Merge branch 'master' into fix/update-explore-unknown-copy

.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md
-2026-07-16-explicit-turn-cancellation.md: cce649976c9f4f596d5306b9fe8c3fd49a0e1adc
-2026-07-16-explicit-turn-cancellation.zh.md: 6f8b83fdb42af03c97dc2e8a9345a01acc6019fc
+2026-07-16-explicit-turn-cancellation.md: ca56c77a097e3008a50c2aec24040a4f4b6f0ba3
+2026-07-16-explicit-turn-cancellation.zh.md: bf410e5c7284a9c9914edbd14445074e71dd6943

.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md

@@ -20,7 +20,7 @@ AgentLoop privately owns one `TurnCancellation` per prospective turn. It install
 
 The driver keeps only a cause-less pre-run marker for queued work cancelled before a turn is claimed. An effective `cancel()` emits the observe-only `agent/cancel-requested` notification with its resolved typed cause before clearing queued and steering work or aborting the holder; notification failures cannot veto the stop, and an idle call emits nothing. Work synchronously queued by a notification observer is included in that clear, while work queued by a later signal abort observer belongs to the next turn. If a `running` listener synchronously cancels old work and sends a replacement, the driver discards the aborted holder and creates a fresh one for the replacement. Repeated cancellation is first-wins for the active holder, while later calls may still clear newly queued pending work.
 
-The explicit event signatures keep their positional form and place `signal` inside `PreStepContext` or immediately before a waterfall's final `next`. Pre-step entry, request configuration, request-error recovery, model generation, tool execution, approval, turn stopping, and subagent or workflow requests all receive the current signal. Hook bridges must also supply `RunHookOptions.signal`, so a turn cancellation reaches the bash executor's process-group kill and join boundary. `SystemPrompt.assemble()` carries `signal?: AbortSignal` in `AssembleContext` because that object is an explicit request value that can also represent signal-less assembly outside a turn. Listeners may cooperate with the signal but must not retain it to control another turn.
+The explicit event signatures pass a single payload object: agent-scoped events carry `agent` and `signal` in the payload with `next` last, and the remaining seams keep `signal` immediately before a waterfall's final `next`. `PreStepContext` and `RequestFailureContext` are retired, with their fields folded into the `agent/pre-step` and `agent/request-error` payloads ([payload-object events](2026-08-06-agent-event-payload-objects.md)). Pre-step entry, request configuration, request-error recovery, model generation, tool execution, approval, turn stopping, and subagent or workflow requests all receive the current signal. Hook bridges must also supply `RunHookOptions.signal`, so a turn cancellation reaches the bash executor's process-group kill and join boundary. `SystemPrompt.assemble()` carries `signal?: AbortSignal` in `AssembleContext` because that object is an explicit request value that can also represent signal-less assembly outside a turn. Listeners may cooperate with the signal but must not retain it to control another turn.
 
 `ctx.agents` continues to carry only the initiating Agent. Ambient Agent presence does not imply liveness, a current turn, or cancellation authority. The cause reader is private to the loop and states the machine-private slot invariant (only `cancel()` aborts a turn controller, always with a canonical frozen cause) instead of re-validating the reason structurally; no public helper reads a cause off an arbitrary signal. Concurrent Agents isolate both their initiator identities and their turn signals; a child driver shadows the parent initiator while its parent request signal still travels through the subagent seam.
 
@@ -44,7 +44,7 @@ Initiator-scope tests assert that every hook still observes the exact Agent and
 
 **Define speculative `superseded`, `timeout`, and `shutdown` variants now.** No current Agent cancellation producer implements those semantics. `shutdown` is already lifecycle disposal, and timeout or supersession should enter the union only with an owning policy and unique terminal meaning.
 
-**Expose public turn or step context wrappers.** Existing positional seams already identify Agent, turn, and step. A wrapper would widen every API, duplicate ownership, and tempt callers to treat a captured object as durable authority.
+**Expose public turn or step context wrappers.** Existing seams already identify Agent, turn, and step. A wrapper would widen every API, duplicate ownership, and tempt callers to treat a captured object as durable authority.
 
 **Abandon uncooperative work after a grace period.** Returning idle while same-process work still runs breaks teardown and resource-ownership guarantees. Hard termination requires a worker or process isolation boundary and is outside this control seam.
 

.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.zh.md

@@ -20,7 +20,7 @@ AgentLoop 为每个待启动轮次私有地持有一个 `TurnCancellation`。它
 
 对于轮次被认领前已取消的排队工作，驱动器只保留一个不携带取消原因的运行前标记。实际生效的 `cancel()` 会先发出仅供观察的 `agent/cancel-requested` 通知并携带最终确定的类型化取消原因，然后才清除排队工作和 steering（中途引导）工作或中止持有者；通知失败不能阻止此次停止，空闲状态下调用则不发出任何通知。通知观察者同步加入队列的工作也会被这次清除，而稍后由 signal 中止观察者加入队列的工作属于下一个轮次。若 `running` 监听器同步取消旧工作并发送替代提示词，驱动器会丢弃已中止的持有者，并为替代提示词创建全新的持有者。同一活跃持有者上的重复取消遵循首次请求优先，后续调用仍可清除新入队的待处理工作。
 
-显式事件签名保留位置参数形式，并把 `signal` 放入 `PreStepContext`，或放在 waterfall（瀑布式事件）的最后一个参数 `next` 之前。pre-step 进入决策、请求配置、请求错误恢复、模型生成、工具执行、审批、轮次停止以及 subagent 或工作流请求都会收到当前 signal。钩子桥接器也必须提供 `RunHookOptions.signal`，使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`，因为该对象是显式请求值，也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消，但不得保留它来控制其他轮次。
+显式事件签名传递单个 payload 对象：agent 作用域事件在 payload 中携带 `agent` 和 `signal`，`next` 位于最后；其余 seam 保持 `signal` 紧邻 waterfall（瀑布式事件）的最终 `next` 之前。`PreStepContext` 与 `RequestFailureContext` 已退役，其字段并入 `agent/pre-step` 与 `agent/request-error` 的 payload（[payload-object 事件](2026-08-06-agent-event-payload-objects.md)）。pre-step 进入决策、请求配置、请求错误恢复、模型生成、工具执行、审批、轮次停止以及 subagent 或工作流请求都会收到当前 signal。钩子桥接器也必须提供 `RunHookOptions.signal`，使轮次取消能够到达 Bash 执行器终止进程组并等待其退出的边界。`SystemPrompt.assemble()` 在 `AssembleContext` 中携带 `signal?: AbortSignal`，因为该对象是显式请求值，也可表示轮次之外不携带 signal 的组装。监听器可以配合该 signal 取消，但不得保留它来控制其他轮次。
 
 `ctx.agents` 仍只携带发起 Agent。环境中的 Agent 并不代表存活、当前轮次或取消权限。cause 读取器是 loop 私有的，它直接陈述机器私有的 slot 不变量（只有 `cancel()` 会中止轮次控制器，且总是携带规范的冻结 cause），而不是对 reason 做结构化再校验；不存在从任意 signal 读取 cause 的公开辅助函数。并发 Agent 会同时隔离各自的发起方身份和轮次 signal；子驱动会遮蔽父发起方，而父请求 signal 仍通过 subagent seam 传递。
 
@@ -44,7 +44,7 @@ Agent dispose（资源释放）会在活跃持有者上请求仅用于运行时
 
 **现在就定义推测性的 `superseded`、`timeout` 和 `shutdown` 变体。** 当前没有 Agent 取消生产方实现这些语义。`shutdown` 已经属于生命周期 dispose；超时或替代只有在拥有明确归属策略和唯一终态含义时才应进入联合类型。
 
-**公开轮次或步骤上下文包装类型。** 现有位置参数 seam 已经标识 Agent、轮次和步骤。包装类型会加宽所有 API、重复归属，并诱导调用方把捕获的对象当成持久权限。
+**公开轮次或步骤上下文包装类型。** 现有 seam 已经标识 Agent、轮次和步骤。包装类型会加宽所有 API、重复归属，并诱导调用方把捕获的对象当成持久权限。
 
 **在宽限期后放弃不协作的工作。** 同进程工作仍在运行时就报告空闲状态，会破坏资源清理与资源归属保证。硬终止需要 worker 或进程隔离边界，不属于该控制 seam。
 

.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md
-2026-07-25-web-client-session-scope-and-provide-channel.md: aeefbe22a397e3d7ffb9f6427a3c70c8c8e8b940
-2026-07-25-web-client-session-scope-and-provide-channel.zh.md: 056d50d45cef891e0e635d8bb4f2e73064ccdb87
+2026-07-25-web-client-session-scope-and-provide-channel.md: 3c51f06fca23a495f0fbc0cc4f1c289edea07b3b
+2026-07-25-web-client-session-scope-and-provide-channel.zh.md: 06fc1005785d9d11b52839f91c3bb4b99cad7d63

.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.md

@@ -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 composer stack, and the overlay chain's fallback frame retain their React instances across the no-session → blank-session switch; `conversation.session` carries only the strict-session header/view. 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 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.
 
 - 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).

.agents/notes/implemented/architecture/2026-07-25-web-client-session-scope-and-provide-channel.zh.md

@@ -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、composer stack 与 overlay chain 的 fallback 外框在无 session → blank session 的切换中保持 React 实例；`conversation.session` 只承载严格 session 的 header/view。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。
 
 - 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）。

.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md
-2026-07-25-web-input-machine-and-slash-pipeline.md: 977df6508e1a1cd54cf1ddb469a6bfb835f60071
-2026-07-25-web-input-machine-and-slash-pipeline.zh.md: f70065c8b356b2ed5ca6ab317fbdeb5177f058fa
+2026-07-25-web-input-machine-and-slash-pipeline.md: 39ef214a94fcd019f535fb60136d5dcc09b54e60
+2026-07-25-web-input-machine-and-slash-pipeline.zh.md: 9b0ca0cadbc5e0212048b165f0d60d567a5639ad

.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.md

@@ -69,9 +69,9 @@ A trigger/menu/pick pipeline with zero knowledge of "commands":
 ### hub / facade: the resident shell and the strict-session input body
 
 - The hub (trigger/decoration registries + send orchestration) takes the slash/command services as optional `ctx.get()` dependencies: without ui-slash or the command surfaces, input still sends and receives normally — graceful degradation.
-- Each materialized Session has exactly one `SessionInputShell` (the facade), created and torn down with the session scope; with no session, no input machine is built. `ConversationRoot` is itself the `session-maybe` resident shell, holding HeroShell, the Workspace picker, the composer stack, and the chain-fallback frame.
+- Each materialized Session has exactly one `SessionInputShell` (the facade), created and torn down with the session scope; with no session, no input machine is built. `ConversationRoot` is itself the `session-maybe` resident shell, holding HeroShell, the Workspace picker, the composer stack, and the chain-fallback frame. It always owns the same scrollport and composer seat; separate strict-session header and body outlets fill those fixed regions after a Session appears.
 - The composer bar is one `session-maybe` slot entry rendered unconditionally: with no session the same InputBar renders inert (machine faces absent, `disabled` owner prop), and once `connectWorkspace` returns a blank session the same instance goes live — the textarea DOM survives the no-session → blank transition and every later phase flip; `ConversationRoot`, the Hero, and the layout skeleton hold throughout.
-- ConversationRoot's Hero criterion is `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || openState === 'loading'))`. The first submit enters engaging synchronously, and a failure keeps the composer and the error context rather than falling back to the blank Hero; the sidebar's blank bit flips false only after a prompt is successfully accepted.
+- ConversationRoot's Hero criterion is `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || summaryBlank === true))`: a summary-proven blank Session remains Hero in every open state, while an unproven Session settles during loading. The first submit enters engaging synchronously, and a failure keeps the composer and the error context rather than falling back to the blank Hero; the sidebar's blank bit flips false only after a prompt is successfully accepted.
 - Sending unifies in the hub defaultSink: after an optimistic draft clear it goes only through `session.prompt` with `mode:'queue'` (the Web UI has no steer entry; host-wire `mode:'steer'` remains outside this machine); backfill happens only when it fails and the live draft is still empty — a user who has kept typing is never overwritten. No Draft materialize or attach transaction exists.
 - When the blank Hero re-picks the Workspace, the shell calls `connectWorkspace`; if the target session differs, the non-empty draft moves from the current shell to the target shell before the new id is opened, and the old blank session survives but is no longer current.
 - The Notifier's two-bit contract: `dirty` (snapshot freshness, clearable by an `ensureFresh` pull) and `notifyPending` (notification debt, cleared only by a flush) are mutually independent — a pull must not swallow a push, and object-layer push subscribers (watchTransaction) depend on this guarantee.
@@ -93,9 +93,10 @@ skill/@subagent references skip the placeholder + occurrence identity chain —
 
 ### The slot system
 
-`conversation` is itself session-maybe; its session content and the composer input slots are strict session, while the Hero Workspace picker stays root. The child slots are all declared by ui-conversation's conversation registration:
+`conversation` is itself session-maybe; its session content and the composer input slots are strict session, while the Hero Workspace picker stays root. The root registration renders the header outlet above its resident scrollport and the body outlet inside it, before the resident composer seat. The child slots are all declared by ui-conversation's conversation registration:
 
-- `conversation.session` (single) — the strict-session header, view ring, and chat store; rebuilt when the session id switches.
+- `conversation.session.header` (single) — strict-session breadcrumb, view tabs, and header actions above the resident scrollport.
+- `conversation.session` (single) — the strict-session view ring and draft mirror inside the resident scrollport. Header and body share the same session-scoped chat store; each is rebuilt when the session id switches.
 - `conversation.composer.bar` (single) — the slot for the InputBar itself: the InputBar is a true slot entry (self-registered into its own slot) and the content of the composer chain's fallback; it is not a chain entry — the chain's single election would unmount it on a takeover, breaking textarea DOM survival.
 - `conversation.input.overlay` — the floating-overlay anchor inside the input card; registrants' inject resolves each one's own per-session controller by the slot sessionId.
 - `conversation.input.dock` — the stacked strip above the input (QueueDock's read-only queue list lands here), ordered by `order`.
@@ -128,7 +129,7 @@ The state machine's entire behavior is covered by pure-JS unit tests (event sequ
 
 ## Consequences
 
-- One resident conversation shell carries no-session/blank/active: no session → blank guarantees only the outer frame's React identity, allowing the disabled textarea to be replaced by the strict InputBar; the same blank session → engaging/active keeps the InputBar and the textarea. EmptyState and the controlled intent chain (`sessions.updateIntent`/`updatePendingPrompt`/`workspaces.sendSession`) are deleted along with their last consumer.
+- One resident conversation shell carries no-session/blank/active: no session → blank preserves ConversationRoot, Hero, the root-scoped Workspace picker, scrollport, composer seat, InputBar, and textarea; only the strict header and body outlets gain content. The same blank session → engaging/active also keeps the InputBar and textarea. EmptyState and the controlled intent chain (`sessions.updateIntent`/`updatePendingPrompt`/`workspaces.sendSession`) are deleted along with their last consumer.
 - The input surface's zero knowledge of commands plus optional dependencies: pure input works without the command packages; `@` references and skill references get free reuse of the same menu/pick pipeline. The cost is that space/enter adjudication is a per-source polling protocol whose answer semantics (sync/async, the meaning of undefined) are a frozen contract.
 - Transactionalized submission (attempt seq + the drift guard) makes the three defect classes — stale-result backwash, session switching, concurrent replay — structurally impossible, pinned by the matrix tests.
 - Known gaps: chip fidelity across refresh (paste matching is reusable for it) has no workstream yet; the subagent reference's model representation awaits its business workstream.

.agents/notes/implemented/architecture/2026-07-25-web-input-machine-and-slash-pipeline.zh.md

@@ -69,9 +69,9 @@ occurrence 表与 chip 三投影：
 ### hub / facade：常驻外壳与严格 session 输入体
 
 - hub（trigger/decoration 注册表 + 发送编排）对 slash/command 服务是可选 `ctx.get()` 依赖：无 ui-slash/命令面时输入正常收发，优雅降级。
-- 每个实体 Session 只有一个 `SessionInputShell`（facade），随 session scope 创建和拆除；无 session 时不造 input machine。`ConversationRoot` 自身是 `session-maybe` 常驻外壳，持有 HeroShell、Workspace picker、composer stack 与 chain fallback 外框。
+- 每个实体 Session 只有一个 `SessionInputShell`（facade），随 session scope 创建和拆除；无 session 时不造 input machine。`ConversationRoot` 自身是 `session-maybe` 常驻外壳，持有 HeroShell、Workspace picker、composer stack 与 chain fallback 外框。它始终拥有同一个 scrollport 与 composer seat；Session 出现后，彼此独立的严格 session header 和 body outlet 只填入这些固定区域。
 - composer bar 是一个无条件渲染的 `session-maybe` slot entry：无 session 时同一个 InputBar 以惰性态渲染（machine face 缺席、`disabled` owner prop），`connectWorkspace` 返回 blank session 后同一实例转为 live——textarea DOM 在无 session → blank 切换及其后每次 phase 翻转中都不重建；`ConversationRoot`、Hero 与布局骨架全程保持。
-- ConversationRoot 的 Hero 判据是 `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || openState === 'loading'))`。首次 submit 同步进入 engaging，失败也保留 composer 与错误上下文，不退回 blank Hero；sidebar 的 blank 位只在 prompt 成功受理后翻 false。
+- ConversationRoot 的 Hero 判据是 `sessionId === undefined || (composerPhase === 'blank' && (openState === 'open' || summaryBlank === true))`：summary 已证实为空的 Session 在任何 open state 下都保持 Hero，未经证实的 Session 则在 loading 期间进入 settling。首次 submit 同步进入 engaging，失败也保留 composer 与错误上下文，不退回 blank Hero；sidebar 的 blank 位只在 prompt 成功受理后翻 false。
 - 发送统一在 hub defaultSink：乐观清稿后只走 `session.prompt` 且固定 `mode:'queue'`（Web UI 无 steer 入口；host 线缆上的 `mode:'steer'` 不经此 machine）；失败且 live draft 仍为空才回填，用户已经继续输入则不覆盖。不存在 Draft materialize 或 attach 事务。
 - blank Hero 改选 Workspace 时，外壳调用 `connectWorkspace`；目标 session 不同时把非空 draft 从当前 shell 搬到目标 shell，再 open 新 id，旧 blank session 留存但不再 current。
 - Notifier 双位契约：`dirty`（快照新鲜度，`ensureFresh` 拉取可清）与 `notifyPending`（通知欠账，只有 flush 清）各自独立——拉取不得吞推送，对象层推订阅者（watchTransaction）依赖这一保证。
@@ -93,9 +93,10 @@ skill/@subagent 引用不走占位符 + occurrence 身份链——pick 直接把
 
 ### slot 体系
 
-`conversation` 本身是 session-maybe；其会话内容与 composer 输入 slot 严格限定为 session，Hero Workspace picker 保持 root。子 slot 均由 ui-conversation 的 conversation 注册声明：
+`conversation` 本身是 session-maybe；其会话内容与 composer 输入 slot 严格限定为 session，Hero Workspace picker 保持 root。root 注册把 header outlet 渲染在常驻 scrollport 上方，把 body outlet 渲染在其内部、常驻 composer seat 之前。子 slot 均由 ui-conversation 的 conversation 注册声明：
 
-- `conversation.session`（single）——严格 session 的 header、view ring 与 chat store；session id 切换时重建。
+- `conversation.session.header`（single）——常驻 scrollport 上方严格 session 的 breadcrumb、view tab 与 header action。
+- `conversation.session`（single）——常驻 scrollport 内严格 session 的 view ring 与 draft mirror。header 和 body 共享同一个 session scope chat store；session id 切换时各自重建。
 - `conversation.composer.bar`（single）——InputBar 本体的 slot：InputBar 是真 slot entry（自有 slot 自注册），composer chain fallback 的内容；不做 chain entry——chain 单选举会在 takeover 时卸载它，破坏 textarea DOM 存活。
 - `conversation.input.overlay`——输入卡内浮层锚点；注册者 inject 按 slot sessionId 解析各自 per-session controller。
 - `conversation.input.dock`——输入上方堆叠条（QueueDock 的队列只读列表落此），order 定序。
@@ -128,7 +129,7 @@ skill/@subagent 引用不走占位符 + occurrence 身份链——pick 直接把
 
 ## 后果
 
-- 一个常驻 conversation 外壳承接 no-session/blank/active：无 session → blank 只保证大框架 React identity，允许 disabled textarea 替换为严格 InputBar；同一 blank session → engaging/active 保持 InputBar 与 textarea。EmptyState 与受控 intent 链（`sessions.updateIntent`/`updatePendingPrompt`/`workspaces.sendSession`）随最后消费者一并删除。
+- 一个常驻 conversation 外壳承接 no-session/blank/active：无 session → blank 保持 ConversationRoot、Hero、root scope Workspace picker、scrollport、composer seat、InputBar 与 textarea；只有严格 session header 和 body outlet 开始承载内容。同一 blank session → engaging/active 也保持 InputBar 与 textarea。EmptyState 与受控 intent 链（`sessions.updateIntent`/`updatePendingPrompt`/`workspaces.sendSession`）随最后消费者一并删除。
 - 输入面对命令零知识 + 可选依赖：无命令包时纯输入可用；`@` 引用与 skill 引用免费复用同一菜单/pick 管线。代价是空格/回车裁决是逐 source 轮询协议，其应答语义（同步/异步、undefined 含义）为冻结契约。
 - 提交事务化（attempt seq + 漂移守卫）使晚到结果回灌、会话切换、concurrent 重放三类缺陷结构性不可能，由矩阵测试钉住。
 - 已知欠账：chip 跨刷新保真（可复用粘贴匹配）未立项；subagent 引用的模型表示待业务立项。

.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.md
-2026-07-27-dispose-ladder-to-consumer.md: 97b551ff509e3b424f6bf5725939cf54acc961a7
-2026-07-27-dispose-ladder-to-consumer.zh.md: 7fff744e64109549a65d4f5bb17ff2d6ddfc6888
+2026-07-27-dispose-ladder-to-consumer.md: e9af88e8e7ef962213a74e96a249241cbe8d5994
+2026-07-27-dispose-ladder-to-consumer.zh.md: 89f8e107c56d42787c59bc6f8fa8fc7b3ef73208

.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.md

@@ -10,7 +10,7 @@ English | [中文](2026-07-27-dispose-ladder-to-consumer.zh.md)
 
 ## Decision
 
-The ladder moves to its one consumer. `dsh-subagent-acp` owns `disposeAcpChild(child, eofGraceMs, graceMs)`, built entirely on the seam's public verbs: close `stdin`, bound a `waitForExit` on `eofGraceMs`, then `terminate()` (whose SIGTERM→spec-grace→SIGKILL escalation already encodes the signal tiers), then a final bounded whole-tree wait that throws if survivors remain. The seam keeps `kill`/`terminate`/`waitForExit` — mechanisms, not policy — and `waitForExit(signal?)` is exactly the quiescence probe a consumer ladder needs to hold each tier on real tree exit. `dsh-subprocess-local` drops its `dsh-timeout` dependency; the seam's handle loses one method and one exported interface.
+The ladder moves to its one consumer. `dsh-subagent-acp` owns `disposeAcpChild(child, eofGraceMs)`, built entirely on the seam's public verbs: close `stdin`, bound a `waitForExit` on `eofGraceMs`, then call `terminate()`, whose SIGTERM→spec-grace→SIGKILL escalation already owns the signal timer, and await an unbounded `waitForExit()` for the subprocess owner's whole-tree exit proof. The seam keeps `kill`/`terminate`/`waitForExit` — mechanisms, not policy — and `waitForExit(signal?)` is exactly the quiescence probe a consumer ladder needs to hold the cooperative tier on real tree exit without deriving another timer from the termination grace. The seam's handle loses one method and one exported interface.
 
 ## Alternatives considered
 
@@ -20,4 +20,4 @@ The ladder moves to its one consumer. `dsh-subagent-acp` owns `disposeAcpChild(c
 
 ## Consequences
 
-Bought: the seam is one method and one type smaller; implementations owe four verbs and no teardown policy; `dsh-subprocess-local` loses a dependency; the ladder's tier windows live beside the config fields that tune them. Cost: a future backend wanting EOF-first teardown writes ~20 lines against the verbs (or lifts the ACP helper); the ladder's tier-tier tests moved from the seam suite to the ACP suite, and the seam suite pins the verbs the ladder composes (bounded `waitForExit` false-then-true across an escalation) instead of the composed policy.
+Bought: the seam is one method and one type smaller; implementations owe four verbs and no teardown policy; the cooperative EOF window lives beside the ACP config field that tunes it, while the subprocess owner alone owns the termination window and final join. Cost: a future backend wanting EOF-first teardown writes ~20 lines against the verbs (or lifts the ACP helper); the ladder's tier tests live in the ACP suite, and the seam suite pins the verbs the ladder composes (bounded `waitForExit` false before escalation and an unbounded whole-tree join after it) instead of the composed policy.

.agents/notes/implemented/architecture/2026-07-27-dispose-ladder-to-consumer.zh.md

@@ -10,7 +10,7 @@ Status: implemented
 
 ## 决策
 
-阶梯移入其唯一消费方。`dsh-subagent-acp` 拥有 `disposeAcpChild(child, eofGraceMs, graceMs)`，完全构建在 seam 的公开动词之上：关闭 `stdin`，以 `eofGraceMs` 约束一次 `waitForExit`，随后 `terminate()`（其 SIGTERM→spec 宽限期→SIGKILL 升级已编码了信号层级），最后进行有界的整树等待，若仍有存活进程则抛出。seam 保留 `kill`／`terminate`／`waitForExit`——机制而非策略——而 `waitForExit(signal?)` 恰是消费方阶梯在每一层确认进程树真正退出所需的完全停稳探针。`dsh-subprocess-local` 卸下 `dsh-timeout` 依赖；seam 的句柄少了一个方法和一个导出接口。
+阶梯移入其唯一消费方。`dsh-subagent-acp` 拥有 `disposeAcpChild(child, eofGraceMs)`，完全构建在 seam 的公开动词之上：关闭 `stdin`，以 `eofGraceMs` 约束一次 `waitForExit`，随后调用 `terminate()`（其 SIGTERM→spec 宽限期→SIGKILL 升级已拥有信号定时器），再无界等待 `waitForExit()`，由子进程责任方证明整棵进程树已经退出。seam 保留 `kill`／`terminate`／`waitForExit`——机制而非策略——而 `waitForExit(signal?)` 恰是消费方阶梯在协作层确认进程树真正退出所需的停稳探针，无需从终止宽限期再派生一个定时器。seam 的句柄少了一个方法和一个导出接口。
 
 ## 曾考虑的替代方案
 
@@ -20,4 +20,4 @@ Status: implemented
 
 ## 后果
 
-换来的是：seam 少了一个方法和一个类型；实现只需提供四个动词，无需提供拆卸策略；`dsh-subprocess-local` 少了一个依赖；阶梯的层级时间窗与调节它们的配置字段住在一起。代价：未来想要 EOF 打头拆卸的后端需针对这些动词写约 20 行（或直接搬 ACP 的辅助函数）；阶梯的层级测试从 seam 套件移入 ACP 套件，seam 套件转而钉住阶梯所组合的动词（升级前后有界 `waitForExit` 先假后真），而非组合后的策略。
+买到的：seam 少了一个方法和一个类型；实现只欠四个动词，不欠拆卸策略；协作式 EOF 时间窗与调节它的 ACP 配置字段住在一起，而终止时间窗与最终的整树退出等待仅由子进程责任方拥有。代价：未来想要 EOF 打头拆卸的后端需针对这些动词写约 20 行（或直接搬 ACP 的辅助函数）；阶梯的层级测试位于 ACP 套件，seam 套件转而钉住阶梯所组合的动词（升级前有界 `waitForExit` 返回假，升级后无界等待整棵进程树退出），而非组合后的策略。

.agents/notes/implemented/architecture/2026-08-03-pi-ai-declared-provider-catalog.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-03-pi-ai-declared-provider-catalog.md
+2026-08-03-pi-ai-declared-provider-catalog.md: d75b6bdb91d60026636bf320f8c6625590849a41
+2026-08-03-pi-ai-declared-provider-catalog.zh.md: f8dba9900b1a7a3abcb16c70a35cc18f0c44219f

.agents/notes/implemented/architecture/2026-08-03-pi-ai-declared-provider-catalog.md

@@ -0,0 +1,67 @@
+# Agent Note: pi-ai routes are declared providers, not catalog lookups
+
+Status: implemented
+
+English | [中文](2026-08-03-pi-ai-declared-provider-catalog.zh.md)
+
+## Problem
+
+`dsh-llm-pi-ai` treated the pi-ai package's generated catalog as the boundary of what could be configured. A route key had to name an installed provider (`resolveProfiles` rejected anything else), model listing returned `getBuiltinModels(provider)` verbatim, and request-time model resolution looked the id up in that same catalog and overrode only `baseURL`. Three consequences followed, and all three were dead ends rather than gaps: an OpenAI-compatible gateway, a self-hosted server, or a provider newer than the installed catalog could not be configured at all; a model the catalog had not caught up with failed with `UNKNOWN_MODEL` even against a correct endpoint; and a model's context window and output cap were whatever the pinned pi-ai release said, so a deployment could neither correct a stale value nor supply one for a model pi-ai had never described. Upgrading the package was the only way to move any of it.
+
+The adapter also streamed through `streamSimple` from `@earendil-works/pi-ai/compat`, an entry point whose own module documentation declares it a temporary compatibility surface — its catalog reads are `@deprecated`, and it is deleted when pi-ai finishes its `ModelManager` migration. The three configuration limits and the deprecated dependency have the same fix, because pi-ai's supported runtime (`createModels()` / `createProvider()`) is built around a provider being *declared* rather than looked up.
+
+## Decision
+
+A provider route is a **declaration**, and the installed catalog is its default. `resolveProfiles` no longer checks route keys against `getBuiltinProviders()`. Instead each route resolves to a materialized model list plus the pi-ai `Provider` that serves it:
+
+- `catalog.ts` merges the installed catalog under the profile's own entries. A profile's `models` list *replaces* the route's catalog (an absent or empty list serves it unchanged), and each entry defaults its unset fields from the installed model of the same `id`. Only the fields the harness consumes are configurable — `id`, `name`, `contextWindow`, `maxTokens`. Pricing and input modalities are absent from the surface because nothing reads them: `replay.ts` zeroes pi-ai's cost metadata and `context.ts` keeps only text blocks. Reasoning is absent for a different reason: a bare capability flag would make pi-ai advertise effort levels with no `thinkingLevelMap` to spell them, so it rides the installed entry or is absent. Materialization spreads the installed entry and overrides those four fields, rather than enumerating the result: an enumerated rebuild silently drops every `Model` field this package does not model, which is how `headers` went missing from an nvidia route once already.
+- `provider.ts` builds the route's `Provider`. A catalog route that keeps its catalog protocol **reuses** the installed provider with `getModels()` replaced; every other route is built by `createProvider()` over a protocol table whose entries are the same `@earendil-works/pi-ai/api/*.lazy` factories pi-ai's own provider factories use. That table is narrower than pi-ai's full API set on purpose — it holds only protocols a profile can completely describe with a key, an endpoint, and headers, so Bedrock (SigV4 plus a region), Vertex (project, location, ADC), Azure (provider environment plus an api-version), and Codex (OAuth) are absent rather than offered as routes that cannot authenticate. Catalog routes still reach them through their own provider; only an explicit override is refused.
+- `adapter.ts` turns each resolution into an **immutable snapshot** — the profiles plus a `createModels()` collection holding those providers — and every operation captures a whole snapshot before its first `await`.
+- A model's **explicitly configured** `maxTokens` becomes the seam's `defaultMaxTokens`. The value inherited from the installed catalog does not: pi-ai requires `Model.maxTokens` as the model's output *capability*, while `defaultMaxTokens` is a cap the deployment chose to send on requests that name none, and materializing the former as the latter would start capping every request at a number nobody picked.
+
+### Snapshots, not a shared collection
+
+`Models.streamSimple()` resolves its provider lazily, when the returned stream is first consumed — which is after the adapter has awaited the route's credential. A single collection mutated in place would therefore let a request that started under one configuration finish under another, or fail on a provider that no longer exists, even though `llm.prepareCall()` already froze that step's config and captured its adapter registration. A configuration change builds a *new* collection and leaves the one in use alone, so the seam's per-step freeze holds all the way down: switching models mid-reply takes effect on the next step, never inside the one in flight.
+
+### The directory replaces atomically
+
+The configurable-provider directory follows the profiles, so it changes whenever a declared route appears or leaves. Withdrawing the old registration and making a new one cannot express that: a candidate set the registry refuses — a profile keyed `deepseek-official`, which `llm-deepseek` already declares — would leave this plugin's whole directory withdrawn and the Models page empty, silently, because the settings-change callback contains the failure. `registerConfigurableProviders` therefore returns a handle carrying `replace(entries)` with the same validate-the-candidate-set-first atomicity `registerAdapter` has, and the plugin uses it. A refused swap costs a diagnostic; the previous entries keep serving.
+
+Resolution fails loud and names the route and model at fault: a model the catalog does not describe falls back to the route's own `defaultContextWindow`/`defaultMaxTokens`, so a listing that discloses nothing but ids still yields a serviceable route; a route the catalog does not ship needs `api`, `baseURL`, and a non-empty `models` list. Because the built `Provider` is part of the resolution result, a protocol or model error keeps the last good route set serving, exactly as a bad settings snapshot already did.
+
+The configurable-provider directory is now the installed catalog **joined with** every route the current profiles declare, re-registered when that set changes. Without the join a hand-declared route would have no settings address and no configuration surface could show or edit it.
+
+### A capability whose only level does nothing is reported unavailable
+
+pi-ai reports a model with no reasoning metadata as supporting the single level `off`, and the adapter used to pass that straight through. It reaches the seam as a one-item effort list, which every surface renders as a picker holding one selectable control — and that control is a lie: `off` becomes an *omitted* reasoning option at dispatch, byte-for-byte the request that naming no effort already produces. A provider whose own default is to think keeps thinking while the surface shows `off` selected.
+
+`reasoningInfo` therefore omits the seam's `reasoning` field whenever `model.reasoning` is falsy. The condition is the model's own metadata, not where the model came from, so this covers every hand-declared model **and** the 251 installed-catalog models pi-ai marks as non-reasoning. Those previously offered the lone `off`; they now offer nothing, and the surface shows the provider default alone. Models that do carry reasoning metadata are untouched — their level list still crosses the seam unfiltered, `off` included, because there it selects between real alternatives.
+
+### Credentials stay outside pi-ai
+
+pi-ai's `Models` carries its own credential concept — a `CredentialStore` keyed by provider id, with `envApiKeyAuth` resolving `credential.key ?? env(VAR)`. Adopting it would have created a second credential source of truth beside `ctx.credentials` and, worse, reintroduced the ambient fallback the harness deliberately forbids: a named-but-missing `apiKeyEnv` must fail with `MISSING_CREDENTIAL` rather than authenticate with whatever unrelated key the environment holds.
+
+`ModelsImpl.applyAuth` honours `options.apiKey` as the request's key, but only through a provider that declares an api-key method: `resolveProviderAuth` short-circuits to that method when the override is present, and otherwise falls through to the credential store and then to ambient discovery, returning nothing — and so failing the request with `Provider is not configured` — when the provider has no api-key method at all. The harness therefore resolves the route's key through its own seam, as before, and passes the result as the request's `apiKey`; the collection is constructed with no credential store.
+
+A route's auth follows from that. A catalog route keeps the installed provider's own `auth`, which preserves provider-native ambient discovery for a profile naming no credential, and keeps it through an `api` override too: which environment a provider reads is a property of the provider, not of the wire format its models speak. The exception is a catalog provider with no api-key method — `openai-codex` authenticates through OAuth alone — where a profile that names a credential also gets the harness method beside the provider's own, because otherwise its configured key would be refused before any request went out. A keyless profile on such a route adds nothing and keeps the honest refusal: this adapter holds no OAuth store to resolve through. A hand-declared route gets a harness-owned `ApiKeyAuth` that reports configured-but-keyless rather than unconfigured, leaving the requirement to the protocol — which is where it lives: pi-ai's OpenAI-compatible implementation still demands a key or an `Authorization` header, and says so itself.
+
+## Alternatives considered
+
+- **Keep `createProvider()` but skip the `Models` collection**, streaming through `provider.streamSimple(model, ctx, {apiKey})`. Smallest diff and the credential path is untouched, but `createProvider`'s `auth` is a required field that this path never invokes — a required-by-signature implementation with no caller. It also leaves `refreshModels` needing a hand-built `RefreshModelsContext`, and keeps the adapter off the runtime pi-ai actually supports.
+- **Reuse the installed provider for catalog routes and `createProvider()` only for declared ones**, with no shared resolution. Zero risk to catalog behavior, but catalog materialization, endpoint override, and per-model configuration would each exist twice, and a catalog route that repoints its protocol would have to jump paths mid-resolution. The chosen split confines the asymmetry to provider construction, where it is forced by pi-ai not exposing a built provider's API implementations.
+- **Rebuild every route through `createProvider()`**, including catalog ones. Fully symmetric, but a built `Provider` does not expose its `api`, so the protocol table would become the ceiling on which providers work — Bedrock loads its Smithy module through a separate entry point and would silently stop working.
+- **Expose pi-ai's whole `Model` shape** (cost, input modalities, `thinkingLevelMap`, `compat`). Maximum configurability, but no current consumer reads those fields, so a configured price or modality would change nothing while reading as supported.
+
+- **Keep one mutable `Models` collection and re-sync it.** Fewer allocations, and correct for every operation that resolves synchronously. It is exactly wrong for the one that does not: `stream()` awaits a credential between capturing its model and dispatching it.
+- **Simulate an atomic directory swap with dispose-then-register.** No seam change, and it works whenever the new set is valid — which is the case that never needed atomicity.
+- **A runtime dynamic catalog** — `fetchModels` plus `ModelsStore`, refreshed in the background. Rejected for this change: it makes the model list external mutable state needing cache, invalidation, and an offline path, and the product need is a one-shot discovery action whose result the user adopts into `settings.yaml`. That action belongs to the configuration surface and is deferred with it; `settings.yaml` stays the single source of truth for what a route serves.
+
+## Consequences
+
+Configuring a provider no longer depends on a pi-ai release. A gateway, a self-hosted server, or a model newer than the pinned catalog is a `settings.yaml` edit, and a stale context window can be corrected in place. The deprecated `/compat` import is gone, so pi-ai deleting it is no longer a breaking event. `defaultMaxTokens` now flows from configuration when a deployment states one, without inventing a cap from catalog metadata.
+
+What it costs: `settings.yaml` grows for a declared route, because it must state its endpoint, protocol, and model ids. `api` applies to a whole route, so a mixed-protocol catalog route cannot host a model of the other protocol — splitting it across two route keys is the workaround. Nothing queries a provider's `/models`, so a model list is only as current as its last edit. Reported error shape shifts in one case: a route whose auth resolves to nothing now surfaces pi-ai's own diagnostic as an error `finish` chunk before any network call, where the previous adapter sent a keyless request and surfaced the provider's 401.
+
+## Testing
+
+`tests/catalog.spec.ts` covers the contract end to end against local mock servers: a hand-declared route streaming to its own endpoint with its own credential, its appearance in the configurable-provider directory, per-model overrides defaulting from the installed catalog, a model added to a catalog route, protocol repointing with and without an endpoint override, catalog-only metadata surviving an override, the keyless posture and its `Authorization`-header workaround, an OAuth-only catalog route authenticating with the key its profile names while a keyless one stays unconfigured, a repointed route keeping its catalog auth, and every resolution failure that names a route or model. `tests/catalog.spec.ts` also pins the snapshot and directory contracts: an in-flight request whose route set changes during its credential await still reaches the endpoint it resolved against, the next request picks up the new one, a colliding declared route leaves the directory whole, and a declared route's entry appears and leaves with its profile. `packages/llm/llm/tests/topology.spec.ts` covers `replace` — refusing a candidate another registration owns while keeping the current set, accepting a swap over its own entries, allowing an empty set, and failing after disposal. `tests/sdk-options.spec.ts` re-targets the SDK boundary from the removed `/compat` import to the protocol table's lazy api module, which also pins that a setup failure arrives as a terminal error chunk rather than a throw. The twin's [design-verification role](2026-06-13-twin-llm-adapters.md) is unchanged.

.agents/notes/implemented/architecture/2026-08-03-pi-ai-declared-provider-catalog.zh.md

@@ -0,0 +1,67 @@
+# Agent Note: pi-ai 路由是被声明的提供方，而不是 catalog 查表
+
+Status: implemented
+
+[English](2026-08-03-pi-ai-declared-provider-catalog.md) | 中文
+
+## Problem
+
+`dsh-llm-pi-ai` 把 pi-ai 包生成的 catalog 当成了可配置范围的边界。路由键必须点名一个已安装提供方（`resolveProfiles` 拒绝其余一切），模型列举原样返回 `getBuiltinModels(provider)`，请求期的模型解析又在同一份 catalog 里查这个 id、且只覆盖 `baseURL`。由此产生三个后果，而且三个都是死路而非缺口：OpenAI 兼容网关、自建服务，或比已安装 catalog 更新的提供方，根本无法配置；catalog 尚未跟上的模型即便端点正确也会以 `UNKNOWN_MODEL` 失败；模型的上下文窗口与输出上限完全由锁定的 pi-ai 版本决定，部署既无法更正过期值，也无法为 pi-ai 从未描述过的模型补上。要动其中任何一条，只能升级依赖。
+
+适配器还经 `@earendil-works/pi-ai/compat` 的 `streamSimple` 发起流式请求，而该入口自己的模块文档声明它是临时兼容面——其 catalog 读取标了 `@deprecated`，并会在 pi-ai 完成 `ModelManager` 迁移时被删除。这三条配置限制与这个废弃依赖的解法是同一个，因为 pi-ai 受支持的运行时（`createModels()` / `createProvider()`）正是围绕「提供方是被*声明*出来的，而非查出来的」建立的。
+
+## Decision
+
+提供方路由是一份**声明**，已安装 catalog 是它的默认值。`resolveProfiles` 不再拿路由键去核对 `getBuiltinProviders()`，而是把每条路由解析成一份物化模型列表，外加服务它的 pi-ai `Provider`：
+
+- `catalog.ts` 把已安装 catalog 合并到 profile 自身条目之下。profile 的 `models` 列表*替换*该路由的 catalog（列表缺席或为空则原样服务），每个条目从同 `id` 的已安装模型继承自身未设置的字段。只有 harness 会消费的字段可配置——`id`、`name`、`contextWindow`、`maxTokens`。定价与输入模态不出现在配置面，因为没有任何读取方：`replay.ts` 把 pi-ai 的成本元数据清零，`context.ts` 只保留文本块。推理缺席则是另一个理由：一个孤立的能力布尔量会让 pi-ai 公布出没有 `thinkingLevelMap` 可供拼写的档位，因此它沿用已安装条目或直接缺席。物化时以已安装条目铺底、再覆盖那四个字段，而不是逐字段枚举结果：枚举式重建会静默丢弃本包未建模的每一个 `Model` 字段——`headers` 就是这样从某条 nvidia 路由上消失过一次。
+- `provider.ts` 构造路由的 `Provider`。保持 catalog 协议不变的 catalog 路由会**复用**已安装提供方，只替换 `getModels()`；其余路由都由 `createProvider()` 基于一张协议表构造，表中条目正是 pi-ai 自己的提供方工厂所用的 `@earendil-works/pi-ai/api/*.lazy` factory。该表刻意窄于 pi-ai 的完整 API 集合——只保留 profile 能用密钥、端点与标头完整描述的协议，因此 Bedrock（SigV4 加 region）、Vertex（project、location、ADC）、Azure（提供方环境加 api-version）与 Codex（OAuth）不在其中，而不是被当作无法认证的路由提供出去。catalog 路由仍可经自己的 provider 抵达它们；被拒的只有显式覆盖。
+- `adapter.ts` 把每次解析变成一份**不可变快照**——profiles 加上持有这些 provider 的 `createModels()` 集合——每个操作都在自己第一个 `await` 之前整体捕获一份。
+- 模型**显式配置**的 `maxTokens` 会成为 seam 的 `defaultMaxTokens`；从已安装 catalog 继承来的那份不会：pi-ai 要求 `Model.maxTokens` 表示模型的输出**能力**，而 `defaultMaxTokens` 是部署选定、发给未点名上限的请求的那个值，把前者物化成后者会让每个请求都被一个无人选择的数字封顶。
+
+### 快照，而不是共享集合
+
+`Models.streamSimple()` 惰性解析 provider——在返回的流首次被消费时，而那已在适配器 await 路由凭据之后。因此就地改动的单一集合，会让一个在旧配置下开始的请求在新配置下结束，或者撞上一个已不存在的 provider，尽管 `llm.prepareCall()` 早已冻结了该步的 config 并捕获了其适配器注册。配置变化改为构造**新**集合，正在被使用的那个原封不动，于是 seam 的每步冻结得以贯通到底：回复途中切换模型在下一步生效，绝不影响在途的那一步。
+
+### 目录原子替换
+
+可配置提供方目录跟随 profiles，因此每当一条声明路由出现或离开它都会变化。「撤销旧注册再新建一个」表达不了这件事：注册表拒绝的候选集合——比如一份键为 `deepseek-official` 的 profile，而 `llm-deepseek` 已声明了它——会让本插件的整个目录被撤走、Models 页变空，而且是静默的，因为 settings 变更回调把失败容住了。因此 `registerConfigurableProviders` 改为返回带 `replace(entries)` 的句柄，其「候选集先整体校验」的原子性与 `registerAdapter` 相同，插件改用它。被拒的替换只付出一条诊断；先前的条目继续服务。
+
+解析失败得响亮，并点名出问题的路由与模型：catalog 未描述的模型会回落到该路由自己的 `defaultContextWindow`／`defaultMaxTokens`，因此只公布 id 的列表也能得到可服务的路由；catalog 未提供的路由需要 `api`、`baseURL` 和非空的 `models` 列表。由于构造出的 `Provider` 是解析结果的一部分，协议或模型出错时最后可用的路由集合会继续服务——与此前坏的 settings 快照的行为完全一致。
+
+可配置提供方目录现在是已安装 catalog **与**当前 profile 声明的每条路由的并集，并在该集合变化时重新登记。没有这个并集，手工声明的路由就没有 settings 地址，任何配置界面都无法展示或编辑它。
+
+### 唯一档位什么也做不到的能力，报告为不可用
+
+pi-ai 把没有推理元数据的模型报告为只支持 `off` 一档，而适配器此前原样透传。它抵达 seam 时是一个单元素的 effort 列表，任何界面都会把它渲染成一个只有一项可选控件的选择器——而这个控件在撒谎：`off` 在派发时变成被*省略*的 reasoning 选项，与「不点名任何档位」产出的请求逐字节相同。自身默认就在思考的提供方会继续思考，界面却显示 `off` 已选中。
+
+因此只要 `model.reasoning` 为假，`reasoningInfo` 就省略 seam 的 `reasoning` 字段。判据是模型自身的元数据，而非模型的来源，所以它覆盖每一个手工声明的模型**以及** pi-ai 标记为不具备推理能力的那 251 个已安装 catalog 模型。它们此前提供那个孤零零的 `off`，现在什么也不提供，界面只剩提供方默认。携带推理元数据的模型不受影响——其档位列表仍不经筛选地穿过 seam、`off` 也在内，因为在那里它是在真实备选之间做选择。
+
+### 凭据留在 pi-ai 之外
+
+pi-ai 的 `Models` 自带一套凭据概念——按提供方 id 索引的 `CredentialStore`，配合 `envApiKeyAuth` 解析 `credential.key ?? env(VAR)`。采用它会在 `ctx.credentials` 之外制造第二个凭据事实源，更糟的是会把 harness 明确禁止的环境回落重新引进来：点名了却取不到的 `apiKeyEnv` 必须以 `MISSING_CREDENTIAL` 失败，而不是用环境里恰好持有的某个无关密钥完成认证。
+
+`ModelsImpl.applyAuth` 会把 `options.apiKey` 当作该请求的密钥，但这条路必须经由一个声明了 api-key 方法的提供方：`resolveProviderAuth` 在覆盖存在时短路到该方法，否则依次落到凭据存储与环境发现；若提供方压根没有 api-key 方法，它返回空，请求随即以 `Provider is not configured` 失败。因此 harness 一如既往经自身 seam 解析路由密钥，并把结果作为请求的 `apiKey` 传入；该集合构造时不带任何凭据存储。
+
+路由的 auth 由此推出。catalog 路由保留已安装提供方自己的 `auth`，从而为不点名凭据的 profile 保住其提供方原生环境发现，且在 `api` 覆盖之下同样保留：提供方读哪个环境是提供方自身的属性，而非其模型所讲协议格式的属性。例外是没有 api-key 方法的 catalog 提供方——`openai-codex` 只走 OAuth——此时点名了凭据的 profile 会在提供方原有 auth 之外再获得 harness 的方法，否则它配置的密钥会在任何请求发出之前被拒。这类路由上不点名凭据的 profile 什么也不加、并保留那句诚实的拒绝：本适配器没有可供解析的 OAuth 存储。手工声明的路由则获得一个 harness 自有的 `ApiKeyAuth`，它报告「已配置但无密钥」而非「未配置」，把该要求留给协议——那才是它真正所在的位置：pi-ai 的 OpenAI 兼容实现仍要求密钥或 `Authorization` 标头，并且会自己说出来。
+
+## Alternatives considered
+
+- **保留 `createProvider()` 但不建 `Models` 集合**，改由 `provider.streamSimple(model, ctx, {apiKey})` 发起。改动最小且凭据路径原封不动，但 `createProvider` 的 `auth` 是必填字段，这条路上它永远不会被调用——一份因签名而必填、却没有调用方的实现。它还让 `refreshModels` 需要手工构造 `RefreshModelsContext`，并使适配器始终不在 pi-ai 真正支持的运行时上。
+- **catalog 路由复用已安装提供方，只有声明式路由走 `createProvider()`**，且两者不共享解析。对 catalog 行为零风险，但 catalog 物化、端点覆盖与每模型配置这三件事都要各写两遍，而改指协议的 catalog 路由还得在解析中途跳到另一条路径。已采纳的拆法把不对称收敛在提供方构造这一处——那里的不对称是 pi-ai 不暴露已构造提供方的 API 实现所强加的。
+- **让每条路由都经 `createProvider()` 重建**，包括 catalog 路由。完全对称，但已构造的 `Provider` 不暴露自己的 `api`，于是协议表会成为「哪些提供方能用」的天花板——Bedrock 经独立入口加载其 Smithy 模块，会因此静默失效。
+- **完整暴露 pi-ai 的 `Model` 形状**（成本、输入模态、`thinkingLevelMap`、`compat`）。可配置性最大，但这些字段当前没有任何读取方，因此配了价格或模态什么也不会改变，却看起来像是受支持的。
+
+- **保留单个可变 `Models` 集合并重新同步。** 分配更少，且对每个同步完成解析的操作都是正确的；唯独对那个不同步的操作恰恰是错的：`stream()` 会在捕获模型与派发模型之间 await 一次凭据。
+- **用「先 dispose 再注册」模拟目录原子替换。** 无需改 seam，且在新集合有效时确实可用——而那正是从不需要原子性的那种情形。
+- **运行时动态 catalog**——`fetchModels` 加 `ModelsStore`，后台刷新。本次变更拒绝：它把模型列表变成需要缓存、失效与离线路径的外部可变状态，而产品需求是一次性的发现动作、其结果由用户采纳进 `settings.yaml`。该动作属于配置界面，与之一并暂缓；`settings.yaml` 始终是「路由服务什么」的唯一事实源。
+
+## Consequences
+
+配置一个提供方不再取决于 pi-ai 的发布节奏。网关、自建服务，或比锁定 catalog 更新的模型，都是一次 `settings.yaml` 编辑，过期的上下文窗口也能就地更正。废弃的 `/compat` 导入已经消失，因此 pi-ai 删除它不再是破坏性事件。`defaultMaxTokens` 现在只在部署明确给出时才自配置流出，不会从 catalog 元数据里发明一个上限。
+
+代价是：声明式路由会让 `settings.yaml` 变长，因为它必须自报端点、协议与模型 id。`api` 作用于整条路由，因此混合协议的 catalog 路由无法承载另一种协议的模型——把它拆成两个路由键是变通办法。没有任何环节查询提供方的 `/models`，因此模型列表的新鲜度只到最近一次编辑为止。有一种情形下报错形状发生变化：auth 解析不出任何值的路由，现在会在任何网络调用之前把 pi-ai 自己的诊断作为错误 `finish` 分片呈现，而此前的适配器会发出无密钥请求并呈现提供方的 401。
+
+## Testing
+
+`tests/catalog.spec.ts` 针对本地 mock 服务器端到端覆盖该契约：手工声明的路由带着自己的凭据流向自己的端点、它在可配置提供方目录中的出现、每模型覆盖从已安装 catalog 继承默认值、向 catalog 路由添加模型、带与不带端点覆盖的协议改指、catalog 独有元数据在覆盖后存活、无密钥姿态及其 `Authorization` 标头变通、只走 OAuth 的 catalog 路由用 profile 点名的密钥完成认证而无密钥者保持未配置、改指协议的路由保留其 catalog auth，以及每一种点名路由或模型的解析失败。`tests/catalog.spec.ts` 还钉住了快照与目录两项契约：在途请求即便其路由集在 credential await 期间改变，仍抵达它解析时对应的端点；下一个请求取用新配置；冲突的声明路由让目录保持完好；声明路由的条目随其 profile 出现与离开。`packages/llm/llm/tests/topology.spec.ts` 覆盖 `replace`——拒绝他人已拥有的候选同时保住当前集合、接受对自身条目的替换、允许空集合，以及 dispose 之后失败。`tests/sdk-options.spec.ts` 把 SDK 边界从已移除的 `/compat` 导入改指到协议表的 lazy api 模块，同时钉住「setup 失败以终止性错误分片而非抛出的形式抵达」。twin 的[设计验证角色](2026-06-13-twin-llm-adapters.md)不变。

.agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.md
+2026-08-04-declaring-a-provider-from-the-models-page.md: 53996e488c467e00754837b83b7a33994d4813ee
+2026-08-04-declaring-a-provider-from-the-models-page.zh.md: fa61c48492eabf51f3d325078ceffa84ac52d12c

.agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.md

@@ -0,0 +1,43 @@
+# Agent Note: Declaring a provider from the Models page
+
+Status: implemented
+
+English | [中文](2026-08-04-declaring-a-provider-from-the-models-page.zh.md)
+
+## Problem
+
+The two layers below made a pi-ai route [a declaration](2026-08-03-pi-ai-declared-provider-catalog.md) and gave the host a way to [interrogate a draft endpoint](2026-08-04-draft-provider-endpoint-interrogation.md). Neither reached a person who does not edit YAML: the Models page still offered one API-key field per provider and a fold with a base URL, so adding a gateway meant opening `$DSH_HOME/settings.yaml` and knowing the profile shape, and correcting a stale context window meant the same. The capability existed and the surface did not expose it.
+
+Two things were missing, and they are not the same shape. Editing an existing route's models is a *field* on a card that already exists. Declaring a route is a *create*: the route id is being chosen, so until it is chosen there is no settings address to edit.
+
+## Decision
+
+The model list is a component shared by both flows; the create is its own card.
+
+`ModelListEditor` edits a profile's `models` array — one row per model with id, display name, context window, and output cap — and owns the fetch action. An empty list means "serve this route's built-in catalog", so a row is only ever added deliberately; clearing an optional field drops it rather than storing a value the schema would reject, and a capacity that is not a positive integer is not stored at all.
+
+Fetching asks about the endpoint **the form currently shows** — a base URL edited but unsaved, a key typed but unstored — so adding a provider is one pass instead of save-then-return. The reply opens a picker rather than being written: candidates already configured start unchecked, so adopting a selection never overwrites a capacity the user corrected. A provider that cannot be interrogated is a detour, not a dead end; the adapter's own message appears beside rows that stay editable by hand.
+
+`CustomProviderCard` declares a route pi-ai does not ship. It is a separate card because the route id is chosen here: one `settings.mutate` sets the whole profile at `providers.<route>`, and the key travels separately through `credentials.set` under the same `<ROUTE>_API_KEY` derivation an existing provider uses. The three facts a hand-declared route cannot default — endpoint, protocol, and at least one model — gate the create button, so a failure names the field while the user is still looking at it.
+
+The protocol choices come from the namespace's **own schema**, read through the settings descriptor the page already fetches (`providers.*.api` is a union of the adapter's `supportedProtocols()`). No new wire field, no constant in the client, and no way for the offered choices to drift from the accepted ones.
+
+## Alternatives considered
+
+**Declare a provider through `ProviderEditor` with extra fields.** One card instead of two, but the editor is addressed by `settingsPath`, and a route being named has no path yet. Recomputing the path per keystroke would remount the card and discard the draft; deferring it would mean the editor's whole write path no longer described what it was editing.
+
+**Add a wire field for the protocol list.** Explicit, and the obvious first instinct. But the settings schema already crosses the wire and already contains the union, so a second copy could disagree with the first — and the one the adapter enforces is the schema.
+
+**Fetch against the stored profile instead of the live form.** No key would leave the form for an unsaved provider. But the flow that needs fetching most is the one where nothing is stored yet, and a form whose endpoint was edited would quietly interrogate the old one.
+
+**Write adopted candidates straight into the list.** Fewer clicks, but a fetch would then overwrite capacities the user had corrected, and a listing that discloses only ids would replace real numbers with nothing.
+
+## Consequences
+
+A gateway, a self-hosted server, or a model newer than the installed catalog is now configurable without leaving the browser, and the endpoint itself supplies the model ids where it can. The page grew two components and one shared list editor; the editor card's pi-ai fold grew from two fields to a list.
+
+What it costs: only pi-ai routes can be hand-declared, because `llm-pi-ai` is the one namespace whose profiles describe a whole provider — a `llm-deepseek` route stays a composition fact. Interrogation reaches only OpenAI-compatible endpoints, so a gateway speaking another protocol reports that it cannot be asked and its models are typed in. And the page now holds a key in component state for the duration of a fetch, which is the same exposure `credentials.set` already has and no longer than the card lives.
+
+## Testing
+
+`packages/client/ui-models/tests/provider-form.spec.tsx` drives the rendered page over a scripted wire face: adding, editing, and removing rows; a cleared optional field leaving the profile and a non-integer capacity never entering it; the interrogation carrying the edited endpoint, the unsaved key, and the profile's protocol; the picker's default selection, toggling, cancel, and adopt-keeps-tuned-rows; the empty, refused, and rejected-transport paths; the create writing one profile plus its credential; every gate on the create button; and the read-only posture. `protocolChoices` is covered against a schema that declares the union and one that does not.

.agents/notes/implemented/architecture/2026-08-04-declaring-a-provider-from-the-models-page.zh.md

@@ -0,0 +1,43 @@
+# Agent Note: 在 Models 页上声明一个提供方
+
+Status: implemented
+
+[English](2026-08-04-declaring-a-provider-from-the-models-page.md) | 中文
+
+## Problem
+
+下面两层已经让 pi-ai 路由变成[一份声明](2026-08-03-pi-ai-declared-provider-catalog.md)，并给了 host [询问草稿端点](2026-08-04-draft-provider-endpoint-interrogation.md)的能力。但两者都没有抵达不编辑 YAML 的人：Models 页仍然只为每个提供方提供一个 API 密钥输入框和一个装着 API 地址的折叠区，因此接入一个网关意味着打开 `$DSH_HOME/settings.yaml` 并知道 profile 的形状，更正一个过期的上下文窗口也是如此。能力已经存在，界面却没有暴露它。
+
+缺的是两件事，而它们的形状并不相同。编辑既有路由的模型，是一张已经存在的卡片上的一个*字段*；声明一条路由则是一次*创建*：路由 id 正在此处被选定，而在选定之前根本没有可编辑的 settings 地址。
+
+## Decision
+
+模型列表是两条流程共用的组件；创建则是它自己的卡片。
+
+`ModelListEditor` 编辑 profile 的 `models` 数组——一行一个模型，含 id、显示名称、上下文窗口与输出上限——并持有获取动作。空列表意味着「使用该路由的内置 catalog」，因此每一行都只会被刻意添加；清空某个可选字段会丢弃它，而不是存入一个 schema 会拒绝的值，不是正整数的容量则根本不会被存下。
+
+获取会询问表单**当前显示**的端点——已修改但未保存的 API 地址、已键入但未存储的密钥——因此新增一个提供方是一趟走完，而不是「先保存再回来」。回复会打开一个选择框而不是直接写入：已配置过的候选默认不勾选，因此采纳一次选择绝不会覆盖用户已更正的容量。无法被询问的提供方只是绕路而非死路；适配器自己的消息会出现在各行旁边，而这些行仍可手工编辑。
+
+`CustomProviderCard` 声明 pi-ai 未提供的路由。它之所以是独立卡片，正因为路由 id 是在这里选定的：一次 `settings.mutate` 在 `providers.<route>` 上设置整个 profile，密钥则经 `credentials.set` 单独传递，使用与既有提供方相同的 `<ROUTE>_API_KEY` 派生。手工声明的路由无法默认的三件事——端点、协议、至少一个模型——会门控创建按钮，因此失败会在用户仍看着该字段时点名它。
+
+协议选项来自该 namespace **自己的 schema**，经页面本就会获取的 settings 描述符读出（`providers.*.api` 是适配器 `supportedProtocols()` 的一个 union）。没有新增协议字段，客户端里没有常量，提供的选项也无从与被接受的集合发生漂移。
+
+## Alternatives considered
+
+**在 `ProviderEditor` 上加字段来声明提供方。** 两张卡片变一张，但编辑器由 `settingsPath` 寻址，而正在被命名的路由还没有路径。逐次按键重算路径会让卡片重新挂载并丢掉草稿；推迟计算则意味着编辑器的整条写入路径不再描述它正在编辑的东西。
+
+**为协议列表新增一个协议字段。** 显式，也是最直觉的第一反应。但 settings schema 本来就会跨越协议层、本来就含有那个 union，因此第二份副本可能与第一份不一致——而适配器强制执行的是 schema 那一份。
+
+**针对已存 profile 而非实时表单发起获取。** 对尚未保存的提供方来说，密钥就不会离开表单。但最需要获取的恰恰是「什么都还没存」的那条流程，而端点已修改的表单会悄悄去询问旧地址。
+
+**把采纳的候选直接写进列表。** 点击更少，但一次获取就会覆盖用户已更正的容量，而只公布 id 的列表会把真实数字替换成空。
+
+## Consequences
+
+网关、自建服务，或比已安装 catalog 更新的模型，如今无需离开浏览器就能配置，而模型 id 在端点能提供时由端点自己给出。页面多了两个组件和一个共用的列表编辑器；编辑卡片的 pi-ai 折叠区从两个字段长成了一个列表。
+
+代价是：只有 pi-ai 路由可以手工声明，因为 `llm-pi-ai` 是唯一一个其 profile 描述整个提供方的 namespace——`llm-deepseek` 路由仍是组合面的事实。询问只覆盖 OpenAI 兼容端点，因此讲其他协议的网关会报告自己无法被询问，其模型需手工键入。另外，页面在一次获取期间会把密钥保存在组件状态里，这与 `credentials.set` 已有的暴露面相同，且不长于卡片的存活时间。
+
+## Testing
+
+`packages/client/ui-models/tests/provider-form.spec.tsx` 在脚本化的协议面之上驱动渲染后的页面：添加、编辑与移除行；被清空的可选字段离开 profile、非整数容量从不进入；询问携带已修改的端点、未保存的密钥，以及 profile 自身的协议；选择框的默认选中、勾选切换、取消，以及「采纳保留已调优的行」；空列表、被拒、传输被拒三条路径；创建写入一份 profile 加其凭据；创建按钮上的每一道门控；以及只读姿态。`protocolChoices` 针对「声明了该 union」与「没有声明」两种 schema 都有覆盖。

.agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.md
+2026-08-04-draft-provider-endpoint-interrogation.md: 65545098cd1063c40081481c1ac8f0afdb4fb390
+2026-08-04-draft-provider-endpoint-interrogation.zh.md: cb09042904f4ab1558c0c214d275a934234955ac

.agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.md

@@ -0,0 +1,50 @@
+# Agent Note: Interrogating a draft provider endpoint
+
+Status: implemented
+
+English | [中文](2026-08-04-draft-provider-endpoint-interrogation.zh.md)
+
+## Problem
+
+Once a pi-ai route became [a declaration rather than a catalog lookup](2026-08-03-pi-ai-declared-provider-catalog.md), a person adding an OpenAI-compatible gateway had to know its model ids before they could configure it. The adapter no longer constrains them to an installed catalog, which is the point, but it also means nothing tells the user what the endpoint actually serves — and most of these endpoints do publish that list at `GET /models`.
+
+The obvious answer, a dynamic runtime catalog refreshed in the background, was rejected with the layer below it: it makes a route's model list external mutable state needing a cache, an invalidation story, and an offline path, while the product need is narrower. What is needed is a *question asked once*, whose answer the user adopts into `settings.yaml` — so `settings.yaml` remains the only thing deciding what a route serves.
+
+The awkward part is that the question is about something that does not exist yet. The provider being added has no route, no stored profile, and no stored credential; the endpoint and key are values in a form the user is still typing. Every existing seam operation is keyed by a registered provider route, so none of them can carry this.
+
+## Decision
+
+Interrogation is keyed by **settings namespace**, not by provider route:
+
+- `ctx.llm.registerModelDiscovery(settingsNs, discover)` lets an adapter plugin offer to interrogate endpoints for the namespace it owns, and `ctx.llm.discoverModels(settingsNs, request)` asks. There is no way to enumerate which namespaces registered: a surface that cannot interrogate learns it from the refusal, and a list nothing consumed would be a required wire field doing nothing. The namespace is the right key because a configuration surface already holds it from the configurable-provider directory, and because a provider being added has no route to name.
+- `LlmModelDiscoveryRequest` carries the draft — an optional `provider`, an optional `baseURL`, an optional `api`, an optional `apiKey`, and a signal — and needs at least one of `provider` or `baseURL` to have anything to answer about. `provider` exists because a route the adapter already describes is answered from its own registry with no network call at all; only a route it does not describe reaches an endpoint. Nothing in this path writes settings or credentials. The one read is the credential of a route the request names: a configuration surface holds a redacted descriptor rather than the stored secret, so the draft's `apiKey` is present only while the user is typing one, and without that read an already-configured route would be interrogated unauthenticated and answer 401. The typed key wins, being the one under test.
+- `LlmDiscoveredModel` makes every field but `id` optional, because most listings disclose an id and nothing else. The reply is candidates, not a catalog: a surface adopting one still owes the capacities the adapter requires.
+- `llm.discoverModels` carries the same draft over the wire. Its `apiKey` is the third and last payload on which a secret may ride, alongside `settings.update`/`mutate` and `credentials.set`, and it is never stored or echoed back. It does ride the client's outgoing envelope like every other secret-bearing payload, where a `subscribeEnvelopes()` observer can see it; redacting that tap is a configuration-plane-wide change, not this method's to make alone. The method is loopback-only for a second reason besides the key: it makes the host issue a GET to a caller-chosen URL and reports the outcome, which is a probe an anonymous LAN caller must not have. Every refusal folds into `model-discovery-failed`, whose message is the adapter's own text and whose details name the endpoint asked but never the credential offered.
+
+`dsh-llm-pi-ai` implements the wire path as a plain `GET {baseURL}/models`, reading `openai-completions` and `openai-responses`: their `GET /models` shape with bearer auth is the one a gateway, a self-hosted server, and the official endpoints all agree on. Azure is excluded despite its OpenAI lineage — it authenticates with an `api-key` header and requires an `api-version` query — and Codex uses OAuth; both would have reported an authentication failure as a provider with no models. Every other protocol answers `DISCOVERY_UNSUPPORTED`, so the surface falls back to hand-entry rather than reporting a guessed response shape as an empty provider. `baseURL` is treated as a prefix rather than a URL to resolve against, so a deployment path such as `https://gateway.example/openai/v1` keeps its segments. The reply is read under a four-megabyte ceiling enforced on the bytes actually received — the endpoint is a URL the user typed, so a declared `content-length` is checked first as a courtesy but never trusted as the bound, matching `dsh-web-fetch`'s two-stage shape for its own caller-supplied URLs.
+
+### Why not pi-ai's own refresh machinery
+
+pi-ai supplies `createProvider({ fetchModels })` plus `Models.refresh()` and a `ModelsStore`, and the layer below already builds pi-ai `Provider` objects. Routing interrogation through them would have meant constructing a throwaway provider and collection per question, with a store whose entire purpose — persisting a catalog across runs — contradicts the decision that `settings.yaml` owns the catalog. It would also have bought nothing: **no built-in pi-ai provider implements `fetchModels`**, so the HTTP call and its response parsing are this package's code either way. A direct fetch says what is actually happening. The route's stored credential is resolved by the plugin's own per-request resolver, and only on the branch that reaches the network, so a catalog route answers without touching credentials and never fails over one the question did not need.
+
+## Alternatives considered
+
+**Key interrogation by provider route.** Symmetric with every other seam operation, and it would let the request omit the endpoint. But the case that motivates the feature — adding a provider — has no route, so the operation would only work for providers already configured, which are the ones that need it least.
+
+**Put the capability on `LlmAdapter`.** Adapters are reached through a route registration, so this has the same problem, plus it would make an adapter instance answer questions about endpoints it does not serve.
+
+**Have the host read the stored profile instead of accepting a draft.** No secret would cross the wire for an already-configured provider. But adding a provider would then require saving an unusable configuration first, and a form whose endpoint was edited but not yet saved would silently interrogate the old one. Accepting the draft keeps what the user sees and what is asked identical — with the credential as the one exception, because it is the one field a surface is never shown and so can never put in the draft.
+
+**Interrogate every pi-ai protocol.** Anthropic's listing happens to share OpenAI's envelope, and Google's does not. Supporting the ones that are easy would make coverage arbitrary and, worse, make a wrong guess at a response shape indistinguishable from a provider with no models. A protocol that says it cannot be interrogated sends the user to hand-entry, which is the documented fallback.
+
+**Buffer the reply with `response.text()` and check its length.** Simpler, but the bound would arrive after the bytes did, and the endpoint is whatever URL the user typed.
+
+## Consequences
+
+A person adding a gateway can ask it what it serves instead of hunting through its documentation, and the answer arrives as candidates they choose from rather than as configuration written behind their back. The seam gained a registry that is deliberately small: one offer per namespace, no storage, no lifecycle beyond the fiber.
+
+What it costs: the wire gained a third secret-carrying payload, so the configuration plane's write-only surface is now three methods rather than two. Discovery coverage is protocol-shaped rather than provider-shaped — an Anthropic-compatible gateway must be filled in by hand even though its listing would parse. And because nothing re-runs the question, a model list is still only as current as its last edit; that is the same trade the layer below made deliberately.
+
+## Testing
+
+`packages/llm/llm/tests/topology.spec.ts` covers the registry: one offer per namespace, disposal with the fiber, normalization that drops duplicate and unusable ids without inventing capacities, and the `NO_DISCOVERY`/`INVALID_DISCOVERY` refusals. `packages/llm/llm-pi-ai/tests/discovery.spec.ts` drives the probe against local HTTP servers — a listing with and without disclosed capacities, a preserved deployment path, an absent credential, a configured route supplying its own where the draft has none and a typed key winning over it, a catalog route answering without resolving one at all, dropped rows, 401/403 versus a server fault, a non-listing and a non-JSON body, an unreachable endpoint, caller cancellation, an unsupported protocol, and the size ceiling in both its declared-length and streamed forms. `packages/host/apiproxy/tests/api-proxy-config.spec.ts` covers the RPC over a real proxy: the draft reaching its namespace whole, absent fields staying absent, no namespace or credential being written, and a failure surfacing as `model-discovery-failed` with the credential absent from the serialized error.

.agents/notes/implemented/architecture/2026-08-04-draft-provider-endpoint-interrogation.zh.md

@@ -0,0 +1,50 @@
+# Agent Note: 询问草稿中的提供方端点
+
+Status: implemented
+
+[English](2026-08-04-draft-provider-endpoint-interrogation.md) | 中文
+
+## Problem
+
+当 pi-ai 路由变成[一份声明而非 catalog 查表](2026-08-03-pi-ai-declared-provider-catalog.md)之后，要接入一个 OpenAI 兼容网关的人，必须先知道它的模型 id 才能完成配置。适配器不再把人限制在已安装 catalog 里——这正是那次改动的目的——但也意味着没有任何东西告诉用户该端点究竟服务什么，而这类端点大多在 `GET /models` 上公布了这份列表。
+
+显而易见的答案——后台刷新的运行时动态 catalog——已随下层一并被拒绝：它会把路由的模型列表变成需要缓存、失效语义与离线路径的外部可变状态，而产品需求要窄得多。真正需要的是**只问一次**，其答案由用户采纳进 `settings.yaml`——从而让 `settings.yaml` 始终是唯一决定路由服务什么的东西。
+
+麻烦之处在于，被问的对象还不存在。正在新增的提供方没有路由、没有已存 profile、也没有已存凭据；端点与密钥都是用户尚在输入的表单值。而现有的每个 seam 操作都以已注册的提供方路由为键，因此没有一个能承载它。
+
+## Decision
+
+询问以 **settings namespace** 为键，而不是提供方路由：
+
+- `ctx.llm.registerModelDiscovery(settingsNs, discover)` 让适配器插件为自己拥有的 namespace 提供「询问端点」的能力，`ctx.llm.discoverModels(settingsNs, request)` 发起询问。没有任何办法枚举哪些 namespace 注册过：询问不了的界面会从那句拒绝里知道，而一份无人消费的列表只会变成一个什么都不做的必填协议字段。以 namespace 为键是对的，因为配置界面已经从可配置提供方目录里拿到了它，也因为正在新增的提供方没有路由可点名。
+- `LlmModelDiscoveryRequest` 携带草稿——可选的 `provider`、可选的 `baseURL`、可选的 `api`、可选的 `apiKey`，以及一个 signal——且 `provider` 与 `baseURL` 至少要有一个，才有东西可答。`provider` 之所以存在，是因为适配器已经描述过的路由直接由它自己的注册表作答、完全不联网；只有它未描述的路由才会抵达某个端点。这条路径不写 settings 与 credentials。唯一的读取是请求所点名路由的凭据：配置界面拿到的是脱敏描述符而非已存的机密，因此草稿里的 `apiKey` 只在用户正键入时才存在；没有这次读取，已配置好的路由就会被不带认证地询问，只换回一个 401。键入的密钥优先，因为那正是被测试的那一把。
+- `LlmDiscoveredModel` 除 `id` 外每个字段都可选，因为大多数列表只公布 id。回复是候选而非 catalog：采纳其中一条的界面仍要补上适配器所需的容量。
+- `llm.discoverModels` 把同一份草稿送过协议层。它的 `apiKey` 是 secret 可以搭乘的第三个、也是最后一个载荷（另两个是 `settings.update`/`mutate` 与 `credentials.set`），且绝不被存储或回显。它确实会像其他承载机密的载荷一样随客户端外发信封同行，`subscribeEnvelopes()` 观察者看得到；把那个抽头脱敏是整个配置面的改动，不该由这一个方法独自决定。除密钥之外它被钉在回环还有第二个理由：它让宿主向调用方选定的 URL 发起 GET 并回报结果，这是匿名 LAN 调用者不该拥有的探测能力。每一种拒绝都折叠为 `model-discovery-failed`，其消息是适配器自己的文本，details 点名被询问的端点，绝不点名所提供的凭据。
+
+`dsh-llm-pi-ai` 的实现只是一次朴素的 `GET {baseURL}/models`，且仅限 OpenAI 兼容协议。它们的列表形状是网关、自建服务与官方端点三方一致认可的那一种，而这正是该动作存在的场景。其余协议一律以 `DISCOVERY_UNSUPPORTED` 回答，让界面回退到手工填写，而不是把猜错的响应形状报成一个空提供方。`baseURL` 按前缀而非待解析 URL 处理，因此 `https://gateway.example/openai/v1` 这类部署路径会保留其路径段。回复在四兆字节上限下读取，且上限落在实际收到的字节上——端点是用户自己填的 URL，因此会先看声明的 `content-length` 作为善意提示，但绝不把它当作边界；这与 `dsh-web-fetch` 面对自己的调用方提供 URL 时所用的两段式形状一致。
+
+### 为什么不用 pi-ai 自己的 refresh 机制
+
+pi-ai 提供了 `createProvider({ fetchModels })` 加上 `Models.refresh()` 与 `ModelsStore`，而下层本来就在构造 pi-ai `Provider` 对象。把询问接到它们上面，意味着每问一次就要构造一个用完即弃的 provider 与集合，而那个 store 的全部目的——跨运行持久化 catalog——恰恰与「`settings.yaml` 拥有 catalog」的决定相抵触。而且它什么也换不来：**没有任何一个 pi-ai 内置 provider 实现了 `fetchModels`**，因此 HTTP 调用及其响应解析无论如何都是本包的代码。直接 fetch 才如实说出正在发生的事。路由已存的凭据由本插件自己那套逐请求解析器取出，且只在真正要联网的那条分支上进行，因此 catalog 路由作答时既不触碰凭据，也不会因为一把这次询问根本用不上的密钥而失败。
+
+## Alternatives considered
+
+**以提供方路由为键。** 与其他每个 seam 操作对称，也能让请求省去端点。但催生该功能的场景——新增提供方——没有路由，于是这个操作只对已配置好的提供方可用，而它们恰恰最不需要它。
+
+**把能力挂在 `LlmAdapter` 上。** 适配器要经由路由注册才能抵达，因此问题相同；而且这会让一个适配器实例去回答它并不服务的端点的问题。
+
+**让 host 读已存 profile，而不是接受草稿。** 对已配置好的提供方来说，不会有 secret 跨越协议层。但这样一来新增提供方就必须先保存一份不可用的配置，而端点已改却尚未保存的表单会静默地去询问旧地址。接受草稿让用户看见的与被询问的保持一致——凭据是唯一的例外，因为它是界面从不被展示、因而永远无法放进草稿的那个字段。
+
+**询问 pi-ai 的每一种协议。** Anthropic 的列表恰好与 OpenAI 共用同一层信封，而 Google 的不是。只支持容易的那几种会让覆盖范围变得任意；更糟的是，猜错的响应形状会与「该提供方没有模型」无法区分。一个明说自己无法被询问的协议，会把用户送去手工填写——那正是既定的回退路径。
+
+**用 `response.text()` 缓冲整个回复再判断长度。** 更简单，但上限会在字节已经到达之后才生效，而端点是用户随手填的任意 URL。
+
+## Consequences
+
+接入网关的人可以直接问它服务什么，而不必去翻它的文档；答案以候选形式抵达，由用户自己挑选，而不是被背着写进配置。seam 因此多了一个刻意保持很小的注册表：每个 namespace 一份、不存储、除 fiber 外没有生命周期。
+
+代价是：协议层多了第三个承载 secret 的载荷，配置面的只写接口从两个方法变成三个。发现能力按协议而非按提供方划分——一个 Anthropic 兼容网关即便其列表能被解析，也仍须手工填写。而且由于没有任何环节会重跑该询问，模型列表的新鲜度依旧只到最近一次编辑为止；这与下层刻意做出的取舍是同一个。
+
+## Testing
+
+`packages/llm/llm/tests/topology.spec.ts` 覆盖注册表：每个 namespace 一份、随 fiber dispose、丢弃重复与不可用 id 且不凭空补容量的归一化，以及 `NO_DISCOVERY`/`INVALID_DISCOVERY` 两种拒绝。`packages/llm/llm-pi-ai/tests/discovery.spec.ts` 针对本地 HTTP 服务器驱动探测——含与不含公布容量的列表、被保留的部署路径、无凭据、草稿没带密钥时已配置路由自行取用凭据且键入的密钥压过它、catalog 路由完全不解析凭据即作答、被丢弃的行、401/403 与服务器故障之别、非列表与非 JSON 响应、不可达端点、调用方取消、不支持的协议，以及尺寸上限的「声明长度」与「流式」两种形态。`packages/host/apiproxy/tests/api-proxy-config.spec.ts` 在真实 proxy 上覆盖该 RPC：草稿完整抵达其 namespace、缺席字段保持缺席、没有 namespace 或凭据被写入，以及失败以 `model-discovery-failed` 呈现且序列化后的错误里不含凭据。

.agents/notes/implemented/architecture/2026-08-05-profile-plugin-bundles.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-05-profile-plugin-bundles.md
+2026-08-05-profile-plugin-bundles.md: 11a8ac3d4005371ca9596ba237aaf42a8e770dee
+2026-08-05-profile-plugin-bundles.zh.md: 0e9ebf657ccb9d05967d90a935b356acf287a24c

.agents/notes/implemented/architecture/2026-08-05-profile-plugin-bundles.md

@@ -0,0 +1,33 @@
+# Agent Note: Profile plugin bundles replace the fixed surface overlays
+
+Status: implemented
+
+English | [中文](2026-08-05-profile-plugin-bundles.zh.md)
+
+## Problem
+
+The `dsh` launcher hardcoded its compositions: `base.cordis.yml` + `web.cordis.yml` shipped inside `apps/cli`, three bespoke entry modes (`--config`, `web`, `-p`) each with its own layer stack, and a single global personal overlay (`$DSH_HOME/config.yaml`). There was no way to install an out-of-tree plugin (a TUI, a provider pack) into a shipped surface without editing the repository, and no place where a third-party package could contribute a default composition.
+
+## Decision
+
+Everything becomes a **profile**: a directory `$DSH_HOME/profiles/<name>` with a `package.json` (pnpm-managed out-of-tree plugin `dependencies` plus the profile manifest `dsh.profile` with its ordered `bundles` layer list) and a user `cordis.patch.yml`. A **bundle** is an npm package declaring `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }`; the two manifest kinds live under distinct `dsh.profile` / `dsh.bundle` keys so a package.json states which role it plays. The tree composes over an empty root by applying each bundle's patch in `dsh.profile.bundles` order, then the user layer, then `--patch` overlays, then flag patches — one `applyEntryPatches` call, identical for boot, flag derivation, and `--dump-config`.
+
+The shipped compositions became bundles: `@deepseek-ai/dsh-base` (the former base rows as one insert), `@deepseek-ai/dsh-web-app` (the former web overlay plus a runtime glue plugin that owns what used to be launcher code — frontend-dist resolution, the web-surface prompt section, bash runtime variables, the URL line), and `@deepseek-ai/dsh-headless` (a one-shot runner plugin over base + web-app). `dsh web` stays as an alias for `--profile web` carrying the Web flag family; `dsh --profile headless "task"` replaces `-p`; `dsh --config` is removed (its uses migrate to `--patch`). `dsh plugin --profile <name> <args...>` is a thin pnpm forwarder that initializes the profile and reconciles `dsh.profile.bundles` after `add`/`remove` (a bundle-less package warns and stays a plain dependency).
+
+Resolution is two-anchored by construction: `dsh.profile.bundles` names resolve from the dsh installation first, then the profile directory — so in-box bundles always come from the same installation as the running `dsh` and pnpm never manages them — while bare plugin names in patch rows resolve through the profile directory's Node parent-walk into the maintained flat fallback `$DSH_HOME/profiles/node_modules` (one symlink per package the installation's app and bundles depend on, healed on every launch).
+
+Two supporting refactors: the webserver's built-in static dist serving became the single-owner **fallback seat** (`registerFallback`/`applyIndexTaps`), with the SPA server extracted to `@deepseek-ai/dsh-frontend-static` so the web bundle owns its dist as composition, not launcher code; and the personal-overlay machinery of the [dsh CLI personal-config decision](../feature/2026-07-20-dsh-cli-personal-config.md) (`loadPersonalPatches`, `$DSH_HOME/config.yaml`) was retargeted to the per-profile and home-level `cordis.patch.yml` layers (`loadOptionalPatches`, `watchUserPatches` taking a filename), superseding that note's entry modes and file location while keeping its Harness-home root, patch semantics, and fail-loud parsing.
+
+## Alternatives considered
+
+- **Dependency-scan plus partial `patchOrder`** (the original sketch): scanning `dependencies` for bundles and ordering unlisted ones alphabetically has two sources of truth and an implicit tie-break; one explicit ordered `dsh.profile.bundles` list is smaller and fully deterministic. A raw `pnpm add` inside the profile installs a library without activating any patch — explicit, no spooky scan.
+- **`link:` entries for in-box bundles**: pnpm cannot version, install, or update a `link:` into the installation, it embeds a machine path in a user file, and it breaks when the installation moves. The two-anchor resolution plus healed symlink fallback gives the same guarantee ("bundles come from the installation") without ceremony.
+- **A pre-boot `context` module in the bundle manifest** for boot-time values (dist path, flag facts): rejected in favor of pure plugins — the glue is ordinary rows the launcher patches, so the composition stays fully dumpable and the manifest stays data-only. The launcher-owned `ctx.headlessIo` seam is the one host-provided slot, and it is provided in `boot()`'s `prepare` hook, before any config-tree entry mounts.
+- **Transitive bundle auto-application**: only direct `dsh.profile.bundles` entries contribute layers; a meta-bundle wanting to re-export another bundle's patch must do so explicitly in its own patch file.
+
+## Consequences
+
+- New composition surfaces (a TUI, provider packs) ship as ordinary npm packages installable per profile; the repository no longer needs a row for every deployment shape.
+- `apps/cli` shrank to argv parsing, profile machinery consumption, and the pnpm forwarder; `AppCLIEntry` and the per-surface boot paths are gone.
+- The keyless web e2e scaffold boots the same bundle layers over the same empty-root shape as production, including the profiles module fallback, so composition drift between test and product fails loudly.
+- Backends reject nothing old on disk (pre-release stance): `$DSH_HOME/config.yaml` is simply no longer read.

.agents/notes/implemented/architecture/2026-08-05-profile-plugin-bundles.zh.md

@@ -0,0 +1,33 @@
+# Agent Note: profile 插件组合包取代固定的表层 overlay
+
+Status: implemented
+
+[English](2026-08-05-profile-plugin-bundles.md) | 中文
+
+## Problem
+
+`dsh` 启动器硬编码了自己的组合：`base.cordis.yml` + `web.cordis.yml` 随 `apps/cli` 一起交付，三种各自定制的入口模式（`--config`、`web`、`-p`）各带一套层栈，外加一个全局的个人 overlay（`$DSH_HOME/config.yaml`）。想把树外插件（一个 TUI、一个提供方扩展包）装进已交付的表层，只能修改仓库；第三方包也没有任何位置可以贡献默认组合。
+
+## Decision
+
+一切都变成 **profile**：即目录 `$DSH_HOME/profiles/<name>`，其中包含一个 `package.json`（pnpm 管理的树外插件 `dependencies`，加上 profile manifest `dsh.profile` 及其有序的 `bundles` 层列表）和一份用户 `cordis.patch.yml`。**组合包**（bundle）是声明了 `"dsh": { "bundle": { "patch": "./cordis.patch.yml" } }` 的 npm 包；两种 manifest 分别位于互不相同的 `dsh.profile` / `dsh.bundle` 键下，因此一份 package.json 能说明自己扮演哪种角色。配置树在空的根之上组合：按 `dsh.profile.bundles` 顺序应用每个组合包的 patch，然后是用户层，然后是 `--patch` overlay，最后是 flag patch——全部收敛为一次 `applyEntryPatches` 调用，启动、flag 派生与 `--dump-config` 使用完全相同的路径。
+
+已交付的组合改造成了组合包：`@deepseek-ai/dsh-base`（原有基础行合并为一次插入）、`@deepseek-ai/dsh-web-app`（原 web overlay，外加一个接管原启动器代码的运行时粘合插件——前端 dist 解析、web 表层提示词段落、bash 运行时变量、URL 行）、`@deepseek-ai/dsh-headless`（叠加在 base + web-app 之上的一次性 runner 插件）。`dsh web` 保留为携带 Web flag 家族的 `--profile web` 别名；`dsh --profile headless "task"` 取代 `-p`；`dsh --config` 被移除（其用途迁移到 `--patch`）。`dsh plugin --profile <name> <args...>` 是一层薄薄的 pnpm 转发器，负责初始化 profile，并在 `add`／`remove` 后调和 `dsh.profile.bundles`（没有组合包声明的包会给出警告，保持为普通依赖）。
+
+解析在构造上就是双锚点的：`dsh.profile.bundles` 中的名称先从 dsh 安装目录解析，再从 profile 目录解析——因此内置组合包始终来自与运行中 `dsh` 相同的安装，pnpm 从不管理它们——而 patch 行中的裸插件名称经 profile 目录的 Node 父目录逐级查找，落到受维护的扁平回退目录 `$DSH_HOME/profiles/node_modules`（安装目录的应用与各组合包所依赖的每个包各一个符号链接，每次启动时修复）。
+
+两项配套重构：webserver 内置的静态 dist 服务改为单一所有者的**回退席位**（`registerFallback`／`applyIndexTaps`），SPA 服务器提取到 `@deepseek-ai/dsh-frontend-static`，使 web 组合包以组合的方式持有自己的 dist，而不是靠启动器代码；[dsh CLI 个人配置决策](../feature/2026-07-20-dsh-cli-personal-config.md)的个人 overlay 机制（`loadPersonalPatches`、`$DSH_HOME/config.yaml`）改为面向逐 profile 与 home 级的 `cordis.patch.yml` 层（`loadOptionalPatches`、接受文件名的 `watchUserPatches`），取代该笔记的各入口模式与文件位置，同时保留其 Harness home 根目录、patch 语义与大声失败的解析。
+
+## Alternatives considered
+
+- **依赖扫描加部分 `patchOrder`**（最初的草案）：扫描 `dependencies` 找出组合包、未列出者按字母序排列，会产生两个真源和一条隐式决胜规则；一份显式有序的 `dsh.profile.bundles` 列表更小、完全确定。在 profile 内直接 `pnpm add` 只会安装一个库，不激活任何 patch——行为显式，没有暗中扫描。
+- **内置组合包使用 `link:` 条目**：pnpm 无法对指向安装目录的 `link:` 做版本管理、安装或更新，它会把机器路径嵌进用户文件，并且在安装目录移动后失效。双锚点解析加上每次启动修复的符号链接回退提供了同样的保证（「组合包来自安装目录」），且没有这些繁文缛节。
+- **在组合包 manifest（元数据清单）中放一个启动前 `context` 模块**承载启动期取值（dist 路径、flag 事实）：否决，改用纯插件——粘合逻辑就是启动器 patch 的普通配置行，因此组合始终可完整 dump，manifest 保持纯数据。启动器持有的 `ctx.headlessIo` seam 是唯一由宿主提供的 slot，且在任何配置树条目挂载之前，于 `boot()` 的 `prepare` 钩子中提供。
+- **组合包的传递式自动应用**：只有直接列在 `dsh.profile.bundles` 中的条目才贡献层；想重新导出另一个组合包 patch 的元组合包，必须在自己的 patch 文件中显式完成。
+
+## Consequences
+
+- 新的组合表层（TUI、提供方扩展包）以普通 npm 包形式交付，可按 profile 安装；仓库不再需要为每种部署形态各留一行。
+- `apps/cli` 收缩为 argv 解析、profile 机制的消费方和 pnpm 转发器；`AppCLIEntry` 与各表层专属的启动路径全部移除。
+- 无密钥 web e2e 脚手架以与生产相同的空根形态启动相同的组合包层，包括 profiles 模块回退，因此测试与产品之间的组合漂移会大声失败。
+- 后端不拒绝磁盘上的任何旧格式（发布前姿态）：`$DSH_HOME/config.yaml` 只是不再被读取。

.agents/notes/implemented/architecture/2026-08-06-agent-event-payload-objects.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-06-agent-event-payload-objects.md
+2026-08-06-agent-event-payload-objects.md: 470c8fb3f9282005829846307778d3d1088c3888
+2026-08-06-agent-event-payload-objects.zh.md: ff201a7c3134c0ef809c9a798d65412541f9f1e7

.agents/notes/implemented/architecture/2026-08-06-agent-event-payload-objects.md

@@ -0,0 +1,27 @@
+# Agent Note: Agent-scoped events dispatch a single payload object
+
+Status: implemented
+
+English | [中文](2026-08-06-agent-event-payload-objects.zh.md)
+
+## Problem
+
+Agent-scoped events historically took positional arguments: a leading `agent` subject, event-specific fields, and a trailing `next` for waterfall/serial events. Adding a field or retiring a context type (as with `PreStepContext` and `RequestFailureContext`) rewrote every listener and emitter across packages, and the contract stayed spread across the parameter list instead of one named payload.
+
+## Decision
+
+Every agent-scoped event takes exactly one payload object as its first argument. The payload always carries the subject (`agent`), the event's fields, and the cancellation `signal` when the event has one; `next` remains the last argument of waterfall/serial events. The affected events are the twelve `agent/*` events, `agent-loop/config-start-failed` (the only one without a subject), and `goal/changed`.
+
+`PreStepContext` and `RequestFailureContext` are retired; their fields live directly in the `agent/pre-step` and `agent/request-error` payloads.
+
+Dispatch is fused: `agentEvents(ctx, agent)` (and the one-shot `emitAgentEvent`) injects the subject so the scope carrier key and the payload's `agent` cannot diverge, and the injected subject wins even over a structurally acceptable payload that happens to carry an `agent` field. `ReactLoopAgent` builds its dispatcher once in the constructor and routes every emit, serial, and waterfall through it, so hot-path dispatches allocate nothing.
+
+## Alternatives considered
+
+**Keep positional signatures.** Adding a field or retiring a context type would keep rewriting every listener and emitter, and the contract would stay spread across the parameter list instead of one named payload.
+
+**Hand-build the subject at each dispatch site.** The loop's intermediate design called `ctx.waterfall(this.carrier, …)` with a manually constructed `{ agent: this, … }` payload; it avoided per-dispatch allocation but duplicated the subject injection and let the scope key and the payload subject diverge. The fused dispatcher is the single injection point for every dispatch mode.
+
+## Consequences
+
+Listener signatures name the full payload once, so extending a payload or retiring a context type is a one-shape change across all listeners and emitters. The subject/scope coupling is enforced by the dispatcher for every dispatch mode, and the loop's hot paths stay allocation-free.

.agents/notes/implemented/architecture/2026-08-06-agent-event-payload-objects.zh.md

@@ -0,0 +1,27 @@
+# Agent Note: Agent 作用域事件 dispatch 单个 payload 对象
+
+Status: implemented
+
+[English](2026-08-06-agent-event-payload-objects.md) | 中文
+
+## 问题
+
+Agent 作用域事件历来采用位置参数：开头的 `agent` 主体、事件专属字段，以及末尾用于 waterfall（瀑布式事件）/serial 事件的 `next`。新增字段或退役上下文类型（如 `PreStepContext` 与 `RequestFailureContext`）都会迫使跨包重写每个监听器和 emitter，契约也一直分散在参数列表中，而不是集中在一个具名 payload 中。
+
+## 决策
+
+每个 agent 作用域事件都将恰好一个 payload 对象作为其第一个参数。payload 始终携带主体（`agent`）、事件的字段，以及事件有取消信号时的取消 `signal`；`next` 仍然是 waterfall/serial 事件的最后一个参数。受影响的事件是十二个 `agent/*` 事件、`agent-loop/config-start-failed`（唯一没有主体的事件）以及 `goal/changed`。
+
+`PreStepContext` 与 `RequestFailureContext` 已退役；它们的字段直接存在于 `agent/pre-step` 与 `agent/request-error` 的 payload 中。
+
+dispatch 是融合的：`agentEvents(ctx, agent)`（以及一次性 `emitAgentEvent`）注入主体，使作用域载体键与 payload 的 `agent` 不可能分叉；即使某个结构上可接受的 payload 恰好携带 `agent` 字段，注入的主体仍然优先。`ReactLoopAgent` 在构造函数中构建一次 dispatcher，并将每个 emit、serial 和 waterfall 都经由它路由，因此热路径上的 dispatch 不产生任何分配。
+
+## 考虑过的替代方案
+
+**保留位置签名。** 新增字段或退役上下文类型依旧会重写每个监听器和 emitter，契约也会继续分散在参数列表中，而不是集中在一个具名 payload 中。
+
+**在每个 dispatch 位置手工构造主体。** loop 的中间设计调用 `ctx.waterfall(this.carrier, …)`，传入手工构造的 `{ agent: this, … }` payload；它避免了每次 dispatch 的分配，却重复了主体注入，并让作用域键与 payload 主体分叉。融合的 dispatcher 是每种 dispatch 模式的唯一注入点。
+
+## 后果
+
+监听器签名一次性命名完整 payload，因此扩展 payload 或退役上下文类型，对所有监听器和 emitter 都是一次形状变更。主体/作用域耦合由 dispatcher 在每种 dispatch 模式下强制执行，且 loop 的热路径保持零分配。

.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.md
+2026-08-06-web-shell-dist-chunk-layout.md: 1c7b4273dc243685317b149e2fd7fddf2a6c18d1
+2026-08-06-web-shell-dist-chunk-layout.zh.md: 6f4b94e0bd7412e480458e34922273b389aa8892

.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.md

@@ -0,0 +1,50 @@
+# Agent Note: Web shell dist chunk split and directory layout
+
+Status: implemented
+
+English | [中文](2026-08-06-web-shell-dist-chunk-layout.zh.md)
+
+## Problem
+
+The apps/web shell previously built into a single ~1.2 MB (minified) index chunk, roughly 80% of it vendor bytes — KaTeX, the boot grammars and the shiki engine, react-dom, the markdown pipeline — fused with all the workspace shell code (about one fifth). Any one-line shell change rehashed the whole chunk, forcing returning clients to redownload everything; `dist/assets/` was a flat single-level spread of 100-plus files (the main chunk, 23 lazy-loaded grammar chunks, 59 KaTeX font faces, and sourcemaps intermixed), impossible to navigate.
+
+## Decision
+
+`apps/web/vite.config.ts` splits the shell into two initial chunks via `manualChunks` and sorts the output into directories via naming functions; the entire configuration contains zero regexes — an exact-package-name Set, a filename list, an extension list.
+
+**Membership** (`VENDOR_PACKAGES`, by exact npm package name):
+
+- `vendor` = the three heavy rendering families: math (katex), highlight (shiki), markdown (the micromark/mdast parse pipeline — the incremental React renderer above it is workspace code and not part of this). The live membership is `VENDOR_PACKAGES`; the list is the packages workspace code **imports directly**: the remaining private transitive dependencies (the oniguruma family, @shikijs/core, character tables, dozens more) are referenced only by listed members, so rollup's chunk coloring pulls them into vendor automatically; dependencies shared with the index side fall back to index, diluting it by a few KB — not a correctness issue.
+- **Every vendor member must be react-free (the boundary invariant)**: rollup folds a module shared between the entry and a manual chunk into the manual chunk — one listed package importing react/jsx-runtime would drag the single shared react copy into vendor, away from index. The React side of markdown/math rendering is workspace code and naturally lives in index, so the whole react family stays pinned to index.
+- `index` (the default chunk) = the react family (react, react-dom, scheduler, use-sync-external-store), vendored cordis, all workspace code, and the unlisted small pieces (anser, clsx).
+- `@shikijs/langs` is special-cased: the boot grammars (`BOOT_GRAMMAR_FILES`: typescript, shellscript, json — the three that highlight.ts statically imports, all self-contained data modules with zero internal imports) go into vendor; the remaining 23 lazy-loaded grammars get no assignment and each keeps its own on-demand chunk.
+- `index.html` is wired up automatically by vite: index loads via `<script>` and vendor via `<link rel="modulepreload">`, so the two chunks fetch in parallel with no waterfall.
+
+**Directory layout** (`chunkFileNames` + `assetFileNames`):
+
+- The `assets/` root keeps only the index and vendor js (with their adjacent sourcemaps) and css.
+- Grammar chunks go under `assets/langs/`. The criterion is whether a chunk's `moduleIds` include an `@shikijs/langs` member, not the facade: the shared chunks of embedded grammars (php/ruby/mdx embed html+javascript, which rollup splits out for sharing) **have no facade**, so a facade criterion would miss them; index and vendor are excluded by name, because vendor legitimately carries the three boot grammars.
+- Fonts go under `assets/fonts/` (`FONT_EXTENSIONS`: woff2/woff/ttf; today all of them are KaTeX faces referenced by vendor.css — katex.min.css is imported by an index-side component, but CSS modules go through manualChunks like any module and follow `katex` into vendor.css; the browser fetches only woff2, on demand and only when a formula renders).
+- Sourcemaps need no arrangement: rollup writes each `.map` next to its js and references it by bare relative filename, so when a chunk moves directories its map follows automatically.
+
+All cross-directory references (index's dynamic imports into `langs/`, same-directory relative references among grammar chunks, vendor.css's relative references into `fonts/`) are emitted by the bundler, so the runtime needs zero accompanying changes; the host-side webserver serves the nested paths verbatim under its static prefix.
+
+## Alternatives considered
+
+- **Serving react and the other vendors from a CDN**: dsh web targets local/intranet hosts (often without internet access), so a CDN is simply unavailable; react is the platform seed external of every plugin bundle (the shell is its sole supplier), and switching to the CDN global-variable form would touch three places — the platform manifest, the seed, and the module table; the caching benefit is already delivered by the vendor split.
+- **An inverse catch-all rule (everything in node_modules except the react family goes to vendor)**: membership cannot be read off the configuration, and small pieces like anser/clsx get misassigned to vendor; superseded by the positive exact-package-name list.
+- **Regex family matching**: hard to read; exact package names plus rollup's automatic coloring of transitive dependencies make pattern matching unnecessary.
+- **Identifying grammar chunks by facadeModuleId**: the facade-less shared chunks of embedded grammars would go undetected and fall back to the root directory; the `moduleIds` membership criterion covers both shapes.
+- **Sheltering a react-edged rendering facade in vendor** (the historical react-markdown was one): rollup's shared-module folding would drag the single react copy into vendor, breaking the "react belongs to index" boundary; the constraint is codified as the list's boundary invariant.
+- **Lazy-loading KaTeX wholesale, or turning the boot TypeScript grammar lazy**: either would change first-frame rendering behavior (the fallback for formulas / the first code block); that trade-off is independent of the dist layout and is decided separately.
+
+## Verification
+
+The audit tool ships with the repository: `node scripts/attribute-chunk-bytes.mjs <chunk.js>` (zero-dependency sourcemap VLQ byte attribution, aggregated by npm package / workspace directory). It verifies that vendor contains no workspace bytes, that the react family (including react/jsx-runtime) sits entirely in index, and that the npm side of index retains only the react family plus anser/clsx; the lazy grammar chunk count matches the `LAZY_GRAMMARS` table one to one; the browser keyless replay case is verbatim-identical to the pre-change baseline (apart from environment-specific local reds), so the two-chunk shell loads and renders with no regression.
+
+## Consequences
+
+- A shell code change rehashes only index (about one third of the dist output); vendor (about two thirds) stays cache-stable across shell releases and is invalidated only by dependency upgrades.
+- `dist/assets/` is navigable: two js/css pairs at the root, on-demand grammars in `langs/`, fonts in `fonts/`.
+- Maintenance cost: when workspace code adds a direct import of a rendering family's facade package, `VENDOR_PACKAGES` must be updated alongside (an omission merely dilutes index, nothing breaks); when the boot grammar set grows in highlight.ts without `BOOT_GRAMMAR_FILES` following, that grammar silently lands in index, visible only to a dist audit.
+- The webserver's static surface has no compression yet, so the gzip size win is still on the table; transport-layer compression is a separate, independent decision.

.agents/notes/implemented/architecture/2026-08-06-web-shell-dist-chunk-layout.zh.md

@@ -0,0 +1,50 @@
+# Agent Note: Web 壳产物的 chunk 切分与目录布局
+
+Status: implemented
+
+[English](2026-08-06-web-shell-dist-chunk-layout.md) | 中文
+
+## Problem
+
+apps/web 的壳此前打成单一约 1.2 MB（minified）的 index chunk，其中约八成是 vendor 字节——KaTeX、boot 语法与 shiki 引擎、react-dom、markdown 管线——与全部 workspace 壳代码（约五分之一）熔在一起。任何一行壳代码改动都让整个 chunk 换哈希，回头客户端全量重新下载；`dist/assets/` 是 100 多个文件的单层平铺（主 chunk、23 个懒加载语法 chunk、59 个 KaTeX 字体面、sourcemap 混居），无从导航。
+
+## Decision
+
+`apps/web/vite.config.ts` 以 `manualChunks` 把壳切成两个初始 chunk，并以输出命名函数归类目录；整套配置零正则——精确包名 Set、文件名清单、扩展名清单。
+
+**成员归属**（`VENDOR_PACKAGES`，按精确 npm 包名）：
+
+- `vendor` = 三个重渲染家族：math（katex）、highlight（shiki）、markdown（micromark/mdast 解析管线——其上的增量 React 渲染器是 workspace 代码，不在此列）。成员以 `VENDOR_PACKAGES` 为活口径，清单 = workspace 代码**直接 import** 的包：其余私有传递依赖（oniguruma 系、@shikijs/core、字符表等数十个）只被清单成员引用，rollup 的 chunk 着色自动将其并入 vendor；与 index 侧共享的依赖回落 index，只稀释几 KB，不构成正确性问题。
+- **vendor 全员必须 react-free（边界不变量）**：rollup 会把入口与 manual chunk 共享的模块并入 manual chunk——清单里出现任何 import react/jsx-runtime 的包，唯一一份 react 副本就会被拽进 vendor、脱离 index。markdown/math 的 React 渲染侧是 workspace 代码天然住 index，react 族因此全部钉在 index。
+- `index`（默认 chunk）= react 族（react、react-dom、scheduler、use-sync-external-store）、vendored cordis、全部 workspace 代码及未列入的小件（anser、clsx）。
+- `@shikijs/langs` 特判：boot 语法（`BOOT_GRAMMAR_FILES`：typescript、shellscript、json——highlight.ts 静态 import 的三件，均为零内部 import 的自含数据模块）进 vendor；其余 23 个懒加载语法不做指派，各自保持按需 chunk。
+- `index.html` 由 vite 自动接线：index 走 `<script>`、vendor 走 `<link rel="modulepreload">`，两 chunk 并行拉取，无瀑布。
+
+**目录布局**（`chunkFileNames` + `assetFileNames`）：
+
+- `assets/` 根只留 index 与 vendor 的 js（含随行 sourcemap）与 css。
+- 语法 chunk 归 `assets/langs/`。判据是 chunk 的 `moduleIds` 含 `@shikijs/langs` 成员，而非 facade：内嵌语法共享 chunk（php/ruby/mdx 内嵌 html+javascript，被 rollup 拆出共享）**没有 facade**，facade 判据会漏；index/vendor 按名排除，因 vendor 合法携带 boot 三语法。
+- 字体归 `assets/fonts/`（`FONT_EXTENSIONS`：woff2/woff/ttf；今日全部为 vendor.css 引用的 KaTeX 字面——katex.min.css 虽由 index 侧组件 import，css 模块同样经 manualChunks 归属、随 `katex` 落入 vendor.css；浏览器按需只拉 woff2，且仅在公式渲染时）。
+- sourcemap 无需安排：rollup 把 `.map` 写在各自 js 旁并以裸相对文件名引用，chunk 挪目录 map 自动跟随。
+
+跨目录引用（index 的动态 import 指向 `langs/`、语法 chunk 间同目录相对引用、vendor.css 相对引用 `fonts/`）均由构建器生成，运行时零配套改动；host 侧 webserver 按静态前缀原样服务嵌套路径。
+
+## Alternatives considered
+
+- **react 等 vendor 走 CDN**：dsh web 面向本机/内网主机（常无外网），CDN 直接不可用；react 是全部插件 bundle 的 platform seed external（壳是唯一供给方），改 CDN 全局变量形态需牵动 platform 清单/seed/模块表三处；缓存收益由 vendor 切分即可取得。
+- **反向兜底规则（node_modules 除 react 族全归 vendor）**：成员从配置上读不出来，且把 anser/clsx 类小件错归 vendor；被正向精确包名清单取代。
+- **正则家族匹配**：可读性差；精确包名 + rollup 对传递依赖的自动着色使模式匹配没有必要。
+- **以 facadeModuleId 识别语法 chunk**：无 facade 的内嵌语法共享 chunk 会漏检落回根目录；`moduleIds` 成员判据覆盖两种形态。
+- **在 vendor 里收留带 react 边的渲染门面**（历史上的 react-markdown 属此类）：会经 rollup 的共享模块归并把唯一 react 副本拽进 vendor，破坏「react 归 index」的边界；该约束已成文为清单的边界不变量。
+- **KaTeX 整体懒加载、boot TypeScript 语法转懒**：会改变首帧渲染行为（公式/首个代码块的回退），是独立于产物布局的取舍，另行决策。
+
+## Verification
+
+审计工具随库：`node scripts/attribute-chunk-bytes.mjs <chunk.js>`（零依赖 sourcemap VLQ 字节归属，按 npm 包/workspace 目录聚合）。以其复核：vendor 不含任何 workspace 字节、react 族（含 react/jsx-runtime）全量位于 index、index 的 npm 侧仅剩 react 族与 anser/clsx；懒语法 chunk 数量与 `LAZY_GRAMMARS` 表一一对应；浏览器 keyless replay 用例与改动前基线逐字一致（本机环境性红除外），两 chunk 壳装载渲染无回归。
+
+## Consequences
+
+- 壳代码改动只重哈希 index（约为产物三分之一）；vendor（约三分之二）跨壳版本缓存稳定，仅依赖升级时失效。
+- `dist/assets/` 可导航：根两对 js/css，`langs/` 按需语法，`fonts/` 字体。
+- 维护成本：workspace 代码新增对某渲染家族门面包的直接 import 时需同步 `VENDOR_PACKAGES`（漏列仅稀释 index，不致坏）；在 highlight.ts 扩 boot 语法集而未同步 `BOOT_GRAMMAR_FILES` 时，该语法静默落入 index，仅产物审计可见。
+- webserver 静态面尚无压缩，gzip 体量是潜在值；传输层压缩是另一项独立决策。

.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.md
-2026-07-28-web-agent-runtime-context.md: 449c9d4ba2b144d02dee4b98ae80c86815aec5c1
-2026-07-28-web-agent-runtime-context.zh.md: def1674be5f193739bfb214a24f34590ee075d5f
+2026-07-28-web-agent-runtime-context.md: 6c2bb8faf0db56d2a29b47726ab295c3501cce2d
+2026-07-28-web-agent-runtime-context.zh.md: 09cbbdeabc244c265381b1ad67c3629b4c0763f5

.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.md

@@ -10,13 +10,13 @@ The shared CLI base configured an empty deployment persona, the Web overlay did
 
 ## Decision
 
-The shared Web/headless overlay (`apps/cli/config/web.cordis.yml`) supplies a concise coding-agent persona containing the resolved `{{model}}` and session `{{cwd}}`. `dsh web` additionally resolves the harness checkout from the launcher's module URL, installs the existing `harness:source` section, and adds an `app:web-surface` section before serving requests. The launcher registers that setup before mounting the config tree; its `systemPrompt` injection therefore installs both sections before later prompt consumers such as the agent loop can activate and emit a request header. The [source-checkout/workdir decision](2026-07-30-source-checkout-workdir-distinction.md) owns the source section's wording and its warning not to infer one path from the other.
+The Web profile composes the `dsh-base` and `dsh-web-app` bundles. The Web bundle supplies a concise coding-agent persona containing the resolved `{{model}}` and session `{{cwd}}`; its `web-runtime` plugin adds the `app:web-surface` section when `surfaceContext` is true. Before mounting the profile tree, the `dsh web` alias reads that same composed setting and installs the existing `harness:source` section only when the surface context is enabled. The headless bundle and a profile that owns its complete prompt set `surfaceContext: false`, suppressing the Web prompt and managed shell facts; the Web alias also suppresses the source section without checking an overlay path. Every mounted prompt contribution still activates before consumers such as the agent loop can emit a request header. The [source-checkout/workdir decision](2026-07-30-source-checkout-workdir-distinction.md) owns the source section's wording and its warning not to infer one path from the other.
 
 The Web section treats unqualified references to “this page,” “this GUI,” or “this app” as references to the DeepSeek Harness Web GUI. It also states that the browser provides no implicit DOM, route, or screenshot context, so the model can identify the product without claiming visual state it did not receive. The assembled text is logged in `request/header`, preserving the model-visible/logged invariant.
 
 ## Verification
 
-The focused startup-order test registers a later `systemPrompt` consumer and proves that it observes both launcher sections on its first activation. The keyless fresh-round-trip Web scenario boots the shipped base plus Web overlay, registers the same launcher context as `dsh web`, runs a real session through the HTTP/SSE application, and snapshots the first four system-prompt sections with source and working-directory paths normalized. The snapshot pins the harness identity, source checkout, Web orientation, and resolved coding-agent persona in request order.
+The Web runtime unit tests pin both enabled and disabled `surfaceContext` behavior, while the Web alias unit test pins default-on and explicit-off source-section gating from the composed row. The keyless fresh-round-trip Web scenario boots the shipped base plus Web bundle, runs a real session through the HTTP/SSE application, and snapshots the system-prompt prefix with source and working-directory paths normalized. The snapshot pins the harness identity, source checkout, Web orientation, and resolved coding-agent persona in request order. The Core Web snapshot applies the RL overlay and pins its complete system prompt with no source or Web section.
 
 ## Alternatives considered
 
@@ -30,4 +30,4 @@ The focused startup-order test registers a later `systemPrompt` consumer and pro
 
 ## Consequences
 
-Web requests gain a short stable prompt prefix and may invalidate provider prefix caches once when this change is deployed. Agents can distinguish the GUI source checkout from the selected Workspace and resolve ordinary references to the current app without a clarification round trip. References to a specific visual state remain bounded by the explicit no-DOM/no-route/no-screenshot statement and may still require a path, description, or attachment.
+Ordinary Web requests gain a short stable prompt prefix and may invalidate provider prefix caches once when this change is deployed. Agents can distinguish the GUI source checkout from the selected Workspace and resolve ordinary references to the current app without a clarification round trip. References to a specific visual state remain bounded by the explicit no-DOM/no-route/no-screenshot statement and may still require a path, description, or attachment. Complete-prompt profiles can opt out through the Web runtime's composition setting without a launcher path check.

.agents/notes/implemented/bug-fix/2026-07-28-web-agent-runtime-context.zh.md

@@ -10,13 +10,13 @@ CLI 共享 base 配置了空的部署 persona，Web overlay 没有替换它，
 
 ## 决策
 
-`apps/cli/config/web.cordis.yml` 这份 Web／无头共享 overlay 提供一段简洁的编码 agent persona，其中包含解析后的 `{{model}}` 与会话 `{{cwd}}`。`dsh web` 还会根据启动器模块的 URL 解析 harness checkout，安装现有的 `harness:source` 提示词段，并在对外提供请求服务前添加 `app:web-surface` 提示词段。启动器会在挂载配置树前注册这项设置；因此，它的 `systemPrompt` 注入会在 agent loop（智能体循环）等后续提示词消费方激活并发出 request header 之前安装这两个提示词段。源码提示词段的措辞，以及其中不得从一条路径推断另一条路径的警告，均由另行记录的[源码 checkout 与工作目录区分决策](2026-07-30-source-checkout-workdir-distinction.md)负责。
+Web profile 会组合 `dsh-base` 与 `dsh-web-app` 两个组合包。Web 组合包提供一段简洁的编码 agent persona，其中包含解析后的 `{{model}}` 与会话 `{{cwd}}`；当 `surfaceContext` 为 true 时，其 `web-runtime` 插件会添加 `app:web-surface` 提示词段。挂载 profile 配置树前，`dsh web` 别名会读取组合后的同一项设置，并且仅在启用表层上下文时安装现有的 `harness:source` 提示词段。无头组合包和拥有完整提示词的 profile 都会设置 `surfaceContext: false`，从而抑制 Web 提示词与受管 shell 事实；Web 别名也会抑制源码提示词段，而无需检查 overlay 路径。每项已挂载的提示词贡献仍会在 agent loop（智能体循环）等消费方发出 request header 前激活。源码提示词段的措辞，以及其中不得从一条路径推断另一条路径的警告，均由另行记录的[源码 checkout 与工作目录区分决策](2026-07-30-source-checkout-workdir-distinction.md)负责。
 
 Web 提示词段把未限定的「这个页面」「这个 GUI」或「这个应用」解释为 DeepSeek Harness Web GUI。同时，它会明确说明浏览器不会隐式提供 DOM、路由或截图上下文，使模型能够识别产品，但不会声称掌握未收到的视觉状态。组装后的文本会记录在 `request/header` 中，从而保持「模型可见内容必须有日志记录」这一不变量。
 
 ## 验证
 
-聚焦启动顺序的测试会注册一个后续的 `systemPrompt` 消费方，并证明该消费方首次激活时就能观察到启动器的两个提示词段。无密钥的 Web fresh-round-trip 场景会启动已交付的 base 与 Web overlay，注册与 `dsh web` 相同的启动器上下文，并通过 HTTP／SSE 应用运行一个真实会话。测试会把源码路径和工作目录规范化，然后对系统提示词的前四个段落生成快照。该快照按请求顺序固定 harness 身份、源码 checkout、Web 界面定位，以及解析后的编码 agent persona。
+Web 运行时单元测试会固定启用和禁用 `surfaceContext` 时的行为，Web 别名单元测试则会固定组合后配置行对源码提示词段的默认启用与显式禁用门控。无密钥的 Web fresh-round-trip 场景会启动已交付的 base 与 Web 组合包，通过 HTTP／SSE 应用运行一个真实会话，并在规范化源码路径与工作目录后对系统提示词前缀生成快照。该快照按请求顺序固定 harness 身份、源码 checkout、Web 界面定位，以及解析后的编码 agent persona。Core Web 快照会应用 RL overlay，并固定不含源码提示词段或 Web 提示词段的完整系统提示词。
 
 ## 考虑过的替代方案
 
@@ -30,4 +30,4 @@ Web 提示词段把未限定的「这个页面」「这个 GUI」或「这个应
 
 ## 影响
 
-Web 请求会增加一段较短且稳定的提示词前缀；部署此变更时，模型提供方的前缀缓存可能失效一次。agent 可以区分 GUI 源码 checkout 与所选 Workspace，并且无需再经过一轮澄清即可解析对当前应用的一般指代。对特定视觉状态的指代仍受「无 DOM／无路由／无截图」这一显式边界约束，必要时仍需用户提供路径、描述或附件。
+常规 Web 请求会增加一段较短且稳定的提示词前缀；部署此变更时，模型提供方的前缀缓存可能失效一次。agent 可以区分 GUI 源码 checkout 与所选 Workspace，并且无需再经过一轮澄清即可解析对当前应用的一般指代。对特定视觉状态的指代仍受「无 DOM／无路由／无截图」这一显式边界约束，必要时仍需用户提供路径、描述或附件。拥有完整提示词的 profile 可以通过 Web 运行时的组合设置选择退出，而无需检查启动器路径。

.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.md
-2026-07-28-web-gui-feedback-loop.md: 039d2aebeeef903d10838a46b48e5172f0195126
-2026-07-28-web-gui-feedback-loop.zh.md: 34b6b26d4ce7c7e194e641536fffc503c013188b
+2026-07-28-web-gui-feedback-loop.md: aa488e1df087722c072d98c67d47cdf63a42f6b8
+2026-07-28-web-gui-feedback-loop.zh.md: d9de988e5a2cc57794ff628b65eb050dee610747

.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.md

@@ -12,7 +12,7 @@ The [incident post-mortem](../../../../docs/postmortem/0003-web-agent-gui-feedba
 
 ## Decision
 
-`dsh web` publishes one canonical loopback URL and its actual runtime mode as both model-visible orientation and managed shell facts. The `app:web-surface` prompt section says that unqualified references identify this GUI and names the URL; `DSH_WEB_URL` and `DSH_WEB_MODE=production|development` carry the same facts into every foreground or managed background bash call. The section preserves the no-implicit-DOM, route, or screenshot boundary and does not claim that a LAN alias equals the browser's literal address.
+The ordinary `dsh web` composition mounts the Web bundle's `web-runtime` plugin, which publishes one canonical loopback URL and its actual runtime mode as both model-visible orientation and managed shell facts. The `app:web-surface` prompt section says that unqualified references identify this GUI and names the URL; `DSH_WEB_URL` and `DSH_WEB_MODE=production|development` carry the same facts into every foreground or managed background bash call. The section preserves the no-implicit-DOM, route, or screenshot boundary and does not claim that a LAN alias equals the browser's literal address. A complete-prompt profile sets the row's `surfaceContext` to false and receives neither the prompt section nor the managed variables; the Web launcher uses the same setting to suppress its source-checkout prompt section.
 
 The mode-specific prompt makes the agent, rather than the user, own the hidden startup contract. Production mode defines acceptance as rebuilding the affected artifacts and refreshing the existing URL. Development mode states that `dsh web --dev` activates only the HMR receiver: automatic client-plugin reload additionally requires a same-checkout `pnpm run dev:web` watcher, which the agent verifies before promising no-refresh updates. Shell and other plain-package changes still require rebuild plus refresh. An agent in production mode explains both commands when a user requests no-refresh updates; it does not launch a replacement GUI unless asked.
 
@@ -36,4 +36,4 @@ The keyless fresh-round-trip browser scenario boots the shipped production Web c
 
 ## Consequences
 
-Web prompts gain a dynamic URL-and-mode paragraph, so provider prefix reuse now varies by bound port and mode. Bash processes gain two non-secret managed environment variables. Bare Vite can no longer be used as a shell-only visual sandbox; developers use the full host or build mode instead. In exchange, GUI work has one mechanically observable target, the agent can teach the user the exact update behavior of the process actually serving their session, and the unsupported startup path fails before a white screen. The URL/mode contract guides the agent away from replacement ports; it does not prohibit arbitrary shell commands from starting one.
+Ordinary Web prompts gain a dynamic URL-and-mode paragraph, so provider prefix reuse now varies by bound port and mode. Their Bash processes gain two non-secret managed environment variables. Bare Vite can no longer be used as a shell-only visual sandbox; developers use the full host or build mode instead. In exchange, GUI work has one mechanically observable target, the agent can teach the user the exact update behavior of the process actually serving their session, and the unsupported startup path fails before a white screen. The URL/mode contract guides the agent away from replacement ports; it does not prohibit arbitrary shell commands from starting one. Profiles that disable `surfaceContext` also give up this feedback-loop guidance and shell context.

.agents/notes/implemented/bug-fix/2026-07-28-web-gui-feedback-loop.zh.md

@@ -12,7 +12,7 @@ Web agent（智能体）既无法识别承载当前会话的 GUI，也不知道
 
 ## 决策
 
-`dsh web` 发布一个规范的回环 URL 及其实际运行时模式，同时将二者作为模型可见的界面定位信息和受管 shell 事实。`app:web-surface` 提示词段说明：未加限定的指代指向此 GUI，并给出 URL；`DSH_WEB_URL` 和 `DSH_WEB_MODE=production|development` 会把同样的事实传入每次前台或受管后台 bash 调用。该段保留「不会隐式获得 DOM、路由或截图」这一边界，也不声称局域网别名等于浏览器中的实际地址。
+常规 `dsh web` 组合会挂载 Web 组合包的 `web-runtime` 插件，由它发布一个规范的回环 URL 及其实际运行时模式，同时将二者作为模型可见的界面定位信息和受管 shell 事实。`app:web-surface` 提示词段说明：未加限定的指代指向此 GUI，并给出 URL；`DSH_WEB_URL` 和 `DSH_WEB_MODE=production|development` 会把同样的事实传入每次前台或受管后台 bash 调用。该段保留「不会隐式获得 DOM、路由或截图」这一边界，也不声称局域网别名等于浏览器中的实际地址。拥有完整提示词的 profile 会把该配置行的 `surfaceContext` 设为 false，并且不会收到该提示词段和这些受管变量中的任何一个；Web 启动器也会使用同一项设置来抑制其源码 checkout 提示词段。
 
 按模式区分的提示词让 agent 而非用户负责隐藏的启动契约。生产模式将验收定义为重新构建受影响的产物并刷新现有 URL。开发模式说明，`dsh web --dev` 只会启用 HMR（热模块替换）接收端：客户端插件要自动重新加载，还需要在同一检出中运行 `pnpm run dev:web` 监听进程，agent 会在承诺无需刷新即可更新前验证这一点。外壳和其他普通包的变更仍然需要重新构建并刷新。生产模式下的 agent 会在用户要求无需刷新即可更新时说明这两个命令；除非用户要求，否则不会启动替代 GUI。
 
@@ -36,4 +36,4 @@ Web agent（智能体）既无法识别承载当前会话的 GUI，也不知道
 
 ## 影响
 
-Web 提示词会增加一个动态 URL 和模式段落，因此模型提供方的前缀复用会随绑定端口和模式变化。Bash 进程会增加两个非敏感的受管环境变量。裸 Vite 不再能用作只依赖 shell 的视觉沙箱；开发者应改用完整宿主或构建模式。作为交换，GUI 工作有了一个可由机制观察的唯一目标，agent 可以向用户说明实际承载其会话的进程究竟如何更新，不受支持的启动路径也会在出现白屏前失败。URL／模式契约会引导 agent 避免使用替代端口，但不会禁止任意 shell 命令启动替代服务。
+常规 Web 提示词会增加一个动态 URL 和模式段落，因此模型提供方的前缀复用会随绑定端口和模式变化。相应的 Bash 进程会增加两个非敏感的受管环境变量。裸 Vite 不再能用作只依赖 shell 的视觉沙箱；开发者应改用完整宿主或构建模式。作为交换，GUI 工作有了一个可由机制观察的唯一目标，agent 可以向用户说明实际承载其会话的进程究竟如何更新，不受支持的启动路径也会在出现白屏前失败。URL／模式契约会引导 agent 避免使用替代端口，但不会禁止任意 shell 命令启动替代服务。禁用 `surfaceContext` 的 profile 也会放弃这项反馈闭环指引与 shell 上下文。

.agents/notes/implemented/bug-fix/2026-07-29-sticky-composer-conversation-scroll.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-29-sticky-composer-conversation-scroll.md
-2026-07-29-sticky-composer-conversation-scroll.md: 69d46894a53b0113f3e4f0fe871bbf3f9697969b
-2026-07-29-sticky-composer-conversation-scroll.zh.md: c0d5a0640468207282316ecd2fa1f209708df7b5
+2026-07-29-sticky-composer-conversation-scroll.md: d3fed7a9d0b1f39f9551fbd85e0f83515b1a2690
+2026-07-29-sticky-composer-conversation-scroll.zh.md: 2beee34d3bb68832d14b7607b43aa11e1425d53d

.agents/notes/implemented/bug-fix/2026-07-29-sticky-composer-conversation-scroll.md

@@ -10,7 +10,7 @@ The active conversation column split scrolling: the chat (and trajectory) view o
 
 ## Decision
 
-While a session exists, `ConversationRoot` always supplies a `wrapActiveBody` owner callback that wraps the view ring in a `data-conversation-scroll` body and places a `data-composer-seat` around the whole `'conversation.composer'` chain output (fallback + elected overlay siblings from `overlay: true`). Active CSS sticks that seat with `position: sticky; bottom: 0` so Question/Approval takeovers stay visible when the user is not pinned to the floor; hero CSS centers the fallback stack inside the scroll body. `ConversationSession` keeps a chrome-hidden header + body shell while blank so that tree seat does not change on the first send. The session header remains `flex: none` column chrome above the scrollport when visible. ChatView and Trajectory/Waterfall keep a local scroller only when mounted outside that host (unit tests); under the host they set `overflow: visible` and resolve bottom-follow / prepend anchoring through `closest('[data-conversation-scroll]')`.
+`ConversationRoot` always owns one `data-conversation-scroll` body, with the strict `conversation.session` view outlet before a `data-composer-seat` around the whole `'conversation.composer'` chain output (fallback + elected overlay siblings from `overlay: true`). The separate strict `conversation.session.header` outlet remains `flex: none` column chrome above that scrollport and hides while the Session is blank. This fixed parent tree keeps the scroll body and composer seat mounted from no session through the blank Hero and active conversation. Active CSS sticks that seat with `position: sticky; bottom: 0` so Question/Approval takeovers stay visible when the user is not pinned to the floor; Hero CSS centers the fallback stack inside the scroll body. ChatView and Trajectory/Waterfall keep a local scroller only when mounted outside that host (unit tests); under the host they set `overflow: visible` and resolve bottom-follow / prepend anchoring through `closest('[data-conversation-scroll]')`.
 
 Session stats live on `'conversation.composer.dock'` (above `'conversation.input.dock'`). The InputBar textarea, when inside the host, chains `wheel` with `{ passive: false }`: while the capped textarea can still scroll in that direction it keeps the native gesture; only at its own edge does it `preventDefault` and apply `deltaY` to the host.
 
@@ -22,7 +22,7 @@ Chat history prepend follows reader intent through stable rendered node/call ide
 
 **Fixed flex-none composer below the scrollport with wheel forwarding.** Rejected: the product requires the composer to stick inside the transcript scrollport so the footer is part of that scroll hit-testing surface, not a sibling that only forwards deltas.
 
-**Portal the composer into ChatView's scroller.** Rejected: the composer is shared across view tabs; the wrap target is the Session body owned by the resident shell.
+**Portal the composer into ChatView's scroller.** Rejected: the composer is shared across view tabs; its target is the root-owned scrollport in the resident shell.
 
 **Keep StatsLine inside ChatView below the message column.** Rejected: outside the sticky composer it would scroll away while the input stayed pinned.
 
@@ -30,4 +30,4 @@ Chat history prepend follows reader intent through stable rendered node/call ide
 
 ## Consequences
 
-Wheel over the footer scrolls the transcript; the visible layout is a fixed header, scrolling transcript, and sticky bottom composer. Stats appear on every active view tab. Nested view scrollers under the host are suppressed so sticky Turn headers in Trajectory stick to the column host. Concurrent history, streaming, tool expansion, and composer reflow preserve wheel/trackpad scroll decisions, including Chromium's compositor-first delivery and stream-finalization clamp/regrow. Other browser scroll inputs do not change follow ownership under this narrow provenance rule. Hero → active keeps the same textarea DOM node (assembled slash-flow snapshot) and the InputHub draft.
+Wheel over the footer scrolls the transcript; the visible layout is a fixed header, scrolling transcript, and sticky bottom composer. Stats appear on every active view tab. Nested view scrollers under the host are suppressed so sticky Turn headers in Trajectory stick to the column host. Concurrent history, streaming, tool expansion, and composer reflow preserve wheel/trackpad scroll decisions, including Chromium's compositor-first delivery and stream-finalization clamp/regrow. Other browser scroll inputs do not change follow ownership under this narrow provenance rule. No session → blank Hero and Hero → active both keep the same textarea DOM node and InputHub draft.

.agents/notes/implemented/bug-fix/2026-07-29-sticky-composer-conversation-scroll.zh.md

@@ -10,7 +10,7 @@ Status: implemented
 
 ## Decision
 
-只要存在会话，`ConversationRoot` 就会始终提供 `wrapActiveBody` owner 回调，将视图环包进 `data-conversation-scroll` 主体，并用 `data-composer-seat` 包住整条 `'conversation.composer'` chain 输出（`overlay: true` 下的 fallback 与选举出的 overlay 兄弟节点）。活跃阶段 CSS 以 `position: sticky; bottom: 0` 钉住该 seat，使用户未贴底时 Question／Approval 接管仍可见；hero CSS 在滚动主体内居中 fallback 栈。`ConversationSession` 在 blank 时保留隐藏 chrome 的 header + body 壳，使首次发送时树座位不变。可见时会话标题栏仍是滚动容器之上的 `flex: none` 列 chrome。ChatView 与 Trajectory/Waterfall 仅在宿主之外挂载时（单元测试）保留本地 scroller；位于宿主下时设为 `overflow: visible`，并通过 `closest('[data-conversation-scroll]')` 解析贴底跟随与前置锚定。
+`ConversationRoot` 始终拥有同一个 `data-conversation-scroll` 主体，其中严格 `conversation.session` view outlet 位于 `data-composer-seat` 之前；该 seat 包住整条 `'conversation.composer'` chain 输出（`overlay: true` 下的 fallback 与选举出的 overlay 兄弟节点）。独立的严格 `conversation.session.header` outlet 作为 `flex: none` 列 chrome 位于滚动容器上方，并在 Session 仍为 blank 时隐藏。固定的父级树让滚动主体与 composer seat 从无 session、blank Hero 到活跃对话始终保持挂载。活跃阶段 CSS 以 `position: sticky; bottom: 0` 钉住该 seat，使用户未贴底时 Question／Approval 接管仍可见；Hero CSS 在滚动主体内居中 fallback 栈。ChatView 与 Trajectory/Waterfall 仅在宿主之外挂载时（单元测试）保留本地 scroller；位于宿主下时设为 `overflow: visible`，并通过 `closest('[data-conversation-scroll]')` 解析贴底跟随与前置锚定。
 
 会话统计挂在 `'conversation.composer.dock'`（位于 `'conversation.input.dock'` 之上）。InputBar 的 textarea 在宿主内以 `{ passive: false }` 链式处理 `wheel`：在限高 textarea 仍能沿该方向滚动时保留原生手势；仅在自身边缘才 `preventDefault` 并将 `deltaY` 施加到宿主。
 
@@ -22,7 +22,7 @@ Chat 历史前插通过稳定的已渲染 node／call 身份跟随读者意图
 
 **滚动容器下方 flex-none 固定编辑器并转发滚轮。** 否决：产品要求编辑器 sticky 在 transcript 滚动容器内，使页脚成为该滚动命中面的一部分，而不是仅转发增量的兄弟节点。
 
-**把编辑器 portal 进 ChatView 的 scroller。** 否决：编辑器跨视图标签共享；包装目标是常驻壳拥有的 Session 主体。
+**把编辑器 portal 进 ChatView 的 scroller。** 否决：编辑器跨视图标签共享；其目标是常驻壳中由 root 持有的滚动容器。
 
 **把 StatsLine 留在 ChatView 消息列下方。** 否决：落在 sticky 编辑器之外会随内容滚走，而输入区仍钉在底部。
 
@@ -30,4 +30,4 @@ Chat 历史前插通过稳定的已渲染 node／call 身份跟随读者意图
 
 ## Consequences
 
-在页脚上滚轮会滚动 transcript；可见布局是固定标题栏、可滚动 transcript 与 sticky 底部编辑器。统计出现在每一个活跃视图标签上。宿主下的嵌套视图 scroller 被抑制，因而 Trajectory 的 sticky Turn 标题贴在列宿主上。并发历史加载、流式输出、工具展开与编辑器重排会保留滚轮／触控板的滚动决定，包括 Chromium 先推进合成器几何状态再交付事件，以及流收尾阶段滚动位置受钳制后滚动容器重新增长的情况。在这条窄范围的输入来源规则下，其他浏览器滚动输入不会改变贴底跟随所有权。hero → active 保持同一 textarea DOM 节点（assembled slash-flow 快照）以及 InputHub 草稿。
+在页脚上滚轮会滚动 transcript；可见布局是固定标题栏、可滚动 transcript 与 sticky 底部编辑器。统计出现在每一个活跃视图标签上。宿主下的嵌套视图 scroller 被抑制，因而 Trajectory 的 sticky Turn 标题贴在列宿主上。并发历史加载、流式输出、工具展开与编辑器重排会保留滚轮／触控板的滚动决定，包括 Chromium 先推进合成器几何状态再交付事件，以及流收尾阶段滚动位置受钳制后滚动容器重新增长的情况。在这条窄范围的输入来源规则下，其他浏览器滚动输入不会改变贴底跟随所有权。无 session → blank Hero 与 Hero → active 都保持同一 textarea DOM 节点以及 InputHub 草稿。

.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md
-2026-07-31-hero-visible-while-blank-session-opens.md: b39963beffa403ef6fa44735aa88395a99139751
-2026-07-31-hero-visible-while-blank-session-opens.zh.md: b451d7c00ec7eb8d736134e738d72e5e07fd1b04
+2026-07-31-hero-visible-while-blank-session-opens.md: 6afa5d0ee2b695d6805d20f54e82073db8028df7
+2026-07-31-hero-visible-while-blank-session-opens.zh.md: f21e549b5811d81094374b1363186a1d18fbadaf

.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.md

@@ -24,12 +24,10 @@ The summary flag and the snapshot's own `blank` are distinct sources: the snapsh
 
 ## Deferred
 
-The no-session→session tree relocation in `ConversationRoot` (the hero/composer subtree moves into the `conversation.session` outlet) still rebuilds the composer DOM on the same transition; removing it means moving `conversation.session` to `session-maybe` scope, a slot-contract change that needs its own proposal.
-
 Object-layer reference churn found while diagnosing this — no-op projections minting fresh snapshots, the create path projecting twice, `select()` using `notifyNow` from async continuations — is real but independent of the visible flash.
 
 ## Consequences
 
 Startup auto-selection renders the hero immediately and keeps the composer seat and header visible through the history round-trip, so launching into a recent workspace no longer looks like a page reload. Sessions whose summary does not prove them blank keep the previous settling behavior, so the guard still covers the case it was written for. Skeleton tests pin all three summary shapes: a row reporting `blank: false` settles, an absent row settles, and a summary-proven blank session opening under `loading` renders hero chrome with a live textarea.
 
-The assembled coverage is `apps/web/tests/startup-auto-selection.e2e.ts` (keyless web browser lane): it registers a workspace, holds the `session.history` response open at the browser's network boundary, and asserts the visible frame while the auto-selected open is in flight — hero phase, hero title, painted composer — plus a recorded phase timeline of exactly `['hero']` for the whole load. Holding the round-trip is what makes it a regression test rather than a race: against a loopback host the open settles too fast to sample, and with the exemption reverted the held window is precisely when the root reports `settling`.
+The assembled coverage is `apps/web/tests/startup-auto-selection.e2e.ts` (keyless web browser lane). Its first Workspace connection asserts that the Hero root, Workspace chip, scroll body, composer seat, and textarea remain the same DOM nodes when the blank Session appears. It then holds the `session.history` response open at the browser's network boundary and asserts the visible frame while the auto-selected open is in flight — hero phase, hero title, painted composer — plus a recorded phase timeline of exactly `['hero']` for the whole load. Holding the round-trip is what makes the second case a regression test rather than a race: against a loopback host the open settles too fast to sample, and with the exemption reverted the held window is precisely when the root reports `settling`.

.agents/notes/implemented/bug-fix/2026-07-31-hero-visible-while-blank-session-opens.zh.md

@@ -24,12 +24,10 @@ Status: implemented
 
 ## 推迟事项
 
-`ConversationRoot` 中"无会话→有会话"的树位置迁移（hero/composer 子树移入 `conversation.session` 出口）仍会在同一次转换中重建 composer 的 DOM；消除它意味着把 `conversation.session` 移到 `session-maybe` 作用域，这是一次插槽契约变更，需要单独立项。
-
 诊断期间发现的对象层引用抖动——空操作投影铸造出新的快照、创建路径重复投影一次、`select()` 在异步续体中使用 `notifyNow`——确实存在，但与这次可见闪烁相互独立。
 
 ## 影响
 
 启动自动选择会立即渲染 hero，并在整个历史往返期间保持 composer 座位与 header 可见，因此启动进入最近工作区不再像页面重载。摘要未证明为空白的会话保持原有的 settling 行为，这道防护仍覆盖它当初针对的场景。骨架测试固定了摘要的三种形态：报告 `blank: false` 的行进入 settling；根本没有该行同样进入 settling；摘要已证明为空白的会话在 `loading` 期间渲染 hero 外壳与可用的文本框。
 
-组装级覆盖是 `apps/web/tests/startup-auto-selection.e2e.ts`（无密钥的 Web 浏览器泳道）：它注册一个工作区，在浏览器网络边界上扣住 `session.history` 的响应，并在自动选择的打开仍在飞行途中断言可见画面——hero 阶段、hero 标题、已绘制的 composer——外加整次加载记录到的阶段时间线恰好为 `['hero']`。扣住这次往返正是它成为回归测试而非竞态的原因：对着回环主机，打开会快到无从采样；而一旦回退这条豁免，被扣住的这段窗口恰恰就是根节点报告 `settling` 的时刻。
+组装级覆盖是 `apps/web/tests/startup-auto-selection.e2e.ts`（无密钥的 Web 浏览器泳道）。首次连接 Workspace 时，它断言 blank Session 出现前后 Hero root、Workspace chip、滚动主体、composer seat 与 textarea 都是同一 DOM 节点。随后它在浏览器网络边界上扣住 `session.history` 的响应，并在自动选择的打开仍在飞行途中断言可见画面——hero 阶段、hero 标题、已绘制的 composer——外加整次加载记录到的阶段时间线恰好为 `['hero']`。扣住这次往返正是第二个用例成为回归测试而非竞态的原因：对着回环主机，打开会快到无从采样；而一旦回退这条豁免，被扣住的这段窗口恰恰就是根节点报告 `settling` 的时刻。

.agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.md
+2026-08-06-onboarding-step-owned-takeover-chrome.md: 4b3bbbc03c4494359297ae6e54bcc9a74c387e80
+2026-08-06-onboarding-step-owned-takeover-chrome.zh.md: 548285d285939325a26df3b8d70c43fe952813a9

.agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.md

@@ -0,0 +1,35 @@
+# Agent Note: onboarding takeover chrome moves into the step
+
+Status: implemented
+
+English | [中文](2026-08-06-onboarding-step-owned-takeover-chrome.zh.md)
+
+## Problem
+
+The settings shell mounted the onboarding takeover chrome — a body-portaled overlay with an opaque `--dsw-alias-bg-layer-1` stage, a blur mask, and `#root` set inert — the moment a `settings.onboarding` step was registered and not yet locally completed. Every step decides whether it actually needs to show by loading a private fact first (WelcomeNotice: the acknowledgement bit through its settings join; DeepSeekOnboardingDialog: credential readiness through the Models join) and renders `null` while that fact is in flight. Rendering `null` could not suppress the chrome, because the opaque stage was painted by the shell around the slot outlet, not by the step.
+
+On every reload while the hero (blank or no session) was current, the sessions list turning `ready` therefore popped a full-screen opaque layer — white in the light palette — and blocked all interaction for exactly one credential/settings RPC round-trip, after which the already-configured steps self-completed and the layer vanished. Users saw the app flash white each refresh the moment the workspace/session lists landed.
+
+## Decision
+
+The takeover chrome belongs to the step, not the shell. A new zero-cordis primitive, `OnboardingSurface` (ui-primitives), renders the body-portaled overlay/mask/stage — CSS class names and geometry moved verbatim from `SettingsRoot.module.css` — and holds `#root` inert for exactly its own mount lifetime. Both step components wrap only their **visible** branch in it; their existing `null` branches now paint and block nothing by construction, because the chrome is part of the same render decision.
+
+`SettingsRoot` keeps the coordinator exactly as it was (ordered ledger projection, one mounted step, local completed set, `stepId`/`complete`/`openSection` currency) but renders the elected step bare — no portal, no stage, no inert effect. The `settings.onboarding` slot contract now states that registrants own the surface wrap and must render `null` while their private facts are undecided.
+
+## Alternatives considered
+
+**Register steps conditionally (ledger as the has-content signal).** Register the entry only after the private join resolves to "needs intervention". Architecturally clean (publish at the commit point) but a larger change: the join load must move from the dialogs into each plugin's apply, and registration/disposal becomes reactive plumbing in two packages. Rejected as oversized for the defect.
+
+**Convert `settings.onboarding` to a chain with an externalized completed-set store.** The composer-takeover pattern; prototyped and reverted. Selectors can only judge owner props, so the private readiness facts still had to be resolved inside the components — the chain bought routing generality the two current steps do not need, at the cost of a contract change across three packages.
+
+**Detect empty slot output at the render site.** `renderSlot` returns an outlet element unconditionally, so the owner cannot branch on a step's `null`; probing rendered DOM emptiness needs a commit-then-retract dance whose dynamic transitions lose the pre-paint guarantee.
+
+## Consequences
+
+While a step is mounted but undecided, the application stays visible and interactive: `#root` is no longer inert during the decision window (previously it was inert behind an opaque layer). For a genuinely unconfigured user the takeover now appears one join round-trip later than before — but with its content already present, instead of an empty stage that fills in.
+
+A future step that registers without wrapping its visible content in `OnboardingSurface` renders bare over the app with no mask; the slot contract JSDoc names the wrap as the registrant's obligation.
+
+## Testing
+
+`packages/client/ui-primitives/tests/onboarding-surface.spec.tsx` pins the primitive: body portal around the content, mask/stage class presence, `#root` inert held for exactly the mount lifetime, and the no-`#root` composition. `packages/client/ui-settings/tests/settings-root.spec.tsx` pins the inverted shell contract: no takeover chrome and no inert while a mounted step renders nothing. `apps/web/tests/onboarding-deepseek-config.e2e.ts` gains the defect's assembled regression pin: a configured world reloads while every `settings.describe` response is held open at the browser's network boundary — widening the steps' deciding window from loopback-invisible to hundreds of milliseconds, which is what keeps the assertions non-vacuous — and an 8 ms in-page sampler proves the takeover chrome never mounts and `#root` never turns inert. The file's existing scenarios and the step specs (`ui-settings-general`, `ui-models`) pass unchanged — the mask selector and geometry pins survive because the stylesheet moved verbatim.

.agents/notes/implemented/bug-fix/2026-08-06-onboarding-step-owned-takeover-chrome.zh.md

@@ -0,0 +1,35 @@
+# Agent Note：首次使用引导的接管界面框架移入步骤自身
+
+状态：已实现
+
+[English](2026-08-06-onboarding-step-owned-takeover-chrome.md) | 中文
+
+## 问题
+
+设置外壳在 `settings.onboarding` 有已注册且本地未完成的步骤时，就立即挂出首次使用引导的接管界面框架——portal 到 body 的浮层，带不透明的 `--dsw-alias-bg-layer-1` 展示层、模糊遮罩，并把 `#root` 置为 `inert`。而每个步骤都要先加载私有事实才能判定自己是否需要出场（WelcomeNotice：经其设置 join 读取确认位；DeepSeekOnboardingDialog：经 Models join 读取凭据就绪状态），判定期间渲染 `null`。渲染 `null` 无法抑制界面框架，因为不透明展示层是外壳画在 slot outlet 外面的，不属于步骤。
+
+于是每次在 hero（空白或无会话）状态下刷新页面，会话列表一变 `ready` 就弹出整屏不透明层——亮色主题下是白色——并阻断全部交互，时长恰好等于一次凭据/设置 RPC 往返；之后已配置好的步骤自我完成，图层消失。用户看到的就是每次刷新在 workspace/会话列表落地的瞬间闪一下白屏。
+
+## 决定
+
+接管界面框架属于步骤，不属于外壳。新增零 cordis 原语 `OnboardingSurface`（ui-primitives）：渲染 portal 到 body 的浮层／遮罩／展示层——CSS 类名与几何从 `SettingsRoot.module.css` 逐字迁移——并在自身挂载生命周期内保持 `#root` 为 `inert`。两个步骤组件只把各自的**可见**分支包进该原语；既有的 `null` 分支由此在构造上不绘制、不阻塞任何内容，因为界面框架已是同一次渲染决策的一部分。
+
+`SettingsRoot` 的协调器原样保留（有序账本投影、每次挂载一个步骤、本地完成集合、`stepId`／`complete`／`openSection` currency），但对当选步骤裸渲染——不再有 portal、展示层和 inert 效果。`settings.onboarding` 的 slot 契约现在写明：注册方持有外层包裹，且在私有事实未决时必须渲染 `null`。
+
+## 曾考虑的替代方案
+
+**条件注册（账本即有内容信号）。** 私有 join 解析出「需要介入」后才注册条目。架构上干净（在 commit point 发布），但改动更大：join 的加载必须从对话框上移到各插件的 apply，注册／销毁在两个包里都变成响应式接线。对本缺陷而言过重，否决。
+
+**把 `settings.onboarding` 改成 chain 并把完成集合外置为 store。** composer takeover 的版型；做过原型后回退。selector 只能判定 owner props，私有就绪事实仍然只能在组件内部解析——chain 买来的是当前两个步骤并不需要的路由通用性，代价却是跨三个包的契约变更。
+
+**在渲染点探测 slot 输出为空。** `renderSlot` 无条件返回 outlet 元素，owner 无法据步骤的 `null` 分支；探测已渲染 DOM 是否为空需要先提交再撤回的手法，其动态翻转会失去 paint 前的保证。
+
+## 后果
+
+步骤已挂载但尚未判定期间，应用保持可见且可交互：判定窗口内 `#root` 不再是 `inert`（此前是在不透明图层背后被置灰）。对真正未配置的用户，接管层比从前晚一个 join 往返出现——但一出现就带着内容，而不是先露出空白展示层再填充。
+
+未来若有步骤注册后不把可见内容包进 `OnboardingSurface`，会无遮罩地裸渲染在应用之上；slot 契约的 JSDoc 已把包裹写为注册方的义务。
+
+## 测试
+
+`packages/client/ui-primitives/tests/onboarding-surface.spec.tsx` 钉住原语行为：内容外的 body portal、遮罩／展示层类名存在、`#root` 的 `inert` 恰好持续挂载生命周期，以及无 `#root` 的组合。`packages/client/ui-settings/tests/settings-root.spec.tsx` 钉住反转后的外壳契约：已挂载步骤什么都不渲染时，无接管界面框架、无 inert。`apps/web/tests/onboarding-deepseek-config.e2e.ts` 新增本缺陷的整装回归钉：已配置世界刷新页面，同时在浏览器网络边界扣住所有 `settings.describe` 响应——把步骤的判定窗口从 loopback 下不可见拉宽到数百毫秒，这正是断言保持非空洞的关键——页内 8ms 采样器证明接管界面框架从未挂载、`#root` 从未变为 inert。该文件的既有场景与步骤 spec（`ui-settings-general`、`ui-models`）原样通过——样式表逐字迁移，遮罩选择器与几何钉子得以幸存。

.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md
+2026-08-06-token-surface-unpriced-replace-compatibility.md: 77b778fba695f560eb68af6da2f416e61ccff181
+2026-08-06-token-surface-unpriced-replace-compatibility.zh.md: dd4c5883c4c6d37809c2f8100f266655d8ba600c

.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.md

@@ -0,0 +1,35 @@
+# Agent Note: unpriced surface replacements fold neutrally
+
+Status: implemented
+
+English | [中文](2026-08-06-token-surface-unpriced-replace-compatibility.zh.md)
+
+## Problem
+
+The `contextPressure` and `contextBreakdown` projections keep a running surface-token total plus at most one pending shadow-price claim, so their persisted checkpoints stay O(1) over a session's life. Current replace producers append a `compact/summary` or `compact/prune` metering event immediately before the replacement; its `shadowedTokenCount` prices the exact replaced range, and `foldSurfaceProjection` turns that into the signed delta.
+
+Sessions recorded before the shadow-price protocol log replacements with no adjacent metering event. The O(1) state cannot reconstruct the replaced range's price, and the fold treated every unpriced replacement as a contract violation and threw — so replaying such a session died at its first replacement (`token surface: replace at seq … has no adjacent shadow price`), leaving the session permanently unopenable.
+
+## Decision
+
+A replace that arrives with no armed claim folds price-neutrally: `foldSurfaceProjection` returns `deltaTokens: 0`, pricing the replaced range as if it had cost exactly what its replacement costs, and replay continues. A claim expired by an intervening event reaches the same neutral path, since the fold cannot distinguish it from a log that never metered.
+
+An armed claim naming a **different** range still throws. There the metering event was adjacent, so the producer wrote contradictory adjacent events — a live shadow-price contract violation, not historical data, and it must fail loud rather than let the total drift silently.
+
+Both projections share the one fold, so neither gains state fields nor bumps its `stateVersion`. `surface-fold.ts` and `ctx.tokenMeter.measure()` are unaffected: they hold the per-node priced surface and never needed the claim protocol.
+
+## Alternatives considered
+
+**Keep throwing.** Preserves the strict producer contract, but every pre-protocol session stays permanently unreplayable, and the projections exist to serve replay.
+
+**Persist the full priced surface in the projection state.** Could price any replaced range exactly, but grows the checkpoint by one node per model-visible message without bound — defeating the O(1) constraint the shadow-price protocol exists to preserve (see [the context-meter note](2026-08-05-context-meter-blind-to-compaction.md)).
+
+## Consequences
+
+An unpriced replacement holds the total still instead of shrinking it, so the compacted-away span stays counted: `contextBreakdown.messageTokens` retains the overcount, and `contextPressure.projectedTokens` overestimates occupancy only until the next usage sample re-anchors it, because that figure tracks movement since the sample rather than the absolute level. The error direction is safe — overestimating occupancy at worst invites an earlier compaction.
+
+The loud failure survives where it still means something: a range-mismatched adjacent claim is a current producer bug and still throws.
+
+## Testing
+
+`packages/llm/token-meter/tests/context-breakdown-projection.spec.ts` pins the neutral fold for the no-claim and expired-claim replacements, the throw for a mismatched claim, and the exact pricing for a matched one. `packages/llm/token-meter/tests/token-usage-projection.spec.ts` pins `contextPressure` holding still across an unpriced replacement.

.agents/notes/implemented/bug-fix/2026-08-06-token-surface-unpriced-replace-compatibility.zh.md

@@ -0,0 +1,35 @@
+# Agent Note: 未计价的表层替换以中性方式折叠
+
+Status: implemented
+
+[English](2026-08-06-token-surface-unpriced-replace-compatibility.md) | 中文
+
+## 问题
+
+`contextPressure` 与 `contextBreakdown` 两个投影只维护一份滚动累计的表层 token 总量，外加至多一条待结算的影子价格（shadow price）声明，因此其持久化检查点在会话整个生命周期内保持 O(1)。当前的替换生产方会紧贴在替换之前追加一条 `compact/summary` 或 `compact/prune` 计量事件；其 `shadowedTokenCount` 对被替换区间精确计价，`foldSurfaceProjection` 再把它换算成有符号增量。
+
+影子价格协议引入之前录制的会话，其日志中的替换没有相邻的计量事件。O(1) 状态无法重建被替换区间的价格，而折叠此前把每一次未计价替换都当作契约违规并抛出异常，于是回放这类会话会在第一处替换就中断（`token surface: replace at seq … has no adjacent shadow price`），会话从此永远无法打开。
+
+## 决策
+
+到达时没有已就位声明的替换以价格中性的方式折叠：`foldSurfaceProjection` 返回 `deltaTokens: 0`，相当于把被替换区间计价为恰好等于其替换内容的成本，回放随即继续。因中间插入的事件而过期的声明也走同一条中性路径，因为折叠无法把它与从未计量过的日志区分开。
+
+已就位但指向**另一个**区间的声明仍会抛出异常。此时计量事件确实相邻，说明生产方写入了互相矛盾的相邻事件：这是现行影子价格契约的违规，不是历史数据，必须响亮失败，而不能任由总量悄然漂移。
+
+两个投影共用同一个折叠，因此二者都不新增状态字段，也不提升 `stateVersion`。`surface-fold.ts` 与 `ctx.tokenMeter.measure()` 不受影响：它们持有逐节点的已计价表层，本来就不需要声明协议。
+
+## 备选方案
+
+**维持抛出异常。**保住了严格的生产方契约，但协议之前的每个会话都将永远无法回放，而投影本就是为服务回放而存在的。
+
+**在投影状态中持久化完整的已计价表层。**可以对任意被替换区间精确计价，但检查点会随每条模型可见消息各增加一个节点、无上限地增长，恰恰破坏了影子价格协议所要守住的 O(1) 约束（见[上下文仪表的 Agent Note](2026-08-05-context-meter-blind-to-compaction.md)）。
+
+## 影响
+
+未计价的替换让总量保持不动而不是缩小，因此被压缩（compaction）掉的区段仍被计入：`contextBreakdown.messageTokens` 保留这部分多计的量；`contextPressure.projectedTokens` 会高估占用率，但只持续到下一个用量样本重新锚定为止，因为该数字追踪的是自样本以来的增减，而非绝对水平。误差方向是安全的：高估占用率最坏不过是招致一次更早的压缩。
+
+响亮失败保留在它仍有意义的地方：区间不匹配的相邻声明是现行生产方的缺陷，仍会抛出异常。
+
+## 测试
+
+`packages/llm/token-meter/tests/context-breakdown-projection.spec.ts` 钉住了无声明与声明过期两种替换的中性折叠、声明区间不匹配时的抛出异常，以及声明匹配时的精确计价。`packages/llm/token-meter/tests/token-usage-projection.spec.ts` 钉住了 `contextPressure` 在一次未计价替换前后保持不动。

.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md
-2026-06-18-compaction-capability-seam.md: 27dbde9f2349681cf47c4d25b16399b26ed9e1ca
-2026-06-18-compaction-capability-seam.zh.md: 1fe9ece2861bd6d75633a866a4a11eaadbf7ef26
+2026-06-18-compaction-capability-seam.md: 26e6e2468c7bea661d85c8fb994adf8b109105ee
+2026-06-18-compaction-capability-seam.zh.md: 8f9cd1f6bc31e648a5b923e816cad75ebc1a0bd8

.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.md

@@ -119,7 +119,7 @@ The lifecycle boundary makes crash state unambiguous:
 ## Consequences
 
 - **Packages**: `packages/compact/compact` supplies the interface, `compact-basic` supplies the backend, `compact-tool-result-prune` supplies optional deterministic rewriting, and `command-compact` supplies human `/compact`. `packages/llm/token-meter` owns replay-aware measurement independently.
-- **Automatic seams**: `agent/pre-step` (`@mode waterfall`) handles pressure before request derivation and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. Pre-step receives the claimed batch and `PreStepContext`, with no compaction-only prompt/prefix payload.
+- **Automatic seams**: `agent/pre-step` (`@mode waterfall`) handles pressure before request derivation and `agent/request-error` (`@mode waterfall`) handles final request failures after the failed step closes. The pre-step payload carries the claimed batch, turn, step, and signal (see the [payload-object events decision](../architecture/2026-08-06-agent-event-payload-objects.md)), with no compaction-only prompt/prefix payload.
 - **`SessionEventMap`** gains `compact/start` / `compact/summary` / `compact/end` by declaration merging (merge-extensible); `SurfaceEventType` is **not** touched. These are session events, not cordis `Events`, so the event-taxonomy gate needs no entry.
 - **`dsh-compact`** owns `COMPACT_CHECKPOINT_SOURCE`, `isCompactCheckpointSource(source)`, `toolPairingBalancedBefore(session, seq)`, and `toolPairingBalancedAfter(session, seq)`. The marker identifies replacement summaries across backend implementations. The cached surface-edge checks prevent `compactRegion` and `compactIfNeeded` from splitting a tool-call/result pair, validate current membership by seq, answer both edges from one per-cut balance sequence, and reject stale or missing seqs and orphan results.
 - **`dsh-session`** validates positional replacement, complete provenance, and content-only single-node `tool/result` rewrites through its one surface manager. Its invariant companion treats fresh appended tool results as executions that require an open step and pending call, while the compaction companion owns numeric-turn versus standalone-null bracket relations.

.agents/notes/implemented/feature/2026-06-18-compaction-capability-seam.zh.md

@@ -119,7 +119,7 @@ compact/end      → log-only. Releases the lock (carries `error` on a recoverab
 ## 后果
 
 - **包**：`packages/compact/compact` 提供接口，`compact-basic` 提供后端，`compact-tool-result-prune` 提供可选的确定性重写，`command-compact` 提供面向用户的 `/compact`。`packages/llm/token-meter` 独立拥有回放感知的测量。
-- **自动 seam**：`agent/pre-step`（`@mode waterfall`）在请求派生前处理压力，`agent/request-error`（`@mode waterfall`）处理失败步骤关闭后的最终请求失败。pre-step 接收已领取批次与 `PreStepContext`，不携带压缩专属的提示词/前缀 payload。
+- **自动 seam**：`agent/pre-step`（`@mode waterfall`）在请求派生前处理压力，`agent/request-error`（`@mode waterfall`）处理失败步骤关闭后的最终请求失败。pre-step 的 payload 携带已领取批次、轮次、步骤与 signal（参见 [payload-object 事件决策](../architecture/2026-08-06-agent-event-payload-objects.md)），不携带压缩专属的提示词/前缀 payload。
 - **`SessionEventMap`** 通过可合并扩展的声明合并获得 `compact/start` / `compact/summary` / `compact/end`；`SurfaceEventType` **未被**触及。这些是会话事件，不是 cordis `Events`，因此事件分类门禁无需新增条目。
 - **`dsh-compact`** 拥有 `COMPACT_CHECKPOINT_SOURCE`、`isCompactCheckpointSource(source)`、`toolPairingBalancedBefore(session, seq)` 与 `toolPairingBalancedAfter(session, seq)`。该标记用于跨后端实现识别替换摘要。带缓存的 surface 边缘检查会防止 `compactRegion` 和 `compactIfNeeded` 拆分工具调用/结果对，按 seq 校验当前成员关系，从每个切割点的一条平衡序列回答两侧边缘，并拒绝陈旧或缺失的 seq 与孤立结果。
 - **`dsh-session`** 通过唯一的 surface 管理器校验位置替换、完整溯源信息和仅内容的单节点 `tool/result` 重写。其不变式配套插件将新追加的工具结果视为执行，要求存在已打开的步骤与待处理调用，而压缩配套组件拥有数字轮次归属与独立 `null` 归属标记对之间的关系。

.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md
-2026-06-21-subagent-capability-seam.md: 043092884731c403a11b71ef8b5a410e9e5af7e0
-2026-06-21-subagent-capability-seam.zh.md: 6a4a5798199ca7d6d7c011668a319d65a0553208
+2026-06-21-subagent-capability-seam.md: 752e639b09ea2ac0ba19841ddfe38b15b44d22e9
+2026-06-21-subagent-capability-seam.zh.md: 6009aeda6773357a4217f8956fb510c2116bbe3f

.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.md

@@ -4,7 +4,7 @@ Status: implemented
 
 English | [中文](2026-06-21-subagent-capability-seam.zh.md)
 
-> The full seam is shipped: the `dsh-subagent` interface and `dsh-tool-subagent` consumer; the two in-process backends (`dsh-subagent-spawn`, `dsh-subagent-fork`); the nested-agent snapshot infrastructure ([per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md)); and the out-of-process `dsh-subagent-acp` backend ([its Agent Note](2026-06-22-acp-subagent-backend.md)).
+> The full seam is shipped: the `dsh-subagent` interface and `dsh-tool-subagent` consumer; the two in-process backends (`dsh-subagent-spawn`, `dsh-subagent-fork`); the nested-agent snapshot infrastructure ([per-session snapshot replay](../testing/2026-06-22-subagent-snapshot-replay.md)); and the out-of-process ACP, Codex, and Claude Code backends ([ACP Agent Note](2026-06-22-acp-subagent-backend.md), [product-provider Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md)).
 
 ## Problem
 
@@ -14,7 +14,8 @@ The distinctive requirement — the one that shapes the whole design — is that
 
 - **in-process** — a child concrete `Agent` on the same `Context` (the cheapest, and nearly free given the existing agent factory);
 - **ACP** — act as an ACP *client* driving another agent process (which can be another instance of ourselves);
-- later: **A2A**, the **Codex app-server**, and the **Claude Code Agent SDK** — each the same out-of-process "start a child, prompt it, stream updates, cancel" shape as the ACP backend.
+- **Codex app-server and Claude Code Agent SDK** — current one-shot siblings that apply the same named-provider seam to official product processes ([product-provider Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md));
+- later: **A2A** using the same out-of-process "start a child, prompt it, settle, cancel" shape.
 
 ## Alternatives considered
 
@@ -34,6 +35,8 @@ A new package group `packages/subagent/`:
 | `@deepseek-ai/dsh-subagent-spawn` | implementation: a fresh in-process child via `ctx.agents.create` |
 | `@deepseek-ai/dsh-subagent-fork` | implementation: an in-process child seeded with a snapshot of the parent's log |
 | `@deepseek-ai/dsh-subagent-acp` | implementation: an ACP client driving a configured child process |
+| `@deepseek-ai/dsh-subagent-codex` | implementation: a one-shot official Codex app-server process |
+| `@deepseek-ai/dsh-subagent-claude-code` | implementation: a one-shot official Claude Code process through the Agent SDK |
 | `@deepseek-ai/dsh-tool-subagent` | consumer: the model-facing `subagent` tool over `ctx.subagents` |
 
 ### The primitive: async `start → SubagentRun`
@@ -51,7 +54,7 @@ Fresh and forked children are separate providers, not a request flag. `dsh-subag
 
 ### Child isolation and the parent log
 
-Each subagent runs in its **own `Session`** (own id, `parentSession` lineage), persisted independently. The parent's log records only the spawn `tool/call` and its `tool/result` (the child's final output) — the child's internal steps and tool calls stay in the child's own session, never injected into the parent log. This is the only design that is identical across transports: an ACP child's internal events physically cannot be injected into our parent log, so making in-process behave the same keeps the seam transport-agnostic.
+Each in-process subagent runs in its **own `Session`** (own id, `parentSession` lineage), persisted independently. Remote ACP and one-shot product providers instead mint a parent-scoped lifecycle id and expose no local `Agent` or child `Session`; their internal state remains in the remote process. Across both forms, the parent's log records only the spawn `tool/call` and its `tool/result` (the child's final output), while child steps and tool calls remain outside the parent log.
 
 ### Synchronous collect (first cut)
 

.agents/notes/implemented/feature/2026-06-21-subagent-capability-seam.zh.md

@@ -4,7 +4,7 @@ Status: implemented
 
 [English](2026-06-21-subagent-capability-seam.md) | 中文
 
-> 完整 seam 已交付：`dsh-subagent` 接口与 `dsh-tool-subagent` 消费方；两个进程内后端（`dsh-subagent-spawn`、`dsh-subagent-fork`）；嵌套 agent 快照基础设施（[逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md)）；以及进程外后端 `dsh-subagent-acp`（[其 Agent Note](2026-06-22-acp-subagent-backend.md)）。
+> 完整 seam 已交付：`dsh-subagent` 接口与 `dsh-tool-subagent` 消费方；两个进程内后端（`dsh-subagent-spawn`、`dsh-subagent-fork`）；嵌套 agent 快照基础设施（[逐会话快照回放](../testing/2026-06-22-subagent-snapshot-replay.md)）；以及进程外的 ACP、Codex 与 Claude Code 后端（[ACP Agent Note](2026-06-22-acp-subagent-backend.md)、[产品提供方 Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md)）。
 
 ## 问题
 
@@ -14,7 +14,8 @@ harness 有一个长期搁置的 seam 用于 **subagent**：一个 agent（智
 
 - **进程内**：在同一个 `Context` 上创建一个具体的子 `Agent`（最廉价，且鉴于现有 agent 工厂几乎零成本）；
 - **ACP**：作为 ACP *客户端*驱动另一个 agent 进程（可以是自身的另一个实例）；
-- 后续：**A2A**、**Codex app-server** 与 **Claude Code Agent SDK**——每种都与 ACP 后端相同的进程外形状：「启动子 agent、发送提示词、流式接收更新、取消」。
+- **Codex app-server 与 Claude Code Agent SDK**：当前的一次性兄弟提供方，将同一个命名提供方 seam 应用于官方产品进程（[产品提供方 Agent Note](2026-08-04-claude-code-and-codex-subagent-backends.md)）；
+- 后续：**A2A**，采用同样的进程外形态：「启动子 agent、发送提示词、结算、取消」。
 
 ## 曾考虑的替代方案
 
@@ -34,6 +35,8 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
 | `@deepseek-ai/dsh-subagent-spawn` | 实现：通过 `ctx.agents.create` 创建全新的进程内子 agent |
 | `@deepseek-ai/dsh-subagent-fork` | 实现：用父 agent 日志快照初始化的进程内子 agent |
 | `@deepseek-ai/dsh-subagent-acp` | 实现：作为 ACP 客户端驱动已配置的子进程 |
+| `@deepseek-ai/dsh-subagent-codex` | 实现：一次性官方 Codex app-server 进程 |
+| `@deepseek-ai/dsh-subagent-claude-code` | 实现：通过 Agent SDK 运行的一次性官方 Claude Code 进程 |
 | `@deepseek-ai/dsh-tool-subagent` | 消费方：基于 `ctx.subagents` 的面向模型的 `subagent` 工具 |
 
 ### 原语：异步 `start → SubagentRun`
@@ -51,7 +54,7 @@ bash seam（[能力 seam](../architecture/2026-06-13-capability-seams.md)）在
 
 ### 子 agent 隔离与父日志
 
-每个 subagent 运行在**自己的 `Session`** 中（独立 id、`parentSession` 谱系），独立持久化。父日志仅记录 spawn `tool/call` 及其 `tool/result`（子 agent 的最终输出）——子 agent 的内部步骤和工具调用留在子 agent 自己的会话中，绝不注入父日志。这是唯一在所有传输方式下行为一致的设计：ACP 子 agent 的内部事件在物理上无法注入我们的父日志，因此让进程内行为保持一致，使 seam 真正与传输方式无关。
+每个进程内 subagent 运行在**自己的 `Session`** 中（独立 id、`parentSession` 谱系），独立持久化。远端 ACP 和一次性产品提供方则会生成一个父级作用域的生命周期 id，且不暴露本地 `Agent` 或子 `Session`；其内部状态留在远端进程中。两种形式下，父日志都仅记录 spawn `tool/call` 及其 `tool/result`（子 agent 的最终输出），而子 agent 的步骤和工具调用均留在父日志之外。
 
 ### 同步收集（首版）
 

.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md
-2026-06-22-acp-subagent-backend.md: 5f12aa1c08d4f4cfaa35f2f7f4b09ad341c3eae8
-2026-06-22-acp-subagent-backend.zh.md: ba9d4255723367ab4afc5ab87e056f12f5c3a285
+2026-06-22-acp-subagent-backend.md: c994ebfa69649bb9e79d3aa389a0e13c178131c7
+2026-06-22-acp-subagent-backend.zh.md: 62d631e95b5d1f299bed1fd00353b5ac9349b9a0

.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.md

@@ -57,6 +57,6 @@ Persistent-process pooling (reuse a warm child across runs) is a performance opt
 
 Every run pays a fresh subprocess (spawn + `initialize` + `newSession`). The parent surfaces only the child's final answer: `session/update` thoughts and tool-call cards are consumed and dropped, and permission prompts never reach a human — the configured policy answers them. The child's environment is credential-scrubbed by default, so its own model key is supplied explicitly via `config.env`.
 
-## Future providers
+## Product-provider siblings
 
-The same out-of-process spawn/prompt/stream/cancel shape generalizes to other transports named in the seam Agent Note — A2A, the Codex app-server, and the Claude Code Agent SDK — each a sibling provider registered by name. The ACP backend is the proof that the seam supports the boundary; those are mechanically similar.
+The [Codex app-server and Claude Code Agent SDK providers](2026-08-04-claude-code-and-codex-subagent-backends.md) apply the same out-of-process spawn/prompt/settle/cancel boundary as siblings registered by name. A2A remains a future sibling transport; the ACP backend proves that the common seam supports this boundary without owning product-private protocols.

.agents/notes/implemented/feature/2026-06-22-acp-subagent-backend.zh.md

@@ -57,6 +57,6 @@ ACP `StopReason` → harness `SubagentStopReason`：`end_turn`→`completed`、`
 
 每次运行都要付出一个全新子进程的代价（spawn + `initialize` + `newSession`）。父进程仅暴露子 agent 的最终回答：`session/update` 中的思考和工具调用卡片被消费后丢弃，权限提示从不到达人类——由配置的策略应答。子进程环境默认经过凭证清洗，因此其自身的模型密钥需通过 `config.env` 显式提供。
 
-## 后续提供方
+## 兄弟产品提供方
 
-同样的进程外启动/提示词/流式输出/取消形态可泛化到 seam Agent Note 中列出的其他传输方式——A2A、Codex app-server 和 Claude Code Agent SDK——每个都是按名称注册的兄弟提供方。ACP 后端证明了 seam 支持跨进程边界；其余在机制上类似。
+[Codex app-server 与 Claude Code Agent SDK 提供方](2026-08-04-claude-code-and-codex-subagent-backends.md)作为按名称注册的兄弟提供方，采用同样的进程外启动/提示词/结算/取消边界。A2A 仍是未来的兄弟传输方式；ACP 后端证明了通用 seam 能够支持这项边界，而无需负责产品私有协议。

.agents/notes/implemented/feature/2026-06-24-workspace-context.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-24-workspace-context.md
-2026-06-24-workspace-context.md: df7ae58f8a42a8c1aac8113a429ef0f50b2fb795
-2026-06-24-workspace-context.zh.md: aecc57a5c63b4c6282260863f4183944c14b5cf8
+2026-06-24-workspace-context.md: 3c21b7599e6bb2dd759e4a040c1b999f1b0516cd
+2026-06-24-workspace-context.zh.md: e913ecb22b4692e1ee7b96d4f5effe2606775cf8

.agents/notes/implemented/feature/2026-06-24-workspace-context.md

@@ -30,9 +30,9 @@ The user-global file is fixed at `$DSH_HOME/AGENTS.md`, is not affected by eithe
 
 At the first `agent/pre-step` of an agent-loop instance, the plugin composes one sourced user-role baseline. When the downstream decision enters a nonempty first-step batch, the plugin folds the baseline into that final batch right after the claimed prompt, so it becomes durable with the direct prompt and reaches the first request. Rejection or an empty first-step decision leaves the baseline in the next-step inbox for a later wakeup. The plugin loads the user-global file first, then finds the project root by walking upward from `agent.session.header.cwd` to a configured root marker (default `.git`), then loads the configured candidates from each directory from the root to the cwd. A `.git` file and a `.git` directory are both valid markers, covering linked worktrees and submodules. Without a marker, the cwd itself is the root.
 
-The baseline becomes a durable `user/message` with a typed `workspace-instructions` source. Its `baseline: true` marker distinguishes the complete startup or resume baseline from later deltas, and its change list persists the included scopes and content digests. If a previously queued workspace baseline is still pending, the plugin removes that exact message and prepends its replacement instead of accumulating duplicates.
+The baseline becomes a durable `user/message` with a typed `workspace-instructions` source. Its `baseline: true` marker distinguishes a complete baseline from later deltas, its `baselineIdentity` records normalized discovery, precedence, project-root, and budget semantics, and its change list persists the included scopes and content digests. If a previously queued workspace baseline is still pending, the plugin removes that exact message and prepends its replacement instead of accumulating duplicates.
 
-A resumed agent creates a new loop instance and injects a baseline composed from current files before its first request. This permits current baseline content on resume without mutating an earlier history event. A resume and a hot plugin remount both face a log that may already hold a baseline; they are told apart by `agent/session-start`, which a startup or resume emits before the first step while a remount attaches to an already-live session and never sees it. A remount retains the existing baseline only when its typed event remains in the current visible surface, and still rebuilds scope and provider-version tracking from current files. If compaction has shadowed that event, the remount injects a current baseline. A resume always re-composes.
+A resumed agent creates a new loop instance over persisted history. At its first `agent/pre-step`, a visible baseline with the current identity remains authoritative while the plugin compares its retained scopes with a complete current rendering. Unchanged and budget-omitted files append nothing; offline additions, edits, removals, and files that leave the retained budget set append `set`, `replace`, or `remove` transitions in the entering batch without mutating or duplicating the original baseline. An incompatible visible baseline is superseded by one complete baseline in current precedence order with explicit replacement language; when no current candidate exists, an explicit empty baseline clears the earlier scopes. A hot plugin remount follows the same rule. If compaction has shadowed the typed baseline, the next entering pre-step composes one complete current baseline and carries it in the same request.
 
 The baseline is a user-role `<system-reminder>` with `Instructions from: <path>` sections and explicit authority and precedence language. This familiar model-facing frame avoids a harness-specific XML vocabulary. Project paths are root-relative and the user-global path is `~/.dsh/AGENTS.md` for the default home or `$DSH_HOME/AGENTS.md` for a configured home. The final rendering boundary escapes a literal `</system-reminder>` anywhere in instruction content or model-visible path, scope, and budget metadata before byte accounting completes. The package README owns the exact current [prompt shape](../../../../packages/context/workspace-context/README.md#prompt-shape).
 
@@ -48,15 +48,15 @@ Shell commands are not discovery triggers. Local bash calls start fresh shells,
 
 ### Duplicate Suppression And Change Detection
 
-Every workspace context event stores versioned metadata with `{ action, scope, path, digest? }`, where `digest` is SHA-1 over the loaded content. Baselines additionally carry `baseline: true`. The model-facing prompt has no HTML comments, hidden markers, or headings that are parsed back into state.
+Every workspace context event stores versioned metadata with `{ action, scope, path, digest? }`, where `digest` is SHA-1 over the loaded content. Complete baselines additionally carry `baseline: true` and `baselineIdentity`. The model-facing prompt has no HTML comments, hidden markers, or headings that are parsed back into state.
 
 At reconciliation time the plugin scans workspace-sourced `user/message` events and derives the latest state for each visible scope. A short per-session pending map begins only after the immutable top-level `tools/result` proves an `additionalContexts` entry survived every post-execute listener, then covers the interval before the loop appends that context to the log. Each entry records the open `{ turn, step }`: an equal durable `user/message` at or after its sequence boundary confirms and removes it, while a matching `step/end` arriving first means the loop discarded its context buffer, so the plugin removes both the pending entry and its version-cache fast path. A nested Code Mode result stages its changes under the parent's opaque execution token so repeated sub-dispatches in one run do not duplicate them; the parent result rolls that provisional state back and commits only contexts retained by outer policy.
 
-An unchanged path and digest is suppressed. A logged removal is a tombstone, so a reappearing candidate becomes a new `set`. Resume works from persisted metadata. If compaction removes an instruction event from the visible surface, that state no longer suppresses a later load, matching the fact that the model can no longer see it. Only changes actually included under the byte budget enter metadata or pending state, so an omitted file remains eligible on a later touch.
+An unchanged path and digest is suppressed. A logged removal is a tombstone, so a reappearing candidate becomes a new `set`. Resume works from persisted metadata: a compatible visible baseline supplies comparison state rather than causing another complete baseline to be appended. If compaction removes an instruction event from the visible surface, that state no longer suppresses a later load, matching the fact that the model can no longer see it. Only changes actually included under the byte budget enter metadata or pending state, so an omitted file remains eligible on a later touch.
 
-The initial baseline's typed changes are comparison state only while its event remains in the visible session surface. A later successful filesystem touch re-adds an unchanged baseline scope after compaction, or appends baseline edits or removals as dynamic messages; it never rewrites the original event. The in-memory scope marker and provider-version cache only select and accelerate probes, so neither can suppress context the model no longer sees. During resumed baseline preparation the plugin also reconciles visible dynamic scopes, so nested changes made while the agent was offline can append an update before the first resumed request.
+The initial baseline's typed changes are comparison state only while its event remains in the visible session surface. Resume retains a compatible baseline and reconciles current baseline and visible dynamic scopes, so changes made while the agent was offline append transitions before the first resumed request. When compaction shadows the baseline event, the next entering pre-step composes the complete current baseline and records it in the same request; a successful filesystem touch can instead re-add an unchanged baseline scope or append baseline edits or removals as dynamic messages. Neither path rewrites the original event. The in-memory scope marker and provider-version cache only select and accelerate probes, so neither can suppress context the model no longer sees.
 
-There is intentionally no watcher. Detection occurs at the next successful structured filesystem touch or resumed baseline preparation. A provider failure produces no removal; absence is only accepted when all configured candidates in that scope were probed successfully.
+There is intentionally no watcher. Detection occurs at the next successful structured filesystem touch, resumed-baseline reconciliation, or entering pre-step that restores a shadowed baseline. A provider failure produces no removal; absence is only accepted when all configured candidates in that scope were probed successfully.
 
 ### Byte Budget And Bounded Reads
 
@@ -82,7 +82,7 @@ Workspace guidance is isolated per session and shared by the demo front doors, W
 
 Repository text remains untrusted input. Lower-authority user-role framing, explicit precedence language, and delimiter escaping reduce risk but do not eliminate prompt injection. Following a candidate symlink to its target widens that surface to off-tree content, so the permission and sandbox layers that confine `ctx.fs` to trusted roots are the boundary that treats workspace files as data rather than authority (the [instruction-symlink follow note](2026-07-21-follow-instruction-symlinks.md) owns the residual risk).
 
-The system is event-driven rather than watch-driven. Edits are not visible at the exact filesystem mutation instant unless that mutation goes through a structured tool; externally changed files are noticed on the next successful structured touch or resume. This keeps the design deterministic and provider-neutral.
+The system is event-driven rather than watch-driven. Edits are not visible at the exact filesystem mutation instant unless that mutation goes through a structured tool; externally changed files are noticed on the next successful structured touch, resume reconciliation, or restoration of a shadowed baseline. This keeps the design deterministic and provider-neutral.
 
 ## Deferred
 

.agents/notes/implemented/feature/2026-06-24-workspace-context.zh.md

@@ -30,9 +30,9 @@ Status: implemented
 
 在 agent loop（智能体循环）实例的第一个 `agent/pre-step`，插件会组合一条带来源的 user 角色基线。当下游决策让非空的第一步批次进入时，插件会将基线折入最终批次、紧随已领取的直接提示词之后，使其与直接提示词一同成为持久记录并抵达第一次请求。reject 或空的第一步决策会将基线留在 next-step inbox，等待后续唤醒。插件先加载用户全局文件，再从 `agent.session.header.cwd` 向上遍历至配置的根标记（默认为 `.git`）以确定项目根目录，随后从根目录至 cwd 的每级目录加载已配置候选项。`.git` 文件与 `.git` 目录都是有效标记，因而能覆盖链接 worktree 和 submodule。找不到标记时，cwd 本身就是根目录。
 
-该基线会成为一条持久 `user/message`，并携带带类型的 `workspace-instructions` 来源。其 `baseline: true` 标记将完整的启动或恢复基线与后续增量区分开来，变更列表则持久保存已纳入的作用域和内容 digest。若先前排队的 workspace 基线仍在等待，插件会删除该确切消息并 prepend 替代值，而不会累积副本。
+该基线会成为一条持久 `user/message`，并携带带类型的 `workspace-instructions` 来源。其 `baseline: true` 标记将完整基线与后续增量区分开来，`baselineIdentity` 记录规范化的发现、优先级、项目根目录和预算语义，变更列表则持久保存已纳入的作用域和内容 digest。若先前排队的 workspace 基线仍在等待，插件会删除该确切消息并 prepend 替代值，而不会累积副本。
 
-恢复 agent 会创建新的循环实例，并在其第一次请求前注入由当前文件组合的基线。这样，恢复时可以使用当前基线内容，而无需修改先前的历史事件。恢复与插件热重挂都会面对日志中可能已存在基线的情况；二者通过 `agent/session-start` 区分：启动或恢复会在第一步前发出该事件，而热重挂附着到一个已存活的会话、永远不会看到它。只有当基线的类型化事件仍在当前可见表层中时，热重挂才保留既有基线，同时仍会根据当前文件重建 scope 与提供方版本跟踪。如果压缩（compaction）已遮蔽该事件，热重挂会注入当前基线。恢复则始终重新组合。
+恢复 agent 会基于持久化历史创建新的 loop 实例。在第一个 `agent/pre-step`，具有当前标识的可见基线仍是权威状态；插件会将其保留的 scope 与当前完整渲染进行比较。未变化和被预算省略的文件不追加任何内容；agent 离线期间新增、编辑、移除或不再属于预算保留集的文件，会在进入步骤的批次中追加 `set`、`replace` 或 `remove` 转换，既不改写也不重复原始基线。不兼容的可见基线会被一条按当前优先级排列的完整基线取代，并以明确措辞说明替换关系；如果当前不存在任何候选文件，一条显式空基线会清除先前的 scope。插件热重挂遵循相同规则。如果压缩（compaction）已遮蔽带类型的基线，下一次进入步骤的 pre-step 会组合一条完整的当前基线，并在同一请求中携带它。
 
 基线是一条 user 角色的 `<system-reminder>`，包含 `Instructions from: <path>` 章节，以及明确的权威性与优先级说明。这种熟悉的模型可见框架避免引入 harness 专用的 XML 词汇。项目路径相对于根目录；使用默认 home 时，用户全局路径为 `~/.dsh/AGENTS.md`，使用已配置 home 时则为 `$DSH_HOME/AGENTS.md`。最终渲染边界会在完成字节核算前，转义指令内容或模型可见的路径、scope 与预算元数据中出现的字面量 `</system-reminder>`。包 README 负责规定当前准确的[提示词形态](../../../../packages/context/workspace-context/README.md#prompt-shape)。
 
@@ -48,15 +48,15 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，
 
 ### 重复抑制与变更检测
 
-每个工作区上下文事件都会存储带版本的元数据，其形态为 `{ action, scope, path, digest? }`；`digest` 是对已加载内容计算的 SHA-1。基线还会额外携带 `baseline: true`。模型可见提示词中没有 HTML 注释、隐藏标记，也没有会被解析回状态的标题。
+每个工作区上下文事件都会存储带版本的元数据，其形态为 `{ action, scope, path, digest? }`；`digest` 是对已加载内容计算的 SHA-1。完整基线还会额外携带 `baseline: true` 和 `baselineIdentity`。模型可见提示词中没有 HTML 注释、隐藏标记，也没有会被解析回状态的标题。
 
 协调时，插件扫描带工作区来源的 `user/message` 事件，并派生每个可见作用域的最新状态。一个简短的逐会话待处理映射只会在不可变的顶层 `tools/result` 证明某个 `additionalContexts` 条目经过所有 post-execute 监听器后仍然保留时开始记录；随后，它覆盖循环将该上下文追加到日志之前的间隔。每个条目记录开启状态的 `{ turn, step }`：如果相同的持久 `user/message` 出现在其序列边界或之后，该条目得到确认并被移除；如果匹配的 `step/end` 先到达，则说明循环丢弃了上下文缓冲区，插件会同时移除待处理条目及其版本缓存快速路径。嵌套的 Code Mode 结果会把变更暂存在父级的不透明执行 token 下，确保一次运行中的重复子分发不会产生重复项；父级结果会回滚这份临时状态，并且只提交外层策略保留的上下文。
 
-路径和 digest 均未变化时会被抑制。日志中的移除操作是一条墓碑记录，因此重新出现的候选项会成为新的 `set`。恢复操作从持久化元数据继续工作。如果压缩从可见表面移除某条指令事件，该状态不再抑制后续加载，这与模型已经无法看见它的事实一致。只有真正纳入字节预算的变更才会进入元数据或待处理状态，因此被省略的文件在之后的触碰中仍有资格加载。
+路径和 digest 均未变化时会被抑制。日志中的移除操作是一条墓碑记录，因此重新出现的候选项会成为新的 `set`。恢复操作从持久化元数据继续工作：兼容的可见基线会提供比较状态，而不会导致再次追加完整基线。如果压缩从可见表面移除某条指令事件，该状态不再抑制后续加载，这与模型已经无法看见它的事实一致。只有真正纳入字节预算的变更才会进入元数据或待处理状态，因此被省略的文件在之后的触碰中仍有资格加载。
 
-只有当初始基线事件仍在可见会话表层中时，其类型化变更才用作比较状态。后续成功的文件系统触碰会在压缩后重新添加未变化的基线 scope，或把基线编辑或移除操作追加为动态消息；它绝不重写原始事件。内存中的 scope 标记和提供方版本 cache 只用于选择探测对象并加速探测，因此二者都不能抑制模型已无法看见的上下文。恢复时准备基线的过程中，插件还会协调可见的动态作用域，因此 agent 离线期间发生的嵌套变更可以在第一次恢复请求前追加更新。
+只有当初始基线事件仍在可见会话表层中时，其类型化变更才用作比较状态。恢复会保留兼容的基线，并对账当前基线和可见的动态 scope，因此 agent 离线期间的变更会在第一次恢复请求前追加为转换。当压缩遮蔽基线事件时，下一次进入步骤的 pre-step 会组合完整的当前基线，并在同一请求中记录它；也可以改由一次成功的文件系统触碰重新添加未变化的基线 scope，或把基线编辑或移除操作追加为动态消息。两条路径都不会重写原始事件。内存中的 scope 标记和提供方版本 cache 只用于选择探测对象并加速探测，因此二者都不能抑制模型已无法看见的上下文。
 
-系统刻意不使用文件监视器。检测发生在下一次成功的结构化文件系统触碰或恢复时的基线准备。提供方失败不会产生移除；只有该作用域中的全部已配置候选项都成功完成探测后，系统才接受「不存在」这一结论。
+系统刻意不使用文件监视器。检测发生在下一次成功的结构化文件系统触碰、恢复时的基线对账，或进入步骤的 pre-step 恢复被遮蔽的基线时。提供方失败不会产生移除；只有该作用域中的全部已配置候选项都成功完成探测后，系统才接受「不存在」这一结论。
 
 ### 字节预算与有界读取
 
@@ -82,7 +82,7 @@ shell 命令不会触发发现。本地 bash 调用会启动全新的 shell，
 
 仓库文本仍是不受信任的输入。低权威 user 角色框架、显式优先级说明和分隔符转义可以降低风险，但无法消除提示词注入。跟随候选符号链接到目标，会把该攻击面扩大至树外内容；因此，把 `ctx.fs` 限制在可信根目录内的权限与沙箱层才是真正的边界，它们让系统把工作区文件当作数据而不是权威（[跟随指令符号链接记录](2026-07-21-follow-instruction-symlinks.md)负责说明残余风险）。
 
-系统由事件驱动，而不是文件监视器驱动。除非文件系统变更通过结构化工具完成，否则编辑不会在确切的文件系统变更时刻可见；外部文件变更会在下一次成功的结构化触碰或恢复时被发现。这使设计保持确定性并且与提供方无关。
+系统由事件驱动，而不是文件监视器驱动。除非文件系统变更通过结构化工具完成，否则编辑不会在确切的文件系统变更时刻可见；外部文件变更会在下一次成功的结构化触碰、恢复对账，或恢复被遮蔽的基线时被发现。这使设计保持确定性并且与提供方无关。
 
 ## 延后事项
 

.agents/notes/implemented/feature/2026-06-30-interception-seams.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-06-30-interception-seams.md
-2026-06-30-interception-seams.md: 629a1aed509bd9bce9a2da89ce84b17a1db8e6b6
-2026-06-30-interception-seams.zh.md: d6958c9d1e7a8af8fa06d859d1905719a19cd43d
+2026-06-30-interception-seams.md: c318e41cfb1d64230b6151f1febad85d75b1451d
+2026-06-30-interception-seams.zh.md: 1b274fae4bc7fde326dbb0eeec54d57f73987803

.agents/notes/implemented/feature/2026-06-30-interception-seams.md

@@ -15,8 +15,8 @@ The surface needs distinct contracts for per-prompt policy (CC's `UserPromptSubm
 The canonical surface separates transformable policy, around-dispatch control, and observe-only notification. Policy waterfalls return small seam-specific **typed Decision unions**; wrappers return normalized results; notifications receive immutable snapshots and cannot affect the outcome. The set covers the hook points in scope (`session-start`, `prompt-submit`, `pre-tool`, `post-tool`, `stop`-via-continuation) while leaving non-hook execution policy independently composable.
 
 **Agent events** (`dsh-agent`):
-- `agent/session-start(agent, source)` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`.
-- `agent/pre-step(agent, messages, context, next) → PreStepDecision` — waterfall, fired before every proposed step after the loop has atomically removed its exclusive inbox batch. `PreStepContext` carries that request's `turn`, `step`, and cancellation `signal`; `messages` is empty for a tool continuation with no intervening input. `enter` returns the complete message batch, including any current-request context a listener contributes; `reject` opens no step and leaves the claimed messages removed.
+- `agent/session-start({ agent, source })` — emit, once before turn 1, carrying a `SessionStartSource` (`startup` for a fresh/forked create, `resume` for a reloaded persisted session; `clear`/`compact` reserved). A pure notification — it CANNOT block startup (a deliberate gap: a bridge logs/injects, it does not gate startup). A listener seeds context via `agent.inject()`.
+- `agent/pre-step({ agent, messages, turn, step, signal }, next) → PreStepDecision` — waterfall, fired before every proposed step after the loop has atomically removed its exclusive inbox batch. The payload carries the request's `turn`, `step`, and cancellation `signal` (the retired `PreStepContext` fields live in the payload; see the [payload-object events decision](../architecture/2026-08-06-agent-event-payload-objects.md)); `messages` is empty for a tool continuation with no intervening input. `enter` returns the complete message batch, including any current-request context a listener contributes; `reject` opens no step and leaves the claimed messages removed.
 
 **`agent/turn-stopping`** is an awaited notification at the natural stop boundary. A listener that needs another step calls `agent.steer()` with explicitly sourced model-facing content; the loop then re-reads the outbox and either continues or closes the turn.
 

.agents/notes/implemented/feature/2026-06-30-interception-seams.zh.md

@@ -15,8 +15,8 @@ harness 需要一套钩子子系统：用户像 Claude Code（CC）和 Codex 那
 规范表面将可变换策略、环绕调度控制与仅观测通知分离。策略 waterfall（瀑布式事件）返回小型的、seam 专属的**类型化 Decision 联合类型**；包装层返回规范化结果；通知接收不可变快照，无法影响结果。覆盖的钩子点包括 `session-start`、`prompt-submit`、`pre-tool`、`post-tool`、通过 continuation 实现的 `stop`，同时将非钩子的执行策略留作独立可组合。
 
 **Agent 事件**（`dsh-agent`）：
-- `agent/session-start(agent, source)` ——emit，在第 1 轮次之前触发一次，携带 `SessionStartSource`（`startup` 表示全新/fork 创建，`resume` 表示重新加载的持久化会话；`clear`/`compact` 保留）。纯通知，不能阻塞启动（这是有意的空白：桥接可以记录/注入，但不管控启动）。监听器通过 `agent.inject()` 注入上下文。
-- `agent/pre-step(agent, messages, context, next) → PreStepDecision` ——waterfall，在每个拟议步骤之前、循环原子移除其独占 inbox 批次后触发。`PreStepContext` 携带该请求的 `turn`、`step` 与取消 `signal`；没有中途输入的工具续步会收到空批次。`enter` 返回完整消息批次，其中包括监听器为当前请求贡献的上下文；`reject` 不打开步骤，并让已领取消息保持已删除。
+- `agent/session-start({ agent, source })` ——emit，在第 1 轮次之前触发一次，携带 `SessionStartSource`（`startup` 表示全新/fork 创建，`resume` 表示重新加载的持久化会话；`clear`/`compact` 保留）。纯通知，不能阻塞启动（这是有意的空白：桥接可以记录/注入，但不管控启动）。监听器通过 `agent.inject()` 注入上下文。
+- `agent/pre-step({ agent, messages, turn, step, signal }, next) → PreStepDecision` ——waterfall，在每个拟议步骤之前、循环原子移除其独占 inbox 批次后触发。payload 携带该请求的 `turn`、`step` 与取消 `signal`（已退役的 `PreStepContext` 字段位于 payload 中；参见 [payload-object 事件决策](../architecture/2026-08-06-agent-event-payload-objects.md)）；没有中途输入的工具续步会收到空批次。`enter` 返回完整消息批次，其中包括监听器为当前请求贡献的上下文；`reject` 不打开步骤，并让已领取消息保持已删除。
 
 **`agent/turn-stopping`** 是自然停止边界上的一次 awaited 通知。需要再执行一步的监听器调用 `agent.steer()`，传入来源显式的 steering（中途引导）内容供模型使用；循环随后重新读取 outbox，继续执行或关闭轮次。
 

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md
-2026-07-20-dsh-cli-personal-config.md: 1fa8cda2b34b58cc7a28b722872520b68a9b7009
-2026-07-20-dsh-cli-personal-config.zh.md: e70b8914cf005e0a2e54ba2b29d3b7def84b00db
+2026-07-20-dsh-cli-personal-config.md: 10f16a1cbabdd8cd383c59ad8e09787c02d0109a
+2026-07-20-dsh-cli-personal-config.zh.md: 22435efbec8ea661c546ffd0c1aa9bb0ff2ebbb2

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.md

@@ -10,6 +10,8 @@ A developer's own preferences — which provider and model the TUI uses, persona
 
 ## Decision
 
+The entry modes and the personal file's name and location below are superseded by the [profile plugin bundles decision](../architecture/2026-08-05-profile-plugin-bundles.md): `dsh` boots profiles, and the personal layer became the per-profile and home-level `cordis.patch.yml`. What survives unchanged is this note's substance — the Harness home as the machine-level layer's root, patch semantics over a shipped composition, and fail-loud parsing.
+
 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.
@@ -46,4 +48,4 @@ The TUI and Web register the exact personal path through Cordis HMR after boot.
 
 ## Testing
 
-`packages/ui/app-boot/tests/personal-config.spec.ts` pins parsing, startup application, exact-path add/failure/recovery/removal, last-good rollback, failure broadcast, and preservation of app-owned patches. `examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` boots the real dsh bin with no overlay, a personal environment and UI patch, a config-only cached repository skill, and invalid personal YAML. Test launchers isolate `$DSH_HOME`, so a developer's real overlay cannot leak into fixtures.
+`packages/ui/app-boot/tests/user-patches.spec.ts` pins parsing, startup application, exact-path add/failure/recovery/removal, last-good rollback, failure broadcast, and preservation of app-owned patches. `apps/cli/tests/built-bin.e2e.ts` boots the real dsh bin over a profile and exercises the live patch layer end to end. Test launchers isolate `$DSH_HOME`, so a developer's real overlay cannot leak into fixtures.

.agents/notes/implemented/feature/2026-07-20-dsh-cli-personal-config.zh.md

@@ -10,6 +10,8 @@ Status: implemented
 
 ## Decision
 
+下文的各入口模式，以及个人文件的名称与位置，已被 [profile 插件组合包决策](../architecture/2026-08-05-profile-plugin-bundles.md)取代：`dsh` 启动 profile，个人层变成逐 profile 与 home 级的 `cordis.patch.yml`。保留不变的是本笔记的实质：以 Harness home 作为机器级层的根目录、在随附组合之上使用 patch 语义，以及解析时的大声失败。
+
 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；该契约由[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。
@@ -46,4 +48,4 @@ TUI 和 Web 启动后通过 Cordis HMR（热模块替换）注册确切的个人
 
 ## Testing
 
-`packages/ui/app-boot/tests/personal-config.spec.ts` 固定解析、启动时应用、确切路径的新增／失败／恢复／移除、最后可用状态回滚、失败广播以及应用自有 patch 的保留。`examples/tui-agent/tests/tui-keyless-smoke.e2e.ts` 启动真实 dsh bin，覆盖无 overlay、个人环境与 UI patch、纯配置的缓存 repository skill，以及无效个人 YAML。测试启动器会隔离 `$DSH_HOME`，因此开发者的真实 overlay 不会泄漏进 fixture。
+`packages/ui/app-boot/tests/user-patches.spec.ts` 固定解析、启动时应用、确切路径的新增／失败／恢复／移除、最后可用状态回滚、失败广播以及应用自有 patch 的保留。`apps/cli/tests/built-bin.e2e.ts` 启动真实 dsh bin 并基于 profile 端到端验证实时 patch 层。测试启动器会隔离 `$DSH_HOME`，因此开发者的真实 overlay 不会泄漏进 fixture。

.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.md
-2026-07-29-persistent-bash-str-replace-editor.md: 22851078c1cc8fa9d5716afa41c8a2e2b7e7725c
-2026-07-29-persistent-bash-str-replace-editor.zh.md: 23f80d1a5911f4f3820d526c2221d3002507d774
+2026-07-29-persistent-bash-str-replace-editor.md: c4750e30370bfd253064c39cb1adc0f5b2baa60d
+2026-07-29-persistent-bash-str-replace-editor.zh.md: 62073571ce2164d88897d4959caafd9cb1dbdd93

.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.md

@@ -18,7 +18,7 @@ Some deployments need a one-call Bash schema whose shell state survives across m
 
 Both plugins are included in the Python runtime closure. The persistent Bash closure also includes the PTY service/local backend and the sandbox services required by that backend. Because `node-pty` executes a native `spawn-helper` on macOS, each packaged macOS runtime executable ships with a `-spawn-helper` sibling; Linux uses `forkpty` directly. A pinned `node-pty` patch checks `DSH_NODE_PTY_SPAWN_HELPER` first, so it remains a true override for a current external consumer that supplies a non-sibling helper. When the override is unset, the patch resolves the packaged executable sibling if present and otherwise preserves upstream lookup in ordinary Node runs. The macOS builders fail before publication when the helper is absent or not executable.
 
-The shipped [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) overlay composes both plugins over the ordinary Web surface, disables its other model-facing consumers, and leaves the Web host, browser, Workspace, persistence, sandbox, and permission stack in place. The local PTY backend resolves the effective session sandbox mode when it creates the shell. While that owner has an open shell or a spawn in progress, a different permission mode is rejected before its session event commits; the editor continues through the Web filesystem sandbox.
+The shipped [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) overlay composes both plugins over the ordinary Web surface for the Claude SWE-compatible RL contract. It pins native tool mode and makes the complete system prompt `DSH_SYSTEM_PROMPT` when set or `You are a helpful software engineer assistant.` otherwise, with no harness identity, source-checkout section, Web orientation, Workspace instructions, or tool-mode guidance. It disables every other model-facing consumer, so the model receives exactly the persistent `bash` and `str_replace_editor` schemas, while the Web host, browser, Workspace, persistence, sandbox, and permission stack remains in place. The local PTY backend resolves the effective session sandbox mode when it creates the shell. While that owner has an open shell or a spawn in progress, a different permission mode is rejected before its session event commits; the editor continues through the Web filesystem sandbox.
 
 ## Alternatives considered
 

.agents/notes/implemented/feature/2026-07-29-persistent-bash-str-replace-editor.zh.md

@@ -18,7 +18,7 @@ Status: implemented
 
 两个插件都进入 Python runtime 闭包。持久 Bash 的闭包还包含 PTY 服务／本地后端，以及该后端要求的沙箱服务。由于 `node-pty` 在 macOS 上会执行原生 `spawn-helper`，每个打包后的 macOS 运行时可执行文件都会携带一个 `-spawn-helper` 伴随文件；Linux 直接使用 `forkpty`。固定版本的 `node-pty` 补丁会先检查 `DSH_NODE_PTY_SPAWN_HELPER`，因此对当前提供非伴随 helper 的外部消费方而言，该变量仍是真正的覆盖项。未设置该覆盖时，补丁会在打包可执行文件的伴随文件存在时解析它，否则在普通 Node 运行中保留上游查找方式。若 helper 缺失或不可执行，macOS 构建器会在发布前失败。
 
-已交付的 [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) 覆盖层在常规 Web 界面之上组合这两个插件，禁用该界面的其他面向模型的消费方，并保留 Web 宿主、浏览器、Workspace、持久化、沙箱与权限栈。本地 PTY 后端会在创建 shell 时解析会话的有效沙箱模式。只要该所有者仍有打开的 shell 或仍在进行中的 spawn，另一种权限模式就会在对应的会话事件提交前遭到拒绝；编辑器则继续经由 Web 文件系统沙箱运行。
+已交付的 [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) overlay 会在常规 Web 界面之上组合这两个插件，以满足与 Claude SWE 兼容的 RL 契约。它固定使用原生工具模式；完整的系统提示词在设置 `DSH_SYSTEM_PROMPT` 时采用其值，否则采用 `You are a helpful software engineer assistant.`，且不包含 harness 身份、源码 checkout 提示词段、Web 界面定位、Workspace 指令或工具模式指引。它会禁用其他所有面向模型的消费方，使模型恰好只收到持久 `bash` 和 `str_replace_editor` 两个 schema，同时保留 Web 宿主、浏览器、Workspace、持久化、沙箱与权限栈。本地 PTY 后端会在创建 shell 时解析会话的有效沙箱模式。只要该所有者仍有打开的 shell 或仍在进行中的 spawn，另一种权限模式就会在对应的会话事件提交前遭到拒绝；编辑器则继续经由 Web 文件系统沙箱运行。
 
 ## 考虑过的替代方案
 

.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md
-2026-07-31-even-out-shipped-tool-rosters.md: 312e61d017abad1a6ac57f2ba491a715f8fd92d0
-2026-07-31-even-out-shipped-tool-rosters.zh.md: c77370c312004052bc4f8ee9545ed287a6d92554
+2026-07-31-even-out-shipped-tool-rosters.md: d12db993654d9f2b41a16a4663dc64aefe8e3a2f
+2026-07-31-even-out-shipped-tool-rosters.zh.md: 8381a457def1a909b300de52dc011e2437c7e9f3

.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.md

@@ -12,7 +12,7 @@ The result was a user-visible difference nobody had decided: the same model, ask
 
 ## Decision
 
-The rows that are not surface-specific move into [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml), and three more join them: `tool-session-query`, `tool-str-replace-editor`, and `repeat-tool-guard`. Web search moves there too; its [deployment decision](2026-07-31-web-default-search.md) owns the security boundary while the shared base owns its surface-neutral mount. Both surfaces assemble the same roster: twenty-two tools on every host — the twenty shared rows plus `glob` and `grep`, which are fixed members because `dsh-tool-fs-search` spawns the [packaged ripgrep binary](../architecture/2026-08-01-packaged-ripgrep-search.md). `tool-session-query` joined and then left again — the [session-search-not-shipped-default decision](2026-08-02-session-search-not-shipped-default.md) keeps the model-facing consumer opt-in — while the rest of this roster stands.
+The rows that are not surface-specific move into [`base.cordis.yml`](../../../../packages/bundle/base/cordis.patch.yml), and three more join them: `tool-session-query`, `tool-str-replace-editor`, and `repeat-tool-guard`. Web search moves there too; its [deployment decision](2026-07-31-web-default-search.md) owns the security boundary while the shared base owns its surface-neutral mount. Both surfaces assemble the same roster: twenty-two tools on every host — the twenty shared rows plus `glob` and `grep`, which are fixed members because `dsh-tool-fs-search` spawns the [packaged ripgrep binary](../architecture/2026-08-01-packaged-ripgrep-search.md). `tool-session-query` joined and then left again — the [session-search-not-shipped-default decision](2026-08-02-session-search-not-shipped-default.md) keeps the model-facing consumer opt-in — while the rest of this roster stands.
 
 Two rows stay surface-specific. `tmux-context` is TUI-only because a browser surface has no terminal multiplexer to describe. `session-reference` is TUI-only because it drives the shared session-query index from the launcher's process-local path, and the browser sidebar reconciles that index on its own first search.
 

.agents/notes/implemented/feature/2026-07-31-even-out-shipped-tool-rosters.zh.md

@@ -12,7 +12,7 @@ Status: implemented
 
 ## 决策
 
-那些并非 surface 专属的行移入 [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml),另有三行加入:`tool-session-query`、`tool-str-replace-editor` 和 `repeat-tool-guard`。Web 搜索也一并移入；其[部署决策](2026-07-31-web-default-search.md)负责安全边界，共享 base 则负责与 surface 无关的挂载。两个 surface 组装同一份清单：每台宿主上都有二十二个工具——二十个共享行加上 `glob` 和 `grep`，它们成为固定成员，因为 `dsh-tool-fs-search` 直接 spawn [打包的 ripgrep 二进制](../architecture/2026-08-01-packaged-ripgrep-search.md)。`tool-session-query` 加入后又退出了——[session-search-not-shipped-default 决策](2026-08-02-session-search-not-shipped-default.md)让面向模型的消费方保持需显式启用——而这份清单的其余部分保持不变。
+那些并非 surface 专属的行移入 [`base.cordis.yml`](../../../../packages/bundle/base/cordis.patch.yml),另有三行加入:`tool-session-query`、`tool-str-replace-editor` 和 `repeat-tool-guard`。Web 搜索也一并移入；其[部署决策](2026-07-31-web-default-search.md)负责安全边界，共享 base 则负责与 surface 无关的挂载。两个 surface 组装同一份清单：每台宿主上都有二十二个工具——二十个共享行加上 `glob` 和 `grep`，它们成为固定成员，因为 `dsh-tool-fs-search` 直接 spawn [打包的 ripgrep 二进制](../architecture/2026-08-01-packaged-ripgrep-search.md)。`tool-session-query` 加入后又退出了——[session-search-not-shipped-default 决策](2026-08-02-session-search-not-shipped-default.md)让面向模型的消费方保持需显式启用——而这份清单的其余部分保持不变。
 
 有两行仍是 surface 专属。`tmux-context` 只在 TUI,因为浏览器 surface 没有终端复用器可描述。`session-reference` 只在 TUI,因为它以 launcher 的进程本地路径驱动共享的 session-query 索引,而浏览器侧边栏会在自己的首次搜索里重建该索引。
 

.agents/notes/implemented/feature/2026-07-31-workspace-write-surface-default.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-07-31-workspace-write-surface-default.md
-2026-07-31-workspace-write-surface-default.md: a0b216122e301b5332ed761155d743dc78fa3bab
-2026-07-31-workspace-write-surface-default.zh.md: 4391daa32b142ea976e3b04833163936913c17bc
+2026-07-31-workspace-write-surface-default.md: e6a36ad4ee7179cabf958114681728c3ac7340b4
+2026-07-31-workspace-write-surface-default.zh.md: 5ced928b167892d9abe1f4423da72a0243590735

.agents/notes/implemented/feature/2026-07-31-workspace-write-surface-default.md

@@ -10,7 +10,7 @@ The shipped terminal and browser surfaces exposed the same coding tools under di
 
 ## Decision
 
-[`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml) owns one sandbox and permission stack for every shipped TUI, Web, and browser-backed headless session: `dsh-sandbox-local`, `dsh-sandbox-policy`, `dsh-bash-sandbox`, `dsh-fs-sandbox`, `dsh-user-approval`, and `dsh-permission`. The composition fallback is the `workspace-write` preset, which bundles `workspace-write` file effects with the `ask` approval policy. `DSH_PERMISSION_MODE` remains an explicit process override; a stored `permission.defaultPreset` remains the user preference for later sessions and outranks the fallback through the Settings seam.
+[`base.cordis.yml`](../../../../packages/bundle/base/cordis.patch.yml) owns one sandbox and permission stack for every shipped TUI, Web, and browser-backed headless session: `dsh-sandbox-local`, `dsh-sandbox-policy`, `dsh-bash-sandbox`, `dsh-fs-sandbox`, `dsh-user-approval`, and `dsh-permission`. The composition fallback is the `workspace-write` preset, which bundles `workspace-write` file effects with the `ask` approval policy. `DSH_PERMISSION_MODE` remains an explicit process override; a stored `permission.defaultPreset` remains the user preference for later sessions and outranks the fallback through the Settings seam.
 
 A genuinely fresh session pins `permission/preset: workspace-write`, `sandbox/mode: workspace-write`, and `approval/policy: ask` before execution. Existing and resumed sessions retain their logged permission, and changing the General-settings default affects only sessions created afterward. The browser keeps its Access picker, answerable approval cards, and risk confirmation for Full access. The TUI gains the existing `/permission` command because the shared Permission service activates its command child there.
 

.agents/notes/implemented/feature/2026-07-31-workspace-write-surface-default.zh.md

@@ -10,7 +10,7 @@ Status: implemented
 
 ## 决策
 
-[`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml) 为所有已交付的 TUI、Web 以及由浏览器支撑的无头会话统一持有一套沙箱与权限栈：`dsh-sandbox-local`、`dsh-sandbox-policy`、`dsh-bash-sandbox`、`dsh-fs-sandbox`、`dsh-user-approval` 和 `dsh-permission`。组合回退值为 `workspace-write` preset，其中包含 `workspace-write` 文件效果模式与 `ask` 审批策略。`DSH_PERMISSION_MODE` 仍是显式的进程级覆盖；已存储的 `permission.defaultPreset` 仍是面向后续会话的用户偏好，并通过 Settings seam 优先于该回退值。
+[`base.cordis.yml`](../../../../packages/bundle/base/cordis.patch.yml) 为所有已交付的 TUI、Web 以及由浏览器支撑的无头会话统一持有一套沙箱与权限栈：`dsh-sandbox-local`、`dsh-sandbox-policy`、`dsh-bash-sandbox`、`dsh-fs-sandbox`、`dsh-user-approval` 和 `dsh-permission`。组合回退值为 `workspace-write` preset，其中包含 `workspace-write` 文件效果模式与 `ask` 审批策略。`DSH_PERMISSION_MODE` 仍是显式的进程级覆盖；已存储的 `permission.defaultPreset` 仍是面向后续会话的用户偏好，并通过 Settings seam 优先于该回退值。
 
 真正的新会话会在执行前固定 `permission/preset: workspace-write`、`sandbox/mode: workspace-write` 和 `approval/policy: ask`。现有会话和恢复的会话保留日志中记录的权限，更改「通用」设置中的默认值只影响之后创建的会话。浏览器保留 Access 选择器、可应答的审批卡片，以及选择 Full access 时的风险确认。共享 Permission 服务在 TUI 中激活其命令子件，因此 TUI 会获得现有的 `/permission` 命令。
 

.agents/notes/implemented/feature/2026-08-02-session-search-not-shipped-default.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-02-session-search-not-shipped-default.md
-2026-08-02-session-search-not-shipped-default.md: ba7299712c0ba3db5e807e928f6f5d98ac917187
-2026-08-02-session-search-not-shipped-default.zh.md: 1678ebfb5514003eabe0221e460c619bab1aa444
+2026-08-02-session-search-not-shipped-default.md: 65bd72fff76210b726e7562fb8e88e5f8802434a
+2026-08-02-session-search-not-shipped-default.zh.md: 5e42a2c2323904117f9322b5c4a53c43c6ed3f2a

.agents/notes/implemented/feature/2026-08-02-session-search-not-shipped-default.md

@@ -6,11 +6,11 @@ English | [中文](2026-08-02-session-search-not-shipped-default.zh.md)
 
 ## Problem
 
-The [shipped-roster decision](2026-07-31-even-out-shipped-tool-rosters.md) made `tool-session-query` a default row of the shared [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml), so the shipped TUI and Web surfaces put the five session-search tools (`session_search`, `session_event_search`, `session_trace`, `session_event_trace`, `session_event_read`) in front of the model. That contradicted the [model-facing session-query-tools decision](2026-07-24-model-facing-session-query-tools.md), whose opt-in stance the package README recorded as "shipped host compositions do not mount it by default". The default also shipped a prompt section teaching a prior-work search workflow that no user had asked for.
+The [shipped-roster decision](2026-07-31-even-out-shipped-tool-rosters.md) made `tool-session-query` a default row of the shared [`cordis.patch.yml`](../../../../packages/bundle/base/cordis.patch.yml), so the shipped TUI and Web surfaces put the five session-search tools (`session_search`, `session_event_search`, `session_trace`, `session_event_trace`, `session_event_read`) in front of the model. That contradicted the [model-facing session-query-tools decision](2026-07-24-model-facing-session-query-tools.md), whose opt-in stance the package README recorded as "shipped host compositions do not mount it by default". The default also shipped a prompt section teaching a prior-work search workflow that no user had asked for.
 
 ## Decision
 
-The shipped TUI, Web, and headless surfaces no longer mount `@deepseek-ai/dsh-tool-session-query`: the row is removed from the shared `base.cordis.yml`, the now-dangling `disabled` patch in the opt-in [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) profile goes with it, and the workspace dependency drops from `apps/cli/package.json`. The consumer stays opt-in exactly as the model-facing-session-query-tools note describes: the ACP example's [`session-query.cordis.yml`](../../../../examples/acp-agent/session-query.cordis.yml) and its snapshot counterpart remain the mounted reference, and a custom composition can mount the package with the timeout and spill policies.
+The shipped TUI, Web, and headless surfaces no longer mount `@deepseek-ai/dsh-tool-session-query`: the row is removed from the shared `cordis.patch.yml`, the now-dangling `disabled` patch in the opt-in [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) profile goes with it, and the workspace dependency drops from `apps/cli/package.json`. The consumer stays opt-in exactly as the model-facing-session-query-tools note describes: the ACP example's [`session-query.cordis.yml`](../../../../examples/acp-agent/session-query.cordis.yml) and its snapshot counterpart remain the mounted reference, and a custom composition can mount the package with the timeout and spill policies.
 
 The `ctx.sessionQuery` service itself stays mounted. `session-query-sqlite` remains a base row — the TUI's `session-reference` consumes it for `/resume` — and the Web overlay keeps patching it to an in-memory index for the browser content search. Only the model-facing consumer is removed.
 

.agents/notes/implemented/feature/2026-08-02-session-search-not-shipped-default.zh.md

@@ -6,11 +6,11 @@ Status: implemented
 
 ## 问题
 
-[交付清单决策](2026-07-31-even-out-shipped-tool-rosters.md)把 `tool-session-query` 设为共享 [`base.cordis.yml`](../../../../apps/cli/config/base.cordis.yml) 的默认行,于是交付的 TUI 与 Web surface 把这五个会话搜索工具(`session_search`、`session_event_search`、`session_trace`、`session_event_trace`、`session_event_read`)呈现给了模型。这与[面向模型的会话查询工具决策](2026-07-24-model-facing-session-query-tools.md)相抵触,该决策持需显式启用的立场,包 README 将其记录为「shipped host compositions do not mount it by default」。这份默认还交付了一个提示词段,向模型讲授一套既往工作搜索工作流,而没有任何用户要求过。
+[交付清单决策](2026-07-31-even-out-shipped-tool-rosters.md)把 `tool-session-query` 设为共享 [`cordis.patch.yml`](../../../../packages/bundle/base/cordis.patch.yml) 的默认行,于是交付的 TUI 与 Web surface 把这五个会话搜索工具(`session_search`、`session_event_search`、`session_trace`、`session_event_trace`、`session_event_read`)呈现给了模型。这与[面向模型的会话查询工具决策](2026-07-24-model-facing-session-query-tools.md)相抵触,该决策持需显式启用的立场,包 README 将其记录为「shipped host compositions do not mount it by default」。这份默认还交付了一个提示词段,向模型讲授一套既往工作搜索工作流,而没有任何用户要求过。
 
 ## 决策
 
-交付的 TUI、Web 与无头 surface 不再挂载 `@deepseek-ai/dsh-tool-session-query`:该行从共享的 `base.cordis.yml` 移除,opt-in 的 [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) profile 中那条已悬空的 `disabled` patch 也随之删除,workspace 依赖也从 `apps/cli/package.json` 中移除。该消费方仍保持 opt-in,与面向模型的会话查询工具决策所述完全一致:ACP 示例的 [`session-query.cordis.yml`](../../../../examples/acp-agent/session-query.cordis.yml) 及其快照对侧文件仍是挂载参考,自定义组合也可以连同超时与 spill 策略一起挂载该包。
+交付的 TUI、Web 与无头 surface 不再挂载 `@deepseek-ai/dsh-tool-session-query`:该行从共享的 `cordis.patch.yml` 移除,opt-in 的 [`core-web.cordis.yml`](../../../../apps/cli/config/core-web.cordis.yml) profile 中那条已悬空的 `disabled` patch 也随之删除,workspace 依赖也从 `apps/cli/package.json` 中移除。该消费方仍保持 opt-in,与面向模型的会话查询工具决策所述完全一致:ACP 示例的 [`session-query.cordis.yml`](../../../../examples/acp-agent/session-query.cordis.yml) 及其快照对侧文件仍是挂载参考,自定义组合也可以连同超时与 spill 策略一起挂载该包。
 
 `ctx.sessionQuery` 服务本身保持挂载。`session-query-sqlite` 仍是 base 的一行,TUI 的 `session-reference` 消费它来实现 `/resume`,Web overlay 也继续把它 patch 成内存索引,供浏览器内容搜索使用。被移除的只有面向模型的消费方。
 

.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md
+2026-08-04-claude-code-and-codex-subagent-backends.md: e81d1fb14f719331c503dba539d6a5ec0f1eed4f
+2026-08-04-claude-code-and-codex-subagent-backends.zh.md: 3c78e8d5a4ca1a86942971721ad05c631901f231

.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.md

@@ -0,0 +1,94 @@
+# Agent Note: Claude Code and Codex subagent backends
+
+Status: implemented
+
+English | [中文](2026-08-04-claude-code-and-codex-subagent-backends.zh.md)
+
+## Problem
+
+The named [`ctx.subagents`](2026-06-21-subagent-capability-seam.md) registry lets a parent agent delegate work without knowing how the child runs, but the harness needs first-party routes to the real Codex and Claude Code products. Each route must hand the product one self-contained task, let it work in the parent Session's workspace, return a final answer or an explicit failure or cancellation, and leave no managed product process behind.
+
+The product integrations must not become second owners for task text, cwd, cancellation, result settlement, or process trees. Required evidence therefore separates three facts: a keyless real-product test proves the official integration, native authentication shape, deterministic answer, and teardown; a Loader composition test proves that the public package and documented tool configuration load without starting the product; and a credentialed e2e proves that the production provider and real product can obtain a unique answer from the real DeepSeek service. Direct model HTTP or a product double cannot replace either product-running tier, and a hand-mounted plugin cannot replace the Loader tier.
+
+## Decision
+
+The harness publishes two sibling one-shot providers as independently installable, opt-in packages. A user loads a provider and the existing common subagent tool in their own `cordis.yml`: `subagent_codex` binds `codex`, while `subagent_claude_code` binds `claude-code`. The shipped CLI dependency closure and base, Web, and headless configurations load neither provider. Each tool accepts only a standalone text task; product selection and background execution are not model arguments.
+
+Both providers report `inheritsParentContext: false`, advertise no optional start capabilities, and pass the parent Session cwd without copying the parent conversation. Their documented tools disable background execution and use `maxDepth: 'provider-managed'`, leaving recursion policy with the out-of-process product instead of sending a limit the provider cannot enforce. Every call creates a fresh product process and a non-resumable product conversation. The shared subagent service continues to own request resolution, lifecycle events, result settlement, and foreground collection; the shared subprocess service owns credential scrubbing, process-tree termination, and whole-tree exit observation.
+
+```text
+fixed tool → shared subagent service → product provider → official product process
+     ← final answer / explicit error / cancellation ← terminal product fact
+     → foreground disposal → shared process-tree termination → whole-tree exit
+```
+
+### Ownership and lifecycle
+
+| Phase | Shared owner | Product-specific responsibility | Observable result |
+| --- | --- | --- | --- |
+| Resolve | `dsh-tool-subagent` and `ctx.subagents` | Validate the product's text-only input and derive native startup parameters | Unsupported context or malformed input fails before a run is published |
+| Start | `dsh-subprocess` owns every acquired process tree | Reach the smallest native point at which the product conversation and process can both be controlled | `start()` publishes one existing `SubagentRun`, or cleans up and rejects |
+| Run | The product owns its native protocol facts; the holder owns their mapping | Submit exactly one task and derive an existing shared stop reason; Codex uses `max-tokens` only for explicit context exhaustion | The parent receives only a final answer or an explicit failure |
+| Dispose | The foreground consumer requests release; `dsh-subprocess` proves exit | Close the native protocol and express any best-effort native cancellation | Disposal is idempotent and returns only after the whole process tree exits |
+
+## Codex provider
+
+`@deepseek-ai/dsh-subagent-codex` registers the fixed `codex` provider and starts `codex app-server --stdio` from `PATH`. Its public configuration contains only an explicit `env` overlay and a positive finite `disposeGraceMs` no greater than the repository's shared `MAX_TIMER_DELAY_MS`. Installation, login, `CODEX_HOME`, model selection, base URL, sandbox, approval policy, and product-session settings remain native Codex or deployment responsibilities.
+
+Before publication, the provider validates a non-empty text-only task, starts the managed app-server in the parent workspace, completes `initialize` → `initialized`, and creates an `ephemeral: true` thread. The published run owns exactly one `turn/start`; its thread and turn ids remain private and are never persisted in the parent Session.
+
+`turn/completed` is the authoritative remote terminal fact. The latest `agentMessage` with `phase: "final_answer"` wins, and that selected message must contain nonblank text. When the product emits no explicit final phase, the latest message with `phase: null` is the compatibility fallback and must likewise be nonblank; commentary never replaces either answer. A failed turn with `error.codexErrorInfo: "contextWindowExceeded"` becomes `max-tokens`. A completed turn without an answer, every other failed or interrupted remote turn, malformed required fields in a recognized app-server frame, protocol closure, early process exit, or unknown server request becomes `error`; this version has no native refusal terminal and therefore produces no `refusal`. Local cancellation wins its race and remains `aborted`.
+
+For command and file approvals, the unattended wire selects a non-approval decision offered by the request, preferring `cancel`; the stable 0.146.0 request shape without an offered-decision list falls back to `decline`. It grants no requested permissions for the turn, answers user-input requests with no answers, and declines MCP elicitation. A request with no legal unattended response, or any unknown server request, fails the run instead of waiting for a user interface the provider does not supply.
+
+An unpublished startup failure closes the wire, terminates the acquired process tree, waits for exit, and then rejects `start()`. Published disposal best-effort interrupts a known turn, closes the wire, ends stdin, invokes the shared termination escalation, and waits for whole-tree exit. Result failure and teardown failure stay independently observable.
+
+Codex 0.146.0 speaks the Responses protocol, while DeepSeek's public OpenAI-compatible endpoint speaks Chat Completions. The credentialed Codex e2e therefore uses a loopback-only, test-private bridge for one no-tool nonce request: real Codex sends Responses to the bridge, the bridge forwards the received bearer credential and extracted task to the fixed official DeepSeek endpoint, and it wraps the real text in the minimal Responses SSE lifecycle. The bridge is neither a production proxy nor evidence that Codex connects to DeepSeek Chat Completions natively.
+
+## Claude Code provider
+
+`@deepseek-ai/dsh-subagent-claude-code` registers the fixed `claude-code` provider and invokes `@anthropic-ai/claude-agent-sdk@0.3.220`. The SDK's platform `optionalDependency` supplies the real Claude Code 2.1.220 CLI. The provider uses the official `query()` entrypoint and passes the SDK's `spawnClaudeCodeProcess` command, arguments, cwd, environment, and forwarded signal unchanged to `dsh-subprocess`; its private `SpawnedProcess` adapter exposes only the stream, event, kill, and exit facts the SDK requires.
+
+The public configuration contains the same two deployment-owned values as the Codex sibling: an explicit `env` overlay and a positive finite `disposeGraceMs` no greater than the repository's shared `MAX_TIMER_DELAY_MS`. Each run creates its own `AbortController`, sets `persistSession: false`, and disables `AskUserQuestion`. The provider deliberately omits `settingSources`, so the SDK reads the host's normal user, project, and local Claude settings relative to the parent Session cwd. It neither copies nor filters those settings and does not create or modify login state. It supplies no `canUseTool`, elicitation, or dialog callback, so unattended interactions fail through the SDK rather than waiting for a user interface the provider does not own.
+
+The provider publishes only after both the SDK `Query` and a live managed CLI handle exist. It consumes the complete SDK stream and completes only when a `result` message has `subtype: "success"`, `is_error: false`, and a nonblank `result`, and the iterator then ends normally. Every SDK error subtype, an error-marked success, a missing result, iterator failure, protocol failure, or process failure becomes `error`. SDK turn, budget, and structured-output limits are not token-window facts, and the SDK exposes no native refusal terminal, so this provider produces neither `max-tokens` nor `refusal`. Local cancellation wins and becomes `aborted`.
+
+Startup rollback and published disposal close the SDK query, abort the per-run controller, invoke shared process-tree termination, and wait for whole-tree exit. `Query.close()` expresses graceful protocol intent but does not replace the subprocess owner's exit proof. Query-close failure, process failure, and teardown failure remain independently observable.
+
+The credentialed Claude Code e2e uses the official DeepSeek Claude Code contract directly: the runtime-only DeepSeek key becomes `ANTHROPIC_AUTH_TOKEN`, the fixed official base gains `/anthropic`, and the main and subagent model variables select the documented DeepSeek models. It starts the production provider and real SDK/CLI, requires one random nonce as the complete answer, persists no credential in settings, and waits for every managed handle to exit.
+
+## Distribution and evidence
+
+Each product owns branch-complete package tests, a required keyless real-product spec, a Loader composition e2e, and a credentialed DeepSeek e2e. The keyless product tier uses the exact official distribution under test, a non-empty fake product key, an isolated temporary workspace and product home, and a loopback fixed-answer model. Missing product requests, wrong authentication, altered task text, a non-exact answer, a skipped real product, or a surviving managed handle fails the required test. The Loader tier boots the README-shaped user configuration, verifies both fixed foreground-only tools in one context, and starts neither product process. The credentialed tier starts the same production provider and real product with a runtime-only key, requires a unique nonce from the fixed official DeepSeek service, and proves quiescence again; it self-skips only when a local operator supplied no key, while trusted CI preflights the secret.
+
+The Codex evidence pins `@openai/codex@0.146.0` and `codex-cli 0.146.0`. Its real-product spec observes the exact Bearer key, original task, byte-exact final answer, unattended command rejection with no file side effect, local cancellation, and whole-tree exit. Production still supplies `codex` on `PATH`.
+
+The Codex credentialed e2e registers the production provider, starts the same real app-server, and requests one random nonce through the test-private bridge described above. It fixes the external endpoint and model, stores no credential or request payload, requires exactly one completed upstream response, compares the trimmed product answer byte-for-byte with the nonce, and waits for every managed handle to exit.
+
+The Claude Code evidence pins Agent SDK 0.3.220 and its platform-distributed Claude Code 2.1.220 CLI. Its real-product spec observes the exact `x-api-key`, original task, byte-exact final answer, inherited temporary host-setting marker, process failure, local cancellation, and whole-tree exit. The Loader e2e resolves both product packages by name while neither product command is available and records zero child starts.
+
+The Claude Code credentialed e2e maps the key and fixed official endpoint only in the provider's in-memory environment, uses the documented `deepseek-v4-pro[1m]` and `deepseek-v4-flash` model variables, and traverses the production provider, official SDK, and real CLI. It compares the trimmed result with a random nonce and proves whole-tree exit without calling the Messages API directly from the test.
+
+The project owner's distribution authorization is scoped to the official `@anthropic-ai/claude-agent-sdk` identity and the official Claude Code CLI/platform payloads each SDK version declares through `optionalDependencies`. [`THIRD_PARTY_NOTICES.md`](../../../../THIRD_PARTY_NOTICES.md) derives and discloses the current payload set without reclassifying its declared terms as permissive. Version, license-field, and payload-set changes still undergo ordinary dependency, lockfile, compatibility, terms, and notices review; unrelated non-permissive runtime packages continue to fail closed.
+
+## Alternatives considered
+
+**Direct model HTTP, `codex exec`, or a hand-written Claude CLI protocol.** These paths bypass the products' official extensible integration surfaces and cannot prove native configuration, tools, approvals, result semantics, or teardown. Each provider uses its official product integration instead.
+
+**A shared product-process helper package.** The existing subagent and subprocess seams already own every shared task, result, environment, and process-tree concern. A new helper would duplicate ownership without deleting either private product adapter, so each adapter calls the existing seams directly.
+
+**A model-visible product selector.** Product availability and authentication are deployment facts. Two fixed tools keep each schema and provider binding explicit and avoid adding dynamic selection state to the common service.
+
+**Product doubles as required evidence.** Doubles cover exhaustive private protocol branches but do not prove package exports, official distributions, authentication, or real process behavior. Required evidence drives each official product against a loopback model fixture.
+
+**Plugin-managed login, product home, models, settings, or permissions.** Those choices would create another authority beside each product's native configuration and enlarge a one-shot provider into account management. The providers expose only an explicit environment overlay and teardown grace; unattended interaction fails closed.
+
+**Continuation, progress, background collection, and shared parent context.** The delivered user result is one self-contained task and one final answer. Product sessions, resume, follow-up, intermediate messages, parent transcript transfer, structured output, and background collection need separate user contracts and are not prebuilt.
+
+## Consequences
+
+Users can install either or both product providers, bind stable foreground tools in their own Cordis configuration, and delegate one self-contained task through the existing subagent contract. Official product integrations preserve native settings and behavior while shared services retain the sole ownership of task settlement and process-tree quiescence.
+
+Every delegation pays for a fresh product process and independent model context, and only final text reaches the parent. Product-native configuration makes behavior depend on the deployment's installed product, account state, and workspace settings. Credentialed e2e runs also spend external API quota and depend on the official DeepSeek endpoint; deterministic protocol, failure, cancellation, and approval coverage remains in the keyless tier. The providers do not resume sessions, stream progress, accept new human interaction, roll back tool or file side effects, or impose a wall-clock timeout.
+
+Compatibility is pinned by package-level unit coverage, keyless real-product loopback tests, credentialed DeepSeek nonce tests, public Loader composition, built-package and NodeNext consumer checks, generated documentation and notices, and the repository CI matrix. A supported product or DeepSeek endpoint/model baseline change must refresh those facts; production performs no separate runtime version probe.

.agents/notes/implemented/feature/2026-08-04-claude-code-and-codex-subagent-backends.zh.md

@@ -0,0 +1,94 @@
+# Agent Note: Claude Code 与 Codex subagent 后端
+
+Status: implemented
+
+[English](2026-08-04-claude-code-and-codex-subagent-backends.md) | 中文
+
+## 问题
+
+命名的 [`ctx.subagents`](2026-06-21-subagent-capability-seam.md) 注册表让父 agent（智能体）无需了解子级的运行方式即可委派工作，但 harness 需要通往真实 Codex 与 Claude Code 产品的第一方路径。每条路径都必须向产品交付一项自包含任务，让它在父会话的工作区中执行，返回最终回答或明确的失败或取消结果，并且不留下任何受管的产品进程。
+
+产品集成不得成为任务文本、cwd、取消、结果结算或进程树的第二责任方。因此，所需证据要区分三个事实：无密钥真实产品测试证明官方集成、原生身份验证形态、确定性答案与资源清理；Loader 组合测试证明公开包（package）和文档所示的工具配置无需启动产品即可加载；带密钥 e2e 证明生产提供方与真实产品能够从真实 DeepSeek 服务取得唯一答案。直接发起模型 HTTP 请求或使用产品替身无法取代上述任一产品运行层级；手工挂载插件无法取代 Loader 层级。
+
+## 决策
+
+harness 将两个一次性兄弟提供方作为可独立安装、选择启用的包交付。用户在自己的 `cordis.yml` 中加载提供方与现有的通用 subagent 工具：`subagent_codex` 绑定 `codex`，`subagent_claude_code` 绑定 `claude-code`。随产品交付的 CLI（命令行界面）依赖闭包，以及基础、Web 与 headless 配置都不会加载任一提供方。每个工具只接受独立文本任务；产品选择与后台执行都不作为模型参数。
+
+这两个提供方都报告 `inheritsParentContext: false`，不声明任何可选的启动能力，并传递父会话 cwd，但不会复制父级对话。文档所示的工具会禁用后台执行，并使用 `maxDepth: 'provider-managed'`，将递归策略留给进程外产品，而不是发送提供方无法强制执行的限制。每次调用都会创建一个全新的产品进程和一次不可续接的产品对话。共享 subagent 服务继续负责请求解析、生命周期事件、结果结算和前台收集；共享子进程服务负责凭证清洗、进程树终止以及整棵进程树的退出观测。
+
+```text
+fixed tool → shared subagent service → product provider → official product process
+     ← final answer / explicit error / cancellation ← terminal product fact
+     → foreground disposal → shared process-tree termination → whole-tree exit
+```
+
+### 归属与生命周期
+
+| 阶段 | 共享责任方 | 产品特定职责 | 可观察结果 |
+| --- | --- | --- | --- |
+| 解析 | `dsh-tool-subagent` 与 `ctx.subagents` | 验证产品的纯文本输入并推导原生启动参数 | 不受支持的上下文或格式错误的输入会在发布运行前报错 |
+| 启动 | `dsh-subprocess` 负责每棵已获取的进程树 | 到达能够同时控制产品对话与进程的最小原生控制点 | `start()` 发布一个已存在的 `SubagentRun`，否则清理后拒绝调用 |
+| 运行 | 产品负责其原生协议事实；持有方负责映射这些事实 | 只提交一项任务，并推导出一种现有的共享停止原因；Codex 仅在明确发生上下文耗尽时使用 `max-tokens` | 父级只会收到最终回答或明确失败 |
+| dispose（资源释放） | 前台消费方请求释放；`dsh-subprocess` 证明进程已退出 | 关闭原生协议，并发出尽力而为的原生取消请求 | 释放操作具有幂等性，且仅在整棵进程树退出后才返回 |
+
+## Codex 提供方
+
+`@deepseek-ai/dsh-subagent-codex` 注册固定的 `codex` 提供方，并启动 `codex app-server --stdio`，该命令从 `PATH` 解析。其公开配置仅包含显式的 `env` 覆盖项和须为正有限值的 `disposeGraceMs`，且后者不得大于仓库共享的 `MAX_TIMER_DELAY_MS`。安装、登录、`CODEX_HOME`、模型选择、基础 URL、沙箱、审批策略和产品会话设置仍由 Codex 原生机制或部署环境负责。
+
+发布前，提供方会验证非空的纯文本任务，在父级工作区中启动受管的 app-server，完成 `initialize` → `initialized` 握手，并创建一个 `ephemeral: true` 线程。已发布的运行只拥有一次 `turn/start`；其线程 ID 与轮次 ID 保持私有，绝不会持久化到父会话。
+
+`turn/completed` 是权威的远端终止事实。以最后一条带有 `phase: "final_answer"` 的 `agentMessage` 为准，且选中的消息必须包含非空白文本。若产品没有发出明确的最终阶段，则以最后一条 `phase: null` 的消息作为兼容性回退，该消息也必须包含非空白文本；过程说明绝不会取代上述任一答案。带有 `error.codexErrorInfo: "contextWindowExceeded"` 的失败轮次会成为 `max-tokens`。轮次完成却没有答案、其他任何远端失败或中断轮次、已识别的 app-server 帧中必需字段格式错误、协议关闭、进程提前退出或未知的服务器请求，都会产生 `error`；本版本没有原生的拒绝终止状态，因此不会产生 `refusal`。本地取消在竞态中胜出并保持为 `aborted`。
+
+对于命令与文件审批，无人值守的协议连接会从请求给出的决策选项中选择一项不予批准的决策，并优先选择 `cancel`；稳定的 0.146.0 请求形态没有决策选项列表，因此回退到 `decline`。它不授予该轮次请求的任何权限，不向用户输入请求提供任何答案，并拒绝 MCP elicitation。若请求在无人值守模式下没有合法响应，或是未知服务器请求，此次运行就会失败，而不会等待本提供方没有提供的用户界面。
+
+若启动在发布前失败，提供方会关闭协议连接、终止已获取的进程树并等待其退出，然后拒绝 `start()`。对已发布的运行执行资源释放时，提供方会尽力中断已知轮次、关闭协议连接、结束标准输入、调用共享的逐级终止机制，并等待整棵进程树退出。结果失败与清理失败仍可彼此独立地观察。
+
+Codex 0.146.0 使用 Responses 协议，而 DeepSeek 的公开 OpenAI 兼容端点使用 Chat Completions。因此，带密钥 Codex e2e 会采用一个仅限回环、仅供测试内部使用的桥接层来处理一次不使用工具的随机数请求：真实 Codex 将 Responses 发送到桥接层，桥接层把收到的 Bearer 凭据与提取出的任务转发到固定的 DeepSeek 官方端点，再将真实文本包装进最小化的 Responses SSE（Server-Sent Events）生命周期。该桥接层既不是生产代理，也不能作为 Codex 原生连接 DeepSeek Chat Completions 的证据。
+
+## Claude Code 提供方
+
+`@deepseek-ai/dsh-subagent-claude-code` 注册固定的 `claude-code` 提供方，并调用 `@anthropic-ai/claude-agent-sdk@0.3.220`。SDK 的平台 `optionalDependency` 提供真实的 Claude Code 2.1.220 CLI。提供方使用官方 `query()` 入口点，并将 SDK 的 `spawnClaudeCodeProcess` 命令、参数、cwd、环境和转发的信号原样传入 `dsh-subprocess`；其私有 `SpawnedProcess` 适配器只公开 SDK 所需的流、事件、终止和退出事实。
+
+公开配置包含与 Codex 兄弟提供方相同、由部署方负责的两个值：显式的 `env` 覆盖项，以及须为正有限值且不得大于仓库共享 `MAX_TIMER_DELAY_MS` 的 `disposeGraceMs`。每次运行都会创建自己的 `AbortController`，设置 `persistSession: false` 并禁用 `AskUserQuestion`。提供方故意省略 `settingSources`，因此 SDK 会相对于父会话 cwd 读取宿主机常规的用户、项目和本地 Claude 设置。它既不复制也不过滤这些设置，也不会创建或修改登录状态。提供方不设置 `canUseTool`、elicitation 或对话回调，因此无人值守交互会经 SDK 失败，而不会等待本提供方不负责的用户界面。
+
+只有在 SDK `Query` 与受管的活动 CLI 句柄都已存在后，提供方才会发布运行。它会消费完整的 SDK 流；只有 `result` 消息具有 `subtype: "success"`、`is_error: false` 和非空白 `result`，且迭代器随后正常结束时，运行才会完成。所有 SDK 错误子类型、标记为错误的成功消息、结果缺失、迭代器失败、协议失败或进程失败都会成为 `error`。SDK 的轮次、预算和结构化输出限制不表示 token 窗口耗尽，而且 SDK 没有原生的拒绝终止状态，因此本提供方不会产生 `max-tokens` 或 `refusal`。本地取消会胜出并成为 `aborted`。
+
+启动回滚和已发布运行的资源释放都会关闭 SDK query、中止该次运行的控制器、调用共享的进程树终止机制，并等待整棵进程树退出。`Query.close()` 表达优雅的协议关闭意图，但不能取代子进程责任方的退出证明。Query 关闭失败、进程失败和清理失败仍可彼此独立地观察。
+
+带密钥 Claude Code e2e 直接使用官方 DeepSeek Claude Code 契约：仅在运行时提供的 DeepSeek 密钥会映射为 `ANTHROPIC_AUTH_TOKEN`，固定的官方基础 URL 会追加 `/anthropic`，主模型与 subagent 模型变量会选择文档所示的 DeepSeek 模型。该测试会启动生产提供方与真实 SDK 和 CLI，要求一个随机数作为完整答案，不会把任何凭据持久化到设置中，并等待所有受管句柄退出。
+
+## 分发与证据
+
+每个产品都负责覆盖所有分支的包测试、一项必跑的无密钥真实产品测试、一项 Loader 组合 e2e 和一项带密钥 DeepSeek e2e。无密钥产品层级使用被测的确切官方发行版、非空的伪产品密钥、隔离的临时工作区与产品主目录，以及能返回固定答案的回环模型。产品请求缺失、身份验证错误、任务文本被改动、答案不完全一致、真实产品被跳过或受管句柄仍存活，都会使这项必跑测试失败。Loader 层级会启动 README 所示形态的用户配置，在同一个上下文中验证两个固定且只支持前台执行的工具，并且不会启动任何产品进程。带密钥层级会使用仅在运行时提供的密钥启动同一生产提供方与真实产品，要求从固定的 DeepSeek 官方服务取得唯一随机数，并再次证明完全停稳；仅当本地操作者未提供密钥时才会自行跳过，而受信任的 CI 会预检该 secret。
+
+Codex 证据锁定 `@openai/codex@0.146.0` 与 `codex-cli 0.146.0`。其真实产品测试会观测确切的 Bearer 密钥、原始任务、逐字节完全一致的最终回答、不会产生文件副作用的无人值守命令拒绝、本地取消以及整棵进程树退出。生产环境仍提供 `codex`，并通过 `PATH` 解析。
+
+带密钥 Codex e2e 会注册生产提供方，启动同样的真实 app-server，并通过上述测试专用桥接层请求一个随机数。该测试固定外部端点与模型，不存储任何凭据或请求载荷，要求上游恰好完成一次响应，将去除首尾空白后的产品答案与该随机数逐字节比较，并等待所有受管句柄退出。
+
+Claude Code 证据锁定 Agent SDK 0.3.220 及其平台分发的 Claude Code 2.1.220 CLI。其真实产品测试会观测确切的 `x-api-key`、原始任务、逐字节完全一致的最终回答、继承的临时宿主设置标记、进程失败、本地取消以及整棵进程树退出。Loader e2e 会在两个产品命令均不可用时按名称解析两个产品包，并记录零次子级启动。
+
+带密钥 Claude Code e2e 仅在提供方的内存环境中映射密钥与固定的官方端点，把模型变量设为文档所示的 `deepseek-v4-pro[1m]` 与 `deepseek-v4-flash`，并实际经过生产提供方、官方 SDK 与真实 CLI。它将去除首尾空白后的结果与一个随机数比较，并证明整棵进程树退出，且测试不会直接调用 Messages API。
+
+项目所有者的分发授权范围限定为官方 `@anthropic-ai/claude-agent-sdk` 身份，以及每个 SDK 版本通过 `optionalDependencies` 声明的官方 Claude Code CLI 与平台载荷。[`THIRD_PARTY_NOTICES.md`](../../../../THIRD_PARTY_NOTICES.md) 会推导并披露当前载荷集合，但不会将其声明条款重新归类为宽松条款。版本、许可证字段和载荷集合发生变化时，仍须经过常规的依赖、锁文件、兼容性、条款和声明评审；无关的非宽松运行时包继续以默认拒绝方式失败。
+
+## 曾考虑的替代方案
+
+**直接模型 HTTP、`codex exec` 或手写的 Claude CLI 协议。** 这些路径会绕过产品的官方可扩展集成接口，无法证明原生配置、工具、审批、结果语义或资源清理。每个提供方都改用相应的官方产品集成。
+
+**共享产品进程辅助包。** 现有 subagent 与子进程 seam 已负责围绕任务、结果、环境和进程树的全部共享职责。新辅助包无法删除任一私有产品适配器，只会造成责任重复，因此每个适配器都会直接调用现有 seam。
+
+**面向模型的产品选择器。** 产品可用性和身份验证属于部署事实。两个固定工具使各自的 schema 与提供方绑定保持明确，也避免在通用服务中添加动态选择状态。
+
+**以产品替身作为强制证据。** 替身可以穷尽覆盖私有协议分支，但无法证明包导出、官方发行版、身份验证或真实进程行为。强制证据会驱动每个官方产品连接回环模型 fixture（测试前置数据）。
+
+**由插件管理登录、产品主目录、模型、设置或权限。** 这些选择会在每个产品的原生配置之外建立另一套权威来源，并将一次性提供方扩张为账户管理功能。提供方只公开显式环境覆盖项和清理宽限期；无人值守交互会以默认拒绝方式失败。
+
+**续接、进度、后台收集和共享父级上下文。** 已交付的用户结果是一项自包含任务和一个最终回答。产品会话、恢复、后续交互、中间消息、父级 transcript（文本记录）传递、结构化输出和后台收集都需要独立的用户契约，当前实现不会预先构建这些功能。
+
+## 后果
+
+用户可以安装任一或两个产品提供方，在自己的 Cordis 配置中绑定稳定的前台工具，并通过现有 subagent 契约委派一项自包含任务。官方产品集成会保留原生设置与行为，而共享服务继续独占任务结算与进程树完全停稳的责任。
+
+每次委派都要承担新建产品进程和独立模型上下文的开销，且只有最终文本会到达父级。产品原生配置使行为取决于部署环境中安装的产品、账户状态和工作区设置。带密钥 e2e 运行还会消耗外部 API 配额，并依赖 DeepSeek 官方端点；对协议、失败、取消与审批的确定性覆盖仍由无密钥层级承担。提供方不会恢复会话、以流式方式传送进度、接受新的人工交互、回滚工具或文件副作用，也不会施加按实际经过时间触发的超时。
+
+兼容性由包级单元测试覆盖率、无密钥真实产品回环测试、带密钥 DeepSeek 随机数测试、公开 Loader 组合、已构建包与 NodeNext 消费方检查、生成的文档与声明以及仓库 CI 矩阵共同锁定。更改受支持的产品基线或 DeepSeek 端点／模型基线时必须刷新这些事实；生产环境不会另行执行运行时版本探测。

.agents/notes/implemented/feature/2026-08-04-web-slash-command-fuzzy-discovery.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-04-web-slash-command-fuzzy-discovery.md
+2026-08-04-web-slash-command-fuzzy-discovery.md: 8d7fe88f8d19a6edc7b51e63578c468df085c238
+2026-08-04-web-slash-command-fuzzy-discovery.zh.md: d3efdc23351a1b50853ee76fb731aee046004750

.agents/notes/implemented/feature/2026-08-04-web-slash-command-fuzzy-discovery.md

@@ -0,0 +1,27 @@
+# Agent Note: Web slash-command fuzzy discovery
+
+Status: implemented
+
+English | [中文](2026-08-04-web-slash-command-fuzzy-discovery.zh.md)
+
+## Problem
+
+The web command menu required a command-name prefix, so discovery failed when a user remembered the significant letters but not their exact positions. Broadening menu matching could make discovery easier, but command execution must remain exact and deterministic: an approximate line must never execute a nearby command.
+
+## Decision
+
+The `/` command source fuzzy-matches the typed query against command names as a case-insensitive ordered subsequence. Exact prefixes form the highest ranking class. Within each class, the strongest alignment score rewards separator boundaries and adjacent characters while penalizing leading characters and gaps; equal scores retain the host-directory and client-contribution order. Position filtering still removes argument-taking commands from inline menus before ranking.
+
+The scorer uses dynamic programming in `O(query length × name length)` time and `O(name length)` memory per candidate. Candidate scoring stays client-side and examines names only; descriptions do not affect matching. Menu selection still dispatches the selected exact name, while space and Enter adjudication continue to require an exact command token.
+
+## Alternatives considered
+
+**Keep prefix-only matching.** Rejected because it preserves the recall failure that motivates the feature; `/cpt` cannot discover `/compact`.
+
+**Match unordered characters or descriptions.** Rejected because unordered matches are difficult to predict, while description matches can surface commands whose visible names do not explain why they ranked.
+
+**Use a general fuzzy-search dependency.** Rejected because this surface needs one constrained subsequence rule over a small command catalog; a configurable search index would add bundle weight and ranking behavior not used by the product.
+
+## Consequences
+
+Users can discover a command from remembered in-order letters, and ranking remains stable across identical catalogs. The score is deliberately heuristic: a separator-aligned match can outrank a match with a shorter raw span. Package tests pin each ranking factor and stable ties, while the assembled Web replay snapshot pins `/cpt` resolving to `/compact`. Exact execution semantics are unchanged.

.agents/notes/implemented/feature/2026-08-04-web-slash-command-fuzzy-discovery.zh.md

@@ -0,0 +1,27 @@
+# Agent Note: Web 斜杠命令模糊发现
+
+Status: implemented
+
+[English](2026-08-04-web-slash-command-fuzzy-discovery.md) | 中文
+
+## Problem
+
+Web 命令菜单要求按命令名前缀匹配，因此用户只记得关键字母却不记得其准确位置时，就无法发现命令。扩大菜单的匹配范围可使命令更易发现，但命令执行仍必须保持精确匹配和确定性：近似输入行绝不能执行相近命令。
+
+## Decision
+
+`/` 命令 source 将键入的查询作为不区分大小写的有序子序列，与命令名进行模糊匹配。精确前缀构成排名最高的一类匹配。在每类匹配中，对齐分数越高越优先：分隔符边界和相邻字符会提高分数，前导字符和间隔会降低分数；分数相同则保持 host 目录和 client contribution 的顺序。位置过滤仍会在排名前从行内菜单中移除接收参数的命令。
+
+评分器对每个候选项使用动态规划，时间复杂度为 `O(query length × name length)`，空间复杂度为 `O(name length)`。候选项评分只在客户端进行且只检查命令名；命令描述不影响匹配。菜单选择仍派发所选的精确名称，而 space 与 Enter 裁决继续要求命令 token 精确匹配。
+
+## Alternatives considered
+
+**保留仅前缀匹配。** 否决，因为本功能要解决的用户无法准确回忆前缀的问题依然存在：`/cpt` 无法发现 `/compact`。
+
+**匹配无序字符或描述。** 否决，因为无序匹配难以预测，而描述匹配可能展示命令，但命令的可见名称无法解释其排名。
+
+**使用通用模糊搜索依赖。** 否决，因为该界面只需对小型命令目录使用一种受限的子序列规则；可配置搜索索引会增加 bundle 体积，并引入产品未使用的排名行为。
+
+## Consequences
+
+用户可以凭按顺序记得的字母发现命令；只要目录相同，排名就保持稳定。评分刻意采用启发式规则：与分隔符对齐的匹配可能排在原始跨度更短的匹配之前。包（package）测试固定各项排名因素以及同分时的稳定顺序，组装后的 Web 回放快照固定 `/cpt` 解析为 `/compact` 的行为。精确执行语义保持不变。

.agents/notes/implemented/feature/2026-08-06-session-completed-done-dot.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write .agents/notes/implemented/feature/2026-08-06-session-completed-done-dot.md
+2026-08-06-session-completed-done-dot.md: bd6911ce137f1272090c86c029710c9f4054ee6d
+2026-08-06-session-completed-done-dot.zh.md: 9ec2199a29d1307c3ebd0238e84d5f90d36fe21c

.agents/notes/implemented/feature/2026-08-06-session-completed-done-dot.md

@@ -0,0 +1,25 @@
+# Agent Note: Session completion dot in the sidebar
+
+Status: implemented
+
+English | [中文](2026-08-06-session-completed-done-dot.zh.md)
+
+## Problem
+
+A session the operator delegated work to and then left (switched to another conversation) gives no signal when it finishes. Its running indicator stops, but the row then looks identical to any idle session, so the operator must poll the list or discover the finished work late. The pending-interaction amber dot covers sessions that need input, not sessions whose work is simply done.
+
+## Decision
+
+`SessionManager` owns a client-side completion-reminder set, a sibling of the pending-interaction bit: a running→idle edge of a session that is not the selected one arms its reminder; `select()`/`selectSubagent()` consume it; starting a new run disarms it and its completion re-arms it; removal prunes it. The bit rides `SessionListEntry` → `SessionSummary` (optional, absent = no reminder) into the workspace browser, whose session and search rows render the existing `StateDot` `done` state — running keeps the ongoing spinner, an idle session without a reminder shows nothing — and whose hover card labels the reminder 已完成 / Completed.
+
+The reminder is in-memory and per browser. It survives connection generations — a transport blip does not invalidate "you have not looked yet" — but not a page reload.
+
+## Consequences
+
+The sidebar row states become three disjoint signals: green = finished and unviewed, amber = awaiting the operator's input, blue = running. No wire, on-disk, or configuration format changes: `SessionSummary.completed` is optional, so existing consumers and test fixtures stay valid, and only the workspace browser reads it. The completion edge is detected eagerly at every list mutation and pull (a snapshot-build-time-only pass would collapse two consecutive status frames into one observation and miss the completion).
+
+## Alternatives considered
+
+- **Component-local UI state.** Rejected because the sidebar unmounts on collapse and multiple surfaces (grouped tree, flat list, search) need the same bit; the manager already owns the running transitions and the selection, so a manager-owned set is the one source all surfaces can project.
+- **Event-driven arming from status frames only.** Rejected because a list pull can also carry a running→idle transition (a session finished while the refresh was in flight); the reminder is reconciled against every mutation and pull.
+- **Persisting the reminder.** Rejected because the reminder means "you have not looked at this session yet" in this browser; reload restores the selection and the user is looking at the list again, so a durable bit would only go stale.

.agents/notes/implemented/feature/2026-08-06-session-completed-done-dot.zh.md

@@ -0,0 +1,25 @@
+# Agent Note: 侧边栏会话完成提醒点
+
+Status: implemented
+
+[English](2026-08-06-session-completed-done-dot.md) | 中文
+
+## Problem
+
+操作者派发任务后切换到其他会话，原会话完成时没有任何信号。运行指示停止后，该行与普通空闲会话看起来完全一样，操作者只能反复查看列表或很晚才发现工作已完成。等待交互的琥珀点只覆盖需要操作者输入的会话，不覆盖"只是干完了活"的会话。
+
+## Decision
+
+`SessionManager` 持有客户端侧的完成提醒集合，与待交互位并列：非当前会话发生 running→idle 边沿时点亮其提醒；`select()`/`selectSubagent()` 消费掉提醒；重新开始一轮运行会熄灭提醒并在再次完成时重新点亮；会话被移除时清理提醒。该位经 `SessionListEntry` → `SessionSummary`（可选字段，缺省 = 无提醒）进入工作区浏览区，其会话行与搜索结果行渲染现有的 `StateDot` `done` 状态——运行中仍显示转圈，无提醒的空闲会话不显示任何点——悬停卡片将该提醒标注为"已完成 / Completed"。
+
+提醒仅存在于内存中且按浏览器实例隔离。它跨连接代存活——传输抖动不会使"你还没回来看"失效——但页面刷新后重置。
+
+## Consequences
+
+侧边栏行状态成为三个互斥信号：绿 = 已完成且未查看，琥珀 = 等待操作者输入，蓝 = 运行中。无 wire、磁盘或配置格式变更：`SessionSummary.completed` 为可选字段，现有消费者与测试 fixture 保持有效，只有工作区浏览区读取它。完成边沿在每次列表变更与拉取时即时检测（仅在建快照时检测会把连续两个状态帧折叠为一次观察，从而漏掉完成事件）。
+
+## Alternatives considered
+
+- **组件本地 UI 状态。** 已拒绝：侧边栏折叠时会卸载，且多个界面（分组树、单列表、搜索）需要同一状态位；manager 本就持有运行状态迁移与选中状态，manager 持有的集合是所有界面都能投影的唯一事实源。
+- **仅从状态帧做事件驱动点亮。** 已拒绝：列表拉取本身也可能携带 running→idle 迁移（刷新在途时会话已完成）；提醒需对每次变更与拉取做对账。
+- **持久化提醒。** 已拒绝：提醒的含义是"此浏览器里你还没查看该会话"；刷新会恢复选中状态且用户正看着列表，持久化位只会过期。

.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write .agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md
-2026-07-30-generated-third-party-notices.md: e480954d29d5dc09ef8ecd4069059a1f0c8b1043
-2026-07-30-generated-third-party-notices.zh.md: 78ba7250e797c57048078d1b4f62b7a9a5d9d561
+2026-07-30-generated-third-party-notices.md: cbabd1142ad292f78a3184723182a834dfb234fc
+2026-07-30-generated-third-party-notices.zh.md: b135c3626b661f1a5b0317a90b700a26d679bf1e

.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.md

@@ -18,7 +18,7 @@ A hand-written inventory answers none of those durably. Roughly a hundred rows o
 
 One trigger gap is accepted rather than worked around: lefthook inspects only files present on disk, so **deleting** a manifest runs no job, and removing a package reaches the assertion in the test lane instead. Reconstructing the staged file list to include deletions was tried and does not work — lefthook filters the list against the working tree either way. The assertion is the backstop for exactly this case.
 
-The file discloses **direct** dependencies only. 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 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).
 
@@ -26,10 +26,14 @@ The runtime tier deliberately covers **every mountable plugin**, not just what t
 
 The manifest set is derived from the `packages:` members each `pnpm-workspace.yaml` declares — the root one and the nested Landlock workspace's — 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 installed pnpm stores, both the root one and the Landlock workspace's, 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.
 
+The project owner separately authorizes distribution of every official `@anthropic-ai/claude-agent-sdk` version and the official Claude Code CLI/platform payloads that version declares through `optionalDependencies`. The generator represents this as one exact direct-package identity exception, not as a permissive-license override: `SEE LICENSE IN README.md` and `SEE LICENSE IN LICENSE.md` remain non-permissive classifications, and every unrelated non-permissive runtime still fails closed. When the SDK is present, the generator reads its installed manifest, rejects optional identities outside the official SDK payload prefix, derives the current SDK, CLI, and payload versions, verifies the installed host payload's identity, version, and declared-license field, and renders the complete SDK-declared payload set in a separate notices section. Version, declared-license, and payload-set changes do not require new identity authorization, but they still require ordinary dependency, lockfile, compatibility, terms, and notices review.
+
 ## Testing
 
 The same spec that asserts freshness pins the tiering rule against fixture manifests — including the two cases that motivate it, a `dependencies` entry of a test-support package and a plugin package no app mounts. It also pins the parsers against the shapes that would otherwise drop a package without a word: a `vendor/README.md` table that stops covering a vendored directory, a requirement array holding extras (`"httpx[http2]"`), a requirement with no version at all, an author-named `[dependency-groups]` table, and a workspace member area absent from any hardcoded list. Each of those is a silent-omission path, which is the failure mode a disclosure file cannot afford.
 
+The Claude distribution tests prove that only the exact direct SDK identity bypasses the ordinary non-permissive-runtime rejection, that the bypass does not change license classification, and that the payload set comes from the SDK manifest rather than a version or platform allowlist. Wrong SDK identities, missing payloads, and unrelated optional package identities all fail.
+
 ## Alternatives considered
 
 **Keep the hand-written file and review it at release time.** Reviewing a hundred derived rows by eye is exactly the work a generator does correctly, and the file's own claim — that it lists every direct dependency — would be unverified between releases.
@@ -42,6 +46,8 @@ The same spec that asserts freshness pins the tiering rule against fixture manif
 
 **Tier by reachability from the shipped assemblies only** (`apps/*` plus `python/sdk-runtime`). This produces a tighter runtime tier, but classifies the MCP client and the OpenTelemetry exporter as development-only even though a user running the installed repository can mount them. It understates the disclosure, which is the wrong direction to err for a legal notice.
 
+**Treat the Claude SDK terms as permissive or add a reusable non-permissive allowlist.** Either shape would misstate the upstream declaration and let an unrelated runtime inherit authorization it was never granted. The narrow exception keys only the official direct SDK identity, while its optional payload identities are accepted solely as data declared by that SDK and remain visibly non-permissive.
+
 **Emit the notices as a bilingual pair.** Every other root document is paired, but the file is a table of upstream package names, SPDX identifiers, and URLs; the translatable surface is a handful of section blurbs. `scripts/translation-pairing.ts` scopes discovery to `README*`, `.agents/notes/**`, `docs/**`, and `python/**`, so a root non-README file is outside the bilingual corpus by construction, and the README pair carries the bilingual entry points into it.
 
 ## Consequences
@@ -51,3 +57,5 @@ A dependency edit now carries a regenerated notices file into the same commit. C
 The generator needs an installed tree, which makes it heavier than a pure-source generator, and a new package with unusable published metadata needs an `OVERRIDES` entry rather than silently rendering a blank license. Both failures are loud and name the remedy.
 
 The tiering rule is a policy encoded in one constant. Adding a workspace area that never ships — a second test-infrastructure tier, another site — requires extending `DEV_ONLY_AREAS`, or its dependencies will be disclosed as runtime.
+
+The Claude identity exception is deliberately narrower than the payload disclosure it activates. Upgrading the SDK needs no new owner authorization, but regeneration fails unless the installed SDK exposes its version, CLI version, and at least one official platform payload, and unless the current host payload matches the SDK declaration. Maintainers still review changed terms and compatibility; the generator prevents the authorization from silently widening to another package.

.agents/notes/implemented/process/2026-07-30-generated-third-party-notices.zh.md

@@ -18,7 +18,7 @@ Status: implemented
 
 有一处触发缺口是接受而非绕过的：lefthook 只检视磁盘上存在的文件，因此**删除**清单文件不会触发任何任务，移除一个包会落到测试 lane 的断言上。重构暂存文件列表以纳入删除的做法试过，不成立——无论怎么给列表，lefthook 都会拿工作树过滤一遍。这个场景正由断言兜底。
 
-文件只披露**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。
+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，而非清单字段名。** 只要 `DEV_ONLY_AREAS` 之外的任一清单——即根清单、`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 exec 经过的 `tsx`，根本没有任何清单把它声明为运行时依赖，只能由生成器显式标记。
 
@@ -26,10 +26,14 @@ Status: implemented
 
 清单集合由两个 `pnpm-workspace.yaml`——根工作区与嵌套的 Landlock 工作区——各自声明的 `packages:` 成员派生，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已安装的 pnpm store，根 store 与 Landlock 工作区的 store 都会查；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` 收录已发布清单答不上来的包：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` 列在运行时表格之后，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。
 
+项目所有者另行授权分发每个官方 `@anthropic-ai/claude-agent-sdk` 版本，以及该版本通过 `optionalDependencies` 声明的官方 Claude Code CLI 与平台载荷。生成器将其表示为一项精确匹配直接包身份的例外，而非宽松许可证覆盖项：`SEE LICENSE IN README.md` 与 `SEE LICENSE IN LICENSE.md` 仍归类为非宽松，所有无关的非宽松运行时依赖仍以默认拒绝方式失败。存在该 SDK 时，生成器会读取其已安装清单，拒绝不符合官方 SDK 载荷前缀的可选包身份，推导当前 SDK、CLI 与载荷版本，核验已安装宿主载荷的身份、版本和声明许可证字段，并在单独的声明章节中渲染 SDK 声明的完整载荷集合。版本、声明许可证和载荷集合发生变化时无需新的身份授权，但仍须经过常规的依赖、锁文件、兼容性、条款和声明评审。
+
 ## Testing
 
 断言新鲜度的同一个 spec 也用夹具清单钉住分层规则，覆盖促成该规则的两个场景：测试支撑包的 `dependencies` 条目，以及没有任何应用挂载的插件包。它还把各解析器钉在那些原本会让某个包无声消失的形态上：不再覆盖全部收编目录的 `vendor/README.md` 表、含 extras 的依赖数组（`"httpx[http2]"`）、完全不带版本的依赖、作者自取名字的 `[dependency-groups]` 表，以及任何硬编码列表都不含的工作区成员区域。这些都是静默漏报路径——正是披露文件最担不起的失败方式。
 
+Claude 分发测试证明：只有精确匹配的直接 SDK 身份会绕过通常的非宽松运行时拒绝；该绕过不会改变许可证分类；载荷集合来自 SDK 清单，而非版本或平台允许列表。SDK 身份错误、载荷缺失或存在无关的可选包身份时，测试都会失败。
+
 ## Alternatives considered
 
 **保留手写文件，发版时人工过一遍。** 用肉眼审阅上百行推导数据，恰恰是生成器能做对的活；而且在两次发版之间，文件自称「列出全部直接依赖」这句话无人验证。
@@ -42,6 +46,8 @@ Status: implemented
 
 **只按已交付装配的可达性分层**（`apps/*` 加 `python/sdk-runtime`）。这样得到的运行时层更紧凑，但会把 MCP 客户端与 OpenTelemetry 导出器判为仅开发用途——而运行已安装仓库的用户完全可以挂载它们。这会低估披露，对法务通告来说错在了更危险的一侧。
 
+**将 Claude SDK 条款视为宽松条款，或新增可复用的非宽松允许列表。** 两种方案都会误述上游声明，并让无关运行时依赖继承从未授予它的授权。这项窄例外只匹配官方直接 SDK 身份；其可选载荷身份仅作为该 SDK 声明的数据被接受，并继续明确归类为非宽松。
+
 **把披露文件做成双语对。** 其他根文档都是成对的，但这份文件是上游包名、SPDX 标识与网址构成的表格，可翻译的只有寥寥几段章节导语。`scripts/translation-pairing.ts` 的发现范围限定在 `README*`、`.agents/notes/**`、`docs/**` 与 `python/**`，根目录下的非 README 文件在构造上就不属于双语语料；双语入口由 README 对承担。
 
 ## Consequences
@@ -51,3 +57,5 @@ Status: implemented
 生成器需要已安装的工作树，因此比纯源码生成器更重；发布元数据不可用的新包需要补一条 `OVERRIDES`，而不是默默渲染出空白许可证。这两类失败都会明确报错并指出补救方式。
 
 分层规则是编码在一个常量里的政策。若新增了不参与交付的工作区区域——第二层测试基础设施、另一个站点——就要同步扩展 `DEV_ONLY_AREAS`，否则其依赖会被当作运行时依赖披露出去。
+
+Claude 身份例外刻意比其启用的载荷披露范围更窄。升级 SDK 无需新的所有者授权，但如果已安装的 SDK 未公开自身版本、CLI 版本和至少一个官方平台载荷，或当前宿主载荷与 SDK 声明不符，重新生成就会失败。维护者仍须评审发生变化的条款与兼容性；生成器会阻止授权悄然扩大到其他包。

.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.i18n.yaml

@@ -1,6 +0,0 @@
-# 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/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md
-2026-07-07-claude-code-and-codex-subagent-backends.md: ee8576f97a9fdef8c88dcad3a73f28b63ca3ebe1
-2026-07-07-claude-code-and-codex-subagent-backends.zh.md: bd76a8f34d86b704494b56331c47ea89bfc8a0aa

.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.md

@@ -1,89 +0,0 @@
-# Agent Note: Claude Code and Codex subagent backends (out-of-process delegation to external coding agents)
-
-Status: proposed
-
-English | [中文](2026-07-07-claude-code-and-codex-subagent-backends.zh.md)
-
-## Problem
-
-The subagent seam ([the seam Agent Note](../../implemented/feature/2026-06-21-subagent-capability-seam.md)) hosts multiple named providers on `ctx.subagents`, and the ACP backend ([the ACP backend Agent Note](../../implemented/feature/2026-06-22-acp-subagent-backend.md)) proved the seam generalizes across a process boundary; its Future-providers section explicitly named the Codex app-server and the Claude Code Agent SDK as mechanically similar siblings. Those two are the engines actually worth delegating to today: a harness turn should be able to hand a self-contained task to a real Claude Code or a real Codex — a separate product with its own model, tools, and sandbox — and get back one final answer, without the parent deployment leaking its secrets into the child or the child's behavior silently depending on whatever `~/.claude` / `~/.codex` state exists on the host machine.
-
-## Proposal
-
-Two sibling provider packages, structural variants of the ACP backend, plus one extraction:
-
-- `@deepseek-ai/dsh-subagent-claude-code` — drives a Claude Code child through `@anthropic-ai/claude-agent-sdk`'s `query()` (the SDK runs in the parent process and spawns its bundled `claude` CLI as the subprocess). Provider name `claude-code`: the child is the Claude Code *product*, not an Anthropic model adapter — "claude" stays reserved for a future `dsh-llm` adapter.
-- `@deepseek-ai/dsh-subagent-codex` — spawns `codex app-server` and drives one thread/turn over its JSON-RPC-over-stdio protocol with a hand-rolled newline-JSON client (~200–300 lines) in the package.
-- `@deepseek-ai/dsh-subagent-process` — a pure library (the `subagent-inprocess` precedent) extracting what `dsh-subagent-acp` already carries and both new backends need: the credential env scrub (`buildChildEnv`), the EOF → SIGTERM → SIGKILL dispose ladder, and new isolated-config-dir helpers (`mkdtemp` create, best-effort remove). The ACP backend migrates onto it; `bash-local`'s sibling copy is left alone to bound the change.
-
-Both providers copy the ACP backend's seam posture verbatim: fresh child per `start`, exactly one prompt round-trip, capabilities all `false`, `inheritsParentContext: false`, `request.parent`/`request.agentOptions` ignored, `id = SessionId(randomUUID())`, `result` never rejects — child-level failure flattens to a stop reason and the original error goes to `ctx.logger` via an `onError` spec callback. Model exposure is zero new code: `dsh-tool-subagent` is loaded once per provider with a distinct `toolName` (`subagent_claude_code`, `subagent_codex`). No new session events are needed — the only model-visible artifact is the tool result, so reconstructability holds exactly as it did for ACP. To be explicit about the boundary: the session log reconstructs the model-visible transcript, not workspace mutation history — a child granted write access mutates files as an ambient side effect outside the log, exactly as the bash tools and the ACP backend already do; replay reproduces requests, not the disk.
-
-## Verified interface facts (pinned versions)
-
-Both integration surfaces were verified against pinned implementations before this proposal — types and bundled source read, keyless spikes run — not from vendor docs alone. The pins are the verification baseline, not a runtime contract: the backends perform no runtime version probe (no `codex --version` gate, no SDK version sniffing). Compatibility is enforced at development time — every dependency bump re-runs the keyless suites against the real load path — and at runtime by failing loudly: a protocol-level surprise settles `error` via `onError`, never a silent misbehavior.
-
-**`@anthropic-ai/claude-agent-sdk` 0.3.202.** `options.env` REPLACES the child environment (no merge with `process.env`), which is exactly what the scrub needs. `settingSources` defaults to loading ALL filesystem settings — isolation requires explicitly passing `[]`. Result subtypes are `success` | `error_during_execution` | `error_max_turns` | `error_max_budget_usd` | `error_max_structured_output_retries`. On abort the SDK escalates the CLI child itself: stdin EOF immediately, SIGTERM ~2s later if the child ignores it (observed; no leftover processes) — no bespoke kill fallback needed. `outputFormat: {type: 'json_schema'}` and an `agents` option exist, giving future landing points for the seam's `outputSchema` capability and named subagent types; both are out of scope here.
-
-**codex CLI 0.142.5, `codex app-server` (v2 vocabulary).** LF-delimited JSON, JSON-RPC 2.0 shapes with the `"jsonrpc"` header omitted.
-
-- Lifecycle: `initialize{clientInfo}` + `initialized` → `thread/start` (accepts `cwd`, `model`, `sandbox`, `approvalPolicy`, `ephemeral`; succeeds unauthenticated) → `turn/start{threadId, input:[{type:'text',text}]}` returns an `inProgress` turn immediately; the terminal signal is the `turn/completed` notification carrying `Turn{status: completed|interrupted|failed|inProgress, error}`.
-- Approvals are server-initiated requests — `item/commandExecution/requestApproval`, `item/fileChange/requestApproval`, `item/permissions/requestApproval`, `item/tool/requestUserInput`, `mcpServer/elicitation/request` — answered with `accept`/`decline`-family decisions.
-- Auth: `account/login/start{type:'apiKey', apiKey}` is a first-class RPC and `account/read` reports `requiresOpenaiAuth` — and an unauthenticated `turn/start` does NOT fail fast (it hangs in retry), so the backend MUST pre-check auth and settle `error` loudly instead of waiting on the turn.
-- Isolation: `CODEX_HOME` redirection is honored (the `initialize` response echoes it, so tests can assert isolation), and `ephemeral: true` threads leave no session files at all.
-
-## Isolation and credentials
-
-Deployments authenticate with API keys only, and the child must not see the host user's Claude Code / Codex configuration: behavior has to be a function of `cordis.yml` alone. Each run gets a fresh `mkdtemp` config dir — `CLAUDE_CONFIG_DIR` for Claude Code (paired with an explicit `settingSources: []`), `CODEX_HOME` for Codex — removed best-effort on dispose; a config field can pin a persistent dir instead. The child env reuses the ACP backend's `buildChildEnv` semantics verbatim via the extraction: the ambient env is forwarded MINUS credential-shaped vars (`/KEY|SECRET|TOKEN/i`), with `config.env` layered on top — so `PATH`, `HOME`, `TMPDIR`, locale, and proxy vars survive and the CLIs run normally, while only credential-shaped ambient vars are scrubbed (`ANTHROPIC_API_KEY` enters explicitly through `config.env` for Claude Code), and the Codex key travels via the `account/login/start` RPC into the isolated `CODEX_HOME` rather than a hand-written `auth.json`.
-
-## Permission and approval policy
-
-Instead of collapsing to ACP's single `permission: allow|reject` knob, each backend exposes its engine's native vocabulary as config, with conservative defaults: Claude Code gets `permissionMode` (default `default`) plus `permission: allow|reject` (default `reject`) as the `canUseTool` auto-answer for whatever falls through; Codex gets `sandboxMode` (default `read-only`) and `approvalPolicy` (default `never`) plus the same `permission` fallback for approval requests that still arrive. Defaults are deliberately do-no-harm (the out-of-box child cannot write files); examples demonstrate opening up (`acceptEdits` / `workspace-write`). The mechanical rule: EVERY server-initiated request is settled programmatically and promptly — the enumerated approval/user-input/elicitation requests by the configured policy, an unknown request method with a JSON-RPC method-not-found error response (never left pending), unknown notifications consumed — so no child request can wedge a turn waiting on an answer that will never come. Prompts never reach a human in this cut, matching ACP.
-
-## StopReason mapping
-
-Claude Code: `success` → `completed`; `error_max_turns`, `error_during_execution`, `error_max_budget_usd`, `error_max_structured_output_retries` → `error` (aligning with the ACP call on `max_turn_requests`: an unfinished task is not success); generator abort → `aborted`; anything unknown → `error`. Codex: `Turn.status` `completed` → `completed`; `interrupted` → `aborted`; `failed` with `codexErrorInfo: 'contextWindowExceeded'` → `max-tokens`, any other `failed` → `error`; transport/spawn/auth-precheck failure → `error` (or `aborted` if cancel was requested). In both, `cancel()` is the ACP shape: flag + abort/interrupt + a cancel-settled race arm so an uncooperative child cannot stall the result.
-
-Liveness posture, stated explicitly: teardown timing is config, turn duration is not. Both backends take the dispose ladder's grace periods as defaulted validated config fields (the ACP backend's `disposeEofGraceMs`/`disposeGraceMs` shape, carried by the extraction), but there is deliberately NO turn-duration or startup timeout — matching ACP, liveness during a turn belongs to the caller via `cancel()`/the abort signal, a subagent turn is legitimately minutes long, and the Codex auth precheck removes the one verified guaranteed-hang; a deployment wanting a wall-clock bound cancels from the parent.
-
-## Testing
-
-Named at every tier per the root AGENTS.md rule, and de-risked up front:
-
-- **Keyless unit/integration**, mirroring the ACP spec list per backend (round-trip and output accumulation, every stop mapping, both cancel paths, already-aborted, permission auto-answer under both policies, unknown-message tolerance, bad-command spawn failure, HMR provider cleanup, export shape, isolation assertions on child env and temp-dir removal; Codex adds the auth-precheck failure path). Claude Code's harness is a scripted fake `claude` executable behind `pathToClaudeCodeExecutable` driven by the REAL SDK — a spike already passed end-to-end keyless in 24ms (the fake CLI answers one `control_request/initialize` and speaks plain stream-json, ~40 lines). Codex's harness is a scripted mock app-server subprocess speaking the verified wire protocol, the `mock-acp-server.ts` shape.
-- **With-key e2e** per backend: the real engine does real file work verified on disk, under a pinned opened-up config so acceptance and the do-no-harm defaults don't collide — `permissionMode: 'acceptEdits'` for Claude Code, `sandboxMode: 'workspace-write'` + `approvalPolicy: 'never'` for Codex; self-skips report exactly what is missing (binary vs key). CI has no secrets, so these run locally per the with-key policy.
-- **Snapshot**: deferred as `TODO(claude-code-subagent-replay)` / `TODO(codex-subagent-replay)` — the same distinct replay shape the ACP backend deferred ([the per-session replay Agent Note](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md)); the keyless suites carry deterministic coverage meanwhile.
-
-## Alternatives considered
-
-### Why not the official `@openai/codex-sdk` instead of a hand-rolled client?
-
-The dispose ladder and env scrub require owning the child process (spawn args, env, signals, exit await); the SDK hides the process. The wire format is trivial to frame (LF JSON), the shapes are generatable per pinned version (`codex app-server generate-json-schema`), and the repo precedent (`hook-protocol`) is to own thin protocol cores rather than wrap someone's runtime. The SDK would save protocol-evolution maintenance but costs the exact control this backend exists to have.
-
-### Why not a model-visible `subagent_type` parameter (one Task-style tool)?
-
-Claude Code's own Task tool puts the subagent type in the model-facing schema, selecting a prompt-plus-toolset persona. Here the choice is between EXECUTION ENGINES, and only the deployer knows which engines have credentials configured — so selection stays deployment config, preserving `dsh-tool-subagent`'s documented one-provider-per-tool contract. A persona-style type selector would be a separate Agent Note against the tool, not the backends.
-
-### Why not login-state credentials and the user's own config?
-
-Inheriting `~/.claude` / `~/.codex` (subscription login, user settings, skills, MCP servers) would make child behavior depend on host-machine state and punch an implicit exception through the "credentials enter explicitly via `config.env`, never ambiently" rule the ACP backend and bash executor established. API-key-only plus forced config-dir isolation keeps runs reproducible; deployments wanting shared state can point the config-dir field at a persistent directory deliberately.
-
-### Why not a driver-injection seam for the Claude Code keyless tests?
-
-Injecting a fake `query()` would mock our own boundary and leave the real SDK load path untested (the real-over-mock policy in docs/testing.md). The risk that justified considering it — the SDK↔CLI stream-json control protocol being internal — was retired by the spike: the fake-CLI harness works against the real pinned SDK today. If an SDK upgrade breaks the mock, the keyless suite fails the upgrade PR, which is the gate working.
-
-### Why not ACP adapters (e.g. `claude-code-acp`) reusing the existing backend?
-
-Community shims wrap both engines in ACP, which would make them "just config" on `dsh-subagent-acp`. But that inserts an unofficial third-party layer between the harness and the engine, erases the native control surfaces this Agent Note exposes (permissionMode, sandboxMode/approvalPolicy, config-dir isolation, apiKey RPC), and trades first-party protocol stability for a shim's release cadence. First-party surfaces — the Agent SDK and the app-server — are the supported integration points.
-
-## Acceptance criteria
-
-On a machine with both engines and keys configured: a REPL-driven model completes one real file task through `subagent_claude_code` and one through `subagent_codex`, the tool result being the child's final answer, with only `tool/call` + `tool/result` in the parent session log. Keyless suites pass at 100% per-file coverage in a credential-less environment, asserting isolation (scrubbed child env, no temp config dirs left after dispose) and that child behavior is unchanged by the presence or absence of `~/.claude` / `~/.codex`. Cancelling a parent turn quiesces both backends in bounded time with no leftover child processes. E2e suites self-skip cleanly, naming the missing prerequisite.
-
-## Risks
-
-- `codex app-server` is CLI-flagged experimental and its v1/v2 vocabularies coexist; the client pins 0.142.5, implements v2 only, and consumes unknown methods/notifications without crashing, but a future codex bump can still force rework (regenerate schemas and re-run the keyless suite on every bump — the development-time enforcement behind the no-runtime-version-probe stance above).
-- The Claude Code fake-CLI mock rides an internal protocol: any SDK upgrade must go through the keyless suite, and a breaking control-protocol change means reworking the mock (fallback: the driver-injection seam rejected above becomes the escape hatch).
-- The SDK's optionalDependencies weigh ~280MB per platform — accepted, and confined to the one backend package.
-- The SDK's SIGKILL branch beyond EOF→SIGTERM was not observed and is trusted; e2e keeps a no-leftover-process assertion.
-- Codex is a deployment prerequisite (no npm-bundled binary); a missing or incompatible binary surfaces as a loud spawn/protocol `error`, not a version probe.
-- Every run pays a fresh child process and only the final answer surfaces — thoughts, tool cards, and usage are consumed and dropped; pooling, intermediate-progress surfacing, `sendMessage`/`resume`, `outputSchema` via the SDK's `outputFormat`, and named subagent types via the SDK's `agents` option are all deliberate deferrals.

.agents/notes/proposed/feature/2026-07-07-claude-code-and-codex-subagent-backends.zh.md

@@ -1,89 +0,0 @@
-# Agent Note: Claude Code 与 Codex subagent 后端（向外部编码 agent 的进程外委派）
-
-Status: proposed
-
-[English](2026-07-07-claude-code-and-codex-subagent-backends.md) | 中文
-
-## 问题
-
-subagent seam（[seam Agent Note](../../implemented/feature/2026-06-21-subagent-capability-seam.md)）在 `ctx.subagents` 上托管多个命名提供方，ACP（Agent Client Protocol）后端（[ACP 后端 Agent Note](../../implemented/feature/2026-06-22-acp-subagent-backend.md)）证明了该 seam 能跨越进程边界泛化；其「未来提供方」一节明确将 Codex app-server 与 Claude Code Agent SDK 列为实现机制相似的同类方案。如今真正值得委派的就是这两个引擎：harness 的一个轮次应能把一个自包含任务交给真实的 Claude Code 或真实的 Codex——一个拥有自身模型、工具与沙箱的独立产品——并取回一个最终答案，同时父部署不向子进程泄漏密钥，子进程行为也不静默依赖宿主机上碰巧存在的 `~/.claude` / `~/.codex` 状态。
-
-## 提案
-
-两个兄弟提供方包，作为 ACP 后端的结构变体，另加一次提取：
-
-- `@deepseek-ai/dsh-subagent-claude-code`：通过 `@anthropic-ai/claude-agent-sdk` 的 `query()` 驱动一个 Claude Code 子进程（SDK 在父进程中运行，并将其内置的 `claude` CLI（命令行界面）作为子进程 spawn）。提供方名称为 `claude-code`：子进程是 Claude Code 这个*产品*，而非 Anthropic 模型适配器——「claude」保留给未来的 `dsh-llm` 适配器。
-- `@deepseek-ai/dsh-subagent-codex`：spawn `codex app-server`，通过其 JSON-RPC-over-stdio 协议驱动一个 thread 及其中的一个轮次，使用包内一个手写的换行 JSON 客户端（约 200–300 行）。
-- `@deepseek-ai/dsh-subagent-process`：纯库（沿用 `subagent-inprocess` 的先例），提取 `dsh-subagent-acp` 已有且两个新后端都需要的内容：凭证环境清洗（`buildChildEnv`）、EOF → SIGTERM → SIGKILL 的 dispose（资源释放）阶梯，以及新的隔离配置目录辅助函数（`mkdtemp` 创建、尽力删除）。ACP 后端迁移到该库上；`bash-local` 的兄弟副本保持不动以限制变更范围。
-
-两个提供方逐字复制 ACP 后端的 seam 姿态：每次 `start` 创建全新子进程、恰好一次提示词往返、所有能力均为 `false`、`inheritsParentContext: false`、忽略 `request.parent`/`request.agentOptions`、`id = SessionId(randomUUID())`，且 `result` 从不 reject——子进程级失败扁平化为 stop reason，原始错误则通过 `onError` spec 回调送到 `ctx.logger`。模型暴露无需新代码：每个提供方各加载一次 `dsh-tool-subagent`，使用不同的 `toolName`（`subagent_claude_code`、`subagent_codex`）。无需新的会话事件——唯一的模型可见产物是工具结果，因此可重建性与 ACP 完全相同。明确边界：会话日志重建模型可见的 transcript（文本记录），而不是工作区变更历史——获准写入的子进程将文件作为日志之外的环境副作用进行修改，与 bash 工具和 ACP 后端现有行为完全一致；回放复现请求，而非磁盘。
-
-## 已验证的接口事实（固定版本）
-
-两个集成面在本提案之前均已针对固定版本进行了验证——阅读类型与打包源码、运行无需密钥的 spike——而非仅依赖厂商文档。固定版本是验证基线，不是运行时契约：后端不执行运行时版本探测（无 `codex --version` 门禁、无 SDK 版本嗅探）。兼容性在开发时强制执行——每次依赖升级都会针对真实加载路径重跑无密钥套件——在运行时则通过显式失败来保障：协议层面的意外通过 `onError` 结算为 `error`，绝不静默异常。
-
-**`@anthropic-ai/claude-agent-sdk` 0.3.202。** `options.env` 会替换子进程环境（不与 `process.env` 合并），恰好满足清洗需求。`settingSources` 默认加载所有文件系统设置——隔离要求显式传入 `[]`。结果子类型为 `success` | `error_during_execution` | `error_max_turns` | `error_max_budget_usd` | `error_max_structured_output_retries`。中止时 SDK 自行逐级加强对 CLI 子进程的终止措施：立即关闭 stdin，约 2 秒后若子进程未退出则发送 SIGTERM（已观察到；无残留进程）——无需自定义 kill 回退。`outputFormat: {type: 'json_schema'}` 和 `agents` 选项已存在，为 seam 的 `outputSchema` 能力和命名 subagent 类型提供了未来着陆点；两者均不在本 Agent Note 范围内。
-
-**codex CLI 0.142.5，`codex app-server`（v2 词汇）。** LF 分隔的 JSON，JSON-RPC 2.0 形状但省略 `"jsonrpc"` 头。
-
-- 生命周期：`initialize{clientInfo}` + `initialized` → `thread/start`（接受 `cwd`、`model`、`sandbox`、`approvalPolicy`、`ephemeral`；未认证即可成功）→ `turn/start{threadId, input:[{type:'text',text}]}` 立即返回一个 `inProgress` 的轮次；终止信号是携带 `Turn{status: completed|interrupted|failed|inProgress, error}` 的 `turn/completed` 通知。
-- 审批是服务端发起的请求——`item/commandExecution/requestApproval`、`item/fileChange/requestApproval`、`item/permissions/requestApproval`、`item/tool/requestUserInput`、`mcpServer/elicitation/request`——以 `accept`/`decline` 系列决策应答。
-- 认证：`account/login/start{type:'apiKey', apiKey}` 是一等 RPC，`account/read` 报告 `requiresOpenaiAuth`——且未认证的 `turn/start` 不会快速失败（它会挂在重试中），因此后端必须预检认证状态，并在失败时明确结算为 `error`，而非等待轮次。
-- 隔离：`CODEX_HOME` 重定向被尊重（`initialize` 响应会回显它，测试可据此断言隔离），`ephemeral: true` 的 thread 不留任何会话文件。
-
-## 隔离与凭证
-
-部署只使用 API key 认证，子进程不得看到宿主用户的 Claude Code / Codex 配置：行为必须只由 `cordis.yml` 决定。每次运行获得一个全新的 `mkdtemp` 配置目录——Claude Code 使用 `CLAUDE_CONFIG_DIR`（并显式设置 `settingSources: []`），Codex 使用 `CODEX_HOME`——dispose 时尽力删除；配置字段也可以固定一个持久目录。子进程环境通过提取逐字复用 ACP 后端的 `buildChildEnv` 语义：转发环境变量，但移除凭证形态的变量（`/KEY|SECRET|TOKEN/i`），再叠加 `config.env`——因此 `PATH`、`HOME`、`TMPDIR`、locale 和代理变量保留，CLI 正常运行；只有环境中的凭证形态变量被清洗（Claude Code 的 `ANTHROPIC_API_KEY` 通过 `config.env` 显式进入），Codex key 则通过 `account/login/start` RPC 进入隔离的 `CODEX_HOME`，而非手写 `auth.json`。
-
-## 权限与审批策略
-
-每个后端不压缩为 ACP 单一的 `permission: allow|reject` 旋钮，而把引擎原生词汇作为配置暴露，并采用保守默认值：Claude Code 获得 `permissionMode`（默认 `default`）以及 `permission: allow|reject`（默认 `reject`），后者作为所有未被前者处理的请求的 `canUseTool` 自动应答；Codex 获得 `sandboxMode`（默认 `read-only`）和 `approvalPolicy`（默认 `never`），以及同一个 `permission` 后备值，用来应答仍然到达的审批请求。默认值刻意做到不造成损害（开箱即用的子进程无法写文件）；示例演示如何开放权限（`acceptEdits` / `workspace-write`）。机械规则是：每一个服务端发起的请求都由程序迅速结算——枚举出的审批/用户输入/elicitation 请求按配置策略应答，未知请求方法用 JSON-RPC method-not-found 错误响应（绝不保持 pending），未知通知被消费——因此任何子进程请求都不会因等待永远不会到来的应答而卡住轮次。这一版中提示词不会到达人类，与 ACP 一致。
-
-## StopReason 映射
-
-Claude Code：`success` → `completed`；`error_max_turns`、`error_during_execution`、`error_max_budget_usd`、`error_max_structured_output_retries` → `error`（与 ACP 对 `max_turn_requests` 的处理对齐：未完成的任务不是成功）；生成器中止 → `aborted`；未知值 → `error`。Codex：`Turn.status` 为 `completed` → `completed`；`interrupted` → `aborted`；`failed` 且 `codexErrorInfo: 'contextWindowExceeded'` → `max-tokens`，其他 `failed` → `error`；传输/spawn/认证预检失败 → `error`（若已请求取消则为 `aborted`）。两者中，`cancel()` 采用 ACP 形状：标志位 + abort/interrupt + 一个 cancel-settled 竞争分支，使不合作的子进程无法阻塞结果。
-
-活性姿态，明确声明：teardown 时序是配置项，轮次时长不是。两个后端将 dispose 阶梯的宽限期作为带默认值的已验证配置字段（ACP 后端的 `disposeEofGraceMs`/`disposeGraceMs` 形状，由提取库承载），但刻意不设轮次时长或启动超时——与 ACP 一致：轮次期间的活性由调用方通过 `cancel()`/abort signal 掌控，subagent 轮次持续数分钟也属合理，而 Codex 认证预检消除了唯一已验证的必然挂起场景；需要墙钟上限的部署从父侧取消即可。
-
-## 测试
-
-依照根 AGENTS.md 规则在每个层级明确命名，并预先消除风险：
-
-- **无密钥单元/集成测试**：每个后端都镜像 ACP spec 清单（往返和输出累积、每种 stop 映射、两条取消路径、已中止、两种策略下的权限自动应答、未知消息容错、错误命令的 spawn 失败、HMR（热模块替换）提供方清理、导出形状、对子进程环境隔离和临时目录删除的断言；Codex 另加认证预检失败路径）。Claude Code harness 是通过 `pathToClaudeCodeExecutable` 接入真实 SDK 的脚本化假 `claude` 可执行文件——一个 spike 已在 24 ms 内完成端到端无密钥验证（假 CLI 应答一次 `control_request/initialize`，并使用普通 stream-json 通信，约 40 行）。Codex harness 是讲已验证协议格式的脚本化 mock app-server 子进程，沿用 `mock-acp-server.ts` 形状。
-- **有密钥 e2e 测试**：每个后端的真实引擎执行真实文件操作，并通过磁盘状态进行验证，固定使用开放后的配置，以免验收与不造成损害的默认值冲突——Claude Code 使用 `permissionMode: 'acceptEdits'`，Codex 使用 `sandboxMode: 'workspace-write'` + `approvalPolicy: 'never'`；自跳过会准确报告缺失的是二进制还是 key。CI 没有密钥，因此依照有密钥策略在本地运行。
-- **快照测试**：以 `TODO(claude-code-subagent-replay)` / `TODO(codex-subagent-replay)` 推迟——即 ACP 后端也推迟的独立回放形状（[按会话回放 Agent Note](../../implemented/testing/2026-06-22-subagent-snapshot-replay.md)）；在此期间由无密钥套件提供确定性覆盖。
-
-## 曾考虑的替代方案
-
-### 为什么不用官方 `@openai/codex-sdk` 而手写客户端？
-
-dispose 阶梯和环境清洗要求拥有子进程（spawn 参数、env、信号、exit 等待）；SDK 隐藏了进程。协议格式（wire format）极其简单（LF JSON），形状可按固定版本生成（`codex app-server generate-json-schema`），仓库先例（`hook-protocol`）是拥有薄协议核心而非包装他人的运行时。SDK 能节省协议演进的维护成本，但代价是失去本后端存在的意义所在的精确控制。
-
-### 为什么不用模型可见的 `subagent_type` 参数（单一 Task 风格工具）？
-
-Claude Code 自身的 Task 工具将 subagent 类型放在模型可见的 schema 中，选择一个提示词 + 工具集人格。这里的选择是在执行引擎之间做出的，而只有部署者知道哪些引擎配置了凭证——因此选择留在部署配置层，保持 `dsh-tool-subagent` 文档中的「一个提供方对应一个工具」契约。人格风格的类型选择器应是针对工具的另一个 Agent Note，而非针对后端。
-
-### 为什么不用登录态凭证和用户自身的配置？
-
-继承 `~/.claude` / `~/.codex`（订阅登录、用户设置、skill（技能）、MCP 服务器）会使子进程行为依赖宿主机状态，并在 ACP 后端和 bash 执行器确立的「凭证通过 `config.env` 显式进入，绝不隐式继承」规则上打开一个隐式例外。仅 API key 加强制配置目录隔离使运行可复现；需要共享状态的部署可以有意将配置目录字段指向一个持久目录。
-
-### 为什么不为 Claude Code 无密钥测试注入驱动层 seam？
-
-注入假的 `query()` 会 mock 我们自己的边界，使真实 SDK 加载路径未被测试（docs/testing.md 中的 real-over-mock 策略）。曾考虑此方案的风险——SDK↔CLI 的 stream-json 控制协议是内部实现——已被 spike 消除：假 CLI harness 今天能对真实固定版本的 SDK 正常工作。如果 SDK 升级破坏了 mock，无密钥套件会让升级 PR（Pull Request）失败，这正是门禁在发挥作用。
-
-### 为什么不用 ACP 适配器（如 `claude-code-acp`）复用既有后端？
-
-社区 shim 将两个引擎包装为 ACP，这会使它们在 `dsh-subagent-acp` 上变成「仅配置」。但这在 harness 与引擎之间插入了一个非官方的第三方层，抹去了本 Agent Note 暴露的原生控制面（permissionMode、sandboxMode/approvalPolicy、配置目录隔离、apiKey RPC），并以 shim 的发布节奏替换了第一方协议的稳定性。第一方接口——Agent SDK 和 app-server——才是受支持的集成点。
-
-## 验收标准
-
-在两个引擎和密钥均已配置的机器上：一个 REPL 驱动的模型通过 `subagent_claude_code` 完成一个真实文件任务，通过 `subagent_codex` 完成另一个，工具结果为子进程的最终答案，父会话日志中仅有 `tool/call` + `tool/result`。无密钥套件在无凭证环境下以逐文件 100% 覆盖率通过，断言隔离（清洗后的子进程环境、dispose 后无残留临时配置目录），并断言 `~/.claude` / `~/.codex` 的存在与否不影响子进程行为。取消父轮次后，两个后端在有界时间内完全停稳，无残留子进程。e2e 套件干净地自跳过，命名缺失的前置条件。
-
-## 风险
-
-- `codex app-server` 被 CLI 标记为实验性，其 v1/v2 词汇共存；客户端固定 0.142.5、仅实现 v2、对未知方法/通知消费而不崩溃，但未来 codex 升级仍可能迫使返工（每次升级重新生成 schema 并重跑无密钥套件——这是上述「不做运行时版本探测」立场背后的开发时强制执行）。
-- Claude Code 假 CLI mock 依赖一个内部协议：任何 SDK 升级都必须通过无密钥套件，控制协议的破坏性变更意味着返工 mock（回退方案：上面否决的驱动注入 seam 成为逃生舱口）。
-- SDK 的 optionalDependencies 每平台约 280 MB——已接受，限制在单个后端包内。
-- SDK 的 SIGKILL 分支（EOF→SIGTERM 之后）未被观察到，信任其实现；e2e 保留无残留进程断言。
-- Codex 是部署前置条件（无 npm 内置二进制）；缺失或不兼容的二进制会明确报出 spawn/协议 `error`，而非版本探测。
-- 每次运行付出一个全新子进程的代价，且仅最终答案浮出——思考、工具卡片和用量被消费后丢弃；池化、中间进度浮出、`sendMessage`/`resume`、通过 SDK 的 `outputFormat` 实现 `outputSchema`、以及通过 SDK 的 `agents` 选项实现命名 subagent 类型，均为刻意推迟。

AGENTS.md

@@ -24,6 +24,7 @@ packages/    @deepseek-ai/dsh-<pkg> workspaces at packages/<group>/<pkg>/
   compact/     compaction seam + basic backend
   context/     request-context plugins
   subagent/    subagent seam + spawn/fork/ACP backends + delegation tool
+  bundle/      profile plugin bundles: installable patch layers for dsh --profile
   workflow/    workflow seam + worker-thread engine + workflow tool
   todo/        todo_write tool
   plan/        plan mode as logged per-agent collaboration state

README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write README.md
-README.md: b8e46044fb8857730b32d9fbbb9ed4de964d6017
-README.zh.md: e289d523bf61a577f1dd2335b3b4567736d9100d
+README.md: d8d3e767d5a9805f34f4df57a5b1f8ff7fdaa955
+README.zh.md: 89abf8d817deeed2bf4416035790c8696c8c8e33

README.md

@@ -39,22 +39,24 @@ 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.
 
-### Configured runtime
+### Profiles
 
-Raw `dsh` requires a patch-list configuration applied over the shipped base:
+`dsh` boots profiles — ordered stacks of plugin-bundle patch layers under your own overrides in `$DSH_HOME/profiles/<name>`:
 
 ```sh
-dsh --config ./app.cordis.yml
+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
 ```
 
-The [CLI contract](apps/cli/README.md#raw-config) describes the base, overlay semantics, and config dump commands.
+The [CLI contract](apps/cli/README.md#profiles) describes profile layout, layer semantics, and config dump commands.
 
 ### Headless
 
 Run one task, print the final answer, and exit:
 
 ```sh
-dsh -p "summarize this workspace"
+dsh --profile headless "summarize this workspace"
 ```
 
 ### Automation and SDKs

README.zh.md

@@ -39,22 +39,24 @@ 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。
 
-### 自定义运行时
+### Profile
 
-原始 `dsh` 要求传入一份 patch 列表配置，并将其叠加在随附 base 之上：
+`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：
 
 ```sh
-dsh --config ./app.cordis.yml
+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
 ```
 
-base、overlay 语义与配置输出命令详见 [CLI（命令行界面）契约](apps/cli/README.md#raw-config)。
+profile 布局、层语义与配置输出命令详见 [CLI（命令行界面）契约](apps/cli/README.md#profiles)。
 
 ### Headless
 
 运行一项任务，打印最终答案后退出：
 
 ```sh
-dsh -p "summarize this workspace"
+dsh --profile headless "summarize this workspace"
 ```
 
 ### 自动化与 SDK

THIRD_PARTY_NOTICES.md

@@ -3,9 +3,9 @@
 
 # Third-Party Notices
 
-DeepSeek Harness is licensed under [BSD 3-Clause](LICENSE). It depends on the third-party open-source software listed below. Each project remains under its own license; nothing in this file changes those terms.
+DeepSeek Harness is licensed under [BSD 3-Clause](LICENSE). It depends on the third-party software listed below. Each project remains under its own license; nothing in this file changes those terms.
 
-This file lists **direct** dependencies declared by the workspace. It is generated from the workspace manifests by `scripts/gen-third-party-notices.ts`: a pre-commit hook regenerates it whenever a staged file changes one of its inputs, and `scripts/gen-third-party-notices.spec.ts` asserts in the test lane that the committed bytes match. Deleting a manifest runs no hook, so that case is caught by the assertion instead. Run `pnpm run verify-third-party-notices` for the standalone check.
+This file lists **direct** dependencies declared by the workspace and the explicitly disclosed official Claude platform payload closure. It is generated from the workspace manifests by `scripts/gen-third-party-notices.ts`: a pre-commit hook regenerates it whenever a staged file changes one of its inputs, and `scripts/gen-third-party-notices.spec.ts` asserts in the test lane that the committed bytes match. Deleting a manifest runs no hook, so that case is caught by the assertion instead. Run `pnpm run verify-third-party-notices` for the standalone check.
 
 The complete npm transitive closure, with exact pinned versions, is recorded in [`pnpm-lock.yaml`](pnpm-lock.yaml) — inspect it with `pnpm licenses list`. The Python closure is recorded in [`python/sdk/uv.lock`](python/sdk/uv.lock), and the Landlock launcher workspace keeps its own in [`native/landlock-run/pnpm-lock.yaml`](native/landlock-run/pnpm-lock.yaml).
 
@@ -32,6 +32,8 @@ External packages that a workspace package resolves at runtime. `scripts/install
 | Package | License |
 | --- | --- |
 | [`@agentclientprotocol/sdk`](https://github.com/agentclientprotocol/typescript-sdk) | Apache-2.0 |
+| [`@anthropic-ai/claude-agent-sdk`](https://github.com/anthropics/claude-agent-sdk-typescript) | SEE LICENSE IN README.md |
+| [`@anthropic-ai/sdk`](https://github.com/anthropics/anthropic-sdk-typescript) | MIT |
 | [`@babel/code-frame`](https://github.com/babel/babel) | MIT |
 | [`@clack/core`](https://github.com/bombshell-dev/clack) | MIT |
 | [`@clack/prompts`](https://github.com/bombshell-dev/clack) | MIT |
@@ -95,6 +97,24 @@ pnpm applies local patches to the following packages at install time, so shipped
 
 - `node-pty@1.1.0` — [`patches/node-pty@1.1.0.patch`](patches/node-pty@1.1.0.patch)
 
+## Official Claude Code platform payloads
+
+The project owner authorizes distribution of every version of the official `@anthropic-ai/claude-agent-sdk` package and the official Claude Code CLI/platform payloads that each version declares through `optionalDependencies`. This identity-scoped authorization does not classify their declared terms as permissive and does not cover any unrelated runtime package; version, declared-license, and payload-set changes still require the ordinary dependency, lockfile, compatibility, terms, and notices review.
+
+The installed SDK 0.3.220 declares the following optional platform packages. Each carries the official Claude Code 2.1.220 executable; the package identities and versions come from the SDK manifest, while the declared license field is verified against the platform payload installed for the current host.
+
+| Optional platform package | Version | Declared license |
+| --- | --- | --- |
+| [`@anthropic-ai/claude-agent-sdk-darwin-arm64`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-darwin-arm64) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+| [`@anthropic-ai/claude-agent-sdk-darwin-x64`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-darwin-x64) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+| [`@anthropic-ai/claude-agent-sdk-linux-arm64`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-linux-arm64) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+| [`@anthropic-ai/claude-agent-sdk-linux-arm64-musl`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-linux-arm64-musl) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+| [`@anthropic-ai/claude-agent-sdk-linux-x64`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-linux-x64) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+| [`@anthropic-ai/claude-agent-sdk-linux-x64-musl`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-linux-x64-musl) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+| [`@anthropic-ai/claude-agent-sdk-win32-arm64`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-win32-arm64) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+| [`@anthropic-ai/claude-agent-sdk-win32-x64`](https://www.npmjs.com/package/@anthropic-ai/claude-agent-sdk-win32-x64) | 0.3.220 | SEE LICENSE IN LICENSE.md |
+
+
 ## Development-only npm dependencies
 
 External packages **directly declared** only by repository tooling, test infrastructure, the documentation site, the demo leaves, or the native launcher's build workspace. No shipped surface names them itself. A package here may still be pulled in transitively by a runtime dependency — `pnpm-lock.yaml` is the authority on the full closure — so this tier records who declares a package, not what a build ultimately bundles.
@@ -104,6 +124,7 @@ External packages **directly declared** only by repository tooling, test infrast
 | [`@braintree/sanitize-url`](https://github.com/braintree/sanitize-url) | MIT |
 | [`@modelcontextprotocol/server-everything`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 |
 | [`@modelcontextprotocol/server-filesystem`](https://github.com/modelcontextprotocol/servers) | MIT / Apache-2.0 |
+| [`@openai/codex`](https://github.com/openai/codex) | Apache-2.0 |
 | [`@stylistic/eslint-plugin`](https://github.com/eslint-stylistic/eslint-stylistic) | MIT |
 | [`@testing-library/dom`](https://github.com/testing-library/dom-testing-library) | MIT |
 | [`@testing-library/react`](https://github.com/testing-library/react-testing-library) | MIT |

apps/cli/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write apps/cli/README.md
-README.md: ce7af5a299e45d6f107686aff043246914dce8ed
-README.zh.md: e97fec9d6bb726cb1e419a1ca2fa1871d4d203ca
+README.md: f50f26ec5de54e094e17221f7cd355483483754e
+README.zh.md: 242e64a0c42064b9f0b7621e665e85fe44523fe5

apps/cli/README.md

@@ -2,24 +2,25 @@
 
 English | [中文](README.zh.md)
 
-The `dsh` command is the product launcher for raw Cordis configurations, the Web UI, and one-shot headless tasks. [`src/args.ts`](src/args.ts) owns the command grammar, and [`src/bin.ts`](src/bin.ts) loads only the selected runner. Invalid commands, options from another mode, configuration errors, and boot failures exit nonzero.
+The `dsh` command is the product launcher for profiles: ordered stacks of plugin-bundle patch layers under the user's own overrides. [`src/args.ts`](src/args.ts) owns the command grammar, and [`src/bin.ts`](src/bin.ts) loads only the selected runner. Invalid commands, options from another mode, configuration errors, and boot failures exit nonzero.
 
 ## Entry modes
 
 | Command | Purpose |
 |---|---|
-| `dsh --config ./app.cordis.yml` | Run an explicit patch-list configuration over the shipped base. |
-| `dsh web` | Start the browser UI with the shipped Web composition and optional personal configuration. |
-| `dsh -p "task"` | Run one fresh persisted session, print the final answer, and exit. |
+| `dsh --profile <name>` | Boot the named profile under `$DSH_HOME/profiles/<name>`. |
+| `dsh --profile headless "task"` | Run one fresh persisted session, print the final answer, and exit. |
+| `dsh web` | Alias of `--profile web` with the Web flag family (`--host`, `--port`, `--dev`, ...). |
+| `dsh plugin --profile <name> <pnpm args>` | Manage a profile's plugins by forwarding to pnpm in the profile directory. |
 
-The invoking directory is the default workspace root. Web and headless share the shipped provider, persistence, policy, tool, repository Plugin, and telemetry composition; raw config selects its own deployment-specific front door.
+The invoking directory is the default workspace root. The `web` and `headless` profiles auto-initialize on first use from shipped templates; any other profile must be created through `dsh plugin`.
 
-## Raw config
+## Profiles
 
-Raw `dsh` requires `--config`. The named patch list is applied directly over [`config/base.cordis.yml`](config/base.cordis.yml); it is not a complete replacement tree and does not add a surface overlay or personal `$DSH_HOME/config.yaml`. Use `--dump-default-config` and `--dump-config` to inspect the resulting tree without booting it.
+A profile directory holds a `package.json` (out-of-tree plugin dependencies plus the profile manifest `dsh.profile` with its ordered `bundles` list) and a `cordis.patch.yml` (the user's own patch layer, hot-reloaded on long-lived surfaces). The tree composes over an empty root: each bundle's patch in `dsh.profile.bundles` order, then the profile's `cordis.patch.yml`, then the home-level `$DSH_HOME/cordis.patch.yml`, then `--patch` overlays, then flag patches. 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 overlay 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 the source launcher.
 
 ## Development
 
-Production Web and headless 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 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.