requestError } } else { stepOutcome = { error: toError(error) } @@ -624,12 +622,18 @@ async function runStep( // --- Model call (streaming-first; raw chunks are the replay record) --- const assembler = new BlockAssembler() const chunkSeqs: number[] = [] - for await (const chunk of ctx.llm.stream(request)) { - /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ - if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) - const chunkEvent = session.append('assistant/chunk', { turn, step, chunk }) - chunkSeqs.push(chunkEvent.seq) - assembler.push(chunk) + const stream = ctx.llm.stream(request) + try { + for await (const chunk of stream) { + /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ + if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) + const chunkEvent = session.append('assistant/chunk', { turn, step, chunk }) + chunkSeqs.push(chunkEvent.seq) + assembler.push(chunk) + } + } catch (error: unknown) { + if (isLlmAdapterFailure(stream, error)) throw new TerminalModelRequestFailure(error) + throw error } // Normalize failure finish chunks into the same path as thrown stream errors. diff --git a/packages/core/agent-loop/tests/request-recovery.spec.ts b/packages/core/agent-loop/tests/request-recovery.spec.ts index 442fba7565..bfbcad23ba 100644 --- a/packages/core/agent-loop/tests/request-recovery.spec.ts +++ b/packages/core/agent-loop/tests/request-recovery.spec.ts @@ -307,6 +307,42 @@ describe('agent post-step and request-error lifecycle', () => { expect(agent.session.events.at(-1)).toMatchObject({ type: 'turn/end', data: { reason: { kind: 'error' } } }) }) + it('does not offer a nested model-call failure as the outer request failure', async () => { + const outer = new FailureScriptAdapter([textResponse('outer adapter must not run')]) + const nested = new FailureScriptAdapter([contextError('nested overflow')]) + const ctx = await harness(outer) + ctx.llm.registerAdapter(['nested'], nested) + ctx.on('llm/stream', (options, next) => { + if (options.provider !== 'mock') return next() + return (async function* () { + yield* ctx.llm.stream({ + provider: 'nested', + model: 'nested', + messages: [], + ...options.signal === undefined ? {} : { signal: options.signal }, + }) + yield* next() + })() + }) + const agent = ctx.agentLoop.create(SessionId('nested-stream-not-recoverable'), { provider: 'mock', model: 'mock' }) + let recoveries = 0 + ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _attempt, _signal, next) => { + recoveries += 1 + return next() + }) + + send(agent) + await waitForIdle(ctx, agent) + + expect(nested.requests).toHaveLength(1) + expect(outer.requests).toHaveLength(0) + expect(recoveries).toBe(0) + expect(agent.session.events.at(-1)).toMatchObject({ + type: 'turn/end', + data: { reason: { kind: 'error', message: 'nested overflow', code: CONTEXT_WINDOW_EXCEEDED_CODE } }, + }) + }) + it.each(['prompt-submit', 'prompt-assembly', 'pre-step', 'request'] as const)( 'does not offer %s middleware failures to request recovery', async (boundary) => { diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 83f5259f8d..44e7d80a05 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -13,7 +13,7 @@ An adapter registry plus a single streaming call surface, interceptable via a wa - `ctx.llm.listModels(provider: string): Promise` Discover the models one registered provider currently advertises. - `ctx.llm.stream(options: GenerateOptions): AsyncIterable` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`. -`LlmService` preserves and privately tags errors from final adapter selection, synchronous dispatch, iterator construction, and iteration. `isLlmAdapterFailure(value)` exposes that provenance without classifying `llm/stream` middleware or downstream consumer failures as provider failures, and without replacing the adapter's original coded `Error`. +`LlmService` preserves errors from final adapter selection, synchronous dispatch, iterator construction, and iteration, and binds their provenance to the exact stream handle returned for that model call. `isLlmAdapterFailure(stream, value)` reports only errors from that call's final adapter boundary; nested model calls, `llm/stream` middleware, and downstream consumer failures remain unclassified for the outer call. Classification does not replace the adapter's original coded `Error`. Provider and model metadata is a discovery surface, not a routing whitelist. `registerAdapter()` still owns provider exclusivity, while an adapter may accept model ids absent from `listModels()`; consumers must not reject a request because its model is unlisted. Returned metadata is detached and invalid or duplicate adapter entries fail with `INVALID_ADAPTER` or `INVALID_CATALOG`. diff --git a/packages/llm/llm/src/adapter-failure.ts b/packages/llm/llm/src/adapter-failure.ts index 240f934c39..745cbbdc64 100644 --- a/packages/llm/llm/src/adapter-failure.ts +++ b/packages/llm/llm/src/adapter-failure.ts @@ -5,30 +5,63 @@ */ import { HarnessError } from './error.ts' +import type { StreamChunk } from './types.ts' -/** Errors proven to originate in final adapter dispatch or iteration. */ -const adapterFailures = new WeakSet() +/** Errors proven to originate in one model call's final adapter boundary. */ +export type AdapterFailureScope = WeakSet + +/** Call-local failure scopes keyed by the exact stream handle returned to a consumer. */ +const adapterFailureScopes = new WeakMap, AdapterFailureScope>() + +/** + * Bind one call's adapter-failure scope to a unique returned stream handle. + * @param stream - the waterfall-selected stream for this call. + * @param failures - errors tagged by this call's final adapter boundary. + * @returns a unique stream handle that delegates iteration to `stream`. + * @internal + */ +export function bindAdapterFailureScope( + stream: AsyncIterable, + failures: AdapterFailureScope, +): AsyncIterable { + const call = { + [Symbol.asyncIterator](): AsyncIterator { + return stream[Symbol.asyncIterator]() + }, + } + adapterFailureScopes.set(call, failures) + return call +} /** * Preserve an adapter's Error identity while tagging its provider origin. + * @param failures - the call-local final-adapter failure scope. * @param value - arbitrary value thrown by adapter dispatch or iteration. * @returns the original Error, or a coded Error wrapping a non-Error throw. * @internal */ -export function markLlmAdapterFailure(value: unknown): Error & { code?: string } { +export function markLlmAdapterFailure( + failures: AdapterFailureScope, + value: unknown, +): Error & { code?: string } { const error = value instanceof Error ? value as Error & { code?: string } : new HarnessError(String(value), 'UNKNOWN', { cause: value }) - adapterFailures.add(error) + failures.add(error) return error } /** * Whether a failure came from final adapter dispatch, iterator construction, - * or iteration rather than from an `llm/stream` waterfall listener. + * or iteration for the call represented by the exact returned stream handle. + * @param stream - the exact stream returned by the model call being classified. * @param value - arbitrary failure caught by a model-call consumer. - * @returns true only for errors tagged at the final adapter boundary. + * @returns true only for errors tagged at that call's final adapter boundary. */ -export function isLlmAdapterFailure(value: unknown): value is Error & { code?: string } { - return value instanceof Error && adapterFailures.has(value) +export function isLlmAdapterFailure( + stream: AsyncIterable, + value: unknown, +): value is Error & { code?: string } { + const failures = adapterFailureScopes.get(stream) + return value instanceof Error && failures !== undefined && failures.has(value) } diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 135b620f45..ac31738a61 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -10,7 +10,8 @@ import { Context, Service } from 'cordis' import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, Message, StreamChunk } from './types.ts' import { deepFreeze } from './call-config.ts' import { HarnessError } from './error.ts' -import { markLlmAdapterFailure } from './adapter-failure.ts' +import { bindAdapterFailureScope, markLlmAdapterFailure } from './adapter-failure.ts' +import type { AdapterFailureScope } from './adapter-failure.ts' export * from './attribution.ts' export * from './brand.ts' @@ -206,14 +207,17 @@ export class LlmService extends Service { * so it cannot suppress the primary provider error. A downstream close awaits * adapter cleanup, whose failures remain ordinary untagged work. */ - private async * adapterStream(options: GenerateOptions): AsyncGenerator { + private async * adapterStream( + options: GenerateOptions, + failures: AdapterFailureScope, + ): AsyncGenerator { let iterator: AsyncIterator try { const adapter = this.registration(options.provider).adapter const stream = adapter.stream(this.forAdapter(options, adapter)) iterator = stream[Symbol.asyncIterator]() } catch (error: unknown) { - throw markLlmAdapterFailure(error) + throw markLlmAdapterFailure(failures, error) } let completed = false @@ -230,7 +234,7 @@ export class LlmService extends Service { value = item.value } catch (error: unknown) { iterationFailed = true - throw markLlmAdapterFailure(error) + throw markLlmAdapterFailure(failures, error) } // End the adapter-owned try before yielding: consumer/middleware // failures resumed into this generator must remain untagged. @@ -251,13 +255,16 @@ export class LlmService extends Service { * `options.provider`. Replay state is retained only when the same adapter * instance owns its historical provider and the target provider. Final * adapter selection, dispatch, and iteration failures retain their original - * Error identity and are tagged for narrow agent-loop request recovery; - * middleware failures remain untagged. + * Error identity and are tagged in a call-local scope for narrow agent-loop + * request recovery; middleware and nested-call failures remain untagged for + * the outer call. * @param options - the full request; `options.provider` selects the adapter. * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. */ stream(options: GenerateOptions): AsyncIterable { - return this.ctx.waterfall(this, 'llm/stream', options, () => this.adapterStream(options)) + const failures: AdapterFailureScope = new WeakSet() + const stream = this.ctx.waterfall(this, 'llm/stream', options, () => this.adapterStream(options, failures)) + return bindAdapterFailureScope(stream, failures) } } diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 0431d4faba..6e14d749ba 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -30,6 +30,16 @@ class RecordingAdapter extends ScriptedAdapter { } } +class ThrowingAdapter extends LlmAdapter { + constructor(private readonly failure: Error) { + super() + } + + stream(_options: GenerateOptions): AsyncIterable { + throw this.failure + } +} + class CatalogAdapter extends ScriptedAdapter { constructor( private readonly provider: LlmProviderInfo, @@ -83,16 +93,17 @@ describe('LlmService', () => { it('throws NO_ADAPTER for unregistered providers', async () => { const ctx = new Context() await ctx.plugin(LlmService) + const stream = ctx.llm.stream({ provider: 'nope', model: 'any-model', messages: [] }) let caught: unknown try { - for await (const _ of ctx.llm.stream({ provider: 'nope', model: 'any-model', messages: [] })) { /* drain */ } + for await (const _ of stream) { /* drain */ } } catch (error: unknown) { caught = error } expect(caught).toBeInstanceOf(LlmError) expect((caught as LlmError).code).toBe('NO_ADAPTER') expect((caught as LlmError).message).toContain('no adapter registered') - expect(isLlmAdapterFailure(caught)).toBe(true) + expect(isLlmAdapterFailure(stream, caught)).toBe(true) }) it.each(['done', 'value'] as const)('tags a throwing IteratorResult.%s getter without replacing its Error', async (field) => { @@ -122,15 +133,16 @@ describe('LlmService', () => { await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], adapter) + const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] }) let caught: unknown try { - for await (const _chunk of ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })) { /* drain */ } + for await (const _chunk of stream) { /* drain */ } } catch (error: unknown) { caught = error } expect(caught).toBe(original) - expect(isLlmAdapterFailure(caught)).toBe(true) + expect(isLlmAdapterFailure(stream, caught)).toBe(true) expect(cleanupLookups).toBe(0) }) @@ -146,15 +158,91 @@ describe('LlmService', () => { await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], adapter) + const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] }) let caught: unknown try { - for await (const _chunk of ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })) { /* drain */ } + for await (const _chunk of stream) { /* drain */ } } catch (error: unknown) { caught = error } expect(caught).toBe(original) - expect(isLlmAdapterFailure(caught)).toBe(true) + expect(isLlmAdapterFailure(stream, caught)).toBe(true) + }) + + it('keeps a nested adapter failure scoped to the nested model call', async () => { + const original = new LlmError('nested provider failed', 'NESTED_FAILED') + const outer = new RecordingAdapter(SCRIPT) + const nested = new ThrowingAdapter(original) + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['outer'], outer) + ctx.llm.registerAdapter(['nested'], nested) + let nestedStream: AsyncIterable | undefined + ctx.on('llm/stream', (options, next) => { + if (options.provider !== 'outer') return next() + return (async function* () { + nestedStream = ctx.llm.stream({ provider: 'nested', model: 'nested', messages: [] }) + yield * nestedStream + })() + }) + + const outerStream = ctx.llm.stream({ provider: 'outer', model: 'outer', messages: [] }) + let caught: unknown + try { + for await (const _chunk of outerStream) { /* drain */ } + } catch (error: unknown) { + caught = error + } + + expect(caught).toBe(original) + expect(nestedStream).toBeDefined() + expect(isLlmAdapterFailure(nestedStream!, caught)).toBe(true) + expect(isLlmAdapterFailure(outerStream, caught)).toBe(false) + expect(outer.lastOptions).toBeUndefined() + }) + + it('keeps call scopes distinct when middleware reuses an iterable', async () => { + const firstFailure = new LlmError('first provider failed', 'FIRST_FAILED') + const secondFailure = new LlmError('second provider failed', 'SECOND_FAILED') + const delegates: AsyncIterable[] = [] + const shared: AsyncIterable = { + [Symbol.asyncIterator](): AsyncIterator { + const delegate = delegates.shift() + if (delegate === undefined) throw new Error('shared stream has no call delegate') + return delegate[Symbol.asyncIterator]() + }, + } + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['first'], new ThrowingAdapter(firstFailure)) + ctx.llm.registerAdapter(['second'], new ThrowingAdapter(secondFailure)) + ctx.on('llm/stream', (_options, next) => { + delegates.push(next()) + return shared + }) + + const firstStream = ctx.llm.stream({ provider: 'first', model: 'first', messages: [] }) + const secondStream = ctx.llm.stream({ provider: 'second', model: 'second', messages: [] }) + const catchFailure = async (stream: AsyncIterable): Promise => { + try { + for await (const _chunk of stream) { /* drain */ } + } catch (error: unknown) { + return error + } + return new Error('expected adapter to fail') + } + + expect(firstStream).not.toBe(secondStream) + const firstCaught = await catchFailure(firstStream) + expect(firstCaught).toBe(firstFailure) + expect(isLlmAdapterFailure(firstStream, firstCaught)).toBe(true) + expect(isLlmAdapterFailure(secondStream, firstCaught)).toBe(false) + const secondCaught = await catchFailure(secondStream) + expect(secondCaught).toBe(secondFailure) + expect(isLlmAdapterFailure(secondStream, secondCaught)).toBe(true) + expect(isLlmAdapterFailure(firstStream, secondCaught)).toBe(false) + expect(delegates).toHaveLength(0) }) it('propagates a rejected next promptly without awaiting a non-settling return', async () => { @@ -179,9 +267,10 @@ describe('LlmService', () => { await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], adapter) + const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] }) const failure = (async (): Promise => { try { - for await (const _chunk of ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })) { /* drain */ } + for await (const _chunk of stream) { /* drain */ } } catch (error: unknown) { return error } @@ -195,7 +284,7 @@ describe('LlmService', () => { if (timer !== undefined) clearTimeout(timer) expect(caught).toBe(original) - expect(isLlmAdapterFailure(caught)).toBe(true) + expect(isLlmAdapterFailure(stream, caught)).toBe(true) expect(cleanupCalls).toBe(0) }) @@ -221,15 +310,16 @@ describe('LlmService', () => { await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], adapter) + const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] }) let caught: unknown try { - for await (const _chunk of ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })) break + for await (const _chunk of stream) break } catch (error: unknown) { caught = error } expect(caught).toBe(cleanup) - expect(isLlmAdapterFailure(caught)).toBe(false) + expect(isLlmAdapterFailure(stream, caught)).toBe(false) expect(cleanupCalls).toBe(1) }) @@ -272,16 +362,17 @@ describe('LlmService', () => { await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], adapter) + const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] }) let caught: unknown try { - for await (const _chunk of ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })) { /* drain */ } + for await (const _chunk of stream) { /* drain */ } } catch (error: unknown) { caught = error } expect(caught).toBeInstanceOf(HarnessError) expect(caught).toMatchObject({ code: 'UNKNOWN', cause: 'plain provider failure' }) - expect(isLlmAdapterFailure(caught)).toBe(true) + expect(isLlmAdapterFailure(stream, caught)).toBe(true) }) it('does not tag a failure thrown downstream while consuming adapter output', async () => { @@ -290,15 +381,20 @@ describe('LlmService', () => { await ctx.plugin(LlmService) ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter(SCRIPT)) + const stream = ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] }) let caught: unknown try { - for await (const _chunk of ctx.llm.stream({ provider: 'test-model', model: 'test-model', messages: [] })) throw downstream + for await (const _chunk of stream) throw downstream } catch (error: unknown) { caught = error } expect(caught).toBe(downstream) - expect(isLlmAdapterFailure(caught)).toBe(false) + expect(isLlmAdapterFailure(stream, caught)).toBe(false) + expect(isLlmAdapterFailure(new ScriptedAdapter(SCRIPT).stream({ + provider: 'unbound', model: 'unbound', messages: [], + }), caught)).toBe(false) + expect(isLlmAdapterFailure(stream, 'consumer failed')).toBe(false) }) it('unregisters adapters when the owning fiber is disposed (HMR safety)', async () => { diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index bc2a9e7e4b..b7b19dd0e2 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -342,7 +342,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t - `options` — the full request. A LOOP-built request arrives deep-frozen (mutation throws): its content is a pure function of the session log (the reconstructability RFC), so listeners read it, never rewrite it. A hand-built one-shot (compaction summarize) is the caller's own object and stays mutable here. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L42) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L43) ## session/* diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md index 0aebd9afe4..288839eca4 100644 --- a/website/zh-CN/api/harness/llm.md +++ b/website/zh-CN/api/harness/llm.md @@ -6,7 +6,7 @@ The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L96) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L97) ### ctx.llm.registerAdapter(providers, adapter) @@ -21,7 +21,7 @@ Register an adapter for the given provider routes. Throws `LlmError` with code ` **Returns** the disposer that unregisters all of them. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L111) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L112) ### ctx.llm.listProviders() @@ -33,7 +33,7 @@ Describe provider routes with a registered adapter. **Returns** detached provider metadata in registration order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L142) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L143) ### ctx.llm.listModels(provider) @@ -47,7 +47,7 @@ Discover models advertised by one registered provider. Catalog membership is adv **Returns** detached model metadata in adapter-preferred order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L152) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L153) ### ctx.llm.stream(options) @@ -55,10 +55,10 @@ Discover models advertised by one registered provider. Catalog membership is adv stream(options: GenerateOptions): AsyncIterable ``` -Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with code `NO_ADAPTER` if no adapter is registered for `options.provider`. Replay state is retained only when the same adapter instance owns its historical provider and the target provider. Final adapter selection, dispatch, and iteration failures retain their original Error identity and are tagged for narrow agent-loop request recovery; middleware failures remain untagged. +Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with code `NO_ADAPTER` if no adapter is registered for `options.provider`. Replay state is retained only when the same adapter instance owns its historical provider and the target provider. Final adapter selection, dispatch, and iteration failures retain their original Error identity and are tagged in a call-local scope for narrow agent-loop request recovery; middleware and nested-call failures remain untagged for the outer call. - `options` — the full request; `options.provider` selects the adapter. **Returns** the chunk stream, possibly wrapped by `llm/stream` listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L259) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L264) From 36dbe686314393efd70a7de3001f587f02d581a0 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 16:22:09 +0800 Subject: [PATCH 255/323] test(cordis): snapshot targeted JSDoc inspection --- examples/acp-agent/tests/acp.snapshot.ts | 7 ++++ .../snapshots/cordis-inspect-jsdoc/input.json | 7 ++++ .../cordis-inspect-jsdoc/session.jsonl | 33 +++++++++++++++++++ .../cordis-inspect-jsdoc/stdout.golden.jsonl | 8 +++++ 4 files changed, 55 insertions(+) create mode 100644 examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/input.json create mode 100644 examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.golden.jsonl diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 124117afef..8f749923ef 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -122,6 +122,13 @@ const SCENARIOS: Scenario[] = [ headerClass: 'advanced', configPath: ADVANCED_CONFIG, }, + { + name: 'cordis-inspect-jsdoc', + hasModelTurn: true, + recorded: false, + headerClass: 'advanced', + configPath: ADVANCED_CONFIG, + }, // Prompt-submit blocks are authored keylessly: they persist a rejected turn // and hook events without starting a model step, so their logs still compare. { name: 'hook-cc-promptsubmit-block', hasModelTurn: false, comparesLog: true, recorded: false }, diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/input.json b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/input.json new file mode 100644 index 0000000000..62df391622 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/input.json @@ -0,0 +1,7 @@ +{ + "steps": [ + { "op": "initialize" }, + { "op": "newSession" }, + { "op": "prompt", "text": "Inspect the exact tools service API and tools/pre-execute event with cordis_inspect, then reply with exactly CORDIS_INSPECT_JSDOC_OK." } + ] +} diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl new file mode 100644 index 0000000000..94ea8a8fec --- /dev/null +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/session.jsonl @@ -0,0 +1,33 @@ +{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783951000000,"cwd":"/tmp/cordis-inspect-jsdoc"} +{"type":"turn/start","seq":0,"time":1784449176717,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784449176718,"data":{"content":[{"type":"text","text":"Inspect the exact tools service API and tools/pre-execute event with cordis_inspect, then reply with exactly CORDIS_INSPECT_JSDOC_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784449176720,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784449176720,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1783951000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":5,"time":1783951000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"inspect-tools-api","name":"cordis_inspect","argumentsDelta":"{\"what\":\"api\",\"name\":\"tools\"}"}}} +{"type":"assistant/chunk","seq":6,"time":1783951000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}}}} +{"type":"assistant/chunk","seq":7,"time":1783951000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":8,"time":1783951000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":9,"time":1784449176722,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"tool/call","seq":10,"time":1784449176722,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","name":"cordis_inspect","arguments":"{\"what\":\"api\",\"name\":\"tools\"}"}} +{"type":"tool/result","seq":11,"time":1784449176732,"data":{"turn":1,"step":1,"callId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - the tool schema, execution, and optional presentation functions.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy, and final\n * notification. Tool and listener failures resolve as materialized error\n * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is\n * the same lossless, frozen snapshot final observers receive.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: InjectOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n }\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running' | 'disposed';\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export type ContextEnvelope = 'context' | 'raw';\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n envelope?: ContextEnvelope;\n meta?: JsonValue;\n }\n export interface InjectOptions extends SendOptions {\n envelope?: ContextEnvelope;\n meta?: JsonValue;\n }\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n }\n export type ScopeKey = object;\n export interface SendOptions {\n source?: MessageSource;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n execute(args: unknown, exec: ToolRunContext): Promise;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export type ToolExecuteReturn = ContentBlock[] | {\n content: ContentBlock[];\n meta?: unknown;\n };\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n signal?: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export interface ToolExecutionResult {\n content: ContentBlock[];\n isError: boolean;\n error?: ToolErrorInfo;\n additionalContexts?: HookContext[];\n meta?: unknown;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: unknown;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: HookContext): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} +{"type":"step/end","seq":12,"time":1784449176732,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":13,"time":1784449176733,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":14,"time":1783951000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":15,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":0,"id":"inspect-tools-event","name":"cordis_inspect","argumentsDelta":"{\"what\":\"events\",\"name\":\"tools/pre-execute\"}"}}} +{"type":"assistant/chunk","seq":16,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"inspect-tools-event","name":"cordis_inspect","arguments":"{\"what\":\"events\",\"name\":\"tools/pre-execute\"}"}}}} +{"type":"assistant/chunk","seq":17,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":18,"time":1784449176734,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":19,"time":1784449176734,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"inspect-tools-event","name":"cordis_inspect","arguments":"{\"what\":\"events\",\"name\":\"tools/pre-execute\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} +{"type":"tool/call","seq":20,"time":1784449176734,"data":{"turn":1,"step":2,"callId":"inspect-tools-event","name":"cordis_inspect","arguments":"{\"what\":\"events\",\"name\":\"tools/pre-execute\"}"}} +{"type":"tool/result","seq":21,"time":1784449176734,"data":{"turn":1,"step":2,"callId":"inspect-tools-event","content":[{"type":"text","text":"## events\n- tools/pre-execute [waterfall] — Allow, deny, or ask before dispatch.\n /**\n * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing\n * approval support turns `ask` into denial.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.\n * @param exec - the pending call (name, parsed arguments, caller agent).\n * @mode waterfall\n */\n 'tools/pre-execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise\nwaterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() vetoes the chain."}],"isError":false},"sourceEventSeqs":[20],"surfaceOp":"append"} +{"type":"step/end","seq":22,"time":1784449176734,"data":{"turn":1,"step":2}} +{"type":"step/start","seq":23,"time":1784449176735,"data":{"turn":1,"step":3}} +{"type":"assistant/chunk","seq":24,"time":1784449176735,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":25,"time":1784449176735,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":0,"text":"CORDIS_INSPECT_JSDOC_OK"}}} +{"type":"assistant/chunk","seq":26,"time":1784449176735,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"CORDIS_INSPECT_JSDOC_OK"}}}} +{"type":"assistant/chunk","seq":27,"time":1784449176735,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":28,"time":1784449176735,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":29,"time":1784449176735,"data":{"turn":1,"step":3,"content":[{"type":"text","text":"CORDIS_INSPECT_JSDOC_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[24,25,26,27,28],"surfaceOp":"append"} +{"type":"step/end","seq":30,"time":1784449176735,"data":{"turn":1,"step":3}} +{"type":"turn/end","seq":31,"time":1784449176735,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.golden.jsonl new file mode 100644 index 0000000000..321c5499a2 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/cordis-inspect-jsdoc/stdout.golden.jsonl @@ -0,0 +1,8 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"inspect-tools-api","title":"Inspect cordis runtime: api: tools","kind":"read","status":"in_progress"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"inspect-tools-api","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - the tool schema, execution, and optional presentation functions.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy, and final\n * notification. Tool and listener failures resolve as materialized error\n * results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is\n * the same lossless, frozen snapshot final observers receive.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly ctx: Context;\n send(content: ContentBlock[], options?: SendOptions): void;\n steer(content: ContentBlock[], options?: SendOptions): void;\n inject(content: ContentBlock[], options?: InjectOptions): void;\n cancel(reason?: string): void;\n whenIdle(): Promise;\n }\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running' | 'disposed';\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export type ContextEnvelope = 'context' | 'raw';\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n envelope?: ContextEnvelope;\n meta?: JsonValue;\n }\n export interface InjectOptions extends SendOptions {\n envelope?: ContextEnvelope;\n meta?: JsonValue;\n }\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n }\n export type ScopeKey = object;\n export interface SendOptions {\n source?: MessageSource;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n execute(args: unknown, exec: ToolRunContext): Promise;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export type ToolExecuteReturn = ContentBlock[] | {\n content: ContentBlock[];\n meta?: unknown;\n };\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n signal?: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export interface ToolExecutionResult {\n content: ContentBlock[];\n isError: boolean;\n error?: ToolErrorInfo;\n additionalContexts?: HookContext[];\n meta?: unknown;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: unknown;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: HookContext): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"inspect-tools-event","title":"Inspect cordis runtime: events: tools/pre-execute","kind":"read","status":"in_progress"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"inspect-tools-event","status":"completed","content":[{"type":"content","content":{"type":"text","text":"## events\n- tools/pre-execute [waterfall] — Allow, deny, or ask before dispatch.\n /**\n * Allow, deny, or ask before dispatch. `next()` delegates to allow; missing\n * approval support turns `ask` into denial.\n * Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.\n * @param exec - the pending call (name, parsed arguments, caller agent).\n * @mode waterfall\n */\n 'tools/pre-execute'(this: Scoped, exec: ToolExecution, next: () => Promise): Promise\nwaterfall listeners receive a trailing next() and MUST call it to delegate — returning without next() vetoes the chain."}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"CORDIS_INSPECT_JSDOC_OK"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} From 5e2607df8c077c1dbab63f8ca080e4bb941ec983 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 16:28:31 +0800 Subject: [PATCH 256/323] refactor(core): capture session inside loop operations --- docs/architecture.md | 2 +- ...2026-07-15-agent-initiator-scope.i18n.yaml | 4 +- .../2026-07-15-agent-initiator-scope.md | 4 +- .../2026-07-15-agent-initiator-scope.zh.md | 4 +- packages/core/agent-loop/README.md | 2 +- packages/core/agent-loop/src/loop.ts | 131 +++++++----------- packages/core/agent-loop/src/tool-calls.ts | 57 ++++---- 7 files changed, 84 insertions(+), 120 deletions(-) diff --git a/docs/architecture.md b/docs/architecture.md index 2644e787b6..c181e4b951 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -120,7 +120,7 @@ Every live agent owns a scoped `agent.ctx`. Its registrations shadow globals, re ### Initiating Agent Scope -`AgentLoop` runs each process-local driver inside `ctx.agents.withInitiator()`; the [decision](rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md) owns boundary and explicit-identity rules. +`AgentLoop` runs each driver inside `ctx.agents.withInitiator()`; private code derives `agent.session`, while other identities stay explicit ([decision](rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md)). ## State diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml index 247dfac57c..52128ea344 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-15-agent-initiator-scope.md: adae5d943faa6df436014ef3657b56adfbc6ea60 -2026-07-15-agent-initiator-scope.zh.md: a494c561c99adad9d1c44159e112b7220ea8468f +2026-07-15-agent-initiator-scope.md: a9df15beb8744216e020c259934db9fdf8b28b79 +2026-07-15-agent-initiator-scope.zh.md: 4198f066ef27042bda0d12fbcaf86f143482d596 diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md index adae5d943f..a9df15beb8 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md @@ -16,7 +16,9 @@ The mandatory `ctx.agents` service uses Node `AsyncLocalStorage` to carry the in `currentInitiator()` reads optionally, `requireInitiator()` throws `no initiating agent is active`, and `withInitiator(agent, operation)` preserves the operation's exact synchronous value or Promise. `withoutInitiator(operation)` establishes a clearing boundary for work that must not inherit an Agent. Session remains derived as `agent.session`; turn, step, tool call, `signal`, model, `cwd`, sandbox, and authorization stay with their existing owners. -`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Its package-private loop, turn, step, and tool-call helpers recover the exact Agent from `ctx.agents` instead of forwarding the concrete driver through their signatures. Concurrent drivers therefore receive independent stores. A child driver's continuations carry the child, while the caller resumes in its prior store as soon as `withInitiator()` returns; active-run tracking keeps the returned Promise in the teardown drain until it settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. +`AgentLoop` already injects `ctx.agents` and wraps each concrete driver's complete `runLoop` lifetime in `agents.withInitiator(agent, ...)`. Its package-private loop, turn, step, and tool-call orchestration entries recover the exact Agent from `ctx.agents`, derive `agent.session` once, and let operation-local helpers capture it instead of forwarding the concrete driver or `Session` through shallow interfaces. A leaf helper keeps a narrow `Session` parameter when that is its actual interface rather than accepting a broader `Context` only for an ambient lookup. + +Concurrent drivers receive independent stores. A child driver's continuations carry the child, while the caller resumes in its prior store as soon as `withInitiator()` returns; active-run tracking keeps the returned Promise in the teardown drain until it settles. Creation, persistence load, and unpublished `setup(agentCtx)` remain outside the child's driver boundary: creation initiated by a parent runs under the parent identity, while `agentCtx.agent` explicitly identifies the child. Ambient identity does not replace explicit contracts. `ToolExecution.agent`, `AssembleContext.agent`, `GenerateOptions.sessionId`, task ownership, parent/child requests, `ctx.agent`, `agentCtx.agent`, approval and hook subjects, `cwd` selection, cancellation, worker/process messages, persistence records, and wire identity remain explicit. A remote boundary materializes the identity it needs into its typed request because ALS is process-local. diff --git a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md index a494c561c9..4198f066ef 100644 --- a/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.zh.md @@ -16,7 +16,9 @@ Harness 中存在两种有用但不同的上下文概念。Cordis `Context` 负 `currentInitiator()` 用于可选读取，`requireInitiator()` 抛出 `no initiating agent is active`，`withInitiator(agent, operation)` 保留操作返回的同步值或 Promise 本身。`withoutInitiator(operation)` 会建立清空边界，供不得继承 Agent 的工作使用。会话仍通过 `agent.session` 推导；轮次、步骤、工具调用、`signal`、模型、`cwd`、沙箱和授权继续由现有归属方管理。 -`AgentLoop` 已经注入 `ctx.agents`，并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。其包内私有的循环、轮次、步骤和工具调用辅助函数从 `ctx.agents` 恢复同一个 Agent，无需在函数签名中转发具体驱动。因此，并发驱动使用彼此独立的存储。子驱动的异步延续携带子 Agent；`withInitiator()` 返回后，调用方立即恢复之前的存储，而活动运行计数仍持续跟踪返回的 Promise，直到其结束。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 +`AgentLoop` 已经注入 `ctx.agents`，并用 `agents.withInitiator(agent, ...)` 包裹每个具体驱动的完整 `runLoop` 生命周期。循环、轮次、步骤和工具调用的包内私有入口从 `ctx.agents` 恢复同一个 Agent，一次推导 `agent.session`，再由操作内辅助函数捕获该值，避免在浅层接口中转发具体驱动或 `Session`。若 `Session` 本身就是底层辅助函数的实际接口，该函数会保留狭窄的 `Session` 参数，而不会只为隐式查找而接收更宽泛的 `Context`。 + +因此，并发驱动使用彼此独立的存储。子驱动的异步延续携带子 Agent；`withInitiator()` 返回后，调用方立即恢复之前的存储，而活动运行计数仍持续跟踪返回的 Promise，直到其结束。创建、持久化加载和尚未发布的 `setup(agentCtx)` 位于子驱动边界之外：由父 Agent 发起的创建使用父身份，而 `agentCtx.agent` 显式标识子 Agent。 隐式身份不会取代显式契约。`ToolExecution.agent`、`AssembleContext.agent`、`GenerateOptions.sessionId`、任务归属、父子请求、`ctx.agent`、`agentCtx.agent`、审批与 hook 主体、`cwd` 选择、取消、worker 和进程消息、持久化记录及协议身份都保持显式传递。远程边界会把所需身份写入类型化请求，因为 ALS 只在进程内有效。 diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index f0030845c1..6d373a303a 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -50,7 +50,7 @@ The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publicati ### Loop lifecycle (`loop.ts`) -The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`, so package-private loop, turn, step, and tool-call helpers recover the exact Agent from `ctx.agents` instead of forwarding the concrete driver through their signatures. Creation, persistence load, and unpublished setup stay outside the driver boundary; explicit Agent fields remain authoritative at service, worker, process, persistence, and wire boundaries. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules. +The driver owns one agent for its lifetime and runs inside `ctx.agents.withInitiator(agent, ...)`. Package-private orchestration entry points recover the exact Agent, derive `agent.session` once, and let operation-local helpers capture it instead of forwarding the concrete driver or per-operation `Session` through shallow interfaces. A helper keeps an explicit `Session` when that is its actual interface, while creation, persistence load, unpublished setup, services, workers, processes, persistence, and wire protocols retain their explicit identities. The [agent service](../agent/README.md#initiating-agent-scope) owns propagation, teardown, and detached-work rules. Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history. diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 4f2f768d89..ce95af3d13 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -95,8 +95,8 @@ export interface LoopHandle { /** * Drive queued batches as durable turns until disposal. Plugin failures end the * current turn without terminating the driver. The caller establishes the - * `ctx.agents.withInitiator()` boundary before entry; package-private helpers - * recover that exact Agent from the inherited store. + * `ctx.agents.withInitiator()` boundary before entry; package-private + * orchestration recovers that exact Agent and captures its Session locally. * @param ctx - the plugin context the loop reaches its initiating Agent, * events (agent/…, session/flush), and services (systemPrompt, llm, tools) * through. @@ -169,6 +169,13 @@ async function runTurn( ): Promise { const agent = ctx.agents.requireInitiator() const { session } = agent + const drainSteering = (): boolean => { + const messages = handle.inbox.drainSteering() + for (const message of messages) { + session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' }) + } + return messages.length > 0 + } // Drain before opening the turn, but append only after `turn/start`. const queued = handle.inbox.drainQueued() @@ -267,7 +274,7 @@ async function runTurn( // Steering from the previous round's continuation listeners joins before // the request. - drainSteering(session, handle.inbox, turn) + drainSteering() // The step's AbortController exists BEFORE any async pre-step work so a // dispose() or cancel() — in a synchronous turn-start listener or an @@ -370,7 +377,7 @@ async function runTurn( if (stepReason) reason = stepReason // Steering that arrived during streaming/tool execution. - const steered = drainSteering(session, handle.inbox, turn) + const steered = drainSteering() closeStep() @@ -459,15 +466,6 @@ async function runTurn( return terminalStopped } -/** Drain the steering queue into the session. Returns whether any arrived. */ -function drainSteering(session: Session, inbox: Inbox, turn: number): boolean { - const messages = inbox.drainSteering() - for (const message of messages) { - session.append('steering/message', { turn, content: message.content, source: message.source }, { surfaceOp: 'append' }) - } - return messages.length > 0 -} - /** * Run one committed step: transform call config, log the request header, build * the request from the cached prefix plus the step-boundary snapshot, stream and @@ -543,15 +541,47 @@ async function runStep( const stepError = finishError(assembler.finish) if (stepError) throw stepError + const recordAssistantMessage = ( + assembledContent: ContentBlock[], + message: Message, + preserveReplayState = true, + ): void => { + session.append( + 'assistant/message', + { + turn, + step, + content: message.content, + provenance: assistantProvenance( + header.config, + assembler.replayState, + preserveReplayState && isDeepStrictEqual(message.content, assembledContent), + ), + ...assembler.usage === undefined ? {} : { usage: assembler.usage }, + }, + { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, + ) + } + + // A rejected result still records the successful provider call without retaining rejected output. + const processStepResult = async (assembledContent: ContentBlock[], message: Message): Promise => { + try { + return await events.waterfall( + 'agent/step-result', turn, step, message, () => Promise.resolve(message), + ) + } catch (error: unknown) { + recordAssistantMessage(assembledContent, { ...message, content: [] }, false) + throw error + } + } + if (assembler.finish.kind === 'max-tokens') { const assembled = assembler.message() const assembledContent = structuredClone(assembled.content) let message: Message = withoutToolCalls(assembled) - message = withoutToolCalls(await processStepResult( - events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs, - )) + message = withoutToolCalls(await processStepResult(assembledContent, message)) // Preserve usage even when max-token truncation produced no content. - recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs) + recordAssistantMessage(assembledContent, message) return { hadToolCalls: false, finish: assembler.finish } } @@ -559,13 +589,11 @@ async function runStep( const assembled = assembler.message() const assembledContent = structuredClone(assembled.content) let message: Message = assembled - message = await processStepResult( - events, session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs, - ) + message = await processStepResult(assembledContent, message) // Every successful call records its completion anchor, including explicit // empty chunk provenance for a contentless, usage-less provider response. - recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs) + recordAssistantMessage(assembledContent, message) // Dispatch may overlap; policy, durable results, and result context stay model-ordered. const toolCalls = message.content.filter(block => block.type === 'tool-call') @@ -578,67 +606,6 @@ async function runStep( }) } -/** Preserve successful-call accounting without retaining output that result processing rejected. */ -async function processStepResult( - events: AgentEventDispatch, - session: Session, - turn: number, - step: number, - config: LlmCallConfig, - assembledContent: ContentBlock[], - message: Message, - assembler: BlockAssembler, - chunkSeqs: number[], -): Promise { - try { - return await events.waterfall( - 'agent/step-result', turn, step, message, () => Promise.resolve(message), - ) - } catch (error: unknown) { - recordAssistantMessage( - session, - turn, - step, - config, - assembledContent, - { ...message, content: [] }, - assembler, - chunkSeqs, - false, - ) - throw error - } -} - -/** Record one content-or-usage assistant message with replay-safe provenance. */ -function recordAssistantMessage( - session: Session, - turn: number, - step: number, - config: LlmCallConfig, - assembledContent: ContentBlock[], - message: Message, - assembler: BlockAssembler, - chunkSeqs: number[], - preserveReplayState = true, -): void { - session.append( - 'assistant/message', - { - turn, - step, - content: message.content, - provenance: assistantProvenance( - config, - assembler.replayState, - preserveReplayState && isDeepStrictEqual(message.content, assembledContent), - ), - ...assembler.usage === undefined ? {} : { usage: assembler.usage }, - }, - { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, - ) -} - /** Build durable assistant provenance, dropping replay state after any content rewrite. */ function assistantProvenance(config: LlmCallConfig, replayState: unknown, contentUnchanged: boolean): NonNullable { return { diff --git a/packages/core/agent-loop/src/tool-calls.ts b/packages/core/agent-loop/src/tool-calls.ts index 5bf41c4895..5ec1ceb4c2 100644 --- a/packages/core/agent-loop/src/tool-calls.ts +++ b/packages/core/agent-loop/src/tool-calls.ts @@ -12,7 +12,6 @@ import type { Context } from 'cordis' import { assertNever, type ToolCallBlock } from '@deepseek-ai/dsh-llm' import type { HookContext } from '@deepseek-ai/dsh-agent' -import type { Session } from '@deepseek-ai/dsh-session' import { TOOL_REGISTRY_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools' /** One tool call after argument parsing, ready to schedule. */ @@ -104,6 +103,29 @@ async function runGroup( acceptContext: (context: HookContext) => void, ): Promise { const { session } = ctx.agents.requireInitiator() + const appendToolCall = (block: ToolCallBlock): number => { + return session.append('tool/call', { + turn, + step, + callId: block.id, + name: block.name, + arguments: block.arguments, + }).seq + } + const appendToolResult = (block: ToolCallBlock, result: ToolExecutionResult, callSeq: number): void => { + session.append('tool/result', { + turn, + step, + // Correlation stays with the loop's authoritative model-transcript call id; + // registry results deliberately do not duplicate it. + callId: block.id, + content: result.content, + isError: result.isError, + ...result.error ? { error: result.error } : {}, + // Persist presentation payloads so UI bridges reproduce result cards on replay. + ...result.meta !== undefined ? { meta: result.meta } : {}, + }, { surfaceOp: 'append', sourceEventSeqs: [callSeq] }) + } /* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */ if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted')) const slots: (Slot | undefined)[] = group.map(() => undefined) @@ -124,7 +146,7 @@ async function runGroup( ? await ctx.tools[TOOL_REGISTRY_SCHEDULER].finalize(slot.exec, slot.result) : ctx.tools[TOOL_REGISTRY_SCHEDULER].finish(slot.exec, slot.result) // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index - appendToolResult(session, turn, step, call!.block, result, callSeqs[committed]!) + appendToolResult(call!.block, result, callSeqs[committed]!) for (const context of result.additionalContexts ?? []) acceptContext(context) committed++ } @@ -135,7 +157,7 @@ async function runGroup( const startCall = async (index: number): Promise => { // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- bounded index const call = group[index]! - callSeqs[index] = appendToolCall(session, turn, step, call.block) + callSeqs[index] = appendToolCall(call.block) started++ const prepared = await ctx.tools[TOOL_REGISTRY_SCHEDULER].prepare(call.exec) switch (prepared.kind) { @@ -197,32 +219,3 @@ async function runGroup( if (committed !== started) throw new Error('tool-call scheduler: uncommitted settled calls') return started } - -/** Append a started call and return its provenance sequence. */ -function appendToolCall(session: Session, turn: number, step: number, block: ToolCallBlock): number { - const event = session.append('tool/call', { turn, step, callId: block.id, name: block.name, arguments: block.arguments }) - return event.seq -} - -/** Append a model-ordered result linked to its call event. */ -function appendToolResult( - session: Session, - turn: number, - step: number, - block: ToolCallBlock, - result: ToolExecutionResult, - callSeq: number, -): void { - session.append('tool/result', { - turn, step, - // Correlation stays with the loop's authoritative model-transcript call id; - // registry results deliberately do not duplicate it. - callId: block.id, - content: result.content, - isError: result.isError, - ...result.error ? { error: result.error } : {}, - // The tool's private presentation payload (e.g. a result-time diff), - // persisted so a UI bridge reproduces the card on replay. - ...result.meta !== undefined ? { meta: result.meta } : {}, - }, { surfaceOp: 'append', sourceEventSeqs: [callSeq] }) -} From 5f9fe1415623d8fe7643a4c9a0bc764d6f7c2c2e Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 16:39:58 +0800 Subject: [PATCH 257/323] docs(bash-local): clarify spill cleanup semantics --- packages/bash/bash-local/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/bash/bash-local/README.md b/packages/bash/bash-local/README.md index 8150119acd..159effec64 100644 --- a/packages/bash/bash-local/README.md +++ b/packages/bash/bash-local/README.md @@ -38,6 +38,6 @@ Indirectly, through `dsh-tool-bash`, which renders this executor's bounded stdou - **No persistent shell or PTY** — every call starts a fresh non-login `bash -c`; cwd-only persistence and interactive terminal sessions remain deferred until a real workflow requires them. - **POSIX-only** — the `bash` binary, detached process groups, group kills, and SIGTERM→SIGKILL escalation are hardcoded; Windows is unsupported. - **The credential scrub is a name heuristic** — `*KEY*`/`*SECRET*`/`*TOKEN*` only; differently-named secrets (e.g. `*PASSWORD*`) pass through, and a whitelist for over-scrubbed vars is noted future work. -- **Completed spill files are not deleted** — bounded full-output recovery files (and the private per-process spill dir) accumulate under the OS tmpdir until something external cleans them; oversize incomplete spills are deleted immediately. +- **Completed spill files are not deleted** — bounded full-output recovery files (and the private per-process spill dir) accumulate under the OS tmpdir until something external cleans them; oversize incomplete spills are discarded and deletion is attempted immediately, but a cleanup failure can leave a bounded file behind. The raw process handling lives in `src/run.ts`; `src/index.ts` is the service wiring. From a1de4d00714556c3a0d00ab0ef6728cc431c4d0d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 16:44:24 +0800 Subject: [PATCH 258/323] docs: codify initiator-owned identity plumbing --- packages/AGENTS.md | 1 + scripts/doc-budgets.manifest.json | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/packages/AGENTS.md b/packages/AGENTS.md index 766a188105..9ab0327cf9 100644 --- a/packages/AGENTS.md +++ b/packages/AGENTS.md @@ -6,6 +6,7 @@ These package-specific rules supplement the repo-wide [conventions](../AGENTS.md - **Optional services use `ctx.get(name)`.** Reserve `ctx.` for declared injections; the property proxy is topology-sensitive, while strict `ctx.get` reads the global service store ([postmortem](../docs/postmortem/0001-acp-default-export-drops-inject.md)). - **Product-visible plugins require a non-unit REAL-composition test.** Hand-built `ctx.plugin(...)` suites are insufficient. Boot test-only `cordis.yml` through the Loader and app/process; mock only external/nondeterministic boundaries and assert model-visible, durable, or user-visible output. Keep opt-ins out of shipped defaults. [Policy](../docs/testing.md). - **Typed same-process service and plugin calls are contracts, not serialization boundaries.** Prefer readonly borrowed values; materialize or defensively validate only at parser/config, queued, model/tool JSON, durable/file, worker, process, or wire boundaries. +- **Initiator-owned private chains derive, then capture.** Under `ctx.agents.withInitiator()`, recover the Agent at each orchestration entry, derive `agent.session`, and let operation-local helpers close over it. Keep `Agent` and `Session` explicit at lifecycle, session-log, service, authority, worker/process, persistence, and wire interfaces; do not widen a leaf helper from `Session` to `Context` merely to hide a parameter ([rationale](../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md)). - **Represent one asynchronous operation with one lifecycle controller or transaction.** Separate readiness, cancellation, disposal, reservation, or sentinel state requires an independent owner or settlement boundary; otherwise fold it while preserving rollback, callback containment, and quiescence. Naming notes: diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json index 3b99ad454a..b4d2bca159 100644 --- a/scripts/doc-budgets.manifest.json +++ b/scripts/doc-budgets.manifest.json @@ -6,6 +6,6 @@ "docs/defensive-patterns.md": 550, "docs/testing.md": 960, "examples/AGENTS.md": 310, - "packages/AGENTS.md": 290, + "packages/AGENTS.md": 370, "packages/README.md": 760 } From d5350cd42e9c3c352567accefff480d2453c590d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 17:08:00 +0800 Subject: [PATCH 259/323] docs(review): distill human review principles --- .agents/skills/dsh-code-review/SKILL.md | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/.agents/skills/dsh-code-review/SKILL.md b/.agents/skills/dsh-code-review/SKILL.md index 2b562cc321..ca42b97323 100644 --- a/.agents/skills/dsh-code-review/SKILL.md +++ b/.agents/skills/dsh-code-review/SKILL.md @@ -29,19 +29,20 @@ description: Use when reviewing a pull request in the deepseek-harness repo — - **Intent and seam contracts:** trace both sides of every changed interface. Confirm the implementation matches the PR and any RFC, including errors, cancellation, ownership, and disposal. - **Lifecycle and concurrency:** for async setup, callbacks, processes, or teardown, apply [defensive-patterns.md](../../../docs/defensive-patterns.md). Check races before publication, cancellation during awaits, independent error reporting, callback containment, ownership before reentry, complete detach cleanup, and quiescent disposal. -- **Capability shape:** a swappable capability follows the interface / implementation / consumer split. Consumers depend on the interface, not a backend. -- **Scope, ownership, and necessity:** tie each abstraction, state machine, option, defensive copy, and compatibility path to a current contract or production consumer. Challenge unrelated features, speculative generality, and behavior placed outside its owning plugin or service. -- **Configuration:** deployment-varying timeouts, caps, models, URLs, paths, and retry counts are validated `Config` fields, not literals or `DEFAULT_*` constants. +- **Capability and consumer fit:** a swappable capability follows the interface / implementation / consumer split. Shape the interface for all current consumers, not one tool schema, loader, UI, transport, or backend; keep consumer-specific behavior in the consumer or adapter. +- **Scope, ownership, and necessity:** tie each abstraction, state machine, option, defensive copy, and compatibility path to a current contract or production consumer. Challenge unrelated features, speculative generality, and behavior placed outside its owning plugin or service. Review whether the PR is one coherent change; move an independently meaningful feature or design decision into a separate or stacked PR when combining it obscures ownership, intent, or verification. +- **Configuration and public choices:** deployment-varying tunables are validated `Config` fields. Do not invent a default, public operation set, format, or borrowed external concept merely because it can be configurable; require evidence from a current consumer or relevant prior art, otherwise keep the choice explicit or defer it. +- **Model perspective:** inspect the exact prompts, tool schemas, results, and diagnostics the model receives across affected modes. Flag UI, transport, or implementation concepts irrelevant to the model's task. Verify stable model-visible text verbatim and dynamic behavior through snapshots or end-to-end coverage. - **Enforcement boundaries:** hidden schema fields, filtered prompts, facades, wrappers, and listener ordering are not authoritative enforcement when direct or alternate callers can bypass them. Exercise denial paths at the boundary that actually executes the operation. - **Borrowed and derived state:** determine whether retained caller-owned values are borrowed or snapshotted by contract; do not demand copies at typed same-process seams. Materialize mutable values that cross queues, model/tool JSON, durable logs or files, workers, processes, or wire boundaries. Commit notifications and derived state only at the documented success boundary, and trace caches, prompts, UI echoes, replay, and query views to one authoritative source. - **Bounds cover the final operation:** verify byte, token, item, and time limits at the boundary that owns the complete emitted or retained result, including wrappers and metadata. Probe tiny limits, exact thresholds, oversized single chunks, and multibyte text for byte limits. - **Real entry path:** tests exercise the shipped Loader, bin, worker, ACP bridge, or subprocess where relevant. A hand-mounted plugin does not catch Loader export-shape failures; a function plugin must named-export its namespace and have no default export. - **Test strength:** assertions fail on the intended regression and verify external state, logs, events, or disposal rather than restating the implementation or trusting an agent's report. Coverage is necessary but not evidence that the scenario is correct. -- **Changed checks have a negative control:** a new automated check, or a changed acceptance path in one, has a deliberately invalid case that reaches the real top-level runner and fails for the intended rule; a green happy path does not prove the check is wired. +- **Mechanized invariants and negative controls:** when a repeatable invariant is mechanically checkable, require it to be wired into an executed top-level gate. A new check, or a changed acceptance path in one, also needs a deliberately invalid case that reaches the real runner and fails for the intended rule. - **Implemented RFCs match shipped reality:** when a PR implements a proposed RFC, move and rewrite it as present-tense shipped state in the same diff, then verify paths, names, and mechanisms against the implementation. - **Transcript changes:** editor-visible or model-visible changes update snapshots or explain why no snapshot applies. Review golden diffs as behavior changes, not formatting noise. - **Bilingual changes:** compare meaning and terminology on both sides; a green pairing hash does not prove translation quality. ## Reporting findings -State the defect, location, impact, and evidence. Separate blockers from suggestions and omit issues already enforced by a green gate. Use the existing GitHub review thread for replies. When receiving review, verify each claim and fix or rebut it on technical grounds without performative agreement. +State the defect, location, impact, and evidence. Place a localized defect inline on the tightest relevant diff range; use a PR-level comment for cross-cutting architecture, scope, or review-wide synthesis. Separate blockers from suggestions and omit issues already enforced by a green gate. Use the existing GitHub review thread for replies. When receiving review, verify each claim and fix or rebut it on technical grounds without performative agreement. From 0d00106fa8a25c148eb67538210104f010cec70d Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 17:20:36 +0800 Subject: [PATCH 260/323] fix(session): persist the delegation depth in the session header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A subagent child's recursion depth lived only in runtime AgentOptions, so a persisted child came back from resume counted as top-level and maxDepth stopped binding after every restart. Add SessionHeader.delegationDepth, round-trip it through the JSONL and SQLite backends (SQLite schema v5), restore it on agent-loop resume, and write it when the in-process backends create a child. The seam now owns the shared depth vocabulary (delegationDepthOf): the persisted header is authoritative and monotone — runtime options may deepen it but never lower it. --- docs/cordis-catalog/events.md | 8 ++-- docs/cordis-catalog/services.md | 6 +-- docs/core-data-structures/persistence.md | 7 ++++ docs/event-producer-consumer.md | 8 ++-- docs/persistence-catalog.md | 30 ++++++------- .../advanced-toolchain/session.1.jsonl | 2 +- .../advanced-toolchain/session.2.jsonl | 2 +- .../cordis/tool-cordis/src/api-catalog.ts | 6 +-- packages/core/agent-loop/src/index.ts | 1 + packages/core/agent-loop/tests/resume.spec.ts | 7 +++- packages/core/agent/src/index.ts | 12 ++++-- packages/core/session/README.md | 4 +- packages/core/session/src/index.ts | 5 +++ packages/core/session/src/types.ts | 7 ++++ packages/core/session/tests/session.spec.ts | 16 +++++++ .../session-persistence-jsonl/src/format.ts | 3 ++ .../session-persistence-sqlite/src/index.ts | 8 ++-- .../session-persistence-sqlite/src/schema.ts | 11 +++-- .../tests/sqlite.spec.ts | 2 +- .../tests/coordinator-contract.ts | 21 ++++++++++ .../subagent/subagent-inprocess/README.md | 4 +- .../subagent/subagent-inprocess/src/index.ts | 27 ++---------- .../tests/subagent-inprocess.spec.ts | 42 ++++++++++++++++++- packages/subagent/subagent/README.md | 4 ++ packages/subagent/subagent/src/index.ts | 26 ++++++++++++ website/zh-CN/api/harness/agents.md | 30 ++++++------- website/zh-CN/api/harness/events.md | 8 ++-- website/zh-CN/api/harness/sessions.md | 18 ++++---- website/zh-CN/api/harness/subagents.md | 10 ++--- 29 files changed, 229 insertions(+), 106 deletions(-) diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index f522790fd0..5bd4d7b6f8 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -542,7 +542,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c Types: [Scoped](../core-data-structures/scope.md) · [SubagentService](../core-data-structures/subagent.md) -Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:138`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -559,7 +559,7 @@ A provider became resolvable in the registry. Types: [SubagentProvider](../core-data-structures/subagent.md) -Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -574,7 +574,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:118`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -596,7 +596,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( Types: [Scoped](../core-data-structures/scope.md) · [SubagentService](../core-data-structures/subagent.md) -Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:129`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 267c2f0caa..378bb03ae8 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -216,7 +216,7 @@ roots(): Agent[] Types: [Agent](../core-data-structures/core.md) · [SessionId](../core-data-structures/core.md) -Source: [`packages/core/agent/src/index.ts:217`](../../packages/core/agent/src/index.ts) +Source: [`packages/core/agent/src/index.ts:223`](../../packages/core/agent/src/index.ts) ## `ctx.approval` — `ApprovalService` @@ -820,7 +820,7 @@ fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Types: [CreateSessionOptions](../core-data-structures/persistence.md) · [Session](../core-data-structures/session.md) · [SessionId](../core-data-structures/core.md) -Source: [`packages/core/session/src/index.ts:577`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:581`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` @@ -934,7 +934,7 @@ async start(name: string, request: SubagentStartRequest): Promise Types: [SubagentProvider](../core-data-structures/subagent.md) · [SubagentRun](../core-data-structures/subagent.md) · [SubagentStartRequest](../core-data-structures/subagent.md) -Source: [`packages/subagent/subagent/src/index.ts:153`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:179`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/persistence.md b/docs/core-data-structures/persistence.md index 72ebcc5852..c4cbf97cdf 100644 --- a/docs/core-data-structures/persistence.md +++ b/docs/core-data-structures/persistence.md @@ -60,6 +60,12 @@ interface SessionHeader { * boundary lets resume and replay distinguish parent history from child work. */ readonly seedLength?: number + /** + * Delegation depth: absent (zero) for a top-level session, parent depth + 1 + * for a subagent child. Persisted so a recursion budget survives restart and + * resume — a runtime-only depth would reset a resumed child to top-level. + */ + readonly delegationDepth?: number } ``` @@ -85,6 +91,7 @@ interface CreateSessionOptions { readonly parentSession?: SessionId readonly createdAt?: number readonly seedLength?: number + readonly delegationDepth?: number } } ``` diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 78f878106c..8f70dd00b6 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -30,10 +30,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:57`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/event` | `emit` | [`packages/core/session/src/index.ts:69`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`cli-demo`](../packages/examples/cli-demo), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`tui`](../packages/ui/tui), [`workspace-context`](../packages/context/workspace-context) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:79`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:112`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:86`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:92`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | -| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:103`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | +| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:138`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:112`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:118`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | +| `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:129`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`acp`](../packages/ui/acp) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 3bc15253a5..2a0500d79b 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -79,7 +79,7 @@ export type SessionEvent = { }[T] ``` -Sources: [`packages/core/session/src/types.ts:255`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:262`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:292`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:324`](../packages/core/session/src/types.ts) +Sources: [`packages/core/session/src/types.ts:262`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:269`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:299`](../packages/core/session/src/types.ts) · [`packages/core/session/src/types.ts:331`](../packages/core/session/src/types.ts) ## Events @@ -151,7 +151,7 @@ Source: [`packages/ui/user-approval/src/index.ts:68`](../packages/ui/user-approv Types: [StreamChunk](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:219`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:226`](../packages/core/session/src/types.ts) #### `assistant/message` — surface @@ -167,7 +167,7 @@ Source: [`packages/core/session/src/types.ts:219`](../packages/core/session/src/ Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) -Source: [`packages/core/session/src/types.ts:226`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:233`](../packages/core/session/src/types.ts) ### `bash/*` @@ -258,7 +258,7 @@ Source: [`packages/compact/compact/src/types.ts:22`](../packages/compact/compact Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:212`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:219`](../packages/core/session/src/types.ts) ### `hook/*` @@ -336,7 +336,7 @@ Source: [`packages/ui/permission/src/index.ts:33`](../packages/ui/permission/src Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:204`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:211`](../packages/core/session/src/types.ts) ### `request/*` @@ -350,7 +350,7 @@ Source: [`packages/core/session/src/types.ts:204`](../packages/core/session/src/ 'request/header': { header: EpochHeader; reason: RequestHeaderReason } ``` -Source: [`packages/core/session/src/types.ts:251`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:258`](../packages/core/session/src/types.ts) ### `steering/*` @@ -363,7 +363,7 @@ Source: [`packages/core/session/src/types.ts:251`](../packages/core/session/src/ Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:244`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:251`](../packages/core/session/src/types.ts) ### `step/*` @@ -374,7 +374,7 @@ Source: [`packages/core/session/src/types.ts:244`](../packages/core/session/src/ 'step/end': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:197`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:204`](../packages/core/session/src/types.ts) #### `step/start` — log-only @@ -383,7 +383,7 @@ Source: [`packages/core/session/src/types.ts:197`](../packages/core/session/src/ 'step/start': { turn: number; step: number } ``` -Source: [`packages/core/session/src/types.ts:195`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:202`](../packages/core/session/src/types.ts) ### `todo/*` @@ -396,7 +396,7 @@ Source: [`packages/core/session/src/types.ts:195`](../packages/core/session/src/ Types: [TodoItem](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:246`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:253`](../packages/core/session/src/types.ts) ### `tool/*` @@ -413,7 +413,7 @@ Source: [`packages/core/session/src/types.ts:246`](../packages/core/session/src/ Types: [CallId](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:232`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:239`](../packages/core/session/src/types.ts) #### `tool/code-dispatch` — log-only @@ -457,7 +457,7 @@ Source: [`packages/core/tools/src/code-mode.ts:34`](../packages/core/tools/src/c Types: [CallId](core-data-structures/core.md) · [ContentBlock](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:242`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:249`](../packages/core/session/src/types.ts) ### `turn/*` @@ -474,7 +474,7 @@ Source: [`packages/core/session/src/types.ts:242`](../packages/core/session/src/ Types: [TurnEndReason](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:193`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:200`](../packages/core/session/src/types.ts) #### `turn/start` — log-only @@ -490,7 +490,7 @@ Source: [`packages/core/session/src/types.ts:193`](../packages/core/session/src/ Types: [TurnTrigger](core-data-structures/session.md) -Source: [`packages/core/session/src/types.ts:187`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:194`](../packages/core/session/src/types.ts) ### `user/*` @@ -503,4 +503,4 @@ Source: [`packages/core/session/src/types.ts:187`](../packages/core/session/src/ Types: [ContentBlock](core-data-structures/core.md) · [MessageSource](core-data-structures/core.md) -Source: [`packages/core/session/src/types.ts:199`](../packages/core/session/src/types.ts) +Source: [`packages/core/session/src/types.ts:206`](../packages/core/session/src/types.ts) diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index b4e8cd6340..d8affeaab8 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -1,4 +1,4 @@ -{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111","delegationDepth":1} {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} diff --git a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index d8d2e59e6e..f0b6154472 100644 --- a/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -1,4 +1,4 @@ -{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"/tmp/advanced-headless","parentSession":"11111111-1111-4111-8111-111111111111","delegationDepth":1} {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5d99506c8a..65f828c383 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -709,11 +709,11 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'CreateAgentOptions', - declaration: 'export interface CreateAgentOptions {\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', + declaration: 'export interface CreateAgentOptions {\n readonly sessionId: SessionId;\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n };\n readonly seed?: readonly SessionEvent[];\n readonly agentOptions?: AgentOptions;\n readonly signal?: AbortSignal;\n readonly setup?: (agentCtx: Context) => Promise | void;\n}', }, { name: 'CreateSessionOptions', - declaration: 'export interface CreateSessionOptions {\n readonly seed?: readonly SessionEvent[];\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly createdAt?: number;\n readonly seedLength?: number;\n };\n}', + declaration: 'export interface CreateSessionOptions {\n readonly seed?: readonly SessionEvent[];\n readonly meta?: {\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly createdAt?: number;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n };\n}', }, { name: 'DiffCallView', @@ -929,7 +929,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionHeader', - declaration: 'export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n}', + declaration: 'export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n}', }, { name: 'SessionId', diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 2a77afc983..519edfdb7e 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -625,6 +625,7 @@ export class AgentLoop extends Service implements AgentFactory { ...loaded.meta.cwd === undefined ? {} : { cwd: loaded.meta.cwd }, ...loaded.meta.parentSession === undefined ? {} : { parentSession: loaded.meta.parentSession }, ...loaded.meta.seedLength === undefined ? {} : { seedLength: loaded.meta.seedLength }, + ...loaded.meta.delegationDepth === undefined ? {} : { delegationDepth: loaded.meta.delegationDepth }, }, }) const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 74192dde90..452f1d66b5 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -411,7 +411,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await ctx.fiber.dispose() }) - it('resume of a forked session preserves the parentSession lineage and seed boundary in the header', async () => { + it('resume of a forked session preserves the lineage, seed boundary, and delegation depth in the header', async () => { // Lifecycle 1: persist a FORKED session (carries parentSession + seedLength // in its header) by creating it with a complete-turn seed — the write path // materializes the fork (header + seed) on disk. @@ -423,7 +423,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const { ctx: ctx1, root } = await persistentHarness(adapter1) const forked = ctx1.sessions.create(SessionId('forked-sess'), { seed, - meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length }, + meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length, delegationDepth: 1 }, }) await ctx1.parallel('session/flush', forked) await ctx1.fiber.dispose() @@ -447,6 +447,9 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { expect(a2.session.header.parentSession).toBe('parent-sess') expect(a2.session.header.cwd).toBe('/w') expect(a2.session.header.seedLength).toBe(seed.length) + // The recursion budget survives resume — a dropped depth would let a + // resumed child delegate as if it were top-level. + expect(a2.session.header.delegationDepth).toBe(1) await ctx2.fiber.dispose() }) diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index 75f00daebb..061ddae53f 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -46,15 +46,21 @@ export interface CreateAgentOptions { readonly sessionId: SessionId /** * Session creation metadata: validated absolute `cwd`, `parentSession` - * fork lineage, and the `seedLength` seed boundary. Mirrors the - * `cwd`/`parentSession`/`seedLength` fields of + * fork lineage, the `seedLength` seed boundary, and the `delegationDepth` + * recursion budget. Mirrors the + * `cwd`/`parentSession`/`seedLength`/`delegationDepth` fields of * {@link CreateSessionOptions.meta} in dsh-session (the internal-only * `createdAt`, used when reconstructing a persisted session, is deliberately * excluded — a factory caller never sets it). This is durable session data, * so the session boundary validates and snapshots it before asynchronous * setup begins. */ - readonly meta?: { readonly cwd?: string; readonly parentSession?: SessionId; readonly seedLength?: number } + readonly meta?: { + readonly cwd?: string + readonly parentSession?: SessionId + readonly seedLength?: number + readonly delegationDepth?: number + } /** * Seed events to reconstruct the child session's log from (the fork lineage * primitive). When present, the factory creates the session with this event diff --git a/packages/core/session/README.md b/packages/core/session/README.md index ba4e8ea94a..ec7daf9408 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -38,7 +38,7 @@ Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. - `session.surface` exposes the readonly `SessionSurface` view owned by the session's single incremental surface manager; `replaceGeneration` changes on every committed rewrite. - `session.events` is a cached frozen snapshot invalidated by append; accepted events remain deeply frozen. - `session.seq`, `session.id` — current sequence and readonly typed identity. -- `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`). Construction validates the durable record and requires its id to match `session.id`. +- `session.header: SessionHeader` — detached, deep-frozen creation metadata (`version`, `id`, `createdAt`, optional `cwd`/`parentSession`/`seedLength`/`delegationDepth`). Construction validates the durable record and requires its id to match `session.id`. ### Lossless JSON utilities @@ -73,7 +73,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) ### Metadata types (`types.ts`) -- `SessionHeader` — session metadata written once when published as `Session.header`, where detachment and deep-freezing enforce immutability at runtime: `{ version, id, createdAt, cwd?, parentSession?, seedLength? }`. Persistence loaders may return mutable detached copies of the same data type. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle). +- `SessionHeader` — session metadata written once when published as `Session.header`, where detachment and deep-freezing enforce immutability at runtime: `{ version, id, createdAt, cwd?, parentSession?, seedLength?, delegationDepth? }`. Persistence loaders may return mutable detached copies of the same data type. Owned here (beside `SessionId`) because `Session.header` is typed by it; persistence backends re-export it rather than own it (which would force a package cycle). ### Extension points diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index b8b76ec2ed..37025ed1c7 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -128,6 +128,10 @@ function snapshotSessionHeader(id: SessionId, source?: SessionHeader): SessionHe && (typeof record.seedLength !== 'number' || !Number.isSafeInteger(record.seedLength) || record.seedLength < 0)) { throw new Error('session header seedLength must be a non-negative safe integer') } + if (record.delegationDepth !== undefined + && (typeof record.delegationDepth !== 'number' || !Number.isSafeInteger(record.delegationDepth) || record.delegationDepth < 0)) { + throw new Error('session header delegationDepth must be a non-negative safe integer') + } return deepFreeze(record as unknown as SessionHeader) } @@ -650,6 +654,7 @@ export class SessionStore extends Service { ...meta?.cwd === undefined ? {} : { cwd: meta.cwd }, ...meta?.parentSession === undefined ? {} : { parentSession: meta.parentSession }, ...meta?.seedLength === undefined ? {} : { seedLength: meta.seedLength }, + ...meta?.delegationDepth === undefined ? {} : { delegationDepth: meta.delegationDepth }, } return new Session(sessionId, seed, header) } diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index dc34760e9c..31903d97db 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -50,6 +50,12 @@ export interface SessionHeader { * boundary lets resume and replay distinguish parent history from child work. */ readonly seedLength?: number + /** + * Delegation depth: absent (zero) for a top-level session, parent depth + 1 + * for a subagent child. Persisted so a recursion budget survives restart and + * resume — a runtime-only depth would reset a resumed child to top-level. + */ + readonly delegationDepth?: number } /** @@ -69,6 +75,7 @@ export interface CreateSessionOptions { readonly parentSession?: SessionId readonly createdAt?: number readonly seedLength?: number + readonly delegationDepth?: number } } diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index 3b15157bde..243908d27f 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -882,6 +882,19 @@ describe('SessionStore', () => { }) }) + it('attaches delegationDepth from meta to the header', async () => { + const ctx = new Context() + await ctx.plugin(SessionStore) + const session = ctx.sessions.create(SessionId('delegated-child'), { + meta: { parentSession: SessionId('parent'), delegationDepth: 2 }, + }) + expect(session.header).toMatchObject({ + id: 'delegated-child', + parentSession: 'parent', + delegationDepth: 2, + }) + }) + it('rejects non-JSON and invalid scalar session metadata', async () => { const ctx = new Context() await ctx.plugin(SessionStore) @@ -893,6 +906,9 @@ describe('SessionStore', () => { { meta: { seedLength: '1' }, error: /seedLength must be a non-negative safe integer/ }, { meta: { seedLength: 0.5 }, error: /seedLength must be a non-negative safe integer/ }, { meta: { seedLength: -1 }, error: /seedLength must be a non-negative safe integer/ }, + { meta: { delegationDepth: '1' }, error: /delegationDepth must be a non-negative safe integer/ }, + { meta: { delegationDepth: 0.5 }, error: /delegationDepth must be a non-negative safe integer/ }, + { meta: { delegationDepth: -1 }, error: /delegationDepth must be a non-negative safe integer/ }, ] for (const [index, { meta, error }] of cases.entries()) { diff --git a/packages/session-persistence/session-persistence-jsonl/src/format.ts b/packages/session-persistence/session-persistence-jsonl/src/format.ts index 39bdecf751..3fe3b2485c 100644 --- a/packages/session-persistence/session-persistence-jsonl/src/format.ts +++ b/packages/session-persistence/session-persistence-jsonl/src/format.ts @@ -25,6 +25,7 @@ export interface HeaderLine { cwd?: string parentSession?: SessionId seedLength?: number + delegationDepth?: number } /** @@ -41,6 +42,7 @@ export function toHeaderLine(header: SessionHeader): HeaderLine { ...header.cwd !== undefined ? { cwd: header.cwd } : {}, ...header.parentSession !== undefined ? { parentSession: header.parentSession } : {}, ...header.seedLength !== undefined ? { seedLength: header.seedLength } : {}, + ...header.delegationDepth !== undefined ? { delegationDepth: header.delegationDepth } : {}, } } @@ -57,6 +59,7 @@ export function fromHeaderLine(line: HeaderLine): SessionHeader { ...line.cwd !== undefined ? { cwd: line.cwd } : {}, ...line.parentSession !== undefined ? { parentSession: line.parentSession } : {}, ...line.seedLength !== undefined ? { seedLength: line.seedLength } : {}, + ...line.delegationDepth !== undefined ? { delegationDepth: line.delegationDepth } : {}, } } diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts index 4661b41309..edba26d9ae 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/index.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts @@ -253,14 +253,15 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers */ private writeRow(meta: SessionHeader): void { this.db.prepare(` - INSERT INTO sessions (id, version, created_at, cwd, parent_session, seed_length) - VALUES (?, ?, ?, ?, ?, ?) + INSERT INTO sessions (id, version, created_at, cwd, parent_session, seed_length, delegation_depth) + VALUES (?, ?, ?, ?, ?, ?, ?) ON CONFLICT(id) DO UPDATE SET version = excluded.version, created_at = excluded.created_at, cwd = excluded.cwd, parent_session = excluded.parent_session, - seed_length = excluded.seed_length + seed_length = excluded.seed_length, + delegation_depth = excluded.delegation_depth `).run( meta.id, meta.version, @@ -268,6 +269,7 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers meta.cwd ?? null, meta.parentSession ?? null, meta.seedLength ?? null, + meta.delegationDepth ?? null, ) } } diff --git a/packages/session-persistence/session-persistence-sqlite/src/schema.ts b/packages/session-persistence/session-persistence-sqlite/src/schema.ts index adb23cbb43..4a7f12e759 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/schema.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/schema.ts @@ -15,7 +15,7 @@ import type { SessionEvent, SessionId, SessionHeader, SurfaceOp } from '@deepsee * layout; orthogonal to a session's own `version` (which versions the EVENT * vocabulary, stored per session in the `sessions` row). */ -export const SCHEMA_VERSION = 4 +export const SCHEMA_VERSION = 5 /** * A row of the `sessions` table — the out-of-log metadata ({@link SessionHeader}). @@ -31,6 +31,7 @@ export interface SessionRow { cwd: string | null parent_session: string | null seed_length: number | null + delegation_depth: number | null } /** An `events` table row: one `SessionEvent` mapped 1:1 (`data` is JSON text). */ @@ -83,9 +84,10 @@ export function openDatabase(path: string, journalMode: JournalMode): DatabaseSy id TEXT PRIMARY KEY, version INTEGER NOT NULL, created_at INTEGER NOT NULL, - cwd TEXT, - parent_session TEXT, - seed_length INTEGER + cwd TEXT, + parent_session TEXT, + seed_length INTEGER, + delegation_depth INTEGER ) STRICT `) db.exec(` @@ -116,6 +118,7 @@ export function rowToMeta(row: SessionRow): SessionHeader { ...row.cwd !== null ? { cwd: row.cwd } : {}, ...row.parent_session !== null ? { parentSession: row.parent_session as SessionId } : {}, ...row.seed_length !== null ? { seedLength: row.seed_length } : {}, + ...row.delegation_depth !== null ? { delegationDepth: row.delegation_depth } : {}, } } diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index f26edfa54d..83d16b3315 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -385,7 +385,7 @@ describe('SessionPersistenceSqlite: durability and crash semantics', () => { }) it('exposes the schema version constant', () => { - expect(SCHEMA_VERSION).toBe(4) + expect(SCHEMA_VERSION).toBe(5) }) }) diff --git a/packages/session-persistence/session-persistence/tests/coordinator-contract.ts b/packages/session-persistence/session-persistence/tests/coordinator-contract.ts index defcaefb6d..5ef2ce2fad 100644 --- a/packages/session-persistence/session-persistence/tests/coordinator-contract.ts +++ b/packages/session-persistence/session-persistence/tests/coordinator-contract.ts @@ -106,6 +106,27 @@ export function runCoordinatorContract(name: string, makeFixture: () => Promise< } }) + it('round-trips the delegation depth through persistence', async () => { + // A subagent child's recursion budget lives in its header; a reload that + // dropped it would reset the child to top-level and un-bound maxDepth + // (JSONL stores it in the header line; SQLite uses `delegation_depth`). + const fix = await makeFixture() + const { ctx, fiber } = await freshCtx(fix) + try { + const session = ctx.sessions.create(SessionId('delegated-child'), { + meta: { cwd: WORK, parentSession: SessionId('root'), delegationDepth: 2 }, + }) + send(session, oneTurnLog()) + await ctx.parallel('session/flush', session) + + const loaded = await ctx.sessionPersistence.load(SessionId('delegated-child')) + expect(loaded.meta.delegationDepth).toBe(2) + } finally { + await fiber.dispose() + await fix.cleanup() + } + }) + it('source-frozen events cannot be mutated after buffering and persist unchanged', async () => { const fix = await makeFixture() const { ctx, fiber } = await freshCtx(fix) diff --git a/packages/subagent/subagent-inprocess/README.md b/packages/subagent/subagent-inprocess/README.md index ca54dab7c0..46d4457764 100644 --- a/packages/subagent/subagent-inprocess/README.md +++ b/packages/subagent/subagent-inprocess/README.md @@ -8,7 +8,7 @@ This package is the shared run driver for the two in-process providers. Spawn pa The driver follows this sequence: -1. Validate the parent depth and optional absolute `maxDepth`, then derive child depth as parent depth plus one. +1. Validate the parent depth and optional absolute `maxDepth`, then derive child depth as parent depth plus one and persist it in the child session header. 2. Call `parent.ctx.agents.create` directly, passing the required request signal into the factory's creation transaction. 3. During that transaction's unpublished setup window, install the requested persona, tool restriction, and structured-output runtime. 4. Publish the child, retain the returned `AgentHandle`, and drive one task with `child.send(prompt)` followed by `child.whenIdle()`. @@ -26,7 +26,7 @@ After fulfillment, the caller owns the run. Provider-plugin unload does not revo `InProcessRunOptions` is `{ seed?: SessionEvent[] }`. Spawn omits it. Fork supplies a balanced completed-turn prefix and records its length so the result reader never mistakes a seeded parent message for child output. -Depth enforcement is internal to `startInProcessRun`: it reads `AgentOptions.subagentDepth`, treats absence as top-level depth zero, rejects malformed stored values, and reports an attempted child depth above `maxDepth`. An unrepresentable depth above the safe-integer domain is a `RangeError`. +Depth enforcement is internal to `startInProcessRun`: it reads the parent depth via `delegationDepthOf` (the persisted `SessionHeader.delegationDepth` is authoritative; runtime `AgentOptions.subagentDepth` may deepen but never lower it, so a resumed child keeps its budget), treats absence as top-level depth zero, rejects malformed stored values, and reports an attempted child depth above `maxDepth`. An unrepresentable depth above the safe-integer domain is a `RangeError`. The child depth is written to the child header, so it survives persistence and resume. ## Structured output diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 6e62ee5127..f0e9731c9d 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -12,7 +12,7 @@ import type { Context } from 'cordis' import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import { SessionId, type SessionEvent, type TurnEndReason } from '@deepseek-ai/dsh-session' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import { assertSubagentMaxDepth } from '@deepseek-ai/dsh-subagent' +import { assertSubagentMaxDepth, delegationDepthOf } from '@deepseek-ai/dsh-subagent' import type { SubagentResult, SubagentRun, SubagentStartRequest, SubagentStopReason } from '@deepseek-ai/dsh-subagent' import { attachStructuredRuntime, @@ -24,27 +24,6 @@ export { STRUCTURED_OUTPUT_INSTRUCTION, } from './structured.ts' -declare module '@deepseek-ai/dsh-agent' { - interface AgentOptions { - /** Delegation depth: zero for a top-level agent and parent depth + 1 for a child. */ - subagentDepth?: number - } -} - -/** - * Read an agent's delegation depth, treating absence as top-level depth zero. - * @param agent - the agent whose options carry the depth. - * @returns its non-negative safe-integer depth. - */ -function depthOf(agent: Agent): number { - const depth = agent.options.subagentDepth - if (depth === undefined) return 0 - if (!Number.isSafeInteger(depth) || depth < 0 || Object.is(depth, -0)) { - throw new TypeError('agent subagentDepth must be a non-negative safe integer') - } - return depth -} - /** Thrown when starting a child would exceed the requested depth cap. */ class SubagentDepthError extends Error { constructor(public readonly attemptedDepth: number, public readonly maxDepth: number) { @@ -96,7 +75,7 @@ export async function startInProcessRun( assertSubagentMaxDepth(request.maxDepth) if (request.signal.aborted) throw prePublicationAbort() const parent = request.parent - const childDepth = depthOf(parent) + 1 + const childDepth = delegationDepthOf(parent) + 1 if (!Number.isSafeInteger(childDepth)) { throw new RangeError('subagent child depth exceeds the safe-integer range') } @@ -133,6 +112,8 @@ export async function startInProcessRun( meta: { ...parentHeader.cwd !== undefined ? { cwd: parentHeader.cwd } : {}, parentSession: parentHeader.id, + // Durable: the recursion budget must survive persistence and resume. + delegationDepth: childDepth, ...seedLength > 0 ? { seedLength } : {}, }, ...options.seed !== undefined ? { seed: options.seed } : {}, diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 13029ef3e7..9c645bc78a 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -58,6 +58,44 @@ describe('startInProcessRun', () => { await run.dispose() }) + it('persists the child depth in its session header', async () => { + const { ctx, parent } = await setup([textResponse('child answer')]) + const run = await startInProcessRun(request(parent), {}) + await run.result + // The recursion budget is durable session data, not only runtime options — + // a depth that lived only in AgentOptions would reset to 0 on resume. + expect(ctx.agents.get(run.id)!.session.header.delegationDepth).toBe(1) + await run.dispose() + }) + + it('counts a RESUMED child by its persisted header depth, not the absent runtime depth', async () => { + // The review-reproduced failure chain: a depth-1 child comes back from + // persistence with a fresh AgentOptions (no subagentDepth). Its header must + // stay authoritative, or maxDepth: 1 would let it delegate as top-level. + const { ctx } = await setup([textResponse('unused')]) + const resumed = (await ctx.agents.create({ + sessionId: SessionId('resumed-child'), + meta: { parentSession: SessionId('root'), delegationDepth: 1 }, + agentOptions: { provider: 'mock', model: 'mock' }, + signal: new AbortController().signal, + })).agent + await expect(startInProcessRun({ ...request(resumed), maxDepth: 1 }, {})) + .rejects.toMatchObject({ name: 'SubagentDepthError', attemptedDepth: 2, maxDepth: 1 }) + }) + + it('lets runtime options deepen but never lower the persisted depth', async () => { + const { ctx } = await setup([textResponse('unused')]) + const parent = (await ctx.agents.create({ + sessionId: SessionId('deep-parent'), + meta: { delegationDepth: 2 }, + agentOptions: { provider: 'mock', model: 'mock', subagentDepth: 1 }, + signal: new AbortController().signal, + })).agent + // Persisted 2 vs runtime 1: the child is depth 3, so maxDepth 2 rejects. + await expect(startInProcessRun({ ...request(parent), maxDepth: 2 }, {})) + .rejects.toMatchObject({ name: 'SubagentDepthError', attemptedDepth: 3, maxDepth: 2 }) + }) + it('rejects invalid and exceeded depth before publication', async () => { const { parent } = await setup([]) await expect(startInProcessRun({ ...request(parent), maxDepth: -1 }, {})) @@ -65,11 +103,11 @@ describe('startInProcessRun', () => { await expect(startInProcessRun({ ...request(parent), maxDepth: 0 }, {})) .rejects.toMatchObject({ name: 'SubagentDepthError' }) for (const value of [Number.NaN, 1.5, -1, -0, Number.MAX_SAFE_INTEGER + 1]) { - const malformed = { options: { subagentDepth: value } } as unknown as Agent + const malformed = { options: { subagentDepth: value }, session: { header: {} } } as unknown as Agent await expect(startInProcessRun(request(malformed), {})) .rejects.toThrow('agent subagentDepth must be a non-negative safe integer') } - const maxParent = { options: { subagentDepth: Number.MAX_SAFE_INTEGER } } as unknown as Agent + const maxParent = { options: { subagentDepth: Number.MAX_SAFE_INTEGER }, session: { header: {} } } as unknown as Agent await expect(startInProcessRun(request(maxParent), {})).rejects.toBeInstanceOf(RangeError) }) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 17edd0e3c7..bde2b61eab 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -40,6 +40,10 @@ Start-time features are advertised in `provider.capabilities` because the servic - `toolFilter` — apply the requested child tool restriction. - `persona` — apply a per-child persona. +## Delegation depth + +The seam owns the depth vocabulary shared by implementations and consumers: the `AgentOptions.subagentDepth` declaration, `assertSubagentMaxDepth`, and `delegationDepthOf(agent)`. The persisted `SessionHeader.delegationDepth` is authoritative and monotone — runtime options may deepen the count but never lower it, so a resumed child cannot be re-counted as top-level. + Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a live child, while `resume?` asynchronously creates a continuation run. Method presence is the capability check. `inheritsParentContext` is descriptive rather than enforceable. It says only whether the child sees completed parent conversation history (`fork` does; `spawn` and ACP do not), not whether it inherits tools, services, or authority. diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 19779f9137..9046ae4a94 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -57,6 +57,32 @@ export type { SubagentStopReasonMap, } from './types.ts' +declare module '@deepseek-ai/dsh-agent' { + interface AgentOptions { + /** Delegation depth: zero for a top-level agent and parent depth + 1 for a child. */ + subagentDepth?: number + } +} + +/** + * Read an agent's delegation depth, treating absence as top-level depth zero. + * The persisted session header is authoritative and monotone: runtime + * `AgentOptions.subagentDepth` may DEEPEN the count but can never lower it — + * a resumed child arrives with fresh options, and counting it from zero would + * let it delegate as if it were top-level. + * @param agent - the agent whose header and options carry the depth. + * @returns its non-negative safe-integer depth. + */ +export function delegationDepthOf(agent: Agent): number { + const runtime = agent.options.subagentDepth + if (runtime !== undefined && (!Number.isSafeInteger(runtime) || runtime < 0 || Object.is(runtime, -0))) { + throw new TypeError('agent subagentDepth must be a non-negative safe integer') + } + // The header value was validated at the session boundary (creation and + // persistence load both construct through the store). + return Math.max(agent.session.header.delegationDepth ?? 0, runtime ?? 0) +} + /** * Reject a recursion cap that cannot represent an exact delegation depth. * @param maxDepth - the optional runtime value to validate. diff --git a/website/zh-CN/api/harness/agents.md b/website/zh-CN/api/harness/agents.md index bba6a7a5d4..a99e7339cb 100644 --- a/website/zh-CN/api/harness/agents.md +++ b/website/zh-CN/api/harness/agents.md @@ -7,7 +7,7 @@ Agent service (`ctx.agents`): tracks live agents and carries the initiating Agent through one process-local asynchronous driver chain. Agent *creation* is provided by whichever plugin implements the AgentFactory (`@deepseek-ai/dsh-agent-loop`), registered via setFactory. Initiator methods provide same-process causal attribution only. Ambient presence is neither liveness proof nor authorization; subjects and owners remain explicit, as does identity at worker, process, persistence, and wire boundaries. Returned Promise boundaries drain during teardown, except a nested lineage that starts an owning-fiber unload is excluded from its own drain. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L217) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L223) ### ctx.agents.currentInitiator() @@ -28,7 +28,7 @@ Read the Agent that initiated the inherited asynchronous driver chain. Use this **Returns** the inherited Agent, or `undefined` outside an initiator boundary and inside an explicit clearing boundary. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L256) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L262) ### ctx.agents.requireInitiator() @@ -48,7 +48,7 @@ Read the initiating Agent and fail when no initiator boundary is active. Use thi **Returns** the inherited Agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L269) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L275) ### ctx.agents.withInitiator(agent, operation) @@ -76,7 +76,7 @@ Run an operation with one exact Agent as its process-local initiator. The exact **Returns** the exact value returned by `operation`. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L288) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L294) ### ctx.agents.withoutInitiator(operation) @@ -101,7 +101,7 @@ Run an operation inside a boundary that hides any inherited initiating Agent. Th **Returns** the exact value returned by `operation`. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L303) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L309) ### ctx.agents.setFactory(factory) @@ -127,7 +127,7 @@ Register the agent-creation factory (the loop calls this on construction, effect **Returns** the disposer that clears the factory slot. The exact Cordis effect disposer (single-shot): composite (generator) effects may yield it directly — exact identity nests the teardown in order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L319) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L325) ### ctx.agents.create(options) @@ -150,7 +150,7 @@ Create and publish a new agent through the registered factory. Distinct from reg **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L352) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L358) ### ctx.agents.resume(options) @@ -171,7 +171,7 @@ Load a persisted session and resume an agent on it through the registered factor **Returns** the handle after setup, rollback-covered publication, and loop start complete. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L371) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L377) ### ctx.agents.register(agent) @@ -203,7 +203,7 @@ Register a live agent. Throws if an agent with the same id is already registered **Returns** the EXACT Cordis effect disposer (single-shot; a repeat call returns undefined without awaiting an in-flight teardown). Exact identity is load-bearing: a composite (generator) effect that owns a teardown ORDER — the agent factory's lifecycle chain — must yield THIS function so Cordis nests the unregistration at that yield position; yielding a wrapper would leave it disposing as a concurrent sibling on owner unload, unregistering the agent (and emitting `agent/disposed`) while its final turn is still draining. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L397) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L403) ### ctx.agents.enter(agent, owner) @@ -233,7 +233,7 @@ Insert an already-constructed agent without announcing it. This is the advanced **Returns** an idempotent closure that removes this exact entry and emits `agent/disposed` with listener failures contained. When called from a synchronous `agent/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L421) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L427) ### ctx.agents.announce(agent) @@ -252,7 +252,7 @@ Announce an agent previously inserted with enter. - `agent` — the live inserted agent to announce. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L496) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L502) ### ctx.agents.get(id) @@ -271,7 +271,7 @@ Look up a live agent. **Returns** the agent, or undefined when no live agent has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L530) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L536) ### ctx.agents.isOwnedBy(id, owner) @@ -294,7 +294,7 @@ Test whether a live agent was created through one exact parent agent's scoped co **Returns** true only while the exact child entry is live under that owner. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L542) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L548) ### ctx.agents.list() @@ -310,7 +310,7 @@ All live agents, in registration order. **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L550) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L556) ### ctx.agents.roots() @@ -328,4 +328,4 @@ All live top-level agents in registration order. A top-level agent was created w **Returns** a fresh array; mutating it does not affect the registry. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L560) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/index.ts#L566) diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index fcfa426a81..ae1633ddaa 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -614,7 +614,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c - `info` — the run identity and terminal outcome. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L112) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L138) ### subagent/provider-added @@ -633,7 +633,7 @@ A provider became resolvable in the registry. - `provider` — the registered provider. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L86) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L112) ### subagent/provider-removed @@ -652,7 +652,7 @@ A provider left the registry. Accepted runs remain holder-owned. - `name` — the provider name that no longer resolves. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L92) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L118) ### subagent/start @@ -676,7 +676,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( - `info` — the provider and ready child identity. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L103) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L129) ## system-prompt/* diff --git a/website/zh-CN/api/harness/sessions.md b/website/zh-CN/api/harness/sessions.md index f59001009d..73ae4385af 100644 --- a/website/zh-CN/api/harness/sessions.md +++ b/website/zh-CN/api/harness/sessions.md @@ -7,7 +7,7 @@ In-memory session store (`ctx.sessions`). Persistence is intentionally not implemented here — persistence plugins subscribe to `session/event` and flush on `session/flush` / dispose. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L577) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L581) ### ctx.sessions.create(id?, options?) @@ -44,7 +44,7 @@ For an agent whose session must be torn down IN ORDER with its loop (so the loop **Returns** the live session, already entered and announced. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L606) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L610) ### ctx.sessions.prepare(id?, options?) @@ -75,7 +75,7 @@ Build a session WITHOUT entering it into the store — validate the id/cwd and c **Returns** the constructed session, NOT yet in the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L635) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L639) ### ctx.sessions.enter(session) @@ -112,7 +112,7 @@ Re-checks the id for a duplicate: `prepare` and `enter` are public cross-package **Returns** the detach disposer (publication hooks + store removal). When called from a synchronous `session/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L679) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L684) ### ctx.sessions.announce(session) @@ -131,7 +131,7 @@ Emit `session/created` exactly once for an entered session (with the carrier ent - `session` — the entered session to announce to listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L734) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L739) ### ctx.sessions.flush(session) @@ -156,7 +156,7 @@ Dispatch the awaited `session/flush` durability checkpoint for `session`, with t **Returns** resolves when every flush listener has settled; after all settle, rejects with the first registered listener failure if any listener failed. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L786) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L791) ### ctx.sessions.get(id) @@ -175,7 +175,7 @@ Look up a live session. **Returns** the session, or undefined when no live session has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L818) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L823) ### ctx.sessions.list() @@ -191,7 +191,7 @@ All live sessions, in creation order. **Returns** a fresh array; mutating it does not affect the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L826) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L831) ### ctx.sessions.fork(source, boundary?, childSessionId?) @@ -220,4 +220,4 @@ Create a live child session from a turn-enclosed prefix of a live source. `bound **Returns** The created live child session. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L843) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L848) diff --git a/website/zh-CN/api/harness/subagents.md b/website/zh-CN/api/harness/subagents.md index de71a5effe..2e0d295eb3 100644 --- a/website/zh-CN/api/harness/subagents.md +++ b/website/zh-CN/api/harness/subagents.md @@ -6,7 +6,7 @@ Named provider registry and capability-checked start surface. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L153) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L179) ### ctx.subagents.registerProvider(provider) @@ -27,7 +27,7 @@ Register a provider under its name. Registration is effect-scoped and HMR safe; **Returns** the exact Cordis effect disposer. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L167) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L193) ### ctx.subagents.getProvider(name) @@ -46,7 +46,7 @@ Look up a provider by name. **Returns** the provider, or undefined when absent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L190) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L216) ### ctx.subagents.list() @@ -62,7 +62,7 @@ List registered provider names in insertion order. **Returns** the registered names. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L198) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L224) ### ctx.subagents.start(name, request) @@ -86,4 +86,4 @@ Establish a ready child on the named provider. Capability and semantic checks ru **Returns** the ready holder-owned run. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L211) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L237) From cb74477d420d3457de121ef256d9f578302ac794 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 17:20:49 +0800 Subject: [PATCH 261/323] feat(tool-subagent): default maxDepth 1 with at-cap schema hiding MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit An omitted maxDepth meant unbounded recursion, and the shipped examples shipped that default. maxDepth now defaults to 1; a numeric cap requires the provider's depthLimit capability (the mount fails loud and points to the explicit 'provider-managed' opt-out for out-of-process providers), and a child AT the cap loses the delegating tool from its own schema via the child toolFilter — prompt-face hiding on top of the execution-face depth check. Examples pin maxDepth explicitly. The ACP snapshot harness gains Scenario.childToolOmissions so a child session may legitimately omit declared delegation tools from its pinned header and prompt; affected subagent/workflow goldens are re-recorded. --- docs/config-catalog.md | 15 +- examples/acp-agent/cordis.yml | 2 + examples/acp-agent/tests/acp.snapshot.ts | 13 +- .../advanced-toolchain/session.1.jsonl | 2 +- .../advanced-toolchain/session.2.jsonl | 2 +- .../snapshots/subagent-fork/session.1.jsonl | 167 +++-- .../snapshots/subagent-fork/session.jsonl | 363 +++++----- .../subagent-fork/stdout.golden.jsonl | 107 ++- .../snapshots/subagent-mixed/session.1.jsonl | 72 +- .../snapshots/subagent-mixed/session.2.jsonl | 156 +++-- .../snapshots/subagent-mixed/session.jsonl | 622 ++++++++++-------- .../subagent-mixed/stdout.golden.jsonl | 204 +++--- .../snapshots/subagent-multi/session.1.jsonl | 72 +- .../snapshots/subagent-multi/session.2.jsonl | 68 +- .../snapshots/subagent-multi/session.jsonl | 402 ++++++----- .../subagent-multi/stdout.golden.jsonl | 80 +-- .../snapshots/subagent-spawn/session.1.jsonl | 68 +- .../snapshots/subagent-spawn/session.jsonl | 287 ++++---- .../subagent-spawn/stdout.golden.jsonl | 62 +- .../snapshots/workflow-run/session.1.jsonl | 72 +- .../snapshots/workflow-run/session.jsonl | 352 ++++------ .../workflow-run/stdout.golden.jsonl | 87 +-- examples/headless-agent/cordis.yml | 2 + examples/repl-agent/cordis.yml | 2 + packages/subagent/tool-subagent/README.md | 2 +- packages/subagent/tool-subagent/src/index.ts | 59 +- .../tool-subagent/tests/tool-subagent.spec.ts | 136 +++- packages/support/acp-snapshot/src/suite.ts | 57 +- .../support/acp-snapshot/tests/suite.spec.ts | 32 + scripts/gen-tool-catalog.ts | 9 +- 30 files changed, 1811 insertions(+), 1763 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index c3b185d13e..1cbddeb023 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -1127,8 +1127,7 @@ export interface Config { /** * Tool filter applied to every child. Filtered tools disappear from its * prompt and reject execution. Requires the provider's `toolFilter` - * capability; unknown names fail startup. Children otherwise see this tool, - * so deny it or set `maxDepth` to bound recursion. + * capability; unknown names fail startup. */ toolFilter?: { /** Global tool names the child keeps; everything else is removed. */ @@ -1137,10 +1136,16 @@ export interface Config { deny?: string[] } /** - * Maximum child depth. Requires the provider's `depthLimit` capability and a - * non-negative safe integer. Omission is unbounded. + * Maximum child depth: a non-negative safe integer (default `1`; `0` forbids + * delegation entirely), or `'provider-managed'` to send no cap. A numeric cap + * requires the provider's `depthLimit` capability (mount fails loud + * otherwise), and a child AT the cap additionally loses this tool from its + * schema when the provider supports `toolFilter` — the prompt face of the + * budget; the service keeps rejecting on the execution face. + * `'provider-managed'` is for an out-of-process provider (ACP) whose + * recursion budget belongs to the child harness's own deployment. */ - maxDepth?: number + maxDepth?: number | 'provider-managed' } ``` diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index cb8890dae7..8e2260387d 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -69,12 +69,14 @@ config: provider: spawn toolName: subagent + maxDepth: 1 - id: tool-subagent-fork name: '@deepseek-ai/dsh-tool-subagent' config: provider: fork toolName: subagent_fork + maxDepth: 1 # The worker-thread workflow engine fans a model-written JavaScript script's diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 124117afef..c541a85e20 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -103,10 +103,12 @@ const SCENARIOS: Scenario[] = [ configPath: WORKSPACE_CONTEXT_CONFIG, }, { name: 'cancel', hasModelTurn: true, recorded: false, overridden: true }, - { name: 'subagent-spawn', hasModelTurn: true, recorded: true }, - { name: 'subagent-multi', hasModelTurn: true, recorded: true }, - { name: 'subagent-fork', hasModelTurn: true, recorded: true }, - { name: 'subagent-mixed', hasModelTurn: true, recorded: true }, + // Children sit AT the default depth cap (maxDepth 1), so each child's header + // legitimately omits the delegation tool that spawned it (schema hiding). + { name: 'subagent-spawn', hasModelTurn: true, recorded: true, childToolOmissions: ['subagent'] }, + { name: 'subagent-multi', hasModelTurn: true, recorded: true, childToolOmissions: ['subagent'] }, + { name: 'subagent-fork', hasModelTurn: true, recorded: true, childToolOmissions: ['subagent_fork'] }, + { name: 'subagent-mixed', hasModelTurn: true, recorded: true, childToolOmissions: ['subagent', 'subagent_fork'] }, // The workflow tool: the model writes a one-child orchestration script; the // child runs as a spawn subagent under the worker-thread engine (its session is the // child fixture), and the tool result carries the script's return value. @@ -121,6 +123,9 @@ const SCENARIOS: Scenario[] = [ pinsHeader: true, headerClass: 'advanced', configPath: ADVANCED_CONFIG, + // The direct spawn child sits AT the default cap and loses `subagent`; + // workflow children bypass tool-subagent and keep the full set. + childToolOmissions: ['subagent'], }, // Prompt-submit blocks are authored keylessly: they persist a rejected turn // and hook events without starting a model step, so their logs still compare. diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 25a6f76411..26519d458e 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -1,4 +1,4 @@ -{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"/tmp/advanced-acp","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"session","version":0,"id":"22222222-2222-4222-8222-222222222222","createdAt":1783950001000,"cwd":"/tmp/advanced-acp","parentSession":"11111111-1111-4111-8111-111111111111","delegationDepth":1} {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 45d9043a4a..9daa8958dc 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -1,4 +1,4 @@ -{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"/tmp/advanced-acp","parentSession":"11111111-1111-4111-8111-111111111111"} +{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783950002000,"cwd":"/tmp/advanced-acp","parentSession":"11111111-1111-4111-8111-111111111111","delegationDepth":1} {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl index 4ecb61b60f..18802ec864 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl @@ -1,89 +1,78 @@ -{"type":"session","version":0,"id":"ada8966c-9fa3-441b-8721-37ff1e795e6a","createdAt":1783352137161,"cwd":"/tmp/acp-snap-cwd-0HLtcD","parentSession":"96cf59c9-b347-48b9-b234-a5200913ad05","seedLength":37} -{"type":"turn/start","seq":0,"time":1783352134837,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352134838,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352134840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352135621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} -{"type":"assistant/chunk","seq":11,"time":1783352135655,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":12,"time":1783352135655,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":13,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":14,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":15,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":16,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} -{"type":"assistant/chunk","seq":17,"time":1783352135683,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ARM"}}} -{"type":"assistant/chunk","seq":18,"time":1783352135683,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":19,"time":1783352135712,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} -{"type":"assistant/chunk","seq":20,"time":1783352135713,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":21,"time":1783352135713,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":22,"time":1783352135713,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":23,"time":1783352135739,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":24,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} -{"type":"assistant/chunk","seq":25,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":26,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"OK"}}} -{"type":"assistant/chunk","seq":27,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":28,"time":1783352135770,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":29,"time":1783352135770,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} -{"type":"assistant/chunk","seq":30,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."}}}} -{"type":"assistant/chunk","seq":31,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} -{"type":"assistant/chunk","seq":32,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}}}} -{"type":"assistant/chunk","seq":33,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} -{"type":"step/end","seq":35,"time":1783352135773,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":36,"time":1783352135773,"data":{"turn":1,"reason":{"kind":"completed"}}} -{"type":"turn/start","seq":37,"time":1783352137162,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":38,"time":1783352137163,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":39,"time":1783352137163,"data":{"turn":2,"step":1}} -{"type":"request/header","seq":40,"time":1783352137163,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} -{"type":"assistant/chunk","seq":41,"time":1783352137783,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":42,"time":1783352137783,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":43,"time":1783352137961,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":44,"time":1783352137989,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":45,"time":1783352138020,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":46,"time":1783352138046,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":47,"time":1783352138046,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} -{"type":"assistant/chunk","seq":48,"time":1783352138046,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":49,"time":1783352138046,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} -{"type":"assistant/chunk","seq":50,"time":1783352138074,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":51,"time":1783352138075,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":52,"time":1783352138075,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":53,"time":1783352138075,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":54,"time":1783352138075,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} -{"type":"assistant/chunk","seq":55,"time":1783352138075,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ARM"}}} -{"type":"assistant/chunk","seq":56,"time":1783352138103,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":57,"time":1783352138103,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} -{"type":"assistant/chunk","seq":58,"time":1783352138103,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":59,"time":1783352138103,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":60,"time":1783352138103,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" now"}}} -{"type":"assistant/chunk","seq":61,"time":1783352138131,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" they"}}} -{"type":"assistant/chunk","seq":62,"time":1783352138159,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'re"}}} -{"type":"assistant/chunk","seq":63,"time":1783352138160,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" asking"}}} -{"type":"assistant/chunk","seq":64,"time":1783352138160,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" what"}}} -{"type":"assistant/chunk","seq":65,"time":1783352138160,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":66,"time":1783352138188,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":67,"time":1783352138188,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":68,"time":1783352138188,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":69,"time":1783352138217,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":70,"time":1783352138217,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} -{"type":"assistant/chunk","seq":71,"time":1783352138217,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":72,"time":1783352138245,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":73,"time":1783352138246,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":74,"time":1783352138274,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":75,"time":1783352138275,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":76,"time":1783352138275,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":77,"time":1783352138275,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"M"}}} -{"type":"assistant/chunk","seq":78,"time":1783352138275,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ARM"}}} -{"type":"assistant/chunk","seq":79,"time":1783352138275,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"AL"}}} -{"type":"assistant/chunk","seq":80,"time":1783352138305,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ADE"}}} -{"type":"assistant/chunk","seq":81,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."}}}} -{"type":"assistant/chunk","seq":82,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"MARMALADE"}}}} -{"type":"assistant/chunk","seq":83,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}}}} -{"type":"assistant/chunk","seq":84,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":85,"time":1783352138308,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."},{"type":"text","text":"MARMALADE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}},"sourceEventSeqs":[41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} -{"type":"step/end","seq":86,"time":1783352138308,"data":{"turn":2,"step":1}} -{"type":"turn/end","seq":87,"time":1783352138308,"data":{"turn":2,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"de67f82f-1a81-463e-8388-b323dafb8843","createdAt":1784451782049,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-CuULie","parentSession":"19a0ab16-a36d-49c8-bac2-c1b2208844ad","seedLength":33,"delegationDepth":1} +{"type":"turn/start","seq":0,"time":1784451778261,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451778262,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451778263,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451778263,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451779662,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451779662,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451779947,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451779948,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451779949,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451779949,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} +{"type":"assistant/chunk","seq":11,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":12,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" fact"}}} +{"type":"assistant/chunk","seq":13,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":14,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":15,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1784451779958,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":17,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":18,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":19,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":20,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" No"}}} +{"type":"assistant/chunk","seq":21,"time":1784451780009,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":22,"time":1784451780009,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" needed"}}} +{"type":"assistant/chunk","seq":23,"time":1784451780009,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":24,"time":1784451780035,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":25,"time":1784451780036,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} +{"type":"assistant/chunk","seq":26,"time":1784451780036,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."}}}} +{"type":"assistant/chunk","seq":27,"time":1784451780037,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} +{"type":"assistant/chunk","seq":28,"time":1784451780037,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3568,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":29,"time":1784451780037,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":30,"time":1784451780041,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3568,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"step/end","seq":31,"time":1784451780041,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":32,"time":1784451780041,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":33,"time":1784451782052,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":34,"time":1784451782052,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":35,"time":1784451782052,"data":{"turn":2,"step":1}} +{"type":"request/header","seq":36,"time":1784451782052,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} +{"type":"assistant/chunk","seq":37,"time":1784451783403,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":38,"time":1784451783403,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":39,"time":1784451783502,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":40,"time":1784451783534,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} +{"type":"assistant/chunk","seq":41,"time":1784451783558,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":42,"time":1784451783558,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":43,"time":1784451783558,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} +{"type":"assistant/chunk","seq":44,"time":1784451783587,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":45,"time":1784451783587,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} +{"type":"assistant/chunk","seq":46,"time":1784451783617,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} +{"type":"assistant/chunk","seq":47,"time":1784451783617,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} +{"type":"assistant/chunk","seq":48,"time":1784451783617,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":49,"time":1784451783617,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} +{"type":"assistant/chunk","seq":50,"time":1784451783617,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ARM"}}} +{"type":"assistant/chunk","seq":51,"time":1784451783617,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":52,"time":1784451783642,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} +{"type":"assistant/chunk","seq":53,"time":1784451783642,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":54,"time":1784451783642,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" earlier"}}} +{"type":"assistant/chunk","seq":55,"time":1784451783642,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":56,"time":1784451783642,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" They"}}} +{"type":"assistant/chunk","seq":57,"time":1784451783668,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'re"}}} +{"type":"assistant/chunk","seq":58,"time":1784451783668,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" now"}}} +{"type":"assistant/chunk","seq":59,"time":1784451783695,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" asking"}}} +{"type":"assistant/chunk","seq":60,"time":1784451783695,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":61,"time":1784451783725,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":62,"time":1784451783725,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" recall"}}} +{"type":"assistant/chunk","seq":63,"time":1784451783725,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":64,"time":1784451783725,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":65,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":66,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"M"}}} +{"type":"assistant/chunk","seq":67,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ARM"}}} +{"type":"assistant/chunk","seq":68,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"AL"}}} +{"type":"assistant/chunk","seq":69,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ADE"}}} +{"type":"assistant/chunk","seq":70,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked me to remember the codeword \"MARMALADE\" earlier. They're now asking me to recall it."}}}} +{"type":"assistant/chunk","seq":71,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"MARMALADE"}}}} +{"type":"assistant/chunk","seq":72,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3331,"outputTokens":32,"cacheReadTokens":0,"reasoningTokens":27}}}} +{"type":"assistant/chunk","seq":73,"time":1784451783776,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":74,"time":1784451783777,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the codeword \"MARMALADE\" earlier. They're now asking me to recall it."},{"type":"text","text":"MARMALADE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3331,"outputTokens":32,"cacheReadTokens":0,"reasoningTokens":27}},"sourceEventSeqs":[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73],"surfaceOp":"append"} +{"type":"step/end","seq":75,"time":1784451783777,"data":{"turn":2,"step":1}} +{"type":"turn/end","seq":76,"time":1784451783777,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl index 64da6e60e5..78846dd11f 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl @@ -1,194 +1,169 @@ -{"type":"session","version":0,"id":"96cf59c9-b347-48b9-b234-a5200913ad05","createdAt":1783352134832,"cwd":"/tmp/acp-snap-cwd-0HLtcD"} -{"type":"turn/start","seq":0,"time":1783352134837,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352134838,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352134840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352135621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352135654,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} -{"type":"assistant/chunk","seq":11,"time":1783352135655,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":12,"time":1783352135655,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":13,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":14,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":15,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":16,"time":1783352135682,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} -{"type":"assistant/chunk","seq":17,"time":1783352135683,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ARM"}}} -{"type":"assistant/chunk","seq":18,"time":1783352135683,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":19,"time":1783352135712,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} -{"type":"assistant/chunk","seq":20,"time":1783352135713,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":21,"time":1783352135713,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":22,"time":1783352135713,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":23,"time":1783352135739,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":24,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} -{"type":"assistant/chunk","seq":25,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":26,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"OK"}}} -{"type":"assistant/chunk","seq":27,"time":1783352135740,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":28,"time":1783352135770,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":29,"time":1783352135770,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} -{"type":"assistant/chunk","seq":30,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."}}}} -{"type":"assistant/chunk","seq":31,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} -{"type":"assistant/chunk","seq":32,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}}}} -{"type":"assistant/chunk","seq":33,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} -{"type":"step/end","seq":35,"time":1783352135773,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":36,"time":1783352135773,"data":{"turn":1,"reason":{"kind":"completed"}}} -{"type":"turn/start","seq":37,"time":1783352135780,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":38,"time":1783352135780,"data":{"content":[{"type":"text","text":"Use the subagent_fork tool exactly once to delegate this subtask to a forked child agent: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.' The forked child inherits this conversation, so it can answer. After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":39,"time":1783352135781,"data":{"turn":2,"step":1}} -{"type":"assistant/chunk","seq":40,"time":1783352136109,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":41,"time":1783352136109,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":42,"time":1783352136226,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":43,"time":1783352136255,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":44,"time":1783352136256,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":45,"time":1783352136256,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":46,"time":1783352136256,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} -{"type":"assistant/chunk","seq":47,"time":1783352136256,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":48,"time":1783352136282,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":49,"time":1783352136283,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} -{"type":"assistant/chunk","seq":50,"time":1783352136283,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ork"}}} -{"type":"assistant/chunk","seq":51,"time":1783352136283,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":52,"time":1783352136314,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" delegate"}}} -{"type":"assistant/chunk","seq":53,"time":1783352136314,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} -{"type":"assistant/chunk","seq":54,"time":1783352136341,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" question"}}} -{"type":"assistant/chunk","seq":55,"time":1783352136366,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":56,"time":1783352136367,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} -{"type":"assistant/chunk","seq":57,"time":1783352136394,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":58,"time":1783352136395,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" agent"}}} -{"type":"assistant/chunk","seq":59,"time":1783352136395,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":60,"time":1783352136423,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} -{"type":"assistant/chunk","seq":61,"time":1783352136423,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":62,"time":1783352136423,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" agent"}}} -{"type":"assistant/chunk","seq":63,"time":1783352136423,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" inher"}}} -{"type":"assistant/chunk","seq":64,"time":1783352136450,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"its"}}} -{"type":"assistant/chunk","seq":65,"time":1783352136451,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} -{"type":"assistant/chunk","seq":66,"time":1783352136478,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} -{"type":"assistant/chunk","seq":67,"time":1783352136478,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":68,"time":1783352136508,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":69,"time":1783352136535,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" be"}}} -{"type":"assistant/chunk","seq":70,"time":1783352136535,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" able"}}} -{"type":"assistant/chunk","seq":71,"time":1783352136563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":72,"time":1783352136563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" answer"}}} -{"type":"assistant/chunk","seq":73,"time":1783352136563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":74,"time":1783352136563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":75,"time":1783352136563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} -{"type":"assistant/chunk","seq":76,"time":1783352136591,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":77,"time":1783352136591,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":78,"time":1783352136592,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":79,"time":1783352136592,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":80,"time":1783352136592,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" MAR"}}} -{"type":"assistant/chunk","seq":81,"time":1783352136620,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} -{"type":"assistant/chunk","seq":82,"time":1783352136620,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":83,"time":1783352136620,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} -{"type":"assistant/chunk","seq":84,"time":1783352136620,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":85,"time":1783352136620,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" After"}}} -{"type":"assistant/chunk","seq":86,"time":1783352136648,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":87,"time":1783352136677,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":88,"time":1783352136677,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":89,"time":1783352136678,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" returns"}}} -{"type":"assistant/chunk","seq":90,"time":1783352136678,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":91,"time":1783352136678,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":92,"time":1783352136678,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":93,"time":1783352136705,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":94,"time":1783352136706,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":95,"time":1783352136706,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" PAR"}}} -{"type":"assistant/chunk","seq":96,"time":1783352136732,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} -{"type":"assistant/chunk","seq":97,"time":1783352136733,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":98,"time":1783352136733,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":99,"time":1783352136733,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":100,"time":1783352136819,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":101,"time":1783352136819,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":102,"time":1783352136847,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":103,"time":1783352136847,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":104,"time":1783352136847,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":105,"time":1783352136847,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":106,"time":1783352136876,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":107,"time":1783352136877,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":108,"time":1783352136877,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"Recall"}}} -{"type":"assistant/chunk","seq":109,"time":1783352136903,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" project"}}} -{"type":"assistant/chunk","seq":110,"time":1783352136903,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" cod"}}} -{"type":"assistant/chunk","seq":111,"time":1783352136904,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"ew"}}} -{"type":"assistant/chunk","seq":112,"time":1783352136904,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"ord"}}} -{"type":"assistant/chunk","seq":113,"time":1783352136904,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":114,"time":1783352136960,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":115,"time":1783352136961,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":116,"time":1783352136961,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"prom"}}} -{"type":"assistant/chunk","seq":117,"time":1783352136961,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"pt"}}} -{"type":"assistant/chunk","seq":118,"time":1783352136961,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":119,"time":1783352136961,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":120,"time":1783352136987,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":121,"time":1783352136987,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"What"}}} -{"type":"assistant/chunk","seq":122,"time":1783352136987,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" is"}}} -{"type":"assistant/chunk","seq":123,"time":1783352136987,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":124,"time":1783352136987,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" project"}}} -{"type":"assistant/chunk","seq":125,"time":1783352137015,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" cod"}}} -{"type":"assistant/chunk","seq":126,"time":1783352137015,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"ew"}}} -{"type":"assistant/chunk","seq":127,"time":1783352137015,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"ord"}}} -{"type":"assistant/chunk","seq":128,"time":1783352137015,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" mentioned"}}} -{"type":"assistant/chunk","seq":129,"time":1783352137015,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" earlier"}}} -{"type":"assistant/chunk","seq":130,"time":1783352137015,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" in"}}} -{"type":"assistant/chunk","seq":131,"time":1783352137043,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" this"}}} -{"type":"assistant/chunk","seq":132,"time":1783352137043,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" conversation"}}} -{"type":"assistant/chunk","seq":133,"time":1783352137043,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"?"}}} -{"type":"assistant/chunk","seq":134,"time":1783352137043,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" Reply"}}} -{"type":"assistant/chunk","seq":135,"time":1783352137043,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":136,"time":1783352137043,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" exactly"}}} -{"type":"assistant/chunk","seq":137,"time":1783352137071,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" that"}}} -{"type":"assistant/chunk","seq":138,"time":1783352137071,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" one"}}} -{"type":"assistant/chunk","seq":139,"time":1783352137071,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" word"}}} -{"type":"assistant/chunk","seq":140,"time":1783352137071,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":141,"time":1783352137071,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" nothing"}}} -{"type":"assistant/chunk","seq":142,"time":1783352137071,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":" else"}}} -{"type":"assistant/chunk","seq":143,"time":1783352137099,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":144,"time":1783352137099,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":145,"time":1783352137099,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":146,"time":1783352137158,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use subagent_fork to delegate a question to a child agent. The child agent inherits this conversation and should be able to answer: the project codeword is MARMALADE. After the subagent returns, I should reply with PARENT_DONE."}}}} -{"type":"assistant/chunk","seq":147,"time":1783352137158,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} -{"type":"assistant/chunk","seq":148,"time":1783352137158,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}}}} -{"type":"assistant/chunk","seq":149,"time":1783352137159,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":150,"time":1783352137159,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use subagent_fork to delegate a question to a child agent. The child agent inherits this conversation and should be able to answer: the project codeword is MARMALADE. After the subagent returns, I should reply with PARENT_DONE."},{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}},"sourceEventSeqs":[40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} -{"type":"tool/call","seq":151,"time":1783352137159,"data":{"turn":2,"step":1,"callId":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} -{"type":"tool/result","seq":152,"time":1783352138315,"data":{"turn":2,"step":1,"callId":"call_00_sAtKUseRzHRBvL4CF7XF1334","content":[{"type":"text","text":"MARMALADE"}],"isError":false},"sourceEventSeqs":[151],"surfaceOp":"append"} -{"type":"step/end","seq":153,"time":1783352138316,"data":{"turn":2,"step":1}} -{"type":"step/start","seq":154,"time":1783352138317,"data":{"turn":2,"step":2}} -{"type":"assistant/chunk","seq":155,"time":1783352138956,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":156,"time":1783352138956,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":157,"time":1783352139100,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" for"}}} -{"type":"assistant/chunk","seq":158,"time":1783352139128,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ked"}}} -{"type":"assistant/chunk","seq":159,"time":1783352139128,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":160,"time":1783352139128,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" agent"}}} -{"type":"assistant/chunk","seq":161,"time":1783352139156,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" correctly"}}} -{"type":"assistant/chunk","seq":162,"time":1783352139157,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":163,"time":1783352139157,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":164,"time":1783352139157,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} -{"type":"assistant/chunk","seq":165,"time":1783352139157,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ARM"}}} -{"type":"assistant/chunk","seq":166,"time":1783352139186,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":167,"time":1783352139186,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} -{"type":"assistant/chunk","seq":168,"time":1783352139186,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":169,"time":1783352139186,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} -{"type":"assistant/chunk","seq":170,"time":1783352139186,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":171,"time":1783352139186,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} -{"type":"assistant/chunk","seq":172,"time":1783352139215,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":173,"time":1783352139215,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":174,"time":1783352139215,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":175,"time":1783352139216,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":176,"time":1783352139256,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} -{"type":"assistant/chunk","seq":177,"time":1783352139257,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} -{"type":"assistant/chunk","seq":178,"time":1783352139257,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":179,"time":1783352139257,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":180,"time":1783352139257,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":181,"time":1783352139273,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":182,"time":1783352139273,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} -{"type":"assistant/chunk","seq":183,"time":1783352139273,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} -{"type":"assistant/chunk","seq":184,"time":1783352139273,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} -{"type":"assistant/chunk","seq":185,"time":1783352139273,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":186,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The forked child agent correctly returned \"MARMALADE\". Now I need to reply with \"PARENT_DONE\"."}}}} -{"type":"assistant/chunk","seq":187,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} -{"type":"assistant/chunk","seq":188,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}}}} -{"type":"assistant/chunk","seq":189,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":190,"time":1783352139274,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The forked child agent correctly returned \"MARMALADE\". Now I need to reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}},"sourceEventSeqs":[155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"} -{"type":"step/end","seq":191,"time":1783352139274,"data":{"turn":2,"step":2}} -{"type":"turn/end","seq":192,"time":1783352139274,"data":{"turn":2,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"19a0ab16-a36d-49c8-bac2-c1b2208844ad","createdAt":1784451778257,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-CuULie"} +{"type":"turn/start","seq":0,"time":1784451778261,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451778262,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451778263,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451778263,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451779662,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451779662,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451779947,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451779948,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451779949,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451779949,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} +{"type":"assistant/chunk","seq":11,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":12,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" fact"}}} +{"type":"assistant/chunk","seq":13,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":14,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":15,"time":1784451779950,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1784451779958,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":17,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":18,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":19,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":20,"time":1784451779972,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" No"}}} +{"type":"assistant/chunk","seq":21,"time":1784451780009,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":22,"time":1784451780009,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" needed"}}} +{"type":"assistant/chunk","seq":23,"time":1784451780009,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":24,"time":1784451780035,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":25,"time":1784451780036,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} +{"type":"assistant/chunk","seq":26,"time":1784451780036,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."}}}} +{"type":"assistant/chunk","seq":27,"time":1784451780037,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} +{"type":"assistant/chunk","seq":28,"time":1784451780037,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3568,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":29,"time":1784451780037,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":30,"time":1784451780041,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3568,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"step/end","seq":31,"time":1784451780041,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":32,"time":1784451780041,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":33,"time":1784451780063,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":34,"time":1784451780063,"data":{"content":[{"type":"text","text":"Use the subagent_fork tool exactly once to delegate this subtask to a forked child agent: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.' The forked child inherits this conversation, so it can answer. After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":35,"time":1784451780063,"data":{"turn":2,"step":1}} +{"type":"assistant/chunk","seq":36,"time":1784451781196,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":37,"time":1784451781197,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":38,"time":1784451781296,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":39,"time":1784451781327,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":40,"time":1784451781327,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":41,"time":1784451781327,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":42,"time":1784451781327,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":43,"time":1784451781327,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":44,"time":1784451781354,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":45,"time":1784451781355,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} +{"type":"assistant/chunk","seq":46,"time":1784451781355,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ork"}}} +{"type":"assistant/chunk","seq":47,"time":1784451781355,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":48,"time":1784451781379,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ask"}}} +{"type":"assistant/chunk","seq":49,"time":1784451781408,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":50,"time":1784451781436,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} +{"type":"assistant/chunk","seq":51,"time":1784451781437,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" agent"}}} +{"type":"assistant/chunk","seq":52,"time":1784451781437,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" about"}}} +{"type":"assistant/chunk","seq":53,"time":1784451781473,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":54,"time":1784451781473,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} +{"type":"assistant/chunk","seq":55,"time":1784451781473,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} +{"type":"assistant/chunk","seq":56,"time":1784451781474,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} +{"type":"assistant/chunk","seq":57,"time":1784451781474,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} +{"type":"assistant/chunk","seq":58,"time":1784451781474,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":59,"time":1784451781490,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} +{"type":"assistant/chunk","seq":60,"time":1784451781490,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} +{"type":"assistant/chunk","seq":61,"time":1784451781519,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} +{"type":"assistant/chunk","seq":62,"time":1784451781519,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} +{"type":"assistant/chunk","seq":63,"time":1784451781519,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} +{"type":"assistant/chunk","seq":64,"time":1784451781519,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" MAR"}}} +{"type":"assistant/chunk","seq":65,"time":1784451781546,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} +{"type":"assistant/chunk","seq":66,"time":1784451781546,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":67,"time":1784451781547,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} +{"type":"assistant/chunk","seq":68,"time":1784451781547,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":69,"time":1784451781547,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":70,"time":1784451781572,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":71,"time":1784451781573,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" delegate"}}} +{"type":"assistant/chunk","seq":72,"time":1784451781573,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} +{"type":"assistant/chunk","seq":73,"time":1784451781598,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" task"}}} +{"type":"assistant/chunk","seq":74,"time":1784451781599,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":75,"time":1784451781688,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":76,"time":1784451781688,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":77,"time":1784451781712,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":78,"time":1784451781712,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":79,"time":1784451781712,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":80,"time":1784451781712,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":81,"time":1784451781712,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":82,"time":1784451781736,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":83,"time":1784451781736,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"Recall"}}} +{"type":"assistant/chunk","seq":84,"time":1784451781772,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" project"}}} +{"type":"assistant/chunk","seq":85,"time":1784451781773,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" cod"}}} +{"type":"assistant/chunk","seq":86,"time":1784451781773,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"ew"}}} +{"type":"assistant/chunk","seq":87,"time":1784451781773,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"ord"}}} +{"type":"assistant/chunk","seq":88,"time":1784451781773,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":89,"time":1784451781833,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":90,"time":1784451781834,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":91,"time":1784451781834,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"prom"}}} +{"type":"assistant/chunk","seq":92,"time":1784451781834,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"pt"}}} +{"type":"assistant/chunk","seq":93,"time":1784451781834,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":94,"time":1784451781834,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":95,"time":1784451781849,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":96,"time":1784451781849,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"What"}}} +{"type":"assistant/chunk","seq":97,"time":1784451781849,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" is"}}} +{"type":"assistant/chunk","seq":98,"time":1784451781849,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":99,"time":1784451781849,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" project"}}} +{"type":"assistant/chunk","seq":100,"time":1784451781878,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" cod"}}} +{"type":"assistant/chunk","seq":101,"time":1784451781879,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"ew"}}} +{"type":"assistant/chunk","seq":102,"time":1784451781879,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"ord"}}} +{"type":"assistant/chunk","seq":103,"time":1784451781879,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" mentioned"}}} +{"type":"assistant/chunk","seq":104,"time":1784451781879,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" earlier"}}} +{"type":"assistant/chunk","seq":105,"time":1784451781879,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" in"}}} +{"type":"assistant/chunk","seq":106,"time":1784451781906,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" this"}}} +{"type":"assistant/chunk","seq":107,"time":1784451781907,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" conversation"}}} +{"type":"assistant/chunk","seq":108,"time":1784451781907,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"?"}}} +{"type":"assistant/chunk","seq":109,"time":1784451781907,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" Reply"}}} +{"type":"assistant/chunk","seq":110,"time":1784451781907,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":111,"time":1784451781907,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":112,"time":1784451781934,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" that"}}} +{"type":"assistant/chunk","seq":113,"time":1784451781934,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" one"}}} +{"type":"assistant/chunk","seq":114,"time":1784451781934,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":115,"time":1784451781934,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":116,"time":1784451781934,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":117,"time":1784451781934,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":118,"time":1784451781991,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":119,"time":1784451781991,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":120,"time":1784451782006,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":121,"time":1784451782045,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use subagent_fork to ask the child agent about the project codeword. The codeword is MARMALADE. Let me delegate this task."}}}} +{"type":"assistant/chunk","seq":122,"time":1784451782045,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":123,"time":1784451782045,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":201,"outputTokens":126,"cacheReadTokens":3456,"reasoningTokens":38}}}} +{"type":"assistant/chunk","seq":124,"time":1784451782045,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":125,"time":1784451782046,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use subagent_fork to ask the child agent about the project codeword. The codeword is MARMALADE. Let me delegate this task."},{"type":"tool-call","id":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":201,"outputTokens":126,"cacheReadTokens":3456,"reasoningTokens":38}},"sourceEventSeqs":[36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124],"surfaceOp":"append"} +{"type":"tool/call","seq":126,"time":1784451782047,"data":{"turn":2,"step":1,"callId":"call_00_3wP4hrLZZQgqILQi2ZXU3942","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} +{"type":"tool/result","seq":127,"time":1784451783786,"data":{"turn":2,"step":1,"callId":"call_00_3wP4hrLZZQgqILQi2ZXU3942","content":[{"type":"text","text":"MARMALADE"}],"isError":false},"sourceEventSeqs":[126],"surfaceOp":"append"} +{"type":"step/end","seq":128,"time":1784451783786,"data":{"turn":2,"step":1}} +{"type":"step/start","seq":129,"time":1784451783787,"data":{"turn":2,"step":2}} +{"type":"assistant/chunk","seq":130,"time":1784451784950,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":131,"time":1784451784950,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":132,"time":1784451785105,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":133,"time":1784451785140,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":134,"time":1784451785140,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":135,"time":1784451785140,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":136,"time":1784451785140,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"M"}}} +{"type":"assistant/chunk","seq":137,"time":1784451785141,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ARM"}}} +{"type":"assistant/chunk","seq":138,"time":1784451785259,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":139,"time":1784451785259,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ADE"}}} +{"type":"assistant/chunk","seq":140,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":141,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" which"}}} +{"type":"assistant/chunk","seq":142,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} +{"type":"assistant/chunk","seq":143,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" correct"}}} +{"type":"assistant/chunk","seq":144,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":145,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":146,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":147,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":148,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":149,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":150,"time":1784451785260,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":151,"time":1784451785265,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" PAR"}}} +{"type":"assistant/chunk","seq":152,"time":1784451785283,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} +{"type":"assistant/chunk","seq":153,"time":1784451785283,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":154,"time":1784451785283,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":155,"time":1784451785283,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":156,"time":1784451785283,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":157,"time":1784451785283,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} +{"type":"assistant/chunk","seq":158,"time":1784451785308,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} +{"type":"assistant/chunk","seq":159,"time":1784451785308,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} +{"type":"assistant/chunk","seq":160,"time":1784451785308,"data":{"turn":2,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":161,"time":1784451785308,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The subagent returned \"MARMALADE\" which is correct. Now I need to reply with PARENT_DONE."}}}} +{"type":"assistant/chunk","seq":162,"time":1784451785309,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} +{"type":"assistant/chunk","seq":163,"time":1784451785309,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":87,"outputTokens":30,"cacheReadTokens":3712,"reasoningTokens":25}}}} +{"type":"assistant/chunk","seq":164,"time":1784451785309,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":165,"time":1784451785309,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The subagent returned \"MARMALADE\" which is correct. Now I need to reply with PARENT_DONE."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":87,"outputTokens":30,"cacheReadTokens":3712,"reasoningTokens":25}},"sourceEventSeqs":[130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164],"surfaceOp":"append"} +{"type":"step/end","seq":166,"time":1784451785309,"data":{"turn":2,"step":2}} +{"type":"turn/end","seq":167,"time":1784451785310,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl index e2941dd851..e4f4298b50 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl @@ -6,23 +6,19 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" remember"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cod"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ew"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ord"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"M"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ARM"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ADE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" fact"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" just"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"OK"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" No"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tools"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" needed"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"OK"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} @@ -36,47 +32,53 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_f"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ork"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" delegate"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" question"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ask"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" child"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" agent"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" child"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" agent"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" inher"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"its"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" this"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" conversation"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" be"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" able"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" answer"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" about"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" project"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cod"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ew"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ord"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cod"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ew"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ord"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" MAR"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"M"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ADE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" After"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" delegate"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" this"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" task"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_3wP4hrLZZQgqILQi2ZXU3942","title":"subagent_fork","kind":"other","status":"in_progress","rawInput":{"description":"Recall project codeword","prompt":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_3wP4hrLZZQgqILQi2ZXU3942","status":"completed","content":[{"type":"content","content":{"type":"text","text":"MARMALADE"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returns"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"M"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ARM"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ADE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" which"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" correct"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" PAR"}}}} @@ -84,33 +86,6 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_sAtKUseRzHRBvL4CF7XF1334","title":"subagent_fork","kind":"other","status":"in_progress","rawInput":{"description":"Recall project codeword","prompt":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_sAtKUseRzHRBvL4CF7XF1334","status":"completed","content":[{"type":"content","content":{"type":"text","text":"MARMALADE"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" for"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" child"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" agent"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" correctly"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"M"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ARM"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ADE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PAR"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENT"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_D"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"PAR"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ENT"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"_D"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl index c99a5681e2..c82688afea 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl @@ -1,36 +1,36 @@ -{"type":"session","version":0,"id":"e4aafa18-b9e3-48d0-8aae-6c9b25dcae80","createdAt":1783352145223,"cwd":"/tmp/acp-snap-cwd-i43JSF","parentSession":"959ffdf5-03e2-465e-9482-009b704632dc"} -{"type":"turn/start","seq":0,"time":1783352145224,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352145224,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352145224,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352145224,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352145820,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352145821,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352145985,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352146014,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":8,"time":1783352146042,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352146043,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352146043,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":11,"time":1783352146043,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":12,"time":1783352146043,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":13,"time":1783352146071,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":14,"time":1783352146071,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":15,"time":1783352146071,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":16,"time":1783352146071,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":17,"time":1783352146071,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":18,"time":1783352146071,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":19,"time":1783352146100,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":20,"time":1783352146100,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":21,"time":1783352146100,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} -{"type":"assistant/chunk","seq":22,"time":1783352146100,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} -{"type":"assistant/chunk","seq":23,"time":1783352146100,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":24,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":25,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"AL"}}} -{"type":"assistant/chunk","seq":26,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"P"}}} -{"type":"assistant/chunk","seq":27,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"HA"}}} -{"type":"assistant/chunk","seq":28,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user asked me to reply with exactly the word \"ALPHA\" and nothing else."}}}} -{"type":"assistant/chunk","seq":29,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} -{"type":"assistant/chunk","seq":30,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}}} -{"type":"assistant/chunk","seq":31,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783352146130,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} -{"type":"step/end","seq":33,"time":1783352146130,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":34,"time":1783352146130,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"f117c899-e0b7-4756-baef-ca24df6c4401","createdAt":1784451789830,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-vBPxcm","parentSession":"91b46b45-a870-42dc-9314-be4ceeb9c3f3","delegationDepth":1} +{"type":"turn/start","seq":0,"time":1784451789831,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451789831,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451789831,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451789832,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451796262,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451796262,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451796377,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451796414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451796414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451796414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451796414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1784451796414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1784451796414,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1784451796437,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":14,"time":1784451796437,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":15,"time":1784451796438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":16,"time":1784451796438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":17,"time":1784451796438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} +{"type":"assistant/chunk","seq":18,"time":1784451796438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} +{"type":"assistant/chunk","seq":19,"time":1784451796464,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":20,"time":1784451796464,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":21,"time":1784451796464,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":22,"time":1784451796464,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":23,"time":1784451796464,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":24,"time":1784451796498,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":25,"time":1784451796498,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"AL"}}} +{"type":"assistant/chunk","seq":26,"time":1784451796498,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"P"}}} +{"type":"assistant/chunk","seq":27,"time":1784451796498,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"HA"}}} +{"type":"assistant/chunk","seq":28,"time":1784451796499,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."}}}} +{"type":"assistant/chunk","seq":29,"time":1784451796499,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} +{"type":"assistant/chunk","seq":30,"time":1784451796499,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3284,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":31,"time":1784451796499,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":32,"time":1784451796500,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3284,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1784451796500,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":34,"time":1784451796500,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl index adfcb6f60e..59b2ee2956 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl @@ -1,79 +1,77 @@ -{"type":"session","version":0,"id":"02b3a8dd-1d5e-4866-825f-5fbf5000a632","createdAt":1783352147504,"cwd":"/tmp/acp-snap-cwd-i43JSF","parentSession":"959ffdf5-03e2-465e-9482-009b704632dc","seedLength":31} -{"type":"turn/start","seq":0,"time":1783352142834,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352142834,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352142835,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352143493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352143494,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352143621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352143652,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} -{"type":"assistant/chunk","seq":11,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} -{"type":"assistant/chunk","seq":12,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":13,"time":1783352143678,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":14,"time":1783352143679,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":15,"time":1783352143679,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":16,"time":1783352143679,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} -{"type":"assistant/chunk","seq":17,"time":1783352143707,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":18,"time":1783352143708,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":19,"time":1783352143708,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":20,"time":1783352143708,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"OK"}}} -{"type":"assistant/chunk","seq":21,"time":1783352143736,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":22,"time":1783352143766,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":23,"time":1783352143766,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} -{"type":"assistant/chunk","seq":24,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."}}}} -{"type":"assistant/chunk","seq":25,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} -{"type":"assistant/chunk","seq":26,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}}}} -{"type":"assistant/chunk","seq":27,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} -{"type":"step/end","seq":29,"time":1783352143771,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":30,"time":1783352143771,"data":{"turn":1,"reason":{"kind":"completed"}}} -{"type":"turn/start","seq":31,"time":1783352147508,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":32,"time":1783352147509,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":33,"time":1783352147509,"data":{"turn":2,"step":1}} -{"type":"request/header","seq":34,"time":1783352147509,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} -{"type":"assistant/chunk","seq":35,"time":1783352147925,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":36,"time":1783352147925,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":37,"time":1783352148019,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":38,"time":1783352148048,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} -{"type":"assistant/chunk","seq":39,"time":1783352148049,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" asking"}}} -{"type":"assistant/chunk","seq":40,"time":1783352148049,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":41,"time":1783352148076,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":42,"time":1783352148076,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" recall"}}} -{"type":"assistant/chunk","seq":43,"time":1783352148077,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":44,"time":1783352148077,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} -{"type":"assistant/chunk","seq":45,"time":1783352148077,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":46,"time":1783352148077,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":47,"time":1783352148106,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":48,"time":1783352148106,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":49,"time":1783352148106,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} -{"type":"assistant/chunk","seq":50,"time":1783352148106,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" mentioned"}}} -{"type":"assistant/chunk","seq":51,"time":1783352148141,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" earlier"}}} -{"type":"assistant/chunk","seq":52,"time":1783352148141,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} -{"type":"assistant/chunk","seq":53,"time":1783352148141,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":54,"time":1783352148141,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} -{"type":"assistant/chunk","seq":55,"time":1783352148141,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":56,"time":1783352148167,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":57,"time":1783352148196,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} -{"type":"assistant/chunk","seq":58,"time":1783352148227,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" told"}}} -{"type":"assistant/chunk","seq":59,"time":1783352148227,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":60,"time":1783352148257,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} -{"type":"assistant/chunk","seq":61,"time":1783352148257,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":62,"time":1783352148257,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":63,"time":1783352148284,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" SA"}}} -{"type":"assistant/chunk","seq":64,"time":1783352148285,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"FF"}}} -{"type":"assistant/chunk","seq":65,"time":1783352148312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"RON"}}} -{"type":"assistant/chunk","seq":66,"time":1783352148312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":67,"time":1783352148313,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":68,"time":1783352148313,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"SA"}}} -{"type":"assistant/chunk","seq":69,"time":1783352148313,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"FF"}}} -{"type":"assistant/chunk","seq":70,"time":1783352148344,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"RON"}}} -{"type":"assistant/chunk","seq":71,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."}}}} -{"type":"assistant/chunk","seq":72,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"SAFFRON"}}}} -{"type":"assistant/chunk","seq":73,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}}}} -{"type":"assistant/chunk","seq":74,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":75,"time":1783352148345,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."},{"type":"text","text":"SAFFRON"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74],"surfaceOp":"append"} -{"type":"step/end","seq":76,"time":1783352148345,"data":{"turn":2,"step":1}} -{"type":"turn/end","seq":77,"time":1783352148345,"data":{"turn":2,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"001332d1-d501-4546-bf82-13e58b28b06b","createdAt":1784451798519,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-vBPxcm","parentSession":"91b46b45-a870-42dc-9314-be4ceeb9c3f3","seedLength":33,"delegationDepth":1} +{"type":"turn/start","seq":0,"time":1784451785951,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451785952,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451785955,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451785955,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451787067,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451787068,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451787176,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451787205,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451787206,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451787206,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451787206,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} +{"type":"assistant/chunk","seq":11,"time":1784451787207,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":12,"time":1784451787207,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" fact"}}} +{"type":"assistant/chunk","seq":13,"time":1784451787223,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":14,"time":1784451787267,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":15,"time":1784451787267,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1784451787284,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":17,"time":1784451787285,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":18,"time":1784451787285,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":19,"time":1784451787285,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":20,"time":1784451787312,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" No"}}} +{"type":"assistant/chunk","seq":21,"time":1784451787312,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":22,"time":1784451787313,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" needed"}}} +{"type":"assistant/chunk","seq":23,"time":1784451787337,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":24,"time":1784451787337,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":25,"time":1784451787338,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} +{"type":"assistant/chunk","seq":26,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."}}}} +{"type":"assistant/chunk","seq":27,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} +{"type":"assistant/chunk","seq":28,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3567,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":29,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":30,"time":1784451787343,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3567,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"step/end","seq":31,"time":1784451787343,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":32,"time":1784451787343,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":33,"time":1784451798520,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":34,"time":1784451798520,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":35,"time":1784451798520,"data":{"turn":2,"step":1}} +{"type":"request/header","seq":36,"time":1784451798520,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} +{"type":"assistant/chunk","seq":37,"time":1784451800033,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":38,"time":1784451800033,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":39,"time":1784451800128,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":40,"time":1784451800164,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} +{"type":"assistant/chunk","seq":41,"time":1784451800165,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" asking"}}} +{"type":"assistant/chunk","seq":42,"time":1784451800165,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":43,"time":1784451800187,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":44,"time":1784451800187,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" recall"}}} +{"type":"assistant/chunk","seq":45,"time":1784451800187,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":46,"time":1784451800187,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} +{"type":"assistant/chunk","seq":47,"time":1784451800187,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} +{"type":"assistant/chunk","seq":48,"time":1784451800187,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} +{"type":"assistant/chunk","seq":49,"time":1784451800219,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} +{"type":"assistant/chunk","seq":50,"time":1784451800219,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" mentioned"}}} +{"type":"assistant/chunk","seq":51,"time":1784451800219,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" earlier"}}} +{"type":"assistant/chunk","seq":52,"time":1784451800219,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} +{"type":"assistant/chunk","seq":53,"time":1784451800241,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":54,"time":1784451800241,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} +{"type":"assistant/chunk","seq":55,"time":1784451800241,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":56,"time":1784451800241,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" The"}}} +{"type":"assistant/chunk","seq":57,"time":1784451800241,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} +{"type":"assistant/chunk","seq":58,"time":1784451800271,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} +{"type":"assistant/chunk","seq":59,"time":1784451800271,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} +{"type":"assistant/chunk","seq":60,"time":1784451800271,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} +{"type":"assistant/chunk","seq":61,"time":1784451800271,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" SA"}}} +{"type":"assistant/chunk","seq":62,"time":1784451800298,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"FF"}}} +{"type":"assistant/chunk","seq":63,"time":1784451800298,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"RON"}}} +{"type":"assistant/chunk","seq":64,"time":1784451800299,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":65,"time":1784451800299,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":66,"time":1784451800299,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"SA"}}} +{"type":"assistant/chunk","seq":67,"time":1784451800299,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"FF"}}} +{"type":"assistant/chunk","seq":68,"time":1784451800323,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"RON"}}} +{"type":"assistant/chunk","seq":69,"time":1784451800329,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user is asking me to recall the project codeword mentioned earlier in the conversation. The codeword is SAFFRON."}}}} +{"type":"assistant/chunk","seq":70,"time":1784451800330,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"SAFFRON"}}}} +{"type":"assistant/chunk","seq":71,"time":1784451800330,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2050,"outputTokens":31,"cacheReadTokens":1280,"reasoningTokens":27}}}} +{"type":"assistant/chunk","seq":72,"time":1784451800330,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":73,"time":1784451800330,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword mentioned earlier in the conversation. The codeword is SAFFRON."},{"type":"text","text":"SAFFRON"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2050,"outputTokens":31,"cacheReadTokens":1280,"reasoningTokens":27}},"sourceEventSeqs":[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72],"surfaceOp":"append"} +{"type":"step/end","seq":74,"time":1784451800330,"data":{"turn":2,"step":1}} +{"type":"turn/end","seq":75,"time":1784451800330,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl index 1ea4f541e1..ee9b134de6 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl @@ -1,288 +1,334 @@ -{"type":"session","version":0,"id":"959ffdf5-03e2-465e-9482-009b704632dc","createdAt":1783352142830,"cwd":"/tmp/acp-snap-cwd-i43JSF"} -{"type":"turn/start","seq":0,"time":1783352142834,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352142834,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352142835,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352143493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352143494,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352143621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352143652,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} -{"type":"assistant/chunk","seq":11,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} -{"type":"assistant/chunk","seq":12,"time":1783352143653,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":13,"time":1783352143678,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":14,"time":1783352143679,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":15,"time":1783352143679,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":16,"time":1783352143679,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" just"}}} -{"type":"assistant/chunk","seq":17,"time":1783352143707,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":18,"time":1783352143708,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":19,"time":1783352143708,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":20,"time":1783352143708,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"OK"}}} -{"type":"assistant/chunk","seq":21,"time":1783352143736,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":22,"time":1783352143766,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":23,"time":1783352143766,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} -{"type":"assistant/chunk","seq":24,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."}}}} -{"type":"assistant/chunk","seq":25,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} -{"type":"assistant/chunk","seq":26,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}}}} -{"type":"assistant/chunk","seq":27,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} -{"type":"step/end","seq":29,"time":1783352143771,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":30,"time":1783352143771,"data":{"turn":1,"reason":{"kind":"completed"}}} -{"type":"turn/start","seq":31,"time":1783352143779,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":32,"time":1783352143779,"data":{"content":[{"type":"text","text":"Do these two delegations, once at a time. First, use the subagent tool (fresh child) exactly once: 'Reply with exactly the word ALPHA and nothing else.' Then, after it returns, use the subagent_fork tool (forked child that inherits this conversation) exactly once: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":33,"time":1783352143779,"data":{"turn":2,"step":1}} -{"type":"assistant/chunk","seq":34,"time":1783352144351,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":35,"time":1783352144352,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Let"}}} -{"type":"assistant/chunk","seq":36,"time":1783352144477,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":37,"time":1783352144504,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} -{"type":"assistant/chunk","seq":38,"time":1783352144533,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" these"}}} -{"type":"assistant/chunk","seq":39,"time":1783352144562,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" two"}}} -{"type":"assistant/chunk","seq":40,"time":1783352144563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" deleg"}}} -{"type":"assistant/chunk","seq":41,"time":1783352144563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ations"}}} -{"type":"assistant/chunk","seq":42,"time":1783352144563,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" one"}}} -{"type":"assistant/chunk","seq":43,"time":1783352144591,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" at"}}} -{"type":"assistant/chunk","seq":44,"time":1783352144592,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} -{"type":"assistant/chunk","seq":45,"time":1783352144592,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" time"}}} -{"type":"assistant/chunk","seq":46,"time":1783352144592,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":47,"time":1783352144621,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" requested"}}} -{"type":"assistant/chunk","seq":48,"time":1783352144650,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".\n\n"}}} -{"type":"assistant/chunk","seq":49,"time":1783352144650,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"First"}}} -{"type":"assistant/chunk","seq":50,"time":1783352144650,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":51,"time":1783352144678,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":52,"time":1783352144679,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'ll"}}} -{"type":"assistant/chunk","seq":53,"time":1783352144679,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} -{"type":"assistant/chunk","seq":54,"time":1783352144679,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":55,"time":1783352144679,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":56,"time":1783352144679,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":57,"time":1783352144707,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":58,"time":1783352144708,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} -{"type":"assistant/chunk","seq":59,"time":1783352144737,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"fresh"}}} -{"type":"assistant/chunk","seq":60,"time":1783352144738,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":61,"time":1783352144738,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":")"}}} -{"type":"assistant/chunk","seq":62,"time":1783352144738,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":63,"time":1783352144765,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":64,"time":1783352144794,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":65,"time":1783352144794,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":66,"time":1783352144795,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":67,"time":1783352144795,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":68,"time":1783352144795,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":69,"time":1783352144824,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":70,"time":1783352144892,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":71,"time":1783352144892,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":72,"time":1783352144931,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":73,"time":1783352144932,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":74,"time":1783352144932,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":75,"time":1783352145000,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":76,"time":1783352145001,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":77,"time":1783352145001,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":78,"time":1783352145001,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"Reply"}}} -{"type":"assistant/chunk","seq":79,"time":1783352145001,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" AL"}}} -{"type":"assistant/chunk","seq":80,"time":1783352145012,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"P"}}} -{"type":"assistant/chunk","seq":81,"time":1783352145013,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"HA"}}} -{"type":"assistant/chunk","seq":82,"time":1783352145013,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" only"}}} -{"type":"assistant/chunk","seq":83,"time":1783352145013,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":84,"time":1783352145047,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":85,"time":1783352145047,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":86,"time":1783352145073,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"prom"}}} -{"type":"assistant/chunk","seq":87,"time":1783352145074,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"pt"}}} -{"type":"assistant/chunk","seq":88,"time":1783352145074,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":89,"time":1783352145074,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":90,"time":1783352145104,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":91,"time":1783352145104,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"Reply"}}} -{"type":"assistant/chunk","seq":92,"time":1783352145105,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":93,"time":1783352145105,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" exactly"}}} -{"type":"assistant/chunk","seq":94,"time":1783352145105,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":95,"time":1783352145105,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" word"}}} -{"type":"assistant/chunk","seq":96,"time":1783352145131,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" AL"}}} -{"type":"assistant/chunk","seq":97,"time":1783352145131,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"P"}}} -{"type":"assistant/chunk","seq":98,"time":1783352145131,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"HA"}}} -{"type":"assistant/chunk","seq":99,"time":1783352145131,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":100,"time":1783352145131,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" nothing"}}} -{"type":"assistant/chunk","seq":101,"time":1783352145131,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":" else"}}} -{"type":"assistant/chunk","seq":102,"time":1783352145160,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":103,"time":1783352145161,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":104,"time":1783352145161,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":105,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Let me do these two delegations one at a time as requested.\n\nFirst, I'll use the subagent tool (fresh child) to reply with \"ALPHA\"."}}}} -{"type":"assistant/chunk","seq":106,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} -{"type":"assistant/chunk","seq":107,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}}}} -{"type":"assistant/chunk","seq":108,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":109,"time":1783352145221,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"Let me do these two delegations one at a time as requested.\n\nFirst, I'll use the subagent tool (fresh child) to reply with \"ALPHA\"."},{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}},"sourceEventSeqs":[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} -{"type":"tool/call","seq":110,"time":1783352145222,"data":{"turn":2,"step":1,"callId":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} -{"type":"tool/result","seq":111,"time":1783352146133,"data":{"turn":2,"step":1,"callId":"call_00_YvHr2bGomk5HhpgDTvE81896","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[110],"surfaceOp":"append"} -{"type":"step/end","seq":112,"time":1783352146134,"data":{"turn":2,"step":1}} -{"type":"step/start","seq":113,"time":1783352146134,"data":{"turn":2,"step":2}} -{"type":"assistant/chunk","seq":114,"time":1783352146748,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":115,"time":1783352146748,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":116,"time":1783352146837,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" first"}}} -{"type":"assistant/chunk","seq":117,"time":1783352146865,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":118,"time":1783352146865,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":119,"time":1783352146866,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":120,"time":1783352146866,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":121,"time":1783352146866,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":122,"time":1783352146866,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":123,"time":1783352146897,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":124,"time":1783352146897,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":125,"time":1783352146897,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} -{"type":"assistant/chunk","seq":126,"time":1783352146897,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":127,"time":1783352146898,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} -{"type":"assistant/chunk","seq":128,"time":1783352146898,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":129,"time":1783352146923,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} -{"type":"assistant/chunk","seq":130,"time":1783352146923,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":131,"time":1783352146923,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":132,"time":1783352146923,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":133,"time":1783352146923,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} -{"type":"assistant/chunk","seq":134,"time":1783352146923,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ork"}}} -{"type":"assistant/chunk","seq":135,"time":1783352146951,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":136,"time":1783352146952,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} -{"type":"assistant/chunk","seq":137,"time":1783352146952,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"fork"}}} -{"type":"assistant/chunk","seq":138,"time":1783352146952,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ed"}}} -{"type":"assistant/chunk","seq":139,"time":1783352146979,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":140,"time":1783352146980,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":141,"time":1783352146980,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" inher"}}} -{"type":"assistant/chunk","seq":142,"time":1783352146980,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"its"}}} -{"type":"assistant/chunk","seq":143,"time":1783352146980,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} -{"type":"assistant/chunk","seq":144,"time":1783352147009,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} -{"type":"assistant/chunk","seq":145,"time":1783352147010,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":")"}}} -{"type":"assistant/chunk","seq":146,"time":1783352147010,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":147,"time":1783352147010,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ask"}}} -{"type":"assistant/chunk","seq":148,"time":1783352147010,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" about"}}} -{"type":"assistant/chunk","seq":149,"time":1783352147037,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":150,"time":1783352147037,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} -{"type":"assistant/chunk","seq":151,"time":1783352147038,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":152,"time":1783352147038,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":153,"time":1783352147038,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":154,"time":1783352147038,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":155,"time":1783352147156,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":156,"time":1783352147156,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":157,"time":1783352147156,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":158,"time":1783352147156,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":159,"time":1783352147186,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":160,"time":1783352147186,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":161,"time":1783352147186,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":162,"time":1783352147186,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":163,"time":1783352147214,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"Recall"}}} -{"type":"assistant/chunk","seq":164,"time":1783352147242,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" project"}}} -{"type":"assistant/chunk","seq":165,"time":1783352147243,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" cod"}}} -{"type":"assistant/chunk","seq":166,"time":1783352147243,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"ew"}}} -{"type":"assistant/chunk","seq":167,"time":1783352147243,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"ord"}}} -{"type":"assistant/chunk","seq":168,"time":1783352147243,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":169,"time":1783352147303,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":170,"time":1783352147304,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":171,"time":1783352147304,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"prom"}}} -{"type":"assistant/chunk","seq":172,"time":1783352147304,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"pt"}}} -{"type":"assistant/chunk","seq":173,"time":1783352147304,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":174,"time":1783352147304,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":175,"time":1783352147330,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":176,"time":1783352147331,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"What"}}} -{"type":"assistant/chunk","seq":177,"time":1783352147331,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" is"}}} -{"type":"assistant/chunk","seq":178,"time":1783352147331,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":179,"time":1783352147331,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" project"}}} -{"type":"assistant/chunk","seq":180,"time":1783352147357,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" cod"}}} -{"type":"assistant/chunk","seq":181,"time":1783352147357,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"ew"}}} -{"type":"assistant/chunk","seq":182,"time":1783352147357,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"ord"}}} -{"type":"assistant/chunk","seq":183,"time":1783352147357,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" mentioned"}}} -{"type":"assistant/chunk","seq":184,"time":1783352147357,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" earlier"}}} -{"type":"assistant/chunk","seq":185,"time":1783352147358,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" in"}}} -{"type":"assistant/chunk","seq":186,"time":1783352147385,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" this"}}} -{"type":"assistant/chunk","seq":187,"time":1783352147385,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" conversation"}}} -{"type":"assistant/chunk","seq":188,"time":1783352147385,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"?"}}} -{"type":"assistant/chunk","seq":189,"time":1783352147385,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" Reply"}}} -{"type":"assistant/chunk","seq":190,"time":1783352147386,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":191,"time":1783352147386,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" exactly"}}} -{"type":"assistant/chunk","seq":192,"time":1783352147414,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" that"}}} -{"type":"assistant/chunk","seq":193,"time":1783352147414,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" one"}}} -{"type":"assistant/chunk","seq":194,"time":1783352147414,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" word"}}} -{"type":"assistant/chunk","seq":195,"time":1783352147414,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":196,"time":1783352147414,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" nothing"}}} -{"type":"assistant/chunk","seq":197,"time":1783352147414,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":" else"}}} -{"type":"assistant/chunk","seq":198,"time":1783352147442,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":199,"time":1783352147442,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":200,"time":1783352147443,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":201,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use the subagent_fork tool (forked child that inherits this conversation) to ask about the project codeword."}}}} -{"type":"assistant/chunk","seq":202,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} -{"type":"assistant/chunk","seq":203,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}}}} -{"type":"assistant/chunk","seq":204,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":205,"time":1783352147503,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use the subagent_fork tool (forked child that inherits this conversation) to ask about the project codeword."},{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}},"sourceEventSeqs":[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} -{"type":"tool/call","seq":206,"time":1783352147503,"data":{"turn":2,"step":2,"callId":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} -{"type":"tool/result","seq":207,"time":1783352148348,"data":{"turn":2,"step":2,"callId":"call_00_JSr5rhREq23wSmwSkCP77184","content":[{"type":"text","text":"SAFFRON"}],"isError":false},"sourceEventSeqs":[206],"surfaceOp":"append"} -{"type":"step/end","seq":208,"time":1783352148348,"data":{"turn":2,"step":2}} -{"type":"step/start","seq":209,"time":1783352148348,"data":{"turn":2,"step":3}} -{"type":"assistant/chunk","seq":210,"time":1783352149007,"data":{"turn":2,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":211,"time":1783352149008,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"Both"}}} -{"type":"assistant/chunk","seq":212,"time":1783352149189,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":213,"time":1783352149217,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"agents"}}} -{"type":"assistant/chunk","seq":214,"time":1783352149217,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":215,"time":1783352149246,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":":\n"}}} -{"type":"assistant/chunk","seq":216,"time":1783352149246,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} -{"type":"assistant/chunk","seq":217,"time":1783352149246,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":218,"time":1783352149246,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" First"}}} -{"type":"assistant/chunk","seq":219,"time":1783352149246,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} -{"type":"assistant/chunk","seq":220,"time":1783352149273,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"fresh"}}} -{"type":"assistant/chunk","seq":221,"time":1783352149274,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":222,"time":1783352149305,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"):"}}} -{"type":"assistant/chunk","seq":223,"time":1783352149306,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":224,"time":1783352149330,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":225,"time":1783352149331,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":226,"time":1783352149331,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":227,"time":1783352149331,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\"\n"}}} -{"type":"assistant/chunk","seq":228,"time":1783352149331,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"2"}}} -{"type":"assistant/chunk","seq":229,"time":1783352149331,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":230,"time":1783352149359,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" Second"}}} -{"type":"assistant/chunk","seq":231,"time":1783352149359,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} -{"type":"assistant/chunk","seq":232,"time":1783352149360,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"fork"}}} -{"type":"assistant/chunk","seq":233,"time":1783352149360,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ed"}}} -{"type":"assistant/chunk","seq":234,"time":1783352149360,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":235,"time":1783352149388,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"):"}}} -{"type":"assistant/chunk","seq":236,"time":1783352149388,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":237,"time":1783352149388,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"SA"}}} -{"type":"assistant/chunk","seq":238,"time":1783352149416,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"FF"}}} -{"type":"assistant/chunk","seq":239,"time":1783352149417,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"RON"}}} -{"type":"assistant/chunk","seq":240,"time":1783352149417,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":241,"time":1783352149445,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" -"}}} -{"type":"assistant/chunk","seq":242,"time":1783352149445,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" correctly"}}} -{"type":"assistant/chunk","seq":243,"time":1783352149474,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" inherited"}}} -{"type":"assistant/chunk","seq":244,"time":1783352149503,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":245,"time":1783352149503,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} -{"type":"assistant/chunk","seq":246,"time":1783352149536,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" context"}}} -{"type":"assistant/chunk","seq":247,"time":1783352149536,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" where"}}} -{"type":"assistant/chunk","seq":248,"time":1783352149559,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":249,"time":1783352149588,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" was"}}} -{"type":"assistant/chunk","seq":250,"time":1783352149619,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" asked"}}} -{"type":"assistant/chunk","seq":251,"time":1783352149650,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":252,"time":1783352149650,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} -{"type":"assistant/chunk","seq":253,"time":1783352149650,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":254,"time":1783352149650,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} -{"type":"assistant/chunk","seq":255,"time":1783352149677,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} -{"type":"assistant/chunk","seq":256,"time":1783352149677,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} -{"type":"assistant/chunk","seq":257,"time":1783352149677,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":258,"time":1783352149677,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"SA"}}} -{"type":"assistant/chunk","seq":259,"time":1783352149677,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"FF"}}} -{"type":"assistant/chunk","seq":260,"time":1783352149677,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"RON"}}} -{"type":"assistant/chunk","seq":261,"time":1783352149706,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\".\n\n"}}} -{"type":"assistant/chunk","seq":262,"time":1783352149706,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"Now"}}} -{"type":"assistant/chunk","seq":263,"time":1783352149706,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":264,"time":1783352149707,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":265,"time":1783352149734,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":266,"time":1783352149735,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":267,"time":1783352149735,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} -{"type":"assistant/chunk","seq":268,"time":1783352149735,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} -{"type":"assistant/chunk","seq":269,"time":1783352149735,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":270,"time":1783352149762,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":271,"time":1783352149763,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":272,"time":1783352149763,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":273,"time":1783352149791,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" instructed"}}} -{"type":"assistant/chunk","seq":274,"time":1783352149792,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":275,"time":1783352149792,"data":{"turn":2,"step":3,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":276,"time":1783352149792,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} -{"type":"assistant/chunk","seq":277,"time":1783352149792,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} -{"type":"assistant/chunk","seq":278,"time":1783352149792,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} -{"type":"assistant/chunk","seq":279,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":280,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Both subagents returned:\n1. First (fresh child): \"ALPHA\"\n2. Second (forked child): \"SAFFRON\" - correctly inherited the conversation context where I was asked to remember the codeword \"SAFFRON\".\n\nNow I reply with \"PARENT_DONE\" as instructed."}}}} -{"type":"assistant/chunk","seq":281,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} -{"type":"assistant/chunk","seq":282,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}}}} -{"type":"assistant/chunk","seq":283,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":284,"time":1783352149822,"data":{"turn":2,"step":3,"content":[{"type":"reasoning","text":"Both subagents returned:\n1. First (fresh child): \"ALPHA\"\n2. Second (forked child): \"SAFFRON\" - correctly inherited the conversation context where I was asked to remember the codeword \"SAFFRON\".\n\nNow I reply with \"PARENT_DONE\" as instructed."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}},"sourceEventSeqs":[210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283],"surfaceOp":"append"} -{"type":"step/end","seq":285,"time":1783352149822,"data":{"turn":2,"step":3}} -{"type":"turn/end","seq":286,"time":1783352149822,"data":{"turn":2,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"91b46b45-a870-42dc-9314-be4ceeb9c3f3","createdAt":1784451785949,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-vBPxcm"} +{"type":"turn/start","seq":0,"time":1784451785951,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451785952,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451785955,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451785955,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451787067,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451787068,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451787176,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451787205,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451787206,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451787206,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451787206,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" remember"}}} +{"type":"assistant/chunk","seq":11,"time":1784451787207,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":12,"time":1784451787207,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" fact"}}} +{"type":"assistant/chunk","seq":13,"time":1784451787223,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":14,"time":1784451787267,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":15,"time":1784451787267,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1784451787284,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":17,"time":1784451787285,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":18,"time":1784451787285,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":19,"time":1784451787285,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":20,"time":1784451787312,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" No"}}} +{"type":"assistant/chunk","seq":21,"time":1784451787312,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":22,"time":1784451787313,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" needed"}}} +{"type":"assistant/chunk","seq":23,"time":1784451787337,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":24,"time":1784451787337,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":25,"time":1784451787338,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"OK"}}} +{"type":"assistant/chunk","seq":26,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."}}}} +{"type":"assistant/chunk","seq":27,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} +{"type":"assistant/chunk","seq":28,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3567,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":29,"time":1784451787342,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":30,"time":1784451787343,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a fact and reply with a single word. No tools needed."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3567,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"step/end","seq":31,"time":1784451787343,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":32,"time":1784451787343,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":33,"time":1784451787362,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":34,"time":1784451787362,"data":{"content":[{"type":"text","text":"Do these two delegations, once at a time. First, use the subagent tool (fresh child) exactly once: 'Reply with exactly the word ALPHA and nothing else.' Then, after it returns, use the subagent_fork tool (forked child that inherits this conversation) exactly once: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":35,"time":1784451787362,"data":{"turn":2,"step":1}} +{"type":"assistant/chunk","seq":36,"time":1784451788687,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":37,"time":1784451788687,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":38,"time":1784451788784,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":39,"time":1784451788814,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":40,"time":1784451788815,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":41,"time":1784451788815,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":42,"time":1784451788815,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} +{"type":"assistant/chunk","seq":43,"time":1784451788841,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" two"}}} +{"type":"assistant/chunk","seq":44,"time":1784451788841,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" deleg"}}} +{"type":"assistant/chunk","seq":45,"time":1784451788867,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ations"}}} +{"type":"assistant/chunk","seq":46,"time":1784451788867,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sequentially"}}} +{"type":"assistant/chunk","seq":47,"time":1784451788899,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":\n\n"}}} +{"type":"assistant/chunk","seq":48,"time":1784451788899,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} +{"type":"assistant/chunk","seq":49,"time":1784451788899,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":50,"time":1784451788899,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" First"}}} +{"type":"assistant/chunk","seq":51,"time":1784451788899,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":52,"time":1784451788900,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":53,"time":1784451788900,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":54,"time":1784451788927,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":55,"time":1784451788927,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":56,"time":1784451788927,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":57,"time":1784451788927,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} +{"type":"assistant/chunk","seq":58,"time":1784451788927,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"fresh"}}} +{"type":"assistant/chunk","seq":59,"time":1784451788927,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} +{"type":"assistant/chunk","seq":60,"time":1784451788953,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":")"}}} +{"type":"assistant/chunk","seq":61,"time":1784451788953,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":62,"time":1784451788954,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":63,"time":1784451788954,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prompt"}}} +{"type":"assistant/chunk","seq":64,"time":1784451788977,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} +{"type":"assistant/chunk","seq":65,"time":1784451789011,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" '"}}} +{"type":"assistant/chunk","seq":66,"time":1784451789011,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Reply"}}} +{"type":"assistant/chunk","seq":67,"time":1784451789011,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":68,"time":1784451789011,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":69,"time":1784451789012,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":70,"time":1784451789012,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":71,"time":1784451789040,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" AL"}}} +{"type":"assistant/chunk","seq":72,"time":1784451789040,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} +{"type":"assistant/chunk","seq":73,"time":1784451789040,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} +{"type":"assistant/chunk","seq":74,"time":1784451789040,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":75,"time":1784451789040,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":76,"time":1784451789040,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":77,"time":1784451789060,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".'\n"}}} +{"type":"assistant/chunk","seq":78,"time":1784451789061,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"2"}}} +{"type":"assistant/chunk","seq":79,"time":1784451789061,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":80,"time":1784451789061,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" After"}}} +{"type":"assistant/chunk","seq":81,"time":1784451789097,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":82,"time":1784451789097,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" returns"}}} +{"type":"assistant/chunk","seq":83,"time":1784451789097,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":84,"time":1784451789097,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":85,"time":1784451789097,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":86,"time":1784451789097,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":87,"time":1784451789119,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":88,"time":1784451789119,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} +{"type":"assistant/chunk","seq":89,"time":1784451789119,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ork"}}} +{"type":"assistant/chunk","seq":90,"time":1784451789119,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":91,"time":1784451789119,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} +{"type":"assistant/chunk","seq":92,"time":1784451789119,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"fork"}}} +{"type":"assistant/chunk","seq":93,"time":1784451789144,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ed"}}} +{"type":"assistant/chunk","seq":94,"time":1784451789144,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} +{"type":"assistant/chunk","seq":95,"time":1784451789145,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":96,"time":1784451789145,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" inher"}}} +{"type":"assistant/chunk","seq":97,"time":1784451789145,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"its"}}} +{"type":"assistant/chunk","seq":98,"time":1784451789145,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} +{"type":"assistant/chunk","seq":99,"time":1784451789173,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} +{"type":"assistant/chunk","seq":100,"time":1784451789174,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":")"}}} +{"type":"assistant/chunk","seq":101,"time":1784451789174,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":102,"time":1784451789174,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":103,"time":1784451789174,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prompt"}}} +{"type":"assistant/chunk","seq":104,"time":1784451789174,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} +{"type":"assistant/chunk","seq":105,"time":1784451789202,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" '"}}} +{"type":"assistant/chunk","seq":106,"time":1784451789202,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"What"}}} +{"type":"assistant/chunk","seq":107,"time":1784451789202,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" is"}}} +{"type":"assistant/chunk","seq":108,"time":1784451789202,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":109,"time":1784451789202,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} +{"type":"assistant/chunk","seq":110,"time":1784451789203,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} +{"type":"assistant/chunk","seq":111,"time":1784451789229,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} +{"type":"assistant/chunk","seq":112,"time":1784451789230,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} +{"type":"assistant/chunk","seq":113,"time":1784451789230,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" mentioned"}}} +{"type":"assistant/chunk","seq":114,"time":1784451789230,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" earlier"}}} +{"type":"assistant/chunk","seq":115,"time":1784451789230,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" in"}}} +{"type":"assistant/chunk","seq":116,"time":1784451789231,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} +{"type":"assistant/chunk","seq":117,"time":1784451789258,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} +{"type":"assistant/chunk","seq":118,"time":1784451789258,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"?"}}} +{"type":"assistant/chunk","seq":119,"time":1784451789258,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Reply"}}} +{"type":"assistant/chunk","seq":120,"time":1784451789258,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":121,"time":1784451789258,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":122,"time":1784451789258,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":123,"time":1784451789286,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" one"}}} +{"type":"assistant/chunk","seq":124,"time":1784451789286,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":125,"time":1784451789286,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":126,"time":1784451789286,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":127,"time":1784451789286,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":128,"time":1784451789312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".'\n"}}} +{"type":"assistant/chunk","seq":129,"time":1784451789312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"3"}}} +{"type":"assistant/chunk","seq":130,"time":1784451789312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":131,"time":1784451789312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" After"}}} +{"type":"assistant/chunk","seq":132,"time":1784451789312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" both"}}} +{"type":"assistant/chunk","seq":133,"time":1784451789313,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" return"}}} +{"type":"assistant/chunk","seq":134,"time":1784451789348,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":135,"time":1784451789348,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":136,"time":1784451789348,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":137,"time":1784451789348,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" '"}}} +{"type":"assistant/chunk","seq":138,"time":1784451789348,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} +{"type":"assistant/chunk","seq":139,"time":1784451789348,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} +{"type":"assistant/chunk","seq":140,"time":1784451789364,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":141,"time":1784451789365,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":142,"time":1784451789405,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'.\n\n"}}} +{"type":"assistant/chunk","seq":143,"time":1784451789405,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Let"}}} +{"type":"assistant/chunk","seq":144,"time":1784451789406,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":145,"time":1784451789406,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" start"}}} +{"type":"assistant/chunk","seq":146,"time":1784451789406,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":147,"time":1784451789406,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" step"}}} +{"type":"assistant/chunk","seq":148,"time":1784451789425,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" "}}} +{"type":"assistant/chunk","seq":149,"time":1784451789425,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} +{"type":"assistant/chunk","seq":150,"time":1784451789425,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":151,"time":1784451789509,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":152,"time":1784451789509,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":153,"time":1784451789537,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":154,"time":1784451789537,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":155,"time":1784451789537,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":156,"time":1784451789537,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":157,"time":1784451789537,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":158,"time":1784451789557,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":159,"time":1784451789557,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":160,"time":1784451789586,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" AL"}}} +{"type":"assistant/chunk","seq":161,"time":1784451789620,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"P"}}} +{"type":"assistant/chunk","seq":162,"time":1784451789620,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"HA"}}} +{"type":"assistant/chunk","seq":163,"time":1784451789620,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" only"}}} +{"type":"assistant/chunk","seq":164,"time":1784451789620,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":165,"time":1784451789641,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":166,"time":1784451789641,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":167,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"prom"}}} +{"type":"assistant/chunk","seq":168,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"pt"}}} +{"type":"assistant/chunk","seq":169,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":170,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":171,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":172,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":173,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":174,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":175,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":176,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":177,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" AL"}}} +{"type":"assistant/chunk","seq":178,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"P"}}} +{"type":"assistant/chunk","seq":179,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"HA"}}} +{"type":"assistant/chunk","seq":180,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":181,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":182,"time":1784451789761,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":183,"time":1784451789766,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":184,"time":1784451789766,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":185,"time":1784451789766,"data":{"turn":2,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":186,"time":1784451789828,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to do two delegations sequentially:\n\n1. First, use the subagent tool (fresh child) with the prompt: 'Reply with exactly the word ALPHA and nothing else.'\n2. After it returns, use the subagent_fork tool (forked child that inherits this conversation) with the prompt: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.'\n3. After both return, reply with 'PARENT_DONE'.\n\nLet me start with step 1."}}}} +{"type":"assistant/chunk","seq":187,"time":1784451789829,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":188,"time":1784451789829,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":229,"outputTokens":189,"cacheReadTokens":3456,"reasoningTokens":114}}}} +{"type":"assistant/chunk","seq":189,"time":1784451789829,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":190,"time":1784451789829,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to do two delegations sequentially:\n\n1. First, use the subagent tool (fresh child) with the prompt: 'Reply with exactly the word ALPHA and nothing else.'\n2. After it returns, use the subagent_fork tool (forked child that inherits this conversation) with the prompt: 'What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.'\n3. After both return, reply with 'PARENT_DONE'.\n\nLet me start with step 1."},{"type":"tool-call","id":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":229,"outputTokens":189,"cacheReadTokens":3456,"reasoningTokens":114}},"sourceEventSeqs":[36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"} +{"type":"tool/call","seq":191,"time":1784451789829,"data":{"turn":2,"step":1,"callId":"call_00_fOmtdGKlmFUAPjPULOUC7301","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} +{"type":"tool/result","seq":192,"time":1784451796518,"data":{"turn":2,"step":1,"callId":"call_00_fOmtdGKlmFUAPjPULOUC7301","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[191],"surfaceOp":"append"} +{"type":"step/end","seq":193,"time":1784451796519,"data":{"turn":2,"step":1}} +{"type":"step/start","seq":194,"time":1784451796519,"data":{"turn":2,"step":2}} +{"type":"assistant/chunk","seq":195,"time":1784451797797,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":196,"time":1784451797797,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":197,"time":1784451797899,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" first"}}} +{"type":"assistant/chunk","seq":198,"time":1784451797911,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":199,"time":1784451797911,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":200,"time":1784451797911,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":201,"time":1784451797911,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":202,"time":1784451797911,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":203,"time":1784451797947,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} +{"type":"assistant/chunk","seq":204,"time":1784451797947,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} +{"type":"assistant/chunk","seq":205,"time":1784451797947,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":206,"time":1784451797947,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":207,"time":1784451797947,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":208,"time":1784451797947,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":209,"time":1784451797972,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":210,"time":1784451797972,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":211,"time":1784451797997,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":212,"time":1784451798035,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":213,"time":1784451798035,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} +{"type":"assistant/chunk","seq":214,"time":1784451798036,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ork"}}} +{"type":"assistant/chunk","seq":215,"time":1784451798036,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":216,"time":1784451798058,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" ask"}}} +{"type":"assistant/chunk","seq":217,"time":1784451798058,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" about"}}} +{"type":"assistant/chunk","seq":218,"time":1784451798090,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":219,"time":1784451798090,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" project"}}} +{"type":"assistant/chunk","seq":220,"time":1784451798091,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" cod"}}} +{"type":"assistant/chunk","seq":221,"time":1784451798091,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ew"}}} +{"type":"assistant/chunk","seq":222,"time":1784451798091,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ord"}}} +{"type":"assistant/chunk","seq":223,"time":1784451798091,"data":{"turn":2,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":224,"time":1784451798192,"data":{"turn":2,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":225,"time":1784451798192,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":226,"time":1784451798225,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":227,"time":1784451798225,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":228,"time":1784451798225,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":229,"time":1784451798225,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":230,"time":1784451798257,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":231,"time":1784451798257,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":232,"time":1784451798257,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"Recall"}}} +{"type":"assistant/chunk","seq":233,"time":1784451798290,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" project"}}} +{"type":"assistant/chunk","seq":234,"time":1784451798290,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" cod"}}} +{"type":"assistant/chunk","seq":235,"time":1784451798290,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"ew"}}} +{"type":"assistant/chunk","seq":236,"time":1784451798290,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"ord"}}} +{"type":"assistant/chunk","seq":237,"time":1784451798290,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":238,"time":1784451798330,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":239,"time":1784451798330,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":240,"time":1784451798330,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"prom"}}} +{"type":"assistant/chunk","seq":241,"time":1784451798330,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"pt"}}} +{"type":"assistant/chunk","seq":242,"time":1784451798330,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":243,"time":1784451798331,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":244,"time":1784451798364,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":245,"time":1784451798364,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"What"}}} +{"type":"assistant/chunk","seq":246,"time":1784451798364,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" is"}}} +{"type":"assistant/chunk","seq":247,"time":1784451798364,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":248,"time":1784451798364,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" project"}}} +{"type":"assistant/chunk","seq":249,"time":1784451798378,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" cod"}}} +{"type":"assistant/chunk","seq":250,"time":1784451798378,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"ew"}}} +{"type":"assistant/chunk","seq":251,"time":1784451798378,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"ord"}}} +{"type":"assistant/chunk","seq":252,"time":1784451798378,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" mentioned"}}} +{"type":"assistant/chunk","seq":253,"time":1784451798378,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" earlier"}}} +{"type":"assistant/chunk","seq":254,"time":1784451798409,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" in"}}} +{"type":"assistant/chunk","seq":255,"time":1784451798410,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" this"}}} +{"type":"assistant/chunk","seq":256,"time":1784451798410,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" conversation"}}} +{"type":"assistant/chunk","seq":257,"time":1784451798410,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"?"}}} +{"type":"assistant/chunk","seq":258,"time":1784451798410,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" Reply"}}} +{"type":"assistant/chunk","seq":259,"time":1784451798410,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":260,"time":1784451798426,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":261,"time":1784451798426,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" that"}}} +{"type":"assistant/chunk","seq":262,"time":1784451798426,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" one"}}} +{"type":"assistant/chunk","seq":263,"time":1784451798426,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":264,"time":1784451798426,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":265,"time":1784451798426,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":266,"time":1784451798454,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":267,"time":1784451798454,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":268,"time":1784451798454,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":269,"time":1784451798476,"data":{"turn":2,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":270,"time":1784451798518,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use subagent_fork to ask about the project codeword."}}}} +{"type":"assistant/chunk","seq":271,"time":1784451798518,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":272,"time":1784451798518,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":49,"outputTokens":116,"cacheReadTokens":3840,"reasoningTokens":28}}}} +{"type":"assistant/chunk","seq":273,"time":1784451798518,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":274,"time":1784451798518,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use subagent_fork to ask about the project codeword."},{"type":"tool-call","id":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":49,"outputTokens":116,"cacheReadTokens":3840,"reasoningTokens":28}},"sourceEventSeqs":[195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273],"surfaceOp":"append"} +{"type":"tool/call","seq":275,"time":1784451798518,"data":{"turn":2,"step":2,"callId":"call_00_4obRCMnU95bJeDWflv6h9606","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} +{"type":"tool/result","seq":276,"time":1784451800338,"data":{"turn":2,"step":2,"callId":"call_00_4obRCMnU95bJeDWflv6h9606","content":[{"type":"text","text":"SAFFRON"}],"isError":false},"sourceEventSeqs":[275],"surfaceOp":"append"} +{"type":"step/end","seq":277,"time":1784451800339,"data":{"turn":2,"step":2}} +{"type":"step/start","seq":278,"time":1784451800340,"data":{"turn":2,"step":3}} +{"type":"assistant/chunk","seq":279,"time":1784451801612,"data":{"turn":2,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":280,"time":1784451801612,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"Both"}}} +{"type":"assistant/chunk","seq":281,"time":1784451801773,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":282,"time":1784451801804,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"agents"}}} +{"type":"assistant/chunk","seq":283,"time":1784451801805,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":284,"time":1784451801830,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":":\n"}}} +{"type":"assistant/chunk","seq":285,"time":1784451801830,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} +{"type":"assistant/chunk","seq":286,"time":1784451801830,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":287,"time":1784451801830,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" First"}}} +{"type":"assistant/chunk","seq":288,"time":1784451801857,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":289,"time":1784451801857,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":290,"time":1784451801857,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} +{"type":"assistant/chunk","seq":291,"time":1784451801888,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"fresh"}}} +{"type":"assistant/chunk","seq":292,"time":1784451801889,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"):"}}} +{"type":"assistant/chunk","seq":293,"time":1784451801889,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" AL"}}} +{"type":"assistant/chunk","seq":294,"time":1784451801919,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} +{"type":"assistant/chunk","seq":295,"time":1784451801919,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} +{"type":"assistant/chunk","seq":296,"time":1784451801919,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\n"}}} +{"type":"assistant/chunk","seq":297,"time":1784451801919,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"2"}}} +{"type":"assistant/chunk","seq":298,"time":1784451801919,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":299,"time":1784451801919,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" Sub"}}} +{"type":"assistant/chunk","seq":300,"time":1784451801939,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":301,"time":1784451801939,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"_f"}}} +{"type":"assistant/chunk","seq":302,"time":1784451801967,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ork"}}} +{"type":"assistant/chunk","seq":303,"time":1784451801967,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} +{"type":"assistant/chunk","seq":304,"time":1784451801967,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"inher"}}} +{"type":"assistant/chunk","seq":305,"time":1784451801993,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"iting"}}} +{"type":"assistant/chunk","seq":306,"time":1784451802026,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" conversation"}}} +{"type":"assistant/chunk","seq":307,"time":1784451802027,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"):"}}} +{"type":"assistant/chunk","seq":308,"time":1784451802027,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" SA"}}} +{"type":"assistant/chunk","seq":309,"time":1784451802027,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"FF"}}} +{"type":"assistant/chunk","seq":310,"time":1784451802027,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"RON"}}} +{"type":"assistant/chunk","seq":311,"time":1784451802055,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\n\n"}}} +{"type":"assistant/chunk","seq":312,"time":1784451802055,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"Now"}}} +{"type":"assistant/chunk","seq":313,"time":1784451802055,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":314,"time":1784451802055,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":315,"time":1784451802086,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":316,"time":1784451802087,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" PAR"}}} +{"type":"assistant/chunk","seq":317,"time":1784451802087,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} +{"type":"assistant/chunk","seq":318,"time":1784451802087,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":319,"time":1784451802087,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":320,"time":1784451802087,"data":{"turn":2,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":321,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":322,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} +{"type":"assistant/chunk","seq":323,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} +{"type":"assistant/chunk","seq":324,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} +{"type":"assistant/chunk","seq":325,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":326,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Both subagents returned:\n1. First subagent (fresh): ALPHA\n2. Subagent_fork (inheriting conversation): SAFFRON\n\nNow I reply with PARENT_DONE."}}}} +{"type":"assistant/chunk","seq":327,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} +{"type":"assistant/chunk","seq":328,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":52,"outputTokens":46,"cacheReadTokens":3968,"reasoningTokens":41}}}} +{"type":"assistant/chunk","seq":329,"time":1784451802126,"data":{"turn":2,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":330,"time":1784451802126,"data":{"turn":2,"step":3,"content":[{"type":"reasoning","text":"Both subagents returned:\n1. First subagent (fresh): ALPHA\n2. Subagent_fork (inheriting conversation): SAFFRON\n\nNow I reply with PARENT_DONE."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":52,"outputTokens":46,"cacheReadTokens":3968,"reasoningTokens":41}},"sourceEventSeqs":[279,280,281,282,283,284,285,286,287,288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329],"surfaceOp":"append"} +{"type":"step/end","seq":331,"time":1784451802126,"data":{"turn":2,"step":3}} +{"type":"turn/end","seq":332,"time":1784451802126,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl index e5cc8bfa90..95a9090889 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl @@ -7,36 +7,35 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" remember"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cod"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ew"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ord"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" fact"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" just"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"OK"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" No"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tools"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" needed"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"OK"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Let"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" do"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" these"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" two"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" deleg"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ations"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" one"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" at"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" time"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" requested"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"First"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sequentially"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":\n\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"1"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" First"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'ll"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" use"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} @@ -46,30 +45,29 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"fresh"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" child"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":")"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prompt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" '"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" AL"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"P"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"HA"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_YvHr2bGomk5HhpgDTvE81896","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Reply ALPHA only","prompt":"Reply with exactly the word ALPHA and nothing else."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_YvHr2bGomk5HhpgDTvE81896","status":"completed","content":[{"type":"content","content":{"type":"text","text":"ALPHA"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"P"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"HA"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nothing"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" else"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".'\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"2"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" After"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returns"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" use"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} @@ -87,6 +85,77 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" this"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" conversation"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":")"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prompt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" '"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"What"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" is"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" project"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cod"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ew"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ord"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" mentioned"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" earlier"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" in"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" this"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" conversation"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"?"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" one"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nothing"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" else"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".'\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"3"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" After"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" both"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" return"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" '"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PAR"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENT"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_D"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'.\n\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Let"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" start"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" step"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" "}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"1"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_fOmtdGKlmFUAPjPULOUC7301","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Reply ALPHA only","prompt":"Reply with exactly the word ALPHA and nothing else."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_fOmtdGKlmFUAPjPULOUC7301","status":"completed","content":[{"type":"content","content":{"type":"text","text":"ALPHA"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"P"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"HA"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" use"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_f"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ork"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ask"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" about"}}}} @@ -96,8 +165,8 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ew"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ord"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_JSr5rhREq23wSmwSkCP77184","title":"subagent_fork","kind":"other","status":"in_progress","rawInput":{"description":"Recall project codeword","prompt":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_JSr5rhREq23wSmwSkCP77184","status":"completed","content":[{"type":"content","content":{"type":"text","text":"SAFFRON"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_4obRCMnU95bJeDWflv6h9606","title":"subagent_fork","kind":"other","status":"in_progress","rawInput":{"description":"Recall project codeword","prompt":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_4obRCMnU95bJeDWflv6h9606","status":"completed","content":[{"type":"content","content":{"type":"text","text":"SAFFRON"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Both"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agents"}}}} @@ -106,61 +175,38 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"1"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" First"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ("}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"fresh"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" child"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"):"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" AL"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"P"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"HA"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\n"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"2"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Second"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Sub"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_f"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ork"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ("}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"fork"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ed"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" child"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"):"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"SA"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"FF"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"RON"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" -"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" correctly"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" inherited"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"inher"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"iting"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" conversation"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" context"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" where"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" was"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" remember"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" cod"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ew"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ord"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"SA"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"):"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" SA"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"FF"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"RON"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\".\n\n"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\n\n"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Now"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PAR"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" PAR"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENT"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instructed"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"PAR"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ENT"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl index 86c481c5ff..7f7fe92b80 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl @@ -1,36 +1,36 @@ -{"type":"session","version":0,"id":"553f8e92-aac1-4df3-8657-eacbb58f9581","createdAt":1783352127669,"cwd":"/tmp/acp-snap-cwd-28z5Of","parentSession":"14dda109-5728-45ba-a002-7db9543fe50e"} -{"type":"turn/start","seq":0,"time":1783352127670,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352127670,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352127671,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352127671,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352128125,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352128125,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352128240,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352128280,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352128280,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352128280,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352128280,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":11,"time":1783352128280,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":12,"time":1783352128281,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":13,"time":1783352128300,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":14,"time":1783352128300,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":15,"time":1783352128300,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":16,"time":1783352128300,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":17,"time":1783352128300,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":18,"time":1783352128301,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":19,"time":1783352128332,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":20,"time":1783352128332,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":21,"time":1783352128332,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} -{"type":"assistant/chunk","seq":22,"time":1783352128332,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} -{"type":"assistant/chunk","seq":23,"time":1783352128332,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":24,"time":1783352128364,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":25,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"AL"}}} -{"type":"assistant/chunk","seq":26,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"P"}}} -{"type":"assistant/chunk","seq":27,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"HA"}}} -{"type":"assistant/chunk","seq":28,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."}}}} -{"type":"assistant/chunk","seq":29,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} -{"type":"assistant/chunk","seq":30,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}}} -{"type":"assistant/chunk","seq":31,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783352128365,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} -{"type":"step/end","seq":33,"time":1783352128365,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":34,"time":1783352128366,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"f425022f-47e5-46e7-84f6-c364c7e969d8","createdAt":1784451769872,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-ogFsTm","parentSession":"23127c8b-3c39-4dca-8cb6-8111f50bd23f","delegationDepth":1} +{"type":"turn/start","seq":0,"time":1784451769874,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451769874,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451769874,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451769875,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451770880,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451770880,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451770966,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451770999,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451770999,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451770999,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451770999,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1784451770999,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1784451770999,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1784451771027,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":14,"time":1784451771027,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":15,"time":1784451771027,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":16,"time":1784451771027,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":17,"time":1784451771027,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} +{"type":"assistant/chunk","seq":18,"time":1784451771027,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} +{"type":"assistant/chunk","seq":19,"time":1784451771060,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":20,"time":1784451771060,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":21,"time":1784451771060,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":22,"time":1784451771060,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":23,"time":1784451771060,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":24,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":25,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"AL"}}} +{"type":"assistant/chunk","seq":26,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"P"}}} +{"type":"assistant/chunk","seq":27,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"HA"}}} +{"type":"assistant/chunk","seq":28,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."}}}} +{"type":"assistant/chunk","seq":29,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} +{"type":"assistant/chunk","seq":30,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3284,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":31,"time":1784451771087,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":32,"time":1784451771087,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3284,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1784451771087,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":34,"time":1784451771087,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl index 483e687a14..4ece8fa0de 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl @@ -1,34 +1,34 @@ -{"type":"session","version":0,"id":"5f49e80c-16fc-42c7-a617-0b6bd0680aa3","createdAt":1783352129662,"cwd":"/tmp/acp-snap-cwd-28z5Of","parentSession":"14dda109-5728-45ba-a002-7db9543fe50e"} -{"type":"turn/start","seq":0,"time":1783352129662,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352129662,"data":{"content":[{"type":"text","text":"Reply with exactly the word BETA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352129663,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352129663,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352130236,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352130236,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352130375,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352130413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352130413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352130413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352130413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":11,"time":1783352130413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":12,"time":1783352130413,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":13,"time":1783352130448,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":14,"time":1783352130448,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":15,"time":1783352130448,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":16,"time":1783352130448,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"B"}}} -{"type":"assistant/chunk","seq":17,"time":1783352130448,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ETA"}}} -{"type":"assistant/chunk","seq":18,"time":1783352130448,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":19,"time":1783352130484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":20,"time":1783352130484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} -{"type":"assistant/chunk","seq":21,"time":1783352130484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} -{"type":"assistant/chunk","seq":22,"time":1783352130484,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":23,"time":1783352130484,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":24,"time":1783352130484,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"B"}}} -{"type":"assistant/chunk","seq":25,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ETA"}}} -{"type":"assistant/chunk","seq":26,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."}}}} -{"type":"assistant/chunk","seq":27,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BETA"}}}} -{"type":"assistant/chunk","seq":28,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}}} -{"type":"assistant/chunk","seq":29,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":30,"time":1783352130528,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} -{"type":"step/end","seq":31,"time":1783352130528,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":32,"time":1783352130528,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"6f1571df-557f-45ff-b434-e13ee06d2b9f","createdAt":1784451773103,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-ogFsTm","parentSession":"23127c8b-3c39-4dca-8cb6-8111f50bd23f","delegationDepth":1} +{"type":"turn/start","seq":0,"time":1784451773104,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451773104,"data":{"content":[{"type":"text","text":"Reply with exactly the word BETA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451773105,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451773105,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451775865,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451775865,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451775999,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451776031,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451776031,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451776031,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451776031,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1784451776031,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1784451776031,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1784451776052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":14,"time":1784451776052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":15,"time":1784451776052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":16,"time":1784451776052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"B"}}} +{"type":"assistant/chunk","seq":17,"time":1784451776052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ETA"}}} +{"type":"assistant/chunk","seq":18,"time":1784451776052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":19,"time":1784451776078,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":20,"time":1784451776078,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":21,"time":1784451776078,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":22,"time":1784451776078,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":23,"time":1784451776078,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":24,"time":1784451776078,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"B"}}} +{"type":"assistant/chunk","seq":25,"time":1784451776102,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ETA"}}} +{"type":"assistant/chunk","seq":26,"time":1784451776108,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."}}}} +{"type":"assistant/chunk","seq":27,"time":1784451776108,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BETA"}}}} +{"type":"assistant/chunk","seq":28,"time":1784451776108,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":83,"outputTokens":21,"cacheReadTokens":3200,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":29,"time":1784451776108,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":30,"time":1784451776109,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":83,"outputTokens":21,"cacheReadTokens":3200,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"step/end","seq":31,"time":1784451776109,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":32,"time":1784451776109,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl index a8093fba04..9649a197bd 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl @@ -1,208 +1,194 @@ -{"type":"session","version":0,"id":"14dda109-5728-45ba-a002-7db9543fe50e","createdAt":1783352126247,"cwd":"/tmp/acp-snap-cwd-28z5Of"} -{"type":"turn/start","seq":0,"time":1783352126251,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352126251,"data":{"content":[{"type":"text","text":"Use the subagent tool TWICE, once at a time, to delegate two subtasks to child agents. First subtask: 'Reply with exactly the word ALPHA and nothing else.' Second subtask (after the first returns): 'Reply with exactly the word BETA and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352126252,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352126253,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352126729,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352126729,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352126848,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352126877,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352126878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352126878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352126878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} -{"type":"assistant/chunk","seq":11,"time":1783352126878,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":12,"time":1783352126907,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":13,"time":1783352126907,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":14,"time":1783352126908,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":15,"time":1783352126908,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" twice"}}} -{"type":"assistant/chunk","seq":16,"time":1783352126908,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":17,"time":1783352126909,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sequentially"}}} -{"type":"assistant/chunk","seq":18,"time":1783352126933,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} -{"type":"assistant/chunk","seq":19,"time":1783352126963,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"one"}}} -{"type":"assistant/chunk","seq":20,"time":1783352126992,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" at"}}} -{"type":"assistant/chunk","seq":21,"time":1783352126992,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} -{"type":"assistant/chunk","seq":22,"time":1783352126992,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" time"}}} -{"type":"assistant/chunk","seq":23,"time":1783352126993,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":")."}}} -{"type":"assistant/chunk","seq":24,"time":1783352126993,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" First"}}} -{"type":"assistant/chunk","seq":25,"time":1783352127023,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":26,"time":1783352127023,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":27,"time":1783352127023,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":28,"time":1783352127052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":29,"time":1783352127053,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":30,"time":1783352127080,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":31,"time":1783352127080,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":32,"time":1783352127080,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":33,"time":1783352127081,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":34,"time":1783352127081,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\","}}} -{"type":"assistant/chunk","seq":35,"time":1783352127081,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" second"}}} -{"type":"assistant/chunk","seq":36,"time":1783352127110,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":37,"time":1783352127139,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":38,"time":1783352127139,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"B"}}} -{"type":"assistant/chunk","seq":39,"time":1783352127139,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ETA"}}} -{"type":"assistant/chunk","seq":40,"time":1783352127139,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":41,"time":1783352127172,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" After"}}} -{"type":"assistant/chunk","seq":42,"time":1783352127197,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" both"}}} -{"type":"assistant/chunk","seq":43,"time":1783352127198,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" return"}}} -{"type":"assistant/chunk","seq":44,"time":1783352127198,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":45,"time":1783352127227,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":46,"time":1783352127227,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":47,"time":1783352127228,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":48,"time":1783352127257,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":49,"time":1783352127257,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} -{"type":"assistant/chunk","seq":50,"time":1783352127257,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} -{"type":"assistant/chunk","seq":51,"time":1783352127257,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":52,"time":1783352127257,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":53,"time":1783352127258,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":54,"time":1783352127343,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":55,"time":1783352127344,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":56,"time":1783352127374,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":57,"time":1783352127374,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":58,"time":1783352127374,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":59,"time":1783352127374,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":60,"time":1783352127401,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":61,"time":1783352127401,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":62,"time":1783352127402,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"Return"}}} -{"type":"assistant/chunk","seq":63,"time":1783352127430,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" AL"}}} -{"type":"assistant/chunk","seq":64,"time":1783352127431,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"P"}}} -{"type":"assistant/chunk","seq":65,"time":1783352127431,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"HA"}}} -{"type":"assistant/chunk","seq":66,"time":1783352127431,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" only"}}} -{"type":"assistant/chunk","seq":67,"time":1783352127460,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":68,"time":1783352127486,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":69,"time":1783352127487,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":70,"time":1783352127487,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"prom"}}} -{"type":"assistant/chunk","seq":71,"time":1783352127487,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"pt"}}} -{"type":"assistant/chunk","seq":72,"time":1783352127487,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":73,"time":1783352127515,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":74,"time":1783352127516,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":75,"time":1783352127516,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"Reply"}}} -{"type":"assistant/chunk","seq":76,"time":1783352127516,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":77,"time":1783352127545,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" exactly"}}} -{"type":"assistant/chunk","seq":78,"time":1783352127545,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":79,"time":1783352127546,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" word"}}} -{"type":"assistant/chunk","seq":80,"time":1783352127546,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" AL"}}} -{"type":"assistant/chunk","seq":81,"time":1783352127546,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"P"}}} -{"type":"assistant/chunk","seq":82,"time":1783352127546,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"HA"}}} -{"type":"assistant/chunk","seq":83,"time":1783352127577,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":84,"time":1783352127577,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" nothing"}}} -{"type":"assistant/chunk","seq":85,"time":1783352127577,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":" else"}}} -{"type":"assistant/chunk","seq":86,"time":1783352127578,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":87,"time":1783352127578,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":88,"time":1783352127605,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":89,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."}}}} -{"type":"assistant/chunk","seq":90,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} -{"type":"assistant/chunk","seq":91,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}}}} -{"type":"assistant/chunk","seq":92,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":93,"time":1783352127668,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."},{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],"surfaceOp":"append"} -{"type":"tool/call","seq":94,"time":1783352127668,"data":{"turn":1,"step":1,"callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} -{"type":"tool/result","seq":95,"time":1783352128371,"data":{"turn":1,"step":1,"callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[94],"surfaceOp":"append"} -{"type":"step/end","seq":96,"time":1783352128371,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":97,"time":1783352128372,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":98,"time":1783352129034,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":99,"time":1783352129034,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"First"}}} -{"type":"assistant/chunk","seq":100,"time":1783352129152,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":101,"time":1783352129166,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":102,"time":1783352129167,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":103,"time":1783352129167,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":104,"time":1783352129196,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":105,"time":1783352129196,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":106,"time":1783352129196,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":107,"time":1783352129197,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":108,"time":1783352129197,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} -{"type":"assistant/chunk","seq":109,"time":1783352129197,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":110,"time":1783352129224,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"'ll"}}} -{"type":"assistant/chunk","seq":111,"time":1783352129254,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" call"}}} -{"type":"assistant/chunk","seq":112,"time":1783352129254,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":113,"time":1783352129254,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" second"}}} -{"type":"assistant/chunk","seq":114,"time":1783352129254,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":115,"time":1783352129254,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":116,"time":1783352129255,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":117,"time":1783352129282,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" return"}}} -{"type":"assistant/chunk","seq":118,"time":1783352129283,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":119,"time":1783352129283,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"B"}}} -{"type":"assistant/chunk","seq":120,"time":1783352129283,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ETA"}}} -{"type":"assistant/chunk","seq":121,"time":1783352129283,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":122,"time":1783352129371,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":123,"time":1783352129371,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":124,"time":1783352129399,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":125,"time":1783352129400,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":126,"time":1783352129400,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":127,"time":1783352129400,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":128,"time":1783352129400,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":129,"time":1783352129428,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":130,"time":1783352129428,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"Return"}}} -{"type":"assistant/chunk","seq":131,"time":1783352129428,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" B"}}} -{"type":"assistant/chunk","seq":132,"time":1783352129428,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"ETA"}}} -{"type":"assistant/chunk","seq":133,"time":1783352129457,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" only"}}} -{"type":"assistant/chunk","seq":134,"time":1783352129457,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":135,"time":1783352129485,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":136,"time":1783352129485,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":137,"time":1783352129485,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"prom"}}} -{"type":"assistant/chunk","seq":138,"time":1783352129485,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"pt"}}} -{"type":"assistant/chunk","seq":139,"time":1783352129515,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":140,"time":1783352129516,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":141,"time":1783352129516,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":142,"time":1783352129516,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"Reply"}}} -{"type":"assistant/chunk","seq":143,"time":1783352129543,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":144,"time":1783352129543,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" exactly"}}} -{"type":"assistant/chunk","seq":145,"time":1783352129543,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":146,"time":1783352129543,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" word"}}} -{"type":"assistant/chunk","seq":147,"time":1783352129543,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" B"}}} -{"type":"assistant/chunk","seq":148,"time":1783352129543,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"ETA"}}} -{"type":"assistant/chunk","seq":149,"time":1783352129574,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":150,"time":1783352129574,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" nothing"}}} -{"type":"assistant/chunk","seq":151,"time":1783352129574,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":" else"}}} -{"type":"assistant/chunk","seq":152,"time":1783352129574,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":153,"time":1783352129574,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":154,"time":1783352129603,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":155,"time":1783352129660,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."}}}} -{"type":"assistant/chunk","seq":156,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}}}} -{"type":"assistant/chunk","seq":157,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}}}} -{"type":"assistant/chunk","seq":158,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":159,"time":1783352129661,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."},{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}},"sourceEventSeqs":[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} -{"type":"tool/call","seq":160,"time":1783352129661,"data":{"turn":1,"step":2,"callId":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}} -{"type":"tool/result","seq":161,"time":1783352130531,"data":{"turn":1,"step":2,"callId":"call_00_FudNKuJ0fchSptGy3Scw1411","content":[{"type":"text","text":"BETA"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"} -{"type":"step/end","seq":162,"time":1783352130531,"data":{"turn":1,"step":2}} -{"type":"step/start","seq":163,"time":1783352130532,"data":{"turn":1,"step":3}} -{"type":"assistant/chunk","seq":164,"time":1783352130930,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":165,"time":1783352130930,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"Both"}}} -{"type":"assistant/chunk","seq":166,"time":1783352131045,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":167,"time":1783352131073,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"agents"}}} -{"type":"assistant/chunk","seq":168,"time":1783352131073,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" have"}}} -{"type":"assistant/chunk","seq":169,"time":1783352131073,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":170,"time":1783352131073,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":171,"time":1783352131096,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" first"}}} -{"type":"assistant/chunk","seq":172,"time":1783352131097,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":173,"time":1783352131128,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":174,"time":1783352131128,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} -{"type":"assistant/chunk","seq":175,"time":1783352131129,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} -{"type":"assistant/chunk","seq":176,"time":1783352131129,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} -{"type":"assistant/chunk","seq":177,"time":1783352131129,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\","}}} -{"type":"assistant/chunk","seq":178,"time":1783352131129,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" second"}}} -{"type":"assistant/chunk","seq":179,"time":1783352131157,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":180,"time":1783352131158,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":181,"time":1783352131158,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"B"}}} -{"type":"assistant/chunk","seq":182,"time":1783352131158,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ETA"}}} -{"type":"assistant/chunk","seq":183,"time":1783352131158,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":184,"time":1783352131158,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} -{"type":"assistant/chunk","seq":185,"time":1783352131185,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":186,"time":1783352131185,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" should"}}} -{"type":"assistant/chunk","seq":187,"time":1783352131186,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":188,"time":1783352131186,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":189,"time":1783352131186,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":190,"time":1783352131213,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} -{"type":"assistant/chunk","seq":191,"time":1783352131213,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} -{"type":"assistant/chunk","seq":192,"time":1783352131213,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":193,"time":1783352131214,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":194,"time":1783352131214,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":195,"time":1783352131241,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":196,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} -{"type":"assistant/chunk","seq":197,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} -{"type":"assistant/chunk","seq":198,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} -{"type":"assistant/chunk","seq":199,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":200,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."}}}} -{"type":"assistant/chunk","seq":201,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} -{"type":"assistant/chunk","seq":202,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}}}} -{"type":"assistant/chunk","seq":203,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":204,"time":1783352131243,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203],"surfaceOp":"append"} -{"type":"step/end","seq":205,"time":1783352131243,"data":{"turn":1,"step":3}} -{"type":"turn/end","seq":206,"time":1783352131243,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"23127c8b-3c39-4dca-8cb6-8111f50bd23f","createdAt":1784451767994,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-ogFsTm"} +{"type":"turn/start","seq":0,"time":1784451767996,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451767996,"data":{"content":[{"type":"text","text":"Use the subagent tool TWICE, once at a time, to delegate two subtasks to child agents. First subtask: 'Reply with exactly the word ALPHA and nothing else.' Second subtask (after the first returns): 'Reply with exactly the word BETA and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451768000,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451768000,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451769159,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451769159,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451769269,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451769299,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451769300,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451769301,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451769301,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":11,"time":1784451769301,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":12,"time":1784451769327,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":13,"time":1784451769328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":14,"time":1784451769328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":15,"time":1784451769328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" twice"}}} +{"type":"assistant/chunk","seq":16,"time":1784451769328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":17,"time":1784451769328,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sequentially"}}} +{"type":"assistant/chunk","seq":18,"time":1784451769350,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} +{"type":"assistant/chunk","seq":19,"time":1784451769381,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"one"}}} +{"type":"assistant/chunk","seq":20,"time":1784451769408,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" at"}}} +{"type":"assistant/chunk","seq":21,"time":1784451769408,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":22,"time":1784451769409,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" time"}}} +{"type":"assistant/chunk","seq":23,"time":1784451769409,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"),"}}} +{"type":"assistant/chunk","seq":24,"time":1784451769409,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":25,"time":1784451769464,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":26,"time":1784451769464,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" prompts"}}} +{"type":"assistant/chunk","seq":27,"time":1784451769469,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":28,"time":1784451769469,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":29,"time":1784451769469,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":30,"time":1784451769469,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" start"}}} +{"type":"assistant/chunk","seq":31,"time":1784451769505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":32,"time":1784451769505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":33,"time":1784451769505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" first"}}} +{"type":"assistant/chunk","seq":34,"time":1784451769505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" subt"}}} +{"type":"assistant/chunk","seq":35,"time":1784451769505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ask"}}} +{"type":"assistant/chunk","seq":36,"time":1784451769505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":37,"time":1784451769563,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":38,"time":1784451769563,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":39,"time":1784451769592,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":40,"time":1784451769592,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":41,"time":1784451769592,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":42,"time":1784451769592,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":43,"time":1784451769620,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":44,"time":1784451769620,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":45,"time":1784451769620,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"First"}}} +{"type":"assistant/chunk","seq":46,"time":1784451769620,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" subt"}}} +{"type":"assistant/chunk","seq":47,"time":1784451769650,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"ask"}}} +{"type":"assistant/chunk","seq":48,"time":1784451769650,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" -"}}} +{"type":"assistant/chunk","seq":49,"time":1784451769650,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" AL"}}} +{"type":"assistant/chunk","seq":50,"time":1784451769670,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"P"}}} +{"type":"assistant/chunk","seq":51,"time":1784451769671,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"HA"}}} +{"type":"assistant/chunk","seq":52,"time":1784451769671,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":53,"time":1784451769696,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":54,"time":1784451769696,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":55,"time":1784451769696,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"prom"}}} +{"type":"assistant/chunk","seq":56,"time":1784451769753,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"pt"}}} +{"type":"assistant/chunk","seq":57,"time":1784451769753,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":58,"time":1784451769753,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":59,"time":1784451769753,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":60,"time":1784451769762,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":61,"time":1784451769762,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":62,"time":1784451769762,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":63,"time":1784451769762,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":64,"time":1784451769762,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":65,"time":1784451769763,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" AL"}}} +{"type":"assistant/chunk","seq":66,"time":1784451769782,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"P"}}} +{"type":"assistant/chunk","seq":67,"time":1784451769782,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"HA"}}} +{"type":"assistant/chunk","seq":68,"time":1784451769783,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":69,"time":1784451769783,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":70,"time":1784451769783,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":71,"time":1784451769803,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":72,"time":1784451769803,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":73,"time":1784451769803,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":74,"time":1784451769866,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time), with specific prompts. Let me start with the first subtask."}}}} +{"type":"assistant/chunk","seq":75,"time":1784451769866,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","arguments":"{\"description\": \"First subtask - ALPHA\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":76,"time":1784451769867,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3621,"outputTokens":109,"cacheReadTokens":0,"reasoningTokens":32}}}} +{"type":"assistant/chunk","seq":77,"time":1784451769867,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":78,"time":1784451769870,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time), with specific prompts. Let me start with the first subtask."},{"type":"tool-call","id":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","arguments":"{\"description\": \"First subtask - ALPHA\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3621,"outputTokens":109,"cacheReadTokens":0,"reasoningTokens":32}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"} +{"type":"tool/call","seq":79,"time":1784451769871,"data":{"turn":1,"step":1,"callId":"call_00_pNGPLxkadUA9vn2Bm42x5565","name":"subagent","arguments":"{\"description\": \"First subtask - ALPHA\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} +{"type":"tool/result","seq":80,"time":1784451771107,"data":{"turn":1,"step":1,"callId":"call_00_pNGPLxkadUA9vn2Bm42x5565","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[79],"surfaceOp":"append"} +{"type":"step/end","seq":81,"time":1784451771108,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":82,"time":1784451771108,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":83,"time":1784451772258,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":84,"time":1784451772258,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":85,"time":1784451772383,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" first"}}} +{"type":"assistant/chunk","seq":86,"time":1784451772412,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":87,"time":1784451772439,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":88,"time":1784451772440,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":89,"time":1784451772440,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":90,"time":1784451772441,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":91,"time":1784451772441,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} +{"type":"assistant/chunk","seq":92,"time":1784451772441,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} +{"type":"assistant/chunk","seq":93,"time":1784451772491,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":94,"time":1784451772491,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":95,"time":1784451772492,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":96,"time":1784451772492,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":97,"time":1784451772492,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":98,"time":1784451772492,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":99,"time":1784451772494,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":100,"time":1784451772494,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" second"}}} +{"type":"assistant/chunk","seq":101,"time":1784451772495,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" subt"}}} +{"type":"assistant/chunk","seq":102,"time":1784451772517,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ask"}}} +{"type":"assistant/chunk","seq":103,"time":1784451772517,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":104,"time":1784451772600,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":105,"time":1784451772600,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":106,"time":1784451772634,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":107,"time":1784451772634,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":108,"time":1784451772635,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":109,"time":1784451772635,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":110,"time":1784451772635,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":111,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":112,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"Second"}}} +{"type":"assistant/chunk","seq":113,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" subt"}}} +{"type":"assistant/chunk","seq":114,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"ask"}}} +{"type":"assistant/chunk","seq":115,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" -"}}} +{"type":"assistant/chunk","seq":116,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" B"}}} +{"type":"assistant/chunk","seq":117,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"ETA"}}} +{"type":"assistant/chunk","seq":118,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":119,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":120,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":121,"time":1784451773100,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"prom"}}} +{"type":"assistant/chunk","seq":122,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"pt"}}} +{"type":"assistant/chunk","seq":123,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":124,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":125,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":126,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":127,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":128,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":129,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":130,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":131,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" B"}}} +{"type":"assistant/chunk","seq":132,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"ETA"}}} +{"type":"assistant/chunk","seq":133,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":134,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":135,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":136,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":137,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":138,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":139,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to run the second subtask."}}}} +{"type":"assistant/chunk","seq":140,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","arguments":"{\"description\": \"Second subtask - BETA\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":141,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":33,"outputTokens":95,"cacheReadTokens":3712,"reasoningTokens":20}}}} +{"type":"assistant/chunk","seq":142,"time":1784451773101,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":143,"time":1784451773102,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to run the second subtask."},{"type":"tool-call","id":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","arguments":"{\"description\": \"Second subtask - BETA\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":33,"outputTokens":95,"cacheReadTokens":3712,"reasoningTokens":20}},"sourceEventSeqs":[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} +{"type":"tool/call","seq":144,"time":1784451773102,"data":{"turn":1,"step":2,"callId":"call_00_xg61TI40vMlqTuVIpJWj8575","name":"subagent","arguments":"{\"description\": \"Second subtask - BETA\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}} +{"type":"tool/result","seq":145,"time":1784451776122,"data":{"turn":1,"step":2,"callId":"call_00_xg61TI40vMlqTuVIpJWj8575","content":[{"type":"text","text":"BETA"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} +{"type":"step/end","seq":146,"time":1784451776122,"data":{"turn":1,"step":2}} +{"type":"step/start","seq":147,"time":1784451776122,"data":{"turn":1,"step":3}} +{"type":"assistant/chunk","seq":148,"time":1784451777273,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":149,"time":1784451777273,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"Both"}}} +{"type":"assistant/chunk","seq":150,"time":1784451777404,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":151,"time":1784451777404,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"agents"}}} +{"type":"assistant/chunk","seq":152,"time":1784451777404,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" have"}}} +{"type":"assistant/chunk","seq":153,"time":1784451777404,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":154,"time":1784451777404,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":155,"time":1784451777404,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" First"}}} +{"type":"assistant/chunk","seq":156,"time":1784451777407,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":157,"time":1784451777407,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":158,"time":1784451777439,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"AL"}}} +{"type":"assistant/chunk","seq":159,"time":1784451777439,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"P"}}} +{"type":"assistant/chunk","seq":160,"time":1784451777439,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"HA"}}} +{"type":"assistant/chunk","seq":161,"time":1784451777439,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\","}}} +{"type":"assistant/chunk","seq":162,"time":1784451777439,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" second"}}} +{"type":"assistant/chunk","seq":163,"time":1784451777439,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":164,"time":1784451777470,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":165,"time":1784451777470,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"B"}}} +{"type":"assistant/chunk","seq":166,"time":1784451777470,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ETA"}}} +{"type":"assistant/chunk","seq":167,"time":1784451777470,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":168,"time":1784451777470,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":169,"time":1784451777470,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":170,"time":1784451777490,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":171,"time":1784451777490,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":172,"time":1784451777490,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":173,"time":1784451777490,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":174,"time":1784451777490,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":175,"time":1784451777515,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":176,"time":1784451777546,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} +{"type":"assistant/chunk","seq":177,"time":1784451777546,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} +{"type":"assistant/chunk","seq":178,"time":1784451777546,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":179,"time":1784451777546,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":180,"time":1784451777547,"data":{"turn":1,"step":3,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":181,"time":1784451777578,"data":{"turn":1,"step":3,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":182,"time":1784451777578,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} +{"type":"assistant/chunk","seq":183,"time":1784451777578,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} +{"type":"assistant/chunk","seq":184,"time":1784451777578,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} +{"type":"assistant/chunk","seq":185,"time":1784451777578,"data":{"turn":1,"step":3,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":186,"time":1784451777586,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Both subagents have returned. First returned \"ALPHA\", second returned \"BETA\". Now I need to reply with exactly \"PARENT_DONE\"."}}}} +{"type":"assistant/chunk","seq":187,"time":1784451777586,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} +{"type":"assistant/chunk","seq":188,"time":1784451777586,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":14,"outputTokens":37,"cacheReadTokens":3840,"reasoningTokens":32}}}} +{"type":"assistant/chunk","seq":189,"time":1784451777586,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":190,"time":1784451777586,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Both subagents have returned. First returned \"ALPHA\", second returned \"BETA\". Now I need to reply with exactly \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":14,"outputTokens":37,"cacheReadTokens":3840,"reasoningTokens":32}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"} +{"type":"step/end","seq":191,"time":1784451777586,"data":{"turn":1,"step":3}} +{"type":"turn/end","seq":192,"time":1784451777586,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl index bd4fb81d4a..487692bb46 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl @@ -18,40 +18,24 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" at"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" time"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":")."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" First"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"),"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"P"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"HA"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" second"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" prompts"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" start"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"B"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ETA"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" After"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" both"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" return"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PAR"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENT"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_D"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Return ALPHA only","prompt":"Reply with exactly the word ALPHA and nothing else."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","status":"completed","content":[{"type":"content","content":{"type":"text","text":"ALPHA"}}]}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"First"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" subt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ask"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_pNGPLxkadUA9vn2Bm42x5565","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"First subtask - ALPHA","prompt":"Reply with exactly the word ALPHA and nothing else."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_pNGPLxkadUA9vn2Bm42x5565","status":"completed","content":[{"type":"content","content":{"type":"text","text":"ALPHA"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} @@ -62,44 +46,42 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'ll"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" call"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" second"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" return"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"B"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ETA"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_FudNKuJ0fchSptGy3Scw1411","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Return BETA only","prompt":"Reply with exactly the word BETA and nothing else."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_FudNKuJ0fchSptGy3Scw1411","status":"completed","content":[{"type":"content","content":{"type":"text","text":"BETA"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" subt"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ask"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_xg61TI40vMlqTuVIpJWj8575","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Second subtask - BETA","prompt":"Reply with exactly the word BETA and nothing else."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_xg61TI40vMlqTuVIpJWj8575","status":"completed","content":[{"type":"content","content":{"type":"text","text":"BETA"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Both"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agents"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" have"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" first"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" First"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"AL"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"P"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"HA"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\","}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" second"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"B"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ETA"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Now"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" should"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" need"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PAR"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENT"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl index 8dd26c4e70..5afa333183 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl @@ -1,34 +1,34 @@ -{"type":"session","version":0,"id":"ea339828-7885-42e1-9083-4355e6f1708d","createdAt":1783352120855,"cwd":"/tmp/acp-snap-cwd-rbeWyt","parentSession":"5138ed0d-e86e-4a7d-b75b-803307e92b17"} -{"type":"turn/start","seq":0,"time":1783352120856,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352120856,"data":{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352120856,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352120856,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352121437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352121438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352121635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352121663,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352121664,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352121664,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352121664,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":11,"time":1783352121664,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":12,"time":1783352121664,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":13,"time":1783352121691,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":14,"time":1783352121691,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":15,"time":1783352121691,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" CH"}}} -{"type":"assistant/chunk","seq":16,"time":1783352121720,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} -{"type":"assistant/chunk","seq":17,"time":1783352121720,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} -{"type":"assistant/chunk","seq":18,"time":1783352121720,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":19,"time":1783352121747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} -{"type":"assistant/chunk","seq":20,"time":1783352121747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} -{"type":"assistant/chunk","seq":21,"time":1783352121747,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":22,"time":1783352121747,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":23,"time":1783352121747,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"CH"}}} -{"type":"assistant/chunk","seq":24,"time":1783352121748,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ILD"}}} -{"type":"assistant/chunk","seq":25,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_OK"}}} -{"type":"assistant/chunk","seq":26,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly the word CHILD_OK and nothing else."}}}} -{"type":"assistant/chunk","seq":27,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CHILD_OK"}}}} -{"type":"assistant/chunk","seq":28,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}}}} -{"type":"assistant/chunk","seq":29,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":30,"time":1783352121777,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word CHILD_OK and nothing else."},{"type":"text","text":"CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} -{"type":"step/end","seq":31,"time":1783352121778,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":32,"time":1783352121778,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"aefc3a97-9b46-42d3-993c-7f7c19f9e327","createdAt":1784451764214,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-ErhW9C","parentSession":"5ab41657-0a0f-4317-88fe-451c5197cdb4","delegationDepth":1} +{"type":"turn/start","seq":0,"time":1784451764215,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451764216,"data":{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451764216,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451764216,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451765645,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451765645,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451765790,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451765802,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451765802,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451765802,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451765802,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1784451765802,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1784451765802,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1784451765826,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":14,"time":1784451765827,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"CH"}}} +{"type":"assistant/chunk","seq":15,"time":1784451765829,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} +{"type":"assistant/chunk","seq":16,"time":1784451765829,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} +{"type":"assistant/chunk","seq":17,"time":1784451765829,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":18,"time":1784451765829,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":19,"time":1784451765854,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":20,"time":1784451765854,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":21,"time":1784451765854,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":22,"time":1784451765854,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":23,"time":1784451765854,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"CH"}}} +{"type":"assistant/chunk","seq":24,"time":1784451765854,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ILD"}}} +{"type":"assistant/chunk","seq":25,"time":1784451765887,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_OK"}}} +{"type":"assistant/chunk","seq":26,"time":1784451765891,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"CHILD_OK\" and nothing else."}}}} +{"type":"assistant/chunk","seq":27,"time":1784451765891,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CHILD_OK"}}}} +{"type":"assistant/chunk","seq":28,"time":1784451765892,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3286,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":17}}}} +{"type":"assistant/chunk","seq":29,"time":1784451765892,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":30,"time":1784451765892,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"CHILD_OK\" and nothing else."},{"type":"text","text":"CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3286,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"step/end","seq":31,"time":1784451765893,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":32,"time":1784451765893,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl index 6a87cfabb5..5dddaa522f 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl @@ -1,160 +1,127 @@ -{"type":"session","version":0,"id":"5138ed0d-e86e-4a7d-b75b-803307e92b17","createdAt":1783352119267,"cwd":"/tmp/acp-snap-cwd-rbeWyt"} -{"type":"turn/start","seq":0,"time":1783352119273,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783352119274,"data":{"content":[{"type":"text","text":"Use the subagent tool exactly once to delegate this subtask to a child agent: 'Reply with exactly the word CHILD_OK and nothing else.' After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783352119275,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352119281,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783352119925,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783352119925,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783352120053,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783352120080,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783352120081,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783352120081,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783352120111,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":\n"}}} -{"type":"assistant/chunk","seq":11,"time":1783352120112,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} -{"type":"assistant/chunk","seq":12,"time":1783352120112,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":13,"time":1783352120112,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Use"}}} -{"type":"assistant/chunk","seq":14,"time":1783352120113,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":15,"time":1783352120136,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":16,"time":1783352120137,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":17,"time":1783352120137,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":18,"time":1783352120137,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":19,"time":1783352120137,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} -{"type":"assistant/chunk","seq":20,"time":1783352120137,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":21,"time":1783352120164,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" delegate"}}} -{"type":"assistant/chunk","seq":22,"time":1783352120164,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":23,"time":1783352120192,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" task"}}} -{"type":"assistant/chunk","seq":24,"time":1783352120192,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":"}}} -{"type":"assistant/chunk","seq":25,"time":1783352120221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":26,"time":1783352120221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Reply"}}} -{"type":"assistant/chunk","seq":27,"time":1783352120221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":28,"time":1783352120221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":29,"time":1783352120221,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":30,"time":1783352120222,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":31,"time":1783352120248,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" CH"}}} -{"type":"assistant/chunk","seq":32,"time":1783352120248,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} -{"type":"assistant/chunk","seq":33,"time":1783352120249,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} -{"type":"assistant/chunk","seq":34,"time":1783352120249,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":35,"time":1783352120249,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} -{"type":"assistant/chunk","seq":36,"time":1783352120249,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} -{"type":"assistant/chunk","seq":37,"time":1783352120277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".\"\n"}}} -{"type":"assistant/chunk","seq":38,"time":1783352120277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"2"}}} -{"type":"assistant/chunk","seq":39,"time":1783352120277,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":40,"time":1783352120278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" After"}}} -{"type":"assistant/chunk","seq":41,"time":1783352120278,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":42,"time":1783352120305,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":43,"time":1783352120305,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":44,"time":1783352120305,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" returns"}}} -{"type":"assistant/chunk","seq":45,"time":1783352120306,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":46,"time":1783352120306,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":47,"time":1783352120306,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":48,"time":1783352120334,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":49,"time":1783352120334,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} -{"type":"assistant/chunk","seq":50,"time":1783352120334,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":51,"time":1783352120334,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" PAR"}}} -{"type":"assistant/chunk","seq":52,"time":1783352120334,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} -{"type":"assistant/chunk","seq":53,"time":1783352120334,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":54,"time":1783352120361,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":55,"time":1783352120362,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":56,"time":1783352120362,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} -{"type":"assistant/chunk","seq":57,"time":1783352120394,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".\n"}}} -{"type":"assistant/chunk","seq":58,"time":1783352120395,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"3"}}} -{"type":"assistant/chunk","seq":59,"time":1783352120395,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":60,"time":1783352120396,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Do"}}} -{"type":"assistant/chunk","seq":61,"time":1783352120396,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" not"}}} -{"type":"assistant/chunk","seq":62,"time":1783352120397,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} -{"type":"assistant/chunk","seq":63,"time":1783352120397,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":64,"time":1783352120421,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" bash"}}} -{"type":"assistant/chunk","seq":65,"time":1783352120421,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":66,"time":1783352120449,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":".\n\n"}}} -{"type":"assistant/chunk","seq":67,"time":1783352120450,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Let"}}} -{"type":"assistant/chunk","seq":68,"time":1783352120450,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":69,"time":1783352120450,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} -{"type":"assistant/chunk","seq":70,"time":1783352120450,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" this"}}} -{"type":"assistant/chunk","seq":71,"time":1783352120476,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":72,"time":1783352120532,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":73,"time":1783352120532,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":74,"time":1783352120559,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":75,"time":1783352120560,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":76,"time":1783352120560,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":77,"time":1783352120588,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":78,"time":1783352120588,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":79,"time":1783352120588,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":80,"time":1783352120588,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"Reply"}}} -{"type":"assistant/chunk","seq":81,"time":1783352120617,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":82,"time":1783352120618,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" CH"}}} -{"type":"assistant/chunk","seq":83,"time":1783352120618,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"ILD"}}} -{"type":"assistant/chunk","seq":84,"time":1783352120618,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"_OK"}}} -{"type":"assistant/chunk","seq":85,"time":1783352120643,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":86,"time":1783352120671,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":87,"time":1783352120671,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":88,"time":1783352120671,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"prom"}}} -{"type":"assistant/chunk","seq":89,"time":1783352120672,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"pt"}}} -{"type":"assistant/chunk","seq":90,"time":1783352120672,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":91,"time":1783352120700,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":92,"time":1783352120702,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":93,"time":1783352120702,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"Reply"}}} -{"type":"assistant/chunk","seq":94,"time":1783352120703,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":95,"time":1783352120728,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" exactly"}}} -{"type":"assistant/chunk","seq":96,"time":1783352120729,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":97,"time":1783352120729,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" word"}}} -{"type":"assistant/chunk","seq":98,"time":1783352120729,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" CH"}}} -{"type":"assistant/chunk","seq":99,"time":1783352120729,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"ILD"}}} -{"type":"assistant/chunk","seq":100,"time":1783352120729,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"_OK"}}} -{"type":"assistant/chunk","seq":101,"time":1783352120765,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":102,"time":1783352120765,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" nothing"}}} -{"type":"assistant/chunk","seq":103,"time":1783352120766,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":" else"}}} -{"type":"assistant/chunk","seq":104,"time":1783352120766,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"."}}} -{"type":"assistant/chunk","seq":105,"time":1783352120766,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":106,"time":1783352120784,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":107,"time":1783352120851,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to:\n1. Use the subagent tool exactly once to delegate the task: \"Reply with exactly the word CHILD_OK and nothing else.\"\n2. After the subagent returns, reply with the single word PARENT_DONE and stop.\n3. Do not use the bash tool.\n\nLet me do this."}}}} -{"type":"assistant/chunk","seq":108,"time":1783352120851,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}}}} -{"type":"assistant/chunk","seq":109,"time":1783352120852,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}}}} -{"type":"assistant/chunk","seq":110,"time":1783352120852,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":111,"time":1783352120854,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Use the subagent tool exactly once to delegate the task: \"Reply with exactly the word CHILD_OK and nothing else.\"\n2. After the subagent returns, reply with the single word PARENT_DONE and stop.\n3. Do not use the bash tool.\n\nLet me do this."},{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"surfaceOp":"append"} -{"type":"tool/call","seq":112,"time":1783352120854,"data":{"turn":1,"step":1,"callId":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}} -{"type":"tool/result","seq":113,"time":1783352121784,"data":{"turn":1,"step":1,"callId":"call_00_gVbLWC12Qu8JheZpVRRz8749","content":[{"type":"text","text":"CHILD_OK"}],"isError":false},"sourceEventSeqs":[112],"surfaceOp":"append"} -{"type":"step/end","seq":114,"time":1783352121784,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":115,"time":1783352121785,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":116,"time":1783352122364,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":117,"time":1783352122364,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":118,"time":1783352122524,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} -{"type":"assistant/chunk","seq":119,"time":1783352122552,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} -{"type":"assistant/chunk","seq":120,"time":1783352122553,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":121,"time":1783352122553,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":122,"time":1783352122553,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"CH"}}} -{"type":"assistant/chunk","seq":123,"time":1783352122553,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} -{"type":"assistant/chunk","seq":124,"time":1783352122553,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} -{"type":"assistant/chunk","seq":125,"time":1783352122581,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":126,"time":1783352122582,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":127,"time":1783352122582,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" expected"}}} -{"type":"assistant/chunk","seq":128,"time":1783352122610,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":129,"time":1783352122610,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} -{"type":"assistant/chunk","seq":130,"time":1783352122610,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":131,"time":1783352122611,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} -{"type":"assistant/chunk","seq":132,"time":1783352122611,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":133,"time":1783352122611,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":134,"time":1783352122642,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":135,"time":1783352122642,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":136,"time":1783352122642,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} -{"type":"assistant/chunk","seq":137,"time":1783352122674,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} -{"type":"assistant/chunk","seq":138,"time":1783352122674,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":139,"time":1783352122674,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} -{"type":"assistant/chunk","seq":140,"time":1783352122674,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} -{"type":"assistant/chunk","seq":141,"time":1783352122675,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":142,"time":1783352122675,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":143,"time":1783352122701,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":144,"time":1783352122701,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":145,"time":1783352122702,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} -{"type":"assistant/chunk","seq":146,"time":1783352122702,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":147,"time":1783352122702,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":148,"time":1783352122702,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} -{"type":"assistant/chunk","seq":149,"time":1783352122731,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} -{"type":"assistant/chunk","seq":150,"time":1783352122731,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} -{"type":"assistant/chunk","seq":151,"time":1783352122731,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":152,"time":1783352122731,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with the single word \"PARENT_DONE\" and stop."}}}} -{"type":"assistant/chunk","seq":153,"time":1783352122731,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} -{"type":"assistant/chunk","seq":154,"time":1783352122732,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}}}} -{"type":"assistant/chunk","seq":155,"time":1783352122732,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":156,"time":1783352122732,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with the single word \"PARENT_DONE\" and stop."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"} -{"type":"step/end","seq":157,"time":1783352122732,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":158,"time":1783352122732,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"5ab41657-0a0f-4317-88fe-451c5197cdb4","createdAt":1784451761926,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-ErhW9C"} +{"type":"turn/start","seq":0,"time":1784451761930,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451761930,"data":{"content":[{"type":"text","text":"Use the subagent tool exactly once to delegate this subtask to a child agent: 'Reply with exactly the word CHILD_OK and nothing else.' After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451761932,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451761932,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451763352,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451763353,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451763485,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451763528,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451763528,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451763528,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451763528,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} +{"type":"assistant/chunk","seq":11,"time":1784451763528,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":12,"time":1784451763542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":13,"time":1784451763542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":14,"time":1784451763542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} +{"type":"assistant/chunk","seq":15,"time":1784451763542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":16,"time":1784451763542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} +{"type":"assistant/chunk","seq":17,"time":1784451763543,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":18,"time":1784451763568,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" delegate"}}} +{"type":"assistant/chunk","seq":19,"time":1784451763568,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":20,"time":1784451763568,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":21,"time":1784451763596,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" task"}}} +{"type":"assistant/chunk","seq":22,"time":1784451763596,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":23,"time":1784451763596,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" then"}}} +{"type":"assistant/chunk","seq":24,"time":1784451763596,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" after"}}} +{"type":"assistant/chunk","seq":25,"time":1784451763618,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} +{"type":"assistant/chunk","seq":26,"time":1784451763649,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" returns"}}} +{"type":"assistant/chunk","seq":27,"time":1784451763650,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":28,"time":1784451763650,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":29,"time":1784451763650,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":30,"time":1784451763650,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":31,"time":1784451763688,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} +{"type":"assistant/chunk","seq":32,"time":1784451763689,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} +{"type":"assistant/chunk","seq":33,"time":1784451763689,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":34,"time":1784451763689,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":35,"time":1784451763689,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":36,"time":1784451763689,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":37,"time":1784451763704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":38,"time":1784451763704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} +{"type":"assistant/chunk","seq":39,"time":1784451763704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} +{"type":"assistant/chunk","seq":40,"time":1784451763704,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":41,"time":1784451763779,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":42,"time":1784451763779,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":43,"time":1784451763807,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":44,"time":1784451763807,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":45,"time":1784451763807,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":46,"time":1784451763833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":47,"time":1784451763833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":48,"time":1784451763833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":49,"time":1784451763833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":50,"time":1784451763863,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":51,"time":1784451763864,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" CH"}}} +{"type":"assistant/chunk","seq":52,"time":1784451763864,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"ILD"}}} +{"type":"assistant/chunk","seq":53,"time":1784451763885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"_OK"}}} +{"type":"assistant/chunk","seq":54,"time":1784451763885,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" only"}}} +{"type":"assistant/chunk","seq":55,"time":1784451763911,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":56,"time":1784451763939,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":57,"time":1784451763939,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":58,"time":1784451763939,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"prom"}}} +{"type":"assistant/chunk","seq":59,"time":1784451763940,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"pt"}}} +{"type":"assistant/chunk","seq":60,"time":1784451763940,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":61,"time":1784451763964,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":62,"time":1784451763964,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":63,"time":1784451763964,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":64,"time":1784451763964,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":65,"time":1784451763996,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":66,"time":1784451763996,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":67,"time":1784451763996,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":68,"time":1784451763996,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" CH"}}} +{"type":"assistant/chunk","seq":69,"time":1784451763996,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"ILD"}}} +{"type":"assistant/chunk","seq":70,"time":1784451763996,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"_OK"}}} +{"type":"assistant/chunk","seq":71,"time":1784451764019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":72,"time":1784451764019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":73,"time":1784451764019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":74,"time":1784451764019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"."}}} +{"type":"assistant/chunk","seq":75,"time":1784451764019,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":76,"time":1784451764043,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":77,"time":1784451764211,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the subagent tool exactly once to delegate a specific task, then after it returns, reply with \"PARENT_DONE\". Let me do that."}}}} +{"type":"assistant/chunk","seq":78,"time":1784451764211,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK only\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}}}} +{"type":"assistant/chunk","seq":79,"time":1784451764211,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3593,"outputTokens":112,"cacheReadTokens":0,"reasoningTokens":36}}}} +{"type":"assistant/chunk","seq":80,"time":1784451764212,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":81,"time":1784451764213,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the subagent tool exactly once to delegate a specific task, then after it returns, reply with \"PARENT_DONE\". Let me do that."},{"type":"tool-call","id":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK only\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3593,"outputTokens":112,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80],"surfaceOp":"append"} +{"type":"tool/call","seq":82,"time":1784451764214,"data":{"turn":1,"step":1,"callId":"call_00_mQHKZdWXRpPe4vDiwr5L0196","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK only\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}} +{"type":"tool/result","seq":83,"time":1784451765917,"data":{"turn":1,"step":1,"callId":"call_00_mQHKZdWXRpPe4vDiwr5L0196","content":[{"type":"text","text":"CHILD_OK"}],"isError":false},"sourceEventSeqs":[82],"surfaceOp":"append"} +{"type":"step/end","seq":84,"time":1784451765918,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":85,"time":1784451765918,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":86,"time":1784451767064,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":87,"time":1784451767064,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":88,"time":1784451767169,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" sub"}}} +{"type":"assistant/chunk","seq":89,"time":1784451767199,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"agent"}}} +{"type":"assistant/chunk","seq":90,"time":1784451767199,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":91,"time":1784451767199,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":92,"time":1784451767199,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"CH"}}} +{"type":"assistant/chunk","seq":93,"time":1784451767202,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} +{"type":"assistant/chunk","seq":94,"time":1784451767202,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} +{"type":"assistant/chunk","seq":95,"time":1784451767224,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":96,"time":1784451767224,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} +{"type":"assistant/chunk","seq":97,"time":1784451767224,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" expected"}}} +{"type":"assistant/chunk","seq":98,"time":1784451767278,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":99,"time":1784451767278,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":100,"time":1784451767278,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":101,"time":1784451767278,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":102,"time":1784451767278,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":103,"time":1784451767278,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":104,"time":1784451767284,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":105,"time":1784451767284,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":106,"time":1784451767284,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"PAR"}}} +{"type":"assistant/chunk","seq":107,"time":1784451767284,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ENT"}}} +{"type":"assistant/chunk","seq":108,"time":1784451767284,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":109,"time":1784451767284,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":110,"time":1784451767312,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":111,"time":1784451767313,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":112,"time":1784451767313,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":113,"time":1784451767313,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":114,"time":1784451767313,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":115,"time":1784451767313,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"PAR"}}} +{"type":"assistant/chunk","seq":116,"time":1784451767343,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ENT"}}} +{"type":"assistant/chunk","seq":117,"time":1784451767343,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} +{"type":"assistant/chunk","seq":118,"time":1784451767343,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":119,"time":1784451767350,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with \"PARENT_DONE\" and stop."}}}} +{"type":"assistant/chunk","seq":120,"time":1784451767350,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} +{"type":"assistant/chunk","seq":121,"time":1784451767350,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":136,"outputTokens":32,"cacheReadTokens":3584,"reasoningTokens":27}}}} +{"type":"assistant/chunk","seq":122,"time":1784451767350,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":123,"time":1784451767351,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with \"PARENT_DONE\" and stop."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":136,"outputTokens":32,"cacheReadTokens":3584,"reasoningTokens":27}},"sourceEventSeqs":[86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122],"surfaceOp":"append"} +{"type":"step/end","seq":124,"time":1784451767351,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":125,"time":1784451767351,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl index 2b77e856e6..1228921ca4 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl @@ -5,10 +5,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"1"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Use"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" use"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} @@ -17,58 +14,30 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" once"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" delegate"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" task"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Reply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" CH"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ILD"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_OK"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" nothing"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" else"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\"\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"2"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" After"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" then"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" after"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returns"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" PAR"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PAR"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENT"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"3"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Do"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" not"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" use"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" bash"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":".\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Let"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" do"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" this"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_gVbLWC12Qu8JheZpVRRz8749","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Reply with CHILD_OK","prompt":"Reply with exactly the word CHILD_OK and nothing else."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_gVbLWC12Qu8JheZpVRRz8749","status":"completed","content":[{"type":"content","content":{"type":"text","text":"CHILD_OK"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_mQHKZdWXRpPe4vDiwr5L0196","title":"subagent","kind":"other","status":"in_progress","rawInput":{"description":"Reply with CHILD_OK only","prompt":"Reply with exactly the word CHILD_OK and nothing else."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_mQHKZdWXRpPe4vDiwr5L0196","status":"completed","content":[{"type":"content","content":{"type":"text","text":"CHILD_OK"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" sub"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"agent"}}}} @@ -87,9 +56,6 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PAR"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ENT"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl index 3d89428bbd..b393644c5b 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl @@ -1,36 +1,36 @@ -{"type":"session","version":0,"id":"583a4db2-3350-436c-b4a5-5615fd159052","createdAt":1783600636316,"cwd":"/var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-vdJYjz","parentSession":"3fd7d599-56b1-493a-930d-f1fc5e1556e8"} -{"type":"turn/start","seq":0,"time":1783600636316,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783600636316,"data":{"content":[{"type":"text","text":"Reply with exactly the word WF_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783600636316,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600636317,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783600638173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":11,"time":1783600638189,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":12,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":13,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":14,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"WF"}}} -{"type":"assistant/chunk","seq":15,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_CH"}}} -{"type":"assistant/chunk","seq":16,"time":1783600638213,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} -{"type":"assistant/chunk","seq":17,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} -{"type":"assistant/chunk","seq":18,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":19,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":20,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} -{"type":"assistant/chunk","seq":21,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} -{"type":"assistant/chunk","seq":22,"time":1783600638242,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":23,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":24,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"WF"}}} -{"type":"assistant/chunk","seq":25,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_CH"}}} -{"type":"assistant/chunk","seq":26,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ILD"}}} -{"type":"assistant/chunk","seq":27,"time":1783600638276,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_OK"}}} -{"type":"assistant/chunk","seq":28,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."}}}} -{"type":"assistant/chunk","seq":29,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WF_CHILD_OK"}}}} -{"type":"assistant/chunk","seq":30,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}}}} -{"type":"assistant/chunk","seq":31,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783600638281,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} -{"type":"step/end","seq":33,"time":1783600638281,"data":{"turn":1,"step":1}} -{"type":"turn/end","seq":34,"time":1783600638281,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"2903e21a-fb6b-4d36-9a78-b9240419c334","createdAt":1784451805556,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-Uzz8l5","parentSession":"6789922c-5a8c-4141-8336-0f9b0809bb17","delegationDepth":1} +{"type":"turn/start","seq":0,"time":1784451805557,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451805557,"data":{"content":[{"type":"text","text":"Reply with exactly the word WF_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451805557,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451805557,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451807175,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451807175,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451807383,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451807416,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451807416,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451807416,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451807416,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1784451807416,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1784451807416,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1784451807459,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":14,"time":1784451807459,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"WF"}}} +{"type":"assistant/chunk","seq":15,"time":1784451807460,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_CH"}}} +{"type":"assistant/chunk","seq":16,"time":1784451807460,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} +{"type":"assistant/chunk","seq":17,"time":1784451807460,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} +{"type":"assistant/chunk","seq":18,"time":1784451807472,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":19,"time":1784451807472,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":20,"time":1784451807472,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" nothing"}}} +{"type":"assistant/chunk","seq":21,"time":1784451807472,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" else"}}} +{"type":"assistant/chunk","seq":22,"time":1784451807472,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":23,"time":1784451807501,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":24,"time":1784451807501,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"WF"}}} +{"type":"assistant/chunk","seq":25,"time":1784451807501,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_CH"}}} +{"type":"assistant/chunk","seq":26,"time":1784451807501,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ILD"}}} +{"type":"assistant/chunk","seq":27,"time":1784451807501,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"_OK"}}} +{"type":"assistant/chunk","seq":28,"time":1784451807504,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."}}}} +{"type":"assistant/chunk","seq":29,"time":1784451807504,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WF_CHILD_OK"}}}} +{"type":"assistant/chunk","seq":30,"time":1784451807504,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3550,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":18}}}} +{"type":"assistant/chunk","seq":31,"time":1784451807504,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":32,"time":1784451807505,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3550,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1784451807505,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":34,"time":1784451807506,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl index 3e0ae3da73..55b622307d 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl @@ -1,209 +1,143 @@ -{"type":"session","version":0,"id":"3fd7d599-56b1-493a-930d-f1fc5e1556e8","createdAt":1783600631835,"cwd":"/var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-vdJYjz"} -{"type":"turn/start","seq":0,"time":1783600631838,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} -{"type":"user/message","seq":1,"time":1783600631838,"data":{"content":[{"type":"text","text":"Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim):\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\nAfter the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} -{"type":"step/start","seq":2,"time":1783600631839,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600631839,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} -{"type":"assistant/chunk","seq":4,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":5,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":6,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} -{"type":"assistant/chunk","seq":7,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} -{"type":"assistant/chunk","seq":8,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":9,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":10,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" use"}}} -{"type":"assistant/chunk","seq":11,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":12,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" workflow"}}} -{"type":"assistant/chunk","seq":13,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tool"}}} -{"type":"assistant/chunk","seq":14,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":15,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" once"}}} -{"type":"assistant/chunk","seq":16,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":17,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} -{"type":"assistant/chunk","seq":18,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" parameters"}}} -{"type":"assistant/chunk","seq":19,"time":1783600635635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":20,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} -{"type":"assistant/chunk","seq":21,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":22,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" carefully"}}} -{"type":"assistant/chunk","seq":23,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" follow"}}} -{"type":"assistant/chunk","seq":24,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":25,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" instructions"}}} -{"type":"assistant/chunk","seq":26,"time":1783600635743,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":":\n\n"}}} -{"type":"assistant/chunk","seq":27,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"1"}}} -{"type":"assistant/chunk","seq":28,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":29,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" args"}}} -{"type":"assistant/chunk","seq":30,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" omitted"}}} -{"type":"assistant/chunk","seq":31,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ("}}} -{"type":"assistant/chunk","seq":32,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"so"}}} -{"type":"assistant/chunk","seq":33,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":34,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" don"}}} -{"type":"assistant/chunk","seq":35,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"'t"}}} -{"type":"assistant/chunk","seq":36,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" include"}}} -{"type":"assistant/chunk","seq":37,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":38,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":")\n"}}} -{"type":"assistant/chunk","seq":39,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"2"}}} -{"type":"assistant/chunk","seq":40,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":41,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" meta"}}} -{"type":"assistant/chunk","seq":42,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ="}}} -{"type":"assistant/chunk","seq":43,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" {"}}} -{"type":"assistant/chunk","seq":44,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":45,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"name"}}} -{"type":"assistant/chunk","seq":46,"time":1783600635744,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\":"}}} -{"type":"assistant/chunk","seq":47,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":48,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"sn"}}} -{"type":"assistant/chunk","seq":49,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"apshot"}}} -{"type":"assistant/chunk","seq":50,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"-flow"}}} -{"type":"assistant/chunk","seq":51,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\","}}} -{"type":"assistant/chunk","seq":52,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":53,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"description"}}} -{"type":"assistant/chunk","seq":54,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\":"}}} -{"type":"assistant/chunk","seq":55,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":56,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"one"}}} -{"type":"assistant/chunk","seq":57,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" child"}}} -{"type":"assistant/chunk","seq":58,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" for"}}} -{"type":"assistant/chunk","seq":59,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":60,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" snapshot"}}} -{"type":"assistant/chunk","seq":61,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":62,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" }\n"}}} -{"type":"assistant/chunk","seq":63,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"3"}}} -{"type":"assistant/chunk","seq":64,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":65,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" script"}}} -{"type":"assistant/chunk","seq":66,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" ="}}} -{"type":"assistant/chunk","seq":67,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} -{"type":"assistant/chunk","seq":68,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" given"}}} -{"type":"assistant/chunk","seq":69,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" verb"}}} -{"type":"assistant/chunk","seq":70,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"atim"}}} -{"type":"assistant/chunk","seq":71,"time":1783600635745,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\n"}}} -{"type":"assistant/chunk","seq":72,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"4"}}} -{"type":"assistant/chunk","seq":73,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":74,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" After"}}} -{"type":"assistant/chunk","seq":75,"time":1783600635746,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" it"}}} -{"type":"assistant/chunk","seq":76,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" returns"}}} -{"type":"assistant/chunk","seq":77,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} -{"type":"assistant/chunk","seq":78,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":79,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":80,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":81,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"WORK"}}} -{"type":"assistant/chunk","seq":82,"time":1783600635754,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"FL"}}} -{"type":"assistant/chunk","seq":83,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"OW"}}} -{"type":"assistant/chunk","seq":84,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":85,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":86,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\"\n\n"}}} -{"type":"assistant/chunk","seq":87,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Let"}}} -{"type":"assistant/chunk","seq":88,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} -{"type":"assistant/chunk","seq":89,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} -{"type":"assistant/chunk","seq":90,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":91,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" that"}}} -{"type":"assistant/chunk","seq":92,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":93,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} -{"type":"assistant/chunk","seq":94,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":""}}} -{"type":"assistant/chunk","seq":95,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"{"}}} -{"type":"assistant/chunk","seq":96,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":97,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"meta"}}} -{"type":"assistant/chunk","seq":98,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":99,"time":1783600635756,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":100,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"{\""}}} -{"type":"assistant/chunk","seq":101,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"name"}}} -{"type":"assistant/chunk","seq":102,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\":"}}} -{"type":"assistant/chunk","seq":103,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" \""}}} -{"type":"assistant/chunk","seq":104,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"sn"}}} -{"type":"assistant/chunk","seq":105,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"apshot"}}} -{"type":"assistant/chunk","seq":106,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"-flow"}}} -{"type":"assistant/chunk","seq":107,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\","}}} -{"type":"assistant/chunk","seq":108,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" \""}}} -{"type":"assistant/chunk","seq":109,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"description"}}} -{"type":"assistant/chunk","seq":110,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\":"}}} -{"type":"assistant/chunk","seq":111,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" \""}}} -{"type":"assistant/chunk","seq":112,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"one"}}} -{"type":"assistant/chunk","seq":113,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" child"}}} -{"type":"assistant/chunk","seq":114,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" for"}}} -{"type":"assistant/chunk","seq":115,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":116,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" snapshot"}}} -{"type":"assistant/chunk","seq":117,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":118,"time":1783600635757,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":119,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":", "}}} -{"type":"assistant/chunk","seq":120,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":121,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"script"}}} -{"type":"assistant/chunk","seq":122,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":123,"time":1783600635759,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":": "}}} -{"type":"assistant/chunk","seq":124,"time":1783600635764,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":125,"time":1783600635764,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\\n"}}} -{"type":"assistant/chunk","seq":126,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"phase"}}} -{"type":"assistant/chunk","seq":127,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"('"}}} -{"type":"assistant/chunk","seq":128,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"Run"}}} -{"type":"assistant/chunk","seq":129,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"')\\n"}}} -{"type":"assistant/chunk","seq":130,"time":1783600636039,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"const"}}} -{"type":"assistant/chunk","seq":131,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" reply"}}} -{"type":"assistant/chunk","seq":132,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" ="}}} -{"type":"assistant/chunk","seq":133,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" await"}}} -{"type":"assistant/chunk","seq":134,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" agent"}}} -{"type":"assistant/chunk","seq":135,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"('"}}} -{"type":"assistant/chunk","seq":136,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"Reply"}}} -{"type":"assistant/chunk","seq":137,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" with"}}} -{"type":"assistant/chunk","seq":138,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" exactly"}}} -{"type":"assistant/chunk","seq":139,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" the"}}} -{"type":"assistant/chunk","seq":140,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" word"}}} -{"type":"assistant/chunk","seq":141,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" WF"}}} -{"type":"assistant/chunk","seq":142,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"_CH"}}} -{"type":"assistant/chunk","seq":143,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"ILD"}}} -{"type":"assistant/chunk","seq":144,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"_OK"}}} -{"type":"assistant/chunk","seq":145,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" and"}}} -{"type":"assistant/chunk","seq":146,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" nothing"}}} -{"type":"assistant/chunk","seq":147,"time":1783600636245,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" else"}}} -{"type":"assistant/chunk","seq":148,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":".')\\n"}}} -{"type":"assistant/chunk","seq":149,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"return"}}} -{"type":"assistant/chunk","seq":150,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" {"}}} -{"type":"assistant/chunk","seq":151,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" reply"}}} -{"type":"assistant/chunk","seq":152,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":" }\\n"}}} -{"type":"assistant/chunk","seq":153,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"\""}}} -{"type":"assistant/chunk","seq":154,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","argumentsDelta":"}"}}} -{"type":"assistant/chunk","seq":155,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."}}}} -{"type":"assistant/chunk","seq":156,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}}}} -{"type":"assistant/chunk","seq":157,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}}}} -{"type":"assistant/chunk","seq":158,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":159,"time":1783600636247,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."},{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} -{"type":"tool/call","seq":160,"time":1783600636247,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}} -{"type":"tool/result","seq":161,"time":1783600638304,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","content":[{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"} -{"type":"step/end","seq":162,"time":1783600638304,"data":{"turn":1,"step":1}} -{"type":"step/start","seq":163,"time":1783600638305,"data":{"turn":1,"step":2}} -{"type":"assistant/chunk","seq":164,"time":1783600640028,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} -{"type":"assistant/chunk","seq":165,"time":1783600640028,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} -{"type":"assistant/chunk","seq":166,"time":1783600640134,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" workflow"}}} -{"type":"assistant/chunk","seq":167,"time":1783600640162,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} -{"type":"assistant/chunk","seq":168,"time":1783600640195,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} -{"type":"assistant/chunk","seq":169,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":170,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} -{"type":"assistant/chunk","seq":171,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":172,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":173,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"WF"}}} -{"type":"assistant/chunk","seq":174,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_CH"}}} -{"type":"assistant/chunk","seq":175,"time":1783600640862,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} -{"type":"assistant/chunk","seq":176,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} -{"type":"assistant/chunk","seq":177,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} -{"type":"assistant/chunk","seq":178,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} -{"type":"assistant/chunk","seq":179,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} -{"type":"assistant/chunk","seq":180,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} -{"type":"assistant/chunk","seq":181,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} -{"type":"assistant/chunk","seq":182,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} -{"type":"assistant/chunk","seq":183,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} -{"type":"assistant/chunk","seq":184,"time":1783600640864,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} -{"type":"assistant/chunk","seq":185,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} -{"type":"assistant/chunk","seq":186,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"WORK"}}} -{"type":"assistant/chunk","seq":187,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"FL"}}} -{"type":"assistant/chunk","seq":188,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"OW"}}} -{"type":"assistant/chunk","seq":189,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} -{"type":"assistant/chunk","seq":190,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} -{"type":"assistant/chunk","seq":191,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} -{"type":"assistant/chunk","seq":192,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} -{"type":"assistant/chunk","seq":193,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} -{"type":"assistant/chunk","seq":194,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} -{"type":"assistant/chunk","seq":195,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} -{"type":"assistant/chunk","seq":196,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"WORK"}}} -{"type":"assistant/chunk","seq":197,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"FL"}}} -{"type":"assistant/chunk","seq":198,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"OW"}}} -{"type":"assistant/chunk","seq":199,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} -{"type":"assistant/chunk","seq":200,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} -{"type":"assistant/chunk","seq":201,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."}}}} -{"type":"assistant/chunk","seq":202,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WORKFLOW_DONE"}}}} -{"type":"assistant/chunk","seq":203,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}}}} -{"type":"assistant/chunk","seq":204,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":205,"time":1783600640865,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} -{"type":"step/end","seq":206,"time":1783600640865,"data":{"turn":1,"step":2}} -{"type":"turn/end","seq":207,"time":1783600640865,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"session","version":0,"id":"6789922c-5a8c-4141-8336-0f9b0809bb17","createdAt":1784451802866,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-Uzz8l5"} +{"type":"turn/start","seq":0,"time":1784451802869,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784451802870,"data":{"content":[{"type":"text","text":"Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim):\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\nAfter the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784451802872,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784451802873,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784451804371,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784451804371,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784451804483,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784451804504,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784451804505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784451804505,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784451804506,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" run"}}} +{"type":"assistant/chunk","seq":11,"time":1784451804537,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" a"}}} +{"type":"assistant/chunk","seq":12,"time":1784451804537,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":13,"time":1784451804561,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" workflow"}}} +{"type":"assistant/chunk","seq":14,"time":1784451804561,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" script"}}} +{"type":"assistant/chunk","seq":15,"time":1784451804561,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":16,"time":1784451804561,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" specific"}}} +{"type":"assistant/chunk","seq":17,"time":1784451804588,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" parameters"}}} +{"type":"assistant/chunk","seq":18,"time":1784451804589,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":19,"time":1784451804589,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" Let"}}} +{"type":"assistant/chunk","seq":20,"time":1784451804589,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":21,"time":1784451804589,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" do"}}} +{"type":"assistant/chunk","seq":22,"time":1784451804613,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":23,"time":1784451804613,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" as"}}} +{"type":"assistant/chunk","seq":24,"time":1784451804640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" instructed"}}} +{"type":"assistant/chunk","seq":25,"time":1784451804641,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":26,"time":1784451804733,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":27,"time":1784451804733,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":""}}} +{"type":"assistant/chunk","seq":28,"time":1784451804733,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"{"}}} +{"type":"assistant/chunk","seq":29,"time":1784451804733,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":30,"time":1784451804746,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"meta"}}} +{"type":"assistant/chunk","seq":31,"time":1784451804778,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":32,"time":1784451804778,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":33,"time":1784451804779,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"{\""}}} +{"type":"assistant/chunk","seq":34,"time":1784451804808,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"name"}}} +{"type":"assistant/chunk","seq":35,"time":1784451804808,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":36,"time":1784451804808,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":37,"time":1784451804809,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"sn"}}} +{"type":"assistant/chunk","seq":38,"time":1784451804809,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"apshot"}}} +{"type":"assistant/chunk","seq":39,"time":1784451804809,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"-flow"}}} +{"type":"assistant/chunk","seq":40,"time":1784451804833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\","}}} +{"type":"assistant/chunk","seq":41,"time":1784451804833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":42,"time":1784451804833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"description"}}} +{"type":"assistant/chunk","seq":43,"time":1784451804833,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\":"}}} +{"type":"assistant/chunk","seq":44,"time":1784451804834,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" \""}}} +{"type":"assistant/chunk","seq":45,"time":1784451804834,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"one"}}} +{"type":"assistant/chunk","seq":46,"time":1784451804858,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" child"}}} +{"type":"assistant/chunk","seq":47,"time":1784451804859,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" for"}}} +{"type":"assistant/chunk","seq":48,"time":1784451804859,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":49,"time":1784451804859,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" snapshot"}}} +{"type":"assistant/chunk","seq":50,"time":1784451804859,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":51,"time":1784451804882,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":52,"time":1784451804923,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":", "}}} +{"type":"assistant/chunk","seq":53,"time":1784451804924,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":54,"time":1784451804924,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"script"}}} +{"type":"assistant/chunk","seq":55,"time":1784451804924,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":56,"time":1784451804924,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":": "}}} +{"type":"assistant/chunk","seq":57,"time":1784451804943,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":58,"time":1784451804943,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"phase"}}} +{"type":"assistant/chunk","seq":59,"time":1784451804943,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"('"}}} +{"type":"assistant/chunk","seq":60,"time":1784451804943,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"Run"}}} +{"type":"assistant/chunk","seq":61,"time":1784451805452,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"')\\n"}}} +{"type":"assistant/chunk","seq":62,"time":1784451805452,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"const"}}} +{"type":"assistant/chunk","seq":63,"time":1784451805452,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" reply"}}} +{"type":"assistant/chunk","seq":64,"time":1784451805452,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" ="}}} +{"type":"assistant/chunk","seq":65,"time":1784451805452,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" await"}}} +{"type":"assistant/chunk","seq":66,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" agent"}}} +{"type":"assistant/chunk","seq":67,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"('"}}} +{"type":"assistant/chunk","seq":68,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"Reply"}}} +{"type":"assistant/chunk","seq":69,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" with"}}} +{"type":"assistant/chunk","seq":70,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" exactly"}}} +{"type":"assistant/chunk","seq":71,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" the"}}} +{"type":"assistant/chunk","seq":72,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" word"}}} +{"type":"assistant/chunk","seq":73,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" WF"}}} +{"type":"assistant/chunk","seq":74,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"_CH"}}} +{"type":"assistant/chunk","seq":75,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"ILD"}}} +{"type":"assistant/chunk","seq":76,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"_OK"}}} +{"type":"assistant/chunk","seq":77,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" and"}}} +{"type":"assistant/chunk","seq":78,"time":1784451805455,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" nothing"}}} +{"type":"assistant/chunk","seq":79,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" else"}}} +{"type":"assistant/chunk","seq":80,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":".')\\n"}}} +{"type":"assistant/chunk","seq":81,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"return"}}} +{"type":"assistant/chunk","seq":82,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" {"}}} +{"type":"assistant/chunk","seq":83,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" reply"}}} +{"type":"assistant/chunk","seq":84,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":" }"}}} +{"type":"assistant/chunk","seq":85,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"\""}}} +{"type":"assistant/chunk","seq":86,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","argumentsDelta":"}"}}} +{"type":"assistant/chunk","seq":87,"time":1784451805456,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to run a specific workflow script with specific parameters. Let me do exactly as instructed."}}}} +{"type":"assistant/chunk","seq":88,"time":1784451805457,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"phase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\"}"}}}} +{"type":"assistant/chunk","seq":89,"time":1784451805457,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3635,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":21}}}} +{"type":"assistant/chunk","seq":90,"time":1784451805457,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":91,"time":1784451805459,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific workflow script with specific parameters. Let me do exactly as instructed."},{"type":"tool-call","id":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"phase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3635,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":21}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90],"surfaceOp":"append"} +{"type":"tool/call","seq":92,"time":1784451805460,"data":{"turn":1,"step":1,"callId":"call_00_dQ54AjERB7zcWCD6mkku2211","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"phase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\"}"}} +{"type":"tool/result","seq":93,"time":1784451807534,"data":{"turn":1,"step":1,"callId":"call_00_dQ54AjERB7zcWCD6mkku2211","content":[{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[92],"surfaceOp":"append"} +{"type":"step/end","seq":94,"time":1784451807534,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":95,"time":1784451807535,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":96,"time":1784451809061,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":97,"time":1784451809061,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":98,"time":1784451809087,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" workflow"}}} +{"type":"assistant/chunk","seq":99,"time":1784451809118,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" returned"}}} +{"type":"assistant/chunk","seq":100,"time":1784451809118,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" successfully"}}} +{"type":"assistant/chunk","seq":101,"time":1784451809118,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":102,"time":1784451809146,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":103,"time":1784451809146,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":104,"time":1784451809172,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":105,"time":1784451809172,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"WF"}}} +{"type":"assistant/chunk","seq":106,"time":1784451809172,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_CH"}}} +{"type":"assistant/chunk","seq":107,"time":1784451809172,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ILD"}}} +{"type":"assistant/chunk","seq":108,"time":1784451809172,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_OK"}}} +{"type":"assistant/chunk","seq":109,"time":1784451809173,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\"."}}} +{"type":"assistant/chunk","seq":110,"time":1784451809203,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" Now"}}} +{"type":"assistant/chunk","seq":111,"time":1784451809203,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" I"}}} +{"type":"assistant/chunk","seq":112,"time":1784451809204,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" need"}}} +{"type":"assistant/chunk","seq":113,"time":1784451809204,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":114,"time":1784451809204,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":115,"time":1784451809222,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":116,"time":1784451809222,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" the"}}} +{"type":"assistant/chunk","seq":117,"time":1784451809381,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" single"}}} +{"type":"assistant/chunk","seq":118,"time":1784451809381,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" word"}}} +{"type":"assistant/chunk","seq":119,"time":1784451809382,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":120,"time":1784451809382,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"WORK"}}} +{"type":"assistant/chunk","seq":121,"time":1784451809382,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"FL"}}} +{"type":"assistant/chunk","seq":122,"time":1784451809382,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"OW"}}} +{"type":"assistant/chunk","seq":123,"time":1784451809382,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"_D"}}} +{"type":"assistant/chunk","seq":124,"time":1784451809382,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"ONE"}}} +{"type":"assistant/chunk","seq":125,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":126,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":127,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":128,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":129,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":130,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"WORK"}}} +{"type":"assistant/chunk","seq":131,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"FL"}}} +{"type":"assistant/chunk","seq":132,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"OW"}}} +{"type":"assistant/chunk","seq":133,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"_D"}}} +{"type":"assistant/chunk","seq":134,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":1,"text":"ONE"}}} +{"type":"assistant/chunk","seq":135,"time":1784451809383,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with the single word \"WORKFLOW_DONE\" and stop."}}}} +{"type":"assistant/chunk","seq":136,"time":1784451809384,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WORKFLOW_DONE"}}}} +{"type":"assistant/chunk","seq":137,"time":1784451809384,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":210,"outputTokens":38,"cacheReadTokens":3584,"reasoningTokens":32}}}} +{"type":"assistant/chunk","seq":138,"time":1784451809384,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":139,"time":1784451809384,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with the single word \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":210,"outputTokens":38,"cacheReadTokens":3584,"reasoningTokens":32}},"sourceEventSeqs":[96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138],"surfaceOp":"append"} +{"type":"step/end","seq":140,"time":1784451809384,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":141,"time":1784451809384,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl index 03f482bcc6..fb2820212c 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl @@ -5,91 +5,24 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" use"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" run"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" a"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" workflow"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tool"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" once"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" script"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" specific"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" parameters"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" Let"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" carefully"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" follow"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instructions"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":":\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"1"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" args"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" omitted"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ("}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"so"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" I"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" don"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'t"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" include"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":")\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"2"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" meta"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ="}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" {"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"name"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\":"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"sn"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"apshot"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"-flow"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"description"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\":"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"one"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" child"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" for"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" snapshot"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" }\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"3"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" script"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" ="}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" given"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" verb"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"atim"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"4"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" After"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" it"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returns"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"WORK"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"FL"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"OW"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"_D"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ONE"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\"\n\n"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Let"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" do"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" that"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" as"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" instructed"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","title":"workflow: snapshot-flow","kind":"other","status":"in_progress","rawInput":"\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\n"}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","status":"completed","content":[{"type":"content","content":{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}}]}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_00_dQ54AjERB7zcWCD6mkku2211","title":"workflow: snapshot-flow","kind":"other","status":"in_progress","rawInput":"phase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }"}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_00_dQ54AjERB7zcWCD6mkku2211","status":"completed","content":[{"type":"content","content":{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" workflow"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" returned"}}}} @@ -109,7 +42,9 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} -{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" the"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" single"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" word"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"WORK"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"FL"}}}} diff --git a/examples/headless-agent/cordis.yml b/examples/headless-agent/cordis.yml index 7f48c529c4..1cd161eea7 100644 --- a/examples/headless-agent/cordis.yml +++ b/examples/headless-agent/cordis.yml @@ -64,12 +64,14 @@ config: provider: spawn toolName: subagent + maxDepth: 1 - id: tool-subagent-fork name: '@deepseek-ai/dsh-tool-subagent' config: provider: fork toolName: subagent_fork + maxDepth: 1 # The worker-thread workflow engine fans a model-written JavaScript script's # `agent()` calls out through the spawn backend. diff --git a/examples/repl-agent/cordis.yml b/examples/repl-agent/cordis.yml index 00a6b4b9a6..1b47629249 100644 --- a/examples/repl-agent/cordis.yml +++ b/examples/repl-agent/cordis.yml @@ -77,12 +77,14 @@ config: provider: spawn toolName: subagent + maxDepth: 1 - id: tool-subagent-fork name: '@deepseek-ai/dsh-tool-subagent' config: provider: fork toolName: subagent_fork + maxDepth: 1 # The worker-thread workflow engine fans a model-written JavaScript script's diff --git a/packages/subagent/tool-subagent/README.md b/packages/subagent/tool-subagent/README.md index 825e252923..932b410abc 100644 --- a/packages/subagent/tool-subagent/README.md +++ b/packages/subagent/tool-subagent/README.md @@ -22,7 +22,7 @@ With `run_in_background: true`, the tool registers the parent-owned task before | `agentOptions` | Default child options, currently including `model`. | | `persona` | Per-child persona; requires provider `persona` capability. | | `toolFilter` | Per-child global-tool restriction; requires `toolFilter` capability. | -| `maxDepth` | Absolute delegation-depth cap; requires `depthLimit` capability. | +| `maxDepth` | Absolute delegation-depth cap, default `1` (`0` forbids delegation); a numeric cap requires the `depthLimit` capability and fails the mount without it. `'provider-managed'` sends no cap — for an out-of-process provider whose budget belongs to the child harness. A child AT the cap also loses this tool from its schema when the provider supports `toolFilter` (prompt-face hiding; the service still rejects on the execution face). | ## Concurrency diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index f46f3dda2c..3cde5d6a1a 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -12,7 +12,7 @@ import z from 'schemastery' import { defineTool } from '@deepseek-ai/dsh-tools' import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import { assertSubagentMaxDepth } from '@deepseek-ai/dsh-subagent' +import { assertSubagentMaxDepth, delegationDepthOf } from '@deepseek-ai/dsh-subagent' import type { SubagentProvider, SubagentResult, SubagentRun, SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import type { TaskOutcome } from '@deepseek-ai/dsh-tasks' @@ -45,8 +45,7 @@ export interface Config { /** * Tool filter applied to every child. Filtered tools disappear from its * prompt and reject execution. Requires the provider's `toolFilter` - * capability; unknown names fail startup. Children otherwise see this tool, - * so deny it or set `maxDepth` to bound recursion. + * capability; unknown names fail startup. */ toolFilter?: { /** Global tool names the child keeps; everything else is removed. */ @@ -55,10 +54,16 @@ export interface Config { deny?: string[] } /** - * Maximum child depth. Requires the provider's `depthLimit` capability and a - * non-negative safe integer. Omission is unbounded. + * Maximum child depth: a non-negative safe integer (default `1`; `0` forbids + * delegation entirely), or `'provider-managed'` to send no cap. A numeric cap + * requires the provider's `depthLimit` capability (mount fails loud + * otherwise), and a child AT the cap additionally loses this tool from its + * schema when the provider supports `toolFilter` — the prompt face of the + * budget; the service keeps rejecting on the execution face. + * `'provider-managed'` is for an out-of-process provider (ACP) whose + * recursion budget belongs to the child harness's own deployment. */ - maxDepth?: number + maxDepth?: number | 'provider-managed' } export const Config: z = z.object({ @@ -76,7 +81,7 @@ export const Config: z = z.object({ allow: z.array(z.string()).default(undefined as unknown as string[]), deny: z.array(z.string()).default(undefined as unknown as string[]), }).default(undefined as unknown as { allow: string[]; deny: string[] }), - maxDepth: z.natural().max(Number.MAX_SAFE_INTEGER), + maxDepth: z.union([z.natural().max(Number.MAX_SAFE_INTEGER), z.const('provider-managed' as const)]).default(1), }) /** @@ -194,15 +199,29 @@ function providerWording(inheritsConversation: boolean): { description: string; } } -function startRequest(config: Config, prompt: string, parent: Agent, signal: AbortSignal): SubagentStartRequest { +function startRequest( + config: Config, + prompt: string, + parent: Agent, + signal: AbortSignal, + hideAtCapToolName: string | undefined, +): SubagentStartRequest { + const maxDepth = typeof config.maxDepth === 'number' ? config.maxDepth : undefined + // A child AT the cap cannot delegate further: deny it this tool so its + // schema hides what the service would reject anyway (prompt face; the + // depth check at start remains the execution face). + const childAtCap = maxDepth !== undefined && delegationDepthOf(parent) + 1 >= maxDepth + const toolFilter = childAtCap && hideAtCapToolName !== undefined + ? { ...config.toolFilter, deny: [...config.toolFilter?.deny ?? [], hideAtCapToolName] } + : config.toolFilter return { prompt: [{ type: 'text', text: prompt }], parent, signal, ...config.agentOptions !== undefined ? { agentOptions: config.agentOptions } : {}, ...config.persona !== undefined ? { persona: config.persona } : {}, - ...config.toolFilter !== undefined ? { toolFilter: config.toolFilter } : {}, - ...config.maxDepth !== undefined ? { maxDepth: config.maxDepth } : {}, + ...toolFilter !== undefined ? { toolFilter } : {}, + ...maxDepth !== undefined ? { maxDepth } : {}, } } @@ -218,8 +237,9 @@ async function settleStart(start: Promise, signal: AbortSignal): Pr } export function apply(ctx: Context, config: Config): void { - // Direct apply() bypasses Schemastery's numeric constraints. - assertSubagentMaxDepth(config.maxDepth) + // Direct apply() bypasses Schemastery's numeric constraints. A direct-apply + // omission stays capless (the schema default only runs through the loader). + if (config.maxDepth !== 'provider-managed') assertSubagentMaxDepth(config.maxDepth) // Reject an empty explicit filter at load instead of failing every delegation. if (config.toolFilter !== undefined && config.toolFilter.allow === undefined && config.toolFilter.deny === undefined) { throw new Error('tool-subagent: `toolFilter` is configured but names neither `allow` nor `deny` — remove the key or fill the filter') @@ -228,6 +248,18 @@ export function apply(ctx: Context, config: Config): void { // can change provider availability while this fiber remains active. let disposeTool: (() => void) | undefined const mount = (provider: SubagentProvider): void => { + // A numeric cap the provider cannot enforce is a misconfiguration — fail at + // mount (the earliest point the provider's capabilities are known), not on + // the first delegation. + if (typeof config.maxDepth === 'number' && !provider.capabilities.depthLimit) { + throw new Error( + `tool-subagent: provider "${provider.name}" cannot enforce maxDepth (no depthLimit capability) — ` + + 'set maxDepth: \'provider-managed\' to leave the recursion budget to the provider', + ) + } + // Schema hiding rides the child toolFilter, so it needs that capability; + // without it the depth check at start remains the only fence. + const hideAtCapToolName = provider.capabilities.toolFilter ? config.toolName ?? 'subagent' : undefined const wording = providerWording(provider.inheritsParentContext) const backgroundEnabled = config.enableRunInBackground !== false disposeTool = ctx.tools.register(defineTool({ @@ -282,7 +314,7 @@ export function apply(ctx: Context, config: Config): void { const controller = new AbortController() const start = ctx.subagents.start( config.provider, - startRequest(config, args.prompt, parent, controller.signal), + startRequest(config, args.prompt, parent, controller.signal, hideAtCapToolName), ) return { cancel: (reason?: string) => { @@ -301,6 +333,7 @@ export function apply(ctx: Context, config: Config): void { args.prompt, parent, exec.signal ?? new AbortController().signal, + hideAtCapToolName, ) const run: SubagentRun = await ctx.subagents.start(config.provider, request) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index d88367ced5..f827d6d2ba 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -7,6 +7,7 @@ import ToolRegistry from '@deepseek-ai/dsh-tools' import { type Agent } from '@deepseek-ai/dsh-agent' import AgentRegistry from '@deepseek-ai/dsh-agent' import SubagentService from '@deepseek-ai/dsh-subagent' +import type { SubagentStartRequest } from '@deepseek-ai/dsh-subagent' import TaskService from '@deepseek-ai/dsh-tasks' import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks' import * as mock from './scripted-provider.ts' @@ -22,9 +23,13 @@ import { SessionId } from '@deepseek-ai/dsh-session' * shipping code path. */ -/** A minimal parent Agent — the tool reads `agent.id` for `parent`. */ -function fakeAgent(id = 'parent-1'): Agent { - return { id: SessionId(id) } as unknown as Agent +/** A minimal parent Agent: the tool reads `agent.id` plus the delegation depth off its header/options. */ +function fakeAgent(id = 'parent-1', delegationDepth?: number): Agent { + return { + id: SessionId(id), + options: {}, + session: { header: { ...delegationDepth === undefined ? {} : { delegationDepth } } }, + } as unknown as Agent } async function setup(toolConfig: tool.Config, mockConfig: Partial = {}) { @@ -85,7 +90,7 @@ describe('dsh-tool-subagent', () => { // Schema omission is advertising, not enforcement: the arg validator // allows undeclared keys, so the opt-out must also hold in execute(). const ctx = await setup({ provider: 'mock', enableRunInBackground: false }) - const parent = { id: SessionId('sess-off'), inject: () => {}, session: { header: { version: 0, id: 'sess-off', createdAt: 0 } } } as unknown as Agent + const parent = { id: SessionId('sess-off'), inject: () => {}, options: {}, session: { header: { version: 0, id: 'sess-off', createdAt: 0 } } } as unknown as Agent const forced = await callSubagent(ctx, { description: 'd', prompt: 'p', run_in_background: true }, { agent: parent }) expect(forced.isError).toBe(true) @@ -162,7 +167,7 @@ describe('dsh-tool-subagent', () => { dispose: async () => {}, }), }) - await ctx.plugin(tool, { provider: 'weird' }) + await ctx.plugin(tool, { provider: 'weird', maxDepth: 'provider-managed' }) const result = await callSubagent(ctx, { description: 'd', prompt: 'p' }) expect(result.isError).toBe(true) @@ -191,7 +196,7 @@ describe('dsh-tool-subagent', () => { } }, }) - await ctx.plugin(tool, { provider: 'capture', agentOptions: { model: 'child-model' } }) + await ctx.plugin(tool, { provider: 'capture', agentOptions: { model: 'child-model' }, maxDepth: 'provider-managed' }) await callSubagent(ctx, { description: 'd', prompt: 'p' }) expect(seen?.agentOptions).toEqual({ model: 'child-model' }) @@ -348,7 +353,7 @@ describe('dsh-tool-subagent', () => { dispose: async () => void disposed(), }), }) - await ctx.plugin(tool, { provider: 'spy' }) + await ctx.plugin(tool, { provider: 'spy', maxDepth: 'provider-managed' }) await callSubagent(ctx, { description: 'd', prompt: 'p' }) expect(disposed).toHaveBeenCalledTimes(1) @@ -371,7 +376,7 @@ describe('dsh-tool-subagent', () => { dispose: async () => void disposed(), }), }) - await ctx.plugin(tool, { provider: 'spy' }) + await ctx.plugin(tool, { provider: 'spy', maxDepth: 'provider-managed' }) const result = await callSubagent(ctx, { description: 'd', prompt: 'p' }) expect(result.isError).toBe(true) @@ -404,7 +409,7 @@ describe('dsh-tool-subagent', () => { } }, }) - await ctx.plugin(tool, { provider: 'spy' }) + await ctx.plugin(tool, { provider: 'spy', maxDepth: 'provider-managed' }) const controller = new AbortController() const pending = callSubagent(ctx, { description: 'd', prompt: 'p' }, { signal: controller.signal }) @@ -432,7 +437,7 @@ describe('dsh-tool-subagent', () => { throw new Error('start aborted') }, }) - await ctx.plugin(tool, { provider: 'spy' }) + await ctx.plugin(tool, { provider: 'spy', maxDepth: 'provider-managed' }) const controller = new AbortController() controller.abort() // already aborted BEFORE the tool runs @@ -511,7 +516,6 @@ describe('dsh-tool-subagent', () => { }) it.each([ - { label: 'null', value: null as unknown as number }, { label: 'a string', value: '1' as unknown as number }, { label: 'NaN', value: Number.NaN }, { label: 'positive infinity', value: Number.POSITIVE_INFINITY }, @@ -555,7 +559,7 @@ describe('dsh-tool-subagent', () => { } }, }) - await ctx.plugin(tool, { provider: 'capture3', toolFilter: { deny: ['subagent'] } }) + await ctx.plugin(tool, { provider: 'capture3', toolFilter: { deny: ['subagent'] }, maxDepth: 'provider-managed' }) await callSubagent(ctx, { description: 'd', prompt: 'p' }) expect(seen?.toolFilter).toEqual({ deny: ['subagent'] }) expect(seen?.toolFilter).not.toHaveProperty('allow') @@ -585,7 +589,7 @@ describe('dsh-tool-subagent', () => { } }, }) - await ctx.plugin(tool, { provider: 'capture4' }) + await ctx.plugin(tool, { provider: 'capture4', maxDepth: 'provider-managed' }) await callSubagent(ctx, { description: 'd', prompt: 'p' }) expect(seen).toBeDefined() expect(seen).not.toHaveProperty('agentOptions') @@ -616,6 +620,7 @@ describe('dsh-tool-subagent background mode', () => { id, ctx: scopeFiber.ctx, inject, + options: {}, session: { id, header: { version: 0, id, createdAt: 0 } }, } as unknown as Agent ctx.agents.register(agent) @@ -846,6 +851,7 @@ describe('background preflight failure (no orphaned child, by construction)', () id, ctx: scopeFiber.ctx, inject: () => {}, + options: {}, session: { id, header: { version: 0, id, createdAt: 0 } }, } as unknown as Agent ctx.agents.register(parent) @@ -879,3 +885,107 @@ describe('background preflight failure (no orphaned child, by construction)', () expect(starts).toBe(0) }) }) + +describe('depth budget defaults and schema hiding', () => { + /** Mount the tool over a request-capturing provider with full capabilities. */ + async function captureSetup(config: Omit = {}) { + const requests: SubagentStartRequest[] = [] + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(SubagentService) + ctx.subagents.registerProvider({ + name: 'capture', + capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: true }, + inheritsParentContext: false, + start: async (request) => { + requests.push(request) + return { + id: SessionId(`capture-child-${requests.length}`), + localAgent: undefined, + result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), + dispose: async () => {}, + } + }, + }) + await ctx.plugin(tool, { provider: 'capture', ...config }) + return { ctx, requests } + } + + it('defaults maxDepth to 1 and forwards it in the start request', async () => { + const { ctx, requests } = await captureSetup() + await callSubagent(ctx, { description: 'd', prompt: 'p' }) + expect(requests[0]?.maxDepth).toBe(1) + }) + + it('denies its own toolName to a child at the depth cap', async () => { + // The child of a depth-0 parent under maxDepth 1 sits AT the cap: any + // delegation it attempted would be rejected, so the tool must not appear in + // its schema at all (prompt-face hiding; the service still rejects). + const { ctx, requests } = await captureSetup() + await callSubagent(ctx, { description: 'd', prompt: 'p' }) + expect(requests[0]?.toolFilter?.deny).toContain('subagent') + }) + + it('merges the cap denial into a configured tool filter', async () => { + const { ctx, requests } = await captureSetup({ toolFilter: { deny: ['dangerous'] } }) + await callSubagent(ctx, { description: 'd', prompt: 'p' }) + expect(requests[0]?.toolFilter?.deny).toEqual(expect.arrayContaining(['dangerous', 'subagent'])) + }) + + it('keeps the tool visible for a child below the cap', async () => { + const { ctx, requests } = await captureSetup({ maxDepth: 2 }) + await callSubagent(ctx, { description: 'd', prompt: 'p' }) + expect(requests[0]?.maxDepth).toBe(2) + expect(requests[0]?.toolFilter?.deny ?? []).not.toContain('subagent') + }) + + it('counts the parent by its persisted header depth when hiding', async () => { + // A resumed depth-1 parent under maxDepth 2: its child is AT the cap and + // must lose the tool even though the parent's runtime options carry no depth. + const { ctx, requests } = await captureSetup({ maxDepth: 2 }) + await callSubagent(ctx, { description: 'd', prompt: 'p' }, { agent: fakeAgent('resumed-parent', 1) }) + expect(requests[0]?.toolFilter?.deny).toContain('subagent') + }) + + it('rejects a numeric maxDepth on a provider without the depthLimit capability at mount', async () => { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(SubagentService) + ctx.subagents.registerProvider({ + name: 'no-depth', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: async () => { throw new Error('unreachable') }, + }) + await expect(ctx.plugin(tool, { provider: 'no-depth' })) + .rejects.toThrow(/provider-managed/) + }) + + it("'provider-managed' omits the cap so a capability-less provider mounts and starts", async () => { + const requests: SubagentStartRequest[] = [] + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + await ctx.plugin(SubagentService) + ctx.subagents.registerProvider({ + name: 'external', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: async (request) => { + requests.push(request) + return { + id: SessionId('external-child'), + localAgent: undefined, + result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), + dispose: async () => {}, + } + }, + }) + await ctx.plugin(tool, { provider: 'external', maxDepth: 'provider-managed' }) + await callSubagent(ctx, { description: 'd', prompt: 'p' }) + expect(requests[0]?.maxDepth).toBeUndefined() + expect(requests[0]?.toolFilter).toBeUndefined() + }) +}) diff --git a/packages/support/acp-snapshot/src/suite.ts b/packages/support/acp-snapshot/src/suite.ts index 938676e4b7..c5eaff1e0b 100644 --- a/packages/support/acp-snapshot/src/suite.ts +++ b/packages/support/acp-snapshot/src/suite.ts @@ -100,6 +100,18 @@ export interface Scenario { * {@link headerClass}. */ configPath?: string + /** + * Global tool names allowed to be ABSENT from a non-primary (child) session's + * request/header relative to the class pin — the delegation tool a child at + * its depth cap loses to tool-subagent's schema hiding. Each child header is + * compared against the pin minus exactly the declared names it actually + * omitted, so any other divergence (or an undeclared omission) still fails. + * A child that omitted a declared tool also skips the text-level initial + * system prompt pin: the prompt embeds the toolset (Code Mode SDK sections), + * so a reduced child cannot equal the full-composition golden — the + * structural header assertion remains its pin. Meaningless on the primary log. + */ + childToolOmissions?: string[] } /** One suite's inputs: the agent to boot, where its fixtures live, and its scenario table. */ @@ -282,6 +294,36 @@ export function restorePinnedToolSchemas(header: unknown, schemas: readonly unkn return { ...header, tools: schemas } } +/** + * The pinned header with exactly the DECLARED omissions a child actually made + * removed from its tool list. A child at its depth cap legitimately lacks the + * delegation tool that spawned it (tool-subagent schema hiding); removing only + * declared-AND-actually-absent names keeps every other divergence — including + * an undeclared omission — a loud mismatch. + * @param pinned The class-pinned full header (tool schemas restored). + * @param actual The child session's normalized header under comparison. + * @param allowed The scenario's declared {@link Scenario.childToolOmissions}. + * @returns The expected header for this child log. + */ +export function applyChildToolOmissions(pinned: unknown, actual: unknown, allowed: readonly string[]): unknown { + if (pinned === null || typeof pinned !== 'object' || Array.isArray(pinned)) { + throw new Error('acp-snapshot: pinned request header must be an object') + } + const toolNames = (header: unknown): Set => { + const tools = (header as { tools?: unknown }).tools + return new Set(Array.isArray(tools) + ? tools.map(tool => (tool as { name?: unknown }).name).filter((name): name is string => typeof name === 'string') + : []) + } + const actualNames = toolNames(actual) + const pinnedTools = (pinned as { tools?: unknown[] }).tools ?? [] + const tools = pinnedTools.filter((tool) => { + const name = (tool as { name?: unknown }).name + return !(typeof name === 'string' && allowed.includes(name) && !actualNames.has(name)) + }) + return { ...pinned, tools } +} + /** * Render a normalized prompt as a repository-friendly Markdown snapshot. * Prompt text is unchanged except that a missing terminal newline is added so @@ -625,9 +667,20 @@ export function defineAcpSnapshotSuite(options: SnapshotSuiteOptions): void { .toBe(headers.length) for (const [k, header] of headers.entries()) { const expected = expectedChanges > 0 ? pinnedHeaders[k] : pinnedHeaders[0] + // A child (non-primary) log may omit declared delegation tools — + // schema hiding at the depth cap; see Scenario.childToolOmissions. + const childOmissions = logIndex === 0 ? [] : scenario.childToolOmissions ?? [] + const target = childOmissions.length === 0 + ? expected + : applyChildToolOmissions(expected, header, childOmissions) expect(header, `session ${log.id}: request/header #${k + 1} diverged from the pinned (${pinningScenario.name}) header`) - .toEqual(expected) - if (expectedChanges === 0) { + .toEqual(target) + // A child that omitted a declared tool cannot equal the text-level + // prompt pin (the prompt embeds the toolset); its header assertion + // above remains the structural pin. + const omittedDeclaredTool = target !== expected + && (target as { tools?: unknown[] }).tools?.length !== (expected as { tools?: unknown[] }).tools?.length + if (expectedChanges === 0 && !omittedDeclaredTool) { expect(formatSystemPromptSnapshot(prompts[k] as string), `session ${log.id}: initial system prompt #${k + 1} diverged from ${pinningScenario.name}/${SYSTEM_PROMPT_SNAPSHOT}`) .toEqual(initialPromptSnapshot) } diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index 92e676b1d6..6d1210c46e 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -16,6 +16,7 @@ import { parseToolSchemasSnapshot, refreshFixtureReplacements, sessionFixtureNames, + applyChildToolOmissions, restorePinnedToolSchemas, stabilizeRefreshLog, unknownToolCallIds, @@ -366,6 +367,37 @@ describe('tool-schema snapshots', () => { }) }) +describe('applyChildToolOmissions', () => { + const pinned = { system: 's', tools: [{ name: 'bash' }, { name: 'subagent' }, { name: 'subagent_fork' }] } + + it('removes exactly the declared tools the child actually omitted', () => { + const actual = { system: 's', tools: [{ name: 'bash' }, { name: 'subagent_fork' }] } + expect(applyChildToolOmissions(pinned, actual, ['subagent', 'subagent_fork'])) + .toEqual({ system: 's', tools: [{ name: 'bash' }, { name: 'subagent_fork' }] }) + }) + + it('keeps a declared tool the child still carries and an undeclared omission', () => { + // The child omitted `bash` (undeclared) — the expectation keeps it, so the + // equality assertion downstream still fails loudly on the real divergence. + const actual = { system: 's', tools: [{ name: 'subagent' }, { name: 'subagent_fork' }] } + expect(applyChildToolOmissions(pinned, actual, ['subagent'])) + .toEqual(pinned) + }) + + it('tolerates a headerless tool list and unnamed tool entries', () => { + expect(applyChildToolOmissions({ system: 's' }, { tools: 'not-an-array' }, ['subagent'])) + .toEqual({ system: 's', tools: [] }) + const unnamed = { system: 's', tools: [{ name: 42 }] } + expect(applyChildToolOmissions(unnamed, { tools: [] }, ['subagent'])).toEqual(unnamed) + }) + + it('rejects a non-object pinned header', () => { + expect(() => applyChildToolOmissions(null, {}, [])).toThrow(/must be an object/) + expect(() => applyChildToolOmissions([], {}, [])).toThrow(/must be an object/) + expect(() => applyChildToolOmissions('x', {}, [])).toThrow(/must be an object/) + }) +}) + describe('unknownToolCallIds', () => { it('returns structured UNKNOWN_TOOL call ids and ignores other results', () => { const log = [ diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 8606d30895..60d3994623 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -39,11 +39,16 @@ import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' const root = resolve(import.meta.dirname, '..') const OUT = 'docs/tool-catalog.md' -/** Register the descriptor needed to mount schema-producing consumers. */ +/** + * Register the descriptor needed to mount schema-producing consumers. Declares + * the full capability set of the shipped in-process providers so consumers + * mount under their shipped defaults (tool-subagent's default numeric maxDepth + * requires `depthLimit`). + */ function registerCatalogSubagentProvider(ctx: Context, name: string): void { const provider: SubagentProvider = { name, - capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + capabilities: { outputSchema: true, depthLimit: true, toolFilter: true, persona: true }, inheritsParentContext: false, start: () => Promise.reject(new Error('tool-catalog provider cannot start a child')), } From d231f3002434325f2b84d5cef57e41cd801b5e14 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Sun, 19 Jul 2026 17:34:10 +0800 Subject: [PATCH 262/323] test(acp-snapshot): cover the child-omission branches synthetically The childToolOmissions comparison arms ran only through the examples snapshot suites, which the unit coverage gate does not count. Add an authored child-omission scenario to the synthetic replay suite: one scripted child omits the declared tool (header pin minus the omission, prompt pin skipped), one keeps the full set (pin and prompt compared verbatim), restoring 100% branch coverage on suite.ts. --- .../suite/child-omission/behavior.json | 116 ++++++++++++++++++ .../fixtures/suite/child-omission/input.json | 1 + .../suite/child-omission/session.1.jsonl | 2 + .../suite/child-omission/session.2.jsonl | 2 + .../suite/child-omission/session.jsonl | 3 + .../suite/child-omission/stdout.golden.jsonl | 5 + .../suite/child-omission/workspace/seed.txt | 1 + .../support/acp-snapshot/tests/suite.spec.ts | 4 + 8 files changed, 134 insertions(+) create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/child-omission/behavior.json create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/child-omission/input.json create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.1.jsonl create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.2.jsonl create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.jsonl create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/child-omission/stdout.golden.jsonl create mode 100644 packages/support/acp-snapshot/tests/fixtures/suite/child-omission/workspace/seed.txt diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/behavior.json b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/behavior.json new file mode 100644 index 0000000000..b8624d4673 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/behavior.json @@ -0,0 +1,116 @@ +{ + "prompt": "respond", + "echoWorkspace": true, + "logs": [ + { + "file": "b/parent.jsonl", + "lines": [ + { + "type": "session", + "id": "{{SID}}", + "createdAt": 200, + "cwd": "{{CWD}}" + }, + { + "type": "request/header", + "seq": 0, + "time": 5, + "data": { + "header": { + "config": { + "model": "fake" + }, + "system": "SYS PROMPT", + "tools": [ + { + "name": "t1", + "description": "D1", + "parameters": { + "type": "object" + } + } + ] + }, + "reason": "initial" + } + }, + { + "type": "assistant/chunk", + "seq": 1, + "time": 5, + "data": { + "turn": 1, + "step": 1, + "chunk": { + "type": "text-delta", + "index": 0, + "text": "hi" + } + } + } + ] + }, + { + "file": "b/child1.jsonl", + "lines": [ + { + "type": "session", + "id": "eeeeeeee-1111-4222-8333-444444444444", + "createdAt": 300, + "cwd": "{{CWD}}", + "parentSession": "{{SID}}" + }, + { + "type": "request/header", + "seq": 0, + "time": 6, + "data": { + "header": { + "config": { + "model": "fake" + }, + "system": "SYS PROMPT", + "tools": [] + }, + "reason": "initial" + } + } + ] + }, + { + "file": "b/child2.jsonl", + "lines": [ + { + "type": "session", + "id": "ffffffff-2222-4333-8444-555555555555", + "createdAt": 400, + "cwd": "{{CWD}}", + "parentSession": "{{SID}}" + }, + { + "type": "request/header", + "seq": 0, + "time": 6, + "data": { + "header": { + "config": { + "model": "fake" + }, + "system": "SYS PROMPT", + "tools": [ + { + "name": "t1", + "description": "D1", + "parameters": { + "type": "object" + } + } + ] + }, + "reason": "initial" + } + } + ] + } + ] +} diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/input.json b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/input.json new file mode 100644 index 0000000000..60b9e363b5 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/input.json @@ -0,0 +1 @@ +{ "steps": [{ "op": "initialize" }, { "op": "newSession" }, { "op": "prompt", "text": "plain" }] } diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.1.jsonl b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.1.jsonl new file mode 100644 index 0000000000..a844f891fc --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.1.jsonl @@ -0,0 +1,2 @@ +{"type":"session","id":"eeeeeeee-1111-4222-8333-444444444444","createdAt":12,"cwd":"/rec/plain-cwd","parentSession":"56565656-7878-4989-8a9a-9b9b9b9b9b9b"} +{"type":"request/header","seq":0,"time":12,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.2.jsonl b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.2.jsonl new file mode 100644 index 0000000000..c3bd629ad7 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.2.jsonl @@ -0,0 +1,2 @@ +{"type":"session","id":"ffffffff-2222-4333-8444-555555555555","createdAt":13,"cwd":"/rec/plain-cwd","parentSession":"56565656-7878-4989-8a9a-9b9b9b9b9b9b"} +{"type":"request/header","seq":0,"time":12,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.jsonl b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.jsonl new file mode 100644 index 0000000000..744998f959 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/session.jsonl @@ -0,0 +1,3 @@ +{"type":"session","id":"56565656-7878-4989-8a9a-9b9b9b9b9b9b","createdAt":11,"cwd":"/rec/plain-cwd"} +{"type":"request/header","seq":0,"time":11,"data":{"header":{"config":{"model":"fake"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":1,"time":11,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"hi"}}} diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/stdout.golden.jsonl b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/stdout.golden.jsonl new file mode 100644 index 0000000000..d0242ae39f --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/stdout.golden.jsonl @@ -0,0 +1,5 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentCapabilities":{"loadSession":false}}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"thinking about it"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"workspace:seed.txt"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/workspace/seed.txt b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/workspace/seed.txt new file mode 100644 index 0000000000..c19e887d68 --- /dev/null +++ b/packages/support/acp-snapshot/tests/fixtures/suite/child-omission/workspace/seed.txt @@ -0,0 +1 @@ +seeded diff --git a/packages/support/acp-snapshot/tests/suite.spec.ts b/packages/support/acp-snapshot/tests/suite.spec.ts index 6d1210c46e..5bf90e0212 100644 --- a/packages/support/acp-snapshot/tests/suite.spec.ts +++ b/packages/support/acp-snapshot/tests/suite.spec.ts @@ -48,6 +48,10 @@ const RECORD_SRC = fileURLToPath(new URL('./fixtures/record-suite', import.meta. const REPLAY_SCENARIOS: Scenario[] = [ { name: 'pin-turn', hasModelTurn: true, recorded: true, pinsHeader: true, expectedHeaderChanges: 1, headerClass: 'main' }, { name: 'plain-turn', hasModelTurn: true, recorded: true, headerClass: 'main', configPath: AGENT.configPath }, + // Two scripted children under a declared omission: one omits t1 (header pin + // minus the declared tool, prompt pin skipped), one keeps the full set (pin + // and prompt compared verbatim) — the childToolOmissions branches. + { name: 'child-omission', hasModelTurn: true, recorded: false, headerClass: 'main', childToolOmissions: ['t1'] }, { name: 'no-model', hasModelTurn: false, recorded: false, headerClass: 'main' }, { name: 'blocked-log', hasModelTurn: false, comparesLog: true, recorded: false, headerClass: 'main' }, { name: 'authored-error', hasModelTurn: true, recorded: false, overridden: true, headerClass: 'main' }, From 4ab5a76317f6763e682f7525d913e08fb205fdd4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 17:35:43 +0800 Subject: [PATCH 263/323] docs(agents): promote review principles --- .agents/skills/dsh-code-review/SKILL.md | 20 ++++++++++---------- AGENTS.md | 6 +++--- docs/AGENTS.md | 2 +- packages/AGENTS.md | 8 ++++++++ scripts/doc-budgets.manifest.json | 6 +++--- 5 files changed, 25 insertions(+), 17 deletions(-) diff --git a/.agents/skills/dsh-code-review/SKILL.md b/.agents/skills/dsh-code-review/SKILL.md index ca42b97323..cabc6211ff 100644 --- a/.agents/skills/dsh-code-review/SKILL.md +++ b/.agents/skills/dsh-code-review/SKILL.md @@ -9,7 +9,7 @@ description: Use when reviewing a pull request in the deepseek-harness repo — ## Sources of truth -- [AGENTS.md](../../../AGENTS.md) and [packages/AGENTS.md](../../../packages/AGENTS.md): repository and package rules. +- [AGENTS.md](../../../AGENTS.md) and [packages/AGENTS.md](../../../packages/AGENTS.md): standing repository and package authoring contracts. - [docs/defensive-patterns.md](../../../docs/defensive-patterns.md): subprocess, callback, async-state, and disposal bug classes. - [docs/AGENTS.md](../../../docs/AGENTS.md): documentation placement and prose discipline. - [dsh-prose-standard](../dsh-prose-standard/SKILL.md): required coverage and editorial judgment for comments, docs, prompts, and visible strings. @@ -22,23 +22,23 @@ description: Use when reviewing a pull request in the deepseek-harness repo — 1. **New prose receives semantic review.** Use [dsh-prose-standard](../dsh-prose-standard/SKILL.md) to critically review every added or changed Markdown passage, JSDoc, comment, prompt, description, diagnostic, and visible string. Verify required coverage, accuracy, placement, and editorial quality against the owning code or behavior; automated checks do not establish those properties. 2. **Docs match the code.** Config, defaults, errors, wire fields, events, and public behavior update the package README and JSDoc in the same diff. Comments state non-obvious contracts; flag implementation narration, test walkthroughs, review history, and duplicated rationale for deletion or a link to their one home. 3. **Core type docs match.** Changes to spine or seam vocabulary update the appropriate [core-data-structures](../../../docs/core-data-structures/core.md) page and any `type-equiv` entry. Internal types need no catalog entry. -4. **Registrations clean up.** A new registry contribution has a test that disposes its owner and observes removal. +4. **Registrations clean up.** Verify each new registry contribution satisfies the disposal-test contract in [packages/AGENTS.md](../../../packages/AGENTS.md). 5. **Required gates pass.** Trust the [current readiness sequence](../../../AGENTS.md#run-the-ci-gates-locally-before-marking-a-pr-ready) and `pnpm run check:pre-push` for their enforced inventory; review the semantic gaps they cannot detect. ## Manual checks - **Intent and seam contracts:** trace both sides of every changed interface. Confirm the implementation matches the PR and any RFC, including errors, cancellation, ownership, and disposal. - **Lifecycle and concurrency:** for async setup, callbacks, processes, or teardown, apply [defensive-patterns.md](../../../docs/defensive-patterns.md). Check races before publication, cancellation during awaits, independent error reporting, callback containment, ownership before reentry, complete detach cleanup, and quiescent disposal. -- **Capability and consumer fit:** a swappable capability follows the interface / implementation / consumer split. Shape the interface for all current consumers, not one tool schema, loader, UI, transport, or backend; keep consumer-specific behavior in the consumer or adapter. -- **Scope, ownership, and necessity:** tie each abstraction, state machine, option, defensive copy, and compatibility path to a current contract or production consumer. Challenge unrelated features, speculative generality, and behavior placed outside its owning plugin or service. Review whether the PR is one coherent change; move an independently meaningful feature or design decision into a separate or stacked PR when combining it obscures ownership, intent, or verification. -- **Configuration and public choices:** deployment-varying tunables are validated `Config` fields. Do not invent a default, public operation set, format, or borrowed external concept merely because it can be configurable; require evidence from a current consumer or relevant prior art, otherwise keep the choice explicit or defer it. -- **Model perspective:** inspect the exact prompts, tool schemas, results, and diagnostics the model receives across affected modes. Flag UI, transport, or implementation concepts irrelevant to the model's task. Verify stable model-visible text verbatim and dynamic behavior through snapshots or end-to-end coverage. -- **Enforcement boundaries:** hidden schema fields, filtered prompts, facades, wrappers, and listener ordering are not authoritative enforcement when direct or alternate callers can bypass them. Exercise denial paths at the boundary that actually executes the operation. -- **Borrowed and derived state:** determine whether retained caller-owned values are borrowed or snapshotted by contract; do not demand copies at typed same-process seams. Materialize mutable values that cross queues, model/tool JSON, durable logs or files, workers, processes, or wire boundaries. Commit notifications and derived state only at the documented success boundary, and trace caches, prompts, UI echoes, replay, and query views to one authoritative source. -- **Bounds cover the final operation:** verify byte, token, item, and time limits at the boundary that owns the complete emitted or retained result, including wrappers and metadata. Probe tiny limits, exact thresholds, oversized single chunks, and multibyte text for byte limits. +- **Capability and consumer fit:** trace every current consumer, then flag consumer-specific behavior leaking into the interface under [the package contract](../../../packages/AGENTS.md). +- **Scope, ownership, and necessity:** map each abstraction, state machine, option, defensive copy, and compatibility path to its current contract, production consumer, and owning plugin or service. Challenge unrelated features and speculative generality, then test the PR's coherence against [the root contract](../../../AGENTS.md#conventions). +- **Configuration and public choices:** ask what current-consumer evidence or prior art supports each default, public operation set, format, or imported external concept. Require an explicit choice or deferral when that evidence is absent. +- **Model perspective:** inspect the exact prompts, tool schemas, results, and diagnostics the model receives across affected modes. Flag concepts outside the model's task, then verify stable text verbatim and dynamic behavior through snapshots or end-to-end coverage. +- **Enforcement boundaries:** follow every denial path to the operation that executes it; exercise direct and alternate callers that can bypass schemas, prompts, facades, wrappers, or listener ordering. +- **Borrowed and derived state:** classify each retained value under the package boundary contract, then trace notifications and every cache, prompt, UI echo, replay, and query view to the documented success point and authoritative source. +- **Bounds cover the final operation:** locate the owner of the complete emitted or retained result, including wrappers and metadata. Probe tiny and exact limits, oversized single chunks, and multibyte text for byte limits. - **Real entry path:** tests exercise the shipped Loader, bin, worker, ACP bridge, or subprocess where relevant. A hand-mounted plugin does not catch Loader export-shape failures; a function plugin must named-export its namespace and have no default export. - **Test strength:** assertions fail on the intended regression and verify external state, logs, events, or disposal rather than restating the implementation or trusting an agent's report. Coverage is necessary but not evidence that the scenario is correct. -- **Mechanized invariants and negative controls:** when a repeatable invariant is mechanically checkable, require it to be wired into an executed top-level gate. A new check, or a changed acceptance path in one, also needs a deliberately invalid case that reaches the real runner and fails for the intended rule. +- **Mechanized invariants and negative controls:** trace each new or changed check through the executed top-level gate and its deliberately invalid case; confirm the real runner fails for the intended rule. - **Implemented RFCs match shipped reality:** when a PR implements a proposed RFC, move and rewrite it as present-tense shipped state in the same diff, then verify paths, names, and mechanisms against the implementation. - **Transcript changes:** editor-visible or model-visible changes update snapshots or explain why no snapshot applies. Review golden diffs as behavior changes, not formatting noise. - **Bilingual changes:** compare meaning and terminology on both sides; a green pairing hash does not prove translation quality. diff --git a/AGENTS.md b/AGENTS.md index efaa29bbac..27b5a655e2 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -110,7 +110,7 @@ Real-API tests and demos read `DEEPSEEK_API_KEY`, optional `DEEPSEEK_BASE_URL`, - **Plugins, not loop changes**: new behavior goes on the documented extension seams; changing `agent-loop` requires updating docs/architecture.md. - **Capability seams are three packages** — interface / implementation / consumer; don't split preemptively. - **Explicit > implicit at package seams**: defaulting is an explicit `resolve(request): Spec` step in the owning implementation, never a hidden `?? default` inside `run()` (the `dsh-bash` request/spec split is the template). -- **No hardcoded tunables in plugins**: deployment choices are defaulted, validated `Config` fields changeable from cordis.yml; a `DEFAULT_*` constant or test seam is not configurability. Protocol constants, external specs, and security invariants stay fixed. +- **No hardcoded tunables in plugins**: deployment-varying choices are validated `Config` fields changeable from cordis.yml; a `DEFAULT_*` constant or test seam is not configurability. Protocol constants, external specs, and security invariants stay fixed. - **Misconfiguration fails loud** at load when self-contained, otherwise at the earliest resolvable point; never silently skip a missing referent. - **Opaque cross-boundary ids are branded** (`Branded` from `dsh-brand`), never bare `string`. - **An empty `catch` names what it swallows** and why nothing else can reach it; keep the `try` to one statement. @@ -120,7 +120,7 @@ Real-API tests and demos read `DEEPSEEK_API_KEY`, optional `DEEPSEEK_BASE_URL`, - **Testing policy** — [docs/testing.md](docs/testing.md). Transcript changes need snapshots or a PR note. Fixtures must replay on macOS/Linux; fix fixtures, not normalizers. - **A tool's ACP render intent is part of its design**, decided up front (`generic`/`terminal`/`diff`, `locations`); presentation methods are pure functions of `args` ([cookbook](docs/cookbook/adding-a-tool.md)). - **Plan unit, e2e, and snapshot coverage** for new seams, lifecycle shapes, and transcript surfaces, and schedule any missing harness support before implementation. -- **Merge PRs with merge commits**, never squash/rebase or rewrite pushed branches. Put a review fix on its introducing PR, then merge down the stack ([guide](docs/cookbook/responding-to-pr-review-on-a-stack.md)). +- **Keep PRs coherent and merge with merge commits.** Split an independently meaningful feature or design decision into a separate or stacked PR when combining it obscures ownership, intent, or verification. Never squash/rebase or rewrite pushed branches; put a review fix on its introducing PR, then merge down the stack ([guide](docs/cookbook/responding-to-pr-review-on-a-stack.md)). - TODO markers: `FIXME`/`TODO`/`XXX` by urgency ([semantics](docs/development.md)). - Files end with exactly one trailing newline; `git diff --check` (pre-push) gates it. @@ -132,7 +132,7 @@ Read [docs/defensive-patterns.md](docs/defensive-patterns.md) before lifecycle, Everything compiles under `strict: true` with `noImplicitAny`; every remaining `any` explains why a narrower type is infeasible. Every module and export has concise JSDoc for its non-obvious contract; function-like exports include `@param`/`@returns`, as enforced by `verify-export-jsdoc`. Heritage-declared members, plugin-protocol slots, and constructors keep their docs at the declaring seam, protocol, or class. -Comments and docs preserve complete contracts and non-obvious orientation, not reasoning transcripts. Do not narrate control flow or tests, preserve review history, or restate code. Keep factual clauses affecting behavior, failure, timing, ownership, or safe use; link aggressively to owning rationale. Use [dsh-prose-standard](.agents/skills/dsh-prose-standard/SKILL.md) for prose decisions. Encode enforceable invariants in checks, using narrow justified exceptions rather than disabling a rule globally. +Comments and docs preserve complete contracts and non-obvious orientation, not reasoning transcripts. Do not narrate control flow or tests, preserve review history, or restate code. Keep factual clauses affecting behavior, failure, timing, ownership, or safe use; link aggressively to owning rationale. Use [dsh-prose-standard](.agents/skills/dsh-prose-standard/SKILL.md) for prose decisions. Wire mechanically checkable invariants into an executed top-level gate and prove each new or changed acceptance path rejects an invalid case. Use narrow justified exceptions instead of disabling a rule globally. Docs are part of every change: code changes update their README and JSDoc in the SAME change; a bilingual-pair edit updates the counterpart and re-records ([i18n contract](docs/i18n/README.md)). The writing rules — document the current state never the history, one physical line per paragraph, one home per fact — and the word-budget gate live in [docs/AGENTS.md](docs/AGENTS.md). diff --git a/docs/AGENTS.md b/docs/AGENTS.md index f7635c659b..a0c30c5545 100644 --- a/docs/AGENTS.md +++ b/docs/AGENTS.md @@ -43,7 +43,7 @@ When the gate goes red: 2. **Condense** content that belongs here but can be shorter. 3. **Raise** the ceiling only when the words truly need the space; justify the manifest diff in the PR. A too-low ceiling is a budget bug. -Ceilings are guardrails, not reduction targets. Retain at least 5% headroom; lower a ceiling only when the document's durable contract still has room, and raise it when necessary content would otherwise be deleted. Targets: root `AGENTS.md` ≤ 1,500 words; `architecture.md` ≤ 1,800; each subtree `AGENTS.md` ≤ 600, except this file ≤ 1,250; `packages/README.md` ≤ 600. Review and the slop checklist govern unbudgeted tiers. +Ceilings are guardrails, not reduction targets. Retain at least 5% headroom; lower a ceiling only when the document's durable contract still has room, and raise it when necessary content would otherwise be deleted. Targets: root `AGENTS.md` ≤ 1,600 words; `architecture.md` ≤ 1,800; each subtree `AGENTS.md` ≤ 600, except `packages/AGENTS.md` ≤ 650 and this file ≤ 1,250; `packages/README.md` ≤ 600. Review and the slop checklist govern unbudgeted tiers. ## The slop checklist diff --git a/packages/AGENTS.md b/packages/AGENTS.md index 9ab0327cf9..e4b5ded6a3 100644 --- a/packages/AGENTS.md +++ b/packages/AGENTS.md @@ -8,6 +8,14 @@ These package-specific rules supplement the repo-wide [conventions](../AGENTS.md - **Typed same-process service and plugin calls are contracts, not serialization boundaries.** Prefer readonly borrowed values; materialize or defensively validate only at parser/config, queued, model/tool JSON, durable/file, worker, process, or wire boundaries. - **Initiator-owned private chains derive, then capture.** Under `ctx.agents.withInitiator()`, recover the Agent at each orchestration entry, derive `agent.session`, and let operation-local helpers close over it. Keep `Agent` and `Session` explicit at lifecycle, session-log, service, authority, worker/process, persistence, and wire interfaces; do not widen a leaf helper from `Session` to `Context` merely to hide a parameter ([rationale](../docs/rfc/implemented/architecture/2026-07-15-agent-initiator-scope.md)). - **Represent one asynchronous operation with one lifecycle controller or transaction.** Separate readiness, cancellation, disposal, reservation, or sentinel state requires an independent owner or settlement boundary; otherwise fold it while preserving rollback, callback containment, and quiescence. +- **Shape capability interfaces around all current consumers.** Keep tool-schema, Loader, UI, transport, and backend-specific behavior in the consumer or adapter; do not let one consumer dictate the interface ([capability-seam rationale](../docs/rfc/implemented/architecture/2026-06-13-capability-seams.md)). +- **Require a current owner and need.** Tie each abstraction, state machine, option, defensive copy, and compatibility path to a current contract or production consumer, and keep behavior in its owning plugin or service. +- **Require evidence for public choices.** Configurability does not justify an unsupported default, public operation set, format, or imported external concept. Use current-consumer evidence or relevant prior art; otherwise require an explicit value or defer the choice. +- **Write model-facing contracts from the model's perspective.** Prompts, tool schemas, results, and diagnostics contain only task-relevant concepts, not UI, transport, or implementation vocabulary. Pin stable model-visible text verbatim and dynamic behavior through snapshots or end-to-end coverage. +- **Enforce at the operation boundary that owns the decision.** Schema omission, prompt filtering, facades, wrappers, and listener order are not enforcement when direct or alternate callers can bypass them; test denial through the executor. +- **Publish state only at its commit point.** Emit each notification and update derived state only after the success boundary that makes it true; derive caches, prompts, UI echoes, replay, and query views from one authoritative source. +- **Apply bounds to the complete result.** Enforce byte, token, item, and time limits where the complete emitted or retained value, including wrappers and metadata, is known; test tiny and exact limits, oversized single chunks, and multibyte byte limits. +- **Registry contributions prove disposal.** Add the HMR-safety test required by the [testing policy](../docs/testing.md): dispose the contributing fiber and observe removal. Naming notes: diff --git a/scripts/doc-budgets.manifest.json b/scripts/doc-budgets.manifest.json index b4d2bca159..d849248189 100644 --- a/scripts/doc-budgets.manifest.json +++ b/scripts/doc-budgets.manifest.json @@ -1,11 +1,11 @@ { - "AGENTS.md": 1500, - "docs/AGENTS.md": 1100, + "AGENTS.md": 1600, + "docs/AGENTS.md": 1150, "docs/architecture.md": 1790, "docs/cordis-primer.md": 600, "docs/defensive-patterns.md": 550, "docs/testing.md": 960, "examples/AGENTS.md": 310, - "packages/AGENTS.md": 370, + "packages/AGENTS.md": 650, "packages/README.md": 760 } From bcc920369c5db08fdbd5ca0e40fac377955f25bf Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 17:39:50 +0800 Subject: [PATCH 264/323] docs: document package KV cache effects --- docs/cookbook/adding-a-package.i18n.yaml | 4 +- docs/cookbook/adding-a-package.md | 8 ++- docs/cookbook/adding-a-package.zh.md | 8 ++- ...07-12-package-model-experience-contract.md | 14 ++--- packages/AGENTS.md | 2 +- packages/bash/bash-local/README.md | 2 + packages/bash/bash-sandbox/README.md | 6 ++ packages/bash/bash/README.md | 2 + packages/bash/tool-bash/README.md | 10 ++++ .../code-runtime-worker/README.md | 2 + packages/code-runtime/code-runtime/README.md | 2 + packages/compact/compact-basic/README.md | 6 ++ packages/compact/compact/README.md | 4 ++ packages/context/time-context/README.md | 2 + packages/context/workspace-context/README.md | 6 ++ packages/cordis/tool-cordis/README.md | 6 ++ packages/core/agent-loop/README.md | 6 ++ packages/core/agent/README.md | 4 ++ packages/core/session/README.md | 6 ++ packages/core/system-prompt/README.md | 4 ++ packages/core/tools/README.md | 6 ++ packages/examples/acp-demo/README.md | 2 + packages/examples/agent-spine-demo/README.md | 2 + packages/examples/cli-demo/README.md | 2 + packages/examples/jsonrpc-demo/README.md | 2 + packages/examples/stdio-demo/README.md | 4 ++ packages/fs/fs-local/README.md | 2 + packages/fs/fs-policy/README.md | 2 + packages/fs/fs/README.md | 2 + packages/fs/tool-fs-search/README.md | 8 +++ packages/fs/tool-fs/README.md | 10 ++++ packages/guard/repeat-tool-guard/README.md | 4 ++ packages/hooks/hook-protocol/README.md | 2 + packages/hooks/hooks-claude/README.md | 4 ++ packages/hooks/hooks-codex/README.md | 4 ++ packages/llm/llm-deepseek/README.md | 4 ++ packages/llm/llm-pi-ai/README.md | 4 ++ packages/llm/llm/README.md | 2 + packages/llm/token-meter/README.md | 2 + packages/mcp/mcp-client/README.md | 4 ++ packages/sandbox/sandbox-local/README.md | 2 + packages/sandbox/sandbox/README.md | 2 + packages/sdk/create-sdk/README.md | 2 + packages/sdk/helper/README.md | 2 + packages/sdk/scripts/README.md | 2 + .../session-persistence-jsonl/README.md | 2 + .../session-persistence-sqlite/README.md | 2 + .../session-persistence/README.md | 2 + .../session-query/session-query/README.md | 2 + packages/skill/skill-local/README.md | 2 + packages/skill/skill/README.md | 2 + packages/skill/tool-skill/README.md | 8 +++ packages/spill/spill-local/README.md | 2 + packages/spill/spill-policy/README.md | 2 + packages/spill/spill/README.md | 2 + packages/subagent/subagent-acp/README.md | 4 ++ packages/subagent/subagent-fork/README.md | 4 ++ .../subagent/subagent-inprocess/README.md | 8 +++ packages/subagent/subagent-spawn/README.md | 4 ++ .../subagent/subagent-subprocess/README.md | 2 + packages/subagent/subagent/README.md | 2 + packages/subagent/tool-subagent/README.md | 6 ++ packages/support/acp-snapshot/README.md | 2 + packages/support/agent-loop-testkit/README.md | 2 + packages/support/invariants/README.md | 2 + packages/support/llm-replay/README.md | 2 + packages/support/loader-smoke/README.md | 2 + packages/tasks/tasks/README.md | 2 + packages/tasks/tool-tasks/README.md | 6 ++ packages/timeout/timeout-policy/README.md | 2 + packages/todo/tool-todo/README.md | 4 ++ packages/ui/acp/README.md | 10 ++++ packages/ui/app-boot/README.md | 2 + packages/ui/jsonrpc/README.md | 2 + packages/ui/permission/README.md | 2 + packages/ui/stdio/README.md | 4 ++ packages/ui/tool-ask-user/README.md | 4 ++ packages/ui/tui/README.md | 4 ++ packages/ui/user-approval/README.md | 4 ++ packages/ui/user-interaction/README.md | 2 + packages/util/home/README.md | 2 + packages/util/retention/README.md | 2 + packages/util/timeout/README.md | 2 + packages/web/tool-web/README.md | 10 ++++ packages/web/web-fetch-local/README.md | 2 + packages/web/web-search-deepseek/README.md | 4 ++ packages/web/web-search-exa/README.md | 2 + packages/web/web-search-perplexity/README.md | 4 ++ packages/web/web/README.md | 2 + packages/workflow/tool-workflow/README.md | 6 ++ .../workflow/workflow-workerthread/README.md | 4 ++ packages/workflow/workflow/README.md | 2 + .../verify-package-readme-model-experience.ts | 58 +++++++++++++------ 93 files changed, 366 insertions(+), 34 deletions(-) diff --git a/docs/cookbook/adding-a-package.i18n.yaml b/docs/cookbook/adding-a-package.i18n.yaml index 27c31ba1ef..692c7448ca 100644 --- a/docs/cookbook/adding-a-package.i18n.yaml +++ b/docs/cookbook/adding-a-package.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -adding-a-package.md: 2930cee9ab64b382f6211335ae639bce45629d1d -adding-a-package.zh.md: 10e906c320203c3658c103fc8936540f72697d65 +adding-a-package.md: 2e4374caff589199288e67bbca58604231a17966 +adding-a-package.zh.md: 35b5b9a0705dd0b752d68093769a65c339f6b4e3 diff --git a/docs/cookbook/adding-a-package.md b/docs/cookbook/adding-a-package.md index 2930cee9ab..2e4374caff 100644 --- a/docs/cookbook/adding-a-package.md +++ b/docs/cookbook/adding-a-package.md @@ -16,7 +16,7 @@ packages/// src/index.ts # service default export or plugin (name/inject/apply/Config) tests/.spec.ts README.md # service API, events, extension points, design notes, - # + gated Model Experience context blocks or short sentence + # + gated Model Experience context blocks or short form # + the gated "Known Limitations and Deferred Work" section # (or a whitelist entry in scripts/verify-package-readme-limitations.ts) ``` @@ -55,6 +55,8 @@ Keep package-specific service API, config, events, extension points, and design **Token effect**: Fixed, conditional, retained, replaced, capped, or zero-direct token effect. +**KV Cache effect**: Append-only, prefix-stable, replacing, or independent behavior, including the exact conditions that may invalidate reuse. + #### Verbatim text for this context surface, when needed ```markdown @@ -66,9 +68,9 @@ Stable system-prompt prose of any length, or another long non-generated literal, - **Consumer-visible gap** — exact boundary, consequence, or maintainer constraint. ```` -Fill Model Experience from the implementation. Use one H3 per direct, conditional, capped, lifetime, or auxiliary-model surface, with the two fields shown above. Quote stable text owned by the package: system-prompt prose goes in a titled H4 plus `markdown` fence, other short literals stay inline with named placeholders, and other long literals use the same nested form. Summarize only data-dependent or provider-owned text. A tool-schema surface links its anchored section in the generated [tool catalog](../tool-catalog.md) and states only deltas absent there. Keep prompt and schema surfaces separate when scoping can hide one without the other. The [prose standard](../../.agents/skills/dsh-prose-standard/SKILL.md) governs completeness and ownership; the verifier enforces the mechanical shape. +Fill Model Experience from the implementation. Use one H3 per direct, conditional, capped, lifetime, or auxiliary-model surface, with the three fields shown above. Quote stable text owned by the package: system-prompt prose goes in a titled H4 plus `markdown` fence, other short literals stay inline with named placeholders, and other long literals use the same nested form. Summarize only data-dependent or provider-owned text. A tool-schema surface links its anchored section in the generated [tool catalog](../tool-catalog.md) and states only deltas absent there. Keep prompt and schema surfaces separate when scoping can hide one without the other. In `KV Cache effect`, distinguish append-only growth, a stable repeated prefix, replacement of earlier request tokens, and an independent model request, then name the package-owned changes that can invalidate reuse. “Does not invalidate” means the package preserves an already-reusable prefix; provider cache availability and eviction remain outside the package contract. The [prose standard](../../.agents/skills/dsh-prose-standard/SKILL.md) governs completeness and ownership; the verifier enforces the mechanical shape. -A package with no context effect or one consumer-owned path uses the audited `None, as ` or `Indirectly, through ` sentence in [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts); a model-agnostic generic package may instead join `NO_MODEL_EXPERIENCE_SECTION`. Do not expand either case into a description of another package's work. The limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) is independent. The [Model Experience RFC](../rfc/implemented/process/2026-07-12-package-model-experience-contract.md) records the rationale. +A package with no context effect or one consumer-owned path uses the audited `None, as ` or `Indirectly, through ` sentence in [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts), followed by a non-empty `**KV Cache effect**` field; a model-agnostic generic package may instead join `NO_MODEL_EXPERIENCE_SECTION`. Do not expand either case into a description of another package's work. The limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) is independent. The [Model Experience RFC](../rfc/implemented/process/2026-07-12-package-model-experience-contract.md) records the rationale. ## 5. Verify diff --git a/docs/cookbook/adding-a-package.zh.md b/docs/cookbook/adding-a-package.zh.md index 10e906c320..35b5b9a070 100644 --- a/docs/cookbook/adding-a-package.zh.md +++ b/docs/cookbook/adding-a-package.zh.md @@ -16,7 +16,7 @@ packages/// src/index.ts # service default export or plugin (name/inject/apply/Config) tests/.spec.ts README.md # service API, events, extension points, design notes, - # + gated Model Experience context blocks or short sentence + # + gated Model Experience context blocks or short form # + the gated "Known Limitations and Deferred Work" section # (or a whitelist entry in scripts/verify-package-readme-limitations.ts) ``` @@ -55,6 +55,8 @@ package.json 不变式（由 `pnpm run constraints` / `scripts/check-workspace-c **Token effect**: Fixed, conditional, retained, replaced, capped, or zero-direct token effect. +**KV Cache effect**: Append-only, prefix-stable, replacing, or independent behavior, including the exact conditions that may invalidate reuse. + #### Verbatim text for this context surface, when needed ```markdown @@ -66,9 +68,9 @@ Stable system-prompt prose of any length, or another long non-generated literal, - **Consumer-visible gap** — exact boundary, consequence, or maintainer constraint. ```` -根据实现填写 Model Experience。每个直接、条件、上限、生命周期或辅助模型的 surface 使用一个 H3，包含上述两个字段。引用包拥有的稳定文本：系统提示词放在带标题的 H4 加 `markdown` 围栏中，其他短文本以命名占位符内联，其他长文本使用相同的嵌套形式。仅概述数据依赖或提供方拥有的文本。tool-schema surface 链接到生成的[工具目录](../tool-catalog.md)中对应的锚定章节，仅说明该处缺失的差异。当作用域可以隐藏 prompt 或 schema 其中之一而不影响另一个时，将二者分开。[行文标准](../../.agents/skills/dsh-prose-standard/SKILL.md)约束完整性与归属；验证器强制执行机械形状。 +根据实现填写 Model Experience。每个直接、条件、上限、生命周期或辅助模型的 surface 使用一个 H3，包含上述三个字段。引用包拥有的稳定文本：系统提示词放在带标题的 H4 加 `markdown` 围栏中，其他短文本以命名占位符内联，其他长文本使用相同的嵌套形式。仅概述数据依赖或提供方拥有的文本。tool-schema surface 链接到生成的[工具目录](../tool-catalog.md)中对应的锚定章节，仅说明该处缺失的差异。当作用域可以隐藏 prompt 或 schema 其中之一而不影响另一个时，将二者分开。填写 `KV Cache effect` 时，应区分仅追加增长、稳定重复的前缀、替换既有请求 token 和独立模型请求，并列出会使缓存复用失效、且由本包拥有的变化。“不使缓存失效”仅表示本包保留了已有的可复用前缀；缓存是否可用以及何时淘汰不属于本包契约。[行文标准](../../.agents/skills/dsh-prose-standard/SKILL.md)约束完整性与归属；验证器强制执行机械形状。 -没有上下文效果或仅有消费方拥有路径的包使用 [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts) 中经过审计的 `None, as ` 或 `Indirectly, through ` 语句；与模型无关的通用包可以改为加入 `NO_MODEL_EXPERIENCE_SECTION`。两种情况都不要展开为对另一个包工作的描述。limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) 独立管理。[Model Experience RFC](../rfc/implemented/process/2026-07-12-package-model-experience-contract.md) 记录了设计动机。 +没有上下文效果或仅有消费方拥有路径的包使用 [`SENTENCE_MODEL_EXPERIENCE`](../../scripts/verify-package-readme-model-experience.ts) 中经过审计的 `None, as ` 或 `Indirectly, through ` 语句，随后添加非空的 `**KV Cache effect**` 字段；与模型无关的通用包可以改为加入 `NO_MODEL_EXPERIENCE_SECTION`。两种情况都不要展开为对另一个包工作的描述。limitations [allowlist](../../scripts/verify-package-readme-limitations.ts) 独立管理。[Model Experience RFC](../rfc/implemented/process/2026-07-12-package-model-experience-contract.md) 记录了设计动机。 ## 5. 验证 diff --git a/docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md b/docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md index 0f9b0b02a0..5fd5d2b7c2 100644 --- a/docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md +++ b/docs/rfc/implemented/process/2026-07-12-package-model-experience-contract.md @@ -4,28 +4,28 @@ Status: implemented ## Problem -A package README can explain APIs and runtime mechanics without answering the question that dominates an agent harness's behavior and cost: what from this package reaches a model request, under which conditions, and how long those tokens remain. The omission is especially hard to audit in a plugin architecture. A consumer may turn a backend result into a tool message, a policy plugin may replace success with an error, compaction may remove old history, and an agent-scoped registration may change one agent's prompt or schemas while leaving every other agent unchanged. Reading only the nominally model-facing packages therefore misses real context effects, while reading source across every dependency is too expensive for routine review. +A package README can explain APIs and runtime mechanics without answering the questions that dominate an agent harness's behavior and cost: what from this package reaches a model request, under which conditions, how long those tokens remain, and whether later requests preserve a reusable KV-cache prefix. The omission is especially hard to audit in a plugin architecture. A consumer may turn a backend result into a tool message, a policy plugin may replace success with an error, compaction may remove old history, and an agent-scoped registration may change one agent's prompt or schemas while leaving every other agent unchanged. Reading only the nominally model-facing packages therefore misses real context effects, while reading source across every dependency is too expensive for routine review. ## Decision Every workspace package README with a model-facing or model-adjacent contract ends with the canonical [Model Experience section](../../../cookbook/adding-a-package.md#4-write-the-package-readme), immediately before `## Known Limitations and Deferred Work`; a package on the no-limitations allowlist ends with Model Experience itself. An audited model-agnostic generic package omits the section through `NO_MODEL_EXPERIENCE_SECTION`. -Packages with direct, conditional, capped, lifetime, multi-surface, or auxiliary-model effects use one H3 per context surface. Each names what the relevant model receives and when, then classifies the token effect. Stable package-owned text is quoted exactly: system-prompt prose and other long literals use a nested H4 plus `markdown` fence, while short literals stay inline with named interpolation placeholders. Tool-schema surfaces link their anchored section in the generated [tool catalog](../../../tool-catalog.md) and state only composition or configuration deltas; runtime-only definitions explain why the catalog omits them. Data-dependent and provider-owned text is summarized. Agent-scoped visibility is explicit, and prompt and schema surfaces remain separate when scoping can hide one without the other. +Packages with direct, conditional, capped, lifetime, multi-surface, or auxiliary-model effects use one H3 per context surface. Each names what the relevant model receives and when, classifies the token effect, and states the KV-cache effect. The cache field distinguishes append-only growth, a stable repeated prefix, replacement of earlier tokens, and an independent model request; it names every package-owned configuration, scope, lifecycle, compaction, or routing change that can alter the request before newly appended content. “Does not invalidate” means the package preserves an already-reusable prefix, not that a provider promises a cache hit or retention period. Stable package-owned text is quoted exactly: system-prompt prose and other long literals use a nested H4 plus `markdown` fence, while short literals stay inline with named interpolation placeholders. Tool-schema surfaces link their anchored section in the generated [tool catalog](../../../tool-catalog.md) and state only composition or configuration deltas; runtime-only definitions explain why the catalog omits them. Data-dependent and provider-owned text is summarized. Agent-scoped visibility is explicit, and prompt and schema surfaces remain separate when scoping can hide one without the other. -A package with no model-context effect, or one path rendered entirely by another package, uses the verifier's audited one-sentence form: `None, as ` or `Indirectly, through `. Pure transport and keyless test-support packages use the none form when they create no model-bound content. Provider backends use the indirect form even when they cap or filter data, and wiring bundles use it when named children own every effect. These sentences locate the contribution without restating the consumer. Structured sections likewise document only package-owned inputs, transformations, and deltas. +A package with no model-context effect, or one path rendered entirely by another package, uses the verifier's audited short form: one sentence beginning `None, as ` or `Indirectly, through ` followed by a `**KV Cache effect**` field. Pure transport and keyless test-support packages use the none form when they create no model-bound content. Provider backends use the indirect form even when they cap or filter data, and wiring bundles use it when named children own every effect. These sections locate the contribution and disclaim direct cache invalidation without restating the consumer. Structured sections likewise document only package-owned inputs, transformations, and deltas. -`verify-package-readme-model-experience` discovers package manifests and validates the three classifications, canonical final-section order, required fields, concrete literal evidence, nested verbatim blocks, and anchored tool-catalog links. It runs in `doc-sync` and the parallel gate runner. Review still owns coverage, link relevance, and factual accuracy. +`verify-package-readme-model-experience` discovers package manifests and validates the three classifications, canonical final-section order, required model-view, token, and KV-cache fields, concrete literal evidence, nested verbatim blocks, and anchored tool-catalog links. It runs in `doc-sync` and the parallel gate runner. Review still owns coverage, link relevance, and factual accuracy. ## Alternatives considered - **Document only packages that register prompts or tools** — rejected because backends, policy plugins, adapters, persistence, scoping, and compaction change the content or lifetime of tokens without owning a model-facing schema. - **Generate one central context-cost catalog from source** — rejected because an AST can find registrations but cannot infer semantic conditions such as history retention, output truncation, parent-versus-child visibility, or an auxiliary model boundary. The package README is the implementation-local contract; a central copy would add another drift surface. - **Require numeric token counts** — rejected because exact counts depend on the selected model tokenizer, adapter serialization, configuration, and runtime data. The stable contract is the growth shape: fixed per request, conditional per call, retained, replaced, capped, or zero-direct. -- **Use a three-column table** — rejected because exact source text and conditional result shapes make cells dense and difficult to scan. Repeated subsections give each context surface readable vertical space while preserving the same fields. +- **Use a table** — rejected because exact source text and conditional result shapes make cells dense and difficult to scan. Repeated subsections give each context surface readable vertical space while preserving the same fields. - **Allow every zero-impact package to omit the section** — rejected because unconstrained absence is ambiguous between an audited zero and forgotten documentation. Omission is reserved for model-agnostic generic packages named with a reason in the verifier; model-adjacent zero-impact packages keep one explicit sentence. -- **Require the full structured form for audited zero or simple indirect packages** — rejected because it repeats labels around one fact. A gated sentence preserves explicit coverage without the ceremony. +- **Require the full structured form for audited zero or simple indirect packages** — rejected because it repeats labels around one fact. A gated sentence plus cache field preserves explicit coverage without the ceremony. - **Convention without a gate** — rejected because a repo-wide contract must also cover every future package; review memory cannot reliably detect an omitted README section. ## Consequences -A reviewer can start at any model-facing or model-adjacent package and see its contribution to the conversation model, child models, and auxiliary calls without reconstructing the full plugin graph. Token-budget work can distinguish repeated request overhead from data-dependent history, and agent-scoped changes have an explicit documentation checkpoint. Package authors maintain one or more compact context-surface blocks or one classified sentence whenever model-visible behavior changes; audited generic packages carry no irrelevant model boilerplate. The structured fields do not promise provider-exact token counts; measurements remain model- and workload-specific, while the documented growth and visibility contract stays stable. +A reviewer can start at any model-facing or model-adjacent package and see its contribution to the conversation model, child models, and auxiliary calls without reconstructing the full plugin graph. Token-budget work can distinguish repeated request overhead from data-dependent history, while cache-sensitive work can identify append-only paths and the earliest package-owned prefix mutation. Agent-scoped changes have an explicit documentation checkpoint. Package authors maintain one or more compact context-surface blocks or one classified short form whenever model-visible behavior changes; audited generic packages carry no irrelevant model boilerplate. The structured fields do not promise provider-exact token counts or cache hits; measurements remain model-, provider-, and workload-specific, while the documented growth, visibility, and prefix-stability contract stays stable. diff --git a/packages/AGENTS.md b/packages/AGENTS.md index 9ab0327cf9..38713e2e58 100644 --- a/packages/AGENTS.md +++ b/packages/AGENTS.md @@ -14,5 +14,5 @@ Naming notes: - `src/types.ts` contains only types — no runtime code. - Tests live at package level under `tests/`, not `src/__tests__/`. - A package's README and JSDoc are part of the change: altered behavior (config keys, defaults, error codes, wire fields) updates them in the same commit. `doc-sync` gates what it can; apply [dsh-prose-standard](../.agents/skills/dsh-prose-standard/SKILL.md) for complete, concise prose and verify accuracy against code. -- Package READMEs document model/token effects using the [canonical Model Experience format](../docs/cookbook/adding-a-package.md#4-write-the-package-readme). +- Package READMEs document model, token, and KV-cache effects using the [canonical Model Experience format](../docs/cookbook/adding-a-package.md#4-write-the-package-readme). - Package READMEs put durable consumer gaps and non-obvious maintainer constraints under `## Known Limitations and Deferred Work`; ordinary cleanup stays in its TODO or RFC. Packages with none use a justified [allowlist entry](../scripts/verify-package-readme-limitations.ts) ([rationale](../docs/rfc/implemented/process/2026-07-10-readme-known-limitations-gate.md)). diff --git a/packages/bash/bash-local/README.md b/packages/bash/bash-local/README.md index afa5000767..cf9f86575e 100644 --- a/packages/bash/bash-local/README.md +++ b/packages/bash/bash-local/README.md @@ -31,6 +31,8 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; Indirectly, through `dsh-tool-bash`, which renders this executor's bounded stdout/stderr tails, background-process deltas, spill-file paths, and infrastructure failures. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Unconfined by itself** — this executor always runs commands with the harness process's authority; deployments needing confinement compose [`dsh-bash-sandbox`](../bash-sandbox/README.md), while per-call allow/deny/ask policy belongs on `tools/pre-execute`. diff --git a/packages/bash/bash-sandbox/README.md b/packages/bash/bash-sandbox/README.md index 347aefb679..ab8b6c62dd 100644 --- a/packages/bash/bash-sandbox/README.md +++ b/packages/bash/bash-sandbox/README.md @@ -42,18 +42,24 @@ The keyless consumer-integration proofs are `tests/bwrap.e2e.ts`, `tests/landloc **Token effect**: Small fixed schema increment on requests where `bash` is visible; mode switches add no context tokens. +**KV Cache effect**: Prefix-stable while the executor advertises the same sandbox capabilities. Changing those capabilities alters the `bash` schema and may invalidate reuse from that definition; per-session mode switches do not. + ### Bash tool result, indirectly **What the model sees**: After ordinary bounded output, a denied call appends exactly `[sandbox: file access denied under mode]`. When escalation is available it next appends `[sandbox: escalation available — retry this exact command once with sandbox_permissions (the narrowest wider mode that suffices) + justification; the approval prompt asks the user]`. A settled background runner failure instead appends `[sandbox: the sandbox runner itself failed under mode — the command did not run; this is a sandbox problem, not a command failure]`. **Token effect**: Zero additional tokens on an unremarkable allowed run beyond ordinary output. Denial or failure adds the quoted conditional marker, retained until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Bash tool error, indirectly **What the model sees**: If no runner can enforce a confined mode, the foreground call propagates the [`SANDBOX_UNAVAILABLE` error owned by `dsh-sandbox`](../../sandbox/sandbox/README.md#confinement-error-indirectly). For an execution-time runner failure, this backend supplies the first stderr line as its detail. **Token effect**: Conditional error text is visible for that call and retained in history until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Confinement covers file effects only** — network access and process visibility are unchanged, so the modes are not a general-purpose security sandbox. diff --git a/packages/bash/bash/README.md b/packages/bash/bash/README.md index e4b5bf1952..fffc206bd4 100644 --- a/packages/bash/bash/README.md +++ b/packages/bash/bash/README.md @@ -37,6 +37,8 @@ The seam also owns the per-session mode override vocabulary: the log-only `'bash Indirectly, through `dsh-tool-bash`, which turns executor output and sandbox facts into guidance and retained tool-result tokens. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **No interactive-input vocabulary** — `stdin` is written once at spawn and closed; the seam has no channel to feed a running task and no PTY session concept. diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index d5e65f1a39..eece3249eb 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -77,6 +77,8 @@ For sandboxing executors, each call resolves mode as one-shot escalation, then s **Token effect**: Small fixed input cost per request while the plugin is active, unchanged by sandbox mode or mode switches. +**KV Cache effect**: Prefix-stable while the registration scope and prompt text are unchanged. Plugin activation or disposal may invalidate reuse from this prompt section; sandbox mode switches do not. + #### Bash guidance ```markdown @@ -89,24 +91,32 @@ Check the [exit code: N] marker on every bash result; investigate failures befor **Token effect**: Fixed schema cost on every request where the tools are visible; sandbox support adds the escalation fields and its conditional description paragraph. +**KV Cache effect**: Prefix-stable while visibility, background support, and executor sandbox capabilities are unchanged. A restriction, config change, or executor change may invalidate reuse from the first changed tool definition. + ### Foreground result **What the model sees**: The renderer emits the data-dependent stdout tail, then optional `[stderr]` and the stderr tail. With no output it emits exactly `(no output)`. Conditional lines are exactly `[output truncated; full output: ]`, `[sandbox: file access denied under mode]`, `[timed out after ms]`, `[killed by signal: ]`, and `[exit code: ]`; the sandbox escalation and runner-failure lines are quoted in [`dsh-bash-sandbox`](../bash-sandbox/README.md). **Token effect**: Zero result tokens before a call. Output is bounded per stream, while each emitted line remains in history until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Background task context and results **What the model sees**: Start returns exactly `started background task `. This producer supplies incremental process output, optional `[some output was dropped from memory; full output: ]`, sandbox facts, and terminal detail such as `exit code: ` or `signal: ` to the generic task runtime. [`dsh-tool-tasks`](../../tasks/tool-tasks/README.md) owns the visible status line, completion notice, listing, and cancellation response. **Token effect**: The start acknowledgement is small and retained; collected output is data-dependent and bounded by the executor's stream buffers. Consuming reads do not repeat prior output. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Tool errors **What the model sees**: Validation and policy failures are normalized as `Error: `. This package's stable messages are `invalid command: expected a non-empty string`, `invalid description: expected a non-empty string`, `invalid timeoutMs: expected a positive number, got `, `invalid escalation: sandbox_permissions requires a justification`, `invalid escalation: justification is only valid together with sandbox_permissions`, `invalid justification: expected a non-empty sentence`, `background execution is disabled for this bash tool`, `background tasks unavailable: load @deepseek-ai/dsh-tasks and @deepseek-ai/dsh-tool-tasks`, `sandbox_permissions is not available in this composition (no sandboxing executor to escalate)`, `sandbox escalation to "" is not strictly wider than this call's current "" mode`, the approval-availability/rejection/cancellation variants, and `command aborted`. **Token effect**: Only the failing call adds these retained tokens; a rejected escalation does not add command output because the command does not run. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Replay exit pills parse from result text** — output whose final line happens to be exactly `[exit code: N]` / `[killed by signal: …]` shows a wrong pill on session replay; a display-only known residual. diff --git a/packages/code-runtime/code-runtime-worker/README.md b/packages/code-runtime/code-runtime-worker/README.md index 342799dabb..ab39d027ba 100644 --- a/packages/code-runtime/code-runtime-worker/README.md +++ b/packages/code-runtime/code-runtime-worker/README.md @@ -37,6 +37,8 @@ The SDK surface is the default/named `WorkerCodeRuntime` class plus `Config`. Th Indirectly, through Code Mode in [`dsh-tools`](../../core/tools/README.md), which renders this worker's capped printed or returned data and exact `[dsh-code-runtime-worker] log capture truncated at bytes` and `… [truncated]` markers into a retained `run_code` result. Binding traffic and worker internals stay outside context. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **OS processes a program spawns survive termination** — `worker.terminate()` ends the thread only, weaker than bash-local's process-group kill; orphan cleanup is a deployment concern until a container backend exists. diff --git a/packages/code-runtime/code-runtime/README.md b/packages/code-runtime/code-runtime/README.md index 1f680741a1..49b79e1f52 100644 --- a/packages/code-runtime/code-runtime/README.md +++ b/packages/code-runtime/code-runtime/README.md @@ -22,6 +22,8 @@ Semantics every implementation must honor (contract details in the class JSDoc): Indirectly, through Code Mode in `dsh-tools`, which exposes `run_code` and returns program logs, values, or failures as retained tool-result tokens. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **`run()` is one-shot** — `logs` arrive only on the resolved `CodeRunResult`; the seam exposes no streaming-log or progress surface for a live program's output. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index 69dd0c5036..77a1e49a5d 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -60,6 +60,8 @@ Loading the plugin registers `ctx.compact`. With `auto: true` (the default) it c **Token effect**: The replacement reduces future input history rather than appending a second copy. The summary remains until a later compaction replaces it; one oversized indivisible unit can still exceed the budget. +**KV Cache effect**: Replacing rather than append-only. Each checkpoint invalidates reuse from the first replaced history token; the unchanged request prefix before that range remains reusable. + #### Conversation checkpoint preamble ```markdown @@ -72,12 +74,16 @@ This is an automatically generated checkpoint condensing an earlier span of the **Token effect**: This is a separate model call with data-dependent input and `maxTokens`-capped output. Convergence retries can pay this cost more than once. +**KV Cache effect**: Independent of the conversation request cache. An auxiliary call can reuse an exact transcript prefix, while a different selected range or rendering invalidates reuse from its first changed token. + ### Auxiliary summarizer system prompt **What the model sees**: The summarization model receives the checkpoint-writing instruction below. **Token effect**: Fixed auxiliary input cost plus the data-dependent transcript on every summarization attempt. +**KV Cache effect**: Prefix-stable for auxiliary calls while this instruction and the summarizer route are unchanged. Changing either starts a different prefix; transcript changes occur after the instruction. + #### Auxiliary summarizer system prompt ```markdown diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index 55abc2b12e..65f89ff4a1 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -65,12 +65,16 @@ Subclass `CompactService`, implement `compactIfNeeded` and `compactRegion`, and **Token effect**: Zero direct tokens from this interface. A backend trades many retained history tokens for one summary and leaves the recent tail unchanged. +**KV Cache effect**: A successful backend replacement invalidates reuse from the first shadowed history token; the seam itself does not alter a request. + ### Transcript supplied to a compaction consumer **What the model sees**: `renderTranscript()` joins entries with one blank line and renders them exactly as `User: `, `Assistant: `, `Tool result (call ): `, `Tool error (call ): `, `[Context: ]`, or `[Steering: ]`. Non-text blocks render exactly as `[reasoning: ]`, `[tool-call: ()]`, `[tool-result: ]`, `[tool-result]`, or `[]`. **Token effect**: Data-dependent input tokens are paid only by the auxiliary model or consumer that requests this transcript; the conversation model does not receive a duplicate transcript. +**KV Cache effect**: No conversation-cache invalidation. A consumer's auxiliary request can reuse only the exact prefix produced by this rendering; changed or compacted entries invalidate reuse from their first difference. + ## Known Limitations and Deferred Work - **No model-facing consumer tier yet** — `@deepseek-ai/dsh-tool-compact` (the `/compact` tool) is deferred; compaction is reachable only via direct `ctx.compact` calls or a backend's auto listener. diff --git a/packages/context/time-context/README.md b/packages/context/time-context/README.md index fea92e726f..e5d462e75a 100644 --- a/packages/context/time-context/README.md +++ b/packages/context/time-context/README.md @@ -36,6 +36,8 @@ The time reading stays in derived conversation history until a later compaction **Token effect**: Each injected two-line message accumulates until compaction shadows it. A positive interval reduces additions; omission or `0` adds one for every eligible preparation attempt. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + #### First step ```markdown diff --git a/packages/context/workspace-context/README.md b/packages/context/workspace-context/README.md index 430ffe8a41..a2e4a70596 100644 --- a/packages/context/workspace-context/README.md +++ b/packages/context/workspace-context/README.md @@ -82,6 +82,8 @@ Instruction content is read through `streamText()` under `maxSourceBytes`, even **Token effect**: The rendered baseline is frozen and resent on every request in that loop instance. `maxBytes` bounds the complete message, broader files are omitted before the most-specific file is truncated, and an empty chain contributes zero tokens. +**KV Cache effect**: Prefix-stable within one loop instance because the baseline is frozen. A new or resumed instance recomposes it, so instruction, precedence, cwd, candidate, or byte-budget changes may invalidate reuse from the first changed baseline token. + #### Baseline instruction template ```markdown @@ -104,6 +106,8 @@ Instructions from: AGENTS.md **Token effect**: Each discovered scope adds bounded history tokens until compaction. Unchanged content is suppressed by visible session state plus version/digest comparison, and Code Mode defers the same message until after the outer `run_code` result. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + #### Additional instruction template ```markdown @@ -122,6 +126,8 @@ These instructions apply to work under `packages/app`. Use them as guidance when **Token effect**: Each confirmed change or removal is one retained history message bounded by `maxBytes`. Provider failures add no message, and an update omitted by the budget remains eligible for a later filesystem touch. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + #### Removal notice ```markdown diff --git a/packages/cordis/tool-cordis/README.md b/packages/cordis/tool-cordis/README.md index c43e2fcc4d..73672048af 100644 --- a/packages/cordis/tool-cordis/README.md +++ b/packages/cordis/tool-cordis/README.md @@ -40,18 +40,24 @@ Namespace plugin: named exports `name` / `inject` / `Config` / `apply`, no defau **Token effect**: Fixed schema cost on every request in that tool view. +**KV Cache effect**: Prefix-stable while this tool view is unchanged. Scoping or plugin lifecycle changes that hide these definitions may invalidate reuse from the first changed schema token. + ### Tool-call history and results **What the model sees**: Inspect joins selected sections exactly as `##
` then a newline and the data-dependent body, with one blank line between sections. Its broad API/event reports omit JSDoc; `name` with `what: "api"` or `what: "events"` returns one exact target with its original JSDoc. Mount returns `mounted (plugin "", state: )`, optionally inserting ` — waiting for service(s): (activates when provided)` before the closing parenthesis. Unmount returns `unmounted (plugin "")`; an unknown id becomes `Error: no dynamic plugin with id "" (list mounts with cordis_inspect what:"dynamic")`. The submitted mount program remains in the assistant tool-call history. **Token effect**: Inspect output and mount code are data-dependent and resent until compaction; lifecycle acknowledgements are small. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Later requests after a mount **What the model sees**: A mounted plugin may register tools, prompt contributions, or listeners that change later requests for the scopes it targets; unmount removes those contributions after quiescence. **Token effect**: Indirect token impact equals the mounted plugin's contributions and lasts only for the mount lifetime. +**KV Cache effect**: Mounting or unmounting a prompt or tool contribution changes later request prefixes and may invalidate reuse from the first changed contribution; an unchanged mount set remains prefix-stable. + ## Known Limitations and Deferred Work - **The sandbox is containment for honest code, not a security boundary** — host-realm helpers on the sandbox global are reachable, so mount code can reach Node; load this plugin as deliberately as you would grant a bash tool (see § Trust stance). diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index d604e2b16f..1045d26a62 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -76,18 +76,24 @@ Everything that goes beyond "call the model, run the tools, repeat" belongs to p **Token effect**: System text, schemas, and prefix are paid again on every step. Per-agent scoping chooses the initial contributions, while the authoritative assembly waterfall can alter the final request and makes its listener responsible for protocol coherence. +**KV Cache effect**: Append-only only while system text, schemas, session prefix, and earlier history remain byte-identical under the same provider and model route. A token-bearing assembly rewrite or composition change may invalidate reuse from the first altered request token. + ### Retained message history **What the model sees**: Accepted user messages, assistant messages, tool calls and results, injected context, and steering are logged and sent on later steps. Raw stream chunks, lifecycle boundaries, and other log-only events are excluded. **Token effect**: Input grows with every surface message until a compaction replacement shadows older nodes; a multi-step tool turn resends the accumulated prefix and history each step. +**KV Cache effect**: Ordinary history growth is append-only and preserves reusable entries. A surface replacement or compaction invalidates reuse from the first shadowed history token. + ### Undispatched calls after cancellation **What the model sees**: If a later request replays an aborted step, each tool call that cancellation prevented from dispatching has the error result text `Error: tool call skipped because the step was aborted before execution`. **Token effect**: One fixed error result per skipped call remains in history until compaction shadows it. +**KV Cache effect**: Append-only; each synthetic result follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Classification is unary** — calls whose safety depends on comparing siblings or resources must remain exclusive ([rationale](../../../docs/rfc/implemented/feature/2026-07-10-parallel-tool-call-execution.md)). diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index bf5e563443..0443061e09 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -75,12 +75,16 @@ The handle every plugin programs against: **Token effect**: Accepted content becomes retained history or a repeated session prefix; blocked content contributes no request tokens. Size is caller- and plugin-dependent. +**KV Cache effect**: Accepted history and steering are append-only; a blocked submission sends no request. A session prefix remains stable within its loop instance, while a new or resumed instance may establish a different prefix. + ### Agent-scoped request composition **What the model sees**: Registrations through `agent.ctx` can shadow prompt sections or tools and can install agent-only interceptors during unpublished setup. **Token effect**: The package adds zero tokens itself; scoped contributions affect only that agent and disappear on disposal. +**KV Cache effect**: Prefix-stable while an agent's scoped registrations are unchanged. Setup or reload that changes prompt sections, tool definitions, or request listeners may invalidate reuse from the first affected request token. + ## Known Limitations and Deferred Work - **Initiator scope is process-local** — workers, child processes, HTTP, durable queues, and restarts materialize any required identity explicitly. diff --git a/packages/core/session/README.md b/packages/core/session/README.md index ba4e8ea94a..13d859e5f7 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -89,18 +89,24 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) **Token effect**: Appended surface entries are resent on later steps. A `replace` surface operation removes the shadowed entries from future inputs without deleting their raw log records. +**KV Cache effect**: Appended surface entries preserve reusable prefixes. A `replace` operation invalidates reuse from the first shadowed message even though the underlying event log stays append-only. + ### Crash-repair result **What the model sees**: If a persisted turn ended with unanswered tool calls, each synthetic error result contains exactly `Tool call interrupted by a crash; no result was recorded.` **Token effect**: Zero tokens in an intact session. Each repaired call adds this retained error text on resume. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Logged request header **What the model sees**: The session reconstructs the system prompt, tool schemas, call config, and session prefix that the loop actually sent. Header events do not add a second copy to message history; the prefix is prepended outside `deriveMessages()`. **Token effect**: Zero duplicate tokens from logging. The reconstructed prefix, system text, and schemas still incur their normal per-request cost. +**KV Cache effect**: Logging causes no invalidation, and exact reconstruction preserves request-prefix identity. A later header with changed prefix, prompt, or schemas may invalidate reuse from its first difference. + ## Known Limitations and Deferred Work - **Session branching/tree** (pi-style entry tree) — deferred unless needed beyond boundary-based `fork()`. diff --git a/packages/core/system-prompt/README.md b/packages/core/system-prompt/README.md index e8975bf17e..05cc92aaf2 100644 --- a/packages/core/system-prompt/README.md +++ b/packages/core/system-prompt/README.md @@ -48,6 +48,8 @@ Design rationale: [the prompt-variables RFC](../../../docs/rfc/implemented/archi **Token effect**: Identity is a fixed per-request cost. Persona and plugin text are repeated per request and scale with their rendered content. +**KV Cache effect**: Prefix-stable while identity, persona, variables, section text, and order render identically. Any change may invalidate reuse from the first changed system-prompt token. + #### Harness identity ```markdown @@ -60,6 +62,8 @@ You are an AI agent powered by the DeepSeek Harness SDK. **Token effect**: Schema tokens repeat on every request. Restricting a tool removes its entire schema cost for that agent but not a separate prompt section; reordering changes cache shape but not semantic content. +**KV Cache effect**: Prefix-stable while the visible schema set, rendering, and order are unchanged. Registration, restriction, or reordering may invalidate reuse from the first changed schema token. + ## Known Limitations and Deferred Work - **Deployment-authored prompt text is config/composition only** — this plugin owns the global persona default, creator plugins may register agent-scoped shadows, and other sections come from the plugin that owns the fact; there is no end-user prompt-editing API. diff --git a/packages/core/tools/README.md b/packages/core/tools/README.md index bfd75fdcb6..b0b79d04cb 100644 --- a/packages/core/tools/README.md +++ b/packages/core/tools/README.md @@ -123,12 +123,16 @@ The agent loop groups consecutive `parallel` calls into a bounded rolling pool a **Token effect**: Fixed per-request cost proportional to the visible definitions. Restrictions that hide tools remove their entire schema cost for that agent. +**KV Cache effect**: Prefix-stable while visible definitions and their order are unchanged. Registration, disposal, or scoped restriction may invalidate reuse from the first changed schema token. + ### Code Mode schema and system prompt **What the model sees**: Code Mode exposes the generated [`run_code` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tools), the SDK instructions below, and the generated exact `declare const tools` block. `both` exposes normal schemas and this Code Mode surface. **Token effect**: Fixed per-request cost proportional to the visible definitions. Code Mode trades end-tool schemas for generated SDK text plus one transport schema rather than promising a universal reduction. +**KV Cache effect**: Prefix-stable while the Code Mode selection, generated SDK, transport schema, and visible tool set are unchanged. Mode or filter changes may invalidate reuse from the first changed prompt or schema token. + #### Code Mode SDK instructions ```markdown @@ -150,6 +154,8 @@ The available tools: **Token effect**: Arguments, results, and additional context are data-dependent and resent until compaction. Restrictions that hide tools also remove their schemas before the model can call them. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Concurrency policy is not an event seam** — `executionMode()` reads the resolved tool definition directly; plugins can only declare a classifier on definitions they own. diff --git a/packages/examples/acp-demo/README.md b/packages/examples/acp-demo/README.md index 1dbda9a08a..98b62fc9bf 100644 --- a/packages/examples/acp-demo/README.md +++ b/packages/examples/acp-demo/README.md @@ -55,6 +55,8 @@ All diagnostics go to **stderr** — stdout is the protocol. Indirectly, through `dsh-agent-spine-demo` and `dsh-acp`, which compose each ACP agent's prompt, tools, and message history; this app bundle adds no model-bound content itself. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **JSONL persistence is baked in** — config chooses its root but cannot select a different backend; that requires a sibling entry or differently composed app package. diff --git a/packages/examples/agent-spine-demo/README.md b/packages/examples/agent-spine-demo/README.md index 409aef5ef2..e2b3c47abe 100644 --- a/packages/examples/agent-spine-demo/README.md +++ b/packages/examples/agent-spine-demo/README.md @@ -56,6 +56,8 @@ A YAML include can deduplicate config but cannot own a bin or provide front-door Indirectly, through `dsh-system-prompt`, `dsh-tool-skill`, `dsh-tool-bash`, and `dsh-tools`, which this bundle mounts without adding model-bound wrapper content. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **The spine set is fixed in code** — `apply()` mounts every child unconditionally (including `tool-bash`); no config excludes or replaces one, so swapping the loop or dropping a spine member means composing a different bundle. diff --git a/packages/examples/cli-demo/README.md b/packages/examples/cli-demo/README.md index c938f6c583..40790885be 100644 --- a/packages/examples/cli-demo/README.md +++ b/packages/examples/cli-demo/README.md @@ -59,6 +59,8 @@ The headless-agent leaf supplies local bash, filesystem, skill, subagent, workfl **Token effect**: The task, prompt sections, tool schemas, assistant output, and tool results consume tokens on each model step. JSON event streaming and final rendering add no model tokens; delegated child work has its own model usage and is not included in the parent result's `usage` total. +**KV Cache effect**: Tool-round history is append-only while the one-shot agent's prompt, schemas, model route, and session prefix remain fixed. Changing that composition establishes a different request prefix; JSON output mode has no cache effect. + ## Known Limitations and Deferred Work - **One fresh top-level session per process** — its workspace cwd is the launch directory; there is no resume, second prompt, stdin context, or concurrent top-level session in this app. diff --git a/packages/examples/jsonrpc-demo/README.md b/packages/examples/jsonrpc-demo/README.md index 39cb4cd917..f7c9a71bea 100644 --- a/packages/examples/jsonrpc-demo/README.md +++ b/packages/examples/jsonrpc-demo/README.md @@ -20,6 +20,8 @@ stdout carries only JSON-RPC frames. The bin and boot guards diagnose on stderr, Indirectly, through the plugins loaded from the external `cordis.yml`, which own every model-bound prompt, schema, message, and result; this bin adds none of its own. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **The bin cannot prove that the config serves JSON-RPC** — a valid config with no `dsh-jsonrpc` entry boots successfully and serves nothing. diff --git a/packages/examples/stdio-demo/README.md b/packages/examples/stdio-demo/README.md index ba4fc10101..4a50b5ccbd 100644 --- a/packages/examples/stdio-demo/README.md +++ b/packages/examples/stdio-demo/README.md @@ -83,12 +83,16 @@ Swap `llm-deepseek` for a `mock-llm` leaf plugin and you have the echo demo — **Token effect**: Child prompt and schema costs repeat per request; user input and tool history grow until compaction. Terminal banners, logger output, cards, and rendered transcripts add zero model tokens. +**KV Cache effect**: User and tool history is append-only while the composed prompt, schemas, child model route, and session prefix remain fixed. A composition change or compaction may invalidate reuse from its first changed token; terminal rendering has no cache effect. + ### Human-answer result **What the model sees**: Through `dsh-tool-ask-user`, successful terminal answers use that package's exact compact JSON shape. Interruption becomes exactly `Error: ask_user_question was interrupted before the user answered`; a closed stdin becomes `Error: ask_user_question cannot be answered because stdin is closed`. **Token effect**: Only a completed or failed tool call adds retained result tokens; prompts printed while waiting are terminal-only. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **One pre-created `main` agent drives the selected terminal UI** — there is no multi-session or concurrent-agent surface in this app; a run is one conversation. diff --git a/packages/fs/fs-local/README.md b/packages/fs/fs-local/README.md index 65ed76efce..3403ef59fd 100644 --- a/packages/fs/fs-local/README.md +++ b/packages/fs/fs-local/README.md @@ -25,6 +25,8 @@ The package-root SDK surface is the default/named `LocalFileSystem` class plus ` Indirectly, through [`dsh-tool-fs`](../tool-fs/README.md), which renders this provider's line-windowed UTF-8 content, mutation acknowledgements, and exact provider messages in capped retained results while versions, atomic-write mechanics, and directory metadata remain internal. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **`config.cwd` is not a sandbox** — it is a resolution default, not containment: absolute paths and `..` escape it. Enforce containment with a stricter `ctx.fs` backend or a permission plugin on the `tools/execute` waterfall ([capability-seam RFC](../../../docs/rfc/implemented/architecture/2026-06-17-filesystem-capability-seam.md#consequences)). diff --git a/packages/fs/fs-policy/README.md b/packages/fs/fs-policy/README.md index bd85be88cf..d509e63645 100644 --- a/packages/fs/fs-policy/README.md +++ b/packages/fs/fs-policy/README.md @@ -55,6 +55,8 @@ Because the plugin influences the world only through events, removing it does no **Token effect**: Zero tokens on allowed operations beyond the ordinary tool result. A denial adds the small retained error result and avoids any success payload. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Observed state does not survive a session resume** — persistence of the `WeakMap` record is deferred, so a resumed session must re-read files before guarded writes/edits. diff --git a/packages/fs/fs/README.md b/packages/fs/fs/README.md index 6dae32d235..b67efe5fad 100644 --- a/packages/fs/fs/README.md +++ b/packages/fs/fs/README.md @@ -48,6 +48,8 @@ This package declares three events (see the generated [events catalog](../../../ Indirectly, through `dsh-tool-fs`, which renders provider text and errors as bounded, retained filesystem tool results. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Text-only by contract** — backends reject binary/non-UTF-8 content with `FS_NOT_TEXT`; binary-safe operations are a deliberate deferral of [the tool-schemas RFC](../../../docs/rfc/implemented/feature/2026-06-17-filesystem-tool-schemas.md). diff --git a/packages/fs/tool-fs-search/README.md b/packages/fs/tool-fs-search/README.md index 29afbebfec..4075890ba2 100644 --- a/packages/fs/tool-fs-search/README.md +++ b/packages/fs/tool-fs-search/README.md @@ -53,6 +53,8 @@ Search failures carry the package-owned `SearchError` (a `HarnessError` subclass **Token effect**: Fixed guidance cost per request while the plugin is active. +**KV Cache effect**: Prefix-stable while the plugin scope and guidance text are unchanged. Activation or disposal may invalidate reuse from this prompt section. + #### Glob guidance ```markdown @@ -71,18 +73,24 @@ Use the grep tool — not shell grep or rg — to search file contents. Use read **Token effect**: Fixed schema cost on every request where the tools are visible. +**KV Cache effect**: Prefix-stable while tool visibility and definitions are unchanged. Registration lifecycle or scoped restrictions may invalidate reuse from the first changed schema token. + ### Results and spill notices **What the model sees**: `glob` returns one path per line; `grep` groups `Line : ` matches beneath each path. Empty searches return `No files found` or `No matches found`. A capped result ends with its omission count plus the spill locator and backend retrieval hint, or says the complete result could not be saved. **Token effect**: Inline paths and matches are bounded by `globMaxResults`, `grepMaxMatches`, and `grepMaxLineBytes`; the call and retained result remain in history until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Tool errors **What the model sees**: Failures are normalized as `Error: ` with structured `SEARCH_INVALID_PATTERN`, `SEARCH_FAILED`, `SEARCH_RAW_OUTPUT_OVERFLOW`, or `SEARCH_ABORTED` metadata for callers. **Token effect**: Only a failing call adds these retained tokens. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Search and file access have no shared-workspace proof** — returned paths are follow-up-readable only when the bash workdir and filesystem root denote the same workspace; the package performs no runtime cross-service validation. diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 2f116a2b71..5bd59f8888 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -58,6 +58,8 @@ The package root exports only the Cordis plugin contract (`name`, `inject`, `Con **Token effect**: Fixed guidance cost per request while the plugin is active, even when a restriction hides one or more tools. +**KV Cache effect**: Prefix-stable while the plugin scope and guidance text are unchanged. Tool restrictions do not remove this section, but plugin activation or disposal may invalidate reuse from it. + #### Read guidance ```markdown @@ -82,24 +84,32 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces **Token effect**: Fixed schema cost on every request in that tool view. +**KV Cache effect**: Prefix-stable while the visible tool definitions and order are unchanged. Registration lifecycle or scoped restrictions may invalidate reuse from the first changed schema token. + ### Read result **What the model sees**: A successful read is exactly ``, newline, `file`, newline, ``, numbered lines as `: `, a blank line, one footer, and ``. The footer is exactly `(Output capped. Showing lines -. Use offset= to continue.)`, `(Showing lines - of . Use offset= to continue.)`, or `(End of file - total lines)`. A long line ends exactly `... (line truncated to chars)`. **Token effect**: Read output is capped by `readLimit`, `readMaxLineLength`, and `readMaxBytes`; the retained call and result are resent until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Write and edit results **What the model sees**: Write returns the exact five-line envelope ``, `file`, ``, `Created file` or `Updated file`, then ``. Edit returns exactly `The file has been updated successfully.` or, for `replace_all`, `The file has been updated. All occurrences were successfully replaced.` The full write or replacement text remains in the assistant tool-call arguments. **Token effect**: Success text is small, but large mutation arguments and any result are resent until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Tool errors **What the model sees**: Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, and `offset is out of range for "" ( lines)`; provider and policy templates are quoted in their package READMEs. **Token effect**: Only a failing call adds these retained tokens. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **No model-facing directory listing ships** — `ctx.fs.listDir` serves provider code such as skill discovery, while the sibling [`dsh-tool-fs-search`](../tool-fs-search/) package supplies bash-backed `glob` and `grep` rather than extending the filesystem seam. diff --git a/packages/guard/repeat-tool-guard/README.md b/packages/guard/repeat-tool-guard/README.md index 2927e3f20a..2ca3edc46a 100644 --- a/packages/guard/repeat-tool-guard/README.md +++ b/packages/guard/repeat-tool-guard/README.md @@ -44,6 +44,8 @@ Unit suites drive a real agent loop against a mock adapter (no network) and cove **Token effect**: Zero tokens before the threshold. The reminder is retained history for that agent. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + #### First-threshold reminder ```markdown @@ -56,6 +58,8 @@ You are repeating the exact same tool call with identical arguments. Carefully a **Token effect**: Each reminder is retained history; `argumentsPreviewChars` bounds its data-dependent argument text, while agents keep independent counters. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + #### Later-threshold reminder ```markdown diff --git a/packages/hooks/hook-protocol/README.md b/packages/hooks/hook-protocol/README.md index 96a423fea9..6513745173 100644 --- a/packages/hooks/hook-protocol/README.md +++ b/packages/hooks/hook-protocol/README.md @@ -33,6 +33,8 @@ Like every event they must sit inside an open turn. The mid-turn points (`PreToo Indirectly, through `dsh-hooks-claude` and `dsh-hooks-codex`, which can turn parsed hook output into prompt context, blocked outcomes, or continuation feedback. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **`HookOutput.updatedInput` is parsed but not honored** — input rewrite is a deferred consistency-design problem ([the pre-tool-input-rewrite RFC](../../../docs/rfc/proposed/feature/2026-06-30-pre-tool-input-rewrite.md)); a bridge logs + warns when a hook sets it. See `src/types.ts` for the full contracts. diff --git a/packages/hooks/hooks-claude/README.md b/packages/hooks/hooks-claude/README.md index 4430f5511a..2498d0ac58 100644 --- a/packages/hooks/hooks-claude/README.md +++ b/packages/hooks/hooks-claude/README.md @@ -60,12 +60,16 @@ Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-claude' } **Token effect**: No cost when hooks return no context. Hook text is data-dependent, logged, and resent in later conversation requests until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Blocked prompt or tool outcome **What the model sees**: Provider-supplied reasons pass through verbatim. When absent, a blocked prompt uses exactly `blocked by UserPromptSubmit hook`, a denied tool becomes `Error: blocked by PreToolUse hook`, blocked post-tool feedback is exactly `blocked by PostToolUse hook`, and a blocking stop adds steering exactly `continue: blocked by Stop hook`. `systemMessage` and `updatedInput` are logged or warned but are not model-visible in this implementation. **Token effect**: Blocking a prompt removes that prompt's request tokens; denial or feedback adds the retained fallback or provider text; forced continuation pays another full request. +**KV Cache effect**: A blocked prompt sends no request and invalidates nothing. Denial, feedback, and forced-continuation context append after the reusable prefix without rewriting it. + ## Known Limitations and Deferred Work - **Unsupported hook events (23 of Claude Code's current 30):** `Setup`, `InstructionsLoaded`, `UserPromptExpansion`, `MessageDisplay`, `PermissionRequest`, `PostToolUseFailure`, `PostToolBatch`, `PermissionDenied`, `Notification`, `TaskCreated`, `TaskCompleted`, `StopFailure`, `TeammateIdle`, `ConfigChange`, `CwdChanged`, `FileChanged`, `WorktreeCreate`, `WorktreeRemove`, `PreCompact`, `PostCompact`, `SessionEnd`, `Elicitation`, and `ElicitationResult`. Config for these events is parsed but never dispatched. The comparison baseline is Claude Code's [official hook-event reference](https://code.claude.com/docs/en/hooks#hook-events). diff --git a/packages/hooks/hooks-codex/README.md b/packages/hooks/hooks-codex/README.md index 0784857286..698fcc7a29 100644 --- a/packages/hooks/hooks-codex/README.md +++ b/packages/hooks/hooks-codex/README.md @@ -64,12 +64,16 @@ Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-codex' }` **Token effect**: No cost when hooks return no context. Hook text is data-dependent, logged, and resent until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Blocked prompt or tool outcome **What the model sees**: Provider-supplied reasons pass through verbatim. When absent, a blocked prompt uses exactly `blocked by UserPromptSubmit hook`, a denied tool becomes `Error: blocked by PreToolUse hook`, blocked post-tool feedback is exactly `blocked by PostToolUse hook`, and a blocking stop adds steering exactly `continue: blocked by Stop hook`. Codex `systemMessage` is not surfaced. **Token effect**: Blocking a prompt removes its request tokens; denial or feedback adds the retained fallback or provider text; forced continuation pays another full request. +**KV Cache effect**: A blocked prompt sends no request and invalidates nothing. Denial, feedback, and forced-continuation context append after the reusable prefix without rewriting it. + ## Known Limitations and Deferred Work - **Unsupported hook events (5 of Codex's current 10):** `PermissionRequest`, `PreCompact`, `PostCompact`, `SubagentStart`, and `SubagentStop`. Config for these events is silently dropped during parsing. The comparison baseline is Codex's [official hook reference](https://learn.chatgpt.com/docs/hooks). diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index b58da7bf57..019284a872 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -56,12 +56,16 @@ Unit suites run against a local `node:http` mock SSE server (no network). Real-A **Token effect**: Provider tokenization governs exact input. Conditional reasoning passback increases tool-round-trip context, while dropping other reasoning avoids paying those tokens again; cache-read usage is reported when available. +**KV Cache effect**: An unchanged assembled prefix is eligible for DeepSeek cache reuse, which this adapter reports in usage. A model-route change or any upstream prompt, schema, prefix, or history change may prevent reuse from the first changed token; reasoning passback appends during tool round trips. + ### DeepSeek response **What the model sees**: Reasoning, text, and raw-string tool arguments are translated into harness chunks for the loop to log and assemble. **Token effect**: Generated tokens follow provider thinking and effort settings plus the request's `maxTokens`; only loop-retained blocks affect later input. +**KV Cache effect**: Loop-retained response blocks append to the next request and preserve its earlier reusable prefix; dropped blocks have no later cache effect. Changing the provider or model selects a different cache domain. + ## Known Limitations and Deferred Work - **`tool_choice` is not mapped** — not part of the core vocabulary (MVP cut, shared with the pi-ai twin). diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index 1deae8f039..d295b9cfcf 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -67,12 +67,16 @@ Unit tests use pi-ai catalog models redirected to local mock servers and cover p **Token effect**: Provider tokenization governs exact input. Conversion adds no model-visible text; replay metadata may let a native API reuse provider-side state. +**KV Cache effect**: Conversion preserves logical request order without adding text, while the selected provider's serialization and replay state determine reuse. Changing adapter instance, provider, model, or any upstream request token may prevent reuse from the first difference. + ### Provider response **What the model sees**: pi-ai events become harness reasoning, text, tool-call, usage, and finish chunks. Parsed tool arguments cross the harness boundary as raw JSON strings. **Token effect**: Generated content affects later inputs only after the loop records it. pi-ai folds reasoning tokens into output usage when the provider does not report them separately. +**KV Cache effect**: Recorded response content appends to the next request and does not invalidate its earlier reusable prefix. Unrecorded transport metadata and usage accounting do not affect cache identity. + ## Known Limitations and Deferred Work - **Catalog membership is required** — custom model ids that are absent from the installed pi-ai catalog fail with `UNKNOWN_MODEL`, even when a provider profile supplies a custom endpoint. diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 44e7d80a05..2332bc0b0d 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -58,6 +58,8 @@ Two adapters implement `LlmAdapter` on different internals: [`@deepseek-ai/dsh-l None, as this adapter registry forwards an already assembled request without adding or changing any model-bound text, schema, or message. +**KV Cache effect**: Pass-through; the registry preserves the assembled request prefix, while the selected adapter and provider own cache reuse and routing boundaries. + ## Known Limitations and Deferred Work - **No default retry/caching/rate-limit policy ships in this service** — `llm/stream` remains the call-wrapper seam; the agent loop separately offers proven model-request failures to `agent/request-error`, whose default preserves the original failure. diff --git a/packages/llm/token-meter/README.md b/packages/llm/token-meter/README.md index 262fc8d152..8db289a05a 100644 --- a/packages/llm/token-meter/README.md +++ b/packages/llm/token-meter/README.md @@ -42,6 +42,8 @@ Both plugins have usable defaults. A deployment with a different capacity config Indirectly, through consumers such as `dsh-compact-basic`; the service itself adds no prompt, message, schema, tool, or model call. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **The fixed heuristic is approximate** — content without reusable provider usage is priced by character count plus structural overhead, not an exact provider tokenizer or request serializer. diff --git a/packages/mcp/mcp-client/README.md b/packages/mcp/mcp-client/README.md index e8c4f54f5f..9968b2b6ff 100644 --- a/packages/mcp/mcp-client/README.md +++ b/packages/mcp/mcp-client/README.md @@ -74,12 +74,16 @@ Every MCP tool has two names: the raw MCP name (sent on the wire in `tools/call` **Token effect**: Data-dependent schema cost is paid on every request while the tools are registered. Re-sync replaces rather than accumulates schemas, and the server-qualified name adds tokens to every tool definition and call. +**KV Cache effect**: Prefix-stable while the discovered tool set and schemas are unchanged. A re-sync that adds, removes, renames, or changes a tool replaces definitions and may invalidate reuse from the first changed schema token. + ### Tool-call history and results **What the model sees**: The public tool name and JSON arguments remain in assistant history. Text result blocks are joined with newlines into one retained text result; image, audio, resource, and unsupported blocks become short placeholders, and MCP `isError` results follow the registry's model-visible error path. **Token effect**: Arguments and mapped text are retained until compaction. Binary and resource payloads are discarded rather than added to context. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Initial discovery is asynchronous** — plugin load does not wait for connection and `listTools()`, so a turn started immediately after boot or HMR can assemble before the MCP tools are registered. diff --git a/packages/sandbox/sandbox-local/README.md b/packages/sandbox/sandbox-local/README.md index cbd765bbf9..723df60f17 100644 --- a/packages/sandbox/sandbox-local/README.md +++ b/packages/sandbox/sandbox-local/README.md @@ -25,6 +25,8 @@ Consumers: [`@deepseek-ai/dsh-bash-sandbox`](../../bash/bash-sandbox/); see [the Indirectly, through [`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md) and [`dsh-tool-bash`](../../bash/tool-bash/README.md), which render this provider's enforcement and denial facts while the [`dsh-sandbox`](../sandbox/README.md) seam owns the `SANDBOX_UNAVAILABLE` text and runner selection and profiles stay outside context. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Windows has no runner** — `win32` fails closed with `SANDBOX_UNAVAILABLE`; an AppContainer-family backend is deferred. diff --git a/packages/sandbox/sandbox/README.md b/packages/sandbox/sandbox/README.md index 93e274b485..9a56b53e8a 100644 --- a/packages/sandbox/sandbox/README.md +++ b/packages/sandbox/sandbox/README.md @@ -18,6 +18,8 @@ Implementations: [`@deepseek-ai/dsh-sandbox-local`](../sandbox-local/) (Linux: ` **Token effect**: Conditional error text is visible for that call and retained in history until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + #### Exact error ```markdown diff --git a/packages/sdk/create-sdk/README.md b/packages/sdk/create-sdk/README.md index 66cddc030a..93d0bffe28 100644 --- a/packages/sdk/create-sdk/README.md +++ b/packages/sdk/create-sdk/README.md @@ -14,6 +14,8 @@ The provider choice is DeepSeek or a custom endpoint backed by `llm-pi-ai`. Deep Indirectly, through the generated project composition and its selected runtime plugins. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **TTY-only creation** — flags prefill questions, but the wizard still requires an interactive terminal before it writes a project. diff --git a/packages/sdk/helper/README.md b/packages/sdk/helper/README.md index 5b5608cdf0..9eb46d978e 100644 --- a/packages/sdk/helper/README.md +++ b/packages/sdk/helper/README.md @@ -18,6 +18,8 @@ The package root explicitly exports only the objects consumed by `create-sdk` an None, as the project domain edits files and never mounts a live agent or model request. +**KV Cache effect**: None; this package neither assembles nor sends a provider request. + ## Known Limitations and Deferred Work - **Commit is not transactional across files** — external edits are detected before each write, but a later failure does not roll back files already written. diff --git a/packages/sdk/scripts/README.md b/packages/sdk/scripts/README.md index e87c375a4f..63f417efbb 100644 --- a/packages/sdk/scripts/README.md +++ b/packages/sdk/scripts/README.md @@ -25,6 +25,8 @@ The root library exports `startSDK`, `runSDK`, and the `SdkBootArgs`/`SdkBootCon Indirectly, through the project `cordis.yml` tree loaded by `start` or `dev`. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Launcher arguments are schema-free** — `start` and `dev` preserve Node `parseArgs()` output rather than validating project-specific flags. diff --git a/packages/session-persistence/session-persistence-jsonl/README.md b/packages/session-persistence/session-persistence-jsonl/README.md index 9fcf537123..dffad31ddb 100644 --- a/packages/session-persistence/session-persistence-jsonl/README.md +++ b/packages/session-persistence/session-persistence-jsonl/README.md @@ -40,6 +40,8 @@ The plugin buffers frozen session events and drains them on flush or disposal. A **Token effect**: Zero live-request tokens. A resumed agent pays for retained history and its current envelope, plus the quoted repair result for each interrupted call. +**KV Cache effect**: JSONL storage does not mutate live request prefixes. A resumed loop can reuse provider cache only when its reconstructed history, current envelope, and model route match; crash-repair results append. + ## Known Limitations and Deferred Work - **Only the current `SESSION_FORMAT_VERSION` (v0) loads** — the on-disk format is pre-release/unstable: a breaking format change is absorbed at v0 and non-current logs are rejected; there is no migration. diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index 11fef96dad..748eb3e851 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -41,6 +41,8 @@ Like the JSONL backend, the plugin also installs the `session/event` → buffer **Token effect**: Zero live-request tokens. Resume restores retained history and pays the current envelope, plus the quoted repair result for each interrupted call. +**KV Cache effect**: SQLite storage does not mutate live request prefixes. A resumed loop can reuse provider cache only when its reconstructed history, current envelope, and model route match; crash-repair results append. + ## Known Limitations and Deferred Work - **`DatabaseSync` is synchronous** — every append transaction blocks the event loop for its duration; acceptable for local stores, a throughput ceiling for busy multi-session servers. diff --git a/packages/session-persistence/session-persistence/README.md b/packages/session-persistence/session-persistence/README.md index 3390b2cc30..dbfa61ef1f 100644 --- a/packages/session-persistence/session-persistence/README.md +++ b/packages/session-persistence/session-persistence/README.md @@ -61,6 +61,8 @@ Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `ve **Token effect**: Zero tokens during ordinary persistence. Resume restores retained history cost and pays the current request envelope normally; each repaired call adds the quoted retained error text. +**KV Cache effect**: Persistence does not mutate live request prefixes. A resumed loop can reuse provider cache only when its reconstructed history, current envelope, and model route match; crash-repair results append without rewriting earlier history. + ## Known Limitations and Deferred Work - **No deletion or retention surface** — the seam is `create`/`append`/`load`/`list` only; pruning stored sessions is out-of-band backend maintenance. diff --git a/packages/session-query/session-query/README.md b/packages/session-query/session-query/README.md index 269ba51e3e..8968a94d80 100644 --- a/packages/session-query/session-query/README.md +++ b/packages/session-query/session-query/README.md @@ -26,6 +26,8 @@ Persistence is optional and may mount or unmount dynamically. Cross-corpus listi None, as this trusted query service returns cloned session records only to its callers and registers no model-facing prompt, schema, tool, or message. +**KV Cache effect**: None; this package neither assembles nor sends a provider request. + ## Known Limitations and Deferred Work - **No caller authorization** — this is trusted context-wide infrastructure; a future model tool or UI must constrain which sessions its caller may inspect. diff --git a/packages/skill/skill-local/README.md b/packages/skill/skill-local/README.md index 8034441272..7fb8e3cdbe 100644 --- a/packages/skill/skill-local/README.md +++ b/packages/skill/skill-local/README.md @@ -40,6 +40,8 @@ Skills can be single-level directory bundles (`/SKILL.md`) or flat Markdow Indirectly, through `dsh-tool-skill`, which renders this provider's invocable names and capped descriptions into the session-prefix catalog and a selected instruction body plus resource-base guidance into retained tool history while paths, provider ranks, and disabled skills remain hidden. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Discovery is one level deep** — only `//SKILL.md` and `/.md` are recognized; nested skill trees and package manifests are ignored. diff --git a/packages/skill/skill/README.md b/packages/skill/skill/README.md index 8edcd71ef0..98e51287f2 100644 --- a/packages/skill/skill/README.md +++ b/packages/skill/skill/README.md @@ -39,6 +39,8 @@ The registry does not render model guidance or register model-facing tools. [`@d Indirectly, through `dsh-tool-skill`, which renders provider summaries into the session prefix and loaded instructions into retained tool results. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Completed catalogs have no TTL or watcher invalidation** — a provider's underlying files or remote data can change without a registration revision, so a cached cwd stays stale until eviction or provider/runtime reload. diff --git a/packages/skill/tool-skill/README.md b/packages/skill/tool-skill/README.md index a2c7ff5c40..5af1131ccf 100644 --- a/packages/skill/tool-skill/README.md +++ b/packages/skill/tool-skill/README.md @@ -32,6 +32,8 @@ The tool does not call `agent.inject()` in v1. Its result is already recorded as **Token effect**: Repeated input cost scales with skill count and `catalogDescriptionMaxLength`; no catalog tokens are sent when the list is empty or the tool is hidden or shadowed. +**KV Cache effect**: Prefix-stable within a loop instance once the session prefix is composed. A new or resumed instance with different providers, skills, descriptions, visibility, or catalog limits may invalidate reuse from the first changed catalog token. + #### Skill catalog template ```markdown @@ -52,12 +54,16 @@ If the user names a skill, or the task clearly matches a skill's description, ca **Token effect**: Fixed schema cost per request where the tool is visible. +**KV Cache effect**: Prefix-stable while the tool definition and visibility are unchanged. Shadowing, restrictions, or plugin lifecycle changes may invalidate reuse from this schema. + ### Tool result **What the model sees**: A successful call uses the result template and the provider-managed, directory, URL, or opaque resource guidance below. **Token effect**: Loaded instructions are data-dependent tool-result tokens, resent on later steps until compaction; no duplicate `agent.inject()` copy is made. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + #### Skill result template ```markdown @@ -106,6 +112,8 @@ Load referenced resources only as needed. **Token effect**: Only a failing call adds these retained tokens. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **The catalog omits `whenToUse`, source, and provider metadata** — routing is based only on name and a capped description; `whenToUse` remains provider metadata and is not rendered by the loaded wrapper either. diff --git a/packages/spill/spill-local/README.md b/packages/spill/spill-local/README.md index 59d23b8a46..e19bc7e50e 100644 --- a/packages/spill/spill-local/README.md +++ b/packages/spill/spill-local/README.md @@ -22,6 +22,8 @@ Files land at `/session-/​-`: Indirectly, through spill consumers that render the local path and `read`/`grep` retrieval guidance. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Local spill files persist until external cleanup** — the backend has no session-lifecycle deletion or age-based retention policy, because persisted, resumed, and forked sessions may still reference a path. diff --git a/packages/spill/spill-policy/README.md b/packages/spill/spill-policy/README.md index bb20ac9dfc..a197c82179 100644 --- a/packages/spill/spill-policy/README.md +++ b/packages/spill/spill-policy/README.md @@ -40,6 +40,8 @@ The policy sees only the FINAL formatted tool result — not a tool's internal r **Token effect**: A successful replacement is at most `maxInlineBytes` UTF-8 bytes and remains in history until compaction; the full spill text is not resent to the model. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Only final plain-text results are spillable** — mixed-content results, blocked feedback, and `read` pass through; provider truncation or tool-owned retention that happened earlier cannot be recovered here. diff --git a/packages/spill/spill/README.md b/packages/spill/spill/README.md index c80277339b..a790b73d5f 100644 --- a/packages/spill/spill/README.md +++ b/packages/spill/spill/README.md @@ -30,6 +30,8 @@ See the [tool output spill RFC](../../../docs/rfc/implemented/architecture/2026- Indirectly, through spill consumers that render a backend locator and retrieval guidance. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **The seam has no retrieval or deletion API** — consumers can only render the backend's locator and guidance; lifecycle and access semantics remain backend-specific. diff --git a/packages/subagent/subagent-acp/README.md b/packages/subagent/subagent-acp/README.md index a620051506..9fd9db3ce6 100644 --- a/packages/subagent/subagent-acp/README.md +++ b/packages/subagent/subagent-acp/README.md @@ -67,12 +67,16 @@ Keyless tests drive a scripted ACP subprocess over real stdio. The with-key e2e **Token effect**: The child pays for an independent full context and its own multi-step history. These tokens never enter the parent's context. +**KV Cache effect**: Independent of the parent request cache. Each ACP child can reuse only prefixes identical under its own provider, model, composition, and history; child steps otherwise grow append-only. + ### Parent tool result, indirectly **What the model sees**: Through `dsh-tool-subagent`, the parent receives only the child's final streamed assistant text or that consumer's exact stop-reason error, not intermediate messages or tool traffic. A request already cancelled before publication becomes exactly `Error: subagent request was aborted before the ACP child started`; other start failures pass through as `Error: `. **Token effect**: Parent input grows only by the final result or error, which is data-dependent and retained until compaction. This provider adds no parent schema itself. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **A fresh process per run** — persistent-process pooling is a future optimization ([the seam RFC](../../../docs/rfc/implemented/feature/2026-06-21-subagent-capability-seam.md)). diff --git a/packages/subagent/subagent-fork/README.md b/packages/subagent/subagent-fork/README.md index 244811ab88..8ed1c38cd9 100644 --- a/packages/subagent/subagent-fork/README.md +++ b/packages/subagent/subagent-fork/README.md @@ -31,12 +31,16 @@ See [`dsh-subagent-spawn`](../subagent-spawn/README.md) for the run lifecycle, m **Token effect**: Forking duplicates retained completed history into separate child requests; the child then accumulates its own tokens independently. Persona changes repeated prompt cost, filtering changes schema or generated SDK cost, and a first-turn fork has no inherited history. +**KV Cache effect**: The child may reuse the inherited byte-identical prefix under the same provider and model. Persona, tool-filter, generated-SDK, or route changes may invalidate reuse before inherited history; later child history is append-only. + ### Parent tool result, indirectly **What the model sees**: The parent receives only the child's own final output through `dsh-tool-subagent`, not the inherited prefix or intermediate work. **Token effect**: Parent input grows by one data-dependent final result retained until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Runs expose no `sendMessage`/`resume`** — the optional runtime capabilities are absent on in-process runs. diff --git a/packages/subagent/subagent-inprocess/README.md b/packages/subagent/subagent-inprocess/README.md index ca54dab7c0..a709df0058 100644 --- a/packages/subagent/subagent-inprocess/README.md +++ b/packages/subagent/subagent-inprocess/README.md @@ -48,12 +48,16 @@ A clean turn that never commits the required structured value reports `error`; t **Token effect**: Child input is isolated from the parent and grows through the child's own steps. A persona changes repeated prompt text; filtering changes schema or generated SDK cost but not independently registered guidance. +**KV Cache effect**: Independent of the parent request cache. The child's later history is append-only, while persona, tool-filter, generated-SDK, provider, or model changes establish a different child prefix. + ### Structured-output system prompt, schema, and results **What the model sees**: A structured run adds the structured-output instruction below. It also adds a child-scoped `structured_output` definition with exact description `Report your final structured result. Call this exactly once, when your answer is complete; the arguments must match this tool's parameter schema exactly.` and the requested schema. This runtime-only definition is outside the generated shipped [tool package map](../../../docs/tool-catalog.md#tool-package-map). Success returns `Structured output recorded.`; a later call becomes ``Error: structured output already recorded: the run is complete, so `` is not executed``. **Token effect**: Fixed instruction and capability tokens are paid only by that child. Result text enters the child history, while the captured value alone becomes the parent result. +**KV Cache effect**: Prefix-stable inside the child while the structured-output instruction and schema are unchanged. Changing the schema or capability may invalidate the child's cache from that early segment; results append in child and parent histories. + #### Structured-output instruction ```markdown @@ -66,12 +70,16 @@ When you have your final answer, you MUST report it by calling the `structured_o **Token effect**: Zero tokens on a successful start; only the failed parent tool call retains this text. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Parent result, indirectly **What the model sees**: The driver extracts only the child's own last assistant output or captured structured value; seeded parent messages and intermediate child work do not become the result. **Token effect**: The parent receives one data-dependent result through the consumer; all other child tokens stay in the child session. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Runs expose no `sendMessage`/`resume`** — the optional runtime capabilities are absent on in-process runs. diff --git a/packages/subagent/subagent-spawn/README.md b/packages/subagent/subagent-spawn/README.md index 6f9982f15b..ca283eee2c 100644 --- a/packages/subagent/subagent-spawn/README.md +++ b/packages/subagent/subagent-spawn/README.md @@ -26,12 +26,16 @@ Spawn advertises `{ outputSchema: true, depthLimit: true, toolFilter: true, pers **Token effect**: The child pays for a new independent context and history; no parent-history tokens are duplicated. Persona changes this child's repeated prompt cost, while filtering changes its schema or generated SDK cost. +**KV Cache effect**: Independent of the parent request cache. Child history grows append-only, while persona, tool-filter, generated-SDK, provider, or model changes establish a different child prefix. + ### Parent tool result, indirectly **What the model sees**: Through `dsh-tool-subagent`, the parent receives only the child's final output or stop-reason error. **Token effect**: Parent input grows by one data-dependent result retained until compaction. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Runs expose no `sendMessage`/`resume`** — the optional runtime capabilities are absent on in-process runs. diff --git a/packages/subagent/subagent-subprocess/README.md b/packages/subagent/subagent-subprocess/README.md index f15defcf2a..cc536e6d0e 100644 --- a/packages/subagent/subagent-subprocess/README.md +++ b/packages/subagent/subagent-subprocess/README.md @@ -41,6 +41,8 @@ A per-run isolated config directory for an external CLI child (the target of `CL Indirectly, through process-based subagent backends, whose child composition is constrained by credential scrubbing and isolated config directories. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **The credential scrub is name-based** — only variables matching `KEY` / `SECRET` / `TOKEN` are removed; differently named secrets such as `PASSWORD` pass through unless the backend supplies a stricter environment. diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 17edd0e3c7..76c66b84b1 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -66,6 +66,8 @@ The model-facing tool collects synchronously by default: it awaits the child res Indirectly, through `dsh-tool-subagent`, which renders provider-specific schemas and foreground or generic-background results while child working context remains child-only. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Runtime steering and continuation are seam-only capabilities** — `sendMessage` and `resume` have no model-facing consumer in the current tool. diff --git a/packages/subagent/tool-subagent/README.md b/packages/subagent/tool-subagent/README.md index 825e252923..a7f8775fa0 100644 --- a/packages/subagent/tool-subagent/README.md +++ b/packages/subagent/tool-subagent/README.md @@ -36,18 +36,24 @@ Foreground and background calls are exclusive. Children may share the parent's w **Token effect**: Fixed schema cost per parent request; each provider instance adds one schema. +**KV Cache effect**: Prefix-stable while provider instances, names, descriptions, and schemas are unchanged. Provider registration lifecycle may invalidate parent reuse from the first changed tool definition. + ### Foreground result **What the model sees**: The call retains the description and prompt. Success contains only the child's final text; other outcomes become `Error: `. Intermediate child steps stay out of the parent. **Token effect**: The prompt and result remain in parent history until compaction; child working context remains in the child. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Background task result **What the model sees**: Start returns exactly `started background subagent task `. The generic task surface provides later status, final output, cancellation responses, and notices. **Token effect**: The acknowledgement is retained; final output enters parent history only when collected or injected. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Background runs expose final output only** — intermediate child steps stay in the child session. diff --git a/packages/support/acp-snapshot/README.md b/packages/support/acp-snapshot/README.md index 27e0012d19..dd22565eb5 100644 --- a/packages/support/acp-snapshot/README.md +++ b/packages/support/acp-snapshot/README.md @@ -46,6 +46,8 @@ Constraints: `suite.ts` imports vitest, so the package entry is importable only None, as this test-only harness records, normalizes, and compares ACP transcripts without changing the agent's assembled model request. +**KV Cache effect**: None; this package neither assembles nor sends a provider request. + ## Known Limitations and Deferred Work - **Session harvest is JSONL-only** — `runScenario` collects persisted `.jsonl` logs, so an example composed over the SQLite persistence backend has no snapshot path. diff --git a/packages/support/agent-loop-testkit/README.md b/packages/support/agent-loop-testkit/README.md index 350a8643e1..24aefeb29a 100644 --- a/packages/support/agent-loop-testkit/README.md +++ b/packages/support/agent-loop-testkit/README.md @@ -22,6 +22,8 @@ Tests of injection failures, partial topology, service load order, or service te None, as this test-only composition helper neither drives nor modifies model requests. +**KV Cache effect**: None; this package neither assembles nor sends a provider request. + ## Known Limitations and Deferred Work - **Only the mandatory prerequisite spine is shared** — adapters, optional plugins, `AgentLoop`, agents, and Context teardown remain caller-owned so scenario-specific ordering stays visible. diff --git a/packages/support/invariants/README.md b/packages/support/invariants/README.md index 661e073d13..d9bb74769b 100644 --- a/packages/support/invariants/README.md +++ b/packages/support/invariants/README.md @@ -56,6 +56,8 @@ A seeded or forked session arrives with events already in its log because constr None, as this observer only validates events and frozen requests and never rewrites prompts, schemas, messages, or streams. +**KV Cache effect**: None; this package neither assembles nor sends a provider request. + ## Known Limitations and Deferred Work - **The request-reconstructability assertion covers loop-built requests only** — hand-built one-shots (e.g. compaction's summarize call) carry no live `sessionId` marker and are skipped. diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index b256ef9a59..2134e722a7 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -56,6 +56,8 @@ Named `name` / `inject` / `Config` / `apply`, with **no default export**: the co None, as this keyless test adapter sends no request to a provider model; it only replays recorded assistant chunks into the test loop. +**KV Cache effect**: None; this package neither assembles nor sends a provider request. + ## Known Limitations and Deferred Work - **First-call-order script binding assumes sequential delegation** — a cut that runs sibling subagents concurrently (or a compaction summarize call landing mid-run) would bind live sessions to recorded scripts non-deterministically; a stronger keying is deferred until such a scenario exists (`XXX(concurrent-subagents)`). diff --git a/packages/support/loader-smoke/README.md b/packages/support/loader-smoke/README.md index 0b783efc0d..bdb25180ca 100644 --- a/packages/support/loader-smoke/README.md +++ b/packages/support/loader-smoke/README.md @@ -10,6 +10,8 @@ This is support-tier test infrastructure, not product API. None, as this test-only harness boots example processes and inspects their streams without changing an assembled model request. +**KV Cache effect**: None; this package neither assembles nor sends a provider request. + ## Known Limitations and Deferred Work - **Built mode requires a prior build** — the config must also resolve every named package upward through `examples/node_modules`. diff --git a/packages/tasks/tasks/README.md b/packages/tasks/tasks/README.md index b061038714..90946c2728 100644 --- a/packages/tasks/tasks/README.md +++ b/packages/tasks/tasks/README.md @@ -26,6 +26,8 @@ See the [task type catalog](../../../docs/core-data-structures/tasks.md) and [ru Indirectly, through producer plugins and [`dsh-tool-tasks`](../tool-tasks/README.md), which render task ids, output, status, cancellation, and completion notices. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Tasks are process-local** — durable or cross-restart execution needs a separate lifecycle. diff --git a/packages/tasks/tool-tasks/README.md b/packages/tasks/tool-tasks/README.md index 520a874df1..cd62770a93 100644 --- a/packages/tasks/tool-tasks/README.md +++ b/packages/tasks/tool-tasks/README.md @@ -31,6 +31,8 @@ A default above the cap fails at load. **Token effect**: Small fixed input cost per request while active. +**KV Cache effect**: Prefix-stable while the plugin scope and guidance text are unchanged. Activation or disposal may invalidate reuse from this prompt section. + #### Background-task guidance ```markdown @@ -43,12 +45,16 @@ Track every background task id you start. You are notified in-session when a tas **Token effect**: Fixed schema cost on each request where the tools are visible. +**KV Cache effect**: Prefix-stable while tool definitions and visibility are unchanged. Registration lifecycle or scoped restrictions may invalidate reuse from the first changed schema token. + ### Results and notices **What the model sees**: Reads return output or `(no new output)` followed by `[status: ]` and optional detail. An empty list returns `(no background tasks)`. Kill returns `requested cancellation of task ` or the existing terminal status. Unreported owned completion uses the notice above. **Token effect**: Results and notices remain in parent history until compaction. Stream reads do not repeat consumed output. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Completion notices do not wake idle agents** — callers needing an immediate result must use `task_output`. diff --git a/packages/timeout/timeout-policy/README.md b/packages/timeout/timeout-policy/README.md index 474185a4eb..37fd75ad01 100644 --- a/packages/timeout/timeout-policy/README.md +++ b/packages/timeout/timeout-policy/README.md @@ -41,6 +41,8 @@ Multiple `tools/execute` listeners compose by cordis registration order. Combine **Token effect**: Zero tokens on non-timeout calls. A timeout adds one small retained error result and can prevent a larger late provider result from entering context. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Cooperative, never a hard kill** — the deadline only notifies via `exec.signal`; a tool that ignores the signal does not stop on timeout (see § Cooperative, not a hard kill). diff --git a/packages/todo/tool-todo/README.md b/packages/todo/tool-todo/README.md index f6097abe96..9517f70e5e 100644 --- a/packages/todo/tool-todo/README.md +++ b/packages/todo/tool-todo/README.md @@ -32,12 +32,16 @@ A function/namespace plugin: it exports `name` / `inject` / `apply` and NO defau **Token effect**: Fixed schema cost on every request where the tool is visible. +**KV Cache effect**: Prefix-stable while the definition and visibility are unchanged. Plugin lifecycle or scoped restrictions may invalidate reuse from this schema. + ### Tool-call history and result **What the model sees**: Each assistant tool call retains the entire replacement list in its arguments. Success returns exactly `Updated todo list: pending, in progress, completed.` Stable failures are ``Error: invalid todo: `content` must be a non-empty string``, `Error: invalid todos: duplicate content ""`, `Error: invalid todos: at most one task may be in_progress, got `, and `Error: todo_write requires an owning agent session`. The full `todo/write` session event is UI and replay state, not a second model message. **Token effect**: Token growth scales with every full list the model submits, and those call arguments remain until compaction. The result itself is small and fixed-shape. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **Single-owner scope only** — the list belongs to the one calling agent session; subagent/shared/swarm scopes are a deliberate cut (see § Single owner), and a non-agent caller is rejected. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 4e19313302..11d3befbd6 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -98,30 +98,40 @@ The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loa **Token effect**: Prompt tokens are data-dependent and remain in that session's history until compaction. Concurrent ACP sessions keep separate contexts. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Human answers and permission decisions **What the model sees**: When optional consumers are loaded, ACP form answers become the exact JSON shape documented by `dsh-tool-ask-user`. Failures become `Error: ACP user questions must come from an agent-owned request`, `Error: ACP user question has no matching session`, `Error: ACP elicitation request failed`, `Error: ask_user_question was cancelled by the user`, `Error: ask_user_question returned no answer`, or `Error: ask_user_question was aborted before the user answered`. Permission decisions control whether another tool yields success or denial. ACP tool cards, terminal output, diffs, and streamed session updates are UI-only. **Token effect**: Answer, error, and denial text enters context only through the owning tool result; presentation metadata adds zero model tokens. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Permission preset switches **What the model sees**: `session/set_config_option` emits no model message itself. When `dsh-permission` is composed, the bridge writes the selected preset through that service; the resulting model-visible policy prompt and change notice belong to [`dsh-user-approval`](../user-approval/README.md), while sandbox-mode effects belong to [`dsh-tool-bash`](../../bash/tool-bash/README.md). The ACP `Permissions` select, its option descriptions, pending idle value, and refreshed config response remain client-only. **Token effect**: Zero direct tokens from the ACP option or the log-only `permission/preset` event. Downstream cost is limited to the owning plugins' policy prompt, conditional retained change notice, and any changed tool outcome. +**KV Cache effect**: The ACP option and log event cause no direct invalidation. The downstream policy-prompt change may invalidate reuse from that system section, while its change notice appends to history. + ### Model switches **What the model sees**: The ACP selector itself emits no message. The selected provider/model pair supplies the next step's `{{provider}}` / `{{model}}` prompt variables and request routing together; all other call-config fields continue through the `agent/request` waterfall unchanged. **Token effect**: The selector adds no direct tokens. A changed model may tokenize the same retained prompt/history differently, and any persona text that interpolates provider or model changes accordingly. +**KV Cache effect**: Switching provider or model selects a different cache domain. If the persona interpolates either value, the rendered system prompt also changes and prevents reuse from its first changed token. + ### Loaded sessions **What the model sees**: `session/load` resumes the persisted log, after which the loop sends its reconstructed history and request header. Replaying that log to the editor is not an extra model message. **Token effect**: Restored context has the persistence and session packages' normal retained cost; ACP replay to the client adds none. +**KV Cache effect**: Loading does not rewrite the stored log, but the next request is reconstructed under the current envelope and route. Reuse requires that reconstruction to match; ACP replay to the client has no cache effect. + ## Known Limitations and Deferred Work - **`additionalDirectories`** — rejected. A session operates in its single `cwd` (see Per-session cwd); widening the tool/filesystem scope to extra roots is a separate sandbox concern, not yet implemented. diff --git a/packages/ui/app-boot/README.md b/packages/ui/app-boot/README.md index 5fed7b5023..d0512d4047 100644 --- a/packages/ui/app-boot/README.md +++ b/packages/ui/app-boot/README.md @@ -20,6 +20,8 @@ This package carries no loader hooks and no dev-mode surface: the `dsh-scripts` Indirectly, through the plugin tree it loads, which determines the prompts, schemas, messages, and model adapter in the resulting application. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Bare package specifiers depend on Loader internals** — production bins need `node --expose-internals` or the Loader's optional native fallback; an in-process caller without either must use resolvable relative/file specifiers or tsx path mapping. diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 6666867598..d3f610b3d3 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -30,6 +30,8 @@ The plugin answers `shutdown`, disposes SDK-owned agents and subscriptions to qu **Token effect**: Data-dependent user-message tokens enter retained session history and are resent on later turns until another package compacts them. The JSON-RPC frames, session notifications, and server bookkeeping add zero model-context tokens. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **The wire has no per-session close or prompt-cancel method** — SDK-created agents remain live until process shutdown, and one accepted prompt runs to agent idle before that session accepts another. diff --git a/packages/ui/permission/README.md b/packages/ui/permission/README.md index bd37890dd1..35eda1c3ac 100644 --- a/packages/ui/permission/README.md +++ b/packages/ui/permission/README.md @@ -10,6 +10,8 @@ The service requires a confining `ctx.bash` executor and `ctx.approval`. A table Indirectly, through `dsh-user-approval` and `dsh-tool-bash`, which render the approval-policy prompt, switch notice, and sandboxed tool outcomes selected by this service's knob events; `permission/preset` itself is log-only. +**KV Cache effect**: No direct invalidation; the named consumer owns any request-prefix changes. + ## Known Limitations and Deferred Work - **Only two mechanism knobs are bundled** — presets select sandbox mode and approval policy; an agent/profile choice is not part of `PresetSpec` yet. diff --git a/packages/ui/stdio/README.md b/packages/ui/stdio/README.md index caaa779c6e..c606d20e30 100644 --- a/packages/ui/stdio/README.md +++ b/packages/ui/stdio/README.md @@ -29,12 +29,16 @@ The plugin seeds display labels from the live agent registry, then tracks `agent **Token effect**: Submitted text is retained under the agent loop's normal session-history and compaction rules. The welcome banner, `> ` prompt, rendered transcript, and `[tool call]` / `[tool result]` terminal lines add no tokens. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Terminal user-interaction answers **What the model sees**: When a consumer calls `ctx.userInteraction.ask()`, this provider renders the question in the terminal and returns selected option labels or `custom` text. Through `dsh-tool-ask-user`, closed stdin becomes `Error: ask_user_question cannot be answered because stdin is closed`; disposal or abort becomes `Error: ask_user_question was interrupted before the user answered`. **Token effect**: Waiting and terminal prompts add no tokens; the resolved answer or error is model-visible only through the calling tool or plugin's result. +**KV Cache effect**: Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ## Known Limitations and Deferred Work - **One configured session receives stdin** — the session/event renderer can print output from any session, but input lines always drive the configured `sessionId` rather than routing by the visible label. diff --git a/packages/ui/tool-ask-user/README.md b/packages/ui/tool-ask-user/README.md index 880b56ecc5..c1d920bff3 100644 --- a/packages/ui/tool-ask-user/README.md +++ b/packages/ui/tool-ask-user/README.md @@ -27,12 +27,16 @@ This is the consumer package for the user-interaction seam. It does not render U **Token effect**: Fixed schema cost on every request where the tool is visible. +**KV Cache effect**: Prefix-stable while the definition and visibility are unchanged. Plugin lifecycle or scoped restrictions may invalidate reuse from this schema. + ### Tool-call history and result **What the model sees**: The model's full questions remain in the assistant tool-call arguments. After the human answers, the next step sees compact JSON in the exact shape `{"answers":[{"id":"","selected":["