Merge commit 'b916cf8aab5bd8bca5ae47df16f72717c0a56b4a' into HEAD

# Conflicts:
#	docs/config-catalog.i18n.yaml
This commit is contained in:
Tianyi Cui
2026-08-10 16:38:17 +08:00
400 changed files with 6882 additions and 1183 deletions
+1 -1
View File
@@ -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/README.md
README.md: 3cfbb5154713046846a3bfcb2ccea62c0e4cb6c0
README.md: d3a8943a78238d974d54028e38b773e932429b0e
README.zh.md: 4b3a1ee57ea61a8e8ba4d01cf7c719bbf8440e30
+1 -1
View File
@@ -2,7 +2,7 @@
English | [中文](README.zh.md)
One kind of design doc lives here. An **Agent Note** records a decision or proposal that shapes this codebase — the *why* and *what we gave up*, the parts code and docs can't carry. This file is the front door and contract: where Agent Notes live, when to write one, and [the in-file format](#the-file-format).
One kind of design doc lives here. An **Agent Note** records a decision or proposal that shapes this codebase — the *why* and *what we gave up*, the parts code and docs can't carry. This file is the entry point and contract: where Agent Notes live, when to write one, and [the in-file format](#the-file-format).
## Layout and naming
@@ -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/2026-07-05-reconstructable-requests.md
2026-07-05-reconstructable-requests.md: c13e40b5b22e5d6fe19f6b5bd137db3a48350390
2026-07-05-reconstructable-requests.zh.md: 746bcd37dabada949873d394776c1ca43eff4ea2
2026-07-05-reconstructable-requests.md: d7b867d6e17c2dfe0e49b70bd0f5e7ff173fb572
2026-07-05-reconstructable-requests.zh.md: c41e5f89558a9c7b09ccd2bf4fd5b7d9a6cde419
@@ -14,7 +14,7 @@ The reference shape for the happy path is MiniCode's `LLMClient`: a stateful con
### The principle
**Model-visible ⟺ logged.** Anything that reaches a model request must be recorded in the session log. The checkable consequence: **every conversation request the loop sends is a pure function of the session log** — anyone holding the log reconstructs it byte-for-byte. Scope, stated precisely: the guarantee covers the loop-built `GenerateOptions`; provider wire bytes follow from it because both adapters' serialization is a pure per-message function at a pinned code version; direct one-shots (compaction's summarize call) log their envelope scalars (`compact/summary.{provider, model, maxTokens}`) and their input is deterministic code over the logged region — reconstructable from log + code, outside the invariant because only the loop marks request ownership.
**Model-visible ⟺ durably referenced.** Anything that reaches a model request must be reconstructable from the session log and the immutable content-addressed objects it references. The checkable consequence: anyone holding the log, its referenced attachment objects, and the pinned code version reconstructs every loop request byte-for-byte. Text-only `GenerateOptions` remain a pure function of the log; image-bearing requests additionally resolve `ImageAttachmentRef` bytes through `ctx.attachments` during adapter serialization, where digest and recorded metadata verification make the object lookup deterministic and fail loud on missing or corrupt data. Direct one-shots (compaction's summarize call) log their envelope scalars (`compact/summary.{provider, model, maxTokens}`), and their input is deterministic code over the logged region plus those referenced objects — outside the invariant because only the loop marks request ownership.
Prefix-cache stability is corollary #1, not the headline: an append-only log projected by a per-node pure function yields requests that are append-extensions of their predecessors whenever the header is unchanged — stability is emergent, not managed. Byte-exact audit/replay is corollary #2; resume and fork with *attributable* drift is corollary #3.
@@ -14,7 +14,7 @@ Status: implemented
### 原则
**模型可见 ⟺ 已记录** 凡到达模型请求的内容都必须记录在会话日志中。可检查的推论:**循环发出的每个对话请求都是会话日志的纯函数**——任何人持有日志即可逐字节重建请求。精确的范围声明:该保证覆盖循环构建的 `GenerateOptions`;提供方协议格式(wire format)字节由此推导而来,因为两个适配器的序列化在固定代码版本下都是逐消息的纯函数;直接的一次性调用(压缩的 summarize 调用)记录其信封标量(`compact/summary.{provider, model, maxTokens}`),其输入是对日志区域的确定性代码运算——可从日志加代码重建,因为只有循环会标记请求归属,所以它们不在不变式内。
**模型可见 ⟺ 已持久引用** 凡到达模型请求的内容都必须能从会话日志及其引用的不可变内容寻址对象中重建。可检查的推论:任何人持有日志、日志引用的附件对象和固定代码版本,即可逐字节重建循环的每个请求。纯文本 `GenerateOptions` 仍是日志的纯函数;含图片请求还会在适配器序列化期间通过 `ctx.attachments` 解析 `ImageAttachmentRef` 字节,其中对内容摘要及已记录元数据的校验使对象查找具有确定性,并在数据缺失或损坏时明确失败。直接的一次性调用(压缩的 summarize 调用)记录其信封标量(`compact/summary.{provider, model, maxTokens}`),其输入是对日志区域及这些引用对象的确定性代码运算——由于只有循环会标记请求归属,因此它们不在不变式内。
前缀缓存稳定性是推论 #1,而非标题:一个仅追加的日志经逐节点纯函数投影,在 header 不变时自然产出前一请求的追加扩展——稳定性是涌现的,不是管理出来的。字节精确的审计/回放是推论 #2;带*可归因*漂移的恢复与 fork 是推论 #3
@@ -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/2026-07-15-llm-model-catalog-and-acp-selection.md
2026-07-15-llm-model-catalog-and-acp-selection.md: 77f8e379e2b07ecf4e67fa7197752543cfedd6dd
2026-07-15-llm-model-catalog-and-acp-selection.zh.md: ce4a04a66e345834bc2b16b743be89dc7a0b9424
2026-07-15-llm-model-catalog-and-acp-selection.md: bfd17c73b01319c10d5dc03333b3c726db5d6f33
2026-07-15-llm-model-catalog-and-acp-selection.zh.md: aeddada5591bb2da2c0861acc368516eff148172
@@ -26,17 +26,17 @@ Catalog membership is advisory. It drives selectors and diagnostics but never ch
`dsh-llm-pi-ai` maps the configured provider's installed `getModels(provider)` entries into the neutral catalog. Its existing request-time catalog lookup remains authoritative and still rejects unknown models with `UNKNOWN_MODEL`. `dsh-llm-deepseek` accepts an optional `models` config containing display entries, defaulting to `deepseek-v4-flash` named `DeepSeek-V4-Flash` and `deepseek-v4-pro` named `DeepSeek-V4-Pro`. An explicit list replaces those defaults and an empty list disables discovery. The entries improve selector UX for known public or private models, while every unlisted model id continues to pass through unchanged.
### Per-session selection in the front door
### Per-session selection in the front end
A selection is owned by the front door that offers it (today the TUI `/model` selector), never by `LlmService` or `AgentOptions`: those are deployment-wide or creation-wide objects, and mutating them would couple concurrent sessions. Each opaque choice carries the full provider/model pair, because the same model id may appear under multiple routes.
A selection is owned by the front end that offers it (today the TUI `/model` selector), never by `LlmService` or `AgentOptions`: those are deployment-wide or creation-wide objects, and mutating them would couple concurrent sessions. Each opaque choice carries the full provider/model pair, because the same model id may appear under multiple routes.
The ACP automation transport is not a catalog consumer. Its deployment config supplies one optional provider/model target for newly created agents, and it advertises no model selector or configuration-option interface.
### Prompt/request consistency and durability
`installModelSelection` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-door-owned selection. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched.
`installModelSelection` (in `dsh-agent`) installs scoped `system-prompt/assemble` and `agent/request` listeners for a front-end-owned selection. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched.
The request header remains the durable source of truth. When a selection is actually used, the existing full `request/header` snapshot records it, and a front door initializes its selection from the folded last request header before falling back to creation options. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state.
The request header remains the durable source of truth. When a selection is actually used, the existing full `request/header` snapshot records it, and a front end initializes its selection from the folded last request header before falling back to creation options. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state.
## Alternatives considered
@@ -26,17 +26,17 @@ ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多
`dsh-llm-pi-ai` 将已配置提供方的安装目录 `getModels(provider)` 映射为中立目录。其现有请求时目录查询仍是权威依据,未知模型仍以 `UNKNOWN_MODEL` 失败。`dsh-llm-deepseek` 接受可选的 `models` 配置作为展示条目,默认包含名为 `DeepSeek-V4-Flash``deepseek-v4-flash` 和名为 `DeepSeek-V4-Pro``deepseek-v4-pro`。显式列表会替换这些默认值,空列表则关闭发现。这些条目改善已知公开或私有模型的选择体验,而所有未列出的模型 ID 仍会原样透传。
### 前内的会话级选择
### 前内的会话级选择
选择由提供它的前拥有(今天是 TUI 的 `/model` 选择器),而不由 `LlmService``AgentOptions` 拥有:它们是部署级或创建级对象,改动它们会把并发会话耦合在一起。每个不透明选项都携带完整的提供方/模型对,因为同一模型 ID 可能出现在多个路由下。
选择由提供它的前拥有(今天是 TUI 的 `/model` 选择器),而不由 `LlmService``AgentOptions` 拥有:它们是部署级或创建级对象,改动它们会把并发会话耦合在一起。每个不透明选项都携带完整的提供方/模型对,因为同一模型 ID 可能出现在多个路由下。
ACP 自动化传输层不是目录消费方。它通过部署配置为新创建的 agent 提供一个可选的提供方/模型目标,不展示模型选择器或配置选项接口。
### 提示词/请求一致性与持久化
`installModelSelection`(位于 `dsh-agent`)为前拥有的选择安装 agent 作用域的 `system-prompt/assemble``agent/request` 监听器。提示词组装在每个步骤对所选组合做一次快照,在下游提示词监听器之后覆写组装出的 `provider``model` 变量;请求监听器在下游请求监听器之后应用同一快照。因此,发生在异步组装期间的选择会从下一个步骤生效,而不会让提示词文本与路由分裂。其他调用配置字段保持不变。
`installModelSelection`(位于 `dsh-agent`)为前拥有的选择安装 agent 作用域的 `system-prompt/assemble``agent/request` 监听器。提示词组装在每个步骤对所选组合做一次快照,在下游提示词监听器之后覆写组装出的 `provider``model` 变量;请求监听器在下游请求监听器之后应用同一快照。因此,发生在异步组装期间的选择会从下一个步骤生效,而不会让提示词文本与路由分裂。其他调用配置字段保持不变。
请求头仍是持久化的真源。当某个选择真正被使用时,现有的完整 `request/header` 快照会记录它;前先从折叠后的最后一个请求头初始化其选择,然后才回退到创建选项。从未被请求使用的选择有意只保留在内存中,因为它从未成为模型可见状态。
请求头仍是持久化的真源。当某个选择真正被使用时,现有的完整 `request/header` 快照会记录它;前先从折叠后的最后一个请求头初始化其选择,然后才回退到创建选项。从未被请求使用的选择有意只保留在内存中,因为它从未成为模型可见状态。
## 考虑过的替代方案
@@ -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/2026-07-19-gui-layering-and-rpc-protocol.md
2026-07-19-gui-layering-and-rpc-protocol.md: 7997a682c8745f7b3d0a9721acfa9355603f9b2e
2026-07-19-gui-layering-and-rpc-protocol.zh.md: cb36b5cb725128e1c5067e5e69e52aa851668e52
2026-07-19-gui-layering-and-rpc-protocol.md: 705b0df5feb5fedaae4d198aed71758b54586e93
2026-07-19-gui-layering-and-rpc-protocol.zh.md: b28b08b4b9da058e01af62e610d4e226d794151f
@@ -31,7 +31,7 @@ Directories layer as follows:
- **Fetch-arrival plugin packages** (`ui-layout`, `ui-sidebar`, `ui-conversation`, `ui-trajectory`): dual-entry — the root index is the node half (an empty `apply`, existing so the host Loader governs lifecycle and the web plugin registry discovers the package.json `dshClient` declaration); the implementation lives under `src/client/`, shipped as the `./client` subpath (a tsdown closure-factory bundle). Cross-plugin consumption of `/client` is type-only; value cooperation goes through cordis services.
- `apps/` holds the externally exported application shapes, assembled from Client / Host mixtures.
- `apps/web` (`dsh-frontend`) is the vite application: a thin `main.ts` over the shell surface exported by `dsh-client-web`.
- `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = Host + webserver + the built `dsh-frontend` dist; `dsh run` = [a direct core Agent/Session front door](2026-08-09-headless-direct-core-front-door.md), with zero Host, HTTP, or browser layer.
- `apps/cli` (`@deepseek-ai/dsh`) dispatches shapes: `dsh web` = Host + webserver + the built `dsh-frontend` dist; `dsh run` = [a direct core Agent/Session entry point](2026-08-09-headless-direct-core-entry-point.md), with zero Host, HTTP, or browser layer.
- A future Electron shape reuses the same web client packages over an IPC fetch carrier.
```
@@ -79,7 +79,7 @@ Packages under `packages/host/*` and `packages/client/*` **must carry the direct
2. **Write an assembly module under `apps/`**: `startHost()` + a client subclass + the shape's private signal/print/exit semantics; a mixture never becomes a package — assembly is written in the app.
3. **Import `dsh-host-webserver` only if you need HTTP carriage**, otherwise zero ports.
The two existing shapes preserve the boundary: the Web shape mounts Host, carrier, and browser composition, while `dsh run` mounts a direct core runner with zero Host, HTTP, or ports. ACP-class protocol bridges do not follow the client-carrier checklist: they expose core to the external ecosystem, mount via `ctx.plugin(front-door plugin)` directly, and wear no fetch.
The two existing shapes preserve the boundary: the Web shape mounts Host, carrier, and browser composition, while `dsh run` mounts a direct core runner with zero Host, HTTP, or ports. ACP-class protocol bridges do not follow the client-carrier checklist: they expose core to the external ecosystem, mount via `ctx.plugin(entry-point plugin)` directly, and wear no fetch.
## Message protocol
@@ -242,7 +242,7 @@ Every client shape consumes one contract: adding a unary method is a five-step m
|---|---|
| Packaging by "product shape" (a web family, an electron family) | What shapes share is host/client capability, not the shape itself; capability-provider layering means a new shape needs zero new packages |
| A package per mixture (e.g. a standalone headless package) | A mixture has exactly one consumer (its own app); packaging it is ownerless abstraction, while assembly in the app is readable and disposable |
| Consuming clients connecting to ctx directly (skipping the apiproxy layer) | Client shapes require wire validation, observability, and multi-client consistency. Direct headless is a local front door with no client boundary and uses the public Agent/Session seams rather than a client command plane |
| Consuming clients connecting to ctx directly (skipping the apiproxy layer) | Client shapes require wire validation, observability, and multi-client consistency. Direct headless is a local entry point with no client boundary and uses the public Agent/Session seams rather than a client command plane |
| webserver depending on runtime (saving the handler injection) | Structural-typing injection keeps webserver reusable by sidecars/tests with zero workspace deps; a package dependency would drag assembly knowledge into the carrier layer |
| Package names without the group prefix (continuing dsh-<tail>) | `dsh-runtime`/`dsh-web-ui` lose their belonging in the flat npm namespace; the cost is one explicit paths entry per package |
| Reusing the in-repo JSON-RPC 2.0 (dsh-jsonrpc) | Numeric error codes degrade to a single fallback code, contracts get aligned by hand in two copies, and naming drifts without a convention |
@@ -29,7 +29,7 @@ Status: implemented
- **fetch 到达插件包**`ui-layout``ui-sidebar``ui-conversation``ui-trajectory`):双入口——根入口是 node 半边(空 `apply`,其存在是为了让 host Loader 管辖生命周期、让 web 插件注册表发现 package.json 的 `dshClient` 声明);实现住在 `src/client/` 下,经 `./client` 子路径发布(tsdown 闭包工厂 bundle)。跨插件消费 `/client` 只限类型;值层面的协作走 cordis 服务。
- `apps/` 作为对外导出的应用形态入口,可以由 Client / Host 混合组装。
- `apps/web``dsh-frontend`)是 vite 应用:`dsh-client-web` 导出的壳表面之上的一层薄 `main.ts`
- `apps/cli``@deepseek-ai/dsh`)做形态分发:`dsh web` = Host + webserver + 构建出的 `dsh-frontend` dist`dsh run` = [直接使用核心 AgentSession 的前门](2026-08-09-headless-direct-core-front-door.md),不含 Host、HTTP 或浏览器层。
- `apps/cli``@deepseek-ai/dsh`)做形态分发:`dsh web` = Host + webserver + 构建出的 `dsh-frontend` dist`dsh run` = [直接使用核心 AgentSession 的入口](2026-08-09-headless-direct-core-entry-point.md),不含 Host、HTTP 或浏览器层。
- 将来的 Electron 形态经由 IPC fetch 载体复用同一套 web client 包。
```
@@ -77,7 +77,7 @@ TypeScript 以 solution 根引用的**两个聚合 program** 检查(`tsconfig.
2. **在 `apps/` 下写拼装模块**`startHost()` + 客户端子类 + 该形态私有的信号/打印/退出语义;混合体不建包,拼装写在 app 里。
3. **需要 HTTP 承载才 import `dsh-host-webserver`**,否则零端口。
现有两种形态保持这一边界:Web 形态挂载 Host、载体与浏览器组合,而 `dsh run` 挂载直接使用核心服务的 runner,不包含 Host、HTTP 或端口。ACP 类协议桥不遵循 client 载体清单:它把 core 暴露给外部生态,直接通过 `ctx.plugin(前门插件)` 挂载,不套 fetch。
现有两种形态保持这一边界:Web 形态挂载 Host、载体与浏览器组合,而 `dsh run` 挂载直接使用核心服务的 runner,不包含 Host、HTTP 或端口。ACP 类协议桥不遵循 client 载体清单:它把 core 暴露给外部生态,直接通过 `ctx.plugin(入口插件)` 挂载,不套 fetch。
## 消息协议
@@ -240,7 +240,7 @@ export type ResponseValue<K> =
|---|---|
| 按「产品形态」分包(web 一族、electron 一族) | 形态间共享的是 host/client 两侧能力而非形态本身;能力支持方分层让新形态零新包 |
| 混合体建包(如 headless 独立包) | 混合体只有一个消费者(它自己的 app),建包是无主抽象;拼装写在 app 里可读可弃 |
| 消费型 client 直连 ctx(省 apiproxy 一层) | client 形态需要 wire 校验、观测与多 client 一致性。直接 headless 是没有 client 边界的本地前门,使用公开的 AgentSession seam,而不是 client 命令面 |
| 消费型 client 直连 ctx(省 apiproxy 一层) | client 形态需要 wire 校验、观测与多 client 一致性。直接 headless 是没有 client 边界的本地入口,使用公开的 AgentSession seam,而不是 client 命令面 |
| webserver 依赖 runtime(省 handler 注入) | 结构 typing 注入让 webserver 可被 sidecar/测试复用且零 workspace 依赖;包依赖会把装配知识拖进承载层 |
| 包名不带组前缀(沿用 dsh-<尾段> | `dsh-runtime`/`dsh-web-ui` 在扁平 npm 命名空间里失去归属信息;代价只是每包一条显式 paths |
| 复用仓内 JSON-RPC 2.0dsh-jsonrpc | 数字错误码退化成单码兜底、约定双份人肉对齐、命名无 convention 自然漂移 |
@@ -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/2026-07-24-web-config-tree-boot-and-transport-layering.md
2026-07-24-web-config-tree-boot-and-transport-layering.md: 496499a691dbca012e5e953cbb6eb1d0bf25b635
2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: c4bed7b730cf37e1d90750f5c93fbccb920ced21
2026-07-24-web-config-tree-boot-and-transport-layering.md: 9bf44e398da66ee286fc9bbc1496c002606d1606
2026-07-24-web-config-tree-boot-and-transport-layering.zh.md: 23d9bc790c792438cb699952ee802e1ffa89de88
@@ -16,23 +16,23 @@ English | [中文](2026-07-24-web-config-tree-boot-and-transport-layering.zh.md)
**Boot glue is a class pair.** `AppCLIEntry` (apps/cli) and `AppWebEntry` (the shell kernel) hold only what must exist independently of cordis: argv facts, the composed patch set, the parsed boot manifest, the module system instance, loading-page handles — everything else lives in plugins. `AppCLIEntry.run()` is three stages: layered env (ambient > cwd `.env` > `$DSH_HOME/.env`, closing the defect above) → patch composition → Loader include boot plus the activation audit. `AppWebEntry.run()` mirrors it browser-side: parse `window.__DSH_BOOT__` into a `BootManifest` (two views: npm-package rows for the module table, cordis-plugin rows for entry composition; malformed wire throws), build the module system, render the loading page, prefetch the `immediately` tier in parallel with Context/Loader setup, **await the prefetch before creating entries** (materialization is `tree.import`'s synchronous require, unprotected by fiber inject waiting; cross-package require edges such as i18n → runtime/client need every immediately-tier factory registered first — an empirically found 1025% boot race otherwise), adopt the modules entry, create the graph rows, settle, sweep.
**Config sources have one declaration place each.** Bundle yml values are engineering defaults, Settings sections are writable user preferences, CLI flags address their owning launcher rows, and env values enter through yml `!!js` expressions. Patches replace a row's config wholesale. The resolved frontend `distIndex` uses that patch channel as an assembly fact. The transport-independent provider/model default belongs to `ctx.agentDefaultModel`; the [direct headless front door](2026-08-09-headless-direct-core-front-door.md) and the Web gateway consume the same state.
**Config sources have one declaration place each.** Bundle yml values are engineering defaults, Settings sections are writable user preferences, CLI flags address their owning launcher rows, and env values enter through yml `!!js` expressions. Patches replace a row's config wholesale. The resolved frontend `distIndex` uses that patch channel as an assembly fact. The transport-independent provider/model default belongs to `ctx.agentDefaultModel`; the [direct headless entry point](2026-08-09-headless-direct-core-entry-point.md) and the Web gateway consume the same state.
**The transport splits five ways.** `dsh-host-apiproxy` is the gateway plugin (`api-gateway` row): it default-exports `ApiProxyService`, configures only `{workspaceRoot?}`, consumes the base layer's front-door-neutral `ctx.agentDefaultModel`, provides `ctx.apiProxy`, remains transport-agnostic, and registers no routes. `dsh-host-webserver` is a plain route-registration plugin: `HttpServerService` provides `ctx.httpServer` (`register(route) → disposer` with duplicate-pattern throw, `tapIndex` transforms applied in registration order, `port`), listens on activation, answers per-request failures with 400 and logging, and knows no harness concepts. The connection node half owns the `/api` binding from `ctx.apiProxy` through `toFetchHandler`. The modules node half (`ClientModuleHostService`, providing `ctx.clientModuleHost`) owns incremental package scanning, the bundle route, the index tap, and `onRebuilt`/`onGraphChanged` notification. The hmr node half owns dev reload through `fs.watchFile` membership and the `/plugins/events` SSE route.
**The transport splits five ways.** `dsh-host-apiproxy` is the gateway plugin (`api-gateway` row): it default-exports `ApiProxyService`, configures only `{nativeOpen?}`, consumes the base layer's entry-point-neutral `ctx.agentDefaultModel`, provides `ctx.apiProxy`, remains transport-agnostic, and registers no routes. `dsh-host-webserver` is a plain route-registration plugin: `HttpServerService` provides `ctx.httpServer` (`register(route) → disposer` with duplicate-pattern throw, `tapIndex` transforms applied in registration order, `port`), listens on activation, answers per-request failures with 400 and logging, and knows no harness concepts. The connection node half owns the `/api` binding from `ctx.apiProxy` through `toFetchHandler`. The modules node half (`ClientModuleHostService`, providing `ctx.clientModuleHost`) owns incremental package scanning, the bundle route, the index tap, and `onRebuilt`/`onGraphChanged` notification. The hmr node half owns dev reload through `fs.watchFile` membership and the `/plugins/events` SSE route.
**Package export discipline.** The modules package exposes exactly `.` (node half) and `./client` (the complete browser half: `ClientModuleSystem`, `parseBootManifest`, the adoption plugin face) — no bespoke subpaths; wire types re-export through the root for host-side consumers. The adoption handshake: the kernel writes the constructed instance to `window.__DSH_MODULES__` before cordis exists; the `./client` apply reads the slot (missing = loud throw) and provides `ctx.modules`.
## Consequences
- Recomposing a web deployment is a yml/patch edit; the retired pieces (`mountWebPlugins`, `CLIENT_PACKAGES`, `createHostWebPluginRegistry`, `startWebServer`, the webserver's graph/SSE/api knowledge) are deleted.
- [Headless is a direct core front door](2026-08-09-headless-direct-core-front-door.md): its shipped profile contains the shared base Agent capabilities and omits Host, HTTP, Web, and browser layers. The transport split in this note is the browser surface's contract.
- [Headless is a direct core entry point](2026-08-09-headless-direct-core-entry-point.md): its shipped profile contains the shared base Agent capabilities and omits Host, HTTP, Web, and browser layers. The transport split in this note is the browser surface's contract.
- A TypeScript pitfall worth remembering: a `declare module 'cordis'` augmentation in a file with **no cordis import** is demoted to a standalone module declaration and silently shatters the program-wide `Context` merge (`ctx.on`/`ctx.effect` vanish across the program). Anchor with `import type {} from 'cordis'`.
## Alternatives considered
| Rejected | One-line reason |
|---|---|
| Dedicated `dsh-host-profile` receiver package | User model state belongs to the Settings-backed `ctx.agentDefaultModel`; an extra Host receiver would duplicate ownership and exclude direct front doors |
| Dedicated `dsh-host-profile` receiver package | User model state belongs to the Settings-backed `ctx.agentDefaultModel`; an extra Host receiver would duplicate ownership and exclude direct entry points |
| Runtime `assembly` shim plugin providing an `apiHandler` service | Existed only because `createApiProxy` lived in runtime; moving it into apiproxy made the gateway self-hosting, and `toFetchHandler` is a pure function the binding side calls |
| Full-rescan + incremental scan coexisting | Two implementations, two semantics; the single per-package path covers the activation pass too |
| A bespoke `./impl` export on the modules package | Non-uniform export surface; the standard `./client` carries the whole browser half |
@@ -16,23 +16,23 @@ Status: implemented
**boot 胶水由两个类组成。** `AppCLIEntry`apps/cli)与 `AppWebEntry`(壳内核)只持有那些必须独立于 cordis、提前存在的东西:argv 事实、合成的 patch 集、解析出的 boot manifest(元数据清单)、模块系统实例、loading 页句柄——其余一律进插件。`AppCLIEntry.run()` 三段:分层 envambient > cwd `.env` > `$DSH_HOME/.env`,顺手关掉上述缺陷)→ patch 合成 → Loader include boot 加 activation audit。`AppWebEntry.run()` 在浏览器侧镜像它:把 `window.__DSH_BOOT__` 解析成 `BootManifest`(双视角:npm 包行给模块表、cordis 插件行给 entry 组合;畸形 wire 大声抛)、建模块系统、渲染 loading 页、immediately 层预取与 Context/Loader 准备并行、**create entry 之前等预取齐**(物化是 `tree.import` 的同步 require,不受 fiber inject 等待保护;i18n → runtime/client 这类跨包 require 边要求 immediately 层工厂全部注册完——否则有实测 10–25% 的 boot 竞态)、收编 modules entry、逐一创建图行、settle、sweep。
**每个配置源有唯一声明位置。** 组合包 yml 值是工程默认,Settings 分节是可写的用户偏好,CLI(命令行界面)flags 面向其归属的启动器配置行,env 值则通过 yml `!!js` 表达式进入。patch 会整体替换一行的 config。解析后的前端 `distIndex` 通过同一条 patch 通道作为组装事实传递。与传输无关的提供方/模型默认值归 `ctx.agentDefaultModel` 所有;[直接 headless 前门](2026-08-09-headless-direct-core-front-door.md)与 Web 网关消费同一份状态。
**每个配置源有唯一声明位置。** 组合包 yml 值是工程默认,Settings 分节是可写的用户偏好,CLI(命令行界面)flags 面向其归属的启动器配置行,env 值则通过 yml `!!js` 表达式进入。patch 会整体替换一行的 config。解析后的前端 `distIndex` 通过同一条 patch 通道作为组装事实传递。与传输无关的提供方/模型默认值归 `ctx.agentDefaultModel` 所有;[直接 headless 入口](2026-08-09-headless-direct-core-entry-point.md)与 Web 网关消费同一份状态。
**传输五分。** `dsh-host-apiproxy` 是网关插件(`api-gateway` 行):默认导出 `ApiProxyService`,只配置 `{workspaceRoot?}`,消费 base 层不偏向特定前门`ctx.agentDefaultModel`provide `ctx.apiProxy`,保持传输无关且不注册路由。`dsh-host-webserver` 是朴素的路由注册插件:`HttpServerService` provide `ctx.httpServer``register(route) → disposer`、重复 pattern 即抛、`tapIndex` 按注册序应用、`port`),激活即 listen,单请求失败时答 400 并记日志,且不认识任何 harness 概念。connection node 半拥有从 `ctx.apiProxy``toFetchHandler` 绑定到 `/api` 的逻辑。modules node 半(`ClientModuleHostService`provide `ctx.clientModuleHost`)拥有单包增量扫描、bundle 路由、index tap 与 `onRebuilt`/`onGraphChanged` 通知。HMR node 半通过 `fs.watchFile` membership 与 `/plugins/events` SSE 路由拥有开发期重载。
**传输五分。** `dsh-host-apiproxy` 是网关插件(`api-gateway` 行):默认导出 `ApiProxyService`,只配置 `{nativeOpen?}`,消费 base 层不偏向特定入口`ctx.agentDefaultModel`provide `ctx.apiProxy`,保持传输无关且不注册路由。`dsh-host-webserver` 是朴素的路由注册插件:`HttpServerService` provide `ctx.httpServer``register(route) → disposer`、重复 pattern 即抛、`tapIndex` 按注册序应用、`port`),激活即 listen,单请求失败时答 400 并记日志,且不认识任何 harness 概念。connection node 半拥有从 `ctx.apiProxy``toFetchHandler` 绑定到 `/api` 的逻辑。modules node 半(`ClientModuleHostService`provide `ctx.clientModuleHost`)拥有单包增量扫描、bundle 路由、index tap 与 `onRebuilt`/`onGraphChanged` 通知。HMR node 半通过 `fs.watchFile` membership 与 `/plugins/events` SSE 路由拥有开发期重载。
**包出口纪律。** modules 包只暴露 `.`node 半)与 `./client`(完整浏览器半:`ClientModuleSystem``parseBootManifest`、收编插件面)——不设专用子路径;wire 类型经根出口 re-export 给 host 侧消费方。收编握手:内核在 cordis 之前把建好的实例写入 `window.__DSH_MODULES__``./client` 的 apply 读取该槽位(缺少时显式抛错)并 provide `ctx.modules`
## 后果
- 重组一个 web 部署 = 改 yml/patch;退役件(`mountWebPlugins``CLIENT_PACKAGES``createHostWebPluginRegistry``startWebServer`、webserver 的图/SSE/api 知识)全部删除。
- [Headless 是直接 core 前门](2026-08-09-headless-direct-core-front-door.md):其随附 profile 包含共享的 base Agent 能力,并省去 Host、HTTP、Web 与浏览器层。本笔记的传输划分是浏览器 surface 的约定。
- [Headless 是直接 core 入口](2026-08-09-headless-direct-core-entry-point.md):其随附 profile 包含共享的 base Agent 能力,并省去 Host、HTTP、Web 与浏览器层。本笔记的传输划分是浏览器 surface 的约定。
- 一个值得记住的 TypeScript 坑:`declare module 'cordis'` augmentation 所在文件若**没有任何 cordis import**,会被降级成独立 module declaration,无声打散全程序的 `Context` merge`ctx.on`/`ctx.effect` 全程序消失)。用 `import type {} from 'cordis'` 锚定。
## 考虑过的替代方案
| 弃案 | 一行理由 |
|---|---|
| 专门的 `dsh-host-profile` 受体包 | 用户模型状态归 Settings 支撑的 `ctx.agentDefaultModel` 所有;额外的 Host 受体会重复归属,并排除直接前门 |
| 专门的 `dsh-host-profile` 受体包 | 用户模型状态归 Settings 支撑的 `ctx.agentDefaultModel` 所有;额外的 Host 受体会重复归属,并排除直接入口 |
| 运行时里的 `assembly` 垫层插件(provide `apiHandler` | 它的存在只因 `createApiProxy` 住运行时;本体迁入 apiproxy 后网关自持插件身份,且 `toFetchHandler` 是绑定方自己调的纯函数 |
| 全量重扫与增量扫描并存 | 两条实现两份语义;单包路径足以覆盖激活初扫 |
| modules 包特设 `./impl` 出口 | 出口面不统一;标准 `./client` 承载完整浏览器半 |
@@ -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/2026-08-05-profile-plugin-bundles.md
2026-08-05-profile-plugin-bundles.md: 8b5ab0c99282f6868fc3f70781e618af9a317c09
2026-08-05-profile-plugin-bundles.zh.md: 2a685d68b3de9210488e26f8e6dd93dfc07f956c
2026-08-05-profile-plugin-bundles.md: 2924b3cb445064fd47d82bcc94ec8d77ded5721b
2026-08-05-profile-plugin-bundles.zh.md: b2287034010bcac1048bb385b2266f1bc75921da
@@ -12,7 +12,7 @@ The `dsh` launcher hardcoded its compositions: `base.cordis.yml` + `web.cordis.y
Everything becomes a **profile**: a directory `$DSH_HOME/profiles/<name>` with a `package.json` (pnpm-managed out-of-tree plugin `dependencies` plus the profile manifest `dsh.profile` with its ordered `bundles` layer list) and a user `cordis.patch.yml`. A **bundle** is an npm package declaring `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }`; the two manifest kinds live under distinct `dsh.profile` / `dsh.bundle` keys so a package.json states which role it plays. The tree composes over an empty root by applying each bundle's patch in `dsh.profile.bundles` order, then the user layer, then `--patch` overlays, then flag patches — one `applyEntryPatches` call, identical for boot, flag derivation, and `--dump-config`.
The shipped bundles are `@deepseek-ai/dsh-base` (shared core rows), `@deepseek-ai/dsh-web-app` (browser Host rows and Web runtime glue), and `@deepseek-ai/dsh-headless` (a direct one-shot runner over base, without web-app). `dsh web` is the Web-flag alias for `--profile web`; `dsh run [--profile <name>] "task"` owns one-shot execution and defaults to the headless profile; generic `dsh --profile <name>` boots without a task. Patch overlays use `--patch`. `dsh plugin --profile <name> <args...>` is a thin pnpm forwarder that initializes the profile and reconciles `dsh.profile.bundles` with installed bundle declarations; a package without a bundle declaration remains a plain dependency. [Headless as a direct core front door](2026-08-09-headless-direct-core-front-door.md) owns the headless composition contract.
The shipped bundles are `@deepseek-ai/dsh-base` (shared core rows), `@deepseek-ai/dsh-web-app` (browser Host rows and Web runtime glue), and `@deepseek-ai/dsh-headless` (a direct one-shot runner over base, without web-app). `dsh web` is the Web-flag alias for `--profile web`; `dsh run [--profile <name>] "task"` owns one-shot execution and defaults to the headless profile; generic `dsh --profile <name>` boots without a task. Patch overlays use `--patch`. `dsh plugin --profile <name> <args...>` is a thin pnpm forwarder that initializes the profile and reconciles `dsh.profile.bundles` with installed bundle declarations; a package without a bundle declaration remains a plain dependency. [Headless as a direct core entry point](2026-08-09-headless-direct-core-entry-point.md) owns the headless composition contract.
The [`dsh run` command decision](../feature/2026-08-08-dsh-run-headless-command.md) owns the one-shot grammar; this note owns the profile composition it selects.
@@ -12,7 +12,7 @@ Status: implemented
一切都变成 **profile**:即目录 `$DSH_HOME/profiles/<name>`,其中包含一个 `package.json`pnpm 管理的树外插件 `dependencies`,加上 profile manifest(元数据清单)`dsh.profile` 及其有序的 `bundles` 层列表)和一份用户 `cordis.patch.yml`。**组合包**(bundle)是声明了 `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }` 的 npm 包;两种 manifest 分别位于互不相同的 `dsh.profile` / `dsh.bundle` 键下,因此一份 package.json 能说明自己扮演哪种角色。配置树在空的根之上组合:按 `dsh.profile.bundles` 顺序应用每个组合包的 patch,然后是用户层,然后是 `--patch` overlay,最后是 flag patch——全部收敛为一次 `applyEntryPatches` 调用,启动、flag 派生与 `--dump-config` 使用完全相同的路径。
随附的组合包是 `@deepseek-ai/dsh-base`(共享核心配置行)、`@deepseek-ai/dsh-web-app`(浏览器 Host 配置行与 Web 运行时粘合层)和 `@deepseek-ai/dsh-headless`(直接叠加在 base 上且不含 web-app 的一次性 runner)。`dsh web` 是携带 Web flag 家族的 `--profile web` 别名;`dsh run [--profile <name>] "task"` 负责一次性执行,默认使用 headless profile;通用的 `dsh --profile <name>` 启动 profile 而不携带任务。patch overlay 使用 `--patch``dsh plugin --profile <name> <args...>` 是一层薄薄的 pnpm 转发器,负责初始化 profile,并依据已安装包的组合包声明调和 `dsh.profile.bundles`;没有组合包声明的包保持为普通依赖。[Headless 作为直接 core 前门](2026-08-09-headless-direct-core-front-door.md)负责 headless 组合约定。
随附的组合包是 `@deepseek-ai/dsh-base`(共享核心配置行)、`@deepseek-ai/dsh-web-app`(浏览器 Host 配置行与 Web 运行时粘合层)和 `@deepseek-ai/dsh-headless`(直接叠加在 base 上且不含 web-app 的一次性 runner)。`dsh web` 是携带 Web flag 家族的 `--profile web` 别名;`dsh run [--profile <name>] "task"` 负责一次性执行,默认使用 headless profile;通用的 `dsh --profile <name>` 启动 profile 而不携带任务。patch overlay 使用 `--patch``dsh plugin --profile <name> <args...>` 是一层薄薄的 pnpm 转发器,负责初始化 profile,并依据已安装包的组合包声明调和 `dsh.profile.bundles`;没有组合包声明的包保持为普通依赖。[Headless 作为直接 core 入口](2026-08-09-headless-direct-core-entry-point.md)负责 headless 组合约定。
[`dsh run` 命令决策](../feature/2026-08-08-dsh-run-headless-command.md)负责一次性语法;本 Agent Note 负责该语法所选择的 profile 组合。
@@ -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/architecture/2026-08-09-headless-direct-core-entry-point.md
2026-08-09-headless-direct-core-entry-point.md: 49afe2993de7302adbedcdf9e8e2347d6424ee2a
2026-08-09-headless-direct-core-entry-point.zh.md: 73c1cbe5ac777025f63f46751b1d5ccebbfe9676
@@ -1,22 +1,22 @@
# Agent Note: headless is a direct core front door
# Agent Note: headless is a direct core entry point
Status: implemented
English | [中文](2026-08-09-headless-direct-core-front-door.zh.md)
English | [中文](2026-08-09-headless-direct-core-entry-point.zh.md)
## Problem
The `headless` product contract is one local task with final assistant text on stdout, a success-sensitive exit code, empty stderr on success, and no listening port. A composition containing Workspace Host services, ApiProxy, HTTP, the Web runtime, or browser plugins contradicts that contract and makes local completion depend on an unrelated transport tree.
The direct front door still needs the same deployment model state as Web-created Agents. A separate provider/model default would give one deployment two answers, while deriving completion before the Agent and Session persistence are quiescent permits stdout and the exit code to observe incomplete state.
The direct entry point still needs the same deployment model state as Web-created Agents. A separate provider/model default would give one deployment two answers, while deriving completion before the Agent and Session persistence are quiescent permits stdout and the exit code to observe incomplete state.
## Decision
The shipped `headless` profile contains `dsh-base` and `dsh-headless`. The headless bundle supplies its persona and tool mode, disables HMR, mounts the Code Mode worker explicitly, and inserts `headless-runner`. Its tree contains no `@deepseek-ai/dsh-host-*` package, ApiProxy, HTTP server, Web runtime, or browser client. Code Mode and Session persistence are one-shot Agent capabilities independent of Web presentation.
`headless-runner` is a direct core front door. After Loader settlement, it reads `ctx.agentDefaultModel.currentSelection()`, creates a fresh persisted Agent through `ctx.agents.create`, installs that `ModelSelection` in the Agent scope, waits for startup quiescence, anchors the Session sequence, submits one ordinary user message, and waits for quiescence again. It awaits `ctx.sessions.flush`, folds its durable event interval for the last non-empty assistant text and final `turn/end` reason, writes the text plus one newline to stdout, and requests bounded launcher shutdown with exit 0 exactly when the reason is `completed`. A terminal `error` reason writes its durable code and message to stderr; unexpected driver failures also use stderr and exit 1.
`headless-runner` is a direct core entry point. After Loader settlement, it reads `ctx.agentDefaultModel.currentSelection()`, creates a fresh persisted Agent through `ctx.agents.create`, installs that `ModelSelection` in the Agent scope, waits for startup quiescence, anchors the Session sequence, submits one ordinary user message, and waits for quiescence again. It awaits `ctx.sessions.flush`, folds its durable event interval for the last non-empty assistant text and final `turn/end` reason, writes the text plus one newline to stdout, and requests bounded launcher shutdown with exit 0 exactly when the reason is `completed`. A terminal `error` reason writes its durable code and message to stderr; unexpected driver failures also use stderr and exit 1.
`@deepseek-ai/dsh-agent-default-model` owns the transport-independent default used for an Agent without a session-local selection. `AgentDefaultModelService` provides `ctx.agentDefaultModel` and registers the `agent-default-model` Settings section. Composition config supplies `{provider, model}`; user settings may also supply `reasoningEffort`. `currentSelection()` returns the live complete selection and `saveSelection()` writes it as a complete section, so a selection without an effort clears any stored effort. `dsh-base` supplies the composition entry. Direct and ApiProxy front doors consume this service; ApiProxy alone owns session-local precedence, model validation, and persistence of accepted Web selections.
`@deepseek-ai/dsh-agent-default-model` owns the transport-independent default used for an Agent without a session-local selection. `AgentDefaultModelService` provides `ctx.agentDefaultModel` and registers the `agent-default-model` Settings section. Composition config supplies `{provider, model}`; user settings may also supply `reasoningEffort`. `currentSelection()` returns the live complete selection and `saveSelection()` writes it as a complete section, so a selection without an effort clears any stored effort. `dsh-base` supplies the composition entry. Direct and ApiProxy entry points consume this service; ApiProxy alone owns session-local precedence, model validation, and persistence of accepted Web selections.
`loadProfile` recognizes the exact installation-owned headless tuple (`dsh-base`, `dsh-web-app`, `dsh-headless`) and normalizes it to the shipped headless template while preserving every other manifest field. Extra, missing, or reordered bundle lists are user-owned and remain untouched.
@@ -31,7 +31,7 @@ Package tests use the real Session store and Agent registry around a scripted Ag
| Alternative | Contract mismatch |
|---|---|
| Keep `dsh-web-app` but suppress its observation line | The process still opens a port and carries the Host, Web, and browser trees. |
| Build a Host-only one-shot bundle around ApiProxy | ApiProxy is a client protocol gateway; a local one-shot front door has no client boundary. |
| Build a Host-only one-shot bundle around ApiProxy | ApiProxy is a client protocol gateway; a local one-shot entry point has no client boundary. |
| Use `InProcessApiClient` for product-level protocol coverage | Product execution would depend on an unrelated protocol solely to exercise that protocol. |
| Give headless a separate provider/model config | Direct and Web creation would have independent defaults and persistence. |
| Omit Code Mode and Session persistence | Both capabilities belong to one-shot Agent execution rather than Web presentation. |
@@ -2,13 +2,13 @@
Status: implemented
[English](2026-08-09-headless-direct-core-front-door.md) | 中文
[English](2026-08-09-headless-direct-core-entry-point.md) | 中文
## 问题
`headless` 的产品约定是一个本地任务:最终 assistant 文本写入 stdout,退出状态反映成功与否,成功时 stderr 为空,并且不打开监听端口。包含 Workspace Host 服务、ApiProxy、HTTP、Web 运行时或浏览器插件的组合违背这一约定,也使本地完成状态依赖无关的传输树。
直接前门仍需要与 Web 所创建 Agent 相同的部署模型状态。独立的提供方/模型默认值会让同一部署产生两种答案,而在 Agent 与会话持久化完全停稳之前推导完成状态,会让 stdout 与退出状态观察到不完整状态。
直接入口仍需要与 Web 所创建 Agent 相同的部署模型状态。独立的提供方/模型默认值会让同一部署产生两种答案,而在 Agent 与会话持久化完全停稳之前推导完成状态,会让 stdout 与退出状态观察到不完整状态。
## 决策
@@ -16,7 +16,7 @@ Status: implemented
`headless-runner` 是直接使用核心服务的入口。Loader 完全加载后,它读取 `ctx.agentDefaultModel.currentSelection()`,通过 `ctx.agents.create` 创建一个新的持久化 Agent,在 Agent 作用域中安装该 `ModelSelection`,等待启动工作完全停稳,锚定会话事件序号,提交一条普通用户消息,再次等待完全停稳。随后,它等待 `ctx.sessions.flush`,折叠自身持有的持久事件区间,以取得最后一条非空 assistant 文本和最终 `turn/end` 结束原因,将文本连同一个换行写入 stdout,并且仅在结束原因为 `completed` 时请求启动器以退出状态 0 有界关闭。结束原因为 `error` 时,其持久化错误码与消息写入 stderr;驱动器的意外失败也写入 stderr 并以 1 退出。
`@deepseek-ai/dsh-agent-default-model` 拥有与传输无关的默认值,供没有会话级选择的 Agent 使用。`AgentDefaultModelService` 提供 `ctx.agentDefaultModel` 并注册 `agent-default-model` Settings 分节。组合配置提供 `{provider, model}`,用户设置还可以提供 `reasoningEffort``currentSelection()` 返回当前的完整选择,`saveSelection()` 则写入完整分节,因此不含强度的选择会清除已存强度。`dsh-base` 提供组合条目。直接前门与 ApiProxy 前门均消费该服务;只有 ApiProxy 负责会话级优先级、模型校验与已接受 Web 选择的持久化。
`@deepseek-ai/dsh-agent-default-model` 拥有与传输无关的默认值,供没有会话级选择的 Agent 使用。`AgentDefaultModelService` 提供 `ctx.agentDefaultModel` 并注册 `agent-default-model` Settings 分节。组合配置提供 `{provider, model}`,用户设置还可以提供 `reasoningEffort``currentSelection()` 返回当前的完整选择,`saveSelection()` 则写入完整分节,因此不含强度的选择会清除已存强度。`dsh-base` 提供组合条目。直接入口与 ApiProxy 入口均消费该服务;只有 ApiProxy 负责会话级优先级、模型校验与已接受 Web 选择的持久化。
`loadProfile` 识别安装过程拥有的精确 headless 元组(`dsh-base``dsh-web-app``dsh-headless`),将其规范化为随附的 headless 模板,并保留 manifest(元数据清单)的其他所有字段。带额外项、缺少项或顺序不同的组合包列表归用户所有,保持不变。
@@ -31,7 +31,7 @@ Status: implemented
| 替代方案 | 约定不匹配之处 |
|---|---|
| 保留 `dsh-web-app`,但隐藏观察行 | 进程仍会打开端口并携带 Host、Web 与浏览器插件树。 |
| 围绕 ApiProxy 构建纯 Host 一次性组合包 | ApiProxy 是客户端协议网关,而本地一次性前门没有客户端边界。 |
| 围绕 ApiProxy 构建纯 Host 一次性组合包 | ApiProxy 是客户端协议网关,而本地一次性入口没有客户端边界。 |
| 使用 `InProcessApiClient` 实现产品级协议覆盖 | 产品执行会仅为测试无关协议而依赖该协议。 |
| 为 headless 单独提供提供方/模型配置 | 直接创建与 Web 创建会拥有彼此独立的默认值和持久化。 |
| 省略 Code Mode 与会话持久化 | 两项能力都属于一次性 Agent 执行,而不是 Web 呈现。 |
@@ -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/bug-fix/2026-07-20-error-cause-chain-diagnostics.md
2026-07-20-error-cause-chain-diagnostics.md: 32716b5a68b3b73bded47633eca95995cdbfc586
2026-07-20-error-cause-chain-diagnostics.zh.md: 9911c32b6d68c1f5569a1fceadb65e23c6586594
2026-07-20-error-cause-chain-diagnostics.md: b80dd08d79a57738a6eef2f8638b0336ca80d4bf
2026-07-20-error-cause-chain-diagnostics.zh.md: 914e983d7ea81eef8bca8fd5aa3791f2f44d4080
@@ -9,7 +9,7 @@ English | [中文](2026-07-20-error-cause-chain-diagnostics.zh.md)
A TUI run against an unreachable DeepSeek endpoint failed with the single notice `fetch failed` and no further detail. Two independent gaps produced that dead end:
1. undici's `fetch` wraps every transport failure (DNS, refused connection, TLS, proxy) in a bare `TypeError: fetch failed` whose actionable detail — `ECONNREFUSED`, `bad port`, the Happy Eyeballs AggregateError — lives on `error.cause`. Every diagnostic boundary in the harness rendered only `error.message` (or `String(error)`, which is equivalent for Errors), so the wrapper masked the diagnosis in the TUI notice, the durable `turn/end` reason, and every logger line.
2. The readline front door (`dsh-stdio`) rendered no failure reason at all: a `turn/end` with `reason.kind === 'error'` printed nothing but the next `> ` prompt, so the same failure in `demo:repl` was pure silence.
2. The readline entry point (`dsh-stdio`) rendered no failure reason at all: a `turn/end` with `reason.kind === 'error'` printed nothing but the next `> ` prompt, so the same failure in `demo:repl` was pure silence.
## Decision
@@ -9,7 +9,7 @@ Status: implemented
TUI 连接不可达的 DeepSeek 端点时,失败只显示一条 `fetch failed` 通知,没有任何进一步细节。两个独立缺口共同造成了这个死胡同:
1. undici 的 `fetch` 把所有传输层失败(DNS、连接被拒、TLS、代理)包装成裸的 `TypeError: fetch failed`,可操作的细节——`ECONNREFUSED``bad port`、Happy Eyeballs 的 AggregateError——都在 `error.cause` 上。harness 里的每个诊断边界都只渲染 `error.message`(或对 Error 等价的 `String(error)`),于是包装层在 TUI 通知、持久化的 `turn/end` reason 和所有日志行里都掩盖了诊断信息。
2. readline 前门`dsh-stdio`)完全不渲染失败原因:`reason.kind === 'error'``turn/end` 只打印下一个 `> ` 提示符,同样的失败在 `demo:repl` 里就是纯粹的沉默。
2. readline 入口`dsh-stdio`)完全不渲染失败原因:`reason.kind === 'error'``turn/end` 只打印下一个 `> ` 提示符,同样的失败在 `demo:repl` 里就是纯粹的沉默。
## 决策
@@ -1,6 +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/architecture/2026-08-09-headless-direct-core-front-door.md
2026-08-09-headless-direct-core-front-door.md: f4604329a9276448a0021bb749b09e8c1b82e3c1
2026-08-09-headless-direct-core-front-door.zh.md: aaa1289894bf3c69b39aa863493dffdc3437ad01
# pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-29-atomic-web-image-admission.md
2026-07-29-atomic-web-image-admission.md: c09d376f101a41994df3a10c22c06da4e59f06f6
2026-07-29-atomic-web-image-admission.zh.md: 8785f7489b0c433cba43a1747533b1d38aada3d3
@@ -0,0 +1,29 @@
# Agent Note: Atomic Web image admission
Status: implemented
English | [中文](2026-07-29-atomic-web-image-admission.zh.md)
## Problem
Image prompt admission and `session.selectModel` each read session modality state across asynchronous model and attachment lookups. Without one ordering boundary, an image prompt could validate an image-capable target while a concurrent selection installed a text-only target, or selection could miss a prompt after inbox dequeue but before its durable message event. Scanning the immutable event log avoided the second race but permanently blocked a text-only selection even after compaction removed the image from current model history.
## Decision
Each live Web agent has one private promise chain shared by image-bearing prompt admission and model selection. A failed operation settles its caller normally and leaves the chain usable. Text-only prompts bypass the chain because they cannot change the modality constraint.
The pending-publication set records a queued occurrence at dequeue and a steering occurrence already at enqueue (steering items never enter the queued UI mirror), and retains each until its matching `user/message` or `steering/message` event publishes. If admission ends without publishing, the transition to idle retires the entries; inbox discard retires the listed work, and session disposal retires every remaining entry. Model selection checks that set, the queued UI mirror, and `Session.deriveMessages()`, which is the current model-visible history after compaction.
Provider adapters remain the final enforcement boundary. The host ordering only prevents its mutable route and pending image state from contradicting each other before request assembly.
## Alternatives considered
**Scan every immutable session event.** This catches published images but treats compacted-away content as permanently model-visible, preventing a valid later switch to a text-only route.
**Retire the pending mirror at inbox dequeue.** Dequeue precedes the durable message append and leaves the exact interval in which model selection can miss both pending and published state.
**Serialize every prompt and session mutation.** Text-only prompts and unrelated session operations cannot introduce an image requirement. A broader lock would add latency and ownership without closing another modality race.
## Consequences
An image prompt and a concurrent model selection have deterministic order, and a text-only target cannot strand an image that has been admitted but not yet published. Selection may wait for an in-flight image admission, while unrelated prompts retain their existing concurrency. Compaction can make a text-only target valid once no pending or derived image remains.
@@ -0,0 +1,29 @@
# Agent Note: Web 图片准入的原子性
Status: implemented
[English](2026-07-29-atomic-web-image-admission.md) | 中文
## 问题
包含图片的提示词准入与 `session.selectModel` 都会在跨越异步模型查询与附件查询的过程中读取会话模态状态。如果没有统一的顺序边界,包含图片的提示词可能在支持图片的目标上通过校验,并发的选择操作却设置了纯文本目标;选择操作也可能在提示词已从 inbox 出队、但其持久消息事件尚未发布时漏掉该提示词。扫描不可变事件日志可以避免第二种竞态,但即使压缩(compaction)已经从当前模型历史中移除图片,仍会永久阻止选择纯文本目标。
## 决策
每个活跃 Web agent(智能体)都有一条私有 promise 链,由包含图片的提示词准入与模型选择共享。操作失败会照常传递给调用方,且不会使该链失效。纯文本提示词绕过该链,因为它们不会改变模态约束。
待发布集合会在排队条目出队时记录它,而 steering 条目在入队时即被记录(steering 条目从不进入排队 UI 镜像),并各自保留到匹配的 `user/message``steering/message` 事件发布。若准入结束时未发布事件,转为空闲状态会移除这些条目;inbox 丢弃会移除列出的工作项,会话 dispose(资源释放)则会移除所有剩余条目。模型选择会检查该集合、排队 UI 镜像以及 `Session.deriveMessages()`;后者表示压缩后模型当前可见的历史。
提供方适配器仍是最终的强制检查边界。宿主的顺序控制仅用于避免其可变路由与待发布图片状态在请求组装前彼此矛盾。
## 曾考虑的替代方案
**扫描每个不可变会话事件。** 这能捕获已发布的图片,但会把经压缩移除的内容视为永久对模型可见,从而阻止之后合法切换到纯文本路由。
**在 inbox 出队时退役待处理镜像。** 出队早于持久消息追加,因此恰好会留下一个时间区间,让模型选择既看不到待处理状态,也看不到已发布状态。
**序列化每个提示词和会话变更。** 纯文本提示词和无关的会话操作无法引入图片要求。更宽的锁会增加延迟与所有权复杂度,却不会再消除任何模态竞态。
## 后果
包含图片的提示词准入与并发模型选择之间具有确定的先后顺序,纯文本目标无法使已获准入但尚未发布的图片搁浅。模型选择可能等待正在进行的图片准入完成,而无关提示词仍按现有方式并发处理。当没有图片等待发布,且派生历史经过压缩后也不再含图片时,纯文本目标可以变得有效。
@@ -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/bug-fix/2026-07-31-same-basename-workspace-adoption.md
2026-07-31-same-basename-workspace-adoption.md: ed53804ea64df0d61db16e579c3d65af803dbb97
2026-07-31-same-basename-workspace-adoption.zh.md: 82cfb7d90afca28f8e666742a758fda0202909f3
2026-07-31-same-basename-workspace-adoption.md: 1192558632fdc8bd732ea59f0eca5051f49f5d2c
2026-07-31-same-basename-workspace-adoption.zh.md: 9c1f1ffd221936e24300b223ad395e1f44552810
@@ -14,7 +14,7 @@ A Workspace is identified by its stable id and canonical directory path, while i
The Host's `workspace.create({ path })` adoption route inherits that rule. The Workspace manager, picker, grouping tree, selection, rename, deletion, and Session creation continue to use `WorkspaceId`, so equal labels neither merge records nor redirect an operation. The sidebar hover card exposes each canonical path when the labels need disambiguation.
Explicit naming remains stricter. `workspace.create({ name })` and `workspace.rename` continue to reject a title already registered, as described by [manual Workspace naming](../feature/2026-07-25-session-list-browsing-and-manual-order.md). This prevents a user from deliberately introducing another ambiguous label while accepting collisions imposed by existing directory names. The path-adoption rule supersedes only the title-conflict clauses in the [Workspace product flow](../feature/2026-07-25-workspace-ui-product-flow.md) and [native directory picker](../feature/2026-07-27-native-workspace-directory-picker.md).
Explicit naming remains stricter. `workspace.rename` continues to reject a title already registered, as described by [manual Workspace naming](../feature/2026-07-25-session-list-browsing-and-manual-order.md). This prevents a user from deliberately introducing another ambiguous label while accepting collisions imposed by existing directory names. The path-adoption rule supersedes only the title-conflict clauses in the [Workspace product flow](../feature/2026-07-25-workspace-ui-product-flow.md) and [native directory picker](../feature/2026-07-27-native-workspace-directory-picker.md).
The durable schema does not change: Workspace records already store id, path, and title independently, bootstrap can derive equal basenames, and startup validates duplicate paths rather than titles.
@@ -30,7 +30,7 @@ Workspace registry and Host API tests create two real directories under differen
**Use the full path as every Workspace title.** This removes the collision but makes the primary navigation label unnecessarily long. The full path remains available in the hover detail while the concise basename stays useful.
**Permit collisions from explicit rename and create-by-name operations too.** The registry supports that state, but those operations intentionally ask the user to choose a display name. Retaining their conflict response preserves the existing naming guard without blocking filesystem-selected paths.
**Permit collisions from the explicit rename operation too.** The registry supports that state, but rename intentionally asks the user to choose a display name. Retaining its conflict response preserves the existing naming guard without blocking filesystem-selected paths.
## Consequences
@@ -14,7 +14,7 @@ Workspace 的身份由其稳定 id 和规范目录路径确定,标题则是可
Host 的 `workspace.create({ path })` 接纳入口沿用该规则。Workspace 管理器、选择器、分组树、选择、重命名、删除和 Session 创建仍使用 `WorkspaceId`,因此相同标签既不会合并记录,也不会把操作指向其他记录。需要区分相同标签时,侧边栏悬停详情卡会显示各自的规范路径。
显式命名仍采用更严格的规则。`workspace.create({ name })``workspace.rename` 仍会拒绝已注册的标题,具体见[手动 Workspace 命名](../feature/2026-07-25-session-list-browsing-and-manual-order.md)。这既防止用户主动引入另一个难以区分的标签,又允许既有目录名称造成的重名。路径接纳规则仅取代 [Workspace 产品流](../feature/2026-07-25-workspace-ui-product-flow.md)和[原生目录选择器](../feature/2026-07-27-native-workspace-directory-picker.md)中的标题冲突条款。
显式命名仍采用更严格的规则。`workspace.rename` 仍会拒绝已注册的标题,具体见[手动 Workspace 命名](../feature/2026-07-25-session-list-browsing-and-manual-order.md)。这既防止用户主动引入另一个难以区分的标签,又允许既有目录名称造成的重名。路径接纳规则仅取代 [Workspace 产品流](../feature/2026-07-25-workspace-ui-product-flow.md)和[原生目录选择器](../feature/2026-07-27-native-workspace-directory-picker.md)中的标题冲突条款。
持久化 schema 未变:Workspace 记录本就分别存储 id、path 和 title,引导初始化可以派生出相同的 basename,启动校验检查的是重复路径而非重复标题。
@@ -30,7 +30,7 @@ Workspace 注册表与 Host API 测试会在不同父目录下创建两个末级
**将完整路径用作每个 Workspace 的标题。** 这会消除冲突,却使主导航标签不必要地过长。完整路径仍可在悬停详情中查看,而简洁的 basename 仍有价值。
**也允许显式重命名和按名称创建操作产生重名。** 注册表支持这种状态,但这些操作本就是明确要求用户选择显示名称。保留冲突响应可维持现有命名防护,同时不阻止从文件系统选取的路径。
**也允许显式重命名操作产生重名。** 注册表支持这种状态,但操作本就是明确要求用户选择显示名称。保留冲突响应可维持现有命名防护,同时不阻止从文件系统选取的路径。
## 后果
@@ -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/bug-fix/2026-08-10-session-row-identity-covers-the-preset.md
2026-08-10-session-row-identity-covers-the-preset.md: 7a89dcb4e4ae292a06a1743842d2e9cf6bd96282
2026-08-10-session-row-identity-covers-the-preset.zh.md: 7ffa3423818bcc867c942651540db1975737e073
@@ -0,0 +1,37 @@
# Agent Note: The session-row identity guard covers the preset
Status: implemented
English | [中文](2026-08-10-session-row-identity-covers-the-preset.zh.md)
## Problem
`SessionManager.buildListSnapshot` memoizes list rows by value: a wire refresh mints all-new summary objects, so an entry equal to the cached one is replaced by the cached instance, and every `SessionListItem` memo downstream keeps hitting. The stated contract is "reuse the cached object when every field matches"; the comparison enumerated the fields by hand and did not enumerate `agentPreset`.
A confirmed preset switch moves exactly that one field. `noteAgentPreset` upserts it and `applyMutation` merges it in — the merge deliberately does not take the mutation's `updatedAt`, so a switched row differs from its cached twin in the preset and in nothing else. The guard therefore judged the row unchanged and served the stale instance, permanently: the manager's own summaries said `minimal` while every reader of the projected snapshot went on reading `standard`.
The hero chip is one of those readers, and it compares the pick against that row before sending anything. Switching back to the preset the session was created under looked to it like "already on that preset", so it dropped the stage and sent no RPC at all — the chip label moved while the composition did not. A session could be switched away from its creation-time preset once and never back.
## Decision
The identity guard compares `agentPreset` alongside the other summary fields, which is what "every field matches" already claimed. Nothing else changes: the memoization, the merge, and the chip's no-op check all stay as they are, because each is correct once the row it reads is.
## Alternatives considered
**Have the chip re-read the host instead of the list row.** It would route around the stale row, but the row is also what the session header labels itself from, so the staleness would survive in the surface where it is most visible — and any future reader of `SessionSummary.agentPreset` would inherit the same trap.
**Drop the entry-identity memoization and rebuild rows every snapshot.** It removes the whole class of missing-field bugs, at the cost the memo exists to avoid: a wire refresh mints new objects for every row, so each refresh would re-render the entire session list.
**Compare summaries structurally rather than field by field.** A generic deep comparison cannot be added blind: the row carries `projectionValues`, whose reference identity is the deliberate signal that the projection store republished, and folding it into a value comparison would either re-render on every projection tick or mask a real one.
## Consequences
Every field a session row carries now participates in row identity, so a surface reading `SessionSummary.agentPreset` sees a switch as soon as the host confirms it — the header label included. The guard is still a hand-written enumeration, so a field added to `SessionSummary` later must be added here too; the `sessions-service` projection test names the failure mode for the next such field rather than only pinning this one.
## Testing
`sessions-service.spec.ts` feeds a blank row, notes a switch, and asserts the projected snapshot reports the new preset — it fails on the old guard because the row differs in nothing else. The `agent-preset-selection` web e2e switches down and back up, asserting the host honors the second switch and the `/` catalog returns with it; without this fix the second switch never reaches the host at all.
## Related
The same e2e covers [the catalog-invalidation fix](2026-08-10-slash-catalog-follows-preset-switch.md), which is what makes the menu follow either switch once the switch itself lands.
@@ -0,0 +1,37 @@
# Agent Note:会话行的标识判定纳入 preset
Status: implemented
[English](2026-08-10-session-row-identity-covers-the-preset.md) | 中文
## Problem
`SessionManager.buildListSnapshot` 按值对列表行做记忆化:一次 wire 刷新会铸造全新的 summary 对象,因此与缓存项相等的行会被替换为缓存实例,下游每一个 `SessionListItem` memo 才能持续命中。它声明的约定是「每个字段都相同就复用缓存对象」,而那段比较是手写枚举字段的,其中没有 `agentPreset`
一次已确认的 preset 切换恰好只移动这一个字段。`noteAgentPreset` 把它 upsert 进去,`applyMutation` 合并它——该合并有意不采用 mutation 的 `updatedAt`,因此切换后的行与它的缓存孪生只在 preset 上不同,别处一致。于是标识判定认为这一行没变,永久地提供了过期实例:manager 自己的 summaries 是 `minimal`,而所有读取投影快照的一方继续读到 `standard`
hero 上的 chip 正是其中一个读取方,而且它在发出任何请求之前会拿这次选择和那一行比较。切回会话创建时的那个 preset,在它看来就是「已经是这个 preset 了」,于是丢弃 stage、根本不发 RPC——chip 的标签变了,组成没变。一个会话可以从创建时的 preset 切走一次,然后再也切不回来。
## Decision
标识判定把 `agentPreset` 与其余 summary 字段一起比较,这本就是「每个字段都相同」所声称的内容。其他一概不动:记忆化、合并、chip 的 no-op 检查各自都是对的——只要它们读到的那一行是对的。
## Alternatives considered
**让 chip 改为直接读宿主,而不是读列表行。** 这样能绕开过期的行,但会话头部的标签同样以这一行为准,过期状态会在最显眼的界面里留下来;而且将来任何 `SessionSummary.agentPreset` 的读取方都会继承同一个陷阱。
**去掉行标识记忆化,每次快照都重建行。** 这能整类消除「漏字段」缺陷,代价却正是这个 memo 存在的理由:一次 wire 刷新会为每一行铸造新对象,于是每次刷新都要重渲染整个会话列表。
**改成结构化比较,而不是逐字段枚举。** 通用的深比较不能盲目加:行上带有 `projectionValues`,它的引用标识本身就是「投影 store 重新发布了」这一有意为之的信号,把它折进值比较,要么每个投影 tick 都重渲染,要么把一次真实变化掩盖掉。
## Consequences
会话行携带的每个字段现在都参与行标识,因此读取 `SessionSummary.agentPreset` 的界面会在宿主确认后立刻看到切换,会话头部标签也包含在内。该判定仍是手写枚举,所以将来给 `SessionSummary` 新增字段时必须同步加进来;`sessions-service` 的投影测试为下一个这样的字段点明了失效形态,而不只是钉住这一次。
## Testing
`sessions-service.spec.ts` 喂入一行空会话、记录一次切换,并断言投影快照报告的是新 preset——在旧判定下它会失败,因为这一行别处都没变。`agent-preset-selection` web e2e 先向下切再向上切,断言宿主认可第二次切换、`/` 目录随之回来;没有这次修复,第二次切换根本到不了宿主。
## Related
同一条 e2e 也覆盖[目录失效的修复](2026-08-10-slash-catalog-follows-preset-switch.md)——正是它让菜单在切换真正落地之后跟随任一方向的切换。
@@ -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/bug-fix/2026-08-10-slash-catalog-follows-preset-switch.md
2026-08-10-slash-catalog-follows-preset-switch.md: 85bd5b2134fd20c86fdeb13f3ce5b007449105b5
2026-08-10-slash-catalog-follows-preset-switch.zh.md: 97c8f08a7b3dfec7c17fbb00bef626e28505c500
@@ -0,0 +1,43 @@
# Agent Note: The slash catalog follows a blank session's preset switch
Status: implemented
English | [中文](2026-08-10-slash-catalog-follows-preset-switch.zh.md)
## Problem
Presets moved the rows that decide what a session's `/` menu contains. The Web composition disables host-plane `skill-local`, `tool-skill`, `plan-mode`, and `command-compact`; a preset supplies them, so which commands and skills exist is a property of the session's composition rather than of the deployment.
Both browser catalogs cache per session — `CommandDirectory` in `dsh-client-ui-command`, the single-flight fetch map in `dsh-client-ui-skill` — and the composer warms both at scope birth, under whatever preset the session was created with. The hero chip then lets the user recompose the still-blank session, and neither cache had an invalidation edge for that: `commands/changed` is registry-wide and `connection/reset` needs a reconnect. `agentPresets.recompose` re-parents the agent's scope onto a standing mount that may already exist, so it registers nothing and the registry-wide signal never fires for it.
The menu therefore kept serving the composition the session no longer ran. Switching down left `compact`, `plan`, and every project skill listed; switching up left the narrower catalog — the four host-plane rows and the client's own `model` contribution — with no skills at all, which is what the bug report described. The catalog only healed when an unrelated registry change or a reconnect happened to invalidate it.
## Decision
The switch's commit point is the logged `agent-preset/selected` event. The host stream frames it as `host/session-preset-changed { sessionId, agentPreset }`, the browser runtime bridges that frame to the typed `session/preset-changed` ctx event beside the registry-invalidation bridges it already owns, and each catalog owner drops its own entry for that session: `ui-command` soft-refreshes the key (the old snapshot keeps serving the open menu until the new one lands), `ui-skill` invalidates it (aborting an in-flight prewarm, so a warm racing the switch cannot publish the stale catalog).
The frame is per session and carries no catalog, only the preset id — which the manager folds into the session row, because the `agentPresets.select` echo reaches only the client that issued the switch and the row is what the session header labels itself from (and what the hero chip compares the next pick against).
Deriving the frame from the logged event rather than from the RPC handler's return keeps one authority for "this session's composition changed": every connected client observes the switch, not only the tab that issued it, and a client that is not the switcher never has to infer it from a registry signal that will not come.
## Alternatives considered
**Invalidate in the client's own `agentPresets.select` callback.** Smallest change, and the preset is locked after the first turn, so the hero chip is the only place a switch can originate. Rejected because the invalidation would then live in the surface that happens to issue the RPC rather than at the commit point: a second tab on the same blank session keeps a stale menu, and any future host-side recomposition has no signal at all.
**Derive the client event from the existing `session/event` mux frame.** The logged event already reaches every subscribed client, so no new wire type would be needed. Rejected on face separation: narrowing `event.type` to `agent-preset/selected` requires the `SessionEventMap` augmentation, and the only ways to load it in the Client program are a project reference to `dsh-agent-presets` — which drags the host `ctx.sessions` merge into a program that publishes its own — or a cast that defeats the discriminant.
**Reuse `host/commands-changed`.** It is the existing catalog-invalidation frame, but it is registry-wide, carries no session, and says nothing about skills; a client would repull every session's commands and still never refresh a skill catalog.
## Consequences
The wire gains one frame and the Client one typed event, and every catalog a preset decides now has one place to subscribe: a future per-session surface derived from the composition invalidates on the same signal instead of inventing another. The cost is that the frame is a second reader of a logged fact — the host stream must keep deriving it from `agent-preset/selected`, so a future switch path that recomposes without logging would go unannounced. `ui-command` stays soft (the open menu never blanks) while `ui-skill` drops its entry outright, because a skill catalog has no partial-serve mode; a menu opened inside the refetch window shows no skills for that instant rather than the wrong ones.
## Testing
`api-proxy-agent-preset.spec.ts` asserts the committed switch frames once with the session and its new preset; `wire-events.spec.ts` asserts the frame-to-event bridge; the `ui-command` and `ui-skill` specs assert that the event repulls the recomposed session and leaves every other session's cache serving. The `agent-preset-selection` web e2e seeds a project skill and, after the hero chip applies `minimal`, asserts the `/` menu drops `compact`, `plan`, and the skill while keeping the host-plane rows — the assembled-application evidence that the panel follows the composition.
That e2e also stopped reading its staged-pick assertion off the serialized session list: the seeded session records `minimal` too, so the substring answered before the switch had landed. It now addresses the live session by id.
## Related
Reaching the host on a SECOND switch is a separate defect with its own cause and fix: [the session-row identity guard](2026-08-10-session-row-identity-covers-the-preset.md). Until it landed, `agent-preset-selection.e2e.ts` could only exercise the first switch — the invalidation edge here is direction-blind, but the switch it reacts to has to happen.
@@ -0,0 +1,43 @@
# Agent Note:斜杠目录跟随空会话的 preset 切换
Status: implemented
[English](2026-08-10-slash-catalog-follows-preset-switch.md) | 中文
## Problem
preset 把决定 `/` 菜单内容的那些行搬走了。Web 组装禁用了宿主面的 `skill-local``tool-skill``plan-mode``command-compact`,改由 preset 提供,因此一个会话有哪些命令和技能,是它自身组成的属性,而不是部署的属性。
浏览器侧两份目录都按会话缓存——`dsh-client-ui-command``CommandDirectory``dsh-client-ui-skill` 的 single-flight 拉取表——并且 composer 在 scope 出生时就按会话创建时的 preset 预热了它们。随后 hero 上的 chip 允许用户重组这个仍为空的会话,而两份缓存都没有对应的失效边:`commands/changed` 是注册表级的,`connection/reset` 需要重连。`agentPresets.recompose` 只是把 agent 的 scope 重新挂接到一个可能已经存在的常驻挂载上,不产生任何注册,注册表级信号因此永远不会为它触发。
于是菜单继续提供会话已经不再运行的那套组成。向下切换后 `compact``plan` 和全部项目技能仍列在菜单里;向上切换后留在原地的是更窄的目录——四条宿主面行加客户端自己的 `model` 贡献——而且完全没有技能,这正是 bug 报告描述的现象。只有当某个无关的注册表变化或一次重连恰好使其失效时,目录才会自愈。
## Decision
这次切换的提交点是落账的 `agent-preset/selected` 事件。宿主流把它成帧为 `host/session-preset-changed { sessionId, agentPreset }`,浏览器运行时在它已经拥有的那组注册表失效桥接旁,把该帧桥接为类型化的 `session/preset-changed` ctx 事件,两份目录各自丢弃该会话的那一项:`ui-command` 软刷新该键(新快照落地前,旧快照继续服务已打开的菜单),`ui-skill` 让它失效(并中止在途的预热,使一次与切换赛跑的 warm 无法发布过期目录)。
该帧按会话粒度,不携带目录,只带 preset id——manager 会把它折进会话行,因为 `agentPresets.select` 的回执只会到达发起切换的那个客户端,而会话头部标签正是以这一行为准(hero chip 比较下一次选择时读的也是它)。
从落账事件而不是 RPC 处理器的返回值派生该帧,使「这个会话的组成变了」只有一个权威来源:每个已连接的客户端都能观察到这次切换,而不只是发起它的那个标签页;不是发起方的客户端也无需从一个根本不会到来的注册表信号里去推断。
## Alternatives considered
**在客户端自己的 `agentPresets.select` 回调里就地失效。** 改动最小,而且第一轮之后 preset 就锁定,hero 上的 chip 是切换唯一可能的发起处。否决理由是失效逻辑会落在恰好发起 RPC 的那个界面上,而不是提交点:同一个空会话在第二个标签页里仍是过期菜单,将来任何宿主侧的重组也完全没有信号。
**从既有的 `session/event` mux 帧派生客户端事件。** 落账事件本来就会送达每个已订阅的客户端,不需要新增协议类型。因面(face)分离而否决:把 `event.type` 收窄到 `agent-preset/selected` 需要 `SessionEventMap` 增补,而在 Client 程序里加载它只有两条路——引用 `dsh-agent-presets` 工程,那会把宿主的 `ctx.sessions` 合并拖进一个自己也发布同名服务的程序;或者用一次类型断言绕过判别式。
**复用 `host/commands-changed`。** 它是既有的目录失效帧,但它是注册表级的、不带会话、也与技能无关;客户端会把每个会话的命令都重拉一遍,却依然永远刷不新技能目录。
## Consequences
协议多了一个帧,Client 多了一个类型化事件,而每一份由 preset 决定的目录从此有了统一的订阅点:将来任何从组成派生的按会话界面,都在同一个信号上失效,而不必再发明一个。代价是该帧成为一项落账事实的第二个读者——宿主流必须持续从 `agent-preset/selected` 派生它,因此将来若出现一条不落账就重组的切换路径,它将无人宣告。`ui-command` 保持软失效(已打开的菜单不会变空),而 `ui-skill` 直接丢弃该项,因为技能目录没有「部分可服务」的状态;在重拉窗口内打开的菜单,那一瞬间显示的是没有技能,而不是错误的技能。
## Testing
`api-proxy-agent-preset.spec.ts` 断言已提交的切换恰好成帧一次,并带上会话与新 preset;`wire-events.spec.ts` 断言帧到事件的桥接;`ui-command``ui-skill` 的 spec 断言该事件只重拉被重组的会话,其他会话的缓存继续服务。`agent-preset-selection` web e2e 播种一个项目技能,并在 hero chip 应用 `minimal` 之后断言 `/` 菜单丢掉了 `compact``plan` 和该技能,同时保留宿主面的那几行——这是面板跟随组成的整装应用证据。
同一条 e2e 也不再从序列化后的会话列表里读它的 staged-pick 断言:被播种的会话同样记录着 `minimal`,子串匹配在切换落地之前就会通过。现在它按 id 寻址那个活跃会话。
## Related
第二次切换能否到达宿主是另一个缺陷,有各自的成因与修复:[会话行的标识判定](2026-08-10-session-row-identity-covers-the-preset.md)。在它落地之前,`agent-preset-selection.e2e.ts` 只能演练第一次切换——这里的失效边对方向无感,但它所响应的那次切换必须真的发生。
@@ -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/2026-06-24-workspace-context.md
2026-06-24-workspace-context.md: 53a580aee50752b7c6daeff5caa42ba6409c8885
2026-06-24-workspace-context.md: e7a3724847b9dc8cfad11e87b2c96a3ef442bcba
2026-06-24-workspace-context.zh.md: 39c3f52da10b7299301d10bd8b78330cbae8e19c
@@ -78,7 +78,7 @@ There is intentionally no watcher. Detection occurs at the next successful struc
## Consequences
Workspace guidance is isolated per session and shared by the demo front doors, Web Host, and every tool presentation mode. Initial, nested, and changed instructions are durable and replayable. The generic session/agent context contract carries typed source data through inbox-staged and durably entered user messages without flattening entries.
Workspace guidance is isolated per session and shared by the demo entry points, Web Host, and every tool presentation mode. Initial, nested, and changed instructions are durable and replayable. The generic session/agent context contract carries typed source data through inbox-staged and durably entered user messages without flattening entries.
Repository text remains untrusted input. Lower-authority user-role framing, explicit precedence language, and delimiter escaping reduce risk but do not eliminate prompt injection. Following a candidate symlink to its target widens that surface to off-tree content, so the permission and sandbox layers that confine `ctx.fs` to trusted roots are the boundary that treats workspace files as data rather than authority (the [instruction-symlink follow note](2026-07-21-follow-instruction-symlinks.md) owns the residual risk).
@@ -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/2026-07-16-harness-level-loop.md
2026-07-16-harness-level-loop.md: e84a5738a55988d3b968eac829d9daaf10d7e304
2026-07-16-harness-level-loop.zh.md: d7cda56d66d4456ac5c3c7d55bb238e85fcacbc5
2026-07-16-harness-level-loop.md: e5dd94fbf76e27f0843666f29622969635ef2fc3
2026-07-16-harness-level-loop.zh.md: 773b5ff1f4b07206d0d817c29774435ce24407b4
@@ -70,7 +70,7 @@ The human UX follows the compact Codex shape in the [public OpenAI Codex TUI dis
The model receives only `get_goal`, `create_goal`, and `update_goal`. It may create a goal when a direct human request clearly asks for substantial multi-round work, and it may infer that intent in any language. It must not turn routine one-turn work into a goal. Code requires a direct human message in the current live root-agent turn; semantic interpretation remains model judgment. An autonomous goal round may report `complete` or `blocked` for the exact current goal round but cannot edit, pause, resume, or replace the human objective.
TUI mounts the shared command registry and complete goal stack by default and exposes `/goal` through one producer. ACP mounts the goal domain, model tools, and same-session driver but deliberately omits the human command plane. Every effective registered command is discoverable and invocable through every composed command adapter; a plugin incompatible with an application omits its command producer from that composition rather than relying on registry-level surface masks. The UI-less agent spine is opt-in so one-shot callers do not silently become multi-round operations. The headless CLI and JSON-RPC front doors do not consume the command plane; ordinary human text can still authorize model goal tools when that stack is composed.
TUI mounts the shared command registry and complete goal stack by default and exposes `/goal` through one producer. ACP mounts the goal domain, model tools, and same-session driver but deliberately omits the human command plane. Every effective registered command is discoverable and invocable through every composed command adapter; a plugin incompatible with an application omits its command producer from that composition rather than relying on registry-level surface masks. The UI-less agent spine is opt-in so one-shot callers do not silently become multi-round operations. The headless CLI and JSON-RPC entry points do not consume the command plane; ordinary human text can still authorize model goal tools when that stack is composed.
### Fresh-agent Ralph execution
@@ -70,7 +70,7 @@ Goal Round 驱动器为每个特定的实时 agent 至多拥有一个待定预
模型只接收 `get_goal``create_goal``update_goal`。当直接人类请求清楚要求大量多 Round 工作时,模型可以创建目标,并且可以从任何语言推断该意图。它不得把日常单 Turn 工作变成目标。代码要求当前实时根 agent Turn 中有一条人类直接发送的消息;语义解释仍是模型判断。自治目标 Round 可以为确切的当前 Goal Round 报告 `complete``blocked`,但不能编辑、暂停、恢复或替换人类目标。
TUI 默认挂载共享命令注册表和完整目标栈,并通过一个生产方暴露 `/goal`。ACPAgent Client Protocol)挂载目标领域、模型工具和同会话驱动器,但有意省略人类命令平面。每条有效已注册命令都能被每个已组合的命令适配器发现和调用;若插件与某应用不兼容,该应用组合会省略其命令生产方,而不是依赖注册表层面的表面掩码。无 UI 的 agent 主干要求显式选择加入,以免单次调用方静默变成多 Round 操作。无头 CLI(命令行界面)与 JSON-RPC 前端不消费命令平面;挂载目标栈后,普通人类文本仍可授权模型目标工具。
TUI 默认挂载共享命令注册表和完整目标栈,并通过一个生产方暴露 `/goal`。ACPAgent Client Protocol)挂载目标领域、模型工具和同会话驱动器,但有意省略人类命令平面。每条有效已注册命令都能被每个已组合的命令适配器发现和调用;若插件与某应用不兼容,该应用组合会省略其命令生产方,而不是依赖注册表层面的表面掩码。无 UI 的 agent 主干要求显式选择加入,以免单次调用方静默变成多 Round 操作。无头 CLI(命令行界面)与 JSON-RPC 运行入口不消费命令平面;挂载目标栈后,普通人类文本仍可授权模型目标工具。
### 全新 agent Ralph 执行
@@ -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/2026-07-16-persistent-pty-sessions.md
2026-07-16-persistent-pty-sessions.md: f27d799574e61d92123c9ca4e31c5c2a9d3229b4
2026-07-16-persistent-pty-sessions.zh.md: 0c23619faf00794c2c4e7b3f85ef961faddd99e0
2026-07-16-persistent-pty-sessions.md: fb9cd06bade7bc357baa738f0d9dd03b7f5b7936
2026-07-16-persistent-pty-sessions.zh.md: 55a5848c1ab1e8c2cd3b29f2d4748ea4abbe088c
@@ -152,7 +152,7 @@ The package ships concise tool guidance explaining persistent state, owner isola
**Include TUI sequences and BEL handling.** Rejected. The source prototype treats those paths as timing-sensitive and still records unresolved alternate-screen and interaction failures. Line-oriented PTY use proves the core value without making those unverified behaviors foundational.
**Use an out-of-process daemon immediately.** Rejected for the initial in-process capability because current persistent front doors already keep a Cordis context alive. A daemon becomes justified by cross-process restoration or multi-client attachment, both deferred here.
**Use an out-of-process daemon immediately.** Rejected for the initial in-process capability because current long-lived entry points already keep a Cordis context alive. A daemon becomes justified by cross-process restoration or multi-client attachment, both deferred here.
## Verification
@@ -152,7 +152,7 @@ plugins:
**包含 TUI sequence 与 BEL 处理。**拒绝。源 prototype 将这些路径视为 timing-sensitive,且仍记录未解决的 alternate-screen 和交互失败。行式 PTY 已能证明核心价值,无需把未经验证的行为放进基础层。
**立即采用进程外 daemon。**初始的进程内功能不采用,因为当前持久 front door 已能维持 Cordis context。跨进程恢复或多客户端 attach 会让 daemon 变得合理,但两者都已推迟。
**立即采用进程外 daemon。**初始的进程内功能不采用,因为当前长驻的运行入口已能维持 Cordis context。跨进程恢复或多客户端 attach 会让 daemon 变得合理,但两者都已推迟。
## 验证
@@ -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/2026-07-19-human-goal-command.md
2026-07-19-human-goal-command.md: 5fdd80f7423b80e84e58f7379130ee59a2e8a723
2026-07-19-human-goal-command.zh.md: 89d29497abfc758ff8373d272aa8620ca1bcfcc2
2026-07-19-human-goal-command.md: d68e4025a4d37d07211f15ddfc6069bc7c637124
2026-07-19-human-goal-command.zh.md: dbda35c731ccdc7aff2d4213a3df8b78070319df
@@ -68,5 +68,5 @@ The producer suite uses the real command registry, goal service, agent registry,
- The portable command contract has no modal editor or confirmation interaction; inline edit and explicit clear are intentional until a general cross-surface interaction primitive exists.
- `/goal` does not accept a per-command round cap. Deployment config owns the default, and the authorized model tool can edit a cap after direct human instruction.
- TUI renders portable plain text rather than a continuously updated goal status widget. Reconnectable command output and adapter-specific status indicators are deferred.
- The ACP automation server, headless CLI, and JSON-RPC front doors do not consume the command registry.
- The ACP automation server, headless CLI, and JSON-RPC entry points do not consume the command registry.
- The command observes and mutates state but does not certify completion or blockers. Evaluator-backed certification remains deferred to a separate policy layer with an explicit authority and isolation contract.
@@ -68,5 +68,5 @@ TUI 应用包作出相反的产品选择。它默认让 `goals` 使用所有者
- 可移植命令约定没有模态编辑器或确认交互;在出现通用跨界面交互原语之前,行内编辑与明确清除是有意选择。
- `/goal` 不接受逐命令 Round 上限。部署配置拥有默认值;得到直接人类指示后,已授权模型工具可以编辑上限。
- TUI 渲染可移植纯文本,而不是持续更新的目标状态组件。可重连命令输出和适配器专用状态指示器予以延期。
- ACP 自动化服务器、无头 CLI 与 JSON-RPC 前端不消费命令注册表。
- ACP 自动化服务器、无头 CLI 与 JSON-RPC 运行入口不消费命令注册表。
- 该命令观察并改变状态,但不认证完成或阻塞。基于评估器的认证延期到具有明确权限与隔离约定的独立策略层。
@@ -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/2026-07-19-plugin-command-registration.md
2026-07-19-plugin-command-registration.md: c8f0f2772a41948e9eb257a16f40194518c568f9
2026-07-19-plugin-command-registration.zh.md: a8f7a3d1e7947aeb41344a72106cee55d249010c
2026-07-19-plugin-command-registration.md: 76feba84492bd6b245246a6f1fb1e8f68d555684
2026-07-19-plugin-command-registration.zh.md: e89cb79ba1e15dfefa527fe7bc37c09c3449f5b4
@@ -12,7 +12,7 @@ A shared mechanism must remain a UI concern rather than a model tool or agent-lo
## Decision
`@deepseek-ai/dsh-commands` in `packages/interaction/commands/` is the product command registry. The TUI app bundle mounts it beside its consuming front door; the [automation-only ACP app](../simplification/2026-07-23-acp-automation-only-protocol.md) and the executor-less, UI-less agent spine omit it. TUI injects the service, while command producers depend only on the registry and any domain they operate.
`@deepseek-ai/dsh-commands` in `packages/interaction/commands/` is the product command registry. The TUI app bundle mounts it beside its consuming front end; the [automation-only ACP app](../simplification/2026-07-23-acp-automation-only-protocol.md) and the executor-less, UI-less agent spine omit it. TUI injects the service, while command producers depend only on the registry and any domain they operate.
### Registry contract
@@ -50,7 +50,7 @@ TUI tests exercise all migrated built-ins, live plugin discovery, help/autocompl
- **Keep adapter-local switches** — rejected because optional plugins cannot contribute discovery and behavior without editing the TUI.
- **Represent human commands as model tools** — rejected because discovery and direct invocation are human UI behavior; routing through the model adds latency, token cost, and reinterpretation.
- **Put the registry in the core agent spine** — rejected because UI-less front doors do not consume it, while TUI can compose it explicitly.
- **Put the registry in the core agent spine** — rejected because UI-less entry points do not consume it, while TUI can compose it explicitly.
- **Make `dsh-agent-loop` inject commands** — rejected because the loop does not execute or discover human commands. Agent-scoped producers declare the UI dependency in a child plugin instead.
- **Attach adapter masks to each definition** — rejected because support is a composition fact, not command-domain state. Every composed adapter exposes a registered command; an incompatible plugin omits registration in that deployment.
- **Send unknown slash input to the model** — rejected because typoed or unavailable direct actions must fail predictably rather than change execution planes.
@@ -68,4 +68,4 @@ TUI tests exercise all migrated built-ins, live plugin discovery, help/autocompl
- Input metadata is limited to an unstructured text hint. Typed forms, argument schemas, and completion providers remain command-owned or require a later registry or consumer extension.
- Generic command output is live-only and is not reconstructed after TUI restart.
- Registry cancellation stops awaiting immediately, but external work stops only when a handler cooperates with its signal.
- The ACP automation server, headless CLI, and JSON-RPC SDK front doors do not expose the command plane; only TUI consumes it.
- The ACP automation server, headless CLI, and JSON-RPC SDK entry points do not expose the command plane; only TUI consumes it.
@@ -12,7 +12,7 @@ TUI 拥有斜杠命令。如果命令名、帮助文本、自动补全、分派
## 决策
位于 `packages/interaction/commands/``@deepseek-ai/dsh-commands` 是产品命令注册表。TUI 应用 bundle(组合包)把它挂载在消费该服务的入口旁;[仅面向自动化的 ACPAgent Client Protocol)应用](../simplification/2026-07-23-acp-automation-only-protocol.md)和无执行器、无 UI 的智能体 spine(主干)都省略该服务。TUI 注入该服务,命令生产者只依赖注册表及其操作的领域。
位于 `packages/interaction/commands/``@deepseek-ai/dsh-commands` 是产品命令注册表。TUI 应用 bundle(组合包)把它挂载在消费该服务的前端旁;[仅面向自动化的 ACPAgent Client Protocol)应用](../simplification/2026-07-23-acp-automation-only-protocol.md)和无执行器、无 UI 的智能体 spine(主干)都省略该服务。TUI 注入该服务,命令生产者只依赖注册表及其操作的领域。
### 注册表约定
@@ -50,7 +50,7 @@ TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与
- **保留适配器本地 switch**——不予采纳,因为可选插件无法贡献发现与行为,除非修改 TUI。
- **把人类命令表示为模型工具**——不予采纳,因为发现与直接调用属于人类 UI 行为;经由模型路由会增加延迟、token 成本和重新解释。
- **把注册表放入核心智能体主干**——不予采纳,因为无 UI 前端不消费它,而 TUI 可以显式组合它。
- **把注册表放入核心智能体主干**——不予采纳,因为无 UI 运行入口不消费它,而 TUI 可以显式组合它。
- **让 `dsh-agent-loop` 注入 commands**——不予采纳,因为循环不执行也不发现人类命令。智能体作用域生产者改为在子插件中声明 UI 依赖。
- **为每个定义附加适配器掩码**——不予采纳,因为支持能力是组合事实,而不是命令领域状态。每个已组合适配器都暴露已注册命令;不兼容插件不会在该部署中注册。
- **把未知斜杠输入发送给模型**——不予采纳,因为输入错误或不可用的直接操作必须可预测地失败,而不能改变执行平面。
@@ -68,4 +68,4 @@ TUI 测试覆盖全部迁移后的内置命令、实时插件发现、帮助与
- 输入元数据仅限非结构化文本提示。类型化表单、参数模式和补全提供器仍由命令拥有,或需要后续注册表或消费方扩展。
- 通用命令输出仅实时存在,TUI 重启后不会重建。
- 注册表取消会立即停止等待,但外部工作只有在处理器配合信号时才会停止。
- ACP 自动化服务器、无头 CLI 与 JSON-RPC SDK 前端不暴露命令平面;只有 TUI 消费它。
- ACP 自动化服务器、无头 CLI 与 JSON-RPC SDK 运行入口不暴露命令平面;只有 TUI 消费它。
@@ -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/2026-07-21-local-instruction-overlay.md
2026-07-21-local-instruction-overlay.md: 3c7b2141b0515b5e667be4add6ad765e26c88cd8
2026-07-21-local-instruction-overlay.md: fb5f916d426595a80bbbaa4192e4a3975b922b8a
2026-07-21-local-instruction-overlay.zh.md: c97ed04607f497d829da0e904c248836252c73f7
@@ -26,7 +26,7 @@ The base and local candidates in one directory must stay independent across base
**Keep it opt-in through `instructionFileCandidates`.** Rejected: one directory has a single winner, so a `.local.` name added to that list shadows the base file rather than supplementing it. The packages guidance to keep opt-ins out of shipped defaults is outweighed here by strong prior art and the user-facing expectation that `.local.` files are always read.
**Default at the product `cordis.yml` level instead of the plugin schema.** Rejected: it would enable `.local.` only for whichever front door remembered to opt in, splitting behavior across TUI/ACP/headless and duplicating a value that belongs beside the existing candidate default.
**Default at the product `cordis.yml` level instead of the plugin schema.** Rejected: it would enable `.local.` only for whichever entry point remembered to opt in, splitting behavior across TUI/ACP/headless and duplicating a value that belongs beside the existing candidate default.
**Reuse the bare directory as the scope key for base and local files.** Rejected: base and local files in one directory would collide in every scope-keyed map, so a change to one would suppress or overwrite the other. A distinct scope key per candidate keeps them independent without widening the persisted metadata shape.
@@ -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/2026-07-22-web-multimodal-image-input-and-durable-attachments.md
2026-07-22-web-multimodal-image-input-and-durable-attachments.md: 2a3925d8b779fed7f8b3330d079fdb3059685fd5
2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md: be478ece73039201a820d804435610faea4cb3fe
@@ -0,0 +1,214 @@
# Agent Note: Web multimodal image input and durable attachments
Status: implemented
English | [中文](2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md)
## Problem
Before this change, the Web composer accepted only text: `InputBar` received a string draft, `ConversationService.send()` created text content, and the host forwarded that content to the agent. Users could not paste an image, inspect it before sending, submit an image-only prompt, or recover sent images from history.
This is not only a composer gap. Core needs a durable image content block, providers need explicit modality handling, and the session log must reconstruct everything visible to a model. [The previous image-block removal](../../implemented/simplification/2026-07-04-drop-image-content-block.md) rejected a partial design that could silently lose or flatten images. A browser object URL, local path, provider URL, or base64 payload cannot be canonical session content.
The [Web client architecture](../../implemented/architecture/2026-07-19-gui-web-client-architecture.md) keeps components pure and per-session composer state in `ctx.conversation`; the [GUI layering and RPC protocol](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md) makes durable events the source of truth for both live rendering and history replay. Image intake, persistence, provider conversion, and rendering therefore need one explicit lifecycle.
Peer products converge on an attachment rail above the editor, but their storage choices differ. Codex-style paths such as `/var/folders/.../codex-clipboard-*.png` are reasonable intake staging locations, not durable message identities: the operating system may delete them, another host cannot read them, and a resumed session cannot rely on them.
## Decision
Pasted or dropped raster images are the Web composer's first consumer of a durable attachment capability. Unsent files remain temporary client-owned draft state. The host validates and durably commits every accepted user image before appending its message event. A provider adapter that produces structured image output must durably commit the output before appending its assistant block. Canonical user and assistant content contains only role-neutral `ImageBlock` references.
Version one supports PNG, JPEG, WebP, and GIF paste and drag-and-drop, image-only or mixed prompts, historical user and assistant image rendering, and original-image preview on double-click. File picking, generic files, PDF, audio, video, image copying, and a custom context menu remain separate follow-ups.
### Product behavior
- Pasting or dropping one or more supported images adds ordered thumbnails above the textarea without inserting placeholder text. Dragging files over the composer highlights the drop target.
- The same resident `InputBar` renders the rail in both blank-session Hero and active-session layouts. The rail is hidden when empty and scrolls horizontally instead of widening the composer.
- Each approximately 72-by-72-pixel thumbnail has a remove action and opens its original draft image on double-click.
- A prompt may contain text and images or images only. Pure text paste remains native browser behavior; mixed clipboard content inserts its text normally while adding its files to the rail, and file-only paste prevents default browser handling. File drops on the composer always prevent browser navigation and report unsupported files locally.
- A failed send restores the complete text and image draft without clobbering text or images added while the request was in flight. Removal, successful send, session-scope disposal, rendered-history disposal, and application disposal revoke the object URLs they own.
- Historical user and assistant images use one `MessageImage` control. Inline images preserve intrinsic aspect ratio, do not upscale, and stay within a 240-by-240-pixel box.
- Double-clicking a message image opens the stored original in a viewport-bounded modal. Escape, the close control, and backdrop activation close it and restore focus.
- Version one does not override the browser context menu and provides no explicit image-copy action.
### Storage lifecycle and ownership
The persistence boundary is message acceptance, not paste:
| State | Allowed representation | Durability and ordering |
| --- | --- | --- |
| Unsent user draft | Browser `File` plus object URL; a native client may use an OS temporary file such as `/var/...` | Temporary and client-owned. It may disappear on reload or process exit and never appears in a session event. |
| Accepted user image | Immutable object below `DSH_HOME` plus `ImageAttachmentRef` | The host commits every image before `agent.send()` or `agent.steer()` can append the owning user event. |
| Structured model image output | Immutable object below `DSH_HOME` plus `ImageAttachmentRef` | The provider adapter commits the bytes before it emits a completed image block or assistant message event. Temporary URLs, paths, and base64 are forbidden in the event. |
Each session's `InputMachine` state keeps the ordered runtime-only attachment identifiers alongside the live draft. The framework-owned chat store receives only the draft's plain-text persistence mirror, while `ConversationService` owns the corresponding browser-only `File` and object-URL registry:
```ts
import type { Branded } from '@deepseek-ai/dsh-brand'
type DraftAttachmentId = Branded<'DraftAttachmentId'>
interface ChatStoreState {
selection: object | null
draft: string
view: string | null
}
interface InputState {
draft: string
imageIds: readonly DraftAttachmentId[]
}
interface ComposerAttachment {
kind: 'image'
id: DraftAttachmentId
file: File
previewUrl: string
}
```
This split uses the session provide channel's input hook and actions as the single subscription path for live composer state while keeping non-serializable browser objects out of persisted JSON. Only the plain-text draft mirror uses `localStorage`; attachment identifiers, browser `File` objects, and object URLs remain scoped to the live session input shell. Unsent images therefore do not survive reload or session-scope disposal. A Workspace switch moves a mixed text-and-image draft only when the destination shell accepts the complete image batch; refusal leaves both parts with the source. A native client may stage input in an OS temporary directory, but it must treat that path exactly like the browser object URL: delete it when no longer needed and copy the bytes into the durable store before message acceptance.
The local attachment backend resolves an explicit `dshHome`, then `$DSH_HOME`, then `~/.dsh`. It stores content-addressed objects below `$DSH_HOME/attachments/v1/objects/<prefix>/<sha256>` with owner-only directory and file permissions. On each process's first save for one home, it creates that home and synchronizes every ancestor entry to the filesystem root; existence is not treated as durability because another process may still be between `mkdir` and parent `fsync`. A temporary file is then written, synchronized, atomically published, and made durable with directory syncs on the publication path (POSIX; Windows relies on filesystem metadata journaling) before the service returns a reference. The content digest is encoded in the opaque `sha256:<digest>` identifier. Admission and reads fully decode supported rasters before accepting their format and dimensions, and every read also verifies the digest, byte length, and logged metadata.
The store performs no automatic deletion in version one. Sent user images and model-generated images remain reachable for history, resume, and fork. Reference-aware garbage collection needs a separate design because an age-only rule can delete data still referenced by a durable session. Deployment byte and pixel limits are admission policy on writes; reads verify the digest and recorded metadata without reapplying current admission limits, so lowering policy does not invalidate older history.
### Durable content and prompt wire
The attachment seam exposes immutable image write and verified read operations. The canonical metadata is deliberately narrower than a generic file record:
```ts
import type { Branded } from '@deepseek-ai/dsh-brand'
type AttachmentId = Branded<'AttachmentId'>
interface ImageAttachmentRef {
attachmentId: AttachmentId
mediaType: 'image/png' | 'image/jpeg' | 'image/webp' | 'image/gif'
bytes: number
width: number
height: number
name?: string
}
interface ImageBlock {
type: 'image'
attachment: ImageAttachmentRef
}
```
`ImageBlock` joins the merge-extensible core `ContentBlockMap` and is valid in either user or assistant content. It never carries base64, an object URL, a filesystem path, or a provider-owned locator. This keeps the session event plus immutable object store sufficient to reconstruct the exact model-visible image. The LLM vocabulary therefore has a type-only dependency on the attachment seam; provider runtime dependencies remain adapter-specific.
The browser cannot mint a durable reference, so `session.prompt` accepts a narrow intake union rather than canonical `ContentBlock[]`:
```ts
export {}
type PromptInputPart =
| { type: 'text'; text: string }
| {
type: 'image'
mediaType: 'image/png' | 'image/jpeg' | 'image/webp' | 'image/gif'
data: string
name?: string
}
```
Base64 crosses JSON-RPC once and is discarded after persistence. The host validates canonical base64, image count, aggregate bytes, individual bytes, the declared MIME against a fully decoded raster, intrinsic dimensions, and decoded-pixel count. It awaits the seam's storage-free `validateImage` for every batch member before saving any member, so one malformed image cannot strand the batch's valid members as unreferenced objects. Storage commits then run in submission order to bound full-raster decoder memory. If a later storage I/O operation fails, the host appends no user event, but an earlier immutable content-addressed object may remain unreferenced; version one leaves cleanup to future reference-aware garbage collection instead of adding destructive rollback to the deduplicated store. Only after every image succeeds does it call the agent with normalized text and durable image blocks in the submitted order. A failure exposes no attachment path or raw bytes.
`session.attachment` is a read-only, session-scoped endpoint. The host serves bytes only when a durable event in that session references the requested attachment identifier. The client deduplicates loads by session and attachment identifier while that session is rendered, revokes resolved URLs on rendered-session disposal, and rejects invalidated late loads before allocating an object URL so an unmounted session or disposed service cannot repopulate the cache.
### Model capabilities and provider behavior
Model catalog entries gain optional merge-extensible input modality declarations. A missing declaration means unknown; a present list without `image` is an explicit negative capability.
The host is the authoritative preflight boundary. It resolves the session's latest routed provider/model, falling back through agent options to host defaults; if that model explicitly excludes image input, it rejects the prompt before writing any attachment or event, and the client restores the draft. Image-bearing prompt admission and model selection share one per-agent serial boundary, and a dequeued prompt remains pending until its durable message event publishes ([ordering decision](../bug-fix/2026-07-29-atomic-web-image-admission.md)); a steering carrier gates from its enqueue until its `steering/message` event publishes, closing the outbox hop that never enters the queued mirror. Selection rejects a text-only target while an image is pending publication or remains in the session's current derived history. Compaction can remove old images and make a later text-only selection valid; idle without publication releases a claimed queued carrier, while steering retained in the outbox stays gated until publication or discard. `session.updateQueue` edits accept text content only, so a queue edit cannot inject an image past this admission boundary. Unknown capability proceeds to the adapter guard so uncatalogued model identifiers remain usable. The browser rejects unsupported declared image media types before allocating preview URLs, but it does not snapshot deployment limits or model capability: a handshake snapshot cannot represent a session's current target after `session.selectModel`, and deployment policy may change independently. The host validates the complete batch against current byte, count, aggregate, media, dimension, pixel, and routed-model policy before writing any attachment or event; its rejection renders through the composer error strip.
The Pi-AI adapter is the first visual-input route: it resolves `ctx.attachments` at request time, recursively converts each durable image reference including references nested inside tool results, and emits native image content only for models that declare image input. The shipped composition registers Pi-AI OpenAI and Anthropic routes alongside the text-only default DeepSeek route; selecting the active provider/model remains a host composition or profile concern rather than an image-input CLI feature. Request-time service resolution keeps Cordis load order from freezing optional attachment availability. The hand-written DeepSeek adapter throws typed `UNSUPPORTED_CONTENT` for an image anywhere in the request, including nested tool results. No adapter may flatten or skip an image.
Core supports structured assistant image blocks, but no current production provider route is certified for image output. Any future output-capable adapter must retrieve provider bytes under bounded size and time policy, validate them through the same attachment service, persist them, and only then publish the atomic `ImageBlock`. A URL in assistant Markdown remains text and is never downloaded automatically.
Provider-neutral token estimation does not guess visual pricing from image dimensions; provider-reported usage remains authoritative. ACP renders an explicit image marker until that protocol surface gains native image support rather than silently omitting the block.
Compaction replays the selected conversation prefix, including image references, into the configured summarization route. A visual-capable route resolves those references through its adapter; a text-only route fails explicitly instead of silently dropping the visual context. The synthesized checkpoint remains text-only, and `compact-basic` rejects image summary output with `UNSUPPORTED_CONTENT`.
### History rendering and original preview
History folding preserves `ImageBlock` in both user and assistant messages. User images align to the trailing edge above their text; assistant images remain in their original content-block position in the leading narration flow. `MessageImage` derives a stable inline box from recorded dimensions, resolves bytes through the session-authorized loader, uses `object-fit: contain`, and turns a missing or corrupt object into a retryable error control.
Composer thumbnails and each `MessageImage` own ephemeral original-preview state and invoke the same pure `ImageLightbox`. The modal uses the already resolved original object URL, constrains only display size, focuses its close control, and restores the previous focus target when closed.
### Limits and trust boundaries
Version one accepts PNG, JPEG, WebP, and GIF only. SVG and remote URLs are excluded. Default limits are 5 MiB per image, 10 images and 20 MiB aggregate image bytes per message, and 40 million intrinsic pixels per image. These deployment-varying limits are validated backend configuration and enforced by the host before persistence. The client connection carrier has an independent configurable `maxRequestBodyBytes` cap (32 MiB by default) for every API request and fails load if it cannot hold the attachment service's aggregate image limit after base64 and envelope expansion; lowering image policy therefore never silently lowers the carrier limit for valid text or other RPCs. A body without a declared length is rejected the moment it crosses the cap rather than drained to its end.
Malformed base64, unsupported or mismatched media, truncated image payloads, excess bytes, excess image count, excess pixels, missing objects, and integrity mismatches return stable structured failures. Original filenames are reduced to a display basename, control characters are removed, and no local path is logged or returned to the browser.
### Package and surface changes
| Surface | Responsibility |
| --- | --- |
| `packages/attachment/attachment` | Opaque attachment identifier, image reference, limits, failures, and `ctx.attachments` service. |
| `packages/attachment/attachment-local` | Private content-addressed storage, complete raster decoding, integrity verification, and configuration. |
| `packages/llm/llm` | Role-neutral `ImageBlock` and input-modality metadata. |
| `packages/llm/llm-pi-ai` | Resolve durable supported image input into native provider content. |
| `packages/llm/llm-deepseek` | Reject image content explicitly. |
| `packages/compact/compact-basic` | Preserve images in summary input and reject non-text checkpoint output explicitly. |
| `packages/host/apiproxy` and `packages/bundle/base` | Narrow upload wire, persist-before-event ordering, session-authorized reads, limits and model preflight, plus default profile composition. |
| `packages/client/connection` and `packages/client/runtime` | Bounded request buffering, wire types, fixture images, prompt uploads, attachment reads, and durable-reference folding. |
| `packages/client/ui-conversation` | Per-session draft images, attachment rail, user and assistant image controls, and original preview. |
| `packages/acp/acp` | Explicit fallback rendering for image blocks. |
The attachment packages form the interface/implementation side of one capability seam. Composer behavior stays in the conversation object layer, provider conversion stays in adapters, and no change is required in `agent-loop`.
### Implementation
The implemented slice includes the attachment seam, role-neutral image block, Pi-AI input conversion, DeepSeek rejection, durable host ordering, Web upload/read protocol, current image-limit enforcement, bounded Web request bodies, in-memory draft images, paste/drop rail, user and assistant history rendering, double-click preview, compaction handling, and keyless assembled Web coverage.
No compatibility shim is required for the pre-release prompt wire; all call sites and fixtures change with the introducing slice.
## Alternatives considered
### Keep every intake image in `/var` or another temporary directory
Temporary storage is appropriate before send, including for a native client that receives clipboard files through the operating system. It is not appropriate after acceptance: cleanup is outside the harness's control, paths are host-specific, and resume or fork can outlive the file. The proposal permits temporary staging but copies accepted bytes into `DSH_HOME` before the event.
### Persist immediately on paste or drop
Immediate persistence makes drafts reload-resistant but creates durable objects before a session or message owns them, which requires quota, orphan lifetime, and cleanup policy. Version one keeps the unsent draft temporary and makes send acceptance the durability boundary.
### Inline base64 in messages and session logs
This duplicates binary data across RPC, events, history pages, forks, compaction, and browser storage, and invites token accounting to treat encoding text as model text. One immutable object plus small references keeps the durable representation bounded.
### Use browser object URLs, local paths, or provider URLs as canonical content
Object URLs expire with the document, local paths are not portable, and provider URLs may expire, track viewers, or expose credentials. They remain temporary transport or preview details only.
### Use one generic `AttachmentBlock` for images, files, audio, and video
Composer presentation can use a generic attachment rail, but provider semantics are modality-specific. Images are native multimodal input; PDFs may be provider files or extracted text; video may be native, sampled, or unsupported. A specific `ImageBlock` forces every consumer to handle or reject the modality explicitly.
### Rely on UI capability checks or silently filter images
UI state can be stale and does not protect direct SDK, ACP, replay, or uncatalogued model paths. Silent filtering changes user intent. Provider enforcement remains mandatory, while UI checks are optional earlier feedback.
## Testing
- Storage tests cover content-addressed deduplication, private permissions, admission failures, corruption/missing-object failures, and reading history after deployment limits are lowered.
- Host and protocol tests cover persist-before-event ordering, absence of base64 in logs, session-scoped authorization, capability rejection, upload limits, bounded HTTP request bodies, image-admission/model-selection races (queued and steering placements), pending publication, idle release without publication, text-only queue edits, and selection against current derived history after compaction.
- Client unit tests cover paste and drop, mixed clipboard text, image-only send, draft restoration, ordering, draft/session-scope/application object-URL cleanup, and a deferred historical read that completes after disposal; the keyless assembled built-client lane (`apps/web/tests/image-display.snapshot.ts`, `DSH_EXAMPLE_MODE=lib pnpm run test:snapshot`) covers the historical user and assistant galleries over the authorized attachment route, the original-size lightbox, and the composer paste rail.
- Adapter and compaction tests cover native Pi-AI image conversion, late attachment-service composition, text-only rejection, recursively nested tool-result images, preserved summary input, and explicit image-output rejection.
- A credentialed real-API test sends a PNG through the Anthropic `claude-opus-4-8` route and requires the model to identify its QR code.
- The current production adapter set has no certified image-output route; output-provider certification remains outside version one.
## Consequences
- Durable storage grows without garbage collection. Version one chooses replay safety over premature deletion.
- A missing or corrupt object makes exact model reconstruction fail. Failing loud preserves integrity but may prevent that session from continuing until repaired.
- JSON-RPC base64 adds upload memory and roughly one-third encoding overhead. Version-one limits bound it; larger media needs streaming or a binary transport.
- Unsent images do not survive reload. Durable drafts need quota and orphan cleanup rather than reusing message storage implicitly.
- Original preview decodes more pixels than the inline control displays. Pixel limits, one clicked preview, and object-URL disposal bound but do not eliminate transient browser memory.
- Capability metadata may be missing or stale. Host preflight improves feedback, while adapter enforcement remains authoritative.
- A future output provider may require authenticated retrieval before an assistant image can complete, adding latency and a new failure point. Persist-before-event ordering favors replay integrity.
- File picking, generic files/PDF, audio/video, durable draft staging, image copying, custom context menus, output-provider certification, and reference-aware garbage collection remain independent designs.
@@ -0,0 +1,214 @@
# Agent Note: Web 多模态图片输入与持久附件
Status: implemented
[English](2026-07-22-web-multimodal-image-input-and-durable-attachments.md) | 中文
## 问题
在此变更之前,Web 输入区仅接受文本:`InputBar` 接收字符串草稿,`ConversationService.send()` 创建文本内容,宿主再把该内容转发给 agent(智能体)。用户无法粘贴图片、在发送前查看图片、提交仅含图片的提示词,也无法从历史记录中恢复已发送图片。
这不只是输入区功能缺失。核心层需要持久图片内容块,提供方需要明确处理模态,会话日志则必须重建模型可见的全部内容。[此前移除图片块的决策](../../implemented/simplification/2026-07-04-drop-image-content-block.md)否决了可能静默丢失图片或将其展平的不完整设计。浏览器对象 URL、本地路径、提供方 URL 或 base64 数据都不能成为规范会话内容。
[Web 客户端架构](../../implemented/architecture/2026-07-19-gui-web-client-architecture.md)要求组件保持纯粹,并将每个会话的输入区状态放在 `ctx.conversation` 中;[GUI 分层与 RPC 协议](../../implemented/architecture/2026-07-19-gui-layering-and-rpc-protocol.md)则要求持久事件成为实时渲染与历史回放的共同真源。因此,图片接收、持久化、提供方转换和渲染需要遵循同一个明确的生命周期。
同类产品普遍在编辑器上方设置附件栏,但存储方案各不相同。诸如 `/var/folders/.../codex-clipboard-*.png` 的 Codex 式路径适合作为接收输入时的暂存位置,却不能作为持久消息身份:操作系统可能删除文件,另一台宿主无法读取文件,恢复后的会话也不能依赖文件仍然存在。
## 决策
粘贴或拖放的光栅图片是 Web 输入区对持久附件能力的首个应用场景。未发送文件仍是由客户端持有的临时草稿状态。宿主在追加相应消息事件前,校验并持久提交每张已接受的用户图片。生成结构化图片输出的提供方适配器在追加相应助手块前,也必须持久提交输出。规范用户内容与助手内容只包含角色无关的 `ImageBlock` 引用。
第一版支持粘贴和拖放 PNG、JPEG、WebP 与 GIF,支持仅图片或混合提示词,支持渲染历史用户图片与助手图片,并支持双击预览原图。文件选择、通用文件、PDF、音频、视频、图片复制和自定义上下文菜单仍分别作为后续工作。
### 产品行为
- 粘贴或拖放一张或多张受支持的图片后,文本框上方会按顺序显示缩略图,但不会插入占位文本。文件拖入输入区时会高亮放置目标。
- 同一个常驻 `InputBar` 会在空白会话 Hero 和活跃会话布局中渲染附件栏。附件栏为空时隐藏,通过横向滚动避免撑宽输入区。
- 每个缩略图约为 72 × 72 像素,带有移除操作;双击时打开草稿原图。
- 提示词可同时包含文本与图片,也可仅包含图片。粘贴纯文本时保持浏览器原生行为;粘贴混合的剪贴板内容时,文本会正常插入,文件则同时添加到附件栏;仅粘贴文件时才阻止浏览器的默认处理。在输入区放置文件时总会阻止浏览器导航,并在本地报告不受支持的文件。
- 发送失败时恢复完整的文本与图片草稿,但不会覆盖请求飞行期间新增的文本或图片。移除、发送成功、会话 scope 释放、已渲染历史记录释放和应用释放都会撤销各自持有的对象 URL。
- 历史用户图片与助手图片共用一个 `MessageImage` 控件。行内图片保持固有宽高比、不放大,并限制在 240 × 240 像素的边界框内。
- 双击消息图片会在不超出视口的模态框中打开存储的原图。按 Escape、激活关闭控件或激活背景区域都会关闭模态框并恢复焦点。
- 第一版不覆盖浏览器上下文菜单,也不提供明确的图片复制操作。
### 存储生命周期与归属
持久化边界是消息被接受,而不是图片被粘贴:
| 状态 | 允许的表示 | 持久性与顺序 |
| --- | --- | --- |
| 未发送的用户草稿 | 浏览器 `File` 加对象 URL;原生客户端可以使用 `/var/...` 等操作系统临时文件 | 临时且由客户端持有。它可能在重载或进程退出后消失,绝不出现在会话事件中。 |
| 已接受的用户图片 | `DSH_HOME` 下的不可变对象加 `ImageAttachmentRef` | 在 `agent.send()``agent.steer()` 能够追加所属用户事件前,宿主提交每张图片。 |
| 结构化模型图片输出 | `DSH_HOME` 下的不可变对象加 `ImageAttachmentRef` | 提供方适配器在发出已完成的图片块或助手消息事件前提交字节。事件中禁止出现临时 URL、路径和 base64。 |
每个会话的 `InputMachine` 状态在实时草稿旁保存仅限运行时的有序附件标识符。框架持有的 chat store 只接收草稿的纯文本持久化镜像,`ConversationService` 则持有相应的浏览器专用 `File` 与对象 URL 注册表:
```ts
import type { Branded } from '@deepseek-ai/dsh-brand'
type DraftAttachmentId = Branded<'DraftAttachmentId'>
interface ChatStoreState {
selection: object | null
draft: string
view: string | null
}
interface InputState {
draft: string
imageIds: readonly DraftAttachmentId[]
}
interface ComposerAttachment {
kind: 'image'
id: DraftAttachmentId
file: File
previewUrl: string
}
```
这一拆分把会话 provide 通道的输入 hook 与 actions 用作实时输入区状态的唯一订阅路径,同时避免把不可序列化的浏览器对象写进持久 JSON。只有纯文本草稿镜像使用 `localStorage`;附件标识符、浏览器 `File` 对象和对象 URL 都限定在实时会话输入外壳的 scope 内。未发送图片因此无法跨重载或会话 scope 释放保留。切换 Workspace 时,只有目标外壳接受完整图片批次,图文混合草稿才会移动;拒绝时,文本和图片都留在来源外壳。原生客户端可以在操作系统临时目录中暂存输入,但必须像对待浏览器对象 URL 一样对待该路径:不再需要时删除,并在消息被接受前把字节复制进持久存储。
本地附件后端依次解析显式 `dshHome``$DSH_HOME``~/.dsh`。它把内容寻址对象存储在 `$DSH_HOME/attachments/v1/objects/<prefix>/<sha256>` 下,并为目录和文件设置仅所有者可访问的权限。每个进程首次为某个 home 保存对象时,都会创建该 home,并逐级同步每个祖先目录项直至文件系统根目录;不能把存在视为持久性,因为另一个进程可能仍处于 `mkdir` 与父目录 `fsync` 之间。随后,服务写入并同步临时文件,再以原子方式发布,并对发布路径执行目录同步使其持久(POSIX;Windows 依赖文件系统元数据日志),之后才返回引用。内容摘要编码在不透明的 `sha256:<digest>` 标识符中。写入准入与读取都会完整解码受支持的光栅图片,之后才接受其格式和尺寸;每次读取还会校验摘要、字节长度和已记录的元数据。
第一版不对存储执行自动删除。已发送的用户图片和模型生成图片会一直保留,以供历史记录、恢复和 fork 使用。按引用感知的垃圾回收需要单独设计,因为仅按时间清理可能删除仍被持久会话引用的数据。部署的字节和像素限制是写入时的准入策略;读取时会校验摘要和已记录的元数据,但不重新应用当前准入限制,因此收紧策略不会导致旧历史记录失效。
### 持久内容与提示词协议
附件服务边界公开不可变图片写入和经过校验的读取操作。规范元数据刻意比通用文件记录更窄:
```ts
import type { Branded } from '@deepseek-ai/dsh-brand'
type AttachmentId = Branded<'AttachmentId'>
interface ImageAttachmentRef {
attachmentId: AttachmentId
mediaType: 'image/png' | 'image/jpeg' | 'image/webp' | 'image/gif'
bytes: number
width: number
height: number
name?: string
}
interface ImageBlock {
type: 'image'
attachment: ImageAttachmentRef
}
```
`ImageBlock` 加入可合并扩展的核心 `ContentBlockMap`,在用户内容和助手内容中都有效。它绝不携带 base64、对象 URL、文件系统路径或提供方持有的定位符。因此,会话事件与不可变对象存储足以共同重建模型可见的确切图片。LLM 词汇由此仅在类型层面依赖附件服务边界;提供方运行时依赖仍由各适配器持有。
浏览器无法生成持久引用,因此 `session.prompt` 接受范围狭窄的接收联合类型,而不是规范 `ContentBlock[]`
```ts
export {}
type PromptInputPart =
| { type: 'text'; text: string }
| {
type: 'image'
mediaType: 'image/png' | 'image/jpeg' | 'image/webp' | 'image/gif'
data: string
name?: string
}
```
Base64 只跨越一次 JSON-RPC,并在持久化后丢弃。宿主会校验规范 base64、图片数量、总字节数、单张图片字节数、声明的 MIME 与完整解码后的光栅图片是否一致、固有尺寸和解码像素数。它会在保存任何成员之前,等待服务边界上不触碰存储的 `validateImage` 完成对每个批次成员的校验,因此一张畸形图片不会把批次中的有效成员留成无引用对象。随后按提交顺序执行存储提交,以限制完整光栅解码器的内存占用。如果后续存储 I/O 操作失败,宿主不会追加用户事件,但先前的不可变内容寻址对象可能保持无引用状态;第一版将清理留给未来按引用感知的垃圾回收,而不向去重存储添加破坏性回滚。只有每张图片都成功后,宿主才会用规范化文本和按提交顺序排列的持久图片块调用 agent。失败时不公开任何附件路径或原始字节。
`session.attachment` 是只读且限定于会话作用域的端点。只有该会话中的持久事件引用了所请求的附件标识符,宿主才提供字节。会话处于渲染状态时,客户端会按会话和附件标识符对加载操作去重;已渲染会话释放时会撤销已解析的 URL,并在分配对象 URL 前拒绝已失效的延迟加载,以免已卸载的会话或已释放的服务重新写入缓存。
### 模型能力与提供方行为
模型目录项增加可选且可合并扩展的输入模态声明。缺少声明表示未知;声明存在但不含 `image`,则明确表示不支持图片。
宿主是权威的前置检查边界。它会解析会话最新路由到的提供方和模型,并在缺失时依次回退到 agent 选项和宿主默认值;如果该模型明确排除图片输入,宿主会在写入任何附件或事件前拒绝提示词,客户端则恢复草稿。包含图片的提示词准入与模型选择共用一个逐 agent 的串行边界,而且已经出队的提示词在其持久消息事件发布前仍保持待发布状态([顺序决策](../bug-fix/2026-07-29-atomic-web-image-admission.md));steering 载体则从入队起就参与门槛,直到其 `steering/message` 事件发布为止,堵住了从不进入排队镜像的 outbox 窗口。当图片正等待发布或仍存在于会话当前的派生历史中时,模型选择会拒绝纯文本目标。压缩(compaction)可以移除旧图片,使之后选择纯文本目标变得有效;未发布任何事件即转入空闲时,已认领的 queued 载体会被释放,而保留在 outbox 中的 steering 在发布或丢弃前始终受门槛约束。`session.updateQueue` 的编辑只接受文本内容,因此队列编辑无法绕过该准入边界注入图片。能力未知时继续进入适配器强制检查,使未收录的模型标识符仍然可用。浏览器会在分配预览 URL 前拒绝声明不支持的图片媒体类型,但不会为部署限制或模型能力保留快照:握手快照无法表达 `session.selectModel` 之后会话的当前目标,部署策略也可能独立变化。宿主会根据当前的单张字节数、图片数量、总字节数、媒体类型、尺寸、像素数和路由模型策略校验整个批次,再写入任何附件或事件;其拒绝通过 composer 错误条呈现。
Pi-AI 适配器是首条视觉输入路径:它在请求时解析 `ctx.attachments`,递归转换每个持久图片引用,包括嵌套在工具结果中的引用,并且仅为声明支持图片输入的模型生成提供方原生图片内容。交付的组合会同时注册 Pi-AI OpenAI、Anthropic 路由和仅支持文本的默认 DeepSeek 路由;选择当前提供方/模型仍由宿主组合或配置承担,而不是图片输入 CLI(命令行界面)的功能。在请求时解析服务,可避免 Cordis 加载顺序将可选附件服务的可用性固化。手写 DeepSeek 适配器遇到请求中任何位置的图片时都会抛出类型化的 `UNSUPPORTED_CONTENT` 错误,包括嵌套工具结果中的图片。任何适配器都不得将图片展平或跳过。
核心层支持结构化助手图片块,但当前没有任何生产提供方路径通过图片输出认证。未来任何支持输出的适配器都必须在有界的大小和时间策略下获取提供方字节,通过同一个附件服务校验并持久化字节,之后才能以原子方式发布 `ImageBlock`。助手 Markdown 中的 URL 仍是文本,绝不自动下载。
提供方无关的 token 估算不会根据图片尺寸猜测视觉定价;提供方返回的用量仍是权威值。在 ACPAgent Client Protocol)接口原生支持图片前,ACP 会渲染明确的图片标记,而不是静默省略该块。
压缩会把选定的会话前缀(包含图片引用)回放到已配置的摘要生成路径中。支持视觉的路径会通过适配器解析这些引用;仅文本路径会明确失败,而不是静默丢弃视觉上下文。合成的检查点仍仅包含文本,`compact-basic` 会以 `UNSUPPORTED_CONTENT` 拒绝包含图片的摘要输出。
### 历史渲染与原图预览
历史记录折叠会在用户消息和助手消息中保留 `ImageBlock`。用户图片在文本上方靠尾端对齐;助手图片则保留在靠前端叙述流中的原内容块位置。`MessageImage` 根据记录的尺寸派生稳定的行内边界框,通过会话授权加载器解析字节,使用 `object-fit: contain`,并将对象缺失或损坏转换为可重试的错误控件。
输入区缩略图和每个 `MessageImage` 各自持有临时原图预览状态,并调用同一个纯 `ImageLightbox`。模态框使用已经解析的原始对象 URL,只限制显示尺寸;它会聚焦关闭控件,并在关闭时把焦点恢复到先前的目标。
### 限制与信任边界
第一版仅接受 PNG、JPEG、WebP 和 GIF。不接受 SVG 和远程 URL。默认限制为每张图片 5 MiB、每条消息 10 张图片和 20 MiB 图片总字节数,以及每张图片 4,000 万个固有像素。这些随部署变化的限制属于经过校验的后端配置,并由宿主在持久化前强制执行。客户端连接载体为每个 API 请求设置独立且可配置的 `maxRequestBodyBytes` 上限(默认 32 MiB);如果该上限无法容纳附件服务的图片总量限制经 base64 和请求封装膨胀后的大小,加载就会失败。因此,降低图片策略绝不会静默降低有效文本或其他 RPC 的载体上限。未声明长度的请求体在越过上限的瞬间即被拒绝,而不是先读完再拒。
格式错误的 base64、不支持或不匹配的媒体、截断的图片数据、超出字节限制、超出图片数量、超出像素限制、对象缺失和完整性不匹配都会返回稳定的结构化错误。原始文件名只保留用于显示的末段,控制字符会被移除,并且任何本地路径都不会写入日志或返回浏览器。
### 包与接口变更
| 接口 | 职责 |
| --- | --- |
| `packages/attachment/attachment` | 不透明附件标识符、图片引用、限制、错误和 `ctx.attachments` 服务。 |
| `packages/attachment/attachment-local` | 私有内容寻址存储、完整光栅解码、完整性校验和配置。 |
| `packages/llm/llm` | 角色无关的 `ImageBlock` 和输入模态元数据。 |
| `packages/llm/llm-pi-ai` | 将持久且受支持的图片输入解析为提供方原生内容。 |
| `packages/llm/llm-deepseek` | 明确拒绝图片内容。 |
| `packages/compact/compact-basic` | 在摘要输入中保留图片,并明确拒绝非文本检查点输出。 |
| `packages/host/apiproxy``packages/bundle/base` | 范围狭窄的上传协议、先持久化再追加事件的顺序、会话授权读取、限制和模型前置检查,以及默认 profile 组合。 |
| `packages/client/connection``packages/client/runtime` | 有界请求缓冲、协议类型、fixture(测试前置数据)图片、提示词上传、附件读取和持久引用折叠。 |
| `packages/client/ui-conversation` | 每个会话的草稿图片、附件栏、用户与助手图片控件和原图预览。 |
| `packages/acp/acp` | 图片块的明确兜底渲染。 |
附件包(package)构成一个能力服务边界的接口与实现侧。输入区行为留在会话对象层,提供方转换留在适配器中,无需修改 `agent-loop`
### 实现
已实现的范围包括附件服务边界、角色无关的图片块、Pi-AI 输入转换、DeepSeek 拒绝、宿主持久化顺序、Web 上传与读取协议、当前图片限制执行、大小受限的 Web 请求体、内存草稿图片、粘贴与拖放附件栏、用户与助手历史图片渲染、双击预览、压缩处理,以及组装后无需密钥的 Web 覆盖。
预发布提示词协议不需要兼容包装层;引入相应切片时会同时修改所有调用点和 fixture。
## 曾考虑的替代方案
### 将每张粘贴图片保留在 `/var` 或其他临时目录中
临时存储适合在发送前使用,也适合通过操作系统接收剪贴板文件的原生客户端。但它不适合在消息被接受后继续使用:清理不在 harness 的控制范围内,路径因宿主而异,恢复或 fork 后的会话也可能比文件存在得更久。提案允许临时暂存,但会在追加事件前将已接受的字节复制进 `DSH_HOME`
### 粘贴或拖放后立即持久化
立即持久化可以让草稿在重载后继续存在,但会在会话或消息持有对象前就创建持久对象,因此必须定义配额、遗留对象生命周期和清理策略。第一版保持未发送草稿为临时状态,并把发送被接受作为持久性边界。
### 在消息与会话日志中内联 base64
这种方式会在 RPC、事件、历史分页、fork、压缩和浏览器存储中复制二进制数据,还会诱使 token 计量把编码文本当成模型文本。单一不可变对象配合小型引用,可以让持久表示保持有界。
### 使用浏览器对象 URL、本地路径或提供方 URL 作为规范内容
对象 URL 会随文档失效,本地路径不可移植,提供方 URL 则可能过期、跟踪查看者或暴露凭据。它们只能作为临时传输或预览细节存在。
### 用一个通用 `AttachmentBlock` 表示图片、文件、音频和视频
输入区展示可以使用通用附件栏,但提供方语义取决于具体模态。图片是原生多模态输入;PDF 可能是提供方文件或提取后的文本;视频可能由模型原生支持、抽帧处理或不受支持。特定的 `ImageBlock` 会迫使每个消费方明确处理或拒绝该模态。
### 依赖 UI 能力检查或静默过滤图片
UI 状态可能陈旧,也无法保护直接 SDK、ACP、回放或未收录模型的路径。静默过滤会改变用户意图。提供方强制检查仍是必需项,UI 检查则是可选的提前反馈。
## 测试
- 存储测试覆盖内容寻址去重、私有权限、准入失败、对象损坏或缺失时的失败,以及收紧部署限制后读取历史数据。
- 宿主与协议测试覆盖先持久化再追加事件的顺序、日志中不含 base64、会话作用域授权、能力拒绝、上传限制、大小受限的 HTTP 请求体、图片准入与模型选择的竞态(排队与 steering 两种放置)、待发布状态、未发布即空闲时的门槛释放、仅文本的队列编辑,以及压缩后依据当前派生历史进行的选择。
- 客户端单元测试覆盖粘贴与拖放、混合剪贴板文本、仅图片发送、草稿恢复、顺序、草稿、会话作用域和应用层级的对象 URL 清理,以及一项在释放后才完成的延迟历史读取;keyless 的组装后构建产物通道(`apps/web/tests/image-display.snapshot.ts``DSH_EXAMPLE_MODE=lib pnpm run test:snapshot`)覆盖经授权附件路由渲染的历史用户与助手图片画廊、原图 lightbox,以及 composer 粘贴缩略图条。
- 适配器与压缩测试覆盖 Pi-AI 原生图片转换、后置附件服务组合、仅文本拒绝、递归嵌套在工具结果中的图片、保留摘要输入,以及明确拒绝图片输出。
- 需要凭据的实际 API 测试会通过 Anthropic `claude-opus-4-8` 路径发送一张 PNG,并要求模型识别其中的二维码。
- 当前生产适配器集合没有经过认证的图片输出路由;输出提供方认证仍不在第一版范围内。
## 后果
- 持久存储会在没有垃圾回收时持续增长。第一版选择回放安全,而不是过早删除。
- 对象缺失或损坏会让模型请求无法精确重建。明确失败可以保持完整性,但在修复前可能阻止该会话继续运行。
- JSON-RPC base64 会增加上传内存,并带来约三分之一的编码开销。第一版的限制可以约束开销;更大的媒体需要流式传输或二进制传输协议。
- 未发送图片无法跨重载保留。持久草稿需要配额和遗留对象清理,而不是隐式复用消息存储。
- 原图预览解码的像素多于行内控件显示的像素。像素限制、一次只打开一个预览和对象 URL 释放可以约束但无法消除浏览器瞬时内存占用。
- 能力元数据可能缺失或陈旧。宿主前置检查可以改善反馈,适配器强制检查仍是权威结果。
- 未来输出提供方可能需要经过身份认证的下载,助手图片才能完成,这会增加延迟与新的故障点。先持久化再追加事件的顺序优先保障回放完整性。
- 文件选择、通用文件与 PDF、音频与视频、持久草稿暂存、图片复制、自定义上下文菜单、输出提供方认证和按引用感知的垃圾回收仍是相互独立的设计。
@@ -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/2026-07-24-web-session-model-selector.md
2026-07-24-web-session-model-selector.md: 78017b14a806f8e609a85e340094cd2a349d47e1
2026-07-24-web-session-model-selector.zh.md: 87a342721f5e47f5bcedfafb578eb6916101d2f5
2026-07-24-web-session-model-selector.md: e6a96ac62f69a3bd312f61cc920caa259d2dc5b0
2026-07-24-web-session-model-selector.zh.md: 5a0245359d69ac6e59a20dc3276b9411c4b25e23
@@ -6,7 +6,7 @@ English | [中文](2026-07-24-web-session-model-selector.zh.md)
## Problem
The Web conversation needs a visible, mutable session model selection sourced from the Host. Copying TUI presentation or hardcoding DeepSeek models in the browser would split model discovery and step-boundary semantics across front doors. A switch made while a response is running also needs one atomic boundary: prompt variables and request routing cannot observe different selections.
The Web conversation needs a visible, mutable session model selection sourced from the Host. Copying TUI presentation or hardcoding DeepSeek models in the browser would split model discovery and step-boundary semantics across front ends. A switch made while a response is running also needs one atomic boundary: prompt variables and request routing cannot observe different selections.
## Decision
@@ -6,13 +6,13 @@ Status: implemented
## 问题
Web 对话需要一项由 Host 提供、可见且可更改的会话模型选择。如果照搬 TUI 的呈现方式,或在浏览器中硬编码 DeepSeek 模型,就会让模型发现逻辑和步骤边界语义分散到不同前中。响应运行期间发生的切换还需要一个原子边界:提示词变量与请求路由不能观测到不同的选择。
Web 对话需要一项由 Host 提供、可见且可更改的会话模型选择。如果照搬 TUI 的呈现方式,或在浏览器中硬编码 DeepSeek 模型,就会让模型发现逻辑和步骤边界语义分散到不同前中。响应运行期间发生的切换还需要一个原子边界:提示词变量与请求路由不能观测到不同的选择。
## 决策
Web Host 为每个新建或恢复的 Agent 安装 `ModelSelection`。如果会话已经使用过模型,提供方/模型/推理(reasoning)选择来自最新的 `request/header`;否则来自 `ctx.agentDefaultModel``session.selectModel` 会赋值会话级选择,提示词组装则将它与请求路由一并捕获,因此运行中步骤发生的切换会应用于下一个组装步骤。下一个实际采用的选择通过完整的 `request/header` 快照持久化;尚未进入请求的选择则仅保存在当前进程中。
会话 RPC 领域公开 `session.models` 模型目录与 `session.selectModel`。该目录从 LLM(大语言模型)注册表动态构建,并按提供方分组;每个已列出模型的精确元数据还会加入由适配器持有的推理强度 ID、名称、说明和可选默认值。各提供方的目录与精确元数据会按提供方并发加载,且彼此独立失败,因此成功加载的分组仍可与可重试的失败记录一同使用。模型是否位于目录仅供参考:`session.models.current` 独立返回,即使不在任何分组中也仍然可以路由,但提供方停止公布该模型后,Host 不会合成未列出行。两个前对这一状态给出不同回答:TUI 把未列出的当前模型渲染为独立一行,Web 则显示未设置状态的触发器标签并要求选择替代模型。Web 是编辑目录的 surface,因此缺席的目录行代表一项待作出的选择;TUI 只从现有行中选择。显示未设置标签的 Web composer 仍可以使用当前可路由选择发送消息。精确解析决定提供方/模型组合与显式推理强度是否可用。选择操作通过 `resolveCallConfig` 拒绝不支持的推理强度 ID,并在赋值该选择前具体化适配器配置的默认值。
会话 RPC 领域公开 `session.models` 模型目录与 `session.selectModel`。该目录从 LLM(大语言模型)注册表动态构建,并按提供方分组;每个已列出模型的精确元数据还会加入由适配器持有的推理强度 ID、名称、说明和可选默认值。各提供方的目录与精确元数据会按提供方并发加载,且彼此独立失败,因此成功加载的分组仍可与可重试的失败记录一同使用。模型是否位于目录仅供参考:`session.models.current` 独立返回,即使不在任何分组中也仍然可以路由,但提供方停止公布该模型后,Host 不会合成未列出行。两个前对这一状态给出不同回答:TUI 把未列出的当前模型渲染为独立一行,Web 则显示未设置状态的触发器标签并要求选择替代模型。Web 是编辑目录所在的前端,因此缺席的目录行代表一项待作出的选择;TUI 只从现有行中选择。显示未设置标签的 Web composer 仍可以使用当前可路由选择发送消息。精确解析决定提供方/模型组合与显式推理强度是否可用。选择操作通过 `resolveCallConfig` 拒绝不支持的推理强度 ID,并在赋值该选择前具体化适配器配置的默认值。
浏览器中的 `ModelService` 为每个实时会话持有一个 `ModelDirectory`。其快照包含当前完整的 `ModelSelection`、分组目录、提供方失败记录、操作错误,以及 `idle``loading``ready``selecting``error` 状态。挂载时会预先填充触发器标签,此后每次打开菜单都会刷新目录。目录与选择调用共用操作代次,防止较早响应覆盖较新结果;连接重置会先丢弃当前进程中的投影,再恢复 Host 选择。失败时保留先前的选择和可用分组。
@@ -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/2026-07-25-session-list-browsing-and-manual-order.md
2026-07-25-session-list-browsing-and-manual-order.md: 323c0db16cc6b9e83155a3fb873ab94e4facd3a2
2026-07-25-session-list-browsing-and-manual-order.zh.md: 85b2b319f03113480b3953c21940c123ba594ca8
2026-07-25-session-list-browsing-and-manual-order.md: 3d2125bdf67a70a1a5bca43c5d5acb09fda178b7
2026-07-25-session-list-browsing-and-manual-order.zh.md: 161ebd2857073d4dd9cfc2883880cd3e2d91c040
@@ -24,7 +24,7 @@ The group-by menu offers two modes, WorkSpace / In one list. WorkSpace mode rend
### workspace.rename
`workspace.rename({ workspaceId, title })`: the title is trimmed and must be non-blank; both the same-title no-op and the duplicate check evaluate inside the Host's serialized workspace-operation chain (shared with create-by-name, so concurrent explicit naming operations cannot interleave a duplicate or an out-of-order fake success), and a conflict returns `workspace-name-conflict`. Path adoption may derive a title already present because canonical path, not title, owns identity ([decision](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)). Durability goes through `setTitle`'s mutate path, and the `domain/changed` listener broadcasts the `host/workspace-changed` frame automatically. The UI is a standard modal with a client-side duplicate pre-check.
`workspace.rename({ workspaceId, title })`: the title is trimmed and must be non-blank; both the same-title no-op and the duplicate check evaluate inside the Host's serialized workspace-operation chain (shared with path adoption and deletion, so concurrent workspace operations cannot interleave a duplicate or an out-of-order fake success), and a conflict returns `workspace-name-conflict`. Path adoption may derive a title already present because canonical path, not title, owns identity ([decision](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)). Durability goes through `setTitle`'s mutate path, and the `domain/changed` listener broadcasts the `host/workspace-changed` frame automatically. The UI is a standard modal with a client-side duplicate pre-check.
### Manual order: insertSessionBefore replaces activity pinning
@@ -24,7 +24,7 @@ group-by 菜单提供 WorkSpace / In one list 两种模式。WorkSpace 模式按
### workspace.rename
`workspace.rename({ workspaceId, title })`title trim 后非空;同名 no-op 与重名查重都在 Host 的 Workspace 操作串行链内求值(与按名称创建共链,并发的显式命名操作不能穿插出重名或乱序假成功),冲突返回 `workspace-name-conflict`。按路径收编可以派生出已有 title,因为拥有身份的是 canonical path,而不是 title(见[身份决策](../bug-fix/2026-07-31-same-basename-workspace-adoption.md))。落盘经 `setTitle` 的 mutate 通道,`domain/changed` 监听自动广播 `host/workspace-changed` 帧。UI 为标准 Modal,client 侧另做重名预检。
`workspace.rename({ workspaceId, title })`title trim 后非空;同名 no-op 与重名查重都在 Host 的 Workspace 操作串行链内求值(与按路径收编和删除共链,并发的 Workspace 操作不能穿插出重名或乱序假成功),冲突返回 `workspace-name-conflict`。按路径收编可以派生出已有 title,因为拥有身份的是 canonical path,而不是 title(见[身份决策](../bug-fix/2026-07-31-same-basename-workspace-adoption.md))。落盘经 `setTitle` 的 mutate 通道,`domain/changed` 监听自动广播 `host/workspace-changed` 帧。UI 为标准 Modal,client 侧另做重名预检。
### 手动排序:insertSessionBefore 取代活动置顶
@@ -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/2026-07-25-workspace-ui-product-flow.md
2026-07-25-workspace-ui-product-flow.md: bfdde9797433eca67e47da73468cba855f2a02b9
2026-07-25-workspace-ui-product-flow.zh.md: 74a9dd6f70396201a78f3204bfdc7d8b5d4f5d98
2026-07-25-workspace-ui-product-flow.md: 98e963195126df2ec8291a11b3d9fc7a2baeb0df
2026-07-25-workspace-ui-product-flow.zh.md: 486093be0b8d10c2ae0b8083b305ecad5386351c
@@ -19,13 +19,12 @@ The Host provides the following GUI wiring on the Workspace entity:
| RPC | Behavior |
| --- | --- |
| `workspace.list` | Returns persistent Workspaces in order and filters out Session ids that fail header validation |
| `workspace.create({ name })` | Creates a directory and Workspace at `workspaceRoot/name`; fails on a display-name conflict |
| `workspace.create({ path })` | Adopts an existing directory by canonical path; basename-derived display titles may repeat |
| `workspace.delete({ workspaceId })` | Removes the Workspace registration while retaining its directory and session logs; its Sessions become Ungrouped |
| `session.create({ workspaceId, sessionId? })` | Resolves cwd from the Workspace, idempotently creates a Session with an optional preallocated id, and attaches it |
| `session.create({ cwd })` | Remains available to non-Workspace callers and creates an Ungrouped Session |
`workspaceRoot` is an independent Host setting that falls back to the Host cwd when unset; it is unrelated to `storageRoot`, which stores Workspace domain data. The Host stream pushes Workspace and Session deltas, including `host/workspace-removed`, and the Client refreshes the `workspace.list` and `session.list` baselines separately after reconnecting. Registration-deletion ownership and safety are defined in the [Workspace registration deletion Agent Note](2026-07-27-workspace-registration-deletion.md).
The Host stream pushes Workspace and Session deltas, including `host/workspace-removed`, and the Client refreshes the `workspace.list` and `session.list` baselines separately after reconnecting. Registration-deletion ownership and safety are defined in the [Workspace registration deletion Agent Note](2026-07-27-workspace-registration-deletion.md).
A Workspace's `sessionIds` is an ordered candidate index. A membership projection requires both that an id appear in the index and that the corresponding canonicalized `SessionHeader.cwd` equal the Workspace path; SessionHeader does not gain a `workspaceId`. A Session whose cwd matches but whose id is absent from the index remains Ungrouped, while an indexed id is filtered out if its header is missing, its cwd is invalid, or its cwd does not match. Two Workspace indexes claiming the same Session is corrupt state and fails loudly.
@@ -52,7 +51,7 @@ When no Workspace exists, the page creates a frontend Workspace object named `wo
Top-level New Session, the plus button on a Workspace row, and the Workspace picker all invoke the same New Session action. An explicit Workspace id becomes the target directly; when none is specified, the action uses the most recent Workspace, or the Workspace Intent if no real Workspace exists. The Workspace picker's one Add workspace action ([one-route Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md); it was a pair of Use-an-existing-folder and create-by-name actions when this was decided) immediately creates a real Workspace when the user confirms a directory, then retargets the frontend Session to it; an explicitly created empty Workspace remains even if the user sends no message.
A new Workspace takes its display name from the directory it was created in. Distinct canonical paths may share the same basename-derived title ([identity decision](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)); explicit create-by-name and rename operations retain their duplicate-title checks. Moving Sessions across Workspaces, manual adoption from Ungrouped, and separate display-name and directory-name inputs remain outside this flow.
A new Workspace takes its display name from the directory it was created in. Distinct canonical paths may share the same basename-derived title ([identity decision](../bug-fix/2026-07-31-same-basename-workspace-adoption.md)); the explicit rename operation retains its duplicate-title check. Moving Sessions across Workspaces, manual adoption from Ungrouped, and separate display-name and directory-name inputs remain outside this flow.
### First send and recovery
@@ -108,7 +107,7 @@ The Sidebar and conversation empty hero receive standardized actions through slo
- Workspace list performs one reentrant bootstrap using only headers; an initialized empty registry does not initialize again after restart, and membership reads validate both the index and canonical cwd.
- The initial default target is determined exactly once after both baselines are ready; Workspace groups are not reordered as a whole by hydration or Session activity, and an active Session moves only itself to the front.
- A frontend Session under a real Workspace temporarily counts toward the sidebar total, while a Workspace Intent remains hidden; neither publication nor refresh leaves duplicate rows or counts.
- The UI and Host admit distinct same-basename directories as separate Workspaces, while explicit create-by-name and rename operations reject duplicate titles; cwd-only Sessions, Sessions with invalid historical cwd values, and unattached Sessions remain Ungrouped.
- The UI and Host admit distinct same-basename directories as separate Workspaces, while the explicit rename operation rejects duplicate titles; cwd-only Sessions, Sessions with invalid historical cwd values, and unattached Sessions remain Ungrouped.
- Confirmed Workspace deletion removes only the registration, retains the current Session, directory, files, and session log, and survives reload; package tests pin unary/frame/baseline races and failure rollback.
- Keyless runnable snapshots cover the zero state, explicit creation, and the first send; package-level tests cover bootstrap, membership validation, ordering, idempotency, failure recovery, and arbitrary frame order.
@@ -19,13 +19,12 @@ Host 在 Workspace entity 上提供以下 GUI 接线:
| RPC | 行为 |
| --- | --- |
| `workspace.list` | 返回持久有序的 Workspace,并过滤未通过 header 校验的 Session id |
| `workspace.create({ name })` | 在 `workspaceRoot/name` 创建目录和 Workspace;显示名冲突时失败 |
| `workspace.create({ path })` | 按 canonical path 收编已有目录;由 basename 派生的显示名可以重复 |
| `workspace.delete({ workspaceId })` | 移除 Workspace 注册记录,同时保留目录和会话日志;相关 Session 进入 Ungrouped |
| `session.create({ workspaceId, sessionId? })` | 从 Workspace 解析 cwd,以可选预分配 id 幂等创建 Session 并 attach |
| `session.create({ cwd })` | 保留给非 Workspace 调用方,创建 Ungrouped Session |
`workspaceRoot` 是独立 Host 配置,未配置时回退到 Host cwd;它与保存 Workspace domain 数据的 `storageRoot` 无关。Host 流推送 Workspace 与 Session 增量,包括 `host/workspace-removed`Client 重连后分别刷新 `workspace.list``session.list` 基线。删除注册记录的所有权与安全边界由 [Workspace 注册记录删除 Agent Note](2026-07-27-workspace-registration-deletion.md)定义。
Host 流推送 Workspace 与 Session 增量,包括 `host/workspace-removed`Client 重连后分别刷新 `workspace.list``session.list` 基线。删除注册记录的所有权与安全边界由 [Workspace 注册记录删除 Agent Note](2026-07-27-workspace-registration-deletion.md)定义。
Workspace 的 `sessionIds` 是有序候选索引。成员投影同时要求 id 位于索引且对应 `SessionHeader.cwd` canonical 后等于 Workspace pathSessionHeader 不增加 `workspaceId`。cwd 匹配但未入索引的 Session 保持 Ungrouped,索引命中但 header 缺失、cwd 无效或 cwd 不匹配的 id 被过滤。同一 Session 被两个 Workspace 索引占用属于损坏状态并明确报错。
@@ -52,7 +51,7 @@ Session 自己持有首条输入并驱动一条内部流水线:必要时以预
顶部 New Session、Workspace 行内加号和 Workspace picker 最终都调用同一 New Session 动作:显式 Workspace id 直接成为目标,未指定时使用最近 Workspace,没有真实 Workspace 时使用 Workspace Intent。Workspace picker 的单一 Add workspace 动作(见[单一路径 Note](../simplification/2026-07-31-one-route-to-add-a-workspace.md);本决策做出时是 Use an existing folder 与按名称创建两个动作)会在用户确认目录时立即创建真实 Workspace,再把前端 Session 定位到该 Workspace;即使用户不发送消息,显式创建的空 Workspace 也保留。
新建 Workspace 的显示名取自其所在目录。不同 canonical path 可以拥有相同的 basename 派生显示名(见[身份决策](../bug-fix/2026-07-31-same-basename-workspace-adoption.md));显式的按名称创建和重命名操作仍保留显示名重名检查。跨 Workspace 移动 Session、从 Ungrouped 手动收编以及分别输入显示名和目录名仍不在此动线范围内。
新建 Workspace 的显示名取自其所在目录。不同 canonical path 可以拥有相同的 basename 派生显示名(见[身份决策](../bug-fix/2026-07-31-same-basename-workspace-adoption.md));显式的重命名操作仍保留显示名重名检查。跨 Workspace 移动 Session、从 Ungrouped 手动收编以及分别输入显示名和目录名仍不在此动线范围内。
### 首次发送与恢复
@@ -108,7 +107,7 @@ Sidebar 与 conversation empty hero 通过 slot 获得标准化动作:`startSe
- Workspace list 只读取 header 完成一次可重入 bootstrapinitialized 的空 registry 重启不重复初始化,成员读取同时校验索引与 canonical cwd。
- 初始默认目标只在两份基线 ready 后确定一次;Workspace 组不因 hydration 或 Session 活跃整体重排,单个活跃 Session 只前移自身。
- 真实 Workspace 下的前端 Session 临时计入 sidebar 数量,Workspace Intent 保持隐藏,发布与刷新都不会留下重复行或重复计数。
- UI 与 Host 会将 canonical path 不同但 basename 相同的目录接纳为独立 Workspace,而显式的按名称创建和重命名操作会拒绝重复显示名;cwd-only Session、无效历史 cwd 和未 attach Session 保持 Ungrouped。
- UI 与 Host 会将 canonical path 不同但 basename 相同的目录接纳为独立 Workspace,而显式的重命名操作会拒绝重复显示名;cwd-only Session、无效历史 cwd 和未 attach Session 保持 Ungrouped。
- 经确认的 Workspace 删除只移除注册记录,保留当前 Session、目录、文件和会话日志,并在刷新后保持该状态;包级测试固定一元响应/帧/基线竞态和失败回滚行为。
- keyless runnable snapshot 覆盖零态、显式创建和首次发送;包级测试覆盖 bootstrap、成员校验、排序、幂等、失败恢复及任意 frame 顺序。
@@ -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/2026-08-04-web-context-source-and-steer-marks.md
2026-08-04-web-context-source-and-steer-marks.md: d74badedaa9623014dbba10ae68ca680daf75de1
2026-08-04-web-context-source-and-steer-marks.zh.md: b2fd990f6f868fdf422ba97ddd25d19705041e3a
2026-08-04-web-context-source-and-steer-marks.md: 01bdca873a847f70b4b8632b961e01e099ae4f04
2026-08-04-web-context-source-and-steer-marks.zh.md: b6a9cc5692826b402b5a08ec65a5c8fc3c547b6b
@@ -37,11 +37,12 @@ The transcript names all three roles a non-prompt message can play — injected
## Testing
- `packages/client/runtime` unit coverage pins each source kind, the label fallbacks when a name field is missing, empty, or wrongly typed, the unnamed degradation for a source with no readable kind, and steering reconstruction on reset and live append paths.
- `packages/client/ui-conversation` jsdom coverage pins the role title, the producer label beside it, the label's survival while expanded, the roleless header, and the steering caption on both durable and pending bubbles.
- The keyless assembled-Web goldens carry the named header and the steering caption, so the assembled transcript — not only component tests — proves the marks.
- `packages/client/ui-conversation` jsdom coverage pins the role title, the producer label beside it, the label's survival while expanded, and the roleless header.
- The keyless assembled-Web goldens carry the named header, so the assembled transcript — not only component tests — proves the marks.
## Consequences
- **Superseded in part.** The steering-caption clause of the Decision no longer describes master: the [caption removal](../simplification/2026-08-10-web-remove-steering-interjection-caption.md) deleted the `插话` / `Interjection` caption, leaving a mid-turn steer recognizable only by its position in the flow. The context-source and recall naming in the Decision stays current, and the `SteeringMessageNode` projection is unchanged.
- A reader can attribute every non-prompt message in the transcript at a glance, and the header stays honest for logs this client version has never seen a producer for.
- Producer names in the UI are package-shaped (`dsh-tool-skill`, `@deepseek-ai/dsh-system-prompt`) wherever the source carries only a plugin id. That is the cost of refusing a client-side name table; a producer that wants a better label must record one in its source fields.
- `ContextMessageNode` gains a required field, so every constructed node — including test fixtures — must supply it.
@@ -37,11 +37,12 @@ transcript 为非提示消息可能承担的三种角色分别命名:注入上
## 测试
- `packages/client/runtime` 单元覆盖钉住每个来源分支、名称字段缺失/为空/类型不符时的回退、来源没有可读 kind 时的无名降级,以及 reset 和实时 append 路径上的 steering 重建。
- `packages/client/ui-conversation` 的 jsdom 覆盖钉住角色标题、标题旁的生产者名称、展开后该名称的留存无名时的标题形态,以及持久与待处理气泡上的 steering 标注
- 无密钥的组装 Web 黄金基线携带带名称的标题栏与 steering 标注,因此证明这些标识的是组装后的 transcript,而不只是组件测试。
- `packages/client/ui-conversation` 的 jsdom 覆盖钉住角色标题、标题旁的生产者名称、展开后该名称的留存,以及无名时的标题形态。
- 无密钥的组装 Web 黄金基线携带带名称的标题栏,因此证明这些标识的是组装后的 transcript,而不只是组件测试。
## 后果
- **部分被取代。** 决策中的 steering 标注条款已不再描述 master:[标注移除决策](../simplification/2026-08-10-web-remove-steering-interjection-caption.md)删除了 `插话` / `Interjection` 标注,轮次中途的 steer 只能靠它在消息流中的位置辨认。决策中的上下文来源与召回命名仍然有效,`SteeringMessageNode` 投影未变。
- 读者一眼即可归因 transcript 中每一条非提示消息;即便面对本客户端版本从未见过其生产者的日志,标题栏依然如实。
- 只要来源仅携带插件 id,UI 中的生产者名称就呈现为包名形态(`dsh-tool-skill``@deepseek-ai/dsh-system-prompt`)。这是拒绝客户端名称表的代价;想要更好标签的生产者必须在来源字段中记录该标签。
- `ContextMessageNode` 增加了一个必填字段,因此每一处构造该节点的代码——包括测试 fixture——都必须提供它。
@@ -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/2026-08-07-default-model-follows-the-picker.md
2026-08-07-default-model-follows-the-picker.md: ed7e7a424d2cacadea890506fd9150ffdf7a993c
2026-08-07-default-model-follows-the-picker.zh.md: 523c6f917dedf21c726ce5631226ba545126c757
2026-08-07-default-model-follows-the-picker.md: 10f2d12a017a63d4651add7ce5c4d30aa3c8090c
2026-08-07-default-model-follows-the-picker.zh.md: b232ee22cc6580d85545d26c1a50e27780e00855
@@ -6,13 +6,13 @@ English | [中文](2026-08-07-default-model-follows-the-picker.zh.md)
## Problem
A session model picker and a deployment default are two layers of the same preference. If the picker affects only its addressed session, the next blank session can select a different model with no user-facing way to align the default. If the default lives inside a Host gateway, direct Agent front doors cannot share it without depending on Host or duplicating state.
A session model picker and a deployment default are two layers of the same preference. If the picker affects only its addressed session, the next blank session can select a different model with no user-facing way to align the default. If the default lives inside a Host gateway, direct Agent entry points cannot share it without depending on Host or duplicating state.
Reasoning effort makes the persistence shape significant: a model selection without an effort must clear a stored effort, or the next Agent may apply an effort that its selected model does not accept.
## Decision
`AgentDefaultModelService` provides `ctx.agentDefaultModel` and registers `{provider, model, reasoningEffort?}` as the `agent-default-model` Settings section. Its `{provider, model}` composition entry is the base layer and `settings.yaml` supplies the user layer. The service is front-door-neutral, so direct creation and ApiProxy-backed creation share one default ([headless direct core front door](../architecture/2026-08-09-headless-direct-core-front-door.md)). `workspaceRoot` remains ApiProxy config because it is a Host launcher fact rather than model state.
`AgentDefaultModelService` provides `ctx.agentDefaultModel` and registers `{provider, model, reasoningEffort?}` as the `agent-default-model` Settings section. Its `{provider, model}` composition entry is the base layer and `settings.yaml` supplies the user layer. The service is entry-point-neutral, so direct creation and ApiProxy-backed creation share one default ([headless direct core entry point](../architecture/2026-08-09-headless-direct-core-entry-point.md)).
`reasoningEffort` belongs to the Settings section but not to the plugin config. Settings layers merge by field, so a configured effort would survive a user selection that omits it. `saveSelection()` instead writes the complete user section; absence therefore clears a stored effort. A deployment-wide effort default belongs to the adapter profile, which resolves it per model.
@@ -6,13 +6,13 @@ Status: implemented
## 问题
会话模型选择器与部署默认值是同一项偏好的两个层次。如果选择器只影响其所在会话,下一个空白会话可能选择不同模型,用户却没有途径使默认值与选择器一致。如果默认值位于 Host 网关内部,直接创建 Agent 的前门只有依赖 Host 或复制状态才能共享它。
会话模型选择器与部署默认值是同一项偏好的两个层次。如果选择器只影响其所在会话,下一个空白会话可能选择不同模型,用户却没有途径使默认值与选择器一致。如果默认值位于 Host 网关内部,直接创建 Agent 的入口只有依赖 Host 或复制状态才能共享它。
推理强度使持久化形态成为约定的一部分:不含强度的模型选择必须清除已存强度,否则下一个 Agent 可能会采用所选模型不接受的强度。
## 决定
`AgentDefaultModelService` 提供 `ctx.agentDefaultModel`,并把 `{provider, model, reasoningEffort?}` 注册为 `agent-default-model` Settings 分节。其 `{provider, model}` 组合条目是 base 层,`settings.yaml` 提供用户层。该服务不偏向特定前门,因此直接创建与 ApiProxy 支撑的创建共享同一个默认值([headless 直接 core 前门](../architecture/2026-08-09-headless-direct-core-front-door.md))。`workspaceRoot` 仍是 ApiProxy 配置,因为它是 Host 启动器事实,而不是模型状态
`AgentDefaultModelService` 提供 `ctx.agentDefaultModel`,并把 `{provider, model, reasoningEffort?}` 注册为 `agent-default-model` Settings 分节。其 `{provider, model}` 组合条目是 base 层,`settings.yaml` 提供用户层。该服务不偏向特定入口,因此直接创建与 ApiProxy 支撑的创建共享同一个默认值([headless 直接 core 入口](../architecture/2026-08-09-headless-direct-core-entry-point.md)
`reasoningEffort` 属于 Settings 分节,但不属于插件配置。Settings 层按字段合并,因此已配置的强度会在用户选择省略它时继续存在。`saveSelection()` 写入完整的用户分节;缺席值由此清除已存强度。部署级强度默认值属于适配器 profile,并由它按模型解析。
@@ -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/2026-08-08-dsh-run-headless-command.md
2026-08-08-dsh-run-headless-command.md: 566eeb5b2a09a0d07d72a68e4a5f449d2822e708
2026-08-08-dsh-run-headless-command.zh.md: 177410e783a37026940829da5f81343ddc61cb29
2026-08-08-dsh-run-headless-command.md: ed095f4077a23e51bffb647d24eed19ba09e11ed
2026-08-08-dsh-run-headless-command.zh.md: 89d54e35573f14786e05d648f2b42891ca27a043
@@ -22,7 +22,7 @@ dsh run [--profile <name>] [--patch <path>...] <task...>
`RunInvocation` is a distinct `DshInvocation` member. The generic profile invocation carries no task state and accepts no positional arguments. Both dispatch paths use `runProfile`: profile boot omits `task`, while `run` supplies it. A one-shot profile without `headless-runner` fails through the composed-row check, and profile boot containing that row without a task points to `dsh run --profile <name> "<task>"`.
The [profile plugin bundle decision](../architecture/2026-08-05-profile-plugin-bundles.md) owns composition. [Headless is a direct core front door](../architecture/2026-08-09-headless-direct-core-front-door.md) owns the execution contract: one fresh persisted Session, final assistant text on stdout, completed/non-completed exit mapping, empty stderr on success, no listening port, and bounded signal shutdown after Agent quiescence and Session flush.
The [profile plugin bundle decision](../architecture/2026-08-05-profile-plugin-bundles.md) owns composition. [Headless is a direct core entry point](../architecture/2026-08-09-headless-direct-core-entry-point.md) owns the execution contract: one fresh persisted Session, final assistant text on stdout, completed/non-completed exit mapping, empty stderr on success, no listening port, and bounded signal shutdown after Agent quiescence and Session flush.
The `run` verb belongs only to one-shot task execution. Application-file launch requires a distinct command name.
@@ -22,7 +22,7 @@ dsh run [--profile <name>] [--patch <path>...] <task...>
`RunInvocation` 是单独的 `DshInvocation` 成员。通用 profile 调用不携带任务状态,也不接受位置参数。两条分派路径都使用 `runProfile`profile 启动省略 `task`,而 `run` 提供该字段。缺少 `headless-runner` 的一次性 profile 会触发组合行检查;如果启动的 profile 包含该行却未提供任务,错误会指向 `dsh run --profile <name> "<task>"`
[profile 插件组合包决策](../architecture/2026-08-05-profile-plugin-bundles.md)负责组合。[Headless 是直接 core 前门](../architecture/2026-08-09-headless-direct-core-front-door.md)负责执行约定:一个新的持久化会话、stdout 上的最终 assistant 文本、completed/非 completed 的退出状态映射、成功时为空的 stderr、无监听端口,以及 Agent 完全停稳且会话 flush 后的有界信号关闭。
[profile 插件组合包决策](../architecture/2026-08-05-profile-plugin-bundles.md)负责组合。[Headless 是直接 core 入口](../architecture/2026-08-09-headless-direct-core-entry-point.md)负责执行约定:一个新的持久化会话、stdout 上的最终 assistant 文本、completed/非 completed 的退出状态映射、成功时为空的 stderr、无监听端口,以及 Agent 完全停稳且会话 flush 后的有界信号关闭。
`run` 动词只负责一次性任务执行。应用文件启动需要不同的命令名。
@@ -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/2026-08-08-user-explicit-skill-invocation.md
2026-08-08-user-explicit-skill-invocation.md: 74d9f01f191005db6d3d283a3c56f5ee664447f8
2026-08-08-user-explicit-skill-invocation.zh.md: 0f7c9e1261dda796d988c17ddf7199b74be4133e
2026-08-08-user-explicit-skill-invocation.md: a7c2c15703af318cb4112f2d3dfda698bc5e3bc2
2026-08-08-user-explicit-skill-invocation.zh.md: a8d685e5eb12766bebddebb7f5993579cf08531e
@@ -10,14 +10,14 @@ A `disable-model-invocation: true` skill is user-only by design: it never enters
## Decision
User-explicit invocation is a host-side pre-step injection, uniform for every user-invocable skill and every front end:
User-explicit invocation is a host-side pre-step injection, uniform for every user-invocable skill and every entry point:
- `dsh-tool-skill` registers a second `agent/pre-step` listener (beside its catalog listener, the same seam `workspace-instructions` and the runtime-context snapshot ride): it scans the step's claimed messages for whitespace-bounded `/name` tokens — anywhere in the text, the same word-boundary shape the transcript chip decoration uses — collects first-seen-deduplicated names, loads each through `ctx.skills.get`, checks `isUserInvocable` on the loaded definition (the single lookup that produces what is injected), renders it with the shared `renderSkillContent`, and appends the injections after every other injection of the step: background first (workspace rules, runtime policy, catalog), the material the model must act on last, closest to its answer. Registration order pins the placement — the gesture listener registers before the catalog listener, so the waterfall hands it the catalog-bearing list to extend.
- Precision is closed-set matching, exactly like slash commands: `/goal` resolves against the command registry, `/name` against the workspace's user-invocable skill directory; a miss stays ordinary prose, so nothing is ever guessed. Only `source.kind === 'user'` messages are scanned — external text cannot forge a gesture. Paths (`/usr/bin`), fractions (`5/8`), and prefixed tokens (`foo/name`) all break the boundary.
- The client keeps the [plain-text-reference decision](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md): a menu pick lands the literal `/name ` and the prompt ships it verbatim; ui-skill implements no adjudication hooks and no reference codec. `skill.list` (now the domain's only RPC) serves every user-invocable skill with `modelInvocable` so menus mark user-only entries. A name shared with a host command resolves to the command — adjudication claims the line client-side before it becomes a prompt.
- The injection is a `user`-role message carrying the `skill-invocation` source (`{ name, form: 'instructions' }`), so `user/message` logging, the context-injection transcript row (labelled with the skill name), and replay all come free; `renderSkillContent` lives in the `dsh-skill` seam, shared verbatim with the `skill` tool result, and the catalog's closing sentence tells the model to follow an injected block instead of re-loading it.
Peer-product survey (Pi, OpenCode, Claude Code, Kimi Code, Codex, DeepSeek-Reasonix — local checkouts) was unanimous that user-explicit triggering is programmatic injection with zero model participation; the final shape is closest to Codex's core-side `$name` mention scanning, which likewise frees every front end from implementing recognition.
Peer-product survey (Pi, OpenCode, Claude Code, Kimi Code, Codex, DeepSeek-Reasonix — local checkouts) was unanimous that user-explicit triggering is programmatic injection with zero model participation; the final shape is closest to Codex's core-side `$name` mention scanning, which likewise frees every entry point from implementing recognition.
## Alternatives considered
@@ -10,14 +10,14 @@ Status: implemented
## 决策
用户显式调用是一次宿主侧的 pre-step 注入,对每一个用户可调用的 skill 和每一种前端一致:
用户显式调用是一次宿主侧的 pre-step 注入,对每一个用户可调用的 skill 和每一种运行入口一致:
- `dsh-tool-skill` 注册第二个 `agent/pre-step` 监听器(与其目录监听器并列,也是 `workspace-instructions` 与运行时上下文快照搭乘的同一 seam):它在该步骤已认领的消息中扫描以空白为界的 `/name` token——文本中任意位置均可,与 transcript(文本记录)chip 装饰所用的词边界形状相同——收集按首见去重的名称,逐个经 `ctx.skills.get` 加载,在已加载定义上检查 `isUserInvocable`(产生注入内容的正是这同一次查找),用共享的 `renderSkillContent` 渲染,并把注入追加在该步骤所有其他注入之后:背景在前(工作区规则、运行时策略、目录),模型必须着手处理的材料在最后、最贴近它的回答。注册顺序钉住了这一位置——手势监听器先于目录监听器注册,因此 waterfall(瀑布式事件)会把携带目录的列表交给它来扩展。
- 精确性来自封闭集合匹配,与斜杠命令完全一致:`/goal` 对照命令注册表解析,`/name` 对照工作区的用户可调用 skill 目录解析;未命中即保持为普通行文,因此绝不猜测。只扫描 `source.kind === 'user'` 的消息——外部文本无法伪造手势。路径(`/usr/bin`)、分数(`5/8`)与带前缀的 token`foo/name`)都会破坏该边界。
- 客户端沿用[纯文本引用决策](../architecture/2026-07-25-web-input-machine-and-slash-pipeline.md):菜单 pick 落下字面文本 `/name `,该文本随提示词原样提交;ui-skill 不实现任何裁决钩子,也没有引用 codec。`skill.list`(现在是该领域唯一的 RPC)提供每一个用户可调用的 skill 并携带 `modelInvocable`,供菜单标出仅限用户的条目。与宿主命令同名的名称解析为命令——客户端会在该行成为提示词之前完成裁决并将其认领。
- 注入是一条携带 `skill-invocation` 来源(`{ name, form: 'instructions' }`)的 `user` 角色消息,因此 `user/message` 落账、上下文注入的 transcript 行(以 skill 名称标注)与回放全部免费获得;`renderSkillContent` 位于 `dsh-skill` seam,由注入和 `skill` 工具结果共用,二者内容逐字相同,目录的结尾一句会告诉模型遵循注入块而不是重新加载。
同类产品调研(Pi、OpenCode、Claude Code、Kimi Code、Codex、DeepSeek-Reasonix——本地检出)一致表明:用户显式触发都是模型零参与的程序化注入;最终形态最接近 Codex 核心侧的 `$name` mention 扫描——它同样让每一种前端免于自行实现识别。
同类产品调研(Pi、OpenCode、Claude Code、Kimi Code、Codex、DeepSeek-Reasonix——本地检出)一致表明:用户显式触发都是模型零参与的程序化注入;最终形态最接近 Codex 核心侧的 `$name` mention 扫描——它同样让每一种运行入口免于自行实现识别。
## 考虑过的替代方案
@@ -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/2026-07-05-uniform-agent-note-format.md
2026-07-05-uniform-agent-note-format.md: 06082251c1b96c90ed470d84224662e00e29791b
2026-07-05-uniform-agent-note-format.md: c05d81c700b81f0d619173a261f405b1cc039df1
2026-07-05-uniform-agent-note-format.zh.md: 3daa686b64b31ee2638b25dd4c42e5d8172f1d97
@@ -23,7 +23,7 @@ The whole corpus was normalized in the same change that defined the format — t
- **A bare `# <title>` H1** — rejected: the `Agent Note: ` prefix self-describes the genre when a file is read outside its tree, and the format gate prevents it from drifting.
- **`## What we give up` as the implemented closer** (the README's own phrase for what an Agent Note records) — rejected: it names only costs, and an honest consequences section records what the trade-off bought as well.
- **Convention without a gate** (write the contract down, enforce by review) — rejected: the slop checklist already outlawed spec-speak in `implemented/` by convention, and nineteen files show what convention alone achieves here.
- **A standalone `FORMAT.md` contract file** — rejected because one front door carrying layout, classification, and format is easier to discover and maintain than two contract files.
- **A standalone `FORMAT.md` contract file** — rejected because one entry point carrying layout, classification, and format is easier to discover and maintain than two contract files.
## Consequences
@@ -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/2026-07-19-remove-generated-agent-note-index.md
2026-07-19-remove-generated-agent-note-index.md: ee85ec0757d5924f5784c43a50003eb96e0a9531
2026-07-19-remove-generated-agent-note-index.md: 652ac72afe69284240667e61af1f3fbfcb182ddb
2026-07-19-remove-generated-agent-note-index.zh.md: 6e1967fbde0c6ac59bbc3a184dad68c989efadbc
@@ -12,7 +12,7 @@ The centralized chronological list adds little discovery value beyond browsing t
## Decision
The lifecycle/class filesystem tree is the Agent Note inventory. [README.md](../../README.md) remains the curated front door and contract, while ordinary tree navigation and repository search provide discovery.
The lifecycle/class filesystem tree is the Agent Note inventory. [README.md](../../README.md) remains the curated entry point and contract, while ordinary tree navigation and repository search provide discovery.
`scripts/agent-note-tree.ts` owns the closed lifecycle/class sets and structural walker. `verify-agent-note-classification` validates that tree and rejects the legacy homes and a root `INDEX.md`; it does not render or freshness-check a centralized list.
@@ -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/2026-07-22-product-first-root-readme.md
2026-07-22-product-first-root-readme.md: 32542a45019d64ed1826d4eb21e68c67c3c3d52e
2026-07-22-product-first-root-readme.md: 00f6084da9e83135c881abfef21b0b249cd4e30a
2026-07-22-product-first-root-readme.zh.md: 8ef6f4b99ca2c935183a225b6357d2d128edb3b0
@@ -6,7 +6,7 @@ English | [中文](2026-07-22-product-first-root-readme.zh.md)
## Problem
The root README is the repository's product front door. Its product-first structure and established voice remain useful, but concrete entry points and capability claims drift as the runtime grows. Rewriting sections whose facts remain correct increases the review surface and discards language that already works.
The root README is the repository's product entry point. Its product-first structure and established voice remain useful, but concrete entry points and capability claims drift as the runtime grows. Rewriting sections whose facts remain correct increases the review surface and discards language that already works.
## Decision
@@ -26,7 +26,7 @@ Detailed package and service inventories remain at their owning documentation. T
**Use a long marketing page with screenshots, badges, and duplicated tutorials.** Rich media can demonstrate a stable product journey, but it ages separately from commands and source contracts. The root stays compact and links to runnable examples and owned guides.
**Project the root README as the documentation website home page.** A single landing page avoids two narratives, but the website's user guide and the repository's product/developer front door have different navigation and maintenance needs.
**Project the root README as the documentation website home page.** A single landing page avoids two narratives, but the website's user guide and the repository's product/developer entry point have different navigation and maintenance needs.
## Consequences
@@ -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/2026-08-03-package-anchored-subsystem-pages.md
2026-08-03-package-anchored-subsystem-pages.md: f429f3d41c1f152e83faeb12c379d221627e767f
2026-08-03-package-anchored-subsystem-pages.zh.md: 3a56fa39357591197606a28b49cf0eac8f58963e
2026-08-03-package-anchored-subsystem-pages.md: 2a47f35e9d3755286bed7d42f59fd21e30f9148d
2026-08-03-package-anchored-subsystem-pages.zh.md: 53216a430b979f0612f256aaec9774b88fe14bbd
@@ -14,7 +14,7 @@ Every `docs/subsystems/` page anchors to the package or package group that decla
Every type a generated signature references must resolve somewhere in the folder: the agent ownership vocabulary moved from the generator's `TYPE_LINK_EXEMPTIONS` into `LINK_MAP → core.md`, so exemptions are reserved for genuinely service-local or vendored shapes. Each pasted declaration has one home (`SessionEvent` lives on [session.md](../../../../docs/subsystems/session.md); core.md summarizes and links).
Every `packages/<group>/README.md` pair is a thin front door in one shape: a why-first intro paragraph, a package table (Package / Role / ctx key), and a closing pointer to the owning subsystems page. Load-bearing prose that outgrows that shape relocates to the owning subsystems page rather than being deleted.
Every `packages/<group>/README.md` pair is a thin entry point in one shape: a why-first intro paragraph, a package table (Package / Role / ctx key), and a closing pointer to the owning subsystems page. Load-bearing prose that outgrows that shape relocates to the owning subsystems page rather than being deleted.
The [subsystems README](../../../../docs/subsystems/README.md) indexes every page in the folder on both language sides; `scripts/project-doc-site.spec.ts` enforces one table row per page, so a page added by a later PR (or absorbed in a merge) cannot silently miss the index.
@@ -14,7 +14,7 @@ Status: implemented
生成签名引用的每个类型都必须能在目录中某处解析:agent 所有权词汇从生成器的 `TYPE_LINK_EXEMPTIONS` 移入 `LINK_MAP → core.md`,因此豁免只留给真正服务本地或 vendored 的形状。每个粘贴的声明只有一个家(`SessionEvent` 位于 [session.md](../../../../docs/subsystems/session.md)core.md 概括并链接)。
每个 `packages/<group>/README.md` 配对都是统一形状的轻薄门面:一段以「为什么」开头的介绍、一张包表格(包 / 角色 / ctx 键)、一个指向拥有方子系统页面的收尾指针。超出该形状的承重散文迁移到拥有方子系统页面,而非删除。
每个 `packages/<group>/README.md` 配对都是统一形状的精简入口:一段以「为什么」开头的介绍、一张包表格(包 / 角色 / ctx 键)、一个指向拥有方子系统页面的收尾指针。超出该形状的承重散文迁移到拥有方子系统页面,而非删除。
[子系统 README](../../../../docs/subsystems/README.md) 在两个语言侧索引目录中的每一页;`scripts/project-doc-site.spec.ts` 强制每页一行表格,因此后续 PR 新增(或合并吸收)的页面无法悄悄缺席索引。
@@ -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/2026-07-23-acp-automation-only-protocol.md
2026-07-23-acp-automation-only-protocol.md: 29da3025251f9826c5780493bb2725b114a40601
2026-07-23-acp-automation-only-protocol.md: 56c433acf59d3a0c4b5c8b6605e422d3c4efede2
2026-07-23-acp-automation-only-protocol.zh.md: bf326ce9f6fea8c55b842bc61e3d8521032ea4d1
@@ -46,7 +46,7 @@ Protocol and lifecycle tests pin stop-reason and prompt codecs, version negotiat
## Consequences
ACP has a narrow contract suitable for agents and automation, while TUI and Web own human interaction and presentation. The package has fewer injected services, dependencies, protocol branches, and lifecycle states, and it no longer claims compatibility as a general editor front door.
ACP has a narrow contract suitable for agents and automation, while TUI and Web own human interaction and presentation. The package has fewer injected services, dependencies, protocol branches, and lifecycle states, and it no longer claims compatibility as a general editor entry point.
Automation clients receive complete committed text rather than token deltas or structured tool UI. They inspect durable logs or another API when they need reasoning, tool traces, titles, or richer state. Fresh-session-only operation also means callers that need durable browsing or resume use a host API rather than ACP.
@@ -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/2026-07-29-simplify-web-image-input-v1.md
2026-07-29-simplify-web-image-input-v1.md: e7847dc2ae18f48146cb2b686dcda64beebf2350
2026-07-29-simplify-web-image-input-v1.zh.md: c9e0a3cc5dc07b70be4b0c1244921ccac567d9af
@@ -0,0 +1,37 @@
# Agent Note: Simplify Web image input version one
Status: implemented
English | [中文](2026-07-29-simplify-web-image-input-v1.zh.md)
## Problem
The first durable Web image-input slice introduced required ordered multi-image intake alongside speculative surfaces for arbitrary CLI provider mounting, output-modality discovery, alternative text, provider-neutral visual token pricing, and browser lifecycle APIs with no cross-package consumer. Keeping the speculative surfaces would turn unchosen future behavior into public contracts and make the initial capability harder to review and maintain.
## Decision
Version one accepts ordered image batches bounded by configurable per-message count and aggregate-byte limits plus per-image byte and pixel limits. The browser rejects unsupported declared formats before preview allocation, while the host authoritatively decodes the complete batch, checks current deployment bounds, validates every image without storage writes, and only then saves every image while preserving submitted order in the resulting durable blocks. Request buffering derives directly from the attachment service's aggregate image-byte limit. This preserves validation atomicity without adding a batch transaction, rollback protocol, or policy snapshot in `host.describe`.
Provider/model selection remains configuration and profile state. The boot composition registers the shipped DeepSeek, OpenAI, and Anthropic routes; the CLI does not add image-specific selection flags, inspect the yml provider roster, or dynamically mount an adapter.
Exact-model metadata carries only the input modalities that current admission decisions consume. `ImageBlock` carries the durable attachment reference; its optional display name supplies accessible UI text, so the core block has no separate alternative-text field. Provider-neutral token estimation does not apply one provider's visual pricing formula to other routes.
The attachment seam exposes its limits plus storage-free `validateImage`, `saveImage`, and `readImage`. The host depends on that seam rather than implementation re-exports. Browser draft and historical-image operations remain concrete conversation-plugin internals; the public `IConversation` face contains only the input registry and the scoped send, cancel, and history verbs used across package boundaries.
## Alternatives considered
**Accept only one image.** Comparing or combining several images is a current product requirement. Count and aggregate-byte bounds keep that path finite without reducing it to a single image.
**Add a storage transaction or rollback protocol.** Storage-free validation prevents malformed later members from leaving earlier valid members unreferenced. Stronger all-or-nothing storage across independent content-addressed objects would require ownership or reclamation semantics that the current product path does not need.
**Keep future-facing fields and methods as placeholders.** Output modalities, block alternative text, and active-model handshake data had no current decision consumer. Adding them later with their first consumer preserves freedom to choose the correct contract.
**Estimate every image with one tile formula.** Visual pricing varies by provider, model, detail mode, and preprocessing. A hard-coded provider-neutral estimate would look authoritative while being wrong; provider usage is the authoritative accounting source.
**Add CLI provider/model selection or dynamic mounting.** Configuration already owns route selection, plugin composition, and credentials. Duplicating those choices in image-input flags would require parsing or mutating the config tree outside the loader.
## Consequences
The feature retains the two batch limits and one storage-free validation method required by multi-image prompts, while removing unrelated public fields, lifecycle operations, policy snapshots, and route-assembly branches. Provider/model selection remains composition or profile configuration. Pre-request token pressure may undercount visual input until a provider-aware estimator is designed, while reported usage remains exact.
Reintroducing any removed surface requires a concrete consumer and its failure, lifecycle, replay, and testing contract rather than compatibility with this pre-release shape.
@@ -0,0 +1,37 @@
# Agent Note: 简化 Web 图片输入第一版
Status: implemented
[English](2026-07-29-simplify-web-image-input-v1.md) | 中文
## 问题
首个持久化 Web 图片输入切片在引入按顺序接收多张图片的必需能力时,也引入了由 CLI(命令行界面)挂载任意提供方、输出模态发现、替代文本、提供方无关的视觉 token 定价,以及没有跨包(package)消费方的浏览器生命周期 API 等推测性表面。保留这些推测性表面会把尚未选择的未来行为变成公共契约,并使初始能力更难评审和维护。
## 决策
第一版接受有序图片批次,并以可配置的每条消息图片数量与图片总字节数上限,以及单张图片字节数与像素上限约束批次。浏览器会在分配预览前拒绝声明不支持的格式,而宿主会以权威方式解码完整批次、检查当前部署上限、在不写入存储的情况下校验每张图片,之后才保存每张图片,并在生成的持久图片块中保留提交顺序。请求缓冲上限直接由附件服务的图片总字节数上限派生。这样无需添加批次事务、回滚协议或 `host.describe` 中的策略快照,就能保持校验的原子性。
提供方/模型选择仍属于配置和 profile 状态。启动组合会注册交付的 DeepSeek、OpenAI 和 Anthropic 路由;CLI 不会添加图片专用选择标志、检查 yml 提供方清单或动态挂载适配器。
确切模型元数据只携带当前准入决策会消费的输入模态。`ImageBlock` 携带持久附件引用;其可选显示名称提供无障碍 UI 文本,因此核心块没有单独的替代文本字段。与提供方无关的 token 估算不会把某一提供方的视觉定价公式应用于其他路由。
附件服务边界公开其限制、不触碰存储的 `validateImage`,以及 `saveImage``readImage`。宿主依赖该服务边界,而不是实现层重新导出的内容。浏览器草稿和历史图片操作仍是具体会话插件的内部实现;公开的 `IConversation` 表面只包含输入注册表,以及跨包边界使用的按作用域发送、取消和历史记录操作。
## 曾考虑的替代方案
**只接受一张图片。** 比较或组合多张图片是当前产品要求。图片数量和总字节数上限使这条路径保持有界,而无需将其缩减为单张图片。
**添加存储事务或回滚协议。** 不触碰存储的校验能防止后面的畸形成员使前面有效的成员成为无引用对象。若要在独立的内容寻址对象之间实现更强的全有或全无存储保证,就需要当前产品路径并不需要的所有权或回收语义。
**将面向未来的字段和方法保留为占位符。** 输出模态、块替代文本和活跃模型握手数据目前都没有决策消费方。等到第一个消费方出现时再加入这些内容,可以保留选择正确契约的自由。
**使用一种图块公式估算每张图片。** 视觉定价因提供方、模型、细节模式和预处理而异。一项硬编码且与提供方无关的估算会看似权威,实际却是错误的;提供方用量才是权威核算来源。
**添加 CLI 提供方/模型选择或动态挂载。** 配置已经负责路由选择、插件组合和凭据。在图片输入标志中重复这些选择,会要求在 loader 之外解析或修改配置树。
## 后果
该功能保留了多图片提示词所需的两个批次上限和一个不触碰存储的校验方法,同时移除了无关的公开字段、生命周期操作、策略快照和路由组装分支。提供方/模型选择仍属于组合或 profile 配置。在设计出提供方感知型估算器之前,请求前的 token 压力计算可能少计视觉输入,而上报的用量仍保持精确。
重新引入任何已移除表面时,都必须有具体消费方,并为其定义失败、生命周期、回放和测试契约,而不是为了兼容这一预发布形态。
@@ -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/2026-07-31-one-route-to-add-a-workspace.md
2026-07-31-one-route-to-add-a-workspace.md: 46bd5d5ca5ecfbc340fcb46b6da5e9f237764ab1
2026-07-31-one-route-to-add-a-workspace.zh.md: 6a6e8b3fc9f64a62d3264f4c7779d11c8515e447
2026-07-31-one-route-to-add-a-workspace.md: 4de79b7db30853a13319aa016d4eb5fb5d9ec1f1
2026-07-31-one-route-to-add-a-workspace.zh.md: 2b305494c5d61db11f9ecf247c323040e6a549bf
@@ -25,9 +25,9 @@ The direct-open path carries the busy rule the menu entry states: while a pick i
`WorkspaceCreateFlow` is now `WorkspacePickFlow` and its `createOnly` prop is `addOnly`; the injected `createWorkspace` narrows from `{ name } | { path }` to `{ path }`.
## Wire and CLI residue
## Wire and CLI surface
The host's `workspace.create` still accepts `{ name }`, and `dsh web --workspace-root` still feeds its target directory, but no product surface reaches either any more. The same is true of the client contract that carried the name to the wire: `WorkspaceCreateInput`, `WorkspacesService.create`'s `{ name }` arm, `intentName`'s name branch, and the manager's "name under workspaceRoot" contract. `apps/cli/README.md` and its Chinese counterpart still document `--workspace-root` as creating named Workspaces. The whole set is marked for deletion at the call site in `packages/host/apiproxy/src/api-proxy.ts` and left to a follow-up change: it is backend, client-contract, and CLI surface with its own test fallout (the api-proxy workspace suite, the runtime workspace suite, the config catalog), and the release-blocking part of this decision is the UI.
`workspace.create` accepts only `{ path }`; the wire schema and `WorkspaceApi` have no `name` member. The gateway has no `workspaceRoot` config, the client contract exposes only path adoption through `WorkspaceCreateInput`, `WorkspacesService.create`, and `intentName`, and `dsh web` has no `--workspace-root` flag. `workspace-name-conflict` remains on the wire as `workspace.rename`'s duplicate-title error.
## Testing
@@ -45,13 +45,13 @@ The host's `workspace.create` still accepts `{ name }`, and `dsh web --workspace
**Keep the menu shell for entries we might add later (clone a repo, remote directory).** Rejected under "require a current owner and need": no such entry exists, and restoring a menu when one arrives is a smaller change than shipping an empty frame now.
**Delete the wire's create-by-name branch in the same change.** Rejected here: it is backend/CLI surface with a wider test fallout, and the urgent decision is the UI. See the residue section — it is marked, not forgotten.
**Delete the wire's create-by-name branch in the same change.** Rejected because the UI decision did not depend on the backend and CLI deletion, whose separate contracts and tests formed an independently reviewable change.
**Register the workspace through the host in the e2e scaffold instead of driving the dialog.** Rejected: it would have decoupled all 15 scenarios from the picker, so nothing in the lane would prove the surviving route reaches a live composer. Every scenario now walks the real dialog to adopt its directory; only the create-a-folder half is concentrated in one scenario, because repeating it everywhere makes the shared helper non-idempotent for no extra signal.
## Consequences
- Creating a Workspace outside the operator's chosen directory is no longer possible from the UI; the server-controlled `--workspace-root` target was the one way to constrain where new workspace folders land, and nothing replaces it. A deployment that needs that constraint has to re-introduce it deliberately.
- The one remaining route browses the host filesystem, so the picker's reach is now the whole host rather than one configured parent. That is already the browse occupant's contract; this change makes it the only contract.
- A composition that mounts `ui-workspace` without any directory-picker package can no longer add a Workspace at all, and now says so by omitting the button instead of offering a create-by-name fallback.
- The UI creates Workspace folders only under a directory the operator chooses. No server-controlled configuration constrains that location; a deployment that needs such a constraint must add it deliberately.
- The picker's configured reach defines the host filesystem available to the remaining route; there is no separate configured parent.
- A composition that mounts `ui-workspace` without a directory-picker package cannot add a Workspace and omits the button.
- The hero chip still announces `aria-haspopup="menu"` while the direct-open path raises a dialog instead. Making that truthful means routing the flow's presentation choice up through the `conversation.hero.workspace` owner contract — the flow owns the decision, the chip owns the announcement, and they sit in different packages — so it is a named follow-up rather than a silent inconsistency. The sidebar button this change added makes no popup claim at all.
@@ -25,9 +25,9 @@ Status: implemented
`WorkspaceCreateFlow` 现更名为 `WorkspacePickFlow`,其 `createOnly` prop 更名为 `addOnly`;注入的 `createWorkspace``{ name } | { path }` 收窄为 `{ path }`
## Wire and CLI residue
## Wire CLI 表层
Host 侧的 `workspace.create` 接受 `{ name }``dsh web --workspace-root` 也仍在为它提供目标目录,但已没有任何产品表层会走到它们。把名称送到 wire 的客户端约定同样如此:`WorkspaceCreateInput``WorkspacesService.create``{ name }` 分支、`intentName` 的名称分支,以及 manager 中"workspaceRoot 下的 name"这一约定。`apps/cli/README.md` 及其中文对照本也仍把 `--workspace-root` 记为"创建具名 Workspace"。这一整套都在 `packages/host/apiproxy/src/api-proxy.ts` 的调用点标记为待删除,并留给后续改动:它横跨 backend、客户端约定与 CLI 面,有各自的测试波及面(api-proxy workspace 套件、runtime workspace 套件、配置目录),而本决定中阻塞发布的部分是 UI
`workspace.create` 接受 `{ path }`wire schema 与 `WorkspaceApi` 没有 `name` 成员。网关没有 `workspaceRoot` 配置;客户端约定只通过 `WorkspaceCreateInput``WorkspacesService.create``intentName` 提供按路径接纳,`dsh web` 没有 `--workspace-root` flag。`workspace-name-conflict` 仍保留在 wire 上,作为 `workspace.rename` 的标题重名错误
## Testing
@@ -45,13 +45,13 @@ Host 侧的 `workspace.create` 仍接受 `{ name }``dsh web --workspace-root`
**为将来可能新增的入口(克隆仓库、远程目录)保留菜单壳。** 否决,依据"require a current owner and need":这样的入口目前并不存在,而等它到来时再恢复菜单,比现在就发一个空壳的改动更小。
**在同一改动中删除 wire 的按名称创建分支。** 在此否决:那是 backend/CLI 面,测试波及面更广,而紧急的决定是 UI。见 residue 一节——它是被标记了,不是被遗忘了
**在同一改动中删除 wire 的按名称创建分支。** 否决,因为 UI 决定不依赖后端与 CLI 删除,后两者各自的约定和测试构成一项可独立评审的改动
**在 e2e scaffold 中经 host 注册 workspace,而不驱动对话框。** 否决:那会让全部 15 个场景与选择器解耦,整条 lane 将无法证明幸存的这条路径能走到可用的 composer。现在每个场景都会走真实对话框来接纳自己的目录;只有"新建文件夹"那一半集中在一个场景里,因为处处重复只会让共享辅助函数失去幂等性,却换不来额外信号。
## Consequences
- UI 已无法在操作者选定目录之外创建 Workspace;服务端控制的 `--workspace-root` 目标曾是约束新 workspace 文件夹落点的唯一手段,现在没有替代品。需要该约束的部署必须有意识地重新引入它
- 仅存的这条路径会浏览宿主机文件系统,因此选择器的可达范围现在是整台宿主机,而非一个配置好的父目录。这本就是浏览占用者的约定,本改动使它成为唯一的约定
- 挂载 `ui-workspace`未挂任何 directory-picker 包的组合,已完全无法添加 Workspace;现在它通过不渲染按钮来说明这一点,而不是提供一个按名称创建的兜底
- UI 在操作者选择的目录下创建 Workspace 文件夹。没有服务端控制的配置约束其位置;需要该约束的部署必须明确加入该约束
- picker 配置的可达范围决定剩余路径可用的 Host 文件系统;不存在另一个配置好的父目录
- 挂载 `ui-workspace`没有 directory-picker 包的组合无法添加 Workspace,也不渲染按钮
- 主视觉区的 chip 仍声明 `aria-haspopup="menu"`,而直接拉起的路径实际弹出的是对话框。要让它如实,需要把流程的展示方式经 `conversation.hero.workspace` 的 owner 约定上报——决定权在流程,播报权在 chip,两者分属不同的包——因此这被列为一项具名的后续工作,而不是一处无声的不一致。本次新增的侧边栏按钮完全不作任何 popup 声明。
@@ -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/2026-08-04-remove-tui-package.md
2026-08-04-remove-tui-package.md: f048a04db02b582d038ebf549999c0fda50e30d3
2026-08-04-remove-tui-package.md: 19cc7d1a89a55bb57a69b9fce301f48f89384acd
2026-08-04-remove-tui-package.zh.md: be18cbd33cd4a2bb592de4e7986b2786da272d0f
@@ -8,7 +8,7 @@ English | [中文](2026-08-04-remove-tui-package.zh.md)
Removing the implicit `dsh` terminal application left `@deepseek-ai/dsh-tui` without a shipped composition. The package still carried a terminal renderer, interactive command and question adapters, extension overlays, snapshot fixtures, a patched `pi-tui` dependency, and SDK scaffolding that advertised TUI as a supported application interface. Keeping that surface required maintaining a product-sized frontend whose only remaining consumer was the project generator itself.
The package also made the repository's supported application inventory misleading. Current runnable products use Web, ACP, JSON-RPC, or one-shot CLI front doors, while the SDK continued to offer a terminal choice that no example or product command exercised.
The package also made the repository's supported application inventory misleading. Current runnable products use Web, ACP, JSON-RPC, or one-shot CLI entry points, while the SDK continued to offer a terminal choice that no example or product command exercised.
## Decision
@@ -34,6 +34,6 @@ Repository searches and generated catalogs contain no TUI package, dependency pa
## Consequences
DeepSeek Harness has no terminal UI package or generated TUI application. Existing imports, `cordis.yml` rows, SDK `--interface=tui` requests, and projects that depend on the package fail instead of being translated. Web remains the shipped interactive surface; ACP, JSON-RPC, and one-shot CLI remain the non-Web front doors.
DeepSeek Harness has no terminal UI package or generated TUI application. Existing imports, `cordis.yml` rows, SDK `--interface=tui` requests, and projects that depend on the package fail instead of being translated. Web remains the shipped interactive surface; ACP, JSON-RPC, and one-shot CLI remain the non-Web entry points.
The provider-neutral command, user-interaction, approval, tool-presentation, PTY, and session-projection capabilities remain available to other hosts. Reintroducing a terminal frontend requires a named product or deployment, an explicit package boundary, a concrete interaction provider, and assembled lifecycle and transcript acceptance for that frontend.
@@ -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: c1153f5e9fcc89585e926f8f088829c849d1f6c1
2026-08-08-remove-cli-demo.md: 403e01f94c976d2d17eb391830721b31675cd6a9
2026-08-08-remove-cli-demo.zh.md: 7f11e0c17a15454b99b32d14ea6eda177f4b01f6
@@ -6,7 +6,7 @@ English | [中文](2026-08-08-remove-cli-demo.zh.md)
## Problem
After [`dsh run`](../feature/2026-08-08-dsh-run-headless-command.md) became the product one-shot command, `@deepseek-ai/dsh-cli-demo` remained a second application package for the same job. It carried another executable, argument grammar, app composition, cancellation lifecycle, text/JSON/stream-JSON output contract, built artifact, documentation surface, and test suite. The two front doors also assembled different trees, so a successful demo did not prove the shipped `headless` profile and users had to choose between overlapping commands.
After [`dsh run`](../feature/2026-08-08-dsh-run-headless-command.md) became the product one-shot command, `@deepseek-ai/dsh-cli-demo` remained a second application package for the same job. It carried another executable, argument grammar, app composition, cancellation lifecycle, text/JSON/stream-JSON output contract, built artifact, documentation surface, and test suite. The two entry points also assembled different trees, so a successful demo did not prove the shipped `headless` profile and users had to choose between overlapping commands.
The replay suites still need canonical session events to pin assembled backend behavior. That testing need does not require a published command or compatibility contract.
@@ -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-web-remove-steering-interjection-caption.md
2026-08-10-web-remove-steering-interjection-caption.md: 2c396f54945fb1c3626f2e5fcc849e81893c23f0
2026-08-10-web-remove-steering-interjection-caption.zh.md: 088b36449130f9e8f1be5bec7a3ee4a812b4b6f1
@@ -0,0 +1,36 @@
# Agent Note: Remove the steering interjection caption
Status: implemented
English | [中文](2026-08-10-web-remove-steering-interjection-caption.zh.md)
## Problem
The [context-source and steer marks decision](../feature/2026-08-04-web-context-source-and-steer-marks.md) captioned every durable and pending steering bubble with `插话` / `Interjection` so the transcript could say which right-aligned bubble interrupted a running turn. The caption repeats what the flow already shows: a steering bubble sits mid-turn, between the assistant content it interrupted, while a turn-opening prompt sits at a turn boundary. A permanent line of tertiary text above every steer bubble buys no reading a position-aware reader does not already have, and it is the only chrome any user-style bubble carries, so it also breaks the otherwise uniform right-aligned rhythm.
## Decision
Steering renders exactly as a user bubble. `UserStyleBubble` has no steering flag, the `message.steering` locale key and the `.steeringMark` style are deleted, and `PendingSteeringBubble` and `UserMessageNodeView` pass only content and actions. A mid-turn steer is recognizable by its position inside the running turn's flow, and by nothing else.
The runtime distinction is untouched. `SteeringMessageNode` projection from durable `agent/inbox/spliced` history, the `data-pending-steering` attribute, and the pending-to-durable hand-off all remain: the pending lifecycle needs the node identity regardless of presentation, and tests still locate pending bubbles through the attribute.
This partially supersedes the steering clause of the [context-source and steer marks decision](../feature/2026-08-04-web-context-source-and-steer-marks.md); its context-source and recall naming stays current. The caption has flipped before: the [archived no-steer decision](../../archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md) removed it while the composer could not steer, and the 2026-08-04 decision reintroduced it after the composer gained a Steer gesture. This removal does not revisit the gesture — steering entry, the Queue dock's steer-send action, and the pending lifecycle keep their owners — it judges only that the transcript need not name the result.
## Alternatives considered
**Keep the caption.** It is the status quo and cheap to keep, but it decorates every steer bubble forever to encode a fact the bubble's position already states. Chrome that carries no information a reader lacks is removed, not maintained.
**Remove the `SteeringMessageNode` distinction too.** The node kind is derived from durable inbox history and drives the pending-to-durable hand-off; it is a replay fact, not presentation. Folding it into `UserMessageNode` would change projection behavior for no UI gain.
**Distinguish steering with quieter chrome (tint, indent, hover-only label).** Any replacement re-raises the same question with a weaker vocabulary. The distinction the transcript needs is positional and already visible; adding subtler decoration keeps the cost and loses the one virtue the text caption had, being explicit.
## Testing
- `packages/client/ui-conversation` jsdom coverage pins the plain bubble: the pending hand-off test locates pending bubbles by `data-pending-steering` and asserts the single-bubble hand-off without any caption, and the MessageItem steering arm asserts copy-without-branch on an uncaptioned bubble.
- The keyless assembled-Web goldens (`steering/mid-steer`, `steering/settled`, `plan-review/approved`) replay the unchanged session fixtures with no caption text.
## Consequences
- A replayed transcript no longer names steering: a reader infers a mid-turn interjection from its position inside the turn. That inference is weaker than an explicit label for a reader skimming turn boundaries; the decision accepts this.
- A pending steer bubble is visually identical to an ordinary sent bubble until admission; only its missing clock time differs.
- Reintroducing steering chrome of any form requires a new product decision superseding this note.
@@ -0,0 +1,36 @@
# Agent Note: 移除 steering 插话标注
Status: implemented
[English](2026-08-10-web-remove-steering-interjection-caption.md) | 中文
## 问题
[上下文来源与 steer 标识决策](../feature/2026-08-04-web-context-source-and-steer-marks.md)给每个持久与待处理的 steering 气泡加上了 `插话` / `Interjection` 标注,让 transcript 能说明哪条右对齐气泡打断了正在运行的轮次。这个标注重复了消息流已经呈现的事实:steering 气泡位于轮次中途、夹在被它打断的助手内容之间,而开轮提示位于轮次边界。在每个 steer 气泡上方常驻一行三级文字,并没有让一个能看到位置的读者多读出任何信息,而且它是所有用户样式气泡中唯一带装饰的,还破坏了原本统一的右对齐节奏。
## 决策
steering 完全按用户气泡渲染。`UserStyleBubble` 不再有 steering 标志,`message.steering` locale 键与 `.steeringMark` 样式已删除,`PendingSteeringBubble``UserMessageNodeView` 只传内容与操作。轮次中途的 steer 只能靠它在运行轮次消息流中的位置辨认,除此之外没有任何标识。
运行时的区分保持不变。从持久 `agent/inbox/spliced` 历史投影 `SteeringMessageNode``data-pending-steering` 属性、待处理到持久的交接全部保留:待处理生命周期无论呈现如何都需要节点身份,测试也仍通过该属性定位待处理气泡。
本决策部分取代[上下文来源与 steer 标识决策](../feature/2026-08-04-web-context-source-and-steer-marks.md)中的 steering 条款;其上下文来源与召回命名仍然有效。这个标注此前已经翻转过一次:[已归档的取消 steer 装饰决策](../../archived/simplification/2026-07-31-web-ui-no-steer-entry-or-interjection-chrome.md)在 composer 无法 steer 时移除了它,2026-08-04 的决策在 composer 获得 Steer 手势后把它加了回来。本次移除不重议手势本身——steering 入口、Queue dock 的插话发送操作、待处理生命周期各归其主——只判定 transcript 不需要为其结果命名。
## 考虑过的替代方案
**保留标注。** 它是现状,维持成本低,但它永久装饰每个 steer 气泡,只为编码气泡位置已经陈述的事实。不承载读者缺少的信息的装饰应当删除,而不是维护。
**连 `SteeringMessageNode` 区分一起删。** 节点类型派生自持久 inbox 历史,驱动待处理到持久的交接;它是回放事实,不是呈现。把它并入 `UserMessageNode` 会改变投影行为,却没有任何 UI 收益。
**换更安静的装饰(底色、缩进、悬停标签)。** 任何替代装饰都会用更弱的表达重新提出同一个问题。transcript 需要的区分是位置性的、已经可见的;换成更含蓄的装饰保留了成本,却丢掉了文字标注唯一的优点,就是明确。
## 测试
- `packages/client/ui-conversation` 的 jsdom 覆盖固定了纯气泡行为:待处理交接测试通过 `data-pending-steering` 定位待处理气泡,在没有任何标注的前提下断言单气泡交接;MessageItem 的 steering 分支在无标注气泡上断言可复制且无分支操作。
- 无密钥的组装 Web goldens`steering/mid-steer``steering/settled``plan-review/approved`)用未变的会话 fixture 回放,不含标注文字。
## 后果
- 回放的 transcript 不再为 steering 命名:读者靠消息在轮次中的位置推断这是一次中途插话。对快速扫读轮次边界的读者,这个推断弱于显式标签;本决策接受这一代价。
- 待处理的 steer 气泡在被准入前与普通已发送气泡在视觉上完全一致,仅缺少时钟时间。
- 重新引入任何形式的 steering 装饰都需要一个取代本 note 的新产品决策。
+1
View File
@@ -83,6 +83,7 @@ External packages that a workspace package resolves at runtime. `scripts/install
| [`pnpm`](https://github.com/pnpm/pnpm) | MIT |
| [`react`](https://github.com/facebook/react) | MIT |
| [`react-dom`](https://github.com/facebook/react) | MIT |
| [`sharp`](https://github.com/lovell/sharp) | Apache-2.0 |
| [`shiki`](https://github.com/shikijs/shiki) | MIT |
| [`supports-color`](https://github.com/chalk/supports-color) | MIT |
| [`tsx`](https://github.com/privatenumber/tsx) | MIT |

Some files were not shown because too many files have changed in this diff Show More