diff --git a/.agents/notes/archived/manifest.json b/.agents/notes/archived/manifest.json index 017fd32b27..1a814aac63 100644 --- a/.agents/notes/archived/manifest.json +++ b/.agents/notes/archived/manifest.json @@ -298,12 +298,18 @@ "process/2026-07-23-browser-demo-gif-recording.i18n.yaml": "sha256:808ccdda39e540645b440e40a2124baed737b98636265d8f6d8cf036a70f0d50", "process/2026-07-23-browser-demo-gif-recording.md": "sha256:4d3a3dc829c75b66f4f57a6a763b4b9562ce10efb90a19308142f598c5ea8524", "process/2026-07-23-browser-demo-gif-recording.zh.md": "sha256:409e5d31ea87f35c5227fcd1bd105167f580a8a24d29a223ce390b29eb31639a", + "process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml": "sha256:cbd5c32f2997713339699f4c12876b1950895fcb21594927c7509e3cb4c5b8d5", + "process/2026-07-23-personal-staging-maintenance-skills.md": "sha256:a1ef960ddc47c8bc14578d8432ed0ac4272e31178937780989e4e3b3e3f4d49f", + "process/2026-07-23-personal-staging-maintenance-skills.zh.md": "sha256:c0f3fcf0914af88cafcc7e094a2131bd1f764003defc6eaa446b743319e73ec1", "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.i18n.yaml": "sha256:89b6dc255cb0dd9d97ae6f34f37d185412d4260d7bf2f87d6b25e340f01dc26e", "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.md": "sha256:1742e09435ade4a09349c8843eb381e870a2be2d51b74449f08260422c8096b3", "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.zh.md": "sha256:220bd53a88617b09ee8970627c46540fa8951724b102acfe296a7ed7d0f7b5fe", "process/2026-07-27-wine-windows-gates-experiment.i18n.yaml": "sha256:6f4cbc12ee9cddbb297bf7e138ccabcd204f66898a0f7411b1633f03d5a9eab5", "process/2026-07-27-wine-windows-gates-experiment.md": "sha256:8d37dcdab058098c7de3da1de00ce61bef92bbc8d6ee71add959474c6fb3e936", "process/2026-07-27-wine-windows-gates-experiment.zh.md": "sha256:77fbf04df36af09e55007a93bd6b22d08ff99869efe8de3e97dac5b4701e0a9e", + "process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml": "sha256:e7d072856cd3df3b717d94647be4ea05db087b114df4b11d68a171677b94c970", + "process/2026-07-31-installer-adopts-existing-checkout.md": "sha256:d97e39d07bde30d534417a406fc6c56ee6765dbc7b671888d17ef2cac9a7c6dc", + "process/2026-07-31-installer-adopts-existing-checkout.zh.md": "sha256:ab445493c1aacf3f8dc091bdbd765ad56c551ae613e0d8156610f0c4614a7431", "process/2026-08-04-forward-only-pr-issue-status.i18n.yaml": "sha256:af23e203a66a95674154899410e2f420d1d0685dbf856c24cfccdaa547a17925", "process/2026-08-04-forward-only-pr-issue-status.md": "sha256:2d31077da47d95ab3ddf64d5efc6b1b8fb7c7709d39aca4a825ef9e9d382d501", "process/2026-08-04-forward-only-pr-issue-status.zh.md": "sha256:b61f865b7a8a0ac901250a3edbb92ea73177067c4c25448c7088925c2caeccd7", diff --git a/.agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml b/.agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml similarity index 66% rename from .agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml rename to .agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml index eb11cc1b92..ecf2ec52a1 100644 --- a/.agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml +++ b/.agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.md -2026-07-23-personal-staging-maintenance-skills.md: a7ccc5b1e0f13e880c58a93d2e4c2cd4f06e2a93 -2026-07-23-personal-staging-maintenance-skills.zh.md: 8593291f510352429cbb29679e7d033589312e41 +2026-07-23-personal-staging-maintenance-skills.md: 86654be1afe986107e7dae4440b497a266636012 +2026-07-23-personal-staging-maintenance-skills.zh.md: 7593a2e8cafc93df02c9418c94f84bbd3f154a0c diff --git a/.agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.md b/.agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.md similarity index 99% rename from .agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.md rename to .agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.md index a7ccc5b1e0..86654be1af 100644 --- a/.agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.md +++ b/.agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.md @@ -1,6 +1,7 @@ # Agent Note: Personal staging maintenance skills Status: implemented +Archived: 2026-08-10 English | [中文](2026-07-23-personal-staging-maintenance-skills.zh.md) diff --git a/.agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.zh.md b/.agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.zh.md similarity index 99% rename from .agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.zh.md rename to .agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.zh.md index 8593291f51..7593a2e8ca 100644 --- a/.agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.zh.md +++ b/.agents/notes/archived/process/2026-07-23-personal-staging-maintenance-skills.zh.md @@ -1,6 +1,7 @@ # Agent Note: 个人集成分支维护 skill Status: implemented +Archived: 2026-08-10 [English](2026-07-23-personal-staging-maintenance-skills.md) | 中文 diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml b/.agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml similarity index 66% rename from .agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml rename to .agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml index 1c58887b2b..c71f556ed2 100644 --- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml +++ b/.agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md -2026-07-31-installer-adopts-existing-checkout.md: 1d45a14273095610e3ed8047da2ce9f4ca95cbb6 -2026-07-31-installer-adopts-existing-checkout.zh.md: 971bc3b389c341b314872b8e45ab20ebd2ed5b2c +2026-07-31-installer-adopts-existing-checkout.md: 08eec47a1cf1254409df93ab83ddf503b4d7d171 +2026-07-31-installer-adopts-existing-checkout.zh.md: dc3cc5ee8dbbe287860ad02f4bdba66afb4fbeaf diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md b/.agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.md similarity index 99% rename from .agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md rename to .agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.md index 1d45a14273..08eec47a1c 100644 --- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md +++ b/.agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.md @@ -1,6 +1,7 @@ # Agent Note: the installer adopts an existing checkout into the managed layout Status: implemented +Archived: 2026-08-10 English | [中文](2026-07-31-installer-adopts-existing-checkout.zh.md) diff --git a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md b/.agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.zh.md similarity index 99% rename from .agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md rename to .agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.zh.md index 971bc3b389..dc3cc5ee8d 100644 --- a/.agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.zh.md +++ b/.agents/notes/archived/process/2026-07-31-installer-adopts-existing-checkout.zh.md @@ -1,6 +1,7 @@ # Agent Note: 安装器把已有检出接管进受管布局 Status: implemented +Archived: 2026-08-10 [English](2026-07-31-installer-adopts-existing-checkout.md) | 中文 diff --git a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml index f4fb753e79..92744d0ead 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml +++ b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md -2026-07-29-dsh-source-launch-tsx-esm.md: 5cf4a227f388a1ac8315594af4e0256864ef17f5 -2026-07-29-dsh-source-launch-tsx-esm.zh.md: b5a52b3d01840337c0091310e50d8fac34245519 +2026-07-29-dsh-source-launch-tsx-esm.md: b2428602a780f2880f0f803ba59b16a76b39790e +2026-07-29-dsh-source-launch-tsx-esm.zh.md: 866bc8886725788e6e619f9507f5c8ccab63f82d diff --git a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md index 5cf4a227f3..b2428602a7 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md +++ b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md @@ -14,11 +14,11 @@ Startup latency also mattered: the off-thread `module.register()` hooks worker s ## Decision -The `dsh` TUI, Web, and headless source launches run `node --import tsx/esm`: tsx's ESM-only hook owns both TypeScript transformation and tsconfig `paths` projection. `bin/dsh`, the root `dsh`/`demo:tui`/`demo:web` scripts, and the Code Mode TUI overlay use the same vector; `bin/dsh` references the hook and tsconfig by absolute checkout paths (bare `tsx/esm` does not resolve from an arbitrary cwd) and pins `TSX_TSCONFIG_PATH` to the root tsconfig. The CJS hook stays off because the CLI source graph is ESM-only; measured TUI time-to-banner is ~0.7s versus ~1.1s under the full tsx default and ~0.75s under the removed native chain. +The `dsh` TUI, Web, and headless source launches run `node --import tsx/esm`: tsx's ESM-only hook owns both TypeScript transformation and tsconfig `paths` projection. The root `dsh` script completes the repository build, then uses that vector from the repository root. The CJS hook stays off because the CLI source graph is ESM-only; measured runtime launch to the TUI banner is ~0.7s versus ~1.1s under the full tsx default and ~0.75s under the removed native chain. `scripts/tspath-loader.ts` and `apps/cli/src/tsconfig-paths-loader.ts` are deleted. With them went the loader's runtime rule of mapping a workspace import only for declared runtime dependencies — tsx applies the `paths` map unconditionally. Declaration completeness now rests on the static gates alone: `verify-cordis-config` for configured bare plugins, and workspace constraints for manifests. (That runtime rule found real bugs: `dsh-plan-mode` and `dsh-tool-tasks` imported `@deepseek-ai/dsh-llm` while declaring it only in devDependencies; since fixed.) -The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (`apps/cli/tests/source-launch.compat.spec.ts`): a keyless piped-stdio launch of the exact production vector asserting the non-zero-exit TTY refusal. Any future Node change to module hooks or TypeScript handling turns this gate red instead of breaking developers' `pnpm dsh`. +The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (`apps/cli/tests/source-launch.compat.spec.ts`): a keyless piped-stdio launch of the exact production runtime vector asserting the non-zero-exit TTY refusal. Any future Node change to module hooks or TypeScript handling turns this gate red instead of breaking developers' `pnpm dsh`. ## Alternatives considered @@ -35,4 +35,4 @@ The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (` - One launch vector across the whole engines range, including future Node lines that change native TypeScript support; the smoke gate enforces it per matrix line. - TypeScript transformation is delegated to tsx/esbuild again, reversing the prior note's goal of proving Node-native transformation; that goal is unreachable while vendored sources use non-erasable syntax and Node ships no transform mode. - The runtime declared-dependency enforcement in source launches is gone; undeclared workspace imports now surface only through static gates or built-mode resolution failures. -- Startup improves ~0.4s over the full tsx default (`demo:headless` now aliases the same `dsh --profile headless` source launch; ACP keeps `--import tsx` because its graph was not audited for CJS-hook dependence and its launch latency is not on the interactive path). +- Runtime launch improves ~0.4s over the full tsx default; ACP keeps `--import tsx` because its graph was not audited for CJS-hook dependence and its launch latency is not on the interactive path. diff --git a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md index b5a52b3d01..866bc88867 100644 --- a/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md +++ b/.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.zh.md @@ -14,11 +14,11 @@ Status: implemented ## 决策 -`dsh` 的 TUI、Web 与无头源码启动运行 `node --import tsx/esm`：由 tsx 的 ESM-only 钩子同时负责 TypeScript 转换与 tsconfig `paths` 投影。`bin/dsh`、根目录的 `dsh`/`demo:tui`/`demo:web` 脚本以及 Code Mode TUI overlay 使用同一向量；`bin/dsh` 以 checkout 的绝对路径引用钩子与 tsconfig（裸的 `tsx/esm` 无法从任意 cwd 解析），并将 `TSX_TSCONFIG_PATH` 固定到根 tsconfig。CJS 钩子保持关闭，因为 CLI 源码图是纯 ESM；实测 TUI 到 banner 约 0.7s，对比完整 tsx 默认形态约 1.1s、已移除的原生链约 0.75s。 +`dsh` 的 TUI、Web 与无头源码启动运行 `node --import tsx/esm`：由 tsx 的 ESM-only 钩子同时负责 TypeScript 转换与 tsconfig `paths` 投影。根目录的 `dsh` 脚本先完成仓库构建，然后从仓库根目录使用同一启动方式。CJS 钩子保持关闭，因为 CLI（命令行界面）源码图是纯 ESM；实测运行时启动至 TUI banner 耗时约 0.7s，对比完整 tsx 默认形态约 1.1s、已移除的原生链约 0.75s。 `scripts/tspath-loader.ts` 与 `apps/cli/src/tsconfig-paths-loader.ts` 已删除。随之消失的还有该 loader「仅为已声明运行时依赖映射 workspace import」的运行时规则——tsx 无条件应用 `paths` 映射。声明完整性现在仅由静态门禁保障：配置的裸插件走 `verify-cordis-config`，manifest（元数据清单）走 workspace constraints。（该运行时规则确实发现过真实缺陷：`dsh-plan-mode` 与 `dsh-tool-tasks` 导入 `@deepseek-ai/dsh-llm` 却只声明在 devDependencies；后已修复。） -node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（`apps/cli/tests/source-launch.compat.spec.ts`）：以精确的生产启动向量做 keyless 管道 stdio 启动，断言非零退出的 TTY 拒绝。未来 Node 对模块钩子或 TypeScript 处理的任何改动都会让该门禁变红，而不是破坏开发者的 `pnpm dsh`。 +node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（`apps/cli/tests/source-launch.compat.spec.ts`）：以精确的生产运行时启动向量做 keyless 管道 stdio 启动，断言非零退出的 TTY 拒绝。未来 Node 对模块钩子或 TypeScript 处理的任何改动都会让该门禁变红，而不是破坏开发者的 `pnpm dsh`。 ## 备选方案 @@ -35,4 +35,4 @@ node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（` - 整个 engines 范围（包括未来改变原生 TypeScript 支持的 Node 版本线）只有一个启动向量；冒烟门禁按矩阵行强制执行。 - TypeScript 转换重新委托给 tsx/esbuild，逆转了前一篇 Agent Note「证明 Node 原生转换可用」的目标；在 vendor 源码使用不可擦除语法且 Node 不再提供 transform 模式的情况下，该目标不可达。 - 源码启动中的运行时依赖声明强制不复存在；未声明的 workspace import 现在只能通过静态门禁或构建模式的解析失败暴露。 -- 启动相比完整 tsx 默认形态快约 0.4s（`demo:headless` 现为同一条 `dsh --profile headless` 源码启动命令的别名；ACP 保留 `--import tsx`，因为它的依赖图尚未就 CJS 钩子依赖性做审计，且其启动延迟不在交互路径上）。 +- 运行时启动相比完整 tsx 默认形态快约 0.4s；ACP（Agent Client Protocol）保留 `--import tsx`，因为它的依赖图尚未就 CJS 钩子依赖性做审计，且其启动延迟不在交互路径上。 diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml index ca61a3783c..678ae169cf 100644 --- a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md -2026-07-07-mcp-client-plugin.md: 756a5c4dc9f1152ecb1955d93b8dc47fcf07c661 -2026-07-07-mcp-client-plugin.zh.md: 9f45203c479379087c5a19eccce3ab7a339d4ed0 +2026-07-07-mcp-client-plugin.md: 077d978d8815d759574f89ed524ab3bc8c24a267 +2026-07-07-mcp-client-plugin.zh.md: 8f58c9359ca8447717cc353f97f1333370fa6fda diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md index 756a5c4dc9..077d978d88 100644 --- a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md @@ -153,13 +153,7 @@ Build the child environment from the subprocess seam's shared `scrubbedParentEnv ### Disconnection / crash -No auto-reconnect. If the MCP server process exits or the transport closes: - -1. The effect disposes → all registered tools are unregistered (fiber-scoped disposers). -2. Subsequent model calls to those tools → `ToolNotFoundError` → `isError: true`. -3. Recovery: user edits `cordis.yml` (triggers HMR reload) or restarts the harness. - -This matches the ACP subagent pattern: "crash = terminal, report error, clean up, don't retry." +A per-instance connection supervisor reconnects automatically after a lost connection with bounded exponential backoff and a per-outage attempt budget, re-running discovery on success; exhaustion unregisters the server's tools and stops until reload. The [auto-reconnect Agent Note](2026-08-06-mcp-client-auto-reconnect.md) owns that decision, including the `reconnect` config block and the `reconnect.enabled: false` opt-out that restores manual HMR/restart recovery. ## Alternatives considered @@ -173,7 +167,7 @@ Rejected. There is no foreseeable alternative MCP client implementation — MCP ### Auto-reconnect with exponential backoff -Rejected for v1. Adds complexity (partial-availability state where tools are registered but temporarily non-functional), and stdio process crashes usually indicate a configuration problem that retrying won't fix. HMR already provides the manual recovery path. Can be added as a future `reconnect: boolean` config if needed. +Rejected for v1: it added a partial-availability state (tools registered but temporarily non-functional), and stdio crashes often indicate configuration problems retrying cannot fix; HMR was the recovery path. Operational feedback reversed the deferral — the [auto-reconnect Agent Note](2026-08-06-mcp-client-auto-reconnect.md) implements it with a bounded per-outage budget and an opt-out. ### Bridge Resources and Prompts @@ -211,4 +205,4 @@ Coverage is named per tier; each behavior lives at the cheapest tier that can ex - **MCP SDK stability**: the `@modelcontextprotocol/sdk` is still evolving; breaking changes require updating the bridge. The version is pinned, and the SDK is widely adopted (Claude Desktop, Cursor, VS Code) so breaking changes are unlikely to be silent. - **Tool schema quality**: MCP servers may expose poorly-described tools (vague descriptions, incomplete JSON schemas). The harness passes them through as-is — garbage-in-garbage-out; that is the server author's responsibility, not the bridge's. - **Stdio process management**: a misbehaving MCP server that ignores signals could wedge dispose. The Cordis fiber disposal has bounded quiescence; a stuck transport eventually times out at the framework level. -- Crash recovery is manual (HMR edit or restart) — accepted for v1; a `reconnect` config remains open as future work. +- Crash recovery is automatic within the [reconnect budget](2026-08-06-mcp-client-auto-reconnect.md); manual reload remains the path after exhaustion or with `reconnect.enabled: false`. diff --git a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md index 9f45203c47..8f58c9359c 100644 --- a/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md +++ b/.agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.zh.md @@ -153,13 +153,7 @@ MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/sp ### 断连 / 崩溃 -不自动重连。如果 MCP 服务器进程退出或传输层关闭： - -1. effect dispose → 所有已注册工具被注销（fiber 作用域的 disposer）。 -2. 后续模型对这些工具的调用 → `ToolNotFoundError` → `isError: true`。 -3. 恢复：用户编辑 `cordis.yml`（触发 HMR 重载）或重启 harness。 - -这与 ACP subagent 模式一致：「崩溃即终态，报告错误，清理资源，不重试。」 +每个实例的连接监督器在连接丢失后以有界指数退避和单次故障尝试预算自动重连，成功后重新执行发现流程；尝试耗尽则注销该服务器的工具并停止，直到重新加载。[自动重连 Agent Note](2026-08-06-mcp-client-auto-reconnect.md) 拥有该决策，包括 `reconnect` 配置块和恢复手动 HMR/重启恢复的 `reconnect.enabled: false` opt-out。 ## 曾考虑的替代方案 @@ -173,7 +167,7 @@ MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/sp ### 指数退避自动重连 -v1 否决。引入复杂性（工具已注册但暂时不可用的部分可用状态），且 stdio 进程崩溃通常表明配置问题，重试无法修复。HMR 已提供手动恢复路径。如有需要，可在未来作为 `reconnect: boolean` 配置项添加。 +v1 否决：引入了部分可用状态（工具已注册但暂时不可用），且 stdio 崩溃往往表明配置问题，重试无法修复；HMR 曾是恢复路径。运营反馈扭转了该延期决定——[自动重连 Agent Note](2026-08-06-mcp-client-auto-reconnect.md) 以有界的单次故障预算和 opt-out 实现了自动重连。 ### 桥接 Resources 和 Prompts @@ -211,4 +205,4 @@ v1 否决。它能防止跨服务器冲突，但无法将 MCP 注册与原生 ha - **MCP SDK 稳定性**：`@modelcontextprotocol/sdk` 仍在演进中；破坏性变更需要更新桥接。版本已固定，且该 SDK 被广泛采用（Claude Desktop、Cursor、VS Code），因此破坏性变更不太可能悄然发生。 - **工具 schema 质量**：MCP 服务器可能暴露描述不佳的工具（模糊的描述、不完整的 JSON Schema）。harness 原样透传——垃圾进垃圾出；这是服务器作者的责任，不是桥接的。 - **Stdio 进程管理**：行为异常的 MCP 服务器如果忽略信号，可能卡住 dispose。Cordis fiber 的 dispose 具有有界的完全停稳过程；卡住的传输层最终会在框架层面超时。 -- 崩溃恢复是手动的（HMR 编辑或重启）——v1 已接受；`reconnect` 配置作为未来工作保持开放。 +- 崩溃恢复在[重连预算](2026-08-06-mcp-client-auto-reconnect.md)内自动进行；耗尽后或配置 `reconnect.enabled: false` 时回退为手动重新加载。 diff --git a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml index a08966f790..9d13851a0d 100644 --- a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml +++ b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md -2026-07-20-dsh-cli-personal-config.md: 02883c89f27e51d6091d4d65167ebdd6a96f6f51 -2026-07-20-dsh-cli-personal-config.zh.md: 6e56e892cf682ea514b036750e44dbb06e944a80 +2026-07-20-dsh-cli-personal-config.md: ed04725e92848bbab550a27ef2f4c021536f765e +2026-07-20-dsh-cli-personal-config.zh.md: cc97987f803f7fb513e94ce0ce079558f5e3dc75 diff --git a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md index 02883c89f2..ed04725e92 100644 --- a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md +++ b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md @@ -14,7 +14,7 @@ The entry modes and the personal file's name and location below are superseded b Two coupled pieces, aligned with the `apps/` assembly tier proposed by the `dsh web` PR (#443): -**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` is the product-assembly tier over `packages/*` libraries. One bin dispatches the default interactive TUI, `-p`/`--prompt` headless turns, and the `web` surface. The TUI boots `examples/tui-agent/cordis.yml` (or `--config`) with the invoking directory as the workspace. The committed `bin/dsh` launcher resolves the checkout through its own real path and runs the app with tsx's ESM hook; the [source-launch decision](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md) owns that contract. `pnpm run demo:tui` runs the same entry. +**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` is the product-assembly tier over `packages/*` libraries. One bin dispatches the default interactive TUI, `-p`/`--prompt` headless turns, and the `web` surface. The TUI boots `examples/tui-agent/cordis.yml` (or `--config`) with the invoking directory as the workspace. From a source checkout, the root `pnpm dsh` script builds the repository and runs the same entry with tsx's ESM hook; the [source-launch decision](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md) owns that contract. **Personal config (`dsh-app-boot`).** The personal overlay lives in the Harness home — `$DSH_HOME`, else `~/.dsh` — resolved by the shared [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md) (`@deepseek-ai/dsh-paths`), the same single root skills and AGENTS.md resolve against. The dsh TUI, Web, and headless surfaces consume its two optional files; the demo bins boot their committed trees verbatim: @@ -40,7 +40,7 @@ The TUI and Web register the exact personal path through Cordis HMR after boot. ## Consequences -- `dsh` from any directory (and `pnpm run demo:tui`) can apply personal providers, models, installed bundle entries, and other Loader entries with no checkout edit; verified end-to-end against a personal Anthropic proxy with Opus 4.8, including a bash tool round trip. +- An installed `dsh` command can run from any directory, while source users invoke `pnpm dsh` from the checkout; both can apply personal providers, models, installed bundle entries, and other Loader entries with no checkout edit. The behavior was verified end to end against a personal Anthropic proxy with Opus 4.8, including a bash tool round trip. - Because an id-targeted patch replaces the whole `config`, a personal override restates the base fields it keeps and can drift when the base entry changes shape; the loader's entry-not-found/name-mismatch warnings and [`dsh --dump-config`](../../../../apps/cli/README.md#profiles) (which prints the composed tree those patches produce) are the diagnostics. - Personal patches resolve ids against the booted file's own tree, so nested-include overlays (Code Mode) are not personalized; live-run parity for those leaves is deferred. - `dsh-app-boot` depends on `js-yaml` and imports the include's `!!js` YAML dialect (`entryListSchema`) directly, and, like `apps/cli`, depends on `@deepseek-ai/dsh-paths` for `resolveDshHome`. diff --git a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md index 6e56e892cf..cc97987f80 100644 --- a/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md +++ b/.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md @@ -14,7 +14,7 @@ Status: implemented 两个耦合的部分，与 `dsh web` PR（#443）提出的 `apps/` 装配层对齐： -**`dsh` CLI（`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 是位于 `packages/*` 库之上的产品组装层。一个 bin 负责分发默认交互式 TUI、`-p`/`--prompt` 无头轮次和 `web` 界面。TUI 以调用目录为 workspace，启动 `examples/tui-agent/cordis.yml`（或 `--config` 指定的配置）。已提交的 `bin/dsh` 启动器通过自身真实路径解析 checkout，并使用 tsx 的 ESM hook 运行应用；该约定由[源码启动决策](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)维护。`pnpm run demo:tui` 运行同一入口。 +**`dsh` CLI（命令行界面；`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 是位于 `packages/*` 库之上的产品组装层。一个 bin 负责分发默认交互式 TUI、`-p`/`--prompt` 无头轮次和 `web` 界面。TUI 以调用目录为 workspace，启动 `examples/tui-agent/cordis.yml`（或 `--config` 指定的配置）。在源码检出中，根目录的 `pnpm dsh` 脚本先构建仓库，再使用 tsx 的 ESM hook 运行同一入口；该约定由[源码启动决策](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)维护。 **个人配置（`dsh-app-boot`）。** 个人 overlay 存放在 Harness home——`$DSH_HOME`，否则 `~/.dsh`——由共享的 [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md)（`@deepseek-ai/dsh-paths`）解析，与 skills、AGENTS.md 解析所依据的单一根目录相同。dsh 的 TUI、Web 和无头界面使用其中两个可选文件；各示例 bin 仍然逐字节按已提交的配置树启动： @@ -40,7 +40,7 @@ TUI 和 Web 启动后通过 Cordis HMR（热模块替换）注册确切的个人 ## Consequences -- 在任意目录运行 `dsh`（以及 `pnpm run demo:tui`），无需修改 checkout，即可应用个人提供方、模型、已安装组合包的配置项和其他 Loader 配置项；已针对个人 Anthropic 代理与 Opus 4.8 端到端验证，包括一次 bash 工具往返。 +- 已安装的 `dsh` 命令可从任意目录运行，源码用户则从 checkout 调用 `pnpm dsh`；两者都无需修改 checkout 即可应用个人提供方、模型、已安装组合包的配置项和其他 Loader 配置项。该行为已针对个人 Anthropic 代理与 Opus 4.8 端到端验证，包括一次 bash 工具往返。 - 由于按 id 定位的补丁替换整个 `config`，个人覆盖必须复述它保留的基础字段，并可能随基础配置项形态变化而漂移；诊断手段是 loader 的「配置项未找到/名称不匹配」警告和 [`dsh --dump-config`](../../../../apps/cli/README.md#profiles)（打印这些补丁合成出的配置树）。 - 个人补丁只在被启动文件自身的树里解析 id，因此嵌套 include 的 overlay（Code Mode）不会被个性化；这些叶子的实际运行等价性暂缓。 - `dsh-app-boot` 依赖 `js-yaml`，并直接导入 include 的 `!!js` YAML 方言（`entryListSchema`）；与 `apps/cli` 一样依赖 `@deepseek-ai/dsh-paths` 以获取 `resolveDshHome`。 diff --git a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.i18n.yaml b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.i18n.yaml new file mode 100644 index 0000000000..2f6713b4ab --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md +2026-08-06-mcp-client-auto-reconnect.md: 99a8aec1abe3713822f8f17c17d8efaca5d61a4d +2026-08-06-mcp-client-auto-reconnect.zh.md: 8d4dc935e6edee9a05f556774e743e48234ca709 diff --git a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md new file mode 100644 index 0000000000..99a8aec1ab --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md @@ -0,0 +1,48 @@ +# Agent Note: MCP client auto-reconnect with bounded backoff + +Status: implemented + +English | [中文](2026-08-06-mcp-client-auto-reconnect.zh.md) + +## Problem + +The [MCP client](2026-07-07-mcp-client-plugin.md) connected once at plugin load. When a stdio server crashed or was killed, its registered tools stayed visible but every call failed with `Not connected` until a human edited the config (HMR) or restarted the Host — v1 explicitly deferred reconnection. Long-running hosts (ACP automation, web) cannot be bounced because a child process died, and for stdio the harness composition is the only party that can respawn it. External feedback escalated this as a real operational gap (issue #1746). + +## Decision + +`packages/mcp/mcp-client/src/connection.ts` owns a per-instance connection supervisor; `apply()` shrinks to config resolution plus two effects (the `serverName` reservation and the supervisor's lifecycle). The supervisor owns the client/transport generations, the live tool registrations, and the reconnect loop. + +**Trigger.** The supervisor arms `client.onclose` per generation. The SDK fires it when the stdio child exits, so a crash is observed without polling. `StreamableHTTPClientTransport` fires `onclose` only for deliberate closes — it owns its internal SSE-stream recovery and surfaces request failures per call — so HTTP servers are effectively outside supervisor restarts; the package README records that limitation. + +**Generations without interleaving.** Each attempt builds a fresh transport and `Client` (the SDK binds a Protocol to one transport for life). One per-supervisor queue serializes every `syncTools` call — initial syncs and `list_changed` re-syncs across all generations — and an `isCurrent` fence makes stale generations inert, so no two syncs can interleave the dispose-previous/register-next swap (which would double-dispose one generation and leak another). The queue also closes a pre-existing race where two rapid `list_changed` notifications re-synced concurrently. The activation attempt, rather than the first queue entrant, explicitly owns strict startup registration: an early `list_changed` notification uses contained re-sync semantics and cannot consume `failOnStartupError`. Failure signals are idempotent per generation: a connect rejection racing its own transport close schedules exactly one retry. A failed attempt cannot enter backoff until both `Client.close()` settles and the transport reports `onclose`, which for stdio proves the child exited; a missing close signal stops reconnection after the SDK's bounded termination window instead of allowing two server processes to overlap. Disposal uses the same bounded close-signal barrier and reports an incomplete shutdown without ever restarting. + +**Bounded backoff with an outage budget.** Delays double from `initialDelayMs` up to `maxDelayMs`. One outage shares `maxAttempts` consecutive failed attempts; exhaustion unregisters the server's tools, logs at error level, and stops until disposal or reload. A connection that survives past the stability window — `maxDelayMs`, derived rather than a fifth tunable, as the longest configured backoff spacing — resets the budget, so an occasionally-crashing server recovers indefinitely while a crash loop whose connects briefly succeed cannot launder its budget into a restart storm. + +**Config and resolution.** Both transports accept `reconnect { enabled, initialDelayMs, maxDelayMs, maxAttempts }` with schemastery defaults (on, 500ms, 30s, 10). `resolveReconnectPolicy()` is the explicit resolve step: it re-judges every bound and cross-field constraint because programmatic construction may bypass Schemastery, and misconfiguration fails the plugin instance at load. + +**Observable states.** An initial or retry-attempt failure says `connection failed`; an established generation ending says `connection lost`. Retrying logs at warn with attempt count and delay, recovery at info, final failure and disabled recovery at error. During an outage the last good generation stays registered and calls against it fail — deterministic public names mean a recovered unchanged tool list reproduces identical definitions, keeping the model-visible schema prefix stable instead of flapping. With `reconnect.enabled: false` a lost connection keeps the v1 manual-recovery behavior. + +**Disposal.** Dispose flips the fence, cancels any pending timer, closes the current client, then awaits the in-flight attempt and the sync queue before unregistering — quiescence, not just a request to stop. The reconnect timer is unref'd so a waiting backoff never holds a finishing process open. + +## Alternatives considered + +**Consecutive-failure counter that resets on every successful connect.** Rejected: a crash-looping server whose connects briefly succeed would reset the budget each cycle and restart forever — exactly the restart storm the failure cap exists to prevent. The uptime-gated reset distinguishes a recovered server from a looping one without new configuration. + +**Reuse one SDK `Client` across reconnects.** The Protocol clears its transport on close and can technically connect again, but the SDK's own guidance is one connection per Protocol instance, and reuse carries notification handlers and negotiated capability state across server incarnations. A fresh `Client` per generation plus the `isCurrent` fence is unambiguous. + +**Unregister tools immediately on disconnect, re-register on recovery.** Rejected: a transient outage would flap the model-visible tool list (two schema-prefix invalidations per crash) for no information gain; failing calls already signal the outage, and the swap on recovery is atomic per generation. Tools are unregistered at final failure so a permanently dead server does not leak permanently broken tools. + +**Route Streamable HTTP request failures into the supervisor.** Rejected for now: the HTTP transport already reconnects its SSE stream with its own backoff, per-request errors do not imply a dead server, and there is no child process the harness could respawn. Transport close stays the single trigger. + +**Restart through Loader/HMR machinery instead of an in-plugin supervisor.** Rejected: the Loader owns config-driven recomposition, not runtime health. A plugin restarting itself through the Loader would conflate config generations with connection generations and lose the per-outage budget. + +## Testing + +Unit (`tests/reconnect.spec.ts`, mocked SDK): recovery swaps generations without duplication or leaks and serves post-recovery calls, diagnostics distinguish initial or retry failure from established connection loss, strict startup registration survives a pre-connect `list_changed` notification, failed initialization waits for the old generation's close signal and fails closed when that signal never arrives, disposal waits for the same signal with a bounded incomplete-shutdown path, the failure cap unregisters tools and stops, dispose cancels a pending backoff and quiesces an in-flight sync, a close after dispose schedules nothing, disabled mode keeps the v1 behavior, the stability window resets the budget while a crash loop exhausts it, double failure signals schedule one retry, stale generations and handlers are inert, and `resolveReconnectPolicy` rejects each invalid bound. E2E (`tests/mcp-client.e2e.ts`, keyless): the fixture server gained a `crash` tool that replies then exits; real-process tests prove a stdio crash recovers end to end and that unloading the plugin mid-outage stops reconnection promptly. Snapshot: deliberately none, per the original note's rationale — reconnection adds no new presentation shape, and a snapshot composition spawning a crashing server would make replays timing-dependent. + +## Consequences + +- A crashed stdio MCP server recovers without human intervention: bounded backoff, re-discovery, atomic generation swap. Default policy retries an outage for roughly 2.5 minutes before giving up. +- Connection state is genuinely more intricate than connect-once — the partial-availability window v1 avoided now exists (registered tools failing during an outage), concentrated in one module with the invariants named. +- `reconnect` is new config surface on both transports, and the stability window is deliberately derived from `maxDelayMs`; making it independently tunable is a compatible future change. +- After final failure or with reconnect disabled, the plugin stays loaded with no (or failing) tools until reload — deliberate and logged, so a chronically broken server cannot restart forever. diff --git a/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.zh.md b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.zh.md new file mode 100644 index 0000000000..8d4dc935e6 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.zh.md @@ -0,0 +1,48 @@ +# Agent Note: MCP client auto-reconnect with bounded backoff + +Status: implemented + +[English](2026-08-06-mcp-client-auto-reconnect.md) | 中文 + +## 问题 + +[MCP 客户端](2026-07-07-mcp-client-plugin.md)在插件加载时仅连接一次。stdio 服务器崩溃或被终止后，其已注册的工具仍然可见，但每次调用均以 `Not connected` 失败，直到人工编辑配置触发 HMR（热模块替换）重载，或重启 Host——v1 明确推迟了重连机制。长时间运行的 Host（ACP 自动化、Web）不能因为子进程死亡就被重启；而对于 stdio 传输，harness 组合层是唯一能重新拉起子进程的一方。外部反馈将此升级为真实的运维缺口（issue #1746）。 + +## 决策 + +`packages/mcp/mcp-client/src/connection.ts` 拥有一个逐实例的连接监督器；`apply()` 收缩为配置解析加两个副作用（`serverName` 预留和监督器的生命周期）。监督器负责管理 client/transport 代、活跃的工具注册以及重连循环。 + +**触发条件。** 监督器在每一代上挂载 `client.onclose`。SDK 在 stdio 子进程退出时触发该回调，因此崩溃无需轮询即可感知。`StreamableHTTPClientTransport` 仅在主动关闭时触发 `onclose`——它内部拥有自己的 SSE（Server-Sent Events）流恢复机制，并将请求失败以逐调用方式暴露——因此 HTTP 服务器实际上不在监督器的重启范围内；包 README 记录了该限制。 + +**代隔离，无交错。** 每次尝试构建一个全新的 transport 和 `Client`（SDK 将一个 Protocol 绑定到一个 transport 上终身使用）。每个监督器内部有一个队列将所有 `syncTools` 调用串行化——跨所有代的初始同步和 `list_changed` 再同步——`isCurrent` 栅栏使过时的代变为惰性，从而确保不会有两次同步交错执行 dispose 上一代/注册下一代的切换（否则会对同一代执行两次 dispose 并泄漏另一代）。该队列还消除了一个先前存在的竞态：两次快速的 `list_changed` 通知同时触发重新同步。严格启动注册由激活尝试本身显式拥有，而非由首个入队者拥有；提前到达的 `list_changed` 采用故障隔离的再同步语义，不能消费 `failOnStartupError`。失败信号按代幂等：一次连接拒绝与其自身 transport 关闭竞态时，仅调度恰好一次重试。失败尝试只有在 `Client.close()` 结算且 transport 报告 `onclose` 后才能进入退避；对 stdio 而言，`onclose` 证明子进程已退出；若关闭信号始终未到，则在 SDK 的有界终止窗口结束后停止重连，而不是允许两个服务器进程重叠运行。dispose 使用同一个有界关闭信号屏障；若关停未完成则予以报告，且绝不重启。 + +**有界退避与故障预算。** 延迟从 `initialDelayMs` 起逐次翻倍，上限为 `maxDelayMs`。一次故障期间共享 `maxAttempts` 次连续失败尝试的预算；耗尽后注销该服务器的工具、以 error 级别记录日志并停止，直到 dispose 或重新加载。连接在存活超过稳定窗口——即 `maxDelayMs`，作为最长退避间隔从配置推导得出而非作为第五个独立调参项——之后重置预算；因此偶尔崩溃的服务器可无限恢复，而连接短暂成功后立即再次崩溃的循环无法将其预算洗白为重启风暴。 + +**配置与解析。** 两种传输均接受 `reconnect { enabled, initialDelayMs, maxDelayMs, maxAttempts }` 配置，Schemastery 默认值为（启用、500ms、30s、10）。`resolveReconnectPolicy()` 是显式的解析步骤：它重新校验每个边界值和跨字段约束，因为程序化构造可能绕过 Schemastery，配置错误在加载时即令插件实例失败。 + +**可观测状态。** 初始尝试或重试尝试失败时记录 `connection failed`，已建立的代结束时记录 `connection lost`；重试的 warn 日志包含尝试次数和延迟，恢复以 info 级别记录，最终失败和禁用重连时的断连以 error 级别记录。故障期间，上一个正常代保持注册，对其工具的调用返回失败——确定性公开名称意味着恢复后未变化的工具列表会复现相同的定义，保持模型可见 schema 前缀稳定而非反复抖动。设置 `reconnect.enabled: false` 后，断连保持 v1 的手动恢复行为。 + +**资源释放。** dispose 翻转栅栏、取消待执行的定时器、关闭当前 client，然后等待正在进行的尝试和同步队列完成后再注销工具——完全停稳，而非仅发出停止请求。重连定时器使用 unref，因此等待中的退避不会阻止进程正常退出。 + +## 曾考虑的替代方案 + +**连续失败计数器，每次成功连接即重置。** 否决：连接短暂成功后立即崩溃的循环服务器会在每个周期重置预算并永远重启——恰恰是失败上限旨在防止的重启风暴。基于运行时间的重置能区分已恢复的服务器与循环崩溃的服务器，无需新增配置。 + +**跨重连复用同一个 SDK `Client`。** Protocol 在关闭时清除其 transport，技术上可以再次连接，但 SDK 自身的指导方针是每个 Protocol 实例对应一次连接，且复用会将通知处理器和已协商的能力状态带入新的服务器实例。每代创建全新 `Client` 加 `isCurrent` 栅栏的方式无歧义。 + +**断连时立即注销工具，恢复时重新注册。** 否决：短暂故障会使模型可见工具列表抖动（每次崩溃触发两次 schema 前缀失效），而无任何信息增益；失败的调用已足以标示故障，恢复时的切换按代原子执行。工具仅在最终失败时注销，确保永久死亡的服务器不会泄漏永久失效的工具。 + +**将 Streamable HTTP 请求失败路由到监督器。** 暂不采纳：HTTP 传输已使用自己的退避机制重连其 SSE 流，逐请求错误并不意味着服务器已死，且 harness 没有可重新拉起的子进程。transport 关闭仍是唯一触发条件。 + +**通过 Loader/HMR 机制重启，而非使用插件内监督器。** 否决：Loader 负责配置驱动的重组合，而非运行时健康管理。插件通过 Loader 重启自身会混淆配置代与连接代，并丢失逐故障预算。 + +## 测试 + +单元测试（`tests/reconnect.spec.ts`，mock SDK）：恢复在不产生重复或泄漏的前提下切换代并服务恢复后的调用、诊断区分初始或重试尝试失败与已建立连接丢失、严格启动注册在连接前收到 `list_changed` 通知后仍然生效、初始化失败会等待旧代的关闭信号，若该信号始终未到则停止重连、dispose 同样等待同一关闭信号，并在有界等待到期时报告关停未完成、失败上限注销工具并停止、dispose 取消待执行的退避并使进行中的同步完全停稳、dispose 后的关闭不调度任何操作、禁用模式保持 v1 行为、稳定窗口重置预算而崩溃循环耗尽预算、双重失败信号仅调度一次重试、过时的代和处理器为惰性、`resolveReconnectPolicy` 拒绝每个无效边界值。E2E（`tests/mcp-client.e2e.ts`，无需密钥）：fixture 服务器新增了一个 `crash` 工具（先回复再退出）；真实进程测试证明 stdio 崩溃端到端恢复，以及在故障期间卸载插件能立即停止重连。快照：刻意不做，原因与原 Agent Note 相同——重连不引入新的展示形态，而在快照组合中 spawn 崩溃服务器会使回放依赖时序。 + +## 后果 + +- 崩溃的 stdio MCP 服务器无需人工干预即可恢复：有界退避、重新发现、原子代切换。默认策略对一次故障大约重试 2.5 分钟后放弃。 +- 连接状态确实比一次性连接更复杂——v1 刻意回避的部分可用窗口现已存在（故障期间已注册工具返回失败），集中在一个模块中并命名了所有不变式。 +- `reconnect` 是两种传输上的新配置表面，稳定窗口刻意从 `maxDelayMs` 推导；将其设为独立可调参数是兼容的未来变更。 +- 最终失败后或禁用重连时，插件保持加载状态但无（或失败的）工具，直到重新加载——行为是刻意的且有日志记录，确保长期故障的服务器不能永远重启。 diff --git a/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.i18n.yaml b/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.i18n.yaml new file mode 100644 index 0000000000..9984adfa0f --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-08-web-background-task-display.md +2026-08-08-web-background-task-display.md: 558d0e26b3b8da83602296c5fdd0944886d4eab7 +2026-08-08-web-background-task-display.zh.md: 9c9f4643bb08c748381ede6bf585858ca1204ff7 diff --git a/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.md b/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.md new file mode 100644 index 0000000000..558d0e26b3 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.md @@ -0,0 +1,136 @@ +# Agent Note: Web background-task display + +Status: implemented + +English | [中文](2026-08-08-web-background-task-display.zh.md) + +## Problem + +`ctx.tasks` already runs every long-lived piece of work the harness starts in the background — `bash`, `pwsh`, `pty-send`, and one-shot background subagents — but its only reader was the model. [`dsh-tool-tasks`](../../../../packages/tasks/tool-tasks/README.md) exposes `task_list`, `task_output`, and `task_kill`, and nothing else observed the registry. + +A human at the Web client therefore could not see that a build was running, could not distinguish a finished task from a stuck one, and could not stop one. The only trace was the `run_in_background` tool card that printed a task id somewhere earlier in the transcript, and that card never updates again. + +The session header was already the place where per-session background activity lives: [`dsh-client-ui-subagent`](../../../../packages/client/ui-subagent/README.md) contributes the subagent catalog to `conversation.session.header.actions`. Placement was settled. What was missing was any channel at all that carried task state to a browser. + +## Decision + +Task state reaches the browser as **one whole-snapshot mux frame per session**, pushed at every registry commit point that changes what that session can see. The client keeps a last-wins mirror; a header action renders it. There is no RPC, no polling, and no client-side staleness bookkeeping. + +This ships the list alone. Per-task streamed output and a human-initiated cancellation are separate phases, and the channel is shaped so neither has to undo it. + +### Wire shape + +One frame in the mux stream: + +```ts ignore-check +| { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] } +``` + +`TaskView` is browser-safe and owned by the carrier at [`packages/host/apiproxy/src/api/tasks.ts`](../../../../packages/host/apiproxy/src/api/tasks.ts), alongside the other domain contracts, with its wire schema beside it in `tasks.schema.ts`: + +```ts +import type { TaskId } from '@deepseek-ai/dsh-tasks/brand' + +export interface TaskView { + id: TaskId + kind: string + label: string + status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed' + detail?: string + startedAt: number + finishedAt?: number +} +``` + +`TaskId` comes from the cordis-free [`@deepseek-ai/dsh-tasks/brand`](../../../../packages/tasks/tasks/src/brand.ts) leaf — the same arrangement as the `@deepseek-ai/dsh-llm/brand` import `api/subagents.ts` already uses, because the `dsh-tasks` root reaches `dsh-agent` and is unreachable from a client program even as a type. Like every other non-root subpath in this workspace, it carries an explicit `tsconfig.base.json` `paths` entry; without one the TypeRT analyzer resolves the specifier to `lib/types/` and rejects the reference as unexported. + +`kind` is `string` on the wire rather than `TaskKind`. The kind map is merge-extensible by producer plugins, so a client build cannot enumerate the closed set; presentation falls through a documented default for an unrecognized kind. + +Three `TaskSnapshot` fields are deliberately absent: `ownerSession` (the frame's `sessionId` already carries it), `reported` (an internal notice-delivery bit with no user meaning), and `outputLimitBytes` (producer-owned model-presentation policy). + +The frame carries a whole snapshot rather than a delta for the reason [`session/queue`](../../../../packages/host/apiproxy/src/api/events.ts) states for itself: start, kill, settlement, reconnect, and a second browser tab all converge through one authoritative value. A session's task set is single-digit; the frame is small. + +### The task-registry change feed + +`TaskService` owns one observation method: + +```ts ignore-check +abstract onTasksChanged(listener: TasksChangedListener): () => void +``` + +It fires **after** every commit that changes what `list(owner)` returns: registration at the end of `start()`, the `stopping` transition in `kill()`, settlement, and the removal `disposeOwner()` performs. An `undefined` owner means an unowned task changed, and therefore every caller's view changed. + +The listener is owner-granular rather than task-granular. The only consumer pushes whole snapshots, so a per-task record would be discarded on arrival — and a per-task feed cannot express the owner-disposal removal at all without inventing a tombstone status nothing else needs. + +`onTaskDone` is not a subset of this. It delivers the terminal record with the exact owner `Agent` under first-wins semantics that `dsh-tool-tasks` couples to `reported`; `onTasksChanged` is pure observation with no delivery meaning and marks nothing reported. Listener throws are contained and never awaited, matching `onTaskDone`, and each registration is an effect on the calling fiber. + +Service disposal deliberately announces nothing. Every `onTasksChanged` registration is an effect on the registry's own fiber, so the listeners are already gone by the time teardown clears the store; an observer learns the registry left through its own disposal, not through a final empty set. + +### The api-proxy carrier + +`mux()` subscribes `ctx.tasks.onTasksChanged` and pushes `session/tasks`; the subscription baseline rides next to the existing `session/subscribed` control frames, so a reconnecting client is current before it renders. + +Four rules the carrier keeps: + +- **Never resume.** A change push reads `tasks.list(owner)` with the exact `Agent` the listener supplied, which stays correct even while that owner's scope is tearing down and a lookup by id would already miss. The baseline instead reads `ctx.tasks.list(ctx.agents.get(session.id))` — the non-resuming registry read, where a session with no live Agent correctly yields only the unowned tasks. Neither path touches the [`api-remotes` Agent resolver](../../../../packages/api/remotes/src/agent-lookup.ts), which resumes a cold session as a side effect of lookup; listing must never revive a session the user merely scrolled past. +- **Fan out unowned changes.** An `undefined` owner pushes a fresh snapshot to every subscribed session, because unowned tasks are visible to every caller. +- **Stay optional.** The carrier reads `ctx.get('tasks')`. A composition without the registry emits no frames, and the client renders no entry point — the posture `sessionProjections` already has in this file. +- **Say nothing about nothing.** The baseline is pushed only for sessions whose list is non-empty, and an absent key on the client means an empty list. A change that empties a list still pushes `[]`, because that one transition is the only thing the client cannot infer from absence. + +### The client mirror + +`SessionListState` carries `tasksBySession: Readonly>`, owned by `SessionManager` and folded from the frame under last-wins, with an emptied set stored as an absent key so absence and `[]` are one representation. + +It lives on the list mirror rather than on `Session` for three reasons: the header action already reads list state through `useSessions`, nothing needs the pre-instantiation buffering `session/queue` requires (no composer behavior depends on tasks), and a later sidebar indicator gets the data without opening a second channel. + +Two clears keep it honest. On re-subscribe the manager drops the session's mirror — the rule `session/queue` already follows, because a fresh baseline is arriving and this generation sends none for an empty set, so a retained list would survive as a phantom. On `host/session-removed` it drops the mirror again: owner disposal already removed the records registry-side, but that lands on the mux stream while the removal frame rides the host stream, so the two have no relative order. + +### The header action + +[`@deepseek-ai/dsh-client-ui-task`](../../../../packages/client/ui-task/README.md) registers one entry in `conversation.session.header.actions`, ordered after the subagent catalog. Its own README owns the presentation contract; the decisions worth recording here are that the control does not render at all until the session has a task, that the live badge is omitted at zero so a history-only session keeps a quiet entry point, and that settled rows stay visible because a failed task's `detail` is the only place its failure is legible. + +A running one-shot background subagent therefore appears both there and in the subagent catalog. The two answer different questions — the catalog navigates into the child's transcript, this list is the only handle a cancellation can ever attach to — and suppressing `kind: 'subagent'` here would leave the cancellation phase with no entry point for exactly those tasks. + +### What this deliberately does not do + +**No web path calls `ctx.tasks.read()`.** It consumes the single output cursor, so a browser read would silently take bytes the model's `task_output` will never see. This is an invariant worth a test rather than a convention, because the failure is invisible at the call site. + +**No cancellation.** That phase owes a decision the seam does not currently answer: `kill()` marks terminal delivery reported, so a human interrupt written against today's contract would leave the model believing its task is still running. + +**No output watermark on the frame.** The output phase's delta channel is where an anchor field earns its place; one added now would have no reader. + +## Alternatives considered + +**Signal frame plus RPC pull, the subagent-catalog shape.** Push a payload-free `tasks-changed` signal, debounce, then re-read authoritative state over a unary RPC. This is what the subagent catalog does, and the cost is visible in [`SessionManager`](../../../../packages/client/runtime/src/client/sessions/manager.ts): `catalogInflight` for single-flight, `catalogStale` for a trailing re-pull when a membership frame lands mid-request, `updateCatalogActivity` patching loaded rows in place *and* writing into the in-flight request so a response older than the frame gets overwritten, `parentAvailableOverride` replaying a stale `false`, and a reconnect path re-pulling every open catalog. That apparatus exists because the catalog's authority is split — durable lineage from a projection, liveness sampled at response time — and tasks have no durable half to justify inheriting it. It also fails specifically at the moment the output phase cares about: a task settles, its output stream closes immediately, but status only arrives after debounce plus round-trip, so the UI shows a running task with a dead stream for that window. + +**Popover-scoped polling with no seam change.** Cheapest to build and the only option that avoids touching `TaskService`. It cannot support a resident count on the trigger without a resident poll, and both later phases need a real change feed anyway, so it buys a week and spends it back. + +**A session-projection unit over durable task events.** Projection units fold over committed session events, so this would first require task lifecycle to become durable — `task/started` … `task/settled` as a standalone open/close bracket, with the last [`session/end-seed`](../../../../packages/core/session/src/types.ts) marking any unmatched opener as dead history, exactly as the compaction bracket already does. It is genuinely cheaper on the client: `dsh-tool-todo` shows the whole pattern in a fifteen-line unit, and the existing `session/projection` frames, history-tail block, and persisted checkpoint cache would have carried the data with no new wire surface, no carrier subscription, and no manager state. It was rejected because it buys that with a durable format change in service of a browser list, and because it does not extend to the phase it would most need to: [`spill/`](../../../../packages/spill/README.md) exists precisely so oversized tool output stays out of the log, so streamed task output cannot ride durable events either way. Nothing here forecloses revisiting it if durable task history becomes valuable on its own merits. + +**Reusing `PublicTaskSnapshot` from `dsh-tool-tasks`.** Nearly the right fields, but it belongs to the model-facing control surface. A wire type a browser program imports from a tool package couples client presentation to prompt-facing decisions and drags a host-only package into a client build. + +**Folding tasks into the subagent catalog as one "activity" panel.** One entry point instead of two. Rejected because `SubagentCatalogAction` is already 605 lines whose subject is a durable session-lineage tree including finished children; process-scoped tasks are a second data model with different identity, lifetime, and affordances, and the catalog's lazily-expanded branch, duration, and token contracts would all need rewriting to host them. + +**A host-global task list across every session.** The literal reading of "show all running tasks". Rejected because the registry's authorization fence is per-owner-session, so a global read needs a new access rule, and a global list has no business in a session's header — it would need its own home in the sidebar. Nothing in this design blocks adding it later; the per-session frames are the same data. + +## Testing + +The [web e2e scenario](../../../../apps/web/tests/background-task-list.e2e.ts) is the end-to-end proof and runs keyless: a real `run_in_background` bash call registers with `ctx.tasks`, the header count and row appear with no user interaction, and killing the task through the registry flips the open list to its producer detail. It asserts the whole delivery path rather than any single layer. + +Below it, [`tasks-local`](../../../../packages/tasks/tasks-local/tests/tasks.spec.ts) pins the change feed at all four commit points, its containment of a throwing observer, and its removal on both explicit disposal and fiber teardown; [`api-proxy-tasks`](../../../../packages/host/apiproxy/tests/api-proxy-tasks.spec.ts) pins the baseline-only-when-non-empty rule, the three change pushes, the dropped internal fields, the unowned fan-out, the no-resume guarantee, and the registry-absent composition; and the client suites pin the last-wins fold, the absent-key representation, both clears, and the component's ordering, duration, and dismissal behavior. + +## Consequences + +**A missed commit point leaks rows.** If `disposeOwner()` removal ever stops firing the feed, the client keeps tasks that no longer exist until the session disappears. The whole-snapshot shape makes this recoverable rather than corrupting — the next legitimate change repairs the list — but the disposal path is the one most easily forgotten, so it carries its own test. + +**Unowned-task fan-out is easy to under-implement.** Pushing only to the changed owner's session is correct for owned tasks and silently wrong for unowned ones, which are visible everywhere. The bug would surface only in compositions that create unowned tasks, which is why the carrier suite covers it directly. + +**The UI set is not the registry's set.** The header shows what one session can see, so a task owned by another session never appears in it even though the registry holds it — and because the registry is process-local, a restart empties every list while the transcript still shows the `run_in_background` cards that started them. Unowned tasks are the opposite case: they reach every session's list, exactly as `list(caller)` reports them to every caller. + +**Settled rows accumulate.** The registry retains settled tasks until owner disposal, so a long session with many background commands grows a long list. Capping the settled tail is a presentation change, not a protocol one, if it becomes a real complaint. + +**`stopping` is nearly unreachable today.** Only the model's `task_kill` produces it, so the state is rendered but rarely seen until human cancellation lands. It is in the union now because leaving a status out would have made that phase a wire change. + +**Two entry points for one running subagent.** Accepted deliberately, and bounded to one-shot background delegations. If it reads as noise in practice, the fix is presentational — the catalog row can cite the task rather than the task list hiding the kind. + +**A new non-root subpath needs its `paths` entry.** `@deepseek-ai/dsh-tasks/brand` had to be registered in `tsconfig.base.json` before the TypeRT analyzer would accept the reference. The failure mode is a confusing "not exported by" error from a generator far from the edit, so the entry is part of adding a subpath, not an optimization. diff --git a/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.zh.md b/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.zh.md new file mode 100644 index 0000000000..9c9f4643bb --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-08-web-background-task-display.zh.md @@ -0,0 +1,136 @@ +# Agent Note: Web 后台任务展示 + +Status: implemented + +[English](2026-08-08-web-background-task-display.md) | 中文 + +## 问题 + +`ctx.tasks` 已经承载了 harness 在后台启动的全部长时工作——`bash`、`pwsh`、`pty-send`，以及一次性后台 subagent——但它唯一的读者是模型。[`dsh-tool-tasks`](../../../../packages/tasks/tool-tasks/README.md) 暴露了 `task_list`、`task_output` 和 `task_kill`，除此之外没有任何东西观察这个注册表。 + +于是 Web 端的人类看不到构建正在跑，分不清一个任务是已经完成还是卡死，也无法把它停掉。唯一的痕迹是 transcript 里更早某处那张打印了 task id 的 `run_in_background` 工具卡片，而那张卡片此后再也不会更新。 + +会话 header 本来就是每会话后台活动的落点：[`dsh-client-ui-subagent`](../../../../packages/client/ui-subagent/README.md) 把 subagent 目录贡献到 `conversation.session.header.actions`。位置没有争议。缺的是任何一条把任务状态送到浏览器的通道。 + +## 决策 + +任务状态以**每会话一帧的整份快照**到达浏览器，在注册表每一个会改变该会话可见内容的提交点推出。客户端保持一份 last-wins 镜像，由一个 header 入口渲染。没有 RPC，没有轮询，客户端不需要任何过期状态管理。 + +本次只交付列表。每个任务的流式输出与人类发起的中断是各自独立的阶段，而通道的形状让两者都不必推翻它。 + +### 线路形状 + +mux 流中的一帧： + +```ts ignore-check +| { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] } +``` + +`TaskView` 是浏览器安全类型，由载体在 [`packages/host/apiproxy/src/api/tasks.ts`](../../../../packages/host/apiproxy/src/api/tasks.ts) 里拥有，与其他领域契约并列，线路 schema 就在旁边的 `tasks.schema.ts`： + +```ts +import type { TaskId } from '@deepseek-ai/dsh-tasks/brand' + +export interface TaskView { + id: TaskId + kind: string + label: string + status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed' + detail?: string + startedAt: number + finishedAt?: number +} +``` + +`TaskId` 取自不依赖 cordis 的 [`@deepseek-ai/dsh-tasks/brand`](../../../../packages/tasks/tasks/src/brand.ts) 叶子——与 `api/subagents.ts` 已经在用的 `@deepseek-ai/dsh-llm/brand` 导入是同一种安排，因为 `dsh-tasks` 根出口会牵到 `dsh-agent`，即便只作类型也无法被客户端程序触及。和本仓库其他每一个非根子路径一样，它带有显式的 `tsconfig.base.json` `paths` 条目；没有这一条，TypeRT 分析器会把该 specifier 解析到 `lib/types/` 并判定该引用未被导出。 + +线路上的 `kind` 是 `string` 而非 `TaskKind`。kind 映射由生产者插件按声明合并扩展，客户端构建无法枚举这个闭集；遇到无法识别的 kind，呈现层走一条有文档的默认分支。 + +`TaskSnapshot` 的三个字段被刻意省去：`ownerSession`（帧的 `sessionId` 已经带了）、`reported`（内部的通知投递位，对用户无意义），以及 `outputLimitBytes`（生产者拥有的模型呈现策略）。 + +这一帧带整份快照而非增量，理由就是 [`session/queue`](../../../../packages/host/apiproxy/src/api/events.ts) 为自己写下的那条：启动、中断、结算、重连，以及第二个浏览器标签页，全都通过同一个权威值收敛。一个会话的任务集是个位数，帧很小。 + +### 任务注册表变更订阅 + +`TaskService` 拥有一个观察方法： + +```ts ignore-check +abstract onTasksChanged(listener: TasksChangedListener): () => void +``` + +它在每一个会改变 `list(owner)` 返回内容的提交点**之后**触发：`start()` 末尾的注册、`kill()` 里转入 `stopping`、结算，以及 `disposeOwner()` 执行的移除。`owner` 为 `undefined` 表示一个无主任务发生了变化，因而每一个调用方的视图都变了。 + +监听器按 owner 而非按任务分粒度。唯一的消费方推的是整份快照，逐任务记录到手即弃——而且逐任务的订阅根本无法表达 owner 销毁时的移除，除非发明一个别处都不需要的墓碑状态。 + +`onTaskDone` 不是它的子集。后者按 first-wins 语义投递终态记录和确切的 owner `Agent`，`dsh-tool-tasks` 把这套语义与 `reported` 绑在一起；`onTasksChanged` 是纯观察，不含任何投递含义，也不把任何东西标为已上报。监听器抛错被包住且从不 await，与 `onTaskDone` 一致，每次注册都是调用方 fiber 上的 effect。 + +服务销毁刻意什么都不通告。每个 `onTasksChanged` 注册都是注册表自身 fiber 上的 effect，等到 teardown 清空 store 时监听器早已消失；观察者通过自己的销毁而不是一份最终空集来得知注册表离开了。 + +### api-proxy 载体 + +`mux()` 订阅 `ctx.tasks.onTasksChanged` 并推送 `session/tasks`；订阅 baseline 紧挨着既有的 `session/subscribed` 控制帧发出，让重连的客户端在渲染前就是最新的。 + +载体守着四条规则： + +- **绝不 resume。** 变更推送用监听器给出的确切 `Agent` 调 `tasks.list(owner)`，即使该 owner 的 scope 正在拆除、按 id 查找已经查不到，它依然正确。baseline 则读 `ctx.tasks.list(ctx.agents.get(session.id))`——不触发 resume 的注册表读法，没有活体 Agent 的会话正确地只得到无主任务。两条路径都不碰 [`api-remotes` 的 Agent 解析器](../../../../packages/api/remotes/src/agent-lookup.ts)，那个解析器会把查询变成复活冷会话的副作用；列个任务不该让用户随手划过的会话活过来。 +- **无主变更要扇出。** `owner` 为 `undefined` 时向每一个已订阅会话推一份新快照，因为无主任务对所有调用方可见。 +- **保持可选。** 载体读 `ctx.get('tasks')`。没有挂注册表的组合不发任何帧，客户端也就不渲染入口——`sessionProjections` 在这个文件里已经是这个姿态。 +- **没有就不说。** baseline 只为列表非空的会话推送，客户端上键缺失即表示空列表。把列表清空的那次变更仍然推 `[]`，因为这一个转换是客户端唯一无法从「缺失」推断出来的东西。 + +### 客户端镜像 + +`SessionListState` 带有 `tasksBySession: Readonly>`，由 `SessionManager` 拥有，按 last-wins 从帧折叠而来；被清空的集合存为缺失的键，使「缺失」与 `[]` 成为同一种表示。 + +它放在列表镜像而不是 `Session` 上，有三个理由：header 入口本来就通过 `useSessions` 读列表状态；没有任何东西需要 `session/queue` 那种实例化前的缓冲（没有 composer 行为依赖任务）；将来侧栏加指示器时不必再开第二条通道。 + +两处清理让它保持诚实。重新订阅时 manager 丢弃该会话的镜像——`session/queue` 已经遵循的规则，因为新的 baseline 正在路上，而这一世代对空集不发 baseline，被留下的列表会变成幽灵。`host/session-removed` 时再丢一次：owner 销毁在注册表侧已经移除了记录，但那件事落在 mux 流上而这一帧走 host 流，两者没有相对顺序。 + +### header 入口 + +[`@deepseek-ai/dsh-client-ui-task`](../../../../packages/client/ui-task/README.md) 在 `conversation.session.header.actions` 注册一个条目，排在 subagent 目录之后。呈现契约归它自己的 README；值得记在这里的决策是：会话没有任务时控件根本不渲染；活跃角标为零时省略，让只剩历史的会话保留一个安静的入口；终态行保持可见，因为失败任务的 `detail` 是其失败唯一可读之处。 + +因此一个运行中的一次性后台 subagent 会同时出现在那里和 subagent 目录里。两者回答不同的问题——目录负责进入子会话的 transcript，而这个列表是中断能力唯一可能附着的句柄——在这里屏蔽 `kind: 'subagent'` 会让中断那一期恰好对这批任务没有入口。 + +### 刻意不做的事 + +**没有任何 Web 路径调用 `ctx.tasks.read()`。** 它消费唯一的输出游标，浏览器读一次就悄悄拿走了模型 `task_output` 永远看不到的字节。这该是一条有测试兜底的不变量而不是一条约定，因为它的故障在调用点完全不可见。 + +**不做中断。** 那一期欠一个 seam 目前没有回答的决策：`kill()` 会把终态投递标为已上报，所以照今天的契约写出来的人类中断，会让模型一直以为它的任务还在跑。 + +**帧上不带输出水位。** 输出那一期的增量通道才是锚点字段该出现的地方；现在加就是一个没有读者的字段。 + +## 备选方案 + +**信号帧加 RPC 拉取，即 subagent 目录的形状。** 推一个无 payload 的 `tasks-changed` 信号，防抖后用一元 RPC 重读权威状态。subagent 目录就是这么做的，代价在 [`SessionManager`](../../../../packages/client/runtime/src/client/sessions/manager.ts) 里一览无余：`catalogInflight` 做单飞行、`catalogStale` 在成员帧落于请求中途时补一次尾拉、`updateCatalogActivity` 既就地打补丁又往在途请求里写一份好让比帧更旧的响应被覆盖、`parentAvailableOverride` 重放一个过期的 `false`，还有重连时逐一重拉每个打开的目录。这套装置之所以存在，是因为目录的权威被劈成两半——持久血缘来自投影，活跃度是响应时刻的采样——而任务没有持久的那一半，不该继承这份复杂度。它还恰好在输出那一期最在意的时刻失效：任务结算，输出流立即关闭，状态却要等防抖加一次往返才到，那段窗口里 UI 显示一个流已死的运行中任务。 + +**只在弹层打开时轮询，不改 seam。** 最省事，也是唯一不碰 `TaskService` 的选项。它无法在不常驻轮询的前提下支持触发器上的常驻计数，而后面两期反正都需要一条真正的变更订阅，所以它省下一周又还回去。 + +**基于持久任务事件的 session-projection 单元。** 投影单元在已提交的会话事件上折叠，所以这条路要先让任务生命周期变持久——`task/started` … `task/settled` 作为一对独立的开合括号，由最后一个 [`session/end-seed`](../../../../packages/core/session/src/types.ts) 把未配对的开括号标为死历史，与 compaction 括号已有的做法完全一致。它在客户端确实更省：`dsh-tool-todo` 用十五行的单元展示了整套模式，而现成的 `session/projection` 帧、history-tail 块和持久化 checkpoint 缓存本可以承载这批数据，无需新线路面、无需载体订阅、无需 manager 状态。否决它，是因为这要拿一次持久格式变更去换一个浏览器列表，而且它并不能延伸到最需要它的那一期：[`spill/`](../../../../packages/spill/README.md) 的存在正是为了让超大工具输出留在日志之外，所以流式任务输出无论如何都不能骑在持久事件上。如果持久任务历史将来凭自身价值站得住，本设计不阻挡重新考虑它。 + +**复用 `dsh-tool-tasks` 的 `PublicTaskSnapshot`。** 字段几乎就是对的，但它属于面向模型的控制面。浏览器程序从一个 tool 包导入线路类型，会把客户端呈现耦合到面向 prompt 的决策上，并把一个 host-only 包拖进客户端构建。 + +**并进 subagent 目录做成统一的「活动」面板。** 一个入口而不是两个。否决的理由是 `SubagentCatalogAction` 已经 605 行，其主题是含已结束子会话的持久会话血缘树；进程域的任务是第二套数据模型，身份、生命期和可用动作都不同，而目录的懒展开分支、时长与 token 契约全都要重写才能容纳它们。 + +**跨全部会话的 host 全局任务列表。**「显示所有运行中任务」的字面读法。否决是因为注册表的鉴权围栏是按 owner 会话的，全局读需要一条新的访问规则，而且全局列表不该出现在某个会话的 header 里——它需要侧栏里自己的位置。本设计没有阻挡后续再加；按会话的帧就是同一批数据。 + +## 测试 + +[web e2e 场景](../../../../apps/web/tests/background-task-list.e2e.ts)是端到端的证据，且无需密钥：一次真实的 `run_in_background` bash 调用注册进 `ctx.tasks`，header 的计数与行在没有任何用户操作的情况下出现，通过注册表杀掉该任务后打开着的列表翻到生产者给出的 detail。它断言的是整条投递链路，而不是其中某一层。 + +在它之下，[`tasks-local`](../../../../packages/tasks/tasks-local/tests/tasks.spec.ts) 钉住变更订阅的全部四个提交点、对抛错观察者的包容，以及显式销毁与 fiber 拆除两条路径上的注销；[`api-proxy-tasks`](../../../../packages/host/apiproxy/tests/api-proxy-tasks.spec.ts) 钉住「非空才发 baseline」、三次变更推送、被丢弃的内部字段、无主扇出、不 resume 的保证，以及没有注册表的组合；客户端各套件钉住 last-wins 折叠、缺失键表示、两处清理，以及组件的排序、时长与关闭行为。 + +## 影响 + +**漏掉一个提交点会漏行。** 如果 `disposeOwner()` 的移除有朝一日不再触发订阅，客户端会一直留着已经不存在的任务，直到会话消失。整份快照的形状让这件事可恢复而非损坏——下一次正当变更就修好了——但销毁路径是最容易被忘掉的一条，所以它自带测试。 + +**无主任务的扇出很容易做漏。** 只推给变更 owner 所在的会话，对有主任务是对的，对处处可见的无主任务则是悄悄错的。这个 bug 只会在会创建无主任务的组合里显形，所以载体套件直接覆盖了它。 + +**UI 的集合不等于注册表的集合。** header 显示的是「一个会话能看到什么」，所以别的会话拥有的任务在这里永远不出现，尽管注册表里有它；而由于注册表是进程本地的，一次重启会清空所有列表，transcript 里那些启动它们的 `run_in_background` 卡片却还在。无主任务是反过来的情形：它们会进入每一个会话的列表，正如 `list(caller)` 对每个调用方都报告它们。 + +**终态行会堆积。** 注册表把已结算任务留到 owner 销毁，所以一个跑了很多后台命令的长会话会积出长列表。如果真的成为抱怨，给终态尾巴加上限是呈现层改动而非协议改动。 + +**`stopping` 今天几乎不可达。** 只有模型的 `task_kill` 会产生它，所以这个状态会被渲染但在人类中断落地之前很少见到。现在就纳入联合类型，是因为把它留在外面会让那一期变成一次线路变更。 + +**一个运行中的 subagent 有两个入口。** 这是刻意接受的，且被限制在一次性后台委派这一种情况。如果实际用起来读着像噪声，修法是呈现层的——可以让目录行引用那个任务，而不是让任务列表隐藏这个 kind。 + +**新增非根子路径必须补 `paths` 条目。** `@deepseek-ai/dsh-tasks/brand` 得先登记进 `tsconfig.base.json`，TypeRT 分析器才会接受该引用。它的故障表现是一条来自远离改动处的生成器的、令人困惑的「not exported by」错误，所以这个条目是新增子路径的组成部分，而不是优化。 diff --git a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.i18n.yaml b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.i18n.yaml new file mode 100644 index 0000000000..dcd01fc6d3 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md +2026-08-10-minimal-read-image-tool.md: a43e53d70e98bac7a50aa6bbabbb1e177237df01 +2026-08-10-minimal-read-image-tool.zh.md: a94e4b296425ad50876b0b45a689442c896a85a1 diff --git a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md new file mode 100644 index 0000000000..a43e53d70e --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md @@ -0,0 +1,33 @@ +# Agent Note: A minimal read_image tool over existing seams + +Status: implemented + +English | [中文](2026-08-10-minimal-read-image-tool.zh.md) + +## Problem + +The multimodal attachment work gave user uploads a complete durable path — bytes committed to the content-addressed attachment store before the owning `user/message`, an `ImageBlock` carrying only the `sha256:` reference, and the pi-ai route re-reading verified bytes per request — but the model itself had no way to look at an image on disk. `read` rejects binary content by contract, so an agent asked about a screenshot or a rendered chart either failed or shelled out to lossy workarounds. A first standalone attempt (PR #598) solved this together with loop-level route scoping: an `agent/request-ready` extension point publishing exact-model modalities before assembly, per-route schema/guidance visibility, and a reversible `image-placeholder-v1` history projection so text routes could continue over placeholder text. That design worked but coupled a tool to new agent-loop machinery, three new session-log concepts, and per-step registration churn — far more surface than the capability needs. + +## Decision + +Ship the smallest tool that loads an image into the next request's context, entirely over existing seams; the withdrawn PR #598 design is the explicit counter-example this note records. + +- **`read_image` lives in `dsh-tool-fs`** beside `read`/`write`/`edit`. Extension selects the declared PNG/JPEG/WebP/GIF media type; the attachment store's magic-byte and pixel validation stays authoritative. Bytes travel `ctx.fs.stat` → bounded `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed`, and the tool result is the metadata envelope plus a real `ImageBlock` — `ToolResultBlock.content` already admits image blocks, the pi-ai adapter already renders them, and the Web host's model-switch guard already scans tool results, so nothing downstream changes. +- **`FileSystem.readBytes(target, signal, maxBytes)`** is a new required provider primitive: the byte bound lives at the seam so no backend can buffer an unbounded file, with the stat-size short-circuit and a one-byte-past-cap stream guard against post-stat growth (`FS_TOO_LARGE`). +- **Registration is composition-conditional, execution is route-gated.** The tool registers only under `ctx.inject(['attachments'], …)` — no store, no tool. At execution, before any I/O, the strict gate resolves the calling route (latest `request/header` config, falling back to agent options) through `ctx.llm.resolveModelInfo` and requires `image` in `inputModalities`; unknown capability refuses. A refusal is a plain `isError` result, so a text route's durable history never acquires an image block and the session cannot brick its own route. +- **Code Mode forwards the image out-of-band**: a nested dispatch returns the canonical value (execution-local, no image block) and defers a `user`-role context message carrying the envelope and image, so the picture still reaches the next request. +- **llm-replay models may declare `inputModalities`**, which is what lets the two keyless ACP snapshots pin both sides of the gate — the sha256-referenced success on an image-capable replay route and the verbatim refusal on a text-only one. + +## Alternatives considered + +- **PR #598's route-scoped design** (request-ready seam, per-route schema/guidance visibility, reversible history projection) — withdrawn in favor of this note's shape. What it bought: text routes could keep running after images entered history, and the tool disappeared from prompts where it cannot succeed. What it cost: agent-loop changes, three new durable concepts (`agent/request-ready`, `messageProjection`, availability notices), and registration that churned per step. The capability itself — see an image on the next request — never needed any of it. If per-route projection becomes a real requirement, that PR's history is the reference implementation. +- **`agent.inject()` instead of the image-bearing tool result** — routes the image around the tool result as a separate injected user message. Rejected: the image *is* the tool's result; splitting them adds a second logged message with no gain, and the tool-result path already works end to end. +- **Magic-byte sniffing instead of extension declaration** — sniffing duplicates detection the attachment store already owns (sharp-backed, authoritative). The extension is only a *declaration*; a mismatch fails closed with a rename remedy rather than being silently accepted, which also keeps the model's mental map (file name ↔ content) honest. +- **Registering unconditionally and failing on a missing store** — rejected; a deployment without an attachment store cannot ever satisfy the tool, so its schema would be a standing lie. The route gate, by contrast, is per-call state and correctly lives at the execution boundary. + +## Consequences + +- A text-only route refuses instead of degrading: no placeholder projection means no delegated-viewing story here — that is deliberately the next PR (subagent image readback rebuilt on the current subagent seams). +- The route gate races a concurrent model switch; the Web host's image-aware switch guard covers its surface, and other front doors own their equivalent. Recorded as a tool-fs Known Limitation. +- Repeated image results accumulate request-token cost until compaction; content addressing deduplicates bytes only. +- The tool-result card renders the durable reference, not pixels; inline preview is deferred to the UI packages. diff --git a/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.zh.md b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.zh.md new file mode 100644 index 0000000000..a94e4b2964 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.zh.md @@ -0,0 +1,33 @@ +# Agent Note: 基于既有 seam 的最小 read_image 工具 + +Status: implemented + +[English](2026-08-10-minimal-read-image-tool.md) | 中文 + +## 问题 + +多模态附件工作为用户上传建立了完整的持久路径：字节在所属 `user/message` 之前提交到内容寻址的附件存储，`ImageBlock` 只携带 `sha256:` 引用，pi-ai 路由在每次请求时重新读取并校验字节。但模型自己没有查看磁盘图像的手段。`read` 按约定拒绝二进制内容，因此被问到截图或渲染图表的 agent 要么失败，要么退到有损的变通做法。第一次独立尝试（PR #598）把这个问题与循环级路由作用域一起解决：新增在组装前发布确切模型模态的 `agent/request-ready` 扩展点、按路由控制 schema／指导可见性，以及可逆的 `image-placeholder-v1` 历史投影让文本路由能在占位符上继续。该设计可行，但让一个工具耦合了新的 agent-loop 机制、三个新的会话日志概念和每步的注册变动，远超这项能力本身的需要。 + +## 决定 + +只交付能把图像载入下一次请求上下文的最小工具，完全建立在既有 seam 之上；撤回的 PR #598 设计是本记录明确保留的反例。 + +- **`read_image` 放在 `dsh-tool-fs`**，与 `read`/`write`/`edit` 并列。扩展名选择声明的 PNG/JPEG/WebP/GIF 媒体类型；附件存储的魔数与像素校验保持权威。字节沿 `ctx.fs.stat` → 有界 `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed` 流动，工具结果是元数据信封加真正的 `ImageBlock`——`ToolResultBlock.content` 本就允许图像块，pi-ai 适配器本就会渲染它们，Web 宿主的模型切换防护本就会扫描工具结果，下游无需任何改动。 +- **`FileSystem.readBytes(target, signal, maxBytes)`** 是新的必备提供方原语：字节上限放在 seam 上，任何后端都无法无界缓冲文件；stat 大小先短路，随后的流最多多读一个字节以防 stat 之后的增长（`FS_TOO_LARGE`）。 +- **注册随组合条件挂载，执行按路由门禁。** 工具只在 `ctx.inject(['attachments'], …)` 作用域内注册——没有存储就没有工具。执行时在任何 I/O 之前，严格门禁通过 `ctx.llm.resolveModelInfo` 解析调用路由（最新 `request/header` 配置，缺失时回退到 agent 选项），要求 `inputModalities` 包含 `image`；能力未知即拒绝。拒绝是普通的 `isError` 结果，因此文本路由的持久历史绝不会出现图像块，会话不会毁掉自己的路由。 +- **Code Mode 以带外方式转发图像**：嵌套分派返回规范值（仅限本次执行，不含图像块），并延迟提交一条携带信封和图像的 `user` 角色上下文消息，图片仍会到达下一次请求。 +- **llm-replay 模型可以声明 `inputModalities`**，这正是两个 keyless ACP 快照能钉住门禁两侧的原因：图像路由上以 sha256 引用的成功结果，和纯文本路由上逐字的拒绝。 + +## 考虑过的替代方案 + +- **PR #598 的路由作用域设计**（request-ready 扩展点、按路由的 schema／指导可见性、可逆历史投影）——被本记录的形态取代后撤回。它换来的是：图像进入历史后文本路由仍能运行，工具在注定失败的提示词里消失。它付出的是：改动 agent-loop、三个新的持久概念（`agent/request-ready`、`messageProjection`、可用性通知）和每步变动的注册。而这项能力本身——下一次请求看到图像——从不需要这些。如果按路由投影将来成为真实需求，该 PR 的历史就是参考实现。 +- **用 `agent.inject()` 代替带图像的工具结果**——把图像绕过工具结果，作为单独注入的用户消息。拒绝：图像就是工具的结果；拆开只会多一条无收益的日志消息，而工具结果路径本就端到端可用。 +- **用魔数嗅探代替扩展名声明**——嗅探重复了附件存储已拥有的检测（基于 sharp，权威）。扩展名只是声明；不匹配时按改名修复提示失败关闭，而不是被静默接受，这也让模型对文件名与内容的对应保持诚实。 +- **无条件注册、缺存储时执行报错**——拒绝；没有附件存储的部署永远无法满足该工具，其 schema 会是常态谎言。相反，路由门禁是逐调用状态，正确的位置就是执行边界。 + +## 后果 + +- 纯文本路由得到拒绝而不是降级：没有占位符投影意味着这里没有委托查看的方案——那有意留给下一个 PR（基于当前 subagent seam 重建的 subagent image readback）。 +- 路由门禁与并发模型切换存在竞态；Web 宿主的图像感知切换防护覆盖其表面，其他前端拥有各自的等价防护。已记入 tool-fs 的已知限制。 +- 重复的图像结果在压缩之前持续累积请求 token 成本；内容寻址只去重字节。 +- 工具结果卡片渲染持久引用而非像素；内嵌预览延后到 UI 包处理。 diff --git a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.i18n.yaml b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.i18n.yaml index b60f3ae3ed..6f6823e3c3 100644 --- a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.i18n.yaml +++ b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md -2026-07-30-generated-third-party-notices.md: 58e3fd5007a16d6391956f423d1ec91e851df295 -2026-07-30-generated-third-party-notices.zh.md: 834ec4ebc349bdee37b0873109de566223bb7d48 +2026-07-30-generated-third-party-notices.md: d13eef8412ecd5c8387a7239b812c835671b6bce +2026-07-30-generated-third-party-notices.zh.md: 0af6a6bcd665197acd6a0b5e9e6f51940a0267e7 diff --git a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md index 58e3fd5007..d13eef8412 100644 --- a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md +++ b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md @@ -20,9 +20,9 @@ One trigger gap is accepted rather than worked around: lefthook inspects only fi The file discloses **direct** dependencies by default. The complete npm closure with pinned versions already lives in `pnpm-lock.yaml` (`pnpm licenses list` renders it) and the Python closure in `python/sdk/uv.lock`; re-materializing either as prose would be a second, worse copy. The one explicit transitive disclosure is the official Claude platform payload set declared by `@anthropic-ai/claude-agent-sdk` through `optionalDependencies`, because those packages carry the distributed Claude Code executable rather than ordinary library implementation detail. -**Tiering is by declaring area, not by manifest section.** A package is a runtime dependency when any manifest outside `DEV_ONLY_AREAS` — the root manifest, `packages/support/`, `packages/client/test-runtime/`, `website/`, `examples/`, `native/` — names it under `dependencies` or `optionalDependencies`. Section names alone are wrong in both directions: a test-support package declares `vitest` under `dependencies` without shipping it, and the `bin/dsh` launcher execs through `tsx`, which no manifest declares as a runtime dependency at all (the generator marks it runtime explicitly). +**Tiering is by declaring area, not by manifest section.** A package is a runtime dependency when any manifest outside `DEV_ONLY_AREAS` — the root manifest, `packages/support/`, `packages/client/test-runtime/`, `website/`, `examples/`, `native/` — names it under `dependencies` or `optionalDependencies`. Section names alone are wrong in both directions: a test-support package declares `vitest` under `dependencies` without shipping it, and the root source-run scripts execute through `tsx`, which no manifest declares as a runtime dependency at all (the generator marks it runtime explicitly). -The runtime tier deliberately covers **every mountable plugin**, not just what the CLI, Web UI, and Python runtime load by default. `scripts/install.sh` installs the repository itself, so a user's `cordis.yml` can mount any plugin package; `@modelcontextprotocol/sdk` and the OpenTelemetry packages reach real users even though no default assembly imports them. Under-disclosure is the costly direction for a legal notice. +The runtime tier deliberately covers **every mountable plugin**, not just what the CLI, Web UI, and Python runtime load by default. Source execution can mount any plugin package from a user's `cordis.yml`; `@modelcontextprotocol/sdk` and the OpenTelemetry packages therefore reach real users even though no default assembly imports them. Under-disclosure is the costly direction for a legal notice. The manifest set is derived from the `packages:` members the root `pnpm-workspace.yaml` declares, including the Landlock workspace and its public packages, so a new member area is read the day it is declared rather than the day someone remembers to extend a list. License and repository metadata come from the root workspace's installed pnpm store and package-local link farms, so the generator requires an installed tree and fails loud when a package resolves to neither, rather than emitting an empty cell. `OVERRIDES` carries the packages whose published manifest cannot answer — Rust-built npm bins that omit `license`, and the `modelcontextprotocol/servers` packages whose repository is mid MIT→Apache-2.0 relicensing, so their effective terms are per-contribution. A runtime dependency whose license is not on the permissive list is a hard error: shipping copyleft is a distribution decision, not something a regenerated table may absorb silently. Vendored packages are cross-checked against `vendor/README.md` and rejected if any is not MIT, and `pnpm-workspace.yaml`'s `patchedDependencies` are listed under the runtime table because pnpm applies those patches at install time — shipped artifacts carry modified copies of `@earendil-works/pi-tui` and `node-pty`, and the patch files are the record of what changed. diff --git a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md index 834ec4ebc3..0af6a6bcd6 100644 --- a/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md +++ b/.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md @@ -20,9 +20,9 @@ Status: implemented 文件默认只披露**直接**依赖。完整的 npm 闭包连同锁定版本已记录在 `pnpm-lock.yaml`（`pnpm licenses list` 可渲染），Python 闭包记录在 `python/sdk/uv.lock`；再用散文誊一遍只会得到一份更差的副本。唯一明确披露的传递依赖，是 `@anthropic-ai/claude-agent-sdk` 通过 `optionalDependencies` 声明的官方 Claude 平台载荷集合，因为这些包承载随产品分发的 Claude Code 可执行文件，而非普通的库实现细节。 -**分层依据是声明方所在区域，而非 manifest 字段名。** 只要 `DEV_ONLY_AREAS` 之外的任一 manifest——即根 manifest、`packages/support/`、`packages/client/test-runtime/`、`website/`、`examples/`、`native/` 之外——在 `dependencies` 或 `optionalDependencies` 里点名某个包，它就是运行时依赖。单看字段名在两个方向上都会出错：测试支撑包把 `vitest` 写在 `dependencies` 里却并不交付它；而 `bin/dsh` 启动器通过 `tsx` 执行，根本没有任何 manifest 把它声明为运行时依赖，只能由生成器显式标记。 +**分层依据是声明方所在区域，而非 manifest 字段名。** 只要 `DEV_ONLY_AREAS` 之外的任一 manifest——即根 manifest、`packages/support/`、`packages/client/test-runtime/`、`website/`、`examples/`、`native/` 之外——在 `dependencies` 或 `optionalDependencies` 里点名某个包，它就是运行时依赖。单看字段名在两个方向上都会出错：测试支撑包把 `vitest` 写在 `dependencies` 里却并不交付它；而根目录的源码运行脚本通过 `tsx` 执行，根本没有任何 manifest 把它声明为运行时依赖，只能由生成器显式标记。 -运行时层刻意覆盖**所有可挂载的插件**，而不止 CLI、Web UI 与 Python 运行时默认加载的那些。`scripts/install.sh` 安装的就是仓库本身，用户的 `cordis.yml` 可以挂载任何插件包；`@modelcontextprotocol/sdk` 与 OpenTelemetry 系列即使没有任何默认装配引入，也会触达真实用户。对法务披露而言，披露不足才是代价更高的那个方向。 +运行时层刻意覆盖**所有可挂载的插件**，而不止 CLI、Web UI 与 Python 运行时默认加载的那些。从源码运行时，用户可以通过 `cordis.yml` 挂载任何插件包；因此，`@modelcontextprotocol/sdk` 与 OpenTelemetry 系列即使没有任何默认装配引入，也会触达真实用户。对法务披露而言，披露不足才是代价更高的那个方向。 manifest 集合由根 `pnpm-workspace.yaml` 声明的 `packages:` 成员派生，其中包括 Landlock 工作区及其公开包，因此新增成员区域在声明当天就会被读取，而不必等谁想起来去补一份列表。许可证与仓库地址取自根工作区已安装的 pnpm store 和包本地链接场；某个包两处都解析不到时直接失败，而不是留下空单元格。`OVERRIDES` 收录已发布 manifest 答不上来的包：用 Rust 构建、发布时省略 `license` 字段的 npm 可执行包，以及 `modelcontextprotocol/servers` 系列——该仓库正处在 MIT 向 Apache-2.0 的重新许可过程中，实际条款按贡献逐条而定。运行时依赖的许可证若不在宽松清单内即为硬失败：交付 copyleft 是一项分发决策，不该被一次重新生成悄悄吸收。被源码收编的包会与 `vendor/README.md` 交叉核对，出现非 MIT 即报错；`pnpm-workspace.yaml` 的 `patchedDependencies` 列入运行时表格，因为 pnpm 在安装期就会打上这些补丁——交付产物携带的是改动过的 `@earendil-works/pi-tui` 与 `node-pty`，补丁文件本身就是改动的完整记录。 diff --git a/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.i18n.yaml index fac9ae9452..e72d9beaf3 100644 --- a/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.i18n.yaml +++ b/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.md -2026-08-08-remove-cli-demo.md: 31879e8284daf5f34af6731b09fce743f9eb5391 -2026-08-08-remove-cli-demo.zh.md: d4dfef1ba8c4d27cd667e319519cfa1ace74baef +2026-08-08-remove-cli-demo.md: f8bc09825797f2165c14a75e5841d74b2e1bc1af +2026-08-08-remove-cli-demo.zh.md: 1044dd136888e33fc9935cf4e24cd3100b41b41f diff --git a/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.md b/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.md index 31879e8284..f8bc098257 100644 --- a/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.md +++ b/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.md @@ -12,7 +12,7 @@ The replay suites still need canonical session events to pin assembled backend b ## Decision -Delete `@deepseek-ai/dsh-cli-demo` completely: its package, bin, parser, app plugin, output formats, tests, workspace references, generated-catalog entries, and active documentation. No alias or compatibility package remains. The root `demo:headless` script is retained only as a direct alias of `dsh --profile headless`; the product command owns final-text stdout, failure diagnostics on stderr, persistence, exit status, and shutdown. +Delete `@deepseek-ai/dsh-cli-demo` completely: its package, bin, parser, app plugin, output formats, tests, workspace references, generated-catalog entries, and active documentation. No alias or compatibility package remains. Source users invoke the product command through `pnpm dsh --profile headless`; it owns final-text stdout, failure diagnostics on stderr, persistence, exit status, and shutdown. `examples/headless-agent` becomes an explicit test composition. Its Loader configs mount `@deepseek-ai/dsh-agent-spine-demo`, one root agent, JSONL persistence, and checkpoint policy as separate rows instead of hiding them behind an app bundle. The support-tier `@deepseek-ai/dsh-loader-smoke` package owns the shared direct-agent turn helper; unexported example-local drivers select their Loader configuration and render canonical events as JSONL. They are launched only by tests, have no bin, and do not define a supported product output format. diff --git a/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.zh.md b/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.zh.md index d4dfef1ba8..1044dd1368 100644 --- a/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.zh.md +++ b/.agents/notes/implemented/simplification/2026-08-08-remove-cli-demo.zh.md @@ -12,7 +12,7 @@ Status: implemented ## 决策 -彻底删除 `@deepseek-ai/dsh-cli-demo`：包括它的包、bin、解析器、应用插件、输出格式、测试、workspace 引用、生成目录条目和现行文档。不保留别名或兼容包。根目录的 `demo:headless` 脚本仅作为 `dsh --profile headless` 的直接别名保留；stdout 上的最终文本、stderr 上的失败诊断、持久化、退出状态和关闭行为均由产品命令负责。 +彻底删除 `@deepseek-ai/dsh-cli-demo`：包括它的包、bin、解析器、应用插件、输出格式、测试、workspace 引用、生成目录条目和现行文档。不保留别名或兼容包。源码用户通过 `pnpm dsh --profile headless` 调用产品命令；stdout 上的最终文本、stderr 上的失败诊断、持久化、退出状态和关闭行为均由该命令负责。 `examples/headless-agent` 成为显式测试组装。其 Loader 配置把 `@deepseek-ai/dsh-agent-spine-demo`、一个根 agent（智能体）、JSONL 持久化和检查点策略挂载为独立配置行，不再将其隐藏在应用组合包之后。支持层的 `@deepseek-ai/dsh-loader-smoke` 包负责共享的直接 agent 轮次 helper；未导出的示例本地 driver 选择各自的 Loader 配置，并将规范事件渲染为 JSONL。这些 driver 只由测试启动，不提供 bin，也不定义受支持的产品输出格式。 diff --git a/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.i18n.yaml b/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.i18n.yaml new file mode 100644 index 0000000000..9920c09c11 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.md +2026-08-10-source-run-without-managed-installer.md: ac506b72acab0dd6c92ce6111487d091b2bf4a73 +2026-08-10-source-run-without-managed-installer.zh.md: 86e44a90a9e7b34ad37b6a4bfd3ad14de40868f5 diff --git a/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.md b/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.md new file mode 100644 index 0000000000..ac506b72ac --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.md @@ -0,0 +1,31 @@ +# Agent Note: Source run without a managed installer + +Status: implemented + +English | [中文](2026-08-10-source-run-without-managed-installer.zh.md) + +## Problem + +A repository-owned source installer can provide a stable launcher, isolated staging worktrees, atomic upgrades, rollback storage, and shared maintenance workflows for personal customizations. It also makes the repository responsible for a second lifecycle beside the package manager: host dependency installation, credential prompting, checkout adoption, symlink ownership, staging branch coordination, upgrade recovery, and continued compatibility between the installer and bundled maintenance skills. + +That lifecycle is not required to run or develop DeepSeek Harness from a source checkout. Maintaining it expands the supported filesystem and Git state space without improving the repository-native execution path. + +## Decision + +The repository supports source execution through its root `pnpm` scripts. The `dsh` entry in `package.json` runs `pnpm run build`, then launches `apps/cli/src/bin.ts` through `node --import tsx/esm`; build output remains visible before the CLI output. The package script forwards arguments and inherits the caller's environment, including `NODE_USE_ENV_PROXY=1` when a supporting Node version must honor `HTTP_PROXY` and `HTTPS_PROXY`. Users select Web with `pnpm dsh web` and headless execution with `pnpm dsh --profile headless "task"`. The independent ACP example remains available through `pnpm run demo:acp`. + +The repository does not distribute a source installer, an installer test suite, or skills that assume a managed `current` symlink and timestamped staging worktrees. Users own source checkout placement, Git updates, and any launcher they create outside the repository. + +## Alternatives considered + +**Keep the installer but document `pnpm run` as another path.** This retains the managed launcher and rollback capability but keeps both lifecycle contracts active, including the installer tests and staging-aware skills. + +**Keep generic customization and upstream-publication skills.** Their safety rules can apply beyond the staging layout, but the shipped workflows form one coupled maintenance system: customization discovers the installed staging checkout, upgrade performs the cutover, and upstream publication is selected from those personal changes. General Git contribution guidance already belongs to repository instructions and does not require product-bundled skills. + +**Replace the installer with a smaller launcher-link script.** This reduces setup behavior but still makes the repository responsible for host PATH mutation and launcher ownership. Source scripts provide the entry points without that state. + +## Consequences + +Source users invoke repository scripts rather than an installed `dsh` command. The repository provides no atomic upgrade cutover or preserved staging rollback checkout, and it does not automate the integration or upstream publication of personal source modifications. A future distribution mechanism must justify its ownership of installation and upgrade state, define recovery behavior, and add tests and user documentation without making the source-run path depend on it. Any future publication workflow must isolate one approved feature and obtain explicit approval before its first push and draft PR. + +Verification covers repository-wide references to the removed entry points, documentation links, generated third-party-notice freshness, the build-first `package.json` command, and a source CLI smoke through the exact `node --import tsx/esm` runtime vector. diff --git a/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.zh.md b/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.zh.md new file mode 100644 index 0000000000..86e44a90a9 --- /dev/null +++ b/.agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.zh.md @@ -0,0 +1,31 @@ +# Agent Note: 无需托管安装器的源码运行 + +Status: implemented + +[English](2026-08-10-source-run-without-managed-installer.md) | 中文 + +## 问题 + +仓库自带的源码安装器可以提供稳定的启动器、相互隔离的 staging worktree、原子升级、回滚存储，以及用于个人定制的共享维护工作流。与此同时，仓库还必须在包管理器之外负责第二套生命周期：安装宿主依赖、提示输入凭证、接管检出、管理符号链接归属、协调 staging 分支、处理升级恢复，以及持续保持安装器与随附维护 skill（技能）的兼容性。 + +从源码检出运行或开发 DeepSeek Harness 并不需要这套生命周期。维护它会扩大需要支持的文件系统和 Git 状态空间，却无法改进仓库原生的执行路径。 + +## 决策 + +仓库通过根目录的 `pnpm` 脚本支持从源码运行。`package.json` 中的 `dsh` 项先执行 `pnpm run build`，再通过 `node --import tsx/esm` 启动 `apps/cli/src/bin.ts`；构建输出会显示在 CLI（命令行界面）输出之前。该包脚本会转发参数并继承调用方环境；当支持环境代理的 Node 版本必须遵循 `HTTP_PROXY` 和 `HTTPS_PROXY` 时，调用方可设置 `NODE_USE_ENV_PROXY=1`。用户使用 `pnpm dsh web` 选择 Web，使用 `pnpm dsh --profile headless "task"` 选择无头执行。独立的 ACP（Agent Client Protocol）示例仍可通过 `pnpm run demo:acp` 运行。 + +仓库不分发源码安装器、安装器测试套件，也不分发依赖受管理的 `current` 符号链接和带时间戳 staging worktree 的 skill。源码检出的存放位置、Git 更新，以及用户在仓库外创建的任何启动器均由用户负责。 + +## 考虑过的备选方案 + +**保留安装器，但将 `pnpm run` 记作另一条路径。**这样可以保留受管理的启动器和回滚能力，但两套生命周期约定仍会同时生效，其中包括安装器测试和依赖 staging 布局的 skill。 + +**保留通用的定制与上游发布 skill。**其中的安全规则也能用于 staging 布局之外，但现有工作流共同构成了一套耦合的维护系统：定制工作流查找已安装的 staging 检出，升级工作流执行切换，上游发布工作流则从这些个人修改中选择发布内容。通用 Git 贡献指南已经属于仓库指令，无需以产品随附 skill 的形式提供。 + +**用更小的启动器链接脚本替换安装器。**这样可以简化设置过程，但仓库仍需负责修改宿主 PATH 和管理启动器归属。源码脚本无需引入这类状态即可提供入口点。 + +## 影响 + +源码用户通过仓库脚本运行程序，而非使用已安装的 `dsh` 命令。仓库不提供原子升级切换，也不保留 staging 回滚检出；仓库同样不会自动集成个人源码修改或将其发布到上游。未来的分发机制必须说明为何应由其管理安装和升级状态，定义恢复行为，并补充测试与用户文档，同时不得让源码运行路径依赖该机制。未来任何发布工作流都必须隔离出一项获批功能，并在首次推送和创建草稿 PR（Pull Request）前取得明确批准。 + +验证范围包括仓库内对已移除入口点的所有引用、文档链接、生成的第三方声明文件的新鲜度、`package.json` 中的先构建后启动命令，以及通过准确的 `node --import tsx/esm` 运行方式对源码 CLI 进行的冒烟测试。 diff --git a/AGENTS.md b/AGENTS.md index e8ed4bc73d..2235cc1a1a 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -73,7 +73,7 @@ pnpm run check:windows-wine # ONLY when diagnosing a known Windows failure (nee pnpm run hygiene # knip + publint + workspace constraints + NodeNext consumer check pnpm run doc-sync # all documentation gates; leaf list in scripts/run-gates.ts pnpm run website:build # VitePress build (doubles as dead-link check) -pnpm run demo:headless "task" # one-shot agent (needs DEEPSEEK_API_KEY) +pnpm dsh --profile headless "task" # build, then run one task (needs DEEPSEEK_API_KEY) pnpm run demo:cordis # the agent modifies its own runtime (needs key) pnpm run demo:acp # ACP automation server (needs DEEPSEEK_API_KEY) ``` diff --git a/README.i18n.yaml b/README.i18n.yaml index 43185dc239..552fb03a25 100644 --- a/README.i18n.yaml +++ b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write README.md -README.md: 9b8944027572072e08a39bd9e482996f8128224c -README.zh.md: a1b2b6a36c4baac8a49b88a42c9f17c986287ff1 +README.md: b2d84672275a4ca996b6ea596c104abfaa52432a +README.zh.md: 747a3c88bc129ad5dd24f5fa150a1661c4db0b11 diff --git a/README.md b/README.md index 9b89440275..b2d8467227 100644 --- a/README.md +++ b/README.md @@ -12,41 +12,34 @@ DeepSeek Harness is under internal testing. Features and interfaces may change. The internal build uploads all Session Logs by default to help diagnose reported problems. Set `DSH_TELEMETRY_DISABLED=1` to disable telemetry. Send feedback through the internal WeChat group. -## Install +## Run from source -Clone the repository, then run the installer: +Clone this repo, complete the [dependency and API-key setup](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key), then run: ```sh -git clone -cd deepseek-harness -scripts/install.sh +pnpm dsh web ``` -The installer requires `git` and Node `^22.19 || >=24`, offers to install `pnpm` when it is missing, prompts for a DeepSeek API key, builds the required repository artifacts, and launches the Web UI. - -The default active checkout is `~/.dsh/source/current`, and the launcher is linked into `~/.local/bin`. Re-run the installer to update. [`scripts/install.sh`](scripts/install.sh) owns alternate locations, update mechanics, and recovery options. - ## Use DeepSeek Harness ### Web UI -For the recommended local interface, choose Web UI when the installer finishes. To start it later, or after updating the active checkout, build the repository and run: +Start the recommended local interface from the repository root: ```sh -(cd ~/.dsh/source/current && pnpm run build) -dsh web +pnpm dsh web ``` -The path above is the installer's default. If you set `DSH_SOURCE` or `DSH_CURRENT`, or reused an existing checkout, replace `~/.dsh/source/current` with that checkout path; see [`scripts/install.sh`](scripts/install.sh) for details. The Web UI is served at `http://127.0.0.1:3080` by default. +The command builds the repository before starting the Web UI, which is served at `http://127.0.0.1:3080` by default. ### Profiles -`dsh` boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/`: +The source CLI boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/`: ```sh -dsh --profile web # the browser UI (same as: dsh web) -dsh plugin --profile tui add # install a plugin into a custom profile -dsh --profile tui # boot it +pnpm dsh --profile web # the browser UI +pnpm dsh plugin --profile tui add # install a plugin into a custom profile +pnpm dsh --profile tui # boot it ``` The [CLI reference](apps/cli/README.md#profiles) describes profile layout, layer semantics, and config dump commands. @@ -56,7 +49,7 @@ The [CLI reference](apps/cli/README.md#profiles) describes profile layout, layer Run one task, print the final answer, and exit: ```sh -dsh --profile headless "summarize this workspace" +pnpm dsh --profile headless "summarize this workspace" ``` ### Automation and SDKs diff --git a/README.zh.md b/README.zh.md index a1b2b6a36c..747a3c88bc 100644 --- a/README.zh.md +++ b/README.zh.md @@ -12,41 +12,34 @@ DeepSeek Harness 正处于内部测试阶段，功能和接口可能发生变化 为帮助诊断上报的问题，内测版本默认上传所有会话日志。设置 `DSH_TELEMETRY_DISABLED=1` 可关闭遥测。请通过内部企业微信群反馈问题和建议。 -## 安装 +## 从源码运行 -克隆仓库，然后运行安装器： +克隆本仓库，完成[依赖安装和 API 密钥配置](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key)，然后运行： ```sh -git clone -cd deepseek-harness -scripts/install.sh +pnpm dsh web ``` -安装器要求系统已安装 `git` 和 Node `^22.19 || >=24`，缺少 `pnpm` 时可代为安装，并会提示输入 DeepSeek API 密钥，然后构建所需的仓库产物并启动 Web UI。 - -默认生效的检出位于 `~/.dsh/source/current`，启动器链接到 `~/.local/bin`。再次运行安装器即可更新。其他位置、更新机制和恢复选项由 [`scripts/install.sh`](scripts/install.sh) 负责。 - ## 使用 DeepSeek Harness ### Web UI -推荐在本地使用 Web UI；安装结束时，选择 Web UI 即可。以后需要启动时，或更新当前生效的检出后，请构建仓库并运行： +请从仓库根目录启动推荐的本地界面： ```sh -(cd ~/.dsh/source/current && pnpm run build) -dsh web +pnpm dsh web ``` -上述路径是安装器的默认位置。如果你设置过 `DSH_SOURCE` 或 `DSH_CURRENT`，或者复用了已有检出，请把 `~/.dsh/source/current` 换成该检出路径；详情见 [`scripts/install.sh`](scripts/install.sh)。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。 +该命令会先构建仓库，再启动 Web UI。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。 ### Profile -`dsh` 启动 profile：按序叠放的插件组合包 patch 层，之上再叠加你在 `$DSH_HOME/profiles/` 中的自有覆盖层： +源码 CLI（命令行界面）会启动 profile：按序叠放的插件组合包 patch 层，之上再叠加你在 `$DSH_HOME/profiles/` 中的自有覆盖层： ```sh -dsh --profile web # the browser UI (same as: dsh web) -dsh plugin --profile tui add # install a plugin into a custom profile -dsh --profile tui # boot it +pnpm dsh --profile web # the browser UI +pnpm dsh plugin --profile tui add # install a plugin into a custom profile +pnpm dsh --profile tui # boot it ``` profile 布局、层语义与配置输出命令详见 [CLI（命令行界面）参考](apps/cli/README.md#profiles)。 @@ -56,7 +49,7 @@ profile 布局、层语义与配置输出命令详见 [CLI（命令行界面） 运行一项任务，打印最终答案后退出： ```sh -dsh --profile headless "summarize this workspace" +pnpm dsh --profile headless "summarize this workspace" ``` ### 自动化与 SDK diff --git a/THIRD_PARTY_NOTICES.md b/THIRD_PARTY_NOTICES.md index 586cd240a0..0ecae4b668 100644 --- a/THIRD_PARTY_NOTICES.md +++ b/THIRD_PARTY_NOTICES.md @@ -27,7 +27,7 @@ The Cordis framework and its foundation libraries are source-vendored into this ## Runtime npm dependencies -External packages that a workspace package resolves at runtime. `scripts/install.sh` installs this repository itself, so the tier covers every plugin a user can mount from `cordis.yml` — not only what the `dsh` CLI, Web UI, and Python SDK runtime load by default. +External packages that a workspace package resolves at runtime. The tier covers every plugin a user can mount from `cordis.yml` — not only what the `dsh` CLI, Web UI, and Python SDK runtime load by default. | Package | License | | --- | --- | diff --git a/apps/cli/README.i18n.yaml b/apps/cli/README.i18n.yaml index 04026262c8..191d6c8e68 100644 --- a/apps/cli/README.i18n.yaml +++ b/apps/cli/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write apps/cli/README.md -README.md: 4fae5338a89ce12c2620e123530acf883ae9efff -README.zh.md: a2d086b8ff12fb07f2446fc4162de09739bcdeab +README.md: 98a856261bc632c97f350db8fc7bb0b10c22235d +README.zh.md: 283e54138e24202ed6b88d1d309538c58cd66b3e diff --git a/apps/cli/README.md b/apps/cli/README.md index 4fae5338a8..98a856261b 100644 --- a/apps/cli/README.md +++ b/apps/cli/README.md @@ -31,8 +31,8 @@ dsh --help # the launcher's own help A profile directory holds a `package.json` (out-of-tree plugin dependencies plus the profile manifest `dsh.profile` with its ordered `bundles` list) and a `cordis.patch.yml` (the user's own patch layer, hot-reloaded on long-lived surfaces). The tree composes over an empty root: each bundle's patch in `dsh.profile.bundles` order, then the profile's `cordis.patch.yml`, then the home-level `$DSH_HOME/cordis.patch.yml`, then `--patch` overlays. Bundles named in `dsh.profile.bundles` resolve from the dsh installation first (`@deepseek-ai/dsh-base`, `@deepseek-ai/dsh-web-app`, `@deepseek-ai/dsh-headless`), then from the profile's own `node_modules`, where pnpm installs out-of-tree plugins. Use `--dump-default-config` and `--dump-config` to inspect the composed tree without booting it. -The [CLI behavior reference](reference/README.md) owns exact layer precedence, flags, shutdown behavior, deployment defaults, and the source launcher. +The [CLI behavior reference](reference/README.md) owns exact layer precedence, flags, shutdown behavior, deployment defaults, and source execution. ## Development -Production runs require built package and frontend artifacts. From a checkout, `pnpm run dsh` runs the TypeScript entry and forwards arguments; the [source-launcher reference](reference/README.md#source-launcher) describes the PATH symlink and module-resolution contract. +Production runs require built package and frontend artifacts. From the repository root, `pnpm dsh ` builds those artifacts, runs the TypeScript entry, and forwards every argument; the [source-execution reference](reference/README.md#source-execution) owns the module-resolution contract. diff --git a/apps/cli/README.zh.md b/apps/cli/README.zh.md index a2d086b8ff..283e54138e 100644 --- a/apps/cli/README.zh.md +++ b/apps/cli/README.zh.md @@ -31,8 +31,8 @@ dsh --help # the launcher's own help profile 目录包含一个 `package.json`（树外插件依赖，加上 profile manifest（元数据清单）`dsh.profile` 及其有序的 `bundles` 列表）和一个 `cordis.patch.yml`（用户自己的 patch 层，在长期运行的 surface 上热重载）。配置树在空根之上组合：先按 `dsh.profile.bundles` 顺序应用各组合包的 patch，然后是 profile 的 `cordis.patch.yml`，然后是 home 级的 `$DSH_HOME/cordis.patch.yml`，然后是 `--patch` overlay。`dsh.profile.bundles` 中列出的组合包先从 dsh 安装目录解析（`@deepseek-ai/dsh-base`、`@deepseek-ai/dsh-web-app`、`@deepseek-ai/dsh-headless`），再从 profile 自己的 `node_modules` 解析；pnpm 把树外插件安装在后者。使用 `--dump-default-config` 和 `--dump-config` 可在不启动的情况下检查组合后的配置树。 -[CLI（命令行界面）行为参考](reference/README.md)负责确切的层优先级、flag、关闭行为、部署默认值和源码启动器。 +[CLI（命令行界面）行为参考](reference/README.md)负责确切的层优先级、flag、关闭行为、部署默认值和源码执行。 ## 开发 -生产运行需要已构建的包与前端产物。在 checkout 中，`pnpm run dsh` 会运行 TypeScript 入口并转发参数；[源码启动器参考](reference/README.md#source-launcher)说明 PATH 符号链接和模块解析契约。 +生产运行需要已构建的包与前端产物。从仓库根目录运行 `pnpm dsh ` 会先构建这些产物，再运行 TypeScript 入口并转发所有参数；模块解析约定由[源码执行参考](reference/README.md#source-execution)负责。 diff --git a/apps/cli/reference/README.i18n.yaml b/apps/cli/reference/README.i18n.yaml index 8f6db85427..a2cfed084a 100644 --- a/apps/cli/reference/README.i18n.yaml +++ b/apps/cli/reference/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write apps/cli/reference/README.md -README.md: fd0647347312051a1814a5e3464b34032ae70dfc -README.zh.md: afe4b9ba5651e962288ffebbe7c095ad20bcc617 +README.md: cef687dc392f97886ea18b162e8f668a44ce2284 +README.zh.md: f6721ec256d404e2b602fb2ed921b41c03633a82 diff --git a/apps/cli/reference/README.md b/apps/cli/reference/README.md index fd06473473..cef687dc39 100644 --- a/apps/cli/reference/README.md +++ b/apps/cli/reference/README.md @@ -79,12 +79,6 @@ Session events stream as OTLP/HTTP logs by default. `DSH_TELEMETRY_OTLP_URL` sel Install external plugin bundles through `dsh plugin --profile add `. The installed package owns its dependencies and contributes its declared `cordis.patch.yml` layer. The CLI also ships `@deepseek-ai/dsh-mcp-client` as a dependency for patch layers, but no MCP server is enabled by default because each server command is trusted executable code outside the agent sandbox. -## Source launcher +## Source execution -Link the source-running launcher onto PATH: - -```sh -ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh -``` - -It resolves the checkout through its real path and launches `apps/cli/src/bin.ts` with `node --import tsx/esm`. `TSX_TSCONFIG_PATH` is pinned to the checkout root, so workspace package resolution is independent of the invoking directory. `pnpm run dsh` uses the same entry and forwards arguments. The built form is `apps/cli/lib/bin.js` after `pnpm run build`. +From the repository root, use `pnpm dsh `. The `package.json` script runs the complete repository build, launches `apps/cli/src/bin.ts` with `node --import tsx/esm`, and forwards every argument. Build output appears before CLI output. The process inherits the launch environment; set `NODE_USE_ENV_PROXY=1` when a supporting Node version must honor `HTTP_PROXY` and `HTTPS_PROXY`. The installed form launches the built `apps/cli/lib/bin.js` without rebuilding the repository. diff --git a/apps/cli/reference/README.zh.md b/apps/cli/reference/README.zh.md index afe4b9ba56..f6721ec256 100644 --- a/apps/cli/reference/README.zh.md +++ b/apps/cli/reference/README.zh.md @@ -79,12 +79,6 @@ dsh web --help 通过 `dsh plugin --profile add ` 安装外部插件组合包。安装的包拥有其依赖，并贡献其声明的 `cordis.patch.yml` 层。CLI 还随附 `@deepseek-ai/dsh-mcp-client` 作为供 patch 层使用的依赖，但默认不启用 MCP 服务器，因为每条服务器命令都是 agent（智能体）沙箱之外的受信任可执行代码。 -## 源码启动器 +## 源码执行 -把源码运行启动器链接到 PATH： - -```sh -ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh -``` - -它通过 real path 解析 checkout，并使用 `node --import tsx/esm` 启动 `apps/cli/src/bin.ts`。`TSX_TSCONFIG_PATH` 固定到 checkout 根目录，因此 workspace 包解析不依赖调用目录。`pnpm run dsh` 使用同一入口并转发参数。运行 `pnpm run build` 后，构建形式为 `apps/cli/lib/bin.js`。 +请从仓库根目录使用 `pnpm dsh `。`package.json` 中的脚本会完成整个仓库的构建，通过 `node --import tsx/esm` 启动 `apps/cli/src/bin.ts`，并转发所有参数。构建输出会显示在 CLI 输出之前。该进程会继承启动环境；当支持环境代理的 Node 版本必须遵循 `HTTP_PROXY` 和 `HTTPS_PROXY` 时，请设置 `NODE_USE_ENV_PROXY=1`。安装形式会直接启动构建后的 `apps/cli/lib/bin.js`，不会重新构建仓库。 diff --git a/apps/cli/tests/install-script.spec.ts b/apps/cli/tests/install-script.spec.ts deleted file mode 100644 index 871f72d056..0000000000 --- a/apps/cli/tests/install-script.spec.ts +++ /dev/null @@ -1,140 +0,0 @@ -import { chmodSync, copyFileSync, mkdirSync, readFileSync, writeFileSync } from 'node:fs' -import { mkdtemp, rm } from 'node:fs/promises' -import { tmpdir } from 'node:os' -import { join } from 'node:path' -import { fileURLToPath } from 'node:url' -import { execa } from 'execa' -import { afterEach, describe, expect, it } from 'vitest' - -const installer = fileURLToPath(new URL('../../../scripts/install.sh', import.meta.url)) -const fixtures: string[] = [] - -const PTY_DRIVER = String.raw` -import errno, json, os, pty, select, signal, sys, time -script, cwd, env_json, actions_json = sys.argv[1:] -env = os.environ.copy() -env.update(json.loads(env_json)) -actions = json.loads(actions_json) -pid, fd = pty.fork() -if pid == 0: - os.chdir(cwd) - os.execvpe("sh", ["sh", script], env) - -output = bytearray() -action_index = 0 -deadline = time.monotonic() + 15 -status = None -while time.monotonic() < deadline: - ready, _, _ = select.select([fd], [], [], 0.05) - if ready: - try: - chunk = os.read(fd, 65536) - except OSError as error: - if error.errno != errno.EIO: - raise - chunk = b"" - output.extend(chunk) - while action_index < len(actions) and actions[action_index]["waitFor"].encode() in output: - os.write(fd, actions[action_index]["send"].encode()) - action_index += 1 - waited, candidate = os.waitpid(pid, os.WNOHANG) - if waited == pid: - status = candidate - break - -if status is None: - os.kill(pid, signal.SIGKILL) - _, status = os.waitpid(pid, 0) -sys.stdout.buffer.write(output) -if action_index != len(actions): - sys.stderr.write(f"completed {action_index}/{len(actions)} PTY actions\n") - sys.exit(124) -sys.exit(os.waitstatus_to_exitcode(status)) -` - -interface Action { - readonly waitFor: string - readonly send: string -} - -interface Fixture { - readonly binDirectory: string - readonly launchLog: string - readonly pnpmLog: string - readonly root: string - readonly script: string -} - -afterEach(async () => { - await Promise.all(fixtures.splice(0).map(async (fixture) => { await rm(fixture, { force: true, recursive: true }) })) -}) - -function executable(path: string, content: string): void { - writeFileSync(path, content) - chmodSync(path, 0o755) -} - -async function createFixture(): Promise { - const root = await mkdtemp(join(tmpdir(), 'dsh-install-')) - fixtures.push(root) - const checkoutDirectory = join(root, 'checkout') - const scriptsDirectory = join(checkoutDirectory, 'scripts') - const sourceBinDirectory = join(checkoutDirectory, 'bin') - const fakeBinDirectory = join(root, 'fake-bin') - const binDirectory = join(root, 'path-bin') - for (const directory of [scriptsDirectory, sourceBinDirectory, fakeBinDirectory, binDirectory, join(root, 'home/.dsh')]) { - mkdirSync(directory, { recursive: true }) - } - const script = join(scriptsDirectory, 'install.sh') - copyFileSync(installer, script) - const launchLog = join(root, 'launch.log') - const pnpmLog = join(root, 'pnpm.log') - executable(join(sourceBinDirectory, 'dsh'), '#!/bin/sh\nprintf \'%s\\n\' "$*" >"$DSH_TEST_LAUNCH_LOG"\n') - executable(join(fakeBinDirectory, 'pnpm'), `#!/bin/sh -if [ "\${1:-}" = --version ]; then printf '11.7.0\\n'; exit 0; fi -printf '%s\\n' "$*" >>"$DSH_TEST_PNPM_LOG" -`) - await execa('git', ['init', '-q'], { cwd: checkoutDirectory }) - await execa('git', ['add', 'bin/dsh', 'scripts/install.sh'], { cwd: checkoutDirectory }) - await execa('git', [ - '-c', 'user.name=dsh-test', - '-c', 'user.email=dsh-test@example.invalid', - 'commit', '-qm', 'fixture', - ], { cwd: checkoutDirectory }) - writeFileSync(join(root, 'home/.dsh/.env'), 'DEEPSEEK_API_KEY=test\n') - return { binDirectory, launchLog, pnpmLog, root, script } -} - -async function runInstaller(fixture: Fixture, actions: readonly Action[]): Promise { - const result = await execa('python3', [ - '-c', - PTY_DRIVER, - fixture.script, - fixture.root, - JSON.stringify({ - DSH_BIN_DIR: fixture.binDirectory, - DSH_HOME: join(fixture.root, 'home/.dsh'), - DSH_TEST_LAUNCH_LOG: fixture.launchLog, - DSH_TEST_PNPM_LOG: fixture.pnpmLog, - HOME: join(fixture.root, 'home'), - PATH: `${join(fixture.root, 'fake-bin')}:${fixture.binDirectory}:${process.env.PATH ?? ''}`, - }), - JSON.stringify(actions), - ], { reject: false, stripFinalNewline: false, timeout: 20_000 }) - expect(result.exitCode, result.stderr).toBe(0) - return result.stdout -} - -describe.runIf(process.platform !== 'win32')('one-line installer launch', { timeout: 25_000 }, () => { - it('builds and launches the Web UI', async () => { - const fixture = await createFixture() - - const output = await runInstaller(fixture, [ - { waitFor: 'Replace it?', send: '\n' }, - ]) - - expect(output).toContain('launching Web UI') - expect(readFileSync(fixture.pnpmLog, 'utf8')).toBe('install\nrun build\n') - expect(readFileSync(fixture.launchLog, 'utf8')).toBe('web\n') - }) -}) diff --git a/apps/cli/tests/source-launch.compat.spec.ts b/apps/cli/tests/source-launch.compat.spec.ts index bd2268231b..597c3cff26 100644 --- a/apps/cli/tests/source-launch.compat.spec.ts +++ b/apps/cli/tests/source-launch.compat.spec.ts @@ -1,11 +1,12 @@ +import { readFile } from 'node:fs/promises' import { fileURLToPath } from 'node:url' import { execa } from 'execa' import { describe, expect, it } from 'vitest' /** - * Keyless smoke for the SOURCE `dsh` launcher: run `apps/cli/src/bin.ts` - * with the exact production launch vector (`node --import tsx/esm`, the same - * executable and arguments as `bin/dsh` and the root `dsh`/`demo:web` scripts) and assert the + * Keyless smoke for SOURCE `dsh` execution: run `apps/cli/src/bin.ts` + * with the exact production runtime vector (`node --import tsx/esm`, the + * vector the root `dsh` script invokes after building) and assert the * required-config diagnostic. The Node compatibility matrix runs this * WHOLE file, so a Node release changing module hooks or TypeScript handling * breaks this gate instead of every developer's `pnpm dsh`; the built-bin @@ -16,6 +17,13 @@ const repoRoot = fileURLToPath(new URL('../../../', import.meta.url)) const dshSourceBin = 'apps/cli/src/bin.ts' describe('dsh SOURCE launcher (node --import tsx/esm)', () => { + it('builds before launching the source CLI', async () => { + const rootPackage = JSON.parse(await readFile(new URL('../../../package.json', import.meta.url), 'utf8')) as { + readonly scripts?: Record + } + expect(rootPackage.scripts?.dsh).toBe('pnpm run build && node --import tsx/esm apps/cli/src/bin.ts') + }) + it('boots the source entry and requires a profile', async () => { const result = await execa(process.execPath, ['--import', 'tsx/esm', dshSourceBin], { cwd: repoRoot, diff --git a/apps/cli/tests/web-agent-presets.e2e.ts b/apps/cli/tests/web-agent-presets.e2e.ts index 85c5227bd4..b59964241b 100644 --- a/apps/cli/tests/web-agent-presets.e2e.ts +++ b/apps/cli/tests/web-agent-presets.e2e.ts @@ -159,7 +159,7 @@ describe('the shipped Web composition', () => { // depend on ripgrep being present on the machine. expect(toolNames(ctx, handle.agent).filter(name => name !== 'glob' && name !== 'grep')).toEqual([ 'ask_user_question', 'bash', 'create_goal', 'edit', 'exit_plan_mode', - 'get_goal', 'interrupt_agent', 'list_agents', 'ralph', 'read', 'send_message', 'skill', + 'get_goal', 'interrupt_agent', 'list_agents', 'ralph', 'read', 'read_image', 'send_message', 'skill', 'subagent', 'subagent_fork', 'task_kill', 'task_list', 'task_output', 'todo_write', 'update_goal', 'web_search', 'workflow', 'write', diff --git a/apps/web/tests/background-task-list.e2e.ts b/apps/web/tests/background-task-list.e2e.ts new file mode 100644 index 0000000000..734d43131a --- /dev/null +++ b/apps/web/tests/background-task-list.e2e.ts @@ -0,0 +1,133 @@ +// Web e2e scenario: the session-header background-task list over the real +// host. No model call is involved — a genuine `run_in_background` bash call +// registers with `ctx.tasks`, and the assertion chain is the whole delivery +// path: registry change feed → api-proxy `session/tasks` frame → the client's +// `tasksBySession` mirror → the header action. +import { readFile } from 'node:fs/promises' +import { fileURLToPath } from 'node:url' +import { join } from 'node:path' +import type { Browser, Page } from 'playwright' +import { chromium } from 'playwright' +import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest' +import type { Agent } from '@deepseek-ai/dsh-agent' +import { CallId } from '@deepseek-ai/dsh-llm' +import { SessionId } from '@deepseek-ai/dsh-session' +import { TaskId } from '@deepseek-ai/dsh-tasks' +import { + assertFixtureInventory, captureStableAria, compareOrRefreshGolden, + launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold, +} from './scaffold.ts' +import { newEnglishPage, saveFailureShot } from './support.ts' + +const FIXTURE = fileURLToPath(new URL('./snapshots/fresh-round-trip/session.jsonl', import.meta.url)) +const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/background-task-list', import.meta.url)) +const RUNNING_EXPECTED = join(SNAPSHOT_DIR, 'running.expected.md') +const SETTLED_EXPECTED = join(SNAPSHOT_DIR, 'settled.expected.md') +const MODE = webSnapshotMode() +const SEED_ID = 'background-task-list-web-e2e' +// Long enough that the running assertions never race the process exiting on +// their own; the test kills it explicitly to reach the settled state. +const COMMAND = 'sleep 45' + +/** + * Wait for the Host to publish the live Agent that opening a session resumes. + * @param scaffold - the booted web scaffold. + * @param sessionId - the opened session's identity. + * @returns the registered Agent instance. + */ +async function liveAgent(scaffold: WebScaffold, sessionId: SessionId): Promise { + const deadline = Date.now() + 30_000 + for (;;) { + const found = scaffold.ctx.agents.get(sessionId) + if (found !== undefined) return found + if (Date.now() > deadline) throw new Error(`opening session "${sessionId}" published no live Agent`) + await new Promise(resolve => setTimeout(resolve, 100)) + } +} + +describe.skipIf(MODE === 'record')('web e2e: background task list', () => { + let scaffold: WebScaffold + let browser: Browser + let page: Page + let tripwire: ReturnType + let agent: Agent + let taskId: TaskId + + beforeAll(async () => { + scaffold = await launchWebScaffold({}) + await seedSession(scaffold, await readFile(FIXTURE, 'utf8'), SEED_ID) + browser = await chromium.launch() + page = await newEnglishPage(browser) + tripwire = watchConsole(page) + await page.goto(scaffold.baseUrl, { waitUntil: 'load' }) + await page.waitForSelector('[class*="frame"]', { timeout: 30_000 }) + + const groupRow = page.locator('[role="treeitem"]').first() + await groupRow.waitFor({ timeout: 15_000 }) + await groupRow.click() + const sessionRow = page.locator('[role="treeitem"]').nth(1) + await sessionRow.waitFor({ timeout: 10_000 }) + await sessionRow.click() + + // Opening the session drives the Host's ordinary Agent resolution; the + // task owner must be that exact live instance, never a second one. + // `expect.poll` is test-scoped, so this hook polls by hand. + agent = await liveAgent(scaffold, SessionId(SEED_ID)) + }, 120_000) + + afterAll(async () => { + await browser?.close() + await scaffold?.close() + }) + + it('shows a running background task in the session header without a refresh', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-background-task-running')) + // Point assertion, not a poll: `expect.poll` retries until a predicate + // holds, so polling for zero passes at t=0 and proves nothing. The + // "renders nothing without a task" branch is owned by the component suite. + const trigger = page.getByRole('button', { name: '1 background task running' }) + expect(await trigger.count()).toBe(0) + + const started = await scaffold.ctx.tools.execute({ + signal: new AbortController().signal, + callId: CallId('background-task-list-e2e'), + name: 'bash', + arguments: { command: COMMAND, description: 'Hold a background slot open', run_in_background: true }, + agent, + }) + const reported = started.content.map(block => block.type === 'text' ? block.text : '').join('') + const matched = /\bbash-\d+\b/.exec(reported) + if (matched === null) throw new Error(`background bash reported no task id: ${reported}`) + taskId = TaskId(matched[0]) + + await trigger.waitFor({ timeout: 15_000 }) + await trigger.click() + const row = page.getByRole('list', { name: 'Background tasks' }).getByRole('listitem').first() + await row.waitFor({ timeout: 10_000 }) + await expect.poll(() => row.textContent()).toContain(COMMAND) + + const snapshot = await captureStableAria(page, '[class*="menu"]', scaffold.workspaceCwd) + await compareOrRefreshGolden(RUNNING_EXPECTED, snapshot, MODE) + expect(tripwire.pageErrors).toEqual([]) + expect(tripwire.warnings).toEqual([]) + }, 60_000) + + it('flips the open list to the cancelled outcome when the registry settles it', async () => { + onTestFailed(() => saveFailureShot(page, 'web-e2e-background-task-settled')) + expect(scaffold.ctx.tasks.kill(taskId, agent, 'web e2e cancellation')).toBe('requested') + + // The trigger drops its live count once the task leaves running/stopping, + // which is also the proof that settlement reached the browser unprompted. + const idle = page.getByRole('button', { name: '1 background task' }) + await idle.waitFor({ timeout: 20_000 }) + + const snapshot = await captureStableAria(page, '[class*="menu"]', scaffold.workspaceCwd) + await compareOrRefreshGolden(SETTLED_EXPECTED, snapshot, MODE) + expect(tripwire.pageErrors).toEqual([]) + expect(tripwire.warnings).toEqual([]) + }, 60_000) + + it('keeps its snapshot inventory closed', async () => { + await assertFixtureInventory(SNAPSHOT_DIR, ['running.expected.md', 'settled.expected.md']) + }) +}) diff --git a/apps/web/tests/math-rendering.e2e.ts b/apps/web/tests/math-rendering.e2e.ts index b183fe7df5..de24c1ca76 100644 --- a/apps/web/tests/math-rendering.e2e.ts +++ b/apps/web/tests/math-rendering.e2e.ts @@ -119,6 +119,10 @@ describe('web e2e: settled Markdown math rendering', () => { await expect.poll(() => page.locator('.katex').count(), { timeout: 10_000 }).toBe(6) await expect.poll(() => page.locator('.katex-display').count(), { timeout: 10_000 }).toBe(2) expect(await page.locator('.katex-error').count()).toBe(0) + await expect.poll( + () => page.getByText('Input 0 tok · Output 0 tok', { exact: false }).count(), + { timeout: 10_000 }, + ).toBe(1) const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)) .split(SEED_ID).join('{{seededId}}') diff --git a/apps/web/tests/shipped-composition.e2e.ts b/apps/web/tests/shipped-composition.e2e.ts index 8e49fded4f..ae0bab04c8 100644 --- a/apps/web/tests/shipped-composition.e2e.ts +++ b/apps/web/tests/shipped-composition.e2e.ts @@ -36,6 +36,7 @@ const EXPECTED_TOOLS = [ 'list_agents', 'ralph', 'read', + 'read_image', 'send_message', 'skill', 'subagent', diff --git a/apps/web/tests/smoke-real.e2e.ts b/apps/web/tests/smoke-real.e2e.ts index ae5805dc8a..24a6f269c3 100644 --- a/apps/web/tests/smoke-real.e2e.ts +++ b/apps/web/tests/smoke-real.e2e.ts @@ -478,7 +478,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke requireDist() sessionsDir = mkdtempSync(join(tmpdir(), 'dsh-web-w5-')) const port = await probeFreePort() - // tsx boot mirrors demo:web — lib/ may be unbuilt in this worktree. Isolate + // tsx boot mirrors the runtime half of the root dsh script. Isolate // the host-level Harness and shared-agent homes inside the temp world; tsx // also needs the repo's loader and tsconfig paths pointed at explicitly. const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href diff --git a/apps/web/tests/snapshots/background-task-list/running.expected.md b/apps/web/tests/snapshots/background-task-list/running.expected.md new file mode 100644 index 0000000000..1adaa965e2 --- /dev/null +++ b/apps/web/tests/snapshots/background-task-list/running.expected.md @@ -0,0 +1,2 @@ +- list "Background tasks": + - listitem: bash sleep 45 running {{duration}} diff --git a/apps/web/tests/snapshots/background-task-list/settled.expected.md b/apps/web/tests/snapshots/background-task-list/settled.expected.md new file mode 100644 index 0000000000..c97ff5026c --- /dev/null +++ b/apps/web/tests/snapshots/background-task-list/settled.expected.md @@ -0,0 +1,2 @@ +- list "Background tasks": + - listitem: "bash sleep 45 signal: SIGTERM {{duration}}" diff --git a/apps/web/tests/workspace-management.e2e.ts b/apps/web/tests/workspace-management.e2e.ts index c18a522d30..a435592da5 100644 --- a/apps/web/tests/workspace-management.e2e.ts +++ b/apps/web/tests/workspace-management.e2e.ts @@ -99,6 +99,19 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff } } + /** + * Reveal and click a row action, re-hovering if a projection update replaces + * the row before its hover-only button becomes visible. + */ + async function clickHoverAction(row: Locator, name: string): Promise { + const button = row.getByRole('button', { name }) + await expect.poll(async () => { + await row.hover() + return await button.isVisible() + }, { timeout: 10_000 }).toBe(true) + await button.click() + } + beforeAll(async () => { scaffold = await launchWebScaffold({}) // Seed one cold session (Ungrouped bucket) for the flat view + hover card. @@ -137,10 +150,8 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff it('renames a workspace over the wire with a duplicate-name pre-check', async () => { onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-rename')) - // The actions button is display:none until its row hovers — hover the - // group row first, then the revealed button becomes actionable. - await page.locator('[role="treeitem"]').filter({ hasText: 'alpha-ws' }).first().hover() - await page.getByRole('button', { name: 'Workspace actions for alpha-ws' }).click() + const alphaRow = page.locator('[role="treeitem"]').filter({ hasText: 'alpha-ws' }).first() + await clickHoverAction(alphaRow, 'Workspace actions for alpha-ws') await page.getByRole('menuitem', { name: 'Rename' }).click() const dialog = page.getByRole('dialog', { name: 'Rename workspace' }) await dialog.waitFor({ timeout: 10_000 }) @@ -214,17 +225,19 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff // The header row is wrapped by its HoverCard anchor span, so the section // is the nearest groupSection ancestor, not the immediate parent. const groupSection = groupRow.locator('xpath=ancestor::*[contains(@class, "groupSection")][1]') - if (await groupSection.locator('[role="treeitem"]').count() < 2) await groupRow.click() - await expect.poll( - () => groupSection.locator('[role="treeitem"]').count(), - { timeout: 10_000 }, - ).toBeGreaterThanOrEqual(2) + await expect.poll(async () => { + const count = await groupSection.locator('[role="treeitem"]').count() + if (count < 2 && await groupRow.getAttribute('aria-expanded') !== 'true') { + await groupRow.click() + await page.waitForTimeout(50) + } + return await groupSection.locator('[role="treeitem"]').count() + }, { timeout: 10_000 }).toBeGreaterThanOrEqual(2) const seededRow = groupSection.locator('[role="treeitem"]').nth(1) await seededRow.click() await expect.poll(() => seededRow.getAttribute('aria-selected'), { timeout: 10_000 }).toBe('true') - await groupRow.hover() - await page.getByRole('button', { name: `Workspace actions for ${workspace.title}` }).click() + await clickHoverAction(groupRow, `Workspace actions for ${workspace.title}`) await page.getByRole('menuitem', { name: 'Delete workspace' }).click() const dialog = page.getByRole('dialog', { name: 'Delete workspace' }) await dialog.waitFor({ timeout: 10_000 }) @@ -338,8 +351,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff if (oldWorkspace === undefined) throw new Error('old same-name Workspace was not registered') const oldRow = page.locator('[role="treeitem"]').filter({ hasText: title }).first() - await oldRow.hover() - await page.getByRole('button', { name: `Workspace actions for ${title}` }).click() + await clickHoverAction(oldRow, `Workspace actions for ${title}`) await page.getByRole('menuitem', { name: 'Delete workspace' }).click() await page.getByRole('dialog', { name: 'Delete workspace' }) .getByRole('button', { name: 'Delete workspace' }).click() @@ -509,9 +521,10 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-row-menu')) const sessionRow = await seededSessionRow() // The trigger is display:none until its row hovers. - await sessionRow.hover() const trigger = sessionRow.locator('button[aria-label^="Session actions for "]') - await trigger.click() + const triggerName = await trigger.getAttribute('aria-label') + if (triggerName === null) throw new Error('seeded Session row has no actions label') + await clickHoverAction(sessionRow, triggerName) const item = page.getByRole('menuitem', { name: 'Rename' }) await item.waitFor({ timeout: 5_000 }) // Into the list, then back up to the trigger across the 4px gap below it: @@ -559,8 +572,7 @@ describe('web e2e: workspace management (create / rename / flat view / hover aff const rowTitle = await sessionRow.locator('[class*="title"]').innerText() // Row menu: hover reveals the actions button; Archive session commits // without a confirmation dialog (non-destructive: log + accounting stay). - await sessionRow.hover() - await sessionRow.getByRole('button', { name: `Session actions for ${rowTitle}` }).click() + await clickHoverAction(sessionRow, `Session actions for ${rowTitle}`) await page.getByRole('menuitem', { name: 'Archive session' }).click() // The row disappears on the archive-set echo; with no other visible // stray, the whole Ungrouped bucket withdraws. diff --git a/apps/web/tsconfig.json b/apps/web/tsconfig.json index fc1a777afc..b80a2f6e2b 100644 --- a/apps/web/tsconfig.json +++ b/apps/web/tsconfig.json @@ -73,6 +73,7 @@ "tests/subagent-interrupt.e2e.ts", "tests/subagent-interrupt-ui.e2e.ts", "tests/sidebar-subagent-activity.e2e.ts", + "tests/background-task-list.e2e.ts", "tests/bash-abort-row.e2e.ts", "tests/skill-tool-row.e2e.ts", "tests/turn-tail-actions.e2e.ts", diff --git a/apps/web/vite.config.ts b/apps/web/vite.config.ts index a8323cdd78..2600d64acb 100644 --- a/apps/web/vite.config.ts +++ b/apps/web/vite.config.ts @@ -5,8 +5,8 @@ import react from '@vitejs/plugin-react' const src = (rel: string): string => fileURLToPath(new URL(rel, import.meta.url)) const STANDALONE_ERROR = 'apps/web is not a standalone application: bare Vite cannot inject window.__DSH_BOOT__. ' - + 'Build with `pnpm run build && pnpm run build:web`, then run `dsh web` (repository checkout: `pnpm run dsh -- web`). ' - + 'For client-plugin HMR, run `pnpm run dsh -- web --dev` together with `pnpm run dev:web`.' + + 'From a repository checkout, run `pnpm dsh web`; an installed package uses `dsh web`. ' + + 'For client-plugin HMR, run `pnpm dsh web --dev` together with `pnpm run dev:web`.' /** Fail before a Vite dev or preview server can expose the boot-manifest-free shell. */ function rejectStandaloneServe(): Plugin { diff --git a/bin/dsh b/bin/dsh deleted file mode 100755 index c578d78e74..0000000000 --- a/bin/dsh +++ /dev/null @@ -1,26 +0,0 @@ -#!/bin/sh -# dsh launcher: runs the apps/cli `dsh` bin FROM SOURCE through the tsx ESM -# hook, so a symlink from anywhere (e.g. ~/.local/bin/dsh) always executes the -# current working tree without a build step. -set -eu - -# Resolve symlink chains without readlink -f (not on every macOS). -script=$0 -while [ -L "$script" ]; do - target=$(readlink "$script") - case $target in - /*) script=$target ;; - *) script=$(dirname "$script")/$target ;; - esac -done -root=$(CDPATH='' cd -- "$(dirname -- "$script")/.." && pwd) - -# The ESM-only tsx hook transforms TypeScript and projects this checkout's -# tsconfig paths into Node resolution (the CJS hook stays off: the graph is -# ESM-only and the CJS resolver costs ~0.4s of startup). Absolute paths keep -# both the hook and the tsconfig anchored to this checkout when the launcher -# runs from any cwd, where bare `tsx/esm` would not resolve. -NODE_USE_ENV_PROXY=1 \ - TSX_TSCONFIG_PATH="$root/tsconfig.json" \ - exec node --import "$root/node_modules/tsx/dist/esm/index.mjs" \ - "$root/apps/cli/src/bin.ts" "$@" diff --git a/docs/api-gateway.i18n.yaml b/docs/api-gateway.i18n.yaml index ba4cbd5f55..a958569942 100644 --- a/docs/api-gateway.i18n.yaml +++ b/docs/api-gateway.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/api-gateway.md -api-gateway.md: 06f98546c8858af08efcb07c007d8e1b95b90c19 -api-gateway.zh.md: 82bf8923c45151d0c00e71848be89806427d1ce3 +api-gateway.md: 3065f3f10861965b327a4412049878dc1ba7faec +api-gateway.zh.md: aa9b726c33fd9f51fc0b2d2ed95c4c9658662796 diff --git a/docs/api-gateway.md b/docs/api-gateway.md index 06f98546c8..3065f3f108 100644 --- a/docs/api-gateway.md +++ b/docs/api-gateway.md @@ -138,16 +138,10 @@ SRC solves only dispatch for a Host process running from source. The Client does ## Development mode -A complete build generates Host contracts before compiling the Host, Client, and Web, so it is the deterministic entry for creating or refreshing all artifacts: +The repository `dsh` script completes the Host, Client, and Web build before starting the source Host. Web development runs that command and the Client plugin watcher in separate terminals: ```sh -pnpm run build -``` - -Web development normally starts the source Host after one complete build and runs the Client plugin watcher in another terminal: - -```sh -pnpm run dsh -- web --dev +pnpm dsh web --dev pnpm run dev:web ``` diff --git a/docs/api-gateway.zh.md b/docs/api-gateway.zh.md index 82bf8923c4..aa9b726c33 100644 --- a/docs/api-gateway.zh.md +++ b/docs/api-gateway.zh.md @@ -138,16 +138,10 @@ SRC 只解决 Host 源码进程的分发问题。Client 不会从运行中的 Ho ## 开发模式 -完整构建会先生成 Host 约定，再编译 Host、Client 与 Web，因此是建立或刷新所有产物的确定性入口： +仓库的 `dsh` 脚本会先完成 Host、Client 与 Web 构建，再启动源码 Host。Web 开发需要在两个终端中分别运行该命令和 Client plugin watcher： ```sh -pnpm run build -``` - -Web 开发通常在完成一次构建后启动源码 Host，并在另一个终端运行 Client plugin watcher： - -```sh -pnpm run dsh -- web --dev +pnpm dsh web --dev pnpm run dev:web ``` diff --git a/docs/config-catalog.i18n.yaml b/docs/config-catalog.i18n.yaml index 3ce68e5c14..4831a38704 100644 --- a/docs/config-catalog.i18n.yaml +++ b/docs/config-catalog.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/config-catalog.md -config-catalog.md: 1646498f379acd628b5c28463b0cabd57d0112a4 -config-catalog.zh.md: 9b8042c616a10da9236b9db0820257a60fd8049d +config-catalog.md: 71a828164b47387f6617dd5abaf7211f39257044 +config-catalog.zh.md: 65a363c2deefbec8b8f01ddcff3dacb29b141b69 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 1646498f37..71a828164b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -533,7 +533,7 @@ export interface Config { } ``` -Source: [`packages/fs/fs-local/src/index.ts:40`](../packages/fs/fs-local/src/index.ts) +Source: [`packages/fs/fs-local/src/index.ts:41`](../packages/fs/fs-local/src/index.ts) ## `@deepseek-ai/dsh-fs-sandbox` @@ -986,6 +986,8 @@ export interface ReplayModelConfig { description?: string /** Optional positive integer context capacity published by the replay adapter. */ contextWindow?: number + /** Optional declared input modalities, so a scenario can exercise capability gates (e.g. image-capable `read_image`). */ + inputModalities?: readonly ModelModality[] /** * Optional per-request output cap the replay route materializes when callers * omit one, so replay reconstructs the request header a live catalog produced. @@ -1001,9 +1003,9 @@ export interface ReplayModelConfig { } ``` -Depends on: [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) +Depends on: [`ModelModality`](../packages/llm/llm/src/index.ts) · [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) -Source: [`packages/support/llm-replay/src/index.ts:769`](../packages/support/llm-replay/src/index.ts) +Source: [`packages/support/llm-replay/src/index.ts:776`](../packages/support/llm-replay/src/index.ts) ## `@deepseek-ai/dsh-llm-retry` @@ -1086,6 +1088,8 @@ export interface StdioConfig { toolCallTimeoutMs: number /** Fail plugin activation when the initial connection or tool synchronization fails. */ failOnStartupError: boolean + /** Automatic reconnect policy after a lost connection; omission uses the defaults. */ + reconnect?: ReconnectConfig } /** Config for connecting to an MCP server over Streamable HTTP (SSE). */ @@ -1106,10 +1110,24 @@ export interface StreamableHttpConfig { toolCallTimeoutMs: number /** Fail plugin activation when the initial connection or tool synchronization fails. */ failOnStartupError: boolean + /** Automatic reconnect policy after a lost connection; omission uses the defaults. */ + reconnect?: ReconnectConfig +} + +/** Automatic reconnect policy for one MCP server connection. */ +export interface ReconnectConfig { + /** Reconnect automatically after a lost connection (default true). */ + enabled?: boolean + /** First reconnect delay in milliseconds; doubles per consecutive failed attempt (default 500). */ + initialDelayMs?: number + /** Backoff ceiling in milliseconds; also the uptime after which the attempt budget resets (default 30000). */ + maxDelayMs?: number + /** Consecutive failed attempts per outage before giving up for good (default 10). */ + maxAttempts?: number } ``` -Source: [`packages/mcp/mcp-client/src/index.ts:94`](../packages/mcp/mcp-client/src/index.ts) +Source: [`packages/mcp/mcp-client/src/index.ts:98`](../packages/mcp/mcp-client/src/index.ts) ## `@deepseek-ai/dsh-permission` @@ -2100,7 +2118,7 @@ export interface Config { } ``` -Source: [`packages/fs/tool-fs/src/index.ts:24`](../packages/fs/tool-fs/src/index.ts) +Source: [`packages/fs/tool-fs/src/index.ts:25`](../packages/fs/tool-fs/src/index.ts) ## `@deepseek-ai/dsh-tool-fs-search` @@ -2721,6 +2739,7 @@ These load from a `cordis.yml` entry with no `config:` block; they declare no co - `@deepseek-ai/dsh-client-ui-skill` ([`packages/client/ui-skill/src/index.ts`](../packages/client/ui-skill/src/index.ts)) - `@deepseek-ai/dsh-client-ui-slash` ([`packages/client/ui-slash/src/index.ts`](../packages/client/ui-slash/src/index.ts)) - `@deepseek-ai/dsh-client-ui-subagent` ([`packages/client/ui-subagent/src/index.ts`](../packages/client/ui-subagent/src/index.ts)) +- `@deepseek-ai/dsh-client-ui-task` ([`packages/client/ui-task/src/index.ts`](../packages/client/ui-task/src/index.ts)) - `@deepseek-ai/dsh-client-ui-theme` ([`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts)) - `@deepseek-ai/dsh-client-ui-tool` ([`packages/client/ui-tool/src/index.ts`](../packages/client/ui-tool/src/index.ts)) - `@deepseek-ai/dsh-client-ui-trajectory` ([`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts)) diff --git a/docs/config-catalog.zh.md b/docs/config-catalog.zh.md index 9b8042c616..65a363c2de 100644 --- a/docs/config-catalog.zh.md +++ b/docs/config-catalog.zh.md @@ -988,6 +988,8 @@ export interface ReplayModelConfig { description?: string /** Optional positive integer context capacity published by the replay adapter. */ contextWindow?: number + /** Optional declared input modalities, so a scenario can exercise capability gates (e.g. image-capable `read_image`). */ + inputModalities?: readonly ModelModality[] /** * Optional per-request output cap the replay route materializes when callers * omit one, so replay reconstructs the request header a live catalog produced. @@ -1003,9 +1005,9 @@ export interface ReplayModelConfig { } ``` -依赖：[`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) +依赖：[`ModelModality`](../packages/llm/llm/src/index.ts) · [`RetryPolicyConfig`](../packages/llm/llm/src/index.ts) -来源：[`packages/support/llm-replay/src/index.ts:769`](../packages/support/llm-replay/src/index.ts) +来源：[`packages/support/llm-replay/src/index.ts:776`](../packages/support/llm-replay/src/index.ts) ## `@deepseek-ai/dsh-llm-retry` @@ -1088,6 +1090,8 @@ export interface StdioConfig { toolCallTimeoutMs: number /** Fail plugin activation when the initial connection or tool synchronization fails. */ failOnStartupError: boolean + /** Automatic reconnect policy after a lost connection; omission uses the defaults. */ + reconnect?: ReconnectConfig } /** Config for connecting to an MCP server over Streamable HTTP (SSE). */ @@ -1108,6 +1112,20 @@ export interface StreamableHttpConfig { toolCallTimeoutMs: number /** Fail plugin activation when the initial connection or tool synchronization fails. */ failOnStartupError: boolean + /** Automatic reconnect policy after a lost connection; omission uses the defaults. */ + reconnect?: ReconnectConfig +} + +/** Automatic reconnect policy for one MCP server connection. */ +export interface ReconnectConfig { + /** Reconnect automatically after a lost connection (default true). */ + enabled?: boolean + /** First reconnect delay in milliseconds; doubles per consecutive failed attempt (default 500). */ + initialDelayMs?: number + /** Backoff ceiling in milliseconds; also the uptime after which the attempt budget resets (default 30000). */ + maxDelayMs?: number + /** Consecutive failed attempts per outage before giving up for good (default 10). */ + maxAttempts?: number } ``` @@ -2722,6 +2740,7 @@ export interface Config { - `@deepseek-ai/dsh-client-ui-skill`（[`packages/client/ui-skill/src/index.ts`](../packages/client/ui-skill/src/index.ts)） - `@deepseek-ai/dsh-client-ui-slash`（[`packages/client/ui-slash/src/index.ts`](../packages/client/ui-slash/src/index.ts)） - `@deepseek-ai/dsh-client-ui-subagent`（[`packages/client/ui-subagent/src/index.ts`](../packages/client/ui-subagent/src/index.ts)） +- `@deepseek-ai/dsh-client-ui-task`（[`packages/client/ui-task/src/index.ts`](../packages/client/ui-task/src/index.ts)） - `@deepseek-ai/dsh-client-ui-theme`（[`packages/client/ui-theme/src/index.ts`](../packages/client/ui-theme/src/index.ts)） - `@deepseek-ai/dsh-client-ui-tool`（[`packages/client/ui-tool/src/index.ts`](../packages/client/ui-tool/src/index.ts)） - `@deepseek-ai/dsh-client-ui-trajectory`（[`packages/client/ui-trajectory/src/index.ts`](../packages/client/ui-trajectory/src/index.ts)） diff --git a/docs/development.i18n.yaml b/docs/development.i18n.yaml index da29debe08..9d8d8fba47 100644 --- a/docs/development.i18n.yaml +++ b/docs/development.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/development.md -development.md: 8e565f21c6e2ede7dab7dbda3c4b18b77ce0920f -development.zh.md: d9c0fbfbb663334b8f7e2ca11d4e8d9a0652c22e +development.md: 7d6ca74df1311560b0d61444c92e74927639ca31 +development.zh.md: 1461717cf496b1863f2f0c47ad4b42990dc789e9 diff --git a/docs/development.md b/docs/development.md index 8e565f21c6..7d6ca74df1 100644 --- a/docs/development.md +++ b/docs/development.md @@ -129,7 +129,7 @@ The root [contributor instructions](../AGENTS.md#commands) summarize common comm The one-shot Headless coding agent needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`: ```sh -pnpm run demo:headless "summarize this workspace" +pnpm dsh --profile headless "summarize this workspace" ``` The self-referential cordis demo can inspect and modify its live plugin runtime and needs the same credentials (`web` by default, or `acp`): diff --git a/docs/development.zh.md b/docs/development.zh.md index d9c0fbfbb6..1461717cf4 100644 --- a/docs/development.zh.md +++ b/docs/development.zh.md @@ -129,7 +129,7 @@ keyless [CI 工作流](../.github/workflows/ci.yml) 将独立门禁分组到若 单次运行的 Headless coding agent 需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`： ```sh -pnpm run demo:headless "summarize this workspace" +pnpm dsh --profile headless "summarize this workspace" ``` 自指的 cordis 演示可以检查并修改其实时插件运行时，并需要相同的凭证（默认 `web`，也可用 `acp`）： diff --git a/docs/module-graph.i18n.yaml b/docs/module-graph.i18n.yaml index b2f838dfce..9804824123 100644 --- a/docs/module-graph.i18n.yaml +++ b/docs/module-graph.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/module-graph.md -module-graph.md: f87070e3eda9ab729dd364cee239b0a4adfcca54 -module-graph.zh.md: 8338461ff4fb50e3eab0b0e68d995138881b8f45 +module-graph.md: 7514e79fbba0fc9d0ce9d3dc63921ca7241916bc +module-graph.zh.md: 86307235d88d98c4e2d7c6333e36630af4cce5c1 diff --git a/docs/module-graph.md b/docs/module-graph.md index f87070e3ed..7514e79fbb 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -167,6 +167,7 @@ flowchart TD pkg_client_ui_slash["client-ui-slash"] pkg_client_ui_slots["client-ui-slots"] pkg_client_ui_subagent["client-ui-subagent"] + pkg_client_ui_task["client-ui-task"] pkg_client_ui_theme["client-ui-theme"] pkg_client_ui_tool["client-ui-tool"] pkg_client_ui_trajectory["client-ui-trajectory"] @@ -792,6 +793,7 @@ flowchart TD pkg_fs_sandbox --> pkg_invariants pkg_fs_sandbox --> pkg_sandbox pkg_fs_sandbox --> pkg_sandbox_policy + pkg_tool_fs --> pkg_attachment pkg_tool_fs --> pkg_fs pkg_tool_fs --> pkg_invariants pkg_tool_fs --> pkg_llm @@ -931,6 +933,7 @@ flowchart TD pkg_mcp_client --> pkg_invariants pkg_mcp_client --> pkg_llm pkg_mcp_client --> pkg_subprocess + pkg_mcp_client --> pkg_timeout pkg_mcp_client --> pkg_tools pkg_tool_bash_persistent --> pkg_agent pkg_tool_bash_persistent --> pkg_invariants @@ -1161,6 +1164,12 @@ flowchart TD pkg_client_ui_subagent --> pkg_invariants pkg_client_ui_subagent --> pkg_subagent pkg_client_ui_subagent --> pkg_token_meter + pkg_client_ui_task --> pkg_client_locale + pkg_client_ui_task --> pkg_client_runtime + pkg_client_ui_task --> pkg_client_ui_conversation + pkg_client_ui_task --> pkg_client_ui_primitives + pkg_client_ui_task --> pkg_client_ui_slots + pkg_client_ui_task --> pkg_invariants pkg_client_ui_tool --> pkg_client_locale pkg_client_ui_tool --> pkg_client_runtime pkg_client_ui_tool --> pkg_client_ui_conversation @@ -1389,7 +1398,7 @@ flowchart TD | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | | [`pwsh-sandbox`](../packages/bash/pwsh-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`pwsh-local`](../packages/bash/pwsh-local), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | | [`fs-sandbox`](../packages/fs/fs-sandbox) | `fs` | [`fs`](../packages/fs/fs), [`fs-local`](../packages/fs/fs-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | -| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) | +| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`attachment`](../packages/attachment/attachment), [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) | | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`subprocess`](../packages/subprocess/subprocess), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-str-replace-editor`](../packages/fs/tool-str-replace-editor) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | @@ -1411,7 +1420,7 @@ flowchart TD | [`timeout-policy`](../packages/guard/timeout-policy) | `guard` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-ask-user`](../packages/interaction/tool-ask-user) | `interaction` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools), [`user-interaction`](../packages/interaction/user-interaction) | | [`tool-lsp`](../packages/lsp/tool-lsp) | `lsp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | -| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`tools`](../packages/core/tools) | +| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-bash-persistent`](../packages/pty/tool-bash-persistent) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/self-modification/tool-cordis) | `self-modification` | [`invariants`](../packages/support/invariants), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | @@ -1446,6 +1455,7 @@ flowchart TD | [`client-ui-goal`](../packages/client/ui-goal) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants) | | [`client-ui-plan`](../packages/client/ui-plan) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants), [`plan-mode`](../packages/plan/plan-mode) | | [`client-ui-subagent`](../packages/client/ui-subagent) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants), [`subagent`](../packages/subagent/subagent), [`token-meter`](../packages/llm/token-meter) | +| [`client-ui-task`](../packages/client/ui-task) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-tool`](../packages/client/ui-tool) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`bash-env`](../packages/bash/bash-env), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`paths`](../packages/util/paths), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-title`](../packages/session/session-title), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks-local`](../packages/tasks/tasks-local), [`tool-bash`](../packages/bash/tool-bash), [`tool-goal`](../packages/goal/tool-goal), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | | [`jsonrpc`](../packages/scaffold/server) | `scaffold` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`sdk-protocol`](../packages/scaffold/protocol), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | diff --git a/docs/module-graph.zh.md b/docs/module-graph.zh.md index 8338461ff4..86307235d8 100644 --- a/docs/module-graph.zh.md +++ b/docs/module-graph.zh.md @@ -169,6 +169,7 @@ flowchart TD pkg_client_ui_slash["client-ui-slash"] pkg_client_ui_slots["client-ui-slots"] pkg_client_ui_subagent["client-ui-subagent"] + pkg_client_ui_task["client-ui-task"] pkg_client_ui_theme["client-ui-theme"] pkg_client_ui_tool["client-ui-tool"] pkg_client_ui_trajectory["client-ui-trajectory"] @@ -794,6 +795,7 @@ flowchart TD pkg_fs_sandbox --> pkg_invariants pkg_fs_sandbox --> pkg_sandbox pkg_fs_sandbox --> pkg_sandbox_policy + pkg_tool_fs --> pkg_attachment pkg_tool_fs --> pkg_fs pkg_tool_fs --> pkg_invariants pkg_tool_fs --> pkg_llm @@ -933,6 +935,7 @@ flowchart TD pkg_mcp_client --> pkg_invariants pkg_mcp_client --> pkg_llm pkg_mcp_client --> pkg_subprocess + pkg_mcp_client --> pkg_timeout pkg_mcp_client --> pkg_tools pkg_tool_bash_persistent --> pkg_agent pkg_tool_bash_persistent --> pkg_invariants @@ -1163,6 +1166,12 @@ flowchart TD pkg_client_ui_subagent --> pkg_invariants pkg_client_ui_subagent --> pkg_subagent pkg_client_ui_subagent --> pkg_token_meter + pkg_client_ui_task --> pkg_client_locale + pkg_client_ui_task --> pkg_client_runtime + pkg_client_ui_task --> pkg_client_ui_conversation + pkg_client_ui_task --> pkg_client_ui_primitives + pkg_client_ui_task --> pkg_client_ui_slots + pkg_client_ui_task --> pkg_invariants pkg_client_ui_tool --> pkg_client_locale pkg_client_ui_tool --> pkg_client_runtime pkg_client_ui_tool --> pkg_client_ui_conversation @@ -1391,7 +1400,7 @@ flowchart TD | [`bash-sandbox`](../packages/bash/bash-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`bash-local`](../packages/bash/bash-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | | [`pwsh-sandbox`](../packages/bash/pwsh-sandbox) | `bash` | [`bash`](../packages/bash/bash), [`invariants`](../packages/support/invariants), [`pwsh-local`](../packages/bash/pwsh-local), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | | [`fs-sandbox`](../packages/fs/fs-sandbox) | `fs` | [`fs`](../packages/fs/fs), [`fs-local`](../packages/fs/fs-local), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy) | -| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) | +| [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`attachment`](../packages/attachment/attachment), [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/interaction/user-approval) | | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`subprocess`](../packages/subprocess/subprocess), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-str-replace-editor`](../packages/fs/tool-str-replace-editor) | `fs` | [`fs`](../packages/fs/fs), [`invariants`](../packages/support/invariants), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | @@ -1413,7 +1422,7 @@ flowchart TD | [`timeout-policy`](../packages/guard/timeout-policy) | `guard` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-ask-user`](../packages/interaction/tool-ask-user) | `interaction` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`tools`](../packages/core/tools), [`user-interaction`](../packages/interaction/user-interaction) | | [`tool-lsp`](../packages/lsp/tool-lsp) | `lsp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`system-prompt`](../packages/core/system-prompt), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | -| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`tools`](../packages/core/tools) | +| [`mcp-client`](../packages/mcp/mcp-client) | `mcp` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-bash-persistent`](../packages/pty/tool-bash-persistent) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`pty`](../packages/pty/pty), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-pty`](../packages/pty/tool-pty) | `pty` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`pty`](../packages/pty/pty), [`retention`](../packages/util/retention), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/self-modification/tool-cordis) | `self-modification` | [`invariants`](../packages/support/invariants), [`scope`](../packages/core/scope), [`tools`](../packages/core/tools) | @@ -1448,6 +1457,7 @@ flowchart TD | [`client-ui-goal`](../packages/client/ui-goal) | `client` | [`api-remotes`](../packages/api/remotes), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`goal`](../packages/goal/goal), [`invariants`](../packages/support/invariants) | | [`client-ui-plan`](../packages/client/ui-plan) | `client` | [`client-connection`](../packages/client/connection), [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants), [`plan-mode`](../packages/plan/plan-mode) | | [`client-ui-subagent`](../packages/client/ui-subagent) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slash`](../packages/client/ui-slash), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants), [`subagent`](../packages/subagent/subagent), [`token-meter`](../packages/llm/token-meter) | +| [`client-ui-task`](../packages/client/ui-task) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`client-ui-tool`](../packages/client/ui-tool) | `client` | [`client-locale`](../packages/client/locale), [`client-runtime`](../packages/client/runtime), [`client-ui-conversation`](../packages/client/ui-conversation), [`client-ui-primitives`](../packages/client/ui-primitives), [`client-ui-slots`](../packages/client/ui-slots), [`invariants`](../packages/support/invariants) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`bash-env`](../packages/bash/bash-env), [`goal`](../packages/goal/goal), [`goal-session`](../packages/goal/goal-session), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-retry`](../packages/llm/llm-retry), [`paths`](../packages/util/paths), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`session-title`](../packages/session/session-title), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks-local`](../packages/tasks/tasks-local), [`tool-bash`](../packages/bash/tool-bash), [`tool-goal`](../packages/goal/tool-goal), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools), [`workspace-context`](../packages/context/workspace-context) | | [`jsonrpc`](../packages/scaffold/server) | `scaffold` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`sdk-protocol`](../packages/scaffold/protocol), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | diff --git a/docs/subsystems/filesystem.i18n.yaml b/docs/subsystems/filesystem.i18n.yaml index 783f8b8d66..73cf951086 100644 --- a/docs/subsystems/filesystem.i18n.yaml +++ b/docs/subsystems/filesystem.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/subsystems/filesystem.md -filesystem.md: 00e28130db9f60e6ad5f8c582ca5531482cdeb32 -filesystem.zh.md: 5cf6be12f41b36c8149a941a4d251c4497ed4738 +filesystem.md: 01fe2d07f5497374019855ca46ced7e173d21445 +filesystem.zh.md: e68246d7a44b8812e132e02979a2c0cda6adb792 diff --git a/docs/subsystems/filesystem.md b/docs/subsystems/filesystem.md index 00e28130db..01fe2d07f5 100644 --- a/docs/subsystems/filesystem.md +++ b/docs/subsystems/filesystem.md @@ -52,7 +52,7 @@ type FsTargetKey = Branded<'FsTargetKey'> type FsVersion = Branded<'FsVersion'> ``` -`stat` returns metadata (never content), or `undefined` when the target is absent. `type` lets the tool reject directories/special files before reading, and `size` lets it choose `readText` vs `streamText` without probing by failure. A protocol consumer that needs a byte ceiling applies it while consuming `streamText`, so the filesystem seam needs no consumer-specific bounded-read primitive. +`stat` returns metadata (never content), or `undefined` when the target is absent. `type` lets consumers reject directories and special files before reading, and `size` lets text consumers choose `readText` vs `streamText` without probing by failure. A text consumer applies its own retention ceiling while consuming `streamText`. Raw-byte consumers use `readBytes(target, signal, maxBytes)`; its required complete-content cap makes a known or discovered overflow fail with `FS_TOO_LARGE` instead of truncating or buffering without a bound. ```ts type-equiv /** @@ -256,6 +256,7 @@ type FsErrorCode = | 'FS_NOT_DIRECTORY' | 'FS_NOT_TEXT' | 'FS_NOT_REGULAR_FILE' + | 'FS_TOO_LARGE' | 'FS_PERMISSION_DENIED' | 'FS_SANDBOX_DENIED' | 'FS_IO_ERROR' @@ -274,7 +275,7 @@ type FsErrorCode = ## The service and the plugin -`FileSystem` (`ctx.fs`, abstract) owns the provider primitives: `resolve`, `processPath`, `fileUrl`, `contains`, `stat`, `lstat`, `readText`, `streamText`, `listDir`, `writeText`, and `editText`. `dsh-fs-policy` registers **no service** — it is a plugin that adds policy through the `fs/*` event gate: it decides the write/edit intent waterfalls from unseen/absent/present state and records `FsObservation` values. The executor is `dsh-tool-fs`: it reads/writes/edits through `ctx.fs`, dispatches the waterfalls, and emits the recording event. The generated [`ctx.fs` section](#ctxfs--filesystem-abstract-seam) below shows the exact signatures. +`FileSystem` (`ctx.fs`, abstract) owns the provider primitives: `resolve`, `processPath`, `fileUrl`, `contains`, `stat`, `lstat`, `readText`, `streamText`, `readBytes`, `listDir`, `writeText`, and `editText`. `dsh-fs-policy` registers **no service** — it is a plugin that adds policy through the `fs/*` event gate: it decides the write/edit intent waterfalls from unseen/absent/present state and records `FsObservation` values. The executor is `dsh-tool-fs`: it reads/writes/edits through `ctx.fs`, dispatches the waterfalls, and emits the recording event. The generated [`ctx.fs` section](#ctxfs--filesystem-abstract-seam) below shows the exact signatures. @@ -373,6 +374,18 @@ abstract readText(target: FsTarget, signal?: AbortSignal): Promise */ abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> +/** + * Read the whole regular file as raw bytes with no decoding or binary + * rejection. The bound lives at this seam so a backend can never buffer an + * unbounded file: a target known or discovered to exceed `maxBytes` fails + * with `FS_TOO_LARGE` instead of returning a truncated result. + * @param target - the resolved target to read. + * @param signal - aborts the read. + * @param maxBytes - inclusive byte cap on the complete content. + * @returns the full raw content, at most `maxBytes` long. + */ +abstract readBytes(target: FsTarget, signal: AbortSignal | undefined, maxBytes: number): Promise + /** * List direct children of a directory in stable name order. Returns resolved * child targets plus cheap metadata only; never reads file contents. diff --git a/docs/subsystems/filesystem.zh.md b/docs/subsystems/filesystem.zh.md index 5cf6be12f4..e68246d7a4 100644 --- a/docs/subsystems/filesystem.zh.md +++ b/docs/subsystems/filesystem.zh.md @@ -52,7 +52,7 @@ type FsTargetKey = Branded<'FsTargetKey'> type FsVersion = Branded<'FsVersion'> ``` -`stat` 返回元数据（从不返回内容），目标不存在时返回 `undefined`。`type` 让工具在读取前拒绝目录或特殊文件；`size` 让工具无需通过失败探测即可选择 `readText` 还是 `streamText`。需要字节上限的协议消费方在消费 `streamText` 时执行该上限，因此文件系统 seam 无需消费方专用的有界读取原语。 +`stat` 返回元数据（从不返回内容），目标不存在时返回 `undefined`。`type` 让消费方在读取前拒绝目录和特殊文件；`size` 让文本消费方无需通过失败探测即可选择 `readText` 还是 `streamText`。文本消费方在消费 `streamText` 时执行自己的保留量上限。原始字节消费方调用 `readBytes(target, signal, maxBytes)`；其必填的完整内容上限会使已知或读取中发现的超限以 `FS_TOO_LARGE` 失败，不会截断结果或无界缓冲。 ```ts type-equiv /** @@ -256,6 +256,7 @@ type FsErrorCode = | 'FS_NOT_DIRECTORY' | 'FS_NOT_TEXT' | 'FS_NOT_REGULAR_FILE' + | 'FS_TOO_LARGE' | 'FS_PERMISSION_DENIED' | 'FS_SANDBOX_DENIED' | 'FS_IO_ERROR' @@ -274,7 +275,7 @@ type FsErrorCode = ## 服务与插件 -`FileSystem`（`ctx.fs`，abstract）拥有提供方原语：`resolve`、`processPath`、`fileUrl`、`contains`、`stat`、`lstat`、`readText`、`streamText`、`listDir`、`writeText` 与 `editText`。`dsh-fs-policy` **不注册服务**——它是一个通过 `fs/*` 事件门禁添加策略的插件：根据未见/缺失/存在状态对写入与编辑意图 waterfall 作出决策，并记录 `FsObservation` 值。执行器是 `dsh-tool-fs`：它通过 `ctx.fs` 读取/写入/编辑，分发 waterfall，并 emit 记录事件。下方生成的 [`ctx.fs` 小节](#ctxfs--filesystem-abstract-seam) 展示确切的 `ctx.fs` 签名。 +`FileSystem`（`ctx.fs`，abstract）拥有提供方原语：`resolve`、`processPath`、`fileUrl`、`contains`、`stat`、`lstat`、`readText`、`streamText`、`readBytes`、`listDir`、`writeText` 与 `editText`。`dsh-fs-policy` **不注册服务**——它是一个通过 `fs/*` 事件门禁添加策略的插件：根据未见/缺失/存在状态对写入与编辑意图 waterfall 作出决策，并记录 `FsObservation` 值。执行器是 `dsh-tool-fs`：它通过 `ctx.fs` 读取/写入/编辑，分发 waterfall，并 emit 记录事件。下方生成的 [`ctx.fs` 小节](#ctxfs--filesystem-abstract-seam) 展示确切的 `ctx.fs` 签名。 @@ -373,6 +374,18 @@ abstract readText(target: FsTarget, signal?: AbortSignal): Promise */ abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> +/** + * Read the whole regular file as raw bytes with no decoding or binary + * rejection. The bound lives at this seam so a backend can never buffer an + * unbounded file: a target known or discovered to exceed `maxBytes` fails + * with `FS_TOO_LARGE` instead of returning a truncated result. + * @param target - the resolved target to read. + * @param signal - aborts the read. + * @param maxBytes - inclusive byte cap on the complete content. + * @returns the full raw content, at most `maxBytes` long. + */ +abstract readBytes(target: FsTarget, signal: AbortSignal | undefined, maxBytes: number): Promise + /** * List direct children of a directory in stable name order. Returns resolved * child targets plus cheap metadata only; never reads file contents. diff --git a/docs/subsystems/tasks.i18n.yaml b/docs/subsystems/tasks.i18n.yaml index 6a95ccf73e..75b47a572b 100644 --- a/docs/subsystems/tasks.i18n.yaml +++ b/docs/subsystems/tasks.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/subsystems/tasks.md -tasks.md: 2da8212b3edf7111180b60162108af0aebb249c1 -tasks.zh.md: 825a69029ae931f9668cca863c6ebb2324634a9a +tasks.md: 6d205d9a7840aef1c115c97836886f51bed829b9 +tasks.zh.md: 59b7c03d240c45e633f55583b3e08776ec470d52 diff --git a/docs/subsystems/tasks.md b/docs/subsystems/tasks.md index 2da8212b3e..6d205d9a78 100644 --- a/docs/subsystems/tasks.md +++ b/docs/subsystems/tasks.md @@ -246,6 +246,30 @@ abstract wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSigna */ abstract onTaskDone(listener: TaskDoneListener): () => void +/** +/** + * Register an effect-scoped observer of visible-set changes. It fires after + * every commit that changes what {@link list} returns for that owner — + * registration, every stopping transition (including the one teardown + * performs before it awaits a slow producer), settlement, owner-disposal + * removal, and the emptying that service disposal commits — so an observer + * re-reads rather than accumulating deltas. + * + * Delivery is owner-relative on the same terms as {@link onTaskDone}: an + * observer registered from an unscoped context — a host composition's own + * carrier — sees every owner, while one registered under an agent + * composition's scope sees exactly the agents composed under it. + * + * This is not a superset of {@link onTaskDone}: that one delivers the terminal + * record under first-wins semantics a control surface couples to notice + * delivery, while this one carries no delivery meaning and marks nothing + * reported. Listeners are contained and never awaited. + * @param listener - receives the owner whose visible set changed, or + * `undefined` when an unowned task changed and every caller's set did. + * @returns disposer that unregisters the listener. + */ +abstract onTasksChanged(listener: TasksChangedListener): () => void + /** * Attach an effect-scoped surface that can read and stop tasks. It serves the * owners its registering context's scope covers, and {@link start} refuses an @@ -258,5 +282,5 @@ abstract attachSurface(name: string): () => void Types: [Agent](core.md) -Source: [`packages/tasks/tasks/src/index.ts:55`](../../packages/tasks/tasks/src/index.ts) +Source: [`packages/tasks/tasks/src/index.ts:58`](../../packages/tasks/tasks/src/index.ts) diff --git a/docs/subsystems/tasks.zh.md b/docs/subsystems/tasks.zh.md index 825a69029a..59b7c03d24 100644 --- a/docs/subsystems/tasks.zh.md +++ b/docs/subsystems/tasks.zh.md @@ -151,7 +151,7 @@ interface TaskRead { ## 服务行为 -抽象的 [`TaskService`](../../packages/tasks/tasks/src/index.ts) Service Definition 规定原子 `start`、限定调用方作用域的 `get` 和 `list`、`read`、`kill`、有界 `wait`、故障隔离的 `onTaskDone` 监听器，以及 `attachSurface` 何时可用；[`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) 是其进程局部 Service provider。授权会比较拥有者会话；拥有者清理会选择确切的已注册 `Agent` 实例。Service Definition 约定见 [`dsh-tasks`](../../packages/tasks/tasks/README.md)，注册表生命周期见 [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md)，面向模型的 Consumer 见 [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md)。 +抽象的 [`TaskService`](../../packages/tasks/tasks/src/index.ts) Service Definition 规定原子 `start`、限定调用方作用域的 `get` 和 `list`、`read`、`kill`、有界 `wait`、故障隔离的 `onTaskDone` 与 `onTasksChanged` 监听器，以及 `attachSurface` 何时可用；[`LocalTaskService`](../../packages/tasks/tasks-local/src/index.ts) 是其进程局部 Service provider。授权会比较拥有者会话；拥有者清理会选择确切的已注册 `Agent` 实例。Service Definition 约定见 [`dsh-tasks`](../../packages/tasks/tasks/README.md)，注册表生命周期见 [`dsh-tasks-local`](../../packages/tasks/tasks-local/README.md)，面向模型的 Consumer 见 [`dsh-tool-tasks`](../../packages/tasks/tool-tasks/README.md)。 @@ -246,6 +246,30 @@ abstract wait(id: TaskId, timeoutMs: number, caller?: Agent, signal?: AbortSigna */ abstract onTaskDone(listener: TaskDoneListener): () => void +/** +/** + * Register an effect-scoped observer of visible-set changes. It fires after + * every commit that changes what {@link list} returns for that owner — + * registration, every stopping transition (including the one teardown + * performs before it awaits a slow producer), settlement, owner-disposal + * removal, and the emptying that service disposal commits — so an observer + * re-reads rather than accumulating deltas. + * + * Delivery is owner-relative on the same terms as {@link onTaskDone}: an + * observer registered from an unscoped context — a host composition's own + * carrier — sees every owner, while one registered under an agent + * composition's scope sees exactly the agents composed under it. + * + * This is not a superset of {@link onTaskDone}: that one delivers the terminal + * record under first-wins semantics a control surface couples to notice + * delivery, while this one carries no delivery meaning and marks nothing + * reported. Listeners are contained and never awaited. + * @param listener - receives the owner whose visible set changed, or + * `undefined` when an unowned task changed and every caller's set did. + * @returns disposer that unregisters the listener. + */ +abstract onTasksChanged(listener: TasksChangedListener): () => void + /** * Attach an effect-scoped surface that can read and stop tasks. It serves the * owners its registering context's scope covers, and {@link start} refuses an @@ -258,5 +282,5 @@ abstract attachSurface(name: string): () => void Types: [Agent](core.md) -Source: [`packages/tasks/tasks/src/index.ts:55`](../../packages/tasks/tasks/src/index.ts) +Source: [`packages/tasks/tasks/src/index.ts:58`](../../packages/tasks/tasks/src/index.ts) diff --git a/docs/tool-catalog.i18n.yaml b/docs/tool-catalog.i18n.yaml index 794985a9e5..6a207bdebb 100644 --- a/docs/tool-catalog.i18n.yaml +++ b/docs/tool-catalog.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/tool-catalog.md -tool-catalog.md: 58d560832ac8de5dc660a3c3ed75ab829cd262e8 -tool-catalog.zh.md: f2e330251db8a1be842dc05d89014a7be65369c6 +tool-catalog.md: 80b088c83c6c63e282dc00c55f22614250016caa +tool-catalog.zh.md: 22b2b4521d58289d1b7f8dbe65454a620ce34ca4 diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 58d560832a..80b088c83c 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -23,7 +23,7 @@ This table connects model-visible tool names to the plugin package and service s | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`, `cordis_mount`, `cordis_unmount` | `ctx.tools` | `tool/call`, `tool/result`, `process-local temporary Plugin lifecycle` | - | Not in any shipped tree (a deliberate opt-in — temporary Plugin code reaches the real runtime, see .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md). Plugins created by cordis_mount may register ADDITIONAL model-visible tools until unmounted or DSH restarts; a full changed request header logs those tool-set changes. | | `@deepseek-ai/dsh-tool-bash-persistent` | `bash` | `ctx.tools`, `ctx.pty`, `an owning Agent at execution time` | `tool/call`, `PTY shell state`, `tool/result` | - | One owner-isolated persistent bash tool; deployment composition supplies the PTY backend and may override the model-facing environment description. | | `@deepseek-ai/dsh-tool-str-replace-editor` | `str_replace_editor` | `ctx.tools`, `ctx.fs` | `tool/call`, `fs/observed after view presence/absence, edit absence, or successful mutation`, `tool/result` | - | Standalone view/create/unique literal replace/line insert tool over the filesystem seam; it composes with any shell or terminal surface. | -| `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after read presence/absence or successful mutation`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. | +| `@deepseek-ai/dsh-tool-fs` | `edit`, `read`, `read_image`, `write` | `ctx.tools`, `ctx.fs`, `ctx.systemPrompt`, `ctx.attachments (read_image registration)`, `ctx.llm + an image-capable route (read_image execution)` | `tool/call`, `fs/write-intent or fs/edit-intent for mutations`, `fs/observed after read presence/absence or successful file operation`, `durable attachment (read_image)`, `tool/result` | - | The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. `read_image` is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. | | `@deepseek-ai/dsh-tool-fs-search` | `glob`, `grep` | `ctx.tools`, `ctx.subprocess`, `ctx.systemPrompt` | `tool/call`, `tool/result` | - | glob and grep are unconditional discovery tools that spawn the packaged ripgrep binary (`@vscode/ripgrep`) through ctx.subprocess as ordinary foreground calls (never background tasks) — no host `rg` install and no shell layer. The catalog uses `sampleOverCapGlobResults: true`; deployments must choose that behavior explicitly. Capped results save the complete formatted list through the optional ctx.spillStore backend; returned locators are follow-up-readable/searchable when the backend exposes local paths in co-located deployments. | | `@deepseek-ai/dsh-tool-pty` | `terminal_close`, `terminal_list`, `terminal_open`, `terminal_read`, `terminal_send`, `terminal_signal` | `ctx.tools`, `ctx.pty`, `ctx.systemPrompt`, `ctx.tasks at call time for run_in_background` | `tool/call`, `tool/result` | - | The six terminal tools are opt-in and complement one-shot bash/filesystem tools. `terminal_send(run_in_background: true)` registers with `ctx.tasks`; TUI, named key sequences, BEL, resize, auto-start, and cross-agent sharing are absent from the schema. | | `@deepseek-ai/dsh-tool-goal` | `create_goal`, `get_goal`, `update_goal` | `ctx.tools`, `ctx.agents`, `ctx.goals`, `ctx.systemPrompt`, `a calling Agent in an authorized open turn` | `tool/call`, `goal/change for mutations`, `tool/result` | - | create, edit, pause, and resume require direct-human root authority; complete and blocked also accept the exact current goal round. The default blocked lower bound is three admitted rounds. | @@ -485,6 +485,27 @@ Read a UTF-8 text file and return line-numbered content. Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) +### `read_image` + +Read a PNG/JPEG/WebP/GIF file and return the image itself. Requires the current model to accept image input. + +```json +{ + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to the image file, resolved by the filesystem backend." + } + }, + "required": [ + "file_path" + ] +} +``` + +Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) + ### `write` Create or fully replace a UTF-8 text file. @@ -511,7 +532,7 @@ Create or fully replace a UTF-8 text file. Source: [`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) -The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin. +The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. `read_image` is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input. ## `@deepseek-ai/dsh-tool-fs-search` diff --git a/docs/tool-catalog.zh.md b/docs/tool-catalog.zh.md index f2e330251d..22b2b4521d 100644 --- a/docs/tool-catalog.zh.md +++ b/docs/tool-catalog.zh.md @@ -25,7 +25,7 @@ | `@deepseek-ai/dsh-tool-cordis` | `cordis_inspect`、`cordis_mount`、`cordis_unmount` | `ctx.tools` | `tool/call`、`tool/result`、`process-local temporary Plugin lifecycle` | - | 不在任何随产品发布的树中，需要有意选择启用；临时 Plugin 代码可以访问真实运行时，见 .agents/notes/implemented/feature/2026-07-08-self-referential-cordis-toolset.md。由 cordis_mount 创建的插件在卸载或 DSH 重启之前可以注册**额外的**模型可见工具；发生这类工具集变更时，系统会记录完整且有变动的请求头。 | | `@deepseek-ai/dsh-tool-bash-persistent` | `bash` | `ctx.tools`、`ctx.pty`、`an owning Agent at execution time` | `tool/call`、`PTY shell state`、`tool/result` | - | 一个按所有者隔离的持久 bash 工具；部署组合提供 PTY 后端，并可覆盖面向模型的环境描述。 | | `@deepseek-ai/dsh-tool-str-replace-editor` | `str_replace_editor` | `ctx.tools`、`ctx.fs` | `tool/call`、`fs/observed after view presence/absence, edit absence, or successful mutation`、`tool/result` | - | 基于文件系统 seam 的独立查看／创建／唯一字面量替换／按行插入工具；可与任何 shell 或终端接口组合。 | -| `@deepseek-ai/dsh-tool-fs` | `edit`、`read`、`write` | `ctx.tools`、`ctx.fs`、`ctx.systemPrompt` | `tool/call`、`fs/write-intent or fs/edit-intent for mutations`、`fs/observed after read presence/absence or successful mutation`、`tool/result` | - | 先读后写／编辑策略由 `@deepseek-ai/dsh-fs-policy` 添加；它是一个 `fs/*` 事件门禁插件，不会改变 schema。加载这些工具的部署按预期也应加载该插件。无论是否加载策略插件，上述工具 schema 都完全相同。 | +| `@deepseek-ai/dsh-tool-fs` | `edit`、`read`、`read_image`、`write` | `ctx.tools`、`ctx.fs`、`ctx.systemPrompt`、`ctx.attachments (read_image registration)`、`ctx.llm + an image-capable route (read_image execution)` | `tool/call`、`fs/write-intent or fs/edit-intent for mutations`、`fs/observed after read presence/absence or successful file operation`、`durable attachment (read_image)`、`tool/result` | - | 先读后写／编辑策略由 `@deepseek-ai/dsh-fs-policy` 添加；它是一个 `fs/*` 事件门禁插件，不会改变 schema。加载这些工具的部署按预期也应加载该插件。没有 `ctx.attachments` 时 `read_image` 不会注册；其 schema 与路由无关，执行时除非确切路由的模型声明图像输入，否则拒绝。 | | `@deepseek-ai/dsh-tool-fs-search` | `glob`、`grep` | `ctx.tools`、`ctx.subprocess`、`ctx.systemPrompt` | `tool/call`、`tool/result` | - | glob 和 grep 是无条件可用的发现工具，通过 ctx.subprocess spawn 随包提供的 ripgrep 二进制文件（`@vscode/ripgrep`），并作为普通前台调用运行，绝不作为后台任务；无需在宿主机安装 `rg`，也不经过 shell 层。本目录使用 `sampleOverCapGlobResults: true`；部署必须显式选择该行为。结果超过上限时，会通过可选的 ctx.spillStore 后端保存完整的格式化列表；在共置部署中，如果后端公开本地路径，返回的定位信息可供后续读取／搜索。 | | `@deepseek-ai/dsh-tool-pty` | `terminal_close`、`terminal_list`、`terminal_open`、`terminal_read`、`terminal_send`、`terminal_signal` | `ctx.tools`、`ctx.pty`、`ctx.systemPrompt`、`ctx.tasks at call time for run_in_background` | `tool/call`、`tool/result` | - | 这 6 个终端工具需要选择启用，用于补充一次性 bash／文件系统工具。`terminal_send(run_in_background: true)` 会注册到 `ctx.tasks`；schema 不包含 TUI、具名按键序列、BEL、调整尺寸、自动启动和跨 agent 共享。 | | `@deepseek-ai/dsh-tool-goal` | `create_goal`、`get_goal`、`update_goal` | `ctx.tools`、`ctx.agents`、`ctx.goals`、`ctx.systemPrompt`、`a calling Agent in an authorized open turn` | `tool/call`、`goal/change for mutations`、`tool/result` | - | create、edit、pause 和 resume 要求直接来自人类的根权限；complete 和 blocked 也接受确切的当前 Goal Round。blocked 的默认下限是 3 个获准的 Round。 | @@ -489,6 +489,27 @@ pwsh 工具是 Windows 组合中 bash 执行器 seam 的 PowerShell 方言消费 来源：[`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) +### `read_image` + +读取 PNG/JPEG/WebP/GIF 文件并返回图像本身。要求当前模型接受图像输入。 + +```json +{ + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to the image file, resolved by the filesystem backend." + } + }, + "required": [ + "file_path" + ] +} +``` + +来源：[`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) + ### `write` 创建或完全替换 UTF-8 文本文件。 @@ -515,7 +536,7 @@ pwsh 工具是 Windows 组合中 bash 执行器 seam 的 PowerShell 方言消费 来源：[`packages/fs/tool-fs/src/index.ts`](../packages/fs/tool-fs/src/index.ts) -先读后写／编辑策略由 `@deepseek-ai/dsh-fs-policy` 添加；它是一个 `fs/*` 事件门禁插件，不会改变 schema。加载这些工具的部署按预期也应加载该插件。无论是否加载策略插件，上述工具 schema 都完全相同。 +先读后写／编辑策略由 `@deepseek-ai/dsh-fs-policy` 添加；它是一个 `fs/*` 事件门禁插件，不会改变 schema。加载这些工具的部署按预期也应加载该插件。没有 `ctx.attachments` 时 `read_image` 不会注册；其 schema 与路由无关，执行时除非确切路由的模型声明图像输入，否则拒绝。 ## `@deepseek-ai/dsh-tool-fs-search` diff --git a/docs/user/develop/basic/index.i18n.yaml b/docs/user/develop/basic/index.i18n.yaml index bb4870f624..6684d18070 100644 --- a/docs/user/develop/basic/index.i18n.yaml +++ b/docs/user/develop/basic/index.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/user/develop/basic/index.md -index.md: fe525018011809abe4dd18ac5739c54cd330c8f6 -index.zh.md: 0dbb7275be3c7147395041fb18d49a7f6ea69cdd +index.md: e57a42b42690bd92450cc26876c13a1622bb80cc +index.zh.md: 240623341618acd6501f2897ae2844fde0a5b73b diff --git a/docs/user/develop/basic/index.md b/docs/user/develop/basic/index.md index fe52501801..e57a42b426 100644 --- a/docs/user/develop/basic/index.md +++ b/docs/user/develop/basic/index.md @@ -56,7 +56,7 @@ Create `scratch-plugin/cordis.yml` as a Web overlay that inserts the local plugi Start the Web UI with that overlay: ```sh -pnpm run dsh web --patch ./scratch-plugin/cordis.yml +pnpm dsh web --patch ./scratch-plugin/cordis.yml ``` Open `http://127.0.0.1:3080`. The terminal prints `[hello-plugin] plugin loaded!` during startup. diff --git a/docs/user/develop/basic/index.zh.md b/docs/user/develop/basic/index.zh.md index 0dbb7275be..2406233416 100644 --- a/docs/user/develop/basic/index.zh.md +++ b/docs/user/develop/basic/index.zh.md @@ -56,7 +56,7 @@ export function apply(ctx: Context) { 使用该覆盖层启动 Web UI： ```sh -pnpm run dsh web --patch ./scratch-plugin/cordis.yml +pnpm dsh web --patch ./scratch-plugin/cordis.yml ``` 打开 `http://127.0.0.1:3080`。启动期间，终端会打印 `[hello-plugin] plugin loaded!`。 diff --git a/docs/user/develop/basic/tool.i18n.yaml b/docs/user/develop/basic/tool.i18n.yaml index 3ddc760f7d..2fdba218d0 100644 --- a/docs/user/develop/basic/tool.i18n.yaml +++ b/docs/user/develop/basic/tool.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/user/develop/basic/tool.md -tool.md: f110bd2c10caf21ea8c87bc32fd43b01b209a9d1 -tool.zh.md: a237b6015de0ea6141a94c56aaa6f68c73fa3feb +tool.md: a149f6876c573c9ece4b066ef6c211f69b0b03a8 +tool.zh.md: 1f9a1172bcde33a1d7319492f15686c47de01174 diff --git a/docs/user/develop/basic/tool.md b/docs/user/develop/basic/tool.md index f110bd2c10..a149f6876c 100644 --- a/docs/user/develop/basic/tool.md +++ b/docs/user/develop/basic/tool.md @@ -40,7 +40,7 @@ export function apply(ctx: Context) { Restart the development command if it is not running: ```sh -pnpm run dsh web --patch ./scratch-plugin/cordis.yml +pnpm dsh web --patch ./scratch-plugin/cordis.yml ``` Open `http://127.0.0.1:3080` and ask: `Use the greet tool to greet Ada.` The model can call `greet` and receives `Hello, Ada!` as the tool result. diff --git a/docs/user/develop/basic/tool.zh.md b/docs/user/develop/basic/tool.zh.md index a237b6015d..1f9a1172bc 100644 --- a/docs/user/develop/basic/tool.zh.md +++ b/docs/user/develop/basic/tool.zh.md @@ -40,7 +40,7 @@ export function apply(ctx: Context) { 如果开发命令未在运行，请重新启动： ```sh -pnpm run dsh web --patch ./scratch-plugin/cordis.yml +pnpm dsh web --patch ./scratch-plugin/cordis.yml ``` 打开 `http://127.0.0.1:3080`，然后输入：`Use the greet tool to greet Ada.` 模型可以调用 `greet`，并收到 `Hello, Ada!` 这一工具结果。 diff --git a/docs/user/guide/providers.i18n.yaml b/docs/user/guide/providers.i18n.yaml index c95a0db6c0..9a702c61e3 100644 --- a/docs/user/guide/providers.i18n.yaml +++ b/docs/user/guide/providers.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/user/guide/providers.md -providers.md: 4667e54161e77a62d454f3f78a8164d5c79b78c8 -providers.zh.md: 15e0ccc826a5c285c71d4776793f8048c11f6254 +providers.md: 31b4be666bd6b7a402a0bae7bc8f810fd2d928d8 +providers.zh.md: bd95c63cacd9718b3ffc1f78e17270e7022b21e0 diff --git a/docs/user/guide/providers.md b/docs/user/guide/providers.md index 4667e54161..31b4be666b 100644 --- a/docs/user/guide/providers.md +++ b/docs/user/guide/providers.md @@ -15,7 +15,7 @@ Adding a provider therefore rarely means editing `cordis.yml` — writing settin ## Configure from the web UI -Start `pnpm run dsh web` and open **Settings → Models**. +Start `pnpm dsh web` and open **Settings → Models**. ![The Models page: the DeepSeek card, with Add provider and Add a custom provider below it](providers-models-page.png) diff --git a/docs/user/guide/providers.zh.md b/docs/user/guide/providers.zh.md index 15e0ccc826..bd95c63cac 100644 --- a/docs/user/guide/providers.zh.md +++ b/docs/user/guide/providers.zh.md @@ -15,7 +15,7 @@ Harness 出厂自带 DeepSeek，同时预装了一个通用的多提供方适配 ## 在 Web 界面里配置 -启动 `pnpm run dsh web`，打开**设置 → 模型**。 +启动 `pnpm dsh web`，打开**设置 → 模型**。 ![模型页：DeepSeek 卡片，以及添加提供方与添加自定义提供方两个入口](providers-models-page.zh.png) diff --git a/docs/user/guide/quickstart.i18n.yaml b/docs/user/guide/quickstart.i18n.yaml index f31426730a..68d0156d3a 100644 --- a/docs/user/guide/quickstart.i18n.yaml +++ b/docs/user/guide/quickstart.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write docs/user/guide/quickstart.md -quickstart.md: 8e883efd470fef329a7308f1017cab0b7afcdd67 -quickstart.zh.md: e0e3f4e4754bca588831b6d204f77d1c97a140b3 +quickstart.md: 635c0dffd6119f95c1951a441691f87f04396b4a +quickstart.zh.md: d0921382bcb0844fa0260c51546622c582867e68 diff --git a/docs/user/guide/quickstart.md b/docs/user/guide/quickstart.md index 8e883efd47..635c0dffd6 100644 --- a/docs/user/guide/quickstart.md +++ b/docs/user/guide/quickstart.md @@ -22,7 +22,6 @@ pnpm -v git clone https://github.com/deepseek-ai/deepseek-harness-sdk.git cd deepseek-harness pnpm install -pnpm run build ``` Create the gitignored repository-root `.env`: @@ -36,7 +35,7 @@ DEEPSEEK_API_KEY=sk-your-key-here Run a non-interactive task and print its final answer: ```sh -pnpm run dsh --profile headless "summarize the architecture of this workspace" +pnpm dsh --profile headless "summarize the architecture of this workspace" ``` `dsh --profile headless` creates and persists a fresh session, prints the final assistant answer, and exits. It starts no Web server or listening port, and a successful run leaves stderr empty. @@ -46,7 +45,7 @@ pnpm run dsh --profile headless "summarize the architecture of this workspace" Start the browser interface: ```sh -pnpm run dsh web +pnpm dsh web ``` Open `http://127.0.0.1:3080`. The agent can read and write files, run commands, delegate subtasks, and track a plan. Try: `Create hello.js in the current directory, print "Hello from Harness!", and run it`. diff --git a/docs/user/guide/quickstart.zh.md b/docs/user/guide/quickstart.zh.md index e0e3f4e475..d0921382bc 100644 --- a/docs/user/guide/quickstart.zh.md +++ b/docs/user/guide/quickstart.zh.md @@ -22,7 +22,6 @@ pnpm -v git clone https://github.com/deepseek-ai/deepseek-harness-sdk.git cd deepseek-harness pnpm install -pnpm run build ``` 在仓库根目录创建已被 Git 忽略的 `.env`： @@ -36,7 +35,7 @@ DEEPSEEK_API_KEY=sk-your-key-here 运行一个非交互式任务并打印最终回答： ```sh -pnpm run dsh --profile headless "summarize the architecture of this workspace" +pnpm dsh --profile headless "summarize the architecture of this workspace" ``` `dsh --profile headless` 创建并持久化一个新会话，打印最终助手回答，然后退出。它不会启动 Web 服务器或监听端口；成功运行时 stderr 为空。 @@ -46,7 +45,7 @@ pnpm run dsh --profile headless "summarize the architecture of this workspace" 启动浏览器界面： ```sh -pnpm run dsh web +pnpm dsh web ``` 打开 `http://127.0.0.1:3080`。agent 可以读写文件、运行命令、分配子任务和跟踪计划。可以尝试：`Create hello.js in the current directory, print "Hello from Harness!", and run it`。 diff --git a/examples/acp-agent/image-text-route.cordis.snapshot.yml b/examples/acp-agent/image-text-route.cordis.snapshot.yml new file mode 100644 index 0000000000..bd1c0e01ea --- /dev/null +++ b/examples/acp-agent/image-text-route.cordis.snapshot.yml @@ -0,0 +1,39 @@ +# Keyless replay for the read-image refusal scenario: identical to the +# image.cordis.snapshot.yml overlay except the replay catalog leaves flash +# text-only, so the strict read_image gate refuses and no image ever enters +# the durable log. +- id: base + name: '@deepseek-ai/cordis-plugin-include' + config: + path: ./cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + config: + provider: deepseek-official + model: deepseek-v4-flash + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + persistenceCompression: none + workspaceContext: + maxBytes: 65536 + persona: | + You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + + Verify your work by running the code or tests. Keep answers brief and factual. + - insert: + - id: attachment-local + name: '@deepseek-ai/dsh-attachment-local' + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek-official + name: DeepSeek + models: + - id: deepseek-v4-flash + inputModalities: [text] + - id: deepseek-v4-pro + inputModalities: [text] diff --git a/examples/acp-agent/image-text-route.cordis.yml b/examples/acp-agent/image-text-route.cordis.yml new file mode 100644 index 0000000000..bbb5b9b4c0 --- /dev/null +++ b/examples/acp-agent/image-text-route.cordis.yml @@ -0,0 +1,27 @@ +# Text-route image overlay: the attachment store registers read_image, but the +# strict execution gate refuses on a route that does not declare image input, +# so a text-only deployment keeps its durable history text-clean. The app +# config is restated to re-pin `deepseek-v4-flash` (base ships pro; the +# authored fixture and the pinned header class are flash), because a config +# patch replaces the whole app config. +- id: base + name: '@deepseek-ai/cordis-plugin-include' + config: + path: ./cordis.yml + patches: + - id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + config: + provider: deepseek-official + model: deepseek-v4-flash + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + persistenceCompression: none + workspaceContext: + maxBytes: 65536 + persona: | + You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + + Verify your work by running the code or tests. Keep answers brief and factual. + - insert: + - id: attachment-local + name: '@deepseek-ai/dsh-attachment-local' diff --git a/examples/acp-agent/image.cordis.snapshot.yml b/examples/acp-agent/image.cordis.snapshot.yml new file mode 100644 index 0000000000..f056f775d3 --- /dev/null +++ b/examples/acp-agent/image.cordis.snapshot.yml @@ -0,0 +1,41 @@ +# Keyless replay for the read-image success scenario. Include patches cannot +# target entries behind a nested include, so this restates the replay overlay +# directly over the base cordis.yml (the fs.cordis.snapshot.yml pattern) and +# re-pins the recorded flash model. The replay catalog declares image input on +# flash, so the strict read_image gate accepts the route and the tool result +# carries the durable image block; the live DeepSeek route cannot record this. +- id: base + name: '@deepseek-ai/cordis-plugin-include' + config: + path: ./cordis.yml + patches: + - id: llm-deepseek + name: '@deepseek-ai/dsh-llm-deepseek' + disabled: true + - id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + config: + provider: deepseek-official + model: deepseek-v4-flash + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + persistenceCompression: none + workspaceContext: + maxBytes: 65536 + persona: | + You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + + Verify your work by running the code or tests. Keep answers brief and factual. + - insert: + - id: attachment-local + name: '@deepseek-ai/dsh-attachment-local' + - id: llm-replay + name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek-official + name: DeepSeek + models: + - id: deepseek-v4-flash + inputModalities: [text, image] + - id: deepseek-v4-pro + inputModalities: [text] diff --git a/examples/acp-agent/image.cordis.yml b/examples/acp-agent/image.cordis.yml new file mode 100644 index 0000000000..a12cef1e85 --- /dev/null +++ b/examples/acp-agent/image.cordis.yml @@ -0,0 +1,27 @@ +# Image-scenario overlay: adds the durable attachment store the read_image tool +# commits through. The store resolves its root from $DSH_HOME, which the +# snapshot harness scopes per run, so the overlay itself carries no paths. The +# app config is restated to re-pin `deepseek-v4-flash` (base ships pro; the +# authored fixture and the pinned header class are flash), because a config +# patch replaces the whole app config. +- id: base + name: '@deepseek-ai/cordis-plugin-include' + config: + path: ./cordis.yml + patches: + - id: acp-agent + name: '@deepseek-ai/dsh-acp-demo' + config: + provider: deepseek-official + model: deepseek-v4-flash + persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' + persistenceCompression: none + workspaceContext: + maxBytes: 65536 + persona: | + You are a coding assistant powered by the {{model}} model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + + Verify your work by running the code or tests. Keep answers brief and factual. + - insert: + - id: attachment-local + name: '@deepseek-ai/dsh-attachment-local' diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 3b89ae8a35..4de0bbfcda 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -38,6 +38,8 @@ const WORKSPACE_CONTEXT_CONFIG = fileURLToPath(new URL('../workspace-context.cor const ADVANCED_CONFIG = fileURLToPath(new URL('../advanced.cordis.yml', import.meta.url)) const FS_CONFIG = fileURLToPath(new URL('../fs.cordis.yml', import.meta.url)) const SESSION_QUERY_CONFIG = fileURLToPath(new URL('../session-query.cordis.yml', import.meta.url)) +const IMAGE_CONFIG = fileURLToPath(new URL('../image.cordis.yml', import.meta.url)) +const IMAGE_TEXT_ROUTE_CONFIG = fileURLToPath(new URL('../image-text-route.cordis.yml', import.meta.url)) const PTY_CONFIG = fileURLToPath(new URL('../pty.cordis.yml', import.meta.url)) const DEPTH_TWO_CONFIG = fileURLToPath(new URL('../depth-two.cordis.yml', import.meta.url)) const CHILD_QUESTION_CONFIG = fileURLToPath(new URL('../child-question.cordis.yml', import.meta.url)) @@ -180,6 +182,30 @@ const SCENARIOS: Scenario[] = [ configPath: SESSION_QUERY_CONFIG, posixOnly: true, }, + // Authored keyless replays through the assembled app: the replay catalog + // declares flash image-capable (success) or text-only (refusal), and the + // real read_image tool executes against the workspace fixture and the real + // attachment store. Both boot the same composed header (the tool registers + // with the attachment store, independent of route), so they share one class. + { + name: 'read-image', + hasModelTurn: true, + recorded: false, + pinsHeader: true, + headerClass: 'image', + // The overlay adds no prompt section (read_image carries no guidance), so + // the composed system prompt is byte-identical to the default class; only + // the tool-schema sidecar is class-specific. + systemPromptSource: 'text-turn', + configPath: IMAGE_CONFIG, + }, + { + name: 'read-image-text-route', + hasModelTurn: true, + recorded: false, + headerClass: 'image', + configPath: IMAGE_TEXT_ROUTE_CONFIG, + }, { name: 'pty-tools', hasModelTurn: true, diff --git a/examples/acp-agent/tests/snapshots/read-image-text-route/input.json b/examples/acp-agent/tests/snapshots/read-image-text-route/input.json new file mode 100644 index 0000000000..551bfee00a --- /dev/null +++ b/examples/acp-agent/tests/snapshots/read-image-text-route/input.json @@ -0,0 +1,14 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "prompt", + "text": "Use read_image on red.png in the current directory. If the tool refuses because the current model is text-only, reply with exactly the single word UNAVAILABLE." + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/read-image-text-route/session.jsonl b/examples/acp-agent/tests/snapshots/read-image-text-route/session.jsonl new file mode 100644 index 0000000000..3e32a50a32 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/read-image-text-route/session.jsonl @@ -0,0 +1,26 @@ +{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783951000000,"cwd":"{{cwd}}","delegationDepth":0} +{"type":"agent/inbox/spliced","seq":0,"time":1783951000001,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use read_image on red.png in the current directory. If the tool refuses because the current model is text-only, reply with exactly the single word UNAVAILABLE."}],"source":{"kind":"user"},"role":"user","id":"0a0a0a0a-0000-4000-8000-000000000001"}]}} +{"type":"turn/start","seq":1,"time":1783951000002,"data":{"turn":1}} +{"type":"agent/inbox/spliced","seq":2,"time":1783951000002,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} +{"type":"step/start","seq":3,"time":1783951000003,"data":{"turn":1,"step":1}} +{"type":"user/message","seq":4,"time":1783951000003,"data":{"content":[{"type":"text","text":"Use read_image on red.png in the current directory. If the tool refuses because the current model is text-only, reply with exactly the single word UNAVAILABLE."}],"source":{"kind":"user"},"role":"user","id":"0a0a0a0a-0000-4000-8000-000000000001"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1786344284632,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"11a08f07-014a-408b-bfc5-634770ce7179"},"surfaceOp":"append"} +{"type":"session/title","seq":6,"time":1786344284632,"data":{"title":"Use read_image on red.png in","messageSeqs":[4],"source":{"kind":"fallback"}}} +{"type":"request/header","seq":7,"time":1786344284632,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/context","seq":8,"time":1786344284633,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} +{"type":"assistant/chunk","seq":9,"time":1783951000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":10,"time":1786344284637,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"read-image-refused","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}}}} +{"type":"assistant/chunk","seq":11,"time":1786344284637,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":12,"time":1786344284637,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":13,"time":1786344284638,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"read-image-refused","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"9676ac40-f7a8-4a7b-9326-a45fef18f11e"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"} +{"type":"tool/call","seq":14,"time":1786344284638,"data":{"turn":1,"step":1,"callId":"read-image-refused","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}} +{"type":"tool/result","seq":15,"time":1786344284643,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"read-image-refused"},"content":[{"type":"tool-result","toolCallId":"read-image-refused","content":[{"type":"text","text":"Error: cannot read \"red.png\" as an image: model \"deepseek-v4-flash\" does not declare image input; switch to an image-capable model to read images"}],"isError":true}],"role":"user","id":"ee31751e-df5a-458e-8497-8113cf6107ef"}},"sourceEventSeqs":[14],"surfaceOp":"append"} +{"type":"step/end","seq":16,"time":1786344284643,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":17,"time":1786344284648,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":18,"time":1783951000016,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":19,"time":1786344284652,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"UNAVAILABLE"}}}} +{"type":"assistant/chunk","seq":20,"time":1786344284652,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":21,"time":1786344284652,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":22,"time":1786344284652,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"UNAVAILABLE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"1c15b391-a95a-4113-9d47-2a1dfc991cf9"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21],"surfaceOp":"append"} +{"type":"step/end","seq":23,"time":1786344284653,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":24,"time":1786344284653,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/read-image-text-route/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/read-image-text-route/stdout.expected.jsonl new file mode 100644 index 0000000000..f93f99ce97 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/read-image-text-route/stdout.expected.jsonl @@ -0,0 +1,4 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"UNAVAILABLE"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/read-image-text-route/workspace/red.png b/examples/acp-agent/tests/snapshots/read-image-text-route/workspace/red.png new file mode 100644 index 0000000000..62a5f8f47f Binary files /dev/null and b/examples/acp-agent/tests/snapshots/read-image-text-route/workspace/red.png differ diff --git a/examples/acp-agent/tests/snapshots/read-image/input.json b/examples/acp-agent/tests/snapshots/read-image/input.json new file mode 100644 index 0000000000..603d2ad4ac --- /dev/null +++ b/examples/acp-agent/tests/snapshots/read-image/input.json @@ -0,0 +1,14 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "prompt", + "text": "Use read_image to look at red.png in the current directory, then reply with exactly the single word DONE." + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/read-image/session.jsonl b/examples/acp-agent/tests/snapshots/read-image/session.jsonl new file mode 100644 index 0000000000..6acde5a0ff --- /dev/null +++ b/examples/acp-agent/tests/snapshots/read-image/session.jsonl @@ -0,0 +1,26 @@ +{"type":"session","version":0,"id":"33333333-3333-4333-8333-333333333333","createdAt":1783951000000,"cwd":"{{cwd}}","delegationDepth":0} +{"type":"agent/inbox/spliced","seq":0,"time":1783951000001,"data":{"target":"next-turn","start":0,"inserted":[{"content":[{"type":"text","text":"Use read_image to look at red.png in the current directory, then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"0a0a0a0a-0000-4000-8000-000000000001"}]}} +{"type":"turn/start","seq":1,"time":1783951000002,"data":{"turn":1}} +{"type":"agent/inbox/spliced","seq":2,"time":1783951000002,"data":{"target":"next-turn","start":0,"removedCount":1,"inserted":[]}} +{"type":"step/start","seq":3,"time":1783951000003,"data":{"turn":1,"step":1}} +{"type":"user/message","seq":4,"time":1783951000003,"data":{"content":[{"type":"text","text":"Use read_image to look at red.png in the current directory, then reply with exactly the single word DONE."}],"source":{"kind":"user"},"role":"user","id":"0a0a0a0a-0000-4000-8000-000000000001"},"surfaceOp":"append"} +{"type":"user/message","seq":5,"time":1786344283033,"data":{"content":[{"type":"text","text":"Current runtime context. This snapshot supersedes earlier runtime-context snapshots.\n\nCurrent DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations.\n\nApproval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}],"source":{"kind":"plugin","plugin":"@deepseek-ai/dsh-system-prompt","form":"snapshot","sections":[{"name":"sandbox:policy","text":"Current DSH file policy: danger-full-access. The DSH file sandbox does not restrict file modifications by available operations."},{"name":"approval:policy","text":"Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`)."}]},"role":"user","id":"eecd1df6-153c-4a34-b198-42bfc9f9701e"},"surfaceOp":"append"} +{"type":"session/title","seq":6,"time":1786344283033,"data":{"title":"Use read_image to look at","messageSeqs":[4],"source":{"kind":"fallback"}}} +{"type":"request/header","seq":7,"time":1786344283034,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/context","seq":8,"time":1786344283034,"data":{"provider":"deepseek-official","model":"deepseek-v4-flash"}} +{"type":"assistant/chunk","seq":9,"time":1783951000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} +{"type":"assistant/chunk","seq":10,"time":1786344283039,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"read-image-call","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}}}} +{"type":"assistant/chunk","seq":11,"time":1786344283039,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":12,"time":1786344283039,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} +{"type":"assistant/message","seq":13,"time":1786344283039,"data":{"turn":1,"step":1,"message":{"role":"assistant","content":[{"type":"tool-call","id":"read-image-call","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"41e9fb55-6edb-419d-b76c-554daa5a1c5d"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[9,10,11,12],"surfaceOp":"append"} +{"type":"tool/call","seq":14,"time":1786344283039,"data":{"turn":1,"step":1,"callId":"read-image-call","name":"read_image","arguments":"{\"file_path\":\"red.png\"}"}} +{"type":"tool/result","seq":15,"time":1786344283069,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"read-image-call"},"content":[{"type":"tool-result","toolCallId":"read-image-call","content":[{"type":"text","text":"{{cwd}}/red.png\nimage\n\nimage/png image, 1x1 px, 69 bytes\n"},{"type":"image","attachment":{"attachmentId":"sha256:b1ff9c8ea3a780bad09b346c423d2d0e46815926879b18e841d928376a946640","mediaType":"image/png","bytes":69,"width":1,"height":1,"name":"red.png"}}],"isError":false}],"role":"user","id":"0b5779fc-523e-4275-9a32-8eb5e39f521e"}},"sourceEventSeqs":[14],"surfaceOp":"append"} +{"type":"step/end","seq":16,"time":1786344283069,"data":{"turn":1,"step":1}} +{"type":"step/start","seq":17,"time":1786344283075,"data":{"turn":1,"step":2}} +{"type":"assistant/chunk","seq":18,"time":1783951000016,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} +{"type":"assistant/chunk","seq":19,"time":1786344283078,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE"}}}} +{"type":"assistant/chunk","seq":20,"time":1786344283079,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} +{"type":"assistant/chunk","seq":21,"time":1786344283079,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":22,"time":1786344283079,"data":{"turn":1,"step":2,"message":{"role":"assistant","content":[{"type":"text","text":"DONE"}],"source":{"kind":"model","provider":"deepseek-official","model":"deepseek-v4-flash"},"id":"73a87a50-8e0b-42af-8c54-d9b6fbe375f1"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[18,19,20,21],"surfaceOp":"append"} +{"type":"step/end","seq":23,"time":1786344283079,"data":{"turn":1,"step":2}} +{"type":"turn/end","seq":24,"time":1786344283079,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/read-image/stdout.expected.jsonl b/examples/acp-agent/tests/snapshots/read-image/stdout.expected.jsonl new file mode 100644 index 0000000000..82ae8907ca --- /dev/null +++ b/examples/acp-agent/tests/snapshots/read-image/stdout.expected.jsonl @@ -0,0 +1,4 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}"}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"DONE"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/read-image/tool-schemas.expected.json b/examples/acp-agent/tests/snapshots/read-image/tool-schemas.expected.json new file mode 100644 index 0000000000..8da6396169 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/read-image/tool-schemas.expected.json @@ -0,0 +1,543 @@ +{ + "initial": [ + { + "name": "bash", + "description": "Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Current harness environment facts are exposed through managed `$DSH_*` variables; inspect them when needed. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; read its output with `task_output` and stop it with `task_kill`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.", + "parameters": { + "type": "object", + "properties": { + "command": { + "type": "string", + "description": "The bash command to execute." + }, + "description": { + "type": "string", + "description": "Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"." + }, + "timeoutMs": { + "type": "number", + "description": "Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry." + }, + "workdir": { + "type": "string", + "description": "Working directory for this command. Defaults to the session workspace; a relative path is resolved against it." + }, + "run_in_background": { + "type": "boolean", + "description": "Run in the background and return a task id immediately (collect with task_output, stop with task_kill). No timeout applies." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access." + } + }, + "required": [ + "command", + "description" + ] + } + }, + { + "name": "create_goal", + "description": "Create one persisted same-session completion goal when the current direct human request is a long-running objective that should continue across autonomous goal rounds. You may infer that intent without requiring the user to say \"create a goal\". Do not use this for trivial single-turn work. Execution rejects non-human and subagent authority.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The concrete completion objective inferred from the direct human request." + }, + "max_goal_rounds": { + "type": "number", + "description": "Optional positive safe-integer limit on automatic continuation rounds." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "edit", + "description": "Edit an existing UTF-8 text file by replacing literal text.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to edit, resolved by the filesystem backend." + }, + "old_string": { + "type": "string", + "description": "Literal text to replace. Must match exactly." + }, + "new_string": { + "type": "string", + "description": "Literal replacement text. Use an empty string to delete the match." + }, + "replace_all": { + "type": "boolean", + "description": "Replace all matches. Defaults to false; when false, old_string must appear exactly once." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access." + } + }, + "required": [ + "file_path", + "old_string", + "new_string" + ] + } + }, + { + "name": "get_goal", + "description": "Read the current same-session goal, including its exact id/revision, objective, phase, completed continuation rounds, round limit, blocker reason when present, and whether another continuation is armed. Call this before updating a goal.", + "parameters": { + "type": "object", + "properties": {} + } + }, + { + "name": "interrupt_agent", + "description": "Request cancellation of a background agent's current turn by its agent id. The target may be your direct child or a deeper agent created under you. Only the current turn stops: messages already queued for the agent stay parked until a later send_message, agents it started keep running, and the agent itself stays available for follow-ups. This call returns as soon as the stop request is accepted, so the target may keep running briefly; interrupting an agent that already finished is an accepted no-op.", + "parameters": { + "type": "object", + "properties": { + "agent_id": { + "type": "string", + "description": "The agent id of the running agent to interrupt." + } + }, + "required": [ + "agent_id" + ] + } + }, + { + "name": "list_agents", + "description": "List your continuable background subagents by durable id and label. Status comes from the live registry: running means the agent is working right now, idle means it is loaded but between turns (it may be waiting on agents it started), and complete means it exists only in storage — a direct child remains a `send_message` candidate in every status. The snapshot is not a delivery promise — `send_message` performs the authoritative check and may still fail. Children that could not be read are reported as diagnostics instead of being silently dropped. Scope `descendants` walks the whole tree below you in stable pre-order, annotating each entry with its durable direct-parent session id and depth. You may use `send_message` only for depth-1 entries; deeper entries are candidates for `interrupt_agent` only.", + "parameters": { + "type": "object", + "properties": { + "scope": { + "type": "string", + "description": "children (default) lists direct children only; descendants walks the complete tree below you.", + "enum": [ + "children", + "descendants" + ] + } + } + } + }, + { + "name": "ralph", + "description": "Run a foreground fresh-agent Ralph loop toward one immutable objective. Use only when the direct human explicitly asks for Ralph or fresh-agent iteration. Each round opens a new child with no parent conversation or prior child session; the shared workspace is long-term memory, and only a bounded structured report crosses rounds. The call returns when a worker reports completion or a concrete blocker, or at the round limit. Ordinary long-running same-session work belongs to goal tools.", + "parameters": { + "type": "object", + "properties": { + "objective": { + "type": "string", + "description": "The immutable completion objective for every fresh Ralph round." + }, + "maxRounds": { + "type": "number", + "description": "Optional positive safe-integer round cap, bounded by the deployment ceiling." + } + }, + "required": [ + "objective" + ] + } + }, + { + "name": "read", + "description": "Read a UTF-8 text file and return line-numbered content.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to read, resolved by the filesystem backend." + }, + "offset": { + "type": "number", + "description": "1-based first line to return. Defaults to 1." + }, + "limit": { + "type": "number", + "description": "Maximum number of lines to return. Defaults to 2000." + } + }, + "required": [ + "file_path" + ] + } + }, + { + "name": "read_image", + "description": "Read a PNG/JPEG/WebP/GIF file and return the image itself. Requires the current model to accept image input.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to the image file, resolved by the filesystem backend." + } + }, + "required": [ + "file_path" + ] + } + }, + { + "name": "send_message", + "description": "Send a message to a background subagent by its subagent id, continuing the same conversation. It becomes the subagent's next turn: if it is still working, the message waits until its current turn finishes, so it cannot redirect work already underway. This call returns no answer from the subagent — only confirmation that the message was delivered — so use it to give it more work. A failure means the message was NOT delivered.", + "parameters": { + "type": "object", + "properties": { + "subagent_id": { + "type": "string", + "description": "The subagent id returned when the background subagent was started." + }, + "message": { + "type": "string", + "description": "The message to deliver to the subagent." + } + }, + "required": [ + "subagent_id", + "message" + ] + } + }, + { + "name": "skill", + "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", + "parameters": { + "type": "object", + "properties": { + "name": { + "type": "string", + "description": "The exact skill name from the available skills list." + } + }, + "required": [ + "name" + ] + } + }, + { + "name": "subagent", + "description": "Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. Set `run_in_background: true` to start a background subagent that keeps its conversation: you receive only its subagent id, never its result, and it works on its own. Use this for work whose result you do not need returned by this call; `send_message` sends it more work.", + "parameters": { + "type": "object", + "properties": { + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs." + }, + "run_in_background": { + "type": "boolean", + "description": "Run as a background subagent that keeps its conversation and return only its subagent id. This call never returns its result; send it more work with send_message." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "subagent_fork", + "description": "Delegate a task to a subagent that inherits this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. Set `run_in_background: true` to start a background subagent that keeps its conversation: you receive only its subagent id, never its result, and it works on its own. Use this for work whose result you do not need returned by this call; `send_message` sends it more work.", + "parameters": { + "type": "object", + "properties": { + "description": { + "type": "string", + "description": "A short (3-5 word) description of the delegated task, for display." + }, + "prompt": { + "type": "string", + "description": "The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new." + }, + "run_in_background": { + "type": "boolean", + "description": "Run as a background subagent that keeps its conversation and return only its subagent id. This call never returns its result; send it more work with send_message." + } + }, + "required": [ + "description", + "prompt" + ] + } + }, + { + "name": "task_kill", + "description": "Request cancellation of a running background task by task id. Returns immediately; the task settles as killed once its work actually stops.", + "parameters": { + "type": "object", + "properties": { + "task_id": { + "type": "string", + "description": "Task id returned by the tool that started the background work." + }, + "reason": { + "type": "string", + "description": "Optional short reason, recorded in the log and forwarded to the task." + } + }, + "required": [ + "task_id" + ] + } + }, + { + "name": "task_list", + "description": "List your background tasks (running and finished) with their ids, kinds, and statuses.", + "parameters": { + "type": "object", + "properties": {} + } + }, + { + "name": "task_output", + "description": "Read a background task. Stream tasks return only output since the previous read; final-output tasks return their result after settlement. Every response ends with `[status: ...]`. Reads are non-blocking unless `wait: true`, which waits up to the configured cap.", + "parameters": { + "type": "object", + "properties": { + "task_id": { + "type": "string", + "description": "Task id returned by the tool that started the background work." + }, + "wait": { + "type": "boolean", + "description": "Block until the task reaches a terminal status or the timeout expires. A timed-out wait returns [status: running] and leaves the task alive." + }, + "timeout_ms": { + "type": "number", + "description": "Max wait in milliseconds (only meaningful with wait: true). Defaults to the configured wait timeout; capped by the configured maximum." + } + }, + "required": [ + "task_id" + ] + } + }, + { + "name": "todo_write", + "description": "Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Mark every todo being actively worked on `in_progress` — several at once when work genuinely runs in parallel (e.g. concurrent subagents or background commands), one for sequential work; while work remains, at least one task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).", + "parameters": { + "type": "object", + "properties": { + "todos": { + "type": "array", + "description": "The COMPLETE task list, replacing any previous list.", + "items": { + "type": "object", + "additionalProperties": false, + "properties": { + "content": { + "type": "string", + "description": "What the task is — a short imperative line." + }, + "status": { + "type": "string", + "description": "pending (not started) | in_progress (now) | completed (done).", + "enum": [ + "pending", + "in_progress", + "completed" + ] + } + }, + "required": [ + "content", + "status" + ] + } + } + }, + "required": [ + "todos" + ] + } + }, + { + "name": "update_goal", + "description": "Update the exact current goal revision. edit, pause, and resume require a direct top-level human request. During an automatic continuation of the current goal, complete and blocked are also allowed. blocked is rejected before the configured minimum round count; the model remains responsible for judging that the same condition persisted across those rounds and must explain it in blocked_reason.", + "parameters": { + "type": "object", + "properties": { + "goal_id": { + "type": "string", + "description": "Exact id returned by get_goal." + }, + "revision": { + "type": "number", + "description": "Exact positive revision returned by get_goal." + }, + "action": { + "type": "string", + "description": "edit | pause | resume | complete | blocked", + "enum": [ + "edit", + "pause", + "resume", + "complete", + "blocked" + ] + }, + "objective": { + "type": "string", + "description": "Replacement objective; valid only with action edit." + }, + "max_goal_rounds": { + "type": "number", + "description": "Replacement cap; valid only with action edit." + }, + "blocked_reason": { + "type": "string", + "description": "Concrete blocking condition; required only with action blocked." + } + }, + "required": [ + "goal_id", + "revision", + "action" + ] + } + }, + { + "name": "workflow", + "description": "Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, provider?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const/oneOf — no pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), and independent `provider`/`model` LLM target overrides (either may be provided alone). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.", + "parameters": { + "type": "object", + "properties": { + "script": { + "type": "string", + "description": "The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)." + }, + "meta": { + "type": "object", + "description": "The workflow identity block (plain JSON — never code).", + "additionalProperties": true, + "properties": { + "name": { + "type": "string", + "description": "Short kebab-case workflow name." + }, + "description": { + "type": "string", + "description": "One-line description of what the workflow does." + }, + "whenToUse": { + "type": "string", + "description": "Optional guidance on when this workflow applies." + }, + "phases": { + "type": "array", + "description": "Optional phase declarations matched by phase() calls.", + "items": { + "type": "object", + "additionalProperties": true, + "properties": { + "title": { + "type": "string", + "description": "The phase title phase() calls match by exact string." + }, + "detail": { + "type": "string", + "description": "Optional one-line description of the phase." + }, + "provider": { + "type": "string", + "description": "Optional provider override this phase is expected to use." + }, + "model": { + "type": "string", + "description": "Optional model override this phase is expected to use." + } + }, + "required": [ + "title" + ] + } + } + }, + "required": [ + "name", + "description" + ] + }, + "args": { + "type": "object", + "description": "Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}).", + "additionalProperties": true + } + }, + "required": [ + "script", + "meta" + ] + } + }, + { + "name": "write", + "description": "Create or fully replace a UTF-8 text file.", + "parameters": { + "type": "object", + "properties": { + "file_path": { + "type": "string", + "description": "Path to write, resolved by the filesystem backend." + }, + "content": { + "type": "string", + "description": "Full UTF-8 text content to write." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this file operation needs. Only valid as a one-shot retry of an operation the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact file operation needs the wider access." + } + }, + "required": [ + "file_path", + "content" + ] + } + } + ], + "changes": [] +} diff --git a/examples/acp-agent/tests/snapshots/read-image/workspace/red.png b/examples/acp-agent/tests/snapshots/read-image/workspace/red.png new file mode 100644 index 0000000000..62a5f8f47f Binary files /dev/null and b/examples/acp-agent/tests/snapshots/read-image/workspace/red.png differ diff --git a/examples/headless-agent/README.i18n.yaml b/examples/headless-agent/README.i18n.yaml index 0871ba2c15..e965ffee3a 100644 --- a/examples/headless-agent/README.i18n.yaml +++ b/examples/headless-agent/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write examples/headless-agent/README.md -README.md: 08b36e9c8e558db3b30175b20bd6e0af160ccef5 -README.zh.md: 40d11ebeeb1631af1421b3c013a5e548fd3fd488 +README.md: 2f854924d4bfd2bf66b3d6f47433136098d7b762 +README.zh.md: 4128645da8a0f8a84b17d819fc614051b68f2a11 diff --git a/examples/headless-agent/README.md b/examples/headless-agent/README.md index 08b36e9c8e..2f854924d4 100644 --- a/examples/headless-agent/README.md +++ b/examples/headless-agent/README.md @@ -10,10 +10,10 @@ This directory owns the replay and real-model test composition for a headless co # repo root .env (gitignored) or exported env: # DEEPSEEK_API_KEY=sk-… # DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API -pnpm run dsh --profile headless "fix the failing test in this workspace" +pnpm dsh --profile headless "fix the failing test in this workspace" ``` -The product command is [`dsh --profile headless`](../../apps/cli/README.md): it accepts one nonblank task, creates and persists a fresh session, prints the final assistant text, and exits. The root `demo:headless` script is only an alias of that command. +The product command is [`dsh --profile headless`](../../apps/cli/README.md): it accepts one nonblank task, creates and persists a fresh session, prints the final assistant text, and exits. Snapshot suites run this directory's configuration through [`tests/fixtures/headless-driver.ts`](tests/fixtures/headless-driver.ts), an unexported test-only process that emits canonical session events as JSONL before its result record. That stream is test infrastructure, not a supported CLI output format. Child sessions surface only through parent tool events and results. diff --git a/examples/headless-agent/README.zh.md b/examples/headless-agent/README.zh.md index 40d11ebeeb..4128645da8 100644 --- a/examples/headless-agent/README.zh.md +++ b/examples/headless-agent/README.zh.md @@ -10,10 +10,10 @@ # repo root .env (gitignored) or exported env: # DEEPSEEK_API_KEY=sk-… # DEEPSEEK_BASE_URL=https://… # optional; defaults to the public API -pnpm run dsh --profile headless "fix the failing test in this workspace" +pnpm dsh --profile headless "fix the failing test in this workspace" ``` -产品命令是 [`dsh --profile headless`](../../apps/cli/README.md)：它接受一项非空任务，创建并持久化新会话，打印最终 assistant 文本，然后退出。根目录的 `demo:headless` 脚本只是该命令的别名。 +产品命令是 [`dsh --profile headless`](../../apps/cli/README.md)：它接受一项非空任务，创建并持久化新会话，打印最终 assistant 文本，然后退出。 快照套件通过 [`tests/fixtures/headless-driver.ts`](tests/fixtures/headless-driver.ts) 运行本目录的配置。这个未导出且仅供测试使用的进程会在结果记录之前，以 JSONL 发出规范会话事件。该事件流属于测试基础设施，不是受支持的 CLI（命令行界面）输出格式。子会话只通过父会话的工具事件和结果对外显示。 diff --git a/examples/package.json b/examples/package.json index 64b1ffdf3d..29818133ef 100644 --- a/examples/package.json +++ b/examples/package.json @@ -14,6 +14,7 @@ "@deepseek-ai/dsh-agent-loop": "workspace:*", "@deepseek-ai/dsh-agent-spine-demo": "workspace:*", "@deepseek-ai/dsh-app-boot": "workspace:*", + "@deepseek-ai/dsh-attachment-local": "workspace:*", "@deepseek-ai/dsh-bash": "workspace:*", "@deepseek-ai/dsh-bash-env": "workspace:*", "@deepseek-ai/dsh-bash-local": "workspace:*", @@ -27,8 +28,8 @@ "@deepseek-ai/dsh-compact-tool-result-prune": "workspace:*", "@deepseek-ai/dsh-credentials-local": "workspace:*", "@deepseek-ai/dsh-e2b": "workspace:*", - "@deepseek-ai/dsh-fs-local": "workspace:*", "@deepseek-ai/dsh-fs-e2b": "workspace:*", + "@deepseek-ai/dsh-fs-local": "workspace:*", "@deepseek-ai/dsh-fs-policy": "workspace:*", "@deepseek-ai/dsh-fs-sandbox": "workspace:^", "@deepseek-ai/dsh-goal": "workspace:*", @@ -76,8 +77,8 @@ "@deepseek-ai/dsh-subagent-dsh-sdk": "workspace:*", "@deepseek-ai/dsh-subagent-fork": "workspace:*", "@deepseek-ai/dsh-subagent-spawn": "workspace:*", - "@deepseek-ai/dsh-subprocess-local": "workspace:*", "@deepseek-ai/dsh-subprocess-e2b": "workspace:*", + "@deepseek-ai/dsh-subprocess-local": "workspace:*", "@deepseek-ai/dsh-system-prompt": "workspace:*", "@deepseek-ai/dsh-tasks-local": "workspace:*", "@deepseek-ai/dsh-time-context": "workspace:*", diff --git a/lefthook.yml b/lefthook.yml index 7ed1fcb886..1c2a693c88 100644 --- a/lefthook.yml +++ b/lefthook.yml @@ -10,6 +10,10 @@ pre-commit: - '.agents/notes/archived/**' run: node_modules/.bin/tsx scripts/verify-translation-pairing.ts --cached {staged_files} + - name: archived agent notes + glob: '.agents/notes/archived/**' + run: node_modules/.bin/tsx scripts/verify-archived-agent-notes.ts + - name: lint (staged) glob: '*.{ts,tsx,mts,cts,mjs}' exclude: @@ -41,6 +45,10 @@ pre-merge-commit: - '.agents/notes/archived/**' run: node_modules/.bin/tsx scripts/verify-translation-pairing.ts --cached {staged_files} + - name: archived agent notes + glob: '.agents/notes/archived/**' + run: node_modules/.bin/tsx scripts/verify-archived-agent-notes.ts + pre-push: jobs: - name: typecheck diff --git a/package.json b/package.json index d99acadf7a..2e2c798faf 100644 --- a/package.json +++ b/package.json @@ -127,12 +127,10 @@ "release:pack": "tsx scripts/release/pack.ts", "release:verify-packed-install": "tsx scripts/release/verify-packed-install.ts", "release:publish": "tsx scripts/release/publish.ts", - "dsh": "node --import tsx/esm apps/cli/src/bin.ts", - "demo:headless": "node --import tsx/esm apps/cli/src/bin.ts --profile headless", + "dsh": "pnpm run build && node --import tsx/esm apps/cli/src/bin.ts", "demo:code-mode": "node scripts/demo-code-mode.mjs", "demo:cordis": "node scripts/demo-cordis.mjs", "demo:acp": "node --import tsx packages/examples/acp-demo/src/bin.ts --config examples/acp-agent/cordis.yml", - "demo:web": "npm run build && node --import tsx/esm apps/cli/src/bin.ts web", "mock:llm": "node --import tsx packages/support/llm-mock-server/src/bin.ts", "dev:web": "tsx scripts/dev-web.ts --poll", "postinstall": "node scripts/install-lefthook.mjs" diff --git a/packages/boot/app-boot/README.i18n.yaml b/packages/boot/app-boot/README.i18n.yaml index d1f9a72df5..efd6a9c844 100644 --- a/packages/boot/app-boot/README.i18n.yaml +++ b/packages/boot/app-boot/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/boot/app-boot/README.md -README.md: 1d56b2b6d22c08574f8e361955bee1dbe2aca601 -README.zh.md: 5429a1322d0311f03c7c43946753a290e28cd936 +README.md: 9639f1c0a2ffe91fd509a2ffdf04be5f0895b700 +README.zh.md: e8bf0374aad2be2311b6e72e91e41f02f403b48a diff --git a/packages/boot/app-boot/README.md b/packages/boot/app-boot/README.md index 1d56b2b6d2..9639f1c0a2 100644 --- a/packages/boot/app-boot/README.md +++ b/packages/boot/app-boot/README.md @@ -29,7 +29,7 @@ The Loader mounts entries concurrently, so a surface can already own the termina `cordis:group` is registered beside `cordis:include` so a composition can give one `isolate` realm to a provider and its consumers together. Both load through the ambient module pipeline rather than the included tree's own specifier resolution, which is what lets a composition outside this workspace — an agent preset under the Harness home — use a group row at all. -Bare plugin specifiers in a config (`@deepseek-ai/dsh-*`, npm packages) resolve through the Cordis Loader's internal module loader. They resolve from the config directory by default; a closed runtime passes `bareModuleBaseUrl` to `boot` or `mountRootInclude` so its installed package tree remains authoritative even when the config lives inside another Node project. Relative specifiers always resolve against the config directory. Repository bins install Loader's optional `node-addon-require-builtin` peer; external callers must supply it or install plugins where plain Node import resolution can find them. The built `dsh-app-boot` artifact embeds the statically mounted Include implementation while leaving Loader external, so the include tree and host bind to one Loader peer. The `dsh` source launcher additionally maps manifest-declared workspace packages to their TypeScript source; its configuration gate requires every shipped raw/Web bare plugin to appear in the resolver manifest's `dependencies`. +Bare plugin specifiers in a config (`@deepseek-ai/dsh-*`, npm packages) resolve through the Cordis Loader's internal module loader. They resolve from the config directory by default; a closed runtime passes `bareModuleBaseUrl` to `boot` or `mountRootInclude` so its installed package tree remains authoritative even when the config lives inside another Node project. Relative specifiers always resolve against the config directory. Repository bins install Loader's optional `node-addon-require-builtin` peer; external callers must supply it or install plugins where plain Node import resolution can find them. The built `dsh-app-boot` artifact embeds the statically mounted Include implementation while leaving Loader external, so the include tree and host bind to one Loader peer. The `pnpm dsh` source path additionally maps manifest-declared workspace packages to their TypeScript source; its configuration gate requires every shipped raw/Web bare plugin to appear in the resolver manifest's `dependencies`. This package carries no loader hooks and no dev-mode surface. The [`dsh` app](../../../apps/cli/README.md) owns its Node source-launch hook and consumes these helpers for the boot sequence; built consumers continue to use plain Node package resolution. diff --git a/packages/boot/app-boot/README.zh.md b/packages/boot/app-boot/README.zh.md index 5429a1322d..e8bf0374aa 100644 --- a/packages/boot/app-boot/README.zh.md +++ b/packages/boot/app-boot/README.zh.md @@ -29,7 +29,7 @@ Loader 并发挂载各个条目，因此当其他环节失败时，某个界面 `cordis:group` 与 `cordis:include` 一并注册，使一份组装能把一个提供方与它的消费方放进同一个 `isolate` realm。两者都通过宿主的模块管线加载，而非被包含树自身的说明符解析，这正是让本工作区之外的组装——放在 Harness home 下的 agent preset——能够使用 group 行的原因。 -配置中的裸插件 specifier（`@deepseek-ai/dsh-*`、npm 包）通过 Cordis Loader 的内部模块 loader 解析。默认情况下，它们从配置目录解析；封闭运行时会向 `boot` 或 `mountRootInclude` 传入 `bareModuleBaseUrl`，使已安装包树保持权威，即使配置位于另一个 Node 项目中也不受遮蔽。相对 specifier 始终以配置目录为基准解析。仓库 bin 会安装 Loader 的可选 peer `node-addon-require-builtin`；外部调用方必须提供该组件，或者把插件安装到普通 Node import 解析可以找到的位置。构建后的 `dsh-app-boot` 产物内嵌静态挂载的 Include 实现，但仍将 Loader 保持为外部依赖，因此 include 树与宿主会绑定到同一个 Loader peer。`dsh` 源码启动器还会将 manifest（元数据清单）声明的 workspace 包映射到其 TypeScript 源码；其配置门禁要求每个随附的原始／Web 裸插件都出现在解析所用 manifest 的 `dependencies` 中。 +配置中的裸插件 specifier（`@deepseek-ai/dsh-*`、npm 包）通过 Cordis Loader 的内部模块 loader 解析。默认情况下，它们从配置目录解析；封闭运行时会向 `boot` 或 `mountRootInclude` 传入 `bareModuleBaseUrl`，使已安装包树保持权威，即使配置位于另一个 Node 项目中也不受遮蔽。相对 specifier 始终以配置目录为基准解析。仓库 bin 会安装 Loader 的可选 peer `node-addon-require-builtin`；外部调用方必须提供该组件，或者把插件安装到普通 Node import 解析可以找到的位置。构建后的 `dsh-app-boot` 产物内嵌静态挂载的 Include 实现，但仍将 Loader 保持为外部依赖，因此 include 树与宿主会绑定到同一个 Loader peer。`pnpm dsh` 源码路径还会将 manifest（元数据清单）声明的 workspace 包映射到其 TypeScript 源码；其配置门禁要求每个随附的原始／Web 裸插件都出现在解析所用 manifest 的 `dependencies` 中。 此包不包含 loader 钩子，也不提供开发模式接口。[`dsh` 应用](../../../apps/cli/README.md) 持有自己的 Node 源码启动钩子，并在启动序列中使用这些 helper；构建后的消费方仍使用普通 Node 包解析。 diff --git a/packages/bundle/web-app/cordis.patch.yml b/packages/bundle/web-app/cordis.patch.yml index fb41923d71..1c06b23157 100644 --- a/packages/bundle/web-app/cordis.patch.yml +++ b/packages/bundle/web-app/cordis.patch.yml @@ -202,6 +202,10 @@ - id: ui-subagent name: '@deepseek-ai/dsh-client-ui-subagent' + # Background tasks: the session-header list over the tasksBySession mirror. + - id: ui-task + name: '@deepseek-ai/dsh-client-ui-task' + # Goal surface: GoalBar in the input dock over the goal session projection. - id: ui-goal name: '@deepseek-ai/dsh-client-ui-goal' diff --git a/packages/bundle/web-app/package.json b/packages/bundle/web-app/package.json index 181bb269c4..3dcfc8ee6a 100644 --- a/packages/bundle/web-app/package.json +++ b/packages/bundle/web-app/package.json @@ -69,6 +69,7 @@ "@deepseek-ai/dsh-client-ui-skill": "workspace:^", "@deepseek-ai/dsh-client-ui-slash": "workspace:^", "@deepseek-ai/dsh-client-ui-subagent": "workspace:^", + "@deepseek-ai/dsh-client-ui-task": "workspace:^", "@deepseek-ai/dsh-client-ui-theme": "workspace:^", "@deepseek-ai/dsh-client-ui-tool": "workspace:^", "@deepseek-ai/dsh-client-ui-trajectory": "workspace:^", diff --git a/packages/client/README.i18n.yaml b/packages/client/README.i18n.yaml index 816f8737e7..c1f21425d6 100644 --- a/packages/client/README.i18n.yaml +++ b/packages/client/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/README.md -README.md: 567e10f74ae9d017abef1d876401a958eb80fcfd -README.zh.md: ad6a9fb199c4118b864b80a466ddef40676b7169 +README.md: bbc32fb3944dcb3b7aa48ef1f8e24e5c93ff7a67 +README.zh.md: 5bfbd1ce6b41a44d3ef421ea59ecc29e1c329b3c diff --git a/packages/client/README.md b/packages/client/README.md index 567e10f74a..bbc32fb394 100644 --- a/packages/client/README.md +++ b/packages/client/README.md @@ -29,6 +29,7 @@ The browser side of the dsh web GUI: shell boot, browser-host communication, sha | [`ui-slash/`](ui-slash/README.md) | Coordinates inline command and reference suggestions. | | [`ui-skill/`](ui-skill/README.md) | Adds skill references to inline suggestions. | | [`ui-subagent/`](ui-subagent/README.md) | Provides subagent navigation, child transcript states, and inline references. | +| [`ui-task/`](ui-task/README.md) | Lists this session's background tasks in the conversation header. | | [`ui-model/`](ui-model/README.md) | Provides model selection in conversation surfaces. | | [`ui-permission/`](ui-permission/README.md) | Configures default permissions and switches the current session's access. | | [`ui-plan/`](ui-plan/README.md) | Presents active plan-mode status and its exit control. | diff --git a/packages/client/README.zh.md b/packages/client/README.zh.md index ad6a9fb199..5bfbd1ce6b 100644 --- a/packages/client/README.zh.md +++ b/packages/client/README.zh.md @@ -29,6 +29,7 @@ dsh web GUI 的浏览器侧：shell 启动、浏览器与宿主通信、共享 U | [`ui-slash/`](ui-slash/README.md) | 协调内联命令和引用建议。 | | [`ui-skill/`](ui-skill/README.md) | 向内联建议添加 skill（技能）引用。 | | [`ui-subagent/`](ui-subagent/README.md) | 提供 subagent 导航、子会话记录状态和内联引用。 | +| [`ui-task/`](ui-task/README.md) | 在会话标题栏列出当前会话的后台任务。 | | [`ui-model/`](ui-model/README.md) | 在会话界面中提供模型选择。 | | [`ui-permission/`](ui-permission/README.md) | 配置默认权限并切换当前会话的访问模式。 | | [`ui-plan/`](ui-plan/README.md) | 展示生效中的 plan mode 状态及其退出控件。 | diff --git a/packages/client/connection/src/client/api.ts b/packages/client/connection/src/client/api.ts index a92db49899..980a2f02a8 100644 --- a/packages/client/connection/src/client/api.ts +++ b/packages/client/connection/src/client/api.ts @@ -17,6 +17,7 @@ export type { SettingsApi, SettingsNamespaceView, SettingsPathOpView, SettingsSecretView, CredentialsApi, CredentialView, ConfigurableProviderView, DiscoveredModelView, LlmApi, SubagentsApi, SubagentAddress, SubagentCatalog, SubagentListEntry, SubagentPromptReceipt, + TaskView, } from '@deepseek-ai/dsh-host-apiproxy/api' export type { ToolCallView, ToolResultView } from '@deepseek-ai/dsh-tools/presentation' export type { diff --git a/packages/client/connection/src/client/index.ts b/packages/client/connection/src/client/index.ts index 99f49ff13a..1a89d0649c 100644 --- a/packages/client/connection/src/client/index.ts +++ b/packages/client/connection/src/client/index.ts @@ -22,6 +22,7 @@ export type { ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning, MessageId, ModelReasoningEffort, ModelSelection, QueueAction, QueuedInboxItem, SessionModels, SubagentsApi, SubagentAddress, SubagentCatalog, SubagentListEntry, SubagentPromptReceipt, + TaskView, RpcRequest, RpcResponse, RpcResult, RpcError, RpcErrorCode, ClientRequest, ServerResponse, ServerRequest, ClientResponse, RpcMessage, RpcReceipt, HostDescription, IApiClient, SessionId, SessionEvent, ContentBlock, StreamChunk, diff --git a/packages/client/locale/tests/language-row.spec.tsx b/packages/client/locale/tests/language-row.spec.tsx index 6addc8c69c..e04fa9c311 100644 --- a/packages/client/locale/tests/language-row.spec.tsx +++ b/packages/client/locale/tests/language-row.spec.tsx @@ -16,7 +16,7 @@ const OPTIONS = [{ id: 'zh', label: '中文' }, { id: 'en', label: 'English' }] /** Empty global standard-kit hooks (the row reads neither). */ function emptySessions() { const store = createSnapshotStore( - { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }) + { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }) return bindSnapshotSelector(store) } function emptyWorkspaces() { diff --git a/packages/client/runtime/README.i18n.yaml b/packages/client/runtime/README.i18n.yaml index 9743f813da..3d3c29e757 100644 --- a/packages/client/runtime/README.i18n.yaml +++ b/packages/client/runtime/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/client/runtime/README.md -README.md: d84cd793c34242759ad04edf0debb91558ec3dfc -README.zh.md: e7a74c454f24fcec5e797427c21222b1dc258b44 +README.md: 7c835deb58db149710495f97a2553c3de58d99da +README.zh.md: edf4473bec7df2253c032c3da86da878cdeade09 diff --git a/packages/client/runtime/README.md b/packages/client/runtime/README.md index d84cd793c3..7c835deb58 100644 --- a/packages/client/runtime/README.md +++ b/packages/client/runtime/README.md @@ -25,6 +25,8 @@ SlotsService gives the renderer separate bare observables for `useSessions` and `indexSubagentDescendants()` derives per-parent total and running descendant counts from the retained list mirror. It follows only uninterrupted `origin: 'subagent'` ancestry, so an ordinary fork starts a separate ownership subtree; cycles stop without throwing, and a missing parent remains a harmless key until its summary arrives. +`SessionListState.tasksBySession` mirrors the Host's `session/tasks` frames last-wins, keyed by session and needing no Session instance. An emptied set is stored as an absent key, so absence and `[]` are one representation and consumers never test a sentinel. Two clears keep it from outliving its truth: `session/subscribed` drops the session's mirror, because a fresh generation sends a baseline only for a non-empty set and a retained list would survive as a phantom, and `host/session-removed` drops it again, because owner disposal removed the records on the mux stream while the removal frame rides the host stream, leaving the two with no relative order. + `SessionsService.search(query, signal)` is a stateless one-shot action over the `session.search` RPC. It returns ranked session/snippet pairs without putting query, loading, or error state into the shared Session list, so each UI owner controls debounce, cancellation, stale-response suppression, and fallback presentation. `searchResultLimit` re-exposes `SESSION_SEARCH_RESULT_LIMIT` — the bound the response schema itself enforces — as injected presentation data, so client plugins do not duplicate it. It is a protocol constant rather than per-connection state, so the connection handle does not carry it. ## New Session and the blank mirror diff --git a/packages/client/runtime/README.zh.md b/packages/client/runtime/README.zh.md index e7a74c454f..edf4473bec 100644 --- a/packages/client/runtime/README.zh.md +++ b/packages/client/runtime/README.zh.md @@ -25,6 +25,8 @@ SlotsService 分别为 renderer 提供 `useSessions` 与 `useWorkspaces` 的裸 `indexSubagentDescendants()` 从保留的列表镜像中派生每个 parent 的后代总数与运行中后代数。它只沿不间断的 `origin: 'subagent'` 祖先链追踪，因此普通 fork 会开启独立的归属子树；遇到环时，追踪会停止但不会抛出异常，缺失的 parent 则会保留为无害的键，直至其摘要到达。 +`SessionListState.tasksBySession` 按 last-wins 镜像宿主的 `session/tasks` 帧，以会话为键，不需要 Session 实例。被清空的集合存为缺失的键，因此「缺失」与 `[]` 是同一种表示，消费方永远不必检测哨兵值。两处清理让它不至于比它所反映的真相活得更久：`session/subscribed` 丢弃该会话的镜像，因为新一代只为非空集合发送 baseline，被留下的列表会变成幽灵；`host/session-removed` 再丢一次，因为 owner 销毁是在 mux 流上移除记录的，而移除帧走 host 流，两者没有相对顺序。 + `SessionsService.search(query, signal)` 是基于 `session.search` RPC 的无状态单次操作。它返回经过排序的会话／snippet 对，但不会将查询条件、加载状态或错误状态写入共享 Session 列表，因此每个 UI 所有者都自行负责防抖、取消、抑制陈旧响应和回退呈现。`searchResultLimit` 将 `SESSION_SEARCH_RESULT_LIMIT`——即响应 schema 自身强制执行的上限——作为注入的呈现数据重新公开，使客户端插件无需复制该值。它是协议常量而非逐连接状态，因此连接 handle 不携带它。 ## New Session 与 blank 镜像 diff --git a/packages/client/runtime/src/client/index.ts b/packages/client/runtime/src/client/index.ts index 49f5491764..d27cc97eda 100644 --- a/packages/client/runtime/src/client/index.ts +++ b/packages/client/runtime/src/client/index.ts @@ -53,7 +53,7 @@ export type { SessionBinding, SessionListState, SessionProvideContribution, SessionProvideDescriptor, SessionSummary, } from './sessions/service.ts' export type { SessionListPhase, SessionSearchResultItem, SubagentCatalogSnapshot } from './sessions/manager.ts' -export type { SubagentAddress } from '@deepseek-ai/dsh-client-connection/client' +export type { SubagentAddress, TaskView } from '@deepseek-ai/dsh-client-connection/client' export type { WorkspaceListPhase } from './workspaces/manager.ts' export type { WorkspaceListState } from './workspaces/service.ts' export type { diff --git a/packages/client/runtime/src/client/sessions/manager.ts b/packages/client/runtime/src/client/sessions/manager.ts index fd601090bf..741b3d36b2 100644 --- a/packages/client/runtime/src/client/sessions/manager.ts +++ b/packages/client/runtime/src/client/sessions/manager.ts @@ -4,7 +4,7 @@ import type { IApiClient, HostFrame, MuxFrame, RpcError, RpcRequest, RpcResult, SessionId, - SessionSummary, SubagentAddress, SubagentCatalog, WorkspaceId, + SessionSummary, SubagentAddress, SubagentCatalog, TaskView, WorkspaceId, } from '@deepseek-ai/dsh-client-connection/client' // Value import from the inline-safe wire layer (not the connection plugin): // plugin-to-plugin value imports are a bundle purity error. @@ -48,6 +48,8 @@ export interface SessionListSnapshot { phase: SessionListPhase error: RpcError | null subagentsByParent: Readonly> + /** Background tasks per session; an absent key is an empty set. */ + tasksBySession: Readonly> currentAddress: SubagentAddress | undefined } @@ -138,6 +140,11 @@ export class SessionManager { private readonly catalogStale = new Set() private readonly openCatalogs = new Set() private readonly catalogDebounce = new Map>() + /** + * Background tasks per session, last-wins from `session/tasks`. An empty set + * is stored as an absent key, so absence and `[]` are one representation. + */ + private readonly tasksBySession = new Map() private selected: SessionId | undefined @@ -682,10 +689,23 @@ export class SessionManager { this.notifier.markDirty() return } + if (frame.type === 'session/tasks') { + // Whole-set snapshot, so last-wins with no reconciliation. The Host omits + // the baseline for an empty set, which is the same fact an emptying change + // reports as `[]` — both land as an absent key. + if (frame.tasks.length === 0) this.tasksBySession.delete(frame.sessionId) + else this.tasksBySession.set(frame.sessionId, frame.tasks) + this.notifier.markDirty() + return + } if (frame.type === 'session/subscribed') { // Rows past the host's durable baseline rode state a restart lost; drop // them so last-wins cannot pin a phantom value over recomputed truth. this.projectionStores.get(frame.sessionId)?.truncate(frame.lastSeq) + // Same re-baseline reasoning as the queue below: this generation sends a + // task baseline only when the set is non-empty, so a mirror kept from the + // previous generation would survive as a phantom list. + this.tasksBySession.delete(frame.sessionId) this.notifier.markDirty() // New mux-generation baseline: discard the previous queue snapshot. // The host omits session/queue when the live queue is empty, so retaining @@ -804,6 +824,11 @@ export class SessionManager { } this.pendingBuffers.delete(frame.sessionId) // a removed session's buffered frames must not replay on a future instantiation this.pendingInteractions.delete(frame.sessionId) // a removed session cannot wait on anyone + // Owner disposal already dropped these registry-side, but that lands on + // the mux stream while this frame rides the host stream, so the two have + // no relative order. Clearing here makes a detached Activation's rows + // disappear whichever arrives first. + this.tasksBySession.delete(frame.sessionId) if (!durableSubagent) this.projectionStores.delete(frame.sessionId) // A pull already in flight was requested before this removal and can // carry the pre-removal parentAvailable:true, which would resurrect @@ -1040,6 +1065,7 @@ export class SessionManager { phase: this.listPhase, error: this.listError, subagentsByParent: Object.fromEntries(this.catalogs), + tasksBySession: Object.fromEntries(this.tasksBySession), currentAddress: current === undefined ? undefined : this.addresses.get(current), } } diff --git a/packages/client/runtime/src/client/sessions/service.ts b/packages/client/runtime/src/client/sessions/service.ts index 0f0f68827d..2b7267402e 100644 --- a/packages/client/runtime/src/client/sessions/service.ts +++ b/packages/client/runtime/src/client/sessions/service.ts @@ -16,7 +16,7 @@ */ import type { Context, Fiber } from '@deepseek-ai/cordis' import type { - IApiClient, RpcError, RpcResult, SessionId, SubagentAddress, WorkspaceId, + IApiClient, RpcError, RpcResult, SessionId, SubagentAddress, TaskView, WorkspaceId, } from '@deepseek-ai/dsh-client-connection/client' // Value import from the inline-safe wire layer (not the connection plugin): // plugin-to-plugin value imports are a bundle purity error. @@ -86,6 +86,12 @@ export interface SessionListState { phase: SessionListPhase /** Direct durable catalogs keyed by their selected parent address. */ subagentsByParent: Readonly> + /** + * Background tasks each session can see, mirrored last-wins from + * `session/tasks`. A missing key is an empty set — the Host sends no baseline + * for a session without tasks — so consumers read absence, never a sentinel. + */ + tasksBySession: Readonly> /** Current session's catalog-derived address, absent on ordinary navigation. */ currentAddress: SubagentAddress | undefined } @@ -291,7 +297,7 @@ export class SessionsService implements ISessions { ) this.list = createSnapshotStore({ ids: [], byId: {}, current: undefined, phase: 'pending', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) // The manager owns wire truth; the store is its projection. Manager // notifications are already microtask-batched. @@ -649,7 +655,7 @@ export class SessionsService implements ISessions { /** Project the manager's list snapshot into the store (title derivation is display-only). */ private projectList(): void { const { - items, current, phase, subagentsByParent, currentAddress, + items, current, phase, subagentsByParent, tasksBySession, currentAddress, } = this.manager.getListSnapshot() const ids: SessionId[] = [] const byId: Record = {} @@ -719,7 +725,7 @@ export class SessionsService implements ISessions { ...(currentAddress === undefined ? {} : { subagentAddress: currentAddress }), }) } - this.list.set({ ids, byId, current, phase, subagentsByParent, currentAddress }) + this.list.set({ ids, byId, current, phase, subagentsByParent, tasksBySession, currentAddress }) this.pruneScopes() } diff --git a/packages/client/runtime/tests/manager.spec.ts b/packages/client/runtime/tests/manager.spec.ts index c69465df45..7eba55fd64 100644 --- a/packages/client/runtime/tests/manager.spec.ts +++ b/packages/client/runtime/tests/manager.spec.ts @@ -1110,3 +1110,60 @@ describe('completed reminder', () => { expect(entry(manager, S2)?.completed).toBe(true) }) }) + +describe('background-task mirror', () => { + const view = (over: Partial<{ id: string; status: string; label: string }> = {}) => ({ + id: 'bash-1', kind: 'bash', label: 'pnpm run build', status: 'running', startedAt: 5, ...over, + }) + const tasksFrame = (sessionId: SessionId, tasks: unknown[]) => + ({ rpcId: 't' as never, payload: { type: 'session/tasks', sessionId, tasks } as never }) + + it('mirrors the whole set last-wins, keyed per session, with no Session instance needed', () => { + const manager = new SessionManager(new FakeApiClient()) + manager.handleMuxEnvelope(tasksFrame(S1, [view()])) + manager.handleMuxEnvelope(tasksFrame(S2, [view({ id: 'pwsh-1', label: 'other' })])) + const first = manager.getListSnapshot().tasksBySession + expect(first[S1]).toEqual([view()]) + expect(first[S2]?.[0]?.label).toBe('other') + + // Last-wins: the newer whole set replaces, it does not merge. + manager.handleMuxEnvelope(tasksFrame(S1, [view({ status: 'completed' })])) + expect(manager.getListSnapshot().tasksBySession[S1]).toEqual([view({ status: 'completed' })]) + }) + + it('stores an emptied set as an absent key so absence and [] read alike', () => { + const manager = new SessionManager(new FakeApiClient()) + manager.handleMuxEnvelope(tasksFrame(S1, [view()])) + expect(S1 in manager.getListSnapshot().tasksBySession).toBe(true) + manager.handleMuxEnvelope(tasksFrame(S1, [])) + expect(S1 in manager.getListSnapshot().tasksBySession).toBe(false) + }) + + it('clears the mirror on re-subscribe, because a task-free generation sends no baseline', () => { + const manager = new SessionManager(new FakeApiClient()) + manager.handleMuxEnvelope(tasksFrame(S1, [view()])) + manager.handleMuxEnvelope({ + rpcId: 's' as never, + payload: { type: 'session/subscribed', sessionId: S1, lastSeq: 3 }, + }) + expect(S1 in manager.getListSnapshot().tasksBySession).toBe(false) + }) + + it('drops the rows when the session is removed, whichever stream lands first', () => { + const manager = new SessionManager(new FakeApiClient()) + manager.handleHostEnvelope({ rpcId: 'a' as never, payload: { type: 'host/session-added', blank: true, sessionId: S1 } }) + manager.handleMuxEnvelope(tasksFrame(S1, [view()])) + manager.handleHostEnvelope({ rpcId: 'r' as never, payload: { type: 'host/session-removed', sessionId: S1 } }) + expect(S1 in manager.getListSnapshot().tasksBySession).toBe(false) + }) + + it('notifies list subscribers so an open header re-renders without a poll', async () => { + const manager = new SessionManager(new FakeApiClient()) + const seen = vi.fn() + manager.subscribe(seen) + manager.handleMuxEnvelope(tasksFrame(S1, [view()])) + // The notifier batches on a microtask; the frame itself is already applied. + await Promise.resolve() + expect(seen).toHaveBeenCalled() + }) +}) diff --git a/packages/client/test-runtime/src/sessions.ts b/packages/client/test-runtime/src/sessions.ts index 315efd8f13..fc41c83975 100644 --- a/packages/client/test-runtime/src/sessions.ts +++ b/packages/client/test-runtime/src/sessions.ts @@ -202,7 +202,7 @@ export class TestSessions implements ISessions { constructor(private readonly stabilize: Stabilizer, private readonly rootCtx: Context) { this.list = createSnapshotStore({ ids: [], byId: {}, current: undefined, phase: 'ready', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) this.channel = new SessionProvideChannel({ rebuildBundles: () => { diff --git a/packages/client/ui-conversation/tests/chat-view.spec.tsx b/packages/client/ui-conversation/tests/chat-view.spec.tsx index 084e4ffa3a..f1d095ab7e 100644 --- a/packages/client/ui-conversation/tests/chat-view.spec.tsx +++ b/packages/client/ui-conversation/tests/chat-view.spec.tsx @@ -134,7 +134,7 @@ const compaction = (over: Partial = {}): CompactionSummar /** Empty sessions-list hook for the global standard-kit seat. */ function emptySessions() { const store = createSnapshotStore( - { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }) + { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }) return bindSnapshotSelector(store) } diff --git a/packages/client/ui-conversation/tests/enter-behavior-row.spec.tsx b/packages/client/ui-conversation/tests/enter-behavior-row.spec.tsx index e8d44c9bf3..573e3a97ed 100644 --- a/packages/client/ui-conversation/tests/enter-behavior-row.spec.tsx +++ b/packages/client/ui-conversation/tests/enter-behavior-row.spec.tsx @@ -16,7 +16,7 @@ afterEach(() => { function emptySessions() { return bindSnapshotSelector(createSnapshotStore({ - ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined, + ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, })) } diff --git a/packages/client/ui-conversation/tests/gate-branch-tails.spec.tsx b/packages/client/ui-conversation/tests/gate-branch-tails.spec.tsx index 6e0df4dd8c..bcda26f6a8 100644 --- a/packages/client/ui-conversation/tests/gate-branch-tails.spec.tsx +++ b/packages/client/ui-conversation/tests/gate-branch-tails.spec.tsx @@ -109,7 +109,7 @@ describe('render branch tails', () => { const chat = createChatStore().create() chat.actions.select({ turnSeq: 1, callId: 'ghost' } satisfies SelectionTarget) const emptyList = createSnapshotStore( - { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }) + { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }) const emptyWorkspaces = createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, baselinesReady: true, recentWorkspaceId: undefined, @@ -165,7 +165,7 @@ describe('render branch tails', () => { const chat = createChatStore().create() chat.actions.select({ turnSeq: 9, callId: 'p1:code:1:code:1', toolName: 'read' } satisfies SelectionTarget) const emptyList = createSnapshotStore( - { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }) + { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }) const emptyWorkspaces = createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, baselinesReady: true, recentWorkspaceId: undefined, diff --git a/packages/client/ui-conversation/tests/input-bar.spec.tsx b/packages/client/ui-conversation/tests/input-bar.spec.tsx index b9aa56f7c8..649133c042 100644 --- a/packages/client/ui-conversation/tests/input-bar.spec.tsx +++ b/packages/client/ui-conversation/tests/input-bar.spec.tsx @@ -136,7 +136,7 @@ function bench(over?: BenchOptions) { useSession: bindSnapshotSelector(session), useSessions: bindSnapshotSelector(createSnapshotStore({ ids: [], byId: {}, current: undefined, phase: 'ready', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, })), useWorkspaces: bindSnapshotSelector(createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, diff --git a/packages/client/ui-conversation/tests/input-matrix.spec.tsx b/packages/client/ui-conversation/tests/input-matrix.spec.tsx index bb6ba10990..69a5b9d6ba 100644 --- a/packages/client/ui-conversation/tests/input-matrix.spec.tsx +++ b/packages/client/ui-conversation/tests/input-matrix.spec.tsx @@ -40,7 +40,7 @@ function mountBar(shell: SessionInputShell, over?: { running?: boolean; disabled useSession: bindSnapshotSelector(session), useSessions: bindSnapshotSelector(createSnapshotStore({ ids: [], byId: {}, current: undefined, phase: 'ready', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, })), useWorkspaces: bindSnapshotSelector(createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, diff --git a/packages/client/ui-conversation/tests/input-scenarios.spec.tsx b/packages/client/ui-conversation/tests/input-scenarios.spec.tsx index 0722ccb2e1..1f9642e236 100644 --- a/packages/client/ui-conversation/tests/input-scenarios.spec.tsx +++ b/packages/client/ui-conversation/tests/input-scenarios.spec.tsx @@ -126,7 +126,7 @@ async function scopedBench(register?: (slash: SlashService) => void) { useSession: bindSnapshotSelector(sessionStore), useSessions: bindSnapshotSelector(createSnapshotStore({ ids: [], byId: {}, current: undefined, phase: 'ready', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, })), useWorkspaces: bindSnapshotSelector(createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, diff --git a/packages/client/ui-conversation/tests/skeleton.spec.tsx b/packages/client/ui-conversation/tests/skeleton.spec.tsx index 616407a82e..d9c3c2837d 100644 --- a/packages/client/ui-conversation/tests/skeleton.spec.tsx +++ b/packages/client/ui-conversation/tests/skeleton.spec.tsx @@ -110,7 +110,7 @@ function mount( ids: listed ? [root, SID] : [root], byId: { [root]: rootRow, ...listed && { [SID]: childRow } }, current: SID, - phase: 'ready', subagentsByParent: {}, currentAddress: undefined, + phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const workspaces = createSnapshotStore(workspaceState(workspaceRows)) const session = createSnapshotStore(snapshot) diff --git a/packages/client/ui-subagent/tests/conversation-ui.spec.tsx b/packages/client/ui-subagent/tests/conversation-ui.spec.tsx index ae6c0f07ee..ebc140405e 100644 --- a/packages/client/ui-subagent/tests/conversation-ui.spec.tsx +++ b/packages/client/ui-subagent/tests/conversation-ui.spec.tsx @@ -61,6 +61,7 @@ function props( }, current: PARENT, phase: 'ready', subagentsByParent: value === undefined ? nested : { [PARENT]: value, ...nested }, + tasksBySession: {}, currentAddress: undefined, } satisfies SessionListState function useSessions(select: (snapshot: SessionListState) => T): T { diff --git a/packages/client/ui-task/README.i18n.yaml b/packages/client/ui-task/README.i18n.yaml new file mode 100644 index 0000000000..39f800e04b --- /dev/null +++ b/packages/client/ui-task/README.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write packages/client/ui-task/README.md +README.md: a1430db55c7519c612e5d39de4627c750976d2d5 +README.zh.md: 5e29c939806f9a6500e78324c5a3322b6fd94539 diff --git a/packages/client/ui-task/README.md b/packages/client/ui-task/README.md new file mode 100644 index 0000000000..a1430db55c --- /dev/null +++ b/packages/client/ui-task/README.md @@ -0,0 +1,24 @@ +# @deepseek-ai/dsh-client-ui-task + +English | [中文](README.zh.md) + +Web background-task feature owner: contributes one entry to `conversation.session.header.actions` listing the `ctx.tasks` records this session can see. The data arrives entirely through the `tasksBySession` list mirror that [`dsh-client-runtime`](../runtime/README.md) folds from `session/tasks` frames, so this package issues no RPC and holds no state beyond popover visibility. + +The trigger renders only when the session has at least one task, so an ordinary conversation never grows a control for a capability it is not using. Its badge counts `running` plus `stopping` and is omitted at zero, leaving a session that holds only finished tasks a quiet entry point into its history rather than one advertising a count of nothing. The popover is a flat list: live rows first by `startedAt` ascending, then settled rows by `finishedAt` descending, with a same-millisecond tie broken on start order so the host's map iteration never decides it. A row shows the producer kind, the label, a status marker, the producer's `detail` in place of the generic status word once it has one, and an elapsed duration. That duration advances once per second while the row is live and freezes at `finishedAt`; the clock runs only while an open list holds something that moves. A settled row missing `finishedAt` reads as zero rather than as a negative figure, and a duration past an hour stays in hours rather than growing a day vocabulary no producer currently reaches. + +Settled rows stay visible and de-emphasized until the registry drops them at owner disposal. They are in the snapshot, a failed task's `detail` is the only place its failure is legible, and filtering them out here is work the output and cancellation phases would undo. A running one-shot background subagent therefore appears both here and in the [subagent catalog](../ui-subagent/README.md): the catalog navigates into the child's transcript, while this list is the only handle a future cancellation can attach to. + +Escape closes the list and returns focus to the trigger, as does a pointer press outside it. The last task disappearing closes the list before the control unmounts, so focus never vanishes from a removed node. Styling uses tokens only; copy goes through the package's own `task` locale namespace. The behavior is specified by the [Web background-task display Agent Note](../../../.agents/notes/implemented/feature/2026-08-08-web-background-task-display.md). + +## Model Experience + +None, as this package renders host-computed registry state for a human and touches no prompt, message, schema, stream, or tool result. The model's own view of the same tasks stays with [`dsh-tool-tasks`](../../tasks/tool-tasks/README.md). + +#### KV Cache effect + +None; the package never assembles or sends provider requests. + +## Known Limitations and Deferred Work + +- **Rows are read-only** — a task's streamed output and a human-initiated cancellation are separate phases. Cancellation additionally owes a model-facing decision the seam does not answer today: `kill()` marks terminal delivery reported, so an interrupt written against the current contract would leave the model believing its task is still running. +- **The list is not the registry's own set** — it shows what one session can see through the wire view, so a task owned by another session never appears here, and a process restart empties the list while the transcript keeps the `run_in_background` cards that started those tasks. An unowned task (one started without a live `Agent`) is the opposite case: it reaches every session's list, matching what `list(caller)` reports to every caller. diff --git a/packages/client/ui-task/README.zh.md b/packages/client/ui-task/README.zh.md new file mode 100644 index 0000000000..5e29c93980 --- /dev/null +++ b/packages/client/ui-task/README.zh.md @@ -0,0 +1,24 @@ +# @deepseek-ai/dsh-client-ui-task + +[English](README.md) | 中文 + +Web 后台任务特性的归属方：向 `conversation.session.header.actions` 贡献一个条目，列出当前会话可见的 `ctx.tasks` 记录。数据完全来自 [`dsh-client-runtime`](../runtime/README.md) 从 `session/tasks` 帧折叠出的 `tasksBySession` 列表镜像，因此本包不发任何 RPC，除弹层开合外不持有任何状态。 + +只有当会话至少有一个任务时才渲染触发器，普通对话不会因为一项未被使用的能力而长出控件。角标计数为 `running` 加 `stopping`，为零时省略，这样只剩已完成任务的会话保留一个安静的历史入口，而不是宣告一个「零」。弹层是一个扁平列表：活跃行在前按 `startedAt` 升序，随后终态行按 `finishedAt` 降序；毫秒相同的并列按启动顺序打破，宿主的 map 迭代顺序永远不参与决定。一行显示生产者 kind、label、状态标记、生产者一旦给出 `detail` 就取代通用状态词的那段文字，以及已耗时。该耗时在活跃时每秒推进，并在 `finishedAt` 冻结；只有当打开的列表里确实有会动的东西时时钟才运行。缺少 `finishedAt` 的终态行读作零而不是负数，超过一小时的耗时停留在小时单位，不会长出任何生产者目前都到不了的「天」词汇。 + +终态行保持可见并弱化，直到注册表在 owner 销毁时把它们丢掉。它们本就在快照里，失败任务的 `detail` 是其失败唯一可读之处，在这里过滤掉它们是输出与中断两期要推翻的工作。因此一个运行中的一次性后台 subagent 会同时出现在这里和 [subagent 目录](../ui-subagent/README.md)里：目录负责进入子会话的 transcript，而这个列表是将来中断能力唯一可能附着的句柄。 + +Escape 关闭列表并把焦点交还触发器，在其外部按下指针同理。最后一个任务消失时先关闭列表再卸载控件，焦点因此不会从一个被移除的节点上凭空消失。样式只用 token；文案走本包自己的 `task` locale 命名空间。行为由 [Web 后台任务展示 Agent Note](../../../.agents/notes/implemented/feature/2026-08-08-web-background-task-display.md) 规定。 + +## Model Experience + +无，因为本包为人类渲染宿主计算出的注册表状态，不触及 prompt、消息、schema、流或工具结果。模型对同一批任务的视角仍属于 [`dsh-tool-tasks`](../../tasks/tool-tasks/README.md)。 + +#### KV Cache effect + +无；本包从不组装或发送 provider 请求。 + +## Known Limitations and Deferred Work + +- **行是只读的** —— 任务的流式输出与人类发起的中断是各自独立的阶段。中断还额外欠一个 seam 目前没有回答的、面向模型的决策：`kill()` 会把终态投递标为已上报，所以照当前契约写出来的中断会让模型一直以为它的任务还在跑。 +- **列表不等于注册表自己的集合** —— 它展示的是「一个会话通过线路视图能看到什么」，所以别的会话拥有的任务在这里永远不出现；而进程重启会清空列表，transcript 里启动这些任务的 `run_in_background` 卡片却还在。无主任务（在没有活体 `Agent` 时启动的）是反过来的情形：它会进入每一个会话的列表，与 `list(caller)` 对每个调用方的报告一致。 diff --git a/packages/client/ui-task/package.json b/packages/client/ui-task/package.json new file mode 100644 index 0000000000..c8354f8f6c --- /dev/null +++ b/packages/client/ui-task/package.json @@ -0,0 +1,77 @@ +{ + "name": "@deepseek-ai/dsh-client-ui-task", + "description": "Session-header background-task list: live registry state mirrored from session/tasks frames", + "version": "0.0.1-rc.1", + "type": "module", + "main": "lib/index.js", + "types": "lib/types/index.d.ts", + "exports": { + ".": { + "types": "./lib/types/index.d.ts", + "default": "./lib/index.js" + }, + "./invariant": { + "types": "./lib/types/invariant.d.ts", + "default": "./lib/invariant.js" + }, + "./client": { + "types": "./lib/types/client/index.d.ts", + "default": "./lib/client.js" + }, + "./src/*": "./src/*", + "./package.json": "./package.json" + }, + "dsh": { + "client": { + "inject": [ + "@deepseek-ai/dsh-client-locale", + "@deepseek-ai/dsh-client-runtime", + "@deepseek-ai/dsh-client-ui-conversation", + "@deepseek-ai/dsh-client-ui-primitives" + ], + "platform": "web" + } + }, + "scripts": { + "bundle": "tsdown", + "watch": "tsdown --watch" + }, + "license": "BSD-3-Clause", + "repository": { + "type": "git", + "url": "git+https://github.com/deepseek-ai/deepseek-harness.git", + "directory": "packages/client/ui-task" + }, + "publishConfig": { + "access": "restricted" + }, + "dependencies": { + "react": "^18.2.0" + }, + "peerDependencies": { + "@deepseek-ai/dsh-client-locale": "workspace:^", + "@deepseek-ai/dsh-client-runtime": "workspace:^", + "@deepseek-ai/dsh-client-ui-conversation": "workspace:^", + "@deepseek-ai/dsh-client-ui-primitives": "workspace:^", + "@deepseek-ai/dsh-client-ui-slots": "workspace:^", + "@deepseek-ai/dsh-invariants": "workspace:^", + "@deepseek-ai/cordis": "workspace:^" + }, + "devDependencies": { + "@deepseek-ai/dsh-client-locale": "workspace:^", + "@deepseek-ai/dsh-client-runtime": "workspace:^", + "@deepseek-ai/dsh-client-test-runtime": "workspace:^", + "@deepseek-ai/dsh-client-ui-conversation": "workspace:^", + "@deepseek-ai/dsh-client-ui-primitives": "workspace:^", + "@deepseek-ai/dsh-client-ui-slots": "workspace:^", + "@deepseek-ai/dsh-invariants": "workspace:^", + "@types/react": "~18.3.1", + "@deepseek-ai/cordis": "workspace:^" + }, + "files": [ + "lib/index.js", + "lib/invariant.js", + "lib/client.js", + "lib/types/**/*.d.ts" + ] +} diff --git a/packages/client/ui-task/src/client/TaskListAction.module.css b/packages/client/ui-task/src/client/TaskListAction.module.css new file mode 100644 index 0000000000..b6ac05aa31 --- /dev/null +++ b/packages/client/ui-task/src/client/TaskListAction.module.css @@ -0,0 +1,125 @@ +.root { + position: relative; +} + +.trigger { + display: inline-flex; + align-items: center; + gap: 3px; + min-height: 28px; + padding: 3px 2px; + border: 0; + border-radius: 6px; + background: transparent; + color: var(--dsw-alias-label-tertiary); + font-size: 12px; + line-height: 18px; + cursor: pointer; +} + +.trigger:hover, +.trigger:focus-visible { + color: var(--dsw-alias-label-secondary); +} + +.trigger svg { + transition: transform 120ms ease; +} + +.triggerOpen { + transform: rotate(180deg); +} + +.triggerDot { + flex: none; +} + +.count { + margin: 0 5px; +} + +.menu { + position: absolute; + top: calc(100% + 5px); + left: 0; + z-index: 100; + box-sizing: border-box; + display: flex; + flex-direction: column; + gap: 1px; + width: 336px; + max-width: min(400px, calc(100vw - 32px)); + max-height: min(420px, calc(100vh - 140px)); + margin: 0; + padding: 4px; + overflow: auto; + list-style: none; + border: 1px solid var(--dsw-alias-border-l2); + border-radius: 12px; + background: var(--dsw-specific-menu); + --dsh-scrollbar-thumb: var(--dsw-alias-scrollbar-bg-l2); + --dsh-scrollbar-thumb-hover: var(--dsw-alias-scrollbar-hover-l2); + box-shadow: var(--dsw-shadow-lv3); +} + +.row { + display: flex; + align-items: center; + gap: 8px; + box-sizing: border-box; + width: 100%; + min-height: 32px; + padding: 6px 8px; + border-radius: 8px; + color: var(--dsw-alias-label-primary); + font-size: 13px; + line-height: 18px; +} + +.rowSettled { + color: var(--dsw-alias-label-tertiary); +} + +.rowDot { + flex: none; +} + +.kind { + flex: none; + padding: 0 6px; + border-radius: 5px; + background: var(--dsw-alias-fill-l2); + color: var(--dsw-alias-label-secondary); + font-size: 11px; + line-height: 18px; +} + +.label { + flex: 1; + min-width: 0; + overflow: hidden; + font-family: var(--dsw-font-mono); + white-space: nowrap; + text-overflow: ellipsis; +} + +.status, +.duration { + flex: none; + color: var(--dsw-alias-label-tertiary); + font-size: 11px; + line-height: 18px; +} + +/* A failed task's detail is the producer's raw error text, so it has no bound; + without this it widens the row past the menu instead of eliding like .label. */ +.status { + max-width: 40%; + overflow: hidden; + white-space: nowrap; + text-overflow: ellipsis; +} + +.duration { + font-variant-numeric: tabular-nums; +} diff --git a/packages/client/ui-task/src/client/TaskListAction.tsx b/packages/client/ui-task/src/client/TaskListAction.tsx new file mode 100644 index 0000000000..ede2eca377 --- /dev/null +++ b/packages/client/ui-task/src/client/TaskListAction.tsx @@ -0,0 +1,192 @@ +import { useEffect, useMemo, useRef, useState, type KeyboardEvent } from 'react' +import type { TaskView } from '@deepseek-ai/dsh-client-runtime/client' +import { IconChevronDownOutline14, StateDot, type StateDotState } from '@deepseek-ai/dsh-client-ui-primitives' +import type { PropsLocale, PropsRuntime, TranslateNS } from '@deepseek-ai/dsh-client-ui-slots' +import { NS } from './locales.ts' +import type {} from '@deepseek-ai/dsh-client-ui-conversation/client' +import css from './TaskListAction.module.css' + +/** Full props for the session-header background-task action. */ +export type TaskListActionProps = + PropsRuntime<'conversation.session.header.actions'> & PropsLocale + +/** Stable empty list so a session with no tasks keeps one array identity. */ +const NO_TASKS: readonly TaskView[] = [] + +/** A task the registry still holds open, and whose duration therefore ticks. */ +function isLive(task: TaskView): boolean { + return task.status === 'running' || task.status === 'stopping' +} + +/** Closed-union exhaustiveness fence for the wire status set. */ +/* v8 ignore next 3 -- closed-union backstop; only reached if a status is forged */ +function assertNever(value: never): never { + throw new Error(`unhandled task status: ${JSON.stringify(value)}`) +} + +/** + * Status marker semantics. `stopping` and `killed` share the attention color: + * both mean the work ended (or is ending) on request rather than on its own. + */ +function dotState(status: TaskView['status']): StateDotState { + switch (status) { + case 'running': return 'ongoing' + case 'stopping': return 'warning' + case 'completed': return 'done' + case 'killed': return 'warning' + case 'failed': return 'error' + /* v8 ignore next -- closed wire status union */ + default: return assertNever(status) + } +} + +/** Human status word for the row and its accessible name. */ +function statusLabel(status: TaskView['status'], t: TranslateNS): string { + switch (status) { + case 'running': return t('status.running') + case 'stopping': return t('status.stopping') + case 'completed': return t('status.completed') + case 'killed': return t('status.killed') + case 'failed': return t('status.failed') + /* v8 ignore next -- closed wire status union */ + default: return assertNever(status) + } +} + +/** + * Elapsed time in at most two adjacent units. A background task that outlives + * an hour is already exceptional, so hours is the widest unit — beyond that the + * figure stays in hours rather than growing a day/month vocabulary no producer + * currently reaches. + */ +function formatDuration(elapsedMs: number, t: TranslateNS): string { + const total = Math.max(0, Math.floor(elapsedMs / 1_000)) + const seconds = total % 60 + const minutes = Math.floor(total / 60) % 60 + const hours = Math.floor(total / 3_600) + if (hours > 0) return t('duration.hours', { hours, minutes }) + if (minutes > 0) return t('duration.minutes', { minutes, seconds }) + return t('duration.seconds', { seconds }) +} + +/** + * Live rows first in start order, then settled rows newest-first. Two tasks + * that settled in the same millisecond fall back to start order, so the sort + * never depends on the host's map iteration. + */ +function ordered(tasks: readonly TaskView[]): TaskView[] { + return [...tasks].sort((left, right) => { + const liveLeft = isLive(left) + if (liveLeft !== isLive(right)) return liveLeft ? -1 : 1 + if (liveLeft) return left.startedAt - right.startedAt + const finished = (right.finishedAt ?? right.startedAt) - (left.finishedAt ?? left.startedAt) + return finished !== 0 ? finished : left.startedAt - right.startedAt + }) +} + +/** + * Session-header entry point for this session's background tasks. It renders + * nothing at all until the session has at least one task, so an ordinary + * conversation never grows a control for a capability it is not using. + * @param props - runtime slot currency plus the namespace translator. + * @returns the trigger and its popover list, or null when there is nothing to show. + */ +export function TaskListAction({ sessionId, useSessions, t }: TaskListActionProps) { + const tasks = useSessions(state => state.tasksBySession[sessionId]) ?? NO_TASKS + const [open, setOpen] = useState(false) + const [now, setNow] = useState(() => Date.now()) + const rootRef = useRef(null) + const triggerRef = useRef(null) + + const rows = useMemo(() => ordered(tasks), [tasks]) + const liveCount = useMemo(() => tasks.filter(isLive).length, [tasks]) + + useEffect(() => { + if (!open) return + const closeOutside = (event: PointerEvent): void => { + if (event.target instanceof Node && !rootRef.current?.contains(event.target)) { + setOpen(false) + } + } + document.addEventListener('pointerdown', closeOutside) + return () => { document.removeEventListener('pointerdown', closeOutside) } + }, [open]) + + // The clock only runs while an open list is showing something that moves. + useEffect(() => { + if (!open || liveCount === 0) return + setNow(Date.now()) + const timer = setInterval(() => { setNow(Date.now()) }, 1_000) + return () => { clearInterval(timer) } + }, [open, liveCount]) + + // The last task disappearing removes this control; close first so focus does + // not vanish from an unmounting node. + useEffect(() => { + if (tasks.length === 0 && open) setOpen(false) + }, [tasks.length, open]) + + if (tasks.length === 0) return null + + const countKey = liveCount > 0 + ? (liveCount === 1 ? 'count.live.one' : 'count.live.other') + : (tasks.length === 1 ? 'count.idle.one' : 'count.idle.other') + const countLabel = t(countKey, { count: liveCount > 0 ? liveCount : tasks.length }) + + const onKeyDown = (event: KeyboardEvent): void => { + if (event.key !== 'Escape' || !open) return + event.preventDefault() + setOpen(false) + triggerRef.current?.focus() + } + + return ( +
+ + {open + ? ( +
    + {rows.map((task) => { + const live = isLive(task) + const elapsed = live ? now - task.startedAt : (task.finishedAt ?? task.startedAt) - task.startedAt + const duration = formatDuration(elapsed, t) + const status = statusLabel(task.status, t) + return ( +
  • + + {task.kind} + {task.label} + {task.detail ?? status} + + {duration} + +
    • + ) + })} +
+ ) + : null} +
+ ) +} diff --git a/packages/client/ui-task/src/client/index.ts b/packages/client/ui-task/src/client/index.ts new file mode 100644 index 0000000000..792b5f39d4 --- /dev/null +++ b/packages/client/ui-task/src/client/index.ts @@ -0,0 +1,40 @@ +/** + * Background-task plugin, browser half: contributes one session-header action + * that renders this session's `ctx.tasks` records. The data arrives entirely + * through the `tasksBySession` list mirror, so the plugin issues no RPC and + * holds no state of its own beyond popover visibility. + */ +import type { ClientContext } from '@deepseek-ai/dsh-client-runtime/client' +import { TaskListAction } from './TaskListAction.tsx' +import type {} from '@deepseek-ai/dsh-client-locale/client' +import { en, NS, zh, type TaskKey } from './locales.ts' + +declare module '@deepseek-ai/dsh-client-ui-slots' { + interface LocaleNamespaceMap { + /** Background-task list copy. */ + 'task': TaskKey + } +} + +export type { TaskListActionProps } from './TaskListAction.tsx' + +/** Required services for locale registration and header-slot contribution. */ +export const inject = ['sessions', 'slots', 'locale'] + +/** + * Client plugin body: register the dictionaries and the header action. + * @param ctx - client root context. + */ +export function apply(ctx: ClientContext): void { + ctx.effect(() => ctx.locale.register(NS, { zh, en }), 'ui-task: dictionaries') + ctx.slots.inject( + 'conversation.session.header.actions', + () => ctx.slots.register({ + name: 'conversation.session.header.actions', + id: 'task-list', + // After the subagent catalog: session lineage reads before process work. + order: 20, + locale: NS, + }, TaskListAction), + ) +} diff --git a/packages/client/ui-task/src/client/locales.ts b/packages/client/ui-task/src/client/locales.ts new file mode 100644 index 0000000000..8c03da56eb --- /dev/null +++ b/packages/client/ui-task/src/client/locales.ts @@ -0,0 +1,45 @@ +/** `task` namespace dictionaries. */ + +/** Dictionary namespace owned by this plugin. */ +export const NS = 'task' + +/** Simplified Chinese dictionary (the key-set source of truth). */ +export const zh = { + 'count.live.one': '{count} 个后台任务运行中', + 'count.live.other': '{count} 个后台任务运行中', + 'count.idle.one': '{count} 个后台任务', + 'count.idle.other': '{count} 个后台任务', + 'list.aria': '后台任务', + 'status.running': '运行中', + 'status.stopping': '正在停止', + 'status.completed': '已完成', + 'status.killed': '已取消', + 'status.failed': '已失败', + 'duration.seconds': '{seconds}秒', + 'duration.minutes': '{minutes}分{seconds}秒', + 'duration.hours': '{hours}小时{minutes}分', + 'duration.title.live': '已运行 {duration}', + 'duration.title.done': '耗时 {duration}', +} as const + +/** English dictionary, key-identical to the Chinese source of truth. */ +export const en: Record = { + 'count.live.one': '{count} background task running', + 'count.live.other': '{count} background tasks running', + 'count.idle.one': '{count} background task', + 'count.idle.other': '{count} background tasks', + 'list.aria': 'Background tasks', + 'status.running': 'running', + 'status.stopping': 'stopping', + 'status.completed': 'completed', + 'status.killed': 'cancelled', + 'status.failed': 'failed', + 'duration.seconds': '{seconds}s', + 'duration.minutes': '{minutes}m {seconds}s', + 'duration.hours': '{hours}h {minutes}m', + 'duration.title.live': 'Running for {duration}', + 'duration.title.done': 'Took {duration}', +} + +/** Key domain of the `task` namespace (zh is the source of truth). */ +export type TaskKey = keyof typeof zh diff --git a/packages/client/ui-task/src/css-modules.d.ts b/packages/client/ui-task/src/css-modules.d.ts new file mode 100644 index 0000000000..bc5e482353 --- /dev/null +++ b/packages/client/ui-task/src/css-modules.d.ts @@ -0,0 +1,6 @@ +declare module '*.module.css' { + const classes: Record + export default classes +} + +declare module '*.css' diff --git a/packages/client/ui-task/src/index.ts b/packages/client/ui-task/src/index.ts new file mode 100644 index 0000000000..3962e1b113 --- /dev/null +++ b/packages/client/ui-task/src/index.ts @@ -0,0 +1,9 @@ +/** + * Background-task list plugin, node half. Pure UI plugin: the empty apply + * exists so the plugin appears in the host cordis.yml / Loader; the browser + * half ships via exports["./client"], discovered through the package.json + * dshClient declaration. + */ + +/** Host plugin body — no host-side behavior for this source plugin. */ +export function apply(): void {} diff --git a/packages/client/ui-task/src/invariant.ts b/packages/client/ui-task/src/invariant.ts new file mode 100644 index 0000000000..cfdad3c1f2 --- /dev/null +++ b/packages/client/ui-task/src/invariant.ts @@ -0,0 +1,32 @@ +/** + * Package-owned invariant companion for `@deepseek-ai/dsh-client-ui-task`. + * @module @deepseek-ai/dsh-client-ui-task/invariant + */ + +/* jscpd:ignore-start */ +import type { Context } from '@deepseek-ai/cordis' +import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants' + +const PACKAGE_NAME = '@deepseek-ai/dsh-client-ui-task' + +/** Cordis companion plugin name. */ +export const name = 'client-ui-task-invariant' +/** Service required before the companion can reserve package ownership. */ +export const inject = ['invariants'] + +/** + * No runtime invariant: this package is a read-only projection of the + * `tasksBySession` mirror onto one header slot entry. It emits no cordis + * events, owns no cross-plugin mutable state, and its single slot registration + * proves disposal through the HMR-safety spec. + */ +const install: InvariantInstaller = () => {} + +/** + * Register this package's invariant companion. + * @param ctx - Cordis context carrying the invariant service. + * @returns the installed registration's disposer after setup succeeds. + */ +export const apply = (ctx: Context): Promise<() => void> => + Promise.resolve(ctx.invariants.register(PACKAGE_NAME, install)) +/* jscpd:ignore-end */ diff --git a/packages/client/ui-task/tests/browser-plugin.spec.ts b/packages/client/ui-task/tests/browser-plugin.spec.ts new file mode 100644 index 0000000000..142668387f --- /dev/null +++ b/packages/client/ui-task/tests/browser-plugin.spec.ts @@ -0,0 +1,91 @@ +/** + * ui-task plugin halves: the browser entry's dictionary and header-slot + * registrations against the real SlotsService (with fiber teardown proving + * removal — HMR safety), the inert node entry, and the invariant companion's + * ownership reservation. + */ +import { Context } from '@deepseek-ai/cordis' +import { describe, expect, it } from 'vitest' +import InvariantService from '@deepseek-ai/dsh-invariants' +import { SlotsService } from '@deepseek-ai/dsh-client-runtime/client' +import { apply as applyLocale, inject as localeInject } from '@deepseek-ai/dsh-client-locale/client' +import { apply, inject } from '../src/client/index.ts' +import { apply as applyNode } from '../src/index.ts' +import * as TaskInvariant from '../src/invariant.ts' +import { en, NS, zh } from '../src/client/locales.ts' + +/** Slot ledger reader: entry ids currently registered in the header list. */ +function headerEntryIds(ctx: Context): (string | undefined)[] { + return ctx.slots + .entries('conversation.session.header.actions') + .map(entry => entry.options.id) +} + +/** Boot the browser half over a real slot tree that declares the header list. */ +async function bench(): Promise<{ ctx: Context; fiber: ReturnType }> { + const ctx = new Context() + await ctx.plugin(SlotsService).await() + ctx.slots.register({ + name: 'root', + children: { + 'conversation.session.header.actions': { kind: 'list', scope: 'session' }, + }, + } as never, () => null) + ctx.provide('sessions', {}) + // The locale plugin binds a settings scope, which reads the connection handle. + ctx.provide('connection', { api: { settings: {} }, isLoopback: false } as never) + await ctx.plugin({ inject: localeInject, apply: applyLocale }).await() + const fiber = ctx.plugin({ inject: [...inject], apply }) + await fiber.await() + return { ctx, fiber } +} + +describe('ui-task browser half', () => { + it('declares the services it binds', () => { + expect(inject).toEqual(['sessions', 'slots', 'locale']) + }) + + it('registers the header action, and fiber teardown removes it (HMR safety)', async () => { + const { ctx, fiber } = await bench() + expect(headerEntryIds(ctx)).toContain('task-list') + await fiber.dispose() + expect(headerEntryIds(ctx)).not.toContain('task-list') + }) + + it('registers both dictionaries under its own namespace and releases them with the fiber', async () => { + const { ctx, fiber } = await bench() + const translate = ctx.locale.bind(NS) + expect(translate('list.aria')).toBe(zh['list.aria']) + ctx.locale.setLocale('en') + expect(translate('list.aria')).toBe(en['list.aria']) + + // Withdrawn dictionaries leave the key unresolved rather than translated. + await fiber.dispose() + expect(translate('list.aria')).not.toBe(en['list.aria']) + }) + + it('keeps the English dictionary key-identical to the Chinese source of truth', () => { + expect(Object.keys(en).sort()).toEqual(Object.keys(zh).sort()) + }) +}) + +describe('ui-task node half', () => { + it('contributes no host behavior', () => { + // The node half exists only so the plugin appears in the Loader tree. + expect(applyNode).not.toThrow() + }) +}) + +describe('ui-task invariant companion', () => { + it('reserves package ownership under its declared companion name', async () => { + const ctx = new Context() + await ctx.plugin(InvariantService, { enabled: true }) + const fiber = ctx.plugin(TaskInvariant) + await fiber.await() + expect(TaskInvariant.name).toBe('client-ui-task-invariant') + expect(TaskInvariant.inject).toEqual(['invariants']) + // Emitting an unrelated event proves the companion installed no audit. + expect(() => { (ctx.emit as (event: string) => void)('slots/changed') }).not.toThrow() + await fiber.dispose() + }) +}) diff --git a/packages/client/ui-task/tests/task-list-action.spec.tsx b/packages/client/ui-task/tests/task-list-action.spec.tsx new file mode 100644 index 0000000000..0d03af3ec0 --- /dev/null +++ b/packages/client/ui-task/tests/task-list-action.spec.tsx @@ -0,0 +1,239 @@ +// @vitest-environment jsdom +import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' +import { act, cleanup, fireEvent, render, screen, within } from '@testing-library/react' +import { makeTranslate } from '@deepseek-ai/dsh-client-test-runtime' +import type { SessionId, SessionListState, TaskView } from '@deepseek-ai/dsh-client-runtime/client' +import { TaskListAction, type TaskListActionProps } from '../src/client/TaskListAction.tsx' +import { zh } from '../src/client/locales.ts' + +// Live rows render `now - startedAt`, so every assertion needs a pinned clock. +beforeEach(() => { + vi.useFakeTimers() + vi.setSystemTime(START) +}) + +afterEach(() => { + cleanup() + vi.useRealTimers() + vi.restoreAllMocks() +}) + +const SESSION = 'session' as SessionId +const START = 1_700_000_000_000 +const t: TaskListActionProps['t'] = makeTranslate(zh) + +function task(over: Partial = {}): TaskView { + return { + id: 'bash-1' as TaskView['id'], + kind: 'bash', + label: 'pnpm run build', + status: 'running', + startedAt: START, + ...over, + } +} + +function props(tasks: readonly TaskView[] | undefined): TaskListActionProps { + const state = { + ids: [SESSION], + byId: {}, + current: SESSION, + phase: 'ready', + subagentsByParent: {}, + tasksBySession: tasks === undefined ? {} : { [SESSION]: tasks }, + currentAddress: undefined, + } satisfies SessionListState + function useSessions(select: (snapshot: SessionListState) => T): T { + return select(state) + } + return { sessionId: SESSION, useSessions, t } as unknown as TaskListActionProps +} + +/** + * Rows in render order as `[kind, label, status, duration]`. Adjacent spans + * carry no whitespace between them, so the cells are read one element at a + * time rather than split out of a flattened string. + */ +function rowCells(): string[][] { + return within(screen.getByRole('list', { name: zh['list.aria'] })) + .getAllByRole('listitem') + .map(row => [...row.children] + .map(cell => cell.textContent ?? '') + .filter(text => text !== '')) +} + +describe('TaskListAction visibility', () => { + it('renders nothing while the session has no tasks', () => { + const { container } = render() + expect(container.innerHTML).toBe('') + }) + + it('counts only live tasks, and falls back to the total when none are live', () => { + const { rerender } = render() + expect(screen.getByRole('button', { name: '2 个后台任务运行中' })).toBeDefined() + + rerender() + expect(screen.getByRole('button', { name: '1 个后台任务' })).toBeDefined() + }) + + it('closes and unmounts when the last task disappears while the list is open', () => { + const { container, rerender } = render() + fireEvent.click(screen.getByRole('button')) + expect(screen.getByRole('list', { name: zh['list.aria'] })).toBeDefined() + + rerender() + expect(container.innerHTML).toBe('') + }) +}) + +describe('TaskListAction rows', () => { + it('orders live tasks by start, then settled tasks newest-first', () => { + render() + fireEvent.click(screen.getByRole('button')) + expect(rowCells()).toEqual([ + ['bash', 'earlier live', '运行中', '0秒'], + ['bash', 'later live', '运行中', '0秒'], + ['bash', 'new done', '已失败', '9秒'], + ['bash', 'old done', '已完成', '1秒'], + ]) + }) + + it('breaks a settled tie on start order so map iteration never decides it', () => { + render() + fireEvent.click(screen.getByRole('button')) + expect(rowCells().map(cells => cells[1])).toEqual(['first', 'second']) + }) + + it('prefers the producer detail over the generic status word', () => { + render() + fireEvent.click(screen.getByRole('button')) + expect(rowCells()[0]).toContain('signal: SIGTERM') + }) + + it('renders every status word, including the stopping transition', () => { + render() + fireEvent.click(screen.getByRole('button')) + const words = rowCells().map(cells => cells[2]) + expect(new Set(words)).toEqual(new Set(['运行中', '正在停止', '已完成', '已取消', '已失败'])) + }) +}) + +describe('TaskListAction duration', () => { + it('advances a live row once per second and freezes a settled one', () => { + vi.setSystemTime(START + 1_000) + render() + fireEvent.click(screen.getByRole('button')) + expect(rowCells()[0]).toContain('1秒') + expect(rowCells()[1]).toContain('4秒') + + act(() => { vi.advanceTimersByTime(2_000) }) + expect(rowCells()[0]).toContain('3秒') + expect(rowCells()[1]).toContain('4秒') + }) + + it('widens to minutes and then hours, and never shows a negative figure', () => { + render() + fireEvent.click(screen.getByRole('button')) + expect(rowCells().map(cells => cells[3])).toEqual(['2小时3分', '2分5秒', '0秒']) + }) + + it('runs no clock while the list is closed', () => { + const interval = vi.spyOn(globalThis, 'setInterval') + render() + expect(interval).not.toHaveBeenCalled() + fireEvent.click(screen.getByRole('button')) + expect(interval).toHaveBeenCalledTimes(1) + }) + + it('runs no clock for an open list holding only settled tasks', () => { + const interval = vi.spyOn(globalThis, 'setInterval') + render() + fireEvent.click(screen.getByRole('button')) + expect(interval).not.toHaveBeenCalled() + }) +}) + +describe('TaskListAction dismissal', () => { + it('closes on Escape and returns focus to the trigger', () => { + render() + const trigger = screen.getByRole('button') + fireEvent.click(trigger) + expect(trigger.getAttribute('aria-expanded')).toBe('true') + + fireEvent.keyDown(trigger, { key: 'Escape' }) + expect(trigger.getAttribute('aria-expanded')).toBe('false') + expect(document.activeElement).toBe(trigger) + }) + + it('ignores other keys and a closed-list Escape', () => { + render() + const trigger = screen.getByRole('button') + fireEvent.keyDown(trigger, { key: 'Escape' }) + expect(trigger.getAttribute('aria-expanded')).toBe('false') + + fireEvent.click(trigger) + fireEvent.keyDown(trigger, { key: 'ArrowDown' }) + expect(trigger.getAttribute('aria-expanded')).toBe('true') + }) + + it('closes on an outside pointer press but not on one inside', () => { + render() + const trigger = screen.getByRole('button') + fireEvent.click(trigger) + + fireEvent.pointerDown(screen.getByRole('list', { name: zh['list.aria'] })) + expect(trigger.getAttribute('aria-expanded')).toBe('true') + + fireEvent.pointerDown(document.body) + expect(trigger.getAttribute('aria-expanded')).toBe('false') + }) +}) + +describe('TaskListAction wire tolerance', () => { + it('treats a settled task with no finishedAt as zero-duration and sorts it by start', () => { + // `finishedAt` is optional on the wire; the Host always sets it, so this + // covers a producer or carrier that ever stops doing so. + render() + fireEvent.click(screen.getByRole('button')) + expect(rowCells().map(cells => [cells[1], cells[3]])).toEqual([ + ['finished', '3秒'], + ['no finish', '0秒'], + ]) + }) + + it('falls back to start order when neither settled task carries a finish time', () => { + render() + fireEvent.click(screen.getByRole('button')) + expect(rowCells().map(cells => cells[1])).toEqual(['later', 'earlier']) + }) +}) diff --git a/packages/client/ui-task/tsconfig.json b/packages/client/ui-task/tsconfig.json new file mode 100644 index 0000000000..76ff7ad167 --- /dev/null +++ b/packages/client/ui-task/tsconfig.json @@ -0,0 +1,33 @@ +{ + "extends": "../../../tsconfig.base.client.json", + "compilerOptions": { + "rootDir": "src", + "outDir": "lib/types" + }, + "include": [ + "src" + ], + "references": [ + { + "path": "../../../vendor/cordis" + }, + { + "path": "../locale" + }, + { + "path": "../runtime" + }, + { + "path": "../ui-conversation" + }, + { + "path": "../ui-primitives" + }, + { + "path": "../ui-slots" + }, + { + "path": "../../support/invariants" + } + ] +} diff --git a/packages/client/ui-task/tsdown.config.ts b/packages/client/ui-task/tsdown.config.ts new file mode 100644 index 0000000000..2be71f65dc --- /dev/null +++ b/packages/client/ui-task/tsdown.config.ts @@ -0,0 +1,3 @@ +import { clientBundle } from '../tsdown.client.ts' + +export default clientBundle('@deepseek-ai/dsh-client-ui-task', ['lib/types/index.js', 'lib/types/invariant.js']) diff --git a/packages/client/ui-theme/tests/appearance-row.spec.tsx b/packages/client/ui-theme/tests/appearance-row.spec.tsx index 7b1e11a69b..a6aa481879 100644 --- a/packages/client/ui-theme/tests/appearance-row.spec.tsx +++ b/packages/client/ui-theme/tests/appearance-row.spec.tsx @@ -22,7 +22,7 @@ const COPY: Record = { /** Empty global standard-kit hooks (the row reads neither). */ function emptySessions() { const store = createSnapshotStore( - { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }) + { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }) return bindSnapshotSelector(store) } function emptyWorkspaces() { diff --git a/packages/client/ui-tool/tests/chat-code-subcalls.spec.tsx b/packages/client/ui-tool/tests/chat-code-subcalls.spec.tsx index 8840e6a19d..5939655118 100644 --- a/packages/client/ui-tool/tests/chat-code-subcalls.spec.tsx +++ b/packages/client/ui-tool/tests/chat-code-subcalls.spec.tsx @@ -112,7 +112,7 @@ async function bench(snapshot: ConversationSnapshot) { ids: [SID], byId: { [SID]: { id: SID, title: 'S', displayTitle: 'S', running: false, blank: false, updatedAt: 1 } }, current: SID, - phase: 'ready', subagentsByParent: {}, currentAddress: undefined, + phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const scoped = { send: vi.fn(async () => {}), cancel: vi.fn(async () => {}) } const layout = { openDetails: vi.fn(), closeDetails: vi.fn() } diff --git a/packages/client/ui-tool/tests/coverage-tails.spec.tsx b/packages/client/ui-tool/tests/coverage-tails.spec.tsx index ab1a0a9632..8010fb8763 100644 --- a/packages/client/ui-tool/tests/coverage-tails.spec.tsx +++ b/packages/client/ui-tool/tests/coverage-tails.spec.tsx @@ -30,7 +30,7 @@ function listStore() { }, current: undefined, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) } diff --git a/packages/client/ui-tool/tests/diff-card.spec.tsx b/packages/client/ui-tool/tests/diff-card.spec.tsx index 3990cba157..1726c81136 100644 --- a/packages/client/ui-tool/tests/diff-card.spec.tsx +++ b/packages/client/ui-tool/tests/diff-card.spec.tsx @@ -159,7 +159,7 @@ describe('FileMutationRow diff card', () => { byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd: '/w/app' } }, current: SID, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) @@ -311,13 +311,13 @@ describe('DetailsPanel diff Output section', () => { const chat = createChatStore().create() if (selection !== null) chat.actions.select(selection) const sessions = createSnapshotStore(cwd === undefined - ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined } + ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined } : { ids: [SID], byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd } }, current: SID, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const workspaces = createSnapshotStore({ diff --git a/packages/client/ui-tool/tests/read-card.spec.tsx b/packages/client/ui-tool/tests/read-card.spec.tsx index 14baac6b9b..ae719173d5 100644 --- a/packages/client/ui-tool/tests/read-card.spec.tsx +++ b/packages/client/ui-tool/tests/read-card.spec.tsx @@ -173,7 +173,7 @@ describe('ReadRow keyed toolview', () => { byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd: '/w/app' } }, current: SID, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) @@ -257,13 +257,13 @@ describe('DetailsPanel Output section (read)', () => { const chat = createChatStore().create() if (selection !== null) chat.actions.select(selection) const sessions = createSnapshotStore(cwd === undefined - ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined } + ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined } : { ids: [SID], byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd } }, current: SID, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const workspaces = createSnapshotStore({ diff --git a/packages/client/ui-tool/tests/search-card.spec.tsx b/packages/client/ui-tool/tests/search-card.spec.tsx index 67d5eea6ca..3ff068b3c9 100644 --- a/packages/client/ui-tool/tests/search-card.spec.tsx +++ b/packages/client/ui-tool/tests/search-card.spec.tsx @@ -380,7 +380,7 @@ describe('DetailsPanel Output section (search)', () => { if (selection !== null) chat.actions.select(selection) const sessions = createSnapshotStore({ ids: [], byId: {}, current: undefined, phase: 'ready', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const workspaces = createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, diff --git a/packages/client/ui-tool/tests/terminal-card.spec.tsx b/packages/client/ui-tool/tests/terminal-card.spec.tsx index c0af5adff7..dd39b8bc88 100644 --- a/packages/client/ui-tool/tests/terminal-card.spec.tsx +++ b/packages/client/ui-tool/tests/terminal-card.spec.tsx @@ -348,7 +348,7 @@ describe('BashRow terminal card', () => { byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0 } }, current: undefined, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) @@ -448,13 +448,13 @@ describe('DetailsPanel Output section', () => { const chat = createChatStore().create() if (selection !== null) chat.actions.select(selection) const sessions = createSnapshotStore(cwd === undefined - ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined } + ? { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined } : { ids: [SID], byId: { [SID]: { id: SID, displayTitle: 'r', running: false, blank: false, updatedAt: 0, cwd } }, current: SID, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const workspaces = createSnapshotStore({ @@ -649,7 +649,7 @@ describe('DetailsPanel Output section', () => { useSessions={bindSnapshotSelector(createSnapshotStore( { ids: [], byId: {}, current: undefined, phase: 'ready', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }))} useWorkspaces={bindSnapshotSelector(createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, diff --git a/packages/client/ui-tool/tests/web-card.spec.tsx b/packages/client/ui-tool/tests/web-card.spec.tsx index 67ec839471..04535a0954 100644 --- a/packages/client/ui-tool/tests/web-card.spec.tsx +++ b/packages/client/ui-tool/tests/web-card.spec.tsx @@ -210,7 +210,7 @@ describe('DetailsPanel web Output section', () => { if (selection !== null) chat.actions.select(selection) const sessions = createSnapshotStore({ ids: [], byId: {}, current: undefined, phase: 'ready', - subagentsByParent: {}, currentAddress: undefined, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const workspaces = createSnapshotStore({ items: [], archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, diff --git a/packages/client/ui-trajectory/tests/views.spec.tsx b/packages/client/ui-trajectory/tests/views.spec.tsx index e4ea44d925..5235235d90 100644 --- a/packages/client/ui-trajectory/tests/views.spec.tsx +++ b/packages/client/ui-trajectory/tests/views.spec.tsx @@ -140,7 +140,7 @@ function fakeSession(nodes: ConversationSnapshot['nodes']) { /** Empty sessions-list hook; breadcrumbs therefore fall back to the raw id. */ function emptySessions() { const store = createSnapshotStore( - { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined }) + { ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined }) return bindSnapshotSelector(store) } diff --git a/packages/client/ui-workspace/tests/tree.spec.ts b/packages/client/ui-workspace/tests/tree.spec.ts index 647e29f6d3..5a6d145e36 100644 --- a/packages/client/ui-workspace/tests/tree.spec.ts +++ b/packages/client/ui-workspace/tests/tree.spec.ts @@ -17,7 +17,7 @@ const list = (...items: SessionSummary[]): SessionListState => ({ ids: items.map(item => item.id), byId: Object.fromEntries(items.map(item => [item.id, item])), current: undefined, - phase: 'ready', subagentsByParent: {}, currentAddress: undefined, + phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, }) const workspace = (id: string, sessionIds: string[], title = id): WorkspaceView => ({ workspaceId: wid(id), path: `/projects/${id}`, title, diff --git a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx index 6c46275894..918a3f6c0e 100644 --- a/packages/client/ui-workspace/tests/workspace-browser.spec.tsx +++ b/packages/client/ui-workspace/tests/workspace-browser.spec.tsx @@ -29,7 +29,7 @@ const sessionState = (items: readonly SessionSummary[], overrides: Partial [item.id, item])), current: undefined, phase: 'ready', - subagentsByParent: {}, + subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, ...overrides, }) diff --git a/packages/client/ui-workspace/tests/workspace-picker.spec.tsx b/packages/client/ui-workspace/tests/workspace-picker.spec.tsx index e7788a3f63..132b64f4b2 100644 --- a/packages/client/ui-workspace/tests/workspace-picker.spec.tsx +++ b/packages/client/ui-workspace/tests/workspace-picker.spec.tsx @@ -28,7 +28,7 @@ function hook(snapshot: T) { return function select(selector: (state: T) => S): S { return selector(snapshot) } } const sessions: SessionListState = { - ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, currentAddress: undefined, + ids: [], byId: {}, current: undefined, phase: 'ready', subagentsByParent: {}, tasksBySession: {}, currentAddress: undefined, } const workspaceState = (items: readonly WorkspaceView[]): WorkspaceListState => ({ items, archivedSessionIds: [], state: 'idle', phase: 'ready', error: null, baselinesReady: true, diff --git a/packages/context/workspace-context/tests/workspace-context.spec.ts b/packages/context/workspace-context/tests/workspace-context.spec.ts index 0f177a1d49..e95b30fa5b 100644 --- a/packages/context/workspace-context/tests/workspace-context.spec.ts +++ b/packages/context/workspace-context/tests/workspace-context.spec.ts @@ -117,6 +117,10 @@ class RecordingFileSystem extends FileSystem { return this.entries.get(target.targetKey)?.content ?? '' } + override async readBytes(_target: FsTarget, _signal: AbortSignal | undefined, _maxBytes: number): Promise { + throw new Error('not needed in workspace-context tests') + } + override async streamText(target: FsTarget, signal?: AbortSignal): Promise> { if (signal !== undefined) this.signals.push(signal) signal?.throwIfAborted() diff --git a/packages/core/tools/tests/gen-tool-catalog.spec.ts b/packages/core/tools/tests/gen-tool-catalog.spec.ts index 2e59ffe32e..dcd9ca01c6 100644 --- a/packages/core/tools/tests/gen-tool-catalog.spec.ts +++ b/packages/core/tools/tests/gen-tool-catalog.spec.ts @@ -23,7 +23,7 @@ describe('gen-tool-catalog collectToolCatalog', () => { it('boots every shipped tool package and harvests its model-facing schemas', async () => { const catalog = await collectToolCatalog() const names = catalog.flatMap(entry => entry.schemas.map(s => s.name)).sort() - expect(names).toEqual(['ask_user_question', 'bash', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'interrupt_agent', 'list_agents', 'lsp', 'pwsh', 'ralph', 'read', 'report', 'run_code', 'send_message', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'str_replace_editor', 'subagent', 'task_kill', 'task_list', 'task_output', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write']) + expect(names).toEqual(['ask_user_question', 'bash', 'bash', 'cordis_inspect', 'cordis_mount', 'cordis_unmount', 'create_goal', 'edit', 'exit_plan_mode', 'get_goal', 'glob', 'grep', 'interrupt_agent', 'list_agents', 'lsp', 'pwsh', 'ralph', 'read', 'read_image', 'report', 'run_code', 'send_message', 'session_event_read', 'session_event_search', 'session_event_trace', 'session_search', 'session_trace', 'skill', 'str_replace_editor', 'subagent', 'task_kill', 'task_list', 'task_output', 'terminal_close', 'terminal_list', 'terminal_open', 'terminal_read', 'terminal_send', 'terminal_signal', 'todo_write', 'update_goal', 'web_fetch', 'web_search', 'workflow', 'write']) // Every tool carries a JSON-Schema `parameters` object (what the model sees). for (const entry of catalog) { for (const schema of entry.schemas) { diff --git a/packages/e2b/fs-e2b/README.i18n.yaml b/packages/e2b/fs-e2b/README.i18n.yaml index 64460f7e87..feb950b196 100644 --- a/packages/e2b/fs-e2b/README.i18n.yaml +++ b/packages/e2b/fs-e2b/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/e2b/fs-e2b/README.md -README.md: 1b66e84defb56cbfaa4a91d6ba6b48377fb52ca9 -README.zh.md: d9cd3ce1e109bf6b0b7fae02157d1ec6be51e575 +README.md: 9171989f968f144593107eb918fe75cd12de7768 +README.zh.md: 9f50bbe4c37bbbfb641690a690be45dbb5158258 diff --git a/packages/e2b/fs-e2b/README.md b/packages/e2b/fs-e2b/README.md index 1b66e84def..9171989f96 100644 --- a/packages/e2b/fs-e2b/README.md +++ b/packages/e2b/fs-e2b/README.md @@ -9,6 +9,7 @@ E2B implementation of the [`@deepseek-ai/dsh-fs`](../../fs/fs/README.md) provide - **Remote identity and metadata** — relative paths resolve as POSIX paths against the caller cwd or `ctx.e2b.cwd`; GNU `realpath -mz` supplies canonical target identity without requiring the final file to exist, and ASCII/base64 plus strict NUL framing preserves newline and multibyte paths across the decoded SDK transport. `stat`, no-follow `lstat`, and stable one-level directory listings project E2B metadata into the filesystem seam; listings reuse returned metadata and resolve symbolic-link entries sequentially. Versions are opaque hashes of E2B metadata plus a per-write extended attribute. - **Execution-world paths** — canonical targets expose absolute POSIX process paths, percent-encoded `file:` URIs, and provider-owned containment checks, so generic subprocess consumers never parse E2B target ids or apply host path rules. - **UTF-8 reads** — whole reads and streamed reads preserve cross-chunk decoding, reject invalid UTF-8, and use the seam's 8192-byte NUL sample for binary detection. The model-facing tool still owns size selection and line windowing. +- **Bounded raw-byte reads** — `readBytes` short-circuits on the stat size before any content transfer, then streams the remote object and cancels the stream at the first chunk past `maxBytes` (`FS_TOO_LARGE`), so neither an at-rest oversized file nor a post-stat grower is buffered whole in host memory. The empty-file quirk of the pinned SDK (content-length 0 returns `''` in stream format) yields an empty result. - **Atomic mutations** — writes create a random sibling staging directory, change it to mode `0700` before uploading content, and preserve an existing file's POSIX mode. Replacements publish through E2B's same-filesystem atomic rename. A guarded `createIfAbsent` publishes with remote `ln -T` instead, making the commit atomically no-replace even when a directory appears at the destination; metadata read from the staged file before that commit is projected to the target path for the returned version, so no fallible metadata request follows either commit point. E2B creates missing parent directories. Literal edits LF-normalize for matching, restore dominant CRLF storage, and serialize mutations per canonical target within the host process. - **Failures and cancellation** — E2B not-found, permission, abort, and other controller failures map to the existing `FsError` vocabulary. Cancellation is best-effort at earlier SDK request boundaries and checked immediately before publication. The signal is not forwarded into the rename or guarded-link commit, so cancellation cannot interrupt atomic publication or turn a committed write into a reported failure. diff --git a/packages/e2b/fs-e2b/README.zh.md b/packages/e2b/fs-e2b/README.zh.md index d9cd3ce1e1..9f50bbe4c3 100644 --- a/packages/e2b/fs-e2b/README.zh.md +++ b/packages/e2b/fs-e2b/README.zh.md @@ -9,6 +9,7 @@ - **远程身份与元数据**：相对路径以调用方 cwd 或 `ctx.e2b.cwd` 为基准，按照 POSIX 路径解析；GNU `realpath -mz` 提供规范化目标身份，且不要求最终文件存在；ASCII/base64 加严格 NUL 分帧会在已解码的 SDK 传输中保留含换行符和多字节字符的路径。`stat`、不跟随链接的 `lstat` 和稳定的单层目录列表会把 E2B 元数据投影到文件系统 seam；目录列表会复用已返回的元数据，并依次解析符号链接条目。版本是 E2B 元数据与每次写入设置的扩展属性所组成的不透明哈希。 - **执行世界路径**：规范化目标公开绝对 POSIX 进程路径、百分号编码的 `file:` URI，以及由提供方负责的包含关系检查，因此通用进程管理消费方无需解析 E2B 目标 ID，也不会套用宿主路径规则。 - **UTF-8 读取**：完整读取和流式读取会保留跨分片解码、拒绝无效 UTF-8，并使用 seam 的 8192 字节 NUL 样本检测二进制内容。面向模型的工具仍负责选择大小和行窗口。 +- **有界原始字节读取**：`readBytes` 在任何内容传输之前先按 stat 大小短路，然后流式读取远程对象，并在第一个超过 `maxBytes` 的分片处取消流（`FS_TOO_LARGE`），因此静态超限文件和 stat 后增长的文件都不会被完整缓冲进宿主内存。所钉版本 SDK 的空文件怪癖（content-length 为 0 时 stream 格式返回 `''`）产生空结果。 - **原子变更**：写入会创建随机的同级暂存目录，在上传内容前将其 mode 改为 `0700`，并保留现有文件的 POSIX mode。替换操作通过 E2B 的同一文件系统原子重命名发布。带防护的 `createIfAbsent` 改用远程 `ln -T` 发布，即使目标位置出现目录，也能使提交具备原子且不替换的语义；系统会把提交前从暂存文件读取的元数据投影到目标路径，以生成返回的版本，因此任何一类提交点之后都不会再进行可能失败的元数据请求。E2B 会创建缺失的父目录。字面量编辑匹配时会规范化为 LF，存储时恢复占主导的 CRLF，并在宿主进程内按规范化目标串行执行变更。 - **失败与取消**：E2B 的未找到、权限、中止及其他控制器故障会映射到现有 `FsError` 词汇。取消在更早的 SDK 请求边界上采用尽力而为语义，并在发布前立即检查。信号不会传入 rename 或防护链接提交，因此取消无法中断原子发布，也不会把已提交的写入报告为失败。 diff --git a/packages/e2b/fs-e2b/src/index.ts b/packages/e2b/fs-e2b/src/index.ts index b26338ffa4..f78a382495 100644 --- a/packages/e2b/fs-e2b/src/index.ts +++ b/packages/e2b/fs-e2b/src/index.ts @@ -90,6 +90,24 @@ function commandOpts(signal: AbortSignal | undefined): { envs: Record> { + try { + // The pinned SDK's stream overload lies for empty files: content-length 0 + // returns '' instead of a ReadableStream. + const read = await sandbox.files.read(String(target.targetKey), { format: 'stream', ...signalOpts(signal) }) as + ReadableStream | string + return typeof read === 'string' + ? new ReadableStream({ start(controller) { controller.close() } }) + : read + } catch (error: unknown) { + throw mapError(error, 'read', target.displayPath, signal) + } +} + function entryType(entry: EntryInfo): FsInfo['type'] { switch (entry.type) { case FileType.FILE: @@ -227,21 +245,57 @@ export class E2BFileSystem extends FileSystem { } } + override async readBytes(target: FsTarget, signal: AbortSignal | undefined, maxBytes: number): Promise { + const sandbox = await this.ctx.e2b.getSandbox() + const info = await this.requireRegular(target, signal) + if (info.size !== undefined && info.size > maxBytes) { + throw new FsError(`cannot read "${target.displayPath}": ${info.size} bytes exceeds the ${maxBytes}-byte limit`, 'FS_TOO_LARGE') + } + const stream = await openReadStream(sandbox, target, signal) + const reader = stream.getReader() + const chunks: Uint8Array[] = [] + let bytes = 0 + let completed = false + try { + while (true) { + assertNotAborted(signal, 'read') + const next = await reader.read() + if (next.done) break + // The stat preflight covers the at-rest case; this streamed bound stops + // a post-stat grower without transferring past the first overflowing chunk. + bytes += next.value.byteLength + if (bytes > maxBytes) { + throw new FsError(`cannot read "${target.displayPath}": content exceeds the ${maxBytes}-byte limit`, 'FS_TOO_LARGE') + } + chunks.push(next.value) + } + completed = true + } catch (error: unknown) { + throw mapError(error, 'read', target.displayPath, signal) + } finally { + if (!completed) { + try { + await reader.cancel() + } catch (_streamCancellationFailure) { + // The read already failed; a cancellation failure on the abandoned + // remote stream adds nothing actionable for the caller. + } + } + reader.releaseLock() + } + const whole = new Uint8Array(bytes) + let offset = 0 + for (const chunk of chunks) { + whole.set(chunk, offset) + offset += chunk.byteLength + } + return whole + } + override async streamText(target: FsTarget, signal?: AbortSignal): Promise> { const sandbox = await this.ctx.e2b.getSandbox() await this.requireRegular(target, signal) - let stream: ReadableStream - try { - // The pinned SDK's stream overload lies for empty files: content-length 0 - // returns '' instead of a ReadableStream. - const read = await sandbox.files.read(String(target.targetKey), { format: 'stream', ...signalOpts(signal) }) as - ReadableStream | string - stream = typeof read === 'string' - ? new ReadableStream({ start(controller) { controller.close() } }) - : read - } catch (error: unknown) { - throw mapError(error, 'read', target.displayPath, signal) - } + const stream = await openReadStream(sandbox, target, signal) const displayPath = target.displayPath return { async *[Symbol.asyncIterator](): AsyncGenerator { @@ -412,10 +466,11 @@ export class E2BFileSystem extends FileSystem { } } - private async requireRegular(target: FsTarget, signal?: AbortSignal): Promise { + private async requireRegular(target: FsTarget, signal?: AbortSignal): Promise { const info = await this.stat(target, signal) if (info === undefined) throw new FsError(`cannot read "${target.displayPath}": not found`, 'FS_NOT_FOUND') if (info.type !== 'file') throw new FsError(`cannot read "${target.displayPath}": not a regular file`, 'FS_NOT_REGULAR_FILE') + return info } private checkWriteIntent(existing: EntryInfo | undefined, expected: FsWriteIntent | undefined, target: FsTarget): void { diff --git a/packages/e2b/fs-e2b/tests/filesystem.spec.ts b/packages/e2b/fs-e2b/tests/filesystem.spec.ts index 5eed6007c4..7ac3d4a764 100644 --- a/packages/e2b/fs-e2b/tests/filesystem.spec.ts +++ b/packages/e2b/fs-e2b/tests/filesystem.spec.ts @@ -40,6 +40,7 @@ class FakeRemote { readonly links: Array<{ from: string; to: string }> = [] readonly removals: string[] = [] readonly commands: string[] = [] + readonly reads: Array<{ path: string; format: 'bytes' | 'stream' }> = [] streamChunks: Uint8Array[] | undefined streamKeepOpen = false readonly streamCancel = vi.fn() @@ -157,6 +158,7 @@ class FakeRemote { }, read: async (path: string, options: { format: 'bytes' | 'stream'; signal?: AbortSignal }): Promise | string> => { this.checkAbort(options) + this.reads.push({ path, format: options.format }) if (this.nextReadError !== undefined) { const error = this.nextReadError this.nextReadError = undefined @@ -471,6 +473,42 @@ describe('E2BFileSystem identity, metadata, and reads', () => { await expectCode(fs.streamText(raced), 'FS_NOT_FOUND') }) + it('readBytes returns raw content, enforces the byte cap, and maps failures', async () => { + const remote = new FakeRemote() + remote.file('/workspace/img.bin', [0x89, 0, 0xff, 0x47]) + remote.dir('/workspace/directory') + const { fs } = await setup(remote) + const target = await fs.resolve('img.bin') + expect(Array.from(await fs.readBytes(target, undefined, 4))).toEqual([0x89, 0, 0xff, 0x47]) + expect(remote.reads).toEqual([{ path: '/workspace/img.bin', format: 'stream' }]) + remote.reads.length = 0 + await expectCode(fs.readBytes(target, undefined, 3), 'FS_TOO_LARGE') + expect(remote.reads).toEqual([]) + await expectCode(fs.readBytes(await fs.resolve('missing'), undefined, 4), 'FS_NOT_FOUND') + await expectCode(fs.readBytes(await fs.resolve('directory'), undefined, 4), 'FS_NOT_REGULAR_FILE') + + const live = new AbortController() + expect((await fs.readBytes(target, live.signal, 4)).byteLength).toBe(4) + remote.nextReadError = new DOMException('aborted', 'AbortError') + await expectCode(fs.readBytes(target, undefined, 4), 'FS_ABORTED') + }) + + it('readBytes bounds a post-stat grower mid-stream and reads an empty file through the SDK quirk', async () => { + const remote = new FakeRemote() + remote.file('/workspace/grow.bin', [1, 1, 1, 1]) + remote.file('/workspace/empty.bin', '') + const { fs } = await setup(remote) + + remote.streamChunks = [bytes([1, 1, 1]), bytes([1, 2, 2])] + remote.streamKeepOpen = true + await expectCode(fs.readBytes(await fs.resolve('grow.bin'), undefined, 4), 'FS_TOO_LARGE') + expect(remote.streamCancel).toHaveBeenCalledOnce() + + remote.streamChunks = undefined + remote.streamKeepOpen = false + expect((await fs.readBytes(await fs.resolve('empty.bin'), undefined, 4)).byteLength).toBe(0) + }) + it('honors aborts before and during remote reads', async () => { const remote = new FakeRemote() remote.file('/workspace/a', 'a') diff --git a/packages/fs/fs-local/README.i18n.yaml b/packages/fs/fs-local/README.i18n.yaml index 149ee2be48..74f6042cf0 100644 --- a/packages/fs/fs-local/README.i18n.yaml +++ b/packages/fs/fs-local/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/fs/fs-local/README.md -README.md: a3239905e3eebaae7fa3099122ee3a4ed91d3fe8 -README.zh.md: bbd9d2f66c4e582011bd0ea459e6c342eb653bda +README.md: d17dc0747833a0ecb85505260badc79ad739f27f +README.zh.md: e13ab2f04b84b59fbb3846c08139e679b2d43be1 diff --git a/packages/fs/fs-local/README.md b/packages/fs/fs-local/README.md index a3239905e3..d17dc07478 100644 --- a/packages/fs/fs-local/README.md +++ b/packages/fs/fs-local/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -The **local-filesystem implementation** of the `ctx.fs` provider contract ([`@deepseek-ai/dsh-fs`](../fs)). Backs the eleven `FileSystem` primitives with the host filesystem; loading it as a plugin populates `ctx.fs`. +The **local-filesystem implementation** of the `ctx.fs` provider contract ([`@deepseek-ai/dsh-fs`](../fs)). Backs the twelve `FileSystem` primitives with the host filesystem; loading it as a plugin populates `ctx.fs`. ```ts ignore-check import { LocalFileSystem } from '@deepseek-ai/dsh-fs-local' @@ -18,6 +18,7 @@ await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) - **Execution-world coordinates** — `processPath` exposes the target's canonical host path, `fileUrl` encodes that path through Node's platform-aware URL conversion, and `contains` uses platform path semantics to test identity or descendant containment without consumers parsing `targetKey`. - **`stat` / `lstat`** — return target metadata or `undefined` when absent. `stat` reports `FsInfo` for an already resolved target (`version` = an opaque token derived from bigint `dev:ino:size:mtimeNs:ctimeNs`, `type` of `file`/`directory`/`other`, byte `size`); path-shaped `lstat` reports `FsPathInfo` without following the final symlink and can therefore return `symlink`. Both check cancellation before and after their asynchronous metadata probe, so an abort that lands in flight reports `FS_ABORTED` rather than stale absence. - **`readText` / `streamText`** — UTF-8 only. `readText` reads the whole file; `streamText` decodes chunks so a huge file need not be held whole in memory and consumers can enforce their own retention bounds. Both reject invalid UTF-8 and NUL-byte binary samples (`FS_NOT_TEXT`) and non-regular targets. The `read` tool (`@deepseek-ai/dsh-tool-fs`) owns line windowing. +- **`readBytes`** — raw whole-file bytes with no decoding or binary rejection (the `read_image` tool validates content through the attachment service). The required byte cap short-circuits on the stat size before any content I/O; the subsequent stream reads at most one byte beyond the cap, so a file growing after stat still fails `FS_TOO_LARGE` without unbounded buffering. - **`listDir`** — lists one directory level in stable `name.localeCompare()` order. Each entry carries the child basename, type, resolved child target (`displayPath` under the listed directory, `targetKey` as the realpath identity), and cheap stat metadata (`version`, plus `size` for regular files). It never opens or decodes file contents. Missing targets report `FS_NOT_FOUND`, file/special-file targets report `FS_NOT_DIRECTORY`, aborted calls report `FS_ABORTED`, permission failures report `FS_PERMISSION_DENIED`, and other listing or child metadata I/O failures report `FS_IO_ERROR`. Broken/disappeared children are returned as `other` without metadata, but permission/IO failures while resolving a child fail the whole listing with a structured `FsError`. - **`writeText`** — atomic: writes to a temp file opened exclusively (`wx`, `0o600`) inside a randomly-named private staging dir (`0o700`) next to the target, then fsyncs and publishes. An existing file's mode is preserved, while new files default to `0o600`; on Windows a new file inherits the destination directory's DACL, while replacement copies the target DACL onto the empty temp before writing and publishes through `ReplaceFileW` so the original access policy survives ([Windows DACL preservation Agent Note](../../../.agents/notes/implemented/bug-fix/2026-07-19-windows-atomic-write-dacl-preservation.md)). The `expected` guard is OPTIONAL: omitting it unconditionally creates-or-overwrites; `createIfAbsent` hard-links the staged file into place as an atomic no-replace publication, so a regular file created after the initial probe is preserved and rejected with `FS_NOT_OBSERVED`, while a non-regular path entry is preserved and rejected with `FS_NOT_REGULAR_FILE`; `replaceIfVersion` replaces only at the observed version (a missing target or mismatch is `FS_STALE_VERSION`). An overwrite returns the prior text as its contextual diff basis only when both the opened prior file and UTF-8 replacement are strictly below `config.diffBasisMaxBytes` (default 10 MiB). The descriptor read enforces that limit even if an external writer replaces or changes the file size after the initial probe. Otherwise the provider returns `before: null`, so presentation uses its whole-file fallback. - **`editText`** — atomic literal read-modify-write over the same primitive, serialized per target by a mutation lock. The `expected` guard is OPTIONAL: when supplied it verifies the version BEFORE literal matching (a stale edit reports `FS_STALE_VERSION`, never `FS_EDIT_NOT_FOUND`/`FS_AMBIGUOUS_EDIT` against newer content); omitting it edits the current content unconditionally. A missing target reports `FS_STALE_VERSION` either way. LF-normalizes for matching, restores the file's dominant CRLF/LF style, and rejects empty `oldString` / zero matches (`FS_EDIT_NOT_FOUND`) or ambiguous multi-matches without `replace_all` (`FS_AMBIGUOUS_EDIT`). diff --git a/packages/fs/fs-local/README.zh.md b/packages/fs/fs-local/README.zh.md index bbd9d2f66c..e13ab2f04b 100644 --- a/packages/fs/fs-local/README.zh.md +++ b/packages/fs/fs-local/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -`ctx.fs` 提供方约定（[`@deepseek-ai/dsh-fs`](../fs)）的**本地文件系统实现**。它使用宿主文件系统支持十一个 `FileSystem` 原语；将其作为插件加载会填充 `ctx.fs`。 +`ctx.fs` 提供方约定（[`@deepseek-ai/dsh-fs`](../fs)）的**本地文件系统实现**。它使用宿主文件系统支持十二个 `FileSystem` 原语；将其作为插件加载会填充 `ctx.fs`。 ```ts ignore-check import { LocalFileSystem } from '@deepseek-ai/dsh-fs-local' @@ -18,6 +18,7 @@ await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) - **执行世界坐标**：`processPath` 公开目标的规范化宿主路径，`fileUrl` 通过 Node 的平台感知 URL 转换对该路径编码，`contains` 则使用平台路径语义检查身份相等或后代包含关系，消费方无需解析 `targetKey`。 - **`stat` / `lstat`**：返回目标元数据；目标不存在时返回 `undefined`。`stat` 为已解析目标报告 `FsInfo`（`version` 是由 bigint `dev:ino:size:mtimeNs:ctimeNs` 派生的不透明 token，`type` 为 `file`/`directory`/`other`，`size` 以字节计）；路径形态的 `lstat` 不跟随最后一个符号链接，报告 `FsPathInfo`，因此可以返回 `symlink`。两者都会在异步元数据探测前后检查取消，因此飞行中的中止会报告 `FS_ABORTED`，而非陈旧的不存在结果。 - **`readText` / `streamText`**：只支持 UTF-8。`readText` 读取整个文件；`streamText` 按分片解码，因此超大文件无需整体保存在内存中，消费方也可以执行各自的保留上限。两者都会拒绝无效 UTF-8、包含 NUL 字节的二进制样本（`FS_NOT_TEXT`）以及非普通文件目标。`read` 工具（`@deepseek-ai/dsh-tool-fs`）拥有行窗口逻辑。 +- **`readBytes`**：按原始字节读取整个文件，不做解码或二进制拒绝（`read_image` 工具通过附件服务校验内容）。必填的字节上限在任何内容 I/O 之前先按 stat 大小短路；随后的流最多多读一个字节，因此 stat 之后增长的文件仍会以 `FS_TOO_LARGE` 失败，不会无界缓冲。 - **`listDir`**：按稳定的 `name.localeCompare()` 顺序列出一层目录。每个条目携带子项 basename、类型、解析后的子目标（`displayPath` 位于所列目录下，`targetKey` 是 realpath 身份）和低成本 stat 元数据（`version`，普通文件另有 `size`）。它绝不会打开或解码文件内容。缺失目标报告 `FS_NOT_FOUND`，文件/特殊文件目标报告 `FS_NOT_DIRECTORY`，已中止调用报告 `FS_ABORTED`，权限失败报告 `FS_PERMISSION_DENIED`，其他列出或子项元数据 I/O 失败报告 `FS_IO_ERROR`。损坏/消失的子项以无元数据的 `other` 返回，但解析子项时出现权限/I/O 失败会让整个列表以结构化 `FsError` 失败。 - **`writeText`**：原子写入。它会向排他打开的临时文件（`wx`、`0o600`）写入；该文件位于目标旁随机命名的私有暂存目录（`0o700`）内，随后执行 fsync 并发布。现有文件的 mode 会保留，新文件默认为 `0o600`；Windows 上的新文件继承目标目录的 DACL，而替换会在写入前把目标 DACL 复制到空临时文件，并通过 `ReplaceFileW` 发布，使原访问政策得以保留（见 [Windows DACL 保留 Agent Note](../../../.agents/notes/implemented/bug-fix/2026-07-19-windows-atomic-write-dacl-preservation.md)）。`expected` 防护是可选的：省略时无条件创建或覆盖；`createIfAbsent` 通过硬链接把暂存文件发布到目标位置，以实现原子且不替换的发布，因此初始探测后创建的普通文件会被保留，并以 `FS_NOT_OBSERVED` 拒绝本次写入；非普通路径条目也会被保留，并以 `FS_NOT_REGULAR_FILE` 拒绝；`replaceIfVersion` 只在观察到的版本上替换（目标缺失或版本不匹配均为 `FS_STALE_VERSION`）。仅当打开后的旧文件和 UTF-8 替换内容都严格低于 `config.diffBasisMaxBytes`（默认 10 MiB）时，覆写才返回旧文本作为上下文 diff 基础。即使外部写入方在初次探测后替换文件或改变文件大小，文件描述符读取仍会强制执行该上限；否则提供方返回 `before: null`，由展示层使用整文件回退。 - **`editText`**：在同一原语之上依次执行原子的字面量读取、修改和写入，并通过变更锁按目标串行化。`expected` 防护是可选的：提供时，会在字面量匹配之前校验版本（陈旧编辑报告 `FS_STALE_VERSION`，绝不会针对较新内容报告 `FS_EDIT_NOT_FOUND`/`FS_AMBIGUOUS_EDIT`）；省略时，无条件编辑当前内容。无论哪种情况，目标缺失都报告 `FS_STALE_VERSION`。匹配时规范化为 LF，随后恢复文件主要的 CRLF/LF 风格；空 `oldString` / 零匹配报告 `FS_EDIT_NOT_FOUND`，未设置 `replace_all` 的多个匹配则报告 `FS_AMBIGUOUS_EDIT`。 diff --git a/packages/fs/fs-local/src/fsio.ts b/packages/fs/fs-local/src/fsio.ts index 1ba027455d..17bfb6115b 100644 --- a/packages/fs/fs-local/src/fsio.ts +++ b/packages/fs/fs-local/src/fsio.ts @@ -98,6 +98,8 @@ export interface FsIoInternals { removeStagingDir?: (stagingDir: string) => Promise /** Test hook after the temp file is written/synced but before final chmod+publication. */ inspectTemp?: (paths: { stagingDir: string; tempPath: string }) => void | Promise + /** Test hook after raw-read stat preflight and before bounded content I/O. */ + inspectReadBytesAfterStat?: (target: LocalTarget) => void | Promise } /** A resolved local path: the absolute path shown to callers and its realpath identity. */ @@ -380,6 +382,50 @@ export async function readWholeText(target: LocalTarget, signal?: AbortSignal): return decodeUtf8(raw, 'read', target.displayPath) } +/** + * Read a whole regular file as raw bytes with no decoding or binary rejection. + * `maxBytes` bounds the complete content: the stat size short-circuits an + * oversized file before any content I/O, and the stream reads at most one byte + * beyond the cap so a file growing after stat cannot cause unbounded buffering. + * @param target - the resolved file to read. + * @param signal - aborts the read (`FS_ABORTED`). + * @param maxBytes - inclusive byte cap on the complete content (`FS_TOO_LARGE`). + * @param internals - test seam for a deterministic post-stat growth race. + * @returns the full raw content, at most `maxBytes` long. + */ +export async function readWholeBytes( + target: LocalTarget, + signal: AbortSignal | undefined, + maxBytes: number, + internals: FsIoInternals = {}, +): Promise { + const info = await statRegularFile(target, 'read', signal) + if (info.size > maxBytes) { + throw new FsError(`cannot read "${target.displayPath}": ${info.size} bytes exceeds the ${maxBytes}-byte limit`, 'FS_TOO_LARGE') + } + await internals.inspectReadBytesAfterStat?.(target) + const stream = createReadStream(target.targetKey, { + end: maxBytes, + ...signal ? { signal } : {}, + }) + const chunks: Buffer[] = [] + let bytes = 0 + try { + for await (const chunk of stream as AsyncIterable) { + bytes += chunk.length + if (bytes > maxBytes) { + throw new FsError(`cannot read "${target.displayPath}": content exceeds the ${maxBytes}-byte limit`, 'FS_TOO_LARGE') + } + chunks.push(chunk) + } + } catch (error: unknown) { + /* v8 ignore next 2 -- a mid-stream abort needs cancellation racing an active read; pre-abort is deterministic. */ + if (isAbortError(error)) throw new FsError('read aborted', 'FS_ABORTED') + throw error + } + return Buffer.concat(chunks, bytes) +} + /** * Stream a whole regular UTF-8 text file as decoded text chunks. Same text * semantics as {@link readWholeText} (regular-file check, binary/NUL rejection, diff --git a/packages/fs/fs-local/src/index.ts b/packages/fs/fs-local/src/index.ts index 5be06c3d1c..661ef236b8 100644 --- a/packages/fs/fs-local/src/index.ts +++ b/packages/fs/fs-local/src/index.ts @@ -28,6 +28,7 @@ import { probeNoFollow, readForEdit, readTextForDiff, + readWholeBytes, readWholeText, resolveLocalTarget, restoreLineEndings, @@ -147,6 +148,10 @@ export class LocalFileSystem extends FileSystem { return Promise.resolve(streamWholeText({ displayPath: target.displayPath, targetKey: target.targetKey }, signal)) } + override async readBytes(target: FsTarget, signal: AbortSignal | undefined, maxBytes: number): Promise { + return readWholeBytes({ displayPath: target.displayPath, targetKey: target.targetKey }, signal, maxBytes, this.internals) + } + override async listDir(target: FsTarget, signal?: AbortSignal): Promise { const entries = await listDirectory({ displayPath: target.displayPath, targetKey: target.targetKey }, signal) return entries.map(entry => ({ diff --git a/packages/fs/fs-local/tests/filesystem.spec.ts b/packages/fs/fs-local/tests/filesystem.spec.ts index 03bad054ec..bad67e6eb8 100644 --- a/packages/fs/fs-local/tests/filesystem.spec.ts +++ b/packages/fs/fs-local/tests/filesystem.spec.ts @@ -265,6 +265,43 @@ describe('readText / streamText', () => { }) }) +describe('readBytes', () => { + it('reads raw bytes without decoding or NUL rejection', async () => { + const raw = Buffer.from([0x68, 0x00, 0x69, 0xff]) + await writeFile(join(dir, 'a.bin'), raw) + expect(Buffer.from(await fs.readBytes(await fs.resolve('a.bin'), undefined, raw.length))).toEqual(raw) + }) + + it('accepts a file exactly at maxBytes and rejects one past it', async () => { + await writeFile(join(dir, 'a.bin'), Buffer.alloc(4, 1)) + const target = await fs.resolve('a.bin') + expect((await fs.readBytes(target, undefined, 4)).length).toBe(4) + await expect(fs.readBytes(target, undefined, 3)).rejects.toMatchObject({ code: 'FS_TOO_LARGE' }) + }) + + it('bounds content I/O when a file grows after stat preflight', async () => { + await writeFile(join(dir, 'a.bin'), Buffer.alloc(4, 1)) + const target = await fs.resolve('a.bin') + fs.internals.inspectReadBytesAfterStat = () => writeFile(join(dir, 'a.bin'), Buffer.alloc(1024 * 1024, 2)) + + await expect(fs.readBytes(target, undefined, 4)).rejects.toMatchObject({ code: 'FS_TOO_LARGE' }) + }) + + it('rejects a missing file and a directory', async () => { + await expect(fs.readBytes(await fs.resolve('nope'), undefined, 1024)).rejects.toMatchObject({ code: 'FS_NOT_FOUND' }) + await expect(fs.readBytes(await fs.resolve('.'), undefined, 1024)).rejects.toMatchObject({ code: 'FS_NOT_REGULAR_FILE' }) + }) + + it('reads under a live signal and rejects an already-aborted one with FS_ABORTED', async () => { + await writeFile(join(dir, 'a.bin'), 'data') + const live = new AbortController() + expect((await fs.readBytes(await fs.resolve('a.bin'), live.signal, 1024)).length).toBe(4) + const controller = new AbortController() + controller.abort() + await expect(fs.readBytes(await fs.resolve('a.bin'), controller.signal, 1024)).rejects.toMatchObject({ code: 'FS_ABORTED' }) + }) +}) + describe('listDir', () => { it('lists files and directories in stable name order with resolved child targets', async () => { await mkdir(join(dir, 'skills', 'dir-skill'), { recursive: true }) diff --git a/packages/fs/fs/README.i18n.yaml b/packages/fs/fs/README.i18n.yaml index c13921729a..c9ae290b78 100644 --- a/packages/fs/fs/README.i18n.yaml +++ b/packages/fs/fs/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/fs/fs/README.md -README.md: 62d3febde82e013ace054a9e6242147c1756b0d1 -README.zh.md: 137c1e8da1014bf7dda7c4bf2e667aca6d2f51b5 +README.md: d53fe69456622e533e5ba5a96bd9dab10c188eaa +README.zh.md: 64b7d79687a0b6a0d81a5037ea6044d4a406f32b diff --git a/packages/fs/fs/README.md b/packages/fs/fs/README.md index 62d3febde8..d53fe69456 100644 --- a/packages/fs/fs/README.md +++ b/packages/fs/fs/README.md @@ -2,7 +2,7 @@ English | [中文](README.zh.md) -The **`FileSystem`** (`ctx.fs`) defines the storage primitives in one execution world — resolve paths, expose canonical process paths and file URIs, test containment, read whole or streaming text, inspect/list metadata, write atomically, and apply a literal edit — without saying HOW. Both mutations take their version guard **optionally**, so `ctx.fs` on its own is a complete, unconstrained text-storage seam. This package also owns the `fs/*` policy event vocabulary the tool dispatches and the policy plugin listens for. +The **`FileSystem`** (`ctx.fs`) defines the storage primitives in one execution world — resolve paths, expose canonical process paths and file URIs, test containment, read whole or streaming text, read bounded raw bytes, inspect/list metadata, write atomically, and apply a literal edit — without saying HOW. Both mutations take their version guard **optionally**, so `ctx.fs` on its own is a complete, unconstrained storage seam. This package also owns the `fs/*` policy event vocabulary the tool dispatches and the policy plugin listens for. This package owns the Service Definition and provider contract layer of the four-layer filesystem stack, split so each concern can evolve (and be swapped) independently (see [the capability-seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md), [the filesystem capability-seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md), [the split-the-filesystem-seam Agent Note](../../../.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md), and [the file-context event-gate Agent Note](../../../.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md)): @@ -17,7 +17,7 @@ This package owns the Service Definition and provider contract layer of the four ## Service API (`ctx.fs`) -A backend subclasses `FileSystem` and implements eleven primitives. +A backend subclasses `FileSystem` and implements twelve primitives. | Member | Semantics | |---|---| @@ -29,6 +29,7 @@ A backend subclasses `FileSystem` and implements eleven primitives. | `lstat(path, opts?, signal?)` | Return `FsPathInfo` metadata without following the final path component when it is a symlink. This is path-shaped so consumers can reject repository-owned symlinks before `resolve` follows them into a target. | | `readText(target, signal?)` | Read the whole regular text file as one decoded string. Owns regular-file checks, UTF-8 decoding, binary/NUL rejection (`FS_NOT_TEXT`). | | `streamText(target, signal?)` | Stream the same text as decoded chunks for large files (cross-chunk UTF-8 decoding stays here); consumers that need a byte ceiling enforce it while consuming the stream. | +| `readBytes(target, signal, maxBytes)` | Read a complete regular file as raw bytes with no decoding or binary rejection. `maxBytes` is required and bounds the complete content at this seam: a known or discovered overflow fails with `FS_TOO_LARGE` instead of truncating or buffering without a bound. | | `listDir(target, signal?)` | List direct directory children in stable name order. Returns entry names, entry types, resolved child targets, and cheap metadata (`version`/file `size` when available); never reads file contents. Missing targets throw `FS_NOT_FOUND`, non-directories throw `FS_NOT_DIRECTORY`, permission failures throw `FS_PERMISSION_DENIED`, and other backend I/O failures throw `FS_IO_ERROR`. Broken/disappeared children may be returned as `other` without metadata; child permission/IO failures fail the whole listing with the same structured codes. | | `writeText(target, content, expected?, signal?)` | Atomic create/replace. `expected` is OPTIONAL: omit ⇒ unconditional create-or-overwrite; supply an `FsWriteIntent` (`createIfAbsent`/`replaceIfVersion`) to guard. `createIfAbsent` must perform a no-replace publication so a creator racing the initial probe is preserved. | | `editText(target, edit, expected?, signal?)` | Literal edit. `expected` is OPTIONAL: omit ⇒ unconditional edit of the current content; supply `{ version }` to guard (verified BEFORE matching). A missing target reports `FS_STALE_VERSION` either way. Applies and writes atomically — one mutation critical section. | @@ -47,7 +48,7 @@ This package declares three events (see the generated region of [filesystem.md]( ## Vocabulary -`FsTargetKey` / `FsVersion` are branded opaque ids ([the branded-ids Agent Note](../../../.agents/notes/implemented/architecture/2026-06-20-branded-ids.md)) — consumers must not parse `targetKey` or interpret `version`; only `displayPath` is for model/UI output. `FsObservation` distinguishes `{ kind: 'present', version }` from `{ kind: 'absent' }`, so a policy can separate an unseen target from confirmed absence without performing I/O. `FsWriteIntent` is the explicit GUARDED write intent (`createIfAbsent` creates a missing target and rejects an existing one with `FS_NOT_OBSERVED`; `replaceIfVersion` replaces only at the observed version, else `FS_STALE_VERSION`); omitting it from `writeText` is the third, unconditional state. `FsPathInfo` is the no-follow metadata shape that can report `symlink`, unlike target-level `FsInfo`. Failures throw `FsError` (extends `HarnessError`, [the structured error taxonomy Agent Note](../../../.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md)) carrying a stable `FsErrorCode` (`FS_NOT_FOUND`, `FS_NOT_DIRECTORY`, `FS_NOT_TEXT`, `FS_NOT_REGULAR_FILE`, `FS_PERMISSION_DENIED`, `FS_IO_ERROR`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, `FS_ABORTED`); the tool registry surfaces `{ name, code }` on `isError` results. See `src/types.ts` for the full contracts. +`FsTargetKey` / `FsVersion` are branded opaque ids ([the branded-ids Agent Note](../../../.agents/notes/implemented/architecture/2026-06-20-branded-ids.md)) — consumers must not parse `targetKey` or interpret `version`; only `displayPath` is for model/UI output. `FsObservation` distinguishes `{ kind: 'present', version }` from `{ kind: 'absent' }`, so a policy can separate an unseen target from confirmed absence without performing I/O. `FsWriteIntent` is the explicit GUARDED write intent (`createIfAbsent` creates a missing target and rejects an existing one with `FS_NOT_OBSERVED`; `replaceIfVersion` replaces only at the observed version, else `FS_STALE_VERSION`); omitting it from `writeText` is the third, unconditional state. `FsPathInfo` is the no-follow metadata shape that can report `symlink`, unlike target-level `FsInfo`. Failures throw `FsError` (extends `HarnessError`, [the structured error taxonomy Agent Note](../../../.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md)) carrying a stable `FsErrorCode` (`FS_NOT_FOUND`, `FS_NOT_DIRECTORY`, `FS_NOT_TEXT`, `FS_NOT_REGULAR_FILE`, `FS_TOO_LARGE`, `FS_PERMISSION_DENIED`, `FS_IO_ERROR`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, `FS_ABORTED`); the tool registry surfaces `{ name, code }` on `isError` results. See `src/types.ts` for the full contracts. ## Model Experience @@ -59,7 +60,7 @@ No direct invalidation; the named consumer owns any request-prefix changes. ## Known Limitations and Deferred Work -- **Text-only by contract** — backends reject binary/non-UTF-8 content with `FS_NOT_TEXT`; binary-safe operations are a deliberate deferral of [the tool-schemas Agent Note](../../../.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md). -- **Eleven primitives only** — no delete, rename/move, copy, or watch; `listDir` is single-level, with recursion, globbing, pagination, and search out of scope per [the directory-listing Agent Note](../../../.agents/notes/archived/architecture/2026-07-03-filesystem-directory-listing-seam.md). +- **Text-only mutations by contract** — text reads and both mutations reject binary/non-UTF-8 content with `FS_NOT_TEXT`; `readBytes` is the one raw-byte primitive, and binary-safe mutations remain a deliberate deferral of [the tool-schemas Agent Note](../../../.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md). +- **Twelve primitives only** — no delete, rename/move, copy, or watch; `listDir` is single-level, with recursion, globbing, pagination, and search out of scope per [the directory-listing Agent Note](../../../.agents/notes/archived/architecture/2026-07-03-filesystem-directory-listing-seam.md). - **No IO deadline** — the seam arms no timeout; cancellation is a best-effort optional `AbortSignal` per primitive (the deliberate [fs-family stance](../README.md)). - **Resolve-then-operate costs a remote backend two round-trips per tool call** — folding or caching resolution is left to such a backend. diff --git a/packages/fs/fs/README.zh.md b/packages/fs/fs/README.zh.md index 137c1e8da1..64b7d79687 100644 --- a/packages/fs/fs/README.zh.md +++ b/packages/fs/fs/README.zh.md @@ -2,7 +2,7 @@ [English](README.md) | 中文 -**`FileSystem`**（`ctx.fs`）定义同一个执行世界中的存储原语，包括解析路径、公开规范化进程路径与文件 URI、检查包含关系、完整或流式读取文本、检查／列出元数据、原子写入和应用字面量编辑，但不规定实现方式。两个变更操作都**可选** 接收版本防护，因此 `ctx.fs` 本身就是完整且不受约束的文本存储 seam。本包还拥有由工具分派、政策插件监听的 `fs/*` 政策事件词汇。 +**`FileSystem`**（`ctx.fs`）定义同一个执行世界中的存储原语，包括解析路径、公开规范化进程路径与文件 URI、检查包含关系、完整或流式读取文本、有界读取原始字节、检查／列出元数据、原子写入和应用字面量编辑，但不规定实现方式。两个变更操作都**可选** 接收版本防护，因此 `ctx.fs` 本身就是完整且不受约束的存储 seam。本包还拥有由工具分派、政策插件监听的 `fs/*` 政策事件词汇。 本包是四层文件系统栈中的提供方约定层；该拆分使每个关注点可以独立演进和替换（见[能力 seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-13-capability-seams.md)、[文件系统能力 seam Agent Note](../../../.agents/notes/implemented/architecture/2026-06-17-filesystem-capability-seam.md)、[拆分文件系统 seam Agent Note](../../../.agents/notes/implemented/simplification/2026-06-26-fsspec-style-fs-seam.md)和[文件上下文事件门禁 Agent Note](../../../.agents/notes/implemented/architecture/2026-06-26-file-context-as-event-gate.md)）： @@ -17,7 +17,7 @@ ## 服务 API（`ctx.fs`） -后端继承 `FileSystem` 并实现十一个原语。 +后端继承 `FileSystem` 并实现十二个原语。 | 成员 | 语义 | |---|---| @@ -29,6 +29,7 @@ | `lstat(path, opts?, signal?)` | 当最后一个路径组件是符号链接时，不跟随该组件，返回 `FsPathInfo` 元数据。该方法采用路径形态，使消费方能在 `resolve` 跟随仓库所有的符号链接进入目标前拒绝它。 | | `readText(target, signal?)` | 把整个普通文本文件读取为一个解码后的字符串。负责普通文件检查、UTF-8 解码和二进制/NUL 拒绝（`FS_NOT_TEXT`）。 | | `streamText(target, signal?)` | 为大文件按解码后的分片流式读取相同文本（跨分片 UTF-8 解码仍由此处负责）；需要字节上限的消费方在消费流时执行该上限。 | +| `readBytes(target, signal, maxBytes)` | 把完整普通文件按原始字节读出，不做解码或二进制拒绝。`maxBytes` 为必填，在该 seam 上限制完整内容：已知或读取中发现的超限以 `FS_TOO_LARGE` 失败，而不是截断或无界缓冲。 | | `listDir(target, signal?)` | 按稳定名称顺序列出直接子项。返回条目名称、条目类型、解析后的子目标和低成本元数据（若可用则包括 `version`/文件 `size`）；绝不读取文件内容。缺失目标抛出 `FS_NOT_FOUND`，非目录抛出 `FS_NOT_DIRECTORY`，权限失败抛出 `FS_PERMISSION_DENIED`，其他后端 I/O 失败抛出 `FS_IO_ERROR`。损坏/消失的子项可以作为无元数据的 `other` 返回；子项权限/I/O 失败会使用相同结构化代码使整个列表失败。 | | `writeText(target, content, expected?, signal?)` | 原子创建/替换。`expected` 是可选的：省略 ⇒ 无条件创建或覆盖；提供 `FsWriteIntent`（`createIfAbsent`/`replaceIfVersion`）⇒ 添加防护。`createIfAbsent` 必须以不替换的方式发布，使初始探测后抢先创建的文件得到保留。 | | `editText(target, edit, expected?, signal?)` | 字面量编辑。`expected` 是可选的：省略 ⇒ 无条件编辑当前内容；提供 `{ version }` ⇒ 添加防护，并在匹配之前校验。无论哪种情况，目标缺失都报告 `FS_STALE_VERSION`。应用和写入以原子方式完成，使用同一个变更临界区。 | @@ -47,7 +48,7 @@ ## 词汇 -`FsTargetKey` / `FsVersion` 是带品牌的不透明 id（见[品牌 id Agent Note](../../../.agents/notes/implemented/architecture/2026-06-20-branded-ids.md)）；消费方不得解析 `targetKey` 或解释 `version`，只有 `displayPath` 用于模型/UI 输出。`FsObservation` 区分 `{ kind: 'present', version }` 与 `{ kind: 'absent' }`，使策略无需执行 I/O 即可分辨未见目标和确认缺失。`FsWriteIntent` 是显式的防护写入意图（`createIfAbsent` 创建缺失目标，并以 `FS_NOT_OBSERVED` 拒绝现有目标；`replaceIfVersion` 只在观察版本上替换，否则为 `FS_STALE_VERSION`）；从 `writeText` 中省略该值就是第三种无条件状态。`FsPathInfo` 是可报告 `symlink` 的不跟随链接元数据形态，区别于目标级 `FsInfo`。失败会抛出 `FsError`（继承 `HarnessError`；见[结构化错误分类 Agent Note](../../../.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md)），并携带稳定的 `FsErrorCode`（`FS_NOT_FOUND`、`FS_NOT_DIRECTORY`、`FS_NOT_TEXT`、`FS_NOT_REGULAR_FILE`、`FS_PERMISSION_DENIED`、`FS_IO_ERROR`、`FS_STALE_VERSION`、`FS_NOT_OBSERVED`、`FS_AMBIGUOUS_EDIT`、`FS_EDIT_NOT_FOUND`、`FS_ABORTED`）；工具注册表公开 `{ name, code }`，并将其附在 `isError` 结果上。完整约定见 `src/types.ts`。 +`FsTargetKey` / `FsVersion` 是带品牌的不透明 id（见[品牌 id Agent Note](../../../.agents/notes/implemented/architecture/2026-06-20-branded-ids.md)）；消费方不得解析 `targetKey` 或解释 `version`，只有 `displayPath` 用于模型/UI 输出。`FsObservation` 区分 `{ kind: 'present', version }` 与 `{ kind: 'absent' }`，使策略无需执行 I/O 即可分辨未见目标和确认缺失。`FsWriteIntent` 是显式的防护写入意图（`createIfAbsent` 创建缺失目标，并以 `FS_NOT_OBSERVED` 拒绝现有目标；`replaceIfVersion` 只在观察版本上替换，否则为 `FS_STALE_VERSION`）；从 `writeText` 中省略该值就是第三种无条件状态。`FsPathInfo` 是可报告 `symlink` 的不跟随链接元数据形态，区别于目标级 `FsInfo`。失败会抛出 `FsError`（继承 `HarnessError`；见[结构化错误分类 Agent Note](../../../.agents/notes/implemented/architecture/2026-06-11-structured-error-taxonomy.md)），并携带稳定的 `FsErrorCode`（`FS_NOT_FOUND`、`FS_NOT_DIRECTORY`、`FS_NOT_TEXT`、`FS_NOT_REGULAR_FILE`、`FS_TOO_LARGE`、`FS_PERMISSION_DENIED`、`FS_IO_ERROR`、`FS_STALE_VERSION`、`FS_NOT_OBSERVED`、`FS_AMBIGUOUS_EDIT`、`FS_EDIT_NOT_FOUND`、`FS_ABORTED`）；工具注册表公开 `{ name, code }`，并将其附在 `isError` 结果上。完整约定见 `src/types.ts`。 ## 模型体验 @@ -59,7 +60,7 @@ ## 已知限制与延期工作 -- **约定只支持文本**：后端以 `FS_NOT_TEXT` 拒绝二进制/非 UTF-8 内容；二进制安全操作是[工具 schema Agent Note](../../../.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md)有意延期的工作。 -- **只有十一个原语**：没有删除、重命名/移动、复制或监视；`listDir` 只支持一层，递归、glob、分页和搜索不在范围内，见[目录列出 Agent Note](../../../.agents/notes/archived/architecture/2026-07-03-filesystem-directory-listing-seam.md)。 +- **变更操作约定只支持文本**：文本读取和两个变更操作都以 `FS_NOT_TEXT` 拒绝二进制/非 UTF-8 内容；`readBytes` 是唯一的原始字节原语，二进制安全的变更操作仍是[工具 schema Agent Note](../../../.agents/notes/implemented/feature/2026-06-17-filesystem-tool-schemas.md)有意延期的工作。 +- **只有十二个原语**：没有删除、重命名/移动、复制或监视；`listDir` 只支持一层，递归、glob、分页和搜索不在范围内，见[目录列出 Agent Note](../../../.agents/notes/archived/architecture/2026-07-03-filesystem-directory-listing-seam.md)。 - **没有 I/O deadline**：该 seam 不启动超时；取消只是每个原语上尽力而为的可选 `AbortSignal`（见有意采用的 [fs 能力族立场](../README.md)）。 - **先解析后操作使远程后端每次工具调用需要两次往返**：折叠或缓存解析由这种后端自行决定。 diff --git a/packages/fs/fs/src/index.ts b/packages/fs/fs/src/index.ts index 569342ab7e..bcd78cd23f 100644 --- a/packages/fs/fs/src/index.ts +++ b/packages/fs/fs/src/index.ts @@ -186,6 +186,18 @@ export abstract class FileSystem extends Service { */ abstract streamText(target: FsTarget, signal?: AbortSignal): Promise> + /** + * Read the whole regular file as raw bytes with no decoding or binary + * rejection. The bound lives at this seam so a backend can never buffer an + * unbounded file: a target known or discovered to exceed `maxBytes` fails + * with `FS_TOO_LARGE` instead of returning a truncated result. + * @param target - the resolved target to read. + * @param signal - aborts the read. + * @param maxBytes - inclusive byte cap on the complete content. + * @returns the full raw content, at most `maxBytes` long. + */ + abstract readBytes(target: FsTarget, signal: AbortSignal | undefined, maxBytes: number): Promise + /** * List direct children of a directory in stable name order. Returns resolved * child targets plus cheap metadata only; never reads file contents. diff --git a/packages/fs/fs/src/types.ts b/packages/fs/fs/src/types.ts index ddef6f117d..a96f4c1a67 100644 --- a/packages/fs/fs/src/types.ts +++ b/packages/fs/fs/src/types.ts @@ -177,6 +177,7 @@ export type FsErrorCode = | 'FS_NOT_DIRECTORY' | 'FS_NOT_TEXT' | 'FS_NOT_REGULAR_FILE' + | 'FS_TOO_LARGE' | 'FS_PERMISSION_DENIED' | 'FS_SANDBOX_DENIED' | 'FS_IO_ERROR' diff --git a/packages/fs/fs/tests/service.spec.ts b/packages/fs/fs/tests/service.spec.ts index 7260af2955..8b9d23f819 100644 --- a/packages/fs/fs/tests/service.spec.ts +++ b/packages/fs/fs/tests/service.spec.ts @@ -50,6 +50,13 @@ class FakeFileSystem extends FileSystem { const content = await this.readText(target) return (async function* () { yield content })() } + override async readBytes(target: FsTarget, _signal: AbortSignal | undefined, maxBytes: number): Promise { + const bytes = new TextEncoder().encode(await this.readText(target)) + if (bytes.length > maxBytes) { + throw new FsError(`too large: ${target.displayPath}`, 'FS_TOO_LARGE') + } + return bytes + } override async listDir(target: FsTarget): Promise { if (target.targetKey !== 'skills') throw new FsError(`not a directory: ${target.displayPath}`, 'FS_NOT_DIRECTORY') return [ @@ -112,6 +119,16 @@ describe('FileSystem provider seam', () => { expect(streamed).toBe(await fs.readText(target)) }) + it('readBytes returns raw content and enforces the byte cap with FS_TOO_LARGE', async () => { + const ctx = new Context() + await ctx.plugin(FakeFileSystem) + const fs = ctx.fs as FakeFileSystem + fs.files.set('a.bin', 'hi') + const target = await fs.resolve('a.bin') + expect(await fs.readBytes(target, undefined, 2)).toEqual(new TextEncoder().encode('hi')) + await expect(fs.readBytes(target, undefined, 1)).rejects.toMatchObject({ code: 'FS_TOO_LARGE' }) + }) + it('listDir returns child entry targets without reading file content', async () => { const ctx = new Context() await ctx.plugin(FakeFileSystem) diff --git a/packages/fs/tool-fs/README.i18n.yaml b/packages/fs/tool-fs/README.i18n.yaml index 96785be516..193fd1a627 100644 --- a/packages/fs/tool-fs/README.i18n.yaml +++ b/packages/fs/tool-fs/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/fs/tool-fs/README.md -README.md: 27b53aca50f470fe9ead4da27d87328264440ff7 -README.zh.md: 5bcf9c471d933702c46d50c56c9539cb9eede3ca +README.md: 7e334f886747cd8dc566a572c699cd80c7cf62fe +README.zh.md: b5eb5ae38aba049d77375d31d1509342a23f13fc diff --git a/packages/fs/tool-fs/README.md b/packages/fs/tool-fs/README.md index 27b53aca50..7e334f8867 100644 --- a/packages/fs/tool-fs/README.md +++ b/packages/fs/tool-fs/README.md @@ -2,17 +2,20 @@ English | [中文](README.zh.md) -The **model-facing filesystem tools** — `read`, `write`, `edit` — and their **executor**. This is the consumer layer of the filesystem stack: it owns tool names, JSON schemas, argument validation, prompt sections, **read windowing**, and result formatting. It reads/writes/edits through the `ctx.fs` provider contract ([`@deepseek-ai/dsh-fs`](../fs)) **directly**. The freshness/observation policy is contributed by a separate plugin ([`@deepseek-ai/dsh-fs-policy`](../fs-policy)) through the `fs/*` event gate; the tool is not method-coupled to it. Under a confining provider, the shared sandbox-policy service is required for per-session execution and the tool exposes escalation for filesystem mutations. +The **model-facing filesystem tools** — `read`, `read_image`, `write`, `edit` — and their **executor**. This is the consumer layer of the filesystem stack: it owns tool names, JSON schemas, argument validation, prompt sections, **read windowing**, and result formatting. It reads/writes/edits through the `ctx.fs` provider contract ([`@deepseek-ai/dsh-fs`](../fs)) **directly**. The freshness/observation policy is contributed by a separate plugin ([`@deepseek-ai/dsh-fs-policy`](../fs-policy)) through the `fs/*` event gate; the tool is not method-coupled to it. Under a confining provider, the shared sandbox-policy service is required for per-session execution and the tool exposes escalation for filesystem mutations. ```ts ignore-check // Default deployment: a ctx.fs provider, the policy plugin, then the tools. await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) // @deepseek-ai/dsh-fs-local await ctx.plugin(FsPolicy) // @deepseek-ai/dsh-fs-policy (policy gate) -await ctx.plugin(ToolFs) // this package — registers read/write/edit +await ctx.plugin(LocalAttachmentStore, { dshHome }) // optional — enables durable read_image results +await ctx.plugin(ToolFs) // this package — read/write/edit, plus read_image with attachments ``` `@deepseek-ai/dsh-fs-policy` is **optional**: omit it and the tools run against the bare provider (unconditional write/overwrite/edit, no observed-state). A deployment that loads these tools is expected to also load it, so the behavior is read-before-write/edit. +`read_image` registers only while a durable `ctx.attachments` service is mounted — without one the deployment cannot commit image bytes, so the tool never appears. Execution additionally requires the exact routed model to declare `image` input (resolved through `ctx.llm.resolveModelInfo` from the session's latest request header, falling back to agent options); an unknown or text-only route gets a refusal result before any filesystem I/O, so a text route's durable history stays free of image blocks. + ## Config All keys are optional; the defaults are the shipped read caps. @@ -29,18 +32,20 @@ All keys are optional; the defaults are the shipped read caps. | Tool | Arguments | Behavior | |---|---|---| | `read` | `file_path`, `offset?`, `limit?` | Line-numbered UTF-8 content with a pagination footer. `offset` is 1-based; `limit` defaults to and caps at the configured `readLimit` (2000). | +| `read_image` | `file_path` | Reads a PNG/JPEG/WebP/GIF file through the bounded byte seam, persists it through `ctx.attachments.saveImage`, and returns an image block beside a small metadata envelope. It succeeds only when the exact routed model declares image input. | | `write` | `file_path`, `content` | Create or fully replace a file. With the policy plugin: overwriting an existing file requires a prior `read` at the unchanged version; creating a new file does not. Without it: unconditional. | | `edit` | `file_path`, non-empty `old_string`, `new_string`, `replace_all?` | Literal replacement; unique match required unless `replace_all` is true. With the policy plugin: requires a prior `read` (any window) and the file unchanged since. Without it: unconditional. | Field names are snake_case to match Claude Code and existing harness tool schemas. -Canonical successes are `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. Native renderers preserve the line-numbered read and mutation acknowledgements below. `write`/`edit` derive replayable diff-card metadata, and `read` derives a replayable read-card window `{ path, offset, lines, totalLines, lang? }`, from these canonical values; the canonical values themselves are execution-local and are not added to `tool/result`, only the derived presentation metadata is persisted. +Canonical successes are `read` → `{ path, offset, lines: [{ number, text }], totalLines }`, `read_image` → `{ path, image: { attachmentId, mediaType, bytes, width, height, name? } }`, `write` → `{ path, operation: 'create' | 'update', before: string | null, after }`, and `edit` → `{ path, before, after }`. Native renderers preserve the line-numbered read and mutation acknowledgements below. `write`/`edit` derive replayable diff-card metadata, and `read` derives a replayable read-card window `{ path, offset, lines, totalLines, lang? }`, from these canonical values; the canonical values themselves are execution-local and are not added to `tool/result`, only the derived presentation metadata is persisted. ## The tool is the executor; policy is an event gate The tools do **not** inject a policy service or inspect any cache. Each tool resolves the path via `ctx.fs.resolve(path, { cwd, signal })` — passing the calling agent's session cwd (`exec.agent.session.header.cwd`) so a relative path resolves against the session's workspace, matching `dsh-tool-bash`, and forwarding tool cancellation through resolution (see [the per-session cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)) — then: - **read** — one `ctx.fs.stat` (type + size routing + version), then `readText`/`streamText`, then builds the line window, then emits `fs/observed` with a plain `ctx.emit`. (1 stat.) +- **read_image** — validates the argument, extension, attachment availability, deployment media types, and the image-capable route before any I/O; then one `ctx.fs.stat` (recording an `absent` observation for a missing target, like `read`), a bounded `ctx.fs.readBytes` capped at the smaller of `imageLimits.maxImageBytes` and `imageLimits.maxMessageImageBytes` (the result is one message carrying one image), `attachments.saveImage` (content-addressed, so the image block references a durably committed object by the time `tool/result` is appended), and finally `fs/observed`. (1 stat.) - **write** — `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` for the optional guard, then `ctx.fs.writeText(target, content, intent)`, then `fs/observed`. (0 stat.) - **edit** — `ctx.waterfall('fs/edit-intent', target, exec, () => undefined)` for the optional guard, then `ctx.fs.editText(target, edit, intent)`, then `fs/observed`. (0 stat.) @@ -50,11 +55,11 @@ When `ctx.fs.sandboxMode` reports confinement, write/edit advertise `sandbox_per ## `fs/observed` is fire-and-forget -`fs/observed` fires AFTER the read/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event. +`fs/observed` fires AFTER the read/read_image/write/edit already succeeded, via a plain `ctx.emit`. A listener is contractually a synchronous, side-effect-only recorder (`@deepseek-ai/dsh-fs-policy`'s is a `WeakMap.set`); the tool does not guard the emit, so a listener that throws would surface as the tool's `isError` result — async or fallible observation does not belong on this event. `read` opts into concurrent scheduling because its only mutation is the synchronous version recorder. Recorder races fail closed when a later `write` or `edit` re-checks the version under its target lock; both mutation tools remain exclusive. See the [parallel tool-call Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md). -The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. +The package root exports only the Cordis plugin contract (`name`, `inject`, `Config`, and `apply`). Read rendering (line windowing + output formatting) lives in `src/read-render.ts` (Cordis-free, independently unit-tested); `src/read.ts`/`read-image.ts`/`write.ts`/`edit.ts` are the tool executors and `src/index.ts` composes them. ## Model Experience @@ -94,7 +99,7 @@ Prefix-stable while the plugin scope and guidance text are unchanged. Tool restr #### What the model sees -The model sees the generated [`read`, `write`, and `edit` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs), with snake_case arguments. Scoped tool restrictions can remove any definition for one agent. +The model sees the generated [`read`, `read_image`, `write`, and `edit` schemas](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs), with snake_case arguments. `read_image` appears only while a durable attachment store is mounted; the schema itself is route-independent, and the strict gate refuses at execution. Scoped tool restrictions can remove any definition for one agent. #### Token effect @@ -118,6 +123,20 @@ Read output is capped by `readLimit`, `readMaxLineLength`, and `readMaxBytes`; t Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. +### Image read result + +#### What the model sees + +A successful `read_image` returns ``, `image`, and a `` envelope naming the media type, dimensions, and byte size, followed by the image itself as a native image block. The session log stores only the durable `sha256:` attachment reference; the routed provider re-reads and digest-verifies the bytes on each request. + +#### Token effect + +The image is billed on every later request until compaction. Each call is independently bounded by the attachment store's `maxImageBytes`/`maxImagePixels`; repeated successful calls accumulate history, and content addressing deduplicates only the stored bytes, not the per-request token cost. + +#### KV Cache effect + +Append-only; newly visible content follows the reusable request prefix and does not invalidate existing KV-cache entries. + ### Write and edit results #### What the model sees @@ -136,7 +155,7 @@ Append-only; newly visible content follows the reusable request prefix and does #### What the model sees -Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, and `offset is out of range for "" ( lines)`; provider and policy templates are quoted in their package READMEs. Guarded-mutation failures additionally carry their recovery instruction in the message, appended by this package's model-facing error wrapper: `FS_STALE_VERSION` gets `— re-read the file, then retry`, and `FS_NOT_OBSERVED` gets `— read the file, then retry`; the structured code is preserved. After that reread confirms absence, edit reports `FS_NOT_FOUND` instead of repeating a stale remedy, while write uses guarded creation. +Failures are normalized as `Error: `. This package's stable validation and read messages are `file_path must be a non-empty string`, `limit must be less than or equal to `, `old_string must be a non-empty string`, `old_string and new_string must differ`, `cannot read "": not found`, `cannot read "": not a regular file`, `offset is out of range for "" ( lines)`, `cannot read "": read_image only accepts PNG/JPEG/WebP/GIF paths`, `cannot read "" as an image: model "" does not declare image input; switch to an image-capable model to read images`, and the mismatch repair `cannot read "": the extension declares , but the bytes use a different image format; rename the file to match its actual format if it is PNG/JPEG/WebP/GIF, or convert it to one of those formats`; provider and policy templates are quoted in their package READMEs. Guarded-mutation failures additionally carry their recovery instruction in the message, appended by this package's model-facing error wrapper: `FS_STALE_VERSION` gets `— re-read the file, then retry`, and `FS_NOT_OBSERVED` gets `— read the file, then retry`; the structured code is preserved. After that reread confirms absence, edit reports `FS_NOT_FOUND` instead of repeating a stale remedy, while write uses guarded creation. #### Token effect @@ -149,5 +168,8 @@ Append-only; newly visible content follows the reusable request prefix and does ## Known Limitations and Deferred Work - **No model-facing directory listing ships** — `ctx.fs.listDir` serves provider code such as skill discovery, while the sibling [`dsh-tool-fs-search`](../tool-fs-search/) package supplies ripgrep-backed `glob` and `grep` rather than extending the filesystem seam. -- **`read` handles UTF-8 text files only** — binary-safe reads and PDF/image/multimodal content are deferred; a directory target is `FS_NOT_REGULAR_FILE`. +- **`read` handles UTF-8 text files only** — images use the separate extension-routed `read_image` tool; PDF, audio, and video remain deferred. A directory target is `FS_NOT_REGULAR_FILE`. +- **The route gate races a concurrent model switch** — `read_image` checks the latest routed model at execution; a switch committed between that check and the next request can leave an image block on a route that rejects image content. The Web host already refuses switching an image-bearing session to a text-only model; other front doors own their equivalent guard. +- **Extension-declared media type** — the extension selects the declared type and the attachment store's magic-byte validation stays authoritative; a correctly formatted image under a wrong extension is refused with the rename remedy rather than sniffed. +- **No inline image preview on the tool-result card** — UI surfaces render the image result generically (the durable reference, not pixels); inline rendering is deferred to the UI packages. - **No timeout surface** — `read`/`write`/`edit` take no timeout argument and declare no `timeout-policy` budget; cancellation rides `exec.signal` only ([provider rationale](../README.md#no-timeouts-on-file-io)). diff --git a/packages/fs/tool-fs/README.zh.md b/packages/fs/tool-fs/README.zh.md index 5bcf9c471d..b5eb5ae38a 100644 --- a/packages/fs/tool-fs/README.zh.md +++ b/packages/fs/tool-fs/README.zh.md @@ -2,17 +2,20 @@ [English](README.md) | 中文 -**面向模型的文件系统工具**（`read`、`write`、`edit`）及其**执行器**。这是文件系统栈的消费方层：拥有工具名称、JSON Schema、参数校验、提示词段、**读取窗口逻辑**和结果格式化。它**直接**通过 `ctx.fs` 提供方约定（[`@deepseek-ai/dsh-fs`](../fs)）读取／写入／编辑。新鲜度／观察策略由独立插件（[`@deepseek-ai/dsh-fs-policy`](../fs-policy)）通过 `fs/*` 事件门禁贡献；工具不与其方法耦合。使用施加沙箱限制的提供方时，逐会话执行需要共享沙箱策略服务，工具还会为文件系统变更提供升权路径。 +**面向模型的文件系统工具**（`read`、`read_image`、`write`、`edit`）及其**执行器**。这是文件系统栈的消费方层：拥有工具名称、JSON Schema、参数校验、提示词段、**读取窗口逻辑**和结果格式化。它**直接**通过 `ctx.fs` 提供方约定（[`@deepseek-ai/dsh-fs`](../fs)）读取／写入／编辑。新鲜度／观察策略由独立插件（[`@deepseek-ai/dsh-fs-policy`](../fs-policy)）通过 `fs/*` 事件门禁贡献；工具不与其方法耦合。使用施加沙箱限制的提供方时，逐会话执行需要共享沙箱策略服务，工具还会为文件系统变更提供升权路径。 ```ts ignore-check // Default deployment: a ctx.fs provider, the policy plugin, then the tools. await ctx.plugin(LocalFileSystem, { cwd: process.cwd() }) // @deepseek-ai/dsh-fs-local await ctx.plugin(FsPolicy) // @deepseek-ai/dsh-fs-policy (policy gate) -await ctx.plugin(ToolFs) // this package — registers read/write/edit +await ctx.plugin(LocalAttachmentStore, { dshHome }) // optional — enables durable read_image results +await ctx.plugin(ToolFs) // this package — read/write/edit, plus read_image with attachments ``` `@deepseek-ai/dsh-fs-policy` 是**可选的**：省略时，工具直接使用裸提供方（无条件写入/覆盖/编辑，无已观察状态）。加载这些工具的部署也应加载该插件，从而提供写入/编辑前读取行为。 +`read_image` 只在持久 `ctx.attachments` 服务已挂载时注册：没有它，部署无法持久提交图像字节，工具就不会出现。执行时还要求确切路由的模型声明 `image` 输入（通过 `ctx.llm.resolveModelInfo` 从会话最新请求 header 解析，缺失时回退到 agent 选项）；未知或纯文本路由在任何文件系统 I/O 之前就得到拒绝结果，因此文本路由的持久历史不会出现图像块。 + ## 配置 所有键均为可选；默认值是随产品交付的读取上限。 @@ -29,18 +32,20 @@ await ctx.plugin(ToolFs) // this package — re | 工具 | 参数 | 行为 | |---|---|---| | `read` | `file_path`、`offset?`、`limit?` | 带行号的 UTF-8 内容和分页 footer。`offset` 从 1 开始；`limit` 默认为配置的 `readLimit`（2000），上限也为该值。 | +| `read_image` | `file_path` | 通过有界字节 seam 读取 PNG/JPEG/WebP/GIF 文件，经 `ctx.attachments.saveImage` 持久保存，并在小型元数据信封旁返回图像块。只有确切路由的模型声明图像输入时才会成功。 | | `write` | `file_path`、`content` | 创建文件或完整替换文件。有策略插件时：覆盖现有文件要求先在未变版本上执行 `read`；创建新文件不需要。没有插件时：无条件执行。 | | `edit` | `file_path`、非空 `old_string`、`new_string`、`replace_all?` | 字面量替换；除非 `replace_all` 为 true，否则要求唯一匹配。有策略插件时：要求先执行 `read`（任何窗口），且文件此后未变。没有插件时：无条件执行。 | 字段名使用 snake_case，与 Claude Code 和现有 harness 工具 schema 一致。 -规范成功值分别为：`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。原生渲染器会保留下方带行号的读取结果和变更确认。`write`/`edit` 从这些规范值派生可回放的 diff 卡片元数据，`read` 派生可回放的读取卡片窗口 `{ path, offset, lines, totalLines, lang? }`；规范值本身仅限于本次执行，不会添加到 `tool/result`，只有派生出的呈现元数据会被持久化。 +规范成功值分别为：`read` → `{ path, offset, lines: [{ number, text }], totalLines }`，`read_image` → `{ path, image: { attachmentId, mediaType, bytes, width, height, name? } }`，`write` → `{ path, operation: 'create' | 'update', before: string | null, after }`，`edit` → `{ path, before, after }`。原生渲染器会保留下方带行号的读取结果和变更确认。`write`/`edit` 从这些规范值派生可回放的 diff 卡片元数据，`read` 派生可回放的读取卡片窗口 `{ path, offset, lines, totalLines, lang? }`；规范值本身仅限于本次执行，不会添加到 `tool/result`，只有派生出的呈现元数据会被持久化。 ## 工具就是执行器；策略是事件门禁 工具**不**注入策略服务，也不检查任何缓存。每个工具通过 `ctx.fs.resolve(path, { cwd, signal })` 解析路径；它会传入调用 agent（智能体）的会话 cwd（`exec.agent.session.header.cwd`），使相对路径以会话工作区为基准解析并与 `dsh-tool-bash` 一致，同时把工具取消转发到解析过程（见[每会话 cwd Agent Note](../../../.agents/notes/implemented/architecture/2026-07-02-fs-per-session-cwd.md)）。随后执行： - **read**：一次 `ctx.fs.stat`（用于类型、大小路由和版本），随后调用 `readText`/`streamText`，构建行窗口，再发出 `fs/observed`，使用普通 `ctx.emit`。（1 次 stat。） +- **read_image**：在任何 I/O 之前校验参数、扩展名、附件可用性、部署接受的媒体类型和图像路由；随后一次 `ctx.fs.stat`（目标缺失时与 `read` 一样记录 `absent` 观察）、以 `imageLimits.maxImageBytes` 与 `imageLimits.maxMessageImageBytes` 中较小者为上限的有界 `ctx.fs.readBytes`（结果是携带一张图像的一条消息）、`attachments.saveImage`（内容寻址，因此在 `tool/result` 事件追加时图像块引用的对象已持久提交），最后发出 `fs/observed`。（1 次 stat。） - **write**：调用 `ctx.waterfall('fs/write-intent', target, exec, () => undefined)` 取得可选防护，然后调用 `ctx.fs.writeText(target, content, intent)`，再发出 `fs/observed`。（0 次 stat。） - **edit**：调用 `ctx.waterfall('fs/edit-intent', target, exec, () => undefined)` 取得可选防护，然后调用 `ctx.fs.editText(target, edit, intent)`，再发出 `fs/observed`。（0 次 stat。） @@ -50,11 +55,11 @@ await ctx.plugin(ToolFs) // this package — re ## `fs/observed` 发后即忘 -`fs/observed` 在读取/写入/编辑已经成功之后，通过普通 `ctx.emit` 发出。监听器的约定是同步且只有副作用的记录器（`@deepseek-ai/dsh-fs-policy` 使用 `WeakMap.set`）；工具不保护这次发出，因此监听器抛出会作为工具的 `isError` 结果出现。异步或可能失败的观察不属于该事件。 +`fs/observed` 在 read/read_image/write/edit 已经成功之后，通过普通 `ctx.emit` 发出。监听器的约定是同步且只有副作用的记录器（`@deepseek-ai/dsh-fs-policy` 使用 `WeakMap.set`）；工具不保护这次发出，因此监听器抛出会作为工具的 `isError` 结果出现。异步或可能失败的观察不属于该事件。 `read` 允许并发调度，因为其唯一变更是同步版本记录器。稍后的 `write` 或 `edit` 会在目标锁内重新检查版本，因此记录器竞态会以拒绝方式关闭；两个变更工具仍保持互斥。见[并行工具调用 Agent Note](../../../.agents/notes/implemented/feature/2026-07-10-parallel-tool-call-execution.md)。 -包根目录只导出 Cordis 插件约定（`name`、`inject`、`Config` 和 `apply`）。读取渲染（行窗口与输出格式化）位于 `src/read-render.ts`（不依赖 Cordis，单独进行单元测试）；`src/read.ts`/`write.ts`/`edit.ts` 是工具执行器，`src/index.ts` 负责组合。 +包根目录只导出 Cordis 插件约定（`name`、`inject`、`Config` 和 `apply`）。读取渲染（行窗口与输出格式化）位于 `src/read-render.ts`（不依赖 Cordis，单独进行单元测试）；`src/read.ts`/`read-image.ts`/`write.ts`/`edit.ts` 是工具执行器，`src/index.ts` 负责组合。 ## 模型体验 @@ -94,7 +99,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -模型会看到已生成的 [`read`、`write` 和 `edit` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs)，参数使用 snake_case。作用域工具限制可以为某个 agent 移除任一定义。 +模型会看到已生成的 [`read`、`read_image`、`write` 和 `edit` schema](../../../docs/tool-catalog.md#deepseek-aidsh-tool-fs)，参数使用 snake_case。`read_image` 只在持久附件存储已挂载时出现；schema 本身与路由无关，严格门禁在执行时拒绝。作用域工具限制可以为某个 agent 移除任一定义。 #### Token 影响 @@ -118,6 +123,20 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces 仅追加；新增可见内容位于可复用请求前缀之后，不会使现有 KV Cache 条目失效。 +### 图像读取结果 + +#### 模型看到的内容 + +成功的 `read_image` 返回 ``、`image` 和写明媒体类型、尺寸与字节数的 `` 信封，随后是作为原生图像块的图像本身。会话日志只存储持久的 `sha256:` 附件引用；路由到的提供方在每次请求时重新读取并校验字节摘要。 + +#### Token 影响 + +图像在之后每次请求中都会计费，直到压缩。每次调用都独立受附件存储的 `maxImageBytes`/`maxImagePixels` 约束；重复成功调用会在历史中累积，内容寻址只去重存储的字节，不去重每次请求的 token 成本。 + +#### KV Cache 影响 + +仅追加；新可见内容跟在可复用请求前缀之后，不会使既有 KV 缓存条目失效。 + ### 写入与编辑结果 #### 模型看到的内容 @@ -136,7 +155,7 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces #### 模型看到的内容 -失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file` 和 `offset is out of range for "" ( lines)`；提供方和策略模板在各自包的 README 中逐字列出。防护变更失败还会在消息中携带恢复指令，由本包面向模型的错误包装追加：`FS_STALE_VERSION` 追加 `— re-read the file, then retry`，`FS_NOT_OBSERVED` 追加 `— read the file, then retry`；结构化错误码保持不变。该次重新读取确认缺失后，edit 会报告 `FS_NOT_FOUND`，而不会重复陈旧恢复指令；write 则使用带防护的创建。 +失败会规范化为 `Error: `。本包稳定的校验和读取消息是 `file_path must be a non-empty string`、`limit must be less than or equal to `、`old_string must be a non-empty string`、`old_string and new_string must differ`、`cannot read "": not found`、`cannot read "": not a regular file`、`offset is out of range for "" ( lines)`、`cannot read "": read_image only accepts PNG/JPEG/WebP/GIF paths`、`cannot read "" as an image: model "" does not declare image input; switch to an image-capable model to read images`，以及类型不匹配的修复消息 `cannot read "": the extension declares , but the bytes use a different image format; rename the file to match its actual format if it is PNG/JPEG/WebP/GIF, or convert it to one of those formats`；提供方和策略模板在各自包的 README 中逐字列出。防护变更失败还会在消息中携带恢复指令，由本包面向模型的错误包装追加：`FS_STALE_VERSION` 追加 `— re-read the file, then retry`，`FS_NOT_OBSERVED` 追加 `— read the file, then retry`；结构化错误码保持不变。该次重新读取确认缺失后，edit 会报告 `FS_NOT_FOUND`，而不会重复陈旧恢复指令；write 则使用带防护的创建。 #### Token 影响 @@ -149,5 +168,8 @@ Use the edit tool for targeted changes to existing UTF-8 text files. It replaces ## 已知限制与暂缓事项 - **未交付面向模型的目录列表工具**：`ctx.fs.listDir` 服务于 skill（技能）发现等提供方代码，同级 [`dsh-tool-fs-search`](../tool-fs-search/) 包则提供基于 ripgrep 的 `glob` 与 `grep`，而不是扩展文件系统 seam。 -- **`read` 只处理 UTF-8 文本文件**：二进制安全读取和 PDF/图像/多模态内容均延期处理；目录目标为 `FS_NOT_REGULAR_FILE`。 +- **`read` 只处理 UTF-8 文本文件**：图像使用独立的、按扩展名路由的 `read_image` 工具；PDF、音频和视频仍延期处理。目录目标为 `FS_NOT_REGULAR_FILE`。 +- **路由门禁与并发模型切换存在竞态**：`read_image` 在执行时检查最新路由的模型；在该检查与下一次请求之间提交的切换，可能让图像块落在拒绝图像内容的路由上。Web 宿主已拒绝把含图像的会话切到纯文本模型；其他前端拥有各自的等价防护。 +- **媒体类型按扩展名声明**：扩展名选择声明类型，附件存储的魔数校验保持权威；扩展名错误但格式正确的图像会得到改名修复提示，而不是被嗅探接受。 +- **工具结果卡片没有内嵌图像预览**：UI 表面以通用形式渲染图像结果（持久引用而非像素）；内嵌渲染延后到 UI 包处理。 - **没有超时接口**：`read`/`write`/`edit` 不接受超时参数，也不声明 `timeout-policy` 预算；取消只通过 `exec.signal` 传递（见[提供方理由](../README.md#no-timeouts-on-file-io)）。 diff --git a/packages/fs/tool-fs/package.json b/packages/fs/tool-fs/package.json index 65ed3dcb1a..65db543d26 100644 --- a/packages/fs/tool-fs/package.json +++ b/packages/fs/tool-fs/package.json @@ -36,6 +36,7 @@ "@deepseek-ai/schemastery": "workspace:^" }, "peerDependencies": { + "@deepseek-ai/dsh-attachment": "workspace:^", "@deepseek-ai/dsh-fs": "workspace:^", "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", @@ -51,6 +52,7 @@ "@deepseek-ai/dsh-agent": "workspace:^", "@deepseek-ai/dsh-agent-loop": "workspace:^", "@deepseek-ai/dsh-agent-loop-testkit": "workspace:^", + "@deepseek-ai/dsh-attachment": "workspace:^", "@deepseek-ai/dsh-fs": "workspace:^", "@deepseek-ai/dsh-fs-local": "workspace:^", "@deepseek-ai/dsh-fs-policy": "workspace:^", diff --git a/packages/fs/tool-fs/src/index.ts b/packages/fs/tool-fs/src/index.ts index c6a311f686..6255a5d3c1 100644 --- a/packages/fs/tool-fs/src/index.ts +++ b/packages/fs/tool-fs/src/index.ts @@ -1,5 +1,5 @@ /** - * Model-facing read, write, and edit tools over `ctx.fs`. This package owns schemas, validation, + * Model-facing read, read_image, write, and edit tools over `ctx.fs`. This package owns schemas, validation, * read windows, formatting, and observation events, never a concrete provider. An optional * event policy supplies mutation guards; without one the tools use unconditional provider calls. * @module @deepseek-ai/dsh-tool-fs @@ -11,6 +11,7 @@ import type {} from '@deepseek-ai/dsh-user-approval' import { applyReadTool, READ_LIMIT, STREAM_MIN_SIZE } from './read.ts' import { applyWriteTool } from './write.ts' import { applyEditTool } from './edit.ts' +import { applyReadImageTool } from './read-image.ts' import { READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from './read-render.ts' import { FsSandboxSurface } from './sandbox.ts' @@ -49,7 +50,7 @@ function assertPositiveInteger(name: string, value: number): void { } } -/** Register the full `read`/`write`/`edit` filesystem tool suite. */ +/** Register the full `read`/`write`/`edit` filesystem tool suite, plus `read_image` while `attachments` is mounted. */ export function apply(ctx: Context, config: Config): void { // schemastery (Config) has already filled every defaulted field. const resolved = config as ResolvedConfig @@ -63,6 +64,12 @@ export function apply(ctx: Context, config: Config): void { maxBytes: resolved.readMaxBytes, streamMinSize: resolved.readStreamMinSize, }) + // read_image is composition-conditional: without a mounted attachment store + // the deployment cannot durably commit image bytes, so the tool never + // registers; the execute body keeps a defensive re-check for direct callers. + ctx.inject(['attachments'], (imageCtx) => { + applyReadImageTool(imageCtx) + }) // One escalation surface shared by both mutating tools: advertisement gating, // per-call policy resolution, and denial-marker mapping, all keyed off whether // the mounted ctx.fs confines (ctx.fs.sandboxMode). diff --git a/packages/fs/tool-fs/src/read-image.ts b/packages/fs/tool-fs/src/read-image.ts new file mode 100644 index 0000000000..85f481bf9f --- /dev/null +++ b/packages/fs/tool-fs/src/read-image.ts @@ -0,0 +1,231 @@ +/** + * The model-facing `read_image` tool: reads a PNG/JPEG/WebP/GIF file, durably + * commits its bytes through the attachment service (the same lifecycle as a + * user-uploaded image), and returns an image block so the image enters model + * context from the next request onward. + * + * The route gate is deliberately stricter than the host upload preflight: a + * tool result enters durable session history, so emitting an image on a route + * that cannot carry it would break that route's continuation. Unknown + * capability therefore refuses instead of relying on the adapter guard. + * @module @deepseek-ai/dsh-tool-fs/src/read-image + */ + +import { basename, extname } from 'node:path' +import type { Context } from '@deepseek-ai/cordis' +import { AttachmentError, AttachmentId } from '@deepseek-ai/dsh-attachment' +import type { ImageAttachmentRef, ImageMediaType } from '@deepseek-ai/dsh-attachment' +import { createUserMessage } from '@deepseek-ai/dsh-llm' +import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import { defineTool } from '@deepseek-ai/dsh-tools' +import type { GenericCallView, ToolExecution } from '@deepseek-ai/dsh-tools' +import type {} from '@deepseek-ai/dsh-fs' +import { resolveRegularReadTarget } from './read-target.ts' + +/** Extensions `read_image` accepts; magic-byte validation at the attachment service stays authoritative. */ +const IMAGE_EXTENSIONS: Readonly> = { + '.png': 'image/png', + '.jpg': 'image/jpeg', + '.jpeg': 'image/jpeg', + '.webp': 'image/webp', + '.gif': 'image/gif', +} + +/** The canonical outcome declared by the `read_image` output schema. */ +export interface ImageReadValue { + path: string + image: { + attachmentId: string + mediaType: ImageMediaType + bytes: number + width: number + height: number + name?: string + } +} + +/** + * Map a model-supplied path to its declared image media type by extension. + * @param filePath - the raw `file_path` argument (not yet resolved). + * @returns the declared media type, or undefined when the path does not claim an image. + */ +export function imageMediaTypeForPath(filePath: string): ImageMediaType | undefined { + return IMAGE_EXTENSIONS[extname(filePath).toLowerCase()] +} + +/** + * Enforce the strict image-capability gate for the calling route. Resolves the + * session's latest routed provider/model (request header config, then agent + * options) and requires the exact resolved route to declare `image` input explicitly. + * @param ctx - the plugin context used to resolve the optional `llm` service. + * @param exec - the tool-execution context supplying the calling agent. + * @param requestedPath - the raw, not-yet-resolved path rendered in refusal messages. + */ +export async function assertImageCapableRoute(ctx: Context, exec: ToolExecution, requestedPath: string): Promise { + const routed = exec.agent?.session.requestHeader()?.config + const provider = routed?.provider ?? exec.agent?.options.provider + const model = routed?.model ?? exec.agent?.options.model + const llm = ctx.get('llm') + if (provider === undefined || model === undefined || llm === undefined) { + throw new Error(`cannot read "${requestedPath}" as an image: the current model route could not be resolved`) + } + const active = await llm.resolveModelInfo(provider, model, exec.signal) + if (active.inputModalities === undefined || !active.inputModalities.includes('image')) { + throw new Error(`cannot read "${requestedPath}" as an image: model "${model}" does not declare image input; switch to an image-capable model to read images`) + } +} + +/** + * Re-brand a canonical image outcome into the durable attachment reference an + * `ImageBlock` carries. + * @param image - the canonical image metadata from the output schema. + * @returns the branded attachment reference. + */ +export function imageRefFromValue(image: ImageReadValue['image']): ImageAttachmentRef { + return { + attachmentId: AttachmentId(image.attachmentId), + mediaType: image.mediaType, + bytes: image.bytes, + width: image.width, + height: image.height, + ...image.name === undefined ? {} : { name: image.name }, + } +} + +/** + * Format an image read as the model-facing envelope beside its image block. + * @param displayPath - the backend-resolved path rendered in the envelope's `` element. + * @param image - the canonical image metadata to summarize. + * @returns the model-facing envelope; the image itself rides the adjacent image block. + */ +export function formatImageReadOutput(displayPath: string, image: ImageReadValue['image']): string { + return `${displayPath} +image + +${image.mediaType} image, ${image.width}x${image.height} px, ${image.bytes} bytes +` +} + +/** + * Project one canonical image read into its model-facing envelope and image. + * @param value - the canonical image-read outcome. + * @returns the two content blocks used by native and nested dispatches. + */ +function imageReadContent(value: ImageReadValue): ContentBlock[] { + return [ + { type: 'text', text: formatImageReadOutput(value.path, value.image) }, + { type: 'image', attachment: imageRefFromValue(value.image) }, + ] +} + +/** + * Register the `read_image` tool into the given context. The composing plugin + * owns the attachments gate: `src/index.ts` calls this inside + * `ctx.inject(['attachments'], …)` so the tool exists only while a durable + * store is mounted. Execution still re-checks `ctx.get('attachments')` for + * direct callers and gates on the calling route's declared image input. + * @param ctx - the registration scope; execution uses its `fs` service plus + * the optional `attachments`/`llm` services. + */ +export function applyReadImageTool(ctx: Context): void { + ctx.tools.register(defineTool({ + name: 'read_image', + description: 'Read a PNG/JPEG/WebP/GIF file and return the image itself. Requires the current model to accept image input.', + parameters: { + file_path: { type: 'string', required: true, description: 'Path to the image file, resolved by the filesystem backend.' }, + }, + output: { + schema: { + type: 'object', + additionalProperties: false, + properties: { + path: { type: 'string', required: true }, + image: { + type: 'object', + additionalProperties: false, + required: true, + properties: { + attachmentId: { type: 'string', required: true }, + mediaType: { type: 'string', enum: ['image/png', 'image/jpeg', 'image/webp', 'image/gif'], required: true }, + bytes: { type: 'integer', required: true }, + width: { type: 'integer', required: true }, + height: { type: 'integer', required: true }, + name: { type: 'string' }, + }, + }, + }, + }, + render: (_args, value) => imageReadContent(value), + }, + // Content-addressed attachment writes are idempotent, so concurrent reads + // of the same file cannot conflict. + isConcurrencySafe: () => true, + async execute(args, exec) { + if (args.file_path.trim().length === 0) throw new Error('file_path must be a non-empty string') + + // Every gate runs before any filesystem I/O so a refusal never leaks + // partial reads or attachment writes. + const mediaType = imageMediaTypeForPath(args.file_path) + if (mediaType === undefined) { + throw new Error(`cannot read "${args.file_path}": read_image only accepts PNG/JPEG/WebP/GIF paths`) + } + const attachments = ctx.get('attachments') + if (attachments === undefined) { + throw new Error(`cannot read "${args.file_path}" as an image: no attachment service is mounted`) + } + if (!attachments.imageLimits.mediaTypes.includes(mediaType)) { + throw new Error(`cannot read "${args.file_path}": ${mediaType} images are not accepted by this deployment`) + } + await assertImageCapableRoute(ctx, exec, args.file_path) + + const { target, info } = await resolveRegularReadTarget(ctx, exec, args.file_path) + + // The tool result is one message carrying one image, so the per-message + // aggregate bound applies beside the per-image bound. + const byteCap = Math.min(attachments.imageLimits.maxImageBytes, attachments.imageLimits.maxMessageImageBytes) + const data = await ctx.fs.readBytes(target, exec.signal, byteCap) + // Persist before returning: the image block must reference a durably + // committed object by the time the tool/result event is appended. + let ref: ImageAttachmentRef + try { + ref = await attachments.saveImage({ data, mediaType, name: basename(target.displayPath) }) + } catch (error: unknown) { + if (!(error instanceof AttachmentError) || error.code !== 'IMAGE_TYPE_MISMATCH') throw error + const extension = extname(target.displayPath).toLowerCase() + throw new Error( + `cannot read "${target.displayPath}": the ${extension} extension declares ${mediaType}, but the bytes use a different image format; rename the file to match its actual format if it is PNG/JPEG/WebP/GIF, or convert it to one of those formats`, + { cause: error }, + ) + } + ctx.emit('fs/observed', target, { kind: 'present', version: info.version }, exec) + const value: ImageReadValue = { + path: target.displayPath, + image: { + attachmentId: ref.attachmentId, + mediaType: ref.mediaType, + bytes: ref.bytes, + width: ref.width, + height: ref.height, + ...ref.name === undefined ? {} : { name: ref.name }, + }, + } + if (exec.parent !== undefined) { + exec.deferContext(createUserMessage({ + content: imageReadContent(value), + source: { kind: 'plugin', plugin: 'tool-fs' }, + })) + } + return value + }, + // Pure display: a generic card in the read family with a follow-along + // location on the image file. + presentCall(args): GenericCallView { + return { + card: 'generic', + title: `Read image ${args.file_path}`, + kind: 'read', + locations: [{ path: args.file_path }], + } + }, + })) +} diff --git a/packages/fs/tool-fs/src/read-target.ts b/packages/fs/tool-fs/src/read-target.ts new file mode 100644 index 0000000000..98f4e05cdb --- /dev/null +++ b/packages/fs/tool-fs/src/read-target.ts @@ -0,0 +1,34 @@ +/** + * Shared path resolution and regular-file validation for model-facing read tools. + * @module @deepseek-ai/dsh-tool-fs/src/read-target + */ + +import type { Context } from '@deepseek-ai/cordis' +import { FsError } from '@deepseek-ai/dsh-fs' +import type { FsInfo, FsTarget } from '@deepseek-ai/dsh-fs' +import type { ToolExecution } from '@deepseek-ai/dsh-tools' +import { sessionResolveOptions } from './session-cwd.ts' + +/** + * Resolve a model-supplied path, observe absence, and require a regular file. + * @param ctx - the plugin context providing filesystem resolution and observation events. + * @param exec - the current tool execution, including session cwd and cancellation. + * @param requestedPath - the raw path supplied to the tool. + * @returns the resolved target and its single stat result. + */ +export async function resolveRegularReadTarget( + ctx: Context, + exec: ToolExecution, + requestedPath: string, +): Promise<{ target: FsTarget; info: FsInfo }> { + const target = await ctx.fs.resolve(requestedPath, sessionResolveOptions(exec, requestedPath)) + const info = await ctx.fs.stat(target, exec.signal) + if (info === undefined) { + ctx.emit('fs/observed', target, { kind: 'absent' }, exec) + throw new FsError(`cannot read "${target.displayPath}": not found`, 'FS_NOT_FOUND') + } + if (info.type !== 'file') { + throw new FsError(`cannot read "${target.displayPath}": not a regular file`, 'FS_NOT_REGULAR_FILE') + } + return { target, info } +} diff --git a/packages/fs/tool-fs/src/read.ts b/packages/fs/tool-fs/src/read.ts index 0c062c129e..cc9bd4e937 100644 --- a/packages/fs/tool-fs/src/read.ts +++ b/packages/fs/tool-fs/src/read.ts @@ -7,11 +7,10 @@ import type { Context } from '@deepseek-ai/cordis' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, ReadResultView, ToolResult } from '@deepseek-ai/dsh-tools' -import { FsError } from '@deepseek-ai/dsh-fs' import type {} from '@deepseek-ai/dsh-fs' import type {} from '@deepseek-ai/dsh-system-prompt' import { buildWindow, formatReadOutput, langFromPath, readMetaFromMeta } from './read-render.ts' -import { sessionResolveOptions } from './session-cwd.ts' +import { resolveRegularReadTarget } from './read-target.ts' /** Default and maximum number of lines returned by one `read` call (the `readLimit` config). */ export const READ_LIMIT = 2000 @@ -136,16 +135,9 @@ export function applyReadTool(ctx: Context, caps: ReadToolCaps): void { isConcurrencySafe: () => true, async execute(args, exec) { const input = parseReadArgs(args, caps.limit) - const target = await ctx.fs.resolve(input.filePath, sessionResolveOptions(exec, input.filePath)) - // One stat: absence observation OR type check + size routing + present version. // A concurrent write can only make a later guarded mutation fail stale and require reread. - const info = await ctx.fs.stat(target, exec.signal) - if (!info) { - ctx.emit('fs/observed', target, { kind: 'absent' }, exec) - throw new FsError(`cannot read "${target.displayPath}": not found`, 'FS_NOT_FOUND') - } - if (info.type !== 'file') throw new FsError(`cannot read "${target.displayPath}": not a regular file`, 'FS_NOT_REGULAR_FILE') + const { target, info } = await resolveRegularReadTarget(ctx, exec, input.filePath) // Stream when the file is large OR size is unknown, so a size-less backend // never buffers an arbitrarily large file. diff --git a/packages/fs/tool-fs/tests/read-image.spec.ts b/packages/fs/tool-fs/tests/read-image.spec.ts new file mode 100644 index 0000000000..03f65d437d --- /dev/null +++ b/packages/fs/tool-fs/tests/read-image.spec.ts @@ -0,0 +1,499 @@ +/** + * The `read_image` tool over the REAL local filesystem and attachment store: + * extension routing, the strict image-modality gate (every refusal arm), + * durable commit + image-block rendering, attachment admission failures, and + * the regression that `read` keeps its text-only contract. + */ + +import { afterEach, beforeEach, describe, expect, it } from 'vitest' +import { mkdir, mkdtemp, rm, writeFile } from 'node:fs/promises' +import { tmpdir } from 'node:os' +import { join } from 'node:path' +import { Context } from '@deepseek-ai/cordis' +import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime' +import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime' +import { CallId, LlmAdapter, LlmService } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelInfo, LlmResolvedModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry, { RUN_CODE_NAME } from '@deepseek-ai/dsh-tools' +import type { Config as ToolConfig } from '@deepseek-ai/dsh-tools' +import LocalFileSystem from '@deepseek-ai/dsh-fs-local' +import * as FsPolicy from '@deepseek-ai/dsh-fs-policy' +import LocalAttachmentStore from '@deepseek-ai/dsh-attachment-local' +import { AttachmentId, AttachmentStore } from '@deepseek-ai/dsh-attachment' +import type { ImageAttachmentLimits, ImageAttachmentRef, SaveImageAttachment, StoredImageAttachment } from '@deepseek-ai/dsh-attachment' +import * as ToolFs from '@deepseek-ai/dsh-tool-fs' +import { + applyReadImageTool, + formatImageReadOutput, + imageMediaTypeForPath, + imageRefFromValue, +} from '../src/read-image.ts' + +/** 1x1 red PNG (valid signature, IHDR, IDAT). */ +const PNG_1X1 = Buffer.from('iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAADElEQVR4nGP4z8AAAAMBAQDJ/pLvAAAAAElFTkSuQmCC', 'base64') +/** 3x3 red PNG used to trip a tiny configured pixel limit. */ +const PNG_3X3 = Buffer.from('iVBORw0KGgoAAAANSUhEUgAAAAMAAAADCAIAAADZSiLoAAAAEElEQVR4nGP4z8AAQQxYWACPjgj4kWPEuQAAAABJRU5ErkJggg==', 'base64') + +const testToolSignal = new AbortController().signal + +/** Exact-route fake adapter; `stream` is unreachable in these tests. */ +class CatalogAdapter extends LlmAdapter { + constructor( + private readonly models: LlmModelInfo[], + private readonly resolvedModels: LlmModelInfo[] = models, + ) { + super() + } + + override listModels(_provider: string): Promise { + return Promise.resolve(this.models) + } + + override resolveModel(provider: string, model: string): Promise { + const resolved = this.resolvedModels.find(candidate => candidate.id === model) + return Promise.resolve({ + provider, + id: model, + name: resolved?.name ?? model, + ...resolved?.inputModalities === undefined ? {} : { inputModalities: [...resolved.inputModalities] }, + }) + } + + override stream(_options: GenerateOptions): AsyncIterable { + throw new Error('read_image tests never stream') + } +} + +/** In-process Code Mode seam fake that invokes the real registry bindings. */ +class FakeRuntime extends CodeRuntime { + readonly language = 'typescript' + readonly isolation = 'fake' + behavior: (request: CodeRunRequest) => Promise = () => Promise.resolve({ logs: [] }) + + run(request: CodeRunRequest): Promise { + return this.behavior(request) + } +} + +let dir: string +let home: string + +beforeEach(async () => { + dir = await mkdtemp(join(tmpdir(), 'dsh-read-image-')) + home = await mkdtemp(join(tmpdir(), 'dsh-read-image-home-')) +}) +afterEach(async () => { + await rm(dir, { recursive: true, force: true }) + await rm(home, { recursive: true, force: true }) +}) + +interface SetupOptions { + models?: LlmModelInfo[] + resolvedModels?: LlmModelInfo[] + attachments?: boolean + llm?: boolean + storeConfig?: { maxImageBytes?: number; maxImagePixels?: number; maxMessageImageBytes?: number } + toolMode?: ToolConfig['mode'] +} + +async function setup(options: SetupOptions = {}) { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry, { mode: options.toolMode ?? 'native' }) + if (options.toolMode === 'code' || options.toolMode === 'both') { + await ctx.plugin(FakeRuntime) + } + await ctx.plugin(LocalFileSystem, { cwd: dir }) + await ctx.plugin(FsPolicy) + if (options.attachments !== false) { + await ctx.plugin(LocalAttachmentStore, { dshHome: home, ...options.storeConfig }) + } + if (options.llm !== false) { + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['visual'], new CatalogAdapter(options.models ?? [ + { provider: 'visual', id: 'vision-model', name: 'Vision', inputModalities: ['text', 'image'] }, + { provider: 'visual', id: 'text-model', name: 'Text', inputModalities: ['text'] }, + { provider: 'visual', id: 'legacy-model', name: 'Legacy' }, + ], options.resolvedModels)) + } + await ctx.plugin(ToolFs) + return ctx +} + +/** A fake calling agent pinned to one routed provider/model. */ +function agentOn(model: string | undefined, provider = 'visual'): object { + return { + options: {}, + session: { + header: { cwd: dir }, + requestHeader: () => (model === undefined ? undefined : { config: { provider, model } }), + append: () => undefined, + }, + } +} + +let callCounter = 0 +function call(ctx: Context, name: string, args: unknown, agent?: object) { + return ctx.tools.execute({ + signal: testToolSignal, + callId: CallId(`img-call-${++callCounter}`), + name, + arguments: args, + ...agent ? { agent: agent as never } : {}, + }) +} + +function readImage(ctx: Context, args: unknown, agent?: object) { + return call(ctx, 'read_image', args, agent) +} + +function text(result: { content: { type: string; text?: string }[] }): string { + return result.content.filter(b => b.type === 'text').map(b => b.text).join('') +} + +describe('imageMediaTypeForPath', () => { + it('maps the four extensions case-insensitively and rejects everything else', () => { + expect(imageMediaTypeForPath('a.png')).toBe('image/png') + expect(imageMediaTypeForPath('a.JPG')).toBe('image/jpeg') + expect(imageMediaTypeForPath('b.jpeg')).toBe('image/jpeg') + expect(imageMediaTypeForPath('c.webp')).toBe('image/webp') + expect(imageMediaTypeForPath('d.Gif')).toBe('image/gif') + expect(imageMediaTypeForPath('note.txt')).toBeUndefined() + expect(imageMediaTypeForPath('png')).toBeUndefined() + }) +}) + +describe('imageRefFromValue', () => { + it('re-brands with and without the optional display name', () => { + const base = { attachmentId: 'sha256:00', mediaType: 'image/png' as const, bytes: 1, width: 1, height: 1 } + expect(imageRefFromValue(base)).toEqual(base) + expect(imageRefFromValue({ ...base, name: 'a.png' })).toEqual({ ...base, name: 'a.png' }) + }) +}) + +describe('read_image happy path', () => { + it('commits the bytes durably and renders the envelope beside an image block', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup() + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + + expect(result.isError).toBe(false) + expect(result.content).toHaveLength(2) + const image = result.content[1] as { type: string; attachment: ImageAttachmentRef } + expect(image.type).toBe('image') + expect(image.attachment.mediaType).toBe('image/png') + expect(image.attachment.width).toBe(1) + expect(image.attachment.height).toBe(1) + expect(image.attachment.bytes).toBe(PNG_1X1.length) + expect(image.attachment.name).toBe('red.png') + expect(image.attachment.attachmentId).toMatch(/^sha256:[0-9a-f]{64}$/) + expect(text(result)).toBe(formatImageReadOutput(join(dir, 'red.png'), { + attachmentId: image.attachment.attachmentId, + mediaType: 'image/png', + bytes: PNG_1X1.length, + width: 1, + height: 1, + })) + + // The committed object must read back verbatim through the store. + const attachments = ctx.get('attachments') + if (attachments === undefined) throw new Error('expected the attachment service') + const stored = await attachments.readImage(image.attachment) + expect(Buffer.from(stored.data)).toEqual(PNG_1X1) + }) + + it('emits fs/observed for the read image', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup() + const observed: string[] = [] + ctx.on('fs/observed', target => void observed.push(target.displayPath)) + await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(observed).toEqual([join(dir, 'red.png')]) + }) + + it('falls back to agent options when no request header exists yet', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup() + const agent = { + options: { provider: 'visual', model: 'vision-model' }, + session: { header: { cwd: dir }, requestHeader: () => undefined }, + } + const result = await readImage(ctx, { file_path: 'red.png' }, agent) + expect(result.isError).toBe(false) + }) + + it('forwards a nested Code Mode image through the outer run_code context', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ toolMode: 'code' }) + const runtime = ctx.codeRuntime as FakeRuntime + runtime.behavior = async (request) => { + const value = await request.bindings[0]!.functions.read_image!({ file_path: 'red.png' }) + return { logs: [], value } + } + + const result = await call(ctx, RUN_CODE_NAME, { + code: 'return await tools.read_image({ file_path: "red.png" })', + description: 'Read the image through Code Mode', + }, agentOn('vision-model')) + + expect(result.isError).toBe(false) + expect(result.content.every(block => block.type === 'text')).toBe(true) + expect(result.additionalContexts).toHaveLength(1) + const forwarded = result.additionalContexts?.[0]?.content + expect(forwarded).toHaveLength(2) + expect(forwarded?.[0]?.type).toBe('text') + expect(forwarded?.[0]?.type === 'text' ? forwarded[0].text : '').toContain('image') + expect(forwarded?.[1]).toMatchObject({ + type: 'image', + attachment: { mediaType: 'image/png', width: 1, height: 1 }, + }) + }) +}) + +describe('strict image-modality gate', () => { + it('accepts an exact visual route even when the advisory model catalog omits it', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ + models: [], + resolvedModels: [ + { provider: 'visual', id: 'hidden-vision', name: 'Hidden Vision', inputModalities: ['text', 'image'] }, + ], + }) + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('hidden-vision')) + expect(result.isError).toBe(false) + }) + + it.each([ + ['a text-only model', 'text-model'], + ['a model without declared modalities', 'legacy-model'], + ['a model absent from the catalog', 'unknown-model'], + ])('refuses on %s', async (_label, model) => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup() + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn(model)) + expect(result.isError).toBe(true) + expect(text(result)).toContain('does not declare image input') + }) + + it('refuses when the route cannot be resolved (no agent, or no header and no options)', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup() + const noAgent = await readImage(ctx, { file_path: 'red.png' }) + expect(noAgent.isError).toBe(true) + expect(text(noAgent)).toContain('route could not be resolved') + + const noRoute = await readImage(ctx, { file_path: 'red.png' }, agentOn(undefined)) + expect(noRoute.isError).toBe(true) + expect(text(noRoute)).toContain('route could not be resolved') + }) + + it('refuses when no llm service is mounted', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ llm: false }) + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + expect(text(result)).toContain('route could not be resolved') + }) +}) + +describe('argument and service preconditions', () => { + it('rejects an empty path and a non-image extension', async () => { + const ctx = await setup() + const empty = await readImage(ctx, { file_path: ' ' }, agentOn('vision-model')) + expect(empty.isError).toBe(true) + expect(text(empty)).toContain('non-empty') + + const nonImage = await readImage(ctx, { file_path: 'notes.txt' }, agentOn('vision-model')) + expect(nonImage.isError).toBe(true) + expect(text(nonImage)).toContain('only accepts PNG/JPEG/WebP/GIF paths') + }) + + it('refuses when no attachment service is mounted', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ attachments: false }) + expect(ctx.tools.get('read_image')).toBeUndefined() + expect(ctx.tools.schemas().map(schema => schema.name)).not.toContain('read_image') + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + expect(text(result)).toContain('unknown tool "read_image"') + }) + + it('defensively refuses execution without an attachment service', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ attachments: false }) + applyReadImageTool(ctx) + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + expect(text(result)).toContain('no attachment service is mounted') + }) + + it('refuses a media type the deployment does not accept', async () => { + /** Store whose deployment accepts JPEG only. */ + class JpegOnlyStore extends AttachmentStore { + readonly imageLimits: ImageAttachmentLimits = Object.freeze({ + maxImageBytes: 1024, + maxImagesPerMessage: 1, + maxMessageImageBytes: 1024, + maxImagePixels: 100, + mediaTypes: Object.freeze(['image/jpeg'] as const), + }) + + validateImage(_input: SaveImageAttachment): Promise { + throw new Error('unreachable: admission refuses before validation') + } + + saveImage(_input: SaveImageAttachment): Promise { + throw new Error('unreachable: admission refuses before save') + } + + readImage(_ref: ImageAttachmentRef): Promise { + throw new Error('unreachable in this test') + } + } + const ctx = await setup({ attachments: false }) + await ctx.plugin(JpegOnlyStore) + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + expect(text(result)).toContain('image/png images are not accepted by this deployment') + }) +}) + +describe('image admission failures', () => { + it('explains how to repair a declared/actual media-type mismatch', async () => { + await writeFile(join(dir, 'wrong.jpg'), PNG_1X1) + const ctx = await setup() + const result = await readImage(ctx, { file_path: 'wrong.jpg' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + expect(text(result)).toContain('the .jpg extension declares image/jpeg') + expect(text(result)).toContain('rename the file to match its actual format if it is PNG/JPEG/WebP/GIF, or convert it to one of those formats') + }) + + it('fails with FS_TOO_LARGE before reading a file past maxImageBytes', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ storeConfig: { maxImageBytes: PNG_1X1.length - 1 } }) + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + expect(text(result)).toContain('exceeds') + }) + + it('honors the tighter per-message aggregate byte bound', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ storeConfig: { maxMessageImageBytes: PNG_1X1.length - 1 } }) + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + expect(text(result)).toContain('exceeds') + }) + + it('surfaces the pixel limit from the attachment admission', async () => { + await writeFile(join(dir, 'big.png'), PNG_3X3) + const ctx = await setup({ storeConfig: { maxImagePixels: 4 } }) + const result = await readImage(ctx, { file_path: 'big.png' }, agentOn('vision-model')) + expect(result.isError).toBe(true) + }) + + it('reports a missing image file and a directory target through the fs vocabulary', async () => { + await mkdir(join(dir, 'folder.png')) + const ctx = await setup() + const observed: { path: string; kind: string }[] = [] + ctx.on('fs/observed', (target, observation) => void observed.push({ path: target.displayPath, kind: observation.kind })) + const missing = await readImage(ctx, { file_path: 'absent.png' }, agentOn('vision-model')) + expect(missing.isError).toBe(true) + expect(text(missing)).toContain('not found') + expect(observed).toEqual([{ path: join(dir, 'absent.png'), kind: 'absent' }]) + + const directory = await readImage(ctx, { file_path: 'folder.png' }, agentOn('vision-model')) + expect(directory.isError).toBe(true) + expect(text(directory)).toContain('not a regular file') + }) + + it('omits the display name when the store returns a reference without one', async () => { + /** Store echoing a fixed nameless reference; deployments may strip names entirely. */ + class NamelessStore extends AttachmentStore { + readonly imageLimits: ImageAttachmentLimits = Object.freeze({ + maxImageBytes: 1024, + maxImagesPerMessage: 1, + maxMessageImageBytes: 1024, + maxImagePixels: 100, + mediaTypes: Object.freeze(['image/png'] as const), + }) + + validateImage(_input: SaveImageAttachment): Promise { + return Promise.resolve() + } + + async saveImage(input: SaveImageAttachment): Promise { + return { attachmentId: AttachmentId('sha256:feed'), mediaType: input.mediaType, bytes: input.data.length, width: 1, height: 1 } + } + + readImage(_ref: ImageAttachmentRef): Promise { + throw new Error('unreachable in this test') + } + } + await writeFile(join(dir, 'red.png'), PNG_1X1) + const ctx = await setup({ attachments: false }) + await ctx.plugin(NamelessStore) + const result = await readImage(ctx, { file_path: 'red.png' }, agentOn('vision-model')) + expect(result.isError).toBe(false) + const image = result.content[1] as { attachment: ImageAttachmentRef } + expect(image.attachment.name).toBeUndefined() + }) +}) + +describe('registration surface', () => { + it('withdraws read_image when the tool-fs fiber or the attachment store is disposed (HMR safety)', async () => { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry, { mode: 'native' }) + await ctx.plugin(LocalFileSystem, { cwd: dir }) + await ctx.plugin(FsPolicy) + const attachmentsFiber = await ctx.plugin(LocalAttachmentStore, { dshHome: home }) + const toolFsFiber = await ctx.plugin(ToolFs) + const names = () => ctx.tools.schemas().map(schema => schema.name).sort() + expect(names()).toEqual(['edit', 'read', 'read_image', 'write']) + + // Disposing only the attachment store tears down the scoped inject fiber: + // read_image withdraws while the unconditional tools stay registered. + await attachmentsFiber.dispose() + expect(names()).toEqual(['edit', 'read', 'write']) + + // Remounting the store restores the conditional registration. + const remounted = await ctx.plugin(LocalAttachmentStore, { dshHome: home }) + expect(names()).toEqual(['edit', 'read', 'read_image', 'write']) + + // Disposing the whole plugin withdraws every tool, read_image included. + await toolFsFiber.dispose() + expect(names()).toEqual([]) + await remounted.dispose() + }) + + it('declares read_image parallel-safe and presents a read-family card', async () => { + const ctx = await setup() + expect(ctx.tools.executionMode({ + signal: testToolSignal, callId: CallId('img-parallel'), name: 'read_image', arguments: { file_path: 'a.png' }, + })).toEqual({ kind: 'parallel' }) + expect(ctx.tools.get('read_image')?.presentCall?.({ file_path: 'shot.png' })).toEqual({ + card: 'generic', + title: 'Read image shot.png', + kind: 'read', + locations: [{ path: 'shot.png' }], + }) + }) +}) + +describe('read keeps its text-only contract', () => { + it('still refuses a PNG as a binary file and line-numbers text', async () => { + await writeFile(join(dir, 'red.png'), PNG_1X1) + await writeFile(join(dir, 'note.txt'), 'hello\nworld') + const ctx = await setup() + + const png = await call(ctx, 'read', { file_path: 'red.png' }, agentOn('vision-model')) + expect(png.isError).toBe(true) + expect(text(png)).toContain('binary file') + + const txt = await call(ctx, 'read', { file_path: 'note.txt' }, agentOn('text-model')) + expect(txt.isError).toBe(false) + expect(text(txt)).toContain('1: hello') + expect(text(txt)).toContain('file') + }) +}) diff --git a/packages/fs/tool-fs/tests/tools.spec.ts b/packages/fs/tool-fs/tests/tools.spec.ts index 73be4131e1..b15bf4ef8f 100644 --- a/packages/fs/tool-fs/tests/tools.spec.ts +++ b/packages/fs/tool-fs/tests/tools.spec.ts @@ -71,6 +71,13 @@ class FakeFs extends FileSystem { const content = this.files.get(target.targetKey) ?? '' return (async function* () { yield content })() } + override async readBytes(target: FsTarget, _signal: AbortSignal | undefined, maxBytes: number): Promise { + const bytes = new TextEncoder().encode(this.files.get(target.targetKey) ?? '') + if (bytes.length > maxBytes) { + throw new FsError(`too large: ${target.displayPath}`, 'FS_TOO_LARGE') + } + return bytes + } override async listDir(_target: FsTarget): Promise { return [] } diff --git a/packages/fs/tool-fs/tsconfig.json b/packages/fs/tool-fs/tsconfig.json index a3f128143c..62e7230554 100644 --- a/packages/fs/tool-fs/tsconfig.json +++ b/packages/fs/tool-fs/tsconfig.json @@ -41,6 +41,9 @@ }, { "path": "../../interaction/user-approval" + }, + { + "path": "../../attachment/attachment" } ] } diff --git a/packages/host/apiproxy/README.i18n.yaml b/packages/host/apiproxy/README.i18n.yaml index 8bf63adb20..d89a5f518b 100644 --- a/packages/host/apiproxy/README.i18n.yaml +++ b/packages/host/apiproxy/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/host/apiproxy/README.md -README.md: d59f3f5ddb9929356e23a467ce5840f1673663f7 -README.zh.md: 737361f2bd85c0ea02b9d29734f58c34bc324969 +README.md: 2a27ab9f2cfcd4f12c32b815583b13f439b3eaac +README.zh.md: ba49ccff82bab1e677bad1495e48b8503564ae1d diff --git a/packages/host/apiproxy/README.md b/packages/host/apiproxy/README.md index d59f3f5ddb..2a27ab9f2c 100644 --- a/packages/host/apiproxy/README.md +++ b/packages/host/apiproxy/README.md @@ -36,6 +36,8 @@ Session model selection is a session-domain contract. `session.models` returns t Pending queued input is a live control-plane contract, not conversation history. The gateway derives the complete `next-turn` queue from durable `agent/inbox/spliced` mutations and broadcasts authoritative `session/queue` snapshots after each change and on reconnect; pending `next-step` steering stays outside this Web projection. Within `next-step`, user-origin messages carry the `steering` placement while injected context (approval notices, task completion, attached snapshots) carries `context` and is not surfaced until claimed. The message-local `agent/inbox/inserted`, `claimed`, and `discarded` notifications remain available to lifecycle observers but do not build the queue view. `session.updateQueue` addresses one `MessageId`; edit and remove mutate the attached Agent through `Inbox.splice()`. A claim's pure deletion splice wins races before pre-step admission, so a later operation returns `queue-item-not-found`. `session.cancel` aborts only the active turn and preserves pending inbox work; after cancellation reaches quiescence and the closing turn flushes, AgentLoop claims the next waking message in FIFO order, and the browser never resends or promotes it. Queue operations never resume a cold session, and the client never infers retirement from turn or status events. +Background tasks ride the same live-push posture. When `ctx.tasks` is composed, the gateway subscribes to its change feed and broadcasts a whole `session/tasks` snapshot after every registry commit that alters what a session can see — registration, the stopping transition, settlement, and owner-disposal removal — plus a subscription baseline for each session that already has tasks (an absent baseline is the empty set; a change that empties a set still sends `[]`). A change carrying an owner reads through that exact `Agent`, so a push stays correct while its scope tears down; the baseline reads `ctx.agents.get(sessionId)`, which yields only unowned tasks for a session with no live Agent and never resumes a cold one. An unowned change fans out to every subscribed session, because unowned tasks are visible to every caller. The wire `TaskView` drops `ownerSession`, `reported`, and `outputLimitBytes`: the frame's own `sessionId` carries the first, and the other two are internal notice and model-presentation policy. A composition without the registry emits no such frames. + Workspace and Session lists are separate reconnect baselines. `workspace.create({ path })` adopts an existing canonical directory and permits basename-derived titles to repeat. `workspace.delete` removes only the Workspace registration, `session.create` accepts an optional preallocated Session id, and `host/workspace-changed`, `host/workspace-removed`, plus `host/session-added` carry committed increments in either arrival order. `workspace.archiveSession` adds one session to the registry-global archive set and answers the full updated set; `workspace.list` carries that set as the reconnect baseline and `host/archived-sessions-changed` pushes the full snapshot after every durable change. Archiving hides the session from grouping surfaces without touching its log or its workspace account; a session neither live nor persisted fails with `session-not-found`. Registration deletion preserves the directory and session logs; its Sessions remain in `session.list` and become Ungrouped. `SessionSummary.blank` and the `host/session-added` frame carry the derived zero-events bit: clients hide blank sessions and reuse them per workspace, flip blank on the first `host/session-status(running:true)`, and treat `session.list` as the reconnect authority; cold summaries are never blank because lazy persistence keeps never-appended sessions out of `list()`. `session.search` is a bounded content-search projection over the sessions visible through `session.list`. The gateway asks the optional `ctx.sessionQuery` service for globally ranked current-surface user, assistant, and steering matches, consumes that stream until it has at most 20 visible session/snippet pairs plus one lookahead, and revalidates every hit against the list-derived authorization set before returning it. Provider pages start at 20 hits; when a first-page request rejects that limit, the gateway probes 10, 5, 2, then 1 and retains the learned size for continuation and stale-generation restarts. Returned snippets contain at most 240 Unicode code points, and the response schema independently enforces that bound at each client boundary. Keeping the authorization set in Host memory avoids SQLite's variable ceiling for large valid corpora without weakening visibility or ranking. diff --git a/packages/host/apiproxy/README.zh.md b/packages/host/apiproxy/README.zh.md index 737361f2bd..ba49ccff82 100644 --- a/packages/host/apiproxy/README.zh.md +++ b/packages/host/apiproxy/README.zh.md @@ -36,6 +36,8 @@ Settings 分节中的 `reasoningEffort` 在 agent-default-model 插件配置中 待处理的 queued 输入属于实时控制平面约定，而非对话历史。网关根据持久 `agent/inbox/spliced` 变更派生完整的 `next-turn` 队列，并在每次变更后及重连时广播权威 `session/queue` 快照；待处理的 `next-step` steering（中途引导）不进入此 Web 投影。在 `next-step` 内，用户来源的消息携带 `steering` placement，而注入上下文（审批通知、任务完成、附加快照）携带 `context`，领取前不对外呈现。面向单条消息的 `agent/inbox/inserted`、`claimed` 与 `discarded` 通知仍供生命周期观察方使用，但不用于构建队列视图。`session.updateQueue` 通过 `MessageId` 寻址单个项；编辑和移除经已挂载 Agent 的 `Inbox.splice()` 修改队列。claim 的纯删除 splice 会在 pre-step 准入前赢得竞态，因此之后的操作返回 `queue-item-not-found`。`session.cancel` 仅中止活动轮次并保留待处理 inbox 工作；取消达到完全停稳且结束中的轮次完成 flush 后，AgentLoop 按 FIFO 顺序认领下一条可唤醒消息，浏览器绝不重发或提升它。队列操作绝不恢复冷会话，客户端也绝不根据轮次或状态事件推断某项已退出队列。 +后台任务沿用同一种实时推送姿态。当组合中有 `ctx.tasks` 时，网关订阅它的变更订阅，并在注册表每一次改变某个会话可见内容的提交后——注册、转入 stopping、结算，以及 owner 销毁时的移除——广播一份完整的 `session/tasks` 快照，另外为每个已经有任务的会话发送订阅 baseline（没有 baseline 即表示空集；把集合清空的那次变更仍然发送 `[]`）。带 owner 的变更通过那个确切的 `Agent` 读取，因此推送在其 scope 拆除期间依然正确；baseline 读 `ctx.agents.get(sessionId)`，对没有活体 Agent 的会话只得到无主任务，且绝不恢复冷会话。无主变更向每一个已订阅会话扇出，因为无主任务对所有调用方可见。线路上的 `TaskView` 丢弃 `ownerSession`、`reported` 和 `outputLimitBytes`：第一个由帧自身的 `sessionId` 携带，另外两个分别是内部通知位和模型呈现策略。没有该注册表的组合不发出这类帧。 + Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.create({ path })` 会接纳已有的规范目录，并允许由 basename 派生的标题重复。`workspace.delete` 只移除 Workspace 注册记录，`session.create` 接受可选的预分配 Session id，`host/workspace-changed`、`host/workspace-removed` 与 `host/session-added` 则以任意到达顺序携带已提交的增量。`workspace.archiveSession` 向注册表级全局归档集合添加一个会话，并应答完整的更新后集合；`workspace.list` 携带该集合作为重连基线，`host/archived-sessions-changed` 在每次持久变更后推送完整快照。归档只把会话从各分组视图中隐藏，不触碰其日志和 workspace 记账；既非实时也未持久化的会话以 `session-not-found` 失败。删除注册记录会保留目录和会话日志；相关 Session 仍留在 `session.list` 中，并进入 Ungrouped。`SessionSummary.blank` 与 `host/session-added` 帧携带派生的零事件位：客户端隐藏空白会话并按 workspace 复用它们，在首个 `host/session-status(running:true)` 时翻转 blank，并以 `session.list` 作为重连权威；冷会话摘要永远不是空白：惰性持久化让从未追加过事件的会话根本不出现在 `list()` 中。 `session.search` 是以 `session.list` 所列会话为范围的有界内容搜索投影。网关向可选的 `ctx.sessionQuery` 服务请求全局排序后的当前内容视图中的 user、assistant 和 steering 匹配项，并持续消费该结果流，直到获得至多 20 个可见会话／snippet 对及一个前瞻项；返回前仍会依据从列表推导的授权集合重新校验每个命中。提供方分页初始请求 20 个命中；如果第一页请求因这一上限被拒绝，网关会依次探测 10、5、2、1，并在续传和陈旧世代重启中沿用探测所得的页面大小。返回的 snippet 最多包含 240 个 Unicode 码点，响应 schema 则会在每个客户端边界独立强制执行该上限。将授权集合保留在宿主内存中，可在不削弱可见性或排序的前提下避开有效大型语料库的 SQLite 变量上限。 diff --git a/packages/host/apiproxy/package.json b/packages/host/apiproxy/package.json index 6ccec04164..7f6d6e53aa 100644 --- a/packages/host/apiproxy/package.json +++ b/packages/host/apiproxy/package.json @@ -65,6 +65,7 @@ "@deepseek-ai/dsh-settings": "workspace:^", "@deepseek-ai/dsh-skill": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", + "@deepseek-ai/dsh-tasks": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "@deepseek-ai/dsh-user-approval": "workspace:^", "@deepseek-ai/dsh-user-interaction": "workspace:^", diff --git a/packages/host/apiproxy/src/api-proxy.ts b/packages/host/apiproxy/src/api-proxy.ts index ea41122cc9..6b71a6ce87 100644 --- a/packages/host/apiproxy/src/api-proxy.ts +++ b/packages/host/apiproxy/src/api-proxy.ts @@ -39,7 +39,7 @@ import type { ApiProxy, ConfigurableProviderView, CredentialView, GoalRef, HistoryEntry, HostFrame, ModelCatalogFailure, ModelProviderGroup, ModelReasoning, MuxFrame, PromptContentPart, QuestionResponsePayload, SessionProjectionsBlock, SessionSearchItem, - QueuedInboxItem, SessionSummary, SettingsNamespaceView, SubagentAddress, ToolEventView, + QueuedInboxItem, SessionSummary, SettingsNamespaceView, SubagentAddress, TaskView, ToolEventView, WorkspaceId, WorkspaceView, } from './api/index.ts' import { @@ -49,6 +49,9 @@ import { } from './api/session-search.ts' // Type-only: resolves `ctx.get('sessionProjections')` to the projection registry. import type {} from '@deepseek-ai/dsh-session-projection' +// Type-only: resolves `ctx.get('tasks')` to the background task registry. +import type {} from '@deepseek-ai/dsh-tasks' +import type { TaskSnapshot } from '@deepseek-ai/dsh-tasks' // Type-only: resolves `ctx.get('sessionProjectionCache')` (the cold listing column). import type {} from '@deepseek-ai/dsh-session-projection-cache' // GoalError narrows domain rejections to their stable codes at the wire boundary. @@ -406,6 +409,22 @@ function subscribeSession(queue: FrameQueue>, session: Sess queue.push(frame({ type: 'session/subscribed', sessionId: session.id, lastSeq: session.seq - 1 })) } +/** + * Project registry snapshots onto the wire view, dropping the three internal + * fields {@link TaskView} documents as absent. + */ +function taskViews(snapshots: readonly TaskSnapshot[]): TaskView[] { + return snapshots.map(task => ({ + id: task.id, + kind: task.kind, + label: task.label, + status: task.status, + ...task.detail === undefined ? {} : { detail: task.detail }, + startedAt: task.startedAt, + ...task.finishedAt === undefined ? {} : { finishedAt: task.finishedAt }, + })) +} + /** * Whether the session's conversation has started: no turn has run yet (a * turn is one model-loop execution). Standalone plugin events — command @@ -3212,6 +3231,19 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro queue.push(frame({ type: 'session/queue', sessionId: session.id, items: queueItems(agent) })) } } + // Background-task baseline. `ctx.agents.get` is the non-resuming read: + // a session with no live Agent owns no tasks, so it correctly sees only + // the unowned ones, and listing never revives a cold session. An empty + // set sends nothing — absence is how the client reads "no tasks". + const tasks = ctx.get('tasks') + if (tasks !== undefined) { + for (const session of ctx.sessions.list()) { + const views = taskViews(tasks.list(ctx.agents.get(session.id))) + if (views.length > 0) { + queue.push(frame({ type: 'session/tasks', sessionId: session.id, tasks: views })) + } + } + } // Per-session open-call table for result-view pairing. Bounded by the // per-turn call count: entries clear on turn/end; a table miss (stream // opened mid-turn) backscans the session's in-memory events instead. @@ -3239,10 +3271,36 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro }), ctx.on('session/created', (session: Session) => { subscribeSession(queue, session) + // The subscribe frame clears the client's task mirror, and a + // session born after the stream opened missed the baseline loop. + // Unowned tasks are visible to it from birth, so without this it + // would show none until the next registry change. + const views = tasks === undefined ? [] : taskViews(tasks.list(ctx.agents.get(session.id))) + if (views.length > 0) { + queue.push(frame({ type: 'session/tasks', sessionId: session.id, tasks: views })) + } }), ctx.on('session/disposed', (session: Session) => { openCalls.delete(session.id) }), + ...tasks === undefined ? [] : [tasks.onTasksChanged((owner) => { + if (owner !== undefined) { + // The exact owner instance the fence compares against, so the + // push stays correct even while that Agent's scope is tearing + // down and a lookup by id would already miss. + queue.push(frame({ type: 'session/tasks', sessionId: owner.id, tasks: taskViews(tasks.list(owner)) })) + return + } + // An unowned task is visible to every caller, so every subscribed + // session's set changed with it. + for (const session of ctx.sessions.list()) { + queue.push(frame({ + type: 'session/tasks', + sessionId: session.id, + tasks: taskViews(tasks.list(ctx.agents.get(session.id))), + })) + } + })], ] return queue.iterate(signal, () => { muxQueues.delete(queue) diff --git a/packages/host/apiproxy/src/api/events.schema.ts b/packages/host/apiproxy/src/api/events.schema.ts index c06efb9057..02516c13bb 100644 --- a/packages/host/apiproxy/src/api/events.schema.ts +++ b/packages/host/apiproxy/src/api/events.schema.ts @@ -13,6 +13,7 @@ import { approvalRequestIdSchema } from './approvals.schema.ts' import { contentBlockSchema, messageIdSchema, sessionEventSchema, sessionIdSchema, toolEventViewSchema, } from './sessions.schema.ts' +import { taskViewSchema } from './tasks.schema.ts' import { workspaceIdSchema, workspaceViewSchema } from './workspace.schema.ts' /** Question fields validated strictly against core dsh-user-interaction. */ @@ -58,6 +59,7 @@ export const muxFrameSchema = z.discriminatedUnion('type', [ message: messageSchema, })), }), + z.object({ type: z.literal('session/tasks'), sessionId: sessionIdSchema, tasks: z.array(taskViewSchema) }), // value stays wide: it already passed its unit's own schema on the host, // and deep-validating here would import every domain's schema into the carrier. z.object({ type: z.literal('session/projection'), sessionId: sessionIdSchema, key: z.string().min(1), value: z.unknown(), seq: z.number().int().nonnegative() }), diff --git a/packages/host/apiproxy/src/api/events.ts b/packages/host/apiproxy/src/api/events.ts index 351ea4115e..73bb9d8bc2 100644 --- a/packages/host/apiproxy/src/api/events.ts +++ b/packages/host/apiproxy/src/api/events.ts @@ -14,6 +14,7 @@ import type { CallId } from '@deepseek-ai/dsh-llm/brand' import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types' import type { ToolCallView, ToolResultView } from '@deepseek-ai/dsh-tools/presentation' import type { RpcError, RpcId, RpcRequest } from './rpc.ts' +import type { TaskView } from './tasks.ts' import type { WorkspaceView } from './workspace.ts' // Client-side consumers take the render-intent vocabulary from the contract; @@ -81,6 +82,20 @@ export type MuxFrame = * in QueueDock, while pending steering renders at the conversation tail. */ | { type: 'session/queue'; sessionId: SessionId; items: QueuedInboxItem[] } + /** + * Complete set of background tasks this session can see, after every registry + * commit that changes it: registration, the stopping transition, settlement, + * and owner-disposal removal. The registry is process-local and holds no + * durable event, so — exactly like `session/queue` — the whole snapshot is + * what makes a start, a kill, a reconnect, and a second tab converge on one + * authoritative value. + * + * Sent as a subscription baseline only for a session that currently has + * tasks; an absent key means an empty set. A change that empties the set + * still sends `[]`, since that transition is the only one absence cannot + * express. + */ + | { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] } /** * One projection unit's finished value changed (session-projection RFC). * Live push state, never logged — replay recomputes on the host (the diff --git a/packages/host/apiproxy/src/api/index.ts b/packages/host/apiproxy/src/api/index.ts index e8eb3f3272..f49dfc9699 100644 --- a/packages/host/apiproxy/src/api/index.ts +++ b/packages/host/apiproxy/src/api/index.ts @@ -48,6 +48,7 @@ export type { SubagentAddress, SubagentCatalog, SubagentInterruptReceipt, SubagentListEntry, SubagentPromptReceipt, SubagentsApi, } from './subagents.ts' +export type { TaskView } from './tasks.ts' export type { WorkspaceApi, WorkspaceId, WorkspaceView } from './workspace.ts' export type { CommandsApi, CommandDescriptor } from './commands.ts' export type { SkillsApi, SkillEntry } from './skills.ts' diff --git a/packages/host/apiproxy/src/api/tasks.schema.ts b/packages/host/apiproxy/src/api/tasks.schema.ts new file mode 100644 index 0000000000..263b895b45 --- /dev/null +++ b/packages/host/apiproxy/src/api/tasks.schema.ts @@ -0,0 +1,33 @@ +/** + * tasks domain zod schemas: the branded task id and the wire view carried by + * `session/tasks` frames. + */ + +import { z } from 'zod' +import type { TaskId } from '@deepseek-ai/dsh-tasks/brand' +import type { TaskView } from './tasks.ts' +import type { Wire } from './rpc.schema.ts' + +/** TaskId: one brand cast after non-empty string validation. */ +export const taskIdSchema = z.string().min(1) as unknown as z.ZodType + +/** + * One wire task view. `kind` stays an open string because producer plugins + * extend the registry's kind map by declaration merging, so the closed set is + * not knowable at this boundary. + */ +export const taskViewSchema = z.object({ + id: taskIdSchema, + kind: z.string().min(1), + label: z.string().min(1), + status: z.union([ + z.literal('running'), + z.literal('stopping'), + z.literal('completed'), + z.literal('killed'), + z.literal('failed'), + ]), + detail: z.string().optional(), + startedAt: z.number().int().nonnegative(), + finishedAt: z.number().int().nonnegative().optional(), +}) satisfies z.ZodType> diff --git a/packages/host/apiproxy/src/api/tasks.ts b/packages/host/apiproxy/src/api/tasks.ts new file mode 100644 index 0000000000..f327b7cc1d --- /dev/null +++ b/packages/host/apiproxy/src/api/tasks.ts @@ -0,0 +1,36 @@ +/** + * Browser-safe background-task domain contract. The registry's live records + * never cross the wire; a view is the subset a human list needs, minted fresh + * per push. + */ + +import type { TaskId } from '@deepseek-ai/dsh-tasks/brand' + +/** + * One background task as the client sees it. + * + * Three registry fields are deliberately absent. `ownerSession` is redundant + * beside the frame's own `sessionId`; `reported` is an internal notice-delivery + * bit with no user meaning; `outputLimitBytes` is producer-owned model + * presentation policy that never reaches a human surface. + */ +export interface TaskView { + /** Registry-issued `-N` identity, stable for the task's whole life. */ + id: TaskId + /** + * Producer kind (`bash`, `pwsh`, `pty-send`, `subagent`, …). Kept as a bare + * string because producer plugins extend the kind map by declaration merging, + * so no client build can enumerate the closed set. + */ + kind: string + /** Producer-supplied one-line label: the command, or the delegation description. */ + label: string + /** Current lifecycle state. */ + status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed' + /** Kind-specific status detail ('exit code: 3'), present once the producer supplied one. */ + detail?: string + /** Epoch ms when the task was registered. */ + startedAt: number + /** Epoch ms when the task settled; absent while live. */ + finishedAt?: number +} diff --git a/packages/host/apiproxy/tests/api-proxy-tasks.spec.ts b/packages/host/apiproxy/tests/api-proxy-tasks.spec.ts new file mode 100644 index 0000000000..0bb7aa0333 --- /dev/null +++ b/packages/host/apiproxy/tests/api-proxy-tasks.spec.ts @@ -0,0 +1,263 @@ +/** + * Background-task carrier paths of the host ApiProxy: the subscription + * baseline is sent only for a session that has tasks, every registry change + * pushes that owner's whole set, an unowned change fans out to every + * subscribed session, the projection drops the three internal snapshot + * fields, a composition without `ctx.tasks` emits nothing, and listing never + * resumes a cold session. + */ + +import { describe, expect, it } from 'vitest' +import { Context } from '@deepseek-ai/cordis' +import AgentRegistry, { Inbox } from '@deepseek-ai/dsh-agent' +import type { Agent } from '@deepseek-ai/dsh-agent' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' +import type { Session } from '@deepseek-ai/dsh-session' +import UserInteractionService from '@deepseek-ai/dsh-user-interaction' +import LocalTaskService from '@deepseek-ai/dsh-tasks-local' +import type { TaskOutcome } from '@deepseek-ai/dsh-tasks' +import type { MuxFrame, RpcRequest } from '@deepseek-ai/dsh-host-apiproxy/api' +import { RpcId } from '@deepseek-ai/dsh-host-apiproxy/api/rpc' +import { createApiProxy } from '@deepseek-ai/dsh-host-apiproxy' + +type TaskFrame = Extract + +/** + * A producer whose settlement the test drives. `cancel` deliberately does not + * settle, so a kill is observable as the distinct `stopping` step before the + * test supplies the terminal outcome and its detail. + */ +function producer(label = 'sleep 60') { + let settle!: (outcome: TaskOutcome) => void + // A stream producer, so the carrier CAN consume the cursor if it ever calls + // `read()`; `reads` is what proves it never does. + const reads = { count: 0 } + const spec = { + kind: 'bash' as const, + label, + run: () => ({ + cancel: () => {}, + done: new Promise((resolve) => { settle = resolve }), + readOutput: () => { reads.count += 1; return 'stolen output' }, + }), + } + return { spec, reads, settle: (outcome: TaskOutcome) => { settle(outcome) } } +} + +async function harness(withRegistry: boolean): Promise<{ ctx: Context; session: Session; agent: Agent }> { + const ctx = new Context() + await ctx.plugin(SessionStore) + await ctx.plugin(UserInteractionService) + await ctx.plugin(AgentRegistry) + if (withRegistry) { + await ctx.plugin(LocalTaskService) + ctx.tasks.attachSurface('api-proxy-test') + } + const session = ctx.sessions.create() + const agent = { + id: session.id, + session, + inbox: new Inbox(session, { inserted: () => {}, discarded: () => {}, claimed: () => {} }), + status: 'idle', + ctx, + } as Agent + ctx.agents.register(agent) + return { ctx, session, agent } +} + +const api = (ctx: Context) => createApiProxy(ctx, { defaultModelSelection: () => ({ provider: 'p', model: 'm' }), cwd: '/tmp' }) + +/** Drain the mux until `count` session/tasks frames arrived, then abort. */ +async function collect( + iterable: AsyncIterable>, + count: number, + abort: AbortController, +): Promise { + const frames: MuxFrame[] = [] + for await (const envelope of iterable) { + frames.push(envelope.payload) + if (frames.filter(frame => frame.type === 'session/tasks').length >= count) abort.abort() + } + return frames.filter((frame): frame is TaskFrame => frame.type === 'session/tasks') +} + +describe('session/tasks subscription baseline', () => { + it('is omitted for a session with no tasks — absence is the empty set', async () => { + const { ctx, session } = await harness(true) + const abort = new AbortController() + const stream = api(ctx).events.mux({ rpcId: RpcId('t-tasks-empty'), payload: {} }, abort.signal) + const frames: MuxFrame[] = [] + const drained = (async () => { + for await (const envelope of stream) { + frames.push(envelope.payload) + if (frames.some(frame => frame.type === 'session/subscribed')) abort.abort() + } + })() + await drained + expect(frames.some(frame => frame.type === 'session/tasks')).toBe(false) + expect(frames.some(frame => frame.type === 'session/subscribed')).toBe(true) + void session + }) + + it('carries the live set for a session that already has tasks when the stream opens', async () => { + const { ctx, session, agent } = await harness(true) + ctx.tasks.start({ ...producer('pnpm run build').spec, owner: agent }) + const abort = new AbortController() + const stream = api(ctx).events.mux({ rpcId: RpcId('t-tasks-baseline'), payload: {} }, abort.signal) + const [baseline] = await collect(stream, 1, abort) + expect(baseline?.sessionId).toBe(session.id) + expect(baseline?.tasks).toHaveLength(1) + const [task] = baseline?.tasks ?? [] + expect(task?.startedAt).toBeTypeOf('number') + expect({ ...task, startedAt: 0 }).toEqual({ + id: 'bash-1', + kind: 'bash', + label: 'pnpm run build', + status: 'running', + startedAt: 0, + }) + }) +}) + +describe('session/tasks change pushes', () => { + it('pushes the owner\'s whole set on registration, stopping, and settlement', async () => { + const { ctx, session, agent } = await harness(true) + const proxy = api(ctx) + const abort = new AbortController() + const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-changes'), payload: {} }, abort.signal) + const collected = collect(stream, 3, abort) + + const p = producer() + const id = ctx.tasks.start({ ...p.spec, owner: agent }) + ctx.tasks.kill(id, agent, 'test') + p.settle({ status: 'killed', detail: 'signal: SIGTERM' }) + + const frames = await collected + expect(frames.map(frame => frame.sessionId)).toEqual([session.id, session.id, session.id]) + expect(frames.map(frame => frame.tasks[0]?.status)).toEqual(['running', 'stopping', 'killed']) + // Terminal detail rides the same whole-set push; no separate signal. + expect(frames[2]?.tasks[0]?.detail).toBe('signal: SIGTERM') + expect(frames[2]?.tasks[0]?.finishedAt).toBeTypeOf('number') + }) + + it('drops ownerSession, reported, and outputLimitBytes from the wire view', async () => { + const { ctx, agent } = await harness(true) + const proxy = api(ctx) + const abort = new AbortController() + const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-fields'), payload: {} }, abort.signal) + const collected = collect(stream, 1, abort) + ctx.tasks.start({ ...producer().spec, owner: agent, outputLimitBytes: 1_024 }) + + const [frame] = await collected + const fields: readonly string[] = Object.keys(frame?.tasks[0] ?? {}) + expect([...fields].sort()).toEqual(['id', 'kind', 'label', 'startedAt', 'status']) + }) + + it('fans an unowned change out to every subscribed session', async () => { + const { ctx } = await harness(true) + const second = ctx.sessions.create() + const proxy = api(ctx) + const abort = new AbortController() + const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-unowned'), payload: {} }, abort.signal) + const collected = collect(stream, 2, abort) + + ctx.tasks.start(producer('open to every caller').spec) + + const frames = await collected + expect(new Set(frames.map(frame => frame.sessionId)).size).toBe(2) + expect(frames.some(frame => frame.sessionId === second.id)).toBe(true) + for (const frame of frames) expect(frame.tasks[0]?.label).toBe('open to every caller') + }) + + it('serves a cold session the unowned set without resuming it', async () => { + const { ctx } = await harness(true) + const coldId = SessionId('session-cold-tasks') + let loaded = false + ctx.provide('sessionPersistence', { + list: async () => [{ version: 0, id: coldId, createdAt: 5, cwd: '/tmp' }], + locate: () => undefined, + load: () => { loaded = true; throw new Error('task listing must not load a cold log') }, + } as never) + const proxy = api(ctx) + const abort = new AbortController() + const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-cold'), payload: {} }, abort.signal) + const collected = collect(stream, 1, abort) + + ctx.tasks.start(producer().spec) + await collected + expect(loaded).toBe(false) + expect(ctx.agents.get(coldId)).toBeUndefined() + }) +}) + +describe('session/tasks without the registry', () => { + it('emits no frames at all, so the client renders no entry point', async () => { + const { ctx, session } = await harness(false) + const proxy = api(ctx) + const abort = new AbortController() + const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-absent'), payload: {} }, abort.signal) + const frames: MuxFrame[] = [] + const drained = (async () => { + for await (const envelope of stream) { + frames.push(envelope.payload) + if (frames.filter(frame => frame.type === 'session/event').length >= 1) abort.abort() + } + })() + session.append('turn/start', { turn: 1 }) + await drained + expect(frames.some(frame => frame.type === 'session/tasks')).toBe(false) + }) +}) + +describe('session/tasks never consumes model output', () => { + it('drives the whole lifecycle without calling the single consuming cursor', async () => { + // `ctx.tasks.read()` consumes the one output cursor, so a carrier read + // silently takes bytes the model's `task_output` will never see. The + // failure is invisible at the call site, which is why this asserts the + // count rather than trusting review. + const { ctx, agent } = await harness(true) + const proxy = api(ctx) + const abort = new AbortController() + const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-no-read'), payload: {} }, abort.signal) + const collected = collect(stream, 3, abort) + + const p = producer() + const id = ctx.tasks.start({ ...p.spec, owner: agent }) + ctx.tasks.kill(id, agent, 'test') + p.settle({ status: 'killed', detail: 'signal: SIGTERM' }) + await collected + + expect(p.reads.count).toBe(0) + }) + + it('reads nothing while minting the subscription baseline either', async () => { + const { ctx, agent } = await harness(true) + const p = producer() + ctx.tasks.start({ ...p.spec, owner: agent }) + + const abort = new AbortController() + const stream = api(ctx).events.mux({ rpcId: RpcId('t-tasks-no-read-baseline'), payload: {} }, abort.signal) + const [baseline] = await collect(stream, 1, abort) + + expect(baseline?.tasks).toHaveLength(1) + expect(p.reads.count).toBe(0) + }) +}) + +describe('session/tasks baseline for a session born after the stream opened', () => { + it('carries the already-visible unowned set to the new session', async () => { + const { ctx } = await harness(true) + const proxy = api(ctx) + const abort = new AbortController() + const stream = proxy.events.mux({ rpcId: RpcId('t-tasks-late-session'), payload: {} }, abort.signal) + + // One unowned task exists before the new session is created; the subscribe + // frame clears the client mirror, so the baseline has to follow it. + ctx.tasks.start(producer('visible to every caller').spec) + const created = ctx.sessions.create() + + const frames = await collect(stream, 2, abort) + const forNew = frames.filter(frame => frame.sessionId === created.id) + expect(forNew.at(-1)?.tasks[0]?.label).toBe('visible to every caller') + }) +}) diff --git a/packages/host/apiproxy/tests/rpc-schemas.spec.ts b/packages/host/apiproxy/tests/rpc-schemas.spec.ts index 3be4bf5715..789639b70d 100644 --- a/packages/host/apiproxy/tests/rpc-schemas.spec.ts +++ b/packages/host/apiproxy/tests/rpc-schemas.spec.ts @@ -436,6 +436,11 @@ describe('events frame schemas', () => { }, ] }, { type: 'session/projection', sessionId: 's', key: 'todos', value: [{ content: 'x', status: 'pending' }], seq: 7 }, + { type: 'session/tasks', sessionId: 's', tasks: [] }, + { type: 'session/tasks', sessionId: 's', tasks: [ + { id: 'bash-1', kind: 'bash', label: 'pnpm run build', status: 'running', startedAt: 5 }, + { id: 'pty-send-2', kind: 'pty-send', label: 'send keys', status: 'failed', detail: 'exit code: 3', startedAt: 5, finishedAt: 9 }, + ] }, { type: 'stream/error', error: { code: 'internal', message: 'm', details: {} } }, ] for (const frame of frames) expect(muxFrameSchema.parse(frame)).toMatchObject({ type: frame.type }) @@ -444,6 +449,14 @@ describe('events frame schemas', () => { { type: 'session/projection', sessionId: 's', key: '', value: null, seq: 0 }, { type: 'session/projection', sessionId: 's', key: 'todos', value: null, seq: -1 }, { type: 'session/projection', sessionId: 's', key: 'todos', value: null, seq: 0.5 }, + // A producer kind stays an open string, but the closed status set and + // the identity/label bounds are the carrier's own wire contract. + { type: 'session/tasks', sessionId: 's', tasks: [{ id: '', kind: 'bash', label: 'l', status: 'running', startedAt: 0 }] }, + { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: '', label: 'l', status: 'running', startedAt: 0 }] }, + { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: '', status: 'running', startedAt: 0 }] }, + { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: 'l', status: 'pending', startedAt: 0 }] }, + { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: 'l', status: 'running', startedAt: -1 }] }, + { type: 'session/tasks', sessionId: 's', tasks: [{ id: 'bash-1', kind: 'bash', label: 'l', status: 'completed', startedAt: 0, finishedAt: 0.5 }] }, ]) expect(() => muxFrameSchema.parse(invalid)).toThrow() expect(askUserQuestionItemSchema.parse({ id: 'q', question: 'Q?' }).id).toBe('q') }) diff --git a/packages/host/apiproxy/tsconfig.json b/packages/host/apiproxy/tsconfig.json index 42b60ce906..2f4622185c 100644 --- a/packages/host/apiproxy/tsconfig.json +++ b/packages/host/apiproxy/tsconfig.json @@ -74,6 +74,9 @@ { "path": "../../skill/skill" }, + { + "path": "../../tasks/tasks" + }, { "path": "../../interaction/commands" }, diff --git a/packages/mcp/mcp-client/README.i18n.yaml b/packages/mcp/mcp-client/README.i18n.yaml index 9568c08454..c66d8ffba8 100644 --- a/packages/mcp/mcp-client/README.i18n.yaml +++ b/packages/mcp/mcp-client/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/mcp/mcp-client/README.md -README.md: 76d1271f6f7a3e9c959bdcf5e969906f25563c56 -README.zh.md: b2da1119af3a8d52761a5040059e7a9d922aa567 +README.md: 97ac9c173fc2b848f524e8c0fdd93eca072567af +README.zh.md: 1b5b5c523e0a477db30f97a748651dbe7e6992ea diff --git a/packages/mcp/mcp-client/README.md b/packages/mcp/mcp-client/README.md index 76d1271f6f..97ac9c173f 100644 --- a/packages/mcp/mcp-client/README.md +++ b/packages/mcp/mcp-client/README.md @@ -45,6 +45,10 @@ The model sees `mcp__github__create_issue`, `mcp__web__search`, … — the same | `headers` | http | no | Extra headers (e.g. auth tokens) | | `toolCallTimeoutMs` | both | no | Timeout per `callTool` invocation (default 60000) | | `failOnStartupError` | both | no | Reject plugin activation when initial connection or tool synchronization fails (default `false`) | +| `reconnect.enabled` | both | no | Reconnect automatically after a lost connection (default `true`) | +| `reconnect.initialDelayMs` | both | no | First reconnect delay in ms; doubles per consecutive failed attempt (default 500) | +| `reconnect.maxDelayMs` | both | no | Backoff ceiling in ms; also the uptime after which the attempt budget resets (default 30000) | +| `reconnect.maxAttempts` | both | no | Consecutive failed attempts per outage before giving up for good (default 10) | ## Tool naming @@ -62,7 +66,9 @@ Every MCP tool has two names: the raw MCP name (sent on the wire in `tools/call` - Tool execute: `client.callTool({ name: rawName, arguments }, { signal })` with timeout + abort support—the public name is never sent to the server. - Canonical success is `{ content: JsonValue[], structuredContent? }`; complete JSON MCP blocks survive for programmatic callers. A supported advertised `outputSchema` validates `structuredContent`; unsupported schema vocabulary falls back to unconstrained `JsonValue`. - Native/model rendering keeps the existing text projection: text blocks join with newlines while image, audio, resource, and unsupported blocks become placeholders. -- On disconnect/crash: no auto-reconnect. Registered tools remain until plugin disposal or a successful re-sync, and calls can fail against the closed transport; reload with HMR or restart the Host to reconnect. +- On disconnect/crash: the supervisor restarts the original server config with exponential backoff (`reconnect.initialDelayMs` doubling up to `reconnect.maxDelayMs`) and re-runs discovery on success — the recovered generation replaces the previous one, so tools neither duplicate nor leak. During the outage the last good generation stays registered; calls against it fail until recovery. +- Reconnection is budgeted per outage: after `reconnect.maxAttempts` consecutive failures the server's tools are unregistered and reconnection stops until an HMR reload or Host restart. A connection that survives past `maxDelayMs` resets the budget, so an occasionally-crashing server recovers indefinitely while a crash-looping one — even with briefly successful connects — still exhausts the cap instead of restarting forever. +- Reconnect states are user-visible in logs: reconnecting (warn, with attempt count and delay), recovered (info), final failure and disabled-loss (error). Disposal cancels any pending reconnect. With `reconnect.enabled: false`, a lost connection keeps tools registered but failing until a reload — the manual-recovery behavior. ## Services consumed @@ -76,7 +82,7 @@ Every MCP tool has two names: the raw MCP name (sent on the wire in `tools/call` #### What the model sees -After initial discovery succeeds, each advertised MCP tool appears as a native tool named `mcp____` (or its deterministic normalized form), with the server-provided description and input schema. A successful re-sync replaces the generation; plugin disposal removes it. +After initial discovery succeeds, each advertised MCP tool appears as a native tool named `mcp____` (or its deterministic normalized form), with the server-provided description and input schema. A successful re-sync — including the one after an automatic reconnect — replaces the generation; plugin disposal or an exhausted reconnect budget removes it. #### Token effect @@ -84,7 +90,7 @@ Data-dependent schema cost is paid on every request while the tools are register #### KV Cache effect -Prefix-stable while the discovered tool set and schemas are unchanged. A re-sync that adds, removes, renames, or changes a tool replaces definitions and may invalidate reuse from the first changed schema token. +Prefix-stable while the discovered tool set and schemas are unchanged. A re-sync that adds, removes, renames, or changes a tool replaces definitions and may invalidate reuse from the first changed schema token; a reconnect that recovers an unchanged list reproduces identical definitions and stays prefix-stable. ### Tool-call history and results @@ -104,6 +110,6 @@ Append-only; newly visible content follows the reusable request prefix and does - **Tools are the only bridged MCP capability** — Resources and Prompts have no harness consumption surface and are deferred. - **Startup timeout is inherited from the MCP SDK** — DSH does not yet expose a connection/discovery timeout. Each initialize or paginated `tools/list` request uses the SDK's 60-second default, so an unresponsive server or cursor chain can delay both activation and teardown while the initial synchronization settles. -- **Crash recovery is manual** — transport closure does not auto-reconnect; registered tools can remain visible but fail against the closed transport until an HMR reload or Host restart. +- **Reconnect triggers on transport close** — a crashed stdio child fires it; Streamable HTTP failures surface per request and through the SDK transport's own SSE-stream recovery, so an unreachable HTTP server is retried per call rather than respawned by the supervisor. - **Native non-text rendering is lossy** — image, audio, and resource payloads become placeholders in model context even though the execution-local canonical value preserves their JSON blocks. Richer Native multimedia projection is deferred. - **Unsupported MCP output schemas are not enforced** — `structuredContent` falls back to `JsonValue` when the advertised schema uses vocabulary outside the harness subset. diff --git a/packages/mcp/mcp-client/README.zh.md b/packages/mcp/mcp-client/README.zh.md index b2da1119af..1b5b5c523e 100644 --- a/packages/mcp/mcp-client/README.zh.md +++ b/packages/mcp/mcp-client/README.zh.md @@ -45,6 +45,10 @@ MCP 客户端桥接插件：连接外部 [Model Context Protocol](https://modelc | `headers` | http | 否 | 额外标头（例如认证 token） | | `toolCallTimeoutMs` | 两者 | 否 | 每次 `callTool` 调用的超时（默认 60000） | | `failOnStartupError` | 两者 | 否 | 初始连接或工具同步失败时拒绝插件激活（默认 `false`） | +| `reconnect.enabled` | 两者 | 否 | 连接丢失后自动重新连接（默认 `true`） | +| `reconnect.initialDelayMs` | 两者 | 否 | 首次重连延迟（毫秒）；每次连续失败尝试翻倍（默认 500） | +| `reconnect.maxDelayMs` | 两者 | 否 | 退避上限（毫秒）；同时也是重置尝试预算所需的正常运行时长（默认 30000） | +| `reconnect.maxAttempts` | 两者 | 否 | 每次中断期间连续失败尝试次数上限，超出后彻底放弃（默认 10） | ## 工具命名 @@ -62,7 +66,9 @@ MCP 客户端桥接插件：连接外部 [Model Context Protocol](https://modelc - 工具执行：`client.callTool({ name: rawName, arguments }, { signal })`，支持超时 + 中止；公开名称绝不会发给服务器。 - 规范成功值是 `{ content: JsonValue[], structuredContent? }`；完整的 JSON MCP 块会保留给编程调用方。受支持且已声明的 `outputSchema` 会验证 `structuredContent`；不受支持的 schema 词汇会回退为不受约束的 `JsonValue`。 - Native／模型渲染保留现有文本投影：文本块以换行连接，图片、音频、资源和不受支持的块会变成占位符。 -- 断开／崩溃时：不自动重新连接。已注册工具会一直保留到对插件执行 dispose（资源释放）或成功重新同步，针对已关闭传输的调用可能失败；请通过 HMR 重新加载或重启 Host 来重新连接。 +- 断开／崩溃时：supervisor 以指数退避（`reconnect.initialDelayMs` 逐次翻倍，上限 `reconnect.maxDelayMs`）重启原始服务器配置，成功后重新执行发现——恢复的世代会替换前一个，因此工具既不会重复也不会泄漏。中断期间最后一个正常世代保持注册；针对它的调用在恢复前会失败。 +- 重连按中断预算控制：连续失败达到 `reconnect.maxAttempts` 次后，该服务器的工具会被注销，重连停止，直到 HMR 重载或重启 Host。连接存活超过 `maxDelayMs` 会重置预算，因此偶尔崩溃的服务器可以无限恢复，而崩溃循环的服务器——即使短暂连接成功——仍会耗尽上限而非永远重启。 +- 重连状态在日志中对用户可见：reconnecting（warn，含尝试次数和延迟）、recovered（info）、最终失败和 disabled-loss（error）。dispose（资源释放）会取消任何待执行的重连。设置 `reconnect.enabled: false` 时，连接丢失后工具保持注册但调用失败，直到重载——即手动恢复行为。 ## 消费的服务 @@ -76,7 +82,7 @@ MCP 客户端桥接插件：连接外部 [Model Context Protocol](https://modelc #### 模型看到的内容 -初始发现成功后，每个已声明的 MCP 工具都会显示为名为 `mcp____`（或其确定性规范化形式）的原生工具，并携带服务器提供的描述和输入 schema。成功的重新同步会替换整个世代；对插件执行 dispose 会移除该世代。 +初始发现成功后，每个已声明的 MCP 工具都会显示为名为 `mcp____`（或其确定性规范化形式）的原生工具，并携带服务器提供的描述和输入 schema。成功的重新同步——包括自动重连后的同步——会替换整个世代；对插件执行 dispose（资源释放）或重连预算耗尽会移除该世代。 #### Token 影响 @@ -84,7 +90,7 @@ MCP 客户端桥接插件：连接外部 [Model Context Protocol](https://modelc #### KV Cache 影响 -只要已发现工具集合及其 schema 不变，前缀就保持稳定。增加、移除、重命名或更改工具的重新同步会替换定义，并可能使从第一个变化的 schema token 起的复用失效。 +只要已发现工具集合及其 schema 不变，前缀就保持稳定。增加、移除、重命名或更改工具的重新同步会替换定义，并可能使从第一个变化的 schema token 起的复用失效；恢复了未变列表的重连会生成完全相同的定义，前缀保持稳定。 ### 工具调用历史与结果 @@ -104,6 +110,6 @@ MCP 客户端桥接插件：连接外部 [Model Context Protocol](https://modelc - **只桥接 MCP 的工具能力**：资源和提示词没有 harness 消费接口，暂缓实现。 - **启动超时继承自 MCP SDK**：DSH 尚未公开连接／发现超时。每次 initialize 请求或分页 `tools/list` 请求都使用 SDK 默认的 60 秒，因此在初始同步完成期间，无响应的 server 或 cursor chain 可能同时延迟激活与 teardown。 -- **崩溃恢复需要手动触发**：传输关闭后不会自动重新连接；已注册工具可能仍然可见，但会因传输已关闭而调用失败，直到 HMR 重载或重启 Host。 +- **重连在传输关闭时触发**：崩溃的 stdio 子进程会触发重连；Streamable HTTP 失败通过每次请求以及 SDK 传输自身的 SSE（Server-Sent Events）流恢复机制暴露，因此不可达的 HTTP 服务器会按调用重试，而非由 supervisor 重新 spawn。 - **Native 非文本渲染有损**：图片、音频与资源载荷在模型上下文中会变成占位符，即使执行局部的规范值保留了其 JSON 块。更丰富的 Native 多媒体投影暂缓实现。 - **不强制执行不受支持的 MCP 输出 schema**：已声明 schema 使用 harness 子集之外的词汇时，`structuredContent` 会回退到 `JsonValue`。 diff --git a/packages/mcp/mcp-client/package.json b/packages/mcp/mcp-client/package.json index 99b3474c6e..1cd533c3db 100644 --- a/packages/mcp/mcp-client/package.json +++ b/packages/mcp/mcp-client/package.json @@ -35,6 +35,7 @@ "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-subprocess": "workspace:^", + "@deepseek-ai/dsh-timeout": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "@deepseek-ai/cordis": "workspace:^" }, @@ -47,6 +48,7 @@ "@deepseek-ai/dsh-invariants": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-subprocess": "workspace:^", + "@deepseek-ai/dsh-timeout": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "@modelcontextprotocol/server-everything": "^2026.7.4", "@modelcontextprotocol/server-filesystem": "^2026.7.4", diff --git a/packages/mcp/mcp-client/src/connection.ts b/packages/mcp/mcp-client/src/connection.ts new file mode 100644 index 0000000000..f452e3a81d --- /dev/null +++ b/packages/mcp/mcp-client/src/connection.ts @@ -0,0 +1,351 @@ +/** + * Connection supervisor: owns the MCP client/transport generations for one + * plugin instance, keeps the harness tool registry in sync with the live + * generation, and — when the connection drops — restarts the configured + * server with bounded exponential backoff. + * + * One outage shares one attempt budget (`maxAttempts` consecutive failed + * attempts, delays doubling from `initialDelayMs` up to `maxDelayMs`). A + * connection that stays up past the stability window closes the outage, so + * the next disconnect starts a fresh budget while a crash-looping server — + * even one whose connects briefly succeed — still exhausts the cap instead of + * restarting forever. Exhaustion unregisters the server's tools and stops; + * disposal (including HMR) is the only way back from that state. + * + * @module + */ + +import { Client } from '@modelcontextprotocol/sdk/client/index.js' +import { ToolListChangedNotificationSchema } from '@modelcontextprotocol/sdk/types.js' +import type { Context } from '@deepseek-ai/cordis' +import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout' +import { createTransport } from './transport.ts' +import { syncTools } from './tools.ts' +import type { ToolBridgeOptions, ToolDisposers } from './tools.ts' +import type { Config } from './index.ts' + +/** Automatic reconnect policy for one MCP server connection. */ +export interface ReconnectConfig { + /** Reconnect automatically after a lost connection (default true). */ + enabled?: boolean + /** First reconnect delay in milliseconds; doubles per consecutive failed attempt (default 500). */ + initialDelayMs?: number + /** Backoff ceiling in milliseconds; also the uptime after which the attempt budget resets (default 30000). */ + maxDelayMs?: number + /** Consecutive failed attempts per outage before giving up for good (default 10). */ + maxAttempts?: number +} + +/** Defaults shared by the Config schema and {@link resolveReconnectPolicy}. */ +export const RECONNECT_DEFAULTS: Required = Object.freeze({ + enabled: true, + initialDelayMs: 500, + maxDelayMs: 30_000, + maxAttempts: 10, +}) + +// The SDK's stdio transport owns two two-second termination grace periods. +// Keep one additional second for the process-close event that proves the old +// generation is gone; timing out fails closed instead of overlapping children. +const GENERATION_CLOSE_TIMEOUT_MS = 5_000 + +/** Fully resolved reconnect policy captured at plugin load. */ +export type ResolvedReconnectPolicy = Readonly> + +/** + * The one explicit resolve step from raw reconnect config to the policy the + * supervisor runs. Programmatic construction may bypass Schemastery + * normalization, so every default and bound is re-judged here — misconfiguration + * fails the plugin instance at load. + * + * @param config - Raw `reconnect` config; omission uses the defaults. + * @param path - Diagnostic prefix naming the config location in thrown messages. + * @returns The frozen resolved policy. + */ +export function resolveReconnectPolicy(config: ReconnectConfig | undefined, path: string): ResolvedReconnectPolicy { + if (config !== undefined) { + for (const key of Object.keys(config)) { + if (!Object.hasOwn(RECONNECT_DEFAULTS, key)) throw new Error(`${path}.${key} is not a reconnect option`) + } + } + const enabled = config?.enabled ?? RECONNECT_DEFAULTS.enabled + const initialDelayMs = config?.initialDelayMs ?? RECONNECT_DEFAULTS.initialDelayMs + const maxDelayMs = config?.maxDelayMs ?? RECONNECT_DEFAULTS.maxDelayMs + const maxAttempts = config?.maxAttempts ?? RECONNECT_DEFAULTS.maxAttempts + /* jscpd:ignore-start — domain-specific delay validation parallels llm retry-policy; not extractable */ + if (!Number.isFinite(initialDelayMs) || initialDelayMs <= 0 || initialDelayMs > MAX_TIMER_DELAY_MS) { + throw new Error(`${path}.initialDelayMs must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`) + } + if (!Number.isFinite(maxDelayMs) || maxDelayMs <= 0 || maxDelayMs > MAX_TIMER_DELAY_MS) { + throw new Error(`${path}.maxDelayMs must be a positive finite number no greater than ${MAX_TIMER_DELAY_MS}`) + } + if (initialDelayMs > maxDelayMs) { + throw new Error(`${path}.initialDelayMs must be less than or equal to maxDelayMs`) + } + if (!Number.isInteger(maxAttempts) || maxAttempts < 1) { + throw new Error(`${path}.maxAttempts must be a positive integer`) + } + /* jscpd:ignore-end */ + return Object.freeze({ enabled, initialDelayMs, maxDelayMs, maxAttempts }) +} + +/** Result from the initial connection attempt, for startup-await semantics. */ +export interface ConnectionOutcome { + /** If the initial connection or tool sync failed, the error; otherwise absent. */ + error?: unknown +} + +/** Handle for one plugin instance's supervised connection. */ +export interface ConnectionHandle { + /** + * Settles when the first connection attempt completes (success or failure). + * The supervisor enters its reconnect loop regardless; the caller decides + * whether a failed startup is fatal via `failOnStartupError`. + */ + ready: Promise + /** + * Stop reconnection, close the live client, wait for the in-flight attempt + * and queued tool syncs to quiesce, then unregister every tool this server + * still owns. + */ + dispose(): Promise +} + +/** + * Start the supervised connection for one MCP server and keep it alive per + * the reconnect policy. + * + * @param ctx - Cordis context providing the `tools` registry and logger. + * @param config - Resolved plugin config selecting the transport and server identity. + * @param policy - Resolved reconnect policy from {@link resolveReconnectPolicy}. + * @returns Handle with a `ready` promise for startup-await and a `dispose` for teardown. + */ +export function startConnection(ctx: Context, config: Config, policy: ResolvedReconnectPolicy): ConnectionHandle { + const label = `mcp-client(${config.serverName})` + const opts: ToolBridgeOptions = { + registrationFailure: 'contain', + serverName: config.serverName, + toolCallTimeoutMs: config.toolCallTimeoutMs, + } + // The initial sync uses 'throw' when failOnStartupError is configured, so + // a registration conflict propagates to the startup-await path. Re-syncs + // and reconnect syncs always contain conflicts. + const startupOpts: ToolBridgeOptions = config.failOnStartupError + ? { ...opts, registrationFailure: 'throw' } + : opts + + let disposed = false + /** Current generation: the connecting or connected client; undefined during backoff waits and after final failure. */ + let client: Client | undefined + /** Close signal paired with {@link client}; captured by dispose before current ownership is cleared. */ + let clientClosed: Promise | undefined + /** Live tool registrations owned by this server; only {@link enqueueSync} and dispose swap it. */ + let disposers: ToolDisposers = new Map() + let reconnectTimer: NodeJS.Timeout | undefined + /** Consecutive failed connection attempts within the current outage. */ + let failedAttempts = 0 + /** When the current generation finished connect + initial sync; undefined while down. */ + let connectedAt: number | undefined + /** The real error from the first connection attempt, for startup-await diagnostics. */ + let firstAttemptError: unknown + + /** A generation may act only while it is the current one on a live plugin. */ + const isCurrent = (generation: Client): boolean => !disposed && client === generation + + /** + * Serializes every syncTools call — initial syncs and notification re-syncs + * across all generations — so two syncs can never interleave their + * dispose-previous/register-next swap (which would double-dispose one + * generation and leak another). + */ + let syncChain: Promise = Promise.resolve() + function enqueueSync(generation: Client, syncOpts: ToolBridgeOptions = opts): Promise { + const run = syncChain.then(async () => { + if (!isCurrent(generation)) return + disposers = await syncTools(generation, ctx, syncOpts, disposers) + }) + // The chain tail must survive a failed sync; the enqueuing caller owns reporting. + syncChain = run.catch(() => {}) + return run + } + + /** One disconnect decision per generation: the isCurrent guard makes racing close/error signals idempotent. */ + function generationDown(generation: Client): void { + if (!isCurrent(generation)) return + client = undefined + clientClosed = undefined + scheduleReconnect() + } + + /** Wait for the transport-owned close signal without letting a broken transport wedge teardown forever. */ + function waitForClose(closed: Promise): Promise { + return new Promise((resolve) => { + const timeout = setTimeout(() => { resolve(false) }, GENERATION_CLOSE_TIMEOUT_MS) + timeout.unref() + void closed.then(() => { + clearTimeout(timeout) + resolve(true) + }) + }) + } + + function scheduleReconnect(): void { + const lostEstablishedConnection = connectedAt !== undefined + if (!policy.enabled) { + const message = lostEstablishedConnection + ? 'connection lost and reconnect is disabled — registered tools will fail until an HMR reload or Host restart' + : 'connection failed and reconnect is disabled — no tools were registered; reload the plugin or restart the Host to connect' + ctx.logger.error(`${label}: ${message}`) + return + } + // A connection that stayed up past the stability window (= maxDelayMs, the + // longest backoff spacing) ended the previous outage: start a fresh budget. + if (connectedAt !== undefined && Date.now() - connectedAt >= policy.maxDelayMs) failedAttempts = 0 + connectedAt = undefined + failedAttempts += 1 + if (failedAttempts > policy.maxAttempts) { + // Enqueue the give-up disposal so it cannot race an in-flight sync's + // phase-2 swap (which checks isCurrent inside the queue). + syncChain = syncChain.then(() => { + for (const dispose of disposers.values()) dispose() + disposers = new Map() + }) + ctx.logger.error(`${label}: giving up after ${policy.maxAttempts} consecutive failed reconnect attempts — tools unregistered; reload the plugin or restart the Host to reconnect`) + return + } + const delayMs = Math.min(policy.maxDelayMs, policy.initialDelayMs * 2 ** (failedAttempts - 1)) + const action = lostEstablishedConnection ? 'connection lost; reconnecting' : 'connection failed; retrying' + ctx.logger.warn(`${label}: ${action} in ${delayMs}ms (attempt ${failedAttempts}/${policy.maxAttempts})`) + reconnectTimer = setTimeout(() => { + reconnectTimer = undefined + settling = connectGeneration(false) + }, delayMs) + // An armed reconnect timer must never hold the process open on its own. + reconnectTimer.unref() + } + + /** + * One connection attempt: fresh transport + client (the MCP SDK binds a + * Protocol to one transport for life), connect, then queue the initial tool + * sync. The startup flag belongs to the attempt rather than the shared sync + * queue, so an early notification cannot consume strict startup semantics. + * Every failure funnels through {@link generationDown}; success arms the + * onclose-driven disconnect path. Never rejects. + * + * @param startup - Whether this is the plugin's activation attempt. + */ + async function connectGeneration(startup: boolean): Promise { + const generation = new Client( + { name: 'dsh-mcp-client', version: '0.0.1' }, + { capabilities: {} }, + ) + const closed: PromiseWithResolvers = Promise.withResolvers() + let attemptSettled = false + let closeObserved = false + const hasClosed = (): boolean => closeObserved + client = generation + clientClosed = closed.promise + generation.onclose = () => { + closeObserved = true + closed.resolve() + // A failed connect owns its close barrier in the catch path below. An + // established generation can transition down directly from this signal. + if (attemptSettled) generationDown(generation) + } + // Registered before connect so a list change during the initial sync is + // queued behind it rather than dropped. + generation.setNotificationHandler( + ToolListChangedNotificationSchema, + async () => { + if (!isCurrent(generation)) return + ctx.logger.info(`${label}: tool list changed, re-syncing`) + try { + await enqueueSync(generation) + } catch (error) { + // Fetch-phase failure: the previous generation is still registered + // and `disposers` still owns it — keep serving the last good list. + if (!disposed) ctx.logger.error(`${label}: tool re-sync failed: ${String(error)}`) + } + }, + ) + try { + await generation.connect(createTransport(config)) + if (hasClosed()) { + attemptSettled = true + generationDown(generation) + return + } + await enqueueSync(generation, startup ? startupOpts : opts) + } catch (error) { + if (firstAttemptError === undefined) firstAttemptError = error + // Disposal clears current ownership before it closes the generation, so + // only a live supervisor reports an attempt failure. + if (isCurrent(generation)) ctx.logger.warn(`${label}: connection attempt failed: ${String(error)}`) + try { await generation.close() } catch { /* transport already gone */ } + const quiesced = hasClosed() || await waitForClose(closed.promise) + attemptSettled = true + if (!isCurrent(generation)) return + if (!quiesced) { + client = undefined + clientClosed = undefined + ctx.logger.error(`${label}: failed generation did not close within ${GENERATION_CLOSE_TIMEOUT_MS}ms — reconnect stopped to avoid overlapping server processes; reload the plugin or restart the Host to retry`) + return + } + generationDown(generation) + return + } + attemptSettled = true + if (hasClosed()) { + generationDown(generation) + return + } + if (!isCurrent(generation)) return + connectedAt = Date.now() + if (failedAttempts > 0) ctx.logger.info(`${label}: reconnected and re-synced tools (attempt ${failedAttempts}/${policy.maxAttempts})`) + } + + /** The in-flight (or last settled) connection attempt; dispose awaits it for quiescence. */ + let settling = connectGeneration(true) + + // The ready promise settles when the first attempt finishes (regardless of + // success). If the first attempt fails and reconnect is enabled, the + // supervisor is already scheduling a retry — ready just reports the outcome. + const ready: Promise = settling.then(() => { + // After settling: if client is set the initial connect+sync succeeded. + // If not, the supervisor either scheduled a retry (error logged) or gave + // up (error logged). Either way the outcome is reported with the real error. + // Note: settling.then() is a microtask; stdio onclose is a macrotask — so + // a server that crashes AFTER a successful initial sync cannot flip client + // to undefined before this continuation runs. + if (client !== undefined) return {} + /* v8 ignore next -- defensive: firstAttemptError is always set when connect/sync fails */ + return { error: firstAttemptError ?? new Error(`${label}: initial connection failed`) } + }) + + return { + ready, + async dispose(): Promise { + disposed = true + if (reconnectTimer !== undefined) { + clearTimeout(reconnectTimer) + reconnectTimer = undefined + } + const current = client + const currentClosed = clientClosed + client = undefined + clientClosed = undefined + if (current !== undefined) { + try { await current.close() } catch { /* transport already gone */ } + if (currentClosed !== undefined && !await waitForClose(currentClosed)) { + ctx.logger.error(`${label}: generation did not close within ${GENERATION_CLOSE_TIMEOUT_MS}ms during disposal — server shutdown may be incomplete`) + } + } + // Quiesce, don't just request it: the in-flight attempt enqueues its + // sync before settling, so awaiting both leaves `disposers` final. + await settling + await syncChain + for (const dispose of disposers.values()) dispose() + disposers = new Map() + }, + } +} diff --git a/packages/mcp/mcp-client/src/index.ts b/packages/mcp/mcp-client/src/index.ts index 7f35ae3ed3..5a2a52f55d 100644 --- a/packages/mcp/mcp-client/src/index.ts +++ b/packages/mcp/mcp-client/src/index.ts @@ -15,14 +15,14 @@ import type { Context } from '@deepseek-ai/cordis' import z from '@deepseek-ai/schemastery' -import { Client } from '@modelcontextprotocol/sdk/client/index.js' -import { ToolListChangedNotificationSchema } from '@modelcontextprotocol/sdk/types.js' -import { createTransport } from './transport.ts' -import { syncTools } from './tools.ts' +import { MAX_TIMER_DELAY_MS } from '@deepseek-ai/dsh-timeout' +import { RECONNECT_DEFAULTS, resolveReconnectPolicy, startConnection } from './connection.ts' +import type { ReconnectConfig } from './connection.ts' // Side-effect type import: declaration-merges `ctx.tools` onto Context. import type {} from '@deepseek-ai/dsh-tools' export type { McpResult } from './tools.ts' +export type { ReconnectConfig, ResolvedReconnectPolicy } from './connection.ts' /** Cordis plugin name used by loader diagnostics. */ export const name = 'mcp-client' @@ -68,6 +68,8 @@ export interface StdioConfig { toolCallTimeoutMs: number /** Fail plugin activation when the initial connection or tool synchronization fails. */ failOnStartupError: boolean + /** Automatic reconnect policy after a lost connection; omission uses the defaults. */ + reconnect?: ReconnectConfig } /** Config for connecting to an MCP server over Streamable HTTP (SSE). */ @@ -88,11 +90,20 @@ export interface StreamableHttpConfig { toolCallTimeoutMs: number /** Fail plugin activation when the initial connection or tool synchronization fails. */ failOnStartupError: boolean + /** Automatic reconnect policy after a lost connection; omission uses the defaults. */ + reconnect?: ReconnectConfig } /** Configuration for one stdio or Streamable HTTP MCP server. */ export type Config = StdioConfig | StreamableHttpConfig +const Reconnect: z = z.object({ + enabled: z.boolean().default(RECONNECT_DEFAULTS.enabled), + initialDelayMs: z.number().min(1).max(MAX_TIMER_DELAY_MS).default(RECONNECT_DEFAULTS.initialDelayMs), + maxDelayMs: z.number().min(1).max(MAX_TIMER_DELAY_MS).default(RECONNECT_DEFAULTS.maxDelayMs), + maxAttempts: z.number().step(1).min(1).max(Number.MAX_SAFE_INTEGER).default(RECONNECT_DEFAULTS.maxAttempts), +}) + export const Config = z.union([ z.object({ transport: z.const('stdio'), @@ -103,6 +114,7 @@ export const Config = z.union([ cwd: z.string().default(''), toolCallTimeoutMs: z.number().default(DEFAULT_TOOL_CALL_TIMEOUT_MS), failOnStartupError: z.boolean().default(false), + reconnect: Reconnect, }), z.object({ transport: z.const('streamable-http'), @@ -111,6 +123,7 @@ export const Config = z.union([ headers: z.dict(String).default({}), toolCallTimeoutMs: z.number().default(DEFAULT_TOOL_CALL_TIMEOUT_MS), failOnStartupError: z.boolean().default(false), + reconnect: Reconnect, }), ]) as unknown as z @@ -125,7 +138,12 @@ export const Config = z.union([ * @returns startup readiness after connection and initial tool discovery settle. */ export async function apply(ctx: Context, config: Config): Promise { - // Reserve the namespace first: a duplicate `serverName` fails THIS instance + // Fail loud at load: reconnect misconfiguration (including programmatic + // construction that bypassed Schemastery) rejects THIS instance before any + // effect registers. + const reconnect = resolveReconnectPolicy(config.reconnect, `mcp-client(${config.serverName}): reconnect`) + + // Reserve the namespace next: a duplicate `serverName` fails THIS instance // at load with an actionable error and leaves the earlier instance intact. ctx.effect(() => { let names = activeServerNames.get(ctx.root) @@ -142,58 +160,22 @@ export async function apply(ctx: Context, config: Config): Promise { return () => void names.delete(config.serverName) }, 'mcp-client.serverName') - const transport = createTransport(config) - const client = new Client( - { name: 'dsh-mcp-client', version: '0.0.1' }, - { capabilities: {} }, - ) + // The supervisor owns the client/transport generations, the reconnect + // loop, and the live tool registrations; disposal stops reconnection, + // quiesces in-flight work, and unregisters the current generation. + const connection = startConnection(ctx, config, reconnect) - const opts = { - registrationFailure: 'contain' as const, - serverName: config.serverName, - toolCallTimeoutMs: config.toolCallTimeoutMs, - } - - // Connect and set up tools. `ready` always settles to an outcome so rollback - // can close a partially opened client even when strict startup later rejects. - // Its accessor returns the CURRENT disposer generation, so disposal always - // unregisters the live set, not the first one. - const ready = (async () => { - await client.connect(transport) - - let disposers = await syncTools(client, ctx, { - ...opts, - registrationFailure: config.failOnStartupError ? 'throw' : 'contain', - }, new Map()) - - client.setNotificationHandler( - ToolListChangedNotificationSchema, - async () => { - ctx.logger.info(`mcp-client(${config.serverName}): tool list changed, re-syncing`) - try { - disposers = await syncTools(client, ctx, opts, disposers) - } catch (error) { - // Fetch-phase failure: the previous generation is still registered - // and `disposers` still owns it — keep serving the last good list. - ctx.logger.error(`mcp-client(${config.serverName}): tool re-sync failed: ${String(error)}`) - } - }, - ) - - return { getDisposers: () => disposers } - })().catch((error: unknown) => { - ctx.logger.error(`mcp-client(${config.serverName}): startup failed: ${String(error)}`) - return { getDisposers: () => new Map void>(), error } - }) - - ctx.effect(() => async () => { - const outcome = await ready - for (const dispose of outcome.getDisposers().values()) dispose() - try { await client.close() } catch { /* transport already gone */ } + ctx.effect(() => { + return () => connection.dispose() }, 'mcp-client.connection') - const outcome = await ready - if ('error' in outcome && config.failOnStartupError) { + // Block plugin activation on the initial connection + tool discovery so + // Cordis consumers observe the tools immediately after the fiber activates. + // When failOnStartupError is true, a failed initial attempt rejects the + // fiber (Cordis rolls it back); otherwise the error is logged and the + // supervisor enters its reconnect loop. + const outcome = await connection.ready + if (outcome.error !== undefined && config.failOnStartupError) { throw new Error(`mcp-client(${config.serverName}): initial connection or tool synchronization failed`, { cause: outcome.error }) } } diff --git a/packages/mcp/mcp-client/tests/apply.spec.ts b/packages/mcp/mcp-client/tests/apply.spec.ts index 06d82eb77e..d4f301be54 100644 --- a/packages/mcp/mcp-client/tests/apply.spec.ts +++ b/packages/mcp/mcp-client/tests/apply.spec.ts @@ -124,6 +124,33 @@ describe('mcp-client plugin module exports', () => { } as never) expect(resolved.serverName).toBe('github-prod_1') }) + + it('Config schema materializes reconnect defaults and merges partial overrides', () => { + const omitted = ConfigSchema({ + transport: 'stdio', + serverName: 'srv', + command: 'echo', + } as never) + expect(omitted.reconnect).toEqual({ enabled: true, initialDelayMs: 500, maxDelayMs: 30_000, maxAttempts: 10 }) + + const partial = ConfigSchema({ + transport: 'stdio', + serverName: 'srv', + command: 'echo', + reconnect: { initialDelayMs: 100 }, + } as never) + expect(partial.reconnect).toEqual({ enabled: true, initialDelayMs: 100, maxDelayMs: 30_000, maxAttempts: 10 }) + }) + + it('Config schema rejects an invalid reconnect block', () => { + // schemastery unions wrap branch errors, so assert the throw only. + expect(() => ConfigSchema({ + transport: 'stdio', + serverName: 'srv', + command: 'echo', + reconnect: { maxAttempts: 0 }, + } as never)).toThrow() + }) }) describe('apply (plugin lifecycle)', () => { @@ -132,7 +159,10 @@ describe('apply (plugin lifecycle)', () => { beforeEach(async () => { vi.clearAllMocks() mockConnect.mockResolvedValue(undefined) - mockClose.mockResolvedValue(undefined) + mockClose.mockImplementation(function (this: { onclose?: () => void }) { + this.onclose?.() + return Promise.resolve() + }) mockListTools.mockResolvedValue({ tools: [{ name: 'remote', description: 'A remote tool', inputSchema: { type: 'object' } }], nextCursor: undefined, @@ -216,19 +246,23 @@ describe('apply (plugin lifecycle)', () => { expect(mockListTools).not.toHaveBeenCalled() expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() - // Disposal exercises the empty fallback accessor: nothing to unregister, - // close still attempted, no throw. + // Disposal cancels the scheduled reconnect attempt: nothing to + // unregister, close already attempted by the failed attempt, no throw. await ctx.fiber.dispose() await sleep(50) expect(mockClose).toHaveBeenCalled() }) it('rejects activation and still closes the client when startup failure is configured as fatal', async () => { - mockConnect.mockRejectedValue(new Error('connection refused')) + const cause = new Error('connection refused') + mockConnect.mockRejectedValue(cause) await expect(apply(ctx, { ...stdioConfig, failOnStartupError: true, - })).rejects.toThrow('initial connection or tool synchronization failed') + })).rejects.toMatchObject({ + message: 'mcp-client(srv): initial connection or tool synchronization failed', + cause, + }) expect(mockListTools).not.toHaveBeenCalled() expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() @@ -258,6 +292,32 @@ describe('apply (plugin lifecycle)', () => { expect(mockClose).toHaveBeenCalled() }) + it('preserves strict startup registration when list_changed arrives before connect resolves', async () => { + ctx.tools.register({ + name: 'mcp__srv__remote', + description: 'Foreign squatter', + parameters: { type: 'object' }, + output: { + schema: { type: 'string' }, + render: (_args, value) => [{ type: 'text', text: value as string }], + }, + execute: async () => 'foreign', + }) + mockConnect.mockImplementation(async () => { + const handler = mockSetNotificationHandler.mock.calls[0]![1] as () => Promise + await handler() + }) + + await expect(apply(ctx, { + ...stdioConfig, + failOnStartupError: true, + })).rejects.toThrow('initial connection or tool synchronization failed') + + expect(mockListTools).toHaveBeenCalledTimes(2) + expect(ctx.tools.get('mcp__srv__remote')?.description).toBe('Foreign squatter') + await ctx.fiber.dispose() + }) + it('re-syncs tools on ToolListChanged notification', async () => { await apply(ctx, stdioConfig) @@ -311,7 +371,10 @@ describe('apply (plugin lifecycle)', () => { }) it('effect disposer handles client.close failure gracefully', async () => { - mockClose.mockRejectedValue(new Error('already closed')) + mockClose.mockImplementation(function (this: { onclose?: () => void }) { + this.onclose?.() + return Promise.reject(new Error('already closed')) + }) await apply(ctx, stdioConfig) diff --git a/packages/mcp/mcp-client/tests/fixture-server.ts b/packages/mcp/mcp-client/tests/fixture-server.ts index 8491b96634..974e2a26b0 100644 --- a/packages/mcp/mcp-client/tests/fixture-server.ts +++ b/packages/mcp/mcp-client/tests/fixture-server.ts @@ -51,6 +51,17 @@ server.registerTool('image', { ], })) +server.registerTool('crash', { + title: 'Crash Tool', + description: 'Replies, then exits the server process (crash-recovery test).', + inputSchema: {}, +}, async () => { + // Exit AFTER the response flushes so the caller observes a clean result + // followed by a transport close, like a real post-reply crash. + setTimeout(() => process.exit(7), 25) + return { content: [{ type: 'text', text: 'crashing' }] } +}) + // Dotted name: legal in MCP, illegal in the DeepSeek function-name contract. // Exercises the bridge's normalize-and-hash public-name path end to end. server.registerTool('admin.reset', { diff --git a/packages/mcp/mcp-client/tests/mcp-client.e2e.ts b/packages/mcp/mcp-client/tests/mcp-client.e2e.ts index 64f76e4a34..34d0970258 100644 --- a/packages/mcp/mcp-client/tests/mcp-client.e2e.ts +++ b/packages/mcp/mcp-client/tests/mcp-client.e2e.ts @@ -13,7 +13,7 @@ import { mkdtemp, rm, writeFile, readFile } from 'node:fs/promises' import { tmpdir } from 'node:os' import { join } from 'node:path' import { fileURLToPath } from 'node:url' -import { afterAll, beforeAll, describe, expect, it } from 'vitest' +import { afterAll, beforeAll, describe, expect, it, vi } from 'vitest' import { Context } from '@deepseek-ai/cordis' import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js' import { StreamableHTTPServerTransport } from '@modelcontextprotocol/sdk/server/streamableHttp.js' @@ -200,6 +200,87 @@ describe('fixture server — disposal', () => { }, 30_000) }) +describe('fixture server — crash recovery', () => { + function crashConfig(serverName: string, reconnect: NonNullable): Config { + return { + transport: 'stdio', + serverName, + command: process.execPath, + args: [fixtureServerPath], + env: {}, + cwd: packageDir, + toolCallTimeoutMs: 15_000, + failOnStartupError: false, + reconnect, + } + } + + it('auto-reconnects after a stdio crash and serves tool calls again', async () => { + const ctx = await mountRegistry() + await apply(ctx, crashConfig('crashy', { initialDelayMs: 50, maxDelayMs: 500, maxAttempts: 40 })) + + const before = await ctx.tools.execute({ + signal: testToolSignal, + callId: nextCallId(), name: 'mcp__crashy__add', arguments: { a: 2, b: 3 }, + }) + expect(textOf(before.content[0])).toBe('5') + + // The crash tool replies, then kills the real child process. + const crash = await ctx.tools.execute({ + signal: testToolSignal, + callId: nextCallId(), name: 'mcp__crashy__crash', arguments: {}, + }) + expect(crash.isError).toBe(false) + + // Recovery is proven by the world: a post-crash call round-trips through + // the respawned server process. + await vi.waitFor(async () => { + const after = await ctx.tools.execute({ + signal: testToolSignal, + callId: nextCallId(), name: 'mcp__crashy__add', arguments: { a: 20, b: 22 }, + }) + expect(after.isError).toBe(false) + expect(textOf(after.content[0])).toBe('42') + }, { timeout: 15_000, interval: 250 }) + + // The recovered generation replaced the dead one: no duplicates, no leak. + const addEntries = ctx.tools.schemas().map(s => s.name).filter(name => name === 'mcp__crashy__add') + expect(addEntries).toHaveLength(1) + + await ctx.fiber.dispose() + await sleep(200) + }, 30_000) + + it('plugin unload during an outage stops reconnection and unregisters tools', async () => { + const ctx = await mountRegistry() + const fiber = ctx.plugin( + { name: 'mcp-client', inject: ['tools'], apply }, + crashConfig('ephemeral', { initialDelayMs: 8_000, maxDelayMs: 8_000, maxAttempts: 5 }), + ) + // Cordis awaits async apply() as startup work; wait for it. + await vi.waitFor(() => { expect(ctx.tools.get('mcp__ephemeral__add')).toBeDefined() }, { timeout: 20_000 }) + + const crash = await ctx.tools.execute({ + signal: testToolSignal, + callId: nextCallId(), name: 'mcp__ephemeral__crash', arguments: {}, + }) + expect(crash.isError).toBe(false) + + // Give the transport close a moment to land the supervisor in its 8s + // backoff wait, then unload: disposal must not sit out the backoff. + await sleep(300) + const started = Date.now() + await fiber.dispose() + expect(Date.now() - started).toBeLessThan(4_000) + + expect(ctx.tools.get('mcp__ephemeral__add')).toBeUndefined() + await sleep(200) + expect(ctx.tools.get('mcp__ephemeral__add')).toBeUndefined() + + await ctx.fiber.dispose() + }, 30_000) +}) + // ---- @modelcontextprotocol/server-everything ---- describe('server-everything — official test server', () => { diff --git a/packages/mcp/mcp-client/tests/reconnect.spec.ts b/packages/mcp/mcp-client/tests/reconnect.spec.ts new file mode 100644 index 0000000000..bdbae26a7e --- /dev/null +++ b/packages/mcp/mcp-client/tests/reconnect.spec.ts @@ -0,0 +1,521 @@ +/** + * Tests for the mcp-client connection supervisor: crash-driven reconnection + * with bounded backoff, generation-safe tool re-registration, the failure + * cap, the stability-window budget reset, and disposal stopping reconnection. + * Isolated file so vi.mock of the MCP SDK doesn't pollute other test suites. + */ +import { describe, expect, it, vi, beforeEach } from 'vitest' +import { Context } from '@deepseek-ai/cordis' +import SystemPrompt from '@deepseek-ai/dsh-system-prompt' +import ToolRegistry from '@deepseek-ai/dsh-tools' +import { CallId } from '@deepseek-ai/dsh-llm' +import type { Config } from '@deepseek-ai/dsh-mcp-client' + +// ---- Mock MCP SDK ---- + +// vi.mock factories are hoisted above every import/const, so the mock fns and +// class must be created inside vi.hoisted to exist when the factories run. +const { mockConnect, mockClose, mockListTools, mockCallTool, mockSetNotificationHandler, MockClient, instances } = vi.hoisted(() => { + const mockConnect = vi.fn<() => Promise>() + const mockClose = vi.fn<() => Promise>() + const mockListTools = vi.fn<(_params?: Record) => Promise>() + const mockCallTool = vi.fn<( + _params?: Record, _compatibilitySchema?: unknown, _options?: unknown, + ) => Promise>() + const mockSetNotificationHandler = vi.fn() + const mockRequest = vi.fn(async ( + request: { method: string; params?: Record }, + _schema: unknown, + options?: unknown, + ): Promise => { + if (request.method === 'tools/list') return await mockListTools(request.params) + if (request.method === 'tools/call') return await mockCallTool(request.params, undefined, options) + throw new Error(`unexpected MCP request: ${request.method}`) + }) + class MockClient { + onclose: (() => void) | undefined + connect = mockConnect + close = mockClose + request = mockRequest + setNotificationHandler = mockSetNotificationHandler + constructor() { instances.push(this) } + } + const instances: MockClient[] = [] + return { mockConnect, mockClose, mockListTools, mockCallTool, mockSetNotificationHandler, MockClient, instances } +}) + +vi.mock('@modelcontextprotocol/sdk/client/index.js', () => ({ + Client: MockClient, +})) + +vi.mock('@modelcontextprotocol/sdk/client/stdio.js', () => ({ + StdioClientTransport: vi.fn(), +})) + +vi.mock('@modelcontextprotocol/sdk/client/streamableHttp.js', () => ({ + StreamableHTTPClientTransport: vi.fn(), +})) + +// vi.mock is hoisted above static imports, so the modules under test see the +// mocked SDK even through a static import. +import { apply } from '@deepseek-ai/dsh-mcp-client/src/index.ts' +import { RECONNECT_DEFAULTS, resolveReconnectPolicy, startConnection } from '@deepseek-ai/dsh-mcp-client/src/connection.ts' + +// ---- Helpers ---- + +const testToolSignal = new AbortController().signal + +async function mountRegistry(): Promise { + const ctx = new Context() + await ctx.plugin(SystemPrompt) + await ctx.plugin(ToolRegistry) + return ctx +} + +function sleep(ms: number): Promise { + // Annotated binding (not withResolvers()): the tests lint layer runs + // no-invalid-void-type with default options, which rejects the explicit + // type argument in call position but accepts the inferred form. + const gate: PromiseWithResolvers = Promise.withResolvers() + setTimeout(gate.resolve, ms) + return gate.promise +} + +/** Capture the supervisor's logger lines by level on one context. */ +function captureLogs(ctx: Context): { warns: string[]; errors: string[]; infos: string[] } { + const warns: string[] = [] + const errors: string[] = [] + const infos: string[] = [] + ctx.logger.warn = ((message: unknown) => { warns.push(String(message)) }) as typeof ctx.logger.warn + ctx.logger.error = ((message: unknown) => { errors.push(String(message)) }) as typeof ctx.logger.error + ctx.logger.info = ((message: unknown) => { infos.push(String(message)) }) as typeof ctx.logger.info + return { warns, errors, infos } +} + +function stdioConfig(reconnect?: Config['reconnect']): Config { + return { + transport: 'stdio', + serverName: 'srv', + command: 'echo', + args: [], + env: {}, + cwd: '', + toolCallTimeoutMs: 60_000, + failOnStartupError: false, + ...reconnect === undefined ? {} : { reconnect }, + } +} + +/** The tool list the mock server advertises after a successful (re)connect. */ +function listing(...names: string[]): { tools: { name: string; inputSchema: { type: string } }[]; nextCursor: undefined } { + return { + tools: names.map(name => ({ name, inputSchema: { type: 'object' } })), + nextCursor: undefined, + } +} + +let callSeq = 0 +function nextCallId(): CallId { + return CallId(`reconnect-${++callSeq}`) +} + +// ---- Tests ---- + +describe('reconnect supervisor', () => { + let ctx: Context + + beforeEach(async () => { + vi.clearAllMocks() + instances.length = 0 + mockConnect.mockResolvedValue(undefined) + mockClose.mockImplementation(function (this: { onclose?: () => void }) { + this.onclose?.() + return Promise.resolve() + }) + mockListTools.mockResolvedValue(listing('remote')) + mockCallTool.mockResolvedValue({ content: [{ type: 'text', text: 'ok' }] }) + ctx = await mountRegistry() + }) + + it('reconnects after a transport close, re-syncs tools through the new generation, and serves calls', async () => { + const { warns, infos } = captureLogs(ctx) + await apply(ctx, stdioConfig({ initialDelayMs: 5, maxDelayMs: 40, maxAttempts: 5 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + expect(instances).toHaveLength(1) + + // The recovered server advertises a different list: the swap must neither + // duplicate nor leak the pre-crash generation. + mockListTools.mockResolvedValue(listing('revived')) + instances[0]!.onclose?.() + + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__revived')).toBeDefined() }) + expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() + expect(instances).toHaveLength(2) + expect(mockConnect).toHaveBeenCalledTimes(2) + + // Post-recovery calls execute through the re-registered definition. + const result = await ctx.tools.execute({ + signal: testToolSignal, + callId: nextCallId(), name: 'mcp__srv__revived', arguments: {}, + }) + expect(result.isError).toBe(false) + + // User-visible state: reconnecting and recovered are distinct lines. + expect(warns.some(line => line.includes('reconnecting in 5ms (attempt 1/5)'))).toBe(true) + expect(infos.some(line => line.includes('reconnected and re-synced tools'))).toBe(true) + + // A late close signal from the replaced generation is ignored. + instances[0]!.onclose?.() + await sleep(30) + expect(instances).toHaveLength(2) + }) + + it('stops at the failure cap, unregisters the tools, and reports final failure', async () => { + const { warns, errors } = captureLogs(ctx) + await apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 2 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + mockConnect.mockRejectedValue(new Error('server gone')) + // A failing close on the failed attempt's cleanup must not break the loop. + mockClose.mockImplementation(function (this: { onclose?: () => void }) { + this.onclose?.() + return Promise.reject(new Error('already closed')) + }) + instances[0]!.onclose?.() + + await vi.waitFor(() => { + expect(errors.some(line => line.includes('giving up after 2 consecutive failed reconnect attempts'))).toBe(true) + }) + // Stale tools do not leak past final failure. + expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() + // Initial connect + exactly maxAttempts reconnect attempts. + expect(mockConnect).toHaveBeenCalledTimes(3) + expect(warns.some(line => line.includes('connection attempt failed: Error: server gone'))).toBe(true) + expect(warns.some(line => line.includes('connection failed; retrying in 4ms (attempt 2/2)'))).toBe(true) + await sleep(30) + expect(mockConnect).toHaveBeenCalledTimes(3) + }) + + it('gives up behind an in-flight re-sync and removes the generation it publishes', async () => { + const { errors } = captureLogs(ctx) + await apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 1 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + const gate: PromiseWithResolvers = Promise.withResolvers() + mockListTools.mockImplementation(() => gate.promise) + const handler = mockSetNotificationHandler.mock.calls[0]![1] as () => Promise + const resync = handler() + await vi.waitFor(() => { expect(mockListTools).toHaveBeenCalledTimes(2) }) + + mockConnect.mockRejectedValue(new Error('server gone')) + instances[0]!.onclose?.() + await vi.waitFor(() => { + expect(errors.some(line => line.includes('giving up after 1 consecutive failed reconnect attempts'))).toBe(true) + }) + + gate.resolve(listing('late')) + await resync + await vi.waitFor(() => { + expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() + expect(ctx.tools.get('mcp__srv__late')).toBeUndefined() + }) + expect(mockConnect).toHaveBeenCalledTimes(2) + }) + + it('does not start a replacement until a failed generation reports that it closed', async () => { + const { warns } = captureLogs(ctx) + mockConnect.mockRejectedValueOnce(new Error('initialize failed')) + // Model the SDK's fire-and-forget close after initialize fails: the + // harness's second close call returns, but the child has not exited yet. + mockClose.mockResolvedValue(undefined) + + const applying = apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 2 })) + await vi.waitFor(() => { expect(mockClose).toHaveBeenCalled() }) + await sleep(30) + expect(instances).toHaveLength(1) + + instances[0]!.onclose?.() + await applying + await vi.waitFor(() => { expect(instances).toHaveLength(2) }) + expect(warns.some(line => line.includes('connection failed; retrying in 2ms (attempt 1/2)'))).toBe(true) + }) + + it('stops reconnecting when a failed generation never reports that it closed', async () => { + vi.useFakeTimers() + try { + const { errors } = captureLogs(ctx) + mockConnect.mockRejectedValue(new Error('initialize failed')) + mockClose.mockResolvedValue(undefined) + + const applying = apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 2 })) + await vi.advanceTimersByTimeAsync(5_000) + await applying + + expect(instances).toHaveLength(1) + expect(errors.some(line => line.includes('reconnect stopped to avoid overlapping server processes'))).toBe(true) + } finally { + vi.useRealTimers() + } + }) + + it('suppresses retry reporting when disposal owns a pending connect rejection', async () => { + const { warns } = captureLogs(ctx) + const gate: PromiseWithResolvers = Promise.withResolvers() + mockConnect.mockImplementation(() => gate.promise) + const handle = startConnection(ctx, stdioConfig(), resolveReconnectPolicy(undefined, 'reconnect')) + await vi.waitFor(() => { expect(instances).toHaveLength(1) }) + + const disposing = handle.dispose() + gate.reject(new Error('disposed connect')) + await disposing + await handle.ready + + expect(warns.some(line => line.includes('connection attempt failed'))).toBe(false) + expect(instances).toHaveLength(1) + }) + + it('bounds disposal while a resolving generation never reports that it closed', async () => { + vi.useFakeTimers() + try { + const { errors } = captureLogs(ctx) + const gate: PromiseWithResolvers = Promise.withResolvers() + mockConnect.mockImplementation(() => gate.promise) + mockClose.mockResolvedValue(undefined) + const handle = startConnection(ctx, stdioConfig(), resolveReconnectPolicy(undefined, 'reconnect')) + await vi.advanceTimersByTimeAsync(0) + + const disposing = handle.dispose() + await vi.advanceTimersByTimeAsync(5_000) + gate.resolve() + await disposing + + expect(mockListTools).not.toHaveBeenCalled() + expect(errors.some(line => line.includes('server shutdown may be incomplete'))).toBe(true) + } finally { + vi.useRealTimers() + } + }) + + it('dispose during the backoff wait cancels the pending reconnect', async () => { + await apply(ctx, stdioConfig({ initialDelayMs: 60_000, maxDelayMs: 60_000, maxAttempts: 5 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + instances[0]!.onclose?.() + // Now waiting out a 60s backoff; disposal must return promptly anyway. + await ctx.fiber.dispose() + await sleep(30) + expect(mockConnect).toHaveBeenCalledTimes(1) + expect(instances).toHaveLength(1) + }) + + it('a transport close after dispose schedules nothing', async () => { + const fiber = ctx.plugin({ name: 'mcp-client', inject: ['tools'], apply }, stdioConfig()) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + await fiber.dispose() + expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() + + // The disposer's client.close() fires onclose in the real SDK. + instances[0]!.onclose?.() + await sleep(30) + expect(instances).toHaveLength(1) + expect(mockConnect).toHaveBeenCalledTimes(1) + }) + + it('reconnect disabled keeps the registered tools and reports manual recovery', async () => { + const { errors } = captureLogs(ctx) + await apply(ctx, stdioConfig({ enabled: false })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + instances[0]!.onclose?.() + await sleep(30) + expect(mockConnect).toHaveBeenCalledTimes(1) + // Pre-reconnect contract: the generation stays registered until disposal. + expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() + expect(errors.some(line => line.includes('connection lost and reconnect is disabled'))).toBe(true) + }) + it('reconnect disabled after a failed initial connect reports no registered tools', async () => { + const { errors } = captureLogs(ctx) + mockConnect.mockRejectedValue(new Error('refused')) + await apply(ctx, stdioConfig({ enabled: false })) + await sleep(30) + expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() + expect(errors.some(line => line.includes('connection failed and reconnect is disabled'))).toBe(true) + expect(errors.some(line => line.includes('no tools were registered'))).toBe(true) + }) + + it('an uptime past the stability window resets the attempt budget', async () => { + const { errors } = captureLogs(ctx) + await apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 30, maxAttempts: 1 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + instances[0]!.onclose?.() + await vi.waitFor(() => { expect(instances).toHaveLength(2) }) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + // Outlive the stability window (= maxDelayMs), then crash again: the + // budget restarts at attempt 1 instead of exceeding maxAttempts. + await sleep(40) + instances[1]!.onclose?.() + await vi.waitFor(() => { expect(instances).toHaveLength(3) }) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + expect(errors).toHaveLength(0) + }) + + it('a crash loop with briefly successful connects still exhausts the cap', async () => { + const { errors } = captureLogs(ctx) + await apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 10_000, maxAttempts: 1 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + // Crash, recover (attempt 1 of 1), crash again well inside the stability + // window: the successful connect must not launder the budget. + instances[0]!.onclose?.() + await vi.waitFor(() => { expect(instances).toHaveLength(2) }) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + instances[1]!.onclose?.() + + await vi.waitFor(() => { + expect(errors.some(line => line.includes('giving up after 1 consecutive failed reconnect attempts'))).toBe(true) + }) + expect(instances).toHaveLength(2) + expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() + }) + + it('a connect rejection racing its own transport close schedules exactly one retry per attempt', async () => { + const { errors } = captureLogs(ctx) + await apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 3 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + // Each reconnect attempt sees the stdio transport die (onclose) AND its + // connect() reject — the real SDK emits both for a spawn failure. + mockConnect.mockImplementation(async () => { + instances.at(-1)!.onclose?.() + throw new Error('spawn failed') + }) + instances[0]!.onclose?.() + + await vi.waitFor(() => { + expect(errors.some(line => line.includes('giving up after 3 consecutive failed reconnect attempts'))).toBe(true) + }) + // Initial generation + exactly one generation per budgeted attempt: a + // double-scheduled retry would create more. + expect(instances).toHaveLength(4) + expect(errors.filter(line => line.includes('giving up')).length).toBe(1) + }) + + it('a transport that closes during a resolving connect registers nothing from the dead generation', async () => { + await apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 2 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + expect(mockListTools).toHaveBeenCalledTimes(1) + + mockConnect.mockImplementation(async () => { + instances.at(-1)!.onclose?.() + }) + instances[0]!.onclose?.() + + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() }) + // The dead generations never reached tool discovery. + expect(mockListTools).toHaveBeenCalledTimes(1) + }) + + it('dispose during an in-flight initial sync quiesces without leaking tools', async () => { + const fiber = ctx.plugin({ name: 'mcp-client', inject: ['tools'], apply }, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 5 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + // Block the reconnect attempt's tool discovery until after dispose starts. + const gate: PromiseWithResolvers = Promise.withResolvers() + mockListTools.mockImplementation(() => gate.promise) + instances[0]!.onclose?.() + await vi.waitFor(() => { expect(mockListTools).toHaveBeenCalledTimes(2) }) + + const disposing = fiber.dispose() + await sleep(10) + gate.resolve(listing('late')) + await disposing + + // The late sync's swap ran, then disposal unregistered its result: no + // generation survives the plugin. + expect(ctx.tools.get('mcp__srv__remote')).toBeUndefined() + expect(ctx.tools.get('mcp__srv__late')).toBeUndefined() + }) + + it('a re-sync failing because dispose closed the transport stays silent', async () => { + const { errors } = captureLogs(ctx) + const fiber = ctx.plugin({ name: 'mcp-client', inject: ['tools'], apply }, stdioConfig()) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + const gate: PromiseWithResolvers = Promise.withResolvers() + mockListTools.mockImplementation(() => gate.promise) + const handler = mockSetNotificationHandler.mock.calls[0]![1] as () => Promise + const resync = handler() + await vi.waitFor(() => { expect(mockListTools).toHaveBeenCalledTimes(2) }) + + const disposing = fiber.dispose() + await sleep(10) + gate.reject(new Error('Connection closed')) + await disposing + await resync + + expect(errors.some(line => line.includes('tool re-sync failed'))).toBe(false) + }) + + it('a stale notification handler from a replaced generation is ignored', async () => { + await apply(ctx, stdioConfig({ initialDelayMs: 2, maxDelayMs: 8, maxAttempts: 5 })) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + + instances[0]!.onclose?.() + await vi.waitFor(() => { expect(instances).toHaveLength(2) }) + await vi.waitFor(() => { expect(ctx.tools.get('mcp__srv__remote')).toBeDefined() }) + const listCalls = mockListTools.mock.calls.length + + const staleHandler = mockSetNotificationHandler.mock.calls[0]![1] as () => Promise + await staleHandler() + expect(mockListTools).toHaveBeenCalledTimes(listCalls) + }) +}) + +// ---- Policy resolution ---- + +describe('resolveReconnectPolicy', () => { + const path = 'mcp-client(srv): reconnect' + + it('resolves omission to the defaults, frozen', () => { + const policy = resolveReconnectPolicy(undefined, path) + expect(policy).toEqual(RECONNECT_DEFAULTS) + expect(Object.isFrozen(policy)).toBe(true) + }) + + it('keeps explicit values', () => { + expect(resolveReconnectPolicy( + { enabled: false, initialDelayMs: 1, maxDelayMs: 2, maxAttempts: 7 }, + path, + )).toEqual({ enabled: false, initialDelayMs: 1, maxDelayMs: 2, maxAttempts: 7 }) + }) + + it('rejects unknown keys', () => { + expect(() => resolveReconnectPolicy({ jitterRatio: 0.5 } as never, path)) + .toThrow(/reconnect\.jitterRatio is not a reconnect option/) + }) + + it('rejects out-of-range delays', () => { + expect(() => resolveReconnectPolicy({ initialDelayMs: 0 }, path)).toThrow(/initialDelayMs must be a positive finite number/) + expect(() => resolveReconnectPolicy({ initialDelayMs: Number.POSITIVE_INFINITY }, path)).toThrow(/initialDelayMs/) + expect(() => resolveReconnectPolicy({ maxDelayMs: -1 }, path)).toThrow(/maxDelayMs must be a positive finite number/) + }) + + it('rejects an initial delay above the ceiling', () => { + expect(() => resolveReconnectPolicy({ initialDelayMs: 100, maxDelayMs: 5 }, path)) + .toThrow(/initialDelayMs must be less than or equal to maxDelayMs/) + }) + + it('rejects non-positive-integer attempt caps', () => { + expect(() => resolveReconnectPolicy({ maxAttempts: 0 }, path)).toThrow(/maxAttempts must be a positive integer/) + expect(() => resolveReconnectPolicy({ maxAttempts: 1.5 }, path)).toThrow(/maxAttempts must be a positive integer/) + }) + + it('apply fails loud at load on a misconfigured reconnect', async () => { + const ctx = await mountRegistry() + await expect(apply(ctx, stdioConfig({ initialDelayMs: 100, maxDelayMs: 5 }))) + .rejects.toThrow(/initialDelayMs must be less than or equal to maxDelayMs/) + }) +}) diff --git a/packages/mcp/mcp-client/tsconfig.json b/packages/mcp/mcp-client/tsconfig.json index 461b250297..f42f4d4c2c 100644 --- a/packages/mcp/mcp-client/tsconfig.json +++ b/packages/mcp/mcp-client/tsconfig.json @@ -26,6 +26,9 @@ }, { "path": "../../support/invariants" + }, + { + "path": "../../util/timeout" } ] } diff --git a/packages/self-modification/tool-cordis/src/api-catalog.ts b/packages/self-modification/tool-cordis/src/api-catalog.ts index d177f49d29..3052b6895d 100644 --- a/packages/self-modification/tool-cordis/src/api-catalog.ts +++ b/packages/self-modification/tool-cordis/src/api-catalog.ts @@ -432,6 +432,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ signature: 'abstract streamText(target: FsTarget, signal?: AbortSignal): Promise>', jsDoc: '/**\n * Stream the whole regular text file as decoded text chunks (same text\n * semantics as {@link readText}, for large files). The backend owns\n * cross-chunk UTF-8 decoding and binary rejection so the policy layer never\n * touches raw bytes.\n * @param target - the resolved target to read.\n * @param signal - aborts the stream, including between chunks.\n * @returns the chunk iterable, decoded and validated like {@link readText}.\n */', }, + { + signature: 'abstract readBytes(target: FsTarget, signal: AbortSignal | undefined, maxBytes: number): Promise', + jsDoc: '/**\n * Read the whole regular file as raw bytes with no decoding or binary\n * rejection. The bound lives at this seam so a backend can never buffer an\n * unbounded file: a target known or discovered to exceed `maxBytes` fails\n * with `FS_TOO_LARGE` instead of returning a truncated result.\n * @param target - the resolved target to read.\n * @param signal - aborts the read.\n * @param maxBytes - inclusive byte cap on the complete content.\n * @returns the full raw content, at most `maxBytes` long.\n */', + }, { signature: 'abstract listDir(target: FsTarget, signal?: AbortSignal): Promise', jsDoc: '/**\n * List direct children of a directory in stable name order. Returns resolved\n * child targets plus cheap metadata only; never reads file contents.\n * @param target - the resolved directory target.\n * @param signal - aborts the listing.\n * @returns one entry per direct child, in stable name order.\n */', @@ -1150,6 +1154,10 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ signature: 'abstract onTaskDone(listener: TaskDoneListener): () => void', jsDoc: '/**\n * Register an effect-scoped completion listener. It receives the settlements\n * of the owners its registering context\'s scope covers; each listener is\n * contained; returned promises are observed but not awaited. No listener runs\n * after service disposal.\n * @param listener - receives each terminal snapshot and its exact owner.\n * @returns disposer that unregisters the listener.\n */', }, + { + signature: 'abstract onTasksChanged(listener: TasksChangedListener): () => void', + jsDoc: '/**\n/**\n * Register an effect-scoped observer of visible-set changes. It fires after\n * every commit that changes what {@link list} returns for that owner —\n * registration, every stopping transition (including the one teardown\n * performs before it awaits a slow producer), settlement, owner-disposal\n * removal, and the emptying that service disposal commits — so an observer\n * re-reads rather than accumulating deltas.\n *\n * Delivery is owner-relative on the same terms as {@link onTaskDone}: an\n * observer registered from an unscoped context — a host composition\'s own\n * carrier — sees every owner, while one registered under an agent\n * composition\'s scope sees exactly the agents composed under it.\n *\n * This is not a superset of {@link onTaskDone}: that one delivers the terminal\n * record under first-wins semantics a control surface couples to notice\n * delivery, while this one carries no delivery meaning and marks nothing\n * reported. Listeners are contained and never awaited.\n * @param listener - receives the owner whose visible set changed, or\n * `undefined` when an unowned task changed and every caller\'s set did.\n * @returns disposer that unregisters the listener.\n */', + }, { signature: 'abstract attachSurface(name: string): () => void', jsDoc: '/**\n * Attach an effect-scoped surface that can read and stop tasks. It serves the\n * owners its registering context\'s scope covers, and {@link start} refuses an\n * owner no attached surface serves.\n * @param name - diagnostic label; duplicate names remain independent.\n * @returns disposer that detaches this surface.\n */', @@ -3115,6 +3123,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'TaskRead', declaration: 'export interface TaskRead {\n text: string;\n snapshot: TaskSnapshot;\n}', }, + { + name: 'TasksChangedListener', + declaration: 'export type TasksChangedListener = (owner: Agent | undefined) => void;', + }, { name: 'TaskSnapshot', declaration: 'export interface TaskSnapshot {\n id: TaskId;\n kind: TaskKind;\n label: string;\n outputLimitBytes?: number;\n ownerSession?: SessionId;\n status: TaskStatus;\n detail?: string;\n startedAt: number;\n finishedAt?: number;\n reported: boolean;\n}', diff --git a/packages/skill/skill-local/tests/skill-local.spec.ts b/packages/skill/skill-local/tests/skill-local.spec.ts index 5948ace8a4..a472b4dbe1 100644 --- a/packages/skill/skill-local/tests/skill-local.spec.ts +++ b/packages/skill/skill-local/tests/skill-local.spec.ts @@ -96,6 +96,10 @@ class TestFileSystem extends FileSystem { throw new Error('not needed in skill tests') } + override async readBytes(_target: FsTarget, _signal: AbortSignal | undefined, _maxBytes: number): Promise { + throw new Error('not needed in skill tests') + } + override async listDir(target: FsTarget): Promise { this.listDirCalls += 1 if (this.failListDirPaths.has(target.displayPath)) throw new Error('list temporarily failed') diff --git a/packages/support/llm-mock-server/README.i18n.yaml b/packages/support/llm-mock-server/README.i18n.yaml index c78f65cc91..df99292c06 100644 --- a/packages/support/llm-mock-server/README.i18n.yaml +++ b/packages/support/llm-mock-server/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/support/llm-mock-server/README.md -README.md: a535c086bf688ad48b1a3bb19c7b81da21cbad92 -README.zh.md: d814d8815b38bb34bd0d871d552e6f3ec75e042a +README.md: 919bbc923110459e9ee4fc26f6db7e8b35ab1abb +README.zh.md: d60c6b2395c14c0cf690c2a94e902eb1cfeffa94 diff --git a/packages/support/llm-mock-server/README.md b/packages/support/llm-mock-server/README.md index a535c086bf..919bbc9231 100644 --- a/packages/support/llm-mock-server/README.md +++ b/packages/support/llm-mock-server/README.md @@ -23,7 +23,7 @@ Point the shipping DeepSeek adapter at the server; it appends `/chat/completions ```sh DEEPSEEK_BASE_URL=http://127.0.0.1:8000/v1 \ DEEPSEEK_API_KEY=mock-key \ -pnpm run demo:headless "test provider recovery" +pnpm dsh --profile headless "test provider recovery" ``` The repository script writes JSONL to stdout: a `ready` record carries the `/v1` base URL and random seed, followed by request/result records that name both the scripted behavior and the concrete selected behavior. The private support package exposes no installable binary. diff --git a/packages/support/llm-mock-server/README.zh.md b/packages/support/llm-mock-server/README.zh.md index d814d8815b..d60c6b2395 100644 --- a/packages/support/llm-mock-server/README.zh.md +++ b/packages/support/llm-mock-server/README.zh.md @@ -23,7 +23,7 @@ pnpm run mock:llm -- \ ```sh DEEPSEEK_BASE_URL=http://127.0.0.1:8000/v1 \ DEEPSEEK_API_KEY=mock-key \ -pnpm run demo:headless "test provider recovery" +pnpm dsh --profile headless "test provider recovery" ``` 仓库脚本将 JSONL 写入 stdout：`ready` 记录携带以 `/v1` 结尾的基础 URL 和随机种子，后续请求/结果记录同时命名脚本行为和实际选中的具体行为。这个私有支持包不公开可安装的二进制命令。 diff --git a/packages/support/llm-replay/README.i18n.yaml b/packages/support/llm-replay/README.i18n.yaml index 6d048c2325..688e259468 100644 --- a/packages/support/llm-replay/README.i18n.yaml +++ b/packages/support/llm-replay/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/support/llm-replay/README.md -README.md: ae7cb5414a28bcf33f9878f6f02220861df9a0d5 -README.zh.md: 2acc0ff8e8c011126452ba3458aaeb0800d9d8f3 +README.md: 6119407c06cf734166300f5f70a3fe65d026d08d +README.zh.md: 75d74b654a9a53e7ada5cc854e275eadcbe01284 diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index ae7cb5414a..6119407c06 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -29,7 +29,7 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s | `file` | string | `$DSH_SNAPSHOT_FILE` | Path to the primary (parent) `session.jsonl` fixture. Required (config or env). | | `overrideFile` | string | `$DSH_SNAPSHOT_OVERRIDE` | Optional `ReplayOverrideDoc` sidecar for the primary session: a bare `ReplayEntry[]` replaces its derived script, while `{ patches }` augments it by call index. | | `childFiles` | string[] | `$DSH_SNAPSHOT_CHILD_FILES` (path-delimited) | Recorded subagent child-session logs for a nested scenario; empty for a single-session scenario. | -| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Each provider may set `retryPolicy`, and each model may publish `contextWindow`; configured routes dispatch through the replay adapter and never perform provider I/O. | +| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Each provider may set `retryPolicy`, and each model may publish `contextWindow` and an `inputModalities` array containing only `text` and `image`; invalid modalities fail during plugin loading. Configured routes dispatch through the replay adapter and never perform provider I/O. | | `paceMs` | number | — (burst) | Optional per-chunk delay in ms so downstream transports (e.g. the web SSE mux observed by a real browser) see genuinely incremental delivery. A realism knob only — tests must not depend on it for correctness. Non-negative integer; abort during a pace wait cancels the stream promptly. | ```yaml diff --git a/packages/support/llm-replay/README.zh.md b/packages/support/llm-replay/README.zh.md index 2acc0ff8e8..75d74b654a 100644 --- a/packages/support/llm-replay/README.zh.md +++ b/packages/support/llm-replay/README.zh.md @@ -29,7 +29,7 @@ fixture 就是持久化的会话日志（`/session.jsonl`）。其 `as | `file` | string | `$DSH_SNAPSHOT_FILE` | 主（父）`session.jsonl` fixture 的路径。必需（配置或 env）。 | | `overrideFile` | string | `$DSH_SNAPSHOT_OVERRIDE` | 主会话的可选 `ReplayOverrideDoc` 伴随文件：裸 `ReplayEntry[]` 替换其派生脚本，`{ patches }` 则按调用索引增补该脚本。 | | `childFiles` | string[] | `$DSH_SNAPSHOT_CHILD_FILES`（以路径分隔符分隔） | 嵌套场景中已记录的 subagent 子会话日志；单会话场景为空。 | -| `providers` | `ReplayProviderConfig[]` | 无 | 可选的仅回放提供方和模型目录。每个提供方可以设置 `retryPolicy`，每个模型可以发布 `contextWindow`；已配置路由通过回放适配器分派，绝不执行提供方 I/O。 | +| `providers` | `ReplayProviderConfig[]` | 无 | 可选的仅回放提供方和模型目录。每个提供方可以设置 `retryPolicy`，每个模型可以发布 `contextWindow` 和仅包含 `text`、`image` 的 `inputModalities` 数组；模态配置无效时，插件加载会失败。已配置路由通过回放适配器分派，绝不执行提供方 I/O。 | | `paceMs` | number | 无（突发） | 可选的每分片毫秒延迟，使下游传输（例如真实浏览器观察到的 Web SSE（Server-Sent Events）多路复用器）看到真正的增量传递。它只是仿真开关，测试不得依赖它保证正确性。值必须是非负整数；pace 等待期间中止会迅速取消流。 | ```yaml diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 22757c53a3..f4a8a82e81 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -19,6 +19,7 @@ import type { LlmModelInfo, LlmProviderInfo, LlmResolvedModelInfo, + ModelModality, ResolvedRetryPolicy, RetryPolicyConfig, StreamChunk, @@ -51,6 +52,8 @@ export interface ReplayModelConfig { description?: string /** Optional positive integer context capacity published by the replay adapter. */ contextWindow?: number + /** Optional declared input modalities, so a scenario can exercise capability gates (e.g. image-capable `read_image`). */ + inputModalities?: readonly ModelModality[] /** * Optional per-request output cap the replay route materializes when callers * omit one, so replay reconstructs the request header a live catalog produced. @@ -581,6 +584,7 @@ class ReplayAdapter extends LlmAdapter { id: model.id, name: model.name ?? model.id, ...model.description === undefined ? {} : { description: model.description }, + ...model.inputModalities === undefined ? {} : { inputModalities: [...model.inputModalities] }, }))) } @@ -594,6 +598,9 @@ class ReplayAdapter extends LlmAdapter { id: model, name: configuredModel?.name ?? model, ...configuredModel?.description === undefined ? {} : { description: configuredModel.description }, + ...configuredModel?.inputModalities === undefined + ? {} + : { inputModalities: [...configuredModel.inputModalities] }, ...configuredModel?.contextWindow === undefined ? {} : { context: { contextWindow: configuredModel.contextWindow } }, @@ -783,11 +790,28 @@ export interface Config { paceMs?: number } +function validateConfiguredModalities(providers: ReplayProviderConfig[] | undefined): void { + for (const provider of providers ?? []) { + for (const model of provider.models ?? []) { + const modalities: unknown = model.inputModalities + if (modalities === undefined) continue + if (!Array.isArray(modalities) + || !modalities.every((modality: unknown) => modality === 'text' || modality === 'image')) { + throw new Error( + `llm-replay: provider "${provider.id}" model "${model.id}" inputModalities ` + + 'must be an array containing only "text" and "image"', + ) + } + } + } +} + export function apply(ctx: Context, config: Config = {}): void { const file = config.file ?? process.env.DSH_SNAPSHOT_FILE if (file === undefined || file.length === 0) { throw new Error('llm-replay: a fixture path is required (Config.file or $DSH_SNAPSHOT_FILE)') } + validateConfiguredModalities(config.providers) const overrideFile = config.overrideFile ?? process.env.DSH_SNAPSHOT_OVERRIDE const childEnv = process.env.DSH_SNAPSHOT_CHILD_FILES const childFiles = config.childFiles diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index d0bd675b48..defcfa7745 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -7,6 +7,7 @@ import type { SessionEvent } from '@deepseek-ai/dsh-session' import { CompactionId } from '@deepseek-ai/dsh-compact' import LlmService, { CallId, createUserMessage, GenerateOptions, LlmAdapter, StreamChunk } from '@deepseek-ai/dsh-llm' import { + type Config, type ReplayEntry, type SessionScript, apply, @@ -595,6 +596,7 @@ describe('installLlmReplay (through the real LlmService)', () => { { id: 'flash', contextWindow: 128_000, + inputModalities: ['text', 'image'], defaultMaxTokens: 64_000, reasoningEfforts: ['off', 'max'], defaultReasoningEffort: 'max', @@ -611,18 +613,20 @@ describe('installLlmReplay (through the real LlmService)', () => { { id: 'empty', name: 'empty' }, ]) await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ - { provider: 'deepseek', id: 'flash', name: 'flash' }, + { provider: 'deepseek', id: 'flash', name: 'flash', inputModalities: ['text', 'image'] }, { provider: 'deepseek', id: 'pro', name: 'Pro', description: 'Larger model' }, ]) await expect(ctx.llm.listModels('empty')).resolves.toEqual([]) await expect(ctx.llm.resolveModelInfo('deepseek', 'flash')).resolves.toMatchObject({ context: { contextWindow: 128_000 }, + inputModalities: ['text', 'image'], defaultMaxTokens: 64_000, reasoning: { efforts: [{ id: 'off', name: 'off' }, { id: 'max', name: 'max' }], defaultEffort: 'max', }, }) + await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('inputModalities') await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.not.toHaveProperty('context') // Efforts without a configured default preserve the provider's own default. await expect(ctx.llm.resolveModelInfo('deepseek', 'pro')).resolves.toMatchObject({ @@ -1111,11 +1115,31 @@ describe('apply (the plugin entry)', () => { writeFileSync(file, sessionJsonl(TEXT_CHUNKS.map((c, i) => chunkEvent(i + 1, 1, 1, c))), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) - apply(ctx, { file, providers: [{ id: 'm', models: [{ id: 'm' }] }], paceMs: 1 }) - expect(ctx.llm.listProviders()).toEqual([{ id: 'm', name: 'm' }]) + apply(ctx, { + file, + providers: [ + { id: 'm', models: [{ id: 'm', inputModalities: ['image'] }, { id: 'text' }] }, + { id: 'empty' }, + ], + paceMs: 1, + }) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm', name: 'm' }, { id: 'empty', name: 'empty' }]) + await expect(ctx.llm.resolveModelInfo('m', 'm')).resolves.toMatchObject({ inputModalities: ['image'] }) expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) + it.each([ + ['a string', 'image'], + ['an unknown modality', ['audio']], + ])('rejects inputModalities configured as %s during load', (_case, inputModalities) => { + const ctx = new Context() + const providers = [{ id: 'm', models: [{ id: 'm', inputModalities }] }] as unknown as + NonNullable + expect(() => { apply(ctx, { file, providers }) }).toThrow( + 'llm-replay: provider "m" model "m" inputModalities must be an array containing only "text" and "image"', + ) + }) + it('falls back to $DSH_SNAPSHOT_FILE / $DSH_SNAPSHOT_OVERRIDE when config is empty', async () => { writeFileSync(file, sessionJsonl([]), 'utf8') const overrideFile = join(dir, 'replay.override.json') diff --git a/packages/tasks/tasks-local/src/index.ts b/packages/tasks/tasks-local/src/index.ts index 7978944edb..6366024f74 100644 --- a/packages/tasks/tasks-local/src/index.ts +++ b/packages/tasks/tasks-local/src/index.ts @@ -15,7 +15,10 @@ import { AnonymousEntries, ScopedLayers, scopeOf } from '@deepseek-ai/dsh-scope' import type { ScopeLayer } from '@deepseek-ai/dsh-scope' import { deadline, timeoutOf } from '@deepseek-ai/dsh-timeout' import { TaskService, TaskId } from '@deepseek-ai/dsh-tasks' -import type { TaskDoneListener, TaskKind, TaskOutcome, TaskRead, TaskSnapshot, TaskStart, TaskStatus } from '@deepseek-ai/dsh-tasks' +import type { + TaskDoneListener, TaskKind, TaskOutcome, TaskRead, TaskSnapshot, TaskStart, TaskStatus, + TasksChangedListener, +} from '@deepseek-ai/dsh-tasks' /** Timeout code that distinguishes a bounded wait from caller cancellation. */ export const TASK_WAIT_TIMEOUT = 'TASK_WAIT_TIMEOUT' @@ -60,9 +63,10 @@ function isTerminal(status: TaskStatus): boolean { class TaskLayer implements ScopeLayer { readonly surfaces = new AnonymousEntries() readonly listeners = new AnonymousEntries() + readonly changed = new AnonymousEntries() isEmpty(): boolean { - return this.surfaces.isEmpty() && this.listeners.isEmpty() + return this.surfaces.isEmpty() && this.listeners.isEmpty() && this.changed.isEmpty() } } @@ -147,6 +151,9 @@ export class LocalTaskService extends TaskService { this.settle(task, { status: 'failed', detail: String(error) }) }, ) + // Registration is complete and cannot fail from here, so the visible set + // has genuinely changed. + this.notifyChanged(task.owner) return id } @@ -184,6 +191,7 @@ export class LocalTaskService extends TaskService { task.cancel(reason) task.status = 'stopping' task.reported = true + this.notifyChanged(task.owner) return 'requested' } @@ -245,6 +253,14 @@ export class LocalTaskService extends TaskService { ) } + onTasksChanged(listener: TasksChangedListener): () => void { + return this.layers.effect( + this.ctx, + layer => layer.changed.append(listener), + { label: 'tasks.onTasksChanged()' }, + ) + } + attachSurface(name: string): () => void { // One token per call keeps duplicate labels independently disposable. const token = Symbol(name) @@ -318,6 +334,35 @@ export class LocalTaskService extends TaskService { } } + /** + * The change observers that own `owner`'s updates, resolved exactly like + * {@link listenersFor}: the global layer — a host composition's own carrier, + * which serves every owner — then each scoped layer along the owner's chain. + * An observer outside that chain belongs to another composition and would + * otherwise be told about agents it does not compose. + * @param owner - the owner whose visible set moved, or undefined for unowned work. + * @returns the observers to notify, in registration order per layer. + */ + private *changedFor(owner?: Agent): IterableIterator { + yield* this.layers.global.changed.values() + const scope = owner === undefined ? undefined : scopeOf(owner.ctx) + for (const layer of this.layers.chainLayers(scope)) yield* layer.changed.values() + } + + /** + * Announce that one owner's visible set changed. Each listener is contained + * so an observer cannot break a lifecycle commit that already happened. + */ + private notifyChanged(owner: Agent | undefined): void { + for (const listener of this.changedFor(owner)) { + try { + listener(owner) + } catch (error: unknown) { + this.selfCtx.logger.warn(`tasks: onTasksChanged listener threw: ${String(error)}`) + } + } + } + /** * Record the first terminal outcome, notify contained listeners, and release * waiters. First-wins preserves a teardown force-failure against late producer @@ -347,6 +392,7 @@ export class LocalTaskService extends TaskService { task.waitResolvers.clear() for (const resolveWait of waitResolvers) resolveWait() task.markSettled() + this.notifyChanged(task.owner) } /** @@ -379,6 +425,9 @@ export class LocalTaskService extends TaskService { this.cancelForTeardown(owned, 'owner disposed') await Promise.all(owned.map(task => task.settled)) for (const task of owned) this.store.delete(task.id) + // Removal is the one visible-set change no per-task record carries, so it + // must be announced here or an observer keeps the dropped rows forever. + if (owned.length > 0) this.notifyChanged(owner) } /** @@ -392,7 +441,14 @@ export class LocalTaskService extends TaskService { const all = [...this.store.values()] this.cancelForTeardown(all, 'tasks service disposed') await Promise.all(all.map(task => task.settled)) + // Distinct owners whose records just disappeared. A change observer files + // into the layer of the context that registered it, so a consumer mounted + // outside this service — the api-proxy carrier registers from the mux + // stream — is still reachable here. Without this it keeps the rows it last + // received after a registry reload. + const emptied = new Set(all.map(task => task.owner)) this.store.clear() + for (const owner of emptied) this.notifyChanged(owner) // Detach cross-fiber owner effects after the shared store is quiescent. const ownerCleanups = [...this.ownerCleanups.values()] this.ownerCleanups.clear() @@ -410,6 +466,10 @@ export class LocalTaskService extends TaskService { try { task.cancel(reason) task.status = 'stopping' + // Teardown reaches settlement only after the producer releases, which a + // slow stop can defer; announcing the transition here is what keeps an + // observer from showing `running` for that whole window. + this.notifyChanged(task.owner) } catch (error: unknown) { const detail = `cancel threw during teardown; work may be orphaned: ${String(error)}` this.selfCtx.logger.warn(`tasks: cancel of ${task.id} threw during teardown; task record forced failed and work may be orphaned: ${String(error)}`) diff --git a/packages/tasks/tasks-local/tests/tasks.spec.ts b/packages/tasks/tasks-local/tests/tasks.spec.ts index b64f2142aa..b4f0ced798 100644 --- a/packages/tasks/tasks-local/tests/tasks.spec.ts +++ b/packages/tasks/tasks-local/tests/tasks.spec.ts @@ -847,3 +847,150 @@ describe('LocalTaskService disposal', () => { expect(() => ctx.tasks.start(producer().spec)).toThrow('no control surface serves this agent') }) }) + +describe('LocalTaskService.onTasksChanged', () => { + it('fires after registration, the stopping transition, and settlement', async () => { + const ctx = await harness() + const owner = stubAgent(ctx, 'alice') + ctx.agents.register(owner) + const seen: (string | undefined)[] = [] + ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id)) + + const p = producer({ owner }) + const id = ctx.tasks.start(p.spec) + // Registration is announced only once the record is readable. + expect(seen).toEqual(['alice']) + expect(ctx.tasks.list(owner)).toHaveLength(1) + + expect(ctx.tasks.kill(id, owner)).toBe('requested') + expect(seen).toEqual(['alice', 'alice']) + expect(ctx.tasks.get(id, owner).status).toBe('stopping') + + p.settle({ status: 'killed' }) + await tick() + expect(seen).toEqual(['alice', 'alice', 'alice']) + expect(ctx.tasks.get(id, owner).status).toBe('killed') + await disposeAgentScope(owner) + }) + + it('reports an unowned change as undefined, since every caller can see it', async () => { + const ctx = await harness() + const seen: (string | undefined)[] = [] + ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id)) + + ctx.tasks.start(producer().spec) + expect(seen).toEqual([undefined]) + }) + + it('announces the owner-disposal removal, and stays silent when that owner had none', async () => { + const ctx = await harness() + const owner = stubAgent(ctx, 'alice') + const bystander = stubAgent(ctx, 'bob') + ctx.agents.register(owner) + ctx.agents.register(bystander) + const p = producer({ owner }) + ctx.tasks.start(p.spec) + + const seen: (string | undefined)[] = [] + ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id)) + p.settle({ status: 'completed' }) + await tick() + expect(seen).toEqual(['alice']) + + // Disposing an owner with no records changes no visible set. + await disposeAgentScope(bystander) + expect(seen).toEqual(['alice']) + + await disposeAgentScope(owner) + expect(seen).toEqual(['alice', 'alice']) + expect(ctx.tasks.list(owner)).toEqual([]) + }) + + it('contains a throwing listener so the lifecycle commit still stands', async () => { + const ctx = await harness() + const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {}) + const seen: (string | undefined)[] = [] + ctx.tasks.onTasksChanged(() => { throw new Error('observer boom') }) + ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id)) + + const id = ctx.tasks.start(producer().spec) + expect(id).toBe('bash-1') + expect(seen).toEqual([undefined]) + expect(warn).toHaveBeenCalledWith(expect.stringContaining('onTasksChanged listener threw')) + }) + + it('unregisters through its disposer and with its fiber (HMR safety)', async () => { + const ctx = await harness() + const seen: number[] = [] + const detach = ctx.tasks.onTasksChanged(() => void seen.push(1)) + const fiber = await ctx.plugin(Object.assign((inner: Context) => { + inner.tasks.onTasksChanged(() => void seen.push(2)) + }, { inject: ['tasks'] })) + + ctx.tasks.start(producer().spec) + expect(seen).toEqual([1, 2]) + + detach() + detach() // second call of the same disposer is a no-op + ctx.tasks.start(producer().spec) + expect(seen).toEqual([1, 2, 2]) + + await fiber.dispose() + ctx.tasks.start(producer().spec) + expect(seen).toEqual([1, 2, 2]) + }) +}) + +describe('LocalTaskService teardown change notifications', () => { + it('announces the stopping transition during owner teardown, before settlement', async () => { + const ctx = await harness() + const owner = stubAgent(ctx, 'alice') + ctx.agents.register(owner) + const p = producer({ owner }) + const id = ctx.tasks.start(p.spec) + + const statuses: (string | undefined)[] = [] + ctx.tasks.onTasksChanged((changed) => { + statuses.push(changed === undefined ? undefined : ctx.tasks.list(changed)[0]?.status) + }) + + // A slow producer keeps teardown parked between cancel and settlement; + // an observer must not be left showing `running` for that whole window. + const disposal = disposeAgentScope(owner) + await tick() + expect(statuses).toEqual(['stopping']) + + p.settle({ status: 'killed' }) + await disposal + // Settlement, then the removal that empties the visible set. + expect(statuses).toEqual(['stopping', 'killed', undefined]) + expect(ctx.tasks.list(owner)).toEqual([]) + void id + }) + + it('announces the emptied set to a listener registered outside this service (reload safety)', async () => { + const ctx = new Context() + await ctx.plugin(AgentRegistry) + const fiber = await ctx.plugin(LocalTaskService) + ctx.tasks.attachSurface('test-surface') + + // The api-proxy carrier registers from its own stream context, not the + // registry's fiber, so it is still listening when the registry unloads. + const seen: (string | undefined)[] = [] + ctx.tasks.onTasksChanged(changed => void seen.push(changed?.id)) + let settle!: (outcome: TaskOutcome) => void + ctx.tasks.start({ + kind: 'bash', + label: 'sleep 600', + run: () => ({ + cancel() { settle({ status: 'killed' }) }, + done: new Promise((resolve) => { settle = resolve }), + }), + }) + seen.length = 0 + + await fiber.dispose() + // stopping (teardown cancel), settlement, then the final empty set. + expect(seen).toEqual([undefined, undefined, undefined]) + }) +}) diff --git a/packages/tasks/tasks/README.i18n.yaml b/packages/tasks/tasks/README.i18n.yaml index 95bb5a3889..7c7ceba672 100644 --- a/packages/tasks/tasks/README.i18n.yaml +++ b/packages/tasks/tasks/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write packages/tasks/tasks/README.md -README.md: f23a93e3cb1fc5aad5bad053f832bb66baa8eb64 -README.zh.md: c3ea9125c4db9f2d86722cbf490b4f0eecfbe25a +README.md: 053e407d2e28cb175ebe9de15c7e16ef04e95cb8 +README.zh.md: dd39b1098cd01d7db9db6e49210c2b1149b37ecb diff --git a/packages/tasks/tasks/README.md b/packages/tasks/tasks/README.md index f23a93e3cb..053e407d2e 100644 --- a/packages/tasks/tasks/README.md +++ b/packages/tasks/tasks/README.md @@ -12,9 +12,10 @@ The background task registry contract (`ctx.tasks`). The abstract `TaskService` - `kill(id, caller?, reason?)` invokes producer cancellation before changing status. A cancellation throw leaves the task running; success changes it to `stopping` and marks terminal delivery reported. - `wait(id, timeoutMs, caller?, signal?)` returns a terminal snapshot or the live snapshot at timeout. Aborting stops only the wait; settlement wins once it has committed terminal delivery to that waiter. - `onTaskDone(listener)` observes each terminal record with the exact owner. Listener throws and rejections are contained; listener work is not awaited. +- `onTasksChanged(listener)` observes visible-set changes — registration, every stopping transition (teardown's included, before it awaits a slow producer), settlement, owner-disposal removal, and the emptying service disposal commits — carrying only the owner whose set moved, or `undefined` when an unowned task changed and every caller's set moved with it. It is owner-granular because removal is a change no per-task record can express, and it is not a superset of `onTaskDone`: it carries no delivery meaning and marks nothing reported. The registration binds to the calling fiber, so an observer mounted outside the registry still sees the disposal emptying. - `attachSurface(name)` declares a control surface for its effect lifetime. `start()` fails before producer execution when no attached surface serves the spec's owner. -Both registrations are owner-relative, because one registry serves every composition in the process. A surface or listener registered from an unscoped context serves every owner; one registered under an agent composition's scope serves exactly the agents composed under it. So a composition that loads no control surface cannot start background work on the strength of another composition's controls, and one settlement notifies only the listeners its owner's composition registered. +All three registrations are owner-relative, because one registry serves every composition in the process. A surface or listener registered from an unscoped context serves every owner; one registered under an agent composition's scope serves exactly the agents composed under it. So a composition that loads no control surface cannot start background work on the strength of another composition's controls, and one settlement notifies only the listeners its owner's composition registered. Owned access compares the task's `SessionId` with the caller's. Ids such as `bash-1` are predictable, so this fence is the boundary. Unowned tasks are open to callers and last until service disposal. diff --git a/packages/tasks/tasks/README.zh.md b/packages/tasks/tasks/README.zh.md index c3ea9125c4..dd39b1098c 100644 --- a/packages/tasks/tasks/README.zh.md +++ b/packages/tasks/tasks/README.zh.md @@ -12,9 +12,10 @@ - `kill(id, caller?, reason?)` 在更改状态前调用生产方取消。取消抛出异常时任务保持运行；成功则把状态改为 `stopping`，并将终止交付标记为已报告。 - `wait(id, timeoutMs, caller?, signal?)` 返回终止快照，或在超时时返回存活快照。中止只会停止等待；一旦终止交付已向该等待方提交，终止结果优先。 - `onTaskDone(listener)` 观察每条终止记录及其精确 owner。监听器抛出的异常和产生的拒绝都会被隔离；系统不会等待监听器工作。 +- `onTasksChanged(listener)` 观察可见集合的变化——注册、每一次转入 stopping（包括 teardown 在等待缓慢生产者之前的那一次）、结算、owner 销毁时的移除，以及服务销毁提交的清空——只携带集合发生变化的那个 owner，或在无主任务变化、因而每个调用方的集合都随之变化时携带 `undefined`。它按 owner 分粒度，因为移除是任何逐任务记录都无法表达的变化；它也不是 `onTaskDone` 的超集：它不含任何投递含义，也不把任何东西标为已上报。注册绑定的是调用方 fiber，因此挂在注册表之外的观察者仍能收到销毁时的清空。 - `attachSurface(name)` 在其 effect 生命周期内声明控制表层。当没有任何已附加的表层服务于 spec 的所有者时，`start()` 会在生产方执行前失败。 -这两类注册都是相对于所有者的，因为一个注册表要服务进程内的每一套组合。从不带 scope 的上下文注册的表层或监听器服务于每个所有者；在某套 agent 组合的 scope 下注册的，则恰好服务于在该组合下组合出的 agent。因此，未加载任何控制表层的组合无法借另一套组合的控制工具启动后台工作，而一次结算也只会通知其所有者所属组合注册的监听器。 +这三类注册都是相对于所有者的，因为一个注册表要服务进程内的每一套组合。从不带 scope 的上下文注册的表层或监听器服务于每个所有者；在某套 agent 组合的 scope 下注册的，则恰好服务于在该组合下组合出的 agent。因此，未加载任何控制表层的组合无法借另一套组合的控制工具启动后台工作，而一次结算也只会通知其所有者所属组合注册的监听器。 有 owner 的访问会比较任务的 `SessionId` 与调用方。`bash-1` 等 id 可预测，因此这道隔离是安全边界。无 owner 的任务向调用方开放，并持续到服务释放。 diff --git a/packages/tasks/tasks/package.json b/packages/tasks/tasks/package.json index cfc7fa70bf..8c968b743b 100644 --- a/packages/tasks/tasks/package.json +++ b/packages/tasks/tasks/package.json @@ -22,12 +22,17 @@ "types": "./lib/types/invariant.d.ts", "default": "./lib/invariant.js" }, + "./brand": { + "types": "./lib/types/brand.d.ts", + "default": "./lib/types/brand.js" + }, "./src/*": "./src/*", "./package.json": "./package.json" }, "files": [ "lib/index.js", "lib/invariant.js", + "lib/types/**/*.js", "lib/types/**/*.d.ts" ], "license": "BSD-3-Clause", diff --git a/packages/tasks/tasks/src/brand.ts b/packages/tasks/tasks/src/brand.ts new file mode 100644 index 0000000000..b9596514b3 --- /dev/null +++ b/packages/tasks/tasks/src/brand.ts @@ -0,0 +1,28 @@ +/** + * dsh-tasks' owned branded id, carried across the registry, the model-facing + * control surface, and the client wire. + * + * It lives in its own leaf because the package root and `./types` both reach + * `dsh-agent` through the owner and listener signatures, which a Client program + * cannot resolve even as a type. A browser-safe consumer imports the id here; + * `Branded` itself comes from the zero-dependency `@deepseek-ai/dsh-brand`. + * + * @module @deepseek-ai/dsh-tasks/brand + */ + +import type { Branded } from '@deepseek-ai/dsh-brand' + +/** + * Identifies a background task. The registry generates `-N`; predictable + * ids rely on owner authorization rather than secrecy. + */ +export type TaskId = Branded<'TaskId'> + +/** + * Brand a string as a {@link TaskId}. + * @param id - the raw task-id string (the registry generates `-N`). + * @returns the same string, branded; no validation is performed. + */ +export function TaskId(id: string): TaskId { + return id as TaskId +} diff --git a/packages/tasks/tasks/src/index.ts b/packages/tasks/tasks/src/index.ts index 126ba075ff..06bb2e38fb 100644 --- a/packages/tasks/tasks/src/index.ts +++ b/packages/tasks/tasks/src/index.ts @@ -8,7 +8,9 @@ import { Context, Service } from '@deepseek-ai/cordis' import type { Agent } from '@deepseek-ai/dsh-agent' -import type { TaskDoneListener, TaskId, TaskRead, TaskSnapshot, TaskStart } from './types.ts' +import type { + TaskDoneListener, TaskId, TaskRead, TaskSnapshot, TaskStart, TasksChangedListener, +} from './types.ts' export { TaskId } from './types.ts' export type { @@ -21,6 +23,7 @@ export type { TaskSnapshot, TaskStart, TaskStatus, + TasksChangedListener, } from './types.ts' declare module '@deepseek-ai/cordis' { @@ -134,6 +137,30 @@ export abstract class TaskService extends Service { */ abstract onTaskDone(listener: TaskDoneListener): () => void + /** + /** + * Register an effect-scoped observer of visible-set changes. It fires after + * every commit that changes what {@link list} returns for that owner — + * registration, every stopping transition (including the one teardown + * performs before it awaits a slow producer), settlement, owner-disposal + * removal, and the emptying that service disposal commits — so an observer + * re-reads rather than accumulating deltas. + * + * Delivery is owner-relative on the same terms as {@link onTaskDone}: an + * observer registered from an unscoped context — a host composition's own + * carrier — sees every owner, while one registered under an agent + * composition's scope sees exactly the agents composed under it. + * + * This is not a superset of {@link onTaskDone}: that one delivers the terminal + * record under first-wins semantics a control surface couples to notice + * delivery, while this one carries no delivery meaning and marks nothing + * reported. Listeners are contained and never awaited. + * @param listener - receives the owner whose visible set changed, or + * `undefined` when an unowned task changed and every caller's set did. + * @returns disposer that unregisters the listener. + */ + abstract onTasksChanged(listener: TasksChangedListener): () => void + /** * Attach an effect-scoped surface that can read and stop tasks. It serves the * owners its registering context's scope covers, and {@link start} refuses an diff --git a/packages/tasks/tasks/src/types.ts b/packages/tasks/tasks/src/types.ts index d722f3fce6..a05b75817c 100644 --- a/packages/tasks/tasks/src/types.ts +++ b/packages/tasks/tasks/src/types.ts @@ -4,24 +4,11 @@ * @module @deepseek-ai/dsh-tasks/types */ -import type { Branded } from '@deepseek-ai/dsh-brand' import type { Agent } from '@deepseek-ai/dsh-agent' import type { SessionId } from '@deepseek-ai/dsh-session' +import type { TaskId } from './brand.ts' -/** - * Identifies a background task. The registry generates `-N`; predictable - * ids rely on owner authorization rather than secrecy. - */ -export type TaskId = Branded<'TaskId'> - -/** - * Brand a string as a {@link TaskId}. - * @param id - the raw task-id string (the registry generates `-N`). - * @returns the same string, branded; no validation is performed. - */ -export function TaskId(id: string): TaskId { - return id as TaskId -} +export { TaskId } from './brand.ts' /** * Task lifecycle: `running`, optionally `stopping`, then exactly one terminal @@ -157,3 +144,14 @@ export type TaskDoneListener = ( snapshot: TaskSnapshot, owner: Agent | undefined, ) => void | PromiseLike + +/** + * Observation callback for a change to what one owner's {@link TaskService.list} + * would return. It is owner-granular rather than task-granular because the + * change may be a removal, which no per-task record can express, and because + * its consumers re-read the whole visible set anyway. + * + * An `undefined` owner means an unowned task changed, so every caller's visible + * set changed with it. + */ +export type TasksChangedListener = (owner: Agent | undefined) => void diff --git a/packages/tasks/tasks/tests/service.spec.ts b/packages/tasks/tasks/tests/service.spec.ts index 73b0a3fe25..c9a3316d94 100644 --- a/packages/tasks/tasks/tests/service.spec.ts +++ b/packages/tasks/tasks/tests/service.spec.ts @@ -2,7 +2,9 @@ import { describe, expect, it } from 'vitest' import { Context } from '@deepseek-ai/cordis' import type { Agent } from '@deepseek-ai/dsh-agent' import { TaskId, TaskService } from '@deepseek-ai/dsh-tasks' -import type { TaskDoneListener, TaskRead, TaskSnapshot, TaskStart } from '@deepseek-ai/dsh-tasks' +import type { + TaskDoneListener, TaskRead, TaskSnapshot, TaskStart, TasksChangedListener, +} from '@deepseek-ai/dsh-tasks' /** * Minimal concrete registry: one canned record. The Service Definition owns the contract @@ -50,6 +52,10 @@ class StubTaskService extends TaskService { return () => {} } + onTasksChanged(_listener: TasksChangedListener): () => void { + return () => {} + } + attachSurface(_name: string): () => void { return () => {} } @@ -70,6 +76,8 @@ describe('TaskService seam', () => { await expect(ctx.tasks.wait(id, 5)).resolves.toMatchObject({ id }) const detachListener = ctx.tasks.onTaskDone(() => {}) detachListener() + const detachChanges = ctx.tasks.onTasksChanged(() => {}) + detachChanges() detachSurface() }) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index fe2a2f978f..fe021d4031 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -422,6 +422,9 @@ importers: '@deepseek-ai/dsh-app-boot': specifier: workspace:* version: link:../packages/boot/app-boot + '@deepseek-ai/dsh-attachment-local': + specifier: workspace:* + version: link:../packages/attachment/attachment-local '@deepseek-ai/dsh-bash': specifier: workspace:* version: link:../packages/bash/bash @@ -1563,6 +1566,9 @@ importers: '@deepseek-ai/dsh-client-ui-subagent': specifier: workspace:^ version: link:../../client/ui-subagent + '@deepseek-ai/dsh-client-ui-task': + specifier: workspace:^ + version: link:../../client/ui-task '@deepseek-ai/dsh-client-ui-theme': specifier: workspace:^ version: link:../../client/ui-theme @@ -2709,6 +2715,40 @@ importers: specifier: ~18.3.1 version: 18.3.31 + packages/client/ui-task: + dependencies: + react: + specifier: ^18.2.0 + version: 18.3.1 + devDependencies: + '@deepseek-ai/cordis': + specifier: workspace:^ + version: link:../../../vendor/cordis + '@deepseek-ai/dsh-client-locale': + specifier: workspace:^ + version: link:../locale + '@deepseek-ai/dsh-client-runtime': + specifier: workspace:^ + version: link:../runtime + '@deepseek-ai/dsh-client-test-runtime': + specifier: workspace:^ + version: link:../test-runtime + '@deepseek-ai/dsh-client-ui-conversation': + specifier: workspace:^ + version: link:../ui-conversation + '@deepseek-ai/dsh-client-ui-primitives': + specifier: workspace:^ + version: link:../ui-primitives + '@deepseek-ai/dsh-client-ui-slots': + specifier: workspace:^ + version: link:../ui-slots + '@deepseek-ai/dsh-invariants': + specifier: workspace:^ + version: link:../../support/invariants + '@types/react': + specifier: ~18.3.1 + version: 18.3.31 + packages/client/ui-theme: dependencies: '@deepseek-ai/dsh-client-connection': @@ -3886,6 +3926,9 @@ importers: '@deepseek-ai/dsh-agent-loop-testkit': specifier: workspace:^ version: link:../../support/agent-loop-testkit + '@deepseek-ai/dsh-attachment': + specifier: workspace:^ + version: link:../../attachment/attachment '@deepseek-ai/dsh-fs': specifier: workspace:^ version: link:../fs @@ -4376,6 +4419,9 @@ importers: '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent + '@deepseek-ai/dsh-tasks': + specifier: workspace:^ + version: link:../../tasks/tasks '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools @@ -5000,6 +5046,9 @@ importers: '@deepseek-ai/dsh-subprocess': specifier: workspace:^ version: link:../../subprocess/subprocess + '@deepseek-ai/dsh-timeout': + specifier: workspace:^ + version: link:../../util/timeout '@deepseek-ai/dsh-tools': specifier: workspace:^ version: link:../../core/tools diff --git a/scripts/gen-cordis-catalog.ts b/scripts/gen-cordis-catalog.ts index 4a26b80c28..b6a315d7ad 100644 --- a/scripts/gen-cordis-catalog.ts +++ b/scripts/gen-cordis-catalog.ts @@ -384,6 +384,7 @@ export const LINK_MAP: Readonly> = { TaskRead: 'tasks.md', TaskSnapshot: 'tasks.md', TaskStart: 'tasks.md', + TasksChangedListener: 'tasks.md', TokenMeasurement: 'token-meter.md', CodeDispatchLog: 'tools.md', PostToolDecision: 'tools.md', @@ -462,6 +463,7 @@ export const FOUNDATION_TYPE_NAMES: ReadonlySet = new Set([ 'Promise', 'Record', 'Readonly', + 'Uint8Array', ]) /** Project types deliberately documented outside the subsystems catalog. */ diff --git a/scripts/gen-third-party-notices.ts b/scripts/gen-third-party-notices.ts index faf8c756dd..fb6838de54 100644 --- a/scripts/gen-third-party-notices.ts +++ b/scripts/gen-third-party-notices.ts @@ -27,8 +27,8 @@ const ALL_KINDS = ['dependencies', 'devDependencies', 'optionalDependencies', 'p * root manifest), test infrastructure, the documentation site, the runnable * demo leaves, and the native launcher's build workspace. A runtime * declaration by anything outside these areas is a disclosure-relevant - * runtime dependency, because `scripts/install.sh` installs the repository - * itself and any plugin package can be mounted from a user's `cordis.yml`. + * runtime dependency because any plugin package can be mounted from a user's + * `cordis.yml`. */ const DEV_ONLY_AREAS = [ 'package.json', @@ -369,7 +369,7 @@ function collectNpmDeps(): ExternalDep[] { */ export function tierExternalDeps(manifests: Map, names: Set): Map { const tiers = new Map() - // `tsx` is runtime by fiat: `bin/dsh` execs the CLI through its ESM hook. + // `tsx` is runtime by fiat: the root source-run scripts execute through its ESM hook. tiers.set('tsx', true) for (const [path, manifest] of manifests) { const devOnly = DEV_ONLY_AREAS.some(area => (area.endsWith('/') ? path.startsWith(area) : path === area)) @@ -707,7 +707,7 @@ ${vendored.map(row => `| \`${row.npmName}\` | \`${row.upstreamName}\` | [${row.u ## Runtime npm dependencies -External packages that a workspace package resolves at runtime. \`scripts/install.sh\` installs this repository itself, so the tier covers every plugin a user can mount from \`cordis.yml\` — not only what the \`dsh\` CLI, Web UI, and Python SDK runtime load by default. +External packages that a workspace package resolves at runtime. The tier covers every plugin a user can mount from \`cordis.yml\` — not only what the \`dsh\` CLI, Web UI, and Python SDK runtime load by default. ${renderNpmTable(runtimeDeps)} diff --git a/scripts/gen-tool-catalog.ts b/scripts/gen-tool-catalog.ts index 1c3aaddf43..a2ff4ce533 100644 --- a/scripts/gen-tool-catalog.ts +++ b/scripts/gen-tool-catalog.ts @@ -24,6 +24,8 @@ import * as BashEnvPlugin from '@deepseek-ai/dsh-bash-env' import { PwshLocalExecutor } from '@deepseek-ai/dsh-pwsh-local' import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local' import LocalFileSystem from '@deepseek-ai/dsh-fs-local' +import { AttachmentStore } from '@deepseek-ai/dsh-attachment' +import type { ImageAttachmentLimits, ImageAttachmentRef, SaveImageAttachment, StoredImageAttachment } from '@deepseek-ai/dsh-attachment' import UserInteractionService from '@deepseek-ai/dsh-user-interaction' import PlanModeService from '@deepseek-ai/dsh-plan-mode' import WebService from '@deepseek-ai/dsh-web' @@ -60,6 +62,29 @@ import VmWorkflowEngine from '@deepseek-ai/dsh-workflow-workerthread' import * as ToolRalph from '@deepseek-ai/dsh-tool-ralph' import * as ToolWorkflow from '@deepseek-ai/dsh-tool-workflow' +/** Attachment seam marker that makes the attachments-conditional `read_image` schema harvestable. */ +class CatalogAttachmentStore extends AttachmentStore { + readonly imageLimits: ImageAttachmentLimits = Object.freeze({ + maxImageBytes: 1, + maxImagesPerMessage: 1, + maxMessageImageBytes: 1, + maxImagePixels: 1, + mediaTypes: Object.freeze(['image/png'] as const), + }) + + override validateImage(_input: SaveImageAttachment): Promise { + return Promise.reject(new Error('gen-tool-catalog: attachment validation is unreachable during schema harvest')) + } + + override saveImage(_input: SaveImageAttachment): Promise { + return Promise.reject(new Error('gen-tool-catalog: attachment writes are unreachable during schema harvest')) + } + + override readImage(_ref: ImageAttachmentRef): Promise { + return Promise.reject(new Error('gen-tool-catalog: attachment reads are unreachable during schema harvest')) + } +} + const root = resolve(import.meta.dirname, '..') const OUT = 'docs/tool-catalog.md' @@ -265,16 +290,18 @@ const TOOL_PACKAGES: ToolPackage[] = [ pkg: '@deepseek-ai/dsh-tool-fs', dir: 'tool-fs', source: 'packages/fs/tool-fs/src/index.ts', - requires: ['ctx.tools', 'ctx.fs', 'ctx.systemPrompt'], - writes: ['tool/call', 'fs/write-intent or fs/edit-intent for mutations', 'fs/observed after read presence/absence or successful mutation', 'tool/result'], + requires: ['ctx.tools', 'ctx.fs', 'ctx.systemPrompt', 'ctx.attachments (read_image registration)', 'ctx.llm + an image-capable route (read_image execution)'], + writes: ['tool/call', 'fs/write-intent or fs/edit-intent for mutations', 'fs/observed after read presence/absence or successful file operation', 'durable attachment (read_image)', 'tool/result'], async mount(ctx) { // The tool needs `fs`; the bare provider is sufficient because policy - // changes behavior, not schema shape. + // changes behavior, not schema shape. The catalog seam marker opts into + // the attachments-conditional read_image schema without attachment I/O. await ctx.plugin(LocalFileSystem) + await ctx.plugin(CatalogAttachmentStore) await ctx.plugin(ToolFs) }, note: - 'The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. The tool schemas above are identical with or without the policy plugin.', + 'The read-before-write/edit policy is added by `@deepseek-ai/dsh-fs-policy` (an `fs/*` event-gate plugin, no schema change); a deployment that loads these tools is expected to also load it. `read_image` is not registered without `ctx.attachments`; its schema is route-independent, and execution refuses unless the exact routed model declares image input.', }, { pkg: '@deepseek-ai/dsh-tool-fs-search', diff --git a/scripts/install.sh b/scripts/install.sh deleted file mode 100755 index f290782892..0000000000 --- a/scripts/install.sh +++ /dev/null @@ -1,425 +0,0 @@ -#!/bin/sh -# dsh one-line installer. -# -# curl -fsSL https://raw.githubusercontent.com/deepseek-ai/deepseek-harness-sdk/master/scripts/install.sh | sh -# -# It clones the harness under ~/.dsh/source (the master clone at -# ~/.dsh/source/master), adds a per-install staging worktree at -# ~/.dsh/source/staging- on branch dsh-staging/, checks -# host dependencies (git, Node, pnpm) and offers to install a missing pnpm, runs -# `pnpm install`, points the stable `~/.dsh/source/current` symlink -# at that staging worktree and symlinks `dsh` onto PATH at `current/bin/dsh`, -# records your API credentials in the Harness home (`~/.dsh`) dsh reads at boot, -# builds the repository artifacts, and launches the Web UI. Keeping every -# checkout under ~/.dsh/source keeps successive -# upgrades in one place instead of scattered sibling clones, and lets staging -# worktrees share the master clone's object store. The PATH symlink resolves through -# `current`, so an upgrade repoints one stable symlink instead of relinking PATH: -# the `dsh` on PATH never moves and can never dangle. -# -# When run from inside an existing checkout (e.g. `sh scripts/install.sh` rather -# than `curl ... | sh`) it never clones and never touches that working tree; -# DSH_REF is ignored. Instead it *adopts* the checkout: `git rev-parse -# --git-common-dir` resolves the repository behind it (for a linked worktree that -# is the real clone, not the worktree), and a fresh staging worktree branched -# from the checkout's HEAD lands in the source container beside `current`. The -# container owns staging worktrees and `current`; the clone is discovered, not -# owned, so an arbitrary clone (~/src/dsh) and a managed one converge on one -# layout and stay upgradable. Adoption carries committed work only: the staging -# worktree branches from HEAD, so uncommitted changes stay in the checkout. -# Setting DSH_SOURCE to a different directory opts back into the normal -# clone/worktree path. -# -# Adopting an arbitrary clone leaves the container not self-contained: its -# staging worktrees hold an absolute gitdir pointer into that clone, so deleting -# it breaks them. `git worktree list` in that clone is the record of which -# worktrees depend on it. -# -# When run through `curl | sh` the script text arrives on stdin, so every -# prompt and the final launch read the controlling terminal (/dev/tty) directly; -# with no terminal the script prints the manual next steps instead. -# -# Overridable via environment: -# DSH_REF branch or tag to clone/checkout (default: master) -# DSH_REPO clone URL (default: the GitHub repo) -# DSH_SOURCE source container directory (default: ~/.dsh/source) -# DSH_MASTER master clone directory (default: $DSH_SOURCE/master) -# DSH_CURRENT stable symlink to the active worktree (default: $DSH_SOURCE/current) -# DSH_BIN_DIR directory the `dsh` symlink lands in (default: ~/.local/bin) -# DSH_HOME Harness home holding profiles and user patches (default: ~/.dsh) -set -eu - -DSH_REF=${DSH_REF:-master} -DSH_REPO=${DSH_REPO:-https://github.com/deepseek-ai/deepseek-harness-sdk.git} -# DSH_SOURCE is the staging-worktree container and the default home of `current`. -# DSH_MASTER names the main clone: clone mode defaults it inside DSH_SOURCE, -# while adoption discovers an existing clone anywhere on disk. Remember whether -# DSH_SOURCE was explicit so a different path selects clone mode. -if [ -n "${DSH_SOURCE:-}" ]; then DSH_SOURCE_EXPLICIT=1; else DSH_SOURCE_EXPLICIT=0; fi -DSH_SOURCE=${DSH_SOURCE:-$HOME/.dsh/source} -DSH_MASTER=${DSH_MASTER:-$DSH_SOURCE/master} -# The stable symlink the PATH launcher resolves through: PATH/dsh -> -# current/bin/dsh -> /bin/dsh. Installs and upgrades repoint `current`; -# the PATH target remains current/bin/dsh. -DSH_CURRENT=${DSH_CURRENT:-$DSH_SOURCE/current} -DSH_BIN_DIR=${DSH_BIN_DIR:-$HOME/.local/bin} -# One UTC basic timestamp names this install's staging branch and worktree. -DSH_STAMP=$(date -u +%Y%m%dT%H%M%SZ) -DSH_STAGING_BRANCH=dsh-staging/$DSH_STAMP -DSH_STAGING=$DSH_SOURCE/staging-$DSH_STAMP - -# --- path helpers --------------------------------------------------------------- -# Every path comparison below runs on physical paths. Git always reports resolved -# paths, so comparing one against an unresolved path disagrees whenever a symlink -# sits anywhere above the checkout — a symlinked home directory is enough, and -# macOS reaches every mktemp path that way through /var -> private/var. The -# mismatch silently misclassifies an existing managed install as a foreign clone -# and builds a second container beside the real one. -# `git rev-parse --path-format=absolute` would do this, but it needs git 2.31+. -# -# A not-yet-created directory (the container on a fresh install) has no physical -# path. Falling back here rather than at each call site keeps every caller a -# plain assignment, so no site can compare against an empty path by forgetting -# its own fallback. -resolve_dir() { CDPATH= cd -- "$1" 2>/dev/null && pwd -P || printf '%s\n' "$1"; } - -# --- in-repo detection --------------------------------------------------------- -# Under `curl ... | sh` the script text arrives on stdin, so $0 is the shell -# name and no file path resolves; running a checked-out copy (`sh -# scripts/install.sh`) makes $0 the script file. When $0 is a readable file whose -# parent is a scripts/ dir inside a real dsh checkout (bin/dsh launcher present), -# this is in-repo mode: never clone, never touch that working tree. An explicit -# DSH_SOURCE pointing elsewhere opts back into the clone/worktree path. -IN_REPO=0 -DSH_CHECKOUT='' -if [ -f "$0" ]; then - _self_dir=$(resolve_dir "$(dirname -- "$0")") - if [ -n "$_self_dir" ]; then - # Physical without its own resolve_dir: dirname is textual, so trimming a - # resolved path leaves one. The comparison below depends on that. - _repo_root=$(dirname -- "$_self_dir") - if [ "$(basename -- "$_self_dir")" = scripts ] \ - && [ -x "$_repo_root/bin/dsh" ] && [ -f "$_repo_root/scripts/install.sh" ]; then - # Compare the explicit DSH_SOURCE physically: an unresolved but equivalent - # path must still count as "the caller meant this checkout". - _src_resolved=$(resolve_dir "$DSH_SOURCE") - if [ "$DSH_SOURCE_EXPLICIT" = 0 ] || [ "$_src_resolved" = "$_repo_root" ]; then - IN_REPO=1 - DSH_CHECKOUT=$_repo_root - fi - fi - fi -fi - -# --- terminal-aware prompting -------------------------------------------------- -# stdin is the piped script, so read the controlling terminal for input. -if { true /dev/null; then - HAS_TTY=1 - # Restore terminal echo on exit or interrupt: ask_secret disables echo between - # its stty toggles, and dash (a common `sh`) does not run an EXIT trap when the - # shell is killed by a signal, so the fatal signals need their own handler. A - # successful run ends in exec, which replaces this process and drops the traps. - trap 'stty echo /dev/null || true' EXIT - trap 'stty echo /dev/null || true; exit 130' INT TERM HUP -else - HAS_TTY=0 -fi - -# Colour only when writing to a terminal. -if [ -t 1 ]; then - B=$(printf '\033[1m'); DIM=$(printf '\033[2m'); RED=$(printf '\033[31m') - GRN=$(printf '\033[32m'); YEL=$(printf '\033[33m'); RST=$(printf '\033[0m') -else - B=''; DIM=''; RED=''; GRN=''; YEL=''; RST='' -fi - -info() { printf '%s==>%s %s\n' "$GRN" "$RST" "$1"; } -step() { printf '\n%s==>%s %s%s%s\n' "$GRN" "$RST" "$B" "$1" "$RST"; } -warn() { printf '%s warn%s %s\n' "$YEL" "$RST" "$1" >&2; } -die() { printf '%serror%s %s\n' "$RED" "$RST" "$1" >&2; exit 1; } - -# ask PROMPT [DEFAULT] -> answer on stdout (plain-text line). -ask() { - [ "$HAS_TTY" = 1 ] || die "no terminal available for input; re-run in an interactive shell" - printf '%s%s%s ' "$B" "$1" "$RST" >/dev/tty - IFS= read -r _ans answer on stdout, with terminal echo suppressed. -ask_secret() { - [ "$HAS_TTY" = 1 ] || die "no terminal available for input; re-run in an interactive shell" - printf '%s%s%s ' "$B" "$1" "$RST" >/dev/tty - stty -echo /dev/null || true - IFS= read -r _sec /dev/null || true - printf '\n' >/dev/tty - printf '%s' "$_sec" -} - -# confirm PROMPT [Y] -> exit 0 on yes. Default is no unless second arg is "Y". -confirm() { - _def=${2:-N} - if [ "$HAS_TTY" != 1 ]; then - [ "$_def" = Y ] # non-interactive: take the default - return - fi - if [ "$_def" = Y ]; then _hint='[Y/n]'; else _hint='[y/N]'; fi - printf '%s%s%s %s ' "$B" "$1" "$RST" "$_hint" >/dev/tty - IFS= read -r _r /dev/null 2>&1 || die "git is required but not found. Install git, then re-run." -info "git ... ok" - -# Node ^22.19.0 || >=24.0.0 (see the root package.json "engines" field). -node_ok() { - command -v node >/dev/null 2>&1 || return 1 - _v=$(node -v 2>/dev/null) || return 1 - _v=${_v#v} - _major=${_v%%.*} - _rest=${_v#*.} - _minor=${_rest%%.*} - case "$_major" in ''|*[!0-9]*) return 1 ;; esac - case "$_minor" in ''|*[!0-9]*) _minor=0 ;; esac - [ "$_major" -ge 24 ] && return 0 - [ "$_major" -eq 22 ] && [ "$_minor" -ge 19 ] && return 0 - return 1 -} -if node_ok; then - info "node $(node -v) ... ok" -else - if command -v node >/dev/null 2>&1; then - die "Node $(node -v) is unsupported. dsh needs ^22.19.0 || >=24.0.0 — upgrade Node, then re-run." - fi - die "Node is required but not found. Install Node ^22.19.0 || >=24, then re-run." -fi - -# pnpm is the only dependency we offer to install for you. -if command -v pnpm >/dev/null 2>&1; then - info "pnpm $(pnpm --version) ... ok" -else - warn "pnpm is not installed." - if confirm "Install pnpm now?" Y; then - if command -v corepack >/dev/null 2>&1 && corepack enable pnpm >/dev/null 2>&1; then - info "enabled pnpm via corepack" - elif command -v npm >/dev/null 2>&1 && npm install -g pnpm >/dev/null 2>&1; then - info "installed pnpm via npm" - else - die "could not install pnpm automatically. Install it (https://pnpm.io/installation), then re-run." - fi - command -v pnpm >/dev/null 2>&1 || die "pnpm still not on PATH after install. Open a new shell, then re-run." - else - die "pnpm is required. Install it (https://pnpm.io/installation), then re-run." - fi -fi - -# --- 2. resolve the repository and lay out the staging worktree --------------- -# The source container owns staging worktrees and `current`; the repository is -# *discovered*, not owned. A curl install discovers it by cloning to $DSH_MASTER; -# in-repo adoption discovers it from the checkout. Both then run one shared -# worktree/exclude/lock path, so an arbitrary clone and a managed install -# converge on the same layout. -# -# REPO_COMMON is the shared git directory every worktree of the repository -# points at; REPO_ROOT is the working tree that owns it (the master clone). -REPO_COMMON='' -REPO_ROOT='' - -if [ "$IN_REPO" = 1 ]; then - step "Using existing checkout at $DSH_CHECKOUT" - info "running from inside the repo — never cloning, and DSH_REF is ignored" - - # Resolve the repository behind the checkout. --git-common-dir returns the - # SHARED git dir, so a linked worktree resolves to the real clone rather than - # itself; it is relative for a plain clone, so anchor it before resolving. - # Require the resolved git dir to exist: resolve_dir echoes its argument back - # for a missing path, so test the directory rather than the returned string. - if _common=$(git -C "$DSH_CHECKOUT" rev-parse --git-common-dir 2>/dev/null) && [ -n "$_common" ]; then - case "$_common" in /*) ;; *) _common=$DSH_CHECKOUT/$_common ;; esac - [ -d "$_common" ] && REPO_COMMON=$(resolve_dir "$_common") - fi - [ -n "$REPO_COMMON" ] || die "$DSH_CHECKOUT is not a git repository — cannot adopt it." - REPO_ROOT=$(dirname -- "$REPO_COMMON") - - # Reuse the container when the repository already lives inside it (the normal - # managed install re-running its own script); otherwise treat that clone as - # its own master and keep worktrees in the default container. - _src_resolved=$(resolve_dir "$DSH_SOURCE") - case "$REPO_ROOT/" in - "$_src_resolved"/*) info "repository $REPO_ROOT is already inside $DSH_SOURCE" ;; - *) info "adopting clone $REPO_ROOT as its own master" ;; - esac - DSH_MASTER=$REPO_ROOT -else - step "Fetching source into $DSH_MASTER" - if [ -d "$DSH_MASTER/.git" ]; then - info "existing master clone found — updating" - git -C "$DSH_MASTER" fetch origin "$DSH_REF" - # Reset the master checkout to the freshly fetched tip. FETCH_HEAD (not - # origin/) so this resolves for a tag as well as a branch, and -B makes - # the re-run idempotent whether or not DSH_REF changed since the last install. - git -C "$DSH_MASTER" checkout -q -B "$DSH_REF" FETCH_HEAD - else - mkdir -p "$DSH_SOURCE" - git clone --branch "$DSH_REF" "$DSH_REPO" "$DSH_MASTER" - fi - # Physical on both branches: REPO_ROOT is compared against resolved paths - # below, and REPO_COMMON stays symmetric with it so neither can be read as - # carrying a different kind of path. - REPO_COMMON=$(resolve_dir "$DSH_MASTER/.git") - REPO_ROOT=$(resolve_dir "$DSH_MASTER") -fi - -step "Adding staging worktree at $DSH_STAGING" -[ -e "$DSH_STAGING" ] && die "staging path $DSH_STAGING already exists — remove it or set DSH_SOURCE elsewhere, then re-run." -mkdir -p "$DSH_SOURCE" -# The staging worktree owns the branch dsh runs from; the repository stays as -# the fetch/upgrade base and is never a launcher target. A clone install -# branches from the ref it just fetched; adoption branches from the checkout's -# HEAD so the contributor's committed work is what runs. -if [ "$IN_REPO" = 1 ]; then - git -C "$DSH_CHECKOUT" worktree add -b "$DSH_STAGING_BRANCH" "$DSH_STAGING" HEAD -else - git -C "$DSH_MASTER" worktree add -b "$DSH_STAGING_BRANCH" "$DSH_STAGING" FETCH_HEAD 2>/dev/null \ - || git -C "$DSH_MASTER" worktree add -b "$DSH_STAGING_BRANCH" "$DSH_STAGING" HEAD -fi -# Exclude the per-worktree merge lock in the shared git dir's info/exclude, -# which every linked worktree inherits. -_exclude="$REPO_COMMON/info/exclude" -if [ -f "$_exclude" ] && ! grep -qxF '.agents/merge.lock' "$_exclude" 2>/dev/null; then - printf '.agents/merge.lock\n' >>"$_exclude" -fi -mkdir -p "$DSH_STAGING/.agents" -: >"$DSH_STAGING/.agents/merge.lock" - -# --- 3. install dependencies (no build; the launcher runs from source) -------- -step "Installing dependencies with pnpm (this can take a while)" -( cd "$DSH_STAGING" && pnpm install ) - -[ -x "$DSH_STAGING/bin/dsh" ] || die "launcher $DSH_STAGING/bin/dsh missing after install — is DSH_REF a branch that ships apps/cli?" - -# --- 4. put `dsh` on PATH ------------------------------------------------------ -# Every install goes through a stable `current` symlink so an upgrade repoints -# one symlink (current -> new worktree) and the PATH launcher never moves: -# PATH/dsh -> current/bin/dsh -> /bin/dsh. -step "Linking dsh into $DSH_BIN_DIR" -mkdir -p "$DSH_BIN_DIR" -# The launcher must resolve to a staging worktree, never to the repository -# itself: an upgrade repoints `current`, so aliasing it onto the master clone -# would make every upgrade rewrite the fetch/upgrade base. Compare physical -# paths — a symlinked or unresolved path would slip past a string compare. -_staging_resolved=$(resolve_dir "$DSH_STAGING") -[ "$_staging_resolved" = "$REPO_ROOT" ] \ - && die "refusing to point $DSH_CURRENT at the repository $REPO_ROOT — the launcher must resolve to a staging worktree." -# Point `current` at this staging worktree with `ln -sfn`: -f replaces an -# existing `current` (re-run or upgrade) and -n stops `ln` from dereferencing -# an existing symlink-to-directory and dropping the new link *inside* the old -# worktree. `mv` is unusable here — BSD/macOS `mv` follows the existing dir -# symlink the same way. The swap is one unlink+symlink pair on a local fs; the -# installer holds no other process racing this path. -ln -sfn "$DSH_STAGING" "$DSH_CURRENT" -info "pointed $DSH_CURRENT -> $DSH_STAGING" -DSH_LAUNCH_TARGET=$DSH_CURRENT/bin/dsh -ln -sf "$DSH_LAUNCH_TARGET" "$DSH_BIN_DIR/dsh" -info "linked $DSH_BIN_DIR/dsh -> $DSH_LAUNCH_TARGET" - -case ":$PATH:" in - *":$DSH_BIN_DIR:"*) ON_PATH=1 ;; - *) ON_PATH=0 ;; -esac -if [ "$ON_PATH" = 0 ]; then - warn "$DSH_BIN_DIR is not on your PATH." - _line="export PATH=\"$DSH_BIN_DIR:\$PATH\"" - _rc='' - _sh=${SHELL:-} # SHELL may be unset; word-removal on an unset var trips set -u under dash. - case "${_sh##*/}" in - zsh) _rc="$HOME/.zshrc" ;; - bash) _rc="$HOME/.bashrc" ;; - esac - if [ -n "$_rc" ] && [ -f "$_rc" ] && grep -qF "$_line" "$_rc" 2>/dev/null; then - info "$_rc already exports $DSH_BIN_DIR — open a new shell to pick it up" - elif [ -n "$_rc" ] && confirm "Add it to $_rc?" Y; then - printf '\n# Added by the dsh installer\n%s\n' "$_line" >>"$_rc" - info "updated $_rc — run 'source $_rc' or open a new shell to pick it up" - else - warn "add this line to your shell profile yourself:" - printf ' %s\n' "$_line" - fi -fi - -# --- 5. credentials ------------------------------------------------------------ -# Mirror app-boot's resolveDshHome precedence ($DSH_HOME, else ~/.dsh) so creds land where dsh reads them. -if [ -n "${DSH_HOME:-}" ]; then - CONF="$DSH_HOME" -else - CONF="$HOME/.dsh" -fi -ENV_FILE="$CONF/.env" - -step "Configuring credentials" -if [ -f "$ENV_FILE" ] && grep -q '^DEEPSEEK_API_KEY=' "$ENV_FILE" 2>/dev/null; then - info "DEEPSEEK_API_KEY already set in $ENV_FILE" - if ! confirm "Replace it?" N; then - SKIP_CREDS=1 - fi -fi -if [ "${SKIP_CREDS:-0}" != 1 ]; then - if [ "$HAS_TTY" = 1 ]; then - API_KEY=$(ask_secret "DeepSeek API key (input hidden):") - if [ -z "$API_KEY" ]; then - warn "no key entered — skipping. Set DEEPSEEK_API_KEY in $ENV_FILE before using dsh." - else - BASE_URL=$(ask "DeepSeek base URL (optional, Enter to skip):") - mkdir -p "$CONF" - # The installer owns exactly the two DEEPSEEK_* lines; any other lines the - # user keeps in this .env are preserved. The rewrite happens in a subshell - # so umask 077 (which closes the create-time permission race) does not leak - # into the exec'd dsh, and lands atomically via a same-dir temp + mv. - _tmp="$ENV_FILE.dsh.$$" - ( - umask 077 - if [ -f "$ENV_FILE" ]; then - grep -v -e '^DEEPSEEK_API_KEY=' -e '^DEEPSEEK_BASE_URL=' "$ENV_FILE" >"$_tmp" || true - else - : >"$_tmp" - fi - printf 'DEEPSEEK_API_KEY=%s\n' "$API_KEY" >>"$_tmp" - if [ -n "$BASE_URL" ]; then printf 'DEEPSEEK_BASE_URL=%s\n' "$BASE_URL" >>"$_tmp"; fi - ) - mv "$_tmp" "$ENV_FILE" - chmod 600 "$ENV_FILE" 2>/dev/null || true - info "wrote $ENV_FILE" - fi - else - warn "no terminal for credential input — set DEEPSEEK_API_KEY in $ENV_FILE before using dsh." - fi -fi - -# --- 6. build and launch the Web interface ------------------------------------- -step "Done" -if [ "$HAS_TTY" = 1 ]; then - step "Building DeepSeek Harness for Web UI" - ( cd "$DSH_STAGING" && pnpm run build ) - info "launching Web UI — run 'dsh web' anytime to start again" - exec "$DSH_BIN_DIR/dsh" web \ncd deepseek-harness\nscripts/install.sh\n```\n\nThe installer requires `git` and Node `^22.19 || >=24`, offers to install `pnpm` when it is missing, prompts for a DeepSeek API key, builds the required repository artifacts, and launches the Web UI.\n\nThe default active checkout is `~/.dsh/source/current`, and the launcher is linked into `~/.local/bin`. Re-run the installer to update. [`scripts/install.sh`](scripts/install.sh) owns alternate locations, update mechanics, and recovery options.\n\n## Use DeepSeek Harness\n\n### Web UI\n\nFor the recommended local interface, choose Web UI when the installer finishes. To start it later, or after updating the active checkout, build the repository and run:\n\n```sh\n(cd ~/.dsh/source/current && pnpm run build)\ndsh web\n```\n\nThe path above is the installer's default. If you set `DSH_SOURCE` or `DSH_CURRENT`, or reused an existing checkout, replace `~/.dsh/source/current` with that checkout path; see [`scripts/install.sh`](scripts/install.sh) for details. The Web UI is served at `http://127.0.0.1:3080` by default.\n\n### Profiles\n\n`dsh` boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/`:\n\n```sh\ndsh --profile web # the browser UI (same as: dsh web)\ndsh plugin --profile tui add # install a plugin into a custom profile\ndsh --profile tui # boot it\n```\n\nThe [CLI reference](apps/cli/README.md#profiles) describes profile layout, layer semantics, and config dump commands.\n\n### Headless\n\nRun one task, print the final answer, and exit:\n\n```sh\ndsh --profile headless \"summarize this workspace\"\n```\n\n### Automation and SDKs\n\nFrom a source checkout with `DEEPSEEK_API_KEY` in the environment or its root `.env`, start the ACP automation server:\n\n```sh\npnpm run demo:acp\n```\n\nThe [Python SDK](python/README.md) drives a bundled JSON-RPC runtime. The [examples](examples/README.md) cover the runnable headless, ACP, JSON-RPC, Code Mode, and self-referential compositions.\n\n## Why DeepSeek Harness\n\nBuilt-in capabilities cover file reading, editing, and search; shell and persistent PTY execution; reusable skills; task tracking, goals, plans, todos, and background tasks; subagents and workflows; sandboxing and approvals; settings and credentials; persistent, resumable, forkable, and queryable sessions; LSP and web access; context compaction; and telemetry. Each composition selects the subset appropriate to its surface. The Web UI includes Plan Mode.\n\n- **Everything is a plugin.** Models, tools, policies, storage, context management, and interfaces are composable [Cordis plugins](docs/user/develop/basic/index.md), so deployments can extend or replace behavior without forking the agent loop. See the [architecture](docs/architecture.md) for the underlying design.\n- **Runs are reconstructable.** Anything visible to the model is logged in the authoritative session stream; persistence, resume/fork/query, replay, telemetry, and UIs derive from the same events. See the [session-log architecture](docs/architecture.md#session-log).\n- **Code Mode (opt-in).** It exposes a `run_code` tool and a generated TypeScript SDK; only program output re-enters model context. See [Code Mode](packages/core/tools/README.md#code-mode).\n- **Self-referential Cordis tools are opt-in.** They let the agent inspect its live runtime and mount or unmount plugins while it runs. See the [Cordis tools](packages/self-modification/tool-cordis/README.md).\n\n## Community\n\nFollow DeepSeek Harness on Twitter for project updates.\n\n## Development\n\nStart with the [development guide](docs/development.md) and read the [architecture](docs/architecture.md) before changing packages.\n\nFor agents, follow [AGENTS.md](AGENTS.md).\n\nDeepSeek Harness is currently in internal testing.\n\n## License\n\n[BSD 3-Clause](LICENSE)\n\nThird-party dependencies and their licenses are disclosed in [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md).\n" + "content": "# DeepSeek Harness\n\nEnglish | [中文](README.zh.md)\n\nDeepSeek Harness (`dsh`) is an open-source coding agent built on the DeepSeek Harness SDK.\n\nIt uses an architecture where **everything is a plugin**.\n\n## Internal testing notice\n\nDeepSeek Harness is under internal testing. Features and interfaces may change.\n\nThe internal build uploads all Session Logs by default to help diagnose reported problems. Set `DSH_TELEMETRY_DISABLED=1` to disable telemetry. Send feedback through the internal WeChat group.\n\n## Run from source\n\nClone this repo, complete the [dependency and API-key setup](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key), then run:\n\n```sh\npnpm dsh web\n```\n\n## Use DeepSeek Harness\n\n### Web UI\n\nStart the recommended local interface from the repository root:\n\n```sh\npnpm dsh web\n```\n\nThe command builds the repository before starting the Web UI, which is served at `http://127.0.0.1:3080` by default.\n\n### Profiles\n\nThe source CLI boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/`:\n\n```sh\npnpm dsh --profile web # the browser UI\npnpm dsh plugin --profile tui add # install a plugin into a custom profile\npnpm dsh --profile tui # boot it\n```\n\nThe [CLI reference](apps/cli/README.md#profiles) describes profile layout, layer semantics, and config dump commands.\n\n### Headless\n\nRun one task, print the final answer, and exit:\n\n```sh\npnpm dsh --profile headless \"summarize this workspace\"\n```\n\n### Automation and SDKs\n\nFrom a source checkout with `DEEPSEEK_API_KEY` in the environment or its root `.env`, start the ACP automation server:\n\n```sh\npnpm run demo:acp\n```\n\nThe [Python SDK](python/README.md) drives a bundled JSON-RPC runtime. The [examples](examples/README.md) cover the runnable headless, ACP, JSON-RPC, Code Mode, and self-referential compositions.\n\n## Why DeepSeek Harness\n\nBuilt-in capabilities cover file reading, editing, and search; shell and persistent PTY execution; reusable skills; task tracking, goals, plans, todos, and background tasks; subagents and workflows; sandboxing and approvals; settings and credentials; persistent, resumable, forkable, and queryable sessions; LSP and web access; context compaction; and telemetry. Each composition selects the subset appropriate to its surface. The Web UI includes Plan Mode.\n\n- **Everything is a plugin.** Models, tools, policies, storage, context management, and interfaces are composable [Cordis plugins](docs/user/develop/basic/index.md), so deployments can extend or replace behavior without forking the agent loop. See the [architecture](docs/architecture.md) for the underlying design.\n- **Runs are reconstructable.** Anything visible to the model is logged in the authoritative session stream; persistence, resume/fork/query, replay, telemetry, and UIs derive from the same events. See the [session-log architecture](docs/architecture.md#session-log).\n- **Code Mode (opt-in).** It exposes a `run_code` tool and a generated TypeScript SDK; only program output re-enters model context. See [Code Mode](packages/core/tools/README.md#code-mode).\n- **Self-referential Cordis tools are opt-in.** They let the agent inspect its live runtime and mount or unmount plugins while it runs. See the [Cordis tools](packages/self-modification/tool-cordis/README.md).\n\n## Community\n\nFollow DeepSeek Harness on Twitter for project updates.\n\n## Development\n\nStart with the [development guide](docs/development.md) and read the [architecture](docs/architecture.md) before changing packages.\n\nFor agents, follow [AGENTS.md](AGENTS.md).\n\nDeepSeek Harness is currently in internal testing.\n\n## License\n\n[BSD 3-Clause](LICENSE)\n\nThird-party dependencies and their licenses are disclosed in [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md).\n" }, { "role": "assistant", - "content": "# DeepSeek Harness\n\n[English](README.md) | 中文\n\nDeepSeek Harness（`dsh`）是一款基于 DeepSeek Harness SDK 构建的开源 coding agent（智能体）。\n\n它采用了**一切皆插件**的架构。\n\n## 内测声明\n\nDeepSeek Harness 正处于内部测试阶段，功能和接口可能发生变化。\n\n为帮助诊断上报的问题，内测版本默认上传所有会话日志。设置 `DSH_TELEMETRY_DISABLED=1` 可关闭遥测。请通过内部企业微信群反馈问题和建议。\n\n## 安装\n\n克隆仓库，然后运行安装器：\n\n```sh\ngit clone \ncd deepseek-harness\nscripts/install.sh\n```\n\n安装器要求系统已安装 `git` 和 Node `^22.19 || >=24`，缺少 `pnpm` 时可代为安装，并会提示输入 DeepSeek API 密钥，然后构建所需的仓库产物并启动 Web UI。\n\n默认生效的检出位于 `~/.dsh/source/current`，启动器链接到 `~/.local/bin`。再次运行安装器即可更新。其他位置、更新机制和恢复选项由 [`scripts/install.sh`](scripts/install.sh) 负责。\n\n## 使用 DeepSeek Harness\n\n### Web UI\n\n推荐在本地使用 Web UI；安装结束时，选择 Web UI 即可。以后需要启动时，或更新当前生效的检出后，请构建仓库并运行：\n\n```sh\n(cd ~/.dsh/source/current && pnpm run build)\ndsh web\n```\n\n上述路径是安装器的默认位置。如果你设置过 `DSH_SOURCE` 或 `DSH_CURRENT`，或者复用了已有检出，请把 `~/.dsh/source/current` 换成该检出路径；详情见 [`scripts/install.sh`](scripts/install.sh)。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。\n\n### Profile\n\n`dsh` 启动 profile：按序叠放的插件组合包 patch 层，之上再叠加你在 `$DSH_HOME/profiles/` 中的自有覆盖层：\n\n```sh\ndsh --profile web # the browser UI (same as: dsh web)\ndsh plugin --profile tui add # install a plugin into a custom profile\ndsh --profile tui # boot it\n```\n\nprofile 布局、层语义与配置输出命令详见 [CLI（命令行界面）参考](apps/cli/README.md#profiles)。\n\n### Headless\n\n运行一项任务，打印最终答案后退出：\n\n```sh\ndsh --profile headless \"summarize this workspace\"\n```\n\n### 自动化与 SDK\n\n在源码检出中通过环境变量或根目录 `.env` 设置 `DEEPSEEK_API_KEY`，然后启动 ACP（Agent Client Protocol）自动化服务器：\n\n```sh\npnpm run demo:acp\n```\n\n[Python SDK](python/README.md) 驱动随附的 JSON-RPC 运行时。[示例](examples/README.md)涵盖可运行的 headless、ACP、JSON-RPC、Code Mode 和自指组合。\n\n## 为什么选择 DeepSeek Harness\n\n内置功能涵盖文件读取、编辑与搜索、shell 和持久 PTY 执行、可复用 skill（技能）、任务跟踪、目标、计划、待办事项与后台任务、subagent 与工作流、沙箱与审批、设置与凭据、可持久化、恢复、fork 与查询的会话、LSP 与 Web 访问、上下文压缩（context compaction），以及遥测。每个组合只选用适合其使用方式的能力子集。Web UI 包含 Plan Mode。\n\n- **一切皆插件。** 模型、工具、策略、存储、上下文管理和界面均为可组合的 [Cordis 插件](docs/user/develop/basic/index.md)，部署方无需 fork agent loop（智能体循环）即可扩展或替换行为。底层设计见[架构文档](docs/architecture.md)。\n- **运行可重建。** 凡是模型可见的内容，都会记录在权威会话流中；持久化、恢复／fork／查询、回放、遥测和 UI 均从同一组事件派生。参见[会话日志架构](docs/architecture.md#session-log)。\n- **Code Mode（需显式启用）。** 它会提供 `run_code` 工具和生成的 TypeScript SDK，只有程序输出会重新进入模型上下文。参见 [Code Mode](packages/core/tools/README.md#code-mode)。\n- **自指 Cordis 工具需显式启用。** 这些工具可让 agent 检查自身的实时运行时，并在运行中挂载或卸载插件。参见 [Cordis 工具](packages/self-modification/tool-cordis/README.md)。\n\n## 社区\n\n扫描二维码，或打开 DeepSeek Harness 微信社区申请页面 申请加入。\n\n

\n \"DeepSeek\n

\n\n## 开发\n\n请先阅读[开发指南](docs/development.md)；修改包之前，请阅读[架构文档](docs/architecture.md)。\n\n面向 agent：遵循 [AGENTS.md](AGENTS.md)。\n\nDeepSeek Harness 目前处于内测阶段。\n\n## 许可证\n\n[BSD 3-Clause](LICENSE)\n\n第三方依赖及其许可证在 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) 中披露。\n" + "content": "# DeepSeek Harness\n\n[English](README.md) | 中文\n\nDeepSeek Harness（`dsh`）是一款基于 DeepSeek Harness SDK 构建的开源 coding agent（智能体）。\n\n它采用了**一切皆插件**的架构。\n\n## 内测声明\n\nDeepSeek Harness 正处于内部测试阶段，功能和接口可能发生变化。\n\n为帮助诊断上报的问题，内测版本默认上传所有会话日志。设置 `DSH_TELEMETRY_DISABLED=1` 可关闭遥测。请通过内部企业微信群反馈问题和建议。\n\n## 从源码运行\n\n克隆本仓库，完成[依赖安装和 API 密钥配置](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key)，然后运行：\n\n```sh\npnpm dsh web\n```\n\n## 使用 DeepSeek Harness\n\n### Web UI\n\n请从仓库根目录启动推荐的本地界面：\n\n```sh\npnpm dsh web\n```\n\n该命令会先构建仓库，再启动 Web UI。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。\n\n### Profile\n\n源码 CLI（命令行界面）会启动 profile：按序叠放的插件组合包 patch 层，之上再叠加你在 `$DSH_HOME/profiles/` 中的自有覆盖层：\n\n```sh\npnpm dsh --profile web # the browser UI\npnpm dsh plugin --profile tui add # install a plugin into a custom profile\npnpm dsh --profile tui # boot it\n```\n\nprofile 布局、层语义与配置输出命令详见 [CLI（命令行界面）参考](apps/cli/README.md#profiles)。\n\n### Headless\n\n运行一项任务，打印最终答案后退出：\n\n```sh\npnpm dsh --profile headless \"summarize this workspace\"\n```\n\n### 自动化与 SDK\n\n在源码检出中通过环境变量或根目录 `.env` 设置 `DEEPSEEK_API_KEY`，然后启动 ACP（Agent Client Protocol）自动化服务器：\n\n```sh\npnpm run demo:acp\n```\n\n[Python SDK](python/README.md) 驱动随附的 JSON-RPC 运行时。[示例](examples/README.md)涵盖可运行的 headless、ACP、JSON-RPC、Code Mode 和自指组合。\n\n## 为什么选择 DeepSeek Harness\n\n内置功能涵盖文件读取、编辑与搜索、shell 和持久 PTY 执行、可复用 skill（技能）、任务跟踪、目标、计划、待办事项与后台任务、subagent 与工作流、沙箱与审批、设置与凭据、可持久化、恢复、fork 与查询的会话、LSP 与 Web 访问、上下文压缩（context compaction），以及遥测。每个组合只选用适合其使用方式的能力子集。Web UI 包含 Plan Mode。\n\n- **一切皆插件。** 模型、工具、策略、存储、上下文管理和界面均为可组合的 [Cordis 插件](docs/user/develop/basic/index.md)，部署方无需 fork agent loop（智能体循环）即可扩展或替换行为。底层设计见[架构文档](docs/architecture.md)。\n- **运行可重建。** 凡是模型可见的内容，都会记录在权威会话流中；持久化、恢复／fork／查询、回放、遥测和 UI 均从同一组事件派生。参见[会话日志架构](docs/architecture.md#session-log)。\n- **Code Mode（需显式启用）。** 它会提供 `run_code` 工具和生成的 TypeScript SDK，只有程序输出会重新进入模型上下文。参见 [Code Mode](packages/core/tools/README.md#code-mode)。\n- **自指 Cordis 工具需显式启用。** 这些工具可让 agent 检查自身的实时运行时，并在运行中挂载或卸载插件。参见 [Cordis 工具](packages/self-modification/tool-cordis/README.md)。\n\n## 社区\n\n扫描二维码，或打开 DeepSeek Harness 微信社区申请页面 申请加入。\n\n

\n \"DeepSeek\n

\n\n## 开发\n\n请先阅读[开发指南](docs/development.md)；修改包之前，请阅读[架构文档](docs/architecture.md)。\n\n面向 agent：遵循 [AGENTS.md](AGENTS.md)。\n\nDeepSeek Harness 目前处于内测阶段。\n\n## 许可证\n\n[BSD 3-Clause](LICENSE)\n\n第三方依赖及其许可证在 [THIRD_PARTY_NOTICES.md](THIRD_PARTY_NOTICES.md) 中披露。\n" }, { "role": "user", - "content": "# Development guide\n\nEnglish | [中文](development.zh.md)\n\nThe setup tutorial takes a new contributor from prerequisites to a checked checkout. The contributor reference that follows covers repository layout, daily workflow, and CI organization. Design rationale and implementation details belong to the linked Agent Notes and scripts.\n\n## Setup tutorial\n\n### Prerequisites\n\n- Node.js supports 22.19+ and 24+. CI covers 22.19, 24, and 26; see the [Node engine floor Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md).\n- Corepack-enabled pnpm. The repo pins `pnpm@11.7.0` in `package.json`; run `corepack enable` if `pnpm --version` does not resolve through Corepack.\n- Git 2.26 or newer; hook setup enables Git's worktree-specific configuration extension.\n- Optional: a DeepSeek API key for the Web, headless, and ACP automation demos and real-API e2e tests.\n\n### First-time setup\n\nInstall dependencies from the repo root:\n\n```sh\npnpm install\n```\n\nThe install also configures worktree-local Lefthook hooks and the `dsh-translation-pairing` Git merge driver through `scripts/install-lefthook.mjs`. The [worktree-local hooks Agent Note](../.agents/notes/implemented/process/2026-07-27-worktree-local-lefthook.md) owns the hook-path safety contract; the [automatic pairing merges Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) owns the merge driver.\n\nIf either integration is missing because dependencies were restored from cache or `postinstall` was skipped, install them manually:\n\n```sh\nnode scripts/install-lefthook.mjs\n```\n\nIf the wrapper rejects existing Git configuration or reports a stale lock, follow its diagnostic and the linked Agent Note rather than editing worktree metadata speculatively. After moving a checkout, rerun the wrapper to regenerate the owned path.\n\nRun typecheck once after a fresh clone:\n\n```sh\npnpm run typecheck\n```\n\nSetup is complete when `pnpm run typecheck` exits successfully.\n\n## Contributor reference\n\n### TypeScript project layout\n\nThe repository uses isolated Host and Client aggregates. An ordinary package is registered in exactly one aggregate: Host packages in `tsconfig.host.json` and Client packages in `tsconfig.client.json`.\n\n| File | Role | Forms a program? |\n|---|---|---|\n| `tsconfig.json` | Solution root: `extends` base, `files: []`, and references to the two aggregates. It is the tsserver discovery entry and the entry for explicitly running the complete Project Reference graph; through the inherited `paths`, it is also the resolution config for tsx running `examples/` and `scripts/`. | No |\n| `tsconfig.host.json` | Host aggregate: Host packages, examples, tests, scripts, website, and the exceptional Host project of `api/remotes`. | Yes |\n| `tsconfig.client.json` | Client aggregate: `packages/client/*` packages and their tests, `apps/web`, and the exceptional Client project of `api/remotes`. | Yes |\n| `tsconfig.base.json` | Shared compilerOptions and the source `paths` map. Also the resolution facade the vitest configs point vite-tsconfig-paths at: it has no `include`, so its `paths` apply to every importer. | No |\n| `tsconfig.base.client.json` | Browser compiler settings (`jsx`, DOM libs, `types: []`) extended by the Client aggregate and every `packages/client/*` package. | No |\n\nHost and Client stay two aggregate programs because both sides declaration-merge the cordis `Context` interface under the same keys with different services; one program seeing both merges reports a collision. The collision exists only inside a `ts.Program` — module resolution never triggers it — which is why the solution may reference both aggregates and one paths facade may span both sides. Three disciplines follow:\n\n- `tsconfig.base.json` never gains `include` or `files`: they would leak into every extending package project and narrow the facade's match-all scope.\n- A script that builds a repo-wide `ts.Program` seeds `tsconfig.host.json` or `tsconfig.client.json` explicitly — never the root solution, because flattening both aggregates into one program collides the `Context` merges.\n- A new package is registered in exactly one aggregate. Having both a Node loader entry and a browser entry is not a reason to split a package; an ordinary Client plugin produces both runtime artifacts during the Client build phase.\n\n`api/remotes` is the repository's only package with split Host and Client tsconfigs. Its Host entry must participate in the Host TypeRT graph, while its Client entry imports `/remote` declarations that Host tsdown must generate first. The package-root `tsconfig.json` is therefore only a solution, and the two aggregates and direct consumers reference `tsconfig.host.json` or `tsconfig.client.json` respectively. The workspace `constraints` gate walks the reachable Project Reference graph and checks each referencing project's own compiler face: a single-config target remains valid from either face, while a split target must name the matching leaf rather than its solution root or opposite leaf. Do not copy this structure to other packages; the [`api-remotes` README](../packages/api/remotes/README.md) explains the Host/Client split and build order.\n\nThe root build follows the generated dependency order:\n\n```sh\ntsc -b tsconfig.host.json\ntsdown --env.DSH_BUILD_FACE host\ntsc -b tsconfig.client.json\ntsdown --env.DSH_BUILD_FACE client\npnpm run build:web\n```\n\nBoth tsdown passes use the same complete workspace match. They neither scan build artifacts to discover Client packages nor maintain a Host/Client package filter list. Package-local tsdown configs select entries for the current phase through `DSH_BUILD_FACE`: an ordinary Client plugin produces both its Node loader and browser bundle during the Client phase; `api-remotes` uses `hostPhase: true` to produce its Host entry early and only its browser bundle during the Client phase. Tsdown consumes only the JavaScript emitted to `lib/types` by the preceding tsc phase.\n\nTypeRT runs only during Host tsdown, seeded by `tsconfig.host.json`. It analyzes Host types and generates both Host reflection artifacts and the Host-for-Client Remote projection; Client tsdown does not start TypeRT. Consequently, `pnpm run typecheck` runs the complete Host lib phase before Client tsc, while `pnpm run build` continues through Client tsdown and the Web build. The [API Remotes generated-contract build note](../.agents/notes/implemented/process/2026-08-08-api-remotes-generated-contract-build.md) records this ordering decision.\n\nStatic analysis and tests resolve workspace imports through the base `paths` map to `src` and must pass on a clean tree; gates that consume built `lib/` output declare that dependency explicitly. Generated Host-for-Client Remote declarations are the deliberate exception: the public `typecheck`, `lint`, and `doc-typecheck` commands generate them first, while internal `*:contracts-ready` scripts assume that an invoking public command or scheduler gate already depends on the TypeRT contract-generation pass or the complete build. See the [solution-root note](../.agents/notes/implemented/process/2026-07-22-tsconfig-solution-root-two-aggregates.md) for the two-aggregate setup, the [ts-build-config note](../.agents/notes/implemented/process/2026-06-17-ts-build-config.md) for tsc-first emit ownership, and the [TypeRT Remote note](../.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md) for the gate-preparation contract.\n\nBusiness services declare callable methods on the Host with `@Remote` or `@RemoteScope`; the Host build generates Host-for-Client types and runtime contributions, and the Client's `api-remotes` composition loads those contributions under `ctx.remote` and scoped `agentCtx.remote` namespaces. See [API Gateway](api-gateway.md) for the generated artifacts on both sides, their assembly relationships, the SRC development fallback, and the Web build order.\n\nIf a relevant local check consumes built package output, build once first:\n\n```sh\npnpm run build\n```\n\n`pnpm run hygiene` includes `publint`, which validates package entrypoints against the built `lib/*.js` files, and `verify-node-next-types`, which validates built declarations against a temporary NodeNext consumer. A fresh worktree has no bundled JS or declarations until `pnpm run build` runs; ordinary commits and pushes do not require that build unless their selected checks consume it.\n\n### Environment variables\n\nThe real DeepSeek adapter and key-backed agent demos read credentials from the environment or from a gitignored `.env` at the repo root:\n\n```sh\nDEEPSEEK_API_KEY=sk-...\nDEEPSEEK_BASE_URL=https://... # optional\n```\n\n`DEEPSEEK_BASE_URL` is optional and defaults to the public API. Never commit real credentials. The real-API e2e suites self-skip when `DEEPSEEK_API_KEY` is not set.\n\n### Git integrations\n\nThe pairing merge driver derives a conflicted `.i18n.yaml` record from the confirmed ancestor, current, and other owner blobs when both language files use Git's default text strategy and merge cleanly. It fails closed on owner conflicts, non-text merge configuration, or invalid records; after an already-stopped merge, run `pnpm run resolve-translation-pairing-conflicts`, which stages every safe pairing record and exits unsuccessfully if other pairing conflicts still need manual work. See the [bilingual documentation contract](i18n/README.md#the-pairing-contract) for the exact files and states the driver accepts.\n\nThe installer probes the exact Node/tsx driver entrypoint before publishing its worktree configuration. If that runtime later becomes unavailable, the Node-independent launcher writes Git's ordinary text result, leaves the sidecar unresolved, and prints the recovery path; restore dependencies and run `pnpm run resolve-translation-pairing-conflicts`, or run `git merge --abort`. If `pre-merge-commit` rejects an otherwise clean merge, Git leaves the complete result staged without a commit; repair the failure and run `git commit`, or abort. The [automatic pairing merges Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md#failure-contract) owns the exact index and `MERGE_HEAD` states.\n\nlefthook is configured in `lefthook.yml` as a fast local checkpoint:\n\n- `pre-commit` verifies staged pairing records against the staged owner blobs, validates staged files with the project-free `.oxlintrc.staged.json` profile and applies Oxlint fixes with one bounded retry, regenerates `THIRD_PARTY_NOTICES.md` when a staged file is one of its inputs, checks the staged diff for whitespace errors, and runs the vendor manifest guard.\n- `pre-merge-commit` performs the same index-backed pairing check before Git creates an automatic merge commit.\n- `pre-push` runs `pnpm run typecheck`, which completes the Host lib phase, including generated TypeRT contracts, before the Client TypeScript check.\n\nThe vendor manifest guard checks that changes under `vendor/*/src` are staged with the matching `vendor/README.md` manifest update. See `vendor/README.md` before editing vendored code.\n\nApart from the scoped staged-record verification, the hooks intentionally do not run tests, snapshots, documentation checks, builds, or hygiene. Contributors run the [checks relevant to the changed behavior](../AGENTS.md#run-relevant-checks-locally) once; CI owns exhaustive coverage, built-artifact smokes, and the Node 22.19, 24, and 26 compatibility matrix.\n\nContributors can opt into the comprehensive local gate set with `pnpm run check:all`. The command is independent of the Git hooks and is not an agent instruction.\n\n### CI gates\n\nThe keyless [CI workflow](../.github/workflows/ci.yml) groups independent gates into broad lanes and runs a smaller compatibility signal across supported Node versions. Artifact consumers wait for one build within their lane. The separate real-API workflow runs `pnpm run test:e2e` with its configured worker bound. See [scripts/run-gates.ts](../scripts/run-gates.ts) and the workflow files for the current gate and job inventory.\n\n### Daily commands\n\nThe root [contributor instructions](../AGENTS.md#commands) summarize common commands, while [`package.json`](../package.json) and [scripts/run-gates.ts](../scripts/run-gates.ts) own the current script and gate inventories. Select the smallest checks that cover the changed surface. Documentation changes use `pnpm run doc-sync`; package-public behavior changes also update the owning README or JSDoc, and built-artifact checks require `pnpm run build` first.\n\n### Demos\n\nThe one-shot Headless coding agent needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`:\n\n```sh\npnpm run demo:headless \"summarize this workspace\"\n```\n\nThe self-referential cordis demo can inspect and modify its live plugin runtime and needs the same credentials (`web` by default, or `acp`):\n\n```sh\npnpm run demo:cordis\n```\n\nThe ACP automation server exposes fresh agent sessions over JSON-RPC stdio and also needs `DEEPSEEK_API_KEY`:\n\n```sh\npnpm run demo:acp\n```\n\n### TODO markers\n\nUse one of three comment tags to flag known issues in the code, ordered by urgency:\n\n- `FIXME` — an issue that should block a new release. A release should not ship with an open `FIXME` unless reviewers explicitly agree the change can be merged anyway.\n- `TODO` — an issue that should be fixed soon, once we have the resources.\n- `XXX` — an issue that we may fix someday; lowest priority, no commitment.\n\nPick the tag that matches the urgency so anyone scanning the code can tell a release blocker from a someday-maybe.\n\n### Documenting types verbatim (`ts type-equiv`)\n\nThe [subsystems](subsystems/README.md) pages paste source-equivalent declarations together with their original JSDoc so a reader sees the exact type definition and source contract. To keep a paste from drifting when source changes, fence it as ` ```ts type-equiv ` (instead of ` ```ts `) and register it in `scripts/type-equiv.manifest.json` with the source file and symbol it mirrors:\n\n```json\n{ \"doc\": \"docs/subsystems/session.md\", \"symbol\": \"SessionEvent\", \"source\": \"packages/core/session/src/types.ts\" }\n```\n\n`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration and attached JSDoc from source via the TypeScript parser and asserts the block matches both. For a class whose implementation bodies do not belong in the catalog, use ` ```ts public-api ` and set `\"projection\": \"public-api\"`; the checked projection retains the public fields, constructor, accessors, methods, and original class/member JSDoc while omitting bodies and private or protected members. Comparison ignores whitespace and non-JSDoc comments but requires every original JSDoc comment, including member documentation, so readers see the source contract beside the exact type definition. The gate enforces a 1:1 correspondence by document, symbol, and projection between primary blocks and manifest entries; a paired `.zh.md` block reuses its unsuffixed sibling's entry only when the whole tracked fence sequence is byte-identical and ordered identically. `doc-typecheck` applies the same derivative rule to compilable fences, while skipping both source-equivalence fence kinds from compilation and its opt-out ratio. When you change a documented declaration or its JSDoc, the gate fails until you update the paste; when you add or remove a primary block, update the manifest in the same change.\n" + "content": "# Development guide\n\nEnglish | [中文](development.zh.md)\n\nThe setup tutorial takes a new contributor from prerequisites to a checked checkout. The contributor reference that follows covers repository layout, daily workflow, and CI organization. Design rationale and implementation details belong to the linked Agent Notes and scripts.\n\n## Setup tutorial\n\n### Prerequisites\n\n- Node.js supports 22.19+ and 24+. CI covers 22.19, 24, and 26; see the [Node engine floor Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md).\n- Corepack-enabled pnpm. The repo pins `pnpm@11.7.0` in `package.json`; run `corepack enable` if `pnpm --version` does not resolve through Corepack.\n- Git 2.26 or newer; hook setup enables Git's worktree-specific configuration extension.\n- Optional: a DeepSeek API key for the Web, headless, and ACP automation demos and real-API e2e tests.\n\n### First-time setup\n\nInstall dependencies from the repo root:\n\n```sh\npnpm install\n```\n\nThe install also configures worktree-local Lefthook hooks and the `dsh-translation-pairing` Git merge driver through `scripts/install-lefthook.mjs`. The [worktree-local hooks Agent Note](../.agents/notes/implemented/process/2026-07-27-worktree-local-lefthook.md) owns the hook-path safety contract; the [automatic pairing merges Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) owns the merge driver.\n\nIf either integration is missing because dependencies were restored from cache or `postinstall` was skipped, install them manually:\n\n```sh\nnode scripts/install-lefthook.mjs\n```\n\nIf the wrapper rejects existing Git configuration or reports a stale lock, follow its diagnostic and the linked Agent Note rather than editing worktree metadata speculatively. After moving a checkout, rerun the wrapper to regenerate the owned path.\n\nRun typecheck once after a fresh clone:\n\n```sh\npnpm run typecheck\n```\n\nSetup is complete when `pnpm run typecheck` exits successfully.\n\n## Contributor reference\n\n### TypeScript project layout\n\nThe repository uses isolated Host and Client aggregates. An ordinary package is registered in exactly one aggregate: Host packages in `tsconfig.host.json` and Client packages in `tsconfig.client.json`.\n\n| File | Role | Forms a program? |\n|---|---|---|\n| `tsconfig.json` | Solution root: `extends` base, `files: []`, and references to the two aggregates. It is the tsserver discovery entry and the entry for explicitly running the complete Project Reference graph; through the inherited `paths`, it is also the resolution config for tsx running `examples/` and `scripts/`. | No |\n| `tsconfig.host.json` | Host aggregate: Host packages, examples, tests, scripts, website, and the exceptional Host project of `api/remotes`. | Yes |\n| `tsconfig.client.json` | Client aggregate: `packages/client/*` packages and their tests, `apps/web`, and the exceptional Client project of `api/remotes`. | Yes |\n| `tsconfig.base.json` | Shared compilerOptions and the source `paths` map. Also the resolution facade the vitest configs point vite-tsconfig-paths at: it has no `include`, so its `paths` apply to every importer. | No |\n| `tsconfig.base.client.json` | Browser compiler settings (`jsx`, DOM libs, `types: []`) extended by the Client aggregate and every `packages/client/*` package. | No |\n\nHost and Client stay two aggregate programs because both sides declaration-merge the cordis `Context` interface under the same keys with different services; one program seeing both merges reports a collision. The collision exists only inside a `ts.Program` — module resolution never triggers it — which is why the solution may reference both aggregates and one paths facade may span both sides. Three disciplines follow:\n\n- `tsconfig.base.json` never gains `include` or `files`: they would leak into every extending package project and narrow the facade's match-all scope.\n- A script that builds a repo-wide `ts.Program` seeds `tsconfig.host.json` or `tsconfig.client.json` explicitly — never the root solution, because flattening both aggregates into one program collides the `Context` merges.\n- A new package is registered in exactly one aggregate. Having both a Node loader entry and a browser entry is not a reason to split a package; an ordinary Client plugin produces both runtime artifacts during the Client build phase.\n\n`api/remotes` is the repository's only package with split Host and Client tsconfigs. Its Host entry must participate in the Host TypeRT graph, while its Client entry imports `/remote` declarations that Host tsdown must generate first. The package-root `tsconfig.json` is therefore only a solution, and the two aggregates and direct consumers reference `tsconfig.host.json` or `tsconfig.client.json` respectively. The workspace `constraints` gate walks the reachable Project Reference graph and checks each referencing project's own compiler face: a single-config target remains valid from either face, while a split target must name the matching leaf rather than its solution root or opposite leaf. Do not copy this structure to other packages; the [`api-remotes` README](../packages/api/remotes/README.md) explains the Host/Client split and build order.\n\nThe root build follows the generated dependency order:\n\n```sh\ntsc -b tsconfig.host.json\ntsdown --env.DSH_BUILD_FACE host\ntsc -b tsconfig.client.json\ntsdown --env.DSH_BUILD_FACE client\npnpm run build:web\n```\n\nBoth tsdown passes use the same complete workspace match. They neither scan build artifacts to discover Client packages nor maintain a Host/Client package filter list. Package-local tsdown configs select entries for the current phase through `DSH_BUILD_FACE`: an ordinary Client plugin produces both its Node loader and browser bundle during the Client phase; `api-remotes` uses `hostPhase: true` to produce its Host entry early and only its browser bundle during the Client phase. Tsdown consumes only the JavaScript emitted to `lib/types` by the preceding tsc phase.\n\nTypeRT runs only during Host tsdown, seeded by `tsconfig.host.json`. It analyzes Host types and generates both Host reflection artifacts and the Host-for-Client Remote projection; Client tsdown does not start TypeRT. Consequently, `pnpm run typecheck` runs the complete Host lib phase before Client tsc, while `pnpm run build` continues through Client tsdown and the Web build. The [API Remotes generated-contract build note](../.agents/notes/implemented/process/2026-08-08-api-remotes-generated-contract-build.md) records this ordering decision.\n\nStatic analysis and tests resolve workspace imports through the base `paths` map to `src` and must pass on a clean tree; gates that consume built `lib/` output declare that dependency explicitly. Generated Host-for-Client Remote declarations are the deliberate exception: the public `typecheck`, `lint`, and `doc-typecheck` commands generate them first, while internal `*:contracts-ready` scripts assume that an invoking public command or scheduler gate already depends on the TypeRT contract-generation pass or the complete build. See the [solution-root note](../.agents/notes/implemented/process/2026-07-22-tsconfig-solution-root-two-aggregates.md) for the two-aggregate setup, the [ts-build-config note](../.agents/notes/implemented/process/2026-06-17-ts-build-config.md) for tsc-first emit ownership, and the [TypeRT Remote note](../.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md) for the gate-preparation contract.\n\nBusiness services declare callable methods on the Host with `@Remote` or `@RemoteScope`; the Host build generates Host-for-Client types and runtime contributions, and the Client's `api-remotes` composition loads those contributions under `ctx.remote` and scoped `agentCtx.remote` namespaces. See [API Gateway](api-gateway.md) for the generated artifacts on both sides, their assembly relationships, the SRC development fallback, and the Web build order.\n\nIf a relevant local check consumes built package output, build once first:\n\n```sh\npnpm run build\n```\n\n`pnpm run hygiene` includes `publint`, which validates package entrypoints against the built `lib/*.js` files, and `verify-node-next-types`, which validates built declarations against a temporary NodeNext consumer. A fresh worktree has no bundled JS or declarations until `pnpm run build` runs; ordinary commits and pushes do not require that build unless their selected checks consume it.\n\n### Environment variables\n\nThe real DeepSeek adapter and key-backed agent demos read credentials from the environment or from a gitignored `.env` at the repo root:\n\n```sh\nDEEPSEEK_API_KEY=sk-...\nDEEPSEEK_BASE_URL=https://... # optional\n```\n\n`DEEPSEEK_BASE_URL` is optional and defaults to the public API. Never commit real credentials. The real-API e2e suites self-skip when `DEEPSEEK_API_KEY` is not set.\n\n### Git integrations\n\nThe pairing merge driver derives a conflicted `.i18n.yaml` record from the confirmed ancestor, current, and other owner blobs when both language files use Git's default text strategy and merge cleanly. It fails closed on owner conflicts, non-text merge configuration, or invalid records; after an already-stopped merge, run `pnpm run resolve-translation-pairing-conflicts`, which stages every safe pairing record and exits unsuccessfully if other pairing conflicts still need manual work. See the [bilingual documentation contract](i18n/README.md#the-pairing-contract) for the exact files and states the driver accepts.\n\nThe installer probes the exact Node/tsx driver entrypoint before publishing its worktree configuration. If that runtime later becomes unavailable, the Node-independent launcher writes Git's ordinary text result, leaves the sidecar unresolved, and prints the recovery path; restore dependencies and run `pnpm run resolve-translation-pairing-conflicts`, or run `git merge --abort`. If `pre-merge-commit` rejects an otherwise clean merge, Git leaves the complete result staged without a commit; repair the failure and run `git commit`, or abort. The [automatic pairing merges Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md#failure-contract) owns the exact index and `MERGE_HEAD` states.\n\nlefthook is configured in `lefthook.yml` as a fast local checkpoint:\n\n- `pre-commit` verifies staged pairing records against the staged owner blobs, validates staged files with the project-free `.oxlintrc.staged.json` profile and applies Oxlint fixes with one bounded retry, regenerates `THIRD_PARTY_NOTICES.md` when a staged file is one of its inputs, checks the staged diff for whitespace errors, and runs the vendor manifest guard.\n- `pre-merge-commit` performs the same index-backed pairing check before Git creates an automatic merge commit.\n- `pre-push` runs `pnpm run typecheck`, which completes the Host lib phase, including generated TypeRT contracts, before the Client TypeScript check.\n\nThe vendor manifest guard checks that changes under `vendor/*/src` are staged with the matching `vendor/README.md` manifest update. See `vendor/README.md` before editing vendored code.\n\nApart from the scoped staged-record verification, the hooks intentionally do not run tests, snapshots, documentation checks, builds, or hygiene. Contributors run the [checks relevant to the changed behavior](../AGENTS.md#run-relevant-checks-locally) once; CI owns exhaustive coverage, built-artifact smokes, and the Node 22.19, 24, and 26 compatibility matrix.\n\nContributors can opt into the comprehensive local gate set with `pnpm run check:all`. The command is independent of the Git hooks and is not an agent instruction.\n\n### CI gates\n\nThe keyless [CI workflow](../.github/workflows/ci.yml) groups independent gates into broad lanes and runs a smaller compatibility signal across supported Node versions. Artifact consumers wait for one build within their lane. The separate real-API workflow runs `pnpm run test:e2e` with its configured worker bound. See [scripts/run-gates.ts](../scripts/run-gates.ts) and the workflow files for the current gate and job inventory.\n\n### Daily commands\n\nThe root [contributor instructions](../AGENTS.md#commands) summarize common commands, while [`package.json`](../package.json) and [scripts/run-gates.ts](../scripts/run-gates.ts) own the current script and gate inventories. Select the smallest checks that cover the changed surface. Documentation changes use `pnpm run doc-sync`; package-public behavior changes also update the owning README or JSDoc, and built-artifact checks require `pnpm run build` first.\n\n### Demos\n\nThe one-shot Headless coding agent needs `DEEPSEEK_API_KEY` in the environment or repo-root `.env`:\n\n```sh\npnpm dsh --profile headless \"summarize this workspace\"\n```\n\nThe self-referential cordis demo can inspect and modify its live plugin runtime and needs the same credentials (`web` by default, or `acp`):\n\n```sh\npnpm run demo:cordis\n```\n\nThe ACP automation server exposes fresh agent sessions over JSON-RPC stdio and also needs `DEEPSEEK_API_KEY`:\n\n```sh\npnpm run demo:acp\n```\n\n### TODO markers\n\nUse one of three comment tags to flag known issues in the code, ordered by urgency:\n\n- `FIXME` — an issue that should block a new release. A release should not ship with an open `FIXME` unless reviewers explicitly agree the change can be merged anyway.\n- `TODO` — an issue that should be fixed soon, once we have the resources.\n- `XXX` — an issue that we may fix someday; lowest priority, no commitment.\n\nPick the tag that matches the urgency so anyone scanning the code can tell a release blocker from a someday-maybe.\n\n### Documenting types verbatim (`ts type-equiv`)\n\nThe [subsystems](subsystems/README.md) pages paste source-equivalent declarations together with their original JSDoc so a reader sees the exact type definition and source contract. To keep a paste from drifting when source changes, fence it as ` ```ts type-equiv ` (instead of ` ```ts `) and register it in `scripts/type-equiv.manifest.json` with the source file and symbol it mirrors:\n\n```json\n{ \"doc\": \"docs/subsystems/session.md\", \"symbol\": \"SessionEvent\", \"source\": \"packages/core/session/src/types.ts\" }\n```\n\n`pnpm run verify-type-equiv` (part of `doc-sync`) then extracts that symbol's declaration and attached JSDoc from source via the TypeScript parser and asserts the block matches both. For a class whose implementation bodies do not belong in the catalog, use ` ```ts public-api ` and set `\"projection\": \"public-api\"`; the checked projection retains the public fields, constructor, accessors, methods, and original class/member JSDoc while omitting bodies and private or protected members. Comparison ignores whitespace and non-JSDoc comments but requires every original JSDoc comment, including member documentation, so readers see the source contract beside the exact type definition. The gate enforces a 1:1 correspondence by document, symbol, and projection between primary blocks and manifest entries; a paired `.zh.md` block reuses its unsuffixed sibling's entry only when the whole tracked fence sequence is byte-identical and ordered identically. `doc-typecheck` applies the same derivative rule to compilable fences, while skipping both source-equivalence fence kinds from compilation and its opt-out ratio. When you change a documented declaration or its JSDoc, the gate fails until you update the paste; when you add or remove a primary block, update the manifest in the same change.\n" }, { "role": "assistant", - "content": "# 开发指南\n\n[English](development.md) | 中文\n\n搭建教程引导新贡献者从准备前置条件开始，直到检出通过检查。后面的贡献者参考介绍仓库布局、日常工作流和 CI 组织方式。设计依据与实现细节属于链接的 Agent Note 和脚本。\n\n## 搭建教程\n\n### 前置条件\n\n- Node.js 支持 22.19+ 与 24+。CI 覆盖 22.19、24 和 26；见 [Node 引擎下限 Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md)。\n- 启用了 Corepack 的 pnpm。仓库在 `package.json` 中固定使用 `pnpm@11.7.0`；如果 `pnpm --version` 无法通过 Corepack 解析，请先运行 `corepack enable`。\n- Git 2.26 或更高版本；钩子设置会启用 Git 的 worktree 专属配置扩展。\n- 可选：一个 DeepSeek API key，用于 Web、headless 和 ACP（Agent Client Protocol）自动化 agent（智能体）演示以及真实 API 的 e2e 测试。\n\n### 首次搭建\n\n在仓库根目录安装依赖：\n\n```sh\npnpm install\n```\n\n安装过程还会通过 `scripts/install-lefthook.mjs` 配置 worktree 本地的 Lefthook 钩子和 `dsh-translation-pairing` Git 合并驱动。[worktree 本地钩子 Agent Note](../.agents/notes/implemented/process/2026-07-27-worktree-local-lefthook.md) 负责钩子路径的安全约定；[自动配对合并 Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) 负责合并驱动。\n\n如果依赖是从缓存恢复或 `postinstall` 被跳过而导致任一集成缺失，请手动安装：\n\n```sh\nnode scripts/install-lefthook.mjs\n```\n\n如果包装脚本拒绝现有 Git 配置或报告陈旧锁，请遵循其诊断和所链接的 Agent Note，不要凭猜测编辑 worktree 元数据。移动检出目录后，请重新运行包装脚本以重新生成自有路径。\n\n新克隆后请先运行一次类型检查：\n\n```sh\npnpm run typecheck\n```\n\n`pnpm run typecheck` 成功退出即表示搭建完成。\n\n## 贡献者参考\n\n### TypeScript 项目布局\n\n仓库使用相互隔离的 Host 与 Client aggregate。普通 package 只登记进其中一个 aggregate；Host 包进入 `tsconfig.host.json`，Client 包进入 `tsconfig.client.json`。\n\n| 文件 | 角色 | 是否构成 program？ |\n|---|---|---|\n| `tsconfig.json` | solution 根：`extends` base、`files: []`、引用两个 aggregate。它是 tsserver 发现入口，也是显式执行整张 Project Reference 图时的入口；经继承的 `paths` 充当 tsx 运行 `examples/` 与 `scripts/` 时的解析配置。 | 否 |\n| `tsconfig.host.json` | Host aggregate：Host package、示例、测试、脚本和 website，以及 `api/remotes` 的 Host 特例 project。 | 是 |\n| `tsconfig.client.json` | Client aggregate：`packages/client/*` package 及其测试、`apps/web`，以及 `api/remotes` 的 Client 特例 project。 | 是 |\n| `tsconfig.base.json` | 共享 compilerOptions 与源码 `paths` 映射。同时是各 vitest 配置让 vite-tsconfig-paths 指向的解析门面：它没有 `include`，因此其 `paths` 适用于任何 importer。 | 否 |\n| `tsconfig.base.client.json` | 浏览器编译设置（`jsx`、DOM lib、`types: []`），由 Client aggregate 和每个 `packages/client/*` package extends。 | 否 |\n\nHost 与 Client 保持两个 aggregate program，是因为两侧在相同键下以不同服务对 cordis `Context` 接口做声明合并；单一 program 同时看到两份合并会报冲突。这种冲突只存在于 `ts.Program` 内部——模块解析永远不会触发它——所以 solution 可以同时引用两个 aggregate，一个 paths 门面也可以横跨两侧。由此推出三条纪律：\n\n- `tsconfig.base.json` 永不添加 `include` 或 `files`：它们会泄漏进每个 extends 它的包项目，并收窄门面的全匹配范围。\n- 构造全仓 `ts.Program` 的脚本显式种子 `tsconfig.host.json` 或 `tsconfig.client.json`——永不种子根 solution，因为把两个 aggregate 展平进一个 program 会撞上 `Context` 合并冲突。\n- 新 package 只登记进一个 aggregate。包同时具有 Node loader 入口和 browser 入口并不构成拆分理由；普通 Client plugin 的两份运行时产物都在 Client 构建阶段生成。\n\n`api/remotes` 是唯一拆分 Host/Client tsconfig 的仓库特例。它的 Host 入口必须进入 Host TypeRT 图，而 Client 入口导入 Host tsdown 才会生成的 `/remote` 声明，因此本包根 `tsconfig.json` 只作为 solution，两个 aggregate 和直接消费方分别引用 `tsconfig.host.json` 或 `tsconfig.client.json`。workspace `constraints` 门禁遍历可达的 Project Reference 图，并按各引用 project 自身的 compiler face 检查：只有单一配置的目标可由任一 face 引用，拆分配置的目标则必须引用匹配的 leaf，不得引用 solution 根或另一侧 leaf。不要把该结构推广到其他包；[`api-remotes` README](../packages/api/remotes/README.md) 说明 Host/Client 拆分与构建顺序。\n\n根构建按生成依赖排序：\n\n```sh\ntsc -b tsconfig.host.json\ntsdown --env.DSH_BUILD_FACE host\ntsc -b tsconfig.client.json\ntsdown --env.DSH_BUILD_FACE client\npnpm run build:web\n```\n\n两次 tsdown 都使用同一组完整 workspace 匹配，不扫描构建产物来发现 Client package，也不维护 Host/Client package 过滤表。包内 tsdown 配置根据 `DSH_BUILD_FACE` 决定当前阶段的入口：普通 Client plugin 在 Client 阶段同时生成 Node loader 与 browser bundle；`api-remotes` 通过 `hostPhase: true` 提前生成 Host 入口，再在 Client 阶段只生成 browser bundle。tsdown 只消费 `lib/types` 中由前置 tsc 发射的 JavaScript。\n\nTypeRT 只在 Host tsdown 中以 `tsconfig.host.json` 为种子运行。它分析 Host 类型并生成 Host 反射产物及 Host-for-Client Remote 投影；Client tsdown 不启动 TypeRT。`pnpm run typecheck` 因此先执行完整 Host lib 阶段，再运行 Client tsc；`pnpm run build` 继续执行 Client tsdown 和 Web 构建。该顺序的决策记录见 [API Remotes 生成约定构建 Note](../.agents/notes/implemented/process/2026-08-08-api-remotes-generated-contract-build.md)。\n\n静态分析和测试通过 base 的 `paths` 映射把工作区 import 解析到 `src`，且必须在干净树上通过；消费构建产物 `lib/` 的门禁显式声明该依赖。生成的 Host-for-Client Remote 声明是有意设置的例外：公共 `typecheck`、`lint` 和 `doc-typecheck` 命令会先生成这些声明，而内部 `*:contracts-ready` 脚本假定调用它的公共命令或调度器门禁已经依赖 TypeRT 约定生成阶段或完整构建。两个 aggregate 的设置见 [solution-root Note](../.agents/notes/implemented/process/2026-07-22-tsconfig-solution-root-two-aggregates.md)，tsc-first 发射职责见 [ts-build-config Note](../.agents/notes/implemented/process/2026-06-17-ts-build-config.md)，门禁准备约定见 [TypeRT Remote Agent Note](../.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md)。\n\n业务 Service 在 Host 使用 `@Remote` 或 `@RemoteScope` 声明可调用方法；Host 构建生成 Host-for-Client 类型与运行时贡献，Client 的 `api-remotes` 组合加载这些贡献并挂到 `ctx.remote` 与作用域 `agentCtx.remote` namespace。两侧的生成产物、装配关系、SRC 开发回退和 Web 构建顺序见 [API Gateway](api-gateway.md)。\n\n如果相关的本地检查需要使用构建后的包产物，请先构建一次：\n\n```sh\npnpm run build\n```\n\n`pnpm run hygiene` 包含 `publint`（用构建出的 `lib/*.js` 文件校验 package 入口点）和 `verify-node-next-types`（用一个临时的 NodeNext 消费方校验构建出的声明文件）。新 worktree 在 `pnpm run build` 运行之前没有打包的 JS 和声明文件；普通提交和推送无需构建，除非所选检查会使用这些产物。\n\n### 环境变量\n\n真实的 DeepSeek 适配器和需要密钥的 agent 演示从环境变量或仓库根目录一个被 gitignore 的 `.env` 文件读取凭证：\n\n```sh\nDEEPSEEK_API_KEY=sk-...\nDEEPSEEK_BASE_URL=https://... # optional\n```\n\n`DEEPSEEK_BASE_URL` 可选，默认为公开 API。请勿提交真实凭证。未设置 `DEEPSEEK_API_KEY` 时，真实 API 的 e2e 套件会自动跳过。\n\n### Git 集成\n\n当两种语言的文件都使用 Git 默认文本策略且能干净合并时，配对合并驱动会根据已确认的祖先、当前和另一侧的配对文档 blob，推导出发生冲突的 `.i18n.yaml` 记录。配对文档发生冲突、存在非文本合并配置或记录无效时，它会拒绝处理并保留冲突；如果合并已经因冲突而停止，请运行 `pnpm run resolve-translation-pairing-conflicts`，该命令会暂存每份可安全生成的配对记录；如果其他配对冲突仍需手工处理，则以非零状态退出。[双语文档约定](i18n/README.md#the-pairing-contract)列出该驱动接受的确切文件和状态。\n\n安装脚本在发布 worktree 配置前，会探测确切的 Node/tsx 驱动入口点。如果该运行时之后变得不可用，不依赖 Node 的启动器会写入 Git 的普通文本合并结果、让伴随文件保持未解决状态，并打印恢复路径；请恢复依赖后运行 `pnpm run resolve-translation-pairing-conflicts`，或运行 `git merge --abort`。如果 `pre-merge-commit` 拒绝原本能干净完成的合并，Git 会把完整结果留在暂存区但不创建提交；请修复失败后运行 `git commit`，或中止合并。确切的索引与 `MERGE_HEAD` 状态由[自动配对合并 Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md#failure-contract)负责记录。\n\nlefthook 在 `lefthook.yml` 中配置，作为快速的本地检查点：\n\n- `pre-commit` 对照暂存的配对文档 blob 校验暂存的配对记录，使用不加载项目的 `.oxlintrc.staged.json` 配置验证暂存文件，并通过一次有界重试应用 Oxlint 修复，在暂存文件属于 `THIRD_PARTY_NOTICES.md` 的输入时重新生成该文件，然后检查暂存 diff 中的空白错误，并运行 vendor manifest（元数据清单）守卫；\n- `pre-merge-commit` 在 Git 创建自动合并提交前执行同样以索引为准的配对检查；\n- `pre-push` 运行 `pnpm run typecheck`；该命令会先完成包含 TypeRT 约定生成的完整 Host lib 阶段，再运行 Client TypeScript 检查。\n\nvendor manifest 守卫检查 `vendor/*/src` 下的改动是否连同对应的 `vendor/README.md` manifest 更新一起暂存。请在编辑 vendor 代码前先阅读 `vendor/README.md`。\n\n除限定范围的暂存记录校验外，这些钩子有意不运行测试、快照、文档检查、构建或 `hygiene`。贡献者只运行一次[与改动行为相关的检查](../AGENTS.md#run-relevant-checks-locally)；CI 负责全量覆盖率门禁、构建产物冒烟测试，以及 Node 22.19、24 和 26 兼容性矩阵。\n\n贡献者可以选择运行 `pnpm run check:all`，执行全面的本地门禁集。该命令独立于 Git 钩子，也不是对 agent 的指令。\n\n### CI 门禁\n\nkeyless [CI 工作流](../.github/workflows/ci.yml) 将独立门禁分组到若干宽粒度 lane，并在受支持的 Node 版本上运行一组较小的兼容性检查。产物消费方在各自 lane 内等待一次 build。单独的真实 API 工作流按其配置的 worker 上限运行 `pnpm run test:e2e`。当前门禁和 job 清单以 [scripts/run-gates.ts](../scripts/run-gates.ts) 和工作流文件为准。\n\n### 日常命令\n\n根目录的[贡献者说明](../AGENTS.md#commands)概述常用命令，[`package.json`](../package.json) 与 [scripts/run-gates.ts](../scripts/run-gates.ts) 则负责当前脚本和门禁清单。请选择覆盖变更表面的最小检查集。文档变更使用 `pnpm run doc-sync`；package 公开行为变更还需更新所属 README 或 JSDoc，而基于构建产物的检查需要先运行 `pnpm run build`。\n\n### 演示\n\n单次运行的 Headless coding agent 需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`：\n\n```sh\npnpm run demo:headless \"summarize this workspace\"\n```\n\n自指的 cordis 演示可以检查并修改其实时插件运行时，并需要相同的凭证（默认 `web`，也可用 `acp`）：\n\n```sh\npnpm run demo:cordis\n```\n\nACP 自动化服务器通过 JSON-RPC stdio 提供全新 agent 会话，同样需要 `DEEPSEEK_API_KEY`：\n\n```sh\npnpm run demo:acp\n```\n\n### TODO 标记\n\n请使用以下三种注释标签之一标记代码中的已知问题，按紧急程度排序：\n\n- `FIXME`：应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并，否则发布版本不应包含未解决的 `FIXME`；\n- `TODO`：应当尽快修复的问题，等资源到位即可处理；\n- `XXX`：也许某天会修复的问题，优先级最低，不作承诺。\n\n请选择与紧急程度匹配的标签，让浏览代码的人一眼分清「发布阻塞」和「有空再说」。\n\n### 逐字记录类型（`ts type-equiv`）\n\n[子系统](subsystems/README.md)页面会把与源码等价的声明及其原始 JSDoc 一并粘贴，让读者看到确切类型定义和源码约定。为防止粘贴内容在源码变化时漂移，请将其围栏为 ` ```ts type-equiv `（而不是 ` ```ts `），并在 `scripts/type-equiv.manifest.json` 中登记它镜像的源文件和符号：\n\n```json\n{ \"doc\": \"docs/subsystems/session.md\", \"symbol\": \"SessionEvent\", \"source\": \"packages/core/session/src/types.ts\" }\n```\n\n`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明及其附带的 JSDoc，并断言代码块同时匹配两者。对于不应把实现体写进目录的类，请使用 ` ```ts public-api ` 并设置 `\"projection\": \"public-api\"`；门禁检查的投影会保留公共字段、构造函数、访问器、方法以及类和成员的原始 JSDoc，同时省略实现体和私有或受保护成员。比对会忽略空白和非 JSDoc 注释，但要求保留每条原始 JSDoc（包括成员文档），让读者同时看到源码约定和确切类型定义。该门禁按文档、符号和投影，在主块与 manifest 条目之间强制 1:1 对应；只有当配对 `.zh.md` 块的完整受跟踪围栏序列与其无后缀兄弟文件按字节一致且顺序相同时，才会复用后者的条目。`doc-typecheck` 对可编译围栏应用同一派生规则，同时跳过两种源码等价围栏的编译，并将其排除在 opt-out 比例之外。当你改动一个已记录的类型声明或其 JSDoc 时，门禁会失败直到你更新粘贴内容；当你增删一个主块时，请在同一个变更里更新 manifest。\n" + "content": "# 开发指南\n\n[English](development.md) | 中文\n\n搭建教程引导新贡献者从准备前置条件开始，直到检出通过检查。后面的贡献者参考介绍仓库布局、日常工作流和 CI 组织方式。设计依据与实现细节属于链接的 Agent Note 和脚本。\n\n## 搭建教程\n\n### 前置条件\n\n- Node.js 支持 22.19+ 与 24+。CI 覆盖 22.19、24 和 26；见 [Node 引擎下限 Agent Note](../.agents/notes/implemented/process/2026-07-06-node-engine-floor.md)。\n- 启用了 Corepack 的 pnpm。仓库在 `package.json` 中固定使用 `pnpm@11.7.0`；如果 `pnpm --version` 无法通过 Corepack 解析，请先运行 `corepack enable`。\n- Git 2.26 或更高版本；钩子设置会启用 Git 的 worktree 专属配置扩展。\n- 可选：一个 DeepSeek API key，用于 Web、headless 和 ACP（Agent Client Protocol）自动化 agent（智能体）演示以及真实 API 的 e2e 测试。\n\n### 首次搭建\n\n在仓库根目录安装依赖：\n\n```sh\npnpm install\n```\n\n安装过程还会通过 `scripts/install-lefthook.mjs` 配置 worktree 本地的 Lefthook 钩子和 `dsh-translation-pairing` Git 合并驱动。[worktree 本地钩子 Agent Note](../.agents/notes/implemented/process/2026-07-27-worktree-local-lefthook.md) 负责钩子路径的安全约定；[自动配对合并 Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md) 负责合并驱动。\n\n如果依赖是从缓存恢复或 `postinstall` 被跳过而导致任一集成缺失，请手动安装：\n\n```sh\nnode scripts/install-lefthook.mjs\n```\n\n如果包装脚本拒绝现有 Git 配置或报告陈旧锁，请遵循其诊断和所链接的 Agent Note，不要凭猜测编辑 worktree 元数据。移动检出目录后，请重新运行包装脚本以重新生成自有路径。\n\n新克隆后请先运行一次类型检查：\n\n```sh\npnpm run typecheck\n```\n\n`pnpm run typecheck` 成功退出即表示搭建完成。\n\n## 贡献者参考\n\n### TypeScript 项目布局\n\n仓库使用相互隔离的 Host 与 Client aggregate。普通 package 只登记进其中一个 aggregate；Host 包进入 `tsconfig.host.json`，Client 包进入 `tsconfig.client.json`。\n\n| 文件 | 角色 | 是否构成 program？ |\n|---|---|---|\n| `tsconfig.json` | solution 根：`extends` base、`files: []`、引用两个 aggregate。它是 tsserver 发现入口，也是显式执行整张 Project Reference 图时的入口；经继承的 `paths` 充当 tsx 运行 `examples/` 与 `scripts/` 时的解析配置。 | 否 |\n| `tsconfig.host.json` | Host aggregate：Host package、示例、测试、脚本和 website，以及 `api/remotes` 的 Host 特例 project。 | 是 |\n| `tsconfig.client.json` | Client aggregate：`packages/client/*` package 及其测试、`apps/web`，以及 `api/remotes` 的 Client 特例 project。 | 是 |\n| `tsconfig.base.json` | 共享 compilerOptions 与源码 `paths` 映射。同时是各 vitest 配置让 vite-tsconfig-paths 指向的解析门面：它没有 `include`，因此其 `paths` 适用于任何 importer。 | 否 |\n| `tsconfig.base.client.json` | 浏览器编译设置（`jsx`、DOM lib、`types: []`），由 Client aggregate 和每个 `packages/client/*` package extends。 | 否 |\n\nHost 与 Client 保持两个 aggregate program，是因为两侧在相同键下以不同服务对 cordis `Context` 接口做声明合并；单一 program 同时看到两份合并会报冲突。这种冲突只存在于 `ts.Program` 内部——模块解析永远不会触发它——所以 solution 可以同时引用两个 aggregate，一个 paths 门面也可以横跨两侧。由此推出三条纪律：\n\n- `tsconfig.base.json` 永不添加 `include` 或 `files`：它们会泄漏进每个 extends 它的包项目，并收窄门面的全匹配范围。\n- 构造全仓 `ts.Program` 的脚本显式种子 `tsconfig.host.json` 或 `tsconfig.client.json`——永不种子根 solution，因为把两个 aggregate 展平进一个 program 会撞上 `Context` 合并冲突。\n- 新 package 只登记进一个 aggregate。包同时具有 Node loader 入口和 browser 入口并不构成拆分理由；普通 Client plugin 的两份运行时产物都在 Client 构建阶段生成。\n\n`api/remotes` 是唯一拆分 Host/Client tsconfig 的仓库特例。它的 Host 入口必须进入 Host TypeRT 图，而 Client 入口导入 Host tsdown 才会生成的 `/remote` 声明，因此本包根 `tsconfig.json` 只作为 solution，两个 aggregate 和直接消费方分别引用 `tsconfig.host.json` 或 `tsconfig.client.json`。workspace `constraints` 门禁遍历可达的 Project Reference 图，并按各引用 project 自身的 compiler face 检查：只有单一配置的目标可由任一 face 引用，拆分配置的目标则必须引用匹配的 leaf，不得引用 solution 根或另一侧 leaf。不要把该结构推广到其他包；[`api-remotes` README](../packages/api/remotes/README.md) 说明 Host/Client 拆分与构建顺序。\n\n根构建按生成依赖排序：\n\n```sh\ntsc -b tsconfig.host.json\ntsdown --env.DSH_BUILD_FACE host\ntsc -b tsconfig.client.json\ntsdown --env.DSH_BUILD_FACE client\npnpm run build:web\n```\n\n两次 tsdown 都使用同一组完整 workspace 匹配，不扫描构建产物来发现 Client package，也不维护 Host/Client package 过滤表。包内 tsdown 配置根据 `DSH_BUILD_FACE` 决定当前阶段的入口：普通 Client plugin 在 Client 阶段同时生成 Node loader 与 browser bundle；`api-remotes` 通过 `hostPhase: true` 提前生成 Host 入口，再在 Client 阶段只生成 browser bundle。tsdown 只消费 `lib/types` 中由前置 tsc 发射的 JavaScript。\n\nTypeRT 只在 Host tsdown 中以 `tsconfig.host.json` 为种子运行。它分析 Host 类型并生成 Host 反射产物及 Host-for-Client Remote 投影；Client tsdown 不启动 TypeRT。`pnpm run typecheck` 因此先执行完整 Host lib 阶段，再运行 Client tsc；`pnpm run build` 继续执行 Client tsdown 和 Web 构建。该顺序的决策记录见 [API Remotes 生成约定构建 Note](../.agents/notes/implemented/process/2026-08-08-api-remotes-generated-contract-build.md)。\n\n静态分析和测试通过 base 的 `paths` 映射把工作区 import 解析到 `src`，且必须在干净树上通过；消费构建产物 `lib/` 的门禁显式声明该依赖。生成的 Host-for-Client Remote 声明是有意设置的例外：公共 `typecheck`、`lint` 和 `doc-typecheck` 命令会先生成这些声明，而内部 `*:contracts-ready` 脚本假定调用它的公共命令或调度器门禁已经依赖 TypeRT 约定生成阶段或完整构建。两个 aggregate 的设置见 [solution-root Note](../.agents/notes/implemented/process/2026-07-22-tsconfig-solution-root-two-aggregates.md)，tsc-first 发射职责见 [ts-build-config Note](../.agents/notes/implemented/process/2026-06-17-ts-build-config.md)，门禁准备约定见 [TypeRT Remote Agent Note](../.agents/notes/implemented/architecture/2026-08-02-typert-remote-method-calls.md)。\n\n业务 Service 在 Host 使用 `@Remote` 或 `@RemoteScope` 声明可调用方法；Host 构建生成 Host-for-Client 类型与运行时贡献，Client 的 `api-remotes` 组合加载这些贡献并挂到 `ctx.remote` 与作用域 `agentCtx.remote` namespace。两侧的生成产物、装配关系、SRC 开发回退和 Web 构建顺序见 [API Gateway](api-gateway.md)。\n\n如果相关的本地检查需要使用构建后的包产物，请先构建一次：\n\n```sh\npnpm run build\n```\n\n`pnpm run hygiene` 包含 `publint`（用构建出的 `lib/*.js` 文件校验 package 入口点）和 `verify-node-next-types`（用一个临时的 NodeNext 消费方校验构建出的声明文件）。新 worktree 在 `pnpm run build` 运行之前没有打包的 JS 和声明文件；普通提交和推送无需构建，除非所选检查会使用这些产物。\n\n### 环境变量\n\n真实的 DeepSeek 适配器和需要密钥的 agent 演示从环境变量或仓库根目录一个被 gitignore 的 `.env` 文件读取凭证：\n\n```sh\nDEEPSEEK_API_KEY=sk-...\nDEEPSEEK_BASE_URL=https://... # optional\n```\n\n`DEEPSEEK_BASE_URL` 可选，默认为公开 API。请勿提交真实凭证。未设置 `DEEPSEEK_API_KEY` 时，真实 API 的 e2e 套件会自动跳过。\n\n### Git 集成\n\n当两种语言的文件都使用 Git 默认文本策略且能干净合并时，配对合并驱动会根据已确认的祖先、当前和另一侧的配对文档 blob，推导出发生冲突的 `.i18n.yaml` 记录。配对文档发生冲突、存在非文本合并配置或记录无效时，它会拒绝处理并保留冲突；如果合并已经因冲突而停止，请运行 `pnpm run resolve-translation-pairing-conflicts`，该命令会暂存每份可安全生成的配对记录；如果其他配对冲突仍需手工处理，则以非零状态退出。[双语文档约定](i18n/README.md#the-pairing-contract)列出该驱动接受的确切文件和状态。\n\n安装脚本在发布 worktree 配置前，会探测确切的 Node/tsx 驱动入口点。如果该运行时之后变得不可用，不依赖 Node 的启动器会写入 Git 的普通文本合并结果、让伴随文件保持未解决状态，并打印恢复路径；请恢复依赖后运行 `pnpm run resolve-translation-pairing-conflicts`，或运行 `git merge --abort`。如果 `pre-merge-commit` 拒绝原本能干净完成的合并，Git 会把完整结果留在暂存区但不创建提交；请修复失败后运行 `git commit`，或中止合并。确切的索引与 `MERGE_HEAD` 状态由[自动配对合并 Agent Note](../.agents/notes/implemented/process/2026-08-08-automatic-translation-pairing-merges.md#failure-contract)负责记录。\n\nlefthook 在 `lefthook.yml` 中配置，作为快速的本地检查点：\n\n- `pre-commit` 对照暂存的配对文档 blob 校验暂存的配对记录，使用不加载项目的 `.oxlintrc.staged.json` 配置验证暂存文件，并通过一次有界重试应用 Oxlint 修复，在暂存文件属于 `THIRD_PARTY_NOTICES.md` 的输入时重新生成该文件，然后检查暂存 diff 中的空白错误，并运行 vendor manifest（元数据清单）守卫；\n- `pre-merge-commit` 在 Git 创建自动合并提交前执行同样以索引为准的配对检查；\n- `pre-push` 运行 `pnpm run typecheck`；该命令会先完成包含 TypeRT 约定生成的完整 Host lib 阶段，再运行 Client TypeScript 检查。\n\nvendor manifest 守卫检查 `vendor/*/src` 下的改动是否连同对应的 `vendor/README.md` manifest 更新一起暂存。请在编辑 vendor 代码前先阅读 `vendor/README.md`。\n\n除限定范围的暂存记录校验外，这些钩子有意不运行测试、快照、文档检查、构建或 `hygiene`。贡献者只运行一次[与改动行为相关的检查](../AGENTS.md#run-relevant-checks-locally)；CI 负责全量覆盖率门禁、构建产物冒烟测试，以及 Node 22.19、24 和 26 兼容性矩阵。\n\n贡献者可以选择运行 `pnpm run check:all`，执行全面的本地门禁集。该命令独立于 Git 钩子，也不是对 agent 的指令。\n\n### CI 门禁\n\nkeyless [CI 工作流](../.github/workflows/ci.yml) 将独立门禁分组到若干宽粒度 lane，并在受支持的 Node 版本上运行一组较小的兼容性检查。产物消费方在各自 lane 内等待一次 build。单独的真实 API 工作流按其配置的 worker 上限运行 `pnpm run test:e2e`。当前门禁和 job 清单以 [scripts/run-gates.ts](../scripts/run-gates.ts) 和工作流文件为准。\n\n### 日常命令\n\n根目录的[贡献者说明](../AGENTS.md#commands)概述常用命令，[`package.json`](../package.json) 与 [scripts/run-gates.ts](../scripts/run-gates.ts) 则负责当前脚本和门禁清单。请选择覆盖变更表面的最小检查集。文档变更使用 `pnpm run doc-sync`；package 公开行为变更还需更新所属 README 或 JSDoc，而基于构建产物的检查需要先运行 `pnpm run build`。\n\n### 演示\n\n单次运行的 Headless coding agent 需要环境变量或仓库根目录 `.env` 中的 `DEEPSEEK_API_KEY`：\n\n```sh\npnpm dsh --profile headless \"summarize this workspace\"\n```\n\n自指的 cordis 演示可以检查并修改其实时插件运行时，并需要相同的凭证（默认 `web`，也可用 `acp`）：\n\n```sh\npnpm run demo:cordis\n```\n\nACP 自动化服务器通过 JSON-RPC stdio 提供全新 agent 会话，同样需要 `DEEPSEEK_API_KEY`：\n\n```sh\npnpm run demo:acp\n```\n\n### TODO 标记\n\n请使用以下三种注释标签之一标记代码中的已知问题，按紧急程度排序：\n\n- `FIXME`：应当阻塞新版本发布的问题。除非评审者明确同意该更改可以合并，否则发布版本不应包含未解决的 `FIXME`；\n- `TODO`：应当尽快修复的问题，等资源到位即可处理；\n- `XXX`：也许某天会修复的问题，优先级最低，不作承诺。\n\n请选择与紧急程度匹配的标签，让浏览代码的人一眼分清「发布阻塞」和「有空再说」。\n\n### 逐字记录类型（`ts type-equiv`）\n\n[子系统](subsystems/README.md)页面会把与源码等价的声明及其原始 JSDoc 一并粘贴，让读者看到确切类型定义和源码约定。为防止粘贴内容在源码变化时漂移，请将其围栏为 ` ```ts type-equiv `（而不是 ` ```ts `），并在 `scripts/type-equiv.manifest.json` 中登记它镜像的源文件和符号：\n\n```json\n{ \"doc\": \"docs/subsystems/session.md\", \"symbol\": \"SessionEvent\", \"source\": \"packages/core/session/src/types.ts\" }\n```\n\n`pnpm run verify-type-equiv`（`doc-sync` 的一环）随后通过 TypeScript 解析器从源码提取该符号的声明及其附带的 JSDoc，并断言代码块同时匹配两者。对于不应把实现体写进目录的类，请使用 ` ```ts public-api ` 并设置 `\"projection\": \"public-api\"`；门禁检查的投影会保留公共字段、构造函数、访问器、方法以及类和成员的原始 JSDoc，同时省略实现体和私有或受保护成员。比对会忽略空白和非 JSDoc 注释，但要求保留每条原始 JSDoc（包括成员文档），让读者同时看到源码约定和确切类型定义。该门禁按文档、符号和投影，在主块与 manifest 条目之间强制 1:1 对应；只有当配对 `.zh.md` 块的完整受跟踪围栏序列与其无后缀兄弟文件按字节一致且顺序相同时，才会复用后者的条目。`doc-typecheck` 对可编译围栏应用同一派生规则，同时跳过两种源码等价围栏的编译，并将其排除在 opt-out 比例之外。当你改动一个已记录的类型声明或其 JSDoc 时，门禁会失败直到你更新粘贴内容；当你增删一个主块时，请在同一个变更里更新 manifest。\n" }, { "role": "user", diff --git a/scripts/verify-package-readme-model-experience.ts b/scripts/verify-package-readme-model-experience.ts index 1ffc0384f3..88b18e7bb0 100644 --- a/scripts/verify-package-readme-model-experience.ts +++ b/scripts/verify-package-readme-model-experience.ts @@ -72,6 +72,7 @@ const SENTENCE_MODEL_EXPERIENCE: Readonly> = { 'packages/client/ui-conversation': { kind: 'none', reason: 'Browser-side UI plugin layer; registers no model surface.' }, 'packages/client/ui-tool': { kind: 'none', reason: 'Browser-side Tool presentation layer; renders logged calls without changing model context.' }, 'packages/client/ui-deliverables': { kind: 'none', reason: 'Browser-side UI plugin layer; registers no model surface.' }, + 'packages/client/ui-task': { kind: 'none', reason: 'Browser-side read-only projection of ctx.tasks records; dsh-tool-tasks owns the model-facing surface.' }, 'packages/client/ui-slash': { kind: 'none', reason: 'Browser-side UI plugin layer; registers no model surface.' }, 'packages/client/ui-command': { kind: 'indirect', reason: 'The dispatch paths trigger the host command.execute RPC; each command handler\'s host package owns any model-visible effect.' }, 'packages/client/ui-model': { kind: 'indirect', reason: 'Selection routes session.selectModel; the Host snapshots the selection at the next prompt-assembly boundary and owns the model-visible effect.' }, diff --git a/skills/dsh-customize/SKILL.md b/skills/dsh-customize/SKILL.md deleted file mode 100644 index 5d67af1e51..0000000000 --- a/skills/dsh-customize/SKILL.md +++ /dev/null @@ -1,37 +0,0 @@ ---- -name: dsh-customize -description: Customize or maintain any dsh source checkout — the one powering the current DSH process, the installed `dsh` command, or a sibling dsh/deepseek-harness clone. Use before any requested action that alters such a checkout's files or git state. Read-only questions that only inspect the checkout do not trigger this. Do not edit the personal staging checkout directly. ---- - -# DSH Customize - -Make personal DSH changes in task worktrees and integrate them under the staging lock. Repository instructions still apply. - -## Find staging - -Do not assume a path or branch name. DSH is usually installed from source with a personal staging branch; create one for the user only when none exists. - -1. Inspect `command -v dsh` in the user's launch environment before resolving symlinks. -2. Follow the launcher through the full symlink chain to reach the source checkout, then ask Git for everything else. The `dsh` on PATH is a symlink, usually through a stable `current` symlink into the active staging worktree; resolve the chain physically and take the launcher's parent directory as the checkout. Derive the rest from that checkout rather than from any path convention: `git -C rev-parse --show-toplevel` confirms the checkout root, and `git -C rev-parse --git-common-dir` gives the shared git directory — a linked worktree reports the real clone's, not its own — whose parent is the main clone, the one real clone whose object store every worktree shares. `--git-common-dir` answers relatively for a plain clone, so anchor it against the checkout before use, and resolve it physically: Git reports resolved paths, so comparing one against an unresolved path silently misidentifies the clone whenever a symlink sits anywhere above the checkout, which a symlinked home directory alone is enough to cause. `git -C
worktree list` then enumerates every checkout sharing it. - - This resolves every checkout, so depend on nothing else: not an environment variable, not a container path, not the main clone's location or branch. A checkout whose launcher links straight at it, with no `current` in the chain, resolves the same way. -3. Verify the checkout with Git, then record its branch, tip, status, remotes, worktrees, in-progress operations, and applicable `AGENTS.md` files. -4. Treat the launcher checkout's branch as staging unless the user says otherwise. The installed launcher must resolve to a staging worktree on a staging branch, never the main clone or a task, preparation, review, publication, or detached checkout. Ask if the launcher, checkout, or branch ownership is ambiguous; warn explicitly for a detached HEAD, the main clone, or a non-staging branch. - -## Customize - -1. Create a fresh task branch and worktree from the recorded staging tip, using the repository-required worktree location — default to `.worktrees/` under the repository root unless the repository requires otherwise. Never implement or commit directly on staging. -2. Implement the change, then select and run the repository-required review and checks. If a check fails, fix the cause and rerun it before integration. -3. Test assembled interactive behavior in the Web UI; unit tests and snapshots alone are insufficient. -4. Record the task tip and confirm the task worktree is clean before integration. - -## Integrate under the lock - -1. Resolve the worktree that owns staging and use `/.agents/merge.lock`. Keep it Git-ignored; never remove or replace it. Require `flock`. -2. Acquire the lock, then re-check branch ownership, exact staging tip, clean status, and absence of an in-progress Git operation. If staging moved, unlock and restart discovery against its current owner's lock. -3. Hold the same lock through final precondition checks, `git merge --no-ff`, required post-merge checks, conflict handling, and rollback. -4. If the merge or a post-merge check fails, abort the merge or restore the recorded clean staging tip before unlocking. Never discard unknown user files. -5. Before unlocking, verify staging's branch, commit, clean status, and required checks. Report that evidence and the commands run. -6. Remove the task worktree and branch only when their commits are reachable from staging and no longer needed. - -Use [`dsh-upstream-customization`](../dsh-upstream-customization/SKILL.md) when the user wants to contribute a personal feature upstream. diff --git a/skills/dsh-upgrade/SKILL.md b/skills/dsh-upgrade/SKILL.md deleted file mode 100644 index 119725274c..0000000000 --- a/skills/dsh-upgrade/SKILL.md +++ /dev/null @@ -1,48 +0,0 @@ ---- -name: dsh-upgrade -description: Upgrades a source-installed, personally customized DSH checkout to upstream master while preserving local changes and an unchanged rollback worktree. Use when the user asks to update or upgrade DSH. ---- - -# DSH Upgrade - -Prepare and validate the upgrade in a fresh staging worktree of the main clone, leave the worktree the installed launcher currently uses unchanged, then atomically repoint the stable `current` symlink once. Read and follow [`dsh-customize`](../dsh-customize/SKILL.md) before starting; it owns checkout discovery and lock handling. - -## Layout - -Resolve the layout, never assume it. [`dsh-customize`](../dsh-customize/SKILL.md) owns the procedure: follow the PATH launcher to the staging worktree, then derive the main clone from that checkout with Git. One resolution covers every checkout, so this workflow needs no special case and depends on no environment variable. - -The resolved layout is one container directory `` holding each staging checkout as a git worktree `/staging-` on branch `dsh-staging/`, plus the stable symlink `/current` pointing at the active one; the PATH launcher links to `/current/bin/dsh`, so it resolves PATH -> `current` -> staging worktree. The main clone is the one real clone whose object store every worktree shares, and is never a launcher target. It may live inside `` or anywhere else on disk, on any branch, with remotes that may point at a fork — so treat it strictly as the object store and worktree host, and take authoritative upstream from step 1 instead. Cutover repoints `current` alone, so the PATH launcher itself never moves. The main clone's `.git/info/exclude` is inherited by every linked worktree, so one `.agents/merge.lock` entry there excludes the lock in all of them. When the launcher links straight at a worktree with no `current` in the chain, the same resolution finds it, and cutover creates `current` and repoints PATH to `current/bin/dsh` as a one-time migration. - -## Names - -One upgrade attempt uses one UTC basic timestamp `YYYYMMDDTHHMMSSZ` for all names: - -- new staging worktree: `/staging-`; -- preparation branch: `dsh-upgrade/prepare-`; -- installed staging branch: `dsh-staging/`; -- fetched upstream ref: `refs/dsh-upgrade/upstream-`; -- recovery ref: `refs/dsh-upgrade/recovery-`; -- recorded `current` target before cutover: the old staging worktree path, kept for symlink rollback. - -The worktree name is always `staging-` under ``, never derived from the current staging directory name, so successive upgrades stay in one place and do not accumulate timestamps. The preparation branch and private refs are local-only and must never be pushed. Before starting, reject a current staging branch named exactly `dsh-staging`, because Git cannot also create `dsh-staging/`; require the user to choose a non-conflicting staging namespace rather than silently renaming it. If the new staging worktree path exists, resume only when it is a clean worktree of this main clone whose recorded old tip, upstream ref, recovery ref, and named branches exactly match this attempt; otherwise stop. Never add an ad hoc suffix or delete an unknown directory. - -## Upgrade - -1. Resolve the installed launcher, its staging worktree and branch, the main clone, the current DSH process source, and authoritative upstream. Record exact tips, paths, clean status, remotes, dependencies, worktrees, and in-progress Git operations. Require the installed staging worktree to be clean and its `.agents/merge.lock` to exist and be Git-excluded. Never stash automatically. -2. Treat the staging worktree behind the installed launcher as immutable for the whole attempt: do not touch its branch, HEAD, index, tracked or untracked files, dependencies, worktree registration, or lock file. Fetching into the shared main clone and creating new branches, worktrees, and private refs there are allowed because they are append-only and never alter the old worktree's checkout; opening and holding the existing lock is the only operation on the old worktree. -3. Allocate the timestamp and new staging worktree path. Acquire the installed worktree's existing `.agents/merge.lock`, repeat every precondition, and keep it through preparation, validation, and the `current` cutover. If staging moves while waiting, unlock and restart with a new timestamp; remove only attempt artifacts that this run created and verified as disposable. -4. In the main clone, create `refs/dsh-upgrade/recovery-` at the recorded old staging tip and `dsh-upgrade/prepare-` from that tip. Fetch exact authoritative upstream `master` into `refs/dsh-upgrade/upstream-` and record its object ID. Add a fresh worktree `/staging-` checked out on the preparation branch. Confirm the main clone's `.git/info/exclude` excludes `.agents/merge.lock`, which the new worktree inherits. -5. Inspect the Git log and commit ranges between the staging base, old staging tip, and fetched upstream tip. Identify incoming upstream changes, personal commits to preserve, likely duplicates, and conflict-prone areas before rebasing. -6. In the new worktree, rebase the preparation branch onto the fetched upstream commit. Preserve intentional customizations and drop behavior already upstream. If upstream contains the customization and its remaining local diff only documents that customization, prefer upstream and drop the documentary diff rather than retaining a stale local account. Preserve documentation only when it adds current, independently useful behavior or rules absent upstream. Abort without changing the installed launcher when resolution is uncertain. -7. Install dependencies in the new worktree, review the resulting diff, and run the repository-required checks. Fix failures and rerun affected checks. Test the new worktree's `bin/dsh` directly. -8. Point `dsh-staging/` at the validated prepared tip and check it out in the new worktree. Ensure its `.agents/merge.lock` exists (Git-excluded through the shared main-clone exclude). Verify its branch, exact commit, clean status, remotes, dependencies, and absence of in-progress Git operations, then smoke its `bin/dsh` from a clean temporary workspace. The preparation branch remains temporary; the timestamped staging branch owns the installed commit. -9. Recheck the old worktree, existing lock, launcher, `current`, main clone, new worktree, refs, and exact tips. Record `current`'s pre-cutover target, then repoint `current` at the new staging worktree in one atomic swap with `ln -sfn` (the `-n` stops `ln` from dereferencing the existing directory symlink and writing the link inside the old worktree; `mv` behaves the same way and is unusable). Leave the PATH launcher alone once it already resolves through `current`; if a legacy install still links PATH straight at a worktree, create `current` and repoint PATH to `current/bin/dsh` as a one-time migration here. The `current` target must be a clean staging worktree on a staging branch and must never be the main clone or a preparation, feature, review, publication, or detached checkout. Smoke the installed `dsh` command from a clean temporary workspace. -10. On failure before the `current` cutover, leave `current`, the launcher, and the old worktree unchanged and remove only verified attempt artifacts created by this run (including the new worktree registration if empty). On failure during or after cutover, inspect `current`'s observed target before acting; if cutover did not verify, atomically repoint `current` back to its recorded pre-cutover target with `ln -sfn` and verify that `dsh` starts from the unchanged old staging worktree. This rollback is the sole exception allowing `current` to return to the old staging worktree. Never retry a side-effecting operation blindly. -11. Release the old worktree's lock and tell the user to restart DSH through the installed launcher. The current process may continue from the old worktree, but no operation may mutate or remove it until the restarted process proves that it runs from `dsh-staging/` and the user confirms stability. Avoid customization integration during this confirmation window; if rollback is required after new work lands, reconcile that work explicitly rather than silently stranding it. -12. After confirmation, remove the preparation branch if no process uses it. Keep the old staging worktree and branch, the recovery ref, and the recorded pre-cutover `current` target as rollback until the user explicitly approves their removal; leave the actual `git worktree remove` and directory deletion to the user. Report old, upstream, prepared, and new staging commits; both staging worktree paths and branches; the main clone path; process-source evidence; the `current` pre-cutover target and cutover; commands and checks; final status; recovery ref; and retained rollback artifacts. - -The installed launcher always resolves through `current` to a staging worktree, never the main clone. Upgrade preparation adds a new worktree that shares the main clone's object store while leaving the old worktree's checkout untouched; cutover is one atomic `current` repoint to the separately validated timestamped staging worktree, and the PATH launcher never moves. - -## Recommend upstream candidates - -After a successful upgrade, load [`dsh-upstream-customization`](../dsh-upstream-customization/SKILL.md) and classify each remaining personal customization by its rules. For each candidate, explain its classification and upstream value and recommend whether to propose it, then ask which named candidate, if any, the user wants to upstream. The answer selects a candidate to start that skill's publication workflow; it is not publishing approval, which that workflow still requires. diff --git a/skills/dsh-upstream-customization/SKILL.md b/skills/dsh-upstream-customization/SKILL.md deleted file mode 100644 index 7ec1618db3..0000000000 --- a/skills/dsh-upstream-customization/SKILL.md +++ /dev/null @@ -1,27 +0,0 @@ ---- -name: dsh-upstream-customization -description: Classifies personal DSH customizations for upstream contribution and, after explicit per-feature approval, rebuilds one on upstream master and opens a draft pull request. Use when the user asks to contribute, publish, or upstream a local DSH change, or asks whether one is worth proposing. ---- - -# DSH Upstream Customization - -Classify and propose personal customizations upstream one feature at a time. - -## Classify - -- **Definitely propose:** bug fixes. -- **Propose:** additive, non-conflicting features implemented as plugins; visual improvements. -- **Do not propose without maintainer approval:** intrusive changes that alter existing architecture, core behavior, or broad contracts. -- Explain the classification and upstream value. If unsure whether a change is intrusive, treat it as intrusive. - -Classification and a recommendation are not publishing approval. Obtain explicit user approval naming one feature before pushing or opening a PR; approval for another feature, an upgrade, or local integration does not apply. - -## Publish an approved feature - -1. Fetch current upstream `master`, then rebuild only the approved feature on a fresh branch and worktree at that exact commit. Never publish the personal staging branch or unrelated customizations. -2. Follow repository instructions for implementation, review, testing, disclosure, PR writing, and pre-push checks. Fix failures and rerun the affected checks before publishing. -3. Review the outgoing commits and diff against upstream. Confirm they contain only the approved feature, no credentials or personal data, and a clean worktree. -4. Reconfirm the approved feature name and publishing target before the first push. Do not infer authorization from earlier local work. -5. Push only that branch and open only a draft PR. Keep its description synchronized with later changes. -6. For a Web UI feature, attach a screenshot or GIF from the assembled application after removing credentials and personal data. -7. Report the upstream base and branch commits, commands and checks run, pushed branch, and draft PR URL. diff --git a/tsconfig.base.json b/tsconfig.base.json index fcdea094f3..a08b438f3a 100644 --- a/tsconfig.base.json +++ b/tsconfig.base.json @@ -71,6 +71,7 @@ "@deepseek-ai/dsh-llm/message": ["./packages/llm/llm/src/message.ts"], "@deepseek-ai/dsh-commands/brand": ["./packages/interaction/commands/src/brand.ts"], "@deepseek-ai/dsh-commands/types": ["./packages/interaction/commands/src/types.ts"], + "@deepseek-ai/dsh-tasks/brand": ["./packages/tasks/tasks/src/brand.ts"], "@deepseek-ai/dsh-compact/checkpoint": ["./packages/compact/compact/src/checkpoint.ts"], "@deepseek-ai/dsh-compact/types": ["./packages/compact/compact/src/types.ts"], "@deepseek-ai/dsh-tools/presentation": ["./packages/core/tools/src/presentation.ts"], @@ -178,6 +179,7 @@ "@deepseek-ai/dsh-client-ui-permission": ["./packages/client/ui-permission/src"], "@deepseek-ai/dsh-client-ui-skill": ["./packages/client/ui-skill/src"], "@deepseek-ai/dsh-client-ui-subagent": ["./packages/client/ui-subagent/src"], + "@deepseek-ai/dsh-client-ui-task": ["./packages/client/ui-task/src"], "@deepseek-ai/dsh-client-ui-plan": ["./packages/client/ui-plan/src"], "@deepseek-ai/dsh-client-ui-question": ["./packages/client/ui-question/src"], "@deepseek-ai/dsh-client-ui-trajectory": ["./packages/client/ui-trajectory/src"], diff --git a/tsconfig.client.json b/tsconfig.client.json index 632f6a84a7..fce7d45b7b 100644 --- a/tsconfig.client.json +++ b/tsconfig.client.json @@ -66,6 +66,7 @@ { "path": "./packages/client/ui-command" }, { "path": "./packages/client/ui-skill" }, { "path": "./packages/client/ui-subagent" }, + { "path": "./packages/client/ui-task" }, { "path": "./packages/client/ui-goal" }, { "path": "./packages/client/ui-model" }, { "path": "./packages/client/ui-agent-preset" }, diff --git a/tsconfig.host.json b/tsconfig.host.json index 12c5d365d6..690656e150 100644 --- a/tsconfig.host.json +++ b/tsconfig.host.json @@ -60,6 +60,7 @@ "apps/web/tests/subagent-interrupt.e2e.ts", "apps/web/tests/subagent-interrupt-ui.e2e.ts", "apps/web/tests/sidebar-subagent-activity.e2e.ts", + "apps/web/tests/background-task-list.e2e.ts", "apps/web/tests/bash-abort-row.e2e.ts", "apps/web/tests/skill-tool-row.e2e.ts", "apps/web/tests/turn-tail-actions.e2e.ts",