Merge remote-tracking branch 'origin/master' into feat/loader-entry-disabled-interpolation

2026-08-11 13:40:24 +08:00
parent 6fb226ea24 b0e022c150
commit f00a29111b
535 changed files with 12687 additions and 1999 deletions
@@ -298,12 +298,24 @@
    "process/2026-07-23-browser-demo-gif-recording.i18n.yaml": "sha256:808ccdda39e540645b440e40a2124baed737b98636265d8f6d8cf036a70f0d50",
    "process/2026-07-23-browser-demo-gif-recording.md": "sha256:4d3a3dc829c75b66f4f57a6a763b4b9562ce10efb90a19308142f598c5ea8524",
    "process/2026-07-23-browser-demo-gif-recording.zh.md": "sha256:409e5d31ea87f35c5227fcd1bd105167f580a8a24d29a223ce390b29eb31639a",
+    "process/2026-07-23-personal-staging-maintenance-skills.i18n.yaml": "sha256:cbd5c32f2997713339699f4c12876b1950895fcb21594927c7509e3cb4c5b8d5",
+    "process/2026-07-23-personal-staging-maintenance-skills.md": "sha256:a1ef960ddc47c8bc14578d8432ed0ac4272e31178937780989e4e3b3e3f4d49f",
+    "process/2026-07-23-personal-staging-maintenance-skills.zh.md": "sha256:c0f3fcf0914af88cafcc7e094a2131bd1f764003defc6eaa446b743319e73ec1",
    "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.i18n.yaml": "sha256:89b6dc255cb0dd9d97ae6f34f37d185412d4260d7bf2f87d6b25e340f01dc26e",
    "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.md": "sha256:1742e09435ade4a09349c8843eb381e870a2be2d51b74449f08260422c8096b3",
    "process/2026-07-26-gui-pr-gif-evidence-and-assets-branch.zh.md": "sha256:220bd53a88617b09ee8970627c46540fa8951724b102acfe296a7ed7d0f7b5fe",
    "process/2026-07-27-wine-windows-gates-experiment.i18n.yaml": "sha256:6f4cbc12ee9cddbb297bf7e138ccabcd204f66898a0f7411b1633f03d5a9eab5",
    "process/2026-07-27-wine-windows-gates-experiment.md": "sha256:8d37dcdab058098c7de3da1de00ce61bef92bbc8d6ee71add959474c6fb3e936",
    "process/2026-07-27-wine-windows-gates-experiment.zh.md": "sha256:77fbf04df36af09e55007a93bd6b22d08ff99869efe8de3e97dac5b4701e0a9e",
+    "process/2026-07-31-installer-adopts-existing-checkout.i18n.yaml": "sha256:e7d072856cd3df3b717d94647be4ea05db087b114df4b11d68a171677b94c970",
+    "process/2026-07-31-installer-adopts-existing-checkout.md": "sha256:d97e39d07bde30d534417a406fc6c56ee6765dbc7b671888d17ef2cac9a7c6dc",
+    "process/2026-07-31-installer-adopts-existing-checkout.zh.md": "sha256:ab445493c1aacf3f8dc091bdbd765ad56c551ae613e0d8156610f0c4614a7431",
+    "process/2026-08-04-forward-only-pr-issue-status.i18n.yaml": "sha256:af23e203a66a95674154899410e2f420d1d0685dbf856c24cfccdaa547a17925",
+    "process/2026-08-04-forward-only-pr-issue-status.md": "sha256:2d31077da47d95ab3ddf64d5efc6b1b8fb7c7709d39aca4a825ef9e9d382d501",
+    "process/2026-08-04-forward-only-pr-issue-status.zh.md": "sha256:b61f865b7a8a0ac901250a3edbb92ea73177067c4c25448c7088925c2caeccd7",
+    "process/2026-08-08-review-driven-issue-lifecycle-triggers.i18n.yaml": "sha256:4c28c59d3fc323e7cd01eff31f1fe759834719c5bede1e82b39f868970bf856d",
+    "process/2026-08-08-review-driven-issue-lifecycle-triggers.md": "sha256:1b0514de5d030170e91e12e4d6ba788a9247f840e82700faa385a1c0c76ab857",
+    "process/2026-08-08-review-driven-issue-lifecycle-triggers.zh.md": "sha256:028d78d61f603d8bac64c4cce20b393a78f8e029d3bb4976e79a47ecaefa6032",
    "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.i18n.yaml": "sha256:ad3d1263cb0051b885173bf064de62065e2c646ccaae2d7250723da3b4eab90c",
    "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.md": "sha256:8fb061d51c8c23b47d2367814bab3623c6d5b972f38d207a273caa9030b579bd",
    "simplification/2026-06-20-drop-unconsumed-llm-adapter-change-event.zh.md": "sha256:2ffeaca91f82844a5616d6dcce6b4af514bb8a7c46f78e47f668b204ac6edc04",
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-23-personal-staging-maintenance-skills.md
-2026-07-23-personal-staging-maintenance-skills.md: a7ccc5b1e0f13e880c58a93d2e4c2cd4f06e2a93
-2026-07-23-personal-staging-maintenance-skills.zh.md: 8593291f510352429cbb29679e7d033589312e41
+2026-07-23-personal-staging-maintenance-skills.md: 86654be1afe986107e7dae4440b497a266636012
+2026-07-23-personal-staging-maintenance-skills.zh.md: 7593a2e8cafc93df02c9418c94f84bbd3f154a0c
@@ -1,6 +1,7 @@
 # Agent Note: Personal staging maintenance skills

 Status: implemented
+Archived: 2026-08-10

 English | [中文](2026-07-23-personal-staging-maintenance-skills.zh.md)

@@ -1,6 +1,7 @@
 # Agent Note: 个人集成分支维护 skill

 Status: implemented
+Archived: 2026-08-10

 [English](2026-07-23-personal-staging-maintenance-skills.md) | 中文

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-31-installer-adopts-existing-checkout.md
-2026-07-31-installer-adopts-existing-checkout.md: 1d45a14273095610e3ed8047da2ce9f4ca95cbb6
-2026-07-31-installer-adopts-existing-checkout.zh.md: 971bc3b389c341b314872b8e45ab20ebd2ed5b2c
+2026-07-31-installer-adopts-existing-checkout.md: 08eec47a1cf1254409df93ab83ddf503b4d7d171
+2026-07-31-installer-adopts-existing-checkout.zh.md: dc3cc5ee8dbbe287860ad02f4bdba66afb4fbeaf
@@ -1,6 +1,7 @@
 # Agent Note: the installer adopts an existing checkout into the managed layout

 Status: implemented
+Archived: 2026-08-10

 English | [中文](2026-07-31-installer-adopts-existing-checkout.zh.md)

@@ -1,6 +1,7 @@
 # Agent Note: 安装器把已有检出接管进受管布局

 Status: implemented
+Archived: 2026-08-10

 [English](2026-07-31-installer-adopts-existing-checkout.md) | 中文

@@ -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/2026-08-04-forward-only-pr-issue-status.md
-2026-08-04-forward-only-pr-issue-status.md: dd567707bc7fccd0a631943ab3ffd2838a7f2f76
-2026-08-04-forward-only-pr-issue-status.zh.md: f7fee58d6afb812f97569ae4d86c3d6504f35752
+2026-08-04-forward-only-pr-issue-status.md: 56004a39ce52c77429574f481d9945cdc4936d30
+2026-08-04-forward-only-pr-issue-status.zh.md: ee85319842d3245bdfab9668de0a42ab29597fac
@@ -1,6 +1,7 @@
 # Agent Note: Forward-only PR-to-Issue status projection

 Status: implemented
+Archived: 2026-08-10

 English | [中文](2026-08-04-forward-only-pr-issue-status.zh.md)

@@ -1,6 +1,7 @@
 # Agent Note: PR 到 Issue 的状态仅向前投射

 Status: implemented
+Archived: 2026-08-10

 [English](2026-08-04-forward-only-pr-issue-status.md) | 中文

@@ -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/2026-08-08-review-driven-issue-lifecycle-triggers.md
-2026-08-08-review-driven-issue-lifecycle-triggers.md: 8a2d48ee23da4c20bb832ae0109e2ea9912dac83
-2026-08-08-review-driven-issue-lifecycle-triggers.zh.md: 004739ff471815b0fe12e111eba0ec7aaaef9507
+2026-08-08-review-driven-issue-lifecycle-triggers.md: 444927968912d93f473e27ae8576e8371b9c287c
+2026-08-08-review-driven-issue-lifecycle-triggers.zh.md: 6e00e2a936b6421824743e779756011fcd4a1c9e
@@ -1,6 +1,7 @@
 # Agent Note: Review-driven Issue lifecycle triggers

 Status: implemented
+Archived: 2026-08-10

 English | [中文](2026-08-08-review-driven-issue-lifecycle-triggers.zh.md)

@@ -1,6 +1,7 @@
 # Agent Note: 由评审驱动的 Issue 生命周期触发器

 Status: implemented
+Archived: 2026-08-10

 [English](2026-08-08-review-driven-issue-lifecycle-triggers.md) | 中文

@@ -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/2026-06-21-mandatory-app-attribution-headers.md
-2026-06-21-mandatory-app-attribution-headers.md: 12482ca80d19e5cd1e62b8860865db6cccea61ab
-2026-06-21-mandatory-app-attribution-headers.zh.md: 43f356887948b88d34ba41d46ed1cd2f1c89a1e2
+2026-06-21-mandatory-app-attribution-headers.md: 39050a53ec76e8c5a6cac4d8e31fa15b992c406e
+2026-06-21-mandatory-app-attribution-headers.zh.md: bfd6aa2540022f68cf9f69ccc2c12b3bc0978960
@@ -32,7 +32,7 @@ The provider-neutral identity is owned by `dsh-llm` (`packages/llm/llm/src/attri

 - product token for `User-Agent`: `deepseek-harness` (continuity with the pre-Agent Note wire value and the repo/org identity)
 - version: read from the owning package's manifest via `createRequire`, never a hand-copied constant
- app URL: `https://github.com/deepseek-ai/deepseek-harness-sdk` - the planned public home, which must exist before release
+- app URL: `https://github.com/deepseek-ai/deepseek-harness` - the repository home

 The default is mandatory and non-empty. White-label deployments pass their own `AppIdentity` to `attributionHeaders(identity)` - the override hook is the function parameter, with no deployment config plumbing until a consumer needs it - and omission falls back to the harness default rather than suppressing attribution. There is no per-request API for the model, user prompt, session id, cwd, user email, API key owner, or local machine identity to influence these fields.

@@ -77,8 +77,6 @@ The landed contract:

 **Providers see that traffic comes from the harness.** That is the point, but it means deployments that previously blended into generic SDK traffic become identifiable. Mitigation: send only static public product data and let forks/white-label deployments pass their own `AppIdentity`.

-**The app URL points at a repository that does not exist yet.** `deepseek-ai/deepseek-harness-sdk` is the planned public home; until it is created the URL is a dangling promise that blocks release.
-
 **Header support differs by client library.** The hand-rolled adapter sets headers directly; the pi-ai-backed adapter depends on pi-ai continuing to honor `StreamOptions.headers` (merged last over provider defaults). The wire-level mock-server tests are the guard: if a pi-ai upgrade stops delivering the header, the suite goes red. This is useful pressure on the abstraction: a provider adapter that cannot set mandatory headers cannot fully implement the harness LLM contract.

 **OpenRouter rankings do not benefit yet.** `User-Agent` is the correct baseline for provider-neutral HTTP identity, but it will not create OpenRouter app pages or rankings because OpenRouter requires `HTTP-Referer` for that product feature. That is deliberate: public app marketplace participation is a separate product decision, not a prerequisite for mandatory request attribution.
@@ -32,7 +32,7 @@ OpenRouter 应用归属刻意未实现。`HTTP-Referer`、`X-OpenRouter-Title`

 - `User-Agent` 的产品 token：`deepseek-harness`（与 Agent Note 之前的线路值及仓库/组织身份保持连续性）
 - 版本：通过 `createRequire` 从所属包的 manifest（元数据清单）读取，绝不手动复制常量
- 应用 URL：`https://github.com/deepseek-ai/deepseek-harness-sdk`——计划中的公开主页，且必须在发布前实际存在
+- 应用 URL：`https://github.com/deepseek-ai/deepseek-harness`——仓库主页

 默认值是强制的且非空。白标部署通过向 `attributionHeaders(identity)` 传入自己的 `AppIdentity` 来覆盖——覆盖钩子就是函数参数，在有消费方需要之前不做部署配置管道——省略时回退到 harness 默认值而非抑制归属。没有逐请求 API 允许模型、用户提示词、会话 id、cwd、用户邮箱、API key 所有者或本地机器身份影响这些字段。

@@ -77,8 +77,6 @@ OpenRouter 应用归属刻意未实现。`HTTP-Referer`、`X-OpenRouter-Title`

 **提供方看到流量来自 harness。** 这正是目的，但意味着此前混在通用 SDK 流量中的部署变得可识别。缓解措施：仅发送静态公开产品数据，并允许 fork/白标部署传入自己的 `AppIdentity`。

-**应用 URL 指向一个尚不存在的仓库。** `deepseek-ai/deepseek-harness-sdk` 是计划中的公开主页；在它创建之前，该 URL 是一个阻塞发布的悬空承诺。
-
 **不同客户端库的头部支持有差异。** 手写适配器直接设置头部；基于 pi-ai 的适配器依赖 pi-ai 继续尊重 `StreamOptions.headers`（最后合并覆盖提供方默认值）。线路级 mock 服务器测试是守卫：如果 pi-ai 升级后不再投递该头部，套件会变红。这对抽象施加了有益的压力：一个无法设置强制头部的提供方适配器不能完整实现 harness 的 LLM 约定。

 **OpenRouter 排名尚未受益。** `User-Agent` 是提供方无关的 HTTP 身份的正确基线，但它不会创建 OpenRouter 应用页面或排名，因为 OpenRouter 要求 `HTTP-Referer` 来实现该产品功能。这是有意为之：公开应用市场参与是一个独立的产品决策，不是强制请求归属的前提。
@@ -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/2026-07-25-web-client-session-scope-and-provide-channel.md
-2026-07-25-web-client-session-scope-and-provide-channel.md: ff411e1b387dcd83b04f8c02d5dde3c70a815932
-2026-07-25-web-client-session-scope-and-provide-channel.zh.md: 593e194654bb3552ad3cac4534847fba11cf3694
+2026-07-25-web-client-session-scope-and-provide-channel.md: f371b93ccf6cb3ba10cbdb73baa670cbf889f393
+2026-07-25-web-client-session-scope-and-provide-channel.zh.md: 78440131c4e09c9a458009fbe5a2a34a707a481c
@@ -93,7 +93,7 @@ Slot scope is the closed set `root | session-maybe | session`:
 - `session-maybe` follows the current session with ADOPTION identity (the only behavior — there is no hold-identity-forever mode): an incarnation born session-less keeps its React instance across the arrival of the FIRST session (the blank shell adopts it — no remount, the DOM survives), and from then on behaves exactly like a strict session entry — switching to a different session remounts, and dropping back to no-session remounts into a fresh blank incarnation that will adopt again. Component-local per-session state therefore clears by construction; state that must survive a switch belongs in session-bound sources (machine, store, hooks). With no session, `sessionId`, the results of `useSession`/`useInput`, and `inputActions` may all be absent. The unkeyed root `SessionMaybeProvider` drives these updates by subscribing to the runtime's atomic `currentProvide` projection — selection moves and provider-roster changes publish through the same source, so a roster change under a stable current id republishes the mounted bundle instead of stranding entries on an obsolete hook/prop schema — while `SessionMaybeProvideInfo` uses the static key map to retain the complete hook/prop shape even with no session; the per-entry adoption bookkeeping (incarnation-counter key) lives in the renderer's `SessionMaybeEntry`.
 - `session` guarantees that `sessionId`, every hook source, and every prop exist; each strict entry's error boundary is keyed by `sessionId`, so switching sessions recreates that entry and its session store.

-`conversation` is the resident `session-maybe` shell: `ConversationRoot`, HeroShell, the Workspace picker, the root-owned scrollport and composer stack, and the overlay chain's fallback frame retain their React instances across the no-session → blank-session switch. Two strict entries fill fixed regions without reparenting that tree: `conversation.session.header` carries breadcrumb/tabs/actions above the scrollport, while `conversation.session` carries the view ring and draft mirror inside it; both share the same session-scoped chat store. The composer bar (`conversation.composer.bar`) is itself `session-maybe`: with no session it renders inert (machine faces absent, `disabled` owner prop), and the same instance — textarea included — goes live when a session appears; the remaining input slots stay strict `session` and dispatch nothing until then. The blank → engaging/active transition never rebuilds the InputBar on a phase flip.
+`conversation` is the resident `session-maybe` shell: `ConversationRoot`, HeroShell, the Workspace picker, the root-owned scrollport and composer stack, and the overlay chain's fallback frame retain their React instances across the no-session → blank-session switch. Two strict entries fill fixed regions without reparenting that tree: `conversation.session.header` carries breadcrumb/tabs/actions above the scrollport, while `conversation.session` carries the view ring and draft mirror inside it; both share the same session-scoped chat store. The composer bar (`conversation.composer.bar`) is itself `session-maybe`: with no session its machine faces and message actions are inert, while the whole dashed card opens the existing Workspace picker by pointer and its read-only textarea does the same through Enter or Space. The same instance — textarea included — goes live when a session appears; the remaining input slots stay strict `session` and dispatch nothing until then. The blank → engaging/active transition never rebuilds the InputBar on a phase flip.

 - The runtime's first built-in entry: the `'session'` hook — `useSession` itself rides the same mechanism, no special-casing.
 - Concurrent discipline: the render plane reads only from the hooks compartment (uSES consistency guarantee); props-compartment callbacks are used only in event-handler space; descriptor resolution is render-safe (idempotent caching, with prune reaping residue from abandoned renders).
@@ -132,5 +132,5 @@ Slot scope is the closed set `root | session-maybe | session`:
 - Plugins gain session context isomorphic to the host's: per-session state hangs on the actx and mounts/tears down in one piece with the scope fiber, making leaks structurally impossible; two-session isolation is structurally guaranteed by the scope filter.
 - The client object layer converges to a wire mirror: session identity, lifecycle, and capability adjudication all defer to the host entity — the input system (the next layer) always faces a session with a real Agent, and providers like slash/skill uniformly address by sessionId directly.
 - Blank-session governance takes zero dedicated mechanisms: state rides one derived bit, visibility rides the unified list projection (only the current blank shows, as `New Session`), reclamation rides lazy persistence's existing contract (evaporation on restart), and the ordinary ceiling rides same-Workspace reuse.
- The cost: the id→ctx handoff discipline and provide's Concurrent discipline are conventions rather than type-enforced, pinned by review and tests; fully disabled input while no workspace is picked is an experience cost the product surface accepts (the price of the single state axis).
+- The cost: the id→ctx handoff discipline and provide's Concurrent discipline are conventions rather than type-enforced, pinned by review and tests. The single state axis still withholds machine faces until a Session exists; the resident card routes activation to the Workspace picker during that interval ([decision](../feature/2026-08-07-workspace-picker-composer-entry.md)).
 - Known gaps: approval/question recovery across prune (TODO); model selection returns in live-mutation shape (the host `selectModel` trio is ready-made, its client consumer not yet built).
@@ -93,7 +93,7 @@ slot scope 是闭集 `root | session-maybe | session`：
 - `session-maybe` 以**收养（adoption）身份语义**跟随 current session（唯一行为——不存在「永久保持实例」模式）：空态出生的化身在**第一个** session 到来时保持 React 实例（空壳收养它——不重挂，DOM 存活）；此后行为与严格 session entry 完全一致——切到不同 session 重挂，跌回无 session 也重挂为崭新的空态化身（之后再次收养）。因此组件本地的 per-session 状态**由构造保证**随切换清零；需要活过切换的状态必须住 session 绑定的源（machine、store、hooks）。无 session 时 `sessionId`、`useSession`/`useInput` 的选择结果及 `inputActions` 均可缺省。根部无 key 的 `SessionMaybeProvider` 通过订阅 runtime 的原子 `currentProvide` 投影驱动这条更新——选择移动和提供方名册变化经同一 source 发布，current id 不变时的名册变化也会重发已挂载 bundle，而不是把 entry 困在过期的钩子/prop 形状上——`SessionMaybeProvideInfo` 靠静态键表在无 session 时仍保留完整钩子/prop 形状；逐 entry 的收养记账（化身计数 key）住在 renderer 的 `SessionMaybeEntry`。
 - `session` 保证 `sessionId`、所有钩子 source 与 props 均存在；每个严格 entry 的错误边界以 `sessionId` 为 key，切换 session 会重建该 entry 及其 session store。

-`conversation` 是 `session-maybe` 的常驻外壳：`ConversationRoot`、HeroShell、Workspace picker、root 持有的 scrollport 与 composer stack，以及 overlay chain 的 fallback 外框，在无 session → blank session 的切换中保持 React 实例。两个严格 session entry 只填入固定区域，不改变该树的父级：`conversation.session.header` 在 scrollport 上方承载 breadcrumb／tab／action，`conversation.session` 在其内部承载 view ring 与 draft mirror；二者共享同一个 session scope chat store。composer bar（`conversation.composer.bar`）本身即为 `session-maybe`：无 session 时以惰性态渲染（machine face 缺席、`disabled` owner prop），session 出现后同一实例（含 textarea）转为 live；其余输入 slot 保持严格 `session`，在此之前不分发任何条目。blank → engaging/active 的 InputBar 不因 phase 翻转而重建。
+`conversation` 是 `session-maybe` 的常驻外壳：`ConversationRoot`、HeroShell、Workspace picker、root 持有的 scrollport 与 composer stack，以及 overlay chain 的 fallback 外框，在无 session → blank session 的切换中保持 React 实例。两个严格 session entry 只填入固定区域，不改变该树的父级：`conversation.session.header` 在 scrollport 上方承载 breadcrumb／tab／action，`conversation.session` 在其内部承载 view ring 与 draft mirror；二者共享同一个 session scope chat store。composer bar（`conversation.composer.bar`）本身即为 `session-maybe`：无 session 时，其 machine face 和消息操作保持惰性，整张虚线卡片可经指针打开现有 Workspace picker，只读 textarea 也可通过 Enter 或 Space 打开。session 出现后同一实例（含 textarea）转为 live；其余输入 slot 保持严格 `session`，在此之前不分发任何条目。blank → engaging/active 的 InputBar 不因 phase 翻转而重建。

 - 运行时内建第一条：`'session'` 钩子——`useSession` 本身走同一机制，无特判。
 - Concurrent 纪律：渲染平面只从 hooks 格读（uSES 一致性保证）；props 格回调只在事件 handler 空间用；描述符解析 render-safe（幂等缓存、废弃渲染残留由 prune 收尸）。
@@ -132,5 +132,5 @@ slot scope 是闭集 `root | session-maybe | session`：
 - 插件获得与 host 同构的会话上下文：逐会话状态挂 actx、随 scope fiber 一次拆装，泄漏结构性不可能；双会话隔离由 scope filter 结构性保证。
 - client 对象层收敛为 wire 镜像：会话身份、生命周期、能力判别全部以 host 实体为准——输入体系（下一层）面对的永远是「有真 Agent 的会话」，slash/skill 等提供方一律以 sessionId 直接寻址。
 - 空会话治理零专用机制：状态靠一个派生位，可见性靠统一列表投影（仅 current blank 以 `New Session` 展示），回收靠 lazy persistence 的既有约定（重启蒸发），常规上限靠同 Workspace 复用。
- 代价：id→ctx 换乘纪律、provide 的 Concurrent 纪律都是约定而非类型强制，靠 review 与测试钉住；「未选 workspace」期间输入全禁是产品面接受的体验代价（单一状态轴换来的）。
+- 代价：id→ctx 换乘纪律、provide 的 Concurrent 纪律都是约定而非类型强制，靠 review 与测试钉住。单一状态轴仍会在 Session 存在前隐藏 machine face；这段时间内，常驻卡片会把激活操作转到 Workspace picker（[决策](../feature/2026-08-07-workspace-picker-composer-entry.md)）。
 - 已知欠账：approval/question 跨 prune 恢复（TODO）；模型选择以 live-mutation 形状回归（host `selectModel` 三件套现成，其 client 消费方尚未构建）。
@@ -1,33 +0,0 @@
-# Agent Note: Experimental and internal package group
-
-Status: implemented
-
-English | [中文](2026-07-28-experimental-plugin-package-group.zh.md)
-
-## Problem
-
-The [package hierarchy](../../../../packages/README.md) groups plugins by product role, but it cannot distinguish release packages from prototypes or internal-only packages. The team needs an obvious shared place for useful work that is not part of the official release.
-
-## Decision
-
-The subtree rules in [`packages/experimental/AGENTS.md`](../../../../packages/experimental/AGENTS.md) make `packages/experimental/<pkg>/` the required home for Cordis plugin packages whose whole public contract is experimental or internal-only. Package names remain `@deepseek-ai/dsh-<pkg>`.
-
-The group is the team's in-repository place to share engineering and product-manager prototypes: members can discover, run, review, and extend one another's work against the real plugin graph without implying product support.
-
-Official releases exclude this directory. A package enters a release only after moving to its product-role group; release packages cannot take runtime dependencies on packages here. Examples may use them, while any other runtime dependent also belongs here. Tests may use them as development dependencies.
-
-Experimental packages carry no stability, compatibility, migration, or support promise: they may change APIs, configuration, or data, or disappear without deprecation or migration. Internal-only packages may define narrower internal contracts but make no public release promise. Neither status relaxes engineering, security, documentation, lifecycle, testing, or snapshot requirements.
-
-The pending `@deepseek-ai/dsh-tui-session-changes` `/diff` viewer and `/btw` plugin are examples governed by this rule. Promotion into an official release requires explicit review of the public contract, limitations, test evidence, and a named owner accepting stable-package obligations.
-
-## Alternatives considered
-
-**Keep experimental and internal-only packages in product-role groups with README labels.** Labels are easy to miss and cannot enforce dependency boundaries.
-
-**Treat every package as experimental until the first tagged release.** This provides no durable incubation boundary.
-
-**Develop prototypes and internal packages elsewhere.** This loses the real plugin graph, examples, snapshots, and lifecycle checks needed to evaluate them.
-
-## Consequences
-
-The path makes release exclusion and dependency blast radius visible while retaining the real plugin graph for team sharing. It gives up product-role colocation and creates path churn on promotion, while the npm name remains stable. The subtree rules, repository [current-owner/current-need rule](../../../../packages/AGENTS.md), and unchanged engineering gates limit junk-drawer growth. Because official release tooling does not yet exist, contributor policy enforces the exclusion; when such tooling is added, the directory is its required exclusion boundary.
@@ -1,33 +0,0 @@
-# Agent Note: 实验性与内部专用包分组
-
-Status: implemented
-
-[English](2026-07-28-experimental-plugin-package-group.md) | 中文
-
-## 问题
-
-[包层级结构](../../../../packages/README.md)按产品角色对插件分组，但无法区分发布包、原型和内部专用包。团队需要一个明确的共享位置，存放不属于官方发布版本的有价值成果。
-
-## 决策
-
-[`packages/experimental/AGENTS.md`](../../../../packages/experimental/AGENTS.md) 中的子树规则要求所有公开约定整体处于实验状态或仅限内部使用的 Cordis 插件包位于 `packages/experimental/<pkg>/`。包名仍为 `@deepseek-ai/dsh-<pkg>`。
-
-该分组供团队在仓库内共享工程人员和产品经理制作的原型：成员可以基于真实插件图发现、运行、评审并扩展彼此的原型，但这不代表产品会提供支持。
-
-官方发布版本不包含此目录。包只有移入对应的产品角色分组后才会纳入发布版本；发布包不得在运行时依赖此处的包。示例可以使用这些包；其他任何运行时依赖方也必须位于此处。测试可以将它们用作开发依赖。
-
-实验性包不提供稳定性、兼容性、迁移或支持保证：其 API、配置或数据可以变更，包也可以移除，均不提供弃用期或迁移路径。内部专用包可以定义范围更窄的内部约定，但不作公开发布承诺。无论哪种状态，都不降低仓库对工程、安全、文档、生命周期、测试或快照的要求。
-
-尚待完成的 `@deepseek-ai/dsh-tui-session-changes` `/diff` 查看器和 `/btw` 插件都受这项规则约束。将包提升为稳定包并纳入官方发布版本，需要明确评审其公开约定、限制和测试证据，并指定一名愿意承担稳定包义务的负责人。
-
-## 考虑过的替代方案
-
-**将实验性和内部专用包留在产品角色分组中，并用 README 标注。** 标注容易被忽略，也无法强制执行依赖边界。
-
-**首个带标签的版本发布前，将所有包都视为实验性。** 这无法提供持久的孵化边界。
-
-**在其他位置开发原型和内部专用包。** 这会失去评估它们所需的真实插件图、示例、快照和生命周期检查。
-
-## 后果
-
-该路径明确标示不纳入发布版本的包及其依赖影响范围，同时保留供团队共享成果的真实插件图。代价是这些包无法与同产品角色的包共置，提升并纳入发布版本时还会产生路径变动，但 npm 包名保持稳定。子树规则、仓库已有的[「必须有当前负责人和实际需求」规则](../../../../packages/AGENTS.md)以及保持不变的工程门禁，可限制该分组无序膨胀。由于官方发布工具尚不存在，目前由贡献者政策执行这项排除规则；添加发布工具后，必须以该目录为排除边界。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md
-2026-07-29-dsh-source-launch-tsx-esm.md: 5cf4a227f388a1ac8315594af4e0256864ef17f5
-2026-07-29-dsh-source-launch-tsx-esm.zh.md: b5a52b3d01840337c0091310e50d8fac34245519
+2026-07-29-dsh-source-launch-tsx-esm.md: b2428602a780f2880f0f803ba59b16a76b39790e
+2026-07-29-dsh-source-launch-tsx-esm.zh.md: 866bc8886725788e6e619f9507f5c8ccab63f82d
@@ -14,11 +14,11 @@ Startup latency also mattered: the off-thread `module.register()` hooks worker s

 ## Decision

-The `dsh` TUI, Web, and headless source launches run `node --import tsx/esm`: tsx's ESM-only hook owns both TypeScript transformation and tsconfig `paths` projection. `bin/dsh`, the root `dsh`/`demo:tui`/`demo:web` scripts, and the Code Mode TUI overlay use the same vector; `bin/dsh` references the hook and tsconfig by absolute checkout paths (bare `tsx/esm` does not resolve from an arbitrary cwd) and pins `TSX_TSCONFIG_PATH` to the root tsconfig. The CJS hook stays off because the CLI source graph is ESM-only; measured TUI time-to-banner is ~0.7s versus ~1.1s under the full tsx default and ~0.75s under the removed native chain.
+The `dsh` TUI, Web, and headless source launches run `node --import tsx/esm`: tsx's ESM-only hook owns both TypeScript transformation and tsconfig `paths` projection. The root `dsh` script completes the repository build, then uses that vector from the repository root. The CJS hook stays off because the CLI source graph is ESM-only; measured runtime launch to the TUI banner is ~0.7s versus ~1.1s under the full tsx default and ~0.75s under the removed native chain.

 `scripts/tspath-loader.ts` and `apps/cli/src/tsconfig-paths-loader.ts` are deleted. With them went the loader's runtime rule of mapping a workspace import only for declared runtime dependencies — tsx applies the `paths` map unconditionally. Declaration completeness now rests on the static gates alone: `verify-cordis-config` for configured bare plugins, and workspace constraints for manifests. (That runtime rule found real bugs: `dsh-plan-mode` and `dsh-tool-tasks` imported `@deepseek-ai/dsh-llm` while declaring it only in devDependencies; since fixed.)

-The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (`apps/cli/tests/source-launch.compat.spec.ts`): a keyless piped-stdio launch of the exact production vector asserting the non-zero-exit TTY refusal. Any future Node change to module hooks or TypeScript handling turns this gate red instead of breaking developers' `pnpm dsh`.
+The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (`apps/cli/tests/source-launch.compat.spec.ts`): a keyless piped-stdio launch of the exact production runtime vector asserting the non-zero-exit TTY refusal. Any future Node change to module hooks or TypeScript handling turns this gate red instead of breaking developers' `pnpm dsh`.

 ## Alternatives considered

@@ -35,4 +35,4 @@ The node-compat CI matrix (Node 22.19 and 26) gains `dsh-source-launch-smoke` (`
 - One launch vector across the whole engines range, including future Node lines that change native TypeScript support; the smoke gate enforces it per matrix line.
 - TypeScript transformation is delegated to tsx/esbuild again, reversing the prior note's goal of proving Node-native transformation; that goal is unreachable while vendored sources use non-erasable syntax and Node ships no transform mode.
 - The runtime declared-dependency enforcement in source launches is gone; undeclared workspace imports now surface only through static gates or built-mode resolution failures.
- Startup improves ~0.4s over the full tsx default (`demo:headless` now aliases the same `dsh --profile headless` source launch; ACP keeps `--import tsx` because its graph was not audited for CJS-hook dependence and its launch latency is not on the interactive path).
+- Runtime launch improves ~0.4s over the full tsx default; ACP keeps `--import tsx` because its graph was not audited for CJS-hook dependence and its launch latency is not on the interactive path.
@@ -14,11 +14,11 @@ Status: implemented

 ## 决策

-`dsh` 的 TUI、Web 与无头源码启动运行 `node --import tsx/esm`：由 tsx 的 ESM-only 钩子同时负责 TypeScript 转换与 tsconfig `paths` 投影。`bin/dsh`、根目录的 `dsh`/`demo:tui`/`demo:web` 脚本以及 Code Mode TUI overlay 使用同一向量；`bin/dsh` 以 checkout 的绝对路径引用钩子与 tsconfig（裸的 `tsx/esm` 无法从任意 cwd 解析），并将 `TSX_TSCONFIG_PATH` 固定到根 tsconfig。CJS 钩子保持关闭，因为 CLI 源码图是纯 ESM；实测 TUI 到 banner 约 0.7s，对比完整 tsx 默认形态约 1.1s、已移除的原生链约 0.75s。
+`dsh` 的 TUI、Web 与无头源码启动运行 `node --import tsx/esm`：由 tsx 的 ESM-only 钩子同时负责 TypeScript 转换与 tsconfig `paths` 投影。根目录的 `dsh` 脚本先完成仓库构建，然后从仓库根目录使用同一启动方式。CJS 钩子保持关闭，因为 CLI（命令行界面）源码图是纯 ESM；实测运行时启动至 TUI banner 耗时约 0.7s，对比完整 tsx 默认形态约 1.1s、已移除的原生链约 0.75s。

 `scripts/tspath-loader.ts` 与 `apps/cli/src/tsconfig-paths-loader.ts` 已删除。随之消失的还有该 loader「仅为已声明运行时依赖映射 workspace import」的运行时规则——tsx 无条件应用 `paths` 映射。声明完整性现在仅由静态门禁保障：配置的裸插件走 `verify-cordis-config`，manifest（元数据清单）走 workspace constraints。（该运行时规则确实发现过真实缺陷：`dsh-plan-mode` 与 `dsh-tool-tasks` 导入 `@deepseek-ai/dsh-llm` 却只声明在 devDependencies；后已修复。）

-node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（`apps/cli/tests/source-launch.compat.spec.ts`）：以精确的生产启动向量做 keyless 管道 stdio 启动，断言非零退出的 TTY 拒绝。未来 Node 对模块钩子或 TypeScript 处理的任何改动都会让该门禁变红，而不是破坏开发者的 `pnpm dsh`。
+node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（`apps/cli/tests/source-launch.compat.spec.ts`）：以精确的生产运行时启动向量做 keyless 管道 stdio 启动，断言非零退出的 TTY 拒绝。未来 Node 对模块钩子或 TypeScript 处理的任何改动都会让该门禁变红，而不是破坏开发者的 `pnpm dsh`。

 ## 备选方案

@@ -35,4 +35,4 @@ node-compat CI 矩阵（Node 22.19 与 26）新增 `dsh-source-launch-smoke`（`
 - 整个 engines 范围（包括未来改变原生 TypeScript 支持的 Node 版本线）只有一个启动向量；冒烟门禁按矩阵行强制执行。
 - TypeScript 转换重新委托给 tsx/esbuild，逆转了前一篇 Agent Note「证明 Node 原生转换可用」的目标；在 vendor 源码使用不可擦除语法且 Node 不再提供 transform 模式的情况下，该目标不可达。
 - 源码启动中的运行时依赖声明强制不复存在；未声明的 workspace import 现在只能通过静态门禁或构建模式的解析失败暴露。
- 启动相比完整 tsx 默认形态快约 0.4s（`demo:headless` 现为同一条 `dsh --profile headless` 源码启动命令的别名；ACP 保留 `--import tsx`，因为它的依赖图尚未就 CJS 钩子依赖性做审计，且其启动延迟不在交互路径上）。
+- 运行时启动相比完整 tsx 默认形态快约 0.4s；ACP（Agent Client Protocol）保留 `--import tsx`，因为它的依赖图尚未就 CJS 钩子依赖性做审计，且其启动延迟不在交互路径上。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-29-package-regrouping.md
-2026-07-29-package-regrouping.md: 3c37bce05bacd6af800a76ac93fb691b896a6772
-2026-07-29-package-regrouping.zh.md: 68903ff1fad6a975c4445fe8971c8fe0dd40117f
+2026-07-29-package-regrouping.md: 30fc45a122263350b4a2ad1998850f631c20f9b8
+2026-07-29-package-regrouping.zh.md: a3a9a11ec71b7f894dcea7c733eb39a80b71ac50
@@ -58,7 +58,7 @@ The moves landed as pure `git mv` moves, so rename detection carries the history

 A group move did not touch: npm names, imports, `cordis.yml` configs, snapshot fixtures, the `pnpm-workspace.yaml`/`tsdown` globs (both `packages/*/*`), or the Python runtime manifest — all reference packages by npm name.

-`client/` and `host/` were out of scope and are unchanged. The `experimental/` group proposal (PR #844) is orthogonal — a release-boundary container, not a clustering decision.
+`client/` and `host/` were out of scope and are unchanged.

 ## Alternatives considered

@@ -58,7 +58,7 @@ Status: implemented

 组移动未触及：npm 包名、import、`cordis.yml` 配置、快照 fixture（测试前置数据）、`pnpm-workspace.yaml` 与 `tsdown` 的 glob（都是 `packages/*/*`），以及 Python 运行时 manifest（元数据清单）——它们全部按 npm 包名引用包。

-`client/` 与 `host/` 不在本次范围内，保持不变。`experimental/` 组提案（PR #844）与本案正交：它是发布边界容器，不是聚类决策。
+`client/` 与 `host/` 不在本次范围内，保持不变。

 ## Alternatives considered

@@ -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/2026-07-28-experimental-plugin-package-group.md
-2026-07-28-experimental-plugin-package-group.md: 1ebae5dbb16d4c966f94ffde69fb0cb9bc163d80
-2026-07-28-experimental-plugin-package-group.zh.md: 2d09451c5069a775906e5bc8748c334c29008164
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-10-message-feedback-sidecar.md
+2026-08-10-message-feedback-sidecar.md: 780cbaa840fcac7bcfa799468bfd61f5b08715cb
+2026-08-10-message-feedback-sidecar.zh.md: 72ecc82717010f65d013418a45c3b38c6084aaf9
@@ -0,0 +1,43 @@
+# Agent Note: Lifecycle-bound message feedback sidecar
+
+Status: implemented
+
+English | [中文](2026-08-10-message-feedback-sidecar.zh.md)
+
+## Problem
+
+The existing `/feedback` command records an immutable Session-level `feedback/record` event. That event can release a pending telemetry prefix under `FEEDBACK_ONLY`, so it is the wrong authority for an editable positive/negative rating and optional note attached to one assistant message. Message feedback needs independent update and delete semantics without entering the canonical Session log, changing a projection, reaching the model surface, or implicitly consenting to telemetry.
+
+A sidecar keyed only by `SessionId` can outlive the log lifecycle it describes when an id is recreated with a different header identity. A Session-wide revision also makes unrelated message edits conflict, while plain storage-domain read/put has no cross-process compare-and-swap. Session disposal is only live-store detach, not durable deletion, and the current Session persistence seam exposes no deletion operation that could own a truthful cascade.
+
+## Decision
+
+`@deepseek-ai/dsh-message-feedback` owns the `ctx.messageFeedback` service and stores message feedback as one storage-domain sidecar row per Session. The sidecar is neither Session-log content nor a Session projection. It emits no `feedback/record` event and performs no telemetry handoff; the command-feedback and message-feedback contracts remain independent.
+
+Every usable row is bound to the inspected Session header identity `{createdAt, cwd}`, not merely its `SessionId`. A lifecycle mismatch is treated as absence: `list` returns no items, and `put` may replace the stale row with one bound to the current identity. An id reused with a different header identity therefore cannot inherit stale feedback. A fork receives its own Session identity and no sidecar copy: even when the fork seed contains the same assistant messages, feedback remains attached to the Session in which the human recorded it.
+
+`put` accepts a target only when `SessionPersistence.inspect()` observes a non-empty, append-origin `assistant/message` with that `MessageId`. Replacement-origin messages, empty usage-only assistant records, and non-assistant targets are rejected. Inspection is the cold-safe authority: it neither publishes or resumes an Agent nor commits cold-log repair merely to validate feedback. A cold `listSnapshots()` preflight classifies definite absence; inspection failure for a catalogued Session remains an infrastructure failure. A request in the narrow live-detach-to-header-materialization interval can therefore return `session-not-found`, and the caller retries after retirement materialization.
+
+Before `put` commits a sidecar row, it puts the target log behind a durability barrier. A matching live Session passes through the canonical `ctx.sessions.flush` checkpoint, then both live and cold paths are physically read from sequence zero through `SessionPersistence.readFrom`. The resulting observation's header identity and target are checked again. A missing flush participant, changed identity, vanished target, or physical-read failure prevents the sidecar write, so a committed feedback item never precedes the durable assistant message it references.
+
+Each message item carries its own opaque version plus Host-assigned `createdAt` and `updatedAt` timestamps. `put` compares the caller's `ifVersion` only with the addressed item, so editing one message does not invalidate another. The comparison is strict even when the desired value already matches, preventing a stale request from crossing an ABA value cycle; a conflict returns the authoritative current item so callers can reconcile without a second read. A matching-version no-op preserves the version and timestamps, while a material update preserves `createdAt`, replaces the version, and keeps `updatedAt` from moving backward. An already-absent delete is likewise successful. Versions are tokens for equality, not counters callers may order or synthesize.
+
+A per-Session mutation queue encloses lifecycle inspection, sidecar read, conflict evaluation, and whole-row write. This makes one service instance's mutations serial and preserves the per-message compare-and-swap contract inside one Host process. Plugin disposal closes admission, drains accepted queue work, and then closes the storage domain. The underlying storage-domain API provides no cross-process conditional write, so the implementation claims no cross-process linearizability or lost-update protection.
+
+`maxNoteBytes` is a required deployment choice and bounds the UTF-8 byte length of an optional note; the Web Host bundle sets it explicitly to `8192`. The package publishes the Host `messageFeedback.list`, `messageFeedback.put`, and `messageFeedback.delete` contract directly through `GatewayService` and `@Remote`. Client Remote aggregate mounting and UI remain separately owned and deferred; their later adapter stays a thin consumer of this Host contract.
+
+The service performs no fake deletion cascade. `session/disposed` and `host/session-removed` describe detach from live ownership, not durable Session deletion, and Session persistence currently has no delete surface. Sidecar rows can therefore remain after out-of-band log removal; a different `{createdAt, cwd}` prevents such an orphan from becoming feedback for a later Session that reuses the id.
+
+## Alternatives considered
+
+**Append edits to the Session log and derive a projection.** Rejected because editable UI metadata would become canonical conversation-adjacent history, forks would replay and inherit it, deletion would require tombstones, and reusing `feedback/record` would silently couple a message rating to telemetry consent.
+
+**Key feedback globally by `MessageId`, copy it on fork, or use one Session revision.** Rejected because message ids are meaningful only within a Session lifecycle, forked conversations need independent human judgments, and unrelated message mutations must not create false conflicts.
+
+**Extend `KvTable` with cross-process compare-and-swap in this change.** Rejected because the shipped storage-domain backends expose no common conditional-write primitive. A process-local queue matches the supported one-Host topology; a real multi-process guarantee requires a backend-level atomic contract and is separate work.
+
+**Delete feedback on Session disposal.** Rejected because disposal includes ordinary detach and rollback paths. Treating it as durable deletion would lose feedback while the Session log still exists; cleanup waits for a real Session deletion authority.
+
+## Consequences
+
+Message feedback is locally durable and independently editable without changing model-visible history or telemetry behavior. Concurrent callers in one Host receive per-message conflict detection and retry-safe outcomes, while deployments with multiple writers to the same storage root remain unsupported. A differing header identity treats a stale row as absent but does not reclaim it; a cloned log that retains the same `{createdAt, cwd}` is indistinguishable by this contract. The Host Remote contract is available now; client assembly and UI can remain thin consumers rather than taking ownership of persistence or concurrency semantics.
@@ -0,0 +1,43 @@
+# Agent Note: 绑定生命周期的消息反馈伴随记录
+
+Status: implemented
+
+[English](2026-08-10-message-feedback-sidecar.md) | 中文
+
+## 问题
+
+现有 `/feedback` 命令记录不可变的 Session 级 `feedback/record` 事件。在 `FEEDBACK_ONLY` 下，该事件可以释放待处理的遥测前缀，因此它不适合作为挂在单条 assistant 消息上的可编辑好评／差评与可选备注的权威来源。消息反馈需要独立的更新与删除语义，且不得进入权威 Session 日志、改变投影、到达模型接口，或隐式表示遥测同意。
+
+只按 `SessionId` 建索引的伴随记录可能在该 id 以不同 header 身份重建后，继续存活于其所描述的日志生命周期之外。Session 级 revision 还会让无关消息的编辑彼此冲突，而普通 storage-domain 读／写不提供跨进程 compare-and-swap。Session disposal 只是从 live store 脱离，并非持久删除；当前 Session 持久化 seam 也没有可拥有真实级联的删除操作。
+
+## 决策
+
+`@deepseek-ai/dsh-message-feedback` 拥有 `ctx.messageFeedback` 服务，并把消息反馈存为每个 Session 一条 storage-domain 伴随记录（sidecar）。该伴随记录既不是 Session 日志内容，也不是 Session 投影。它不发出 `feedback/record` 事件，也不执行遥测交接；command-feedback 与 message-feedback 契约保持独立。
+
+每条可用记录都绑定到经检查的 Session header 身份 `{createdAt, cwd}`，而不只是其 `SessionId`。生命周期不匹配按不存在处理：`list` 返回空条目，`put` 可以用绑定当前身份的新记录替换陈旧行。因此，以不同 header 身份复用的 id 不会继承陈旧反馈。fork 拥有自己的 Session 身份，且不复制伴随记录：即使 fork 种子包含相同的 assistant 消息，反馈仍只属于人类记录它的那个 Session。
+
+`put` 只接受由 `SessionPersistence.inspect()` 观测到的非空、append-origin `assistant/message`，且其 `MessageId` 必须与目标相同。replacement-origin 消息、仅承载 usage 的空 assistant 记录以及非 assistant 目标都会被拒绝。检查使用 cold-safe 权威路径：它不会仅为验证反馈而发布或恢复 Agent，也不会提交 cold 日志修复。cold 路径由 `listSnapshots()` 预检明确不存在；已进入目录的 Session 若检查失败，仍按基础设施故障处理。因此，请求若恰落在 live detach 到 header materialization 的极短窗口，可能返回 `session-not-found`，调用方在 retirement materialization 后重试。
+
+`put` 提交伴随记录前，会先让目标日志通过 durability barrier。身份匹配的 live Session 经过权威 `ctx.sessions.flush` checkpoint，随后 live 与 cold 路径都会通过 `SessionPersistence.readFrom` 从序列零做物理复读。之后再次校验所得观测的 header 身份与目标。缺少 flush 参与方、身份变化、目标消失或物理读取失败都会阻止伴随记录写入，因此已提交反馈绝不会先于它引用的持久 assistant 消息。
+
+每个消息条目都携带自己的 opaque version，以及 Host 分配的 `createdAt` 和 `updatedAt` 时间戳。`put` 只把调用方的 `ifVersion` 与目标条目比较，因此编辑一条消息不会使另一条消息失效。即使目标值已经相同，比较仍然严格执行，从而防止陈旧请求穿过 ABA 值循环；冲突会返回权威当前条目，调用方无需二次读取即可协调。携带匹配 version 的无变化请求会保留 version 与时间戳；实质更新保留 `createdAt`、替换 version，并保证 `updatedAt` 不倒退。删除已经不存在的条目也同样成功。version 是只能做相等比较的 token，不是调用方可以排序或自行合成的计数器。
+
+按 Session 划分的变更队列覆盖生命周期检查、伴随记录读取、冲突判断与整行写入。这使同一个服务实例的变更串行化，并在单个 Host 进程内保持逐消息 compare-and-swap 契约。Plugin disposal 会关闭接纳、排空已进入队列的工作，然后关闭 storage domain。底层 storage-domain API 不提供跨进程条件写，因此实现不承诺跨进程线性一致性或防止丢失更新。
+
+`maxNoteBytes` 是必填的部署选择，用于限制可选备注的 UTF-8 字节长度；Web Host bundle 将其显式设为 `8192`。该包通过 `GatewayService` 与 `@Remote` 直接发布 Host `messageFeedback.list`、`messageFeedback.put` 与 `messageFeedback.delete` 契约。客户端 Remote 聚合挂载与 UI 由各自边界负责并保持延后；后续适配层只是该 Host 契约的薄消费者。
+
+服务不伪造删除级联。`session/disposed` 与 `host/session-removed` 表示脱离 live ownership，而非持久删除，Session persistence 当前也没有删除接口。因此在带外移除日志后，伴随记录可能继续存在；不同的 `{createdAt, cwd}` 可阻止此类孤儿记录变成后来复用该 id 的 Session 反馈。
+
+## 考虑过的替代方案
+
+**把编辑追加到 Session 日志并派生投影。** 不予采纳，因为可编辑 UI 元数据会变成权威且邻近对话的历史，fork 会回放并继承它，删除需要 tombstone，而复用 `feedback/record` 会把消息评分与遥测同意静默耦合。
+
+**按全局 `MessageId` 建索引、在 fork 时复制，或使用一个 Session revision。** 不予采纳，因为消息 id 仅在某个 Session 生命周期内有意义，fork 后的对话需要独立的人类判断，而且无关消息的变更不应制造虚假冲突。
+
+**在本次变更中为 `KvTable` 扩展跨进程 compare-and-swap。** 不予采纳，因为出厂 storage-domain 后端没有共同的条件写原语。进程内队列符合受支持的单 Host 拓扑；真实的多进程保证需要后端级原子契约，属于独立工作。
+
+**在 Session disposal 时删除反馈。** 不予采纳，因为 disposal 包含普通 detach 与 rollback 路径。把它当成持久删除会在 Session 日志仍存在时丢失反馈；清理必须等待真正的 Session 删除权威。
+
+## 后果
+
+消息反馈在本地持久化并可独立编辑，且不改变模型可见历史或遥测行为。同一 Host 中的并发调用方获得逐消息冲突检测与可安全重试的结果；多个写入者共享同一存储根目录的部署仍不受支持。不同的 header 身份会让陈旧记录被视为不存在，但不会将其回收；本契约无法区分保留相同 `{createdAt, cwd}` 的克隆日志。Host Remote 契约现在可用；客户端组装与 UI 可以保持为薄消费者，而不接管持久化或并发语义。
@@ -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/2026-08-10-session-log-version-mechanism.md
+2026-08-10-session-log-version-mechanism.md: 25eb1230a254219c827b1d2750dba367b113f9f7
+2026-08-10-session-log-version-mechanism.zh.md: c47670f2de77773c17c9595eff442bf7f1e8ec3e
@@ -0,0 +1,30 @@
+# Agent Note: Session log versioning — one integer, an upgrade chain, and a per-event ignorable marker
+
+Status: implemented
+
+English | [中文](2026-08-10-session-log-version-mechanism.zh.md)
+
+## Problem
+
+Session logs must be upgradable after release, and the runtime that ships first is the floor for every later decision: whatever refusal and degradation behavior is missing from the first released reader can never be added to the copies users already run. Release issue #1901 required at minimum that an old runtime reading a newer session format reports "unsupported" instead of misreading it. The pre-change reader did the opposite on both axes: `assertVersion` rejected any version mismatch with one direction-blind message, and the JSONL decoder passed unknown event types through untouched, so reconstruction silently skipped them — resuming a gutted session with no diagnostic at all.
+
+## Decision
+
+**One monotonic integer, no major/minor split.** Whether a version step is auto-upgradable is a property of that step — expressed by whether its upgrader exists — not something a two-level numbering scheme should promise in advance (you rarely know at design time whether the next change will turn out "major"). This matches the SQLite backend's `SCHEMA_VERSION` precedent.
+
+**The writer decides bumps, not the reader.** A bump is required exactly when an old runtime could no longer handle a new log with full semantic correctness. "Parses without error" is not the bar: silently skipping content that shapes reconstruction is a wrong read. Only structural changes qualify — header shape, event envelope, core event semantics, the surface mechanism (`SurfaceEventType` set, `SurfaceOp` variants). When unsure, bump: a near-identity upgrader is almost free, a missed bump silently corrupts old readers.
+
+**Read rules by direction.** Equal version: read normally. Newer than the reader: refuse, name the direction ("written by a newer harness — upgrade"), and point at the raw log artifact so the user can still see the text (`SessionFormatUnsupportedError`, distinct from `SessionPersistenceCorruptionError` because nothing is damaged). Older than the reader: convert in memory through the chain of n→n+1 upgraders for viewing; persist the converted log only when the session is actually continued (atomic temp-file replace, original kept as backup). A step whose upgrader cannot be written is left empty, which cuts off every version at or below it — those degrade to raw-text viewing.
+
+**A per-event `ignorable` marker covers vocabulary growth, so ordinary event additions never bump the version.** The event vocabulary is decided by which plugins are mounted, which a single version integer cannot describe. A reader meeting an unrecognized event type refuses to interpret the log unless the event carries `ignorable: true` in its envelope. The default is *required*: forgetting the marker over-refuses a resumable session (an inconvenience), while a default of ignorable would make the same mistake silently resume a gutted one (a safety failure). The architecture makes this sound: model-visible content flows only through the three `surfaceOp`-marked surface event types plus the `request/header`/`request/context` folds, so the dangerous unknowns are exactly the non-surface events that change how the rest of the log is read (`session/end-seed` is the existing example).
+
+## Consequences
+
+What shipped in v0 (release 0812): direction-aware refusal with the raw-log path; the unknown-event guard against a generated known-vocabulary list (`KNOWN_SESSION_EVENT_TYPES`, emitted by `gen-persistence-catalog` from every `SessionEventMap` merge and kept fresh by `verify-persistence-catalog`); the `ignorable` envelope field accepted by seed validation, both backends (a dedicated SQLite column, `SCHEMA_VERSION` 15), and the BFF wire schema. The upgrader chain itself is deferred until the first real v0→v1 step exists to test it against; writers do not yet set `ignorable` (no producer needs it), so `Session.append` gains that surface with its first user. Until a registration surface exists, an out-of-repo plugin's events refuse resume under first-party readers — the pre-release stance accepts that, and the refusal is loud rather than silent. The unknown-type guard is read-side only: `appendCore` keeps rejecting retired legacy shapes but does not vocabulary-check new types, because an append-time refusal would stall a live session's durability mid-flight, which costs more than a loud refusal at the log's next load. The JSONL backend additionally refuses a foreign version from the raw header line before validating today's header shape or decoding any event row, so a structurally different future format still reports the upgrade direction instead of "corrupt"; SQLite gates whole-file structure through its own `SCHEMA_VERSION` pragma first.
+
+## Alternatives considered
+
+- **Major/minor versioning** — the "is it convertible" bit lives on each step's upgrader, and pre-committing it into a number shape invites wrong promises.
+- **Default-ignorable unknown events** — inverts the failure mode of a forgotten marker from visible over-refusal into silent corruption.
+- **Auto-migrating on view** — rewriting the artifact on open turns a read into a destructive write: a converter bug corrupts logs at browse time, and a same-directory older runtime loses access because a newer one merely looked.
+- **Per-plugin runtime registration of known event types** — would make the known set composition-dependent, so a leaner same-version composition would refuse logs a fuller one wrote. The generated repo-wide list keeps same-version reads uniform; out-of-repo plugin events are outside it by construction, and a registration surface for them is deferred until such a consumer exists.
@@ -0,0 +1,30 @@
+# Agent Note：Session log 版本机制：单调整数、升级器链、逐事件可忽略标记
+
+Status: implemented
+
+[English](2026-08-10-session-log-version-mechanism.md) | 中文
+
+## 问题
+
+Session log 在发布后必须能升级格式，而最先发布的运行时决定了此后一切的下限：第一个发布版的读取器缺少哪种拒绝和降级行为，用户手里已经装上的副本就永远补不上。发布 issue #1901 的最低要求是老运行时读到新 Session 格式时明确报不支持，而不是读错。改动前的读取器在两个方向上都做反了：`assertVersion` 对任何版本不匹配抛出同一条不区分方向的消息；JSONL 解码器把不认识的事件类型原样放行，重建时静默跳过，恢复出一个内容残缺的会话且没有任何诊断。
+
+## 决定
+
+**一个单调递增的整数，不分大小版本。**某一步能不能自动升级是那一步自己的属性，由它的升级器存在与否表达，不该由两级编号方案提前承诺（设计时很少能预知下一个变更算不算"大"）。这与 SQLite 后端 `SCHEMA_VERSION` 的先例一致。
+
+**升不升版本由写入方决定，与读取方能力无关。**当且仅当老运行时无法在语义上完全正确地处理新日志时才必须升版本。"解析不报错"不是标准：静默跳过影响重建的内容就是读错。只有结构性变更够得上这条线：header 形状、事件信封、核心事件语义、surface 机制（`SurfaceEventType` 集合、`SurfaceOp` 变体）。拿不准就升：近似恒等的升级器几乎没有成本，漏升一次会让老读取器静默读坏。
+
+**读取规则按方向区分。**版本相等：正常读。比读取器新：拒绝，说明方向（"由更新的 harness 写入，请升级"），并给出原始日志文件的路径，用户仍能看到文本（`SessionFormatUnsupportedError`，与 `SessionPersistenceCorruptionError` 区分，因为数据没有损坏）。比读取器旧：查看时经 n→n+1 升级器链在内存中逐级转换；只有会话真正被继续时才把转换落盘（临时文件原子替换，原文件留备份）。写不出升级器的那一步留空，这会切断该步及更早所有版本的升级路径，它们降级为只能看原文。
+
+**逐事件的 `ignorable` 标记吸收词汇表增长，普通的新增事件永远不用升版本。**事件词汇表由挂载了哪些插件决定，单个版本整数描述不了它。读取器遇到不认识的事件类型时拒绝解读日志，除非该事件的信封带 `ignorable: true`。默认为必需：忘写标记的后果是把一个本可恢复的会话拒绝过头（体验问题），而默认可忽略会让同样的疏忽静默恢复出残缺会话（安全事故）。架构保证了这条规则成立：模型可见内容只经三种带 `surfaceOp` 标记的 surface 事件加 `request/header`、`request/context` 折叠进入重建，危险的未知事件恰好是那些不进 surface 但改变日志其余部分解读方式的事件（`session/end-seed` 是现存例子）。
+
+## 影响
+
+v0（0812 发布）交付的内容：分方向的拒绝并带原始日志路径；基于生成的已知词汇清单（`KNOWN_SESSION_EVENT_TYPES`，由 `gen-persistence-catalog` 从所有 `SessionEventMap` 声明合并生成，`verify-persistence-catalog` 保证新鲜）的未知事件守卫；`ignorable` 信封字段被种子校验、两个后端（SQLite 专用列，`SCHEMA_VERSION` 升到 15）和 BFF 线上 schema 接受。升级器链本身推迟到第一个真实的 v0→v1 变更出现、有真实对象可测时再建；写入侧目前不写 `ignorable`（还没有生产者需要它），`Session.append` 的这一表面随第一个使用者一起落地。在注册表面出现之前，仓库外插件的事件在第一方读取器下无法恢复会话，预发布立场接受这一点，而且拒绝是显式的而非静默的。未知类型守卫只在读取侧生效：`appendCore` 继续拒绝已淘汰的 legacy 形状，但不对新类型做词汇检查，因为写入时拒绝会让活跃会话的持久化中途停摆，代价大于下次加载时的显式拒绝。JSONL 后端还会在校验当前 header 形状、解码任何事件行之前，直接从原始 header 行拒绝外来版本，因此结构完全不同的未来格式仍会报告升级方向而不是"损坏"；SQLite 则先由自己的 `SCHEMA_VERSION` pragma 把关整个文件的结构。
+
+## 曾考虑的替代方案
+
+- **大小两级版本号**：能否转换这一位信息属于每一步的升级器，把它预先固化进编号形状会做出错误承诺。
+- **未知事件默认可忽略**：把忘写标记的后果从可见的过度拒绝反转成静默损坏。
+- **查看时自动迁移落盘**：打开即改写把读操作变成破坏性写操作，转换器的 bug 会在浏览时损坏日志，同目录的旧版本运行时也会因为新版本只是看了一眼就失去访问能力。
+- **插件运行时注册已知事件类型**：会让已知集依赖插件组合，同版本的精简组合会拒绝完整组合写出的日志。生成的全仓库清单保证同版本读取行为一致；仓库外插件的事件按构造就在清单之外，为它们提供注册表面推迟到真有这样的消费者时再做。
@@ -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-subagent-empty-terminal-message-output.md
+2026-08-10-subagent-empty-terminal-message-output.md: 693013f6810005ce02b08bd82f1f6a18511c40fb
+2026-08-10-subagent-empty-terminal-message-output.zh.md: 64d61af21f838ef3f515db8af116cbdd74e96179
@@ -0,0 +1,31 @@
+# Agent Note: One selection rule keeps subagent output past an empty terminal message
+
+Status: implemented
+
+English | [中文](2026-08-10-subagent-empty-terminal-message-output.zh.md)
+
+## Problem
+
+The agent loop appends an empty-content `assistant/message` when a `max-tokens` step assembled only tool-call blocks because `BlockAssembler.blocks()` drops truncated tool calls; the message records usage only. Three consumers selected the child's output independently and treated that usage record as output. The in-process driver's `readResult` and the continuable Activation's `subagent/end` capture selected the last `assistant/message` without filtering, while the SDK backend's observer let any `assistant/message` take precedence over accumulated text. In a multi-step turn cut off at max-tokens, the final empty message caused the real partial answer to be omitted from `SubagentResult.output`, the tool result, telemetry, and `subagent/end.lastAssistantMessage`. The in-process driver also lacked a streamed-text fallback, so a cancelled child whose only text existed in `assistant/chunk` events reported `[]`.
+
+## Decision
+
+`dsh-subagent` owns one canonical selection rule in `src/assistant-output.ts`: select the last non-empty assistant message; without one, select the accumulated `text-delta` stream; ignore empty-content messages. The incremental `AssistantOutputFold` implements the rule through `push(event)` for session-event transports, `pushText(text)` for chunk-only transports, and `collect()` for selection. `finalAssistantOutput(events)` applies it to a complete event suffix for the in-process `readResult` and Activation capture. The SDK backend folds notification events; the ACP backend exposes no complete assistant messages and folds raw chunk text. `SubagentResult.output` defines the result contract, and `subagent/end.lastAssistantMessage` uses the same rule. When a child produces neither form of output, the lifecycle field is absent rather than an empty array for both one-shot and continuable runs. A `max-tokens` or `aborted` result retains its actual stop reason.
+
+The foreground delegation tool uses the same selection. A non-`completed` result remains an `isError` tool result, but its message appends the child's partial text after the stop-reason headline so the parent model receives both the failure and available output.
+
+## Verification
+
+The keyless SDK backend test uses `FAKE_EMPTY_MESSAGE` to emit a usage-only terminal message. The `subagent-max-tokens-partial` ACP snapshot records a child that streams text and a tool call, ends at a tool-only max-tokens step with an empty usage message in its durable log, and returns the partial text through the parent's errored tool result. Unit coverage checks empty terminal messages, cancellation, message ordering, textless non-empty messages, and exclusion of tool-result content.
+
+## Alternatives considered
+
+**Fix each consumer in place without a shared helper.** Rejected: three independent selections had diverged, while observers of one run must agree on its output.
+
+**Stop the loop from appending the empty message.** Rejected: the message records usage and preserves the step in the durable log ("model-visible ⟺ logged"); changing session events to address output selection would affect every replay and projection consumer.
+
+**Treat empty-content messages as an error.** Rejected: the streamed text is the child's real partial answer, and the stop reason already tells the consumer the turn was cut short.
+
+## Consequences
+
+Multi-step children cut off at max-tokens report their earlier text; cancelled in-process children retain text streamed before the abort; one-shot and continuable `subagent/end` events agree with `SubagentResult.output`. A message whose content is non-empty but textless, such as reasoning-only content, is selected instead of streamed text because the rule tests content length rather than text presence. A non-empty message is also selected instead of text streamed after it: a child cancelled while streaming a later step reports its earlier complete message, while the stop reason records the truncation.
@@ -0,0 +1,31 @@
+# Agent Note: 用同一条选取规则在空终止消息后保留子代理输出
+
+Status: implemented
+
+[English](2026-08-10-subagent-empty-terminal-message-output.md) | 中文
+
+## 问题
+
+当 `max-tokens` 步骤只组装了工具调用块时，agent loop（智能体循环）会追加一条空内容的 `assistant/message`，因为 `BlockAssembler.blocks()` 会丢弃被截断的工具调用；这条消息仅记录 usage。三个消费方独立选取子 agent 的输出，并把这条 usage 记录当成输出。进程内驱动的 `readResult` 与 continuable Activation 的 `subagent/end` capture 不加过滤地选取最后一条 `assistant/message`，SDK 后端的观察器则让任何 `assistant/message` 优先于累积的文本。在被 max-tokens 截断的多步轮次中，最后那条空消息导致 `SubagentResult.output`、工具结果、遥测与 `subagent/end.lastAssistantMessage` 都漏掉真实的部分回答。进程内驱动也没有流式文本兜底，因此被取消的子 agent 若其唯一文本只存在于 `assistant/chunk` 事件中，也会报告 `[]`。
+
+## 决策
+
+`dsh-subagent` 在 `src/assistant-output.ts` 中拥有唯一的规范选取规则：选取最后一条非空 assistant 消息；没有时选取累积的 `text-delta` 流；忽略空内容消息。增量的 `AssistantOutputFold` 通过 `push(event)` 处理会话事件传输，通过 `pushText(text)` 处理仅分片传输，并通过 `collect()` 完成选取。`finalAssistantOutput(events)` 把规则应用于完整的事件后缀，供进程内 `readResult` 与 Activation capture 使用。SDK 后端折叠通知事件；ACP 后端不暴露完整的 assistant 消息，而是折叠原始分片文本。`SubagentResult.output` 定义结果约定，`subagent/end.lastAssistantMessage` 使用同一规则。子 agent 不产生这两种输出中的任何一种时，一次性与 continuable 运行的生命周期字段都会缺省，而不是空数组。`max-tokens` 或 `aborted` 结果保留实际的终止原因。
+
+前台委派工具使用同一选取规则。非 `completed` 的结果仍是 `isError` 工具结果，但其消息会在终止原因标题之后附上子 agent 的部分文本，让父模型同时接收失败信息与已有输出。
+
+## 验证
+
+无密钥 SDK 后端测试使用 `FAKE_EMPTY_MESSAGE` 发出一条仅记录 usage 的终止消息。`subagent-max-tokens-partial` ACP 快照记录一个子 agent：它流式输出文本与一次工具调用，结束于仅含工具调用的 max-tokens 步骤，持久化日志中含一条空的 usage 消息，并通过父侧的错误工具结果返回部分文本。单元覆盖检查空终止消息、取消、消息顺序、不含文本的非空消息，以及排除工具结果内容。
+
+## 考虑过的替代方案
+
+**各消费方就地修复、不抽共享辅助函数。** 之所以否决：三处独立选取已发生分歧，而同一次运行的观察方必须对其输出达成一致。
+
+**让 loop 不再追加空消息。** 之所以否决：这条消息记录 usage，并在持久化日志中保留该步骤（"model-visible ⟺ logged"）；为处理输出选取而改动会话事件，会影响所有 replay 与 projection 消费方。
+
+**把空内容消息视为错误。** 之所以否决：流式文本才是子代理真实的部分回答，且终止原因已经告诉消费方轮次被截断。
+
+## 后果
+
+被 max-tokens 截断的多步子 agent 会报告其更早的文本；被取消的进程内子 agent 保留中止前已流式的文本；一次性与 continuable 的 `subagent/end` 事件同 `SubagentResult.output` 一致。内容非空但不含文本的消息（例如仅含 reasoning 的内容）仍然优先于流式文本，因为规则检查内容长度，而不是文本是否存在。非空消息同样优先于其后才流式出的文本：子 agent 在流式输出后续步骤时被取消，报告的是更早那条完整消息，终止原因则记录该截断。
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-07-mcp-client-plugin.md
-2026-07-07-mcp-client-plugin.md: 756a5c4dc9f1152ecb1955d93b8dc47fcf07c661
-2026-07-07-mcp-client-plugin.zh.md: 9f45203c479379087c5a19eccce3ab7a339d4ed0
+2026-07-07-mcp-client-plugin.md: 077d978d8815d759574f89ed524ab3bc8c24a267
+2026-07-07-mcp-client-plugin.zh.md: 8f58c9359ca8447717cc353f97f1333370fa6fda
@@ -153,13 +153,7 @@ Build the child environment from the subprocess seam's shared `scrubbedParentEnv

 ### Disconnection / crash

-No auto-reconnect. If the MCP server process exits or the transport closes:
-
-1. The effect disposes → all registered tools are unregistered (fiber-scoped disposers).
-2. Subsequent model calls to those tools → `ToolNotFoundError` → `isError: true`.
-3. Recovery: user edits `cordis.yml` (triggers HMR reload) or restarts the harness.
-
-This matches the ACP subagent pattern: "crash = terminal, report error, clean up, don't retry."
+A per-instance connection supervisor reconnects automatically after a lost connection with bounded exponential backoff and a per-outage attempt budget, re-running discovery on success; exhaustion unregisters the server's tools and stops until reload. The [auto-reconnect Agent Note](2026-08-06-mcp-client-auto-reconnect.md) owns that decision, including the `reconnect` config block and the `reconnect.enabled: false` opt-out that restores manual HMR/restart recovery.

 ## Alternatives considered

@@ -173,7 +167,7 @@ Rejected. There is no foreseeable alternative MCP client implementation — MCP

 ### Auto-reconnect with exponential backoff

-Rejected for v1. Adds complexity (partial-availability state where tools are registered but temporarily non-functional), and stdio process crashes usually indicate a configuration problem that retrying won't fix. HMR already provides the manual recovery path. Can be added as a future `reconnect: boolean` config if needed.
+Rejected for v1: it added a partial-availability state (tools registered but temporarily non-functional), and stdio crashes often indicate configuration problems retrying cannot fix; HMR was the recovery path. Operational feedback reversed the deferral — the [auto-reconnect Agent Note](2026-08-06-mcp-client-auto-reconnect.md) implements it with a bounded per-outage budget and an opt-out.

 ### Bridge Resources and Prompts

@@ -211,4 +205,4 @@ Coverage is named per tier; each behavior lives at the cheapest tier that can ex
 - **MCP SDK stability**: the `@modelcontextprotocol/sdk` is still evolving; breaking changes require updating the bridge. The version is pinned, and the SDK is widely adopted (Claude Desktop, Cursor, VS Code) so breaking changes are unlikely to be silent.
 - **Tool schema quality**: MCP servers may expose poorly-described tools (vague descriptions, incomplete JSON schemas). The harness passes them through as-is — garbage-in-garbage-out; that is the server author's responsibility, not the bridge's.
 - **Stdio process management**: a misbehaving MCP server that ignores signals could wedge dispose. The Cordis fiber disposal has bounded quiescence; a stuck transport eventually times out at the framework level.
- Crash recovery is manual (HMR edit or restart) — accepted for v1; a `reconnect` config remains open as future work.
+- Crash recovery is automatic within the [reconnect budget](2026-08-06-mcp-client-auto-reconnect.md); manual reload remains the path after exhaustion or with `reconnect.enabled: false`.
@@ -153,13 +153,7 @@ MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/sp

 ### 断连 / 崩溃

-不自动重连。如果 MCP 服务器进程退出或传输层关闭：
-
-1. effect dispose → 所有已注册工具被注销（fiber 作用域的 disposer）。
-2. 后续模型对这些工具的调用 → `ToolNotFoundError` → `isError: true`。
-3. 恢复：用户编辑 `cordis.yml`（触发 HMR 重载）或重启 harness。
-
-这与 ACP subagent 模式一致：「崩溃即终态，报告错误，清理资源，不重试。」
+每个实例的连接监督器在连接丢失后以有界指数退避和单次故障尝试预算自动重连，成功后重新执行发现流程；尝试耗尽则注销该服务器的工具并停止，直到重新加载。[自动重连 Agent Note](2026-08-06-mcp-client-auto-reconnect.md) 拥有该决策，包括 `reconnect` 配置块和恢复手动 HMR/重启恢复的 `reconnect.enabled: false` opt-out。

 ## 曾考虑的替代方案

@@ -173,7 +167,7 @@ MCP 仅保证工具名在[单个服务器内](https://modelcontextprotocol.io/sp

 ### 指数退避自动重连

-v1 否决。引入复杂性（工具已注册但暂时不可用的部分可用状态），且 stdio 进程崩溃通常表明配置问题，重试无法修复。HMR 已提供手动恢复路径。如有需要，可在未来作为 `reconnect: boolean` 配置项添加。
+v1 否决：引入了部分可用状态（工具已注册但暂时不可用），且 stdio 崩溃往往表明配置问题，重试无法修复；HMR 曾是恢复路径。运营反馈扭转了该延期决定——[自动重连 Agent Note](2026-08-06-mcp-client-auto-reconnect.md) 以有界的单次故障预算和 opt-out 实现了自动重连。

 ### 桥接 Resources 和 Prompts

@@ -211,4 +205,4 @@ v1 否决。它能防止跨服务器冲突，但无法将 MCP 注册与原生 ha
 - **MCP SDK 稳定性**：`@modelcontextprotocol/sdk` 仍在演进中；破坏性变更需要更新桥接。版本已固定，且该 SDK 被广泛采用（Claude Desktop、Cursor、VS Code），因此破坏性变更不太可能悄然发生。
 - **工具 schema 质量**：MCP 服务器可能暴露描述不佳的工具（模糊的描述、不完整的 JSON Schema）。harness 原样透传——垃圾进垃圾出；这是服务器作者的责任，不是桥接的。
 - **Stdio 进程管理**：行为异常的 MCP 服务器如果忽略信号，可能卡住 dispose。Cordis fiber 的 dispose 具有有界的完全停稳过程；卡住的传输层最终会在框架层面超时。
- 崩溃恢复是手动的（HMR 编辑或重启）——v1 已接受；`reconnect` 配置作为未来工作保持开放。
+- 崩溃恢复在[重连预算](2026-08-06-mcp-client-auto-reconnect.md)内自动进行；耗尽后或配置 `reconnect.enabled: false` 时回退为手动重新加载。
@@ -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/2026-07-10-parallel-tool-call-execution.md
-2026-07-10-parallel-tool-call-execution.md: 830691b7596accd1c5746fc51e38a9022f09e501
-2026-07-10-parallel-tool-call-execution.zh.md: bd336919adbf9b96f64477c1e24964172cde6d92
+2026-07-10-parallel-tool-call-execution.md: 47a95e88c3d0d8bb9e3ddd820b1e63849effd914
+2026-07-10-parallel-tool-call-execution.zh.md: 024e5d4e4cdbf9d1d980bc67db5969fb34941752
@@ -60,7 +60,7 @@ Any shared state touched during execution must be concurrency-safe. This include

 `maxParallelToolCalls` is a positive AgentLoop deployment cap shared by every agent the factory creates. It defaults to `10`; `1` preserves serial execution. Exact fields and defaults live in the generated [configuration catalog](../../../../docs/config-catalog.md).

-The shipped declarations are conservative. Web search, web fetch, and filesystem read opt in. Filesystem writes and edits, bash tools, subagent delegation, workflow, user interaction, todo mutation, Code Mode, and Cordis mutation tools remain exclusive. A subagent may share its parent's workspace or external resources, and the unary classifier cannot prove that sibling delegations have disjoint effects. Bash has no proven input-sensitive classifier and remains exclusive.
+The shipped declarations are conservative. Web search, web fetch, filesystem read, the session-query trace/read tools, and subagent delegation opt in — delegation because a child works in its own session and its run never mutates the parent session, with sibling workspace coordination owned by the model ([parallel subagent Agent Note](2026-08-09-parallel-subagent-delegations.md)). Filesystem writes and edits, bash tools, the session-query search tools, workflow, user interaction, todo mutation, Code Mode, and Cordis mutation tools remain exclusive. Bash has no proven input-sensitive classifier and remains exclusive.

 Filesystem read relies on a narrow recorder exception: its synchronous observation updates may settle out of order, but write and edit re-check the observed version before mutation, so stale state only produces `FS_STALE_VERSION`.

@@ -60,7 +60,7 @@ Code Mode 仍不使用此调度器，因为模型只会发出一个原生 `run_c

 `maxParallelToolCalls` 是 AgentLoop 的正整数部署上限，由工厂创建的所有 agent（智能体）共享。默认值为 `10`；`1` 保持串行执行。字段和默认值的精确定义见生成的[配置目录](../../../../docs/config-catalog.md)。

-当前实现中的声明保持保守。Web 搜索、Web 获取和文件系统读取选择并行。文件系统写入与编辑、bash 工具、subagent 委派、工作流、用户交互、todo 变更、Code Mode 以及 Cordis 变更工具仍按独占方式执行。subagent 可能共享父级的工作区或外部资源，而一元分类器无法证明并列委派的作用互不重叠。Bash 没有已证明的输入敏感分类器，因此仍按独占方式执行。
+当前实现中的声明保持保守。Web 搜索、Web 获取、文件系统读取、会话查询的 trace/read 工具和 subagent 委派选择并行；委派之所以并行，是因为子 agent 在自己的会话中工作，其运行绝不变更父会话，并列委派间的工作区协调由模型负责（[并行 subagent Agent Note](2026-08-09-parallel-subagent-delegations.md)）。文件系统写入与编辑、bash 工具、会话查询的 search 工具、工作流、用户交互、todo 变更、Code Mode 以及 Cordis 变更工具仍按独占方式执行。Bash 没有已证明的输入敏感分类器，因此仍按独占方式执行。

 文件系统读取依赖一个范围很窄的记录器例外：其同步观察更新可以不按顺序结算，但写入和编辑在变更前会重新检查已观察的版本，因此陈旧状态只会导致 `FS_STALE_VERSION`。

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md
-2026-07-20-dsh-cli-personal-config.md: 02883c89f27e51d6091d4d65167ebdd6a96f6f51
-2026-07-20-dsh-cli-personal-config.zh.md: 6e56e892cf682ea514b036750e44dbb06e944a80
+2026-07-20-dsh-cli-personal-config.md: ed04725e92848bbab550a27ef2f4c021536f765e
+2026-07-20-dsh-cli-personal-config.zh.md: cc97987f803f7fb513e94ce0ce079558f5e3dc75
@@ -14,7 +14,7 @@ The entry modes and the personal file's name and location below are superseded b

 Two coupled pieces, aligned with the `apps/` assembly tier proposed by the `dsh web` PR (#443):

-**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` is the product-assembly tier over `packages/*` libraries. One bin dispatches the default interactive TUI, `-p`/`--prompt` headless turns, and the `web` surface. The TUI boots `examples/tui-agent/cordis.yml` (or `--config`) with the invoking directory as the workspace. The committed `bin/dsh` launcher resolves the checkout through its own real path and runs the app with tsx's ESM hook; the [source-launch decision](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md) owns that contract. `pnpm run demo:tui` runs the same entry.
+**The `dsh` CLI (`apps/cli`, npm name `@deepseek-ai/dsh`).** `apps/*` is the product-assembly tier over `packages/*` libraries. One bin dispatches the default interactive TUI, `-p`/`--prompt` headless turns, and the `web` surface. The TUI boots `examples/tui-agent/cordis.yml` (or `--config`) with the invoking directory as the workspace. From a source checkout, the root `pnpm dsh` script builds the repository and runs the same entry with tsx's ESM hook; the [source-launch decision](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md) owns that contract.

 **Personal config (`dsh-app-boot`).** The personal overlay lives in the Harness home — `$DSH_HOME`, else `~/.dsh` — resolved by the shared [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md) (`@deepseek-ai/dsh-paths`), the same single root skills and AGENTS.md resolve against. The dsh TUI, Web, and headless surfaces consume its two optional files; the demo bins boot their committed trees verbatim:

@@ -40,7 +40,7 @@ The TUI and Web register the exact personal path through Cordis HMR after boot.

 ## Consequences

- `dsh` from any directory (and `pnpm run demo:tui`) can apply personal providers, models, installed bundle entries, and other Loader entries with no checkout edit; verified end-to-end against a personal Anthropic proxy with Opus 4.8, including a bash tool round trip.
+- An installed `dsh` command can run from any directory, while source users invoke `pnpm dsh` from the checkout; both can apply personal providers, models, installed bundle entries, and other Loader entries with no checkout edit. The behavior was verified end to end against a personal Anthropic proxy with Opus 4.8, including a bash tool round trip.
 - Because an id-targeted patch replaces the whole `config`, a personal override restates the base fields it keeps and can drift when the base entry changes shape; the loader's entry-not-found/name-mismatch warnings and [`dsh --dump-config`](../../../../apps/cli/README.md#profiles) (which prints the composed tree those patches produce) are the diagnostics.
 - Personal patches resolve ids against the booted file's own tree, so nested-include overlays (Code Mode) are not personalized; live-run parity for those leaves is deferred.
 - `dsh-app-boot` depends on `js-yaml` and imports the include's `!!js` YAML dialect (`entryListSchema`) directly, and, like `apps/cli`, depends on `@deepseek-ai/dsh-paths` for `resolveDshHome`.
@@ -14,7 +14,7 @@ Status: implemented

 两个耦合的部分，与 `dsh web` PR（#443）提出的 `apps/` 装配层对齐：

-**`dsh` CLI（`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 是位于 `packages/*` 库之上的产品组装层。一个 bin 负责分发默认交互式 TUI、`-p`/`--prompt` 无头轮次和 `web` 界面。TUI 以调用目录为 workspace，启动 `examples/tui-agent/cordis.yml`（或 `--config` 指定的配置）。已提交的 `bin/dsh` 启动器通过自身真实路径解析 checkout，并使用 tsx 的 ESM hook 运行应用；该约定由[源码启动决策](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)维护。`pnpm run demo:tui` 运行同一入口。
+**`dsh` CLI（命令行界面；`apps/cli`，npm 名 `@deepseek-ai/dsh`）。** `apps/*` 是位于 `packages/*` 库之上的产品组装层。一个 bin 负责分发默认交互式 TUI、`-p`/`--prompt` 无头轮次和 `web` 界面。TUI 以调用目录为 workspace，启动 `examples/tui-agent/cordis.yml`（或 `--config` 指定的配置）。在源码检出中，根目录的 `pnpm dsh` 脚本先构建仓库，再使用 tsx 的 ESM hook 运行同一入口；该约定由[源码启动决策](../architecture/2026-07-29-dsh-source-launch-tsx-esm.md)维护。

 **个人配置（`dsh-app-boot`）。** 个人 overlay 存放在 Harness home——`$DSH_HOME`，否则 `~/.dsh`——由共享的 [`resolveDshHome`](../architecture/2026-07-24-single-harness-home-resolver.md)（`@deepseek-ai/dsh-paths`）解析，与 skills、AGENTS.md 解析所依据的单一根目录相同。dsh 的 TUI、Web 和无头界面使用其中两个可选文件；各示例 bin 仍然逐字节按已提交的配置树启动：

@@ -40,7 +40,7 @@ TUI 和 Web 启动后通过 Cordis HMR（热模块替换）注册确切的个人

 ## Consequences

- 在任意目录运行 `dsh`（以及 `pnpm run demo:tui`），无需修改 checkout，即可应用个人提供方、模型、已安装组合包的配置项和其他 Loader 配置项；已针对个人 Anthropic 代理与 Opus 4.8 端到端验证，包括一次 bash 工具往返。
+- 已安装的 `dsh` 命令可从任意目录运行，源码用户则从 checkout 调用 `pnpm dsh`；两者都无需修改 checkout 即可应用个人提供方、模型、已安装组合包的配置项和其他 Loader 配置项。该行为已针对个人 Anthropic 代理与 Opus 4.8 端到端验证，包括一次 bash 工具往返。
 - 由于按 id 定位的补丁替换整个 `config`，个人覆盖必须复述它保留的基础字段，并可能随基础配置项形态变化而漂移；诊断手段是 loader 的「配置项未找到/名称不匹配」警告和 [`dsh --dump-config`](../../../../apps/cli/README.md#profiles)（打印这些补丁合成出的配置树）。
 - 个人补丁只在被启动文件自身的树里解析 id，因此嵌套 include 的 overlay（Code Mode）不会被个性化；这些叶子的实际运行等价性暂缓。
 - `dsh-app-boot` 依赖 `js-yaml`，并直接导入 include 的 `!!js` YAML 方言（`entryListSchema`）；与 `apps/cli` 一样依赖 `@deepseek-ai/dsh-paths` 以获取 `resolveDshHome`。
@@ -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/2026-07-28-feedback-command.md
-2026-07-28-feedback-command.md: 3edb29283c289d6d006891a4c19087b01fa8166f
-2026-07-28-feedback-command.zh.md: c2513d2570474cbbaf8d94f87603d8ce10d40c14
+2026-07-28-feedback-command.md: d3b2774e41a82f6edb4303280f813ddbed75ebd1
+2026-07-28-feedback-command.zh.md: 3eeef92f2ed39c9546f013f217dd7f851d30c78c
@@ -18,7 +18,7 @@ The package declares the log-only `feedback/record { text }` session event and e

 `dsh-commands` still writes its `command/run` / `command/done` lifecycle pair around `/feedback`, but this command sets `recordInput: false`. Its `command/run` therefore carries the command identity and source without `args`; the feedback text exists only in `feedback/record`, while `command/done` carries the acknowledgement outcome. All three records are log-only and non-surface. Their appends enter persistence's ordinary bounded write path; nothing forces a flush, so acknowledgement reports that the feedback is in the log rather than already on disk.

-Capture remains inert for the running agent and model. The optional OTel telemetry package later adds one infrastructure consumer: it observes `feedback/record` as a release trigger in `FEEDBACK_ONLY` mode and as the local-only warning trigger in `DISABLED` mode, without changing the feedback event or command path. See [Feedback-gated session telemetry](2026-08-05-feedback-gated-session-telemetry.md).
+Capture remains inert for the running agent and model. The optional OTel telemetry package later adds one infrastructure consumer: it observes `feedback/record` as a release trigger in `FEEDBACK_ONLY` mode and as the local-only warning trigger in `DISABLED` mode, without changing the feedback event or command path. See [Feedback-gated session telemetry](2026-08-05-feedback-gated-session-telemetry.md) and the [acknowledgement sharing disclosure](2026-08-07-feedback-acknowledgement-sharing-disclosure.md).

 ### Why feedback owns an event

@@ -18,7 +18,7 @@ Status: implemented

 `dsh-commands` 仍会围绕 `/feedback` 写入 `command/run` / `command/done` 生命周期配对，但该命令设置了 `recordInput: false`。因此，它的 `command/run` 携带命令标识与来源，但不携带 `args`；反馈文本只存在于 `feedback/record` 中，而 `command/done` 携带确认结果。三个记录都仅写入日志且非 surface。它们的追加会进入持久化的常规有界写入路径；没有任何环节强制 flush，因此确认文本报告的是反馈已进入日志，而非已经落盘。

-采集对正在运行的 agent（智能体）与模型仍不产生后续动作。可选的 OTel 遥测包后续增加了一个基础设施消费方：它在 `FEEDBACK_ONLY` 模式下将 `feedback/record` 作为释放触发器，在 `DISABLED` 模式下将其作为仅限本地的警告触发器，且不改变反馈事件或命令路径。见[反馈门控的会话遥测](2026-08-05-feedback-gated-session-telemetry.md)。
+采集对正在运行的 agent（智能体）与模型仍不产生后续动作。可选的 OTel 遥测包后续增加了一个基础设施消费方：它在 `FEEDBACK_ONLY` 模式下将 `feedback/record` 作为释放触发器，在 `DISABLED` 模式下将其作为仅限本地的警告触发器，且不改变反馈事件或命令路径。见[反馈门控的会话遥测](2026-08-05-feedback-gated-session-telemetry.md)与[确认文本中的共享披露](2026-08-07-feedback-acknowledgement-sharing-disclosure.md)。

 ### 为何反馈拥有自己的事件

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-mcp-client-auto-reconnect.md
+2026-08-06-mcp-client-auto-reconnect.md: 99a8aec1abe3713822f8f17c17d8efaca5d61a4d
+2026-08-06-mcp-client-auto-reconnect.zh.md: 8d4dc935e6edee9a05f556774e743e48234ca709
@@ -0,0 +1,48 @@
+# Agent Note: MCP client auto-reconnect with bounded backoff
+
+Status: implemented
+
+English | [中文](2026-08-06-mcp-client-auto-reconnect.zh.md)
+
+## Problem
+
+The [MCP client](2026-07-07-mcp-client-plugin.md) connected once at plugin load. When a stdio server crashed or was killed, its registered tools stayed visible but every call failed with `Not connected` until a human edited the config (HMR) or restarted the Host — v1 explicitly deferred reconnection. Long-running hosts (ACP automation, web) cannot be bounced because a child process died, and for stdio the harness composition is the only party that can respawn it. External feedback escalated this as a real operational gap (issue #1746).
+
+## Decision
+
+`packages/mcp/mcp-client/src/connection.ts` owns a per-instance connection supervisor; `apply()` shrinks to config resolution plus two effects (the `serverName` reservation and the supervisor's lifecycle). The supervisor owns the client/transport generations, the live tool registrations, and the reconnect loop.
+
+**Trigger.** The supervisor arms `client.onclose` per generation. The SDK fires it when the stdio child exits, so a crash is observed without polling. `StreamableHTTPClientTransport` fires `onclose` only for deliberate closes — it owns its internal SSE-stream recovery and surfaces request failures per call — so HTTP servers are effectively outside supervisor restarts; the package README records that limitation.
+
+**Generations without interleaving.** Each attempt builds a fresh transport and `Client` (the SDK binds a Protocol to one transport for life). One per-supervisor queue serializes every `syncTools` call — initial syncs and `list_changed` re-syncs across all generations — and an `isCurrent` fence makes stale generations inert, so no two syncs can interleave the dispose-previous/register-next swap (which would double-dispose one generation and leak another). The queue also closes a pre-existing race where two rapid `list_changed` notifications re-synced concurrently. The activation attempt, rather than the first queue entrant, explicitly owns strict startup registration: an early `list_changed` notification uses contained re-sync semantics and cannot consume `failOnStartupError`. Failure signals are idempotent per generation: a connect rejection racing its own transport close schedules exactly one retry. A failed attempt cannot enter backoff until both `Client.close()` settles and the transport reports `onclose`, which for stdio proves the child exited; a missing close signal stops reconnection after the SDK's bounded termination window instead of allowing two server processes to overlap. Disposal uses the same bounded close-signal barrier and reports an incomplete shutdown without ever restarting.
+
+**Bounded backoff with an outage budget.** Delays double from `initialDelayMs` up to `maxDelayMs`. One outage shares `maxAttempts` consecutive failed attempts; exhaustion unregisters the server's tools, logs at error level, and stops until disposal or reload. A connection that survives past the stability window — `maxDelayMs`, derived rather than a fifth tunable, as the longest configured backoff spacing — resets the budget, so an occasionally-crashing server recovers indefinitely while a crash loop whose connects briefly succeed cannot launder its budget into a restart storm.
+
+**Config and resolution.** Both transports accept `reconnect { enabled, initialDelayMs, maxDelayMs, maxAttempts }` with schemastery defaults (on, 500ms, 30s, 10). `resolveReconnectPolicy()` is the explicit resolve step: it re-judges every bound and cross-field constraint because programmatic construction may bypass Schemastery, and misconfiguration fails the plugin instance at load.
+
+**Observable states.** An initial or retry-attempt failure says `connection failed`; an established generation ending says `connection lost`. Retrying logs at warn with attempt count and delay, recovery at info, final failure and disabled recovery at error. During an outage the last good generation stays registered and calls against it fail — deterministic public names mean a recovered unchanged tool list reproduces identical definitions, keeping the model-visible schema prefix stable instead of flapping. With `reconnect.enabled: false` a lost connection keeps the v1 manual-recovery behavior.
+
+**Disposal.** Dispose flips the fence, cancels any pending timer, closes the current client, then awaits the in-flight attempt and the sync queue before unregistering — quiescence, not just a request to stop. The reconnect timer is unref'd so a waiting backoff never holds a finishing process open.
+
+## Alternatives considered
+
+**Consecutive-failure counter that resets on every successful connect.** Rejected: a crash-looping server whose connects briefly succeed would reset the budget each cycle and restart forever — exactly the restart storm the failure cap exists to prevent. The uptime-gated reset distinguishes a recovered server from a looping one without new configuration.
+
+**Reuse one SDK `Client` across reconnects.** The Protocol clears its transport on close and can technically connect again, but the SDK's own guidance is one connection per Protocol instance, and reuse carries notification handlers and negotiated capability state across server incarnations. A fresh `Client` per generation plus the `isCurrent` fence is unambiguous.
+
+**Unregister tools immediately on disconnect, re-register on recovery.** Rejected: a transient outage would flap the model-visible tool list (two schema-prefix invalidations per crash) for no information gain; failing calls already signal the outage, and the swap on recovery is atomic per generation. Tools are unregistered at final failure so a permanently dead server does not leak permanently broken tools.
+
+**Route Streamable HTTP request failures into the supervisor.** Rejected for now: the HTTP transport already reconnects its SSE stream with its own backoff, per-request errors do not imply a dead server, and there is no child process the harness could respawn. Transport close stays the single trigger.
+
+**Restart through Loader/HMR machinery instead of an in-plugin supervisor.** Rejected: the Loader owns config-driven recomposition, not runtime health. A plugin restarting itself through the Loader would conflate config generations with connection generations and lose the per-outage budget.
+
+## Testing
+
+Unit (`tests/reconnect.spec.ts`, mocked SDK): recovery swaps generations without duplication or leaks and serves post-recovery calls, diagnostics distinguish initial or retry failure from established connection loss, strict startup registration survives a pre-connect `list_changed` notification, failed initialization waits for the old generation's close signal and fails closed when that signal never arrives, disposal waits for the same signal with a bounded incomplete-shutdown path, the failure cap unregisters tools and stops, dispose cancels a pending backoff and quiesces an in-flight sync, a close after dispose schedules nothing, disabled mode keeps the v1 behavior, the stability window resets the budget while a crash loop exhausts it, double failure signals schedule one retry, stale generations and handlers are inert, and `resolveReconnectPolicy` rejects each invalid bound. E2E (`tests/mcp-client.e2e.ts`, keyless): the fixture server gained a `crash` tool that replies then exits; real-process tests prove a stdio crash recovers end to end and that unloading the plugin mid-outage stops reconnection promptly. Snapshot: deliberately none, per the original note's rationale — reconnection adds no new presentation shape, and a snapshot composition spawning a crashing server would make replays timing-dependent.
+
+## Consequences
+
+- A crashed stdio MCP server recovers without human intervention: bounded backoff, re-discovery, atomic generation swap. Default policy retries an outage for roughly 2.5 minutes before giving up.
+- Connection state is genuinely more intricate than connect-once — the partial-availability window v1 avoided now exists (registered tools failing during an outage), concentrated in one module with the invariants named.
+- `reconnect` is new config surface on both transports, and the stability window is deliberately derived from `maxDelayMs`; making it independently tunable is a compatible future change.
+- After final failure or with reconnect disabled, the plugin stays loaded with no (or failing) tools until reload — deliberate and logged, so a chronically broken server cannot restart forever.
@@ -0,0 +1,48 @@
+# Agent Note: MCP client auto-reconnect with bounded backoff
+
+Status: implemented
+
+[English](2026-08-06-mcp-client-auto-reconnect.md) | 中文
+
+## 问题
+
+[MCP 客户端](2026-07-07-mcp-client-plugin.md)在插件加载时仅连接一次。stdio 服务器崩溃或被终止后，其已注册的工具仍然可见，但每次调用均以 `Not connected` 失败，直到人工编辑配置触发 HMR（热模块替换）重载，或重启 Host——v1 明确推迟了重连机制。长时间运行的 Host（ACP 自动化、Web）不能因为子进程死亡就被重启；而对于 stdio 传输，harness 组合层是唯一能重新拉起子进程的一方。外部反馈将此升级为真实的运维缺口（issue #1746）。
+
+## 决策
+
+`packages/mcp/mcp-client/src/connection.ts` 拥有一个逐实例的连接监督器；`apply()` 收缩为配置解析加两个副作用（`serverName` 预留和监督器的生命周期）。监督器负责管理 client/transport 代、活跃的工具注册以及重连循环。
+
+**触发条件。** 监督器在每一代上挂载 `client.onclose`。SDK 在 stdio 子进程退出时触发该回调，因此崩溃无需轮询即可感知。`StreamableHTTPClientTransport` 仅在主动关闭时触发 `onclose`——它内部拥有自己的 SSE（Server-Sent Events）流恢复机制，并将请求失败以逐调用方式暴露——因此 HTTP 服务器实际上不在监督器的重启范围内；包 README 记录了该限制。
+
+**代隔离，无交错。** 每次尝试构建一个全新的 transport 和 `Client`（SDK 将一个 Protocol 绑定到一个 transport 上终身使用）。每个监督器内部有一个队列将所有 `syncTools` 调用串行化——跨所有代的初始同步和 `list_changed` 再同步——`isCurrent` 栅栏使过时的代变为惰性，从而确保不会有两次同步交错执行 dispose 上一代/注册下一代的切换（否则会对同一代执行两次 dispose 并泄漏另一代）。该队列还消除了一个先前存在的竞态：两次快速的 `list_changed` 通知同时触发重新同步。严格启动注册由激活尝试本身显式拥有，而非由首个入队者拥有；提前到达的 `list_changed` 采用故障隔离的再同步语义，不能消费 `failOnStartupError`。失败信号按代幂等：一次连接拒绝与其自身 transport 关闭竞态时，仅调度恰好一次重试。失败尝试只有在 `Client.close()` 结算且 transport 报告 `onclose` 后才能进入退避；对 stdio 而言，`onclose` 证明子进程已退出；若关闭信号始终未到，则在 SDK 的有界终止窗口结束后停止重连，而不是允许两个服务器进程重叠运行。dispose 使用同一个有界关闭信号屏障；若关停未完成则予以报告，且绝不重启。
+
+**有界退避与故障预算。** 延迟从 `initialDelayMs` 起逐次翻倍，上限为 `maxDelayMs`。一次故障期间共享 `maxAttempts` 次连续失败尝试的预算；耗尽后注销该服务器的工具、以 error 级别记录日志并停止，直到 dispose 或重新加载。连接在存活超过稳定窗口——即 `maxDelayMs`，作为最长退避间隔从配置推导得出而非作为第五个独立调参项——之后重置预算；因此偶尔崩溃的服务器可无限恢复，而连接短暂成功后立即再次崩溃的循环无法将其预算洗白为重启风暴。
+
+**配置与解析。** 两种传输均接受 `reconnect { enabled, initialDelayMs, maxDelayMs, maxAttempts }` 配置，Schemastery 默认值为（启用、500ms、30s、10）。`resolveReconnectPolicy()` 是显式的解析步骤：它重新校验每个边界值和跨字段约束，因为程序化构造可能绕过 Schemastery，配置错误在加载时即令插件实例失败。
+
+**可观测状态。** 初始尝试或重试尝试失败时记录 `connection failed`，已建立的代结束时记录 `connection lost`；重试的 warn 日志包含尝试次数和延迟，恢复以 info 级别记录，最终失败和禁用重连时的断连以 error 级别记录。故障期间，上一个正常代保持注册，对其工具的调用返回失败——确定性公开名称意味着恢复后未变化的工具列表会复现相同的定义，保持模型可见 schema 前缀稳定而非反复抖动。设置 `reconnect.enabled: false` 后，断连保持 v1 的手动恢复行为。
+
+**资源释放。** dispose 翻转栅栏、取消待执行的定时器、关闭当前 client，然后等待正在进行的尝试和同步队列完成后再注销工具——完全停稳，而非仅发出停止请求。重连定时器使用 unref，因此等待中的退避不会阻止进程正常退出。
+
+## 曾考虑的替代方案
+
+**连续失败计数器，每次成功连接即重置。** 否决：连接短暂成功后立即崩溃的循环服务器会在每个周期重置预算并永远重启——恰恰是失败上限旨在防止的重启风暴。基于运行时间的重置能区分已恢复的服务器与循环崩溃的服务器，无需新增配置。
+
+**跨重连复用同一个 SDK `Client`。** Protocol 在关闭时清除其 transport，技术上可以再次连接，但 SDK 自身的指导方针是每个 Protocol 实例对应一次连接，且复用会将通知处理器和已协商的能力状态带入新的服务器实例。每代创建全新 `Client` 加 `isCurrent` 栅栏的方式无歧义。
+
+**断连时立即注销工具，恢复时重新注册。** 否决：短暂故障会使模型可见工具列表抖动（每次崩溃触发两次 schema 前缀失效），而无任何信息增益；失败的调用已足以标示故障，恢复时的切换按代原子执行。工具仅在最终失败时注销，确保永久死亡的服务器不会泄漏永久失效的工具。
+
+**将 Streamable HTTP 请求失败路由到监督器。** 暂不采纳：HTTP 传输已使用自己的退避机制重连其 SSE 流，逐请求错误并不意味着服务器已死，且 harness 没有可重新拉起的子进程。transport 关闭仍是唯一触发条件。
+
+**通过 Loader/HMR 机制重启，而非使用插件内监督器。** 否决：Loader 负责配置驱动的重组合，而非运行时健康管理。插件通过 Loader 重启自身会混淆配置代与连接代，并丢失逐故障预算。
+
+## 测试
+
+单元测试（`tests/reconnect.spec.ts`，mock SDK）：恢复在不产生重复或泄漏的前提下切换代并服务恢复后的调用、诊断区分初始或重试尝试失败与已建立连接丢失、严格启动注册在连接前收到 `list_changed` 通知后仍然生效、初始化失败会等待旧代的关闭信号，若该信号始终未到则停止重连、dispose 同样等待同一关闭信号，并在有界等待到期时报告关停未完成、失败上限注销工具并停止、dispose 取消待执行的退避并使进行中的同步完全停稳、dispose 后的关闭不调度任何操作、禁用模式保持 v1 行为、稳定窗口重置预算而崩溃循环耗尽预算、双重失败信号仅调度一次重试、过时的代和处理器为惰性、`resolveReconnectPolicy` 拒绝每个无效边界值。E2E（`tests/mcp-client.e2e.ts`，无需密钥）：fixture 服务器新增了一个 `crash` 工具（先回复再退出）；真实进程测试证明 stdio 崩溃端到端恢复，以及在故障期间卸载插件能立即停止重连。快照：刻意不做，原因与原 Agent Note 相同——重连不引入新的展示形态，而在快照组合中 spawn 崩溃服务器会使回放依赖时序。
+
+## 后果
+
+- 崩溃的 stdio MCP 服务器无需人工干预即可恢复：有界退避、重新发现、原子代切换。默认策略对一次故障大约重试 2.5 分钟后放弃。
+- 连接状态确实比一次性连接更复杂——v1 刻意回避的部分可用窗口现已存在（故障期间已注册工具返回失败），集中在一个模块中并命名了所有不变式。
+- `reconnect` 是两种传输上的新配置表面，稳定窗口刻意从 `maxDelayMs` 推导；将其设为独立可调参数是兼容的未来变更。
+- 最终失败后或禁用重连时，插件保持加载状态但无（或失败的）工具，直到重新加载——行为是刻意的且有日志记录，确保长期故障的服务器不能永远重启。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-07-feedback-acknowledgement-sharing-disclosure.md
+2026-08-07-feedback-acknowledgement-sharing-disclosure.md: 1e9cd0fb95d78aff9f6434e0583154e2c3f847da
+2026-08-07-feedback-acknowledgement-sharing-disclosure.zh.md: ac26b18ad523feeabc297b212210dd73eff93a0a
@@ -0,0 +1,27 @@
+# Agent Note: Feedback acknowledgement sharing disclosure
+
+Status: implemented
+
+English | [中文](2026-08-07-feedback-acknowledgement-sharing-disclosure.zh.md)
+
+## Problem
+
+The `/feedback` command records a log-only `feedback/record` event and acknowledges the user, but the acknowledgement carried no durable context about what happened to the session: deployments that mount session telemetry (`FULL`, `FEEDBACK_ONLY`, or `DISABLED`) had no way to tell the user whether their feedback and session left the process, and the receiving session id was not echoed. The command plugin could not read the sharing policy because the telemetry seam exposed capture only, and the OTel mode enum lived in the optional backend package.
+
+## Decision
+
+The telemetry seam (`@deepseek-ai/dsh-session-telemetry`) now owns a backend-independent sharing vocabulary: `TelemetrySharingStatus` (`full` | `feedback-only` | `disabled`) plus a required abstract `sharing` member on the `Telemetry` service class — every backend must disclose its policy, so a consumer renders "not configured" only when no telemetry service is mounted. `@deepseek-ai/dsh-session-telemetry-otel` maps its serialized `TelemetryMode` (the [feedback-gated delivery decision](2026-08-05-feedback-gated-session-telemetry.md) owns the mode semantics) onto that status in the constructor and discloses it, including in `DISABLED`. The `/feedback` handler reads the mounted service through the plugin context (`ctx.get('telemetry')`, never a declared injection, so the command loads and runs without telemetry) and appends one sharing sentence to the acknowledgement: `Feedback recorded for session {id}. <sentence>`. No service → `Session sharing is not configured.`; `disabled` → `Session sharing is disabled.`; `feedback-only` → `Session sharing is feedback-gated; recording feedback releases the session prefix for sharing.`; `full` → `Session sharing is enabled.`
+
+The disclosure states the current sharing policy only; it never promises delivery or retention. Handoff is the backend's non-blocking enqueue and batching, retry, and loss policy stay the backend SDK's, and a later reconfiguration can change what was shared, so the sentences claim nothing about what reached a collector or about future retention. The disclosure adds no session event and never reaches the model surface; the web client renders it through the existing command row (`CommandNode` outcome text) with no client change.
+
+## Alternatives considered
+
+**A client-side status RPC and badge.** Rejected because the acknowledgement is host-produced and the web client already renders the command result text verbatim in the command row; a separate RPC would duplicate the status in a second surface and add a wire contract for a sentence.
+
+**Declared `telemetry` injection in `command-feedback`.** Rejected because telemetry is optional: a declared injection fails plugin load when the service is absent, while the command must work without it. The plugin reads the service with `ctx.get('telemetry')` at handler time instead.
+
+**OTel package owns the vocabulary.** Rejected because `command-feedback` must not depend on the optional OTel backend package. The seam owns `TelemetrySharingStatus` so any backend can disclose a policy.
+
+## Consequences
+
+The acknowledgement is user-visible: it names the receiving session and reports the current sharing policy, honest about the fire-and-forget handoff. Package tests pin the sentence for each status and for the absent-service case; the assembled-browser e2e mounts the shipped telemetry row in FULL mode against a local dead endpoint and pins the shipped default sentence (`Session sharing is enabled.`) as a golden. The seam member is required, so a mounted backend always discloses a policy and the "not configured" sentence truthfully means no telemetry service; the `/feedback` command keeps working with no telemetry mounted. A still-blank web session renders no command row, so feedback recorded before the first message gets no visible acknowledgement (documented under the package README's limitations).
@@ -0,0 +1,27 @@
+# Agent Note: 反馈确认中的会话共享披露
+
+Status: implemented
+
+[English](2026-08-07-feedback-acknowledgement-sharing-disclosure.md) | 中文
+
+## 问题
+
+`/feedback` 命令会记录一个仅写入日志的 `feedback/record` 事件并确认用户，但确认文本没有携带关于会话去向的持久信息：挂载了会话遥测（`FULL`、`FEEDBACK_ONLY` 或 `DISABLED`）的部署无法告知用户其反馈和会话是否离开了进程，确认文本也没有回显接收会话的 id。命令插件无法读取共享策略，因为遥测 seam 只暴露采集能力，而 OTel 模式枚举位于可选的后端包中。
+
+## 决策
+
+遥测 seam（`@deepseek-ai/dsh-session-telemetry`）现在拥有与后端无关的共享词汇：`TelemetrySharingStatus`（`full` | `feedback-only` | `disabled`），并在 `Telemetry` 服务类上增加一个必需的抽象 `sharing` 成员——每个后端都必须披露其策略，因此消费方只有在未挂载任何遥测服务时才渲染「未配置」。`@deepseek-ai/dsh-session-telemetry-otel` 在构造函数中把序列化的 `TelemetryMode`（模式语义由[反馈门控投递决策](2026-08-05-feedback-gated-session-telemetry.md)负责）映射到该状态并披露，包括 `DISABLED` 模式。`/feedback` 处理器通过插件上下文读取已挂载的服务（`ctx.get('telemetry')`，绝不是声明的注入，因此命令在无遥测时也能加载和运行），并在确认文本后追加一句共享披露：`Feedback recorded for session {id}. <句子>`。无服务 → `Session sharing is not configured.`；`disabled` → `Session sharing is disabled.`；`feedback-only` → `Session sharing is feedback-gated; recording feedback releases the session prefix for sharing.`；`full` → `Session sharing is enabled.`
+
+披露只陈述当前的共享策略，绝不承诺投递或留存：交接是后端的非阻塞入队，批处理、重试与丢失策略仍归后端 SDK，且后续重新配置可能改变已共享的内容，因此句子不声称任何内容已到达采集端，也不声称未来的留存。披露不新增任何会话事件，也绝不会进入模型 surface；Web 客户端通过现有的命令行（`CommandNode` 的结果文本）原样渲染，无需客户端改动。
+
+## 备选方案
+
+**客户端新增状态 RPC 与徽标。** 拒绝，因为确认文本由宿主生成，Web 客户端已经在命令行中原样渲染命令结果文本；单独的 RPC 会在第二个 surface 重复该状态，并为一句文案新增线上契约。
+
+**在 `command-feedback` 中声明 `telemetry` 注入。** 拒绝，因为遥测是可选的：服务缺失时声明注入会导致插件加载失败，而命令必须在无遥测时可用。插件改为在处理器执行时用 `ctx.get('telemetry')` 读取服务。
+
+**由 OTel 包拥有词汇。** 拒绝，因为 `command-feedback` 不能依赖可选的 OTel 后端包。seam 拥有 `TelemetrySharingStatus`，任何后端都能披露策略。
+
+## 后果
+
+确认文本对用户可见：它点名接收会话并报告当前的共享策略，如实说明 fire-and-forget 交接。包级测试为每种状态以及无服务场景固定句子；组装浏览器 e2e 以 FULL 模式挂载随附的遥测行（指向本地 dead 端点），并以 golden 固定随附默认句子（`Session sharing is enabled.`）。seam 成员是必需的，因此已挂载的后端总会披露策略，「未配置」句子如实地表示没有遥测服务；`/feedback` 命令在未挂载遥测时仍能正常工作。仍为空白的新 Web 会话不渲染命令行，因此首条消息之前记录的反馈没有可见确认（已在包 README 的限制中记录）。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-07-workspace-picker-composer-entry.md
+2026-08-07-workspace-picker-composer-entry.md: dc9c26c291de6e7614ace3c787030c0032a9740d
+2026-08-07-workspace-picker-composer-entry.zh.md: 585c59b12392823a7388ab7a635a864bd4108929
@@ -0,0 +1,29 @@
+# Agent Note: The no-Workspace composer opens the existing picker
+
+Status: implemented
+
+English | [中文](2026-08-07-workspace-picker-composer-entry.zh.md)
+
+## Problem
+
+The [session-scope decision](../architecture/2026-07-25-web-client-session-scope-and-provide-channel.md) keeps one resident composer before a Workspace exists, but its textarea was disabled and only the smaller Workspace chip could open the picker. The largest and most familiar starting affordance therefore rejected the user's first click even though a recovery action was available on the same surface.
+
+## Decision
+
+While no Workspace owns the new Session, the whole composer card activates the existing `conversation.hero.workspace` picker by pointer click — the card owns the click handler and its disabled controls let pointer events fall through, so the full capsule is one target — and the read-only resident textarea does the same by Enter or Space. `aria-haspopup="menu"` and `aria-expanded` describe the shared picker menu while it is mounted. On a fresh installation with no Workspace rows, the picker immediately hands off to the directory dialog and clears its expanded state; that dialog exposes its own accessibility semantics. A dashed l4 stroke (an SVG dash ring, since native `dashed` has a fixed pattern) with a business-blue hover marks the card as the pick affordance. The card contains `pointerdown`, so the open picker's outside-close cannot race the click's reopen — that close-then-open flickered the chip's expansion echo. Message submission, command, permission, model, and other Session-scoped controls remain locked until Workspace selection creates or reconnects a real Session.
+
+Workspace selection retains the existing owner and flow. `ConversationRoot` opens the picker, `WorkspacePicker` lists or creates the Workspace, and the same textarea DOM node becomes the editable composer after the Session arrives.
+
+## Alternatives considered
+
+**Keep the textarea disabled and emphasize the Workspace chip.** This preserves the old control boundary but leaves the dominant composer surface inert during the first action.
+
+**Place a transparent button over the textarea.** A button has direct trigger semantics, but it creates a second focusable element over the resident textarea and complicates the DOM-identity transition that preserves focus, IME, and draft behavior.
+
+**Accept a draft before Workspace selection.** This would require a client-owned draft Session or another pre-Session state axis. The feature only needs a discoverable path into the existing picker.
+
+## Consequences
+
+The first composer click now continues the required setup flow, and keyboard users can activate the same path. The textarea accurately reports read-only state until a Session exists, while adjacent controls remain disabled. The UI introduces no new Workspace state, transport, or directory-selection flow.
+
+Component coverage pins pointer and keyboard activation, the card-wide click target, the contained `pointerdown`, locked adjacent controls, picker expansion, and the same-node transition to an editable textarea. The assembled Web helper begins fresh Workspace setup through the textarea, so replayed browser scenarios exercise the shipped path.
@@ -0,0 +1,29 @@
+# Agent Note: 未选择 Workspace 时从编辑器打开现有选择器
+
+Status: implemented
+
+[English](2026-08-07-workspace-picker-composer-entry.md) | 中文
+
+## 问题
+
+[Session scope 决策](../architecture/2026-07-25-web-client-session-scope-and-provide-channel.md)会在 Workspace 存在前保留同一个常驻编辑器，但 textarea 处于禁用状态，只有较小的 Workspace chip 能打开选择器。用户首次点击最显眼、也最熟悉的输入区域时，界面不会响应，尽管同一界面已有继续操作的入口。
+
+## 决策
+
+新会话尚未归属任何 Workspace 时，整张输入卡片都可通过鼠标点击激活现有的 `conversation.hero.workspace` 选择器——点击处理器归卡片所有，其禁用控件放行指针事件，因此整个胶囊是同一个目标；只读的常驻 textarea 也可经 Enter 或 Space 激活。`aria-haspopup="menu"` 和 `aria-expanded` 在共享选择器菜单挂载时描述其展开状态。全新安装没有 Workspace 行时，选择器会立即转交目录对话框并清除自身的展开状态；该对话框使用自己的可访问性语义。虚线 l4 描边（SVG dash ring，因为原生 `dashed` 的间距不可调）配合 hover 时的 business 蓝，把卡片标记为选择入口。卡片会拦下 `pointerdown`，使已打开选择器的外点关闭无法与点击的重新打开竞态——先关后开会让 chip 的展开回显闪动。消息提交、命令、权限、模型及其他 Session 作用域控件会保持锁定，直到用户选择 Workspace 并创建或重新连接真实 Session。
+
+Workspace 选择继续使用现有 owner 和流程。`ConversationRoot` 打开选择器，`WorkspacePicker` 列出或创建 Workspace；Session 到达后，同一个 textarea DOM 节点变为可编辑状态。
+
+## 考虑过的替代方案
+
+**保持 textarea 禁用并突出 Workspace chip。** 这样能保留原有控件边界，但首次操作时最主要的编辑器区域仍然没有响应。
+
+**在 textarea 上方放置透明按钮。** 按钮具备直接的触发器语义，但它会在常驻 textarea 上方增加第二个可聚焦元素，并使保留焦点、输入法和草稿行为的 DOM identity 过渡更复杂。
+
+**在选择 Workspace 前接收草稿。** 这需要由 client 拥有的草稿 Session 或另一条 Session 前状态轴。此功能只需要提供一个更容易发现的现有选择器入口。
+
+## 后果
+
+用户首次点击编辑器即可继续必要的设置流程，键盘用户也能激活同一路径。textarea 会如实报告只读状态，直到 Session 存在；相邻控件仍处于禁用状态。界面没有引入新的 Workspace 状态、传输或目录选择流程。
+
+组件测试会固定鼠标和键盘激活、覆盖整卡的点击目标、被拦下的 `pointerdown`、相邻控件锁定、选择器展开，以及同一节点变为可编辑 textarea 的过渡。组装后的 Web helper 会通过 textarea 开始全新 Workspace 设置，因此重放浏览器场景会覆盖实际交付路径。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-08-web-background-task-display.md
+2026-08-08-web-background-task-display.md: 558d0e26b3b8da83602296c5fdd0944886d4eab7
+2026-08-08-web-background-task-display.zh.md: 9c9f4643bb08c748381ede6bf585858ca1204ff7
@@ -0,0 +1,136 @@
+# Agent Note: Web background-task display
+
+Status: implemented
+
+English | [中文](2026-08-08-web-background-task-display.zh.md)
+
+## Problem
+
+`ctx.tasks` already runs every long-lived piece of work the harness starts in the background — `bash`, `pwsh`, `pty-send`, and one-shot background subagents — but its only reader was the model. [`dsh-tool-tasks`](../../../../packages/tasks/tool-tasks/README.md) exposes `task_list`, `task_output`, and `task_kill`, and nothing else observed the registry.
+
+A human at the Web client therefore could not see that a build was running, could not distinguish a finished task from a stuck one, and could not stop one. The only trace was the `run_in_background` tool card that printed a task id somewhere earlier in the transcript, and that card never updates again.
+
+The session header was already the place where per-session background activity lives: [`dsh-client-ui-subagent`](../../../../packages/client/ui-subagent/README.md) contributes the subagent catalog to `conversation.session.header.actions`. Placement was settled. What was missing was any channel at all that carried task state to a browser.
+
+## Decision
+
+Task state reaches the browser as **one whole-snapshot mux frame per session**, pushed at every registry commit point that changes what that session can see. The client keeps a last-wins mirror; a header action renders it. There is no RPC, no polling, and no client-side staleness bookkeeping.
+
+This ships the list alone. Per-task streamed output and a human-initiated cancellation are separate phases, and the channel is shaped so neither has to undo it.
+
+### Wire shape
+
+One frame in the mux stream:
+
+```ts ignore-check
+| { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] }
+```
+
+`TaskView` is browser-safe and owned by the carrier at [`packages/host/apiproxy/src/api/tasks.ts`](../../../../packages/host/apiproxy/src/api/tasks.ts), alongside the other domain contracts, with its wire schema beside it in `tasks.schema.ts`:
+
+```ts
+import type { TaskId } from '@deepseek-ai/dsh-tasks/brand'
+
+export interface TaskView {
+  id: TaskId
+  kind: string
+  label: string
+  status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed'
+  detail?: string
+  startedAt: number
+  finishedAt?: number
+}
+```
+
+`TaskId` comes from the cordis-free [`@deepseek-ai/dsh-tasks/brand`](../../../../packages/tasks/tasks/src/brand.ts) leaf — the same arrangement as the `@deepseek-ai/dsh-llm/brand` import `api/subagents.ts` already uses, because the `dsh-tasks` root reaches `dsh-agent` and is unreachable from a client program even as a type. Like every other non-root subpath in this workspace, it carries an explicit `tsconfig.base.json` `paths` entry; without one the TypeRT analyzer resolves the specifier to `lib/types/` and rejects the reference as unexported.
+
+`kind` is `string` on the wire rather than `TaskKind`. The kind map is merge-extensible by producer plugins, so a client build cannot enumerate the closed set; presentation falls through a documented default for an unrecognized kind.
+
+Three `TaskSnapshot` fields are deliberately absent: `ownerSession` (the frame's `sessionId` already carries it), `reported` (an internal notice-delivery bit with no user meaning), and `outputLimitBytes` (producer-owned model-presentation policy).
+
+The frame carries a whole snapshot rather than a delta for the reason [`session/queue`](../../../../packages/host/apiproxy/src/api/events.ts) states for itself: start, kill, settlement, reconnect, and a second browser tab all converge through one authoritative value. A session's task set is single-digit; the frame is small.
+
+### The task-registry change feed
+
+`TaskService` owns one observation method:
+
+```ts ignore-check
+abstract onTasksChanged(listener: TasksChangedListener): () => void
+```
+
+It fires **after** every commit that changes what `list(owner)` returns: registration at the end of `start()`, the `stopping` transition in `kill()`, settlement, and the removal `disposeOwner()` performs. An `undefined` owner means an unowned task changed, and therefore every caller's view changed.
+
+The listener is owner-granular rather than task-granular. The only consumer pushes whole snapshots, so a per-task record would be discarded on arrival — and a per-task feed cannot express the owner-disposal removal at all without inventing a tombstone status nothing else needs.
+
+`onTaskDone` is not a subset of this. It delivers the terminal record with the exact owner `Agent` under first-wins semantics that `dsh-tool-tasks` couples to `reported`; `onTasksChanged` is pure observation with no delivery meaning and marks nothing reported. Listener throws are contained and never awaited, matching `onTaskDone`, and each registration is an effect on the calling fiber.
+
+Service disposal deliberately announces nothing. Every `onTasksChanged` registration is an effect on the registry's own fiber, so the listeners are already gone by the time teardown clears the store; an observer learns the registry left through its own disposal, not through a final empty set.
+
+### The api-proxy carrier
+
+`mux()` subscribes `ctx.tasks.onTasksChanged` and pushes `session/tasks`; the subscription baseline rides next to the existing `session/subscribed` control frames, so a reconnecting client is current before it renders.
+
+Four rules the carrier keeps:
+
+- **Never resume.** A change push reads `tasks.list(owner)` with the exact `Agent` the listener supplied, which stays correct even while that owner's scope is tearing down and a lookup by id would already miss. The baseline instead reads `ctx.tasks.list(ctx.agents.get(session.id))` — the non-resuming registry read, where a session with no live Agent correctly yields only the unowned tasks. Neither path touches the [`api-remotes` Agent resolver](../../../../packages/api/remotes/src/agent-lookup.ts), which resumes a cold session as a side effect of lookup; listing must never revive a session the user merely scrolled past.
+- **Fan out unowned changes.** An `undefined` owner pushes a fresh snapshot to every subscribed session, because unowned tasks are visible to every caller.
+- **Stay optional.** The carrier reads `ctx.get('tasks')`. A composition without the registry emits no frames, and the client renders no entry point — the posture `sessionProjections` already has in this file.
+- **Say nothing about nothing.** The baseline is pushed only for sessions whose list is non-empty, and an absent key on the client means an empty list. A change that empties a list still pushes `[]`, because that one transition is the only thing the client cannot infer from absence.
+
+### The client mirror
+
+`SessionListState` carries `tasksBySession: Readonly<Record<SessionId, readonly TaskView[]>>`, owned by `SessionManager` and folded from the frame under last-wins, with an emptied set stored as an absent key so absence and `[]` are one representation.
+
+It lives on the list mirror rather than on `Session` for three reasons: the header action already reads list state through `useSessions`, nothing needs the pre-instantiation buffering `session/queue` requires (no composer behavior depends on tasks), and a later sidebar indicator gets the data without opening a second channel.
+
+Two clears keep it honest. On re-subscribe the manager drops the session's mirror — the rule `session/queue` already follows, because a fresh baseline is arriving and this generation sends none for an empty set, so a retained list would survive as a phantom. On `host/session-removed` it drops the mirror again: owner disposal already removed the records registry-side, but that lands on the mux stream while the removal frame rides the host stream, so the two have no relative order.
+
+### The header action
+
+[`@deepseek-ai/dsh-client-ui-task`](../../../../packages/client/ui-task/README.md) registers one entry in `conversation.session.header.actions`, ordered after the subagent catalog. Its own README owns the presentation contract; the decisions worth recording here are that the control does not render at all until the session has a task, that the live badge is omitted at zero so a history-only session keeps a quiet entry point, and that settled rows stay visible because a failed task's `detail` is the only place its failure is legible.
+
+A running one-shot background subagent therefore appears both there and in the subagent catalog. The two answer different questions — the catalog navigates into the child's transcript, this list is the only handle a cancellation can ever attach to — and suppressing `kind: 'subagent'` here would leave the cancellation phase with no entry point for exactly those tasks.
+
+### What this deliberately does not do
+
+**No web path calls `ctx.tasks.read()`.** It consumes the single output cursor, so a browser read would silently take bytes the model's `task_output` will never see. This is an invariant worth a test rather than a convention, because the failure is invisible at the call site.
+
+**No cancellation.** That phase owes a decision the seam does not currently answer: `kill()` marks terminal delivery reported, so a human interrupt written against today's contract would leave the model believing its task is still running.
+
+**No output watermark on the frame.** The output phase's delta channel is where an anchor field earns its place; one added now would have no reader.
+
+## Alternatives considered
+
+**Signal frame plus RPC pull, the subagent-catalog shape.** Push a payload-free `tasks-changed` signal, debounce, then re-read authoritative state over a unary RPC. This is what the subagent catalog does, and the cost is visible in [`SessionManager`](../../../../packages/client/runtime/src/client/sessions/manager.ts): `catalogInflight` for single-flight, `catalogStale` for a trailing re-pull when a membership frame lands mid-request, `updateCatalogActivity` patching loaded rows in place *and* writing into the in-flight request so a response older than the frame gets overwritten, `parentAvailableOverride` replaying a stale `false`, and a reconnect path re-pulling every open catalog. That apparatus exists because the catalog's authority is split — durable lineage from a projection, liveness sampled at response time — and tasks have no durable half to justify inheriting it. It also fails specifically at the moment the output phase cares about: a task settles, its output stream closes immediately, but status only arrives after debounce plus round-trip, so the UI shows a running task with a dead stream for that window.
+
+**Popover-scoped polling with no seam change.** Cheapest to build and the only option that avoids touching `TaskService`. It cannot support a resident count on the trigger without a resident poll, and both later phases need a real change feed anyway, so it buys a week and spends it back.
+
+**A session-projection unit over durable task events.** Projection units fold over committed session events, so this would first require task lifecycle to become durable — `task/started` … `task/settled` as a standalone open/close bracket, with the last [`session/end-seed`](../../../../packages/core/session/src/types.ts) marking any unmatched opener as dead history, exactly as the compaction bracket already does. It is genuinely cheaper on the client: `dsh-tool-todo` shows the whole pattern in a fifteen-line unit, and the existing `session/projection` frames, history-tail block, and persisted checkpoint cache would have carried the data with no new wire surface, no carrier subscription, and no manager state. It was rejected because it buys that with a durable format change in service of a browser list, and because it does not extend to the phase it would most need to: [`spill/`](../../../../packages/spill/README.md) exists precisely so oversized tool output stays out of the log, so streamed task output cannot ride durable events either way. Nothing here forecloses revisiting it if durable task history becomes valuable on its own merits.
+
+**Reusing `PublicTaskSnapshot` from `dsh-tool-tasks`.** Nearly the right fields, but it belongs to the model-facing control surface. A wire type a browser program imports from a tool package couples client presentation to prompt-facing decisions and drags a host-only package into a client build.
+
+**Folding tasks into the subagent catalog as one "activity" panel.** One entry point instead of two. Rejected because `SubagentCatalogAction` is already 605 lines whose subject is a durable session-lineage tree including finished children; process-scoped tasks are a second data model with different identity, lifetime, and affordances, and the catalog's lazily-expanded branch, duration, and token contracts would all need rewriting to host them.
+
+**A host-global task list across every session.** The literal reading of "show all running tasks". Rejected because the registry's authorization fence is per-owner-session, so a global read needs a new access rule, and a global list has no business in a session's header — it would need its own home in the sidebar. Nothing in this design blocks adding it later; the per-session frames are the same data.
+
+## Testing
+
+The [web e2e scenario](../../../../apps/web/tests/background-task-list.e2e.ts) is the end-to-end proof and runs keyless: a real `run_in_background` bash call registers with `ctx.tasks`, the header count and row appear with no user interaction, and killing the task through the registry flips the open list to its producer detail. It asserts the whole delivery path rather than any single layer.
+
+Below it, [`tasks-local`](../../../../packages/tasks/tasks-local/tests/tasks.spec.ts) pins the change feed at all four commit points, its containment of a throwing observer, and its removal on both explicit disposal and fiber teardown; [`api-proxy-tasks`](../../../../packages/host/apiproxy/tests/api-proxy-tasks.spec.ts) pins the baseline-only-when-non-empty rule, the three change pushes, the dropped internal fields, the unowned fan-out, the no-resume guarantee, and the registry-absent composition; and the client suites pin the last-wins fold, the absent-key representation, both clears, and the component's ordering, duration, and dismissal behavior.
+
+## Consequences
+
+**A missed commit point leaks rows.** If `disposeOwner()` removal ever stops firing the feed, the client keeps tasks that no longer exist until the session disappears. The whole-snapshot shape makes this recoverable rather than corrupting — the next legitimate change repairs the list — but the disposal path is the one most easily forgotten, so it carries its own test.
+
+**Unowned-task fan-out is easy to under-implement.** Pushing only to the changed owner's session is correct for owned tasks and silently wrong for unowned ones, which are visible everywhere. The bug would surface only in compositions that create unowned tasks, which is why the carrier suite covers it directly.
+
+**The UI set is not the registry's set.** The header shows what one session can see, so a task owned by another session never appears in it even though the registry holds it — and because the registry is process-local, a restart empties every list while the transcript still shows the `run_in_background` cards that started them. Unowned tasks are the opposite case: they reach every session's list, exactly as `list(caller)` reports them to every caller.
+
+**Settled rows accumulate.** The registry retains settled tasks until owner disposal, so a long session with many background commands grows a long list. Capping the settled tail is a presentation change, not a protocol one, if it becomes a real complaint.
+
+**`stopping` is nearly unreachable today.** Only the model's `task_kill` produces it, so the state is rendered but rarely seen until human cancellation lands. It is in the union now because leaving a status out would have made that phase a wire change.
+
+**Two entry points for one running subagent.** Accepted deliberately, and bounded to one-shot background delegations. If it reads as noise in practice, the fix is presentational — the catalog row can cite the task rather than the task list hiding the kind.
+
+**A new non-root subpath needs its `paths` entry.** `@deepseek-ai/dsh-tasks/brand` had to be registered in `tsconfig.base.json` before the TypeRT analyzer would accept the reference. The failure mode is a confusing "not exported by" error from a generator far from the edit, so the entry is part of adding a subpath, not an optimization.
@@ -0,0 +1,136 @@
+# Agent Note: Web 后台任务展示
+
+Status: implemented
+
+[English](2026-08-08-web-background-task-display.md) | 中文
+
+## 问题
+
+`ctx.tasks` 已经承载了 harness 在后台启动的全部长时工作——`bash`、`pwsh`、`pty-send`，以及一次性后台 subagent——但它唯一的读者是模型。[`dsh-tool-tasks`](../../../../packages/tasks/tool-tasks/README.md) 暴露了 `task_list`、`task_output` 和 `task_kill`，除此之外没有任何东西观察这个注册表。
+
+于是 Web 端的人类看不到构建正在跑，分不清一个任务是已经完成还是卡死，也无法把它停掉。唯一的痕迹是 transcript 里更早某处那张打印了 task id 的 `run_in_background` 工具卡片，而那张卡片此后再也不会更新。
+
+会话 header 本来就是每会话后台活动的落点：[`dsh-client-ui-subagent`](../../../../packages/client/ui-subagent/README.md) 把 subagent 目录贡献到 `conversation.session.header.actions`。位置没有争议。缺的是任何一条把任务状态送到浏览器的通道。
+
+## 决策
+
+任务状态以**每会话一帧的整份快照**到达浏览器，在注册表每一个会改变该会话可见内容的提交点推出。客户端保持一份 last-wins 镜像，由一个 header 入口渲染。没有 RPC，没有轮询，客户端不需要任何过期状态管理。
+
+本次只交付列表。每个任务的流式输出与人类发起的中断是各自独立的阶段，而通道的形状让两者都不必推翻它。
+
+### 线路形状
+
+mux 流中的一帧：
+
+```ts ignore-check
+| { type: 'session/tasks'; sessionId: SessionId; tasks: TaskView[] }
+```
+
+`TaskView` 是浏览器安全类型，由载体在 [`packages/host/apiproxy/src/api/tasks.ts`](../../../../packages/host/apiproxy/src/api/tasks.ts) 里拥有，与其他领域契约并列，线路 schema 就在旁边的 `tasks.schema.ts`：
+
+```ts
+import type { TaskId } from '@deepseek-ai/dsh-tasks/brand'
+
+export interface TaskView {
+  id: TaskId
+  kind: string
+  label: string
+  status: 'running' | 'stopping' | 'completed' | 'killed' | 'failed'
+  detail?: string
+  startedAt: number
+  finishedAt?: number
+}
+```
+
+`TaskId` 取自不依赖 cordis 的 [`@deepseek-ai/dsh-tasks/brand`](../../../../packages/tasks/tasks/src/brand.ts) 叶子——与 `api/subagents.ts` 已经在用的 `@deepseek-ai/dsh-llm/brand` 导入是同一种安排，因为 `dsh-tasks` 根出口会牵到 `dsh-agent`，即便只作类型也无法被客户端程序触及。和本仓库其他每一个非根子路径一样，它带有显式的 `tsconfig.base.json` `paths` 条目；没有这一条，TypeRT 分析器会把该 specifier 解析到 `lib/types/` 并判定该引用未被导出。
+
+线路上的 `kind` 是 `string` 而非 `TaskKind`。kind 映射由生产者插件按声明合并扩展，客户端构建无法枚举这个闭集；遇到无法识别的 kind，呈现层走一条有文档的默认分支。
+
+`TaskSnapshot` 的三个字段被刻意省去：`ownerSession`（帧的 `sessionId` 已经带了）、`reported`（内部的通知投递位，对用户无意义），以及 `outputLimitBytes`（生产者拥有的模型呈现策略）。
+
+这一帧带整份快照而非增量，理由就是 [`session/queue`](../../../../packages/host/apiproxy/src/api/events.ts) 为自己写下的那条：启动、中断、结算、重连，以及第二个浏览器标签页，全都通过同一个权威值收敛。一个会话的任务集是个位数，帧很小。
+
+### 任务注册表变更订阅
+
+`TaskService` 拥有一个观察方法：
+
+```ts ignore-check
+abstract onTasksChanged(listener: TasksChangedListener): () => void
+```
+
+它在每一个会改变 `list(owner)` 返回内容的提交点**之后**触发：`start()` 末尾的注册、`kill()` 里转入 `stopping`、结算，以及 `disposeOwner()` 执行的移除。`owner` 为 `undefined` 表示一个无主任务发生了变化，因而每一个调用方的视图都变了。
+
+监听器按 owner 而非按任务分粒度。唯一的消费方推的是整份快照，逐任务记录到手即弃——而且逐任务的订阅根本无法表达 owner 销毁时的移除，除非发明一个别处都不需要的墓碑状态。
+
+`onTaskDone` 不是它的子集。后者按 first-wins 语义投递终态记录和确切的 owner `Agent`，`dsh-tool-tasks` 把这套语义与 `reported` 绑在一起；`onTasksChanged` 是纯观察，不含任何投递含义，也不把任何东西标为已上报。监听器抛错被包住且从不 await，与 `onTaskDone` 一致，每次注册都是调用方 fiber 上的 effect。
+
+服务销毁刻意什么都不通告。每个 `onTasksChanged` 注册都是注册表自身 fiber 上的 effect，等到 teardown 清空 store 时监听器早已消失；观察者通过自己的销毁而不是一份最终空集来得知注册表离开了。
+
+### api-proxy 载体
+
+`mux()` 订阅 `ctx.tasks.onTasksChanged` 并推送 `session/tasks`；订阅 baseline 紧挨着既有的 `session/subscribed` 控制帧发出，让重连的客户端在渲染前就是最新的。
+
+载体守着四条规则：
+
+- **绝不 resume。** 变更推送用监听器给出的确切 `Agent` 调 `tasks.list(owner)`，即使该 owner 的 scope 正在拆除、按 id 查找已经查不到，它依然正确。baseline 则读 `ctx.tasks.list(ctx.agents.get(session.id))`——不触发 resume 的注册表读法，没有活体 Agent 的会话正确地只得到无主任务。两条路径都不碰 [`api-remotes` 的 Agent 解析器](../../../../packages/api/remotes/src/agent-lookup.ts)，那个解析器会把查询变成复活冷会话的副作用；列个任务不该让用户随手划过的会话活过来。
+- **无主变更要扇出。** `owner` 为 `undefined` 时向每一个已订阅会话推一份新快照，因为无主任务对所有调用方可见。
+- **保持可选。** 载体读 `ctx.get('tasks')`。没有挂注册表的组合不发任何帧，客户端也就不渲染入口——`sessionProjections` 在这个文件里已经是这个姿态。
+- **没有就不说。** baseline 只为列表非空的会话推送，客户端上键缺失即表示空列表。把列表清空的那次变更仍然推 `[]`，因为这一个转换是客户端唯一无法从「缺失」推断出来的东西。
+
+### 客户端镜像
+
+`SessionListState` 带有 `tasksBySession: Readonly<Record<SessionId, readonly TaskView[]>>`，由 `SessionManager` 拥有，按 last-wins 从帧折叠而来；被清空的集合存为缺失的键，使「缺失」与 `[]` 成为同一种表示。
+
+它放在列表镜像而不是 `Session` 上，有三个理由：header 入口本来就通过 `useSessions` 读列表状态；没有任何东西需要 `session/queue` 那种实例化前的缓冲（没有 composer 行为依赖任务）；将来侧栏加指示器时不必再开第二条通道。
+
+两处清理让它保持诚实。重新订阅时 manager 丢弃该会话的镜像——`session/queue` 已经遵循的规则，因为新的 baseline 正在路上，而这一世代对空集不发 baseline，被留下的列表会变成幽灵。`host/session-removed` 时再丢一次：owner 销毁在注册表侧已经移除了记录，但那件事落在 mux 流上而这一帧走 host 流，两者没有相对顺序。
+
+### header 入口
+
+[`@deepseek-ai/dsh-client-ui-task`](../../../../packages/client/ui-task/README.md) 在 `conversation.session.header.actions` 注册一个条目，排在 subagent 目录之后。呈现契约归它自己的 README；值得记在这里的决策是：会话没有任务时控件根本不渲染；活跃角标为零时省略，让只剩历史的会话保留一个安静的入口；终态行保持可见，因为失败任务的 `detail` 是其失败唯一可读之处。
+
+因此一个运行中的一次性后台 subagent 会同时出现在那里和 subagent 目录里。两者回答不同的问题——目录负责进入子会话的 transcript，而这个列表是中断能力唯一可能附着的句柄——在这里屏蔽 `kind: 'subagent'` 会让中断那一期恰好对这批任务没有入口。
+
+### 刻意不做的事
+
+**没有任何 Web 路径调用 `ctx.tasks.read()`。** 它消费唯一的输出游标，浏览器读一次就悄悄拿走了模型 `task_output` 永远看不到的字节。这该是一条有测试兜底的不变量而不是一条约定，因为它的故障在调用点完全不可见。
+
+**不做中断。** 那一期欠一个 seam 目前没有回答的决策：`kill()` 会把终态投递标为已上报，所以照今天的契约写出来的人类中断，会让模型一直以为它的任务还在跑。
+
+**帧上不带输出水位。** 输出那一期的增量通道才是锚点字段该出现的地方；现在加就是一个没有读者的字段。
+
+## 备选方案
+
+**信号帧加 RPC 拉取，即 subagent 目录的形状。** 推一个无 payload 的 `tasks-changed` 信号，防抖后用一元 RPC 重读权威状态。subagent 目录就是这么做的，代价在 [`SessionManager`](../../../../packages/client/runtime/src/client/sessions/manager.ts) 里一览无余：`catalogInflight` 做单飞行、`catalogStale` 在成员帧落于请求中途时补一次尾拉、`updateCatalogActivity` 既就地打补丁又往在途请求里写一份好让比帧更旧的响应被覆盖、`parentAvailableOverride` 重放一个过期的 `false`，还有重连时逐一重拉每个打开的目录。这套装置之所以存在，是因为目录的权威被劈成两半——持久血缘来自投影，活跃度是响应时刻的采样——而任务没有持久的那一半，不该继承这份复杂度。它还恰好在输出那一期最在意的时刻失效：任务结算，输出流立即关闭，状态却要等防抖加一次往返才到，那段窗口里 UI 显示一个流已死的运行中任务。
+
+**只在弹层打开时轮询，不改 seam。** 最省事，也是唯一不碰 `TaskService` 的选项。它无法在不常驻轮询的前提下支持触发器上的常驻计数，而后面两期反正都需要一条真正的变更订阅，所以它省下一周又还回去。
+
+**基于持久任务事件的 session-projection 单元。** 投影单元在已提交的会话事件上折叠，所以这条路要先让任务生命周期变持久——`task/started` … `task/settled` 作为一对独立的开合括号，由最后一个 [`session/end-seed`](../../../../packages/core/session/src/types.ts) 把未配对的开括号标为死历史，与 compaction 括号已有的做法完全一致。它在客户端确实更省：`dsh-tool-todo` 用十五行的单元展示了整套模式，而现成的 `session/projection` 帧、history-tail 块和持久化 checkpoint 缓存本可以承载这批数据，无需新线路面、无需载体订阅、无需 manager 状态。否决它，是因为这要拿一次持久格式变更去换一个浏览器列表，而且它并不能延伸到最需要它的那一期：[`spill/`](../../../../packages/spill/README.md) 的存在正是为了让超大工具输出留在日志之外，所以流式任务输出无论如何都不能骑在持久事件上。如果持久任务历史将来凭自身价值站得住，本设计不阻挡重新考虑它。
+
+**复用 `dsh-tool-tasks` 的 `PublicTaskSnapshot`。** 字段几乎就是对的，但它属于面向模型的控制面。浏览器程序从一个 tool 包导入线路类型，会把客户端呈现耦合到面向 prompt 的决策上，并把一个 host-only 包拖进客户端构建。
+
+**并进 subagent 目录做成统一的「活动」面板。** 一个入口而不是两个。否决的理由是 `SubagentCatalogAction` 已经 605 行，其主题是含已结束子会话的持久会话血缘树；进程域的任务是第二套数据模型，身份、生命期和可用动作都不同，而目录的懒展开分支、时长与 token 契约全都要重写才能容纳它们。
+
+**跨全部会话的 host 全局任务列表。**「显示所有运行中任务」的字面读法。否决是因为注册表的鉴权围栏是按 owner 会话的，全局读需要一条新的访问规则，而且全局列表不该出现在某个会话的 header 里——它需要侧栏里自己的位置。本设计没有阻挡后续再加；按会话的帧就是同一批数据。
+
+## 测试
+
+[web e2e 场景](../../../../apps/web/tests/background-task-list.e2e.ts)是端到端的证据，且无需密钥：一次真实的 `run_in_background` bash 调用注册进 `ctx.tasks`，header 的计数与行在没有任何用户操作的情况下出现，通过注册表杀掉该任务后打开着的列表翻到生产者给出的 detail。它断言的是整条投递链路，而不是其中某一层。
+
+在它之下，[`tasks-local`](../../../../packages/tasks/tasks-local/tests/tasks.spec.ts) 钉住变更订阅的全部四个提交点、对抛错观察者的包容，以及显式销毁与 fiber 拆除两条路径上的注销；[`api-proxy-tasks`](../../../../packages/host/apiproxy/tests/api-proxy-tasks.spec.ts) 钉住「非空才发 baseline」、三次变更推送、被丢弃的内部字段、无主扇出、不 resume 的保证，以及没有注册表的组合；客户端各套件钉住 last-wins 折叠、缺失键表示、两处清理，以及组件的排序、时长与关闭行为。
+
+## 影响
+
+**漏掉一个提交点会漏行。** 如果 `disposeOwner()` 的移除有朝一日不再触发订阅，客户端会一直留着已经不存在的任务，直到会话消失。整份快照的形状让这件事可恢复而非损坏——下一次正当变更就修好了——但销毁路径是最容易被忘掉的一条，所以它自带测试。
+
+**无主任务的扇出很容易做漏。** 只推给变更 owner 所在的会话，对有主任务是对的，对处处可见的无主任务则是悄悄错的。这个 bug 只会在会创建无主任务的组合里显形，所以载体套件直接覆盖了它。
+
+**UI 的集合不等于注册表的集合。** header 显示的是「一个会话能看到什么」，所以别的会话拥有的任务在这里永远不出现，尽管注册表里有它；而由于注册表是进程本地的，一次重启会清空所有列表，transcript 里那些启动它们的 `run_in_background` 卡片却还在。无主任务是反过来的情形：它们会进入每一个会话的列表，正如 `list(caller)` 对每个调用方都报告它们。
+
+**终态行会堆积。** 注册表把已结算任务留到 owner 销毁，所以一个跑了很多后台命令的长会话会积出长列表。如果真的成为抱怨，给终态尾巴加上限是呈现层改动而非协议改动。
+
+**`stopping` 今天几乎不可达。** 只有模型的 `task_kill` 会产生它，所以这个状态会被渲染但在人类中断落地之前很少见到。现在就纳入联合类型，是因为把它留在外面会让那一期变成一次线路变更。
+
+**一个运行中的 subagent 有两个入口。** 这是刻意接受的，且被限制在一次性后台委派这一种情况。如果实际用起来读着像噪声，修法是呈现层的——可以让目录行引用那个任务，而不是让任务列表隐藏这个 kind。
+
+**新增非根子路径必须补 `paths` 条目。** `@deepseek-ai/dsh-tasks/brand` 得先登记进 `tsconfig.base.json`，TypeRT 分析器才会接受该引用。它的故障表现是一条来自远离改动处的生成器的、令人困惑的「not exported by」错误，所以这个条目是新增子路径的组成部分，而不是优化。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-09-parallel-subagent-delegations.md
+2026-08-09-parallel-subagent-delegations.md: 01dc2043c9a79666857c4f5aa988fc45dc7cdf56
+2026-08-09-parallel-subagent-delegations.zh.md: 2c2bd700e362000b41adbd1f3cec9ba26ff60b93
@@ -0,0 +1,47 @@
+# Agent Note: Parallel subagent delegations
+
+Status: implemented
+
+English | [中文](2026-08-09-parallel-subagent-delegations.zh.md)
+
+## Problem
+
+A model that wants fan-out batches several `subagent` calls into one assistant message — that batch is the parallel intent. The delegation tool declared no `isConcurrencySafe` classifier, so the fail-closed scheduler ([parallel tool-call Agent Note](2026-07-10-parallel-tool-call-execution.md)) treated every foreground delegation as an exclusive barrier: nine cards in the GUI, one child running, eight queued behind it for its full runtime.
+
+The original conservative stance — a unary classifier cannot prove that sibling delegations have disjoint workspace effects — had stopped protecting anything. `run_in_background: true` and continuable delegations already overlap with every later call, including writes; `dsh-workflow-workerthread` already runs up to its concurrency ceiling of children through the same `ctx.subagents.start()` providers against the shared workspace. Only the foreground variant was serialized.
+
+## Decision
+
+`dsh-tool-subagent` declares `isConcurrencySafe: () => true` for every call form (foreground, one-shot background, continuable), so sibling delegations in one assistant step overlap under the loop's rolling pool up to `maxParallelToolCalls`, with results still committed in model order.
+
+The declaration satisfies the scheduler's safety contract structurally: a child works in its own session, a run never mutates the parent session (the start-time appends — `sandbox/mode`, `approval/policy`, `subagent/descriptor` — land only in the child's own log), and the tool returns its outputs to the loop for ordered commit. The one-shot background form's one parent-owned write is registering a Task through `tasks.start` — a synchronous, commutative insertion that satisfies the scheduler note's shared-state clause rather than the stronger no-mutation property. The provider seam requires concurrent starts and continuable preparations for distinct children to isolate operation-local state, cancellation, settlement, and cleanup. The bundled providers satisfy that contract: spawn and fork keep no mutable state between starts, fork reads only the parent's completed-turn prefix, out-of-process providers allocate state per run, and the continuation manager reserves a unique child identity and lock for each preparation.
+
+Coordinating sibling workspace effects is the model's responsibility, the stance the product already takes for background, continuable, and workflow children. Peer harnesses agree: Claude Code's Task tool is unconditionally concurrency-safe (cap 10), oh-my-pi's task tool defaults to its overlapping `shared` class, opencode's task tool runs unbounded under its SDK, and Codex sidesteps the question by making delegation an asynchronous spawn/wait mailbox.
+
+Capacity stays where the scheduler note put it: `maxParallelToolCalls` caps one step's unsettled tool calls — and therefore concurrently running foreground children — while background and continuable calls settle at start and free their pool slot, so children they leave running are not capped by it. LLM providers own their own capacity controls.
+
+## Testing
+
+Package tests pin the classifier for both call forms. A gate test drives the registry directly with two children that each block until both have started, proving the half the declaration depends on: the tool body and provider start path tolerate concurrent dispatch — hidden serialization in that stack would deadlock instead of passing silently. A continuable gate holds two provider preparations at the same await, cancels one caller before publication, and proves that the cancelled child leaves no Agent or durable Session while its sibling reaches inbox acceptance and persists independently. The scheduling half, classification actually producing overlap, is owned by the classifier pin and the snapshot below.
+
+The authored `subagent-parallel` snapshot pins the assembled-app transcript: one assistant message carries two subagent calls, the parent log records `tool/call, tool/call, tool/result, tool/result` (serial execution would interleave call/result pairs), and both children complete as separate sessions. Its twin delegations are deliberately identical: `dsh-llm-replay` binds child scripts by first-call order and the harvester orders children by `createdAt`, and neither is deterministic across concurrent children (the `XXX(concurrent-subagents)` marker), so only interchangeable twins replay race-free today.
+
+## Alternatives considered
+
+**Keep delegations exclusive.** The status quo protected nothing: background and workflow children already overlap freely with writes, so serializing the foreground variant only added latency and contradicted the model's explicit batching intent.
+
+**An input-sensitive classifier.** The call's arguments are a free-text description and prompt; nothing in them distinguishes a safe delegation from an unsafe one, so a conditional classifier would be theater.
+
+**A Codex-style asynchronous spawn/wait redesign.** Continuable children plus `send_message` already provide the asynchronous channel; rebuilding the foreground contract around a mailbox would discard a working synchronous result path to solve a scheduling problem one declaration fixes.
+
+**A per-instance `concurrencySafe` config knob.** No consumer needs a serial deployment: `maxParallelToolCalls: 1` already restores global serial execution, and peer-harness prior art defaults delegation to concurrency-safe.
+
+## Consequences
+
+Sibling children can race on shared workspace or external resources; the model owns that coordination, as it already does for every other overlapping child. Concurrent children also compete for LLM provider quota; `maxParallelToolCalls` caps only unsettled calls, not children a background or continuable call left running.
+
+Two one-shot background delegations in one message acquire their model-visible task ids (`subagent-<n>`) in dispatch-race order. The ids are logged, so replay stays valid, but a snapshot scenario that distinguishes its background children would inherit the same determinism constraint as twin child sessions.
+
+Ordered commits may hold a fast child's result behind a slow earlier sibling — the trade the [scheduler note](2026-07-10-parallel-tool-call-execution.md) already accepted; live surfaces still show each child's own progress.
+
+A concurrent-children snapshot scenario with distinct prompts still needs replay-harness support (deterministic child-script binding and harvest ordering); until then such scenarios must use interchangeable twin delegations.
@@ -0,0 +1,47 @@
+# Agent Note: 并行 subagent 委派
+
+Status: implemented
+
+[English](2026-08-09-parallel-subagent-delegations.md) | 中文
+
+## 问题
+
+想要扇出的模型会把多个 `subagent` 调用合并进同一条 assistant 消息：这个批次本身就是并行意图。委派工具此前没有声明 `isConcurrencySafe` 分类器，按安全侧原则设计的调度器（[并行工具调用 Agent Note](2026-07-10-parallel-tool-call-execution.md)）便把每个前台委派都当作独占屏障：GUI 里显示九张卡片，却只有一个子 agent（智能体）在运行，其余八个要在它的整个运行期间排在其后等待。
+
+最初的保守立场（一元分类器无法证明同级委派的工作区效果互不相交）已经不再保护任何东西：`run_in_background: true` 和可继续委派本来就会与其后的每个调用重叠执行，包括写入；`dsh-workflow-workerthread` 也早已通过同样的 `ctx.subagents.start()` 提供方在共享工作区上并发运行子 agent，数量可达其并发上限。只有前台形态被串行化。
+
+## 决策
+
+`dsh-tool-subagent` 为每种调用形态（前台、一次性后台、可继续）都声明 `isConcurrencySafe: () => true`，因此同一 assistant 步骤中的同级委派会在循环的滚动池下重叠执行，上限为 `maxParallelToolCalls`，结果仍按模型顺序提交。
+
+该声明在结构上满足调度器的安全约定：子 agent 在自己的会话中工作，运行绝不变更父会话（启动时追加的 `sandbox/mode`、`approval/policy`、`subagent/descriptor` 只落在子 agent 自己的日志里），工具把输出返回给循环，由循环按顺序提交。一次性后台形态对父级拥有状态的唯一写入是通过 `tasks.start` 注册一个 Task——这是一次同步、可交换的插入，满足的是调度器 Agent Note 中的共享状态条款，而非更强的「无变更」性质。提供方 seam 要求针对不同子 agent 的并发启动和可继续准备分别隔离操作局部状态、取消、结算和清理。内置提供方满足这项约定：spawn 和 fork 在各次启动之间不保留可变状态，fork 只读取父级已完成轮次的前缀，进程外提供方按每次运行分配状态，继续执行管理器则为每次准备预留唯一的子 agent 身份和锁。
+
+协调同级工作区效果是模型的职责，产品对后台、可继续和工作流子 agent 已经采取同样的立场。同类 harness 的做法一致：Claude Code 的 Task 工具无条件并发安全（上限 10）；oh-my-pi 的 task 工具默认归入其可重叠的 `shared` 类别；opencode 的 task 工具在其 SDK 下不设上限地运行；Codex 则把委派做成异步 spawn/wait 信箱，绕开了这个问题。
+
+容量控制仍保持在调度器 Agent Note 所定的位置：`maxParallelToolCalls` 限制单个步骤中未结算的工具调用数量——因而也限制并发运行的前台子 agent 数量——而后台和可继续调用在启动时即结算并释放池位，它们留下运行的子 agent 不受该上限约束。LLM（大语言模型）提供方负责自身的容量控制。
+
+## 测试
+
+包测试固定了两种调用形态的分类器。一个门控测试直接驱动注册表，其两个子 agent 各自阻塞，直到两者都已启动，以此证明该声明所依赖的那一半：工具体和提供方启动路径能容忍并发分发——这条栈中任何隐藏的串行化都会造成死锁，而不是静默通过。一个可继续门控测试让两项提供方准备停在同一个 await 上，在发布前取消其中一个调用方，并证明已取消的子 agent 不会留下 agent 或持久会话，而其同级则到达 inbox 接受状态并独立持久化。另一半（分类真正产生重叠执行）由分类器 pin 测试和下述快照负责。
+
+人工编写的 `subagent-parallel` 快照固定了组装后应用的 transcript（文本记录）：一条 assistant 消息携带两个 subagent 调用，父级日志记录为 `tool/call, tool/call, tool/result, tool/result`（串行执行会让调用/结果成对交错出现），两个子 agent 各自作为独立会话完成。其中的孪生委派刻意做成完全相同：`dsh-llm-replay` 按首次调用顺序绑定子脚本，harvester 按 `createdAt` 对子 agent 排序，二者在并发子 agent 之间都不具确定性（即 `XXX(concurrent-subagents)` 标记），因此目前只有可互换的孪生委派才能无竞态地回放。
+
+## 备选方案
+
+**保持委派独占。** 现状没有保护任何东西：后台和工作流子 agent 本来就可以带着写入自由重叠，串行化前台形态只会增加延迟，还违背模型显式表达的批量意图。
+
+**使用输入敏感的分类器。** 该调用的参数只有自由文本的描述和提示词；其中没有任何内容能区分安全委派与不安全委派，因此条件式分类器只会流于形式。
+
+**按 Codex 风格重新设计为异步 spawn/wait。** 可继续子 agent 加上 `send_message` 已经提供了异步通道；围绕信箱重建前台约定，等于为了解决一条声明就能修复的调度问题，丢弃一条可用的同步结果路径。
+
+**按实例提供 `concurrencySafe` 配置开关。** 没有消费方需要串行部署：`maxParallelToolCalls: 1` 已能恢复全局串行执行，同类 harness 的先例也默认委派并发安全。
+
+## 影响
+
+同级子 agent 可能在共享工作区或外部资源上发生竞态；这项协调由模型负责，正如模型对其他所有重叠子 agent 已经承担的那样。并发子 agent 还会争用 LLM 提供方配额；`maxParallelToolCalls` 只限制未结算的调用，不限制后台或可继续调用留下运行的子 agent。
+
+同一条消息中的两个一次性后台委派按分发竞态顺序获得各自模型可见的 task id（`subagent-<n>`）。这些 id 已被记录，因此回放仍然有效；但需要区分后台子 agent 的快照场景会继承与孪生子会话相同的确定性约束。
+
+有序提交可能让快速子 agent 的结果排在更早的缓慢同级之后等待，这是[调度器 Agent Note](2026-07-10-parallel-tool-call-execution.md)已经接受的取舍；实时界面仍会展示每个子 agent 各自的进度。
+
+使用不同提示词的并发子 agent 快照场景仍需要回放 harness 的支持（确定性的子脚本绑定与收集排序）；在此之前，此类场景必须使用可互换的孪生委派。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-creator-guidance-introduce-cue.md
+2026-08-10-creator-guidance-introduce-cue.md: 888fee7b3def585ed3098fedcb7bc6169ee26a22
+2026-08-10-creator-guidance-introduce-cue.zh.md: d80260abd1995df1f95e3f24fefcb265bda64c11
@@ -0,0 +1,33 @@
+# Agent Note: Creator guidance lands as an introduce cue on the preset chip
+
+Status: implemented
+
+English | [中文](2026-08-10-creator-guidance-introduce-cue.zh.md)
+
+## Problem
+
+Authoring a preset happens inside a Creator-mode session, but the settings section gave no path into that fact. The creator entry sat outside the roster groups, the custom group vanished entirely while it had no member, and clicking the entry dropped the user onto the new-session screen with nothing marking what had changed: the staged preset chip rendered exactly as if the user had picked it by hand. Users reported not understanding that the flow had moved, or that the session they were about to start was the place where the preset gets built (#2184).
+
+## Decision
+
+The custom group stays on screen while empty — heading plus the creator entry, which lives inside the group as the standing "your preset will appear here" affordance rather than floating below the roster.
+
+A pick staged from another screen carries a one-shot `introduce` flag through the seat store (`stage(id, introduce)`), and the chip announces it: the preset icon eases in over 150ms, then the name's characters fade up on a stagger the moment the icon lands. The stagger is capped twice — 40ms per tick for short CJK names, and one shared 200ms reveal window (`min(40, 200/(n-1))`) so a long Latin name finishes in the same time as its CJK counterpart instead of dragging the run out per character. CSS owns the motion; the component arms it and acknowledges the cue once the run is over, so the flag never replays on a later mount. `prefers-reduced-motion` and an empty display name acknowledge immediately with no run.
+
+The cue is pure presentation: it is client-side seat-store state, never a session event, because the model-visible composition is already carried by the staged preset itself.
+
+## Alternatives considered
+
+**A toast or callout on the new-session screen.** It explains more, but it points at nothing — the chip is the artifact the user must find again later, and a dismissable box teaches the box, not the control. The cue puts the motion on the control itself.
+
+**A fixed per-character tick.** The first implementation used 60ms per character unconditionally; an English preset name took over three times as long as its four-character Chinese counterpart, reading as lag rather than emphasis. The shared reveal window makes duration a property of the cue, not of the locale.
+
+**Animating the pick inside the settings dialog before leaving.** The dialog closes as part of the gesture — leaving settings is how the flow says the work happens in the session — so anything played there would be cut off or would delay the navigation it exists to explain.
+
+## Consequences
+
+The intro timeline lives in two places that must agree: the component's `INTRO_TEXT_DELAY_MS` and the `.introIcon` CSS animation duration. The component's constants are the source of the character delays and the acknowledgement timeout; the CSS comment names the coupling. The seat store gains one bit of UI state (`introduce`) that every stage decides explicitly, and the section keeps rendering a group with no members — a shape the section golden and unit tests now pin.
+
+## Testing
+
+Component tests pin the capped stagger (11-character Latin name at 20ms steps, 4-character CJK name at the 40ms tick, single character with no stagger), the acknowledgement timing, and the reduced-motion and empty-name skips. `apply.spec.ts` drives the cross-screen stage end to end: the creator draft stages with the cue set, one acknowledgement clears it, and a repeat acknowledgement leaves the snapshot untouched. The `agent-preset-authoring` web e2e holds the empty custom group (heading plus creator entry) in its goldens.
@@ -0,0 +1,33 @@
+# Agent Note: 创造模式引导以介绍动效落在预设 chip 上
+
+Status: implemented
+
+[English](2026-08-10-creator-guidance-introduce-cue.md) | 中文
+
+## 问题
+
+预设的创作发生在创造模式 session 内部，但设置分区没有把这条路径讲清楚。创建入口游离在名册分组之外；自定义分组在没有成员时整个消失；点击入口后用户被抛到新会话屏幕，没有任何标记说明发生了什么变化：暂存的预设 chip 渲染得和用户亲手挑选时一模一样。用户反馈看不懂流程已经移动，也不明白即将开始的 session 正是构建预设的地方（#2184）。
+
+## 决定
+
+自定义分组在空的时候也常驻屏幕——分组标题加创建入口，入口移入分组内部，作为"你的预设会出现在这里"的常设指引，而不是漂在名册下方。
+
+从另一屏幕暂存的选择会经由 seat store 携带一次性的 `introduce` 标志（`stage(id, introduce)`），chip 据此自我介绍：预设图标在 150ms 内缓入，落定的瞬间名称逐字符错峰浮现。错峰有两重上限——短的中文名按每字符 40ms 的节拍，同时共享一个 200ms 的整体揭示窗口（`min(40, 200/(n-1))`），让长的拉丁名与中文名在相同时间内完成，而不是按字符数拖长整轮动画。动效由 CSS 负责；组件只负责触发，并在一轮结束后确认该提示，因此标志不会在后续挂载时重放。`prefers-reduced-motion` 与空显示名会立即确认、不播放动画。
+
+该提示纯属呈现层：它是客户端 seat-store 状态，永远不是 session 事件，因为模型可见的组合已由暂存的预设本身承载。
+
+## 曾考虑的替代方案
+
+**在新会话屏幕上弹 toast 或提示框。** 它能解释更多，但什么也没指向——chip 才是用户之后必须再次找到的对象，可关闭的提示框教会的是提示框本身，不是控件。介绍动效把动作放在控件本体上。
+
+**固定的每字符节拍。** 第一版实现无条件使用每字符 60ms；英文预设名的时长超过四字中文名的三倍，读起来像卡顿而非强调。共享揭示窗口让时长成为提示的属性，而不是语言的属性。
+
+**离开前在设置对话框内播放选中动画。** 关闭对话框本身就是这个手势的一部分——离开设置正是流程在表达"工作发生在 session 里"——在那里播放的任何内容要么被截断，要么会拖延它本要解释的跳转。
+
+## 后果
+
+介绍时间线存在于两处且必须一致：组件的 `INTRO_TEXT_DELAY_MS` 与 `.introIcon` 的 CSS 动画时长。组件常量是字符延迟与确认超时的来源；CSS 注释点明了这层耦合。seat store 多出一位 UI 状态（`introduce`），每次暂存都显式决定它；分区则会渲染没有成员的分组——这一形态现由分区 golden 与单元测试钉住。
+
+## 测试
+
+组件测试钉住带上限的错峰（11 字符拉丁名走 20ms 步进、4 字中文名走 40ms 节拍、单字符无错峰）、确认时机，以及 reduced-motion 与空名的跳过路径。`apply.spec.ts` 端到端驱动跨屏暂存：创造模式草稿携带提示暂存，一次确认将其清除，重复确认让快照原样不动。`agent-preset-authoring` web e2e 在 golden 中保持空自定义分组（标题加创建入口）。
@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-10-minimal-read-image-tool.md
+2026-08-10-minimal-read-image-tool.md: a43e53d70e98bac7a50aa6bbabbb1e177237df01
+2026-08-10-minimal-read-image-tool.zh.md: a94e4b296425ad50876b0b45a689442c896a85a1
@@ -0,0 +1,33 @@
+# Agent Note: A minimal read_image tool over existing seams
+
+Status: implemented
+
+English | [中文](2026-08-10-minimal-read-image-tool.zh.md)
+
+## Problem
+
+The multimodal attachment work gave user uploads a complete durable path — bytes committed to the content-addressed attachment store before the owning `user/message`, an `ImageBlock` carrying only the `sha256:` reference, and the pi-ai route re-reading verified bytes per request — but the model itself had no way to look at an image on disk. `read` rejects binary content by contract, so an agent asked about a screenshot or a rendered chart either failed or shelled out to lossy workarounds. A first standalone attempt (PR #598) solved this together with loop-level route scoping: an `agent/request-ready` extension point publishing exact-model modalities before assembly, per-route schema/guidance visibility, and a reversible `image-placeholder-v1` history projection so text routes could continue over placeholder text. That design worked but coupled a tool to new agent-loop machinery, three new session-log concepts, and per-step registration churn — far more surface than the capability needs.
+
+## Decision
+
+Ship the smallest tool that loads an image into the next request's context, entirely over existing seams; the withdrawn PR #598 design is the explicit counter-example this note records.
+
+- **`read_image` lives in `dsh-tool-fs`** beside `read`/`write`/`edit`. Extension selects the declared PNG/JPEG/WebP/GIF media type; the attachment store's magic-byte and pixel validation stays authoritative. Bytes travel `ctx.fs.stat` → bounded `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed`, and the tool result is the metadata envelope plus a real `ImageBlock` — `ToolResultBlock.content` already admits image blocks, the pi-ai adapter already renders them, and the Web host's model-switch guard already scans tool results, so nothing downstream changes.
+- **`FileSystem.readBytes(target, signal, maxBytes)`** is a new required provider primitive: the byte bound lives at the seam so no backend can buffer an unbounded file, with the stat-size short-circuit and a one-byte-past-cap stream guard against post-stat growth (`FS_TOO_LARGE`).
+- **Registration is composition-conditional, execution is route-gated.** The tool registers only under `ctx.inject(['attachments'], …)` — no store, no tool. At execution, before any I/O, the strict gate resolves the calling route (latest `request/header` config, falling back to agent options) through `ctx.llm.resolveModelInfo` and requires `image` in `inputModalities`; unknown capability refuses. A refusal is a plain `isError` result, so a text route's durable history never acquires an image block and the session cannot brick its own route.
+- **Code Mode forwards the image out-of-band**: a nested dispatch returns the canonical value (execution-local, no image block) and defers a `user`-role context message carrying the envelope and image, so the picture still reaches the next request.
+- **llm-replay models may declare `inputModalities`**, which is what lets the two keyless ACP snapshots pin both sides of the gate — the sha256-referenced success on an image-capable replay route and the verbatim refusal on a text-only one.
+
+## Alternatives considered
+
+- **PR #598's route-scoped design** (request-ready seam, per-route schema/guidance visibility, reversible history projection) — withdrawn in favor of this note's shape. What it bought: text routes could keep running after images entered history, and the tool disappeared from prompts where it cannot succeed. What it cost: agent-loop changes, three new durable concepts (`agent/request-ready`, `messageProjection`, availability notices), and registration that churned per step. The capability itself — see an image on the next request — never needed any of it. If per-route projection becomes a real requirement, that PR's history is the reference implementation.
+- **`agent.inject()` instead of the image-bearing tool result** — routes the image around the tool result as a separate injected user message. Rejected: the image *is* the tool's result; splitting them adds a second logged message with no gain, and the tool-result path already works end to end.
+- **Magic-byte sniffing instead of extension declaration** — sniffing duplicates detection the attachment store already owns (sharp-backed, authoritative). The extension is only a *declaration*; a mismatch fails closed with a rename remedy rather than being silently accepted, which also keeps the model's mental map (file name ↔ content) honest.
+- **Registering unconditionally and failing on a missing store** — rejected; a deployment without an attachment store cannot ever satisfy the tool, so its schema would be a standing lie. The route gate, by contrast, is per-call state and correctly lives at the execution boundary.
+
+## Consequences
+
+- A text-only route refuses instead of degrading: no placeholder projection means no delegated-viewing story here — that is deliberately the next PR (subagent image readback rebuilt on the current subagent seams).
+- The route gate races a concurrent model switch; the Web host's image-aware switch guard covers its surface, and other front doors own their equivalent. Recorded as a tool-fs Known Limitation.
+- Repeated image results accumulate request-token cost until compaction; content addressing deduplicates bytes only.
+- The tool-result card renders the durable reference, not pixels; inline preview is deferred to the UI packages.
@@ -0,0 +1,33 @@
+# Agent Note: 基于既有 seam 的最小 read_image 工具
+
+Status: implemented
+
+[English](2026-08-10-minimal-read-image-tool.md) | 中文
+
+## 问题
+
+多模态附件工作为用户上传建立了完整的持久路径：字节在所属 `user/message` 之前提交到内容寻址的附件存储，`ImageBlock` 只携带 `sha256:` 引用，pi-ai 路由在每次请求时重新读取并校验字节。但模型自己没有查看磁盘图像的手段。`read` 按约定拒绝二进制内容，因此被问到截图或渲染图表的 agent 要么失败，要么退到有损的变通做法。第一次独立尝试（PR #598）把这个问题与循环级路由作用域一起解决：新增在组装前发布确切模型模态的 `agent/request-ready` 扩展点、按路由控制 schema／指导可见性，以及可逆的 `image-placeholder-v1` 历史投影让文本路由能在占位符上继续。该设计可行，但让一个工具耦合了新的 agent-loop 机制、三个新的会话日志概念和每步的注册变动，远超这项能力本身的需要。
+
+## 决定
+
+只交付能把图像载入下一次请求上下文的最小工具，完全建立在既有 seam 之上；撤回的 PR #598 设计是本记录明确保留的反例。
+
+- **`read_image` 放在 `dsh-tool-fs`**，与 `read`/`write`/`edit` 并列。扩展名选择声明的 PNG/JPEG/WebP/GIF 媒体类型；附件存储的魔数与像素校验保持权威。字节沿 `ctx.fs.stat` → 有界 `ctx.fs.readBytes` → `ctx.attachments.saveImage` → `fs/observed` 流动，工具结果是元数据信封加真正的 `ImageBlock`——`ToolResultBlock.content` 本就允许图像块，pi-ai 适配器本就会渲染它们，Web 宿主的模型切换防护本就会扫描工具结果，下游无需任何改动。
+- **`FileSystem.readBytes(target, signal, maxBytes)`** 是新的必备提供方原语：字节上限放在 seam 上，任何后端都无法无界缓冲文件；stat 大小先短路，随后的流最多多读一个字节以防 stat 之后的增长（`FS_TOO_LARGE`）。
+- **注册随组合条件挂载，执行按路由门禁。** 工具只在 `ctx.inject(['attachments'], …)` 作用域内注册——没有存储就没有工具。执行时在任何 I/O 之前，严格门禁通过 `ctx.llm.resolveModelInfo` 解析调用路由（最新 `request/header` 配置，缺失时回退到 agent 选项），要求 `inputModalities` 包含 `image`；能力未知即拒绝。拒绝是普通的 `isError` 结果，因此文本路由的持久历史绝不会出现图像块，会话不会毁掉自己的路由。
+- **Code Mode 以带外方式转发图像**：嵌套分派返回规范值（仅限本次执行，不含图像块），并延迟提交一条携带信封和图像的 `user` 角色上下文消息，图片仍会到达下一次请求。
+- **llm-replay 模型可以声明 `inputModalities`**，这正是两个 keyless ACP 快照能钉住门禁两侧的原因：图像路由上以 sha256 引用的成功结果，和纯文本路由上逐字的拒绝。
+
+## 考虑过的替代方案
+
+- **PR #598 的路由作用域设计**（request-ready 扩展点、按路由的 schema／指导可见性、可逆历史投影）——被本记录的形态取代后撤回。它换来的是：图像进入历史后文本路由仍能运行，工具在注定失败的提示词里消失。它付出的是：改动 agent-loop、三个新的持久概念（`agent/request-ready`、`messageProjection`、可用性通知）和每步变动的注册。而这项能力本身——下一次请求看到图像——从不需要这些。如果按路由投影将来成为真实需求，该 PR 的历史就是参考实现。
+- **用 `agent.inject()` 代替带图像的工具结果**——把图像绕过工具结果，作为单独注入的用户消息。拒绝：图像就是工具的结果；拆开只会多一条无收益的日志消息，而工具结果路径本就端到端可用。
+- **用魔数嗅探代替扩展名声明**——嗅探重复了附件存储已拥有的检测（基于 sharp，权威）。扩展名只是声明；不匹配时按改名修复提示失败关闭，而不是被静默接受，这也让模型对文件名与内容的对应保持诚实。
+- **无条件注册、缺存储时执行报错**——拒绝；没有附件存储的部署永远无法满足该工具，其 schema 会是常态谎言。相反，路由门禁是逐调用状态，正确的位置就是执行边界。
+
+## 后果
+
+- 纯文本路由得到拒绝而不是降级：没有占位符投影意味着这里没有委托查看的方案——那有意留给下一个 PR（基于当前 subagent seam 重建的 subagent image readback）。
+- 路由门禁与并发模型切换存在竞态；Web 宿主的图像感知切换防护覆盖其表面，其他前端拥有各自的等价防护。已记入 tool-fs 的已知限制。
+- 重复的图像结果在压缩之前持续累积请求 token 成本；内容寻址只去重字节。
+- 工具结果卡片渲染持久引用而非像素；内嵌预览延后到 UI 包处理。
@@ -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/2026-07-13-documentation-site-projection.md
-2026-07-13-documentation-site-projection.md: d9af915754fa6a1df51a27d18d412597472aaa73
-2026-07-13-documentation-site-projection.zh.md: 7d7b4752b8f27d55aae8426a7dc001ce4340e661
+2026-07-13-documentation-site-projection.md: 309dbd96c5f1ca87d137cdc3839acfc5c5aa22f2
+2026-07-13-documentation-site-projection.zh.md: b01965fb1b46ab618b5b8bcb748bb5a8940d6e69
@@ -18,9 +18,9 @@ Canonical Markdown remains in the repository tier that owns it. Product-facing g

 Locale home projections retain only the canonical YAML frontmatter. The repository-facing body can keep its H1 and bilingual source links, while the VitePress home theme owns the rendered hero and features and the site navigation owns locale switching.

-The projector parses Markdown links without reserializing the document. A link to another published source becomes a site-relative route; a link to an unpublished repository file becomes a source link under the public `deepseek-ai/deepseek-harness-sdk` home; a repository image is copied into the generated tree and referenced from there ([why](2026-08-06-doc-site-carries-its-images.md)). Missing relative targets fail projection. Unit tests pin these transformations, and `docs:check` runs the projector tests plus a production VitePress build as part of `doc-sync` and the parallel documentation gates.
+The projector parses Markdown links without reserializing the document. A link to another published source becomes a site-relative route; a link to an unpublished repository file becomes a source link under the `deepseek-ai/deepseek-harness` repository home; a repository image is copied into the generated tree and referenced from there ([why](2026-08-06-doc-site-carries-its-images.md)). Missing relative targets fail projection. Unit tests pin these transformations, and `docs:check` runs the projector tests plus a production VitePress build as part of `doc-sync` and the parallel documentation gates.

-`verify-public-repository-links` rejects internal repository remotes from tracked files. Public source links use the public home, while work tracking stays in repository metadata and source carries a TODO only when the local boundary matters to maintainers.
+`verify-public-repository-links` rejects references to the unavailable legacy repository from tracked files. Source and edit links use the current repository home.

 `website/AGENTS.md` is the only maintained Markdown file in the website subtree. The projector test enumerates tracked and unignored files and rejects any other website Markdown, so site-specific locale, route, API, or generated source copies cannot bypass the publication manifest.

@@ -18,9 +18,9 @@ Status: implemented

 各 locale 的首页投影只保留权威 YAML frontmatter。面向仓库的正文可以保留其 H1 和双语源文件链接，而 VitePress 首页主题负责渲染 hero 与功能区，网站导航负责切换 locale。

-投影器解析 Markdown 链接，但不会重新序列化文档。指向另一个已发布源文件的链接会变成站内相对路由；指向未发布仓库文件的链接会变成公开 `deepseek-ai/deepseek-harness-sdk` 主页下的源文件链接；仓库图片会被拷贝进生成树并从那里引用（[原因](2026-08-06-doc-site-carries-its-images.md)）。相对目标不存在时，投影会失败。单元测试会锁定这些转换行为，`docs:check` 则运行投影器测试和 VitePress 生产构建，并将二者纳入 `doc-sync` 和并行文档门禁。
+投影器解析 Markdown 链接，但不会重新序列化文档。指向另一个已发布源文件的链接会变成站内相对路由；指向未发布仓库文件的链接会变成 `deepseek-ai/deepseek-harness` 仓库主页下的源文件链接；仓库图片会被拷贝进生成树并从那里引用（[原因](2026-08-06-doc-site-carries-its-images.md)）。相对目标不存在时，投影会失败。单元测试会锁定这些转换行为，`docs:check` 则运行投影器测试和 VitePress 生产构建，并将二者纳入 `doc-sync` 和并行文档门禁。

-`verify-public-repository-links` 会拒绝已跟踪文件中的内部仓库远程链接。公开源文件链接使用公开主页，而工作跟踪留在仓库元数据中；只有本地边界对维护者有意义时，源文件才保留 TODO。
+`verify-public-repository-links` 会拒绝已跟踪文件中指向不可用旧仓库的引用。源文件链接和编辑链接使用当前仓库主页。

 `website/AGENTS.md` 是网站子树中唯一维护的 Markdown 文件。投影器测试会枚举所有已跟踪文件和未被忽略的未跟踪文件，并拒绝网站中的任何其他 Markdown，因此网站专用的 locale、路由、API 或生成源文件副本无法绕过发布 manifest。

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md
-2026-07-30-generated-third-party-notices.md: 58e3fd5007a16d6391956f423d1ec91e851df295
-2026-07-30-generated-third-party-notices.zh.md: 834ec4ebc349bdee37b0873109de566223bb7d48
+2026-07-30-generated-third-party-notices.md: d13eef8412ecd5c8387a7239b812c835671b6bce
+2026-07-30-generated-third-party-notices.zh.md: 0af6a6bcd665197acd6a0b5e9e6f51940a0267e7
@@ -20,9 +20,9 @@ One trigger gap is accepted rather than worked around: lefthook inspects only fi

 The file discloses **direct** dependencies by default. The complete npm closure with pinned versions already lives in `pnpm-lock.yaml` (`pnpm licenses list` renders it) and the Python closure in `python/sdk/uv.lock`; re-materializing either as prose would be a second, worse copy. The one explicit transitive disclosure is the official Claude platform payload set declared by `@anthropic-ai/claude-agent-sdk` through `optionalDependencies`, because those packages carry the distributed Claude Code executable rather than ordinary library implementation detail.

-**Tiering is by declaring area, not by manifest section.** A package is a runtime dependency when any manifest outside `DEV_ONLY_AREAS` — the root manifest, `packages/support/`, `packages/client/test-runtime/`, `website/`, `examples/`, `native/` — names it under `dependencies` or `optionalDependencies`. Section names alone are wrong in both directions: a test-support package declares `vitest` under `dependencies` without shipping it, and the `bin/dsh` launcher execs through `tsx`, which no manifest declares as a runtime dependency at all (the generator marks it runtime explicitly).
+**Tiering is by declaring area, not by manifest section.** A package is a runtime dependency when any manifest outside `DEV_ONLY_AREAS` — the root manifest, `packages/support/`, `packages/client/test-runtime/`, `website/`, `examples/`, `native/` — names it under `dependencies` or `optionalDependencies`. Section names alone are wrong in both directions: a test-support package declares `vitest` under `dependencies` without shipping it, and the root source-run scripts execute through `tsx`, which no manifest declares as a runtime dependency at all (the generator marks it runtime explicitly).

-The runtime tier deliberately covers **every mountable plugin**, not just what the CLI, Web UI, and Python runtime load by default. `scripts/install.sh` installs the repository itself, so a user's `cordis.yml` can mount any plugin package; `@modelcontextprotocol/sdk` and the OpenTelemetry packages reach real users even though no default assembly imports them. Under-disclosure is the costly direction for a legal notice.
+The runtime tier deliberately covers **every mountable plugin**, not just what the CLI, Web UI, and Python runtime load by default. Source execution can mount any plugin package from a user's `cordis.yml`; `@modelcontextprotocol/sdk` and the OpenTelemetry packages therefore reach real users even though no default assembly imports them. Under-disclosure is the costly direction for a legal notice.

 The manifest set is derived from the `packages:` members the root `pnpm-workspace.yaml` declares, including the Landlock workspace and its public packages, so a new member area is read the day it is declared rather than the day someone remembers to extend a list. License and repository metadata come from the root workspace's installed pnpm store and package-local link farms, so the generator requires an installed tree and fails loud when a package resolves to neither, rather than emitting an empty cell. `OVERRIDES` carries the packages whose published manifest cannot answer — Rust-built npm bins that omit `license`, and the `modelcontextprotocol/servers` packages whose repository is mid MIT→Apache-2.0 relicensing, so their effective terms are per-contribution. A runtime dependency whose license is not on the permissive list is a hard error: shipping copyleft is a distribution decision, not something a regenerated table may absorb silently. Vendored packages are cross-checked against `vendor/README.md` and rejected if any is not MIT, and `pnpm-workspace.yaml`'s `patchedDependencies` are listed under the runtime table because pnpm applies those patches at install time — shipped artifacts carry modified copies of `@earendil-works/pi-tui` and `node-pty`, and the patch files are the record of what changed.

@@ -20,9 +20,9 @@ Status: implemented

 文件默认只披露**直接**依赖。完整的 npm 闭包连同锁定版本已记录在 `pnpm-lock.yaml`（`pnpm licenses list` 可渲染），Python 闭包记录在 `python/sdk/uv.lock`；再用散文誊一遍只会得到一份更差的副本。唯一明确披露的传递依赖，是 `@anthropic-ai/claude-agent-sdk` 通过 `optionalDependencies` 声明的官方 Claude 平台载荷集合，因为这些包承载随产品分发的 Claude Code 可执行文件，而非普通的库实现细节。

-**分层依据是声明方所在区域，而非 manifest 字段名。** 只要 `DEV_ONLY_AREAS` 之外的任一 manifest——即根 manifest、`packages/support/`、`packages/client/test-runtime/`、`website/`、`examples/`、`native/` 之外——在 `dependencies` 或 `optionalDependencies` 里点名某个包，它就是运行时依赖。单看字段名在两个方向上都会出错：测试支撑包把 `vitest` 写在 `dependencies` 里却并不交付它；而 `bin/dsh` 启动器通过 `tsx` 执行，根本没有任何 manifest 把它声明为运行时依赖，只能由生成器显式标记。
+**分层依据是声明方所在区域，而非 manifest 字段名。** 只要 `DEV_ONLY_AREAS` 之外的任一 manifest——即根 manifest、`packages/support/`、`packages/client/test-runtime/`、`website/`、`examples/`、`native/` 之外——在 `dependencies` 或 `optionalDependencies` 里点名某个包，它就是运行时依赖。单看字段名在两个方向上都会出错：测试支撑包把 `vitest` 写在 `dependencies` 里却并不交付它；而根目录的源码运行脚本通过 `tsx` 执行，根本没有任何 manifest 把它声明为运行时依赖，只能由生成器显式标记。

-运行时层刻意覆盖**所有可挂载的插件**，而不止 CLI、Web UI 与 Python 运行时默认加载的那些。`scripts/install.sh` 安装的就是仓库本身，用户的 `cordis.yml` 可以挂载任何插件包；`@modelcontextprotocol/sdk` 与 OpenTelemetry 系列即使没有任何默认装配引入，也会触达真实用户。对法务披露而言，披露不足才是代价更高的那个方向。
+运行时层刻意覆盖**所有可挂载的插件**，而不止 CLI、Web UI 与 Python 运行时默认加载的那些。从源码运行时，用户可以通过 `cordis.yml` 挂载任何插件包；因此，`@modelcontextprotocol/sdk` 与 OpenTelemetry 系列即使没有任何默认装配引入，也会触达真实用户。对法务披露而言，披露不足才是代价更高的那个方向。

 manifest 集合由根 `pnpm-workspace.yaml` 声明的 `packages:` 成员派生，其中包括 Landlock 工作区及其公开包，因此新增成员区域在声明当天就会被读取，而不必等谁想起来去补一份列表。许可证与仓库地址取自根工作区已安装的 pnpm store 和包本地链接场；某个包两处都解析不到时直接失败，而不是留下空单元格。`OVERRIDES` 收录已发布 manifest 答不上来的包：用 Rust 构建、发布时省略 `license` 字段的 npm 可执行包，以及 `modelcontextprotocol/servers` 系列——该仓库正处在 MIT 向 Apache-2.0 的重新许可过程中，实际条款按贡献逐条而定。运行时依赖的许可证若不在宽松清单内即为硬失败：交付 copyleft 是一项分发决策，不该被一次重新生成悄悄吸收。被源码收编的包会与 `vendor/README.md` 交叉核对，出现非 MIT 即报错；`pnpm-workspace.yaml` 的 `patchedDependencies` 列入运行时表格，因为 pnpm 在安装期就会打上这些补丁——交付产物携带的是改动过的 `@earendil-works/pi-tui` 与 `node-pty`，补丁文件本身就是改动的完整记录。

@@ -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/process/2026-08-10-event-directed-pr-review-status.md
+2026-08-10-event-directed-pr-review-status.md: 9db9c64fc87c1701028ae825357c3cbd7fef44d1
+2026-08-10-event-directed-pr-review-status.zh.md: 381a3f64a62930a584f48cfbc3571679bbcbcef7
@@ -0,0 +1,41 @@
+# Agent Note: Event-directed PR review status commands
+
+Status: implemented
+
+English | [中文](2026-08-10-event-directed-pr-review-status.zh.md)
+
+## Problem
+
+The Issue Project status records who owns the next step of resolving work. Aggregate pull-request review state answers whether GitHub considers the pull request mergeable, but it cannot represent that handoff: an earlier `CHANGES_REQUESTED` review can remain effective after the author fixes the code and requests review again.
+
+A monotonic projection also cannot return an automation-owned Issue from `In review` to `In progress` when a reviewer requests changes. Reconstructing review rounds or reviewer blockers would add state that the required two-event contract does not need.
+
+## Decision
+
+The Issue lifecycle workflow treats review webhooks as commands. `pull_request.review_requested`, including a repeated request, targets `In review`. `pull_request_review.submitted` targets `In progress` only when `review.state` is `changes_requested`; the submitted event remains necessary because a reviewer can request changes without an earlier review-request event. Approved and commented submissions skip their lifecycle job before it creates a Project token, while dismissed reviews are not subscribed.
+
+Ordinary subscribed pull-request events remain forward-only implementation signals: they can move `Inbox`, `Backlog`, or `Ready` to `In progress`, but they cannot move `In review` backward. Review-request commands can move any earlier active status to `In review`. Changes-requested commands can move earlier active statuses forward to `In progress` and can move `In review` back only when the latest status event for the target Project was written by the configured lifecycle actor. A human or unknown latest actor preserves the current status.
+
+The handler resolves only exact same-repository `Fixes`, `Closes`, or `Resolves` references. It does not alter terminal statuses, add an Issue with no Project status, depend on PR metadata validity, query `reviewDecision`, reconstruct review rounds, look up pull requests from Issues, or run a scheduled reconciler.
+
+[Issue lifecycle](../../../../.github/workflows/issue-lifecycle.yml) remains unsubscribed from `pull_request.ready_for_review`; neither event command depends on that action. [Issue policy](../../../../.github/workflows/issue-policy.yml) retains `ready_for_review` because it owns required-check enforcement when a human pull request enters review.
+
+## Verification
+
+[Issue-management tests](../../../../.github/issue-management/policy.test.mjs) pin the event-to-command mapping, the repeated-review-request transition after a changes-requested command, the changes-requested regression, terminal protection, and human override preservation. [Workflow tests](../../../../scripts/ci-workflow.spec.ts) pin the subscribed events, the changes-requested job condition, and the separate `ready_for_review` policy trigger.
+
+## Alternatives considered
+
+**Derive status from `reviewDecision` or a reconstructed review round.** GitHub's aggregate can remain `CHANGES_REQUESTED` after a repeated review request, while a round reducer introduces reviewer and ordering semantics beyond the two explicit handoffs.
+
+**Keep the forward-only projection.** Monotonic advancement protects later statuses, but it leaves an Issue in `In review` while the author is implementing requested changes.
+
+**Apply every review command unconditionally.** This is the smallest event handler, but it lets automation overwrite a human-owned Project status. The latest target-Project status actor therefore guards the only backward transition.
+
+**Restore `ready_for_review` or add a debounce queue.** Ready status carries neither review handoff, while another queue adds latency and control-plane state without changing either command.
+
+## Consequences
+
+A repeated review request moves an automation-managed resolving Issue to `In review` even while GitHub still reports an older blocking review. A later changes-requested review returns it to `In progress`; approval, comments, dismissal, pushes, and reviewer removal leave the most recent command's status unchanged.
+
+The projection remains event-driven and does not repair an event that never runs. Replaying an old workflow run can replay its old command, and ProjectV2 still provides no atomic compare-and-swap between the latest-state read and mutation. Per-pull-request workflow concurrency and the human-ownership guard reduce these races without introducing durable lifecycle state.
@@ -0,0 +1,41 @@
+# Agent Note: 由事件直接指定的 PR 评审状态命令
+
+Status: implemented
+
+[English](2026-08-10-event-directed-pr-review-status.md) | 中文
+
+## 问题
+
+Issue 所在 Project 中的状态记录了解决工作的下一步由谁负责。PR（Pull Request）的汇总评审状态可以回答 GitHub 是否认为该 PR 可合并，却无法表示这次交接：作者修复代码并重新请求评审后，先前的 `CHANGES_REQUESTED` 评审仍可能继续生效。
+
+单调投影也无法在评审人提出修改要求时，将由自动化管理的 Issue 从 `In review` 退回 `In progress`。重建评审轮次或评审人阻塞项会引入既定双事件约定并不需要的状态。
+
+## 决策
+
+Issue 生命周期工作流把评审 webhook 视为命令。`pull_request.review_requested`（包括重复请求）将目标状态指定为 `In review`。`pull_request_review.submitted` 将目标状态指定为 `In progress`，但仅在 `review.state` 为 `changes_requested` 时生效；submitted 事件仍不可省略，因为评审人即使没有先触发 review-request 事件，也可以直接提出修改要求。对于 approved 和 commented 提交，工作流会在生命周期作业创建 Project token 前跳过该作业；dismissed 评审则不在订阅范围内。
+
+工作流订阅的普通 PR 事件仍是只向前推进的实现信号：它们可以将 `Inbox`、`Backlog` 或 `Ready` 推进至 `In progress`，但不能让 `In review` 倒退。请求评审命令可将任意较早的活跃状态推进至 `In review`。请求修改命令可将较早的活跃状态推进至 `In progress`；它也可以让 `In review` 状态回退，但仅在目标 Project 的最新状态事件由配置的生命周期执行主体写入时进行。若最新状态事件的执行主体是人工用户或未知主体，则保留当前状态。
+
+处理器仅解析同一仓库内严格匹配的 `Fixes`、`Closes` 或 `Resolves` 引用。它不会更改终态、将没有 Project 状态的 Issue 添加到 Project、依赖 PR 元数据是否有效、查询 `reviewDecision`、重建评审轮次、从 Issue 反向查找 PR，或运行定时协调器。
+
+[Issue 生命周期](../../../../.github/workflows/issue-lifecycle.yml)仍不订阅 `pull_request.ready_for_review`；两条事件命令均不依赖该动作。[Issue 策略](../../../../.github/workflows/issue-policy.yml)保留 `ready_for_review`，因为人工提交的 PR 进入评审时，该工作流负责执行必需检查门禁。
+
+## 验证
+
+[Issue 管理测试](../../../../.github/issue-management/policy.test.mjs)锁定事件到命令的映射、请求修改命令后重复请求评审所触发的状态转换、请求修改后的状态回退、终态保护，以及保留人工覆盖状态。[工作流测试](../../../../scripts/ci-workflow.spec.ts)锁定订阅事件、请求修改作业的条件，以及独立的 `ready_for_review` 策略触发器。
+
+## 考虑过的替代方案
+
+**根据 `reviewDecision` 或重建的评审轮次派生状态。** GitHub 的汇总状态在重复请求评审后仍可能保持为 `CHANGES_REQUESTED`，而轮次归约器会引入超出两个显式交接动作所需范围的评审人语义和顺序语义。
+
+**保留只向前推进的投影。** 单调推进可保护较后的状态不被回退，但作者正在按要求修改代码时，Issue 会一直停留在 `In review`。
+
+**无条件应用每条评审命令。** 这是最精简的事件处理器，但会让自动化覆盖由人工管理的 Project 状态。因此，处理器通过目标 Project 最新状态事件的执行主体保护唯一允许的回退转换。
+
+**恢复 `ready_for_review` 或添加防抖队列。** Ready 状态并不表示两种评审交接中的任何一种；新增队列只会增加延迟和控制平面状态，不会改变任一命令。
+
+## 后果
+
+即使 GitHub 仍报告一个较早的阻塞性评审，重复请求评审也会将正由当前 PR 解决且由自动化管理的 Issue 推进至 `In review`。后续提出修改要求的评审会将其退回 `In progress`；批准、评论、撤销评审、推送和移除评审人都不会改变最近一条命令设定的状态。
+
+投影仍由事件驱动；如果某个事件从未触发工作流运行，投影不会自行修复。回放旧的工作流运行可能会再次执行其中的旧命令；ProjectV2 仍不提供在读取最新状态与执行变更之间进行原子比较并交换（compare-and-swap）的能力。以单个 PR 为粒度的工作流并发控制和人工状态所有权保护机制可减少这些竞态，而无需引入持久化生命周期状态。
@@ -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/2026-08-08-remove-cli-demo.md
-2026-08-08-remove-cli-demo.md: 31879e8284daf5f34af6731b09fce743f9eb5391
-2026-08-08-remove-cli-demo.zh.md: d4dfef1ba8c4d27cd667e319519cfa1ace74baef
+2026-08-08-remove-cli-demo.md: f8bc09825797f2165c14a75e5841d74b2e1bc1af
+2026-08-08-remove-cli-demo.zh.md: 1044dd136888e33fc9935cf4e24cd3100b41b41f
@@ -12,7 +12,7 @@ The replay suites still need canonical session events to pin assembled backend b

 ## Decision

-Delete `@deepseek-ai/dsh-cli-demo` completely: its package, bin, parser, app plugin, output formats, tests, workspace references, generated-catalog entries, and active documentation. No alias or compatibility package remains. The root `demo:headless` script is retained only as a direct alias of `dsh --profile headless`; the product command owns final-text stdout, failure diagnostics on stderr, persistence, exit status, and shutdown.
+Delete `@deepseek-ai/dsh-cli-demo` completely: its package, bin, parser, app plugin, output formats, tests, workspace references, generated-catalog entries, and active documentation. No alias or compatibility package remains. Source users invoke the product command through `pnpm dsh --profile headless`; it owns final-text stdout, failure diagnostics on stderr, persistence, exit status, and shutdown.

 `examples/headless-agent` becomes an explicit test composition. Its Loader configs mount `@deepseek-ai/dsh-agent-spine-demo`, one root agent, JSONL persistence, and checkpoint policy as separate rows instead of hiding them behind an app bundle. The support-tier `@deepseek-ai/dsh-loader-smoke` package owns the shared direct-agent turn helper; unexported example-local drivers select their Loader configuration and render canonical events as JSONL. They are launched only by tests, have no bin, and do not define a supported product output format.

@@ -12,7 +12,7 @@ Status: implemented

 ## 决策

-彻底删除 `@deepseek-ai/dsh-cli-demo`：包括它的包、bin、解析器、应用插件、输出格式、测试、workspace 引用、生成目录条目和现行文档。不保留别名或兼容包。根目录的 `demo:headless` 脚本仅作为 `dsh --profile headless` 的直接别名保留；stdout 上的最终文本、stderr 上的失败诊断、持久化、退出状态和关闭行为均由产品命令负责。
+彻底删除 `@deepseek-ai/dsh-cli-demo`：包括它的包、bin、解析器、应用插件、输出格式、测试、workspace 引用、生成目录条目和现行文档。不保留别名或兼容包。源码用户通过 `pnpm dsh --profile headless` 调用产品命令；stdout 上的最终文本、stderr 上的失败诊断、持久化、退出状态和关闭行为均由该命令负责。

 `examples/headless-agent` 成为显式测试组装。其 Loader 配置把 `@deepseek-ai/dsh-agent-spine-demo`、一个根 agent（智能体）、JSONL 持久化和检查点策略挂载为独立配置行，不再将其隐藏在应用组合包之后。支持层的 `@deepseek-ai/dsh-loader-smoke` 包负责共享的直接 agent 轮次 helper；未导出的示例本地 driver 选择各自的 Loader 配置，并将规范事件渲染为 JSONL。这些 driver 只由测试启动，不提供 bin，也不定义受支持的产品输出格式。

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/simplification/2026-08-10-source-run-without-managed-installer.md
+2026-08-10-source-run-without-managed-installer.md: ac506b72acab0dd6c92ce6111487d091b2bf4a73
+2026-08-10-source-run-without-managed-installer.zh.md: 86e44a90a9e7b34ad37b6a4bfd3ad14de40868f5
@@ -0,0 +1,31 @@
+# Agent Note: Source run without a managed installer
+
+Status: implemented
+
+English | [中文](2026-08-10-source-run-without-managed-installer.zh.md)
+
+## Problem
+
+A repository-owned source installer can provide a stable launcher, isolated staging worktrees, atomic upgrades, rollback storage, and shared maintenance workflows for personal customizations. It also makes the repository responsible for a second lifecycle beside the package manager: host dependency installation, credential prompting, checkout adoption, symlink ownership, staging branch coordination, upgrade recovery, and continued compatibility between the installer and bundled maintenance skills.
+
+That lifecycle is not required to run or develop DeepSeek Harness from a source checkout. Maintaining it expands the supported filesystem and Git state space without improving the repository-native execution path.
+
+## Decision
+
+The repository supports source execution through its root `pnpm` scripts. The `dsh` entry in `package.json` runs `pnpm run build`, then launches `apps/cli/src/bin.ts` through `node --import tsx/esm`; build output remains visible before the CLI output. The package script forwards arguments and inherits the caller's environment, including `NODE_USE_ENV_PROXY=1` when a supporting Node version must honor `HTTP_PROXY` and `HTTPS_PROXY`. Users select Web with `pnpm dsh web` and headless execution with `pnpm dsh --profile headless "task"`. The independent ACP example remains available through `pnpm run demo:acp`.
+
+The repository does not distribute a source installer, an installer test suite, or skills that assume a managed `current` symlink and timestamped staging worktrees. Users own source checkout placement, Git updates, and any launcher they create outside the repository.
+
+## Alternatives considered
+
+**Keep the installer but document `pnpm run` as another path.** This retains the managed launcher and rollback capability but keeps both lifecycle contracts active, including the installer tests and staging-aware skills.
+
+**Keep generic customization and upstream-publication skills.** Their safety rules can apply beyond the staging layout, but the shipped workflows form one coupled maintenance system: customization discovers the installed staging checkout, upgrade performs the cutover, and upstream publication is selected from those personal changes. General Git contribution guidance already belongs to repository instructions and does not require product-bundled skills.
+
+**Replace the installer with a smaller launcher-link script.** This reduces setup behavior but still makes the repository responsible for host PATH mutation and launcher ownership. Source scripts provide the entry points without that state.
+
+## Consequences
+
+Source users invoke repository scripts rather than an installed `dsh` command. The repository provides no atomic upgrade cutover or preserved staging rollback checkout, and it does not automate the integration or upstream publication of personal source modifications. A future distribution mechanism must justify its ownership of installation and upgrade state, define recovery behavior, and add tests and user documentation without making the source-run path depend on it. Any future publication workflow must isolate one approved feature and obtain explicit approval before its first push and draft PR.
+
+Verification covers repository-wide references to the removed entry points, documentation links, generated third-party-notice freshness, the build-first `package.json` command, and a source CLI smoke through the exact `node --import tsx/esm` runtime vector.
@@ -0,0 +1,31 @@
+# Agent Note: 无需托管安装器的源码运行
+
+Status: implemented
+
+[English](2026-08-10-source-run-without-managed-installer.md) | 中文
+
+## 问题
+
+仓库自带的源码安装器可以提供稳定的启动器、相互隔离的 staging worktree、原子升级、回滚存储，以及用于个人定制的共享维护工作流。与此同时，仓库还必须在包管理器之外负责第二套生命周期：安装宿主依赖、提示输入凭证、接管检出、管理符号链接归属、协调 staging 分支、处理升级恢复，以及持续保持安装器与随附维护 skill（技能）的兼容性。
+
+从源码检出运行或开发 DeepSeek Harness 并不需要这套生命周期。维护它会扩大需要支持的文件系统和 Git 状态空间，却无法改进仓库原生的执行路径。
+
+## 决策
+
+仓库通过根目录的 `pnpm` 脚本支持从源码运行。`package.json` 中的 `dsh` 项先执行 `pnpm run build`，再通过 `node --import tsx/esm` 启动 `apps/cli/src/bin.ts`；构建输出会显示在 CLI（命令行界面）输出之前。该包脚本会转发参数并继承调用方环境；当支持环境代理的 Node 版本必须遵循 `HTTP_PROXY` 和 `HTTPS_PROXY` 时，调用方可设置 `NODE_USE_ENV_PROXY=1`。用户使用 `pnpm dsh web` 选择 Web，使用 `pnpm dsh --profile headless "task"` 选择无头执行。独立的 ACP（Agent Client Protocol）示例仍可通过 `pnpm run demo:acp` 运行。
+
+仓库不分发源码安装器、安装器测试套件，也不分发依赖受管理的 `current` 符号链接和带时间戳 staging worktree 的 skill。源码检出的存放位置、Git 更新，以及用户在仓库外创建的任何启动器均由用户负责。
+
+## 考虑过的备选方案
+
+**保留安装器，但将 `pnpm run` 记作另一条路径。**这样可以保留受管理的启动器和回滚能力，但两套生命周期约定仍会同时生效，其中包括安装器测试和依赖 staging 布局的 skill。
+
+**保留通用的定制与上游发布 skill。**其中的安全规则也能用于 staging 布局之外，但现有工作流共同构成了一套耦合的维护系统：定制工作流查找已安装的 staging 检出，升级工作流执行切换，上游发布工作流则从这些个人修改中选择发布内容。通用 Git 贡献指南已经属于仓库指令，无需以产品随附 skill 的形式提供。
+
+**用更小的启动器链接脚本替换安装器。**这样可以简化设置过程，但仓库仍需负责修改宿主 PATH 和管理启动器归属。源码脚本无需引入这类状态即可提供入口点。
+
+## 影响
+
+源码用户通过仓库脚本运行程序，而非使用已安装的 `dsh` 命令。仓库不提供原子升级切换，也不保留 staging 回滚检出；仓库同样不会自动集成个人源码修改或将其发布到上游。未来的分发机制必须说明为何应由其管理安装和升级状态，定义恢复行为，并补充测试与用户文档，同时不得让源码运行路径依赖该机制。未来任何发布工作流都必须隔离出一项获批功能，并在首次推送和创建草稿 PR（Pull Request）前取得明确批准。
+
+验证范围包括仓库内对已移除入口点的所有引用、文档链接、生成的第三方声明文件的新鲜度、`package.json` 中的先构建后启动命令，以及通过准确的 `node --import tsx/esm` 运行方式对源码 CLI 进行的冒烟测试。
@@ -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/2026-08-11-remove-empty-experimental-package-group.md
+2026-08-11-remove-empty-experimental-package-group.md: e5e81e3e3763f216921b3f3b74709b64be3dee37
+2026-08-11-remove-empty-experimental-package-group.zh.md: d44d0daaf346a5fea317f8c8c6a23f26eaa3cec0
@@ -0,0 +1,37 @@
+# Agent Note: Remove the empty experimental package group
+
+Status: implemented
+
+English | [中文](2026-08-11-remove-empty-experimental-package-group.zh.md)
+
+## Problem
+
+The package hierarchy reserves `packages/experimental/` for prototypes and internal-only plugins, but no package has used the group. The empty group adds placement, dependency, promotion, and release rules without a current package or release mechanism that needs them.
+
+The original group aimed to let the team share prototypes against the real plugin graph without implying product support. That need remains possible, but it does not justify a permanent repository category before a concrete package exists.
+
+## Decision
+
+The package hierarchy has no reserved experimental or internal-only group. Packages continue to live in groups selected for their current product role.
+
+A concrete package that needs different release, stability, or dependency treatment requires a decision based on its actual consumers and release mechanism. That decision may reintroduce a dedicated group when it can also define and enforce the exclusion rules.
+
+This note consolidates and supersedes the experimental-package-group decision, whose active triplet is removed with the empty directory.
+
+## Alternatives considered
+
+**Keep the empty group.** It provides an obvious future incubation location, but it also keeps repository rules with no current owner, package, or enforcement mechanism.
+
+**Move the experimental rules into the general package instructions.** This preserves the policy without an empty directory, but makes every package change carry rules for a hypothetical package class.
+
+**Put concrete experimental packages in product-role groups with README labels.** This preserves product-role colocation, but labels alone cannot enforce release and runtime-dependency rules. A future package can evaluate this option against its actual release mechanism.
+
+**Treat every package as experimental until the first tagged release.** This applies a broad temporary status without providing durable treatment for packages that remain experimental after releases begin.
+
+**Require prototypes to stay outside the repository.** This would lose access to the real plugin graph, examples, snapshots, and lifecycle checks. Removing the reserved group does not impose that restriction; a concrete prototype can establish the placement it needs.
+
+## Consequences
+
+The hierarchy loses an unused group and its special release and dependency policy. It also gives up a predeclared location for team discovery and a ready-made promotion path.
+
+The first package that needs experimental or internal-only treatment must define where it lives, how releases exclude it, which runtime dependencies are allowed, and what condition promotes or removes it. A dedicated group can return when those rules have a current consumer and enforceable mechanism.
@@ -0,0 +1,37 @@
+# Agent Note: 移除空的实验性包分组
+
+Status: implemented
+
+[English](2026-08-11-remove-empty-experimental-package-group.md) | 中文
+
+## 问题
+
+包层级结构预留 `packages/experimental/` 用于原型和内部专用插件，但从未有包使用该分组。这个空分组添加了放置、依赖、提升和发布规则，却没有需要这些规则的现有包或发布机制。
+
+原分组旨在让团队基于真实插件图共享原型，同时不暗示产品会提供支持。这项需求将来可能出现，但在具体包出现前，不足以支持一个永久的仓库类别。
+
+## 决策
+
+包层级结构不再预留实验性或内部专用分组。包继续按照当前产品职责放入对应分组。
+
+如果具体包需要不同的发布、稳定性或依赖处理，必须根据其实际消费方和发布机制做出决策。只要该决策同时定义并强制执行排除规则，就可以重新引入专用分组。
+
+本 Agent Note 整合并取代实验性包分组决策；该旧决策的活跃三文件组随空目录一并移除。
+
+## 考虑过的替代方案
+
+**保留空分组。** 它为未来孵化工作提供明确位置，但也会保留没有当前负责人、包或强制执行机制的仓库规则。
+
+**将实验性规则移入通用包指令。** 这可以在不保留空目录的情况下延续政策，但会让每次包变更都携带针对假设包类别的规则。
+
+**将具体实验性包放入产品职责分组，并用 README 标注。** 这会保持产品职责共置，但仅靠标注无法强制执行发布和运行时依赖规则。未来的包可以根据实际发布机制评估此选项。
+
+**在首个带标签的版本发布前，将每个包都视为实验性。** 这会施加宽泛的临时状态，却无法为发布开始后仍处于实验状态的包提供持久处理方式。
+
+**要求原型留在仓库外。** 这会失去真实插件图、示例、快照和生命周期检查。移除预留分组并不施加这项限制；具体原型可以建立自身所需的放置规则。
+
+## 后果
+
+包层级结构移除了未使用的分组及其特殊发布和依赖政策，同时也放弃了预先声明的团队发现位置和现成的提升路径。
+
+第一个需要实验性或内部专用处理的包必须定义其存放位置、发布版本如何排除它、允许哪些运行时依赖，以及包在何种条件下获得提升或被移除。当这些规则具有当前消费方和可强制执行的机制时，可以恢复专用分组。
@@ -3,6 +3,7 @@
  "repository": "deepseek-harness",
  "projectNumber": 1,
  "projectTitle": "DSH Issue Management",
+  "lifecycleActor": "dsh-issue-management",
  "priorityField": "Priority",
  "allowUnassignedOwner": true,
  "statuses": [
@@ -37,10 +37,21 @@ const LEGACY_LABELS = new Set([
 ])
 const TERMINAL_STATUSES = new Set(['Done', 'No action'])
 const ACTIVE_STATUS_ORDER = config.statuses.filter((status) => !TERMINAL_STATUSES.has(status))
+const IMPLEMENTATION_PULL_REQUEST_ACTIONS = new Set([
+  'opened',
+  'edited',
+  'synchronize',
+  'reopened',
+  'labeled',
+  'unlabeled',
+])

 for (const status of ['In progress', 'In review']) {
  if (!ACTIVE_STATUS_ORDER.includes(status)) throw new Error(`config.statuses 缺少 ${status}`)
 }
+if (typeof config.lifecycleActor !== 'string' || !config.lifecycleActor) {
+  throw new Error('config.lifecycleActor 未设置')
+}

 /**
 * Return Markdown outside balanced details elements.
@@ -159,18 +170,48 @@ export function requiresPullRequestPolicy({
 }

 /**
- * Derive a forward-only Issue status from the current PR phase.
- * @param {string|null} currentStatus Current Project status.
- * @param {{isDraft: boolean, reviewRequestCount: number, reviewCount: number}} pull PR phase.
- * @returns {string|null} Status to write, or null when no forward transition exists.
+ * Translate a repository event into one resolving-Issue lifecycle command.
+ * @param {string} eventName GitHub event name.
+ * @param {{action?: string, review?: {state?: string}}} event GitHub event payload.
+ * @returns {'implementation'|'review-requested'|'changes-requested'|null} Lifecycle command.
 */
-export function nextResolvingIssueStatus(currentStatus, pull) {
-  const target =
-    !pull.isDraft && (pull.reviewRequestCount > 0 || pull.reviewCount > 0)
-      ? 'In review'
-      : 'In progress'
+export function resolvingIssueStatusCommand(eventName, event) {
+  if (eventName === 'pull_request') {
+    if (event.action === 'review_requested') return 'review-requested'
+    return IMPLEMENTATION_PULL_REQUEST_ACTIONS.has(event.action) ? 'implementation' : null
+  }
+  if (
+    eventName === 'pull_request_review' &&
+    event.action === 'submitted' &&
+    event.review?.state?.toLowerCase() === 'changes_requested'
+  ) {
+    return 'changes-requested'
+  }
+  return null
+}
+
+/**
+ * Plan one event-directed resolving-Issue status transition.
+ * @param {string|null} currentStatus Current Project status.
+ * @param {'implementation'|'review-requested'|'changes-requested'} command Lifecycle command.
+ * @param {string|null} currentStatusActor Actor that last set the current Project status.
+ * @returns {string|null} Status to write, or null when no permitted transition exists.
+ */
+export function nextResolvingIssueStatus(currentStatus, command, currentStatusActor = null) {
+  let target
+  if (command === 'review-requested') target = 'In review'
+  else if (command === 'implementation' || command === 'changes-requested') target = 'In progress'
+  else throw new Error(`未知 lifecycle command：${command}`)
+
  const currentIndex = ACTIVE_STATUS_ORDER.indexOf(currentStatus)
  const targetIndex = ACTIVE_STATUS_ORDER.indexOf(target)
+  if (
+    command === 'changes-requested' &&
+    currentStatus === 'In review' &&
+    currentStatusActor === config.lifecycleActor
+  ) {
+    return target
+  }
  return currentIndex >= 0 && currentIndex < targetIndex ? target : null
 }

@@ -396,9 +437,15 @@ async function issueSnapshot(number, status = undefined) {
  }
 }

-async function projectContext(number) {
+async function projectContext(number, includeStatusActor = false) {
  const data = await graphql(
-    `query($organization: String!, $repository: String!, $number: Int!, $project: Int!) {
+    `query(
+      $organization: String!
+      $repository: String!
+      $number: Int!
+      $project: Int!
+      $includeStatusActor: Boolean!
+    ) {
      organization(login: $organization) {
        projectV2(number: $project) {
          id
@@ -413,6 +460,16 @@ async function projectContext(number) {
      repository(owner: $organization, name: $repository) {
        issue(number: $number) {
          id
+          timelineItems(last: 100, itemTypes: [PROJECT_V2_ITEM_STATUS_CHANGED_EVENT])
+            @include(if: $includeStatusActor) {
+            nodes {
+              ... on ProjectV2ItemStatusChangedEvent {
+                actor { login }
+                project { id }
+                status
+              }
+            }
+          }
          projectItems(first: 20, includeArchived: true) {
            nodes {
              id
@@ -430,6 +487,7 @@ async function projectContext(number) {
      repository: config.repository,
      number,
      project: config.projectNumber,
+      includeStatusActor,
    },
  )
  const project = data.organization?.projectV2
@@ -439,7 +497,14 @@ async function projectContext(number) {
  const statusField = project.fields.nodes.find((field) => field?.name === 'Status')
  if (!statusField) throw new Error('Project 缺少 Status 字段')
  const item = issue.projectItems.nodes.find((candidate) => candidate.project.id === project.id)
-  return { project, issue, statusField, item }
+  const latestStatusEvent = issue.timelineItems?.nodes
+    ?.filter((event) => event?.project?.id === project.id)
+    .at(-1)
+  const statusActor =
+    latestStatusEvent?.status === item?.fieldValueByName?.name
+      ? (latestStatusEvent.actor?.login ?? null)
+      : null
+  return { project, issue, statusField, item, statusActor }
 }

 async function projectStatus(number) {
@@ -530,12 +595,7 @@ async function auditIssue(number, extraErrors = [], status = undefined) {
  return errors
 }

-async function pullRequestSnapshot(number) {
-  const pull = await api(`/repos/${config.organization}/${config.repository}/pulls/${number}`)
-  const [reviewRequests, reviews] = await Promise.all([
-    api(`/repos/${config.organization}/${config.repository}/pulls/${number}/requested_reviewers`),
-    api(`/repos/${config.organization}/${config.repository}/pulls/${number}/reviews?per_page=100`),
-  ])
+async function resolvingReferencesSnapshot(number, pull) {
  const references = parseReferences({
    body: pull.body ?? '',
    repository: `${config.organization}/${config.repository}`,
@@ -547,20 +607,41 @@ async function pullRequestSnapshot(number) {
  }
  return {
    number,
-    isDraft: pull.draft,
-    authorType: pull.user?.type ?? 'User',
-    reviewRequestCount: reviewRequests.users.length + reviewRequests.teams.length,
-    reviewCount: reviews.length,
-    labels: pull.labels.map((label) => label.name),
    references: retainIssueReferences(references, issues),
    issues,
  }
 }

-async function advanceResolvingIssues(pull) {
+async function pullRequestSnapshot(number) {
+  const [pull, reviewRequests, reviews] = await Promise.all([
+    api(`/repos/${config.organization}/${config.repository}/pulls/${number}`),
+    api(`/repos/${config.organization}/${config.repository}/pulls/${number}/requested_reviewers`),
+    api(`/repos/${config.organization}/${config.repository}/pulls/${number}/reviews?per_page=100`),
+  ])
+  const resolving = await resolvingReferencesSnapshot(number, pull)
+  return {
+    ...resolving,
+    isDraft: pull.draft,
+    authorType: pull.user?.type ?? 'User',
+    reviewRequestCount: reviewRequests.users.length + reviewRequests.teams.length,
+    reviewCount: reviews.length,
+    labels: pull.labels.map((label) => label.name),
+  }
+}
+
+async function lifecyclePullRequestSnapshot(number) {
+  const pull = await api(`/repos/${config.organization}/${config.repository}/pulls/${number}`)
+  return resolvingReferencesSnapshot(number, pull)
+}
+
+async function transitionResolvingIssues(pull, command) {
  for (const number of pull.references.resolving) {
-    const context = await projectContext(number)
-    const target = nextResolvingIssueStatus(context.item?.fieldValueByName?.name ?? null, pull)
+    const context = await projectContext(number, command === 'changes-requested')
+    const target = nextResolvingIssueStatus(
+      context.item?.fieldValueByName?.name ?? null,
+      command,
+      context.statusActor,
+    )
    if (!target) continue
    // TODO: Replace this latest-state guard with per-Issue serialization or a
    // conditional ProjectV2 update; GraphQL currently has no compare-and-swap.
@@ -598,8 +679,10 @@ async function runLifecycle(eventName, event) {
  }

  if (eventName === 'pull_request' || eventName === 'pull_request_review') {
-    const pull = await pullRequestSnapshot(event.pull_request.number)
-    await advanceResolvingIssues(pull)
+    const command = resolvingIssueStatusCommand(eventName, event)
+    if (!command) return
+    const pull = await lifecyclePullRequestSnapshot(event.pull_request.number)
+    await transitionResolvingIssues(pull, command)
  }
 }

@@ -6,6 +6,7 @@ import {
  nextResolvingIssueStatus,
  parseReferences,
  retainIssueReferences,
+  resolvingIssueStatusCommand,
  requiresPullRequestPolicy,
  validateBody,
  validateIssue,
@@ -243,32 +244,73 @@ test('requires policy only after a human PR enters review', () => {
  )
 })

-test('advances resolving Issues to the live PR phase', () => {
-  const draft = { isDraft: true, reviewRequestCount: 1, reviewCount: 4 }
-  const open = { isDraft: false, reviewRequestCount: 0, reviewCount: 0 }
-  const requestedReview = { isDraft: false, reviewRequestCount: 1, reviewCount: 0 }
-  const submittedReview = { isDraft: false, reviewRequestCount: 0, reviewCount: 1 }
-
-  for (const status of ['Inbox', 'Backlog', 'Ready']) {
-    assert.equal(nextResolvingIssueStatus(status, draft), 'In progress')
-    assert.equal(nextResolvingIssueStatus(status, open), 'In progress')
-    assert.equal(nextResolvingIssueStatus(status, requestedReview), 'In review')
-    assert.equal(nextResolvingIssueStatus(status, submittedReview), 'In review')
+test('maps only explicit review handoffs to review status commands', () => {
+  assert.equal(
+    resolvingIssueStatusCommand('pull_request', {
+      action: 'review_requested',
+    }),
+    'review-requested',
+  )
+  assert.equal(
+    resolvingIssueStatusCommand('pull_request_review', {
+      action: 'submitted',
+      review: { state: 'changes_requested' },
+    }),
+    'changes-requested',
+  )
+  for (const state of ['approved', 'commented']) {
+    assert.equal(
+      resolvingIssueStatusCommand('pull_request_review', {
+        action: 'submitted',
+        review: { state },
+      }),
+      null,
+    )
  }
-  assert.equal(nextResolvingIssueStatus('In progress', requestedReview), 'In review')
-  assert.equal(nextResolvingIssueStatus('In progress', submittedReview), 'In review')
+  assert.equal(
+    resolvingIssueStatusCommand('pull_request_review', {
+      action: 'dismissed',
+      review: { state: 'changes_requested' },
+    }),
+    null,
+  )
 })

-test('never regresses or reopens a resolving Issue', () => {
-  const implementation = { isDraft: false, reviewRequestCount: 0, reviewCount: 0 }
-  const review = { isDraft: false, reviewRequestCount: 0, reviewCount: 1 }
+test('keeps ordinary pull request events as forward-only implementation signals', () => {
+  for (const action of ['opened', 'edited', 'synchronize', 'reopened', 'labeled', 'unlabeled']) {
+    assert.equal(resolvingIssueStatusCommand('pull_request', { action }), 'implementation')
+  }
+  assert.equal(
+    resolvingIssueStatusCommand('pull_request', { action: 'review_request_removed' }),
+    null,
+  )
+})

-  assert.equal(nextResolvingIssueStatus('In progress', implementation), null)
-  assert.equal(nextResolvingIssueStatus('In review', implementation), null)
-  assert.equal(nextResolvingIssueStatus('In review', review), null)
-  assert.equal(nextResolvingIssueStatus('Done', review), null)
-  assert.equal(nextResolvingIssueStatus('No action', review), null)
-  assert.equal(nextResolvingIssueStatus(null, review), null)
+test('toggles automation-owned work on request changes and repeated review request', () => {
+  for (const status of ['Inbox', 'Backlog', 'Ready']) {
+    assert.equal(nextResolvingIssueStatus(status, 'implementation'), 'In progress')
+    assert.equal(nextResolvingIssueStatus(status, 'review-requested'), 'In review')
+    assert.equal(nextResolvingIssueStatus(status, 'changes-requested'), 'In progress')
+  }
+  let status = nextResolvingIssueStatus(
+    'In review',
+    'changes-requested',
+    'dsh-issue-management',
+  )
+  assert.equal(status, 'In progress')
+  status = nextResolvingIssueStatus(status, 'review-requested')
+  assert.equal(status, 'In review')
+})
+
+test('preserves human review status and terminal Issues', () => {
+  assert.equal(nextResolvingIssueStatus('In progress', 'implementation'), null)
+  assert.equal(nextResolvingIssueStatus('In review', 'implementation'), null)
+  assert.equal(nextResolvingIssueStatus('In review', 'review-requested'), null)
+  assert.equal(nextResolvingIssueStatus('In review', 'changes-requested', 'tianyicui'), null)
+  assert.equal(nextResolvingIssueStatus('In review', 'changes-requested'), null)
+  assert.equal(nextResolvingIssueStatus('Done', 'review-requested'), null)
+  assert.equal(nextResolvingIssueStatus('No action', 'changes-requested'), null)
+  assert.equal(nextResolvingIssueStatus(null, 'review-requested'), null)
 })

 test('keeps lifecycle projection independent of PR metadata enforcement', () => {
@@ -283,7 +325,7 @@ test('keeps lifecycle projection independent of PR metadata enforcement', () =>
  }

  assert.ok(validatePullRequest(pull).length > 0)
-  assert.equal(nextResolvingIssueStatus('Inbox', pull), 'In review')
+  assert.equal(nextResolvingIssueStatus('Inbox', 'review-requested'), 'In review')
 })

 test('exempts Draft, Bot, and App PRs', () => {
@@ -36,6 +36,7 @@ concurrency:
 jobs:
  lifecycle:
    name: Issue lifecycle
+    if: ${{ github.event_name != 'pull_request_review' || (github.event.action == 'submitted' && github.event.review.state == 'changes_requested') }}
    runs-on: ubuntu-latest
    steps:
      - name: Check out trusted policy
@@ -73,7 +73,7 @@ pnpm run check:windows-wine  # ONLY when diagnosing a known Windows failure (nee
 pnpm run hygiene        # knip + publint + workspace constraints + NodeNext consumer check
 pnpm run doc-sync       # all documentation gates; leaf list in scripts/run-gates.ts
 pnpm run website:build  # VitePress build (doubles as dead-link check)
-pnpm run demo:headless "task" # one-shot agent (needs DEEPSEEK_API_KEY)
+pnpm dsh --profile headless "task"  # build, then run one task (needs DEEPSEEK_API_KEY)
 pnpm run demo:cordis    # the agent modifies its own runtime (needs key)
 pnpm run demo:acp       # ACP automation server (needs DEEPSEEK_API_KEY)
 ```
@@ -100,7 +100,7 @@ Real-API tests and demos read `DEEPSEEK_API_KEY`, optional `DEEPSEEK_BASE_URL`,
 - ESM everywhere (`"type": "module"`). Use package names across packages and `.ts` in local relative imports. Config subprocesses run built `lib/` under plain Node; source regressions use their declared launcher ([testing policy](docs/testing.md#test-subprocess-launch-modes)). The `dsh` CLI source launch runs through tsx's ESM-only hook (`node --import tsx/esm`); modules it reaches must stay ESM (no CJS-only exports) — Node's native TypeScript modes are unavailable across the engines range ([source-launch contract](.agents/notes/implemented/architecture/2026-07-29-dsh-source-launch-tsx-esm.md)). Raw/Web `cordis.yml` bare plugins must appear in their resolver manifest's `dependencies`; `verify-cordis-config` enforces it.
 - **Registrations are effects**: every contribution goes through `ctx.effect()` / `ctx.on()`; a registry's `register()` returns the disposer.
 - **Runtime invariants assert owned relationships.** Check authoritative event streams or mutable data, not service or method presence, plugin metadata or effects, or fixed pure examples. Without a plausible relationship, an explained empty companion is correct ([package invariant rules](packages/AGENTS.md)).
- **Typed events use declaration merging** and merge-extensible maps. Event JSDoc needs `@mode` and payload `@param`; scoped keys absent from payloads need `@dshScopeScan unsupported`. Public service methods document parameters and non-void returns.
+- **Typed events use declaration merging** and merge-extensible maps. Event JSDoc needs `@mode` and payload `@param`; scoped keys absent from payloads need `@dshScopeScan unsupported`. Public service methods document parameters and non-void returns. A `SessionEventMap` member is required-on-read by default — builds that do not know its type refuse the log unless the event carries the envelope's `ignorable: true`; only structural format changes bump `SESSION_FORMAT_VERSION` ([mechanism](.agents/notes/implemented/architecture/2026-08-10-session-log-version-mechanism.md)).
 - **Switch on discriminant tags.** Closed unions end in `assertNever`; merge-extensible unions fall through a documented default.
 - **Waterfall listeners MUST call `next()`** to delegate; returning without it short-circuits the chain ([semantics](docs/cordis-primer.md#cordis-waterfall-semantics)).
 - **Model-visible ⟺ logged**: anything that reaches a model request must be reconstructable from the session log; a new model-visible input requires a session event.
@@ -0,0 +1,3 @@
+# Running benchmarks
+
+To run benchmark tasks with the minimal agent composition, follow [Get started with the Python SDK](docs/user/guide/python-sdk.md). The guide covers installation, running [`minimal.cordis.yml`](examples/jsonrpc-agent/minimal.cordis.yml), and isolating workspaces and session IDs between tasks.
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write README.md
-README.md: 9b8944027572072e08a39bd9e482996f8128224c
-README.zh.md: a1b2b6a36c4baac8a49b88a42c9f17c986287ff1
+README.md: b2d84672275a4ca996b6ea596c104abfaa52432a
+README.zh.md: 747a3c88bc129ad5dd24f5fa150a1661c4db0b11
@@ -12,41 +12,34 @@ DeepSeek Harness is under internal testing. Features and interfaces may change.

 The internal build uploads all Session Logs by default to help diagnose reported problems. Set `DSH_TELEMETRY_DISABLED=1` to disable telemetry. Send feedback through the internal WeChat group.

-## Install
+## Run from source

-Clone the repository, then run the installer:
+Clone this repo, complete the [dependency and API-key setup](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key), then run:

 ```sh
-git clone <repo-url>
-cd deepseek-harness
-scripts/install.sh
+pnpm dsh web
 ```

-The installer requires `git` and Node `^22.19 || >=24`, offers to install `pnpm` when it is missing, prompts for a DeepSeek API key, builds the required repository artifacts, and launches the Web UI.
-
-The default active checkout is `~/.dsh/source/current`, and the launcher is linked into `~/.local/bin`. Re-run the installer to update. [`scripts/install.sh`](scripts/install.sh) owns alternate locations, update mechanics, and recovery options.
-
 ## Use DeepSeek Harness

 ### Web UI

-For the recommended local interface, choose Web UI when the installer finishes. To start it later, or after updating the active checkout, build the repository and run:
+Start the recommended local interface from the repository root:

 ```sh
-(cd ~/.dsh/source/current && pnpm run build)
-dsh web
+pnpm dsh web
 ```

-The path above is the installer's default. If you set `DSH_SOURCE` or `DSH_CURRENT`, or reused an existing checkout, replace `~/.dsh/source/current` with that checkout path; see [`scripts/install.sh`](scripts/install.sh) for details. The Web UI is served at `http://127.0.0.1:3080` by default.
+The command builds the repository before starting the Web UI, which is served at `http://127.0.0.1:3080` by default.

 ### Profiles

-`dsh` boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/<name>`:
+The source CLI boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/<name>`:

 ```sh
-dsh --profile web                       # the browser UI (same as: dsh web)
-dsh plugin --profile tui add <package>  # install a plugin into a custom profile
-dsh --profile tui                       # boot it
+pnpm dsh --profile web                       # the browser UI
+pnpm dsh plugin --profile tui add <package>  # install a plugin into a custom profile
+pnpm dsh --profile tui                       # boot it
 ```

 The [CLI reference](apps/cli/README.md#profiles) describes profile layout, layer semantics, and config dump commands.
@@ -56,7 +49,7 @@ The [CLI reference](apps/cli/README.md#profiles) describes profile layout, layer
 Run one task, print the final answer, and exit:

 ```sh
-dsh --profile headless "summarize this workspace"
+pnpm dsh --profile headless "summarize this workspace"
 ```

 ### Automation and SDKs
@@ -12,41 +12,34 @@ DeepSeek Harness 正处于内部测试阶段，功能和接口可能发生变化

 为帮助诊断上报的问题，内测版本默认上传所有会话日志。设置 `DSH_TELEMETRY_DISABLED=1` 可关闭遥测。请通过内部企业微信群反馈问题和建议。

-## 安装
+## 从源码运行

-克隆仓库，然后运行安装器：
+克隆本仓库，完成[依赖安装和 API 密钥配置](docs/user/guide/quickstart.md#step-1-install-and-configure-the-api-key)，然后运行：

 ```sh
-git clone <repo-url>
-cd deepseek-harness
-scripts/install.sh
+pnpm dsh web
 ```

-安装器要求系统已安装 `git` 和 Node `^22.19 || >=24`，缺少 `pnpm` 时可代为安装，并会提示输入 DeepSeek API 密钥，然后构建所需的仓库产物并启动 Web UI。
-
-默认生效的检出位于 `~/.dsh/source/current`，启动器链接到 `~/.local/bin`。再次运行安装器即可更新。其他位置、更新机制和恢复选项由 [`scripts/install.sh`](scripts/install.sh) 负责。
-
 ## 使用 DeepSeek Harness

 ### Web UI

-推荐在本地使用 Web UI；安装结束时，选择 Web UI 即可。以后需要启动时，或更新当前生效的检出后，请构建仓库并运行：
+请从仓库根目录启动推荐的本地界面：

 ```sh
-(cd ~/.dsh/source/current && pnpm run build)
-dsh web
+pnpm dsh web
 ```

-上述路径是安装器的默认位置。如果你设置过 `DSH_SOURCE` 或 `DSH_CURRENT`，或者复用了已有检出，请把 `~/.dsh/source/current` 换成该检出路径；详情见 [`scripts/install.sh`](scripts/install.sh)。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。
+该命令会先构建仓库，再启动 Web UI。Web UI 默认通过 `http://127.0.0.1:3080` 提供服务。

 ### Profile

-`dsh` 启动 profile：按序叠放的插件组合包 patch 层，之上再叠加你在 `$DSH_HOME/profiles/<name>` 中的自有覆盖层：
+源码 CLI（命令行界面）会启动 profile：按序叠放的插件组合包 patch 层，之上再叠加你在 `$DSH_HOME/profiles/<name>` 中的自有覆盖层：

 ```sh
-dsh --profile web                       # the browser UI (same as: dsh web)
-dsh plugin --profile tui add <package>  # install a plugin into a custom profile
-dsh --profile tui                       # boot it
+pnpm dsh --profile web                       # the browser UI
+pnpm dsh plugin --profile tui add <package>  # install a plugin into a custom profile
+pnpm dsh --profile tui                       # boot it
 ```

 profile 布局、层语义与配置输出命令详见 [CLI（命令行界面）参考](apps/cli/README.md#profiles)。
@@ -56,7 +49,7 @@ profile 布局、层语义与配置输出命令详见 [CLI（命令行界面）
 运行一项任务，打印最终答案后退出：

 ```sh
-dsh --profile headless "summarize this workspace"
+pnpm dsh --profile headless "summarize this workspace"
 ```

 ### 自动化与 SDK
@@ -27,7 +27,7 @@ The Cordis framework and its foundation libraries are source-vendored into this

 ## Runtime npm dependencies

-External packages that a workspace package resolves at runtime. `scripts/install.sh` installs this repository itself, so the tier covers every plugin a user can mount from `cordis.yml` — not only what the `dsh` CLI, Web UI, and Python SDK runtime load by default.
+External packages that a workspace package resolves at runtime. The tier covers every plugin a user can mount from `cordis.yml` — not only what the `dsh` CLI, Web UI, and Python SDK runtime load by default.

 | Package | License |
 | --- | --- |
@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write apps/cli/README.md
-README.md: 4fae5338a89ce12c2620e123530acf883ae9efff
-README.zh.md: a2d086b8ff12fb07f2446fc4162de09739bcdeab
+README.md: 98a856261bc632c97f350db8fc7bb0b10c22235d
+README.zh.md: 283e54138e24202ed6b88d1d309538c58cd66b3e
@@ -31,8 +31,8 @@ dsh --help                          # the launcher's own help

 A profile directory holds a `package.json` (out-of-tree plugin dependencies plus the profile manifest `dsh.profile` with its ordered `bundles` list) and a `cordis.patch.yml` (the user's own patch layer, hot-reloaded on long-lived surfaces). The tree composes over an empty root: each bundle's patch in `dsh.profile.bundles` order, then the profile's `cordis.patch.yml`, then the home-level `$DSH_HOME/cordis.patch.yml`, then `--patch` overlays. Bundles named in `dsh.profile.bundles` resolve from the dsh installation first (`@deepseek-ai/dsh-base`, `@deepseek-ai/dsh-web-app`, `@deepseek-ai/dsh-headless`), then from the profile's own `node_modules`, where pnpm installs out-of-tree plugins. Use `--dump-default-config` and `--dump-config` to inspect the composed tree without booting it.

-The [CLI behavior reference](reference/README.md) owns exact layer precedence, flags, shutdown behavior, deployment defaults, and the source launcher.
+The [CLI behavior reference](reference/README.md) owns exact layer precedence, flags, shutdown behavior, deployment defaults, and source execution.

 ## Development

-Production runs require built package and frontend artifacts. From a checkout, `pnpm run dsh` runs the TypeScript entry and forwards arguments; the [source-launcher reference](reference/README.md#source-launcher) describes the PATH symlink and module-resolution contract.
+Production runs require built package and frontend artifacts. From the repository root, `pnpm dsh <args...>` builds those artifacts, runs the TypeScript entry, and forwards every argument; the [source-execution reference](reference/README.md#source-execution) owns the module-resolution contract.
@@ -31,8 +31,8 @@ dsh --help                          # the launcher's own help

 profile 目录包含一个 `package.json`（树外插件依赖，加上 profile manifest（元数据清单）`dsh.profile` 及其有序的 `bundles` 列表）和一个 `cordis.patch.yml`（用户自己的 patch 层，在长期运行的 surface 上热重载）。配置树在空根之上组合：先按 `dsh.profile.bundles` 顺序应用各组合包的 patch，然后是 profile 的 `cordis.patch.yml`，然后是 home 级的 `$DSH_HOME/cordis.patch.yml`，然后是 `--patch` overlay。`dsh.profile.bundles` 中列出的组合包先从 dsh 安装目录解析（`@deepseek-ai/dsh-base`、`@deepseek-ai/dsh-web-app`、`@deepseek-ai/dsh-headless`），再从 profile 自己的 `node_modules` 解析；pnpm 把树外插件安装在后者。使用 `--dump-default-config` 和 `--dump-config` 可在不启动的情况下检查组合后的配置树。

-[CLI（命令行界面）行为参考](reference/README.md)负责确切的层优先级、flag、关闭行为、部署默认值和源码启动器。
+[CLI（命令行界面）行为参考](reference/README.md)负责确切的层优先级、flag、关闭行为、部署默认值和源码执行。

 ## 开发

-生产运行需要已构建的包与前端产物。在 checkout 中，`pnpm run dsh` 会运行 TypeScript 入口并转发参数；[源码启动器参考](reference/README.md#source-launcher)说明 PATH 符号链接和模块解析契约。
+生产运行需要已构建的包与前端产物。从仓库根目录运行 `pnpm dsh <args...>` 会先构建这些产物，再运行 TypeScript 入口并转发所有参数；模块解析约定由[源码执行参考](reference/README.md#source-execution)负责。
--- a/Show More
+++ b/Show More